From 80583c0ef61cc966c7eee79cf3623a83197e19b8 Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Mon, 11 Jun 2007 00:34:54 -0700 Subject: Lift 16kB limit of log message output Traditionally we had 16kB limit when formatting log messages for output, because it was easier to arrange for the caller to have a reasonably big buffer and pass it down without ever worrying about reallocating. This changes the calling convention of pretty_print_commit() to lift this limit. Instead of the buffer and remaining length, it now takes a pointer to the pointer that points at the allocated buffer, and another pointer to the location that stores the allocated length, and reallocates the buffer as necessary. To support the user format, the error return of interpolate() needed to be changed. It used to return a bool telling "Ok the result fits", or "Sorry, I had to truncate it". Now it returns 0 on success, and returns the size of the buffer it wants in order to fit the whole result. Signed-off-by: Junio C Hamano --- builtin-branch.c | 17 ++++++++++------ builtin-log.c | 6 ++++-- builtin-rev-list.c | 8 +++++--- builtin-show-branch.c | 23 +++++++++++---------- commit.c | 55 ++++++++++++++++++++++++++++++++++++++++----------- commit.h | 2 +- interpolate.c | 46 ++++++++++++++++++++---------------------- interpolate.h | 6 +++--- log-tree.c | 35 +++++++++++++++++++++----------- 9 files changed, 124 insertions(+), 74 deletions(-) diff --git a/builtin-branch.c b/builtin-branch.c index da480519d7..d7c321af4f 100644 --- a/builtin-branch.c +++ b/builtin-branch.c @@ -242,7 +242,6 @@ static void print_ref_item(struct ref_item *item, int maxwidth, int verbose, char c; int color; struct commit *commit; - char subject[256]; switch (item->kind) { case REF_LOCAL_BRANCH: @@ -263,17 +262,23 @@ static void print_ref_item(struct ref_item *item, int maxwidth, int verbose, } if (verbose) { + char *subject = NULL; + unsigned long subject_len = 0; + const char *sub = " **** invalid ref ****"; + commit = lookup_commit(item->sha1); - if (commit && !parse_commit(commit)) + if (commit && !parse_commit(commit)) { pretty_print_commit(CMIT_FMT_ONELINE, commit, ~0, - subject, sizeof(subject), 0, + &subject, &subject_len, 0, NULL, NULL, 0); - else - strcpy(subject, " **** invalid ref ****"); + sub = subject; + } printf("%c %s%-*s%s %s %s\n", c, branch_get_color(color), maxwidth, item->name, branch_get_color(COLOR_BRANCH_RESET), - find_unique_abbrev(item->sha1, abbrev), subject); + find_unique_abbrev(item->sha1, abbrev), sub); + if (subject) + free(subject); } else { printf("%c %s%s%s\n", c, branch_get_color(color), item->name, branch_get_color(COLOR_BRANCH_RESET)); diff --git a/builtin-log.c b/builtin-log.c index 0aede76839..b9035ab799 100644 --- a/builtin-log.c +++ b/builtin-log.c @@ -742,11 +742,13 @@ int cmd_cherry(int argc, const char **argv, const char *prefix) sign = '-'; if (verbose) { - static char buf[16384]; + char *buf = NULL; + unsigned long buflen = 0; pretty_print_commit(CMIT_FMT_ONELINE, commit, ~0, - buf, sizeof(buf), 0, NULL, NULL, 0); + &buf, &buflen, 0, NULL, NULL, 0); printf("%c %s %s\n", sign, sha1_to_hex(commit->object.sha1), buf); + free(buf); } else { printf("%c %s\n", sign, diff --git a/builtin-rev-list.c b/builtin-rev-list.c index ebf53f5944..813aadf596 100644 --- a/builtin-rev-list.c +++ b/builtin-rev-list.c @@ -92,11 +92,13 @@ static void show_commit(struct commit *commit) putchar('\n'); if (revs.verbose_header) { - static char pretty_header[16384]; + char *buf = NULL; + unsigned long buflen = 0; pretty_print_commit(revs.commit_format, commit, ~0, - pretty_header, sizeof(pretty_header), + &buf, &buflen, revs.abbrev, NULL, NULL, revs.date_mode); - printf("%s%c", pretty_header, hdr_termination); + printf("%s%c", buf, hdr_termination); + free(buf); } fflush(stdout); if (commit->parents) { diff --git a/builtin-show-branch.c b/builtin-show-branch.c index c892f1f7a6..4fa87f6081 100644 --- a/builtin-show-branch.c +++ b/builtin-show-branch.c @@ -259,17 +259,19 @@ static void join_revs(struct commit_list **list_p, static void show_one_commit(struct commit *commit, int no_name) { - char pretty[256], *cp; + char *pretty = NULL; + const char *pretty_str = "(unavailable)"; + unsigned long pretty_len = 0; struct commit_name *name = commit->util; - if (commit->object.parsed) + + if (commit->object.parsed) { pretty_print_commit(CMIT_FMT_ONELINE, commit, ~0, - pretty, sizeof(pretty), 0, NULL, NULL, 0); - else - strcpy(pretty, "(unavailable)"); - if (!prefixcmp(pretty, "[PATCH] ")) - cp = pretty + 