From b4f5bb074721823cc016b66a9984abe2c271cb1f Mon Sep 17 00:00:00 2001 From: Russell Belfer Date: Tue, 23 Oct 2012 16:40:51 -0700 Subject: Initial implementation of diff rename detection This implements the basis for diff rename and copy detection, although it is based on simple SHA comparison right now instead of using a matching algortihm. Just as `git_diff_merge` can be used as a post-pass on diffs to emulate certain command line behaviors, there is a new API `git_diff_detect` which will update a diff list in-place, adjusting some deltas to RENAMED or COPIED state (and also, eventually, splitting MODIFIED deltas where the change is too large into DELETED/ADDED pairs). This also adds a new test repo that will hold rename/copy/split scenarios. Right now, it just has exact-match rename and copy, but the tests are written to use tree diffs, so we should be able to add new test scenarios easily without breaking tests. --- tests-clar/diff/rename.c | 105 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 105 insertions(+) create mode 100644 tests-clar/diff/rename.c (limited to 'tests-clar/diff/rename.c') diff --git a/tests-clar/diff/rename.c b/tests-clar/diff/rename.c new file mode 100644 index 000000000..8a50fd5ea --- /dev/null +++ b/tests-clar/diff/rename.c @@ -0,0 +1,105 @@ +#include "clar_libgit2.h" +#include "diff_helpers.h" + +static git_repository *g_repo = NULL; + +void test_diff_rename__initialize(void) +{ + g_repo = cl_git_sandbox_init("renames"); +} + +void test_diff_rename__cleanup(void) +{ + cl_git_sandbox_cleanup(); +} + +/* + * Renames repo has: + * + * commit 31e47d8c1fa36d7f8d537b96158e3f024de0a9f2 - + * serving.txt (25 lines) + * sevencities.txt (50 lines) + * commit 2bc7f351d20b53f1c72c16c4b036e491c478c49a - + * serving.txt -> sixserving.txt (rename, no change, 100% match) + * sevencities.txt -> sevencities.txt (no change) + * sevencities.txt -> songofseven.txt (copy, no change, 100% match) + * + * TODO: add commits with various % changes of copy / rename + */ + +void test_diff_rename__match_oid(void) +{ + const char *old_sha = "31e47d8c1fa36d7f8d537b96158e3f024de0a9f2"; + const char *new_sha = "2bc7f351d20b53f1c72c16c4b036e491c478c49a"; + git_tree *old_tree, *new_tree; + git_diff_list *diff; + git_diff_options diffopts = {0}; + git_diff_detect_options opts; + diff_expects exp; + + old_tree = resolve_commit_oid_to_tree(g_repo, old_sha); + new_tree = resolve_commit_oid_to_tree(g_repo, new_sha); + + /* Must pass GIT_DIFF_INCLUDE_UNMODIFIED if you expect to emulate + * --find-copies-harder during rename detection... + */ + memset(&diffopts, 0, sizeof(diffopts)); + diffopts.flags |= GIT_DIFF_INCLUDE_UNMODIFIED; + + cl_git_pass(git_diff_tree_to_tree( + g_repo, &diffopts, old_tree, new_tree, &diff)); + + /* git diff --no-renames \ + * 31e47d8c1fa36d7f8d537b96158e3f024de0a9f2 \ + * 2bc7f351d20b53f1c72c16c4b036e491c478c49a + */ + memset(&exp, 0, sizeof(exp)); + cl_git_pass(git_diff_foreach( + diff, &exp, diff_file_fn, diff_hunk_fn, diff_line_fn)); + + cl_assert_equal_i(4, exp.files); + cl_assert_equal_i(1, exp.file_status[GIT_DELTA_UNMODIFIED]); + cl_assert_equal_i(2, exp.file_status[GIT_DELTA_ADDED]); + cl_assert_equal_i(1, exp.file_status[GIT_DELTA_DELETED]); + + /* git diff 31e47d8c1fa36d7f8d537b96158e3f024de0a9f2 \ + * 2bc7f351d20b53f1c72c16c4b036e491c478c49a + */ + cl_git_pass(git_diff_detect(diff, NULL)); + + memset(&exp, 