diff options
author | Shawn O. Pearce <spearce@spearce.org> | 2007-10-16 00:15:25 -0400 |
---|---|---|
committer | Shawn O. Pearce <spearce@spearce.org> | 2007-10-16 00:15:25 -0400 |
commit | 2e13e5d89252ceef606a0a7be32dbf5bea7e5aca (patch) | |
tree | 91f34e2fa799880e917238a7794b3dde35536c09 /convert.c | |
parent | ccfc02a30057a5fa7376e1fc8e8c3fe5478556f4 (diff) | |
parent | d55e7c3acf72413563e695a19f7f66efac442064 (diff) | |
download | git-2e13e5d89252ceef606a0a7be32dbf5bea7e5aca.tar.gz |
Merge branch 'master' into db/fetch-pack
There's a number of tricky conflicts between master and
this topic right now due to the rewrite of builtin-push.
Junio must have handled these via rerere; I'd rather not
deal with them again so I'm pre-merging master into the
topic. Besides this topic somehow started to depend on
the strbuf series that was in next, but is now in master.
It no longer compiles on its own without the strbuf API.
* master: (184 commits)
Whip post 1.5.3.4 maintenance series into shape.
Minor usage update in setgitperms.perl
manual: use 'URL' instead of 'url'.
manual: add some markup.
manual: Fix example finding commits referencing given content.
Fix wording in push definition.
Fix some typos, punctuation, missing words, minor markup.
manual: Fix or remove em dashes.
Add a --dry-run option to git-push.
Add a --dry-run option to git-send-pack.
Fix in-place editing functions in convert.c
instaweb: support for Ruby's WEBrick server
instaweb: allow for use of auto-generated scripts
Add 'git-p4 commit' as an alias for 'git-p4 submit'
hg-to-git speedup through selectable repack intervals
git-svn: respect Subversion's [auth] section configuration values
gtksourceview2 support for gitview
fix contrib/hooks/post-receive-email hooks.recipients error message
Support cvs via git-shell
rebase -i: use diff plumbing instead of porcelain
...
Conflicts:
Makefile
builtin-push.c
rsh.c
Diffstat (limited to 'convert.c')
-rw-r--r-- | convert.c | 419 |
1 files changed, 172 insertions, 247 deletions
@@ -80,24 +80,19 @@ static int is_binary(unsigned long size, struct text_stat *stats) return 0; } -static char *crlf_to_git(const char *path, const char *src, unsigned long *sizep, int action) +static int crlf_to_git(const char *path, const char *src, size_t len, + struct strbuf *buf, int action) { - char *buffer, *dst; - unsigned long size, nsize; struct text_stat stats; + char *dst; - if ((action == CRLF_BINARY) || !auto_crlf) - return NULL; - - size = *sizep; - if (!size) - return NULL; - - gather_stats(src, size, &stats); + if ((action == CRLF_BINARY) || !auto_crlf || !len) + return 0; + gather_stats(src, len, &stats); /* No CR? Nothing to convert, regardless. */ if (!stats.cr) - return NULL; + return 0; if (action == CRLF_GUESS) { /* @@ -106,24 +101,19 @@ static char *crlf_to_git(const char *path, const char *src, unsigned long *sizep * stuff? */ if (stats.cr != stats.crlf) - return NULL; + return 0; /* * And add some heuristics for binary vs text, of course... */ - if (is_binary(size, &stats)) - return NULL; + if (is_binary(len, &stats)) + return 0; } - /* - * Ok, allocate a new buffer, fill it in, and return it - * to let the caller know that we switched buffers. - */ - nsize = size - stats.crlf; - buffer = xmalloc(nsize); - *sizep = nsize; - - dst = buffer; + /* only grow if not in place */ + if (strbuf_avail(buf) + buf->len < len) + strbuf_grow(buf, len - buf->len); + dst = buf->buf; if (action == CRLF_GUESS) { /* * If we guessed, we already know we rejected a file with @@ -134,71 +124,72 @@ static char *crlf_to_git(const char *path, const char *src, unsigned long *sizep unsigned char c = *src++; if (c != '\r') *dst++ = c; - } while (--size); + } while (--len); } else { do { unsigned char c = *src++; - if (! (c == '\r' && (1 < size && *src == '\n'))) + if (! (c == '\r' && (1 < len && *src == '\n'))) *dst++ = c; - } while (--size); + } while (--len); } - - return buffer; + strbuf_setlen(buf, dst - buf->buf); + return 1; } -static char *crlf_to_worktree(const