diff options
176 files changed, 7836 insertions, 1779 deletions
diff --git a/.gitignore b/.gitignore index b5f9defed3..dc600f9b36 100644 --- a/.gitignore +++ b/.gitignore @@ -182,6 +182,7 @@ /test-dump-cache-tree /test-scrap-cache-tree /test-genrandom +/test-hashmap /test-index-version /test-line-buffer /test-match-trees diff --git a/Documentation/RelNotes/2.0.0.txt b/Documentation/RelNotes/2.0.0.txt new file mode 100644 index 0000000000..acc7415505 --- /dev/null +++ b/Documentation/RelNotes/2.0.0.txt @@ -0,0 +1,146 @@ +Git v2.0 Release Notes +====================== + +Backward compatibility notes +---------------------------- + +When "git push [$there]" does not say what to push, we have used the +traditional "matching" semantics so far (all your branches were sent +to the remote as long as there already are branches of the same name +over there). In Git 2.0, the default is now the "simple" semantics, +which pushes: + + - only the current branch to the branch with the same name, and only + when the current branch is set to integrate with that remote + branch, if you are pushing to the same remote as you fetch from; or + + - only the current branch to the branch with the same name, if you + are pushing to a remote that is not where you usually fetch from. + +You can use the configuration variable "push.default" to change +this. If you are an old-timer who wants to keep using the +"matching" semantics, you can set the variable to "matching", for +example. Read the documentation for other possibilities. + +When "git add -u" and "git add -A" are run inside a subdirectory +without specifying which paths to add on the command line, they +operate on the entire tree for consistency with "git commit -a" and +other commands (these commands used to operate only on the current +subdirectory). Say "git add -u ." or "git add -A ." if you want to +limit the operation to the current directory. + +"git add <path>" is the same as "git add -A <path>" now, so that +"git add dir/" will notice paths you removed from the directory and +record the removal. In older versions of Git, "git add <path>" used +to ignore removals. You can say "git add --ignore-removal <path>" to +add only added or modified paths in <path>, if you really want to. + +The "-q" option to "git diff-files", which does *NOT* mean "quiet", +has been removed (it told Git to ignore deletion, which you can do +with "git diff-files --diff-filter=d"). + + +Updates since v1.9 series +------------------------- + +Foreign interfaces, subsystems and ports. + + +UI, Workflows & Features + + * The "simple" mode is the default for "git push". + + * "git add -u" and "git add -A", when run without any pathspec, is a + tree-wide operation even when run inside a subdirectory of a + working tree. + + * "git add <path> is the same as "git add -A <path>" now. + + * "core.statinfo" configuration variable, which is a + never-advertised synonym to "core.checkstat", has been removed. + + * The "-q" option to "git diff-files", which does *NOT* mean + "quiet", has been removed (it told Git to ignore deletion, which + you can do with "git diff-files --diff-filter=d"). + + * Many commands that creates commits, e.g. "pull", "rebase", + learned to take the --gpg-sign option on the command line. + + * "git commit" can be told to always GPG sign the resulting commit + by setting "commit.gpgsign" configuration variable to true (the + command line option --no-gpg-sign should override it). + + * "git pull" can be told to only accept fast-forward by setting the + new "pull.ff" configuration. + + * "git reset" learned "-N" option, which does not reset the index + fully for paths the index knows about but the tree-ish the command + resets to does not (these paths are kept as intend-to-add entries). + + * Newly cloned submodule repositories by "git submodule update", + when the "checkout" update mode is used, will be on a local + branch instead of on a detached HEAD, just like submodules added + with "git submodule add". + + +Performance, Internal Implementation, etc. + + * The bitmap-index feature from JGit has been ported, which should + significantly improve performance when serving objects form a + repository that uses it. + + * The way "git log --cc" shows a combined diff against multiple + parents have been optimized. + + * The prefixcmp() and suffixcmp() functions are gone. Use + starts_with() and ends_with(), and also consider if skip_prefix() + suits your needs better when using the former. + + +Also contains various documentation updates and code clean-ups. + + +Fixes since v1.9 series +----------------------- + +Unless otherwise noted, all the fixes since v1.9 in the maintenance +track are contained in this release (see the maintenance releases' +notes for details). + + * "merge-recursive" was broken in 1.7.7 era and stopped working in + an empty (temporary) working tree, when there are renames + involved. This has been corrected. + (merge 6e2068a bk/refresh-missing-ok-in-merge-recursive later to maint.) + + * "git rev-parse" was loose in rejecting command line arguments + that do not make sense, e.g. "--default" without the required + value for that option. + (merge a43219f ds/rev-parse-required-args later to maint.) + + * include.path variable (or any variable that expects a path that + can use ~username expansion) in the configuration file is not a + boolean, but the code failed to check it. + (merge 67beb60 jk/config-path-include-fix later to maint.) + + * Commands that take pathspecs on the command line misbehaved when + the pathspec is given as an absolute pathname (which is a + practice not particularly encouraged) that points at a symbolic + link in the working tree. + (merge later 655ee9e mw/symlinks to maint.) + + * "git diff --quiet -- pathspec1 pathspec2" sometimes did not return + correct status value. + (merge f34b205 nd/diff-quiet-stat-dirty later to maint.) + + * Attempting to deepen a shallow repository by fetching over smart + HTTP transport failed in the protocol exchange, when no-done + extension was used. The fetching side waited for the list of + shallow boundary commits after the sending end stopped talking to + it. + (merge 0232852 nd/http-fetch-shallow-fix later to maint.) + + * Allow "git cmd path/", when the 'path' is where a submodule is + bound to the top-level working tree, to match 'path', despite the + extra and unnecessary trailing slash (such a slash is often + given by command line completion). + (merge 2e70c01 nd/submodule-pathspec-ending-with-slash later to maint.) diff --git a/Documentation/config.txt b/Documentation/config.txt index 5f4d7939ed..73904bce55 100644 --- a/Documentation/config.txt +++ b/Documentation/config.txt @@ -142,19 +142,13 @@ advice.*:: -- pushUpdateRejected:: Set this variable to 'false' if you want to disable - 'pushNonFFCurrent', 'pushNonFFDefault', + 'pushNonFFCurrent', 'pushNonFFMatching', 'pushAlreadyExists', 'pushFetchFirst', and 'pushNeedsForce' simultaneously. pushNonFFCurrent:: Advice shown when linkgit:git-push[1] fails due to a non-fast-forward update to the current branch. - pushNonFFDefault:: - Advice to set 'push.default' to 'upstream' or 'current' - when you ran linkgit:git-push[1] and pushed 'matching - refs' by default (i.e. you did not provide an explicit - refspec, and no 'push.default' configuration was set) - and it resulted in a non-fast-forward error. pushNonFFMatching:: Advice shown when you ran linkgit:git-push[1] and pushed 'matching refs' explicitly (i.e. you used ':', or @@ -992,6 +986,14 @@ commit.cleanup:: have to remove the help lines that begin with `#` in the commit log template yourself, if you do this). +commit.gpgsign:: + + A boolean to specify whether all commits should be GPG signed. + Use of this option when doing operations such as rebase can + result in a large number of commits being signed. It may be + convenient to use an agent to avoid typing your GPG passphrase + several times. + commit.status:: A boolean to enable/disable inclusion of status information in the commit message template when using an editor to prepare the commit @@ -1167,6 +1169,10 @@ gc.autopacklimit:: --auto` consolidates them into one larger pack. The default value is 50. Setting this to 0 disables it. +gc.autodetach:: + Make `git gc --auto` return immediately andrun in background + if the system supports it. Default is true. + gc.packrefs:: Running `git pack-refs` in a repository renders it unclonable by Git versions prior to 1.5.1.2 over dumb @@ -1862,6 +1868,31 @@ pack.packSizeLimit:: Common unit suffixes of 'k', 'm', or 'g' are supported. +pack.useBitmaps:: + When true, git will use pack bitmaps (if available) when packing + to stdout (e.g., during the server side of a fetch). Defaults to + true. You should not generally need to turn this off unless + you are debugging pack bitmaps. + +pack.writebitmaps:: + When true, git will write a bitmap index when packing all + objects to disk (e.g., when `git repack -a` is run). This + index can speed up the "counting objects" phase of subsequent + packs created for clones and fetches, at the cost of some disk + space and extra time spent on the initial repack. Defaults to + false. + +pack.writeBitmapHashCache:: + When true, git will include a "hash cache" section in the bitmap + index (if one is written). This cache can be used to feed git's + delta heuristics, potentially leading to better deltas between + bitmapped and non-bitmapped objects (e.g., when serving a fetch + between an older, bitmapped pack and objects that have been + pushed since the last gc). The downside is that it consumes 4 + bytes per object of disk space, and that JGit's bitmap + implementation does not understand it, causing it to complain if + Git and JGit are used on the same repository. Defaults to false. + pager.<cmd>:: If the value is boolean, turns on or off pagination of the output of a particular Git subcommand when writing to a tty. @@ -1881,6 +1912,16 @@ pretty.<name>:: Note that an alias with the same name as a built-in format will be silently ignored. +pull.ff:: + By default, Git does not create an extra merge commit when merging + a commit that is a descendant of the current commit. Instead, the + tip of the current branch is fast-forwarded. When set to `false`, + this variable tells Git to create an extra merge commit in such + a case (equivalent to giving the `--no-ff` option from the command + line). When set to `only`, only such fast-forward merges are + allowed (equivalent to giving the `--ff-only` option from the + command line). + pull.rebase:: When true, rebase branches on top of the fetched branch, instead of merging the default branch from the default remote when "git @@ -1933,7 +1974,7 @@ When pushing to a remote that is different from the remote you normally pull from, work as `current`. This is the safest option and is suited for beginners. + -This mode will become the default in Git 2.0. +This mode has become the default in Git 2.0. * `matching` - push all branches having the same name on both ends. This makes the repository you are pushing to remember the set of @@ -1952,8 +1993,8 @@ suitable for pushing into a shared central repository, as other people may add new branches there, or update the tip of existing branches outside your control. + -This is currently the default, but Git 2.0 will change the default -to `simple`. +This used to be the default, but not since Git 2.0 (`simple` is the +new default). -- diff --git a/Documentation/git-add.txt b/Documentation/git-add.txt index 48754cbc67..895922e27c 100644 --- a/Documentation/git-add.txt +++ b/Documentation/git-add.txt @@ -53,8 +53,14 @@ OPTIONS Files to add content from. Fileglobs (e.g. `*.c`) can be given to add all matching files. Also a leading directory name (e.g. `dir` to add `dir/file1` - and `dir/file2`) can be given to add all files in the - directory, recursively. + and `dir/file2`) can be given to update the index to + match the current state of the directory as a whole (e.g. + specifying `dir` will record not just a file `dir/file1` + modified in the working tree, a file `dir/file2` added to + the working tree, but also a file `dir/file3` removed from + the working tree. Note that older versions of Git used + to ignore removed files; use `--no-all` option if you want + to add modified or new files but ignore removed ones. -n:: --dry-run:: @@ -104,10 +110,10 @@ apply to the index. See EDITING PATCHES below. <pathspec>. This removes as well as modifies index entries to match the working tree, but adds no new files. + -If no <pathspec> is given, the current version of Git defaults to -"."; in other words, update all tracked files in the current directory -and its subdirectories. This default will change in a future version -of Git, hence the form without <pathspec> should not be used. +If no <pathspec> is given when `-u` option is used, all +tracked files in the entire working tree are updated (old versions +of Git used to limit the update to the current directory and its +subdirectories). -A:: --all:: @@ -117,10 +123,10 @@ of Git, hence the form without <pathspec> should not be used. entry. This adds, modifies, and removes index entries to match the working tree. + -If no <pathspec> is given, the current version of Git defaults to -"."; in other words, update all files in the current directory -and its subdirectories. This default will change in a future version -of Git, hence the form without <pathspec> should not be used. +If no <pathspec> is given when `-A` option is used, all +files in the entire working tree are updated (old versions +of Git used to limit the update to the current directory and its +subdirectories). --no-all:: --ignore-removal:: @@ -129,11 +135,9 @@ of Git, hence the form without <pathspec> should not be used. files that have been removed from the working tree. This option is a no-op when no <pathspec> is used. + -This option is primarily to help the current users of Git, whose -"git add <pathspec>..." ignores removed files. In future versions -of Git, "git add <pathspec>..." will be a synonym to "git add -A -<pathspec>..." and "git add --ignore-removal <pathspec>..." will behave like -today's "git add <pathspec>...", ignoring removed files. +This option is primarily to help users who are used to older +versions of Git, whose "git add <pathspec>..." was a synonym +for "git add --no-all <pathspec>...", i.e. ignored removed files. -N:: --intent-to-add:: diff --git a/Documentation/git-am.txt b/Documentation/git-am.txt index 54d8461d61..17924d0f3f 100644 --- a/Documentation/git-am.txt +++ b/Documentation/git-am.txt @@ -14,7 +14,7 @@ SYNOPSIS [--ignore-date] [--ignore-space-change | --ignore-whitespace] [--whitespace=<option>] [-C<n>] [-p<n>] [--directory=<dir>] [--exclude=<path>] [--include=<path>] [--reject] [-q | --quiet] - [--[no-]scissors] + [--[no-]scissors] [-S[<keyid>]] [(<mbox> | <Maildir>)...] 'git am' (--continue | --skip | --abort) @@ -119,6 +119,10 @@ default. You can use `--no-utf8` to override this. Skip the current patch. This is only meaningful when restarting an aborted patch. +-S[<keyid>]:: +--gpg-sign[=<keyid>]:: + GPG-sign commits. + --continue:: -r:: --resolved:: diff --git a/Documentation/git-blame.txt b/Documentation/git-blame.txt index 8e70a61840..9f23a861ce 100644 --- a/Documentation/git-blame.txt +++ b/Documentation/git-blame.txt @@ -35,7 +35,8 @@ Apart from supporting file annotation, Git also supports searching the development history for when a code snippet occurred in a change. This makes it possible to track when a code snippet was added to a file, moved or copied between files, and eventually deleted or replaced. It works by searching for -a text string in the diff. A small example: +a text string in the diff. A small example of the pickaxe interface +that searches for `blame_usage`: ----------------------------------------------------------------------------- $ git log --pretty=oneline -S'blame_usage' diff --git a/Documentation/git-cherry-pick.txt b/Documentation/git-cherry-pick.txt index c205d2363e..f1e6b2fd6d 100644 --- a/Documentation/git-cherry-pick.txt +++ b/Documentation/git-cherry-pick.txt @@ -8,7 +8,8 @@ git-cherry-pick - Apply the changes introduced by some existing commits SYNOPSIS -------- [verse] -'git cherry-pick' [--edit] [-n] [-m parent-number] [-s] [-x] [--ff] <commit>... +'git cherry-pick' [--edit] [-n] [-m parent-number] [-s] [-x] [--ff] + [-S[<keyid>]] <commit>... 'git cherry-pick' --continue 'git cherry-pick' --quit 'git cherry-pick' --abort @@ -100,6 +101,10 @@ effect to your index in a row. --signoff:: Add Signed-off-by line at the end of the commit message. +-S[<keyid>]:: +--gpg-sign[=<keyid>]:: + GPG-sign commits. + --ff:: If the current HEAD is the same as the parent of the cherry-pick'ed commit, then a fast forward to this commit will diff --git a/Documentation/git-clone.txt b/Documentation/git-clone.txt index bf3dac0cef..0363d0039b 100644 --- a/Documentation/git-clone.txt +++ b/Documentation/git-clone.txt @@ -55,15 +55,12 @@ repository is specified as a URL, then this flag is ignored (and we never use the local optimizations). Specifying `--no-local` will override the default when `/path/to/repo` is given, using the regular Git transport instead. -+ -To force copying instead of hardlinking (which may be desirable if you -are trying to make a back-up of your repository), but still avoid the -usual "Git aware" transport mechanism, `--no-hardlinks` can be used. --no-hardlinks:: - Optimize the cloning process from a repository on a - local filesystem by copying files under `.git/objects` - directory. + Force the cloning process from a repository on a local + filesystem to copy the files under the `.git/objects` + directory instead of using hardlinks. This may be desirable + if you are trying to make a back-up of your repository. --shared:: -s:: diff --git a/Documentation/git-commit-tree.txt b/Documentation/git-commit-tree.txt index cafdc9642d..a469eab066 100644 --- a/Documentation/git-commit-tree.txt +++ b/Documentation/git-commit-tree.txt @@ -55,8 +55,13 @@ OPTIONS from the standard input. -S[<keyid>]:: +--gpg-sign[=<keyid>]:: GPG-sign commit. +--no-gpg-sign:: + Countermand `commit.gpgsign` configuration variable that is + set to force each and every commit to be signed. + Commit Information ------------------ diff --git a/Documentation/git-commit.txt b/Documentation/git-commit.txt index 1a7616c73a..7c42e9cabc 100644 --- a/Documentation/git-commit.txt +++ b/Documentation/git-commit.txt @@ -302,6 +302,10 @@ configuration variable documented in linkgit:git-config[1]. --gpg-sign[=<keyid>]:: GPG-sign commit. +--no-gpg-sign:: + Countermand `commit.gpgsign` configuration variable that is + set to force each and every commit to be signed. + \--:: Do not interpret any more arguments as options. diff --git a/Documentation/git-push.txt b/Documentation/git-push.txt index 2b7f4f939f..14862fb203 100644 --- a/Documentation/git-push.txt +++ b/Documentation/git-push.txt @@ -83,8 +83,8 @@ the local side, the remote side is updated if a branch of the same name already exists on the remote side. --all:: - Instead of naming each ref to push, specifies that all - refs under `refs/heads/` be pushed. + Push all branches (i.e. refs under `refs/heads/`); cannot be + used with other <refspec>. --prune:: Remove remote branches that don't have a local counterpart. For example @@ -442,8 +442,10 @@ Examples configured for the current branch). `git push origin`:: - Without additional configuration, works like - `git push origin :`. + Without additional configuration, pushes the current branch to + the configured upstream (`remote.origin.merge` configuration + variable) if it has the same name as the current branch, and + errors out without pushing otherwise. + The default behavior of this command when no <refspec> is given can be configured by setting the `push` option of the remote, or the `push.default` diff --git a/Documentation/git-rebase.txt b/Documentation/git-rebase.txt index 2889be6bdc..2a93c645bd 100644 --- a/Documentation/git-rebase.txt +++ b/Documentation/git-rebase.txt @@ -281,6 +281,10 @@ which makes little sense. specified, `-s recursive`. Note the reversal of 'ours' and 'theirs' as noted above for the `-m` option. +-S[<keyid>]:: +--gpg-sign[=<keyid>]:: + GPG-sign commits. + -q:: --quiet:: Be quiet. Implies --no-stat. diff --git a/Documentation/git-remote.txt b/Documentation/git-remote.txt index 2507c8bd91..cb103c8b6f 100644 --- a/Documentation/git-remote.txt +++ b/Documentation/git-remote.txt @@ -3,7 +3,7 @@ git-remote(1) NAME ---- -git-remote - manage set of tracked repositories +git-remote - Manage set of tracked repositories SYNOPSIS diff --git a/Documentation/git-repack.txt b/Documentation/git-repack.txt index 509cf73e50..002cfd5eb9 100644 --- a/Documentation/git-repack.txt +++ b/Documentation/git-repack.txt @@ -9,7 +9,7 @@ git-repack - Pack unpacked objects in a repository SYNOPSIS -------- [verse] -'git repack' [-a] [-A] [-d] [-f] [-F] [-l] [-n] [-q] [--window=<n>] [--depth=<n>] +'git repack' [-a] [-A] [-d] [-f] [-F] [-l] [-n] [-q] [-b] [--window=<n>] [--depth=<n>] DESCRIPTION ----------- @@ -110,6 +110,13 @@ other objects in that pack they already have locally. The default is unlimited, unless the config variable `pack.packSizeLimit` is set. +-b:: +--write-bitmap-index:: + Write a reachability bitmap index as part of the repack. This + only makes sense when used with `-a` or `-A`, as the bitmaps + must be able to refer to all reachable objects. This option + overrides the setting of `pack.writebitmaps`. + Configuration ------------- diff --git a/Documentation/git-reset.txt b/Documentation/git-reset.txt index f445cb38fa..a077ba0ddc 100644 --- a/Documentation/git-reset.txt +++ b/Documentation/git-reset.txt @@ -10,7 +10,7 @@ SYNOPSIS [verse] 'git reset' [-q] [<tree-ish>] [--] <paths>... 'git reset' (--patch | -p) [<tree-ish>] [--] [<paths>...] -'git reset' [--soft | --mixed | --hard | --merge | --keep] [-q] [<commit>] +'git reset' [--soft | --mixed [-N] | --hard | --merge | --keep] [-q] [<commit>] DESCRIPTION ----------- @@ -60,6 +60,9 @@ section of linkgit:git-add[1] to learn how to operate the `--patch` mode. Resets the index but not the working tree (i.e., the changed files are preserved but not marked for commit) and reports what has not been updated. This is the default action. ++ +If `-N` is specified, removed paths are marked as intent-to-add (see +linkgit:git-add[1]). --hard:: Resets the index and working tree. Any changes to tracked files in the diff --git a/Documentation/git-rev-list.txt b/Documentation/git-rev-list.txt index 045b37b82e..7a1585def0 100644 --- a/Documentation/git-rev-list.txt +++ b/Documentation/git-rev-list.txt @@ -55,6 +55,7 @@ SYNOPSIS [ \--reverse ] [ \--walk-reflogs ] [ \--no-walk ] [ \--do-walk ] + [ \--use-bitmap-index ] <commit>... [ \-- <paths>... ] DESCRIPTION diff --git a/Documentation/git-revert.txt b/Documentation/git-revert.txt index 2de67a5496..9eb83f01a4 100644 --- a/Documentation/git-revert.txt +++ b/Documentation/git-revert.txt @@ -8,7 +8,7 @@ git-revert - Revert some existing commits SYNOPSIS -------- [verse] -'git revert' [--[no-]edit] [-n] [-m parent-number] [-s] <commit>... +'git revert' [--[no-]edit] [-n] [-m parent-number] [-s] [-S[<keyid>]] <commit>... 'git revert' --continue 'git revert' --quit 'git revert' --abort @@ -80,6 +80,10 @@ more details. This is useful when reverting more than one commits' effect to your index in a row. +-S[<keyid>]:: +--gpg-sign[=<keyid>]:: + GPG-sign commits. + -s:: --signoff:: Add Signed-off-by line at the end of the commit message. diff --git a/Documentation/git-submodule.txt b/Documentation/git-submodule.txt index bfef8a0c62..21cb59a6d6 100644 --- a/Documentation/git-submodule.txt +++ b/Documentation/git-submodule.txt @@ -15,8 +15,8 @@ SYNOPSIS 'git submodule' [--quiet] init [--] [<path>...] 'git submodule' [--quiet] deinit [-f|--force] [--] <path>... 'git submodule' [--quiet] update [--init] [--remote] [-N|--no-fetch] - [-f|--force] [--rebase] [--reference <repository>] [--depth <depth>] - [--merge] [--recursive] [--] [<path>...] + [-f|--force] [--rebase|--merge|--checkout] [--reference <repository>] + [--depth <depth>] [--recursive] [--] [<path>...] 'git submodule' [--quiet] summary [--cached|--files] [(-n|--summary-limit) <n>] [commit] [--] [<path>...] 'git submodule' [--quiet] foreach [--recursive] <command> @@ -155,13 +155,31 @@ it contains local modifications. update:: Update the registered submodules, i.e. clone missing submodules and - checkout the commit specified in the index of the containing repository. - This will make the submodules HEAD be detached unless `--rebase` or - `--merge` is specified or the key `submodule.$name.update` is set to - `rebase`, `merge` or `none`. `none` can be overridden by specifying - `--checkout`. Setting the key `submodule.$name.update` to `!command` - will cause `command` to be run. `command` can be any arbitrary shell - command that takes a single argument, namely the sha1 to update to. + checkout the commit specified in the index of the containing + repository. The update mode defaults to `checkout`, but can be + configured with the `submodule.<name>.update` setting or the + `--rebase`, `--merge`, or `--checkout` options. ++ +For updates that clone missing submodules, checkout-mode updates will +create submodules with detached HEADs; all other modes will create +submodules with a local branch named after `submodule.<path>.branch`. ++ +For updates that do not clone missing submodules, the submodule's HEAD +is only touched when the remote reference does not match the +submodule's HEAD (for none-mode updates, the submodule is never +touched). The remote reference is usually the gitlinked commit from +the superproject's tree, but with `--remote` it is the upstream +subproject's `submodule.<name>.branch`. This remote reference is +integrated with the submodule's HEAD using the specified update mode. +For checkout-mode updates, that will result in a detached HEAD. For +rebase- and merge-mode updates, the commit referenced by the +submodule's HEAD may change, but the symbolic reference will remain +unchanged (i.e. checked-out branches will still be checked-out +branches, and detached HEADs will still be detached HEADs). If none +of the builtin modes fit your needs, set `submodule.<name>.update` to +`!command` to configure a custom integration command. `command` can +be any arbitrary shell command that takes a single argument, namely +the sha1 to update to. + If the submodule is not yet initialized, and you just want to use the setting as stored in .gitmodules, you can automatically initialize the @@ -281,6 +299,16 @@ In order to ensure a current tracking branch state, `update --remote` fetches the submodule's remote repository before calculating the SHA-1. If you don't want to fetch, you should use `submodule update --remote --no-fetch`. ++ +Use this option to integrate changes from the upstream subproject with +your submodule's current HEAD. Alternatively, you can run `git pull` +from the submodule, which is equivalent except for the remote branch +name: `update --remote` uses the default upstream repository and +`submodule.<name>.branch`, while `git pull` uses the submodule's +`branch.<name>.merge`. Prefer `submodule.<name>.branch` if you want +to distribute the default upstream branch with the superproject and +`branch.<name>.merge` if you want a more native feel while working in +the submodule itself. -N:: --no-fetch:: diff --git a/Documentation/gitignore.txt b/Documentation/gitignore.txt index b08d34d84e..8734c1566c 100644 --- a/Documentation/gitignore.txt +++ b/Documentation/gitignore.txt @@ -77,6 +77,9 @@ PATTERN FORMAT Put a backslash ("`\`") in front of the first hash for patterns that begin with a hash. + - Trailing spaces are ignored unless they are quoted with backlash + ("`\`"). + - An optional prefix "`!`" which negates the pattern; any matching file excluded by a previous pattern will become included again. It is not possible to re-include a file if a parent diff --git a/Documentation/gitmodules.txt b/Documentation/gitmodules.txt index 347a9f76ee..f539e3f66a 100644 --- a/Documentation/gitmodules.txt +++ b/Documentation/gitmodules.txt @@ -55,6 +55,10 @@ submodule.<name>.branch:: A remote branch name for tracking updates in the upstream submodule. If the option is not specified, it defaults to 'master'. See the `--remote` documentation in linkgit:git-submodule[1] for details. ++ +This branch name is also used for the local branch created by +non-checkout cloning updates. See the `update` documentation in +linkgit:git-submodule[1] for details. submodule.<name>.fetchRecurseSubmodules:: This option can be used to control recursive fetching of this diff --git a/Documentation/merge-strategies.txt b/Documentation/merge-strategies.txt index fb6e593e7c..350949810e 100644 --- a/Documentation/merge-strategies.txt +++ b/Documentation/merge-strategies.txt @@ -20,7 +20,7 @@ recursive:: merged tree of the common ancestors and uses that as the reference tree for the 3-way merge. This has been reported to result in fewer merge conflicts without - causing mis-merges by tests done on actual merge commits + causing mismerges by tests done on actual merge commits taken from Linux 2.6 kernel development history. Additionally this can detect and handle merges involving renames. This is the default merge strategy when diff --git a/Documentation/rev-list-options.txt b/Documentation/rev-list-options.txt index 03533af715..9a3da3646e 100644 --- a/Documentation/rev-list-options.txt +++ b/Documentation/rev-list-options.txt @@ -257,6 +257,14 @@ See also linkgit:git-reflog[1]. Output excluded boundary commits. Boundary commits are prefixed with `-`. +ifdef::git-rev-list[] +--use-bitmap-index:: + + Try to speed up the traversal using the pack bitmap index (if + one is available). Note that when traversing with `--objects`, + trees and blobs will not have their associated path printed. +endif::git-rev-list[] + -- History Simplification diff --git a/Documentation/technical/api-hash.txt b/Documentation/technical/api-hash.txt deleted file mode 100644 index e5061e0677..0000000000 --- a/Documentation/technical/api-hash.txt +++ /dev/null @@ -1,52 +0,0 @@ -hash API -======== - -The hash API is a collection of simple hash table functions. Users are expected -to implement their own hashing. - -Data Structures ---------------- - -`struct hash_table`:: - - The hash table structure. The `array` member points to the hash table - entries. The `size` member counts the total number of valid and invalid - entries in the table. The `nr` member keeps track of the number of - valid entries. - -`struct hash_table_entry`:: - - An opaque structure representing an entry in the hash table. The `hash` - member is the entry's hash key and the `ptr` member is the entry's - value. - -Functions ---------- - -`init_hash`:: - - Initialize the hash table. - -`free_hash`:: - - Release memory associated with the hash table. - -`insert_hash`:: - - Insert a pointer into the hash table. If an entry with that hash - already exists, a pointer to the existing entry's value is returned. - Otherwise NULL is returned. This allows callers to implement - chaining, etc. - -`lookup_hash`:: - - Lookup an entry in the hash table. If an entry with that hash exists - the entry's value is returned. Otherwise NULL is returned. - -`for_each_hash`:: - - Call a function for each entry in the hash table. The function is - expected to take the entry's value as its only argument and return an - int. If the function returns a negative int the loop is aborted - immediately. Otherwise, the return value is accumulated and the sum - returned upon completion of the loop. diff --git a/Documentation/technical/api-hashmap.txt b/Documentation/technical/api-hashmap.txt new file mode 100644 index 0000000000..42ca2347ed --- /dev/null +++ b/Documentation/technical/api-hashmap.txt @@ -0,0 +1,235 @@ +hashmap API +=========== + +The hashmap API is a generic implementation of hash-based key-value mappings. + +Data Structures +--------------- + +`struct hashmap`:: + + The hash table structure. ++ +The `size` member keeps track of the total number of entries. The `cmpfn` +member is a function used to compare two entries for equality. The `table` and +`tablesize` members store the hash table and its size, respectively. + +`struct hashmap_entry`:: + + An opaque structure representing an entry in the hash table, which must + be used as first member of user data structures. Ideally it should be + followed by an int-sized member to prevent unused memory on 64-bit + systems due to alignment. ++ +The `hash` member is the entry's hash code and the `next` member points to the +next entry in case of collisions (i.e. if multiple entries map to the same +bucket). + +`struct hashmap_iter`:: + + An iterator structure, to be used with hashmap_iter_* functions. + +Types +----- + +`int (*hashmap_cmp_fn)(const void *entry, const void *entry_or_key, const void *keydata)`:: + + User-supplied function to test two hashmap entries for equality. Shall + return 0 if the entries are equal. ++ +This function is always called with non-NULL `entry` / `entry_or_key` +parameters that have the same hash code. When looking up an entry, the `key` +and `keydata` parameters to hashmap_get and hashmap_remove are always passed +as second and third argument, respectively. Otherwise, `keydata` is NULL. + +Functions +--------- + +`unsigned int strhash(const char *buf)`:: +`unsigned int strihash(const char *buf)`:: +`unsigned int memhash(const void *buf, size_t len)`:: +`unsigned int memihash(const void *buf, size_t len)`:: + + Ready-to-use hash functions for strings, using the FNV-1 algorithm (see + http://www.isthe.com/chongo/tech/comp/fnv). ++ +`strhash` and `strihash` take 0-terminated strings, while `memhash` and +`memihash` operate on arbitrary-length memory. ++ +`strihash` and `memihash` are case insensitive versions. + +`void hashmap_init(struct hashmap *map, hashmap_cmp_fn equals_function, size_t initial_size)`:: + + Initializes a hashmap structure. ++ +`map` is the hashmap to initialize. ++ +The `equals_function` can be specified to compare two entries for equality. +If NULL, entries are considered equal if their hash codes are equal. ++ +If the total number of entries is known in advance, the `initial_size` +parameter may be used to preallocate a sufficiently large table and thus +prevent expensive resizing. If 0, the table is dynamically resized. + +`void hashmap_free(struct hashmap *map, int free_entries)`:: + + Frees a hashmap structure and allocated memory. ++ +`map` is the hashmap to free. ++ +If `free_entries` is true, each hashmap_entry in the map is freed as well +(using stdlib's free()). + +`void hashmap_entry_init(void *entry, unsigned int hash)`:: + + Initializes a hashmap_entry structure. ++ +`entry` points to the entry to initialize. ++ +`hash` is the hash code of the entry. + +`void *hashmap_get(const struct hashmap *map, const void *key, const void *keydata)`:: + + Returns the hashmap entry for the specified key, or NULL if not found. ++ +`map` is the hashmap structure. ++ +`key` is a hashmap_entry structure (or user data structure that starts with +hashmap_entry) that has at least been initialized with the proper hash code +(via `hashmap_entry_init`). ++ +If an entry with matching hash code is found, `key` and `keydata` are passed +to `hashmap_cmp_fn` to decide whether the entry matches the key. + +`void *hashmap_get_next(const struct hashmap *map, const void *entry)`:: + + Returns the next equal hashmap entry, or NULL if not found. This can be + used to iterate over duplicate entries (see `hashmap_add`). ++ +`map` is the hashmap structure. ++ +`entry` is the hashmap_entry to start the search from, obtained via a previous +call to `hashmap_get` or `hashmap_get_next`. + +`void hashmap_add(struct hashmap *map, void *entry)`:: + + Adds a hashmap entry. This allows to add duplicate entries (i.e. + separate values with the same key according to hashmap_cmp_fn). ++ +`map` is the hashmap structure. ++ +`entry` is the entry to add. + +`void *hashmap_put(struct hashmap *map, void *entry)`:: + + Adds or replaces a hashmap entry. If the hashmap contains duplicate + entries equal to the specified entry, only one of them will be replaced. ++ +`map` is the hashmap structure. ++ +`entry` is the entry to add or replace. ++ +Returns the replaced entry, or NULL if not found (i.e. the entry was added). + +`void *hashmap_remove(struct hashmap *map, const void *key, const void *keydata)`:: + + Removes a hashmap entry matching the specified key. If the hashmap + contains duplicate entries equal to the specified key, only one of + them will be removed. ++ +`map` is the hashmap structure. ++ +`key` is a hashmap_entry structure (or user data structure that starts with +hashmap_entry) that has at least been initialized with the proper hash code +(via `hashmap_entry_init`). ++ +If an entry with matching hash code is found, `key` and `keydata` are +passed to `hashmap_cmp_fn` to decide whether the entry matches the key. ++ +Returns the removed entry, or NULL if not found. + +`void hashmap_iter_init(struct hashmap *map, struct hashmap_iter *iter)`:: +`void *hashmap_iter_next(struct hashmap_iter *iter)`:: +`void *hashmap_iter_first(struct hashmap *map, struct hashmap_iter *iter)`:: + + Used to iterate over all entries of a hashmap. ++ +`hashmap_iter_init` initializes a `hashmap_iter` structure. ++ +`hashmap_iter_next` returns the next hashmap_entry, or NULL if there are no +more entries. ++ +`hashmap_iter_first` is a combination of both (i.e. initializes the iterator +and returns the first entry, if any). + +Usage example +------------- + +Here's a simple usage example that maps long keys to double values. +[source,c] +------------ +struct hashmap map; + +struct long2double { + struct hashmap_entry ent; /* must be the first member! */ + long key; + double value; +}; + +static int long2double_cmp(const struct long2double *e1, const struct long2double *e2, const void *unused) +{ + return !(e1->key == e2->key); +} + +void long2double_init(void) +{ + hashmap_init(&map, (hashmap_cmp_fn) long2double_cmp, 0); +} + +void long2double_free(void) +{ + hashmap_free(&map, 1); +} + +static struct long2double *find_entry(long key) +{ + struct long2double k; + hashmap_entry_init(&k, memhash(&key, sizeof(long))); + k.key = key; + return hashmap_get(&map, &k, NULL); +} + +double get_value(long key) +{ + struct long2double *e = find_entry(key); + return e ? e->value : 0; +} + +void set_value(long key, double value) +{ + struct long2double *e = find_entry(key); + if (!e) { + e = malloc(sizeof(struct long2double)); + hashmap_entry_init(e, memhash(&key, sizeof(long))); + e->key = key; + hashmap_add(&map, e); + } + e->value = value; +} +------------ + +Using variable-sized keys +------------------------- + +The `hashmap_entry_get` and `hashmap_entry_remove` functions expect an ordinary +`hashmap_entry` structure as key to find the correct entry. If the key data is +variable-sized (e.g. a FLEX_ARRAY string) or quite large, it is undesirable +to create a full-fledged entry structure on the heap and copy all the key data +into the structure. + +In this case, the `keydata` parameter can be used to pass +variable-sized key data directly to the comparison function, and the `key` +parameter can be a stripped-down, fixed size entry structure allocated on the +stack. + +See test-hashmap.c for an example using arbitrary-length strings as keys. diff --git a/Documentation/technical/bitmap-format.txt b/Documentation/technical/bitmap-format.txt new file mode 100644 index 0000000000..f8c18a0f7a --- /dev/null +++ b/Documentation/technical/bitmap-format.txt @@ -0,0 +1,164 @@ +GIT bitmap v1 format +==================== + + - A header appears at the beginning: + + 4-byte signature: {'B', 'I', 'T', 'M'} + + 2-byte version number (network byte order) + The current implementation only supports version 1 + of the bitmap index (the same one as JGit). + + 2-byte flags (network byte order) + + The following flags are supported: + + - BITMAP_OPT_FULL_DAG (0x1) REQUIRED + This flag must always be present. It implies that the bitmap + index has been generated for a packfile with full closure + (i.e. where every single object in the packfile can find + its parent links inside the same packfile). This is a + requirement for the bitmap index format, also present in JGit, + that greatly reduces the complexity of the implementation. + + - BITMAP_OPT_HASH_CACHE (0x4) + If present, the end of the bitmap file contains + `N` 32-bit name-hash values, one per object in the + pack. The format and meaning of the name-hash is + described below. + + 4-byte entry count (network byte order) + + The total count of entries (bitmapped commits) in this bitmap index. + + 20-byte checksum + + The SHA1 checksum of the pack this bitmap index belongs to. + + - 4 EWAH bitmaps that act as type indexes + + Type indexes are serialized after the hash cache in the shape + of four EWAH bitmaps stored consecutively (see Appendix A for + the serialization format of an EWAH bitmap). + + There is a bitmap for each Git object type, stored in the following + order: + + - Commits + - Trees + - Blobs + - Tags + + In each bitmap, the `n`th bit is set to true if the `n`th object + in the packfile is of that type. + + The obvious consequence is that the OR of all 4 bitmaps will result + in a full set (all bits set), and the AND of all 4 bitmaps will + result in an empty bitmap (no bits set). + + - N entries with compressed bitmaps, one for each indexed commit + + Where `N` is the total amount of entries in this bitmap index. + Each entry contains the following: + + - 4-byte object position (network byte order) + The position **in the index for the packfile** where the + bitmap for this commit is found. + + - 1-byte XOR-offset + The xor offset used to compress this bitmap. For an entry + in position `x`, a XOR offset of `y` means that the actual + bitmap representing this commit is composed by XORing the + bitmap for this entry with the bitmap in entry `x-y` (i.e. + the bitmap `y` entries before this one). + + Note that this compression can be recursive. In order to + XOR this entry with a previous one, the previous entry needs + to be decompressed first, and so on. + + The hard-limit for this offset is 160 (an entry can only be + xor'ed against one of the 160 entries preceding it). This + number is always positive, and hence entries are always xor'ed + with **previous** bitmaps, not bitmaps that will come afterwards + in the index. + + - 1-byte flags for this bitmap + At the moment the only available flag is `0x1`, which hints + that this bitmap can be re-used when rebuilding bitmap indexes + for the repository. + + - The compressed bitmap itself, see Appendix A. + +== Appendix A: Serialization format for an EWAH bitmap + +Ewah bitmaps are serialized in the same protocol as the JAVAEWAH +library, making them backwards compatible with the JGit +implementation: + + - 4-byte number of bits of the resulting UNCOMPRESSED bitmap + + - 4-byte number of words of the COMPRESSED bitmap, when stored + + - N x 8-byte words, as specified by the previous field + + This is the actual content of the compressed bitmap. + + - 4-byte position of the current RLW for the compressed + bitmap + +All words are stored in network byte order for their corresponding +sizes. + +The compressed bitmap is stored in a form of run-length encoding, as +follows. It consists of a concatenation of an arbitrary number of +chunks. Each chunk consists of one or more 64-bit words + + H L_1 L_2 L_3 .... L_M + +H is called RLW (run length word). It consists of (from lower to higher +order bits): + + - 1 bit: the repeated bit B + + - 32 bits: repetition count K (unsigned) + + - 31 bits: literal word count M (unsigned) + +The bitstream represented by the above chunk is then: + + - K repetitions of B + + - The bits stored in `L_1` through `L_M`. Within a word, bits at + lower order come earlier in the stream than those at higher + order. + +The next word after `L_M` (if any) must again be a RLW, for the next +chunk. For efficient appending to the bitstream, the EWAH stores a +pointer to the last RLW in the stream. + + +== Appendix B: Optional Bitmap Sections + +These sections may or may not be present in the `.bitmap` file; their +presence is indicated by the header flags section described above. + +Name-hash cache +--------------- + +If the BITMAP_OPT_HASH_CACHE flag is set, the end of the bitmap contains +a cache of 32-bit values, one per object in the pack. The value at +position `i` is the hash of the pathname at which the `i`th object +(counting in index order) in the pack can be found. This can be fed +into the delta heuristics to compare objects with similar pathnames. + +The hash algorithm used is: + + hash = 0; + while ((c = *name++)) + if (!isspace(c)) + hash = (hash >> 2) + (c << 24); + +Note that this hashing scheme is tied to the BITMAP_OPT_HASH_CACHE flag. +If implementations want to choose a different hashing scheme, they are +free to do so, but MUST allocate a new header flag (because comparing +hashes made under two different schemes would be pointless). diff --git a/Documentation/technical/pack-protocol.txt b/Documentation/technical/pack-protocol.txt index c73b62f5e1..39c64105a6 100644 --- a/Documentation/technical/pack-protocol.txt +++ b/Documentation/technical/pack-protocol.txt @@ -338,7 +338,8 @@ during a prior round. This helps to ensure that at least one common ancestor is found before we give up entirely. Once the 'done' line is read from the client, the server will either -send a final 'ACK obj-id' or it will send a 'NAK'. The server only sends +send a final 'ACK obj-id' or it will send a 'NAK'. 'obj-id' is the object +name of the last commit determined to be common. The server only sends ACK after 'done' if there is at least one common base and multi_ack or multi_ack_detailed is enabled. The server always sends NAK after 'done' if there is no common base found. diff --git a/Documentation/technical/protocol-capabilities.txt b/Documentation/technical/protocol-capabilities.txt index e3e792476e..e174343847 100644 --- a/Documentation/technical/protocol-capabilities.txt +++ b/Documentation/technical/protocol-capabilities.txt @@ -69,6 +69,24 @@ ends. Without multi_ack the client would have sent that c-b-a chain anyway, interleaved with S-R-Q. +multi_ack_detailed +------------------ +This is an extension of multi_ack that permits client to better +understand the server's in-memory state. See pack-protocol.txt, +section "Packfile Negotiation" for more information. + +no-done +------- +This capability should only be used with the smart HTTP protocol. If +multi_ack_detailed and no-done are both present, then the sender is +free to immediately send a pack following its first "ACK obj-id ready" +message. + +Without no-done in the smart HTTP protocol, the server session would +end and the client has to make another trip to send "done" before +the server can send the pack. no-done removes the last round and +thus slightly reduces latency. + thin-pack --------- @@ -547,6 +547,7 @@ TEST_PROGRAMS_NEED_X += test-date TEST_PROGRAMS_NEED_X += test-delta TEST_PROGRAMS_NEED_X += test-dump-cache-tree TEST_PROGRAMS_NEED_X += test-genrandom +TEST_PROGRAMS_NEED_X += test-hashmap TEST_PROGRAMS_NEED_X += test-index-version TEST_PROGRAMS_NEED_X += test-line-buffer TEST_PROGRAMS_NEED_X += test-match-trees @@ -655,6 +656,8 @@ LIB_H += diff.h LIB_H += diffcore.h LIB_H += dir.h LIB_H += exec_cmd.h +LIB_H += ewah/ewok.h +LIB_H += ewah/ewok_rlw.h LIB_H += fetch-pack.h LIB_H += fmt-merge-msg.h LIB_H += fsck.h @@ -663,7 +666,7 @@ LIB_H += git-compat-util.h LIB_H += gpg-interface.h LIB_H += graph.h LIB_H += grep.h -LIB_H += hash.h +LIB_H += hashmap.h LIB_H += help.h LIB_H += http.h LIB_H += kwset.h @@ -682,8 +685,10 @@ LIB_H += notes-merge.h LIB_H += notes-utils.h LIB_H += notes.h LIB_H += object.h +LIB_H += pack-objects.h LIB_H += pack-revindex.h LIB_H += pack.h +LIB_H += pack-bitmap.h LIB_H += parse-options.h LIB_H += patch-ids.h LIB_H += pathspec.h @@ -787,6 +792,10 @@ LIB_OBJS += dir.o LIB_OBJS += editor.o LIB_OBJS += entry.o LIB_OBJS += environment.o +LIB_OBJS += ewah/bitmap.o +LIB_OBJS += ewah/ewah_bitmap.o +LIB_OBJS += ewah/ewah_io.o +LIB_OBJS += ewah/ewah_rlw.o LIB_OBJS += exec_cmd.o LIB_OBJS += fetch-pack.o LIB_OBJS += fsck.o @@ -794,7 +803,7 @@ LIB_OBJS += gettext.o LIB_OBJS += gpg-interface.o LIB_OBJS += graph.o LIB_OBJS += grep.o -LIB_OBJS += hash.o +LIB_OBJS += hashmap.o LIB_OBJS += help.o LIB_OBJS += hex.o LIB_OBJS += ident.o @@ -818,7 +827,10 @@ LIB_OBJS += notes-cache.o LIB_OBJS += notes-merge.o LIB_OBJS += notes-utils.o LIB_OBJS += object.o +LIB_OBJS += pack-bitmap.o +LIB_OBJS += pack-bitmap-write.o LIB_OBJS += pack-check.o +LIB_OBJS += pack-objects.o LIB_OBJS += pack-revindex.o LIB_OBJS += pack-write.o LIB_OBJS += pager.o @@ -2457,8 +2469,9 @@ profile-clean: $(RM) $(addsuffix *.gcno,$(addprefix $(PROFILE_DIR)/, $(object_dirs))) clean: profile-clean coverage-clean - $(RM) *.o *.res block-sha1/*.o ppc/*.o compat/*.o compat/*/*.o xdiff/*.o vcs-svn/*.o \ - builtin/*.o $(LIB_FILE) $(XDIFF_LIB) $(VCSSVN_LIB) + $(RM) *.o *.res block-sha1/*.o ppc/*.o compat/*.o compat/*/*.o + $(RM) xdiff/*.o vcs-svn/*.o ewah/*.o builtin/*.o + $(RM) $(LIB_FILE) $(XDIFF_LIB) $(VCSSVN_LIB) $(RM) $(ALL_PROGRAMS) $(SCRIPT_LIB) $(BUILT_INS) git$X $(RM) $(TEST_PROGRAMS) $(NO_INSTALL) $(RM) -r bin-wrappers $(dep_dirs) @@ -1 +1 @@ -Documentation/RelNotes/1.9.0.txt
\ No newline at end of file +Documentation/RelNotes/2.0.0.txt