0, sizeof(exp)); + cl_git_pass(git_diff_foreach( + diff, &exp, diff_file_fn, diff_hunk_fn, diff_line_fn)); + + cl_assert_equal_i(3, exp.files); + cl_assert_equal_i(1, exp.file_status[GIT_DELTA_UNMODIFIED]); + cl_assert_equal_i(1, exp.file_status[GIT_DELTA_ADDED]); + cl_assert_equal_i(1, exp.file_status[GIT_DELTA_RENAMED]); + + git_diff_list_free(diff); + + cl_git_pass(git_diff_tree_to_tree( + g_repo, &diffopts, old_tree, new_tree, &diff)); + + /* git diff --find-copies-harder \ + * 31e47d8c1fa36d7f8d537b96158e3f024de0a9f2 \ + * 2bc7f351d20b53f1c72c16c4b036e491c478c49a + */ + memset(&opts, 0, sizeof(opts)); + opts.flags = GIT_DIFF_DETECT_COPIES_FROM_UNMODIFIED; + cl_git_pass(git_diff_detect(diff, &opts)); + + memset(&exp, 0, sizeof(exp)); + cl_git_pass(git_diff_foreach( + diff, &exp, diff_file_fn, diff_hunk_fn, diff_line_fn)); + + cl_assert_equal_i(3, exp.files); + cl_assert_equal_i(1, exp.file_status[GIT_DELTA_UNMODIFIED]); + cl_assert_equal_i(1, exp.file_status[GIT_DELTA_COPIED]); + cl_assert_equal_i(1, exp.file_status[GIT_DELTA_RENAMED]); + + git_diff_list_free(diff); + + git_tree_free(old_tree); + git_tree_free(new_tree); +} -- cgit v1.2.1 From db106d01f093b3e61170e3738d6651a2866cb76e Mon Sep 17 00:00:00 2001 From: Russell Belfer Date: Tue, 30 Oct 2012 09:40:50 -0700 Subject: Move rename detection into new file This improves the naming for the rename related functionality moving it to be called `git_diff_find_similar()` and renaming all the associated constants, etc. to make more sense. I also moved the new code (plus the existing `git_diff_merge`) into a new file `diff_tform.c` where I can put new functions related to manipulating git diff lists. This also updates the implementation significantly from the last revision fixing some ordering issues (where break-rewrite needs to be handled prior to copy and rename detection) and improving config option handling. --- tests-clar/diff/rename.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'tests-clar/diff/rename.c') diff --git a/tests-clar/diff/rename.c b/tests-clar/diff/rename.c index 8a50fd5ea..0ee1db842 100644 --- a/tests-clar/diff/rename.c +++ b/tests-clar/diff/rename.c @@ -34,14 +34,14 @@ void test_diff_rename__match_oid(void) git_tree *old_tree, *new_tree; git_diff_list *diff; git_diff_options diffopts = {0}; - git_diff_detect_options opts; + git_diff_find_options opts; diff_expects exp; old_tree = resolve_commit_oid_to_tree(g_repo, old_sha); new_tree = resolve_commit_oid_to_tree(g_repo, new_sha); /* Must pass GIT_DIFF_INCLUDE_UNMODIFIED if you expect to emulate - * --find-copies-harder during rename detection... + * --find-copies-harder during rename transformion... */ memset(&diffopts, 0, sizeof(diffopts)); diffopts.flags |= GIT_DIFF_INCLUDE_UNMODIFIED; @@ -65,7 +65,7 @@ void test_diff_rename__match_oid(void) /* git diff 31e47d8c1fa36d7f8d537b96158e3f024de0a9f2 \ * 2bc7f351d20b53f1c72c16c4b036e491c478c49a */ - cl_git_pass(git_diff_detect(diff, NULL)); + cl_git_pass(git_diff_find_similar(diff, NULL)); memset(&exp, 0, sizeof(exp)); cl_git_pass(git_diff_foreach( @@ -86,8 +86,8 @@ void test_diff_rename__match_oid(void) * 2bc7f351d20b53f1c72c16c4b036e491c478c49a */ memset(&opts, 0, sizeof(opts)); - opts.flags = GIT_DIFF_DETECT_COPIES_FROM_UNMODIFIED; - cl_git_pass(git_diff_detect(diff, &opts)); + opts.flags = GIT_DIFF_FIND_COPIES_FROM_UNMODIFIED; + cl_git_pass(git_diff_find_similar(diff, &opts)); memset(&exp, 0, sizeof(exp)); cl_git_pass(git_diff_foreach( -- cgit v1.2.1