char *path, const char *src, unsigned long *sizep, int action) +static int crlf_to_worktree(const char *path, const char *src, size_t len, + struct strbuf *buf, int action) { - char *buffer, *dst; - unsigned long size, nsize; + char *to_free = NULL; struct text_stat stats; - unsigned char last; if ((action == CRLF_BINARY) || (action == CRLF_INPUT) || auto_crlf <= 0) - return NULL; + return 0; - size = *sizep; - if (!size) - return NULL; + if (!len) + return 0; - gather_stats(src, size, &stats); + gather_stats(src, len, &stats); /* No LF? Nothing to convert, regardless. */ if (!stats.lf) - return NULL; + return 0; /* Was it already in CRLF format? */ if (stats.lf == stats.crlf) - return NULL; + return 0; if (action == CRLF_GUESS) { /* If we have any bare CR characters, we're not going to touch it */ if (stats.cr != stats.crlf) - return NULL; + return 0; - if (is_binary(size, &stats)) - return NULL; + if (is_binary(len, &stats)) + return 0; } - /* - * Ok, allocate a new buffer, fill it in, and return it - * to let the caller know that we switched buffers. - */ - nsize = size + stats.lf - stats.crlf; - buffer = xmalloc(nsize); - *sizep = nsize; - last = 0; - - dst = buffer; - do { - unsigned char c = *src++; - if (c == '\n' && last != '\r') - *dst++ = '\r'; - *dst++ = c; - last = c; - } while (--size); - - return buffer; + /* are we "faking" in place editing ? */ + if (src == buf->buf) + to_free = strbuf_detach(buf, NULL); + + strbuf_grow(buf, len + stats.lf - stats.crlf); + for (;;) { + const char *nl = memchr(src, '\n', len); + if (!nl) + break; + if (nl > src && nl[-1] == '\r') { + strbuf_add(buf, src, nl + 1 - src); + } else { + strbuf_add(buf, src, nl - src); + strbuf_addstr(buf, "\r\n"); + } + len -= nl + 1 - src; + src = nl + 1; + } + strbuf_add(buf, src, len); + + free(to_free); + return 1; } static int filter_buffer(const char *path, const char *src, @@ -246,8 +237,8 @@ static int filter_buffer(const char *path, const char *src, return (write_err || status); } -static char *apply_filter(const char *path, const char *src, - unsigned long *sizep, const char *cmd) +static int apply_filter(const char *path, const char *src, size_t len, + struct strbuf *dst, const char *cmd) { /* * Create a pipeline to have the command filter the buffer's @@ -255,21 +246,19 @@ static char *apply_filter(const char *path, const char *src, * * (child --> cmd) --> us */ - const int SLOP = 4096; int pipe_feed[2]; - int status; - char *dst; - unsigned long dstsize, dstalloc; + int status, ret = 1; struct child_process child_process; + struct strbuf nbuf; if (!cmd) - return NULL; + return 0; memset(&child_process, 0, sizeof(child_process)); if (pipe(pipe_feed) < 0) { error("cannot create pipe to run external filter %s", cmd); - return NULL; + return 0; } fflush(NULL); @@ -278,54 +267,36 @@ static char *apply_filter(const char *path, const char *src, error("cannot fork to run external filter %s", cmd); close(pipe_feed[0]); close(pipe_feed[1]); - return NULL; + return 0; } if (!child_process.pid) { dup2(pipe_feed[1], 1); close(pipe_feed[0]); close(pipe_feed[1]); - exit(filter_buffer(path, src, *sizep, cmd)); + exit(filter_buffer(path, src, len, cmd)); } close(pipe_feed[1]); - dstalloc = *sizep; - dst = xmalloc(dstalloc); - dstsize = 0; - - while (1) { - ssize_t numread = xread(pipe_feed[0], dst + dstsize, - dstalloc - dstsize); - - if (numread <= 0) { - if (!numread) - break; - error("read from external filter %s failed", cmd); - free(dst); - dst = NULL; - break; - } - dstsize += numread; - if (dstalloc <= dstsize + SLOP) { - dstalloc = dstsize + SLOP; - dst = xrealloc(dst, dstalloc); - } + strbuf_init(&nbuf, 0); + if (strbuf_read(&nbuf, pipe_feed[0], len) < 0) { + error("read from external filter %s failed", cmd); + ret = 0; } if (close(pipe_feed[0])) { error("read from external filter %s failed", cmd); - free(dst); - dst = NULL; + ret = 0; } - status = finish_command(&child_process); if (status) { error("external filter %s failed %d", cmd, -status); - free(dst); - dst = NULL; + ret = 0; } - if (dst) - *sizep = dstsize; - return dst; + if (ret) { + strbuf_swap(dst, &nbuf); + } + strbuf_release(&nbuf); + return ret; } static struct convert_driver { @@ -353,13 +324,8 @@ static int read_convert_config(const char *var, const char *value) if (!strncmp(drv->name, name, namelen) && !drv->name[namelen]) break; if (!drv) { - char *namebuf; drv = xcalloc(1, sizeof(struct convert_driver)); - namebuf = xmalloc(namelen + 1); - memcpy(namebuf, name, namelen); - namebuf[namelen] = 0; - drv->name = namebuf; - drv->next = NULL; + drv->name = xmemdupz(name, namelen); *user_convert_tail = drv; user_convert_tail = &(drv->next); } @@ -449,137 +415,106 @@ static int count_ident(const char *cp, unsigned long size) return cnt; } -static char *ident_to_git(const char *path, const char *src, unsigned long *sizep, int ident) +static int ident_to_git(const char *path, const char *src, size_t len, + struct strbuf *buf, int ident) { - int cnt; - unsigned long size; - char *dst, *buf; + char *dst, *dollar; - if (!ident) - return NULL; - size = *sizep; - cnt = count_ident(src, size); - if (!cnt) - return NULL; - buf = xmalloc(size); - - for (dst = buf; size; size--) { - char ch = *src++; - *dst++ = ch; - if ((ch == '$') && (3 <= size) && - !memcmp("Id:", src, 3)) { - unsigned long rem = size - 3; - const char *cp = src + 3; - do { - ch = *cp++; - if (ch == '$') - break; - rem--; - } while (rem); - if (!rem) - continue; + if (!ident || !count_ident(src, len)) + return 0; + + /* only grow if not in place */ + if (strbuf_avail(buf) + buf->len < len) + strbuf_grow(buf, len - buf->len); + dst = buf->buf; + for (;;) { + dollar = memchr(src, '$', len); + if (!dollar) + break; + memcpy(dst, src, dollar + 1 - src); + dst += dollar + 1 - src; + len -= dollar + 1 - src; + src = dollar + 1; + + if (len > 3 && !memcmp(src, "Id:", 3)) { + dollar = memchr(src + 3, '$', len - 3); + if (!dollar) + break; memcpy(dst, "Id$", 3); dst += 3; - size -= (cp - src); - src = cp; + len -= dollar + 1 - src; + src = dollar + 1; } } - - *sizep = dst - buf; - return buf; + memcpy(dst, src, len); + strbuf_setlen(buf, dst + len - buf->buf); + return 1; } -static char *ident_to_worktree(const char *path, const char *src, unsigned long *sizep, int ident) +static int ident_to_worktree(const char *path, const char *src, size_t len, + struct strbuf *buf, int ident) { - int cnt; - unsigned long size; - char *dst, *buf; unsigned char sha1[20]; + char *to_free = NULL, *dollar; + int cnt; if (!ident) - return NULL; + return 0; - size = *sizep; - cnt = count_ident(src, size); + cnt = count_ident(src, len); if (!cnt) - return NULL; + return 0; - hash_sha1_file(src, size, "blob", sha1); - buf = xmalloc(size + cnt * 43); - - for (dst = buf; size; size--) { - const char *cp; - /* Fetch next source character, move the pointer on */ - char ch = *src++; - /* Copy the current character to the destination */ - *dst++ = ch; - /* If the current character is "$" or there are less than three - * remaining bytes or the two bytes following this one are not - * "Id", then simply read the next character */ - if ((ch != '$') || (size < 3) || memcmp("Id", src, 2)) - continue; - /* - * Here when - * - There are more than 2 bytes remaining - * - The current three bytes are "$Id" - * with - * - ch == "$" - * - src[0] == "I" - */ + /* are we "faking" in place editing ? */ + if (src == buf->buf) + to_free = strbuf_detach(buf, NULL); + hash_sha1_file(src, len, "blob", sha1); - /* - * It's possible that an expanded Id has crept its way into the - * repository, we cope with that by stripping the expansion out - */ - if (src[2] == ':') { - /* Expanded keywords have "$Id:" at the front */ + strbuf_grow(buf, len + cnt * 43); + for (;;) { + /* step 1: run to the next '$' */ + dollar = memchr(src, '$', len); + if (!dollar) + break; + strbuf_add(buf, src, dollar + 1 - src); + len -= dollar + 1 - src; + src = dollar + 1; - /* discard up to but not including the closing $ */ - unsigned long rem = size - 