\ No newline at end of file @@ -2,7 +2,6 @@ int advice_push_update_rejected = 1; int advice_push_non_ff_current = 1; -int advice_push_non_ff_default = 1; int advice_push_non_ff_matching = 1; int advice_push_already_exists = 1; int advice_push_fetch_first = 1; @@ -23,7 +22,6 @@ static struct { } advice_config[] = { { "pushupdaterejected", &advice_push_update_rejected }, { "pushnonffcurrent", &advice_push_non_ff_current }, - { "pushnonffdefault", &advice_push_non_ff_default }, { "pushnonffmatching", &advice_push_non_ff_matching }, { "pushalreadyexists", &advice_push_already_exists }, { "pushfetchfirst", &advice_push_fetch_first }, @@ -5,7 +5,6 @@ extern int advice_push_update_rejected; extern int advice_push_non_ff_current; -extern int advice_push_non_ff_default; extern int advice_push_non_ff_matching; extern int advice_push_already_exists; extern int advice_push_fetch_first; @@ -685,7 +685,6 @@ static void mark_expected_rev(char *bisect_rev_hex) static int bisect_checkout(char *bisect_rev_hex, int no_checkout) { - int res; mark_expected_rev(bisect_rev_hex); @@ -696,6 +695,7 @@ static int bisect_checkout(char *bisect_rev_hex, int no_checkout) die("update-ref --no-deref HEAD failed on %s", bisect_rev_hex); } else { + int res; res = run_command_v_opt(argv_checkout, RUN_GIT_CMD); if (res) exit(res); diff --git a/block-sha1/sha1.c b/block-sha1/sha1.c index e1a1eb6097..22b125cf8c 100644 --- a/block-sha1/sha1.c +++ b/block-sha1/sha1.c @@ -62,38 +62,6 @@ #define setW(x, val) (W(x) = (val)) #endif -/* - * Performance might be improved if the CPU architecture is OK with - * unaligned 32-bit loads and a fast ntohl() is available. - * Otherwise fall back to byte loads and shifts which is portable, - * and is faster on architectures with memory alignment issues. - */ - -#if defined(__i386__) || defined(__x86_64__) || \ - defined(_M_IX86) || defined(_M_X64) || \ - defined(__ppc__) || defined(__ppc64__) || \ - defined(__powerpc__) || defined(__powerpc64__) || \ - defined(__s390__) || defined(__s390x__) - -#define get_be32(p) ntohl(*(unsigned int *)(p)) -#define put_be32(p, v) do { *(unsigned int *)(p) = htonl(v); } while (0) - -#else - -#define get_be32(p) ( \ - (*((unsigned char *)(p) + 0) << 24) | \ - (*((unsigned char *)(p) + 1) << 16) | \ - (*((unsigned char *)(p) + 2) << 8) | \ - (*((unsigned char *)(p) + 3) << 0) ) -#define put_be32(p, v) do { \ - unsigned int __v = (v); \ - *((unsigned char *)(p) + 0) = __v >> 24; \ - *((unsigned char *)(p) + 1) = __v >> 16; \ - *((unsigned char *)(p) + 2) = __v >> 8; \ - *((unsigned char *)(p) + 3) = __v >> 0; } while (0) - -#endif - /* This "rolls" over the 512-bit array */ #define W(x) (array[(x)&15]) diff --git a/builtin/add.c b/builtin/add.c index 2a2722fa10..4b045bace1 100644 --- a/builtin/add.c +++ b/builtin/add.c @@ -26,55 +26,8 @@ static int take_worktree_changes; struct update_callback_data { int flags; int add_errors; - const char *implicit_dot; - size_t implicit_dot_len; - - /* only needed for 2.0 transition preparation */ - int warn_add_would_remove; }; -static const char *option_with_implicit_dot; -static const char *short_option_with_implicit_dot; - -static void warn_pathless_add(void) -{ - static int shown; - assert(option_with_implicit_dot && short_option_with_implicit_dot); - - if (shown) - return; - shown = 1; - - /* - * To be consistent with "git add -p" and most Git - * commands, we should default to being tree-wide, but - * this is not the original behavior and can't be - * changed until users trained themselves not to type - * "git add -u" or "git add -A". For now, we warn and - * keep the old behavior. Later, the behavior can be changed - * to tree-wide, keeping the warning for a while, and - * eventually we can drop the warning. - */ - warning(_("The behavior of 'git add %s (or %s)' with no path argument from a\n" - "subdirectory of the tree will change in Git 2.0 and should not be used anymore.\n" - "To add content for the whole tree, run:\n" - "\n" - " git add %s :/\n" - " (or git add %s :/)\n" - "\n" - "To restrict the command to the current directory, run:\n" - "\n" - " git add %s .\n" - " (or git add %s .)\n" - "\n" - "With the current Git version, the command is restricted to " - "the current directory.\n" - ""), - option_with_implicit_dot, short_option_with_implicit_dot, - option_with_implicit_dot, short_option_with_implicit_dot, - option_with_implicit_dot, short_option_with_implicit_dot); -} - static int fix_unmerged_status(struct diff_filepair *p, struct update_callback_data *data) { @@ -96,49 +49,15 @@ static int fix_unmerged_status(struct diff_filepair *p, return DIFF_STATUS_MODIFIED; } -static const char *add_would_remove_warning = N_( - "You ran 'git add' with neither '-A (--all)' or '--ignore-removal',\n" -"whose behaviour will change in Git 2.0 with respect to paths you removed.\n" -"Paths like '%s' that are\n" -"removed from your working tree are ignored with this version of Git.\n" -"\n" -"* 'git add --ignore-removal <pathspec>', which is the current default,\n" -" ignores paths you removed from your working tree.\n" -"\n" -"* 'git add --all <pathspec>' will let you also record the removals.\n" -"\n" -"Run 'git status' to check the paths you removed from your working tree.\n"); - -static void warn_add_would_remove(const char *path) -{ - warning(_(add_would_remove_warning), path); -} - static void update_callback(struct diff_queue_struct *q, struct diff_options *opt, void *cbdata) { int i; struct update_callback_data *data = cbdata; - const char *implicit_dot = data->implicit_dot; - size_t implicit_dot_len = data->implicit_dot_len; for (i = 0; i < q->nr; i++) { struct diff_filepair *p = q->queue[i]; const char *path = p->one->path; - /* - * Check if "git add -A" or "git add -u" was run from a - * subdirectory with a modified file outside that directory, - * and warn if so. - * - * "git add -u" will behave like "git add -u :/" instead of - * "git add -u ." in the future. This warning prepares for - * that change. - */ - if (implicit_dot && - strncmp_icase(path, implicit_dot, implicit_dot_len)) { - warn_pathless_add(); - continue; - } switch (fix_unmerged_status(p, data)) { default: die(_("unexpected diff status %c"), p->status); @@ -151,10 +70,6 @@ static void update_callback(struct diff_queue_struct *q, } break; case DIFF_STATUS_DELETED: - if (data->warn_add_would_remove) { - warn_add_would_remove(path); - data->warn_add_would_remove = 0; - } if (data->flags & ADD_CACHE_IGNORE_REMOVAL) break; if (!(data->flags & ADD_CACHE_PRETEND)) @@ -166,37 +81,28 @@ static void update_callback(struct diff_queue_struct *q, } } -static void update_files_in_cache(const char *prefix, - const struct pathspec *pathspec, - struct update_callback_data *data) +int add_files_to_cache(const char *prefix, + const struct pathspec *pathspec, int flags) { + struct update_callback_data data; struct rev_info rev; + memset(&data, 0, sizeof(data)); + data.flags = flags; + init_revisions(&rev, prefix); setup_revisions(0, NULL, &rev, NULL); if (pathspec) copy_pathspec(&rev.prune_data, pathspec); rev.diffopt.output_format = DIFF_FORMAT_CALLBACK; rev.diffopt.format_callback = update_callback; - rev.diffopt.format_callback_data = data; + rev.diffopt.format_callback_data = &data; rev.max_count = 0; /* do not compare unmerged paths with stage #2 */ run_diff_files(&rev, DIFF_RACY_IS_MODIFIED); -} - -int add_files_to_cache(const char *prefix, - const struct pathspec *pathspec, int flags) -{ - struct update_callback_data data; - - memset(&data, 0, sizeof(data)); - data.flags = flags; - update_files_in_cache(prefix, pathspec, &data); return !!data.add_errors; } -#define WARN_IMPLICIT_DOT (1u << 0) -static char *prune_directory(struct dir_struct *dir, struct pathspec *pathspec, - int prefix, unsigned flag) +static char *prune_directory(struct dir_struct *dir, struct pathspec *pathspec, int prefix) { char *seen; int i; @@ -208,19 +114,8 @@ static char *prune_directory(struct dir_struct *dir, struct pathspec *pathspec, i = dir->nr; while (--i >= 0) { struct dir_entry *entry = *src++; - if (match_pathspec_depth(pathspec, entry->name, entry->len, - prefix, seen)) + if (dir_path_match(entry, pathspec, prefix, seen)) *dst++ = entry; - else if (flag & WARN_IMPLICIT_DOT) - /* - * "git add -A" was run from a subdirectory with a - * new file outside that directory. - * - * "git add -A" will behave like "git add -A :/" - * instead of "git add -A ." in the future. - * Warn about the coming behavior change. - */ - warn_pathless_add(); } dir->nr = dst - dir->entries; add_pathspec_matches_against_index(pathspec, seen); @@ -339,7 +234,7 @@ N_("The following paths are ignored by one of your .gitignore files:\n"); static int verbose, show_only, ignored_too, refresh_only; static int ignore_add_errors, intent_to_add, ignore_missing; -#define ADDREMOVE_DEFAULT 0 /* Change to 1 in Git 2.0 */ +#define ADDREMOVE_DEFAULT 1 static int addremove = ADDREMOVE_DEFAULT; static int addremove_explicit = -1; /* unspecified */ @@ -412,8 +307,6 @@ int cmd_add(int argc, const char **argv, const char *prefix) int add_new_files; int require_pathspec; char *seen = NULL; - int implicit_dot = 0; - struct update_callback_data update_data; git_config(add_config, NULL); @@ -437,36 +330,17 @@ int cmd_add(int argc, const char **argv, const char *prefix) if (addremove && take_worktree_changes) die(_("-A and -u are mutually incompatible")); - /* - * Warn when "git add pathspec..." was given without "-u" or "-A" - * and pathspec... covers a removed path. - */ - memset(&update_data, 0, sizeof(update_data)); - if (!take_worktree_changes && addremove_explicit < 0) - update_data.warn_add_would_remove = 1; - if (!take_worktree_changes && addremove_explicit < 0 && argc) - /* - * Turn "git add pathspec..." to "git add -A pathspec..." - * in Git 2.0 but not yet - */ - ; /* addremove = 1; */ + /* Turn "git add pathspec..." to "git add -A pathspec..." */ + addremove = 1; if (!show_only && ignore_missing) die(_("Option --ignore-missing can only be used together with --dry-run")); - if (addremove) { - option_with_implicit_dot = "--all"; - short_option_with_implicit_dot = "-A"; - } - if (take_worktree_changes) { - option_with_implicit_dot = "--update"; - short_option_with_implicit_dot = "-u"; - } - if (option_with_implicit_dot && !argc) { - static const char *here[2] = { ".", NULL }; + + if ((0 < addremove_explicit || take_worktree_changes) && !argc) { + static const char *whole[2] = { ":/", NULL }; argc = 1; - argv = here; - implicit_dot = 1; + argv = whole; } add_new_files = !take_worktree_changes && !refresh_only; @@ -479,8 +353,7 @@ int cmd_add(int argc, const char **argv, const char *prefix) (intent_to_add ? ADD_CACHE_INTENT : 0) | (ignore_add_errors ? ADD_CACHE_IGNORE_ERRORS : 0) | (!(addremove || take_worktree_changes) - ? ADD_CACHE_IGNORE_REMOVAL : 0)) | - (implicit_dot ? ADD_CACHE_IMPLICIT_DOT : 0); + ? ADD_CACHE_IGNORE_REMOVAL : 0)); if (require_pathspec && argc == 0) { fprintf(stderr, _("Nothing specified, nothing added.\n")); @@ -514,18 +387,15 @@ int cmd_add(int argc, const char **argv, const char *prefix) memset(&empty_pathspec, 0, sizeof(empty_pathspec)); /* This picks up the paths that are not tracked */ - baselen = fill_directory(&dir, implicit_dot ? &empty_pathspec : &pathspec); + baselen = fill_directory(&dir, &pathspec); if (pathspec.nr) - seen = prune_directory(&dir, &pathspec, baselen, - implicit_dot ? WARN_IMPLICIT_DOT : 0); + seen = prune_directory(&dir, &pathspec, baselen); } if (refresh_only) { refresh(verbose, &pathspec); goto finish; } - if (implicit_dot && prefix) - refresh_cache(REFRESH_QUIET); if (pathspec.nr) { int i; @@ -565,21 +435,8 @@ int cmd_add(int argc, const char **argv, const char *prefix) plug_bulk_checkin(); - if ((flags & ADD_CACHE_IMPLICIT_DOT) && prefix) { - /* - * Check for modified files throughout the worktree so - * update_callback has a chance to warn about changes - * outside the cwd. - */ - update_data.implicit_dot = prefix; - update_data.implicit_dot_len = strlen(prefix); - free_pathspec(&pathspec); - memset(&pathspec, 0, sizeof(pathspec)); - } - update_data.flags = flags & ~ADD_CACHE_IMPLICIT_DOT; - update_files_in_cache(prefix, &pathspec, &update_data); + exit_status |= add_files_to_cache(prefix, &pathspec, flags); - exit_status |= !!update_data.add_errors; if (add_new_files) exit_status |= add_files(&dir, flags); diff --git a/builtin/apply.c b/builtin/apply.c index 66e2eed539..0189523798 100644 --- a/builtin/apply.c +++ b/builtin/apply.c @@ -1943,13 +1943,7 @@ static int parse_chunk(char *buffer, unsigned long size, struct patch *patch) size - offset - hdrsize, patch); if (!patchsize) { - static const char *binhdr[] = { - "Binary files ", - "Files ", - NULL, - }; static const char git_binary[] = "GIT binary patch\n"; - int i; int hd = hdrsize + offset; unsigned long llen = linelen(buffer + hd, size - hd); @@ -1965,6 +1959,12 @@ static int parse_chunk(char *buffer, unsigned long size, struct patch *patch) patchsize = 0; } else if (!memcmp(" differ\n", buffer + hd + llen - 8, 8)) { + static const char *binhdr[] = { + "Binary files ", + "Files ", + NULL, + }; + int i; for (i = 0; binhdr[i]; i++) { int len = strlen(binhdr[i]); if (len < size - hd && diff --git a/builtin/blame.c b/builtin/blame.c index e44a6bb30a..e5b5d71bad 100644 --- a/builtin/blame.c +++ b/builtin/blame.c @@ -197,7 +197,6 @@ static void drop_origin_blob(struct origin *o) * scoreboard structure, sorted by the target line number. */ struct blame_entry { - struct blame_entry *prev; struct blame_entry *next; /* the first line of this group in the final image; @@ -256,15 +255,6 @@ struct scoreboard { int *lineno; }; -static inline int same_suspect(struct origin *a, struct origin *b) -{ - if (a == b) - return 1; - if (a->commit != b->commit) - return 0; - return !strcmp(a->path, b->path); -} - static void sanity_check_refcnt(struct scoreboard *); /* @@ -277,13 +267,11 @@ static void coalesce(struct scoreboard *sb) struct blame_entry *ent, *next; for (ent = sb->ent; ent && (next = ent->next); ent = next) { - if (same_suspect(ent->suspect, next->suspect) && + if (ent->suspect == next->suspect && ent->guilty == next->guilty && ent->s_lno + ent->num_lines == next->s_lno) { ent->num_lines += next->num_lines; ent->next = next->next; - if (ent->next) - ent->next->prev = ent; origin_decref(next->suspect); free(next); ent->score = 0; @@ -534,7 +522,7 @@ static void add_blame_entry(struct scoreboard *sb, struct blame_entry *e) prev = ent; /* prev, if not NULL, is the last one that is below e */ - e->prev = prev; + if (prev) { e->next = prev->next; prev->next = e; @@ -543,8 +531,6 @@ static void add_blame_entry(struct scoreboard *sb, struct blame_entry *e) e->next = sb->ent; sb->ent = e; } - if (e->next) - e->next->prev = e; } /* @@ -555,14 +541,12 @@ static void add_blame_entry(struct scoreboard *sb, struct blame_entry *e) */ static void dup_entry(struct blame_entry *dst, struct blame_entry *src) { - struct blame_entry *p, *n; + struct blame_entry *n; - p = dst->prev; n = dst->next; origin_incref(src->suspect); origin_decref(dst->suspect); memcpy(dst, src, sizeof(*src)); - dst->prev = p; dst->next = n; dst->score = 0; } @@ -742,7 +726,7 @@ static int find_last_in_target(struct scoreboard *sb, struct origin *target) int last_in_target = -1; for (e = sb->ent; e; e = e->next) { - if (e->guilty || !same_suspect(e->suspect, target)) + if (e->guilty || e->suspect != target) continue; if (last_in_target < e->s_lno + e->num_lines) last_in_target = e->s_lno + e->num_lines; @@ -762,7 +746,7 @@ static void blame_chunk(struct scoreboard *sb, struct blame_entry *e; for (e = sb->ent; e; e = e->next) { - if (e->guilty || !same_suspect(e->suspect, target)) + if (e->guilty || e->suspect != target) continue; if (same <= e->s_lno) continue; @@ -939,7 +923,6 @@ static void find_copy_in_blob(struct scoreboard *sb, mmfile_t *file_p) { const char *cp; - int cnt; mmfile_t file_o; struct handle_split_cb_data d; @@ -950,13 +933,7 @@ static void find_copy_in_blob(struct scoreboard *sb, */ cp = nth_line(sb, ent->lno); file_o.ptr = (char *) cp; - cnt = ent->num_lines; - - while (cnt && cp < sb->final_buf + sb->final_buf_size) { - if (*cp++ == '\n') - cnt--; - } - file_o.size = cp - file_o.ptr; + file_o.size = nth_line(sb, ent->lno + ent->num_lines) - cp; /* * file_o is a part of final image we are annotating. @@ -992,7 +969,7 @@ static int find_move_in_parent(struct scoreboard *sb, while (made_progress) { made_progress = 0; for (e = sb->ent; e; e = e->next) { - if (e->guilty || !same_suspect(e->suspect, target) || + if (e->guilty || e->suspect != target || ent_score(sb, e) < blame_move_score) continue; find_copy_in_blob(sb, e, parent, split, &file_p); @@ -1027,14 +1004,14 @@ static struct blame_list *setup_blame_list(struct scoreboard *sb, for (e = sb->ent, num_ents = 0; e; e = e->next) if (!e->scanned && !e->guilty && - same_suspect(e->suspect, target) && + e->suspect == target && min_score < ent_score(sb, e)) num_ents++; if (num_ents) { blame_list = xcalloc(num_ents, sizeof(struct blame_list)); for (e = sb->ent, i = 0; e; e = e->next) if (!e->scanned && !e->guilty && - same_suspect(e->suspect, target) && + e->suspect == target && min_score < ent_score(sb, e)) blame_list[i++].ent = e; } @@ -1178,7 +1155,7 @@ static void pass_whole_blame(struct scoreboard *sb, origin->file.ptr = NULL; } for (e = sb->ent; e; e = e->next) { - if (!same_suspect(e->suspect, origin)) + if (e->suspect != origin) continue; origin_incref(porigin); origin_decref(e->suspect); @@ -1567,7 +1544,7 @@ static void assign_blame(struct scoreboard *sb, int opt) /* Take responsibility for the remaining entries */ for (ent = sb->ent; ent; ent = ent->next) - if (same_suspect(ent->suspect, suspect)) + if (ent->suspect == suspect) found_guilty_entry(ent); origin_decref(suspect); @@ -1580,14 +1557,14 @@ static const char *format_time(unsigned long time, const char *tz_str, int show_raw_time) { static char time_buf[128]; - const char *time_str; - int time_len; - int tz; if (show_raw_time) { snprintf(time_buf, sizeof(time_buf), "%lu %s", time, tz_str); } else { + const char *time_str; + int time_len; + int tz; tz = atoi(tz_str); time_str = show_date(time, tz, blame_date_mode); time_len = strlen(time_str); @@ -1772,25 +1749,41 @@ static int prepare_lines(struct scoreboard *sb) { const char *buf = sb->final_buf; unsigned long len = sb->final_buf_size; - int num = 0, incomplete = 0, bol = 1; + const char *end = buf + len; + const char *p; + int *lineno; + int num = 0, incomplete = 0; - if (len && buf[len-1] != '\n') - incomplete++; /* incomplete line at the end */ - while (len--) { - if (bol) { - sb->lineno = xrealloc(sb->lineno, - sizeof(int *) * (num + 1)); - sb->lineno[num] = buf - sb->final_buf; - bol = 0; - } - if (*buf++ == '\n') { + for (p = buf;;) { + p = memchr(p, '\n', end - p); + if (p) { + p++; num++; - bol = 1; + continue; } + break; } - sb->lineno = xrealloc(sb->lineno, - sizeof(int *) * (num + incomplete + 1)); - sb->lineno[num + incomplete] = buf - sb->final_buf; + + if (len && end[-1] != '\n') + incomplete++; /* incomplete line at the end */ + + sb->lineno = xmalloc(sizeof(*sb->lineno) * (num + incomplete + 1)); + lineno = sb->lineno; + + *lineno++ = 0; + for (p = buf;;) { + p = memchr(p, '\n', end - p); + if (p) { + p++; + *lineno++ = p - buf; + continue; + } + break; + } + + if (incomplete) + *lineno++ = len; + sb->num_lines = num + incomplete; return sb->num_lines; } @@ -2502,8 +2495,6 @@ parse_done: ent->suspect = o; ent->s_lno = bottom; ent->next = next; - if (next) - next->prev = ent; origin_incref(o); } origin_decref(o); diff --git a/builtin/check-attr.c b/builtin/check-attr.c index e9af7b2bfb..5600ec3f61 100644 --- a/builtin/check-attr.c +++ b/builtin/check-attr.c @@ -102,6 +102,9 @@ int cmd_check_attr(int argc, const char **argv, const char *prefix) struct git_attr_check *check; int cnt, i, doubledash, filei; + if (!is_bare_repository()) + setup_work_tree(); + git_config(git_default_config, NULL); argc = parse_options(argc, argv, prefix, check_attr_options, diff --git a/builtin/checkout.c b/builtin/checkout.c index 5df3837e31..ada51fa70f 100644 --- a/builtin/checkout.c +++ b/builtin/checkout.c @@ -297,8 +297,7 @@ static int checkout_paths(const struct checkout_opts *opts, * match_pathspec() for _all_ entries when * opts->source_tree != NULL. */ - if (match_pathspec_depth(&opts->pathspec, ce->name, ce_namelen(ce), - 0, ps_matched)) + if (ce_path_match(ce, &opts->pathspec, ps_matched)) ce->ce_flags |= CE_MATCHED; } diff --git a/builtin/clean.c b/builtin/clean.c index 2f26297142..114d7bf879 100644 --- a/builtin/clean.c +++ b/builtin/clean.c @@ -154,7 +154,7 @@ static int remove_dirs(struct strbuf *path, const char *prefix, int force_flag, DIR *dir; struct strbuf quoted = STRBUF_INIT; struct dirent *e; - int res = 0, ret = 0, gone = 1, original_len = path->len, len, i; + int res = 0, ret = 0, gone = 1, original_len = path->len, len; unsigned char submodule_head[20]; struct string_list dels = STRING_LIST_INIT_DUP; @@ -242,6 +242,7 @@ static int remove_dirs(struct strbuf *path, const char *prefix, int force_flag, } if (!*dir_gone && !quiet) { + int i; for (i = 0; i < dels.nr; i++) printf(dry_run ? _(msg_would_remove) : _(msg_remove), dels.items[i].string); } @@ -933,36 +934,18 @@ int cmd_clean(int argc, const char **argv, const char *prefix) for (i = 0; i < dir.nr; i++) { struct dir_entry *ent = dir.entries[i]; - int len, pos; int matches = 0; - const struct cache_entry *ce; struct stat st; const char *rel; - /* - * Remove the '/' at the end that directory - * walking adds for directory entries. - */ - len = ent->len; - if (len && ent->name[len-1] == '/') - len--; - pos = cache_name_pos(ent->name, len); - if (0 <= pos) - continue; /* exact match */ - pos = -pos - 1; - if (pos < active_nr) { - ce = active_cache[pos]; - if (ce_namelen(ce) == len && - !memcmp(ce->name, ent->name, len)) - continue; /* Yup, this one exists unmerged */ - } + if (!cache_name_is_other(ent->name, ent->len)) + continue; if (lstat(ent->name, &st)) die_errno("Cannot lstat '%s'", ent->name); if (pathspec.nr) - matches = match_pathspec_depth(&pathspec, ent->name, - len, 0, NULL); + matches = dir_path_match(ent, &pathspec, 0, NULL); if (S_ISDIR(st.st_mode)) { if (remove_directories || (matches == MATCHED_EXACTLY)) { diff --git a/builtin/commit-tree.c b/builtin/commit-tree.c index f641ff2a89..987a4c3d73 100644 --- a/builtin/commit-tree.c +++ b/builtin/commit-tree.c @@ -12,6 +12,8 @@ static const char commit_tree_usage[] = "git commit-tree [(-p <sha1>)...] [-S[<keyid>]] [-m <message>] [-F <file>] <sha1> <changelog"; +static const char *sign_commit; + static void new_parent(struct commit *parent, struct commit_list **parents_p) { unsigned char *sha1 = parent->object.sha1; @@ -31,6 +33,10 @@ static int commit_tree_config(const char *var, const char *value, void *cb) int status = git_gpg_config(var, value, NULL); if (status) return status; + if (!strcmp(var, "commit.gpgsign")) { + sign_commit = git_config_bool(var, value) ? "" : NULL; + return 0; + } return git_default_config(var, value, cb); } @@ -41,7 +47,6 @@ int cmd_commit_tree(int argc, const char **argv, const char *prefix) unsigned char tree_sha1[20]; unsigned char commit_sha1[20]; struct strbuf buffer = STRBUF_INIT; - const char *sign_commit = NULL; git_config(commit_tree_config, NULL); @@ -66,6 +71,11 @@ int cmd_commit_tree(int argc, const char **argv, const char *prefix) continue; } + if (!strcmp(arg, "--no-gpg-sign")) { + sign_commit = NULL; + continue; + } + if (!strcmp(arg, "-m")) { if (argc <= ++i) usage(commit_tree_usage); diff --git a/builtin/commit.c b/builtin/commit.c index 3767478c6d..3783bcadcd 100644 --- a/builtin/commit.c +++ b/builtin/commit.c @@ -234,7 +234,7 @@ static int list_paths(struct string_list *list, const char *with_tree, if (ce->ce_flags & CE_UPDATE) continue; - if (!match_pathspec_depth(pattern, ce->name, ce_namelen(ce), 0, m)) + if (!ce_path_match(ce, pattern, m)) continue; item = string_list_insert(list, ce->name); if (ce_skip_worktree(ce)) @@ -307,7 +307,6 @@ static char *prepare_index(int argc, const char **argv, const char *prefix, int fd; struct string_list partial; struct pathspec pathspec; - char *old_index_env = NULL; int refresh_flags = REFRESH_QUIET; if (is_status) @@ -320,6 +319,7 @@ static char *prepare_index(int argc, const char **argv, const char *prefix, die(_("index file corrupt")); if (interactive) { + char *old_index_env = NULL; fd = hold_locked_index(&index_lock, 1); refresh_cache_or_die(refresh_flags); @@ -600,12 +600,10 @@ static int prepare_to_commit(const char *index_file, const char *prefix, { struct stat statbuf; struct strbuf committer_ident = STRBUF_INIT; - int commitable, saved_color_setting; + int commitable; struct strbuf sb = STRBUF_INIT; - char *buffer; const char *hook_arg1 = NULL; const char *hook_arg2 = NULL; - int ident_shown = 0; int clean_message_contents = (cleanup_mode != CLEANUP_NONE); int old_display_comment_prefix; @@ -649,6 +647,7 @@ static int prepare_to_commit(const char *index_file, const char *prefix, logfile); hook_arg1 = "message"; } else if (use_message) { + char *buffer; buffer = strstr(use_message_buffer, "\n\n"); if (!use_editor && (!buffer || buffer[2] == '\0')) die(_("commit has empty message")); @@ -753,6 +752,8 @@ static int prepare_to_commit(const char *index_file, const char *prefix, /* This checks if committer ident is explicitly given */ strbuf_addstr(&committer_ident, git_committer_info(IDENT_STRICT)); if (use_editor && include_status) { + int ident_shown = 0; + int saved_color_setting; char *ai_tmp, *ci_tmp; if (whence != FROM_COMMIT) status_printf_ln(s, GIT_COLOR_NORMAL, @@ -1406,6 +1407,10 @@ static int git_commit_config(const char *k, const char *v, void *cb) } if (!strcmp(k, "commit.cleanup")) return git_config_string(&cleanup_arg, k, v); + if (!strcmp(k, "commit.gpgsign")) { + sign_commit = git_config_bool(k, v) ? "" : NULL; + return 0; + } status = git_gpg_config(k, v, NULL); if (status) @@ -1510,7 +1515,6 @@ int cmd_commit(int argc, const char **argv, const char *prefix) struct ref_lock *ref_lock; struct commit_list *parents = NULL, **pptr = &parents; struct stat statbuf; - int allow_fast_forward = 1; struct commit *current_head = NULL; struct commit_extra_header *extra = NULL; @@ -1558,6 +1562,7 @@ int cmd_commit(int argc, const char **argv, const char *prefix) } else if (whence == FROM_MERGE) { struct strbuf m = STRBUF_INIT; FILE *fp; + int allow_fast_forward = 1; if (!reflog_msg) reflog_msg = "commit (merge)"; diff --git a/builtin/config.c b/builtin/config.c index 92ebf23f0a..5677c942b6 100644 --- a/builtin/config.c +++ b/builtin/config.c @@ -21,8 +21,7 @@ static char key_delim = ' '; static char term = '\n'; static int use_global_config, use_system_config, use_local_config; -static const char *given_config_file; -static const char *given_config_blob; +static struct git_config_source given_config_source; static int actions, types; static const char *get_color_slot, *get_colorbool_slot; static int end_null; @@ -55,8 +54,8 @@ static struct option builtin_config_options[] = { OPT_BOOL(0, "global", &use_global_config, N_("use global config file")), OPT_BOOL(0, "system", &use_system_config, N_("use system config file")), OPT_BOOL(0, "local", &use_local_config, N_("use repository config file")), - OPT_STRING('f', "file", &given_config_file, N_("file"), N_("use given config file")), - OPT_STRING(0, "blob", &given_config_blob, N_("blob-id"), N_("read config from given blob object")), + OPT_STRING('f', "file", &given_config_source.file, N_("file"), N_("use given config file")), + OPT_STRING(0, "blob", &given_config_source.blob, N_("blob-id"), N_("read config from given blob object")), OPT_GROUP(N_("Action")), OPT_BIT(0, "get", &actions, N_("get value: name [value-regex]"), ACTION_GET), OPT_BIT(0, "get-all", &actions, N_("get all values: key [value-regex]"), ACTION_GET_ALL), @@ -224,8 +223,7 @@ static int get_value(const char *key_, const char *regex_) } git_config_with_options(collect_config, &values, - given_config_file, given_config_blob, - respect_includes); + &given_config_source, respect_includes); ret = !values.nr; @@ -309,8 +307,7 @@ static void get_color(const char *def_color) get_color_found = 0; parsed_color[0] = '\0'; git_config_with_options(git_get_color_config, NULL, - given_config_file, given_config_blob, - respect_includes); + &given_config_source, respect_includes); if (!get_color_found && def_color) color_parse(def_color, "command line", parsed_color); @@ -339,8 +336,7 @@ static int get_colorbool(int print) get_diff_color_found = -1; get_color_ui_found = -1; git_config_with_options(git_get_colorbool_config, NULL, - given_config_file, given_config_blob, - respect_includes); + &given_config_source, respect_includes); if (get_colorbool_found < 0) { if (!strcmp(get_colorbool_slot, "color.diff")) @@ -362,9 +358,12 @@ static int get_colorbool(int print) return get_colorbool_found ? 0 : 1; } -static void check_blob_write(void) +static void check_write(void) { - if (given_config_blob) + if (given_config_source.use_stdin) + die("writing to stdin is not supported"); + + if (given_config_source.blob) die("writing config blobs is not supported"); } @@ -435,7 +434,7 @@ static int get_urlmatch(const char *var, const char *url) } git_config_with_options(urlmatch_config_entry, &config, - given_config_file, NULL, respect_includes); + &given_config_source, respect_includes); for_each_string_list_item(item, &values) { struct urlmatch_current_candidate_value *matched = item->util; @@ -464,18 +463,24 @@ int cmd_config(int argc, const char **argv, const char *prefix) int nongit = !startup_info->have_repository; char *value; - given_config_file = getenv(CONFIG_ENVIRONMENT); + given_config_source.file = getenv(CONFIG_ENVIRONMENT); argc = parse_options(argc, argv, prefix, builtin_config_options, builtin_config_usage, PARSE_OPT_STOP_AT_NON_OPTION); if (use_global_config + use_system_config + use_local_config + - !!given_config_file + !!given_config_blob > 1) { + !!given_config_source.file + !!given_config_source.blob > 1) { error("only one config file at a time."); usage_with_options(builtin_config_usage, builtin_config_options); } + if (given_config_source.file && + !strcmp(given_config_source.file, "-")) { + given_config_source.file = NULL; + given_config_source.use_stdin = 1; + } + if (use_global_config) { char *user_config = NULL; char *xdg_config = NULL; @@ -493,24 +498,24 @@ int cmd_config(int argc, const char **argv, const char *prefix) if (access_or_warn(user_config, R_OK, 0) && xdg_config && !access_or_warn(xdg_config, R_OK, 0)) - given_config_file = xdg_config; + given_config_source.file = xdg_config; else - given_config_file = user_config; + given_config_source.file = user_config; } else if (use_system_config) - given_config_file = git_etc_gitconfig(); + given_config_source.file = git_etc_gitconfig(); else if (use_local_config) - given_config_file = git_pathdup("config"); - else if (given_config_file) { - if (!is_absolute_path(given_config_file) && prefix) - given_config_file = + given_config_source.file = git_pathdup("config"); + else if (given_config_source.file) { + if (!is_absolute_path(given_config_source.file) && prefix) + given_config_source.file = xstrdup(prefix_filename(prefix, strlen(prefix), - given_config_file)); + given_config_source.file)); } if (respect_includes == -1) - respect_includes = !given_config_file; + respect_includes = !given_config_source.file; if (end_null) { term = '\0'; @@ -549,57 +554,58 @@ int cmd_config(int argc, const char **argv, const char *prefix) if (actions == ACTION_LIST) { check_argc(argc, 0, 0); if (git_config_with_options(show_all_config, NULL, - given_config_file, - given_config_blob, + &given_config_source, respect_includes) < 0) { - if (given_config_file) + if (given_config_source.file) die_errno("unable to read config file '%s'", - given_config_file); + given_config_source.file); else die("error processing config file(s)"); } } else if (actions == ACTION_EDIT) { check_argc(argc, 0, 0); - if (!given_config_file && nongit) + if (!given_config_source.file && nongit) die("not in a git directory"); - if (given_config_blob) + if (given_config_source.use_stdin) + die("editing stdin is not supported"); + if (given_config_source.blob) die("editing blobs is not supported"); git_config(git_default_config, NULL); - launch_editor(given_config_file ? - given_config_file : git_path("config"), + launch_editor(given_config_source.file ? + given_config_source.file : git_path("config"), NULL, NULL); } else if (actions == ACTION_SET) { int ret; - check_blob_write(); + check_write(); check_argc(argc, 2, 2); value = normalize_value(argv[0], argv[1]); - ret = git_config_set_in_file(given_config_file, argv[0], value); + ret = git_config_set_in_file(given_config_source.file, argv[0], value); if (ret == CONFIG_NOTHING_SET) error("cannot overwrite multiple values with a single value\n" " Use a regexp, --add or --replace-all to change %s.", argv[0]); return ret; } else if (actions == ACTION_SET_ALL) { - check_blob_write(); + check_write(); check_argc(argc, 2, 3); value = normalize_value(argv[0], argv[1]); - return git_config_set_multivar_in_file(given_config_file, + return git_config_set_multivar_in_file(given_config_source.file, argv[0], value, argv[2], 0); } else if (actions == ACTION_ADD) { - check_blob_write(); + check_write(); check_argc(argc, 2, 2); value = normalize_value(argv[0], argv[1]); - return git_config_set_multivar_in_file(given_config_file, + return git_config_set_multivar_in_file(given_config_source.file, argv[0], value, "^$", 0); } else if (actions == ACTION_REPLACE_ALL) { - check_blob_write(); + check_write(); check_argc(argc, 2, 3); value = normalize_value(argv[0], argv[1]); - return git_config_set_multivar_in_file(given_config_file, + return git_config_set_multivar_in_file(given_config_source.file, argv[0], value, argv[2], 1); } else if (actions == ACTION_GET) { @@ -623,26 +629,26 @@ int cmd_config(int argc, const char **argv, const char *prefix) return get_urlmatch(argv[0], argv[1]); } else if (actions == ACTION_UNSET) { - check_blob_write(); + check_write(); check_argc(argc, 1, 2); if (argc == 2) - return git_config_set_multivar_in_file(given_config_file, + return git_config_set_multivar_in_file(given_config_source.file, argv[0], NULL, argv[1], 0); else - return git_config_set_in_file(given_config_file, + return git_config_set_in_file(given_config_source.file, argv[0], NULL); } else if (actions == ACTION_UNSET_ALL) { - check_blob_write(); + check_write(); check_argc(argc, 1, 2); - return git_config_set_multivar_in_file(given_config_file, + return git_config_set_multivar_in_file(given_config_source.file, argv[0], NULL, argv[1], 1); } else if (actions == ACTION_RENAME_SECTION) { int ret; - check_blob_write(); + check_write(); check_argc(argc, 2, 2); - ret = git_config_rename_section_in_file(given_config_file, + ret = git_config_rename_section_in_file(given_config_source.file, argv[0], argv[1]); if (ret < 0) return ret; @@ -651,9 +657,9 @@ int cmd_config(int argc, const char **argv, const char *prefix) } else if (actions == ACTION_REMOVE_SECTION) { int ret; - check_blob_write(); + check_write(); check_argc(argc, 1, 1); - ret = git_config_rename_section_in_file(given_config_file, + ret = git_config_rename_section_in_file(given_config_source.file, argv[0], NULL); if (ret < 0) return ret; diff --git a/builtin/describe.c b/builtin/describe.c index 848acdf299..24d740c8b1 100644 --- a/builtin/describe.c +++ b/builtin/describe.c @@ -6,7 +6,7 @@ #include "exec_cmd.h" #include "parse-options.h" #include "diff.h" -#include "hash.h" +#include "hashmap.h" #include "argv-array.h" #define SEEN (1u << 0) @@ -25,7 +25,7 @@ static int longformat; static int first_parent; static int abbrev = -1; /* unspecified */ static int max_candidates = 10; -static struct hash_table names; +static struct hashmap names; static int have_util; static const char *pattern; static int always; @@ -37,7 +37,7 @@ static const char *diff_index_args[] = { }; struct commit_name { - struct commit_name *next; + struct hashmap_entry entry; unsigned char peeled[20]; struct tag *tag; unsigned prio:2; /* annotated tag = 2, tag = 1, head = 0 */ @@ -50,6 +50,12 @@ static const char *prio_names[] = { "head", "lightweight", "annotated", }; +static int commit_name_cmp(const struct commit_name *cn1, + const struct commit_name *cn2, const void *peeled) +{ + return hashcmp(cn1->peeled, peeled ? peeled : cn2->peeled); +} + static inline unsigned int hash_sha1(const unsigned char *sha1) { unsigned int hash; @@ -59,21 +65,9 @@ static inline unsigned int hash_sha1(const unsigned char *sha1) static inline struct commit_name *find_commit_name(const unsigned char *peeled) { - struct commit_name *n = lookup_hash(hash_sha1(peeled), &names); - while (n && !!hashcmp(peeled, n->peeled)) - n = n->next; - return n; -} - -static int set_util(void *chain, void *data) -{ - struct commit_name *n; - for (n = chain; n; n = n->next) { - struct commit *c = lookup_commit_reference_gently(n->peeled, 1); - if (c) - c->util = n; - } - return 0; + struct commit_name key; + hashmap_entry_init(&key, hash_sha1(peeled)); + return hashmap_get(&names, &key, peeled); } static int replace_name(struct commit_name *e, @@ -118,16 +112,10 @@ static void add_to_known_names(const char *path, struct tag *tag = NULL; if (replace_name(e, prio, sha1, &tag)) { if (!e) { - void **pos; e = xmalloc(sizeof(struct commit_name)); hashcpy(e->peeled, peeled); - pos = insert_hash(hash_sha1(peeled), e, &names); - if (pos) { - e->next = *pos; - *pos = e; - } else { - e->next = NULL; - } + hashmap_entry_init(e, hash_sha1(peeled)); + hashmap_add(&names, e); e->path = NULL; } e->tag = tag; @@ -292,7 +280,14 @@ static void describe(const char *arg, int last_one) fprintf(stderr, _("searching to describe %s\n"), arg); if (!have_util) { - for_each_hash(&names, set_util, NULL); + struct hashmap_iter iter; + struct commit *c; + struct commit_name *n = hashmap_iter_first(&names, &iter); + for (; n; n = hashmap_iter_next(&iter)) { + c = lookup_commit_reference_gently(n->peeled, 1); + if (c) + c->util = n; + } have_util = 1; } @@ -463,9 +458,9 @@ int cmd_describe(int argc, const char **argv, const char *prefix) return cmd_name_rev(args.argc, args.argv, prefix); } - init_hash(&names); + hashmap_init(&names, (hashmap_cmp_fn) commit_name_cmp, 0); for_each_rawref(get_name, NULL); - if (!names.nr && !always) + if (!names.size && !always) die(_("No names found, cannot describe anything.")); if (argc == 0) { diff --git a/builtin/fetch.c b/builtin/fetch.c index 025bc3e38d..55f457c04f 100644 --- a/builtin/fetch.c +++ b/builtin/fetch.c @@ -1026,7 +1026,6 @@ static int fetch_multiple(struct string_list *list) static int fetch_one(struct remote *remote, int argc, const char **argv) { - int i; static const char **refs = NULL; struct refspec *refspec; int ref_nr = 0; @@ -1050,6 +1049,7 @@ static int fetch_one(struct remote *remote, int argc, const char **argv) if (argc > 0) { int j = 0; + int i; refs = xcalloc(argc + 1, sizeof(const char *)); for (i = 0; i < argc; i++) { if (!strcmp(argv[i], "tag")) { diff --git a/builtin/gc.c b/builtin/gc.c index c19545d49e..63d400bcb2 100644 --- a/builtin/gc.c +++ b/builtin/gc.c @@ -29,6 +29,7 @@ static int pack_refs = 1; static int aggressive_window = 250; static int gc_auto_threshold = 6700; static int gc_auto_pack_limit = 50; +static int detach_auto = 1; static const char *prune_expire = "2.weeks.ago"; static struct argv_array pack_refs_cmd = ARGV_ARRAY_INIT; @@ -73,6 +74,10 @@ static int gc_config(const char *var, const char *value, void *cb) gc_auto_pack_limit = git_config_int(var, value); return 0; } + if (!strcmp(var, "gc.autodetach")) { + detach_auto = git_config_bool(var, value); + return 0; + } if (!strcmp(var, "gc.pruneexpire")) { if (value && strcmp(value, "now")) { unsigned long now = approxidate("now"); @@ -188,13 +193,12 @@ static int need_to_gc(void) static const char *lock_repo_for_gc(int force, pid_t* ret_pid) { static struct lock_file lock; - static char locking_host[128]; char my_host[128]; struct strbuf sb = STRBUF_INIT; struct stat st; uintmax_t pid; FILE *fp; - int fd, should_exit; + int fd; if (pidfile) /* already locked */ @@ -206,6 +210,8 @@ static const char *lock_repo_for_gc(int force, pid_t* ret_pid) fd = hold_lock_file_for_update(&lock, git_path("gc.pid"), LOCK_DIE_ON_ERROR); if (!force) { + static char locking_host[128]; + int should_exit; fp = fopen(git_path("gc.pid"), "r"); memset(locking_host, 0, sizeof(locking_host)); should_exit = @@ -301,11 +307,19 @@ int cmd_gc(int argc, const char **argv, const char *prefix) */ if (!need_to_gc()) return 0; - if (!quiet) - fprintf(stderr, - _("Auto packing the repository for optimum performance. You may also\n" - "run \"git gc\" manually. See " - "\"git help gc\" for more information.\n")); + if (!quiet) { + if (detach_auto) + fprintf(stderr, _("Auto packing the repository in background for optimum performance.\n")); + else + fprintf(stderr, _("Auto packing the repository for optimum performance.\n")); + fprintf(stderr, _("See \"git help gc\" for manual housekeeping.\n")); + } + if (detach_auto) + /* + * failure to daemonize is ok, we'll continue + * in foreground + */ + daemonize(); } else add_repack_all_option(); diff --git a/builtin/grep.c b/builtin/grep.c index 63f86032d9..69ac2d8797 100644 --- a/builtin/grep.c +++ b/builtin/grep.c @@ -379,7 +379,7 @@ static int grep_cache(struct grep_opt *opt, const struct pathspec *pathspec, int const struct cache_entry *ce = active_cache[nr]; if (!S_ISREG(ce->ce_mode)) continue; - if (!match_pathspec_depth(pathspec, ce->name, ce_namelen(ce), 0, NULL)) + if (!ce_path_match(ce, pathspec, NULL)) continue; /* * If CE_VALID is on, we assume worktree file and its cache entry @@ -524,9 +524,7 @@ static int grep_directory(struct grep_opt *opt, const struct pathspec *pathspec, fill_directory(&dir, pathspec); for (i = 0; i < dir.nr; i++) { - const char *name = dir.entries[i]->name; - int namelen = strlen(name); - if (!match_pathspec_depth(pathspec, name, namelen, 0, NULL)) + if (!dir_path_match(dir.entries[i], pathspec, 0, NULL)) continue; hit |= grep_file(opt, dir.entries[i]->name); if (hit && opt->status_only) diff --git a/builtin/ls-files.c b/builtin/ls-files.c index e1cf6d8547..47c38808a2 100644 --- a/builtin/ls-files.c +++ b/builtin/ls-files.c @@ -64,7 +64,7 @@ static void show_dir_entry(const char *tag, struct dir_entry *ent) if (len >= ent->len) die("git ls-files: internal error - directory entry not superset of prefix"); - if (!match_pathspec_depth(&pathspec, ent->name, ent->len, len, ps_matched)) + if (!dir_path_match(ent, &pathspec, len, ps_matched)) return; fputs(tag, stdout); @@ -139,7 +139,9 @@ static void show_ce_entry(const char *tag, const struct cache_entry *ce) if (len >= ce_namelen(ce)) die("git ls-files: internal error - cache entry not superset of prefix"); - if (!match_pathspec_depth(&pathspec, ce->name, ce_namelen(ce), len, ps_matched)) + if (!match_pathspec(&pathspec, ce->name, ce_namelen(ce), + len, ps_matched, + S_ISDIR(ce->ce_mode) || S_ISGITLINK(ce->ce_mode))) return; if (tag && *tag && show_valid_bit && @@ -195,7 +197,8 @@ static void show_ru_info(void) len = strlen(path); if (len < max_prefix_len) continue; /* outside of the prefix */ - if (!match_pathspec_depth(&pathspec, path, len, max_prefix_len, ps_matched)) + if (!match_pathspec(&pathspec, path, len, + max_prefix_len, ps_matched, 0)) continue; /* uninterested */ for (i = 0; i < 3; i++) { if (!ui->mode[i]) diff --git a/builtin/ls-tree.c b/builtin/ls-tree.c index 65ec931846..51184dfa2e 100644 --- a/builtin/ls-tree.c +++ b/builtin/ls-tree.c @@ -171,7 +171,7 @@ int cmd_ls_tree(int argc, const char **argv, const char *prefix) * show_recursive() rolls its own matching code and is * generally ignorant of 'struct pathspec'. The magic mask * cannot be lifted until it is converted to use - * match_pathspec_depth() or tree_entry_interesting() + * match_pathspec() or tree_entry_interesting() */ parse_pathspec(&pathspec, PATHSPEC_GLOB | PATHSPEC_ICASE, PATHSPEC_PREFER_CWD, diff --git a/builtin/merge.c b/builtin/merge.c index e576a7fdc6..f0cf1205fa 100644 --- a/builtin/merge.c +++ b/builtin/merge.c @@ -597,6 +597,9 @@ static int git_merge_config(const char *k, const char *v, void *cb) } else if (!strcmp(k, "merge.defaulttoupstream")) { default_to_upstream = git_config_bool(k, v); return 0; + } else if (!strcmp(k, "commit.gpgsign")) { + sign_commit = git_config_bool(k, v) ? "" : NULL; + return 0; } status = fmt_merge_msg_config(k, v, cb); diff --git a/builtin/mv.c b/builtin/mv.c index 21c46d1636..7e26eb5229 100644 --- a/builtin/mv.c +++ b/builtin/mv.c @@ -162,7 +162,8 @@ int cmd_mv(int argc, const char **argv, const char *prefix) if (strncmp(path, src_w_slash, len_w_slash)) break; } - free((char *)src_w_slash); + if (src_w_slash != src) + free((char *)src_w_slash); if (last - first < 1) bad = _("source directory is empty"); diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c index 541667f102..c73337931b 100644 --- a/builtin/pack-objects.c +++ b/builtin/pack-objects.c @@ -14,10 +14,12 @@ #include "diff.h" #include "revision.h" #include "list-objects.h" +#include "pack-objects.h" #include "progress.h" #include "refs.h" #include "streaming.h" #include "thread-utils.h" +#include "pack-bitmap.h" static const char *pack_usage[] = { N_("git pack-objects --stdout [options...] [< ref-list | < object-list]"), @@ -25,42 +27,15 @@ static const char *pack_usage[] = { NULL }; -struct object_entry { - struct pack_idx_entry idx; - unsigned long size; /* uncompressed size */ - struct packed_git *in_pack; /* already in pack */ - off_t in_pack_offset; - struct object_entry *delta; /* delta base object */ - struct object_entry *delta_child; /* deltified objects who bases me */ - struct object_entry *delta_sibling; /* other deltified objects who - * uses the same base as me - */ - void *delta_data; /* cached delta (uncompressed) */ - unsigned long delta_size; /* delta data size (uncompressed) */ - unsigned long z_delta_size; /* delta data size (compressed) */ - enum object_type type; - enum object_type in_pack_type; /* could be delta */ - uint32_t hash; /* name hint hash */ - unsigned char in_pack_header_size; - unsigned preferred_base:1; /* - * we do not pack this, but is available - * to be used as the base object to delta - * objects against. - */ - unsigned no_try_delta:1; - unsigned tagged:1; /* near the very tip of refs */ - unsigned filled:1; /* assigned write-order */ -}; - /* - * Objects we are going to pack are collected in objects array (dynamically - * expanded). nr_objects & nr_alloc controls this array. They are stored - * in the order we see -- typically rev-list --objects order that gives us - * nice "minimum seek" order. + * Objects we are going to pack are collected in the `to_pack` structure. + * It contains an array (dynamically expanded) of the object data, and a map + * that can resolve SHA1s to their position in the array. */ -static struct object_entry *objects; +static struct packing_data to_pack; + static struct pack_idx_entry **written_list; -static uint32_t nr_objects, nr_alloc, nr_result, nr_written; +static uint32_t nr_result, nr_written; static int non_empty; static int reuse_delta = 1, reuse_object = 1; @@ -83,6 +58,14 @@ static struct progress *progress_state; static int pack_compression_level = Z_DEFAULT_COMPRESSION; static int pack_compression_seen; +static struct packed_git *reuse_packfile; +static uint32_t reuse_packfile_objects; +static off_t reuse_packfile_offset; + +static int use_bitmap_index = 1; +static int write_bitmap_index; +static uint16_t write_bitmap_options; + static unsigned long delta_cache_size = 0; static unsigned long max_delta_cache_size = 256 * 1024 * 1024; static unsigned long cache_max_small_delta_size = 1000; @@ -90,20 +73,28 @@ static unsigned long cache_max_small_delta_size = 1000; static unsigned long window_memory_limit = 0; /* - * The object names in objects array are hashed with this hashtable, - * to help looking up the entry by object name. - * This hashtable is built after all the objects are seen. - */ -static int *object_ix; -static int object_ix_hashsz; -static struct object_entry *locate_object_entry(const unsigned char *sha1); - -/* * stats */ static uint32_t written, written_delta; static uint32_t reused, reused_delta; +/* + * Indexed commits + */ +static struct commit **indexed_commits; +static unsigned int indexed_commits_nr; +static unsigned int indexed_commits_alloc; + +static void index_commit_for_bitmap(struct commit *commit) +{ + if (indexed_commits_nr >= indexed_commits_alloc) { + indexed_commits_alloc = (indexed_commits_alloc + 32) * 2; + indexed_commits = xrealloc(indexed_commits, + indexed_commits_alloc * sizeof(struct commit *)); + } + + indexed_commits[indexed_commits_nr++] = commit; +} static void *get_delta(struct object_entry *entry) { @@ -553,12 +544,12 @@ static int mark_tagged(const char *path, const unsigned char *sha1, int flag, void *cb_data) { unsigned char peeled[20]; - struct object_entry *entry = locate_object_entry(sha1); + struct object_entry *entry = packlist_find(&to_pack, sha1, NULL); if (entry) entry->tagged = 1; if (!peel_ref(path, peeled)) { - entry = locate_object_entry(peeled); + entry = packlist_find(&to_pack, peeled, NULL); if (entry) entry->tagged = 1; } @@ -633,9 +624,10 @@ static struct object_entry **compute_write_order(void) { unsigned int i, wo_end, last_untagged; - struct object_entry **wo = xmalloc(nr_objects * sizeof(*wo)); + struct object_entry **wo = xmalloc(to_pack.nr_objects * sizeof(*wo)); + struct object_entry *objects = to_pack.objects; - for (i = 0; i < nr_objects; i++) { + for (i = 0; i < to_pack.nr_objects; i++) { objects[i].tagged = 0; objects[i].filled = 0; objects[i].delta_child = NULL; @@ -647,7 +639,7 @@ static struct object_entry **compute_write_order(void) * Make sure delta_sibling is sorted in the original * recency order. */ - for (i = nr_objects; i > 0;) { + for (i = to_pack.nr_objects; i > 0;) { struct object_entry *e = &objects[--i]; if (!e->delta) continue; @@ -665,7 +657,7 @@ static struct object_entry **compute_write_order(void) * Give the objects in the original recency order until * we see a tagged tip. */ - for (i = wo_end = 0; i < nr_objects; i++) { + for (i = wo_end = 0; i < to_pack.nr_objects; i++) { if (objects[i].tagged) break; add_to_write_order(wo, &wo_end, &objects[i]); @@ -675,7 +667,7 @@ static struct object_entry **compute_write_order(void) /* * Then