8; - else - cp = pretty; + &pretty, &pretty_len, + 0, NULL, NULL, 0); + pretty_str = pretty; + } + if (!prefixcmp(pretty_str, "[PATCH] ")) + pretty_str += 8; if (!no_name) { if (name && name->head_name) { @@ -286,7 +288,8 @@ static void show_one_commit(struct commit *commit, int no_name) printf("[%s] ", find_unique_abbrev(commit->object.sha1, 7)); } - puts(cp); + puts(pretty_str); + free(pretty); } static char *ref_name[MAX_REVS + 1]; diff --git a/commit.c b/commit.c index 4ca4d44ba0..d43a68ecb1 100644 --- a/commit.c +++ b/commit.c @@ -776,7 +776,7 @@ static void fill_person(struct interp *table, const char *msg, int len) } static long format_commit_message(const struct commit *commit, - const char *msg, char *buf, unsigned long space) + const char *msg, char **buf_p, unsigned long *space_p) { struct interp table[] = { { "%H" }, /* commit hash */ @@ -905,16 +905,27 @@ static long format_commit_message(const struct commit *commit, if (!table[i].value) interp_set_entry(table, i, ""); - interpolate(buf, space, user_format, table, ARRAY_SIZE(table)); + do { + char *buf = *buf_p; + unsigned long space = *space_p; + + space = interpolate(buf, space, user_format, + table, ARRAY_SIZE(table)); + if (!space) + break; + buf = xrealloc(buf, space); + *buf_p = buf; + *space_p = space; + } while (1); interp_clear_table(table, ARRAY_SIZE(table)); - return strlen(buf); + return strlen(*buf_p); } unsigned long pretty_print_commit(enum cmit_fmt fmt, const struct commit *commit, unsigned long len, - char *buf, unsigned long space, + char **buf_p, unsigned long *space_p, int abbrev, const char *subject, const char *after_subject, enum date_mode dmode) @@ -927,9 +938,11 @@ unsigned long pretty_print_commit(enum cmit_fmt fmt, int plain_non_ascii = 0; char *reencoded; const char *encoding; + char *buf; + unsigned long space, slop; if (fmt == CMIT_FMT_USERFORMAT) - return format_commit_message(commit, msg, buf, space); + return format_commit_message(commit, msg, buf_p, space_p); encoding = (git_log_output_encoding ? git_log_output_encoding @@ -969,6 +982,26 @@ unsigned long pretty_print_commit(enum cmit_fmt fmt, } } + space = *space_p; + buf = *buf_p; + + /* + * We do not want to repeatedly realloc below, so + * preallocate with enough slop to hold MIME headers, + * "Subject: " prefix, etc. + */ + slop = 1000; + if (subject) + slop += strlen(subject); + if (after_subject) + slop += strlen(after_subject); + if (space < strlen(msg) + slop) { + space = strlen(msg) + slop; + buf = xrealloc(buf, space); + *space_p = space; + *buf_p = buf; + } + for (;;) { const char *line = msg; int linelen = get_one_line(msg, len); @@ -976,14 +1009,12 @@ unsigned long pretty_print_commit(enum cmit_fmt fmt, if (!linelen) break; - /* - * We want some slop for indentation and a possible - * final "...". Thus the "+ 20". - */ + /* 20 would cover indent and leave us some slop */ if (offset + linelen + 20 > space) { - memcpy(buf + offset, " ...\n", 8); - offset += 8; - break; + space = offset + linelen + 20; + buf = xrealloc(buf, space); + *buf_p = buf; + *space_p = space; } msg += linelen; diff --git a/commit.h b/commit.h index a313b53c31..467872eeca 100644 --- a/commit.h +++ b/commit.h @@ -61,7 +61,7 @@ enum cmit_fmt { }; extern enum cmit_fmt get_commit_format(const char *arg); -extern unsigned long pretty_print_commit(enum cmit_fmt fmt, const struct commit *, unsigned long len, char *buf, unsigned long space, int abbrev, const char *subject, const char *after_subject, enum date_mode dmode); +extern unsigned long pretty_print_commit(enum cmit_fmt fmt, const struct commit *, unsigned long len, char **buf_p, unsigned long *space_p, int abbrev, const char *subject, const char *after_subject, enum date_mode dmode); /** Removes the first commit from a list sorted by date, and adds all * of its parents. diff --git a/interpolate.c b/interpolate.c index fb30694f47..00826778fc 100644 --- a/interpolate.c +++ b/interpolate.c @@ -44,33 +44,33 @@ void interp_clear_table(struct interp *table, int ninterps) * { "%%", "%"}, * } * - * Returns 1 on a successful substitution pass that fits in result, - * Returns 0 on a failed or overflowing substitution pass. + * Returns 0 on a successful substitution pass that fits in result, + * Returns a number of bytes needed to hold the full substituted + * string otherwise. */ -int interpolate(char *result, int reslen, +unsigned long interpolate(char *result, unsigned long reslen, const char *orig, const struct interp *interps, int ninterps) { const char *src = orig; char *dest = result; - int newlen = 0; + unsigned long newlen = 0; const char *name, *value; - int namelen, valuelen; + unsigned long namelen, valuelen; int i; char c; memset(result, 0, reslen); - while ((c = *src) && newlen < reslen - 1) { + while ((c = *src)) { if (c == '%') { /* Try to match an interpolation string. */ for (i = 0; i < ninterps; i++) { name = interps[i].name; namelen = strlen(name); - if (strncmp(src, name, namelen) == 0) { + if (strncmp(src, name, namelen) == 0) break; - } } /* Check for valid interpolation. */ @@ -78,29 +78,25 @@ int interpolate(char *result, int reslen, value = interps[i].value; valuelen = strlen(value); - if (newlen + valuelen < reslen - 1) { + if (newlen + valuelen + 1 < reslen) { /* Substitute. */ strncpy(dest, value, valuelen); - newlen += valuelen; dest += valuelen; - src += namelen; - } else { - /* Something's not fitting. */ - return 0; } - - } else { - /* Skip bogus interpolation. */ - *dest++ = *src++; - newlen++; + newlen += valuelen; + src += namelen; + continue; } - - } else { - /* Straight copy one non-interpolation character. */ - *dest++ = *src++; - newlen++; } + /* Straight copy one non-interpolation character. */ + if (newlen + 1 < reslen) + *dest++ = *src; + src++; + newlen++; } - return newlen < reslen - 1; + if (newlen + 1 < reslen) + return 0; + else + return newlen + 2; } diff --git a/interpolate.h b/interpolate.h index 16a26b9986..77407e67dc 100644 --- a/interpolate.h +++ b/interpolate.h @@ -19,8 +19,8 @@ struct interp { extern void interp_set_entry(struct interp *table, int slot, const char *value); extern void interp_clear_table(struct interp *table, int ninterps); -extern int interpolate(char *result, int reslen, - const char *orig, - const struct interp *interps, int ninterps); +extern unsigned long interpolate(char *result, unsigned long reslen, + const char *orig, + const struct interp *interps, int ninterps); #endif /* INTERPOLATE_H */ diff --git a/log-tree.c b/log-tree.c index 4bef909144..0cf21bc051 100644 --- a/log-tree.c +++ b/log-tree.c @@ -79,16 +79,25 @@ static int detect_any_signoff(char *letter, int size) return seen_head && seen_name; } -static int append_signoff(char *buf, int buf_sz, int at, const char *signoff) +static unsigned long append_signoff(char **buf_p, unsigned long *buf_sz_p, + unsigned long at, const char *signoff) { static const char signed_off_by[] = "Signed-off-by: "; - int signoff_len = strlen(signoff); + size_t signoff_len = strlen(signoff); int has_signoff = 0; - char *cp = buf; - - /* Do we have enough space to add it? */ - if (buf_sz - at <= strlen(signed_off_by) + signoff_len + 3) - return at; + char *cp; + char *buf; + unsigned long buf_sz; + + buf = *buf_p; + buf_sz = *buf_sz_p; + if (buf_sz <= at + strlen(signed_off_by) + signoff_len + 3) { + buf_sz += strlen(signed_off_by) + signoff_len + 3; + buf = xrealloc(buf, buf_sz); + *buf_p = buf; + *buf_sz_p = buf_sz; + } + cp = buf; /* First see if we already have the sign-off by the signer */ while ((cp = strstr(cp, signed_off_by))) { @@ -133,7 +142,8 @@ static unsigned int digits_in_number(unsigned int number) void show_log(struct rev_info *opt, const char *sep) { - static char this_header[16384]; + char *msgbuf = NULL; + unsigned long msgbuf_len = 0; struct log_info *log = opt->loginfo; struct commit *commit = log->commit, *parent = log->parent; int abbrev = opt->diffopt.abbrev; @@ -278,14 +288,15 @@ void show_log(struct rev_info *opt, const char *sep) /* * And then the pretty-printed message itself */ - len = pretty_print_commit(opt->commit_format, commit, ~0u, this_header, - sizeof(this_header), abbrev, subject, + len = pretty_print_commit(opt->commit_format, commit, ~0u, + &msgbuf, &msgbuf_len, abbrev, subject, extra_headers, opt->date_mode); if (opt->add_signoff) - len = append_signoff(this_header, sizeof(this_header), len, + len = append_signoff(&msgbuf, &msgbuf_len, len, opt->add_signoff); - printf("%s%s%s", this_header, extra, sep); + printf("%s%s%s", msgbuf, extra, sep); + free(msgbuf); } int log_tree_diff_flush(struct rev_info *opt) -- cgit v1.2.1 From 4234a76167b12a7669dae0e6386c62e712b9dcf5 Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Mon, 11 Jun 2007 22:10:55 -0700 Subject: Extend --pretty=oneline to cover the first paragraph, so that an ugly commit message like this can be handled sanely. Currently, --pretty=oneline and --pretty=email (hence format-patch) take and use only the first line of the commit log message. This changes them to: - Take the first paragraph, where the definition of the first paragraph