3; - /* Point at first byte after the ":" */ - cp = src + 3; - /* - * Throw away characters until either - * - we reach a "$" - * - we run out of bytes (rem == 0) - */ - do { - ch = *cp; - if (ch == '$') - break; - cp++; - rem--; - } while (rem); - /* If the above finished because it ran out of characters, then - * this is an incomplete keyword, so don't run the expansion */ - if (!rem) - continue; - } else if (src[2] == '$') - cp = src + 2; - else - /* Anything other than "$Id:XXX$" or $Id$ and we skip the - * expansion */ + /* step 2: does it looks like a bit like Id:xxx$ or Id$ ? */ + if (len < 3 || memcmp("Id", src, 2)) continue; - /* cp is now pointing at the last $ of the keyword */ - - memcpy(dst, "Id: ", 4); - dst += 4; - memcpy(dst, sha1_to_hex(sha1), 40); - dst += 40; - *dst++ = ' '; + /* step 3: skip over Id$ or Id:xxxxx$ */ + if (src[2] == '$') { + src += 3; + len -= 3; + } else if (src[2] == ':') { + /* + * It's possible that an expanded Id has crept its way into the + * repository, we cope with that by stripping the expansion out + */ + dollar = memchr(src + 3, '$', len - 3); + if (!dollar) { + /* incomplete keyword, no more '$', so just quit the loop */ + break; + } - /* Adjust for the characters we've discarded */ - size -= (cp - src); - src = cp; + len -= dollar + 1 - src; + src = dollar + 1; + } else { + /* it wasn't a "Id$" or "Id:xxxx$" */ + continue; + } - /* Copy the final "$" */ - *dst++ = *src++; - size--; + /* step 4: substitute */ + strbuf_addstr(buf, "Id: "); + strbuf_add(buf, sha1_to_hex(sha1), 40); + strbuf_addstr(buf, " $"); } + strbuf_add(buf, src, len); - *sizep = dst - buf; - return buf; + free(to_free); + return 1; } static int git_path_check_crlf(const char *path, struct git_attr_check *check) @@ -618,13 +553,12 @@ static int git_path_check_ident(const char *path, struct git_attr_check *check) return !!ATTR_TRUE(value); } -char *convert_to_git(const char *path, const char *src, unsigned long *sizep) +int convert_to_git(const char *path, const char *src, size_t len, struct strbuf *dst) { struct git_attr_check check[3]; int crlf = CRLF_GUESS; - int ident = 0; + int ident = 0, ret = 0; char *filter = NULL; - char *buf, *buf2; setup_convert_check(check); if (!git_checkattr(path, ARRAY_SIZE(check), check)) { @@ -636,30 +570,25 @@ char *convert_to_git(const char *path, const char *src, unsigned long *sizep) filter = drv->clean; } - buf = apply_filter(path, src, sizep, filter); - - buf2 = crlf_to_git(path, buf ? buf : src, sizep, crlf); - if (buf2) { - free(buf); - buf = buf2; + ret |= apply_filter(path, src, len, dst, filter); + if (ret) { + src = dst->buf; + len = dst->len; } - - buf2 = ident_to_git(path, buf ? buf : src, sizep, ident); - if (buf2) { - free(buf); - buf = buf2; + ret |= crlf_to_git(path, src, len, dst, crlf); + if (ret) { + src = dst->buf; + len = dst->len; } - - return buf; + return ret | ident_to_git(path, src, len, dst, ident); } -char *convert_to_working_tree(const char *path, const char *src, unsigned long *sizep) +int convert_to_working_tree(const char *path, const char *src, size_t len, struct strbuf *dst) { struct git_attr_check check[3]; int crlf = CRLF_GUESS; - int ident = 0; + int ident = 0, ret = 0; char *filter = NULL; - char *buf, *buf2; setup_convert_check(check); if (!git_checkattr(path, ARRAY_SIZE(check), check)) { @@ -671,19 +600,15 @@ char *convert_to_working_tree(const char *path, const char *src, unsigned long * filter = drv->smudge; } - buf = ident_to_worktree(path, src, sizep, ident); - - buf2 = crlf_to_worktree(path, buf ? buf : src, sizep, crlf); - if (buf2) { - free(buf); - buf = buf2; + ret |= ident_to_worktree(path, src, len, dst, ident); + if (ret) { + src = dst->buf; + len = dst->len; } - - buf2 = apply_filter(path, buf ? buf : src, sizep, filter); - if (buf2) { - free(buf); - buf = buf2; + ret |= crlf_to_worktree(path, src, len, dst, crlf); + if (ret) { + src = dst->buf; + len = dst->len; } - - return buf; + return ret | apply_filter(path, src, len, dst, filter); } |