fill all the tagged tips. */ - for (; i < nr_objects; i++) { + for (; i < to_pack.nr_objects; i++) { if (objects[i].tagged) add_to_write_order(wo, &wo_end, &objects[i]); } @@ -683,7 +675,7 @@ static struct object_entry **compute_write_order(void) /* * And then all remaining commits and tags. */ - for (i = last_untagged; i < nr_objects; i++) { + for (i = last_untagged; i < to_pack.nr_objects; i++) { if (objects[i].type != OBJ_COMMIT && objects[i].type != OBJ_TAG) continue; @@ -693,7 +685,7 @@ static struct object_entry **compute_write_order(void) /* * And then all the trees. */ - for (i = last_untagged; i < nr_objects; i++) { + for (i = last_untagged; i < to_pack.nr_objects; i++) { if (objects[i].type != OBJ_TREE) continue; add_to_write_order(wo, &wo_end, &objects[i]); @@ -702,17 +694,57 @@ static struct object_entry **compute_write_order(void) /* * Finally all the rest in really tight order */ - for (i = last_untagged; i < nr_objects; i++) { + for (i = last_untagged; i < to_pack.nr_objects; i++) { if (!objects[i].filled) add_family_to_write_order(wo, &wo_end, &objects[i]); } - if (wo_end != nr_objects) - die("ordered %u objects, expected %"PRIu32, wo_end, nr_objects); + if (wo_end != to_pack.nr_objects) + die("ordered %u objects, expected %"PRIu32, wo_end, to_pack.nr_objects); return wo; } +static off_t write_reused_pack(struct sha1file *f) +{ + unsigned char buffer[8192]; + off_t to_write; + int fd; + + if (!is_pack_valid(reuse_packfile)) + die("packfile is invalid: %s", reuse_packfile->pack_name); + + fd = git_open_noatime(reuse_packfile->pack_name); + if (fd < 0) + die_errno("unable to open packfile for reuse: %s", + reuse_packfile->pack_name); + + if (lseek(fd, sizeof(struct pack_header), SEEK_SET) == -1) + die_errno("unable to seek in reused packfile"); + + if (reuse_packfile_offset < 0) + reuse_packfile_offset = reuse_packfile->pack_size - 20; + + to_write = reuse_packfile_offset - sizeof(struct pack_header); + + while (to_write) { + int read_pack = xread(fd, buffer, sizeof(buffer)); + + if (read_pack <= 0) + die_errno("unable to read from reused packfile"); + + if (read_pack > to_write) + read_pack = to_write; + + sha1write(f, buffer, read_pack); + to_write -= read_pack; + } + + close(fd); + written += reuse_packfile_objects; + return reuse_packfile_offset - sizeof(struct pack_header); +} + static void write_pack_file(void) { uint32_t i = 0, j; @@ -724,7 +756,7 @@ static void write_pack_file(void) if (progress > pack_to_stdout) progress_state = start_progress("Writing objects", nr_result); - written_list = xmalloc(nr_objects * sizeof(*written_list)); + written_list = xmalloc(to_pack.nr_objects * sizeof(*written_list)); write_order = compute_write_order(); do { @@ -737,8 +769,17 @@ static void write_pack_file(void) f = create_tmp_packfile(&pack_tmp_name); offset = write_pack_header(f, nr_remaining); + + if (reuse_packfile) { + off_t packfile_size; + assert(pack_to_stdout); + + packfile_size = write_reused_pack(f); + offset += packfile_size; + } + nr_written = 0; - for (; i < nr_objects; i++) { + for (; i < to_pack.nr_objects; i++) { struct object_entry *e = write_order[i]; if (write_one(f, e, &offset) == WRITE_ONE_BREAK) break; @@ -789,9 +830,31 @@ static void write_pack_file(void) if (sizeof(tmpname) <= strlen(base_name) + 50) die("pack base name '%s' too long", base_name); snprintf(tmpname, sizeof(tmpname), "%s-", base_name); + + if (write_bitmap_index) { + bitmap_writer_set_checksum(sha1); + bitmap_writer_build_type_index(written_list, nr_written); + } + finish_tmp_packfile(tmpname, pack_tmp_name, written_list, nr_written, &pack_idx_opts, sha1); + + if (write_bitmap_index) { + char *end_of_name_prefix = strrchr(tmpname, 0); + sprintf(end_of_name_prefix, "%s.bitmap", sha1_to_hex(sha1)); + + stop_progress(&progress_state); + + bitmap_writer_show_progress(progress); + bitmap_writer_reuse_bitmaps(&to_pack); + bitmap_writer_select_commits(indexed_commits, indexed_commits_nr, -1); + bitmap_writer_build(&to_pack); + bitmap_writer_finish(written_list, nr_written, + tmpname, write_bitmap_options); + write_bitmap_index = 0; + } + free(pack_tmp_name); puts(sha1_to_hex(sha1)); } @@ -801,7 +864,7 @@ static void write_pack_file(void) written_list[j]->offset = (off_t)-1; } nr_remaining -= nr_written; - } while (nr_remaining && i < nr_objects); + } while (nr_remaining && i < to_pack.nr_objects); free(written_list); free(write_order); @@ -811,73 +874,6 @@ static void write_pack_file(void) written, nr_result); } -static int locate_object_entry_hash(const unsigned char *sha1) -{ - int i; - unsigned int ui; - memcpy(&ui, sha1, sizeof(unsigned int)); - i = ui % object_ix_hashsz; - while (0 < object_ix[i]) { - if (!hashcmp(sha1, objects[object_ix[i] - 1].idx.sha1)) - return i; - if (++i == object_ix_hashsz) - i = 0; - } - return -1 - i; -} - -static struct object_entry *locate_object_entry(const unsigned char *sha1) -{ - int i; - - if (!object_ix_hashsz) - return NULL; - - i = locate_object_entry_hash(sha1); - if (0 <= i) - return &objects[object_ix[i]-1]; - return NULL; -} - -static void rehash_objects(void) -{ - uint32_t i; - struct object_entry *oe; - - object_ix_hashsz = nr_objects * 3; - if (object_ix_hashsz < 1024) - object_ix_hashsz = 1024; - object_ix = xrealloc(object_ix, sizeof(int) * object_ix_hashsz); - memset(object_ix, 0, sizeof(int) * object_ix_hashsz); - for (i = 0, oe = objects; i < nr_objects; i++, oe++) { - int ix = locate_object_entry_hash(oe->idx.sha1); - if (0 <= ix) - continue; - ix = -1 - ix; - object_ix[ix] = i + 1; - } -} - -static uint32_t name_hash(const char *name) -{ - uint32_t c, hash = 0; - - if (!name) - return 0; - - /* - * This effectively just creates a sortable number from the - * last sixteen non-whitespace characters. Last characters - * count "most", so things that end in ".c" sort together. - */ - while ((c = *name++) != 0) { - if (isspace(c)) - continue; - hash = (hash >> 2) + (c << 24); - } - return hash; -} - static void setup_delta_attr_check(struct git_attr_check *check) { static struct git_attr *attr_delta; @@ -900,42 +896,69 @@ static int no_try_delta(const char *path) return 0; } -static int add_object_entry(const unsigned char *sha1, enum object_type type, - const char *name, int exclude) +/* + * When adding an object, check whether we have already added it + * to our packing list. If so, we can skip. However, if we are + * being asked to excludei t, but the previous mention was to include + * it, make sure to adjust its flags and tweak our numbers accordingly. + * + * As an optimization, we pass out the index position where we would have + * found the item, since that saves us from having to look it up again a + * few lines later when we want to add the new entry. + */ +static int have_duplicate_entry(const unsigned char *sha1, + int exclude, + uint32_t *index_pos) { struct object_entry *entry; - struct packed_git *p, *found_pack = NULL; - off_t found_offset = 0; - int ix; - uint32_t hash = name_hash(name); - - ix = nr_objects ? locate_object_entry_hash(sha1) : -1; - if (ix >= 0) { - if (exclude) { - entry = objects + object_ix[ix] - 1; - if (!entry->preferred_base) - nr_result--; - entry->preferred_base = 1; - } + + entry = packlist_find(&to_pack, sha1, index_pos); + if (!entry) return 0; + + if (exclude) { + if (!entry->preferred_base) + nr_result--; + entry->preferred_base = 1; } + return 1; +} + +/* + * Check whether we want the object in the pack (e.g., we do not want + * objects found in non-local stores if the "--local" option was used). + * + * As a side effect of this check, we will find the packed version of this + * object, if any. We therefore pass out the pack information to avoid having + * to look it up again later. + */ +static int want_object_in_pack(const unsigned char *sha1, + int exclude, + struct packed_git **found_pack, + off_t *found_offset) +{ + struct packed_git *p; + if (!exclude && local && has_loose_object_nonlocal(sha1)) return 0; + *found_pack = NULL; + *found_offset = 0; + for (p = packed_git; p; p = p->next) { off_t offset = find_pack_entry_one(sha1, p); if (offset) { - if (!found_pack) { + if (!*found_pack) { if (!is_pack_valid(p)) { warning("packfile %s cannot be accessed", p->pack_name); continue; } - found_offset = offset; - found_pack = p; + *found_offset = offset; + *found_pack = p; } if (exclude) - break; + return 1; if (incremental) return 0; if (local && !p->pack_local) @@ -945,14 +968,21 @@ static int add_object_entry(const unsigned char *sha1, enum object_type type, } } - if (nr_objects >= nr_alloc) { - nr_alloc = (nr_alloc + 1024) * 3 / 2; - objects = xrealloc(objects, nr_alloc * sizeof(*entry)); - } + return 1; +} + +static void create_object_entry(const unsigned char *sha1, + enum object_type type, + uint32_t hash, + int exclude, + int no_try_delta, + uint32_t index_pos, + struct packed_git *found_pack, + off_t found_offset) +{ + struct object_entry *entry; - entry = objects + nr_objects++; - memset(entry, 0, sizeof(*entry)); - hashcpy(entry->idx.sha1, sha1); + entry = packlist_alloc(&to_pack, sha1, index_pos); entry->hash = hash; if (type) entry->type = type; @@ -965,16 +995,43 @@ static int add_object_entry(const unsigned char *sha1, enum object_type type, entry->in_pack_offset = found_offset; } - if (object_ix_hashsz * 3 <= nr_objects * 4) - rehash_objects(); - else - object_ix[-1 - ix] = nr_objects; + entry->no_try_delta = no_try_delta; +} + +static int add_object_entry(const unsigned char *sha1, enum object_type type, + const char *name, int exclude) +{ + struct packed_git *found_pack; + off_t found_offset; + uint32_t index_pos; - display_progress(progress_state, nr_objects); + if (have_duplicate_entry(sha1, exclude, &index_pos)) + return 0; + + if (!want_object_in_pack(sha1, exclude, &found_pack, &found_offset)) + return 0; - if (name && no_try_delta(name)) - entry->no_try_delta = 1; + create_object_entry(sha1, type, pack_name_hash(name), + exclude, name && no_try_delta(name), + index_pos, found_pack, found_offset); + display_progress(progress_state, to_pack.nr_objects); + return 1; +} + +static int add_object_entry_from_bitmap(const unsigned char *sha1, + enum object_type type, + int flags, uint32_t name_hash, + struct packed_git *pack, off_t offset) +{ + uint32_t index_pos; + + if (have_duplicate_entry(sha1, 0, &index_pos)) + return 0; + + create_object_entry(sha1, type, name_hash, 0, 0, index_pos, pack, offset); + + display_progress(progress_state, to_pack.nr_objects); return 1; } @@ -1175,7 +1232,7 @@ static void add_preferred_base_object(const char *name) { struct pbase_tree *it; int cmplen; - unsigned hash = name_hash(name); + unsigned hash = pack_name_hash(name); if (!num_preferred_base || check_pbase_path(hash)) return; @@ -1327,7 +1384,7 @@ static void check_object(struct object_entry *entry) break; } - if (base_ref && (base_entry = locate_object_entry(base_ref))) { + if (base_ref && (base_entry = packlist_find(&to_pack, base_ref, NULL))) { /* * If base_ref was set above that means we wish to * reuse delta data, and we even found that base @@ -1401,12 +1458,12 @@ static void get_object_details(void) uint32_t i; struct object_entry **sorted_by_offset; - sorted_by_offset = xcalloc(nr_objects, sizeof(struct object_entry *)); - for (i = 0; i < nr_objects; i++) - sorted_by_offset[i] = objects + i; - qsort(sorted_by_offset, nr_objects, sizeof(*sorted_by_offset), pack_offset_sort); + sorted_by_offset = xcalloc(to_pack.nr_objects, sizeof(struct object_entry *)); + for (i = 0; i < to_pack.nr_objects; i++) + sorted_by_offset[i] = to_pack.objects + i; + qsort(sorted_by_offset, to_pack.nr_objects, sizeof(*sorted_by_offset), pack_offset_sort); - for (i = 0; i < nr_objects; i++) { + for (i = 0; i < to_pack.nr_objects; i++) { struct object_entry *entry = sorted_by_offset[i]; check_object(entry); if (big_file_threshold < entry->size) @@ -2032,7 +2089,7 @@ static int add_ref_tag(const char *path, const unsigned char *sha1, int flag, vo if (starts_with(path, "refs/tags/") && /* is a tag? */ !peel_ref(path, peeled) && /* peelable? */ - locate_object_entry(peeled)) /* object packed? */ + packlist_find(&to_pack, peeled, NULL)) /* object packed? */ add_object_entry(sha1, OBJ_TAG, NULL, 0); return 0; } @@ -2055,14 +2112,14 @@ static void prepare_pack(int window, int depth) if (!pack_to_stdout) do_check_packed_object_crc = 1; - if (!nr_objects || !window || !depth) + if (!to_pack.nr_objects || !window || !depth) return; - delta_list = xmalloc(nr_objects * sizeof(*delta_list)); + delta_list = xmalloc(to_pack.nr_objects * sizeof(*delta_list)); nr_deltas = n = 0; - for (i = 0; i < nr_objects; i++) { - struct object_entry *entry = objects + i; + for (i = 0; i < to_pack.nr_objects; i++) { + struct object_entry *entry = to_pack.objects + i; if (entry->delta) /* This happens if we decided to reuse existing @@ -2140,6 +2197,20 @@ static int git_pack_config(const char *k, const char *v, void *cb) cache_max_small_delta_size = git_config_int(k, v); return 0; } + if (!strcmp(k, "pack.writebitmaps")) { + write_bitmap_index = git_config_bool(k, v); + return 0; + } + if (!strcmp(k, "pack.writebitmaphashcache")) { + if (git_config_bool(k, v)) + write_bitmap_options |= BITMAP_OPT_HASH_CACHE; + else + write_bitmap_options &= ~BITMAP_OPT_HASH_CACHE; + } + if (!strcmp(k, "pack.usebitmaps")) { + use_bitmap_index = git_config_bool(k, v); + return 0; + } if (!strcmp(k, "pack.threads")) { delta_search_threads = git_config_int(k, v); if (delta_search_threads < 0) @@ -2198,6 +2269,9 @@ static void show_commit(struct commit *commit, void *data) { add_object_entry(commit->object.sha1, OBJ_COMMIT, NULL, 0); commit->object.flags |= OBJECT_ADDED; + + if (write_bitmap_index) + index_commit_for_bitmap(commit); } static void show_object(struct object *obj, @@ -2340,7 +2414,7 @@ static void loosen_unused_packed_objects(struct rev_info *revs) for (i = 0; i < p->num_objects; i++) { sha1 = nth_packed_object_sha1(p, i); - if (!locate_object_entry(sha1) && + if (!packlist_find(&to_pack, sha1, NULL) && !has_sha1_pack_kept_or_nonlocal(sha1)) if (force_object_loose(sha1, p->mtime)) die("unable to force loose object"); @@ -2348,6 +2422,29 @@ static void loosen_unused_packed_objects(struct rev_info *revs) } } +static int get_object_list_from_bitmap(struct rev_info *revs) +{ + if (prepare_bitmap_walk(revs) < 0) + return -1; + + if (!reuse_partial_packfile_from_bitmap( + &reuse_packfile, + &reuse_packfile_objects, + &reuse_packfile_offset)) { + assert(reuse_packfile_objects); + nr_result += reuse_packfile_objects; + + if (progress) { + fprintf(stderr, "Reusing existing pack: %d, done.\n", + reuse_packfile_objects); + fflush(stderr); + } + } + + traverse_bitmap_commit_list(&add_object_entry_from_bitmap); + return 0; +} + static void get_object_list(int ac, const char **av) { struct rev_info revs; @@ -2367,6 +2464,7 @@ static void get_object_list(int ac, const char **av) if (*line == '-') { if (!strcmp(line, "--not")) { flags ^= UNINTERESTING; + write_bitmap_index = 0; continue; } die("not a rev '%s'", line); @@ -2375,6 +2473,9 @@ static void get_object_list(int ac, const char **av) die("bad revision '%s'", line); } + if (use_bitmap_index && !get_object_list_from_bitmap(&revs)) + return; + if (prepare_revision_walk(&revs)) die("revision walk setup failed"); mark_edges_uninteresting(&revs, show_edge); @@ -2504,6 +2605,10 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) N_("pack compression level")), OPT_SET_INT(0, "keep-true-parents", &grafts_replace_parents, N_("do not hide commits by grafts"), 0), + OPT_BOOL(0, "use-bitmap-index", &use_bitmap_index, + N_("use a bitmap index if available to speed up counting objects")), + OPT_BOOL(0, "write-bitmap-index", &write_bitmap_index, + N_("write a bitmap index together with the pack index")), OPT_END(), }; @@ -2570,6 +2675,12 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) if (keep_unreachable && unpack_unreachable) die("--keep-unreachable and --unpack-unreachable are incompatible."); + if (!use_internal_rev_list || !pack_to_stdout || is_repository_shallow()) + use_bitmap_index = 0; + + if (pack_to_stdout || !rev_list_all) + write_bitmap_index = 0; + if (progress && all_progress_implied) progress = 2; diff --git a/builtin/push.c b/builtin/push.c index 0e50ddbb01..f8dfea41e1 100644 --- a/builtin/push.c +++ b/builtin/push.c @@ -26,7 +26,6 @@ static struct push_cas_option cas; static const char **refspec; static int refspec_nr; static int refspec_alloc; -static int default_matching_used; static void add_refspec(const char *ref) { @@ -59,7 +58,7 @@ static const char *map_refspec(const char *ref, } if (push_default == PUSH_DEFAULT_UPSTREAM && - !prefixcmp(matched->name, "refs/heads/")) { + starts_with(matched->name, "refs/heads/")) { struct branch *branch = branch_get(matched->name + 11); if (branch->merge_nr == 1 && branch->merge[0]->src) { struct strbuf buf = STRBUF_INIT; @@ -204,9 +203,9 @@ static void setup_push_current(struct remote *remote, struct branch *branch) } static char warn_unspecified_push_default_msg[] = -N_("push.default is unset; its implicit value is changing in\n" +N_("push.default is unset; its implicit value has changed in\n" "Git 2.0 from 'matching' to 'simple'. To squelch this message\n" - "and maintain the current behavior after the default changes, use:\n" + "and maintain the traditional behavior, use:\n" "\n" " git config --global push.default matching\n" "\n" @@ -217,7 +216,7 @@ N_("push.default is unset; its implicit value is changing in\n" "When push.default is set to 'matching', git will push local branches\n" "to the remote branches that already exist with the same name.\n" "\n" - "In Git 2.0, Git will default to the more conservative 'simple'\n" + "Since Git 2.0, Git defaults to the more conservative 'simple'\n" "behavior, which only pushes the current branch to the corresponding\n" "remote branch that 'git pull' uses to update the current branch.\n" "\n" @@ -247,14 +246,14 @@ static void setup_default_push_refspecs(struct remote *remote) switch (push_default) { default: - case PUSH_DEFAULT_UNSPECIFIED: - default_matching_used = 1; - warn_unspecified_push_default_configuration(); - /* fallthru */ case PUSH_DEFAULT_MATCHING: add_refspec(":"); break; + case PUSH_DEFAULT_UNSPECIFIED: + warn_unspecified_push_default_configuration(); + /* fallthru */ + case PUSH_DEFAULT_SIMPLE: if (triangular) setup_push_current(remote, branch); @@ -283,12 +282,6 @@ static const char message_advice_pull_before_push[] = "'git pull ...') before pushing again.\n" "See the 'Note about fast-forwards' in 'git push --help' for details."); -static const char message_advice_use_upstream[] = - N_("Updates were rejected because a pushed branch tip is behind its remote\n" - "counterpart. If you did not intend to push that branch, you may want to\n" - "specify branches to push or set the 'push.default' configuration variable\n" - "to 'simple', 'current' or 'upstream' to push only the current branch."); - static const char message_advice_checkout_pull_push[] = N_("Updates were rejected because a pushed branch tip is behind its remote\n" "counterpart. Check out this branch and integrate the remote changes\n" @@ -317,13 +310,6 @@ static void advise_pull_before_push(void) advise(_(message_advice_pull_before_push)); } -static void advise_use_upstream(void) -{ - if (!advice_push_non_ff_default || !advice_push_update_rejected) - return; - advise(_(message_advice_use_upstream)); -} - static void advise_checkout_pull_push(void) { if (!advice_push_non_ff_matching || !advice_push_update_rejected) @@ -385,10 +371,7 @@ static int push_with_options(struct transport *transport, int flags) if (reject_reasons & REJECT_NON_FF_HEAD) { advise_pull_before_push(); } else if (reject_reasons & REJECT_NON_FF_OTHER) { - if (default_matching_used) - advise_use_upstream(); - else - advise_checkout_pull_push(); + advise_checkout_pull_push(); } else if (reject_reasons & REJECT_ALREADY_EXISTS) { advise_ref_already_exists(); } else if (reject_reasons & REJECT_FETCH_FIRST) { diff --git a/builtin/repack.c b/builtin/repack.c index bb2314c9cb..49f5857627 100644 --- a/builtin/repack.c +++ b/builtin/repack.c @@ -94,7 +94,7 @@ static void get_non_kept_pack_filenames(struct string_list *fname_list) static void remove_redundant_pack(const char *dir_name, const char *base_name) { - const char *exts[] = {".pack", ".idx", ".keep"}; + const char *exts[] = {".pack", ".idx", ".keep", ".bitmap"}; int i; struct strbuf buf = STRBUF_INIT; size_t plen; @@ -115,7 +115,14 @@ static void remove_redundant_pack(const char *dir_name, const char *base_name) int cmd_repack(int argc, const char **argv, const char *prefix) { - const char *exts[2] = {".pack", ".idx"}; + struct { + const char *name; + unsigned optional:1; + } exts[] = { + {".pack"}, + {".idx"}, + {".bitmap", 1}, + }; struct child_process cmd; struct string_list_item *item; struct argv_array cmd_args = ARGV_ARRAY_INIT; @@ -137,6 +144,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix) int no_update_server_info = 0; int quiet = 0; int local = 0; + int write_bitmap = -1; struct option builtin_repack_options[] = { OPT_BIT('a', NULL, &pack_everything, @@ -155,6 +163,8 @@ int cmd_repack(int argc, const char **argv, const char *prefix) OPT__QUIET(&quiet, N_("be quiet")), OPT_BOOL('l', "local", &local, N_("pass --local to git-pack-objects")), + OPT_BOOL('b', "write-bitmap-index", &write_bitmap, + N_("write bitmap index")), OPT_STRING(0, "unpack-unreachable", &unpack_unreachable, N_("approxidate"), N_("with -A, do not loosen objects older than this")), OPT_STRING(0, "window", &window, N_("n"), @@ -196,6 +206,9 @@ int cmd_repack(int argc, const char **argv, const char *prefix) argv_array_pushf(&cmd_args, "--no-reuse-delta"); if (no_reuse_object) argv_array_pushf(&cmd_args, "--no-reuse-object"); + if (write_bitmap >= 0) + argv_array_pushf(&cmd_args, "--%swrite-bitmap-index", + write_bitmap ? "" : "no-"); if (pack_everything & ALL_INTO_ONE) { get_non_kept_pack_filenames(&existing_packs); @@ -256,17 +269,17 @@ int cmd_repack(int argc, const char **argv, const char *prefix) */ failed = 0; for_each_string_list_item(item, &names) { - for (ext = 0; ext < 2; ext++) { + for (ext = 0; ext < ARRAY_SIZE(exts); ext++) { char *fname, *fname_old; fname = mkpathdup("%s/pack-%s%s", packdir, - item->string, exts[ext]); + item->string, exts[ext].name); if (!file_exists(fname)) { free(fname); continue; } fname_old = mkpath("%s/old-%s%s", packdir, - item->string, exts[ext]); + item->string, exts[ext].name); if (file_exists(fname_old)) if (unlink(fname_old)) failed = 1; @@ -313,19 +326,23 @@ int cmd_repack(int argc, const char **argv, const char *prefix) /* Now the ones with the same name are out of the way... */ for_each_string_list_item(item, &names) { - for (ext = 0; ext < 2; ext++) { + for (ext = 0; ext < ARRAY_SIZE(exts); ext++) { char *fname, *fname_old; struct stat statbuffer; + int exists = 0; fname = mkpathdup("%s/pack-%s%s", - packdir, item->string, exts[ext]); + packdir, item->string, exts[ext].name); fname_old = mkpathdup("%s-%s%s", - packtmp, item->string, exts[ext]); + packtmp, item->string, exts[ext].name); if (!stat(fname_old, &statbuffer)) { statbuffer.st_mode &= ~(S_IWUSR | S_IWGRP | S_IWOTH); chmod(fname_old, statbuffer.st_mode); + exists = 1; + } + if (exists || !exts[ext].optional) { + if (rename(fname_old, fname)) + die_errno(_("renaming '%s' failed"), fname_old); } - if (rename(fname_old, fname)) - die_errno(_("renaming '%s' failed"), fname_old); free(fname); free(fname_old); } @@ -333,12 +350,12 @@ int cmd_repack(int argc, const char **argv, const char *prefix) /* Remove the "old-" files */ for_each_string_list_item(item, &names) { - for (ext = 0; ext < 2; ext++) { + for (ext = 0; ext < ARRAY_SIZE(exts); ext++) { char *fname; fname = mkpath("%s/old-%s%s", packdir, item->string, - exts[ext]); + exts[ext].name); if (remove_path(fname)) warning(_("removing '%s' failed"), fname); } diff --git a/builtin/reset.c b/builtin/reset.c index 60048030dd..f4e087596b 100644 --- a/builtin/reset.c +++ b/builtin/reset.c @@ -116,25 +116,34 @@ static void update_index_from_diff(struct diff_queue_struct *q, struct diff_options *opt, void *data) { int i; + int intent_to_add = *(int *)data; for (i = 0; i < q->nr; i++) { struct diff_filespec *one = q->queue[i]->one; - if (one->mode && !is_null_sha1(one->sha1)) { - struct cache_entry *ce; - ce = make_cache_entry(one->mode, one->sha1, one->path, - 0, 0); - if (!ce) - die(_("make_cache_entry failed for path '%s'"), - one->path); - add_cache_entry(ce, ADD_CACHE_OK_TO_ADD | - ADD_CACHE_OK_TO_REPLACE); - } else + int is_missing = !(one->mode && !is_null_sha1(one->sha1)); + struct cache_entry *ce; + + if (is_missing && !intent_to_add) { remove_file_from_cache(one->path); + continue; + } + + ce = make_cache_entry(one->mode, one->sha1, one->path, + 0, 0); + if (!ce) + die(_("make_cache_entry failed for path '%s'"), + one->path); + if (is_missing) { + ce->ce_flags |= CE_INTENT_TO_ADD; + set_object_name_for_intent_to_add_entry(ce); + } + add_cache_entry(ce, ADD_CACHE_OK_TO_ADD | ADD_CACHE_OK_TO_REPLACE); } } static int read_from_tree(const struct pathspec *pathspec, - unsigned char *tree_sha1) + unsigned char *tree_sha1, + int intent_to_add) { struct diff_options opt; @@ -142,6 +151,7 @@ static int read_from_tree(const struct pathspec *pathspec, copy_pathspec(&opt.pathspec, pathspec); opt.output_format = DIFF_FORMAT_CALLBACK; opt.format_callback = update_index_from_diff; + opt.format_callback_data = &intent_to_add; if (do_diff_cache(tree_sha1, &opt)) return 1; @@ -258,6 +268,7 @@ int cmd_reset(int argc, const char **argv, const char *prefix) const char *rev; unsigned char sha1[20]; struct pathspec pathspec; + int intent_to_add = 0; const struct option options[] = { OPT__QUIET(&quiet, N_("be quiet, only report errors")), OPT_SET_INT(0, "mixed", &reset_type, @@ -270,6 +281,8 @@ int cmd_reset(int argc, const char **argv, const char *prefix) OPT_SET_INT(0, "keep", &reset_type, N_("reset HEAD but keep local changes"), KEEP), OPT_BOOL('p', "patch", &patch_mode, N_("select hunks interactively")), + OPT_BOOL('N', "intent-to-add", &intent_to_add, + N_("record only the fact that removed paths will be added later")), OPT_END() }; @@ -320,13 +333,16 @@ int cmd_reset(int argc, const char **argv, const char *prefix) if (reset_type == NONE) reset_type = MIXED; /* by default */ - if (reset_type != SOFT && reset_type != MIXED) + if (reset_type != SOFT && (reset_type != MIXED || get_git_work_tree())) setup_work_tree(); if (reset_type == MIXED && is_bare_repository()) die(_("%s reset is not allowed in a bare repository"), _(reset_type_names[reset_type])); + if (intent_to_add && reset_type != MIXED) + die(_("-N can only be used with --mixed")); + /* Soft reset does not touch the index file nor the working tree * at all, but requires them in a good order. Other resets reset * the index file to the tree object we are switching to. */ @@ -338,10 +354,11 @@ int cmd_reset(int argc, const char **argv, const char *prefix) int newfd = hold_locked_index(lock, 1); if (reset_type == MIXED) { int flags = quiet ? REFRESH_QUIET : REFRESH_IN_PORCELAIN; - if (read_from_tree(&pathspec, sha1)) + if (read_from_tree(&pathspec, sha1, intent_to_add)) return 1; - refresh_index(&the_index, flags, NULL, NULL, - _("Unstaged changes after reset:")); + if (get_git_work_tree()) + refresh_index(&the_index, flags, NULL, NULL, + _("Unstaged changes after reset:")); } else { int err = reset_index(sha1, reset_type, quiet); if (reset_type == KEEP && !err) diff --git a/builtin/rev-list.c b/builtin/rev-list.c index 0745e2d053..9f92905379 100644 --- a/builtin/rev-list.c +++ b/builtin/rev-list.c @@ -3,6 +3,8 @@ #include "diff.h" #include "revision.h" #include "list-objects.h" +#include "pack.h" +#include "pack-bitmap.h" #include "builtin.h" #include "log-tree.h" #include "graph.h" @@ -257,6 +259,18 @@ static int show_bisect_vars(struct rev_list_info *info, int reaches, int all) return 0; } +static int show_object_fast( + const unsigned char *sha1, + enum object_type type, + int exclude, + uint32_t name_hash, + struct packed_git *found_pack, + off_t found_offset) +{ + fprintf(stdout, "%s\n", sha1_to_hex(sha1)); + return 1; +} + int cmd_rev_list(int argc, const char **argv, const char *prefix) { struct rev_info revs; @@ -265,6 +279,7 @@ int cmd_rev_list(int argc, const char **argv, const char *prefix) int bisect_list = 0; int bisect_show_vars = 0; int bisect_find_all = 0; + int use_bitmap_index = 0; git_config(git_default_config, NULL); init_revisions(&revs, prefix); @@ -306,6 +321,14 @@ int cmd_rev_list(int argc, const char **argv, const char *prefix) bisect_show_vars = 1; continue; } + if (!strcmp(arg, "--use-bitmap-index")) { + use_bitmap_index = 1; + continue; + } + if (!strcmp(arg, "--test-bitmap")) { + test_bitmap_walk(&revs); + return 0; + } usage(rev_list_usage); } @@ -333,6 +356,22 @@ int cmd_rev_list(int argc, const char **argv, const char *prefix) if (bisect_list) revs.limited = 1; + if (use_bitmap_index) { + if (revs.count && !revs.left_right && !revs.cherry_mark) { + uint32_t commit_count; + if (!prepare_bitmap_walk(&revs)) { + count_bitmap_commit_list(&commit_count, NULL, NULL, NULL); + printf("%d\n", commit_count); + return 0; + } + } else if (revs.tag_objects && revs.tree_objects && revs.blob_objects) { + if (!prepare_bitmap_walk(&revs)) { + traverse_bitmap_commit_list(&show_object_fast); + return 0; + } + } + } + if (prepare_revision_walk(&revs)) die("revision walk setup failed"); if (revs.tree_objects) diff --git a/builtin/rev-parse.c b/builtin/rev-parse.c index aaeb611a97..45901df371 100644 --- a/builtin/rev-parse.c +++ b/builtin/rev-parse.c @@ -547,15 +547,17 @@ int cmd_rev_parse(int argc, const char **argv, const char *prefix) continue; } if (!strcmp(arg, "--default")) { - def = argv[i+1]; - i++; + def = argv[++i]; + if (!def) + die("--default requires an argument"); continue; } if (!strcmp(arg, "--prefix")) { - prefix = argv[i+1]; + prefix = argv[++i]; + if (!prefix) + die("--prefix requires an argument"); startup_info->prefix = prefix; output_prefix = 1; - i++; continue; } if (!strcmp(arg, "--revs-only")) { @@ -738,9 +740,12 @@ int cmd_rev_parse(int argc, const char **argv, const char *prefix) continue; } if (!strcmp(arg, "--resolve-git-dir")) { - const char *gitdir = resolve_gitdir(argv[i+1]); + const char *gitdir = argv[++i]; if (!gitdir) - die("not a gitdir '%s'", argv[i+1]); + die("--resolve-git-dir requires an argument"); + gitdir = resolve_gitdir(gitdir); + if (!gitdir) + die("not a gitdir '%s'", argv[i]); puts(gitdir); continue; } diff --git a/builtin/revert.c b/builtin/revert.c index 87659c9fdb..065d88dd05 100644 --- a/builtin/revert.c +++ b/builtin/revert.c @@ -89,6 +89,8 @@ static void parse_args(int argc, const char **argv, struct replay_opts *opts) OPT_STRING(0, "strategy", &opts->strategy, N_("strategy"), N_("merge strategy")), OPT_CALLBACK('X', "strategy-option", &opts, N_("option"), N_("option for merge strategy"), option_parse_x), + { OPTION_STRING, 'S', "gpg-sign", &opts->gpg_sign, N_("key id"), + N_("GPG sign commit"), PARSE_OPT_OPTARG, NULL, (intptr_t) "" }, OPT_END(), OPT_END(), OPT_END(), diff --git a/builtin/rm.c b/builtin/rm.c index 3a0e0eaab7..960634dd0c 100644 --- a/builtin/rm.c +++ b/builtin/rm.c @@ -308,10 +308,10 @@ int cmd_rm(int argc, const char **argv, const char *prefix) for (i = 0; i < active_nr; i++) { const struct cache_entry *ce = active_cache[i]; - if (!match_pathspec_depth(&pathspec, ce->name, ce_namelen(ce), 0, seen)) + if (!ce_path_match(ce, &pathspec, seen)) continue; ALLOC_GROW(list.entry, list.nr + 1, list.alloc); - list.entry[list.nr].name = ce->name; + list.entry[list.nr].name = xstrdup(ce->name); list.entry[list.nr].is_submodule = S_ISGITLINK(ce->ce_mode); if (list.entry[list.nr++].is_submodule && !is_staging_gitmodules_ok()) diff --git a/builtin/update-index.c b/builtin/update-index.c index e3a10d706d..d12ad95f3e 100644 --- a/builtin/update-index.c +++ b/builtin/update-index.c @@ -12,6 +12,7 @@ #include "resolve-undo.h" #include "parse-options.h" #include "pathspec.h" +#include "dir.h" /* * Default to not allowing changes to the list of files. The @@ -274,36 +275,32 @@ static void chmod_path(int flip, const char *path) die("git update-index: cannot chmod %cx '%s'", flip, path); } -static void update_one(const char *path, const char *prefix, int prefix_length) +static void update_one(const char *path) { - const char *p = prefix_path(prefix, prefix_length, path); - if (!verify_path(p)) { + if (!verify_path(path)) { fprintf(stderr, "Ignoring path %s\n", path); - goto free_return; + return; } if (mark_valid_only) { - if (mark_ce_flags(p, CE_VALID, mark_valid_only == MARK_FLAG)) + if (mark_ce_flags(path, CE_VALID, mark_valid_only == MARK_FLAG)) die("Unable to mark file %s", path); - goto free_return; + return; } if (mark_skip_worktree_only) { - if (mark_ce_flags(p, CE_SKIP_WORKTREE, mark_skip_worktree_only == MARK_FLAG)) + if (mark_ce_flags(path, CE_SKIP_WORKTREE, mark_skip_worktree_only == MARK_FLAG)) die("Unable to mark file %s", path); - goto free_return; + return; } if (force_remove) { - if (remove_file_from_cache(p)) + if (remove_file_from_cache(path)) die("git update-index: unable to remove %s", path); report("remove '%s'", path); - goto free_return; + return; } - if (process_path(p)) + if (process_path(path)) die("Unable to process path %s", path); report("add '%s'", path); - free_return: - if (p < path || p > path + strlen(path)) - free((char *)p); } static void read_index_info(int line_termination) @@ -563,8 +560,9 @@ static int do_reupdate(int ac, const char **av, const struct cache_entry *ce = active_cache[pos]; struct cache_entry *old = NULL; int save_nr; + char *path; - if (ce_stage(ce) || !ce_path_match(ce, &pathspec)) + if (ce_stage(ce) || !ce_path_match(ce, &pathspec, NULL)) continue; if (has_head) old = read_one_ent(NULL, head_sha1, @@ -579,7 +577,9 @@ static int do_reupdate(int ac, const char **av, * or worse yet 'allow_replace', active_nr may decrease. */ save_nr = active_nr; - update_one(ce->name + prefix_length, prefix, prefix_length); + path = xstrdup(ce->name); + update_one(path); + free(path); if (save_nr != active_nr) goto redo; } @@ -836,11 +836,10 @@ int cmd_update_index(int argc, const char **argv, const char *prefix) setup_work_tree(); p = prefix_path(prefix, prefix_length, path); - update_one(p, NULL, 0); + update_one(p); if (set_executable_bit) chmod_path(set_executable_bit, p); - if (p < path || p > path + strlen(path)) - free((char *)p); + free((char *)p); ctx.argc--; ctx.argv++; break; @@ -879,11 +878,10 @@ int cmd_update_index(int argc, const char **argv, const char *prefix) strbuf_swap(&buf, &nbuf); } p = prefix_path(prefix, prefix_length, buf.buf); - update_one(p, NULL, 0); + update_one(p); if (set_executable_bit) chmod_path(set_executable_bit, p); - if (p < buf.buf || p > buf.buf + buf.len) - free((char *)p); + free((char *)p); } strbuf_release(&nbuf); strbuf_release(&buf); @@ -3,7 +3,7 @@ #include "git-compat-util.h" #include "strbuf.h" -#include "hash.h" +#include "hashmap.h" #include "advice.h" #include "gettext.h" #include "convert.h" @@ -130,12 +130,12 @@ struct stat_data { }; struct cache_entry { + struct hashmap_entry ent; struct stat_data ce_stat_data; unsigned int ce_mode; unsigned int ce_flags; unsigned int ce_namelen; unsigned char sha1[20]; - struct cache_entry *next; char name[FLEX_ARRAY]; /* more */ }; @@ -159,7 +159,6 @@ struct cache_entry { #define CE_ADDED (1 << 19) #define CE_HASHED (1 << 20) -#define CE_UNHASHED (1 << 21) #define CE_WT_REMOVE (1 << 22) /* remove in work directory */ #define CE_CONFLICTED (1 << 23) @@ -195,17 +194,18 @@ struct pathspec; * Copy the sha1 and stat state of a cache entry from one to * another. But we never change the name, or the hash state! */ -#define CE_STATE_MASK (CE_HASHED | CE_UNHASHED) static inline void copy_cache_entry(struct cache_entry *dst, const struct cache_entry *src) { - unsigned int state = dst->ce_flags & CE_STATE_MASK; + unsigned int state = dst->ce_flags & CE_HASHED; /* Don't copy hash chain and name */ - memcpy(dst, src, offsetof(struct cache_entry, next)); + memcpy(&dst->ce_stat_data, &src->ce_stat_data, + offsetof(struct cache_entry, name) - + offsetof(struct cache_entry, ce_stat_data)); /* Restore the hash state */ - dst->ce_flags = (dst->ce_flags & ~CE_STATE_MASK) | state; + dst->ce_flags = (dst->ce_flags & ~CE_HASHED) | state; } static inline unsigned create_ce_flags(unsigned stage) @@ -277,8 +277,8 @@ struct index_state { struct cache_time timestamp; unsigned name_hash_initialized : 1, initialized : 1; - struct hash_table name_hash; - struct hash_table dir_hash; + struct hashmap name_hash; + struct hashmap dir_hash; }; extern struct index_state the_index; @@ -316,7 +316,6 @@ extern void free_name_hash(struct index_state *istate); #define ce_modified(ce, st, options) ie_modified(&the_index, (ce), (st), (options)) #define cache_dir_exists(name, namelen) index_dir_exists(&the_index, (name), (namelen)) #define cache_file_exists(name, namelen, igncase) index_file_exists(&the_index, (name), (namelen), (igncase)) -#define cache_name_exists(name, namelen, igncase) index_name_exists(&the_index, (name), (namelen), (igncase)) #define cache_name_is_other(name, namelen) index_name_is_other(&the_index, (name), (namelen)) #define resolve_undo_clear() resolve_undo_clear_index(&the_index) #define unmerge_cache_entry_at(at) unmerge_index_entry_at(&the_index, at) @@ -434,6 +433,7 @@ extern int set_git_dir_init(const char *git_dir, const char *real_git_dir, int); extern int init_db(const char *template_dir, unsigned int flags); extern void sanitize_stdfds(void); +extern int daemonize(void); #define alloc_nr(x) (((x)+16)*3/2) @@ -467,7 +467,6 @@ extern int unmerged_index(const struct index_state *); extern int verify_path(const char *path); extern struct cache_entry *index_dir_exists(struct index_state *istate, const char *name, int namelen); extern struct cache_entry *index_file_exists(struct index_state *istate, const char *name, int namelen, int igncase); -extern struct cache_entry *index_name_exists(struct index_state *istate, const char *name, int namelen, int igncase); extern int index_name_pos(const struct index_state *, const char *name, int namelen); #define ADD_CACHE_OK_TO_ADD 1 /* Ok to add */ #define ADD_CACHE_OK_TO_REPLACE 2 /* Ok to replace file/directory */ @@ -484,11 +483,11 @@ extern int remove_file_from_index(struct index_state *, const char *path); #define ADD_CACHE_IGNORE_ERRORS 4 #define ADD_CACHE_IGNORE_REMOVAL 8 #define ADD_CACHE_INTENT 16 -#define ADD_CACHE_IMPLICIT_DOT 32 /* internal to "git add -u/-A" */ extern int add_to_index(struct index_state *, const char *path, struct stat *, int flags); extern int add_file_to_index(struct index_state *, const char *path, int flags); -extern struct cache_entry *make_cache_entry(unsigned int mode, const unsigned char *sha1, const char *path, int stage, int refresh); +extern struct cache_entry *make_cache_entry(unsigned int mode, const unsigned char *sha1, const char *path, int stage, unsigned int refresh_options); extern int ce_same_name(const struct cache_entry *a, const struct cache_entry *b); +extern void set_object_name_for_intent_to_add_entry(struct cache_entry *ce); extern int index_name_is_other(const struct index_state *, const char *, int); extern void *read_blob_data_from_index(struct index_state *, const char *, unsigned long *); @@ -498,11 +497,13 @@ extern void *read_blob_data_from_index(struct index_state *, const char *, unsig #define CE_MATCH_RACY_IS_DIRTY 02 /* do stat comparison even if CE_SKIP_WORKTREE is true */ #define CE_MATCH_IGNORE_SKIP_WORKTREE 04 +/* ignore non-existent files during stat update */ +#define CE_MATCH_IGNORE_MISSING 0x08 +/* enable stat refresh */ +#define CE_MATCH_REFRESH 0x10 extern int ie_match_stat(const struct index_state *, const struct cache_entry *, struct stat *, unsigned int); extern int ie_modified(const struct index_state *, const struct cache_entry *, struct stat *, unsigned int); -extern int ce_path_match(const struct cache_entry *ce, const struct pathspec *pathspec); - #define HASH_WRITE_OBJECT 1 #define HASH_FORMAT_CHECK 2 extern int index_fd(unsigned char *sha1, int fd, struct stat *st, enum object_type type, const char *path, unsigned flags); @@ -808,6 +809,7 @@ extern int hash_sha1_file(const void *buf, unsigned long len, const char *type, extern int write_sha1_file(const void *buf, unsigned long len, const char *type, unsigned char *return_sha1); extern int pretend_sha1_file(void *, unsigned long, enum object_type, unsigned char *); extern int force_object_loose(const unsigned char *sha1, time_t mtime); +extern int git_open_noatime(const char *name); extern void *map_sha1_file(const unsigned char *sha1, unsigned long *size); extern int unpack_sha1_header(git_zstream *stream, unsigned char *map, unsigned long mapsize, void *buffer, unsigned long bufsiz); extern int parse_sha1_header(const char *hdr, unsigned long *sizep); @@ -1146,6 +1148,12 @@ extern int update_server_info(int); #define CONFIG_INVALID_PATTERN 6 #define CONFIG_GENERIC_ERROR 7 +struct git_config_source { + unsigned int use_stdin:1; + const char *file; + const char *blob; +}; + typedef int (*config_fn_t)(const char *, const char *, void *); extern int git_default_config(const char *, const char *, void *); extern int git_config_from_file(config_fn_t fn, const char *, void *); @@ -1155,8 +1163,7 @@ extern void git_config_push_parameter(const char *text); extern int git_config_from_parameters(config_fn_t fn, void *data); extern int git_config(config_fn_t fn, void *); extern int git_config_with_options(config_fn_t fn, void *, - const char *filename, - const char *blob_ref, + struct git_config_source *config_source, int respect_includes); extern int git_config_early(config_fn_t fn, void *, const char *repo_config); extern int git_parse_ulong(const char *, unsigned long *); diff --git a/combine-diff.c b/combine-diff.c index 3b92c44880..24ca7e2334 100644 --- a/combine-diff.c +++ b/combine-diff.c @@ -15,11 +15,10 @@ static struct combine_diff_path *intersect_paths(struct combine_diff_path *curr, int n, int num_parent) { struct diff_queue_struct *q = &diff_queued_diff; - struct combine_diff_path *p; - int i; + struct combine_diff_path *p, **tail = &curr; + int i, cmp; if (!n) { - struct combine_diff_path *list = NULL, **tail = &list; for (i = 0; i < q->nr; i++) { int len; const char *path; @@ -31,7 +30,6 @@ static struct combine_diff_path *intersect_paths(struct combine_diff_path *curr, p->path = (char *) &(p->parent[num_parent]); memcpy(p->path, path, len); p->path[len] = 0; - p->len = len; p->next = NULL; memset(p->parent, 0, sizeof(p->parent[0]) * num_parent); @@ -44,31 +42,37 @@ static struct combine_diff_path *intersect_paths(struct combine_diff_path *curr, *tail = p; tail = &p->next; } - return list; + return curr; } - for (p = curr; p; p = p->next) { - int found = 0; - if (!p->len) + /* + * paths in curr (linked list) and q->queue[] (array) are + * both sorted in the tree order. + */ + i = 0; + while ((p = *tail) != NULL) { + cmp = ((i >= q->nr) + ? -1 : strcmp(p->path, q->queue[i]->two->path)); + + if (cmp < 0) { + /* p->path not in q->queue[]; drop it */ + *tail = p->next; + free(p); continue; - for (i = 0; i < q->nr; i++) { - const char *path; - int len; + } - if (diff_unmodified_pair(q->queue[i])) - continue; - path = q->queue[i]->two->path; - len = strlen(path); - if (len == p->len && !memcmp(path, p->path, len)) { - found = 1; - hashcpy(p->parent[n].sha1, q->queue[i]->one->sha1); - p->parent[n].mode = q->queue[i]->one->mode; - p->parent[n].status = q->queue[i]->status; - break; - } + if (cmp > 0) { + /* q->queue[i] not in p->path; skip it */ + i++; + continue; } - if (!found) - p->len = 0; + + hashcpy(p->parent[n].sha1, q->queue[i]->one->sha1); + p->parent[n].mode = q->queue[i]->one->mode; + p->parent[n].status = q->queue[i]->status; + + tail = &p->next; + i++; } return curr; } @@ -1219,8 +1223,6 @@ void show_combined_diff(struct combine_diff_path *p, { struct diff_options *opt = &rev->diffopt; - if (!p->len) - return; if (opt->output_format & (DIFF_FORMAT_RAW | DIFF_FORMAT_NAME | DIFF_FORMAT_NAME_STATUS)) @@ -1284,17 +1286,21 @@ static void handle_combined_callback(struct diff_options *opt, q.queue = xcalloc(num_paths, sizeof(struct diff_filepair *)); q.alloc = num_paths; q.nr = num_paths; - for (i = 0, p = paths; p; p = p->next) { - if (!p->len) - continue; + for (i = 0, p = paths; p; p = p->next) q.queue[i++] = combined_pair(p, num_parent); - } opt->format_callback(&q, opt, opt->format_callback_data); for (i = 0; i < num_paths; i++) free_combined_pair(q.queue[i]); free(q.queue); } +static const char *path_path(void *obj) +{ + struct combine_diff_path *path = (struct combine_diff_path *)obj; + + return path->path; +} + void diff_tree_combined(const unsigned char *sha1, const struct sha1_array *parents, int dense, @@ -1310,6 +1316,8 @@ void diff_tree_combined(const unsigned char *sha1, diffopts.output_format = DIFF_FORMAT_NO_OUTPUT; DIFF_OPT_SET(&diffopts, RECURSIVE); DIFF_OPT_CLR(&diffopts, ALLOW_EXTERNAL); + /* tell diff_tree to emit paths in sorted (=tree) order */ + diffopts.orderfile = NULL; show_log_first = !!rev->loginfo && !rev->no_commit_id; needsep = 0; @@ -1335,22 +1343,46 @@ void diff_tree_combined(const unsigned char *sha1, printf("%s%c", diff_line_prefix(opt), opt->line_termination); } + + /* if showing diff, show it in requested order */ + if (diffopts.output_format != DIFF_FORMAT_NO_OUTPUT && + opt->orderfile) { + diffcore_order(opt->orderfile); + } + diff_flush(&diffopts); } - /* find out surviving paths */ - for (num_paths = 0, p = paths; p; p = p->next) { - if (p->len) - num_paths++; + /* find out number of surviving paths */ + for (num_paths = 0, p = paths; p; p = p->next) + num_paths++; + + /* order paths according to diffcore_order */ + if (opt->orderfile && num_paths) { + struct obj_order *o; + + o = xmalloc(sizeof(*o) * num_paths); + for (i = 0, p = paths; p; p = p->next, i++) + o[i].obj = p; + order_objects(opt->orderfile, path_path, o, num_paths); + for (i = 0; i < num_paths - 1; i++) { + p = o[i].obj; + p->next = o[i+1].obj; + } + + p = o[num_paths-1].obj; + p->next = NULL; + paths = o[0].obj; + free(o); } + + if (num_paths) { if (opt->output_format & (DIFF_FORMAT_RAW | DIFF_FORMAT_NAME | DIFF_FORMAT_NAME_STATUS)) { - for (p = paths; p; p = p->next) { - if (p->len) - show_raw_diff(p, num_parent, rev); - } + for (p = paths; p; p = p->next) + show_raw_diff(p, num_parent, rev); needsep = 1; } else if (opt->output_format & @@ -1363,11 +1395,9 @@ void diff_tree_combined(const unsigned char *sha1, if (needsep) printf("%s%c", diff_line_prefix(opt), opt->line_termination); - for (p = paths; p; p = p->next) { - if (p->len) - show_patch_diff(p, num_parent, dense, - 0, rev); - } + for (p = paths; p; p = p->next) + show_patch_diff(p, num_parent, dense, + 0, rev); } } diff --git a/compat/bswap.h b/compat/bswap.h index 5061214f73..120c6c1d37 100644 --- a/compat/bswap.h +++ b/compat/bswap.h @@ -17,7 +17,20 @@ static inline uint32_t default_swab32(uint32_t val) ((val & 0x000000ff) << 24)); } +static inline uint64_t default_bswap64(uint64_t val) +{ + return (((val & (uint64_t)0x00000000000000ffULL) << 56) | + ((val & (uint64_t)0x000000000000ff00ULL) << 40) | + ((val & (uint64_t)0x0000000000ff0000ULL) << 24) | + ((val & (uint64_t)0x00000000ff000000ULL) << 8) | + ((val & (uint64_t)0x000000ff00000000ULL) >> 8) | + ((val & (uint64_t)0x0000ff0000000000ULL) >> 24) | + ((val & (uint64_t)0x00ff000000000000ULL) >> 40) | + ((val & (uint64_t)0xff00000000000000ULL) >> 56)); +} + #undef bswap32 +#undef bswap64 #if defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__)) @@ -32,15 +45,42 @@ static inline uint32_t git_bswap32(uint32_t x) return result; } +#define bswap64 git_bswap64 +#if defined(__x86_64__) +static inline uint64_t git_bswap64(uint64_t x) +{ + uint64_t result; + if (__builtin_constant_p(x)) + result = default_bswap64(x); + else + __asm__("bswap %q0" : "=r" (result) : "0" (x)); + return result; +} +#else +static inline uint64_t git_bswap64(uint64_t x) +{ + union { uint64_t i64; uint32_t i32[2]; } tmp, result; + if (__builtin_constant_p(x)) + result.i64 = default_bswap64(x); + else { + tmp.i64 = x; + result.i32[0] = git_bswap32(tmp.i32[1]); + result.i32[1] = git_bswap32(tmp.i32[0]); + } + return result.i64; +} +#endif + #elif defined(_MSC_VER) && (defined(_M_IX86) || defined(_M_X64)) #include <stdlib.h> #define bswap32(x) _byteswap_ulong(x) +#define bswap64(x) _byteswap_uint64(x) #endif -#ifdef bswap32 +#if defined(bswap32) #undef ntohl #undef htonl @@ -48,3 +88,73 @@ static inline uint32_t git_bswap32(uint32_t x) #define htonl(x) bswap32(x) #endif + +#if defined(bswap64) + +#undef ntohll +#undef htonll +#define ntohll(x) bswap64(x) +#define htonll(x) bswap64(x) + +#else + +#undef ntohll +#undef htonll + +#if !defined(__BYTE_ORDER) +# if defined(BYTE_ORDER) && defined(LITTLE_ENDIAN) && defined(BIG_ENDIAN) +# define __BYTE_ORDER BYTE_ORDER +# define __LITTLE_ENDIAN LITTLE_ENDIAN +# define __BIG_ENDIAN BIG_ENDIAN +# endif +#endif + +#if !defined(__BYTE_ORDER) +# error "Cannot determine endianness" +#endif + +#if __BYTE_ORDER == __BIG_ENDIAN +# define ntohll(n) (n) +# define htonll(n) (n) +#else +# define ntohll(n) default_bswap64(n) +# define htonll(n) default_bswap64(n) +#endif + +#endif + +/* + * Performance might be improved if the CPU architecture is OK with + * unaligned 32-bit loads and a fast ntohl() is available. + * Otherwise fall back to byte loads and shifts which is portable, + * and is faster on architectures with memory alignment issues. + */ + +#if defined(__i386__) || defined(__x86_64__) || \ + defined(_M_IX86) || defined(_M_X64) || \ + defined(__ppc__) || defined(__ppc64__) || \ + defined(__powerpc__) || defined(__powerpc64__) || \ + defined(__s390__) || defined(__s390x__) + +#define get_be16(p) ntohs(*(unsigned short *)(p)) +#define get_be32(p) ntohl(*(unsigned int *)(p)) +#define put_be32(p, v) do { *(unsigned int *)(p) = htonl(v); } while (0) + +#else + +#define get_be16(p) ( \ + (*((unsigned char *)(p) + 0) << 8) | \ + (*((unsigned char *)(p) + 1) << 0) ) +#define get_be32(p) ( \ + (*((unsigned char *)(p) + 0) << 24) | \ + (*((unsigned char *)(p) + 1) << 16) | \ + (*((unsigned char *)(p) + 2) << 8) | \ + (*((unsigned char *)(p) + 3) << 0) ) +#define put_be32(p, v) do { \ + unsigned int __v = (v); \ + *((unsigned char *)(p) + 0) = __v >> 24; \ + *((unsigned char *)(p) + 1) = __v >> 16; \ + *((unsigned char *)(p) + 2) = __v >> 8; \ + *((unsigned char *)(p) + 3) = __v >> 0; } while (0) + +#endif @@ -21,6 +21,7 @@ struct config_source { } buf; } u; const char *name; + const char *path; int die_on_error; int linenr; int eof; @@ -84,8 +85,12 @@ static int handle_path_include(const char *path, struct config_include_data *inc { int ret = 0; struct strbuf buf = STRBUF_INIT; - char *expanded = expand_user_path(path); + char *expanded; + if (!path) + return config_error_nonbool("include.path"); + + expanded = expand_user_path(path); if (!expanded) return error("Could not expand include path '%s'", path); path = expanded; @@ -97,12 +102,12 @@ static int handle_path_include(const char *path, struct config_include_data *inc if (!is_absolute_path(path)) { char *slash; - if (!cf || !cf->name) + if (!cf || !cf->path) return error("relative config includes must come from files"); - slash = find_last_dir_sep(cf->name); + slash = find_last_dir_sep(cf->path); if (slash) - strbuf_add(&buf, cf->name, slash - cf->name + 1); + strbuf_add(&buf, cf->path, slash - cf->path + 1); strbuf_addstr(&buf, path); path = buf.buf; } @@ -663,20 +668,7 @@ static int git_default_core_config(const char *var, const char *value) trust_ctime = git_config_bool(var, value); return 0; } - if (!strcmp(var, "core.statinfo") || - !strcmp(var, "core.checkstat")) { - /* - * NEEDSWORK: statinfo was a typo in v1.8.2 that has - * never been advertised. we will remove it at Git - * 2.0 boundary. - */ - if (!strcmp(var, "core.statinfo")) { - static int warned; - if (!warned++) { - warning("'core.statinfo' will be removed in Git 2.0; " - "use 'core.checkstat' instead."); - } - } + if (!strcmp(var, "core.checkstat")) { if (!strcasecmp(value, "default")) check_stat = 1; else if (!strcasecmp(value, "minimal")) @@ -1030,24 +1022,35 @@ static int do_config_from(struct config_source *top, config_fn_t fn, void *data) return ret; } -int git_config_from_file(config_fn_t fn, const char *filename, void *data) +static int do_config_from_file(config_fn_t fn, + const char *name, const char *path, FILE *f, void *data) { - int ret; - FILE *f = fopen(filename, "r"); + struct config_source top; - ret = -1; - if (f) { - struct config_source top; + top.u.file = f; + top.name = name; + top.path = path; + top.die_on_error = 1; + top.do_fgetc = config_file_fgetc; + top.do_ungetc = config_file_ungetc; + top.do_ftell = config_file_ftell; - top.u.file = f; - top.name = filename; - top.die_on_error = 1; - top.do_fgetc = config_file_fgetc; - top.do_ungetc = config_file_ungetc; - top.do_ftell = config_file_ftell; + return do_config_from(&top, fn, data); +} - ret = do_config_from(&top, fn, data); +static int git_config_from_stdin(config_fn_t fn, void *data) +{ + return do_config_from_file(fn, "<stdin>", NULL, stdin, data); +} +int git_config_from_file(config_fn_t fn, const char *filename, void *data) +{ + int ret = -1; + FILE *f; + + f = fopen(filename, "r"); + if (f) { + ret = do_config_from_file(fn, filename, filename, f, data); fclose(f); } return ret; @@ -1062,6 +1065,7 @@ int git_config_from_buf(config_fn_t fn, const char *name, const char *buf, top.u.buf.len = len; top.u.buf.pos = 0; top.name = name; + top.path = NULL; top.die_on_error = 0; top.do_fgetc = config_buf_fgetc; top.do_ungetc = config_buf_ungetc; @@ -1170,8 +1174,7 @@ int git_config_early(config_fn_t fn, void *data, const char *repo_config) } int git_config_with_options(config_fn_t fn, void *data, - const char *filename, - const char *blob_ref, + struct git_config_source *config_source, int respect_includes) { char *repo_config = NULL; @@ -1189,10 +1192,12 @@ int git_config_with_options(config_fn_t fn, void *data, * If we have a specific filename, use it. Otherwise, follow the * regular lookup sequence. */ - if (filename) - return git_config_from_file(fn, filename, data); - else if (blob_ref) - return git_config_from_blob_ref(fn, blob_ref, data); + if (config_source && config_source->use_stdin) + return git_config_from_stdin(fn, data); + else if (config_source && config_source->file) + return git_config_from_file(fn, config_source->file, data); + else if (config_source && config_source->blob) + return git_config_from_blob_ref(fn, config_source->blob, data); repo_config = git_pathdup("config"); ret = git_config_early(fn, data, repo_config); @@ -1203,7 +1208,7 @@ int git_config_with_options(config_fn_t fn, void *data, int git_config(config_fn_t fn, void *data) { - return git_config_with_options(fn, data, NULL, NULL, 1); + return git_config_with_options(fn, data, NULL, 1); } /* diff --git a/contrib/completion/git-completion.bash b/contrib/completion/git-completion.bash index 9525343fcd..87de809d23 100644 --- a/contrib/completion/git-completion.bash +++ b/contrib/completion/git-completion.bash @@ -1221,14 +1221,20 @@ _git_difftool () __git_complete_revlist_file } +__git_fetch_recurse_submodules="yes on-demand no" + __git_fetch_options=" --quiet --verbose --append --upload-pack --force --keep --depth= - --tags --no-tags --all --prune --dry-run + --tags --no-tags --all --prune --dry-run --recurse-submodules= " _git_fetch () { case "$cur" in + --recurse-submodules=*) + __gitcomp "$__git_fetch_recurse_submodules" "" "${cur##--recurse-submodules=}" + return + ;; --*) __gitcomp "$__git_fetch_options" return @@ -1583,6 +1589,10 @@ _git_pull () __git_complete_strategy && return case "$cur" in + --recurse-submodules=*) + __gitcomp "$__git_fetch_recurse_submodules" "" "${cur##--recurse-submodules=}" + return + ;; --*) __gitcomp " --rebase --no-rebase @@ -1595,6 +1605,8 @@ _git_pull () __git_complete_remote_or_refspec } +__git_push_recurse_submodules="check on-demand" + _git_push () { case "$prev" in @@ -1607,10 +1619,15 @@ _git_push () __gitcomp_nl "$(__git_remotes)" "" "${cur##--repo=}" return ;; + --recurse-submodules=*) + __gitcomp "$__git_push_recurse_submodules" "" "${cur##--recurse-submodules=}" + return + ;; --*) __gitcomp " --all --mirror --tags --dry-run --force --verbose --receive-pack= --repo= --set-upstream + --recurse-submodules= " return ;; diff --git a/contrib/contacts/git-contacts b/contrib/contacts/git-contacts index 428cc1a9a1..dbe2abf277 100755 --- a/contrib/contacts/git-contacts +++ b/contrib/contacts/git-contacts @@ -96,8 +96,6 @@ sub scan_patches { next unless $id; if (m{^--- (?:a/(.