is "skip all blank lines from the beginning, and then grab everything up to the next empty line". - Replace all line breaks with a whitespace. This change would not affect a well-behaved commit message that adheres to the convention of "single line summary, a blank line, and then body of message", as its first paragraph always consists of a single line. Commit messages from different culture, such as the ones imported from CVS/SVN, can however get chomped with the existing behaviour at the first linebreak in the middle of sentence right now, which would become much easier to see with this change. The Subject: and --pretty=oneline output would become very long and unsightly for non-conforming commits, but their messages are already ugly anyway, and thischange at least avoids the loss of information. The Subject: line from a multi-line paragraph is folded using RFC2822 line folding rules at the places where line breaks were in the original. Signed-off-by: Junio C Hamano --- cache.h | 5 +- commit.c | 388 +++++++++++++++++++++++++++++++++++++++++---------------------- 2 files changed, 258 insertions(+), 135 deletions(-) diff --git a/cache.h b/cache.h index 6761554e6c..9700ca5018 100644 --- a/cache.h +++ b/cache.h @@ -235,7 +235,10 @@ extern void verify_non_filename(const char *prefix, const char *name); #define ALLOC_GROW(x, nr, alloc) \ do { \ if ((nr) >= alloc) { \ - alloc = alloc_nr(alloc); \ + if (alloc_nr(alloc) < (nr)) \ + alloc = (nr); \ + else \ + alloc = alloc_nr(alloc); \ x = xrealloc((x), alloc * sizeof(*(x))); \ } \ } while(0) diff --git a/commit.c b/commit.c index d43a68ecb1..40c87a7471 100644 --- a/commit.c +++ b/commit.c @@ -529,6 +529,14 @@ static int add_rfc2047(char *buf, const char *line, int len, return bp - buf; } +static unsigned long bound_rfc2047(unsigned long len, const char *encoding) +{ + /* upper bound of q encoded string of length 'len' */ + unsigned long elen = strlen(encoding); + + return len * 3 + elen + 100; +} + static int add_user_info(const char *what, enum cmit_fmt fmt, char *buf, const char *line, enum date_mode dmode, const char *encoding) @@ -922,6 +930,216 @@ static long format_commit_message(const struct commit *commit, return strlen(*buf_p); } +static void pp_header(enum cmit_fmt fmt, + int abbrev, + enum date_mode dmode, + const char *encoding, + const struct commit *commit, + const char **msg_p, + unsigned long *len_p, + unsigned long *ofs_p, + char **buf_p, + unsigned long *space_p) +{ + int parents_shown = 0; + + for (;;) { + const char *line = *msg_p; + char *dst; + int linelen = get_one_line(*msg_p, *len_p); + unsigned long len; + + if (!linelen) + return; + *msg_p += linelen; + *len_p -= linelen; + + if (linelen == 1) + /* End of header */ + return; + + ALLOC_GROW(*buf_p, linelen + *ofs_p + 20, *space_p); + dst = *buf_p + *ofs_p; + + if (fmt == CMIT_FMT_RAW) { + memcpy(dst, line, linelen); + *ofs_p += linelen; + continue; + } + + if (!memcmp(line, "parent ", 7)) { + if (linelen != 48) + die("bad parent line in commit"); + continue; + } + + if (!parents_shown) { + struct commit_list *parent; + int num; + for (parent = commit->parents, num = 0; + parent; + parent = parent->next, num++) + ; + /* with enough slop */ + num = *ofs_p + num * 50 + 20; + ALLOC_GROW(*buf_p, num, *space_p); + dst = *buf_p + *ofs_p; + *ofs_p += add_merge_info(fmt, dst, commit, abbrev); + parents_shown = 1; + } + + /* + * MEDIUM == DEFAULT shows only author with dates. + * FULL shows both authors but not dates. + * FULLER shows both authors and dates. + */ + if (!memcmp(line, "author ", 7)) { + len = linelen; + if (fmt == CMIT_FMT_EMAIL) + len = bound_rfc2047(linelen, encoding); + ALLOC_GROW(*buf_p, *ofs_p + len, *space_p); + dst = *buf_p + *ofs_p; + *ofs_p += add_user_info("Author", fmt, dst, + line + 7, dmode, encoding); + } + + if (!memcmp(line, "committer ", 10) && + (fmt == CMIT_FMT_FULL || fmt == CMIT_FMT_FULLER)) { + len = linelen; + if (fmt == CMIT_FMT_EMAIL) + len = bound_rfc2047(linelen, encoding); + ALLOC_GROW(*buf_p, *ofs_p + len, *space_p); + dst = *buf_p + *ofs_p; + *ofs_p += add_user_info("Commit", fmt, dst, + line + 10, dmode, encoding); + } + } +} + +static void pp_title_line(enum cmit_fmt fmt, + const char **msg_p, + unsigned long *len_p, + unsigned long *ofs_p, + char **buf_p, + unsigned long *space_p, + int indent, + const char *subject, + const char *after_subject, + const char *encoding, + int plain_non_ascii) +{ + char *title; + unsigned long title_alloc, title_len; + unsigned long len; + + title_len = 0; + title_alloc = 80; + title = xmalloc(title_alloc); + for (;;) { + const char *line = *msg_p; + int linelen = get_one_line(line, *len_p); + *msg_p += linelen; + *len_p -= linelen; + + if (!linelen || is_empty_line(line, &linelen)) + break; + + if (title_alloc <= title_len + linelen + 2) { + title_alloc = title_len + linelen + 80; + title = xrealloc(title, title_alloc); + } + len = 0; + if (title_len) { + if (fmt == CMIT_FMT_EMAIL) { + len++; + title[title_len++] = '\n'; + } + len++; + title[title_len++] = ' '; + } + memcpy(title + title_len, line, linelen); + title_len += linelen; + } + + /* Enough slop for the MIME header and rfc2047 */ + len = bound_rfc2047(title_len, encoding)+ 1000; + if (subject) + len += strlen(subject); + if (after_subject) + len += strlen(after_subject); + if (encoding) + len += strlen(encoding); + ALLOC_GROW(*buf_p, title_len + *ofs_p + len, *space_p); + + if (subject) { + len = strlen(subject); + memcpy(*buf_p + *ofs_p, subject, len); + *ofs_p += len; + *ofs_p += add_rfc2047(*buf_p + *ofs_p, + title, title_len, encoding); + } else { + memcpy(*buf_p + *ofs_p, title, title_len); + *ofs_p += title_len; + } + (*buf_p)[(*ofs_p)++] = '\n'; + if (plain_non_ascii) { + const char *header_fmt = + "MIME-Version: 1.0\n" + "Content-Type: text/plain; charset=%s\n" + "Content-Transfer-Encoding: 8bit\n"; + *ofs_p += snprintf(*buf_p + *ofs_p, + *space_p - *ofs_p, + header_fmt, encoding); + } + if (after_subject) { + len = strlen(after_subject); + memcpy(*buf_p + *ofs_p, after_subject, len); + *ofs_p += len; + } + free(title); + if (fmt == CMIT_FMT_EMAIL) { + ALLOC_GROW(*buf_p, *ofs_p + 20, *space_p); + (*buf_p)[(*ofs_p)++] = '\n'; + } +} + +static void pp_remainder(enum cmit_fmt fmt, + const char **msg_p, + unsigned long *len_p, + unsigned long *ofs_p, + char **buf_p, + unsigned long *space_p, + int indent) +{ + int first = 1; + for (;;) { + const char *line = *msg_p; + int linelen = get_one_line(line, *len_p); + *msg_p += linelen; + *len_p -= linelen; + + if (!linelen) + break; + + if (is_empty_line(line, &linelen)) { + if (first) + continue; + if (fmt == CMIT_FMT_SHORT) + break; + } + first = 0; + + ALLOC_GROW(*buf_p, *ofs_p + linelen + indent + 20, *space_p); + if (indent) { + memset(*buf_p + *ofs_p, ' ', indent); + *ofs_p += indent; + } + memcpy(*buf_p + *ofs_p, line, linelen); + *ofs_p += linelen; + (*buf_p)[(*ofs_p)++] = '\n'; + } +} + unsigned long pretty_print_commit(enum cmit_fmt fmt, const struct commit *commit, unsigned long len, @@ -930,16 +1148,14 @@ unsigned long pretty_print_commit(enum cmit_fmt fmt, const char *after_subject, enum date_mode dmode) { - int hdr = 1, body = 0, seen_title = 0; unsigned long offset = 0; + unsigned long beginning_of_body; int indent = 4; - int parents_shown = 0; const char *msg = commit->buffer; int plain_non_ascii = 0; char *reencoded; const char *encoding; char *buf; - unsigned long space, slop; if (fmt == CMIT_FMT_USERFORMAT) return format_commit_message(commit, msg, buf_p, space_p); @@ -950,8 +1166,10 @@ unsigned long pretty_print_commit(enum cmit_fmt fmt, if (!encoding) encoding = "utf-8"; reencoded = logmsg_reencode(commit, encoding); - if (reencoded) + if (reencoded) { msg = reencoded; + len = strlen(reencoded); + } if (fmt == CMIT_FMT_ONELINE || fmt == CMIT_FMT_EMAIL) indent = 0; @@ -982,155 +1200,57 @@ unsigned long pretty_print_commit(enum cmit_fmt fmt, } } - space = *space_p; - buf = *buf_p; - - /* - * We do not want to repeatedly realloc below, so - * preallocate with enough slop to hold MIME headers, - * "Subject: " prefix, etc. - */ - slop = 1000; - if (subject) - slop += strlen(subject); - if (after_subject) - slop += strlen(after_subject); - if (space < strlen(msg) + slop) { - space = strlen(msg) + slop; - buf = xrealloc(buf, space); - *space_p = space; - *buf_p = buf; + pp_header(fmt, abbrev, dmode, encoding, + commit, &msg, &len, + &offset, buf_p, space_p); + if (fmt != CMIT_FMT_ONELINE && !subject) { + ALLOC_GROW(*buf_p, offset + 20, *space_p); + (*buf_p)[offset++] = '\n'; } + /* Skip excess blank lines at the beginning of body, if any... */ for (;;) { - const char *line = msg; int linelen = get_one_line(msg, len); - + int ll = linelen; if (!linelen) break; - - /* 20 would cover indent and leave us some slop */ - if (offset + linelen + 20 > space) { - space = offset + linelen + 20; - buf = xrealloc(buf, space); - *buf_p = buf; - *space_p = space; - } - + if (!is_empty_line(msg, &ll)) + break; msg += linelen; len -= linelen; - if (hdr) { - if (linelen == 1) { - hdr = 0; - if ((fmt != CMIT_FMT_ONELINE) && !subject) - buf[offset++] = '\n'; - continue; - } - if (fmt == CMIT_FMT_RAW) { - memcpy(buf + offset, line, linelen); - offset += linelen; - continue; - } - if (!memcmp(line, "parent ", 7)) { - if (linelen != 48) - die("bad parent line in commit"); - continue; - } - - if (!parents_shown) { - offset += add_merge_info(fmt, buf + offset, - commit, abbrev); - parents_shown = 1; - continue; - } - /* - * MEDIUM == DEFAULT shows only author with dates. - * FULL shows both authors but not dates. - * FULLER shows both authors and dates. - */ - if (!memcmp(line, "author ", 7)) - offset += add_user_info("Author", fmt, - buf + offset, - line + 7, - dmode, - encoding); - if (!memcmp(line, "committer ", 10) && - (fmt == CMIT_FMT_FULL || fmt == CMIT_FMT_FULLER)) - offset += add_user_info("Commit", fmt, - buf + offset, - line + 10, - dmode, - encoding); - continue; - } + } - if (!subject) - body = 1; + /* These formats treat the title line specially. */ + if (fmt == CMIT_FMT_ONELINE + || fmt == CMIT_FMT_EMAIL) + pp_title_line(fmt, &msg, &len, &offset, + buf_p, space_p, indent, + subject, after_subject, encoding, + plain_non_ascii); - if (is_empty_line(line, &linelen)) { - if (!seen_title) - continue; - if (!body) - continue; - if (subject) - continue; - if (fmt == CMIT_FMT_SHORT) - break; - } + beginning_of_body = offset; + if (fmt != CMIT_FMT_ONELINE) + pp_remainder(fmt, &msg, &len, &offset, + buf_p, space_p, indent); - seen_title = 1; - if (subject) { - int slen = strlen(subject); - memcpy(buf + offset, subject, slen); - offset += slen; - offset += add_rfc2047(buf + offset, line, linelen, - encoding); - } - else { - memset(buf + offset, ' ', indent); - memcpy(buf + offset + indent, line, linelen); - offset += linelen + indent; - } - buf[offset++] = '\n'; - if (fmt == CMIT_FMT_ONELINE) - break; - if (subject && plain_non_ascii) { - int sz; - char header[512]; - const char *header_fmt = - "MIME-Version: 1.0\n" - "Content-Type: text/plain; charset=%s\n" - "Content-Transfer-Encoding: 8bit\n"; - sz = snprintf(header, sizeof(header), header_fmt, - encoding); - if (sizeof(header) < sz) - die("Encoding name %s too long", encoding); - memcpy(buf + offset, header, sz); - offset += sz; - } - if (after_subject) { - int slen = strlen(after_subject); - if (slen > space - offset - 1) - slen = space - offset - 1; - memcpy(buf + offset, after_subject, slen); - offset += slen; - after_subject = NULL; - } - subject = NULL; - } - while (offset && isspace(buf[offset-1])) + while (offset && isspace((*buf_p)[offset-1])) offset--; + + ALLOC_GROW(*buf_p, offset + 20, *space_p); + buf = *buf_p; + /* Make sure there is an EOLN for the non-oneline case */ if (fmt != CMIT_FMT_ONELINE) buf[offset++] = '\n'; + /* - * make sure there is another EOLN to separate the headers from whatever - * body the caller appends if we haven't already written a body + * The caller may append additional body text in e-mail + * format. Make sure we did not strip the blank line + * between the header and the body. */ - if (fmt == CMIT_FMT_EMAIL && !body) + if (fmt == CMIT_FMT_EMAIL && offset <= beginning_of_body) buf[offset++] = '\n'; buf[offset] = '\0'; - free(reencoded); return offset; } -- cgit v1.2.1 From 2abd31b07864049f0352d86c0c90413123f40945 Mon Sep 17 00:00:00 2001 From: Jeff King Date: Mon, 11 Jun 2007 09:39:50 -0400 Subject: dir_struct: add collect_ignored option When set, this option will cause read_directory to keep track of which entries were ignored. While this shouldn't effect functionality in most cases, it can make warning messages to the user much more useful. Signed-off-by: Jeff King Signed-off-by: Junio C Hamano --- dir.c | 12 ++++++++++++ dir.h | 5 ++++- 2 files changed, 16 insertions(+), 1 deletion(-) diff --git a/dir.c b/dir.c index 5ba6030e9a..6ed9eda954 100644 --- a/dir.c +++ b/dir.c @@ -291,6 +291,15 @@ struct dir_entry *dir_add_name(struct dir_struct *dir, const char *pathname, int return dir->entries[dir->nr++] = dir_entry_new(pathname, len); } +struct dir_entry *dir_add_ignored(struct dir_struct *dir, const char *pathname, int len) +{ + if (cache_name_pos(pathname, len) >= 0) + return NULL; + + ALLOC_GROW(dir->ignored, dir->ignored_nr, dir->ignored_alloc); + return dir->ignored[dir->ignored_nr++] = dir_entry_new(pathname, len); +} + enum exist_status { index_nonexistent = 0, index_directory, @@ -463,6 +472,8 @@ static int read_directory_recursive(struct dir_struct *dir, const char *path, co continue; exclude = excluded(dir, fullname); + if (exclude && dir->collect_ignored) + dir_add_ignored(dir, fullname, baselen + len); if (exclude != dir->show_ignored) { if (!dir->show_ignored || DTYPE(de) != DT_DIR) { continue; @@ -609,6 +620,7 @@ int read_directory(struct dir_struct *dir, const char *path, const char *base, i read_directory_recursive(dir, path, base, baselen, 0, simplify); free_simplify(simplify); qsort(dir->entries, dir->nr, sizeof(struct dir_entry *), cmp_name); + qsort(dir->ignored, dir->ignored_nr, sizeof(struct dir_entry *), cmp_name); return dir->nr; } diff --git a/dir.h b/dir.h index 172147fd3d..c94f3cb066 100644 --- a/dir.h +++ b/dir.h @@ -31,11 +31,14 @@ struct exclude_list { struct dir_struct { int nr, alloc; + int ignored_nr, ignored_alloc; unsigned int show_ignored:1, show_other_directories:1, hide_empty_directories:1, - no_gitlinks:1; + no_gitlinks:1, + collect_ignored:1; struct dir_entry **entries; + struct dir_entry **ignored; /* Exclude info */ const char *exclude_per_dir; -- cgit v1.2.1 From e96980ef8164f266308ea5fec536863a629866dc Mon Sep 17 00:00:00 2001 From: Jeff King Date: Tue, 12 Jun 2007 23:42:14 +0200 Subject: builtin-add: simplify (and increase accuracy of) exclude handling Previously, the code would always set up the excludes, and then manually pick through the pathspec we were given, assuming that non-added but existing paths were just ignored. This was mostly correct, but would erroneously mark a totally empty directory as 'ignored'. Instead, we now use the collect_ignored option of dir_struct, which unambiguously tells us whether a path was ignored. This simplifies the code, and means empty directories are now just not mentioned at all. Furthermore, we now conditionally ask dir_struct to respect excludes, depending on whether the '-f' flag has been set. This means we don't have to pick through the result, checking for an 'ignored' flag; ignored entries were either added or not in the first place. We can safely get rid of the special 'ignored' flags to dir_entry, which were not used anywhere else. Signed-off-by: Jeff King Signed-off-by: Jonas Fonseca Signed-off-by: Junio C Hamano --- builtin-add.c | 69 ++++++++++++++++++----------------------------------------- dir.c | 16 ++++++++++++-- dir.h | 4 +--- 3 files changed, 36 insertions(+), 53 deletions(-) diff --git a/builtin-add.c b/builtin-add.c index 159117106a..734547994f 100644 --- a/builtin-add.c +++ b/builtin-add.c @@ -40,42 +40,29 @@ static void prune_directory(struct dir_struct *dir, const char **pathspec, int p dir->nr = dst - dir->entries; for (i = 0; i < specs; i++) { - struct stat st; - const char *match; - if (seen[i]) - continue; - - match = pathspec[i]; - if (!match[0]) - continue; - - /* Existing file? We must have ignored it */ - if (!lstat(match, &st)) { - struct dir_entry *ent; - - ent = dir_add_name(dir, match, strlen(match)); - ent->ignored = 1; - if (S_ISDIR(st.st_mode)) - ent->ignored_dir = 1; - continue; - } - die("pathspec '%s' did not match any files", match); + if (!seen[i] && !file_exists(pathspec[i])) + die("pathspec '%s' did not match any files", + pathspec[i]); } } -static void fill_directory(struct dir_struct *dir, const char **pathspec) +static void fill_directory(struct dir_struct *dir, const char **pathspec, + int ignored_too) { const char *path, *base; int baselen; /* Set up the default git porcelain excludes */ memset(dir, 0, sizeof(*dir)); - dir->exclude_per_dir = ".gitignore"; - path = git_path("info/exclude"); - if (!access(path, R_OK)) - add_excludes_from_file(dir, path); - if (!access(excludes_file, R_OK)) - add_excludes_from_file(dir, excludes_file); + if (!ignored_too) { + dir->collect_ignored = 1; + dir->exclude_per_dir = ".gitignore"; + path = git_path("info/exclude"); + if (!access(path, R_OK)) + add_excludes_from_file(dir, path); + if (!access(excludes_file, R_OK)) + add_excludes_from_file(dir, excludes_file); + } /* * Calculate common prefix for the pathspec, and @@ -219,13 +206,11 @@ int cmd_add(int argc, const char **argv, const char *prefix) } pathspec = get_pathspec(prefix, argv + i); - fill_directory(&dir, pathspec); + fill_directory(&dir, pathspec, ignored_too); if (show_only) { const char *sep = "", *eof = ""; for (i = 0; i < dir.nr; i++) { - if (!ignored_too && dir.entries[i]->ignored) - continue; printf("%s%s", sep, dir.entries[i]->name); sep = " "; eof = "\n"; @@ -237,25 +222,13 @@ int cmd_add(int argc, const char **argv, const char *prefix) if (read_cache() < 0) die("index file corrupt"); - if (!ignored_too) { - int has_ignored = 0; - for (i = 0; i < dir.nr; i++) - if (dir.entries[i]->ignored) - has_ignored = 1; - if (has_ignored) { - fprintf(stderr, ignore_warning); - for (i = 0; i < dir.nr; i++) { - if (!dir.entries[i]->ignored) - continue; - fprintf(stderr, "%s", dir.entries[i]->name); - if (dir.entries[i]->ignored_dir) - fprintf(stderr, " (directory)"); - fputc('\n', stderr); - } - fprintf(stderr, - "Use -f if you really want to add them.