+)|/dev/null)$}) { $source = $1; - } elsif (/^--- /) { - die "Cannot parse hunk source: $_\n"; } elsif (/^@@ -(\d+)(?:,(\d+))?/ && $source) { my $len = defined($2) ? $2 : 1; push @{$sources->{$source}{$id}}, [$1, $len] if $len; diff --git a/contrib/git-resurrect.sh b/contrib/git-resurrect.sh index a4ed4c3c62..d7e97bbc76 100755 --- a/contrib/git-resurrect.sh +++ b/contrib/git-resurrect.sh @@ -10,6 +10,7 @@ is rather slow but allows you to resurrect other people's topic branches." OPTIONS_KEEPDASHDASH= +OPTIONS_STUCKLONG= OPTIONS_SPEC="\ git resurrect $USAGE -- @@ -1056,11 +1056,6 @@ static void drop_privileges(struct credentials *cred) /* nothing */ } -static void daemonize(void) -{ - die("--detach not supported on this platform"); -} - static struct credentials *prepare_credentials(const char *user_name, const char *group_name) { @@ -1102,24 +1097,6 @@ static struct credentials *prepare_credentials(const char *user_name, return &c; } - -static void daemonize(void) -{ - switch (fork()) { - case 0: - break; - case -1: - die_errno("fork failed"); - default: - exit(0); - } - if (setsid() == -1) - die_errno("setsid failed"); - close(0); - close(1); - close(2); - sanitize_stdfds(); -} #endif static void store_pid(const char *path) @@ -1333,9 +1310,10 @@ int main(int argc, char **argv) if (inetd_mode || serve_mode) return execute(); - if (detach) - daemonize(); - else + if (detach) { + if (daemonize()) + die("--detach not supported on this platform"); + } else sanitize_stdfds(); if (pid_file) diff --git a/diff-lib.c b/diff-lib.c index 346cac651d..044872935c 100644 --- a/diff-lib.c +++ b/diff-lib.c @@ -11,6 +11,7 @@ #include "unpack-trees.h" #include "refs.h" #include "submodule.h" +#include "dir.h" /* * diff-files @@ -90,9 +91,6 @@ int run_diff_files(struct rev_info *revs, unsigned int option) unsigned ce_option = ((option & DIFF_RACY_IS_MODIFIED) ? CE_MATCH_RACY_IS_DIRTY : 0); - if (option & DIFF_SILENT_ON_REMOVED) - handle_deprecated_show_diff_q(&revs->diffopt); - diff_set_mnemonic_prefix(&revs->diffopt, "i/", "w/"); if (diff_unmerged_stage < 0) @@ -108,7 +106,7 @@ int run_diff_files(struct rev_info *revs, unsigned int option) if (diff_can_quit_early(&revs->diffopt)) break; - if (!ce_path_match(ce, &revs->prune_data)) + if (!ce_path_match(ce, &revs->prune_data, NULL)) continue; if (ce_stage(ce)) { @@ -124,7 +122,6 @@ int run_diff_files(struct rev_info *revs, unsigned int option) dpath->path = (char *) &(dpath->parent[5]); dpath->next = NULL; - dpath->len = path_len; memcpy(dpath->path, ce->name, path_len); dpath->path[path_len] = '\0'; hashclr(dpath->sha1); @@ -326,7 +323,6 @@ static int show_modified(struct rev_info *revs, p = xmalloc(combine_diff_path_size(2, pathlen)); p->path = (char *) &p->parent[2]; p->next = NULL; - p->len = pathlen; memcpy(p->path, new->name, pathlen); p->path[pathlen] = 0; p->mode = mode; @@ -438,7 +434,7 @@ static int oneway_diff(const struct cache_entry * const *src, if (tree == o->df_conflict_entry) tree = NULL; - if (ce_path_match(idx ? idx : tree, &revs->prune_data)) { + if (ce_path_match(idx ? idx : tree, &revs->prune_data, NULL)) { do_oneway_diff(o, idx, tree); if (diff_can_quit_early(&revs->diffopt)) { o->exiting_early = 1; diff --git a/diff-no-index.c b/diff-no-index.c index 33e5982a1c..8e10bff30e 100644 --- a/diff-no-index.c +++ b/diff-no-index.c @@ -186,7 +186,6 @@ void diff_no_index(struct rev_info *revs, const char *prefix) { int i, prefixlen; - unsigned deprecated_show_diff_q_option_used = 0; const char *paths[2]; diff_setup(&revs->diffopt); @@ -194,10 +193,6 @@ void diff_no_index(struct rev_info *revs, int j; if (!strcmp(argv[i], "--no-index")) i++; - else if (!strcmp(argv[i], "-q")) { - deprecated_show_diff_q_option_used = 1; - i++; - } else if (!strcmp(argv[i], "--")) i++; else { @@ -230,9 +225,6 @@ void diff_no_index(struct rev_info *revs, revs->max_count = -2; diff_setup_done(&revs->diffopt); - if (deprecated_show_diff_q_option_used) - handle_deprecated_show_diff_q(&revs->diffopt); - setup_diff_pager(&revs->diffopt); DIFF_OPT_SET(&revs->diffopt, EXIT_WITH_STATUS); @@ -2845,8 +2845,9 @@ static struct diff_tempfile *prepare_temp_file(const char *name, remove_tempfile_installed = 1; } - if (!one->sha1_valid || - reuse_worktree_file(name, one->sha1, 1)) { + if (!S_ISGITLINK(one->mode) && + (!one->sha1_valid || + reuse_worktree_file(name, one->sha1, 1))) { struct stat st; if (lstat(name, &st) < 0) { if (errno == ENOENT) @@ -3599,14 +3600,6 @@ static int parse_diff_filter_opt(const char *optarg, struct diff_options *opt) return 0; } -/* Used only by "diff-files" and "diff --no-index" */ -void handle_deprecated_show_diff_q(struct diff_options *opt) -{ - warning("'diff -q' and 'diff-files -q' are deprecated."); - warning("Use 'diff --diff-filter=d' instead to ignore deleted filepairs."); - parse_diff_filter_opt("d", opt); -} - static void enable_patch_output(int *fmt) { *fmt &= ~DIFF_FORMAT_NO_OUTPUT; *fmt |= DIFF_FORMAT_PATCH; @@ -4697,6 +4690,38 @@ static int diff_filespec_is_identical(struct diff_filespec *one, return !memcmp(one->data, two->data, one->size); } +static int diff_filespec_check_stat_unmatch(struct diff_filepair *p) +{ + if (p->done_skip_stat_unmatch) + return p->skip_stat_unmatch_result; + + p->done_skip_stat_unmatch = 1; + p->skip_stat_unmatch_result = 0; + /* + * 1. Entries that come from stat info dirtiness + * always have both sides (iow, not create/delete), + * one side of the object name is unknown, with + * the same mode and size. Keep the ones that + * do not match these criteria. They have real + * differences. + * + * 2. At this point, the file is known to be modified, + * with the same mode and size, and the object + * name of one side is unknown. Need to inspect + * the identical contents. + */ + if (!DIFF_FILE_VALID(p->one) || /* (1) */ + !DIFF_FILE_VALID(p->two) || + (p->one->sha1_valid && p->two->sha1_valid) || + (p->one->mode != p->two->mode) || + diff_populate_filespec(p->one, 1) || + diff_populate_filespec(p->two, 1) || + (p->one->size != p->two->size) || + !diff_filespec_is_identical(p->one, p->two)) /* (2) */ + p->skip_stat_unmatch_result = 1; + return p->skip_stat_unmatch_result; +} + static void diffcore_skip_stat_unmatch(struct diff_options *diffopt) { int i; @@ -4707,27 +4732,7 @@ static void diffcore_skip_stat_unmatch(struct diff_options *diffopt) for (i = 0; i < q->nr; i++) { struct diff_filepair *p = q->queue[i]; - /* - * 1. Entries that come from stat info dirtiness - * always have both sides (iow, not create/delete), - * one side of the object name is unknown, with - * the same mode and size. Keep the ones that - * do not match these criteria. They have real - * differences. - * - * 2. At this point, the file is known to be modified, - * with the same mode and size, and the object - * name of one side is unknown. Need to inspect - * the identical contents. - */ - if (!DIFF_FILE_VALID(p->one) || /* (1) */ - !DIFF_FILE_VALID(p->two) || - (p->one->sha1_valid && p->two->sha1_valid) || - (p->one->mode != p->two->mode) || - diff_populate_filespec(p->one, 1) || - diff_populate_filespec(p->two, 1) || - (p->one->size != p->two->size) || - !diff_filespec_is_identical(p->one, p->two)) /* (2) */ + if (diff_filespec_check_stat_unmatch(p)) diff_q(&outq, p); else { /* @@ -4890,6 +4895,7 @@ void diff_change(struct diff_options *options, unsigned old_dirty_submodule, unsigned new_dirty_submodule) { struct diff_filespec *one, *two; + struct diff_filepair *p; if (S_ISGITLINK(old_mode) && S_ISGITLINK(new_mode) && is_submodule_ignored(concatpath, options)) @@ -4916,10 +4922,16 @@ void diff_change(struct diff_options *options, fill_filespec(two, new_sha1, new_sha1_valid, new_mode); one->dirty_submodule = old_dirty_submodule; two->dirty_submodule = new_dirty_submodule; + p = diff_queue(&diff_queued_diff, one, two); - diff_queue(&diff_queued_diff, one, two); - if (!DIFF_OPT_TST(options, DIFF_FROM_CONTENTS)) - DIFF_OPT_SET(options, HAS_CHANGES); + if (DIFF_OPT_TST(options, DIFF_FROM_CONTENTS)) + return; + + if (DIFF_OPT_TST(options, QUICK) && options->skip_stat_unmatch && + !diff_filespec_check_stat_unmatch(p)) + return; + + DIFF_OPT_SET(options, HAS_CHANGES); } struct diff_filepair *diff_unmerge(struct diff_options *options, const char *path) @@ -198,7 +198,6 @@ extern int diff_root_tree_sha1(const unsigned char *new, const char *base, struct combine_diff_path { struct combine_diff_path *next; - int len; char *path; unsigned int mode; unsigned char sha1[20]; @@ -346,8 +345,6 @@ extern int parse_rename_score(const char **cp_p); extern long parse_algorithm_value(const char *value); -extern void handle_deprecated_show_diff_q(struct diff_options *); - extern int print_stat_summary(FILE *fp, int files, int insertions, int deletions); extern void setup_diff_pager(struct diff_options *); diff --git a/diffcore-order.c b/diffcore-order.c index 53ea4d14c2..97dd3d0095 100644 --- a/diffcore-order.c +++ b/diffcore-order.c @@ -57,12 +57,6 @@ static void prepare_order(const char *orderfile) } } -struct pair_order { - struct diff_filepair *pair; - int orig_order; - int order; -}; - static int match_order(const char *path) { int i; @@ -84,35 +78,54 @@ static int match_order(const char *path) return order_cnt; } -static int compare_pair_order(const void *a_, const void *b_) +static int compare_objs_order(const void *a_, const void *b_) { - struct pair_order const *a, *b; - a = (struct pair_order const *)a_; - b = (struct pair_order const *)b_; + struct obj_order const *a, *b; + a = (struct obj_order const *)a_; + b = (struct obj_order const *)b_; if (a->order != b->order) return a->order - b->order; return a->orig_order - b->orig_order; } +void order_objects(const char *orderfile, obj_path_fn_t obj_path, + struct obj_order *objs, int nr) +{ + int i; + + if (!nr) + return; + + prepare_order(orderfile); + for (i = 0; i < nr; i++) { + objs[i].orig_order = i; + objs[i].order = match_order(obj_path(objs[i].obj)); + } + qsort(objs, nr, sizeof(*objs), compare_objs_order); +} + +static const char *pair_pathtwo(void *obj) +{ + struct diff_filepair *pair = (struct diff_filepair *)obj; + + return pair->two->path; +} + void diffcore_order(const char *orderfile) { struct diff_queue_struct *q = &diff_queued_diff; - struct pair_order *o; + struct obj_order *o; int i; if (!q->nr) return; o = xmalloc(sizeof(*o) * q->nr); - prepare_order(orderfile); - for (i = 0; i < q->nr; i++) { - o[i].pair = q->queue[i]; - o[i].orig_order = i; - o[i].order = match_order(o[i].pair->two->path); - } - qsort(o, q->nr, sizeof(*o), compare_pair_order); for (i = 0; i < q->nr; i++) - q->queue[i] = o[i].pair; + o[i].obj = q->queue[i]; + order_objects(orderfile, pair_pathtwo, o, q->nr); + for (i = 0; i < q->nr; i++) + q->queue[i] = o[i].obj; free(o); return; } diff --git a/diffcore-rename.c b/diffcore-rename.c index 6c7a72fbe7..9b4f068eb3 100644 --- a/diffcore-rename.c +++ b/diffcore-rename.c @@ -4,7 +4,7 @@ #include "cache.h" #include "diff.h" #include "diffcore.h" -#include "hash.h" +#include "hashmap.h" #include "progress.h" /* Table of rename/copy destinations */ @@ -243,137 +243,82 @@ static int score_compare(const void *a_, const void *b_) } struct file_similarity { - int src_dst, index; + struct hashmap_entry entry; + int index; struct diff_filespec *filespec; - struct file_similarity *next; }; -static int find_identical_files(struct file_similarity *src, - struct file_similarity *dst, +static unsigned int hash_filespec(struct diff_filespec *filespec) +{ + unsigned int hash; + if (!filespec->sha1_valid) { + if (diff_populate_filespec(filespec, 0)) + return 0; + hash_sha1_file(filespec->data, filespec->size, "blob", filespec->sha1); + } + memcpy(&hash, filespec->sha1, sizeof(hash)); + return hash; +} + +static int find_identical_files(struct hashmap *srcs, + int dst_index, struct diff_options *options) { int renames = 0; + struct diff_filespec *target = rename_dst[dst_index].two; + struct file_similarity *p, *best, dst; + int i = 100, best_score = -1; + /* - * Walk over all the destinations ... + * Find the best source match for specified destination. */ - do { - struct diff_filespec *target = dst->filespec; - struct file_similarity *p, *best; - int i = 100, best_score = -1; - - /* - * .. to find the best source match - */ - best = NULL; - for (p = src; p; p = p->next) { - int score; - struct diff_filespec *source = p->filespec; - - /* False hash collision? */ - if (hashcmp(source->sha1, target->sha1)) - continue; - /* Non-regular files? If so, the modes must match! */ - if (!S_ISREG(source->mode) || !S_ISREG(target->mode)) { - if (source->mode != target->mode) - continue; - } - /* Give higher scores to sources that haven't been used already */ - score = !source->rename_used; - if (source->rename_used && options->detect_rename != DIFF_DETECT_COPY) + best = NULL; + hashmap_entry_init(&dst, hash_filespec(target)); + for (p = hashmap_get(srcs, &dst, NULL); p; p = hashmap_get_next(srcs, p)) { + int score; + struct diff_filespec *source = p->filespec; + + /* False hash collision? */ + if (hashcmp(source->sha1, target->sha1)) + continue; + /* Non-regular files? If so, the modes must match! */ + if (!S_ISREG(source->mode) || !S_ISREG(target->mode)) { + if (source->mode != target->mode) continue; - score += basename_same(source, target); - if (score > best_score) { - best = p; - best_score = score; - if (score == 2) - break; - } - - /* Too many identical alternatives? Pick one */ - if (!--i) - break; } - if (best) { - record_rename_pair(dst->index, best->index, MAX_SCORE); - renames++; + /* Give higher scores to sources that haven't been used already */ + score = !source->rename_used; + if (source->rename_used && options->detect_rename != DIFF_DETECT_COPY) + continue; + score += basename_same(source, target); + if (score > best_score) { + best = p; + best_score = score; + if (score == 2) + break; } - } while ((dst = dst->next) != NULL); - return renames; -} -static void free_similarity_list(struct file_similarity *p) -{ - while (p) { - struct file_similarity *entry = p; - p = p->next; - free(entry); + /* Too many identical alternatives? Pick one */ + if (!--i) + break; } -} - -static int find_same_files(void *ptr, void *data) -{ - int ret; - struct file_similarity *p = ptr; - struct file_similarity *src = NULL, *dst = NULL; - struct diff_options *options = data; - - /* Split the hash list up into sources and destinations */ - do { - struct file_similarity *entry = p; - p = p->next; - if (entry->src_dst < 0) { - entry->next = src; - src = entry; - } else { - entry->next = dst; - dst = entry; - } - } while (p); - - /* - * If we have both sources *and* destinations, see if - * we can match them up - */ - ret = (src && dst) ? find_identical_files(src, dst, options) : 0; - - /* Free the hashes and return the number of renames found */ - free_similarity_list(src); - free_similarity_list(dst); - return ret; -} - -static unsigned int hash_filespec(struct diff_filespec *filespec) -{ - unsigned int hash; - if (!filespec->sha1_valid) { - if (diff_populate_filespec(filespec, 0)) - return 0; - hash_sha1_file(filespec->data, filespec->size, "blob", filespec->sha1); + if (best) { + record_rename_pair(dst_index, best->index, MAX_SCORE); + renames++; } - memcpy(&hash, filespec->sha1, sizeof(hash)); - return hash; + return renames; } -static void insert_file_table(struct hash_table *table, int src_dst, int index, struct diff_filespec *filespec) +static void insert_file_table(struct hashmap *table, int index, struct diff_filespec *filespec) { - void **pos; - unsigned int hash; struct file_similarity *entry = xmalloc(sizeof(*entry)); - entry->src_dst = src_dst; entry->index = index; entry->filespec = filespec; - entry->next = NULL; - - hash = hash_filespec(filespec); - pos = insert_hash(hash, entry, table); - /* We already had an entry there? */ - if (pos) { - entry->next = *pos; - *pos = entry; - } + hashmap_entry_init(entry, hash_filespec(filespec)); + hashmap_add(table, entry); } /* @@ -385,24 +330,22 @@ static void insert_file_table(struct hash_table *table, int src_dst, int index, */ static int find_exact_renames(struct diff_options *options) { - int i; - struct hash_table file_table; + int i, renames = 0; + struct hashmap file_table; - init_hash(&file_table); - preallocate_hash(&file_table, rename_src_nr + rename_dst_nr); + /* Add all sources to the hash table */ + hashmap_init(&file_table, NULL, rename_src_nr); for (i = 0; i < rename_src_nr; i++) - insert_file_table(&file_table, -1, i, rename_src[i].p->one); + insert_file_table(&file_table, i, rename_src[i].p->one); + /* Walk the destinations and find best source match */ for (i = 0; i < rename_dst_nr; i++) - insert_file_table(&file_table, 1, i, rename_dst[i].two); - - /* Find the renames */ - i = for_each_hash(&file_table, find_same_files, options); + renames += find_identical_files(&file_table, i, options); - /* .. and free the hash data structure */ - free_hash(&file_table); + /* Free the hash data structure and entries */ + hashmap_free(&file_table, 1); - return i; + return renames; } #define NUM_CANDIDATE_PER_DST 4 diff --git a/diffcore.h b/diffcore.h index 79de8cf28d..92788ee4de 100644 --- a/diffcore.h +++ b/diffcore.h @@ -68,6 +68,8 @@ struct diff_filepair { unsigned broken_pair : 1; unsigned renamed_pair : 1; unsigned is_unmerged : 1; + unsigned done_skip_stat_unmatch : 1; + unsigned skip_stat_unmatch_result : 1; }; #define DIFF_PAIR_UNMERGED(p) ((p)->is_unmerged) @@ -109,6 +111,20 @@ extern void diffcore_merge_broken(void); extern void diffcore_pickaxe(struct diff_options *); extern void diffcore_order(const char *orderfile); +/* low-level interface to diffcore_order */ +struct obj_order { + void *obj; /* setup by caller */ + + /* setup/used by order_objects() */ + int orig_order; + int order; +}; + +typedef const char *(*obj_path_fn_t)(void *obj); + +void order_objects(const char *orderfile, obj_path_fn_t obj_path, + struct obj_order *objs, int nr); + #define DIFF_DEBUG 0 #if DIFF_DEBUG void diff_debug_filespec(struct diff_filespec *, int, const char *); @@ -198,6 +198,9 @@ int within_depth(const char *name, int namelen, return 1; } +#define DO_MATCH_EXCLUDE 1 +#define DO_MATCH_DIRECTORY 2 + /* * Does 'match' match the given name? * A match is found if @@ -211,7 +214,7 @@ int within_depth(const char *name, int namelen, * It returns 0 when there is no match. */ static int match_pathspec_item(const struct pathspec_item *item, int prefix, - const char *name, int namelen) + const char *name, int namelen, unsigned flags) { /* name/namelen has prefix cut off by caller */ const char *match = item->match + prefix; @@ -221,7 +224,7 @@ static int match_pathspec_item(const struct pathspec_item *item, int prefix, * The normal call pattern is: * 1. prefix = common_prefix_len(ps); * 2. prune something, or fill_directory - * 3. match_pathspec_depth() + * 3. match_pathspec() * * 'prefix' at #1 may be shorter than the command's prefix and * it's ok for #2 to match extra files. Those extras will be @@ -260,7 +263,11 @@ static int match_pathspec_item(const struct pathspec_item *item, int prefix, if (match[matchlen-1] == '/' || name[matchlen] == '/') return MATCHED_RECURSIVELY; - } + } else if ((flags & DO_MATCH_DIRECTORY) && + match[matchlen - 1] == '/' && + namelen == matchlen - 1 && + !ps_strncmp(item, match, name, namelen)) + return MATCHED_EXACTLY; if (item->nowildcard_len < item->len && !git_fnmatch(item, match, name, @@ -285,12 +292,12 @@ static int match_pathspec_item(const struct pathspec_item *item, int prefix, * pathspec did not match any names, which could indicate that the * user mistyped the nth pathspec. */ -static int match_pathspec_depth_1(const struct pathspec *ps, - const char *name, int namelen, - int prefix, char *seen, - int exclude) +static int do_match_pathspec(const struct pathspec *ps, + const char *name, int namelen, + int prefix, char *seen, + unsigned flags) { - int i, retval = 0; + int i, retval = 0, exclude = flags & DO_MATCH_EXCLUDE; GUARD_PATHSPEC(ps, PATHSPEC_FROMTOP | @@ -330,7 +337,8 @@ static int match_pathspec_depth_1(const struct pathspec *ps, */ if (seen && ps->items[i].magic & PATHSPEC_EXCLUDE) seen[i] = MATCHED_FNMATCH; - how = match_pathspec_item(ps->items+i, prefix, name, namelen); + how = match_pathspec_item(ps->items+i, prefix, name, + namelen, flags); if (ps->recursive && (ps->magic & PATHSPEC_MAXDEPTH) && ps->max_depth != -1 && @@ -353,15 +361,19 @@ static int match_pathspec_depth_1(const struct pathspec *ps, return retval; } -int match_pathspec_depth(const struct pathspec *ps, - const char *name, int namelen, - int prefix, char *seen) +int match_pathspec(const struct pathspec *ps, + const char *name, int namelen, + int prefix, char *seen, int is_dir) { int positive, negative; - positive = match_pathspec_depth_1(ps, name, namelen, prefix, seen, 0); + unsigned flags = is_dir ? DO_MATCH_DIRECTORY : 0; + positive = do_match_pathspec(ps, name, namelen, + prefix, seen, flags); if (!(ps->magic & PATHSPEC_EXCLUDE) || !positive) return positive; - negative = match_pathspec_depth_1(ps, name, namelen, prefix, seen, 1); + negative = do_match_pathspec(ps, name, namelen, + prefix, seen, + flags | DO_MATCH_EXCLUDE); return negative ? 0 : positive; } @@ -494,6 +506,25 @@ void clear_exclude_list(struct exclude_list *el) el->filebuf = NULL; } +static void trim_trailing_spaces(char *buf) +{ + int i, last_space = -1, nr_spaces, len = strlen(buf); + for (i = 0; i < len; i++) + if (buf[i] == '\\') + i++; + else if (buf[i] == ' ') { + if (last_space == -1) { + last_space = i; + nr_spaces = 1; + } else + nr_spaces++; + } else + last_space = -1; + + if (last_space != -1 && last_space + nr_spaces == len) + buf[last_space] = '\0'; +} + int add_excludes_from_file_to_list(const char *fname, const char *base, int baselen, @@ -545,6 +576,7 @@ int add_excludes_from_file_to_list(const char *fname, if (buf[i] == '\n') { if (entry != buf + i && entry[0] != '#') { buf[i - (i && buf[i-1] == '\r')] = 0; + trim_trailing_spaces(entry); add_exclude(entry, base, baselen, el, lineno); } lineno++; @@ -132,9 +132,9 @@ struct dir_struct { extern int simple_length(const char *match); extern int no_wildcard(const char *string); extern char *common_prefix(const struct pathspec *pathspec); -extern int match_pathspec_depth(const struct pathspec *pathspec, - const char *name, int namelen, - int prefix, char *seen); +extern int match_pathspec(const struct pathspec *pathspec, + const char *name, int namelen, + int prefix, char *seen, int is_dir); extern int within_depth(const char *name, int namelen, int depth, int max_depth); extern int fill_directory(struct dir_struct *dir, const struct pathspec *pathspec); @@ -205,4 +205,22 @@ extern int git_fnmatch(const struct pathspec_item *item, const char *pattern, const char *string, int prefix); +static inline int ce_path_match(const struct cache_entry *ce, + const struct pathspec *pathspec, + char *seen) +{ + return match_pathspec(pathspec, ce->name, ce_namelen(ce), 0, seen, + S_ISDIR(ce->ce_mode) || S_ISGITLINK(ce->ce_mode)); +} + +static inline int dir_path_match(const struct dir_entry *ent, + const struct pathspec *pathspec, + int prefix, char *seen) +{ + int has_trailing_dir = ent->len && ent->name[ent->len - 1] == '/'; + int len = has_trailing_dir ? ent->len - 1 : ent->len; + return match_pathspec(pathspec, ent->name, len, prefix, seen, + has_trailing_dir); +} + #endif diff --git a/ewah/bitmap.c b/ewah/bitmap.c new file mode 100644 index 0000000000..710e58c1bf --- /dev/null +++ b/ewah/bitmap.c @@ -0,0 +1,221 @@ +/** + * Copyright 2013, GitHub, Inc + * Copyright 2009-2013, Daniel Lemire, Cliff Moon, + * David McIntosh, Robert Becho, Google Inc. and Veronika Zenz + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + */ +#include "git-compat-util.h" +#include "ewok.h" + +#define MASK(x) ((eword_t)1 << (x % BITS_IN_WORD)) +#define BLOCK(x) (x / BITS_IN_WORD) + +struct bitmap *bitmap_new(void) +{ + struct bitmap *bitmap = ewah_malloc(sizeof(struct bitmap)); + bitmap->words = ewah_calloc(32, sizeof(eword_t)); + bitmap->word_alloc = 32; + return bitmap; +} + +void bitmap_set(struct bitmap *self, size_t pos) +{ + size_t block = BLOCK(pos); + + if (block >= self->word_alloc) { + size_t old_size = self->word_alloc; + self->word_alloc = block * 2; + self->words = ewah_realloc(self->words, + self->word_alloc * sizeof(eword_t)); + + memset(self->words + old_size, 0x0, + (self->word_alloc - old_size) * sizeof(eword_t)); + } + + self->words[block] |= MASK(pos); +} + +void bitmap_clear(struct bitmap *self, size_t pos) +{ + size_t block = BLOCK(pos); + + if (block < self->word_alloc) + self->words[block] &= ~MASK(pos); +} + +int bitmap_get(struct bitmap *self, size_t pos) +{ + size_t block = BLOCK(pos); + return block < self->word_alloc && + (self->words[block] & MASK(pos)) != 0; +} + +struct ewah_bitmap *bitmap_to_ewah(struct bitmap *bitmap) +{ + struct ewah_bitmap *ewah = ewah_new(); + size_t i, running_empty_words = 0; + eword_t last_word = 0; + + for (i = 0; i < bitmap->word_alloc; ++i) { + if (bitmap->words[i] == 0) { + running_empty_words++; + continue; + } + + if (last_word != 0) + ewah_add(ewah, last_word); + + if (running_empty_words > 0) { + ewah_add_empty_words(ewah, 0, running_empty_words); + running_empty_words = 0; + } + + last_word = bitmap->words[i]; + } + + ewah_add(ewah, last_word); + return ewah; +} + +struct bitmap *ewah_to_bitmap(struct ewah_bitmap *ewah) +{ + struct bitmap *bitmap = bitmap_new(); + struct ewah_iterator it; + eword_t blowup; + size_t i = 0; + + ewah_iterator_init(&it, ewah); + + while (ewah_iterator_next(&blowup, &it)) { + if (i >= bitmap->word_alloc) { + bitmap->word_alloc *= 1.5; + bitmap->words = ewah_realloc( + bitmap->words, bitmap->word_alloc * sizeof(eword_t)); + } + + bitmap->words[i++] = blowup; + } + + bitmap->word_alloc = i; + return bitmap; +} + +void bitmap_and_not(struct bitmap *self, struct bitmap *other) +{ + const size_t count = (self->word_alloc < other->word_alloc) ? + self->word_alloc : other->word_alloc; + + size_t i; + + for (i = 0; i < count; ++i) + self->words[i] &= ~other->words[i]; +} + +void bitmap_or_ewah(struct bitmap *self, struct ewah_bitmap *other) +{ + size_t original_size = self->word_alloc; + size_t other_final = (other->bit_size / BITS_IN_WORD) + 1; + size_t i = 0; + struct ewah_iterator it; + eword_t word; + + if (self->word_alloc < other_final) { + self->word_alloc = other_final; + self->words = ewah_realloc(self->words, + self->word_alloc * sizeof(eword_t)); + memset(self->words + original_size, 0x0, + (self->word_alloc - original_size) * sizeof(eword_t)); + } + + ewah_iterator_init(&it, other); + + while (ewah_iterator_next(&word, &it)) + self->words[i++] |= word; +} + +void bitmap_each_bit(struct bitmap *self, ewah_callback callback, void *data) +{ + size_t pos = 0, i; + + for (i = 0; i < self->word_alloc; ++i) { + eword_t word = self->words[i]; + uint32_t offset; + + if (word == (eword_t)~0) { + for (offset = 0; offset < BITS_IN_WORD; ++offset) + callback(pos++, data); + } else { + for (offset = 0; offset < BITS_IN_WORD; ++offset) { + if ((word >> offset) == 0) + break; + + offset += ewah_bit_ctz64(word >> offset); + callback(pos + offset, data); + } + pos += BITS_IN_WORD; + } + } +} + +size_t bitmap_popcount(struct bitmap *self) +{ + size_t i, count = 0; + + for (i = 0; i < self->word_alloc; ++i) + count += ewah_bit_popcount64(self->words[i]); + + return count; +} + +int bitmap_equals(struct bitmap *self, struct bitmap *other) +{ + struct bitmap *big, *small; + size_t i; + + if (self->word_alloc < other->word_alloc) { + small = self; + big = other; + } else { + small = other; + big = self; + } + + for (i = 0; i < small->word_alloc; ++i) { + if (small->words[i] != big->words[i]) + return 0; + } + + for (; i < big->word_alloc; ++i) { + if (big->words[i] != 0) + return 0; + } + + return 1; +} + +void bitmap_reset(struct bitmap *bitmap) +{ + memset(bitmap->words, 0x0, bitmap->word_alloc * sizeof(eword_t)); +} + +void bitmap_free(struct bitmap *bitmap) +{ + if (bitmap == NULL) + return; + + free(bitmap->words); + free(bitmap); +} diff --git a/ewah/ewah_bitmap.c b/ewah/ewah_bitmap.c new file mode 100644 index 0000000000..9ced2dadfe --- /dev/null +++ b/ewah/ewah_bitmap.c @@ -0,0 +1,714 @@ +/** + * Copyright 2013, GitHub, Inc + * Copyright 2009-2013, Daniel Lemire, Cliff Moon, + * David McIntosh, Robert Becho, Google Inc. and Veronika Zenz + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + */ +#include "git-compat-util.h" +#include "ewok.h" +#include "ewok_rlw.h" + +static inline size_t min_size(size_t a, size_t b) +{ + return a < b ? a : b; +} + +static inline size_t max_size(size_t a, size_t b) +{ + return a > b ? a : b; +} + +static inline void buffer_grow(struct ewah_bitmap *self, size_t new_size) +{ + size_t rlw_offset = (uint8_t *)self->rlw - (uint8_t *)self->buffer; + + if (self->alloc_size >= new_size) + return; + + self->alloc_size = new_size; + self->buffer = ewah_realloc(self->buffer, + self->alloc_size * sizeof(eword_t)); + self->rlw = self->buffer + (rlw_offset / sizeof(size_t)); +} + +static inline void buffer_push(struct ewah_bitmap *self, eword_t value) +{ + if (self->buffer_size + 1 >= self->alloc_size) + buffer_grow(self, self->buffer_size * 3 / 2); + + self->buffer[self->buffer_size++] = value; +} + +static void buffer_push_rlw(struct ewah_bitmap *self, eword_t value) +{ + buffer_push(self, value); + self->rlw = self->buffer + self->buffer_size - 1; +} + +static size_t add_empty_words(struct ewah_bitmap *self, int v, size_t number) +{ + size_t added = 0; + eword_t runlen, can_add; + + if (rlw_get_run_bit(self->rlw) != v && rlw_size(self->rlw) == 0) { + rlw_set_run_bit(self->rlw, v); + } else if (rlw_get_literal_words(self->rlw) != 0 || + rlw_get_run_bit(self->rlw) != v) { + buffer_push_rlw(self, 0); + if (v) rlw_set_run_bit(self->rlw, v); + added++; + } + + runlen = rlw_get_running_len(self->rlw); + can_add = min_size(number, RLW_LARGEST_RUNNING_COUNT - runlen); + + rlw_set_running_len(self->rlw, runlen + can_add); + number -= can_add; + + while (number >= RLW_LARGEST_RUNNING_COUNT) { + buffer_push_rlw(self, 0); + added++; + if (v) rlw_set_run_bit(self->rlw, v); + rlw_set_running_len(self->rlw, RLW_LARGEST_RUNNING_COUNT); + number -= RLW_LARGEST_RUNNING_COUNT; + } + + if (number > 0) { + buffer_push_rlw(self, 0); + added++; + + if (v) rlw_set_run_bit(self->rlw, v); + rlw_set_running_len(self->rlw, number); + } + + return added; +} + +size_t ewah_add_empty_words(struct ewah_bitmap *self, int v, size_t number) +{ + if (number == 0) + return 0; + + self->bit_size += number * BITS_IN_WORD; + return add_empty_words(self, v, number); +} + +static size_t add_literal(struct ewah_bitmap *self, eword_t new_data) +{ + eword_t current_num = rlw_get_literal_words(self->rlw); + + if (current_num >= RLW_LARGEST_LITERAL_COUNT) { + buffer_push_rlw(self, 0); + + rlw_set_literal_words(self->rlw, 1); + buffer_push(self, new_data); + return 2; + } + + rlw_set_literal_words(self->rlw, current_num + 1); + + /* sanity check */ + assert(rlw_get_literal_words(self->rlw) == current_num + 1); + + buffer_push(self, new_data); + return 1; +} + +void ewah_add_dirty_words( + struct ewah_bitmap *self, const eword_t *buffer, + size_t number, int negate) +{ + size_t literals, can_add; + + while (1) { + literals = rlw_get_literal_words(self->rlw); + can_add = min_size(number, RLW_LARGEST_LITERAL_COUNT - literals); + + rlw_set_literal_words(self->rlw, literals + can_add); + + if (self->buffer_size + can_add >= self->alloc_size) + buffer_grow(self, (self->buffer_size + can_add) * 3 / 2); + + if (negate) { + size_t i; + for (i = 0; i < can_add; ++i) + self->buffer[self->buffer_size++] = ~buffer[i]; + } else { + memcpy(self->buffer + self->buffer_size, + buffer, can_add * sizeof(eword_t)); + self->buffer_size += can_add; + } + + self->bit_size += can_add * BITS_IN_WORD; + + if (number - can_add == 0) + break; + + buffer_push_rlw(self, 0); + buffer += can_add; + number -= can_add; + } +} + +static size_t add_empty_word(struct ewah_bitmap *self, int v) +{ + int no_literal = (rlw_get_literal_words(self->rlw) == 0); + eword_t run_len = rlw_get_running_len(self->rlw); + + if (no_literal && run_len == 0) { + rlw_set_run_bit(self->rlw, v); + assert(rlw_get_run_bit(self->rlw) == v); + } + + if (no_literal && rlw_get_run_bit(self->rlw) == v && + run_len < RLW_LARGEST_RUNNING_COUNT) { + rlw_set_running_len(self->rlw, run_len + 1); + assert(rlw_get_running_len(self->rlw) == run_len + 1); + return 0; + } else { + buffer_push_rlw(self, 0); + + assert(rlw_get_running_len(self->rlw) == 0); + assert(rlw_get_run_bit(self->rlw) == 0); + assert(rlw_get_literal_words(self->rlw) == 0); + + rlw_set_run_bit(self->rlw, v); + assert(rlw_get_run_bit(self->rlw) == v); + + rlw_set_running_len(self->rlw, 1); + assert(rlw_get_running_len(self->rlw) == 1); + assert(rlw_get_literal_words(self->rlw) == 0); + return 1; + } +} + +size_t ewah_add(struct ewah_bitmap *self, eword_t word) +{ + self->bit_size += BITS_IN_WORD; + + if (word == 0) + return add_empty_word(self, 0); + + if (word == (eword_t)(~0)) + return add_empty_word(self, 1); + + return add_literal(self, word); +} + +void ewah_set(struct ewah_bitmap *self, size_t i) +{ + const size_t dist = + (i + BITS_IN_WORD) / BITS_IN_WORD - + (self->bit_size + BITS_IN_WORD - 1) / BITS_IN_WORD; + + assert(i >= self->bit_size); + + self->bit_size = i + 1; + + if (dist > 0) { + if (dist > 1) + add_empty_words(self, 0, dist - 1); + + add_literal(self, (eword_t)1 << (i % BITS_IN_WORD)); + return; + } + + if (rlw_get_literal_words(self->rlw) == 0) { + rlw_set_running_len(self->rlw, + rlw_get_running_len(self->rlw) - 1); + add_literal(self, (eword_t)1 << (i % BITS_IN_WORD)); + return; + } + + self->buffer[self->buffer_size - 1] |= + ((eword_t)1 << (i % BITS_IN_WORD)); + + /* check if we just completed a stream of 1s */ + if (self->buffer[self->buffer_size - 1] == (eword_t)(~0)) { + self->buffer[--self->buffer_size] = 0; + rlw_set_literal_words(self->rlw, + rlw_get_literal_words(self->rlw) - 1); + add_empty_word(self, 1); + } +} + +void ewah_each_bit(struct ewah_bitmap *self, void (*callback)(size_t, void*), void *payload) +{ + size_t pos = 0; + size_t pointer = 0; + size_t k; + + while (pointer < self->buffer_size) { + eword_t *word = &self->buffer[pointer]; + + if (rlw_get_run_bit(word)) { + size_t len = rlw_get_running_len(word) * BITS_IN_WORD; + for (k = 0; k < len; ++k, ++pos) + callback(pos, payload); + } else { + pos += rlw_get_running_len(word) * BITS_IN_WORD; + } + + ++pointer; + + for (k = 0; k < rlw_get_literal_words(word); ++k) { + int c; + + /* todo: zero count optimization */ + for (c = 0; c < BITS_IN_WORD; ++c, ++pos) { + if ((self->buffer[pointer] & ((eword_t)1 << c)) != 0) + callback(pos, payload); + } + + ++pointer; + } + } +} + +struct ewah_bitmap *ewah_new(void) +{ + struct ewah_bitmap *self; + + self = ewah_malloc(sizeof(struct ewah_bitmap)); + if (self == NULL) + return NULL; + + self->buffer = ewah_malloc(32 * sizeof(eword_t)); + self->alloc_size = 32; + + ewah_clear(self); + return self; +} + +void ewah_clear(struct ewah_bitmap *self) +{ + self->buffer_size = 1; + self->buffer[0] = 0; + self->bit_size = 0; + self->rlw = self->buffer; +} + +void ewah_free(struct ewah_bitmap *self) +{ + if (!self) + return; + + if (self->alloc_size) + free(self->buffer); + + free(self); +} + +static void read_new_rlw(struct ewah_iterator *it) +{ + const eword_t *word = NULL; + + it->literals = 0; + it->compressed = 0; + + while (1) { + word = &it->buffer[it->pointer]; + + it->rl = rlw_get_running_len(word); + it->lw = rlw_get_literal_words(word); + it->b = rlw_get_run_bit(word); + + if (it->rl || it->lw) + return; + + if (it->pointer < it->buffer_size - 1) { + it->pointer++; + } else { + it->pointer = it->buffer_size; + return; + } + } +} + +int ewah_iterator_next(eword_t *next, struct ewah_iterator *it) +{ + if (it->pointer >= it->buffer_size) + return 0; + + if (it->compressed < it->rl) { + it->compressed++; + *next = it->b ? (eword_t)(~0) : 0; + } else { + assert(it->literals < it->lw); + + it->literals++; + it->pointer++; + + assert(it->pointer < it->buffer_size); + + *next = it->buffer[it->pointer]; + } + + if (it->compressed == it->rl && it->literals == it->lw) { + if (++it->pointer < it->buffer_size) + read_new_rlw(it); + } + + return 1; +} + +void ewah_iterator_init(struct ewah_iterator *it, struct ewah_bitmap *parent) +{ + it->buffer = parent->buffer; + it->buffer_size = parent->buffer_size; + it->pointer = 0; + + it->lw = 0; + it->rl = 0; + it->compressed = 0; + it->literals = 0; + it->b = 0; + + if (it->pointer < it->buffer_size) + read_new_rlw(it); +} + +void ewah_not(struct ewah_bitmap *self) +{ + size_t pointer = 0; + + while (pointer < self->buffer_size) { + eword_t *word = &self->buffer[pointer]; + size_t literals, k; + + rlw_xor_run_bit(word); + ++pointer; + + literals = rlw_get_literal_words(word); + for (k = 0; k < literals; ++k) { + self->buffer[pointer] = ~self->buffer[pointer]; + ++pointer; + } + } +} + +void ewah_xor( + struct ewah_bitmap *ewah_i, + struct ewah_bitmap *ewah_j, + struct ewah_bitmap *out) +{ + struct rlw_iterator rlw_i; + struct rlw_iterator rlw_j; + size_t literals; + + rlwit_init(&rlw_i, ewah_i); + rlwit_init(&rlw_j, ewah_j); + + while (rlwit_word_size(&rlw_i) > 0 && rlwit_word_size(&rlw_j) > 0) { + while (rlw_i.rlw.running_len > 0 || rlw_j.rlw.running_len > 0) { + struct rlw_iterator *prey, *predator; + size_t index; + int negate_words; + + if (rlw_i.rlw.running_len < rlw_j.rlw.running_len) { + prey = &rlw_i; + predator = &rlw_j; + } else { + prey = &rlw_j; + predator = &rlw_i; + } + + negate_words = !!predator->rlw.running_bit; + index = rlwit_discharge(prey, out, + predator->rlw.running_len, negate_words); + + ewah_add_empty_words(out, negate_words, + predator->rlw.running_len - index); + + rlwit_discard_first_words(predator, + predator->rlw.running_len); + } + + literals = min_size( + rlw_i.rlw.literal_words, + rlw_j.rlw.literal_words); + + if (literals) { + size_t k; + + for (k = 0; k < literals; ++k) { + ewah_add(out, + rlw_i.buffer[rlw_i.literal_word_start + k] ^ + rlw_j.buffer[rlw_j.literal_word_start + k] + ); + } + + rlwit_discard_first_words(&rlw_i, literals); + rlwit_discard_first_words(&rlw_j, literals); + } + } + + if (rlwit_word_size(&rlw_i) > 0) + rlwit_discharge(&rlw_i, out, ~0, 0); + else + rlwit_discharge(&rlw_j, out, ~0, 0); + + out->bit_size = max_size(ewah_i->bit_size, ewah_j->bit_size); +} + +void ewah_and( + struct ewah_bitmap *ewah_i, + struct ewah_bitmap *ewah_j, + struct ewah_bitmap *out) +{ + struct rlw_iterator rlw_i; + struct rlw_iterator rlw_j; + size_t literals; + + rlwit_init(&rlw_i, ewah_i); + rlwit_init(&rlw_j, ewah_j); + + while (rlwit_word_size(&rlw_i) > 0 && rlwit_word_size(&rlw_j) > 0) { + while (rlw_i.rlw.running_len > 0 || rlw_j.rlw.running_len > 0) { + struct rlw_iterator *prey, *predator; + + if (rlw_i.rlw.running_len < rlw_j.rlw.running_len) { + prey = &rlw_i; + predator = &rlw_j; + } else { + prey = &rlw_j; + predator = &rlw_i; + } + + if (predator->rlw.running_bit == 0) { + ewah_add_empty_words(out, 0, + predator->rlw.running_len); + rlwit_discard_first_words(prey, + predator->rlw.running_len); + rlwit_discard_first_words(predator, + predator->rlw.running_len); + } else { + size_t index = rlwit_discharge(prey, out, + predator->rlw.running_len, 0); + ewah_add_empty_words(out, 0, + predator->rlw.running_len - index); + rlwit_discard_first_words(predator, + predator->rlw.running_len); + } + } + + literals = min_size( + rlw_i.rlw.literal_words, + rlw_j.rlw.literal_words); + + if (literals) { + size_t k; + + for (k = 0; k < literals; ++k) { + ewah_add(out, + rlw_i.buffer[rlw_i.literal_word_start + k] & + rlw_j.buffer[rlw_j.literal_word_start + k] + ); + } + + rlwit_discard_first_words(&rlw_i, literals); + rlwit_discard_first_words(&rlw_j, literals); + } + } + + if (rlwit_word_size(&rlw_i) > 0) + rlwit_discharge_empty(&rlw_i, out); + else + rlwit_discharge_empty(&rlw_j, out); + + out->bit_size = max_size(ewah_i->bit_size, ewah_j->bit_size); +} + +void ewah_and_not( + struct ewah_bitmap *ewah_i, + struct ewah_bitmap *ewah_j, + struct ewah_bitmap *out) +{ + struct rlw_iterator rlw_i; + struct rlw_iterator rlw_j; + size_t literals; + + rlwit_init(&rlw_i, ewah_i); + rlwit_init(&rlw_j, ewah_j); + + while (rlwit_word_size(&rlw_i) > 0 && rlwit_word_size(&rlw_j) > 0) { + while (rlw_i.rlw.running_len > 0 || rlw_j.rlw.running_len > 0) { + struct rlw_iterator *prey, *predator; + + if (rlw_i.rlw.running_len < rlw_j.rlw.running_len) { + prey = &rlw_i; + predator = &rlw_j; + } else { + prey = &rlw_j; + predator = &rlw_i; + } + + if ((predator->rlw.running_bit && prey == &rlw_i) || + (!predator->rlw.running_bit && prey != &rlw_i)) { + ewah_add_empty_words(out, 0, + predator->rlw.running_len); + rlwit_discard_first_words(prey, + predator->rlw.running_len); + rlwit_discard_first_words(predator, + predator->rlw.running_len); + } else { + size_t index; + int negate_words; + + negate_words = (&rlw_i != prey); + index = rlwit_discharge(prey, out, + predator->rlw.running_len, negate_words); + ewah_add_empty_words(out, negate_words, + predator->rlw.running_len - index); + rlwit_discard_first_words(predator, + predator->rlw.running_len); + } + } + + literals = min_size( + rlw_i.rlw.literal_words, + rlw_j.rlw.literal_words); + + if (literals) { + size_t k; + + for (k = 0; k < literals; ++k) { + ewah_add(out, + rlw_i.buffer[rlw_i.literal_word_start + k] & + ~(rlw_j.buffer[rlw_j.literal_word_start + k]) + ); + } + + rlwit_discard_first_words(&rlw_i, literals); + rlwit_discard_first_words(&rlw_j, literals); + } + } + + if (rlwit_word_size(&rlw_i) > 0) + rlwit_discharge(&rlw_i, out, ~0, 0); + else + rlwit_discharge_empty(&rlw_j, out); + + out->bit_size = max_size(ewah_i->bit_size, ewah_j->bit_size); +} + +void ewah_or( + struct ewah_bitmap *ewah_i, + struct ewah_bitmap *ewah_j, + struct ewah_bitmap *out) +{ + struct rlw_iterator rlw_i; + struct rlw_iterator rlw_j; + size_t literals; + + rlwit_init(&rlw_i, ewah_i); + rlwit_init(&rlw_j, ewah_j); + + while (rlwit_word_size(&rlw_i) > 0 && rlwit_word_size(&rlw_j) > 0) { + while (rlw_i.rlw.running_len > 0 || rlw_j.rlw.running_len > 0) { + struct rlw_iterator *prey, *predator; + + if (rlw_i.rlw.running_len < rlw_j.rlw.running_len) { + prey = &rlw_i; + predator = &rlw_j; + } else { + prey = &rlw_j; + predator = &rlw_i; + } + + if (predator->rlw.running_bit) { + ewah_add_empty_words(out, 0, + predator->rlw.running_len); + rlwit_discard_first_words(prey, + predator->rlw.running_len); + rlwit_discard_first_words(predator, + predator->rlw.running_len); + } else { + size_t index = rlwit_discharge(prey, out, + predator->rlw.running_len, 0); + ewah_add_empty_words(out, 0, + predator->rlw.running_len - index); + rlwit_discard_first_words(predator, + predator->rlw.running_len); + } + } + + literals = min_size( + rlw_i.rlw.literal_words, + rlw_j.rlw.literal_words); + + if (literals) { + size_t k; + + for (k = 0; k < literals; ++k) { + ewah_add(out, + rlw_i.buffer[rlw_i.literal_word_start + k] | + rlw_j.buffer[rlw_j.literal_word_start + k] + ); + } + + rlwit_discard_first_words(&rlw_i, literals); + rlwit_discard_first_words(&rlw_j, literals); + } + } + + if (rlwit_word_size(&rlw_i) > 0) + rlwit_discharge(&rlw_i, out, ~0, 0); + else + rlwit_discharge(&rlw_j, out, ~0, 0); + + out->bit_size = max_size(ewah_i->bit_size, ewah_j->bit_size); +} + + +#define BITMAP_POOL_MAX 16 +static struct ewah_bitmap *bitmap_pool[BITMAP_POOL_MAX]; +static size_t bitmap_pool_size; + +struct ewah_bitmap *ewah_pool_new(void) +{ + if (bitmap_pool_size) + return bitmap_pool[--bitmap_pool_size]; + + return ewah_new(); +} + +void ewah_pool_free(struct ewah_bitmap *self) +{ + if (self == NULL) + return; + + if (bitmap_pool_size == BITMAP_POOL_MAX || + self->alloc_size == 0) { + ewah_free(self); + return; + } + + ewah_clear(self); + bitmap_pool[bitmap_pool_size++] = self; +} + +uint32_t ewah_checksum(struct ewah_bitmap *self) +{ + const uint8_t *p = (uint8_t *)self->buffer; + uint32_t crc = (uint32_t)self->bit_size; + size_t size = self->buffer_size * sizeof(eword_t); + + while (size--) + crc = (crc << 5) - crc + (uint32_t)*p++; + + return crc; +} diff --git a/ewah/ewah_io.c b/ewah/ewah_io.c new file mode 100644 index 0000000000..f7f700ef51 --- /dev/null +++ b/ewah/ewah_io.c @@ -0,0 +1,204 @@ +/** + * Copyright 2013, GitHub, Inc + * Copyright 2009-2013, Daniel Lemire, Cliff Moon, + * David McIntosh, Robert Becho, Google Inc. and Veronika Zenz + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + */ +#include "git-compat-util.h" +#include "ewok.h" + +int ewah_serialize_native(struct ewah_bitmap *self, int fd) +{ + uint32_t write32; + size_t to_write = self->buffer_size * 8; + + /* 32 bit -- bit size for the map */ + write32 = (uint32_t)self->bit_size; + if (write(fd, &write32, 4) != 4) + return -1; + + /** 32 bit -- number of compressed 64-bit words */ + write32 = (uint32_t)self->buffer_size; + if (write(fd, &write32, 4) != 4) + return -1; + + if (write(fd, self->buffer, to_write) != to_write) + return -1; + + /** 32 bit -- position for the RLW */ + write32 = self->rlw - self->buffer; + if (write(fd, &write32, 4) != 4) + return -1; + + return (3 * 4) + to_write; +} + +int ewah_serialize_to(struct ewah_bitmap *self, + int (*write_fun)(void *, const void *, size_t), + void *data) +{ + size_t i; + eword_t dump[2048]; + const size_t words_per_dump = sizeof(dump) / sizeof(eword_t); + uint32_t bitsize, word_count, rlw_pos; + + const eword_t *buffer; + size_t words_left; + + /* 32 bit -- bit size for the map */ + bitsize = htonl((uint32_t)self->bit_size); + if (write_fun(data, &bitsize, 4) != 4) + return -1; + + /** 32 bit -- number of compressed 64-bit words */ + word_count = htonl((uint32_t)self->buffer_size); + if (write_fun(data, &word_count, 4) != 4) + return -1; + + /** 64 bit x N -- compressed words */ + buffer = self->buffer; + words_left = self->buffer_size; + + while (words_left >= words_per_dump) { + for (i = 0; i < words_per_dump; ++i, ++buffer) + dump[i] = htonll(*buffer); + + if (write_fun(data, dump, sizeof(dump)) != sizeof(dump)) + return -1; + + words_left -= words_per_dump; + } + + if (words_left) { + for (i = 0; i < words_left; ++i, ++buffer) + dump[i] = htonll(*buffer); + + if (write_fun(data, dump, words_left * 8) != words_left * 8) + return -1; + } + + /** 32 bit -- position for the RLW */ + rlw_pos = (uint8_t*)self->rlw - (uint8_t *)self->buffer; + rlw_pos = htonl(rlw_pos / sizeof(eword_t)); + + if (write_fun(data, &rlw_pos, 4) != 4) + return -1; + + return (3 * 4) + (self->buffer_size * 8); +} + +static int write_helper(void *fd, const void *buf, size_t len) +{ + return write((intptr_t)fd, buf, len); +} + +int ewah_serialize(struct ewah_bitmap *self, int fd) +{ + return ewah_serialize_to(self, write_helper, (void *)(intptr_t)fd); +} + +int ewah_read_mmap(struct ewah_bitmap *self, void *map, size_t len) +{ + uint8_t *ptr = map; + size_t i; + + self->bit_size = get_be32(ptr); + ptr += sizeof(uint32_t); + + self->buffer_size = self->alloc_size = get_be32(ptr); + ptr += sizeof(uint32_t); + + self->buffer = ewah_realloc(self->buffer, + self->alloc_size * sizeof(eword_t)); + + if (!self->buffer) + return -1; + + /* + * Copy the raw data for the bitmap as a whole chunk; + * if we're in a little-endian platform, we'll perform + * the endianness conversion in a separate pass to ensure + * we're loading 8-byte aligned words. + */ + memcpy(self->buffer, ptr, self->buffer_size * sizeof(uint64_t)); + ptr += self->buffer_size * sizeof(uint64_t); + + for (i = 0; i < self->buffer_size; ++i) + self->buffer[i] = ntohll(self->buffer[i]); + + self->rlw = self->buffer + get_be32(ptr); + + return (3 * 4) + (self->buffer_size * 8); +} + +int ewah_deserialize(struct ewah_bitmap *self, int fd) +{ + size_t i; + eword_t dump[2048]; + const size_t words_per_dump = sizeof(dump) / sizeof(eword_t); + uint32_t bitsize, word_count, rlw_pos; + + eword_t *buffer = NULL; + size_t words_left; + + ewah_clear(self); + + /* 32 bit -- bit size for the map */ + if (read(fd, &bitsize, 4) != 4) + return -1; + + self->bit_size = (size_t)ntohl(bitsize); + + /** 32 bit -- number of compressed 64-bit words */ + if (read(fd, &word_count, 4) != 4) + return -1; + + self->buffer_size = self->alloc_size = (size_t)ntohl(word_count); + self->buffer = ewah_realloc(self->buffer, + self->alloc_size * sizeof(eword_t)); + + if (!self->buffer) + return -1; + + /** 64 bit x N -- compressed words */ + buffer = self->buffer; + words_left = self->buffer_size; + + while (words_left >= words_per_dump) { + if (read(fd, dump, sizeof(dump)) != sizeof(dump)) + return -1; + + for (i = 0; i < words_per_dump; ++i, ++buffer) + *buffer = ntohll(dump[i]); + + words_left -= words_per_dump; + } + + if (words_left) { + if (read(fd, dump, words_left * 8) != words_left * 8) + return -1; + + for (i = 0; i < words_left; ++i, ++buffer) + *buffer = ntohll(dump[i]); + } + + /** 32 bit -- position for the RLW */ + if (read(fd, &rlw_pos, 4) != 4) + return -1; + + self->rlw = self->buffer + ntohl(rlw_pos); + return 0; +} diff --git a/ewah/ewah_rlw.c b/ewah/ewah_rlw.c new file mode 100644 index 0000000000..c723f1aefd --- /dev/null +++ b/ewah/ewah_rlw.c @@ -0,0 +1,115 @@ +/** + * Copyright 2013, GitHub, Inc + * Copyright 2009-2013, Daniel Lemire, Cliff Moon, + * David McIntosh, Robert Becho, Google Inc. and Veronika Zenz + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + */ +#include "git-compat-util.h" +#include "ewok.h" +#include "ewok_rlw.h" + +static inline int next_word(struct rlw_iterator *it) +{ + if (it->pointer >= it->size) + return 0; + + it->rlw.word = &it->buffer[it->pointer]; + it->pointer += rlw_get_literal_words(it->rlw.word) + 1; + + it->rlw.literal_words = rlw_get_literal_words(it->rlw.word); + it->rlw.running_len = rlw_get_running_len(it->rlw.word); + it->rlw.running_bit = rlw_get_run_bit(it->rlw.word); + it->rlw.literal_word_offset = 0; + + return 1; +} + +void rlwit_init(struct rlw_iterator *it, struct ewah_bitmap *from_ewah) +{ + it->buffer = from_ewah->buffer; + it->size = from_ewah->buffer_size; + it->pointer = 0; + + next_word(it); + + it->literal_word_start = rlwit_literal_words(it) + + it->rlw.literal_word_offset; +} + +void rlwit_discard_first_words(struct rlw_iterator *it, size_t x) +{ + while (x > 0) { + size_t discard; + + if (it->rlw.running_len > x) { + it->rlw.running_len -= x; + return; + } + + x -= it->rlw.running_len; + it->rlw.running_len = 0; + + discard = (x > it->rlw.literal_words) ? it->rlw.literal_words : x; + + it->literal_word_start += discard; + it->rlw.literal_words -= discard; + x -= discard; + + if (x > 0 || rlwit_word_size(it) == 0) { + if (!next_word(it)) + break; + + it->literal_word_start = + rlwit_literal_words(it) + it->rlw.literal_word_offset; + } + } +} + +size_t rlwit_discharge( + struct rlw_iterator *it, struct ewah_bitmap *out, size_t max, int negate) +{ + size_t index = 0; + + while (index < max && rlwit_word_size(it) > 0) { + size_t pd, pl = it->rlw.running_len; + + if (index + pl > max) + pl = max - index; + + ewah_add_empty_words(out, it->rlw.running_bit ^ negate, pl); + index += pl; + + pd = it->rlw.literal_words; + if (pd + index > max) + pd = max - index; + + ewah_add_dirty_words(out, + it->buffer + it->literal_word_start, pd, negate); + + rlwit_discard_first_words(it, pd + pl); + index += pd; + } + + return index; +} + +void rlwit_discharge_empty(struct rlw_iterator *it, struct ewah_bitmap *out) +{ + while (rlwit_word_size(it) > 0) { + ewah_add_empty_words(out, 0, rlwit_word_size(it)); + rlwit_discard_first_words(it, rlwit_word_size(it)); + } +} diff --git a/ewah/ewok.h b/ewah/ewok.h new file mode 100644 index 0000000000..43adeb5c68 --- /dev/null +++ b/ewah/ewok.h @@ -0,0 +1,233 @@ +/** + * Copyright 2013, GitHub, Inc + * Copyright 2009-2013, Daniel Lemire, Cliff Moon, + * David McIntosh, Robert Becho, Google Inc. and Veronika Zenz + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + */ +#ifndef __EWOK_BITMAP_H__ +#define __EWOK_BITMAP_H__ + +#ifndef ewah_malloc +# define ewah_malloc xmalloc +#endif +#ifndef ewah_realloc +# define ewah_realloc xrealloc +#endif +#ifndef ewah_calloc +# define ewah_calloc xcalloc +#endif + +typedef uint64_t eword_t; +#define BITS_IN_WORD (sizeof(eword_t) * 8) + +/** + * Do not use __builtin_popcountll. The GCC implementation + * is notoriously slow on all platforms. + * + * See: http://gcc.gnu.org/bugzilla/show_bug.cgi?id=36041 + */ +static inline uint32_t ewah_bit_popcount64(uint64_t x) +{ + x = (x & 0x5555555555555555ULL) + ((x >> 1) & 0x5555555555555555ULL); + x = (x & 0x3333333333333333ULL) + ((x >> 2) & 0x3333333333333333ULL); + x = (x & 0x0F0F0F0F0F0F0F0FULL) + ((x >> 4) & 0x0F0F0F0F0F0F0F0FULL); + return (x * 0x0101010101010101ULL) >> 56; +} + +#ifdef __GNUC__ +#define ewah_bit_ctz64(x) __builtin_ctzll(x) +#else +static inline int ewah_bit_ctz64(uint64_t x) +{ + int n = 0; + if ((x & 0xffffffff) == 0) { x >>= 32; n += 32; } + if ((x & 0xffff) == 0) { x >>= 16; n += 16; } + if ((x & 0xff) == 0) { x >>= 8; n += 8; } + if ((x & 0xf) == 0) { x >>= 4; n += 4; } + if ((x & 0x3) == 0) { x >>= 2; n += 2; } + if ((x & 0x1) == 0) { x >>= 1; n += 1; } + return n + !x; +} +#endif + +struct ewah_bitmap { + eword_t *buffer; + size_t buffer_size; + size_t alloc_size; + size_t bit_size; + eword_t *rlw; +}; + +typedef void (*ewah_callback)(size_t pos, void *); + +struct ewah_bitmap *ewah_pool_new(void); +void ewah_pool_free(struct ewah_bitmap *self); + +/** + * Allocate a new EWAH Compressed bitmap + */ +struct ewah_bitmap *ewah_new(void); + +/** + * Clear all the bits in the bitmap. Does not free or resize + * memory. + */ +void ewah_clear(struct ewah_bitmap *self); + +/** + * Free all the memory of the bitmap + */ +void ewah_free(struct ewah_bitmap *self); + +int ewah_serialize_to(struct ewah_bitmap *self, + int (*write_fun)(void *out, const void *buf, size_t len), + void *out); +int ewah_serialize(struct ewah_bitmap *self, int fd); +int ewah_serialize_native(struct ewah_bitmap *self, int fd); + +int ewah_deserialize(struct ewah_bitmap *self, int fd); +int ewah_read_mmap(struct ewah_bitmap *self, void *map, size_t len); +int ewah_read_mmap_native(struct ewah_bitmap *self, void *map, size_t len); + +uint32_t ewah_checksum(struct ewah_bitmap *self); + +/** + * Logical not (bitwise negation) in-place on the bitmap + * + * This operation is linear time based on the size of the bitmap. + */ +void ewah_not(struct ewah_bitmap *self); + +/** + * Call the given callback with the position of every single bit + * that has been set on the bitmap. + * + * This is an efficient operation that does not fully decompress + * the bitmap. + */ +void ewah_each_bit(struct ewah_bitmap *self, ewah_callback callback, void *payload); + +/** + * Set a given bit on the bitmap. + * + * The bit at position `pos` will be set to true. Because of the + * way that the bitmap is compressed, a set bit cannot be unset + * later on. + * + * Furthermore, since the bitmap uses streaming compression, bits + * can only set incrementally. + * + * E.g. + * ewah_set(bitmap, 1); // ok + * ewah_set(bitmap, 76); // ok + * ewah_set(bitmap, 77); // ok + * ewah_set(bitmap, 8712800127); // ok + * ewah_set(bitmap, 25); // failed, assert raised + */ +void ewah_set(struct ewah_bitmap *self, size_t i); + +struct ewah_iterator { + const eword_t *buffer; + size_t buffer_size; + + size_t pointer; + eword_t compressed, literals; + eword_t rl, lw; + int b; +}; + +/** + * Initialize a new iterator to run through the bitmap in uncompressed form. + * + * The iterator can be stack allocated. The underlying bitmap must not be freed + * before the iteration is over. + * + * E.g. + * + * struct ewah_bitmap *bitmap = ewah_new(); + * struct ewah_iterator it; + * + * ewah_iterator_init(&it, bitmap); + */ +void ewah_iterator_init(struct ewah_iterator *it, struct ewah_bitmap *parent); + +/** + * Yield every single word in the bitmap in uncompressed form. This is: + * yield single words (32-64 bits) where each bit represents an actual + * bit from the bitmap. + * + * Return: true if a word was yield, false if there are no words left + */ +int ewah_iterator_next(eword_t *next, struct ewah_iterator *it); + +void ewah_or( + struct ewah_bitmap *ewah_i, + struct ewah_bitmap *ewah_j, + struct ewah_bitmap *out); + +void ewah_and_not( + struct ewah_bitmap *ewah_i, + struct ewah_bitmap *ewah_j, + struct ewah_bitmap *out); + +void ewah_xor( + struct ewah_bitmap *ewah_i, + struct ewah_bitmap *ewah_j, + struct ewah_bitmap *out); + +void ewah_and( + struct ewah_bitmap *ewah_i, + struct ewah_bitmap *ewah_j, + struct ewah_bitmap *out); + +/** + * Direct word access + */ +size_t ewah_add_empty_words(struct ewah_bitmap *self, int v, size_t number); +void ewah_add_dirty_words( + struct ewah_bitmap *self, const eword_t *buffer, size_t number, int negate); +size_t ewah_add(struct ewah_bitmap *self, eword_t word); + + +/** + * Uncompressed, old-school bitmap that can be efficiently compressed + * into an `ewah_bitmap`. + */ +struct bitmap { + eword_t *words; + size_t word_alloc; +}; + +struct bitmap *bitmap_new(void); +void bitmap_set(struct bitmap *self, size_t pos); +void bitmap_clear(struct bitmap *self, size_t pos); +int bitmap_get(struct bitmap *self, size_t pos); +void bitmap_reset(struct bitmap *self); +void bitmap_free(struct bitmap *self); +int bitmap_equals(struct bitmap *self, struct bitmap *other); +int bitmap_is_subset(struct bitmap *self, struct bitmap *super); + +struct ewah_bitmap * bitmap_to_ewah(struct bitmap *bitmap); +struct bitmap *ewah_to_bitmap(struct ewah_bitmap *ewah); + +void bitmap_and_not(struct bitmap *self, struct bitmap *other); +void bitmap_or_ewah(struct bitmap *self, struct ewah_bitmap *other); +void bitmap_or(struct bitmap *self, const struct bitmap *other); + +void bitmap_each_bit(struct bitmap *self, ewah_callback callback, void *data); +size_t bitmap_popcount(struct bitmap *self); + +#endif diff --git a/ewah/ewok_rlw.h b/ewah/ewok_rlw.h new file mode 100644 index 0000000000..63efdf9698 --- /dev/null +++ b/ewah/ewok_rlw.h @@ -0,0 +1,114 @@ +/** + * Copyright 2013, GitHub, Inc + * Copyright 2009-2013, Daniel Lemire, Cliff Moon, + * David McIntosh, Robert Becho, Google Inc. and Veronika Zenz + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + */ +#ifndef __EWOK_RLW_H__ +#define __EWOK_RLW_H__ + +#define RLW_RUNNING_BITS (sizeof(eword_t) * 4) +#define RLW_LITERAL_BITS (sizeof(eword_t) * 8 - 1 - RLW_RUNNING_BITS) + +#define RLW_LARGEST_RUNNING_COUNT (((eword_t)1 << RLW_RUNNING_BITS) - 1) +#define RLW_LARGEST_LITERAL_COUNT (((eword_t)1 << RLW_LITERAL_BITS) - 1) + +#define RLW_LARGEST_RUNNING_COUNT_SHIFT (RLW_LARGEST_RUNNING_COUNT << 1) + +#define RLW_RUNNING_LEN_PLUS_BIT (((eword_t)1 << (RLW_RUNNING_BITS + 1)) - 1) + +static int rlw_get_run_bit(const eword_t *word) +{ + return *word & (eword_t)1; +} + +static inline void rlw_set_run_bit(eword_t *word, int b) +{ + if (b) { + *word |= (eword_t)1; + } else { + *word &= (eword_t)(~1); + } +} + +static inline void rlw_xor_run_bit(eword_t *word) +{ + if (*word & 1) { + *word &= (eword_t)(~1); + } else { + *word |= (eword_t)1; + } +} + +static inline void rlw_set_running_len(eword_t *word, eword_t l) +{ + *word |= RLW_LARGEST_RUNNING_COUNT_SHIFT; + *word &= (l << 1) | (~RLW_LARGEST_RUNNING_COUNT_SHIFT); +} + +static inline eword_t rlw_get_running_len(const eword_t *word) +{ + return (*word >> 1) & RLW_LARGEST_RUNNING_COUNT; +} + +static inline eword_t rlw_get_literal_words(const eword_t *word) +{ + return *word >> (1 + RLW_RUNNING_BITS); +} + +static inline void rlw_set_literal_words(eword_t *word, eword_t l) +{ + *word |= ~RLW_RUNNING_LEN_PLUS_BIT; + *word &= (l << (RLW_RUNNING_BITS + 1)) | RLW_RUNNING_LEN_PLUS_BIT; +} + +static inline eword_t rlw_size(const eword_t *self) +{ + return rlw_get_running_len(self) + rlw_get_literal_words(self); +} + +struct rlw_iterator { + const eword_t *buffer; + size_t size; + size_t pointer; + size_t literal_word_start; + + struct { + const eword_t *word; + int literal_words; + int running_len; + int literal_word_offset; + int running_bit; + } rlw; +}; + +void rlwit_init(struct rlw_iterator *it, struct ewah_bitmap *bitmap); +void rlwit_discard_first_words(struct rlw_iterator *it, size_t x); +size_t rlwit_discharge( + struct rlw_iterator *it, struct ewah_bitmap *out, size_t max, int negate); +void rlwit_discharge_empty(struct rlw_iterator *it, struct ewah_bitmap *out); + +static inline size_t rlwit_word_size(struct rlw_iterator *it) +{ + return it->rlw.running_len + it->rlw.literal_words; +} + +static inline size_t rlwit_literal_words(struct rlw_iterator *it) +{ + return it->pointer - it->rlw.literal_words; +} + +#endif diff --git a/fetch-pack.c b/fetch-pack.c index 90fdd49821..f061f1fe85 100644 --- a/fetch-pack.c +++ b/fetch-pack.c @@ -439,7 +439,8 @@ done: } strbuf_release(&req_buf); - consume_shallow_list(args, fd[0]); + if (!got_ready || !no_done) + consume_shallow_list(args, fd[0]); while (flushes || multi_ack) { int ack = get_ack(fd[0], result_sha1); if (ack) { @@ -4,6 +4,7 @@ SUBDIRECTORY_OK=Yes OPTIONS_KEEPDASHDASH= +OPTIONS_STUCKLONG=t OPTIONS_SPEC="\ git am [options] [(<mbox>|<Maildir>)...] git am [options] (--continue | --skip | --abort) @@ -37,6 +38,7 @@ abort restore the original branch and abort the patching operation. committer-date-is-author-date lie about committer date ignore-date use current timestamp for author date rerere-autoupdate update the index with reused conflict resolution if possible +S,gpg-sign? GPG-sign commits rebasing* (internal use for git-rebase)" . git-sh-setup @@ -374,6 +376,7 @@ git_apply_opt= committer_date_is_author_date= ignore_date= allow_rerere_autoupdate= +gpg_sign_opt= if test "$(git config --bool --get am.keepcr)" = true then @@ -413,14 +416,14 @@ it will be removed. Please do not use it anymore." abort=t ;; --rebasing) rebasing=t threeway=t ;; - --resolvemsg) - shift; resolvemsg=$1 ;; - --whitespace|--directory|--exclude|--include) - git_apply_opt="$git_apply_opt $(sq "$1=$2")"; shift ;; - -C|-p) - git_apply_opt="$git_apply_opt $(sq "$1$2")"; shift ;; - --patch-format) - shift ; patch_format="$1" ;; + --resolvemsg=*) + resolvemsg="${1#--resolvemsg=}" ;; + --whitespace=*|--directory=*|--exclude=*|--include=*) + git_apply_opt="$git_apply_opt $(sq "$1")" ;; + -C*|-p*) + git_apply_opt="$git_apply_opt $(sq "$1")" ;; + --patch-format=*) + patch_format="${1#--patch-format=}" ;; --reject|--ignore-whitespace|--ignore-space-change) git_apply_opt="$git_apply_opt $1" ;; --committer-date-is-author-date) @@ -435,6 +438,10 @@ it will be removed. Please do not use it anymore." keepcr=t ;; --no-keep-cr) keepcr=f ;; + --gpg-sign) + gpg_sign_opt=-S ;; + --gpg-sign=*) + gpg_sign_opt="-S${1#--gpg-sign=}" ;; --) shift; break ;; *) @@ -899,7 +906,8 @@ did you forget to use 'git add'?" GIT_COMMITTER_DATE="$GIT_AUTHOR_DATE" export GIT_COMMITTER_DATE fi && - git commit-tree $tree ${parent:+-p} $parent <"$dotest/final-commit" + git commit-tree ${parent:+-p} $parent ${gpg_sign_opt:+"$gpg_sign_opt"} $tree \ + <"$dotest/final-commit" ) && git update-ref -m "$GIT_REFLOG_ACTION: $FIRSTLINE" HEAD $commit $parent || stop_here $this diff --git a/git-compat-util.h b/git-compat-util.h index eaee4381f2..585ef8a79b 100644 --- a/git-compat-util.h +++ b/git-compat-util.h @@ -339,9 +339,7 @@ extern void set_error_routine(void (*routine)(const char *err, va_list params)); extern void set_die_is_recursing_routine(int (*routine)(void)); extern int starts_with(const char *str, const char *prefix); -extern int prefixcmp(const char *str, const char *prefix); extern int ends_with(const char *str, const char *suffix); -extern int suffixcmp(const char *str, const char *suffix); static inline const char *skip_prefix(const char *str, const char *prefix) { @@ -468,9 +466,15 @@ extern FILE *git_fopen(const char*, const char*); #endif #ifdef SNPRINTF_RETURNS_BOGUS +#ifdef snprintf +#undef snprintf +#endif #define snprintf git_snprintf extern int git_snprintf(char *str, size_t maxsize, const char *format, ...); +#ifdef vsnprintf +#undef vsnprintf +#endif #define vsnprintf git_vsnprintf extern int git_vsnprintf(char *str, size_t maxsize, const char *format, va_list ap); diff --git a/git-instaweb.sh b/git-instaweb.sh index e93a238675..4aa3eb80fd 100755 --- a/git-instaweb.sh +++ b/git-instaweb.sh @@ -5,6 +5,7 @@ PERL='@@PERL@@' OPTIONS_KEEPDASHDASH= +OPTIONS_STUCKLONG= OPTIONS_SPEC="\ git instaweb [options] (--start | --stop | --restart) -- diff --git a/git-pull.sh b/git-pull.sh index 0a5aa2c821..6cd8ebc534 100755 --- a/git-pull.sh +++ b/git-pull.sh @@ -4,7 +4,7 @@ # # Fetch one or more remote refs and merge it/them into the current HEAD. -USAGE='[-n | --no-stat] [--[no-]commit] [--[no-]squash] [--[no-]ff] [--[no-]rebase|--rebase=preserve] [-s strategy]... [<fetch-options>] <repo> <head>...' +USAGE='[-n | --no-stat] [--[no-]commit] [--[no-]squash] [--[no-]ff|--ff-only] [--[no-]rebase|--rebase=preserve] [-s strategy]... [<fetch-options>] <repo> <head>...' LONG_USAGE='Fetch one or more remote refs and integrate it/them with the current HEAD.' SUBDIRECTORY_OK=Yes OPTIONS_SPEC= @@ -52,6 +52,21 @@ if test -z "$rebase" then rebase=$(bool_or_string_config pull.rebase) fi + +# Setup default fast-forward options via `pull.ff` +pull_ff=$(git config pull.ff) +case "$pull_ff" in +false) + no_ff=--no-ff + break + ;; +only) + ff_only=--ff-only + break + ;; +esac + + dry_run= while : do @@ -138,6 +153,15 @@ do --no-verify-signatures) verify_signatures=--no-verify-signatures ;; + --gpg-sign|-S) + gpg_sign_args=-S + ;; + --gpg-sign=*) + gpg_sign_args=$(git rev-parse --sq-quote "-S${1#--gpg-sign=}") + ;; + -S*) + gpg_sign_args=$(git rev-parse --sq-quote "$1") + ;; --d|--dr|--dry|--dry-|--dry-r|--dry-ru|--dry-run) dry_run=--dry-run ;; @@ -305,11 +329,13 @@ merge_name=$(git fmt-merge-msg $log_arg <"$GIT_DIR/FETCH_HEAD") || exit case "$rebase" in true) eval="git-rebase $diffstat $strategy_args $merge_args $rebase_args $verbosity" + eval="$eval $gpg_sign_args" eval="$eval --onto $merge_head ${oldremoteref:-$merge_head}" ;; *) eval="git-merge $diffstat $no_commit $verify_signatures $edit $squash $no_ff $ff_only" - eval="$eval $log_arg $strategy_args $merge_args $verbosity $progress" + eval="$eval $log_arg $strategy_args $merge_args $verbosity $progress" + eval="$eval $gpg_sign_args" eval="$eval \"\$merge_name\" HEAD $merge_head" ;; esac diff --git a/git-quiltimport.sh b/git-quiltimport.sh index 8e17525dd8..167d79fea8 100755 --- a/git-quiltimport.sh +++ b/git-quiltimport.sh @@ -1,5 +1,6 @@ #!/bin/sh OPTIONS_KEEPDASHDASH= +OPTIONS_STUCKLONG= OPTIONS_SPEC="\ git quiltimport [options] -- diff --git a/git-rebase--am.sh b/git-rebase--am.sh index a4f683a5d7..df46f4ca96 100644 --- a/git-rebase--am.sh +++ b/git-rebase--am.sh @@ -6,7 +6,8 @@ case "$action" in continue) - git am --resolved --resolvemsg="$resolvemsg" && + git am --resolved --resolvemsg="$resolvemsg" \ + ${gpg_sign_opt:+"$gpg_sign_opt"} && move_to_original_branch return ;; @@ -26,7 +27,7 @@ then # empty commits and even if it didn't the format doesn't really lend # itself well to recording empty patches. fortunately, cherry-pick # makes this easy - git cherry-pick --allow-empty "$revisions" + git cherry-pick ${gpg_sign_opt:+"$gpg_sign_opt"} --allow-empty "$revisions" ret=$? else rm -f "$GIT_DIR/rebased-patches" @@ -60,7 +61,8 @@ else return $? fi - git am $git_am_opt --rebasing --resolvemsg="$resolvemsg" <"$GIT_DIR/rebased-patches" + git am $git_am_opt --rebasing --resolvemsg="$resolvemsg" \ + ${gpg_sign_opt:+"$gpg_sign_opt"} <"$GIT_DIR/rebased-patches" ret=$? rm -f "$GIT_DIR/rebased-patches" diff --git a/git-rebase--interactive.sh b/git-rebase--interactive.sh index 43c19e0829..a1adae8313 100644 --- a/git-rebase--interactive.sh +++ b/git-rebase--interactive.sh @@ -179,9 +179,10 @@ exit_with_patch () { echo "$1" > "$state_dir"/stopped-sha make_patch $1 git rev-parse --verify HEAD > "$amend" + gpg_sign_opt_quoted=${gpg_sign_opt:+$(git rev-parse --sq-quote "$gpg_sign_opt")} warn "You can amend the commit now, with" warn - warn " git commit --amend" + warn " git commit --amend $gpg_sign_opt_quoted" warn warn "Once you are satisfied with your changes, run" warn @@ -248,7 +249,9 @@ pick_one () { test -d "$rewritten" && pick_one_preserving_merges "$@" && return - output eval git cherry-pick "$strategy_args" $empty_args $ff "$@" + output eval git cherry-pick \ + ${gpg_sign_opt:+$(git rev-parse --sq-quote "$gpg_sign_opt")} \ + "$strategy_args" $empty_args $ff "$@" } pick_one_preserving_merges () { @@ -351,7 +354,8 @@ pick_one_preserving_merges () { new_parents=${new_parents# $first_parent} merge_args="--no-log --no-ff" if ! do_with_author output eval \ - 'git merge $merge_args $strategy_args -m "$msg_content" $new_parents' + 'git merge ${gpg_sign_opt:+"$gpg_sign_opt"} \ + $merge_args $strategy_args -m "$msg_content" $new_parents' then printf "%s\n" "$msg_content" > "$GIT_DIR"/MERGE_MSG die_with_patch $sha1 "Error redoing merge $sha1" @@ -359,7 +363,9 @@ pick_one_preserving_merges () { echo "$sha1 $(git rev-parse HEAD^0)" >> "$rewritten_list" ;; *) - output eval git cherry-pick "$strategy_args" "$@" || + output eval git cherry-pick \ + ${gpg_sign_opt:+$(git rev-parse --sq-quote "$gpg_sign_opt")} \ + "$strategy_args" "$@" || die_with_patch $sha1 "Could not pick $sha1" ;; esac @@ -470,7 +476,8 @@ do_pick () { --no-post-rewrite -n -q -C $1 && pick_one -n $1 && git commit --allow-empty --allow-empty-message \ - --amend --no-post-rewrite -n -q -C $1 || + --amend --no-post-rewrite -n -q -C $1 \ + ${gpg_sign_opt:+"$gpg_sign_opt"} || die_with_patch $1 "Could not apply $1... $2" else pick_one $1 || @@ -497,7 +504,7 @@ do_next () { mark_action_done do_pick $sha1 "$rest" - git commit --amend --no-post-rewrite || { + git commit --amend --no-post-rewrite ${gpg_sign_opt:+"$gpg_sign_opt"} || { warn "Could not amend commit after successfully picking $sha1... $rest" warn "This is most likely due to an empty commit message, or the pre-commit hook" warn "failed. If the pre-commit hook failed, you may need to resolve the issue before" @@ -542,19 +549,22 @@ do_next () { squash|s|fixup|f) # This is an intermediate commit; its message will only be # used in case of trouble. So use the long version: - do_with_author output git commit --amend --no-verify -F "$squash_msg" || + do_with_author output git commit --amend --no-verify -F "$squash_msg" \ + ${gpg_sign_opt:+"$gpg_sign_opt"} || die_failed_squash $sha1 "$rest" ;; *) # This is the final command of this squash/fixup group if test -f "$fixup_msg" then - do_with_author git commit --amend --no-verify -F "$fixup_msg" || + do_with_author git commit --amend --no-verify -F "$fixup_msg" \ + ${gpg_sign_opt:+"$gpg_sign_opt"} || die_failed_squash $sha1 "$rest" else cp "$squash_msg" "$GIT_DIR"/SQUASH_MSG || exit rm -f "$GIT_DIR"/MERGE_MSG - do_with_author git commit --amend --no-verify -F "$GIT_DIR"/SQUASH_MSG -e || + do_with_author git commit --amend --no-verify -F "$GIT_DIR"/SQUASH_MSG -e \ + ${gpg_sign_opt:+"$gpg_sign_opt"} || die_failed_squash $sha1 "$rest" fi rm -f "$squash_msg" "$fixup_msg" @@ -819,14 +829,15 @@ continue) else if ! test -f "$author_script" then + gpg_sign_opt_quoted=${gpg_sign_opt:+$(git rev-parse --sq-quote "$gpg_sign_opt")} die "You have staged changes in your working tree. If these changes are meant to be squashed into the previous commit, run: - git commit --amend + git commit --amend $gpg_sign_opt_quoted If they are meant to go into a new commit, run: - git commit + git commit $gpg_sign_opt_quoted In both case, once you're done, continue with: @@ -842,10 +853,12 @@ In both case, once you're done, continue with: die "\ You have uncommitted changes in your working tree. Please, commit them first and then run 'git rebase --continue' again." - do_with_author git commit --amend --no-verify -F "$msg" -e || + do_with_author git commit --amend --no-verify -F "$msg" -e \ + ${gpg_sign_opt:+"$gpg_sign_opt"} || die "Could not commit staged changes." else - do_with_author git commit --no-verify -F "$msg" -e || + do_with_author git commit --no-verify -F "$msg" -e \ + ${gpg_sign_opt:+"$gpg_sign_opt"} || die "Could not commit staged changes." fi fi diff --git a/git-rebase--merge.sh b/git-rebase--merge.sh index e7d96de9ad..5381857c59 100644 --- a/git-rebase--merge.sh +++ b/git-rebase--merge.sh @@ -27,7 +27,7 @@ continue_merge () { cmt=`cat "$state_dir/current"` if ! git diff-index --quiet --ignore-submodules HEAD -- then - if ! git commit --no-verify -C "$cmt" + if ! git commit ${gpg_sign_opt:+"$gpg_sign_opt"} --no-verify -C "$cmt" then echo "Commit failed, please do not call \"git commit\"" echo "directly, but instead do one of the following: " diff --git a/git-rebase.sh b/git-rebase.sh index 8a3efa2983..5f6732bf3d 100755 --- a/git-rebase.sh +++ b/git-rebase.sh @@ -5,6 +5,7 @@ SUBDIRECTORY_OK=Yes OPTIONS_KEEPDASHDASH= +OPTIONS_STUCKLONG=t OPTIONS_SPEC="\ git rebase [-i] [options] [--exec <cmd>] [--onto <newbase>] [<upstream>] [<branch>] git rebase [-i] [options] [--exec <cmd>] [--onto <newbase>] --root [<branch>] @@ -36,6 +37,7 @@ ignore-date! passed to 'git am' whitespace=! passed to 'git apply' ignore-whitespace! passed to 'git apply' C=! passed to 'git apply' +S,gpg-sign? GPG-sign commits Actions: continue! continue abort! abort and check out the original branch @@ -84,6 +86,7 @@ preserve_merges= autosquash= keep_empty= test "$(git config --bool rebase.autosquash)" = "true" && autosquash=t +gpg_sign_opt= read_basic_state () { test -f "$state_dir/head-name" && @@ -106,6 +109,8 @@ read_basic_state () { strategy_opts="$(cat "$state_dir"/strategy_opts)" test -f "$state_dir"/allow_rerere_autoupdate && allow_rerere_autoupdate="$(cat "$state_dir"/allow_rerere_autoupdate)" + test -f "$state_dir"/gpg_sign_opt && + gpg_sign_opt="$(cat "$state_dir"/gpg_sign_opt)" } write_basic_state () { @@ -119,6 +124,7 @@ write_basic_state () { "$state_dir"/strategy_opts test -n "$allow_rerere_autoupdate" && echo "$allow_rerere_autoupdate" > \ "$state_dir"/allow_rerere_autoupdate + test -n "$gpg_sign_opt" && echo "$gpg_sign_opt" > "$state_dir"/gpg_sign_opt } output () { @@ -236,23 +242,19 @@ do test $total_argc -eq 2 || usage action=${1##--} ;; - --onto) - test 2 -le "$#" || usage - onto="$2" - shift + --onto=*) + onto="${1#--onto=}" ;; - -x) - test 2 -le "$#" || usage - cmd="${cmd}exec $2${LF}" - shift + --exec=*) + cmd="${cmd}exec ${1#--exec=}${LF}" ;; - -i) + --interactive) interactive_rebase=explicit ;; - -k) + --keep-empty) keep_empty=yes ;; - -p) + --preserve-merges) preserve_merges=t test -z "$interactive_rebase" && interactive_rebase=implied ;; @@ -268,21 +270,19 @@ do --no-fork-point) fork_point= ;; - -M|-m) + --merge) do_merge=t ;; - -X) - shift - strategy_opts="$strategy_opts $(git rev-parse --sq-quote "--$1")" + --strategy-option=*) + strategy_opts="$strategy_opts $(git rev-parse --sq-quote "--${1#--strategy-option=}")" do_merge=t test -z "$strategy" && strategy=recursive ;; - -s) - shift - strategy="$1" + --strategy=*) + strategy="${1#--strategy=}" do_merge=t ;; - -n) + --no-stat) diffstat= ;; --stat) @@ -291,21 +291,20 @@ do --autostash) autostash=true ;; - -v) + --verbose) verbose=t diffstat=t GIT_QUIET= ;; - -q) + --quiet) GIT_QUIET=t git_am_opt="$git_am_opt -q" verbose= diffstat= ;; - --whitespace) - shift - git_am_opt="$git_am_opt --whitespace=$1" - case "$1" in + --whitespace=*) + git_am_opt="$git_am_opt --whitespace=${1#--whitespace=}" + case "${1#--whitespace=}" in fix|strip) force_rebase=t ;; @@ -318,19 +317,24 @@ do git_am_opt="$git_am_opt $1" force_rebase=t ;; - -C) - shift - git_am_opt="$git_am_opt -C$1" + -C*) + git_am_opt="$git_am_opt $1" ;; --root) rebase_root=t ;; - -f|--no-ff) + --force-rebase|--no-ff) force_rebase=t ;; --rerere-autoupdate|--no-rerere-autoupdate) allow_rerere_autoupdate="$1" ;; + --gpg-sign) + gpg_sign_opt=-S + ;; + --gpg-sign=*) + gpg_sign_opt="-S${1#--gpg-sign=}" + ;; --) shift break diff --git a/git-request-pull.sh b/git-request-pull.sh index fe21d5db63..cf4f1505a5 100755 --- a/git-request-pull.sh +++ b/git-request-pull.sh @@ -9,6 +9,7 @@ LONG_USAGE='Summarizes the changes between two commits to the standard output, and includes the given URL in the generated summary.' SUBDIRECTORY_OK='Yes' OPTIONS_KEEPDASHDASH= +OPTIONS_STUCKLONG= OPTIONS_SPEC='git request-pull [options] start url [end] -- p show patch text as well diff --git a/git-sh-setup.sh b/git-sh-setup.sh index fffa3c72d7..5f28b32dc7 100644 --- a/git-sh-setup.sh +++ b/git-sh-setup.sh @@ -72,6 +72,8 @@ if test -n "$OPTIONS_SPEC"; then parseopt_extra= [ -n "$OPTIONS_KEEPDASHDASH" ] && parseopt_extra="--keep-dashdash" + [ -n "$OPTIONS_STUCKLONG" ] && + parseopt_extra="$parseopt_extra --stuck-long" eval "$( echo "$OPTIONS_SPEC" | diff --git a/git-submodule.sh b/git-submodule.sh index 4a30087768..a33f68d27c 100755 --- a/git-submodule.sh +++ b/git-submodule.sh @@ -241,6 +241,15 @@ module_name() # # Clone a submodule # +# $1 = submodule path +# $2 = submodule name +# $3 = URL to clone +# $4 = reference repository to reuse (empty for independent) +# $5 = depth argument for shallow clones (empty for deep) +# $6 = (remote-tracking) starting point for the local branch (empty for HEAD) +# $7 = local branch to create (empty for a detached HEAD, unless $6 is +# also empty, in which case the local branch is left unchanged) +# # Prior to calling, cmd_update checks that a possibly existing # path is not a git repository. # Likewise, cmd_add checks that path does not exist at all, @@ -253,6 +262,8 @@ module_clone() url=$3 reference="$4" depth="$5" + start_point="$6" + local_branch="$7" quiet= if test -n "$GIT_QUIET" then @@ -306,7 +317,16 @@ module_clone() echo "gitdir: $rel/$a" >"$sm_path/.git" rel=$(echo $a | sed -e 's|[^/][^/]*|..|g') - (clear_local_git_env; cd "$sm_path" && GIT_WORK_TREE=. git config core.worktree "$rel/$b") + ( + clear_local_git_env + cd "$sm_path" && + GIT_WORK_TREE=. git config core.worktree "$rel/$b" && + # ash fails to wordsplit ${local_branch:+-B "$local_branch"...} + case "$local_branch" in + '') git checkout -f -q ${start_point:+"$start_point"} ;; + ?*) git checkout -f -q -B "$local_branch" ${start_point:+"$start_point"} ;; + esac + ) || die "$(eval_gettext "Unable to setup cloned submodule '\$sm_path'")" } isnumber() @@ -469,16 +489,15 @@ Use -f if you really want to add it." >&2 echo "$(eval_gettext "Reactivating local git directory for submodule '\$sm_name'.")" fi fi - module_clone "$sm_path" "$sm_name" "$realrepo" "$reference" "$depth" || exit - ( - clear_local_git_env - cd "$sm_path" && - # ash fails to wordsplit ${branch:+-b "$branch"...} - case "$branch" in - '') git checkout -f -q ;; - ?*) git checkout -f -q -B "$branch" "origin/$branch" ;; - esac - ) || die "$(eval_gettext "Unable to checkout submodule '\$sm_path'")" + if test -n "$branch" + then + start_point="origin/$branch" + local_branch="$branch" + else + start_point="" + local_branch="" + fi + module_clone "$sm_path" "$sm_name" "$realrepo" "$reference" "$depth" "$start_point" "$local_branch" || exit fi git config submodule."$sm_name".url "$realrepo" @@ -799,32 +818,35 @@ cmd_update() fi name=$(module_name "$sm_path") || exit url=$(git config submodule."$name".url) - branch=$(get_submodule_config "$name" branch master) + config_branch=$(get_submodule_config "$name" branch) + branch="${config_branch:-master}" + local_branch="$branch" if ! test -z "$update" then update_module=$update else update_module=$(git config submodule."$name".update) - case "$update_module" in - '') - ;; # Unset update mode - checkout | rebase | merge | none) - ;; # Known update modes - !*) - ;; # Custom update command - *) - die "$(eval_gettext "Invalid update mode '$update_module' for submodule '$name'")" - ;; - esac + if test -z "$update_module" + then + update_module="checkout" + fi fi displaypath=$(relative_path "$prefix$sm_path") - if test "$update_module" = "none" - then + case "$update_module" in + none) echo "Skipping submodule '$displaypath'" continue - fi + ;; + checkout) + local_branch="" + ;; + rebase | merge | !*) + ;; + *) + die "$(eval_gettext "Invalid update mode '$update_module' for submodule '$name'")" + esac if test -z "$url" then @@ -838,7 +860,8 @@ Maybe you want to use 'update --init'?")" if ! test -d "$sm_path"/.git -o -f "$sm_path"/.git then - module_clone "$sm_path" "$name" "$url" "$reference" "$depth" || exit + start_point="origin/${branch}" + module_clone "$sm_path" "$name" "$url" "$reference" "$depth" "$start_point" "$local_branch" || exit cloned_modules="$cloned_modules;$name" subsha1= else @@ -884,11 +907,16 @@ Maybe you want to use 'update --init'?")" case ";$cloned_modules;" in *";$name;"*) # then there is no local change to integrate - update_module= ;; + update_module='!git reset --hard -q' esac must_die_on_failure= case "$update_module" in + checkout) + command="git checkout $subforce -q" + die_msg="$(eval_gettext "Unable to checkout '\$sha1' in submodule path '\$displaypath'")" + say_msg="$(eval_gettext "Submodule path '\$displaypath': checked out '\$sha1'")" + ;; rebase) command="git rebase" die_msg="$(eval_gettext "Unable to rebase '\$sha1' in submodule path '\$displaypath'")" @@ -908,10 +936,7 @@ Maybe you want to use 'update --init'?")" must_die_on_failure=yes ;; *) - command="git checkout $subforce -q" - die_msg="$(eval_gettext "Unable to checkout '\$sha1' in submodule path '\$displaypath'")" - say_msg="$(eval_gettext "Submodule path '\$displaypath': checked out '\$sha1'")" - ;; + die "$(eval_gettext "Invalid update mode '$update_module' for submodule '$name'")" esac if (clear_local_git_env; cd "$sm_path" && $command "$sha1") diff --git a/gitweb/gitweb.perl b/gitweb/gitweb.perl index 3bc0f0b5ca..79057b7d0e 100755 --- a/gitweb/gitweb.perl +++ b/gitweb/gitweb.perl @@ -7094,7 +7094,7 @@ sub git_blob { git_print_page_path($file_name, "blob", $hash_base); print "<div class=\"page_body\">\n"; if ($mimetype =~ m!^image/!) { - print qq!<img type="!.esc_attr($mimetype).qq!"!; + print qq!<img class="blob" type="!.esc_attr($mimetype).qq!"!; if ($file_name) { print qq! alt="!.esc_attr($file_name).qq!" title="!.esc_attr($file_name).qq!"!; } diff --git a/gitweb/static/gitweb.css b/gitweb/static/gitweb.css index 3b4d833823..3212601032 100644 --- a/gitweb/static/gitweb.css +++ b/gitweb/static/gitweb.css @@ -32,6 +32,11 @@ img.avatar { vertical-align: middle; } +img.blob { + max-height: 100%; + max-width: 100%; +} + a.list img.avatar { border-style: none; } diff --git a/hash.c b/hash.c deleted file mode 100644 index 749ecfe484..0000000000 --- a/hash.c +++ /dev/null @@ -1,110 +0,0 @@ -/* - * Some generic hashing helpers. - */ -#include "cache.h" -#include "hash.h" - -/* - * Look up a hash entry in the hash table. Return the pointer to - * the existing entry, or the empty slot if none existed. The caller - * can then look at the (*ptr) to see whether it existed or not. - */ -static struct hash_table_entry *lookup_hash_entry(unsigned int hash, const struct hash_table *table) -{ - unsigned int size = table->size, nr = hash % size; - struct hash_table_entry *array = table->array; - - while (array[nr].ptr) { - if (array[nr].hash == hash) - break; - nr++; - if (nr >= size) - nr = 0; - } - return array + nr; -} - - -/* - * Insert a new hash entry pointer into the table. - * - * If that hash entry already existed, return the pointer to - * the existing entry (and the caller can create a list of the - * pointers or do anything else). If it didn't exist, return - * NULL (and the caller knows the pointer has been inserted). - */ -static void **insert_hash_entry(unsigned int hash, void *ptr, struct hash_table *table) -{ - struct hash_table_entry *entry = lookup_hash_entry(hash, table); - - if (!entry->ptr) { - entry->ptr = ptr; - entry->hash = hash; - table->nr++; - return NULL; - } - return &entry->ptr; -} - -static void grow_hash_table(struct hash_table *table) -{ - unsigned int i; - unsigned int old_size = table->size, new_size; - struct hash_table_entry *old_array = table->array, *new_array; - - new_size = alloc_nr(old_size); - new_array = xcalloc(sizeof(struct hash_table_entry), new_size); - table->size = new_size; - table->array = new_array; - table->nr = 0; - for (i = 0; i < old_size; i++) { - unsigned int hash = old_array[i].hash; - void *ptr = old_array[i].ptr; - if (ptr) - insert_hash_entry(hash, ptr, table); - } - free(old_array); -} - -void *lookup_hash(unsigned int hash, const struct hash_table *table) -{ - if (!table->array) - return NULL; - return lookup_hash_entry(hash, table)->ptr; -} - -void **insert_hash(unsigned int hash, void *ptr, struct hash_table *table) -{ - unsigned int nr = table->nr; - if (nr >= table->size/2) - grow_hash_table(table); - return insert_hash_entry(hash, ptr, table); -} - -int for_each_hash(const struct hash_table *table, int (*fn)(void *, void *), void *data) -{ - int sum = 0; - unsigned int i; - unsigned int size = table->size; - struct hash_table_entry *array = table->array; - - for (i = 0; i < size; i++) { - void *ptr = array->ptr; - array++; - if (ptr) { - int val = fn(ptr, data); - if (val < 0) - return val; - sum += val; - } - } - return sum; -} - -void free_hash(struct hash_table *table) -{ - free(table->array); - table->array = NULL; - table->size = 0; - table->nr = 0; -} diff --git a/hash.h b/hash.h deleted file mode 100644 index 1d43ac0ba0..0000000000 --- a/hash.h +++ /dev/null @@ -1,50 +0,0 @@ -#ifndef HASH_H -#define HASH_H - -/* - * These are some simple generic hash table helper functions. - * Not necessarily suitable for all users, but good for things - * where you want to just keep track of a list of things, and - * have a good hash to use on them. - * - * It keeps the hash table at roughly 50-75% free, so the memory - * cost of the hash table itself is roughly - * - * 3 * 2*sizeof(void *) * nr_of_objects - * - * bytes. - * - * FIXME: on 64-bit architectures, we waste memory. It would be - * good to have just 32-bit pointers, requiring a special allocator - * for hashed entries or something. - */ -struct hash_table_entry { - unsigned int hash; - void *ptr; -}; - -struct hash_table { - unsigned int size, nr; - struct hash_table_entry *array; -}; - -extern void *lookup_hash(unsigned int hash, const struct hash_table *table); -extern void **insert_hash(unsigned int hash, void *ptr, struct hash_table *table); -extern int for_each_hash(const struct hash_table *table, int (*fn)(void *, void *), void *data); -extern void free_hash(struct hash_table *table); - -static inline void init_hash(struct hash_table *table) -{ - table->size = 0; - table->nr = 0; - table->array = NULL; -} - -static inline void preallocate_hash(struct hash_table *table, unsigned int elts) -{ - assert(table->size == 0 && table->nr == 0 && table->array == NULL); - table->size = elts * 2; - table->array = xcalloc(sizeof(struct hash_table_entry), table->size); -} - -#endif diff --git a/hashmap.c b/hashmap.c new file mode 100644 index 0000000000..d1b8056d8d --- /dev/null +++ b/hashmap.c @@ -0,0 +1,228 @@ +/* + * Generic implementation of hash-based key value mappings. + */ +#include "cache.h" +#include "hashmap.h" + +#define FNV32_BASE ((unsigned int) 0x811c9dc5) +#define FNV32_PRIME ((unsigned int) 0x01000193) + +unsigned int strhash(const char *str) +{ + unsigned int c, hash = FNV32_BASE; + while ((c = (unsigned char) *str++)) + hash = (hash * FNV32_PRIME) ^ c; + return hash; +} + +unsigned int strihash(const char *str) +{ + unsigned int c, hash = FNV32_BASE; + while ((c = (unsigned char) *str++)) { + if (c >= 'a' && c <= 'z') + c -= 'a' - 'A'; + hash = (hash * FNV32_PRIME) ^ c; + } + return hash; +} + +unsigned int memhash(const void *buf, size_t len) +{ + unsigned int hash = FNV32_BASE; + unsigned char *ucbuf = (unsigned char *) buf; + while (len--) { + unsigned int c = *ucbuf++; + hash = (hash * FNV32_PRIME) ^ c; + } + return hash; +} + +unsigned int memihash(const void *buf, size_t len) +{ + unsigned int hash = FNV32_BASE; + unsigned char *ucbuf = (unsigned char *) buf; + while (len--) { + unsigned int c = *ucbuf++; + if (c >= 'a' && c <= 'z') + c -= 'a' - 'A'; + hash = (hash * FNV32_PRIME) ^ c; + } + return hash; +} + +#define HASHMAP_INITIAL_SIZE 64 +/* grow / shrink by 2^2 */ +#define HASHMAP_RESIZE_BITS 2 +/* load factor in percent */ +#define HASHMAP_LOAD_FACTOR 80 + +static void alloc_table(struct hashmap *map, unsigned int size) +{ + map->tablesize = size; + map->table = xcalloc(size, sizeof(struct hashmap_entry *)); + + /* calculate resize thresholds for new size */ + map->grow_at = (unsigned int) ((uint64_t) size * HASHMAP_LOAD_FACTOR / 100); + if (size <= HASHMAP_INITIAL_SIZE) + map->shrink_at = 0; + else + /* + * The shrink-threshold must be slightly smaller than + * (grow-threshold / resize-factor) to prevent erratic resizing, + * thus we divide by (resize-factor + 1). + */ + map->shrink_at = map->grow_at / ((1 << HASHMAP_RESIZE_BITS) + 1); +} + +static inline int entry_equals(const struct hashmap *map, + const struct hashmap_entry *e1, const struct hashmap_entry *e2, + const void *keydata) +{ + return (e1 == e2) || (e1->hash == e2->hash && !map->cmpfn(e1, e2, keydata)); +} + +static inline unsigned int bucket(const struct hashmap *map, + const struct hashmap_entry *key) +{ + return key->hash & (map->tablesize - 1); +} + +static void rehash(struct hashmap *map, unsigned int newsize) +{ + unsigned int i, oldsize = map->tablesize; + struct hashmap_entry **oldtable = map->table; + + alloc_table(map, newsize); + for (i = 0; i < oldsize; i++) { + struct hashmap_entry *e = oldtable[i]; + while (e) { + struct hashmap_entry *next = e->next; + unsigned int b = bucket(map, e); + e->next = map->table[b]; + map->table[b] = e; + e = next; + } + } + free(oldtable); +} + +static inline struct hashmap_entry **find_entry_ptr(const struct hashmap *map, + const struct hashmap_entry *key, const void *keydata) +{ + struct hashmap_entry **e = &map->table[bucket(map, key)]; + while (*e && !entry_equals(map, *e, key, keydata)) + e = &(*e)->next; + return e; +} + +static int always_equal(const void *unused1, const void *unused2, const void *unused3) +{ + return 0; +} + +void hashmap_init(struct hashmap *map, hashmap_cmp_fn equals_function, + size_t initial_size) +{ + unsigned int size = HASHMAP_INITIAL_SIZE; + map->size = 0; + map->cmpfn = equals_function ? equals_function : always_equal; + + /* calculate initial table size and allocate the table */ + initial_size = (unsigned int) ((uint64_t) initial_size * 100 + / HASHMAP_LOAD_FACTOR); + while (initial_size > size) + size <<= HASHMAP_RESIZE_BITS; + alloc_table(map, size); +} + +void hashmap_free(struct hashmap *map, int free_entries) +{ + if (!map || !map->table) + return; + if (free_entries) { + struct hashmap_iter iter; + struct hashmap_entry *e; + hashmap_iter_init(map, &iter); + while ((e = hashmap_iter_next(&iter))) + free(e); + } + free(map->table); + memset(map, 0, sizeof(*map)); +} + +void *hashmap_get(const struct hashmap *map, const void *key, const void *keydata) +{ + return *find_entry_ptr(map, key, keydata); +} + +void *hashmap_get_next(const struct hashmap *map, const void *entry) +{ + struct hashmap_entry *e = ((struct hashmap_entry *) entry)->next; + for (; e; e = e->next) + if (entry_equals(map, entry, e, NULL)) + return e; + return NULL; +} + +void hashmap_add(struct hashmap *map, void *entry) +{ + unsigned int b = bucket(map, entry); + + /* add entry */ + ((struct hashmap_entry *) entry)->next = map->table[b]; + map->table[b] = entry; + + /* fix size and rehash if appropriate */ + map->size++; + if (map->size > map->grow_at) + rehash(map, map->tablesize << HASHMAP_RESIZE_BITS); +} + +void *hashmap_remove(struct hashmap *map, const void *key, const void *keydata) +{ + struct hashmap_entry *old; + struct hashmap_entry **e = find_entry_ptr(map, key, keydata); + if (!