\n"); - exit(1); + if (dir.ignored_nr) { + fprintf(stderr, ignore_warning); + for (i = 0; i < dir.ignored_nr; i++) { + fprintf(stderr, "%s\n", dir.ignored[i]->name); } + fprintf(stderr, "Use -f if you really want to add them.\n"); + exit(1); } for (i = 0; i < dir.nr; i++) diff --git a/dir.c b/dir.c index 6ed9eda954..98e24adcd7 100644 --- a/dir.c +++ b/dir.c @@ -275,7 +275,6 @@ static struct dir_entry *dir_entry_new(const char *pathname, int len) { struct dir_entry *ent; ent = xmalloc(sizeof(*ent) + len + 1); - ent->ignored = ent->ignored_dir = 0; ent->len = len; memcpy(ent->name, pathname, len); ent->name[len] = 0; @@ -432,6 +431,18 @@ static int simplify_away(const char *path, int pathlen, const struct path_simpli return 0; } +static int in_pathspec(const char *path, int len, const struct path_simplify *simplify) +{ + if (simplify) { + for (; simplify->path; simplify++) { + if (len == simplify->len + && !memcmp(path, simplify->path, len)) + return 1; + } + } + return 0; +} + /* * Read a directory tree. We currently ignore anything but * directories, regular files and symlinks. That's because git @@ -472,7 +483,8 @@ static int read_directory_recursive(struct dir_struct *dir, const char *path, co continue; exclude = excluded(dir, fullname); - if (exclude && dir->collect_ignored) + if (exclude && dir->collect_ignored + && in_pathspec(fullname, baselen + len, simplify)) dir_add_ignored(dir, fullname, baselen + len); if (exclude != dir->show_ignored) { if (!dir->show_ignored || DTYPE(de) != DT_DIR) { diff --git a/dir.h b/dir.h index c94f3cb066..ec0e8ababc 100644 --- a/dir.h +++ b/dir.h @@ -13,9 +13,7 @@ struct dir_entry { - unsigned int ignored : 1; - unsigned int ignored_dir : 1; - unsigned int len : 30; + unsigned int len; char name[FLEX_ARRAY]; /* more */ }; -- cgit v1.2.1 From c927e6c69b50877e116340671ed35aaf6d3a8f49 Mon Sep 17 00:00:00 2001 From: Jeff King Date: Sat, 16 Jun 2007 18:37:39 -0400 Subject: Fix ALLOC_GROW off-by-one The ALLOC_GROW macro will never let us fill the array completely, instead allocating an extra chunk if that would be the case. This is because the 'nr' argument was originally treated as "how much we do have now" instead of "how much do we want". The latter makes much more sense because you can grow by more than one item. This off-by-one never resulted in an error because it meant we were overly conservative about when to allocate. Any callers which passed "how much we have now" need to be updated, or they will fail to allocate enough. Signed-off-by: Jeff King Signed-off-by: Junio C Hamano --- cache.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/cache.h b/cache.h index 9700ca5018..aba7a5ec04 100644 --- a/cache.h +++ b/cache.h @@ -234,7 +234,7 @@ extern void verify_non_filename(const char *prefix, const char *name); */ #define ALLOC_GROW(x, nr, alloc) \ do { \ - if ((nr) >= alloc) { \ + if ((nr) > alloc) { \ if (alloc_nr(alloc) < (nr)) \ alloc = (nr); \ else \ -- cgit v1.2.1 From 25fd2f7a310df17dca298a3acf2aba716ceb8ce3 Mon Sep 17 00:00:00 2001 From: Jeff King Date: Sat, 16 Jun 2007 18:43:40 -0400 Subject: Fix ALLOC_GROW calls with obsolete semantics ALLOC_GROW now expects the 'nr' argument to be "how much you want" and not "how much you have". This fixes all cases where we weren't previously adding anything to the 'nr'. Signed-off-by: Jeff King Signed-off-by: Junio C Hamano --- dir.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/dir.c b/dir.c index 98e24adcd7..8d8faf5d78 100644 --- a/dir.c +++ b/dir.c @@ -286,7 +286,7 @@ struct dir_entry *dir_add_name(struct dir_struct *dir, const char *pathname, int if (cache_name_pos(pathname, len) >= 0) return NULL; - ALLOC_GROW(dir->entries, dir->nr, dir->alloc); + ALLOC_GROW(dir->entries, dir->nr+1, dir->alloc); return dir->entries[dir->nr++] = dir_entry_new(pathname, len); } @@ -295,7 +295,7 @@ struct dir_entry *dir_add_ignored(struct dir_struct *dir, const char *pathname, if (cache_name_pos(pathname, len) >= 0) return NULL; - ALLOC_GROW(dir->ignored, dir->ignored_nr, dir->ignored_alloc); + ALLOC_GROW(dir->ignored, dir->ignored_nr+1, dir->ignored_alloc); return dir->ignored[dir->ignored_nr++] = dir_entry_new(pathname, len); } -- cgit v1.2.1