*e) + return NULL; + + /* remove existing entry */ + old = *e; + *e = old->next; + old->next = NULL; + + /* fix size and rehash if appropriate */ + map->size--; + if (map->size < map->shrink_at) + rehash(map, map->tablesize >> HASHMAP_RESIZE_BITS); + return old; +} + +void *hashmap_put(struct hashmap *map, void *entry) +{ + struct hashmap_entry *old = hashmap_remove(map, entry, NULL); + hashmap_add(map, entry); + return old; +} + +void hashmap_iter_init(struct hashmap *map, struct hashmap_iter *iter) +{ + iter->map = map; + iter->tablepos = 0; + iter->next = NULL; +} + +void *hashmap_iter_next(struct hashmap_iter *iter) +{ + struct hashmap_entry *current = iter->next; + for (;;) { + if (current) { + iter->next = current->next; + return current; + } + + if (iter->tablepos >= iter->map->tablesize) + return NULL; + + current = iter->map->table[iter->tablepos++]; + } +} diff --git a/hashmap.h b/hashmap.h new file mode 100644 index 0000000000..a816ad47b1 --- /dev/null +++ b/hashmap.h @@ -0,0 +1,71 @@ +#ifndef HASHMAP_H +#define HASHMAP_H + +/* + * Generic implementation of hash-based key-value mappings. + * See Documentation/technical/api-hashmap.txt. + */ + +/* FNV-1 functions */ + +extern unsigned int strhash(const char *buf); +extern unsigned int strihash(const char *buf); +extern unsigned int memhash(const void *buf, size_t len); +extern unsigned int memihash(const void *buf, size_t len); + +/* data structures */ + +struct hashmap_entry { + struct hashmap_entry *next; + unsigned int hash; +}; + +typedef int (*hashmap_cmp_fn)(const void *entry, const void *entry_or_key, + const void *keydata); + +struct hashmap { + struct hashmap_entry **table; + hashmap_cmp_fn cmpfn; + unsigned int size, tablesize, grow_at, shrink_at; +}; + +struct hashmap_iter { + struct hashmap *map; + struct hashmap_entry *next; + unsigned int tablepos; +}; + +/* hashmap functions */ + +extern void hashmap_init(struct hashmap *map, hashmap_cmp_fn equals_function, + size_t initial_size); +extern void hashmap_free(struct hashmap *map, int free_entries); + +/* hashmap_entry functions */ + +static inline void hashmap_entry_init(void *entry, unsigned int hash) +{ + struct hashmap_entry *e = entry; + e->hash = hash; + e->next = NULL; +} +extern void *hashmap_get(const struct hashmap *map, const void *key, + const void *keydata); +extern void *hashmap_get_next(const struct hashmap *map, const void *entry); +extern void hashmap_add(struct hashmap *map, void *entry); +extern void *hashmap_put(struct hashmap *map, void *entry); +extern void *hashmap_remove(struct hashmap *map, const void *key, + const void *keydata); + +/* hashmap_iter functions */ + +extern void hashmap_iter_init(struct hashmap *map, struct hashmap_iter *iter); +extern void *hashmap_iter_next(struct hashmap_iter *iter); +static inline void *hashmap_iter_first(struct hashmap *map, + struct hashmap_iter *iter) +{ + hashmap_iter_init(map, iter); + return hashmap_iter_next(iter); +} + +#endif @@ -880,6 +880,20 @@ int handle_curl_result(struct slot_results *results) } } +int run_one_slot(struct active_request_slot *slot, + struct slot_results *results) +{ + slot->results = results; + if (!start_active_slot(slot)) { + snprintf(curl_errorstr, sizeof(curl_errorstr), + "failed to start HTTP request"); + return HTTP_START_FAILED; + } + + run_active_slot(slot); + return handle_curl_result(results); +} + static CURLcode curlinfo_strbuf(CURL *curl, CURLINFO info, struct strbuf *buf) { char *ptr; @@ -907,7 +921,6 @@ static int http_request(const char *url, int ret; slot = get_active_slot(); - slot->results = &results; curl_easy_setopt(slot->curl, CURLOPT_HTTPGET, 1); if (result == NULL) { @@ -942,14 +955,7 @@ static int http_request(const char *url, curl_easy_setopt(slot->curl, CURLOPT_HTTPHEADER, headers); curl_easy_setopt(slot->curl, CURLOPT_ENCODING, "gzip"); - if (start_active_slot(slot)) { - run_active_slot(slot); - ret = handle_curl_result(&results); - } else { - snprintf(curl_errorstr, sizeof(curl_errorstr), - "failed to start HTTP request"); - ret = HTTP_START_FAILED; - } + ret = run_one_slot(slot, &results); if (options && options->content_type) curlinfo_strbuf(slot->curl, CURLINFO_CONTENT_TYPE, @@ -90,6 +90,15 @@ extern void finish_active_slot(struct active_request_slot *slot); extern void finish_all_active_slots(void); extern int handle_curl_result(struct slot_results *results); +/* + * This will run one slot to completion in a blocking manner, similar to how + * curl_easy_perform would work (but we don't want to use that, because + * we do not want to intermingle calls to curl_multi and curl_easy). + * + */ +int run_one_slot(struct active_request_slot *slot, + struct slot_results *results); + #ifdef USE_CURL_MULTI extern void fill_active_slots(void); extern void add_fill_function(void *data, int (*fill)(void *)); diff --git a/khash.h b/khash.h new file mode 100644 index 0000000000..57ff6038c5 --- /dev/null +++ b/khash.h @@ -0,0 +1,338 @@ +/* The MIT License + + Copyright (c) 2008, 2009, 2011 by Attractive Chaos <attractor@live.co.uk> + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to + permit persons to whom the Software is furnished to do so, subject to + the following conditions: + + The above copyright notice and this permission notice shall be + included in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + SOFTWARE. +*/ + +#ifndef __AC_KHASH_H +#define __AC_KHASH_H + +#define AC_VERSION_KHASH_H "0.2.8" + +typedef uint32_t khint32_t; +typedef uint64_t khint64_t; + +typedef khint32_t khint_t; +typedef khint_t khiter_t; + +#define __ac_isempty(flag, i) ((flag[i>>4]>>((i&0xfU)<<1))&2) +#define __ac_isdel(flag, i) ((flag[i>>4]>>((i&0xfU)<<1))&1) +#define __ac_iseither(flag, i) ((flag[i>>4]>>((i&0xfU)<<1))&3) +#define __ac_set_isdel_false(flag, i) (flag[i>>4]&=~(1ul<<((i&0xfU)<<1))) +#define __ac_set_isempty_false(flag, i) (flag[i>>4]&=~(2ul<<((i&0xfU)<<1))) +#define __ac_set_isboth_false(flag, i) (flag[i>>4]&=~(3ul<<((i&0xfU)<<1))) +#define __ac_set_isdel_true(flag, i) (flag[i>>4]|=1ul<<((i&0xfU)<<1)) + +#define __ac_fsize(m) ((m) < 16? 1 : (m)>>4) + +#define kroundup32(x) (--(x), (x)|=(x)>>1, (x)|=(x)>>2, (x)|=(x)>>4, (x)|=(x)>>8, (x)|=(x)>>16, ++(x)) + +static inline khint_t __ac_X31_hash_string(const char *s) +{ + khint_t h = (khint_t)*s; + if (h) for (++s ; *s; ++s) h = (h << 5) - h + (khint_t)*s; + return h; +} + +#define kh_str_hash_func(key) __ac_X31_hash_string(key) +#define kh_str_hash_equal(a, b) (strcmp(a, b) == 0) + +static const double __ac_HASH_UPPER = 0.77; + +#define __KHASH_TYPE(name, khkey_t, khval_t) \ + typedef struct { \ + khint_t n_buckets, size, n_occupied, upper_bound; \ + khint32_t *flags; \ + khkey_t *keys; \ + khval_t *vals; \ + } kh_##name##_t; + +#define __KHASH_PROTOTYPES(name, khkey_t, khval_t) \ + extern kh_##name##_t *kh_init_##name(void); \ + extern void kh_destroy_##name(kh_##name##_t *h); \ + extern void kh_clear_##name(kh_##name##_t *h); \ + extern khint_t kh_get_##name(const kh_##name##_t *h, khkey_t key); \ + extern int kh_resize_##name(kh_##name##_t *h, khint_t new_n_buckets); \ + extern khint_t kh_put_##name(kh_##name##_t *h, khkey_t key, int *ret); \ + extern void kh_del_##name(kh_##name##_t *h, khint_t x); + +#define __KHASH_IMPL(name, SCOPE, khkey_t, khval_t, kh_is_map, __hash_func, __hash_equal) \ + SCOPE kh_##name##_t *kh_init_##name(void) { \ + return (kh_##name##_t*)xcalloc(1, sizeof(kh_##name##_t)); \ + } \ + SCOPE void kh_destroy_##name(kh_##name##_t *h) \ + { \ + if (h) { \ + free((void *)h->keys); free(h->flags); \ + free((void *)h->vals); \ + free(h); \ + } \ + } \ + SCOPE void kh_clear_##name(kh_##name##_t *h) \ + { \ + if (h && h->flags) { \ + memset(h->flags, 0xaa, __ac_fsize(h->n_buckets) * sizeof(khint32_t)); \ + h->size = h->n_occupied = 0; \ + } \ + } \ + SCOPE khint_t kh_get_##name(const kh_##name##_t *h, khkey_t key) \ + { \ + if (h->n_buckets) { \ + khint_t k, i, last, mask, step = 0; \ + mask = h->n_buckets - 1; \ + k = __hash_func(key); i = k & mask; \ + last = i; \ + while (!__ac_isempty(h->flags, i) && (__ac_isdel(h->flags, i) || !__hash_equal(h->keys[i], key))) { \ + i = (i + (++step)) & mask; \ + if (i == last) return h->n_buckets; \ + } \ + return __ac_iseither(h->flags, i)? h->n_buckets : i; \ + } else return 0; \ + } \ + SCOPE int kh_resize_##name(kh_##name##_t *h, khint_t new_n_buckets) \ + { /* This function uses 0.25*n_buckets bytes of working space instead of [sizeof(key_t+val_t)+.25]*n_buckets. */ \ + khint32_t *new_flags = NULL; \ + khint_t j = 1; \ + { \ + kroundup32(new_n_buckets); \ + if (new_n_buckets < 4) new_n_buckets = 4; \ + if (h->size >= (khint_t)(new_n_buckets * __ac_HASH_UPPER + 0.5)) j = 0; /* requested size is too small */ \ + else { /* hash table size to be changed (shrink or expand); rehash */ \ + new_flags = (khint32_t*)xmalloc(__ac_fsize(new_n_buckets) * sizeof(khint32_t)); \ + if (!new_flags) return -1; \ + memset(new_flags, 0xaa, __ac_fsize(new_n_buckets) * sizeof(khint32_t)); \ + if (h->n_buckets < new_n_buckets) { /* expand */ \ + khkey_t *new_keys = (khkey_t*)xrealloc((void *)h->keys, new_n_buckets * sizeof(khkey_t)); \ + if (!new_keys) return -1; \ + h->keys = new_keys; \ + if (kh_is_map) { \ + khval_t *new_vals = (khval_t*)xrealloc((void *)h->vals, new_n_buckets * sizeof(khval_t)); \ + if (!new_vals) return -1; \ + h->vals = new_vals; \ + } \ + } /* otherwise shrink */ \ + } \ + } \ + if (j) { /* rehashing is needed */ \ + for (j = 0; j != h->n_buckets; ++j) { \ + if (__ac_iseither(h->flags, j) == 0) { \ + khkey_t key = h->keys[j]; \ + khval_t val; \ + khint_t new_mask; \ + new_mask = new_n_buckets - 1; \ + if (kh_is_map) val = h->vals[j]; \ + __ac_set_isdel_true(h->flags, j); \ + while (1) { /* kick-out process; sort of like in Cuckoo hashing */ \ + khint_t k, i, step = 0; \ + k = __hash_func(key); \ + i = k & new_mask; \ + while (!__ac_isempty(new_flags, i)) i = (i + (++step)) & new_mask; \ + __ac_set_isempty_false(new_flags, i); \ + if (i < h->n_buckets && __ac_iseither(h->flags, i) == 0) { /* kick out the existing element */ \ + { khkey_t tmp = h->keys[i]; h->keys[i] = key; key = tmp; } \ + if (kh_is_map) { khval_t tmp = h->vals[i]; h->vals[i] = val; val = tmp; } \ + __ac_set_isdel_true(h->flags, i); /* mark it as deleted in the old hash table */ \ + } else { /* write the element and jump out of the loop */ \ + h->keys[i] = key; \ + if (kh_is_map) h->vals[i] = val; \ + break; \ + } \ + } \ + } \ + } \ + if (h->n_buckets > new_n_buckets) { /* shrink the hash table */ \ + h->keys = (khkey_t*)xrealloc((void *)h->keys, new_n_buckets * sizeof(khkey_t)); \ + if (kh_is_map) h->vals = (khval_t*)xrealloc((void *)h->vals, new_n_buckets * sizeof(khval_t)); \ + } \ + free(h->flags); /* free the working space */ \ + h->flags = new_flags; \ + h->n_buckets = new_n_buckets; \ + h->n_occupied = h->size; \ + h->upper_bound = (khint_t)(h->n_buckets * __ac_HASH_UPPER + 0.5); \ + } \ + return 0; \ + } \ + SCOPE khint_t kh_put_##name(kh_##name##_t *h, khkey_t key, int *ret) \ + { \ + khint_t x; \ + if (h->n_occupied >= h->upper_bound) { /* update the hash table */ \ + if (h->n_buckets > (h->size<<1)) { \ + if (kh_resize_##name(h, h->n_buckets - 1) < 0) { /* clear "deleted" elements */ \ + *ret = -1; return h->n_buckets; \ + } \ + } else if (kh_resize_##name(h, h->n_buckets + 1) < 0) { /* expand the hash table */ \ + *ret = -1; return h->n_buckets; \ + } \ + } /* TODO: to implement automatically shrinking; resize() already support shrinking */ \ + { \ + khint_t k, i, site, last, mask = h->n_buckets - 1, step = 0; \ + x = site = h->n_buckets; k = __hash_func(key); i = k & mask; \ + if (__ac_isempty(h->flags, i)) x = i; /* for speed up */ \ + else { \ + last = i; \ + while (!__ac_isempty(h->flags, i) && (__ac_isdel(h->flags, i) || !__hash_equal(h->keys[i], key))) { \ + if (__ac_isdel(h->flags, i)) site = i; \ + i = (i + (++step)) & mask; \ + if (i == last) { x = site; break; } \ + } \ + if (x == h->n_buckets) { \ + if (__ac_isempty(h->flags, i) && site != h->n_buckets) x = site; \ + else x = i; \ + } \ + } \ + } \ + if (__ac_isempty(h->flags, x)) { /* not present at all */ \ + h->keys[x] = key; \ + __ac_set_isboth_false(h->flags, x); \ + ++h->size; ++h->n_occupied; \ + *ret = 1; \ + } else if (__ac_isdel(h->flags, x)) { /* deleted */ \ + h->keys[x] = key; \ + __ac_set_isboth_false(h->flags, x); \ + ++h->size; \ + *ret = 2; \ + } else *ret = 0; /* Don't touch h->keys[x] if present and not deleted */ \ + return x; \ + } \ + SCOPE void kh_del_##name(kh_##name##_t *h, khint_t x) \ + { \ + if (x != h->n_buckets && !__ac_iseither(h->flags, x)) { \ + __ac_set_isdel_true(h->flags, x); \ + --h->size; \ + } \ + } + +#define KHASH_DECLARE(name, khkey_t, khval_t) \ + __KHASH_TYPE(name, khkey_t, khval_t) \ + __KHASH_PROTOTYPES(name, khkey_t, khval_t) + +#define KHASH_INIT2(name, SCOPE, khkey_t, khval_t, kh_is_map, __hash_func, __hash_equal) \ + __KHASH_TYPE(name, khkey_t, khval_t) \ + __KHASH_IMPL(name, SCOPE, khkey_t, khval_t, kh_is_map, __hash_func, __hash_equal) + +#define KHASH_INIT(name, khkey_t, khval_t, kh_is_map, __hash_func, __hash_equal) \ + KHASH_INIT2(name, static inline, khkey_t, khval_t, kh_is_map, __hash_func, __hash_equal) + +/* Other convenient macros... */ + +/*! @function + @abstract Test whether a bucket contains data. + @param h Pointer to the hash table [khash_t(name)*] + @param x Iterator to the bucket [khint_t] + @return 1 if containing data; 0 otherwise [int] + */ +#define kh_exist(h, x) (!__ac_iseither((h)->flags, (x))) + +/*! @function + @abstract Get key given an iterator + @param h Pointer to the hash table [khash_t(name)*] + @param x Iterator to the bucket [khint_t] + @return Key [type of keys] + */ +#define kh_key(h, x) ((h)->keys[x]) + +/*! @function + @abstract Get value given an iterator + @param h Pointer to the hash table [khash_t(name)*] + @param x Iterator to the bucket [khint_t] + @return Value [type of values] + @discussion For hash sets, calling this results in segfault. + */ +#define kh_val(h, x) ((h)->vals[x]) + +/*! @function + @abstract Alias of kh_val() + */ +#define kh_value(h, x) ((h)->vals[x]) + +/*! @function + @abstract Get the start iterator + @param h Pointer to the hash table [khash_t(name)*] + @return The start iterator [khint_t] + */ +#define kh_begin(h) (khint_t)(0) + +/*! @function + @abstract Get the end iterator + @param h Pointer to the hash table [khash_t(name)*] + @return The end iterator [khint_t] + */ +#define kh_end(h) ((h)->n_buckets) + +/*! @function + @abstract Get the number of elements in the hash table + @param h Pointer to the hash table [khash_t(name)*] + @return Number of elements in the hash table [khint_t] + */ +#define kh_size(h) ((h)->size) + +/*! @function + @abstract Get the number of buckets in the hash table + @param h Pointer to the hash table [khash_t(name)*] + @return Number of buckets in the hash table [khint_t] + */ +#define kh_n_buckets(h) ((h)->n_buckets) + +/*! @function + @abstract Iterate over the entries in the hash table + @param h Pointer to the hash table [khash_t(name)*] + @param kvar Variable to which key will be assigned + @param vvar Variable to which value will be assigned + @param code Block of code to execute + */ +#define kh_foreach(h, kvar, vvar, code) { khint_t __i; \ + for (__i = kh_begin(h); __i != kh_end(h); ++__i) { \ + if (!kh_exist(h,__i)) continue; \ + (kvar) = kh_key(h,__i); \ + (vvar) = kh_val(h,__i); \ + code; \ + } } + +/*! @function + @abstract Iterate over the values in the hash table + @param h Pointer to the hash table [khash_t(name)*] + @param vvar Variable to which value will be assigned + @param code Block of code to execute + */ +#define kh_foreach_value(h, vvar, code) { khint_t __i; \ + for (__i = kh_begin(h); __i != kh_end(h); ++__i) { \ + if (!kh_exist(h,__i)) continue; \ + (vvar) = kh_val(h,__i); \ + code; \ + } } + +static inline khint_t __kh_oid_hash(const unsigned char *oid) +{ + khint_t hash; + memcpy(&hash, oid, sizeof(hash)); + return hash; +} + +#define __kh_oid_cmp(a, b) (hashcmp(a, b) == 0) + +KHASH_INIT(sha1, const unsigned char *, void *, 1, __kh_oid_hash, __kh_oid_cmp) +typedef kh_sha1_t khash_sha1; + +KHASH_INIT(sha1_pos, const unsigned char *, int, 1, __kh_oid_hash, __kh_oid_cmp) +typedef kh_sha1_pos_t khash_sha1_pos; + +#endif /* __AC_KHASH_H */ diff --git a/line-log.c b/line-log.c index 717638b333..1500101058 100644 --- a/line-log.c +++ b/line-log.c @@ -766,16 +766,6 @@ void line_log_init(struct rev_info *rev, const char *prefix, struct string_list } } -static void load_tree_desc(struct tree_desc *desc, void **tree, - const unsigned char *sha1) -{ - unsigned long size; - *tree = read_object_with_reference(sha1, tree_type, &size, NULL); - if (!*tree) - die("Unable to read tree (%s)", sha1_to_hex(sha1)); - init_tree_desc(desc, *tree, size); -} - static int count_parents(struct commit *commit) { struct commit_list *parents = commit->parents; @@ -842,18 +832,11 @@ static void queue_diffs(struct line_log_data *range, struct diff_queue_struct *queue, struct commit *commit, struct commit *parent) { - void *tree1 = NULL, *tree2 = NULL; - struct tree_desc desc1, desc2; - assert(commit); - load_tree_desc(&desc2, &tree2, commit->tree->object.sha1); - if (parent) - load_tree_desc(&desc1, &tree1, parent->tree->object.sha1); - else - init_tree_desc(&desc1, "", 0); DIFF_QUEUE_CLEAR(&diff_queued_diff); - diff_tree(&desc1, &desc2, "", opt); + diff_tree_sha1(parent ? parent->tree->object.sha1 : NULL, + commit->tree->object.sha1, "", opt); if (opt->detect_rename) { filter_diffs_for_paths(range, 1); if (diff_might_be_rename()) @@ -861,11 +844,6 @@ static void queue_diffs(struct line_log_data *range, filter_diffs_for_paths(range, 0); } move_diff_queue(queue, &diff_queued_diff); - - if (tree1) - free(tree1); - if (tree2) - free(tree2); } static char *get_nth_line(long line, unsigned long *ends, void *data) diff --git a/merge-recursive.c b/merge-recursive.c index 8400a8e937..4177092942 100644 --- a/merge-recursive.c +++ b/merge-recursive.c @@ -201,7 +201,9 @@ static int add_cacheinfo(unsigned int mode, const unsigned char *sha1, const char *path, int stage, int refresh, int options) { struct cache_entry *ce; - ce = make_cache_entry(mode, sha1 ? sha1 : null_sha1, path, stage, refresh); + ce = make_cache_entry(mode, sha1 ? sha1 : null_sha1, path, stage, + (refresh ? (CE_MATCH_REFRESH | + CE_MATCH_IGNORE_MISSING) : 0 )); if (!ce) return error(_("addinfo_cache failed for path '%s'"), path); return add_cache_entry(ce, options); diff --git a/name-hash.c b/name-hash.c index e5b6e1ad23..97444d0201 100644 --- a/name-hash.c +++ b/name-hash.c @@ -8,49 +8,28 @@ #define NO_THE_INDEX_COMPATIBILITY_MACROS #include "cache.h" -/* - * This removes bit 5 if bit 6 is set. - * - * That will make US-ASCII characters hash to their upper-case - * equivalent. We could easily do this one whole word at a time, - * but that's for future worries. - */ -static inline unsigned char icase_hash(unsigned char c) -{ - return c & ~((c & 0x40) >> 1); -} - -static unsigned int hash_name(const char *name, int namelen) -{ - unsigned int hash = 0x123; - - while (namelen--) { - unsigned char c = *name++; - c = icase_hash(c); - hash = hash*101 + c; - } - return hash; -} - struct dir_entry { - struct dir_entry *next; + struct hashmap_entry ent; struct dir_entry *parent; struct cache_entry *ce; int nr; unsigned int namelen; }; +static int dir_entry_cmp(const struct dir_entry *e1, + const struct dir_entry *e2, const char *name) +{ + return e1->namelen != e2->namelen || strncasecmp(e1->ce->name, + name ? name : e2->ce->name, e1->namelen); +} + static struct dir_entry *find_dir_entry(struct index_state *istate, const char *name, unsigned int namelen) { - unsigned int hash = hash_name(name, namelen); - struct dir_entry *dir; - - for (dir = lookup_hash(hash, &istate->dir_hash); dir; dir = dir->next) - if (dir->namelen == namelen && - !strncasecmp(dir->ce->name, name, namelen)) - return dir; - return NULL; + struct dir_entry key; + hashmap_entry_init(&key, memihash(name, namelen)); + key.namelen = namelen; + return hashmap_get(&istate->dir_hash, &key, name); } static struct dir_entry *hash_dir_entry(struct index_state *istate, @@ -84,18 +63,11 @@ static struct dir_entry *hash_dir_entry(struct index_state *istate, dir = find_dir_entry(istate, ce->name, namelen); if (!dir) { /* not found, create it and add to hash table */ - void **pdir; - unsigned int hash = hash_name(ce->name, namelen); - dir = xcalloc(1, sizeof(struct dir_entry)); + hashmap_entry_init(dir, memihash(ce->name, namelen)); dir->namelen = namelen; dir->ce = ce; - - pdir = insert_hash(hash, dir, &istate->dir_hash); - if (pdir) { - dir->next = *pdir; - *pdir = dir; - } + hashmap_add(&istate->dir_hash, dir); /* recursively add missing parent directories */ dir->parent = hash_dir_entry(istate, ce, namelen); @@ -114,45 +86,50 @@ static void add_dir_entry(struct index_state *istate, struct cache_entry *ce) static void remove_dir_entry(struct index_state *istate, struct cache_entry *ce) { /* - * Release reference to the directory entry (and parents if 0). - * - * Note: we do not remove / free the entry because there's no - * hash.[ch]::remove_hash and dir->next may point to other entries - * that are still valid, so we must not free the memory. + * Release reference to the directory entry. If 0, remove and continue + * with parent directory. */ struct dir_entry *dir = hash_dir_entry(istate, ce, ce_namelen(ce)); - while (dir && dir->nr && !(--dir->nr)) - dir = dir->parent; + while (dir && !(--dir->nr)) { + struct dir_entry *parent = dir->parent; + hashmap_remove(&istate->dir_hash, dir, NULL); + free(dir); + dir = parent; + } } static void hash_index_entry(struct index_state *istate, struct cache_entry *ce) { - void **pos; - unsigned int hash; - if (ce->ce_flags & CE_HASHED) return; ce->ce_flags |= CE_HASHED; - ce->next = NULL; - hash = hash_name(ce->name, ce_namelen(ce)); - pos = insert_hash(hash, ce, &istate->name_hash); - if (pos) { - ce->next = *pos; - *pos = ce; - } + hashmap_entry_init(ce, memihash(ce->name, ce_namelen(ce))); + hashmap_add(&istate->name_hash, ce); - if (ignore_case && !(ce->ce_flags & CE_UNHASHED)) + if (ignore_case) add_dir_entry(istate, ce); } +static int cache_entry_cmp(const struct cache_entry *ce1, + const struct cache_entry *ce2, const void *remove) +{ + /* + * For remove_name_hash, find the exact entry (pointer equality); for + * index_file_exists, find all entries with matching hash code and + * decide whether the entry matches in same_name. + */ + return remove ? !(ce1 == ce2) : 0; +} + static void lazy_init_name_hash(struct index_state *istate) { int nr; if (istate->name_hash_initialized) return; - if (istate->cache_nr) - preallocate_hash(&istate->name_hash, istate->cache_nr); + hashmap_init(&istate->name_hash, (hashmap_cmp_fn) cache_entry_cmp, + istate->cache_nr); + hashmap_init(&istate->dir_hash, (hashmap_cmp_fn) dir_entry_cmp, 0); for (nr = 0; nr < istate->cache_nr; nr++) hash_index_entry(istate, istate->cache[nr]); istate->name_hash_initialized = 1; @@ -160,31 +137,19 @@ static void lazy_init_name_hash(struct index_state *istate) void add_name_hash(struct index_state *istate, struct cache_entry *ce) { - /* if already hashed, add reference to directory entries */ - if (ignore_case && (ce->ce_flags & CE_STATE_MASK) == CE_STATE_MASK) - add_dir_entry(istate, ce); - - ce->ce_flags &= ~CE_UNHASHED; if (istate->name_hash_initialized) hash_index_entry(istate, ce); } -/* - * We don't actually *remove* it, we can just mark it invalid so that - * we won't find it in lookups. - * - * Not only would we have to search the lists (simple enough), but - * we'd also have to rehash other hash buckets in case this makes the - * hash bucket empty (common). So it's much better to just mark - * it. - */ void remove_name_hash(struct index_state *istate, struct cache_entry *ce) { - /* if already hashed, release reference to directory entries */ - if (ignore_case && (ce->ce_flags & CE_STATE_MASK) == CE_HASHED) - remove_dir_entry(istate, ce); + if (!istate->name_hash_initialized || !(ce->ce_flags & CE_HASHED)) + return; + ce->ce_flags &= ~CE_HASHED; + hashmap_remove(&istate->name_hash, ce, ce); - ce->ce_flags |= CE_UNHASHED; + if (ignore_case) + remove_dir_entry(istate, ce); } static int slow_same_name(const char *name1, int len1, const char *name2, int len2) @@ -247,49 +212,27 @@ struct cache_entry *index_dir_exists(struct index_state *istate, const char *nam struct cache_entry *index_file_exists(struct index_state *istate, const char *name, int namelen, int icase) { - unsigned int hash = hash_name(name, namelen); struct cache_entry *ce; + struct hashmap_entry key; lazy_init_name_hash(istate); - ce = lookup_hash(hash, &istate->name_hash); + hashmap_entry_init(&key, memihash(name, namelen)); + ce = hashmap_get(&istate->name_hash, &key, NULL); while (ce) { - if (!(ce->ce_flags & CE_UNHASHED)) { - if (same_name(ce, name, namelen, icase)) - return ce; - } - ce = ce->next; + if (same_name(ce, name, namelen, icase)) + return ce; + ce = hashmap_get_next(&istate->name_hash, ce); } return NULL; } -struct cache_entry *index_name_exists(struct index_state *istate, const char *name, int namelen, int icase) -{ - if (namelen > 0 && name[namelen - 1] == '/') - return index_dir_exists(istate, name, namelen - 1); - return index_file_exists(istate, name, namelen, icase); -} - -static int free_dir_entry(void *entry, void *unused) -{ - struct dir_entry *dir = entry; - while (dir) { - struct dir_entry *next = dir->next; - free(dir); - dir = next; - } - return 0; -} - void free_name_hash(struct index_state *istate) { if (!istate->name_hash_initialized) return; istate->name_hash_initialized = 0; - if (ignore_case) - /* free directory entries */ - for_each_hash(&istate->dir_hash, free_dir_entry, NULL); - free_hash(&istate->name_hash); - free_hash(&istate->dir_hash); + hashmap_free(&istate->name_hash, 0); + hashmap_free(&istate->dir_hash, 1); } diff --git a/notes-utils.c b/notes-utils.c index 2975dcd581..4aa7023903 100644 --- a/notes-utils.c +++ b/notes-utils.c @@ -75,7 +75,7 @@ static int notes_rewrite_config(const char *k, const char *v, void *cb) return 0; } else if (!c->mode_from_env && !strcmp(k, "notes.rewritemode")) { if (!v) - config_error_nonbool(k); + return config_error_nonbool(k); c->combine = parse_combine_notes_fn(v); if (!c->combine) { error(_("Bad notes.rewriteMode value: '%s'"), v); diff --git a/pack-bitmap-write.c b/pack-bitmap-write.c new file mode 100644 index 0000000000..1218befaf2 --- /dev/null +++ b/pack-bitmap-write.c @@ -0,0 +1,552 @@ +#include "cache.h" +#include "commit.h" +#include "tag.h" +#include "diff.h" +#include "revision.h" +#include "list-objects.h" +#include "progress.h" +#include "pack-revindex.h" +#include "pack.h" +#include "pack-bitmap.h" +#include "sha1-lookup.h" +#include "pack-objects.h" + +struct bitmapped_commit { + struct commit *commit; + struct ewah_bitmap *bitmap; + struct ewah_bitmap *write_as; + int flags; + int xor_offset; + uint32_t commit_pos; +}; + +struct bitmap_writer { + struct ewah_bitmap *commits; + struct ewah_bitmap *trees; + struct ewah_bitmap *blobs; + struct ewah_bitmap *tags; + + khash_sha1 *bitmaps; + khash_sha1 *reused; + struct packing_data *to_pack; + + struct bitmapped_commit *selected; + unsigned int selected_nr, selected_alloc; + + struct progress *progress; + int show_progress; + unsigned char pack_checksum[20]; +}; + +static struct bitmap_writer writer; + +void bitmap_writer_show_progress(int show) +{ + writer.show_progress = show; +} + +/** + * Build the initial type index for the packfile + */ +void bitmap_writer_build_type_index(struct pack_idx_entry **index, + uint32_t index_nr) +{ + uint32_t i; + + writer.commits = ewah_new(); + writer.trees = ewah_new(); + writer.blobs = ewah_new(); + writer.tags = ewah_new(); + + for (i = 0; i < index_nr; ++i) { + struct object_entry *entry = (struct object_entry *)index[i]; + enum object_type real_type; + + entry->in_pack_pos = i; + + switch (entry->type) { + case OBJ_COMMIT: + case OBJ_TREE: + case OBJ_BLOB: + case OBJ_TAG: + real_type = entry->type; + break; + + default: + real_type = sha1_object_info(entry->idx.sha1, NULL); + break; + } + + switch (real_type) { + case OBJ_COMMIT: + ewah_set(writer.commits, i); + break; + + case OBJ_TREE: + ewah_set(writer.trees, i); + break; + + case OBJ_BLOB: + ewah_set(writer.blobs, i); + break; + + case OBJ_TAG: + ewah_set(writer.tags, i); + break; + + default: + die("Missing type information for %s (%d/%d)", + sha1_to_hex(entry->idx.sha1), real_type, entry->type); + } + } +} + +/** + * Compute the actual bitmaps + */ +static struct object **seen_objects; +static unsigned int seen_objects_nr, seen_objects_alloc; + +static inline void push_bitmapped_commit(struct commit *commit, struct ewah_bitmap *reused) +{ + if (writer.selected_nr >= writer.selected_alloc) { + writer.selected_alloc = (writer.selected_alloc + 32) * 2; + writer.selected = xrealloc(writer.selected, + writer.selected_alloc * sizeof(struct bitmapped_commit)); + } + + writer.selected[writer.selected_nr].commit = commit; + writer.selected[writer.selected_nr].bitmap = reused; + writer.selected[writer.selected_nr].flags = 0; + + writer.selected_nr++; +} + +static inline void mark_as_seen(struct object *object) +{ + ALLOC_GROW(seen_objects, seen_objects_nr + 1, seen_objects_alloc); + seen_objects[seen_objects_nr++] = object; +} + +static inline void reset_all_seen(void) +{ + unsigned int i; + for (i = 0; i < seen_objects_nr; ++i) { + seen_objects[i]->flags &= ~(SEEN | ADDED | SHOWN); + } + seen_objects_nr = 0; +} + +static uint32_t find_object_pos(const unsigned char *sha1) +{ + struct object_entry *entry = packlist_find(writer.to_pack, sha1, NULL); + + if (!entry) { + die("Failed to write bitmap index. Packfile doesn't have full closure " + "(object %s is missing)", sha1_to_hex(sha1)); + } + + return entry->in_pack_pos; +} + +static void show_object(struct object *object, const struct name_path *path, + const char *last, void *data) +{ + struct bitmap *base = data; + bitmap_set(base, find_object_pos(object->sha1)); + mark_as_seen(object); +} + +static void show_commit(struct commit *commit, void *data) +{ + mark_as_seen((struct object *)commit); +} + +static int +add_to_include_set(struct bitmap *base, struct commit *commit) +{ + khiter_t hash_pos; + uint32_t bitmap_pos = find_object_pos(commit->object.sha1); + + if (bitmap_get(base, bitmap_pos)) + return 0; + + hash_pos = kh_get_sha1(writer.bitmaps, commit->object.sha1); + if (hash_pos < kh_end(writer.bitmaps)) { + struct bitmapped_commit *bc = kh_value(writer.bitmaps, hash_pos); + bitmap_or_ewah(base, bc->bitmap); + return 0; + } + + bitmap_set(base, bitmap_pos); + return 1; +} + +static int +should_include(struct commit *commit, void *_data) +{ + struct bitmap *base = _data; + + if (!add_to_include_set(base, commit)) { + struct commit_list *parent = commit->parents; + + mark_as_seen((struct object *)commit); + + while (parent) { + parent->item->object.flags |= SEEN; + mark_as_seen((struct object *)parent->item); + parent = parent->next; + } + + return 0; + } + + return 1; +} + +static void compute_xor_offsets(void) +{ + static const int MAX_XOR_OFFSET_SEARCH = 10; + + int i, next = 0; + + while (next < writer.selected_nr) { + struct bitmapped_commit *stored = &writer.selected[next]; + + int best_offset = 0; + struct ewah_bitmap *best_bitmap = stored->bitmap; + struct ewah_bitmap *test_xor; + + for (i = 1; i <= MAX_XOR_OFFSET_SEARCH; ++i) { + int curr = next - i; + + if (curr < 0) + break; + + test_xor = ewah_pool_new(); + ewah_xor(writer.selected[curr].bitmap, stored->bitmap, test_xor); + + if (test_xor->buffer_size < best_bitmap->buffer_size) { + if (best_bitmap != stored->bitmap) + ewah_pool_free(best_bitmap); + + best_bitmap = test_xor; + best_offset = i; + } else { + ewah_pool_free(test_xor); + } + } + + stored->xor_offset = best_offset; + stored->write_as = best_bitmap; + + next++; + } +} + +void bitmap_writer_build(struct packing_data *to_pack) +{ + static const double REUSE_BITMAP_THRESHOLD = 0.2; + + int i, reuse_after, need_reset; + struct bitmap *base = bitmap_new(); + struct rev_info revs; + + writer.bitmaps = kh_init_sha1(); + writer.to_pack = to_pack; + + if (writer.show_progress) + writer.progress = start_progress("Building bitmaps", writer.selected_nr); + + init_revisions(&revs, NULL); + revs.tag_objects = 1; + revs.tree_objects = 1; + revs.blob_objects = 1; + revs.no_walk = 0; + + revs.include_check = should_include; + reset_revision_walk(); + + reuse_after = writer.selected_nr * REUSE_BITMAP_THRESHOLD; + need_reset = 0; + + for (i = writer.selected_nr - 1; i >= 0; --i) { + struct bitmapped_commit *stored; + struct object *object; + + khiter_t hash_pos; + int hash_ret; + + stored = &writer.selected[i]; + object = (struct object *)stored->commit; + + if (stored->bitmap == NULL) { + if (i < writer.selected_nr - 1 && + (need_reset || + !in_merge_bases(writer.selected[i + 1].commit, + stored->commit))) { + bitmap_reset(base); + reset_all_seen(); + } + + add_pending_object(&revs, object, ""); + revs.include_check_data = base; + + if (prepare_revision_walk(&revs)) + die("revision walk setup failed"); + + traverse_commit_list(&revs, show_commit, show_object, base); + + revs.pending.nr = 0; + revs.pending.alloc = 0; + revs.pending.objects = NULL; + + stored->bitmap = bitmap_to_ewah(base); + need_reset = 0; + } else + need_reset = 1; + + if (i >= reuse_after) + stored->flags |= BITMAP_FLAG_REUSE; + + hash_pos = kh_put_sha1(writer.bitmaps, object->sha1, &hash_ret); + if (hash_ret == 0) + die("Duplicate entry when writing index: %s", + sha1_to_hex(object->sha1)); + + kh_value(writer.bitmaps, hash_pos) = stored; + display_progress(writer.progress, writer.selected_nr - i); + } + + bitmap_free(base); + stop_progress(&writer.progress); + + compute_xor_offsets(); +} + +/** + * Select the commits that will be bitmapped + */ +static inline unsigned int next_commit_index(unsigned int idx) +{ + static const unsigned int MIN_COMMITS = 100; + static const unsigned int MAX_COMMITS = 5000; + + static const unsigned int MUST_REGION = 100; + static const unsigned int MIN_REGION = 20000; + + unsigned int offset, next; + + if (idx <= MUST_REGION) + return 0; + + if (idx <= MIN_REGION) { + offset = idx - MUST_REGION; + return (offset < MIN_COMMITS) ? offset : MIN_COMMITS; + } + + offset = idx - MIN_REGION; + next = (offset < MAX_COMMITS) ? offset : MAX_COMMITS; + + return (next > MIN_COMMITS) ? next : MIN_COMMITS; +} + +static int date_compare(const void *_a, const void *_b) +{ + struct commit *a = *(struct commit **)_a; + struct commit *b = *(struct commit **)_b; + return (long)b->date - (long)a->date; +} + +void bitmap_writer_reuse_bitmaps(struct packing_data *to_pack) +{ + if (prepare_bitmap_git() < 0) + return; + + writer.reused = kh_init_sha1(); + rebuild_existing_bitmaps(to_pack, writer.reused, writer.show_progress); +} + +static struct ewah_bitmap *find_reused_bitmap(const unsigned char *sha1) +{ + khiter_t hash_pos; + + if (!writer.reused) + return NULL; + + hash_pos = kh_get_sha1(writer.reused, sha1); + if (hash_pos >= kh_end(writer.reused)) + return NULL; + + return kh_value(writer.reused, hash_pos); +} + +void bitmap_writer_select_commits(struct commit **indexed_commits, + unsigned int indexed_commits_nr, + int max_bitmaps) +{ + unsigned int i = 0, j, next; + + qsort(indexed_commits, indexed_commits_nr, sizeof(indexed_commits[0]), + date_compare); + + if (writer.show_progress) + writer.progress = start_progress("Selecting bitmap commits", 0); + + if (indexed_commits_nr < 100) { + for (i = 0; i < indexed_commits_nr; ++i) + push_bitmapped_commit(indexed_commits[i], NULL); + return; + } + + for (;;) { + struct ewah_bitmap *reused_bitmap = NULL; + struct commit *chosen = NULL; + + next = next_commit_index(i); + + if (i + next >= indexed_commits_nr) + break; + + if (max_bitmaps > 0 && writer.selected_nr >= max_bitmaps) { + writer.selected_nr = max_bitmaps; + break; + } + + if (next == 0) { + chosen = indexed_commits[i]; + reused_bitmap = find_reused_bitmap(chosen->object.sha1); + } else { + chosen = indexed_commits[i + next]; + + for (j = 0; j <= next; ++j) { + struct commit *cm = indexed_commits[i + j]; + + reused_bitmap = find_reused_bitmap(cm->object.sha1); + if (reused_bitmap || (cm->object.flags & NEEDS_BITMAP) != 0) { + chosen = cm; + break; + } + + if (cm->parents && cm->parents->next) + chosen = cm; + } + } + + push_bitmapped_commit(chosen, reused_bitmap); + + i += next + 1; + display_progress(writer.progress, i); + } + + stop_progress(&writer.progress); +} + + +static int sha1write_ewah_helper(void *f, const void *buf, size_t len) +{ + /* sha1write will die on error */ + sha1write(f, buf, len); + return len; +} + +/** + * Write the bitmap index to disk + */ +static inline void dump_bitmap(struct sha1file *f, struct ewah_bitmap *bitmap) +{ + if (ewah_serialize_to(bitmap, sha1write_ewah_helper, f) < 0) + die("Failed to write bitmap index"); +} + +static const unsigned char *sha1_access(size_t pos, void *table) +{ + struct pack_idx_entry **index = table; + return index[pos]->sha1; +} + +static void write_selected_commits_v1(struct sha1file *f, + struct pack_idx_entry **index, + uint32_t index_nr) +{ + int i; + + for (i = 0; i < writer.selected_nr; ++i) { + struct bitmapped_commit *stored = &writer.selected[i]; + struct bitmap_disk_entry on_disk; + + int commit_pos = + sha1_pos(stored->commit->object.sha1, index, index_nr, sha1_access); + + if (commit_pos < 0) + die("BUG: trying to write commit not in index"); + + on_disk.object_pos = htonl(commit_pos); + on_disk.xor_offset = stored->xor_offset; + on_disk.flags = stored->flags; + + sha1write(f, &on_disk, sizeof(on_disk)); + dump_bitmap(f, stored->write_as); + } +} + +static void write_hash_cache(struct sha1file *f, + struct pack_idx_entry **index, + uint32_t index_nr) +{ + uint32_t i; + + for (i = 0; i < index_nr; ++i) { + struct object_entry *entry = (struct object_entry *)index[i]; + uint32_t hash_value = htonl(entry->hash); + sha1write(f, &hash_value, sizeof(hash_value)); + } +} + +void bitmap_writer_set_checksum(unsigned char *sha1) +{ + hashcpy(writer.pack_checksum, sha1); +} + +void bitmap_writer_finish(struct pack_idx_entry **index, + uint32_t index_nr, + const char *filename, + uint16_t options) +{ + static char tmp_file[PATH_MAX]; + static uint16_t default_version = 1; + static uint16_t flags = BITMAP_OPT_FULL_DAG; + struct sha1file *f; + + struct bitmap_disk_header header; + + int fd = odb_mkstemp(tmp_file, sizeof(tmp_file), "pack/tmp_bitmap_XXXXXX"); + + if (fd < 0) + die_errno("unable to create '%s'", tmp_file); + f = sha1fd(fd, tmp_file); + + memcpy(header.magic, BITMAP_IDX_SIGNATURE, sizeof(BITMAP_IDX_SIGNATURE)); + header.version = htons(default_version); + header.options = htons(flags | options); + header.entry_count = htonl(writer.selected_nr); + memcpy(header.checksum, writer.pack_checksum, 20); + + sha1write(f, &header, sizeof(header)); + dump_bitmap(f, writer.commits); + dump_bitmap(f, writer.trees); + dump_bitmap(f, writer.blobs); + dump_bitmap(f, writer.tags); + write_selected_commits_v1(f, index, index_nr); + + if (options & BITMAP_OPT_HASH_CACHE) + write_hash_cache(f, index, index_nr); + + sha1close(f, NULL, CSUM_FSYNC); + + if (adjust_shared_perm(tmp_file)) + die_errno("unable to make temporary bitmap file readable"); + + if (rename(tmp_file, filename)) + die_errno("unable to rename temporary bitmap file to '%s'", filename); +} diff --git a/pack-bitmap.c b/pack-bitmap.c new file mode 100644 index 0000000000..ae0b57b950 --- /dev/null +++ b/pack-bitmap.c @@ -0,0 +1,1073 @@ +#include "cache.h" +#include "commit.h" +#include "tag.h" +#include "diff.h" +#include "revision.h" +#include "progress.h" +#include "list-objects.h" +#include "pack.h" +#include "pack-bitmap.h" +#include "pack-revindex.h" +#include "pack-objects.h" + +/* + * An entry on the bitmap index, representing the bitmap for a given + * commit. + */ +struct stored_bitmap { + unsigned char sha1[20]; + struct ewah_bitmap *root; + struct stored_bitmap *xor; + int flags; +}; + +/* + * The currently active bitmap index. By design, repositories only have + * a single bitmap index available (the index for the biggest packfile in + * the repository), since bitmap indexes need full closure. + * + * If there is more than one bitmap index available (e.g. because of alternates), + * the active bitmap index is the largest one. + */ +static struct bitmap_index { + /* Packfile to which this bitmap index belongs to */ + struct packed_git *pack; + + /* reverse index for the packfile */ + struct pack_revindex *reverse_index; + + /* + * Mark the first `reuse_objects` in the packfile as reused: + * they will be sent as-is without using them for repacking + * calculations + */ + uint32_t reuse_objects; + + /* mmapped buffer of the whole bitmap index */ + unsigned char *map; + size_t map_size; /* size of the mmaped buffer */ + size_t map_pos; /* current position when loading the index */ + + /* + * Type indexes. + * + * Each bitmap marks which objects in the packfile are of the given + * type. This provides type information when yielding the objects from + * the packfile during a walk, which allows for better delta bases. + */ + struct ewah_bitmap *commits; + struct ewah_bitmap *trees; + struct ewah_bitmap *blobs; + struct ewah_bitmap *tags; + + /* Map from SHA1 -> `stored_bitmap` for all the bitmapped comits */ + khash_sha1 *bitmaps; + + /* Number of bitmapped commits */ + uint32_t entry_count; + + /* Name-hash cache (or NULL if not present). */ + uint32_t *hashes; + + /* + * Extended index. + * + * When trying to perform bitmap operations with objects that are not + * packed in `pack`, these objects are added to this "fake index" and + * are assumed to appear at the end of the packfile for all operations + */ + struct eindex { + struct object **objects; + uint32_t *hashes; + uint32_t count, alloc; + khash_sha1_pos *positions; + } ext_index; + + /* Bitmap result of the last performed walk */ + struct bitmap *result; + + /* Version of the bitmap index */ + unsigned int version; + + unsigned loaded : 1; + +} bitmap_git; + +static struct ewah_bitmap *lookup_stored_bitmap(struct stored_bitmap *st) +{ + struct ewah_bitmap *parent; + struct ewah_bitmap *composed; + + if (st->xor == NULL) + return st->root; + + composed = ewah_pool_new(); + parent = lookup_stored_bitmap(st->xor); + ewah_xor(st->root, parent, composed); + + ewah_pool_free(st->root); + st->root = composed; + st->xor = NULL; + + return composed; +} + +/* + * Read a bitmap from the current read position on the mmaped + * index, and increase the read position accordingly + */ +static struct ewah_bitmap *read_bitmap_1(struct bitmap_index *index) +{ + struct ewah_bitmap *b = ewah_pool_new(); + + int bitmap_size = ewah_read_mmap(b, + index->map + index->map_pos, + index->map_size - index->map_pos); + + if (bitmap_size < 0) { + error("Failed to load bitmap index (corrupted?)"); + ewah_pool_free(b); + return NULL; + } + + index->map_pos += bitmap_size; + return b; +} + +static int load_bitmap_header(struct bitmap_index *index) +{ + struct bitmap_disk_header *header = (void *)index->map; + + if (index->map_size < sizeof(*header) + 20) + return error("Corrupted bitmap index (missing header data)"); + + if (memcmp(header->magic, BITMAP_IDX_SIGNATURE, sizeof(BITMAP_IDX_SIGNATURE)) != 0) + return error("Corrupted bitmap index file (wrong header)"); + + index->version = ntohs(header->version); + if (index->version != 1) + return error("Unsupported version for bitmap index file (%d)", index->version); + + /* Parse known bitmap format options */ + { + uint32_t flags = ntohs(header->options); + + if ((flags & BITMAP_OPT_FULL_DAG) == 0) + return error("Unsupported options for bitmap index file " + "(Git requires BITMAP_OPT_FULL_DAG)"); + + if (flags & BITMAP_OPT_HASH_CACHE) { + unsigned char *end = index->map + index->map_size - 20; + index->hashes = ((uint32_t *)end) - index->pack->num_objects; + } + } + + index->entry_count = ntohl(header->entry_count); + index->map_pos += sizeof(*header); + return 0; +} + +static struct stored_bitmap *store_bitmap(struct bitmap_index *index, + struct ewah_bitmap *root, + const unsigned char *sha1, + struct stored_bitmap *xor_with, + int flags) +{ + struct stored_bitmap *stored; + khiter_t hash_pos; + int ret; + + stored = xmalloc(sizeof(struct stored_bitmap)); + stored->root = root; + stored->xor = xor_with; + stored->flags = flags; + hashcpy(stored->sha1, sha1); + + hash_pos = kh_put_sha1(index->bitmaps, stored->sha1, &ret); + + /* a 0 return code means the insertion succeeded with no changes, + * because the SHA1 already existed on the map. this is bad, there + * shouldn't be duplicated commits in the index */ + if (ret == 0) { + error("Duplicate entry in bitmap index: %s", sha1_to_hex(sha1)); + return NULL; + } + + kh_value(index->bitmaps, hash_pos) = stored; + return stored; +} + +static int load_bitmap_entries_v1(struct bitmap_index *index) +{ + static const size_t MAX_XOR_OFFSET = 160; + + uint32_t i; + struct stored_bitmap **recent_bitmaps; + struct bitmap_disk_entry *entry; + + recent_bitmaps = xcalloc(MAX_XOR_OFFSET, sizeof(struct stored_bitmap)); + + for (i = 0; i < index->entry_count; ++i) { + int xor_offset, flags; + struct ewah_bitmap *bitmap = NULL; + struct stored_bitmap *xor_bitmap = NULL; + uint32_t commit_idx_pos; + const unsigned char *sha1; + + entry = (struct bitmap_disk_entry *)(index->map + index->map_pos); + index->map_pos += sizeof(struct bitmap_disk_entry); + + commit_idx_pos = ntohl(entry->object_pos); + sha1 = nth_packed_object_sha1(index->pack, commit_idx_pos); + + xor_offset = (int)entry->xor_offset; + flags = (int)entry->flags; + + bitmap = read_bitmap_1(index); + if (!bitmap) + return -1; + + if (xor_offset > MAX_XOR_OFFSET || xor_offset > i) + return error("Corrupted bitmap pack index"); + + if (xor_offset > 0) { + xor_bitmap = recent_bitmaps[(i - xor_offset) % MAX_XOR_OFFSET]; + + if (xor_bitmap == NULL) + return error("Invalid XOR offset in bitmap pack index"); + } + + recent_bitmaps[i % MAX_XOR_OFFSET] = store_bitmap( + index, bitmap, sha1, xor_bitmap, flags); + } + + return 0; +} + +static int open_pack_bitmap_1(struct packed_git *packfile) +{ + int fd; + struct stat st; + char *idx_name; + + if (open_pack_index(packfile)) + return -1; + + idx_name = pack_bitmap_filename(packfile); + fd = git_open_noatime(idx_name); + free(idx_name); + + if (fd < 0) + return -1; + + if (fstat(fd, &st)) { + close(fd); + return -1; + } + + if (bitmap_git.pack) { + warning("ignoring extra bitmap file: %s", packfile->pack_name); + close(fd); + return -1; + } + + bitmap_git.pack = packfile; + bitmap_git.map_size = xsize_t(st.st_size); + bitmap_git.map = xmmap(NULL, bitmap_git.map_size, PROT_READ, MAP_PRIVATE, fd, 0); + bitmap_git.map_pos = 0; + close(fd); + + if (load_bitmap_header(&bitmap_git) < 0) { + munmap(bitmap_git.map, bitmap_git.map_size); + bitmap_git.map = NULL; + bitmap_git.map_size = 0; + return -1; + } + + return 0; +} + +static int load_pack_bitmap(void) +{ + assert(bitmap_git.map && !bitmap_git.loaded); + + bitmap_git.bitmaps = kh_init_sha1(); + bitmap_git.ext_index.positions = kh_init_sha1_pos(); + bitmap_git.reverse_index = revindex_for_pack(bitmap_git.pack); + + if (!(bitmap_git.commits = read_bitmap_1(&bitmap_git)) || + !(bitmap_git.trees = read_bitmap_1(&bitmap_git)) || + !(bitmap_git.blobs = read_bitmap_1(&bitmap_git)) || + !(bitmap_git.tags = read_bitmap_1(&bitmap_git))) + goto failed; + + if (load_bitmap_entries_v1(&bitmap_git) < 0) + goto failed; + + bitmap_git.loaded = 1; + return 0; + +failed: + munmap(bitmap_git.map, bitmap_git.map_size); + bitmap_git.map = NULL; + bitmap_git.map_size = 0; + return -1; +} + +char *pack_bitmap_filename(struct packed_git *p) +{ + char *idx_name; + int len; + + len = strlen(p->pack_name) - strlen(".pack"); + idx_name = xmalloc(len + strlen(".bitmap") + 1); + + memcpy(idx_name, p->pack_name, len); + memcpy(idx_name + len, ".bitmap", strlen(".bitmap") + 1); + + return idx_name; +} + +static int open_pack_bitmap(void) +{ + struct packed_git *p; + int ret = -1; + + assert(!bitmap_git.map && !bitmap_git.loaded); + + prepare_packed_git(); + for (p = packed_git; p; p = p->next) { + if (open_pack_bitmap_1(p) == 0) + ret = 0; + } + + return ret; +} + +int prepare_bitmap_git(void) +{ + if (bitmap_git.loaded) + return 0; + + if (!open_pack_bitmap()) + return load_pack_bitmap(); + + return -1; +} + +struct include_data { + struct bitmap *base; + struct bitmap *seen; +}; + +static inline int bitmap_position_extended(const unsigned char *sha1) +{ + khash_sha1_pos *positions = bitmap_git.ext_index.positions; + khiter_t pos = kh_get_sha1_pos(positions, sha1); + + if (pos < kh_end(positions)) { + int bitmap_pos = kh_value(positions, pos); + return bitmap_pos + bitmap_git.pack->num_objects; + } + + return -1; +} + +static inline int bitmap_position_packfile(const unsigned char *sha1) +{ + off_t offset = find_pack_entry_one(sha1, bitmap_git.pack); + if (!offset) + return -1; + + return find_revindex_position(bitmap_git.reverse_index, offset); +} + +static int bitmap_position(const unsigned char *sha1) +{ + int pos = bitmap_position_packfile(sha1); + return (pos >= 0) ? pos : bitmap_position_extended(sha1); +} + +static int ext_index_add_object(struct object *object, const char *name) +{ + struct eindex *eindex = &bitmap_git.ext_index; + + khiter_t hash_pos; + int hash_ret; + int bitmap_pos; + + hash_pos = kh_put_sha1_pos(eindex->positions, object->sha1, &hash_ret); + if (hash_ret > 0) { + if (eindex->count >= eindex->alloc) { + eindex->alloc = (eindex->alloc + 16) * 3 / 2; + eindex->objects = xrealloc(eindex->objects, + eindex->alloc * sizeof(struct object *)); + eindex->hashes = xrealloc(eindex->hashes, + eindex->alloc * sizeof(uint32_t)); + } + + bitmap_pos = eindex->count; + eindex->objects[eindex->count] = object; + eindex->hashes[eindex->count] = pack_name_hash(name); + kh_value(eindex->positions, hash_pos) = bitmap_pos; + eindex->count++; + } else { + bitmap_pos = kh_value(eindex->positions, hash_pos); + } + + return bitmap_pos + bitmap_git.pack->num_objects; +} + +static void show_object(struct object *object, const struct name_path *path, + const char *last, void *data) +{ + struct bitmap *base = data; + int bitmap_pos; + + bitmap_pos = bitmap_position(object->sha1); + + if (bitmap_pos < 0) { + char *name = path_name(path, last); + bitmap_pos = ext_index_add_object(object, name); + free(name); + } + + bitmap_set(base, bitmap_pos); +} + +static void show_commit(struct commit *commit, void *data) +{ +} + +static int add_to_include_set(struct include_data *data, + const unsigned char *sha1, + int bitmap_pos) +{ + khiter_t hash_pos; + + if (data->seen && bitmap_get(data->seen, bitmap_pos)) + return 0; + + if (bitmap_get(data->base, bitmap_pos)) + return 0; + + hash_pos = kh_get_sha1(bitmap_git.bitmaps, sha1); + if (hash_pos < kh_end(bitmap_git.bitmaps)) { + struct stored_bitmap *st = kh_value(bitmap_git.bitmaps, hash_pos); + bitmap_or_ewah(data->base, lookup_stored_bitmap(st)); + return 0; + } + + bitmap_set(data->base, bitmap_pos); + return 1; +} + +static int should_include(struct commit *commit, void *_data) +{ + struct include_data *data = _data; + int bitmap_pos; + + bitmap_pos = bitmap_position(commit->object.sha1); + if (bitmap_pos < 0) + bitmap_pos = ext_index_add_object((struct object *)commit, NULL); + + if (!add_to_include_set(data, commit->object.sha1, bitmap_pos)) { + struct commit_list *parent = commit->parents; + + while (parent) { + parent->item->object.flags |= SEEN; + parent = parent->next; + } + + return 0; + } + + return 1; +} + +static struct bitmap *find_objects(struct rev_info *revs, + struct object_list *roots, + struct bitmap *seen) +{ + struct bitmap *base = NULL; + int needs_walk = 0; + + struct object_list *not_mapped = NULL; + + /* + * Go through all the roots for the walk. The ones that have bitmaps + * on the bitmap index will be `or`ed together to form an initial + * global reachability analysis. + * + * The ones without bitmaps in the index will be stored in the + * `not_mapped_list` for further processing. + */ + while (roots) { + struct object *object = roots->item; + roots = roots->next; + + if (object->type == OBJ_COMMIT) { + khiter_t pos = kh_get_sha1(bitmap_git.bitmaps, object->sha1); + + if (pos < kh_end(bitmap_git.bitmaps)) { + struct stored_bitmap *st = kh_value(bitmap_git.bitmaps, pos); + struct ewah_bitmap *or_with = lookup_stored_bitmap(st); + + if (base == NULL) + base = ewah_to_bitmap(or_with); + else + bitmap_or_ewah(base, or_with); + + object->flags |= SEEN; + continue; + } + } + + object_list_insert(object, ¬_mapped); + } + + /* + * Best case scenario: We found bitmaps for all the roots, + * so the resulting `or` bitmap has the full reachability analysis + */ + if (not_mapped == NULL) + return base; + + roots = not_mapped; + + /* + * Let's iterate through all the roots that don't have bitmaps to + * check if we can determine them to be reachable from the existing + * global bitmap. + * + * If we cannot find them in the existing global bitmap, we'll need + * to push them to an actual walk and run it until we can confirm + * they are reachable + */ + while (roots) { + struct object *object = roots->item; + int pos; + + roots = roots->next; + pos = bitmap_position(object->sha1); + + if (pos < 0 || base == NULL || !bitmap_get(base, pos)) { + object->flags &= ~UNINTERESTING; + add_pending_object(revs, object, ""); + needs_walk = 1; + } else { + object->flags |= SEEN; + } + } + + if (needs_walk) { + struct include_data incdata; + + if (base == NULL) + base = bitmap_new(); + + incdata.base = base; + incdata.seen = seen; + + revs->include_check = should_include; + revs->include_check_data = &incdata; + + if (prepare_revision_walk(revs)) + die("revision walk setup failed"); + + traverse_commit_list(revs, show_commit, show_object, base); + } + + return base; +} + +static void show_extended_objects(struct bitmap *objects, + show_reachable_fn show_reach) +{ + struct eindex *eindex = &bitmap_git.ext_index; + uint32_t i; + + for (i = 0; i < eindex->count; ++i) { + struct object *obj; + + if (!bitmap_get(objects, bitmap_git.pack->num_objects + i)) + continue; + + obj = eindex->objects[i]; + show_reach(obj->sha1, obj->type, 0, eindex->hashes[i], NULL, 0); + } +} + +static void show_objects_for_type( + struct bitmap *objects, + struct ewah_bitmap *type_filter, + enum object_type object_type, + show_reachable_fn show_reach) +{ + size_t pos = 0, i = 0; + uint32_t offset; + + struct ewah_iterator it; + eword_t filter; + + if (bitmap_git.reuse_objects == bitmap_git.pack->num_objects) + return; + + ewah_iterator_init(&it, type_filter); + + while (i < objects->word_alloc && ewah_iterator_next(&filter, &it)) { + eword_t word = objects->words[i] & filter; + + for (offset = 0; offset < BITS_IN_WORD; ++offset) { + const unsigned char *sha1; + struct revindex_entry *entry; + uint32_t hash = 0; + + if ((word >> offset) == 0) + break; + + offset += ewah_bit_ctz64(word >> offset); + + if (pos + offset < bitmap_git.reuse_objects) + continue; + + entry = &bitmap_git.reverse_index->revindex[pos + offset]; + sha1 = nth_packed_object_sha1(bitmap_git.pack, entry->nr); + + if (bitmap_git.hashes) + hash = ntohl(bitmap_git.hashes[entry->nr]); + + show_reach(sha1, object_type, 0, hash, bitmap_git.pack, entry->offset); + } + + pos += BITS_IN_WORD; + i++; + } +} + +static int in_bitmapped_pack(struct object_list *roots) +{ + while (roots) { + struct object *object = roots->item; + roots = roots->next; + + if (find_pack_entry_one(object->sha1, bitmap_git.pack) > 0) + return 1; + } + + return 0; +} + +int prepare_bitmap_walk(struct rev_info *revs) +{ + unsigned int i; + unsigned int pending_nr = revs->pending.nr; + struct object_array_entry *pending_e = revs->pending.objects; + + struct object_list *wants = NULL; + struct object_list *haves = NULL; + + struct bitmap *wants_bitmap = NULL; + struct bitmap *haves_bitmap = NULL; + + if (!bitmap_git.loaded) { + /* try to open a bitmapped pack, but don't parse it yet + * because we may not need to use it */ + if (open_pack_bitmap() < 0) + return -1; + } + + for (i = 0; i < pending_nr; ++i) { + struct object *object = pending_e[i].item; + + if (object->type == OBJ_NONE) + parse_object_or_die(object->sha1, NULL); + + while (object->type == OBJ_TAG) { + struct tag *tag = (struct tag *) object; + + if (object->flags & UNINTERESTING) + object_list_insert(object, &haves); + else + object_list_insert(object, &wants); + + if (!tag->tagged) + die("bad tag"); + object = parse_object_or_die(tag->tagged->sha1, NULL); + } + + if (object->flags & UNINTERESTING) + object_list_insert(object, &haves); + else + object_list_insert(object, &wants); + } + + /* + * if we have a HAVES list, but none of those haves is contained + * in the packfile that has a bitmap, we don't have anything to + * optimize here + */ + if (haves && !in_bitmapped_pack(haves)) + return -1; + + /* if we don't want anything, we're done here */ + if (!wants) + return -1; + + /* + * now we're going to use bitmaps, so load the actual bitmap entries + * from disk. this is the point of no return; after this the rev_list + * becomes invalidated and we must perform the revwalk through bitmaps + */ + if (!bitmap_git.loaded && load_pack_bitmap() < 0) + return -1; + + revs->pending.nr = 0; + revs->pending.alloc = 0; + revs->pending.objects = NULL; + + if (haves) { + haves_bitmap = find_objects(revs, haves, NULL); + reset_revision_walk(); + + if (haves_bitmap == NULL) + die("BUG: failed to perform bitmap walk"); + } + + wants_bitmap = find_objects(revs, wants, haves_bitmap); + + if (!wants_bitmap) + die("BUG: failed to perform bitmap walk"); + + if (haves_bitmap) + bitmap_and_not(wants_bitmap, haves_bitmap); + + bitmap_git.result = wants_bitmap; + + bitmap_free(haves_bitmap); + return 0; +} + +int reuse_partial_packfile_from_bitmap(struct packed_git **packfile, + uint32_t *entries, + off_t *up_to) +{ + /* + * Reuse the packfile content if we need more than + * 90% of its objects + */ + static const double REUSE_PERCENT = 0.9; + + struct bitmap *result = bitmap_git.result; + uint32_t reuse_threshold; + uint32_t i, reuse_objects = 0; + + assert(result); + + for (i = 0; i < result->word_alloc; ++i) { + if (result->words[i] != (eword_t)~0) { + reuse_objects += ewah_bit_ctz64(~result->words[i]); + break; + } + + reuse_objects += BITS_IN_WORD; + } + +#ifdef GIT_BITMAP_DEBUG + { + const unsigned char *sha1; + struct revindex_entry *entry; + + entry = &bitmap_git.reverse_index->revindex[reuse_objects]; + sha1 = nth_packed_object_sha1(bitmap_git.pack, entry->nr); + + fprintf(stderr, "Failed to reuse at %d (%016llx)\n", + reuse_objects, result->words[i]); + fprintf(stderr, " %s\n", sha1_to_hex(sha1)); + } +#endif + + if (!reuse_objects) + return -1; + + if (reuse_objects >= bitmap_git.pack->num_objects) { + bitmap_git.reuse_objects = *entries = bitmap_git.pack->num_objects; + *up_to = -1; /* reuse the full pack */ + *packfile = bitmap_git.pack; + return 0; + } + + reuse_threshold = bitmap_popcount(bitmap_git.result) * REUSE_PERCENT; + + if (reuse_objects < reuse_threshold) + return -1; + + bitmap_git.reuse_objects = *entries = reuse_objects; + *up_to = bitmap_git.reverse_index->revindex[reuse_objects].offset; + *packfile = bitmap_git.pack; + + return 0; +} + +void traverse_bitmap_commit_list(show_reachable_fn show_reachable) +{ + assert(bitmap_git.result); + + show_objects_for_type(bitmap_git.result, bitmap_git.commits, + OBJ_COMMIT, show_reachable); + show_objects_for_type(bitmap_git.result, bitmap_git.trees, + OBJ_TREE, show_reachable); + show_objects_for_type(bitmap_git.result, bitmap_git.blobs, + OBJ_BLOB, show_reachable); + show_objects_for_type(bitmap_git.result, bitmap_git.tags, + OBJ_TAG, show_reachable); + + show_extended_objects(bitmap_git.result, show_reachable); + + bitmap_free(bitmap_git.result); + bitmap_git.result = NULL; +} + +static uint32_t count_object_type(struct bitmap *objects, + enum object_type type) +{ + struct eindex *eindex = &bitmap_git.ext_index; + + uint32_t i = 0, count = 0; + struct ewah_iterator it; + eword_t filter; + + switch (type) { + case OBJ_COMMIT: + ewah_iterator_init(&it, bitmap_git.commits); + break; + + case OBJ_TREE: + ewah_iterator_init(&it, bitmap_git.trees); + break; + + case OBJ_BLOB: + ewah_iterator_init(&it, bitmap_git.blobs); + break; + + case OBJ_TAG: + ewah_iterator_init(&it, bitmap_git.tags); + break; + + default: + return 0; + } + + while (i < objects->word_alloc && ewah_iterator_next(&filter, &it)) { + eword_t word = objects->words[i++] & filter; + count += ewah_bit_popcount64(word); + } + + for (i = 0; i < eindex->count; ++i) { + if (eindex->objects[i]->type == type && + bitmap_get(objects, bitmap_git.pack->num_objects + i)) + count++; + } + + return count; +} + +void count_bitmap_commit_list(uint32_t *commits, uint32_t *trees, + uint32_t *blobs, uint32_t *tags) +{ + assert(bitmap_git.result); + + if (commits) + *commits = count_object_type(bitmap_git.result, OBJ_COMMIT); + + if (trees) + *trees = count_object_type(bitmap_git.result, OBJ_TREE); + + if (blobs) + *blobs = count_object_type(bitmap_git.result, OBJ_BLOB); + + if (tags) + *tags = count_object_type(bitmap_git.result, OBJ_TAG); +} + +struct bitmap_test_data { + struct bitmap *base; + struct progress *prg; + size_t seen; +}; + +static void test_show_object(struct object *object, + const struct name_path *path, + const char *last, void *data) +{ + struct bitmap_test_data *tdata = data; + int bitmap_pos; + + bitmap_pos = bitmap_position(object->sha1); + if (bitmap_pos < 0) + die("Object not in bitmap: %s\n", sha1_to_hex(object->sha1)); + + bitmap_set(tdata->base, bitmap_pos); + display_progress(tdata->prg, ++tdata->seen); +} + +static void test_show_commit(struct commit *commit, void *data) +{ + struct bitmap_test_data *tdata = data; + int bitmap_pos; + + bitmap_pos = bitmap_position(commit->object.sha1); + if (bitmap_pos < 0) + die("Object not in bitmap: %s\n", sha1_to_hex(commit->object.sha1)); + + bitmap_set(tdata->base, bitmap_pos); + display_progress(tdata->prg, ++tdata->seen); +} + +void test_bitmap_walk(struct rev_info *revs) +{ + struct object *root; + struct bitmap *result = NULL; + khiter_t pos; + size_t result_popcnt; + struct bitmap_test_data tdata; + + if (prepare_bitmap_git()) + die("failed to load bitmap indexes"); + + if (revs->pending.nr != 1) + die("you must specify exactly one commit to test"); + + fprintf(stderr, "Bitmap v%d test (%d entries loaded)\n", + bitmap_git.version, bitmap_git.entry_count); + + root = revs->pending.objects[0].item; + pos = kh_get_sha1(bitmap_git.bitmaps, root->sha1); + + if (pos < kh_end(bitmap_git.bitmaps)) { + struct stored_bitmap *st = kh_value(bitmap_git.bitmaps, pos); + struct ewah_bitmap *bm = lookup_stored_bitmap(st); + + fprintf(stderr, "Found bitmap for %s. %d bits / %08x checksum\n", + sha1_to_hex(root->sha1), (int)bm->bit_size, ewah_checksum(bm)); + + result = ewah_to_bitmap(bm); + } + + if (result == NULL) + die("Commit %s doesn't have an indexed bitmap", sha1_to_hex(root->sha1)); + + revs->tag_objects = 1; + revs->tree_objects = 1; + revs->blob_objects = 1; + + result_popcnt = bitmap_popcount(result); + + if (prepare_revision_walk(revs)) + die("revision walk setup failed"); + + tdata.base = bitmap_new(); + tdata.prg = start_progress("Verifying bitmap entries", result_popcnt); + tdata.seen = 0; + + traverse_commit_list(revs, &test_show_commit, &test_show_object, &tdata); + + stop_progress(&tdata.prg); + + if (bitmap_equals(result, tdata.base)) + fprintf(stderr, "OK!\n"); + else + fprintf(stderr, "Mismatch!\n"); +} + +static int rebuild_bitmap(uint32_t *reposition, + struct ewah_bitmap *source, + struct bitmap *dest) +{ + uint32_t pos = 0; + struct ewah_iterator it; + eword_t word; + + ewah_iterator_init(&it, source); + + while (ewah_iterator_next(&word, &it)) { + uint32_t offset, bit_pos; + + for (offset = 0; offset < BITS_IN_WORD; ++offset) { + if ((word >> offset) == 0) + break; + + offset += ewah_bit_ctz64(word >> offset); + + bit_pos = reposition[pos + offset]; + if (bit_pos > 0) + bitmap_set(dest, bit_pos - 1); + else /* can't reuse, we don't have the object */ + return -1; + } + + pos += BITS_IN_WORD; + } + return 0; +} + +int rebuild_existing_bitmaps(struct packing_data *mapping, + khash_sha1 *reused_bitmaps, + int show_progress) +{ + uint32_t i, num_objects; + uint32_t *reposition; + struct bitmap *rebuild; + struct stored_bitmap *stored; + struct progress *progress = NULL; + + khiter_t hash_pos; + int hash_ret; + + if (prepare_bitmap_git() < 0) + return -1; + + num_objects = bitmap_git.pack->num_objects; + reposition = xcalloc(num_objects, sizeof(uint32_t)); + + for (i = 0; i < num_objects; ++i) { + const unsigned char *sha1; + struct revindex_entry *entry; + struct object_entry *oe; + + entry = &bitmap_git.reverse_index->revindex[i]; + sha1 = nth_packed_object_sha1(bitmap_git.pack, entry->nr); + oe = packlist_find(mapping, sha1, NULL); + + if (oe) + reposition[i] = oe->in_pack_pos + 1; + } + + rebuild = bitmap_new(); + i = 0; + + if (show_progress) + progress = start_progress("Reusing bitmaps", 0); + + kh_foreach_value(bitmap_git.bitmaps, stored, { + if (stored->flags & BITMAP_FLAG_REUSE) { + if (!rebuild_bitmap(reposition, + lookup_stored_bitmap(stored), + rebuild)) { + hash_pos = kh_put_sha1(reused_bitmaps, + stored->sha1, + &hash_ret); + kh_value(reused_bitmaps, hash_pos) = + bitmap_to_ewah(rebuild); + } + bitmap_reset(rebuild); + display_progress(progress, ++i); + } + }); + + stop_progress(&progress); + + free(reposition); + bitmap_free(rebuild); + return 0; +} diff --git a/pack-bitmap.h b/pack-bitmap.h new file mode 100644 index 0000000000..8b7f4e9f0d --- /dev/null +++ b/pack-bitmap.h @@ -0,0 +1,64 @@ +#ifndef PACK_BITMAP_H +#define PACK_BITMAP_H + +#include "ewah/ewok.h" +#include "khash.h" +#include "pack-objects.h" + +struct bitmap_disk_entry { + uint32_t object_pos; + uint8_t xor_offset; + uint8_t flags; +} __attribute__((packed)); + +struct bitmap_disk_header { + char magic[4]; + uint16_t version; + uint16_t options; + uint32_t entry_count; + unsigned char checksum[20]; +}; + +static const char BITMAP_IDX_SIGNATURE[] = {'B', 'I', 'T', 'M'}; + +#define NEEDS_BITMAP (1u<<22) + +enum pack_bitmap_opts { + BITMAP_OPT_FULL_DAG = 1, + BITMAP_OPT_HASH_CACHE = 4, +}; + +enum pack_bitmap_flags { + BITMAP_FLAG_REUSE = 0x1 +}; + +typedef int (*show_reachable_fn)( + const unsigned char *sha1, + enum object_type type, + int flags, + uint32_t hash, + struct packed_git *found_pack, + off_t found_offset); + +int prepare_bitmap_git(void); +void count_bitmap_commit_list(uint32_t *commits, uint32_t *trees, uint32_t *blobs, uint32_t *tags); +void traverse_bitmap_commit_list(show_reachable_fn show_reachable); +void test_bitmap_walk(struct rev_info *revs); +char *pack_bitmap_filename(struct packed_git *p); +int prepare_bitmap_walk(struct rev_info *revs); +int reuse_partial_packfile_from_bitmap(struct packed_git **packfile, uint32_t *entries, off_t *up_to); +int rebuild_existing_bitmaps(struct packing_data *mapping, khash_sha1 *reused_bitmaps, int show_progress); + +void bitmap_writer_show_progress(int show); +void bitmap_writer_set_checksum(unsigned char *sha1); +void bitmap_writer_build_type_index(struct pack_idx_entry **index, uint32_t index_nr); +void bitmap_writer_reuse_bitmaps(struct packing_data *to_pack); +void bitmap_writer_select_commits(struct commit **indexed_commits, + unsigned int indexed_commits_nr, int max_bitmaps); +void bitmap_writer_build(struct packing_data *to_pack); +void bitmap_writer_finish(struct pack_idx_entry **index, + uint32_t index_nr, + const char *filename, + uint16_t options); + +#endif diff --git a/pack-objects.c b/pack-objects.c new file mode 100644 index 0000000000..d01d851ce9 --- /dev/null +++ b/pack-objects.c @@ -0,0 +1,111 @@ +#include "cache.h" +#include "object.h" +#include "pack.h" +#include "pack-objects.h" + +static uint32_t locate_object_entry_hash(struct packing_data *pdata, + const unsigned char *sha1, + int *found) +{ + uint32_t i, hash, mask = (pdata->index_size - 1); + + memcpy(&hash, sha1, sizeof(uint32_t)); + i = hash & mask; + + while (pdata->index[i] > 0) { + uint32_t pos = pdata->index[i] - 1; + + if (!hashcmp(sha1, pdata->objects[pos].idx.sha1)) { + *found = 1; + return i; + } + + i = (i + 1) & mask; + } + + *found = 0; + return i; +} + +static inline uint32_t closest_pow2(uint32_t v) +{ + v = v - 1; + v |= v >> 1; + v |= v >> 2; + v |= v >> 4; + v |= v >> 8; + v |= v >> 16; + return v + 1; +} + +static void rehash_objects(struct packing_data *pdata) +{ + uint32_t i; + struct object_entry *entry; + + pdata->index_size = closest_pow2(pdata->nr_objects * 3); + if (pdata->index_size < 1024) + pdata->index_size = 1024; + + pdata->index = xrealloc(pdata->index, sizeof(uint32_t) * pdata->index_size); + memset(pdata->index, 0, sizeof(int) * pdata->index_size); + + entry = pdata->objects; + + for (i = 0; i < pdata->nr_objects; i++) { + int found; + uint32_t ix = locate_object_entry_hash(pdata, entry->idx.sha1, &found); + + if (found) + die("BUG: Duplicate object in hash"); + + pdata->index[ix] = i + 1; + entry++; + } +} + +struct object_entry *packlist_find(struct packing_data *pdata, + const unsigned char *sha1, + uint32_t *index_pos) +{ + uint32_t i; + int found; + + if (!pdata->index_size) + return NULL; + + i = locate_object_entry_hash(pdata, sha1, &found); + + if (index_pos) + *index_pos = i; + + if (!found) + return NULL; + + return &pdata->objects[pdata->index[i] - 1]; +} + +struct object_entry *packlist_alloc(struct packing_data *pdata, + const unsigned char *sha1, + uint32_t index_pos) +{ + struct object_entry *new_entry; + + if (pdata->nr_objects >= pdata->nr_alloc) { + pdata->nr_alloc = (pdata->nr_alloc + 1024) * 3 / 2; + pdata->objects = xrealloc(pdata->objects, + pdata->nr_alloc * sizeof(*new_entry)); + } + + new_entry = pdata->objects + pdata->nr_objects++; + + memset(new_entry, 0, sizeof(*new_entry)); + hashcpy(new_entry->idx.sha1, sha1); + + if (pdata->index_size * 3 <= pdata->nr_objects * 4) + rehash_objects(pdata); + else + pdata->index[index_pos] = pdata->nr_objects; + + return new_entry; +} diff --git a/pack-objects.h b/pack-objects.h new file mode 100644 index 0000000000..d1b98b30ff --- /dev/null +++ b/pack-objects.h @@ -0,0 +1,68 @@ +#ifndef PACK_OBJECTS_H +#define PACK_OBJECTS_H + +struct object_entry { + struct pack_idx_entry idx; + unsigned long size; /* uncompressed size */ + struct packed_git *in_pack; /* already in pack */ + off_t in_pack_offset; + struct object_entry *delta; /* delta base object */ + struct object_entry *delta_child; /* deltified objects who bases me */ + struct object_entry *delta_sibling; /* other deltified objects who + * uses the same base as me + */ + void *delta_data; /* cached delta (uncompressed) */ + unsigned long delta_size; /* delta data size (uncompressed) */ + unsigned long z_delta_size; /* delta data size (compressed) */ + enum object_type type; + enum object_type in_pack_type; /* could be delta */ + uint32_t hash; /* name hint hash */ + unsigned int in_pack_pos; + unsigned char in_pack_header_size; + unsigned preferred_base:1; /* + * we do not pack this, but is available + * to be used as the base object to delta + * objects against. + */ + unsigned no_try_delta:1; + unsigned tagged:1; /* near the very tip of refs */ + unsigned filled:1; /* assigned write-order */ +}; + +struct packing_data { + struct object_entry *objects; + uint32_t nr_objects, nr_alloc; + + int32_t *index; + uint32_t index_size; +}; + +struct object_entry *packlist_alloc(struct packing_data *pdata, + const unsigned char *sha1, + uint32_t index_pos); + +struct object_entry *packlist_find(struct packing_data *pdata, + const unsigned char *sha1, + uint32_t *index_pos); + +static inline uint32_t pack_name_hash(const char *name) +{ + uint32_t c, hash = 0; + + if (!name) + return 0; + + /* + * This effectively just creates a sortable number from the + * last sixteen non-whitespace characters. Last characters + * count "most", so things that end in ".c" sort together. + */ + while ((c = *name++) != 0) { + if (isspace(c)) + continue; + hash = (hash >> 2) + (c << 24); + } + return hash; +} + +#endif diff --git a/pack-revindex.c b/pack-revindex.c index b4d2b35bb3..5bd7c61980 100644 --- a/pack-revindex.c +++ b/pack-revindex.c @@ -16,11 +16,6 @@ * get the object sha1 from the main index. */ -struct pack_revindex { - struct packed_git *p; - struct revindex_entry *revindex; -}; - static struct pack_revindex *pack_revindex; static int pack_revindex_hashsz; @@ -201,15 +196,14 @@ static void create_pack_revindex(struct pack_revindex *rix) sort_revindex(rix->revindex, num_ent, p->pack_size); } -struct revindex_entry *find_pack_revindex(struct packed_git *p, off_t ofs) +struct pack_revindex *revindex_for_pack(struct packed_git *p) { int num; - unsigned lo, hi; struct pack_revindex *rix; - struct revindex_entry *revindex; if (!pack_revindex_hashsz) init_pack_revindex(); + num = pack_revindex_ix(p); if (num < 0) die("internal error: pack revindex fubar"); @@ -217,30 +211,37 @@ struct revindex_entry *find_pack_revindex(struct packed_git *p, off_t ofs) rix = &pack_revindex[num]; if (!rix->revindex) create_pack_revindex(rix); - revindex = rix->revindex; - lo = 0; - hi = p->num_objects + 1; + return rix; +} + +int find_revindex_position(struct pack_revindex *pridx, off_t ofs) +{ + int lo = 0; + int hi = pridx->p->num_objects + 1; + struct revindex_entry *revindex = pridx->revindex; + do { unsigned mi = lo + (hi - lo) / 2; if (revindex[mi].offset == ofs) { - return revindex + mi; + return mi; } else if (ofs < revindex[mi].offset) hi = mi; else lo = mi + 1; } while (lo < hi); + error("bad offset for revindex"); - return NULL; + return -1; } -void discard_revindex(void) +struct revindex_entry *find_pack_revindex(struct packed_git *p, off_t ofs) { - if (pack_revindex_hashsz) { - int i; - for (i = 0; i < pack_revindex_hashsz; i++) - free(pack_revindex[i].revindex); - free(pack_revindex); - pack_revindex_hashsz = 0; - } + struct pack_revindex *pridx = revindex_for_pack(p); + int pos = find_revindex_position(pridx, ofs); + + if (pos < 0) + return NULL; + + return pridx->revindex + pos; } diff --git a/pack-revindex.h b/pack-revindex.h index 8d5027ad91..d737f98965 100644 --- a/pack-revindex.h +++ b/pack-revindex.h @@ -6,7 +6,14 @@ struct revindex_entry { unsigned int nr; }; +struct pack_revindex { + struct packed_git *p; + struct revindex_entry *revindex; +}; + +struct pack_revindex *revindex_for_pack(struct packed_git *p); +int find_revindex_position(struct pack_revindex *pridx, off_t ofs); + struct revindex_entry *find_pack_revindex(struct packed_git *p, off_t ofs); -void discard_revindex(void); #endif diff --git a/pack-write.c b/pack-write.c index 605d01b25c..9b8308b759 100644 --- a/pack-write.c +++ b/pack-write.c @@ -364,5 +364,7 @@ void finish_tmp_packfile(char *name_buffer, if (rename(idx_tmp_name, name_buffer)) die_errno("unable to rename temporary index file"); + *end_of_name_prefix = '\0'; + free((void *)idx_tmp_name); } @@ -265,12 +265,12 @@ static struct passwd *getpw_str(const char *username, size_t len) char *expand_user_path(const char *path) { struct strbuf user_path = STRBUF_INIT; - const char *first_slash = strchrnul(path, '/'); const char *to_copy = path; if (path == NULL) goto return_null; if (path[0] == '~') { + const char *first_slash = strchrnul(path, '/'); const char *username = path + 1; size_t username_len = first_slash - username; if (username_len == 0) { diff --git a/pathspec.c b/pathspec.c index 6cb9fd3014..8043099955 100644 --- a/pathspec.c +++ b/pathspec.c @@ -33,7 +33,7 @@ void add_pathspec_matches_against_index(const struct pathspec *pathspec, return; for (i = 0; i < active_nr; i++) { const struct cache_entry *ce = active_cache[i]; - match_pathspec_depth(pathspec, ce->name, ce_namelen(ce), 0, seen); + ce_path_match(ce, pathspec, seen); } } @@ -1075,7 +1075,7 @@ msgstr "Votre branche est basée sur '%s', mais la branche amont a disparu.\n" #: remote.c:1875 msgid " (use \"git branch --unset-upstream\" to fixup)\n" -msgstr " (utilisez \"git branch -unset-upstream\" pour corriger)\n" +msgstr " (utilisez \"git branch --unset-upstream\" pour corriger)\n" #: remote.c:1878 #, c-format @@ -3266,7 +3266,7 @@ msgstr " git branch -d %s\n" #: builtin/branch.c:1027 #, c-format msgid " git branch --set-upstream-to %s\n" -msgstr " git branch -set-upstream-to %s\n" +msgstr " git branch --set-upstream-to %s\n" #: builtin/bundle.c:47 #, c-format diff --git a/preload-index.c b/preload-index.c index 8c44ceb2c7..968ee25eae 100644 --- a/preload-index.c +++ b/preload-index.c @@ -3,6 +3,7 @@ */ #include "cache.h" #include "pathspec.h" +#include "dir.h" #ifdef NO_PTHREADS static void preload_index(struct index_state *index, @@ -53,7 +54,7 @@ static void *preload_thread(void *_data) continue; if (ce_uptodate(ce)) continue; - if (!ce_path_match(ce, &p->pathspec)) + if (!ce_path_match(ce, &p->pathspec, NULL)) continue; if (threaded_has_symlink_leading_path(&cache, ce->name, ce_namelen(ce))) continue; diff --git a/read-cache.c b/read-cache.c index 33dd676ccb..fb440b4d9d 100644 --- a/read-cache.c +++ b/read-cache.c @@ -15,7 +15,8 @@ #include "strbuf.h" #include "varint.h" -static struct cache_entry *refresh_cache_entry(struct cache_entry *ce, int really); +static struct cache_entry *refresh_cache_entry(struct cache_entry *ce, + unsigned int options); /* Mask for the name length in ce_flags in the on-disk index */ @@ -47,6 +48,7 @@ static void replace_index_entry(struct index_state *istate, int nr, struct cache struct cache_entry *old = istate->cache[nr]; remove_name_hash(istate, old); + free(old); set_index_entry(istate, nr, ce); istate->cache_changed = 1; } @@ -58,7 +60,7 @@ void rename_index_entry_at(struct index_state *istate, int nr, const char *new_n new = xmalloc(cache_entry_size(namelen)); copy_cache_entry(new, old); - new->ce_flags &= ~CE_STATE_MASK; + new->ce_flags &= ~CE_HASHED; new->ce_namelen = namelen; memcpy(new->name, new_name, namelen + 1); @@ -478,6 +480,7 @@ int remove_index_entry_at(struct index_state *istate, int pos) record_resolve_undo(istate, ce); remove_name_hash(istate, ce); + free(ce); istate->cache_changed = 1; istate->cache_nr--; if (pos >= istate->cache_nr) @@ -499,8 +502,10 @@ void remove_marked_cache_entries(struct index_state *istate) unsigned int i, j; for (i = j = 0; i < istate->cache_nr; i++) { - if (ce_array[i]->ce_flags & CE_REMOVE) + if (ce_array[i]->ce_flags & CE_REMOVE) { remove_name_hash(istate, ce_array[i]); + free(ce_array[i]); + } else ce_array[j++] = ce_array[i]; } @@ -579,7 +584,7 @@ static struct cache_entry *create_alias_ce(struct cache_entry *ce, struct cache_ return new; } -static void record_intent_to_add(struct cache_entry *ce) +void set_object_name_for_intent_to_add_entry(struct cache_entry *ce) { unsigned char sha1[20]; if (write_sha1_file("", 0, blob_type, sha1)) @@ -665,7 +670,7 @@ int add_to_index(struct index_state *istate, const char *path, struct stat *st, if (index_path(ce->sha1, path, st, HASH_WRITE_OBJECT)) return error("unable to index file %s", path); } else - record_intent_to_add(ce); + set_object_name_for_intent_to_add_entry(ce); if (ignore_case && alias && different_name(ce, alias)) ce = create_alias_ce(ce, alias); @@ -696,7 +701,7 @@ int add_file_to_index(struct index_state *istate, const char *path, int flags) struct cache_entry *make_cache_entry(unsigned int mode, const unsigned char *sha1, const char *path, int stage, - int refresh) + unsigned int refresh_options) { int size, len; struct cache_entry *ce; @@ -716,10 +721,7 @@ struct cache_entry *make_cache_entry(unsigned int mode, ce->ce_namelen = len; ce->ce_mode = create_ce_mode(mode); - if (refresh) - return refresh_cache_entry(ce, 0); - - return ce; + return refresh_cache_entry(ce, refresh_options); } int ce_same_name(const struct cache_entry *a, const struct cache_entry *b) @@ -728,11 +730,6 @@ int ce_same_name(const struct cache_entry *a, const struct cache_entry *b) return ce_namelen(b) == len && !memcmp(a->name, b->name, len); } -int ce_path_match(const struct cache_entry *ce, const struct pathspec *pathspec) -{ - return match_pathspec_depth(pathspec, ce->name, ce_namelen(ce), 0, NULL); -} - /* * We fundamentally don't like some paths: we don't want * dot or dot-dot anywhere, and for obvious reasons don't @@ -1029,10 +1026,12 @@ static struct cache_entry *refresh_cache_ent(struct index_state *istate, struct stat st; struct cache_entry *updated; int changed, size; + int refresh = options & CE_MATCH_REFRESH; int ignore_valid = options & CE_MATCH_IGNORE_VALID; int ignore_skip_worktree = options & CE_MATCH_IGNORE_SKIP_WORKTREE; + int ignore_missing = options & CE_MATCH_IGNORE_MISSING; - if (ce_uptodate(ce)) + if (!refresh || ce_uptodate(ce)) return ce; /* @@ -1050,6 +1049,8 @@ static struct cache_entry *refresh_cache_ent(struct index_state *istate, } if (lstat(ce->name, &st) < 0) { + if (ignore_missing && errno == ENOENT) + return ce; if (err) *err = errno; return NULL; @@ -1127,7 +1128,9 @@ int refresh_index(struct index_state *istate, unsigned int flags, int ignore_submodules = (flags & REFRESH_IGNORE_SUBMODULES) != 0; int first = 1; int in_porcelain = (flags & REFRESH_IN_PORCELAIN); - unsigned int options = really ? CE_MATCH_IGNORE_VALID : 0; + unsigned int options = (CE_MATCH_REFRESH | + (really ? CE_MATCH_IGNORE_VALID : 0) | + (not_new ? CE_MATCH_IGNORE_MISSING : 0)); const char *modified_fmt; const char *deleted_fmt; const char *typechange_fmt; @@ -1149,8 +1152,7 @@ int refresh_index(struct index_state *istate, unsigned int flags, if (ignore_submodules && S_ISGITLINK(ce->ce_mode)) continue; - if (pathspec && - !match_pathspec_depth(pathspec, ce->name, ce_namelen(ce), 0, seen)) + if (pathspec && !ce_path_match(ce, pathspec, seen)) filtered = 1; if (ce_stage(ce)) { @@ -1176,8 +1178,6 @@ int refresh_index(struct index_state *istate, unsigned int flags, if (!new) { const char *fmt; - if (not_new && cache_errno == ENOENT) - continue; if (really && cache_errno == EINVAL) { /* If we are doing --really-refresh that * means the index is not valid anymore. @@ -1207,9 +1207,10 @@ int refresh_index(struct index_state *istate, unsigned int flags, return has_errors; } -static struct cache_entry *refresh_cache_entry(struct cache_entry *ce, int really) +static struct cache_entry *refresh_cache_entry(struct cache_entry *ce, + unsigned int options) { - return refresh_cache_ent(&the_index, ce, really, NULL, NULL); + return refresh_cache_ent(&the_index, ce, options, NULL, NULL); } @@ -1313,26 +1314,6 @@ int read_index(struct index_state *istate) return read_index_from(istate, get_index_file()); } -#ifndef NEEDS_ALIGNED_ACCESS -#define ntoh_s(var) ntohs(var) -#define ntoh_l(var) ntohl(var) -#else -static inline uint16_t ntoh_s_force_align(void *p) -{ - uint16_t x; - memcpy(&x, p, sizeof(x)); - return ntohs(x); -} -static inline uint32_t ntoh_l_force_align(void *p) -{ - uint32_t x; - memcpy(&x, p, sizeof(x)); - return ntohl(x); -} -#define ntoh_s(var) ntoh_s_force_align(&(var)) -#define ntoh_l(var) ntoh_l_force_align(&(var)) -#endif - static struct cache_entry *cache_entry_from_ondisk(struct ondisk_cache_entry *ondisk, unsigned int flags, const char *name, @@ -1340,16 +1321,16 @@ static struct cache_entry *cache_entry_from_ondisk(struct ondisk_cache_entry *on { struct cache_entry *ce = xmalloc(cache_entry_size(len)); - ce->ce_stat_data.sd_ctime.sec = ntoh_l(ondisk->ctime.sec); - ce->ce_stat_data.sd_mtime.sec = ntoh_l(ondisk->mtime.sec); - ce->ce_stat_data.sd_ctime.nsec = ntoh_l(ondisk->ctime.nsec); - ce->ce_stat_data.sd_mtime.nsec = ntoh_l(ondisk->mtime.nsec); - ce->ce_stat_data.sd_dev = ntoh_l(ondisk->dev); - ce->ce_stat_data.sd_ino = ntoh_l(ondisk->ino); - ce->ce_mode = ntoh_l(ondisk->mode); - ce->ce_stat_data.sd_uid = ntoh_l(ondisk->uid); - ce->ce_stat_data.sd_gid = ntoh_l(ondisk->gid); - ce->ce_stat_data.sd_size = ntoh_l(ondisk->size); + ce->ce_stat_data.sd_ctime.sec = get_be32(&ondisk->ctime.sec); + ce->ce_stat_data.sd_mtime.sec = get_be32(&ondisk->mtime.sec); + ce->ce_stat_data.sd_ctime.nsec = get_be32(&ondisk->ctime.nsec); + ce->ce_stat_data.sd_mtime.nsec = get_be32(&ondisk->mtime.nsec); + ce->ce_stat_data.sd_dev = get_be32(&ondisk->dev); + ce->ce_stat_data.sd_ino = get_be32(&ondisk->ino); + ce->ce_mode = get_be32(&ondisk->mode); + ce->ce_stat_data.sd_uid = get_be32(&ondisk->uid); + ce->ce_stat_data.sd_gid = get_be32(&ondisk->gid); + ce->ce_stat_data.sd_size = get_be32(&ondisk->size); ce->ce_flags = flags & ~CE_NAMEMASK; ce->ce_namelen = len; hashcpy(ce->sha1, ondisk->sha1); @@ -1389,14 +1370,14 @@ static struct cache_entry *create_from_disk(struct ondisk_cache_entry *ondisk, unsigned int flags; /* On-disk flags are just 16 bits */ - flags = ntoh_s(ondisk->flags); + flags = get_be16(&ondisk->flags); len = flags & CE_NAMEMASK; if (flags & CE_EXTENDED) { struct ondisk_cache_entry_extended *ondisk2; int extended_flags; ondisk2 = (struct ondisk_cache_entry_extended *)ondisk; - extended_flags = ntoh_s(ondisk2->flags2) << 16; + extended_flags = get_be16(&ondisk2->flags2) << 16; /* We do not yet understand any bit out of CE_EXTENDED_FLAGS */ if (extended_flags & ~CE_EXTENDED_FLAGS) die("Unknown index entry format %08x", extended_flags); @@ -1894,7 +1875,7 @@ int read_index_unmerged(struct index_state *istate) new_ce->ce_mode = ce->ce_mode; if (add_index_entry(istate, new_ce, 0)) return error("%s: cannot drop to stage #0", - ce->name); + new_ce->name); i = index_name_pos(istate, new_ce->name, len); } return unmerged; diff --git a/remote-curl.c b/remote-curl.c index 10cb0114ea..52c2d96ce6 100644 --- a/remote-curl.c +++ b/remote-curl.c @@ -423,11 +423,8 @@ static int run_slot(struct active_request_slot *slot, if (!results) results = &results_buf; - slot->results = results; - slot->curl_result = curl_easy_perform(slot->curl); - finish_active_slot(slot); + err = run_one_slot(slot, results); - err = handle_curl_result(results); if (err != HTTP_OK && err != HTTP_REAUTH) { error("RPC failed; result=%d, HTTP code = %ld", results->curl_result, results->http_code); @@ -672,8 +672,8 @@ int rerere_forget(struct pathspec *pathspec) find_conflict(&conflict); for (i = 0; i < conflict.nr; i++) { struct string_list_item *it = &conflict.items[i]; - if (!match_pathspec_depth(pathspec, it->string, strlen(it->string), - 0, NULL)) + if (!match_pathspec(pathspec, it->string, + strlen(it->string), 0, NULL, 0)) continue; rerere_forget_one_path(it->string, &merge_rr); } diff --git a/resolve-undo.c b/resolve-undo.c index c09b00664e..44c697c36d 100644 --- a/resolve-undo.c +++ b/resolve-undo.c @@ -119,6 +119,7 @@ int unmerge_index_entry_at(struct index_state *istate, int pos) struct string_list_item *item; struct resolve_undo_info *ru; int i, err = 0, matched; + char *name; if (!istate->resolve_undo) return pos; @@ -138,20 +139,22 @@ int unmerge_index_entry_at(struct index_state *istate, int pos) if (!ru) return pos; matched = ce->ce_flags & CE_MATCHED; + name = xstrdup(ce->name); remove_index_entry_at(istate, pos); for (i = 0; i < 3; i++) { struct cache_entry *nce; if (!ru->mode[i]) continue; nce = make_cache_entry(ru->mode[i], ru->sha1[i], - ce->name, i + 1, 0); + name, i + 1, 0); if (matched) nce->ce_flags |= CE_MATCHED; if (add_index_entry(istate, nce, ADD_CACHE_OK_TO_ADD)) { err = 1; - error("cannot unmerge '%s'", ce->name); + error("cannot unmerge '%s'", name); } } + free(name); if (err) return pos; free(ru); @@ -182,7 +185,7 @@ void unmerge_index(struct index_state *istate, const struct pathspec *pathspec) for (i = 0; i < istate->cache_nr; i++) { const struct cache_entry *ce = istate->cache[i]; - if (!match_pathspec_depth(pathspec, ce->name, ce_namelen(ce), 0, NULL)) + if (!ce_path_match(ce, pathspec, NULL)) continue; i = unmerge_index_entry_at(istate, i); } diff --git a/revision.c b/revision.c index 6addff1b5f..78b5c3ac0b 100644 --- a/revision.c +++ b/revision.c @@ -16,6 +16,7 @@ #include "line-log.h" #include "mailmap.h" #include "commit-slab.h" +#include "dir.h" volatile show_early_output_fn_t show_early_output; @@ -496,24 +497,14 @@ static int rev_compare_tree(struct rev_info *revs, static int rev_same_tree_as_empty(struct rev_info *revs, struct commit *commit) { int retval; - void *tree; - unsigned long size; - struct tree_desc empty, real; struct tree *t1 = commit->tree; if (!t1) return 0; - tree = read_object_with_reference(t1->object.sha1, tree_type, &size, NULL); - if (!tree) - return 0; - init_tree_desc(&real, tree, size); - init_tree_desc(&empty, "", 0); - tree_difference = REV_TREE_SAME; DIFF_OPT_CLR(&revs->pruning, HAS_CHANGES); - retval = diff_tree(&empty, &real, "", &revs->pruning); - free(tree); + retval = diff_tree_sha1(NULL, t1->object.sha1, "", &revs->pruning); return retval >= 0 && (tree_difference == REV_TREE_SAME); } @@ -783,6 +774,10 @@ static int add_parents_to_list(struct rev_info *revs, struct commit *commit, return 0; commit->object.flags |= ADDED; + if (revs->include_check && + !revs->include_check(commit, revs->include_check_data)) + return 0; + /* * If the commit is uninteresting, don't try to * prune parents - we want the maximal uninteresting @@ -1400,7 +1395,7 @@ static void prepare_show_merge(struct rev_info *revs) const struct cache_entry *ce = active_cache[i]; if (!ce_stage(ce)) continue; - if (ce_path_match(ce, &revs->prune_data)) { + if (ce_path_match(ce, &revs->prune_data, NULL)) { prune_num++; prune = xrealloc(prune, sizeof(*prune) * prune_num); prune[prune_num-2] = ce->name; diff --git a/revision.h b/revision.h index 88967d6a24..1eb94c1548 100644 --- a/revision.h +++ b/revision.h @@ -172,6 +172,8 @@ struct rev_info { unsigned long min_age; int min_parents; int max_parents; + int (*include_check)(struct commit *, void *); + void *include_check_data; /* diff info for patches and for paths limiting */ struct diff_options diffopt; diff --git a/sequencer.c b/sequencer.c index 90cac7b02e..bde5f047b0 100644 --- a/sequencer.c +++ b/sequencer.c @@ -392,11 +392,18 @@ static int run_git_commit(const char *defmsg, struct replay_opts *opts, { struct argv_array array; int rc; + char *gpg_sign; argv_array_init(&array); argv_array_push(&array, "commit"); argv_array_push(&array, "-n"); + if (opts->gpg_sign) { + gpg_sign = xmalloc(3 + strlen(opts->gpg_sign)); + sprintf(gpg_sign, "-S%s", opts->gpg_sign); + argv_array_push(&array, gpg_sign); + free(gpg_sign); + } if (opts->signoff) argv_array_push(&array, "-s"); if (!opts->edit) { @@ -808,6 +815,8 @@ static int populate_opts_cb(const char *key, const char *value, void *data) opts->mainline = git_config_int(key, value); else if (!strcmp(key, "options.strategy")) git_config_string(&opts->strategy, key, value); + else if (!strcmp(key, "options.gpg-sign")) + git_config_string(&opts->gpg_sign, key, value); else if (!strcmp(key, "options.strategy-option")) { ALLOC_GROW(opts->xopts, opts->xopts_nr + 1, opts->xopts_alloc); opts->xopts[opts->xopts_nr++] = xstrdup(value); @@ -981,6 +990,8 @@ static void save_opts(struct replay_opts *opts) } if (opts->strategy) git_config_set_in_file(opts_file, "options.strategy", opts->strategy); + if (opts->gpg_sign) + git_config_set_in_file(opts_file, "options.gpg-sign", opts->gpg_sign); if (opts->xopts) { int i; for (i = 0; i < opts->xopts_nr; i++) diff --git a/sequencer.h b/sequencer.h index 1fc22dcabe..db43e9cf86 100644 --- a/sequencer.h +++ b/sequencer.h @@ -37,6 +37,8 @@ struct replay_opts { int mainline; + const char *gpg_sign; + /* Merge strategy */ const char *strategy; const char **xopts; @@ -6,6 +6,70 @@ static int inside_git_dir = -1; static int inside_work_tree = -1; /* + * The input parameter must contain an absolute path, and it must already be + * normalized. + * + * Find the part of an absolute path that lies inside the work tree by + * dereferencing symlinks outside the work tree, for example: + * /dir1/repo/dir2/file (work tree is /dir1/repo) -> dir2/file + * /dir/file (work tree is /) -> dir/file + * /dir/symlink1/symlink2 (symlink1 points to work tree) -> symlink2 + * /dir/repolink/file (repolink points to /dir/repo) -> file + * /dir/repo (exactly equal to work tree) -> (empty string) + */ +static int abspath_part_inside_repo(char *path) +{ + size_t len; + size_t wtlen; + char *path0; + int off; + const char *work_tree = get_git_work_tree(); + + if (!work_tree) + return -1; + wtlen = strlen(work_tree); + len = strlen(path); + off = 0; + + /* check if work tree is already the prefix */ + if (wtlen <= len && !strncmp(path, work_tree, wtlen)) { + if (path[wtlen] == '/') { + memmove(path, path + wtlen + 1, len - wtlen); + return 0; + } else if (path[wtlen - 1] == '/' || path[wtlen] == '\0') { + /* work tree is the root, or the whole path */ + memmove(path, path + wtlen, len - wtlen + 1); + return 0; + } + /* work tree might match beginning of a symlink to work tree */ + off = wtlen; + } + path0 = path; + path += offset_1st_component(path) + off; + + /* check each '/'-terminated level */ + while (*path) { + path++; + if (*path == '/') { + *path = '\0'; + if (strcmp(real_path(path0), work_tree) == 0) { + memmove(path0, path + 1, len - (path - path0)); + return 0; + } + *path = '/'; + } + } + + /* check whole path */ + if (strcmp(real_path(path0), work_tree) == 0) { + *path0 = '\0'; + return 0; + } + + return -1; +} + +/* * Normalize "path", prepending the "prefix" for relative paths. If * remaining_prefix is not NULL, return the actual prefix still * remains in the path. For example, prefix = sub1/sub2/ and path is @@ -22,11 +86,17 @@ char *prefix_path_gently(const char *prefix, int len, const char *orig = path; char *sanitized; if (is_absolute_path(orig)) { - const char *temp = real_path(path); - sanitized = xmalloc(len + strlen(temp) + 1); - strcpy(sanitized, temp); + sanitized = xmalloc(strlen(path) + 1); if (remaining_prefix) *remaining_prefix = 0; + if (normalize_path_copy_len(sanitized, path, remaining_prefix)) { + free(sanitized); + return NULL; + } + if (abspath_part_inside_repo(sanitized)) { + free(sanitized); + return NULL; + } } else { sanitized = xmalloc(len + strlen(path) + 1); if (len) @@ -34,26 +104,10 @@ char *prefix_path_gently(const char *prefix, int len, strcpy(sanitized + len, path); if (remaining_prefix) *remaining_prefix = len; - } - if (normalize_path_copy_len(sanitized, sanitized, remaining_prefix)) - goto error_out; - if (is_absolute_path(orig)) { - size_t root_len, len, total; - const char *work_tree = get_git_work_tree(); - if (!work_tree) - goto error_out; - len = strlen(work_tree); - root_len = offset_1st_component(work_tree); - total = strlen(sanitized) + 1; - if (strncmp(sanitized, work_tree, len) || - (len > root_len && sanitized[len] != '\0' && sanitized[len] != '/')) { - error_out: + if (normalize_path_copy_len(sanitized, sanitized, remaining_prefix)) { free(sanitized); return NULL; } - if (sanitized[len] == '/') - len++; - memmove(sanitized, sanitized + len, total - len); } return sanitized; } @@ -787,3 +841,27 @@ void sanitize_stdfds(void) if (fd > 2) close(fd); } + +int daemonize(void) +{ +#ifdef NO_POSIX_GOODIES + errno = ENOSYS; + return -1; +#else + switch (fork()) { + case 0: + break; + case -1: + die_errno("fork failed"); + default: + exit(0); + } + if (setsid() == -1) + die_errno("setsid failed"); + close(0); + close(1); + close(2); + sanitize_stdfds(); + return 0; +#endif +} diff --git a/sha1_file.c b/sha1_file.c index 6e8c05d108..019628add5 100644 --- a/sha1_file.c +++ b/sha1_file.c @@ -252,8 +252,6 @@ char *sha1_pack_index_name(const unsigned char *sha1) struct alternate_object_database *alt_odb_list; static struct alternate_object_database **alt_odb_tail; -static int git_open_noatime(const char *name); - /* * Prepare alternate object database registry. * @@ -1232,6 +1230,7 @@ static void prepare_packed_git_one(char *objdir, int local) if (has_extension(de->d_name, ".idx") || has_extension(de->d_name, ".pack") || + has_extension(de->d_name, ".bitmap") || has_extension(de->d_name, ".keep")) string_list_append(&garbage, path); else @@ -1316,7 +1315,6 @@ void prepare_packed_git(void) void reprepare_packed_git(void) { - discard_revindex(); prepare_packed_git_run_once = 0; prepare_packed_git(); } @@ -1393,7 +1391,7 @@ int check_sha1_signature(const unsigned char *sha1, void *map, return hashcmp(sha1, real_sha1) ? -1 : 0; } -static int git_open_noatime(const char *name) +int git_open_noatime(const char *name) { static int sha1_file_open_flag = O_NOATIME; @@ -10,15 +10,6 @@ int starts_with(const char *str, const char *prefix) return 0; } -int prefixcmp(const char *str, const char *prefix) -{ - for (; ; str++, prefix++) - if (!*prefix) - return 0; - else if (*str != *prefix) - return (unsigned char)*prefix - (unsigned char)*str; -} - int ends_with(const char *str, const char *suffix) { int len = strlen(str), suflen = strlen(suffix); @@ -28,15 +19,6 @@ int ends_with(const char *str, const char *suffix) return !strcmp(str + len - suflen, suffix); } -int suffixcmp(const char *str, const char *suffix) -{ - int len = strlen(str), suflen = strlen(suffix); - if (len < suflen) - return -1; - else - return strcmp(str + len - suflen, suffix); -} - /* * Used as the default ->buf value, so that people can always assume * buf is non NULL and ->buf is NUL terminated even for a freshly diff --git a/streaming.c b/streaming.c index d7c9f32f0c..2ff036a0fa 100644 --- a/streaming.c +++ b/streaming.c @@ -152,8 +152,10 @@ struct git_istream *open_istream(const unsigned char *sha1, if (filter) { /* Add "&& !is_null_stream_filter(filter)" for performance */ struct git_istream *nst = attach_stream_filter(st, filter); - if (!nst) + if (!nst) { close_istream(st); + return NULL; + } st = nst; } diff --git a/submodule.c b/submodule.c index 613857e400..b80ecacf60 100644 --- a/submodule.c +++ b/submodule.c @@ -116,30 +116,7 @@ int remove_path_from_gitmodules(const char *path) void stage_updated_gitmodules(void) { - struct strbuf buf = STRBUF_INIT; - struct stat st; - int pos; - struct cache_entry *ce; - int namelen = strlen(".gitmodules"); - - pos = cache_name_pos(".gitmodules", namelen); - if (pos < 0) { - warning(_("could not find .gitmodules in index")); - return; - } - ce = active_cache[pos]; - ce->ce_flags = namelen; - if (strbuf_read_file(&buf, ".gitmodules", 0) < 0) - die(_("reading updated .gitmodules failed")); - if (lstat(".gitmodules", &st) < 0) - die_errno(_("unable to stat updated .gitmodules")); - fill_stat_cache_info(ce, &st); - ce->ce_mode = ce_mode_from_stat(ce, st.st_mode); - if (remove_cache_entry_at(pos) < 0) - die(_("unable to remove .gitmodules from index")); - if (write_sha1_file(buf.buf, buf.len, blob_type, ce->sha1)) - die(_("adding updated .gitmodules failed")); - if (add_cache_entry(ce, ADD_CACHE_OK_TO_ADD|ADD_CACHE_OK_TO_REPLACE)) + if (add_file_to_cache(".gitmodules", 0)) die(_("staging updated .gitmodules failed")); } diff --git a/t/lib-git-daemon.sh b/t/lib-git-daemon.sh index 394b06b32f..bc4b3412fb 100644 --- a/t/lib-git-daemon.sh +++ b/t/lib-git-daemon.sh @@ -16,13 +16,14 @@ # stop_git_daemon # test_done -if test -z "$GIT_TEST_GIT_DAEMON" +test_tristate GIT_TEST_GIT_DAEMON +if test "$GIT_TEST_GIT_DAEMON" = false then - skip_all="git-daemon testing disabled (define GIT_TEST_GIT_DAEMON to enable)" + skip_all="git-daemon testing disabled (unset GIT_TEST_GIT_DAEMON to enable)" test_done fi -LIB_GIT_DAEMON_PORT=${LIB_GIT_DAEMON_PORT-'8121'} +LIB_GIT_DAEMON_PORT=${LIB_GIT_DAEMON_PORT-${this_test#t}} GIT_DAEMON_PID= GIT_DAEMON_DOCUMENT_ROOT_PATH="$PWD"/repo @@ -58,7 +59,8 @@ start_git_daemon() { kill "$GIT_DAEMON_PID" wait "$GIT_DAEMON_PID" trap 'die' EXIT - error "git daemon failed to start" + test_skip_or_die $GIT_TEST_GIT_DAEMON \ + "git daemon failed to start" fi } diff --git a/t/lib-httpd.sh b/t/lib-httpd.sh index bfdff2a8c9..252cbf163b 100644 --- a/t/lib-httpd.sh +++ b/t/lib-httpd.sh @@ -30,9 +30,10 @@ # Copyright (c) 2008 Clemens Buchacher <drizzd@aon.at> # -if test -z "$GIT_TEST_HTTPD" +test_tristate GIT_TEST_HTTPD +if test "$GIT_TEST_HTTPD" = false then - skip_all="Network testing disabled (define GIT_TEST_HTTPD to enable)" + skip_all="Network testing disabled (unset GIT_TEST_HTTPD to enable)" test_done fi @@ -64,7 +65,7 @@ case $(uname) in esac LIB_HTTPD_PATH=${LIB_HTTPD_PATH-"$DEFAULT_HTTPD_PATH"} -LIB_HTTPD_PORT=${LIB_HTTPD_PORT-'8111'} +LIB_HTTPD_PORT=${LIB_HTTPD_PORT-${this_test#t}} TEST_PATH="$TEST_DIRECTORY"/lib-httpd HTTPD_ROOT_PATH="$PWD"/httpd @@ -76,8 +77,7 @@ GIT_VALGRIND_OPTIONS=$GIT_VALGRIND_OPTIONS; export GIT_VALGRIND_OPTIONS if ! test -x "$LIB_HTTPD_PATH" then - skip_all="skipping test, no web server found at '$LIB_HTTPD_PATH'" - test_done + test_skip_or_die $GIT_TEST_HTTPD "no web server found at '$LIB_HTTPD_PATH'" fi HTTPD_VERSION=`$LIB_HTTPD_PATH -v | \ @@ -89,19 +89,20 @@ then then if ! test $HTTPD_VERSION -ge 2 then - skip_all="skipping test, at least Apache version 2 is required" - test_done + test_skip_or_die $GIT_TEST_HTTPD \ + "at least Apache version 2 is required" fi if ! test -d "$DEFAULT_HTTPD_MODULE_PATH" then - skip_all="Apache module directory not found. Skipping tests." - test_done + test_skip_or_die $GIT_TEST_HTTPD \ + "Apache module directory not found" fi LIB_HTTPD_MODULE_PATH="$DEFAULT_HTTPD_MODULE_PATH" fi else - error "Could not identify web server at '$LIB_HTTPD_PATH'" + test_skip_or_die $GIT_TEST_HTTPD \ + "Could not identify web server at '$LIB_HTTPD_PATH'" fi prepare_httpd() { @@ -155,9 +156,8 @@ start_httpd() { >&3 2>&4 if test $? -ne 0 then - skip_all="skipping test, web server setup failed" trap 'die' EXIT - test_done + test_skip_or_die $GIT_TEST_HTTPD "web server setup failed" fi } diff --git a/t/perf/p5310-pack-bitmaps.sh b/t/perf/p5310-pack-bitmaps.sh new file mode 100755 index 0000000000..685d46f8b7 --- /dev/null +++ b/t/perf/p5310-pack-bitmaps.sh @@ -0,0 +1,57 @@ +#!/bin/sh + +test_description='Tests pack performance using bitmaps' +. ./perf-lib.sh + +test_perf_large_repo + +# note that we do everything through config, +# since we want to be able to compare bitmap-aware +# git versus non-bitmap git +test_expect_success 'setup bitmap config' ' + git config pack.writebitmaps true && + git config pack.writebitmaphashcache true +' + +test_perf 'repack to disk' ' + git repack -ad +' + +test_perf 'simulated clone' ' + git pack-objects --stdout --all </dev/null >/dev/null +' + +test_perf 'simulated fetch' ' + have=$(git rev-list HEAD~100 -1) && + { + echo HEAD && + echo ^$have + } | git pack-objects --revs --stdout >/dev/null +' + +test_expect_success 'create partial bitmap state' ' + # pick a commit to represent the repo tip in the past + cutoff=$(git rev-list HEAD~100 -1) && + orig_tip=$(git rev-parse HEAD) && + + # now kill off all of the refs and pretend we had + # just the one tip + rm -rf .git/logs .git/refs/* .git/packed-refs + git update-ref HEAD $cutoff + + # and then repack, which will leave us with a nice + # big bitmap pack of the "old" history, and all of + # the new history will be loose, as if it had been pushed + # up incrementally and exploded via unpack-objects + git repack -Ad + + # and now restore our original tip, as if the pushes + # had happened + git update-ref HEAD $orig_tip +' + +test_perf 'partial bitmap' ' + git pack-objects --stdout --all </dev/null >/dev/null +' + +test_done diff --git a/t/t0003-attributes.sh b/t/t0003-attributes.sh index b9d79476e2..f0fbb42554 100755 --- a/t/t0003-attributes.sh +++ b/t/t0003-attributes.sh @@ -243,40 +243,58 @@ EOF test_line_count = 0 err ' +test_expect_success 'using --git-dir and --work-tree' ' + mkdir unreal real && + git init real && + echo "file test=in-real" >real/.gitattributes && + ( + cd unreal && + attr_check file in-real "--git-dir ../real/.git --work-tree ../real" + ) +' + test_expect_success 'setup bare' ' - git clone --bare . bare.git && - cd bare.git + git clone --bare . bare.git ' test_expect_success 'bare repository: check that .gitattribute is ignored' ' ( - echo "f test=f" - echo "a/i test=a/i" - ) >.gitattributes && - attr_check f unspecified && - attr_check a/f unspecified && - attr_check a/c/f unspecified && - attr_check a/i unspecified && - attr_check subdir/a/i unspecified + cd bare.git && + ( + echo "f test=f" + echo "a/i test=a/i" + ) >.gitattributes && + attr_check f unspecified && + attr_check a/f unspecified && + attr_check a/c/f unspecified && + attr_check a/i unspecified && + attr_check subdir/a/i unspecified + ) ' test_expect_success 'bare repository: check that --cached honors index' ' - GIT_INDEX_FILE=../.git/index \ - git check-attr --cached --stdin --all <../stdin-all | - sort >actual && - test_cmp ../specified-all actual + ( + cd bare.git && + GIT_INDEX_FILE=../.git/index \ + git check-attr --cached --stdin --all <../stdin-all | + sort >actual && + test_cmp ../specified-all actual + ) ' test_expect_success 'bare repository: test info/attributes' ' ( - echo "f test=f" - echo "a/i test=a/i" - ) >info/attributes && - attr_check f f && - attr_check a/f f && - attr_check a/c/f f && - attr_check a/i a/i && - attr_check subdir/a/i unspecified + cd bare.git && + ( + echo "f test=f" + echo "a/i test=a/i" + ) >info/attributes && + attr_check f f && + attr_check a/f f && + attr_check a/c/f f && + attr_check a/i a/i && + attr_check subdir/a/i unspecified + ) ' test_done diff --git a/t/t0008-ignores.sh b/t/t0008-ignores.sh index b4d98e602f..63beb99828 100755 --- a/t/t0008-ignores.sh +++ b/t/t0008-ignores.sh @@ -775,4 +775,35 @@ test_expect_success PIPE 'streaming support for --stdin' ' echo "$response" | grep "^:: two" ' +############################################################################ +# +# test whitespace handling + +test_expect_success 'trailing whitespace is ignored' ' + mkdir whitespace && + >whitespace/trailing && + >whitespace/untracked && + echo "whitespace/trailing " >ignore && + cat >expect <<EOF && +whitespace/untracked +EOF + : >err.expect && + git ls-files -o -X ignore whitespace >actual 2>err && + test_cmp expect actual && + test_cmp err.expect err +' + +test_expect_success !MINGW 'quoting allows trailing whitespace' ' + rm -rf whitespace && + mkdir whitespace && + >"whitespace/trailing " && + >whitespace/untracked && + echo "whitespace/trailing\\ \\ " >ignore && + echo whitespace/untracked >expect && + : >err.expect && + git ls-files -o -X ignore whitespace >actual 2>err && + test_cmp expect actual && + test_cmp err.expect err +' + test_done diff --git a/t/t0011-hashmap.sh b/t/t0011-hashmap.sh new file mode 100755 index 0000000000..391e2b6492 --- /dev/null +++ b/t/t0011-hashmap.sh @@ -0,0 +1,240 @@ +#!/bin/sh + +test_description='test hashmap and string hash functions' +. ./test-lib.sh + +test_hashmap() { + echo "$1" | test-hashmap $3 > actual && + echo "$2" > expect && + test_cmp expect actual +} + +test_expect_success 'hash functions' ' + +test_hashmap "hash key1" "2215982743 2215982743 116372151 116372151" && +test_hashmap "hash key2" "2215982740 2215982740 116372148 116372148" && +test_hashmap "hash fooBarFrotz" "1383912807 1383912807 3189766727 3189766727" && +test_hashmap "hash foobarfrotz" "2862305959 2862305959 3189766727 3189766727" + +' + +test_expect_success 'put' ' + +test_hashmap "put key1 value1 +put key2 value2 +put fooBarFrotz value3 +put foobarfrotz value4 +size" "NULL +NULL +NULL +NULL +64 4" + +' + +test_expect_success 'put (case insensitive)' ' + +test_hashmap "put key1 value1 +put key2 value2 +put fooBarFrotz value3 +size" "NULL +NULL +NULL +64 3" ignorecase + +' + +test_expect_success 'replace' ' + +test_hashmap "put key1 value1 +put key1 value2 +put fooBarFrotz value3 +put fooBarFrotz value4 +size" "NULL +value1 +NULL +value3 +64 2" + +' + +test_expect_success 'replace (case insensitive)' ' + +test_hashmap "put key1 value1 +put Key1 value2 +put fooBarFrotz value3 +put foobarfrotz value4 +size" "NULL +value1 +NULL +value3 +64 2" ignorecase + +' + +test_expect_success 'get' ' + +test_hashmap "put key1 value1 +put key2 value2 +put fooBarFrotz value3 +put foobarfrotz value4 +get key1 +get key2 +get fooBarFrotz +get notInMap" "NULL +NULL +NULL +NULL +value1 +value2 +value3 +NULL" + +' + +test_expect_success 'get (case insensitive)' ' + +test_hashmap "put key1 value1 +put key2 value2 +put fooBarFrotz value3 +get Key1 +get keY2 +get foobarfrotz +get notInMap" "NULL +NULL +NULL +value1 +value2 +value3 +NULL" ignorecase + +' + +test_expect_success 'add' ' + +test_hashmap "add key1 value1 +add key1 value2 +add fooBarFrotz value3 +add fooBarFrotz value4 +get key1 +get fooBarFrotz +get notInMap" "value2 +value1 +value4 +value3 +NULL" + +' + +test_expect_success 'add (case insensitive)' ' + +test_hashmap "add key1 value1 +add Key1 value2 +add fooBarFrotz value3 +add foobarfrotz value4 +get key1 +get Foobarfrotz +get notInMap" "value2 +value1 +value4 +value3 +NULL" ignorecase + +' + +test_expect_success 'remove' ' + +test_hashmap "put key1 value1 +put key2 value2 +put fooBarFrotz value3 +remove key1 +remove key2 +remove notInMap +size" "NULL +NULL +NULL +value1 +value2 +NULL +64 1" + +' + +test_expect_success 'remove (case insensitive)' ' + +test_hashmap "put key1 value1 +put key2 value2 +put fooBarFrotz value3 +remove Key1 +remove keY2 +remove notInMap +size" "NULL +NULL +NULL +value1 +value2 +NULL +64 1" ignorecase + +' + +test_expect_success 'iterate' ' + +test_hashmap "put key1 value1 +put key2 value2 +put fooBarFrotz value3 +iterate" "NULL +NULL +NULL +key2 value2 +key1 value1 +fooBarFrotz value3" + +' + +test_expect_success 'iterate (case insensitive)' ' + +test_hashmap "put key1 value1 +put key2 value2 +put fooBarFrotz value3 +iterate" "NULL +NULL +NULL +fooBarFrotz value3 +key2 value2 +key1 value1" ignorecase + +' + +test_expect_success 'grow / shrink' ' + + rm -f in && + rm -f expect && + for n in $(test_seq 51) + do + echo put key$n value$n >> in && + echo NULL >> expect + done && + echo size >> in && + echo 64 51 >> expect && + echo put key52 value52 >> in && + echo NULL >> expect + echo size >> in && + echo 256 52 >> expect && + for n in $(test_seq 12) + do + echo remove key$n >> in && + echo value$n >> expect + done && + echo size >> in && + echo 256 40 >> expect && + echo remove key40 >> in && + echo value40 >> expect && + echo size >> in && + echo 64 39 >> expect && + cat in | test-hashmap > out && + test_cmp expect out + +' + +test_done diff --git a/t/t0060-path-utils.sh b/t/t0060-path-utils.sh index 07c10c8dca..c0143a0a70 100755 --- a/t/t0060-path-utils.sh +++ b/t/t0060-path-utils.sh @@ -190,6 +190,27 @@ test_expect_success SYMLINKS 'real path works on symlinks' ' test "$sym" = "$(test-path-utils real_path "$dir2/syml")" ' +test_expect_success SYMLINKS 'prefix_path works with absolute paths to work tree symlinks' ' + ln -s target symlink && + test "$(test-path-utils prefix_path prefix "$(pwd)/symlink")" = "symlink" +' + +test_expect_success 'prefix_path works with only absolute path to work tree' ' + echo "" >expected && + test-path-utils prefix_path prefix "$(pwd)" >actual && + test_cmp expected actual +' + +test_expect_success 'prefix_path rejects absolute path to dir with same beginning as work tree' ' + test_must_fail test-path-utils prefix_path prefix "$(pwd)a" +' + +test_expect_success SYMLINKS 'prefix_path works with absolute path to a symlink to work tree having same beginning as work tree' ' + git init repo && + ln -s repo repolink && + test "a" = "$(cd repo && test-path-utils prefix_path prefix "$(pwd)/../repolink/a")" +' + relative_path /foo/a/b/c/ /foo/a/b/ c/ relative_path /foo/a/b/c/ /foo/a/b c/ relative_path /foo/a//b//c/ ///foo/a/b// c/ POSIX diff --git a/t/t1300-repo-config.sh b/t/t1300-repo-config.sh index 967359344d..c9c426c273 100755 --- a/t/t1300-repo-config.sh +++ b/t/t1300-repo-config.sh @@ -475,15 +475,28 @@ ein.bahn=strasse EOF test_expect_success 'alternative GIT_CONFIG' ' - GIT_CONFIG=other-config git config -l >output && + GIT_CONFIG=other-config git config --list >output && test_cmp expect output ' test_expect_success 'alternative GIT_CONFIG (--file)' ' - git config --file other-config -l > output && + git config --file other-config --list >output && test_cmp expect output ' +test_expect_success 'alternative GIT_CONFIG (--file=-)' ' + git config --file - --list <other-config >output && + test_cmp expect output +' + +test_expect_success 'setting a value in stdin is an error' ' + test_must_fail git config --file - some.value foo +' + +test_expect_success 'editing stdin is an error' ' + test_must_fail git config --file - --edit +' + test_expect_success 'refer config from subdirectory' ' mkdir x && ( diff --git a/t/t1305-config-include.sh b/t/t1305-config-include.sh index a70707620f..9ba2ba11c3 100755 --- a/t/t1305-config-include.sh +++ b/t/t1305-config-include.sh @@ -113,7 +113,7 @@ test_expect_success 'missing include files are ignored' ' test_expect_success 'absolute includes from command line work' ' echo "[test]one = 1" >one && echo 1 >expect && - git -c include.path="$PWD/one" config test.one >actual && + git -c include.path="$(pwd)/one" config test.one >actual && test_cmp expect actual ' @@ -122,6 +122,36 @@ test_expect_success 'relative includes from command line fail' ' test_must_fail git -c include.path=one config test.one ' +test_expect_success 'absolute includes from blobs work' ' + echo "[test]one = 1" >one && + echo "[include]path=$(pwd)/one" >blob && + blob=$(git hash-object -w blob) && + echo 1 >expect && + git config --blob=$blob test.one >actual && + test_cmp expect actual +' + +test_expect_success 'relative includes from blobs fail' ' + echo "[test]one = 1" >one && + echo "[include]path=one" >blob && + blob=$(git hash-object -w blob) && + test_must_fail git config --blob=$blob test.one +' + +test_expect_success 'absolute includes from stdin work' ' + echo "[test]one = 1" >one && + echo 1 >expect && + echo "[include]path=\"$(pwd)/one\"" | + git config --file - test.one >actual && + test_cmp expect actual +' + +test_expect_success 'relative includes from stdin line fail' ' + echo "[test]one = 1" >one && + echo "[include]path=one" | + test_must_fail git config --file - test.one +' + test_expect_success 'include cycles are detected' ' cat >.gitconfig <<-\EOF && [test]value = gitconfig diff --git a/t/t2200-add-update.sh b/t/t2200-add-update.sh index 9bf2bdffd2..e16b15d3e5 100755 --- a/t/t2200-add-update.sh +++ b/t/t2200-add-update.sh @@ -80,18 +80,13 @@ test_expect_success 'change gets noticed' ' ' -# Note that this is scheduled to change in Git 2.0, when -# "git add -u" will become full-tree by default. -test_expect_success 'non-limited update in subdir leaves root alone' ' +test_expect_success 'non-qualified update in subdir updates from the root' ' ( cd dir1 && echo even more >>sub2 && git add -u ) && - cat >expect <<-\EOF && - check - top - EOF + : >expect && git diff-files --name-only >actual && test_cmp expect actual ' diff --git a/t/t3004-ls-files-basic.sh b/t/t3004-ls-files-basic.sh index 8d9bc3c2af..9c7adbdbe1 100755 --- a/t/t3004-ls-files-basic.sh +++ b/t/t3004-ls-files-basic.sh @@ -36,4 +36,21 @@ test_expect_success 'ls-files -h in corrupt repository' ' test_i18ngrep "[Uu]sage: git ls-files " broken/usage ' +test_expect_success SYMLINKS 'ls-files with absolute paths to symlinks' ' + mkdir subs && + ln -s nosuch link && + ln -s ../nosuch subs/link && + git add link subs/link && + git ls-files -s link subs/link >expect && + git ls-files -s "$(pwd)/link" "$(pwd)/subs/link" >actual && + test_cmp expect actual && + + ( + cd subs && + git ls-files -s link >../expect && + git ls-files -s "$(pwd)/link" >../actual + ) && + test_cmp expect actual +' + test_done diff --git a/t/t3030-merge-recursive.sh b/t/t3030-merge-recursive.sh index 2f96100a5f..82e18548c3 100755 --- a/t/t3030-merge-recursive.sh +++ b/t/t3030-merge-recursive.sh @@ -257,6 +257,7 @@ test_expect_success 'setup 8' ' git add e && test_tick && git commit -m "rename a->e" && + c7=$(git rev-parse --verify HEAD) && git checkout rename-ln && git mv a e && test_ln_s_add e a && @@ -517,6 +518,52 @@ test_expect_success 'reset and bind merge' ' ' +test_expect_success 'merge-recursive w/ empty work tree - ours has rename' ' + ( + GIT_WORK_TREE="$PWD/ours-has-rename-work" && + export GIT_WORK_TREE && + GIT_INDEX_FILE="$PWD/ours-has-rename-index" && + export GIT_INDEX_FILE && + mkdir "$GIT_WORK_TREE" && + git read-tree -i -m $c7 && + git update-index --ignore-missing --refresh && + git merge-recursive $c0 -- $c7 $c3 && + git ls-files -s >actual-files + ) 2>actual-err && + >expected-err && + cat >expected-files <<-EOF && + 100644 $o3 0 b/c + 100644 $o0 0 c + 100644 $o0 0 d/e + 100644 $o0 0 e + EOF + test_cmp expected-files actual-files && + test_cmp expected-err actual-err +' + +test_expect_success 'merge-recursive w/ empty work tree - theirs has rename' ' + ( + GIT_WORK_TREE="$PWD/theirs-has-rename-work" && + export GIT_WORK_TREE && + GIT_INDEX_FILE="$PWD/theirs-has-rename-index" && + export GIT_INDEX_FILE && + mkdir "$GIT_WORK_TREE" && + git read-tree -i -m $c3 && + git update-index --ignore-missing --refresh && + git merge-recursive $c0 -- $c3 $c7 && + git ls-files -s >actual-files + ) 2>actual-err && + >expected-err && + cat >expected-files <<-EOF && + 100644 $o3 0 b/c + 100644 $o0 0 c + 100644 $o0 0 d/e + 100644 $o0 0 e + EOF + test_cmp expected-files actual-files && + test_cmp expected-err actual-err +' + test_expect_success 'merge removes empty directories' ' git reset --hard master && diff --git a/t/t4010-diff-pathspec.sh b/t/t4010-diff-pathspec.sh index 9f5659f7fe..2bb973655b 100755 --- a/t/t4010-diff-pathspec.sh +++ b/t/t4010-diff-pathspec.sh @@ -140,4 +140,10 @@ test_expect_success 'diff multiple wildcard pathspecs' ' test_cmp expect actual ' +test_expect_success 'diff-cache ignores trailing slash on submodule path' ' + git diff --name-only HEAD^ submod >expect && + git diff --name-only HEAD^ submod/ >actual && + test_cmp expect actual +' + test_done diff --git a/t/t4020-diff-external.sh b/t/t4020-diff-external.sh index bcae35ac1c..044620186d 100755 --- a/t/t4020-diff-external.sh +++ b/t/t4020-diff-external.sh @@ -226,12 +226,13 @@ keep_only_cr () { } test_expect_success 'external diff with autocrlf = true' ' - git config core.autocrlf true && + test_config core.autocrlf true && GIT_EXTERNAL_DIFF=./fake-diff.sh git diff && test $(wc -l < crlfed.txt) = $(cat crlfed.txt | keep_only_cr | wc -c) ' test_expect_success 'diff --cached' ' + test_config core.autocrlf true && git add file && git update-index --assume-unchanged file && echo second >file && @@ -239,4 +240,31 @@ test_expect_success 'diff --cached' ' test_cmp "$TEST_DIRECTORY"/t4020/diff.NUL actual ' +test_expect_success 'clean up crlf leftovers' ' + git update-index --no-assume-unchanged file && + rm -f file* && + git reset --hard +' + +test_expect_success 'submodule diff' ' + git init sub && + ( cd sub && test_commit sub1 ) && + git add sub && + test_tick && + git commit -m "add submodule" && + ( cd sub && test_commit sub2 ) && + write_script gather_pre_post.sh <<-\EOF && + echo "$1 $4" # path, mode + cat "$2" # old file + cat "$5" # new file + EOF + GIT_EXTERNAL_DIFF=./gather_pre_post.sh git diff >actual && + cat >expected <<-EOF && + sub 160000 + Subproject commit $(git rev-parse HEAD:sub) + Subproject commit $(cd sub && git rev-parse HEAD) + EOF + test_cmp expected actual +' + test_done diff --git a/t/t4035-diff-quiet.sh b/t/t4035-diff-quiet.sh index 231412d100..e8ae2a03fd 100755 --- a/t/t4035-diff-quiet.sh +++ b/t/t4035-diff-quiet.sh @@ -148,4 +148,10 @@ test_expect_success 'git diff --ignore-all-space, both files outside repo' ' ) ' +test_expect_success 'git diff --quiet ignores stat-change only entries' ' + test-chmtime +10 a && + echo modified >>b && + test_expect_code 1 git diff --quiet +' + test_done diff --git a/t/t4056-diff-order.sh b/t/t4056-diff-order.sh index 9e2b29ede5..c0460bb0e5 100755 --- a/t/t4056-diff-order.sh +++ b/t/t4056-diff-order.sh @@ -97,4 +97,25 @@ do ' done +test_expect_success 'setup for testing combine-diff order' ' + git checkout -b tmp HEAD~ && + create_files 3 && + git checkout master && + git merge --no-commit -s ours tmp && + create_files 5 +' + +test_expect_success "combine-diff: no order (=tree object order)" ' + git diff --name-only HEAD HEAD^ HEAD^2 >actual && + test_cmp expect_none actual +' + +for i in 1 2 +do + test_expect_success "combine-diff: orderfile using option ($i)" ' + git diff -Oorder_file_$i --name-only HEAD HEAD^ HEAD^2 >actual && + test_cmp expect_$i actual + ' +done + test_done diff --git a/t/t4057-diff-combined-paths.sh b/t/t4057-diff-combined-paths.sh new file mode 100755 index 0000000000..097e63215e --- /dev/null +++ b/t/t4057-diff-combined-paths.sh @@ -0,0 +1,106 @@ +#!/bin/sh + +test_description='combined diff show only paths that are different to all parents' + +. ./test-lib.sh + +# verify that diffc.expect matches output of +# `git diff -c --name-only HEAD HEAD^ HEAD^2` +diffc_verify () { + git diff -c --name-only HEAD HEAD^ HEAD^2 >diffc.actual && + test_cmp diffc.expect diffc.actual +} + +test_expect_success 'trivial merge - combine-diff empty' ' + for i in $(test_seq 1 9) + do + echo $i >$i.txt && + git add $i.txt + done && + git commit -m "init" && + git checkout -b side && + for i in $(test_seq 2 9) + do + echo $i/2 >>$i.txt + done && + git commit -a -m "side 2-9" && + git checkout master && + echo 1/2 >1.txt && + git commit -a -m "master 1" && + git merge side && + >diffc.expect && + diffc_verify +' + + +test_expect_success 'only one trully conflicting path' ' + git checkout side && + for i in $(test_seq 2 9) + do + echo $i/3 >>$i.txt + done && + echo "4side" >>4.txt && + git commit -a -m "side 2-9 +4" && + git checkout master && + for i in $(test_seq 1 9) + do + echo $i/3 >>$i.txt + done && + echo "4master" >>4.txt && + git commit -a -m "master 1-9 +4" && + test_must_fail git merge side && + cat <<-\EOF >4.txt && + 4 + 4/2 + 4/3 + 4master + 4side + EOF + git add 4.txt && + git commit -m "merge side (2)" && + echo 4.txt >diffc.expect && + diffc_verify +' + +test_expect_success 'merge introduces new file' ' + git checkout side && + for i in $(test_seq 5 9) + do + echo $i/4 >>$i.txt + done && + git commit -a -m "side 5-9" && + git checkout master && + for i in $(test_seq 1 3) + do + echo $i/4 >>$i.txt + done && + git commit -a -m "master 1-3 +4hello" && + git merge side && + echo "Hello World" >4hello.txt && + git add 4hello.txt && + git commit --amend && + echo 4hello.txt >diffc.expect && + diffc_verify +' + +test_expect_success 'merge removed a file' ' + git checkout side && + for i in $(test_seq 5 9) + do + echo $i/5 >>$i.txt + done && + git commit -a -m "side 5-9" && + git checkout master && + for i in $(test_seq 1 3) + do + echo $i/4 >>$i.txt + done && + git commit -a -m "master 1-3" && + git merge side && + git rm 4.txt && + git commit --amend && + echo 4.txt >diffc.expect && + diffc_verify +' + +test_done diff --git a/t/t5310-pack-bitmaps.sh b/t/t5310-pack-bitmaps.sh new file mode 100755 index 0000000000..d3a3afaba8 --- /dev/null +++ b/t/t5310-pack-bitmaps.sh @@ -0,0 +1,139 @@ +#!/bin/sh + +test_description='exercise basic bitmap functionality' +. ./test-lib.sh + +test_expect_success 'setup repo with moderate-sized history' ' + for i in $(test_seq 1 10); do + test_commit $i + done && + git checkout -b other HEAD~5 && + for i in $(test_seq 1 10); do + test_commit side-$i + done && + git checkout master && + blob=$(echo tagged-blob | git hash-object -w --stdin) && + git tag tagged-blob $blob && + git config pack.writebitmaps true && + git config pack.writebitmaphashcache true +' + +test_expect_success 'full repack creates bitmaps' ' + git repack -ad && + ls .git/objects/pack/ | grep bitmap >output && + test_line_count = 1 output +' + +test_expect_success 'rev-list --test-bitmap verifies bitmaps' ' + git rev-list --test-bitmap HEAD +' + +rev_list_tests() { + state=$1 + + test_expect_success "counting commits via bitmap ($state)" ' + git rev-list --count HEAD >expect && + git rev-list --use-bitmap-index --count HEAD >actual && + test_cmp expect actual + ' + + test_expect_success "counting partial commits via bitmap ($state)" ' + git rev-list --count HEAD~5..HEAD >expect && + git rev-list --use-bitmap-index --count HEAD~5..HEAD >actual && + test_cmp expect actual + ' + + test_expect_success "counting non-linear history ($state)" ' + git rev-list --count other...master >expect && + git rev-list --use-bitmap-index --count other...master >actual && + test_cmp expect actual + ' + + test_expect_success "enumerate --objects ($state)" ' + git rev-list --objects --use-bitmap-index HEAD >tmp && + cut -d" " -f1 <tmp >tmp2 && + sort <tmp2 >actual && + git rev-list --objects HEAD >tmp && + cut -d" " -f1 <tmp >tmp2 && + sort <tmp2 >expect && + test_cmp expect actual + ' + + test_expect_success "bitmap --objects handles non-commit objects ($state)" ' + git rev-list --objects --use-bitmap-index HEAD tagged-blob >actual && + grep $blob actual + ' +} + +rev_list_tests 'full bitmap' + +test_expect_success 'clone from bitmapped repository' ' + git clone --no-local --bare . clone.git && + git rev-parse HEAD >expect && + git --git-dir=clone.git rev-parse HEAD >actual && + test_cmp expect actual +' + +test_expect_success 'setup further non-bitmapped commits' ' + for i in $(test_seq 1 10); do + test_commit further-$i + done +' + +rev_list_tests 'partial bitmap' + +test_expect_success 'fetch (partial bitmap)' ' + git --git-dir=clone.git fetch origin master:master && + git rev-parse HEAD >expect && + git --git-dir=clone.git rev-parse HEAD >actual && + test_cmp expect actual +' + +test_expect_success 'incremental repack cannot create bitmaps' ' + test_commit more-1 && + test_must_fail git repack -d +' + +test_expect_success 'incremental repack can disable bitmaps' ' + test_commit more-2 && + git repack -d --no-write-bitmap-index +' + +test_expect_success 'full repack, reusing previous bitmaps' ' + git repack -ad && + ls .git/objects/pack/ | grep bitmap >output && + test_line_count = 1 output +' + +test_expect_success 'fetch (full bitmap)' ' + git --git-dir=clone.git fetch origin master:master && + git rev-parse HEAD >expect && + git --git-dir=clone.git rev-parse HEAD >actual && + test_cmp expect actual +' + +test_lazy_prereq JGIT ' + type jgit +' + +test_expect_success JGIT 'we can read jgit bitmaps' ' + git clone . compat-jgit && + ( + cd compat-jgit && + rm -f .git/objects/pack/*.bitmap && + jgit gc && + git rev-list --test-bitmap HEAD + ) +' + +test_expect_success JGIT 'jgit can read our bitmaps' ' + git clone . compat-us && + ( + cd compat-us && + git repack -adb && + # jgit gc will barf if it does not like our bitmaps + jgit gc + ) +' + +test_done diff --git a/t/t5400-send-pack.sh b/t/t5400-send-pack.sh index 129fc88bd2..0736bcbcd5 100755 --- a/t/t5400-send-pack.sh +++ b/t/t5400-send-pack.sh @@ -164,6 +164,7 @@ test_expect_success 'receive-pack runs auto-gc in remote repo' ' # Set the child to auto-pack if more than one pack exists cd child && git config gc.autopacklimit 1 && + git config gc.autodetach false && git branch test_auto_gc && # And create a file that follows the temporary object naming # convention for the auto-gc to remove diff --git a/t/t5537-fetch-shallow.sh b/t/t5537-fetch-shallow.sh index b0fa7387cb..3ae9092f5c 100755 --- a/t/t5537-fetch-shallow.sh +++ b/t/t5537-fetch-shallow.sh @@ -173,32 +173,4 @@ EOF ) ' -if test -n "$NO_CURL" -o -z "$GIT_TEST_HTTPD"; then - say 'skipping remaining tests, git built without http support' - test_done -fi - -LIB_HTTPD_PORT=${LIB_HTTPD_PORT-'5537'} -. "$TEST_DIRECTORY"/lib-httpd.sh -start_httpd - -test_expect_success 'clone http repository' ' - git clone --bare --no-local shallow "$HTTPD_DOCUMENT_ROOT_PATH/repo.git" && - git clone $HTTPD_URL/smart/repo.git clone && - ( - cd clone && - git fsck && - git log --format=%s origin/master >actual && - cat <<EOF >expect && -7 -6 -5 -4 -3 -EOF - test_cmp expect actual - ) -' - -stop_httpd test_done diff --git a/t/t5538-push-shallow.sh b/t/t5538-push-shallow.sh index 0a6e40f144..8e54ac5746 100755 --- a/t/t5538-push-shallow.sh +++ b/t/t5538-push-shallow.sh @@ -126,7 +126,6 @@ if test -n "$NO_CURL" -o -z "$GIT_TEST_HTTPD"; then test_done fi -LIB_HTTPD_PORT=${LIB_HTTPD_PORT-'5537'} . "$TEST_DIRECTORY"/lib-httpd.sh start_httpd diff --git a/t/t5539-fetch-http-shallow.sh b/t/t5539-fetch-http-shallow.sh new file mode 100755 index 0000000000..94553e1039 --- /dev/null +++ b/t/t5539-fetch-http-shallow.sh @@ -0,0 +1,82 @@ +#!/bin/sh + +test_description='fetch/clone from a shallow clone over http' + +. ./test-lib.sh + +if test -n "$NO_CURL"; then + skip_all='skipping test, git built without http support' + test_done +fi + +. "$TEST_DIRECTORY"/lib-httpd.sh +start_httpd + +commit() { + echo "$1" >tracked && + git add tracked && + git commit -m "$1" +} + +test_expect_success 'setup shallow clone' ' + commit 1 && + commit 2 && + commit 3 && + commit 4 && + commit 5 && + commit 6 && + commit 7 && + git clone --no-local --depth=5 .git shallow && + git config --global transfer.fsckObjects true +' + +test_expect_success 'clone http repository' ' + git clone --bare --no-local shallow "$HTTPD_DOCUMENT_ROOT_PATH/repo.git" && + git clone $HTTPD_URL/smart/repo.git clone && + ( + cd clone && + git fsck && + git log --format=%s origin/master >actual && + cat <<EOF >expect && +7 +6 +5 +4 +3 +EOF + test_cmp expect actual + ) +' + +# This test is tricky. We need large enough "have"s that fetch-pack +# will put pkt-flush in between. Then we need a "have" the server +# does not have, it'll send "ACK %s ready" +test_expect_success 'no shallow lines after receiving ACK ready' ' + ( + cd shallow && + for i in $(test_seq 15) + do + git checkout --orphan unrelated$i && + test_commit unrelated$i && + git push -q "$HTTPD_DOCUMENT_ROOT_PATH/repo.git" \ + refs/heads/unrelated$i:refs/heads/unrelated$i && + git push -q ../clone/.git \ + refs/heads/unrelated$i:refs/heads/unrelated$i || + exit 1 + done && + git checkout master && + test_commit new && + git push "$HTTPD_DOCUMENT_ROOT_PATH/repo.git" master + ) && + ( + cd clone && + git checkout --orphan newnew && + test_commit new-too && + GIT_TRACE_PACKET="$TRASH_DIRECTORY/trace" git fetch --depth=2 && + grep "fetch-pack< ACK .* ready" ../trace && + ! grep "fetch-pack> done" ../trace + ) +' + +stop_httpd +test_done diff --git a/t/t5540-http-push.sh b/t/t5540-http-push-webdav.sh index 5b0198cbc8..8d7b3c57e3 100755 --- a/t/t5540-http-push.sh +++ b/t/t5540-http-push-webdav.sh @@ -16,7 +16,6 @@ then fi LIB_HTTPD_DAV=t -LIB_HTTPD_PORT=${LIB_HTTPD_PORT-'5540'} . "$TEST_DIRECTORY"/lib-httpd.sh ROOT_PATH="$PWD" start_httpd diff --git a/t/t5541-http-push.sh b/t/t5541-http-push-smart.sh index bfd241ea8a..73af16f481 100755 --- a/t/t5541-http-push.sh +++ b/t/t5541-http-push-smart.sh @@ -12,7 +12,6 @@ if test -n "$NO_CURL"; then fi ROOT_PATH="$PWD" -LIB_HTTPD_PORT=${LIB_HTTPD_PORT-'5541'} . "$TEST_DIRECTORY"/lib-httpd.sh . "$TEST_DIRECTORY"/lib-terminal.sh start_httpd diff --git a/t/t5550-http-fetch.sh b/t/t5550-http-fetch-dumb.sh index 8392624714..1a3a2b6c1a 100755 --- a/t/t5550-http-fetch.sh +++ b/t/t5550-http-fetch-dumb.sh @@ -8,7 +8,6 @@ if test -n "$NO_CURL"; then test_done fi -LIB_HTTPD_PORT=${LIB_HTTPD_PORT-'5550'} . "$TEST_DIRECTORY"/lib-httpd.sh start_httpd diff --git a/t/t5551-http-fetch.sh b/t/t5551-http-fetch-smart.sh index a124efe114..e07eaf35f1 100755 --- a/t/t5551-http-fetch.sh +++ b/t/t5551-http-fetch-smart.sh @@ -8,7 +8,6 @@ if test -n "$NO_CURL"; then test_done fi -LIB_HTTPD_PORT=${LIB_HTTPD_PORT-'5551'} . "$TEST_DIRECTORY"/lib-httpd.sh start_httpd diff --git a/t/t5561-http-backend.sh b/t/t5561-http-backend.sh index b5d7fbc381..d23fb02384 100755 --- a/t/t5561-http-backend.sh +++ b/t/t5561-http-backend.sh @@ -8,7 +8,6 @@ if test -n "$NO_CURL"; then test_done fi -LIB_HTTPD_PORT=${LIB_HTTPD_PORT-'5561'} . "$TEST_DIRECTORY"/lib-httpd.sh start_httpd diff --git a/t/t5570-git-daemon.sh b/t/t5570-git-daemon.sh index e06146835c..6b16379951 100755 --- a/t/t5570-git-daemon.sh +++ b/t/t5570-git-daemon.sh @@ -3,7 +3,6 @@ test_description='test fetching over git protocol' . ./test-lib.sh -LIB_GIT_DAEMON_PORT=${LIB_GIT_DAEMON_PORT-5570} . "$TEST_DIRECTORY"/lib-git-daemon.sh start_git_daemon diff --git a/t/t6131-pathspec-icase.sh b/t/t6131-pathspec-icase.sh index a7c7ff5f49..39fc3f6769 100755 --- a/t/t6131-pathspec-icase.sh +++ b/t/t6131-pathspec-icase.sh @@ -69,7 +69,7 @@ test_expect_success 'tree_entry_interesting matches :(icase)bar with empty prefi test_cmp expect actual ' -test_expect_success 'match_pathspec_depth matches :(icase)bar' ' +test_expect_success 'match_pathspec matches :(icase)bar' ' cat <<-EOF >expect && BAR bAr @@ -79,7 +79,7 @@ test_expect_success 'match_pathspec_depth matches :(icase)bar' ' test_cmp expect actual ' -test_expect_success 'match_pathspec_depth matches :(icase)bar with prefix' ' +test_expect_success 'match_pathspec matches :(icase)bar with prefix' ' cat <<-EOF >expect && fOo/BAR fOo/bAr @@ -89,7 +89,7 @@ test_expect_success 'match_pathspec_depth matches :(icase)bar with prefix' ' test_cmp expect actual ' -test_expect_success 'match_pathspec_depth matches :(icase)bar with empty prefix' ' +test_expect_success 'match_pathspec matches :(icase)bar with empty prefix' ' cat <<-EOF >expect && bar fOo/BAR diff --git a/t/t7101-reset.sh b/t/t7101-reset-empty-subdirs.sh index 96e163f084..96e163f084 100755 --- a/t/t7101-reset.sh +++ b/t/t7101-reset-empty-subdirs.sh diff --git a/t/t7102-reset.sh b/t/t7102-reset.sh index 8d4b50d1b5..450529404c 100755 --- a/t/t7102-reset.sh +++ b/t/t7102-reset.sh @@ -535,4 +535,30 @@ test_expect_success 'reset with paths accepts tree' ' git diff HEAD --exit-code ' +test_expect_success 'reset -N keeps removed files as intent-to-add' ' + echo new-file >new-file && + git add new-file && + git reset -N HEAD && + + tree=$(git write-tree) && + git ls-tree $tree new-file >actual && + >expect && + test_cmp expect actual && + + git diff --name-only >actual && + echo new-file >expect && + test_cmp expect actual +' + +test_expect_success 'reset --mixed sets up work tree' ' + git init mixed_worktree && + ( + cd mixed_worktree && + test_commit dummy + ) && + : >expect && + git --git-dir=mixed_worktree/.git --work-tree=mixed_worktree reset >actual && + test_cmp expect actual +' + test_done diff --git a/t/t7104-reset.sh b/t/t7104-reset-hard.sh index f136ee7bb5..f136ee7bb5 100755 --- a/t/t7104-reset.sh +++ b/t/t7104-reset-hard.sh diff --git a/t/t7406-submodule-update.sh b/t/t7406-submodule-update.sh index 0246e80b1a..28ca76384f 100755 --- a/t/t7406-submodule-update.sh +++ b/t/t7406-submodule-update.sh @@ -63,6 +63,9 @@ test_expect_success 'setup a submodule tree' ' git submodule add ../none none && test_tick && git commit -m "none" + ) && + (cd super && + git tag initial-setup ) ' @@ -703,7 +706,7 @@ test_expect_success 'submodule update places git-dir in superprojects git-dir re git clone super_update_r super_update_r2 && (cd super_update_r2 && git submodule update --init --recursive >actual && - test_i18ngrep "Submodule path .submodule/subsubmodule.: checked out" actual && + test_i18ngrep "Submodule path .submodule/subsubmodule.: .git reset --hard -q" actual && (cd submodule/subsubmodule && git log > ../../expected ) && @@ -775,4 +778,37 @@ test_expect_success 'submodule update --recursive drops module name before recur ) ' +test_expect_success 'submodule update --checkout clones detached HEAD' ' + git clone super super4 && + echo "detached HEAD" >expected && + (cd super4 && + git reset --hard initial-setup && + git submodule init submodule && + git submodule update >> /tmp/log 2>&1 && + (cd submodule && + git symbolic-ref HEAD > ../../actual || + echo "detached HEAD" > ../../actual + ) + ) && + test_cmp actual expected && + rm -rf super4 +' + +test_expect_success 'submodule update --merge clones attached HEAD' ' + git clone super super4 && + echo "refs/heads/master" >expected && + (cd super4 && + git reset --hard initial-setup && + git submodule init submodule && + git config submodule.submodule.update merge && + git submodule update --merge && + (cd submodule && + git symbolic-ref HEAD > ../../actual || + echo "detached HEAD" > ../../actual + ) + ) && + test_cmp actual expected && + rm -rf super4 +' + test_done diff --git a/t/t7510-signed-commit.sh b/t/t7510-signed-commit.sh index 1d3c56fe61..5ddac1a9f7 100755 --- a/t/t7510-signed-commit.sh +++ b/t/t7510-signed-commit.sh @@ -5,6 +5,8 @@ test_description='signed commit tests' . "$TEST_DIRECTORY/lib-gpg.sh" test_expect_success GPG 'create signed commits' ' + test_when_finished "test_unconfig commit.gpgsign" && + echo 1 >file && git add file && test_tick && git commit -S -m initial && git tag initial && @@ -25,12 +27,27 @@ test_expect_success GPG 'create signed commits' ' git tag fourth-unsigned && test_tick && git commit --amend -S -m "fourth signed" && - git tag fourth-signed + git tag fourth-signed && + + git config commit.gpgsign true && + echo 5 >file && test_tick && git commit -a -m "fifth signed" && + git tag fifth-signed && + + git config commit.gpgsign false && + echo 6 >file && test_tick && git commit -a -m "sixth" && + git tag sixth-unsigned && + + git config commit.gpgsign true && + echo 7 >file && test_tick && git commit -a -m "seventh" --no-gpg-sign && + git tag seventh-unsigned && + + test_tick && git rebase -f HEAD^^ && git tag sixth-signed HEAD^ && + git tag seventh-signed ' test_expect_success GPG 'show signatures' ' ( - for commit in initial second merge master + for commit in initial second merge fourth-signed fifth-signed sixth-signed master do git show --pretty=short --show-signature $commit >actual && grep "Good signature from" actual || exit 1 @@ -39,7 +56,7 @@ test_expect_success GPG 'show signatures' ' done ) && ( - for commit in merge^2 fourth-unsigned + for commit in merge^2 fourth-unsigned sixth-unsigned seventh-unsigned do git show --pretty=short --show-signature $commit >actual && grep "Good signature from" actual && exit 1 @@ -52,7 +69,7 @@ test_expect_success GPG 'show signatures' ' test_expect_success GPG 'detect fudged signature' ' git cat-file commit master >raw && - sed -e "s/fourth signed/4th forged/" raw >forged1 && + sed -e "s/seventh/7th forged/" raw >forged1 && git hash-object -w -t commit forged1 >forged1.commit && git show --pretty=short --show-signature $(cat forged1.commit) >actual1 && grep "BAD signature from" actual1 && diff --git a/t/t7601-merge-pull-config.sh b/t/t7601-merge-pull-config.sh index 830a4c3e9d..f768c900ab 100755 --- a/t/t7601-merge-pull-config.sh +++ b/t/t7601-merge-pull-config.sh @@ -38,6 +38,27 @@ test_expect_success 'merge c1 with c2' ' test -f c2.c ' +test_expect_success 'fast-forward pull succeeds with "true" in pull.ff' ' + git reset --hard c0 && + test_config pull.ff true && + git pull . c1 && + test "$(git rev-parse HEAD)" = "$(git rev-parse c1)" +' + +test_expect_success 'fast-forward pull creates merge with "false" in pull.ff' ' + git reset --hard c0 && + test_config pull.ff false && + git pull . c1 && + test "$(git rev-parse HEAD^1)" = "$(git rev-parse c0)" && + test "$(git rev-parse HEAD^2)" = "$(git rev-parse c1)" +' + +test_expect_success 'pull prevents non-fast-forward with "only" in pull.ff' ' + git reset --hard c1 && + test_config pull.ff only && + test_must_fail git pull . c3 +' + test_expect_success 'merge c1 with c2 (ours in pull.twohead)' ' git reset --hard c1 && git config pull.twohead ours && diff --git a/t/test-lib-functions.sh b/t/test-lib-functions.sh index aeae3ca769..b333e3ff86 100644 --- a/t/test-lib-functions.sh +++ b/t/test-lib-functions.sh @@ -716,6 +716,64 @@ perl () { command "$PERL_PATH" "$@" } +# Is the value one of the various ways to spell a boolean true/false? +test_normalize_bool () { + git -c magic.variable="$1" config --bool magic.variable 2>/dev/null +} + +# Given a variable $1, normalize the value of it to one of "true", +# "false", or "auto" and store the result to it. +# +# test_tristate GIT_TEST_HTTPD +# +# A variable set to an empty string is set to 'false'. +# A variable set to 'false' or 'auto' keeps its value. +# Anything else is set to 'true'. +# An unset variable defaults to 'auto'. +# +# The last rule is to allow people to set the variable to an empty +# string and export it to decline testing the particular feature +# for versions both before and after this change. We used to treat +# both unset and empty variable as a signal for "do not test" and +# took any non-empty string as "please test". + +test_tristate () { + if eval "test x\"\${$1+isset}\" = xisset" + then + # explicitly set + eval " + case \"\$$1\" in + '') $1=false ;; + auto) ;; + *) $1=\$(test_normalize_bool \$$1 || echo true) ;; + esac + " + else + eval "$1=auto" + fi +} + +# Exit the test suite, either by skipping all remaining tests or by +# exiting with an error. If "$1" is "auto", we then we assume we were +# opportunistically trying to set up some tests and we skip. If it is +# "true", then we report a failure. +# +# The error/skip message should be given by $2. +# +test_skip_or_die () { + case "$1" in + auto) + skip_all=$2 + test_done + ;; + true) + error "$2" + ;; + *) + error "BUG: test tristate is '$1' (real error: $2)" + esac +} + # The following mingw_* functions obey POSIX shell syntax, but are actually # bash scripts, and are meant to be used only with bash on Windows. diff --git a/test-hashmap.c b/test-hashmap.c new file mode 100644 index 0000000000..f5183fb9e8 --- /dev/null +++ b/test-hashmap.c @@ -0,0 +1,255 @@ +#include "git-compat-util.h" +#include "hashmap.h" + +struct test_entry +{ + struct hashmap_entry ent; + /* key and value as two \0-terminated strings */ + char key[FLEX_ARRAY]; +}; + +static const char *get_value(const struct test_entry *e) +{ + return e->key + strlen(e->key) + 1; +} + +static int test_entry_cmp(const struct test_entry *e1, + const struct test_entry *e2, const char* key) +{ + return strcmp(e1->key, key ? key : e2->key); +} + +static int test_entry_cmp_icase(const struct test_entry *e1, + const struct test_entry *e2, const char* key) +{ + return strcasecmp(e1->key, key ? key : e2->key); +} + +static struct test_entry *alloc_test_entry(int hash, char *key, int klen, + char *value, int vlen) +{ + struct test_entry *entry = malloc(sizeof(struct test_entry) + klen + + vlen + 2); + hashmap_entry_init(entry, hash); + memcpy(entry->key, key, klen + 1); + memcpy(entry->key + klen + 1, value, vlen + 1); + return entry; +} + +#define HASH_METHOD_FNV 0 +#define HASH_METHOD_I 1 +#define HASH_METHOD_IDIV10 2 +#define HASH_METHOD_0 3 +#define HASH_METHOD_X2 4 +#define TEST_SPARSE 8 +#define TEST_ADD 16 +#define TEST_SIZE 100000 + +static unsigned int hash(unsigned int method, unsigned int i, const char *key) +{ + unsigned int hash; + switch (method & 3) + { + case HASH_METHOD_FNV: + hash = strhash(key); + break; + case HASH_METHOD_I: + hash = i; + break; + case HASH_METHOD_IDIV10: + hash = i / 10; + break; + case HASH_METHOD_0: + hash = 0; + break; + } + + if (method & HASH_METHOD_X2) + hash = 2 * hash; + return hash; +} + +/* + * Test performance of hashmap.[ch] + * Usage: time echo "perfhashmap method rounds" | test-hashmap + */ +static void perf_hashmap(unsigned int method, unsigned int rounds) +{ + struct hashmap map; + char buf[16]; + struct test_entry **entries; + unsigned int *hashes; + unsigned int i, j; + + entries = malloc(TEST_SIZE * sizeof(struct test_entry *)); + hashes = malloc(TEST_SIZE * sizeof(int)); + for (i = 0; i < TEST_SIZE; i++) { + snprintf(buf, sizeof(buf), "%i", i); + entries[i] = alloc_test_entry(0, buf, strlen(buf), "", 0); + hashes[i] = hash(method, i, entries[i]->key); + } + + if (method & TEST_ADD) { + /* test adding to the map */ + for (j = 0; j < rounds; j++) { + hashmap_init(&map, (hashmap_cmp_fn) test_entry_cmp, 0); + + /* add entries */ + for (i = 0; i < TEST_SIZE; i++) { + hashmap_entry_init(entries[i], hashes[i]); + hashmap_add(&map, entries[i]); + } + + hashmap_free(&map, 0); + } + } else { + /* test map lookups */ + hashmap_init(&map, (hashmap_cmp_fn) test_entry_cmp, 0); + + /* fill the map (sparsely if specified) */ + j = (method & TEST_SPARSE) ? TEST_SIZE / 10 : TEST_SIZE; + for (i = 0; i < j; i++) { + hashmap_entry_init(entries[i], hashes[i]); + hashmap_add(&map, entries[i]); + } + + for (j = 0; j < rounds; j++) { + for (i = 0; i < TEST_SIZE; i++) { + struct hashmap_entry key; + hashmap_entry_init(&key, hashes[i]); + hashmap_get(&map, &key, entries[i]->key); + } + } + + hashmap_free(&map, 0); + } +} + +#define DELIM " \t\r\n" + +/* + * Read stdin line by line and print result of commands to stdout: + * + * hash key -> strhash(key) memhash(key) strihash(key) memihash(key) + * put key value -> NULL / old value + * get key -> NULL / value + * remove key -> NULL / old value + * iterate -> key1 value1\nkey2 value2\n... + * size -> tablesize numentries + * + * perfhashmap method rounds -> test hashmap.[ch] performance + */ +int main(int argc, char *argv[]) +{ + char line[1024]; + struct hashmap map; + int icase; + + /* init hash map */ + icase = argc > 1 && !strcmp("ignorecase", argv[1]); + hashmap_init(&map, (hashmap_cmp_fn) (icase ? test_entry_cmp_icase + : test_entry_cmp), 0); + + /* process commands from stdin */ + while (fgets(line, sizeof(line), stdin)) { + char *cmd, *p1 = NULL, *p2 = NULL; + int l1 = 0, l2 = 0, hash = 0; + struct test_entry *entry; + + /* break line into command and up to two parameters */ + cmd = strtok(line, DELIM); + /* ignore empty lines */ + if (!cmd || *cmd == '#') + continue; + + p1 = strtok(NULL, DELIM); + if (p1) { + l1 = strlen(p1); + hash = icase ? strihash(p1) : strhash(p1); + p2 = strtok(NULL, DELIM); + if (p2) + l2 = strlen(p2); + } + + if (!strcmp("hash", cmd) && l1) { + + /* print results of different hash functions */ + printf("%u %u %u %u\n", strhash(p1), memhash(p1, l1), + strihash(p1), memihash(p1, l1)); + + } else if (!strcmp("add", cmd) && l1 && l2) { + + /* create entry with key = p1, value = p2 */ + entry = alloc_test_entry(hash, p1, l1, p2, l2); + + /* add to hashmap */ + hashmap_add(&map, entry); + + } else if (!strcmp("put", cmd) && l1 && l2) { + + /* create entry with key = p1, value = p2 */ + entry = alloc_test_entry(hash, p1, l1, p2, l2); + + /* add / replace entry */ + entry = hashmap_put(&map, entry); + + /* print and free replaced entry, if any */ + puts(entry ? get_value(entry) : "NULL"); + free(entry); + + } else if (!strcmp("get", cmd) && l1) { + + /* setup static key */ + struct hashmap_entry key; + hashmap_entry_init(&key, hash); + + /* lookup entry in hashmap */ + entry = hashmap_get(&map, &key, p1); + + /* print result */ + if (!entry) + puts("NULL"); + while (entry) { + puts(get_value(entry)); + entry = hashmap_get_next(&map, entry); + } + + } else if (!strcmp("remove", cmd) && l1) { + + /* setup static key */ + struct hashmap_entry key; + hashmap_entry_init(&key, hash); + + /* remove entry from hashmap */ + entry = hashmap_remove(&map, &key, p1); + + /* print result and free entry*/ + puts(entry ? get_value(entry) : "NULL"); + free(entry); + + } else if (!strcmp("iterate", cmd)) { + + struct hashmap_iter iter; + hashmap_iter_init(&map, &iter); + while ((entry = hashmap_iter_next(&iter))) + printf("%s %s\n", entry->key, get_value(entry)); + + } else if (!strcmp("size", cmd)) { + + /* print table sizes */ + printf("%u %u\n", map.tablesize, map.size); + + } else if (!strcmp("perfhashmap", cmd) && l1 && l2) { + + perf_hashmap(atoi(p1), atoi(p2)); + + } else { + + printf("Unknown command %s\n", cmd); + + } + } + + hashmap_free(&map, 1); + return 0; +} diff --git a/tree-diff.c b/tree-diff.c index 456660c7a2..11c3550177 100644 --- a/tree-diff.c +++ b/tree-diff.c @@ -294,14 +294,10 @@ int diff_tree_sha1(const unsigned char *old, const unsigned char *new, const cha unsigned long size1, size2; int retval; - tree1 = read_object_with_reference(old, tree_type, &size1, NULL); - if (!tree1) - die("unable to read source tree (%s)", sha1_to_hex(old)); - tree2 = read_object_with_reference(new, tree_type, &size2, NULL); - if (!tree2) - die("unable to read destination tree (%s)", sha1_to_hex(new)); - init_tree_desc(&t1, tree1, size1); - init_tree_desc(&t2, tree2, size2); + tree1 = fill_tree_descriptor(&t1, old); + tree2 = fill_tree_descriptor(&t2, new); + size1 = t1.size; + size2 = t2.size; retval = diff_tree(&t1, &t2, base, opt); if (!*base && DIFF_OPT_TST(opt, FOLLOW_RENAMES) && diff_might_be_rename()) { init_tree_desc(&t1, tree1, size1); @@ -315,18 +311,5 @@ int diff_tree_sha1(const unsigned char *old, const unsigned char *new, const cha int diff_root_tree_sha1(const unsigned char *new, const char *base, struct diff_options *opt) { - int retval; - void *tree; - unsigned long size; - struct tree_desc empty, real; - - tree = read_object_with_reference(new, tree_type, &size, NULL); - if (!tree) - die("unable to read root tree (%s)", sha1_to_hex(new)); - init_tree_desc(&real, tree, size); - - init_tree_desc(&empty, "", 0); - retval = diff_tree(&empty, &real, base, opt); - free(tree); - return retval; + return diff_tree_sha1(NULL, new, base, opt); } diff --git a/tree-walk.c b/tree-walk.c index 79dba1d0f4..4dc86c7fe5 100644 --- a/tree-walk.c +++ b/tree-walk.c @@ -37,7 +37,7 @@ static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned /* Initialize the descriptor entry */ desc->entry.path = path; - desc->entry.mode = mode; + desc->entry.mode = canon_mode(mode); desc->entry.sha1 = (const unsigned char *)(path + len); } diff --git a/tree-walk.h b/tree-walk.h index ae04b6417d..ae7fb3a824 100644 --- a/tree-walk.h +++ b/tree-walk.h @@ -16,7 +16,7 @@ struct tree_desc { static inline const unsigned char *tree_entry_extract(struct tree_desc *desc, const char **pathp, unsigned int *modep) { *pathp = desc->entry.path; - *modep = canon_mode(desc->entry.mode); + *modep = desc->entry.mode; return desc->entry.sha1; } diff --git a/unpack-trees.c b/unpack-trees.c index 164354dad7..0692ebe16e 100644 --- a/unpack-trees.c +++ b/unpack-trees.c @@ -105,12 +105,11 @@ void setup_unpack_trees_porcelain(struct unpack_trees_options *opts, static void do_add_entry(struct unpack_trees_options *o, struct cache_entry *ce, unsigned int set, unsigned int clear) { - clear |= CE_HASHED | CE_UNHASHED; + clear |= CE_HASHED; if (set & CE_REMOVE) set |= CE_WT_REMOVE; - ce->next = NULL; ce->ce_flags = (ce->ce_flags & ~clear) | set; add_index_entry(&o->result, ce, ADD_CACHE_OK_TO_ADD | ADD_CACHE_OK_TO_REPLACE); @@ -5,8 +5,8 @@ /* This code is originally from http://www.cl.cam.ac.uk/~mgk25/ucs/ */ struct interval { - int first; - int last; + ucs_char_t first; + ucs_char_t last; }; size_t display_mode_esc_sequence_len(const char *s) @@ -529,7 +529,7 @@ char *reencode_string_iconv(const char *in, size_t insz, iconv_t conv, int *outs while (1) { size_t cnt = iconv(conv, &cp, &insz, &outpos, &outsz); - if (cnt == -1) { + if (cnt == (size_t) -1) { size_t sofar; if (errno != E2BIG) { free(out); diff --git a/wt-status.c b/wt-status.c index 4e55810059..a452407dad 100644 --- a/wt-status.c +++ b/wt-status.c @@ -510,7 +510,7 @@ static void wt_status_collect_changes_initial(struct wt_status *s) struct wt_status_change_data *d; const struct cache_entry *ce = active_cache[i]; - if (!ce_path_match(ce, &s->pathspec)) + if (!ce_path_match(ce, &s->pathspec, NULL)) continue; it = string_list_insert(&s->change, ce->name); d = it->util; @@ -552,7 +552,7 @@ static void wt_status_collect_untracked(struct wt_status *s) for (i = 0; i < dir.nr; i++) { struct dir_entry *ent = dir.entries[i]; if (cache_name_is_other(ent->name, ent->len) && - match_pathspec_depth(&s->pathspec, ent->name, ent->len, 0, NULL)) + dir_path_match(ent, &s->pathspec, 0, NULL)) string_list_insert(&s->untracked, ent->name); free(ent); } @@ -560,7 +560,7 @@ static void wt_status_collect_untracked(struct wt_status *s) for (i = 0; i < dir.ignored_nr; i++) { struct dir_entry *ent = dir.ignored[i]; if (cache_name_is_other(ent->name, ent->len) && - match_pathspec_depth(&s->pathspec, ent->name, ent->len, 0, NULL)) + dir_path_match(ent, &s->pathspec, 0, NULL)) string_list_insert(&s->ignored, ent->name); free(ent); } |