From 4acfd1b799acf43642a28a22cc794266c25129ef Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Mon, 10 Sep 2007 12:35:05 +0200 Subject: Change semantics of interpolate to work like snprintf. Also fix many off-by-ones and a useless memset. Signed-off-by: Pierre Habouzit Signed-off-by: Junio C Hamano --- commit.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'commit.c') diff --git a/commit.c b/commit.c index 99f65cee0e..25781cc833 100644 --- a/commit.c +++ b/commit.c @@ -923,15 +923,14 @@ long format_commit_message(const struct commit *commit, const void *format, do { char *buf = *buf_p; - unsigned long space = *space_p; + unsigned long len; - space = interpolate(buf, space, format, + len = interpolate(buf, *space_p, format, table, ARRAY_SIZE(table)); - if (!space) + if (len < *space_p) break; - buf = xrealloc(buf, space); + ALLOC_GROW(buf, len + 1, *space_p); *buf_p = buf; - *space_p = space; } while (1); interp_clear_table(table, ARRAY_SIZE(table)); -- cgit v1.2.1 From 674d1727305211f7ade4ade70440220f74f55162 Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Mon, 10 Sep 2007 12:35:06 +0200 Subject: Rework pretty_print_commit to use strbufs instead of custom buffers. Also remove the "len" parameter, as: (1) it was used as a max boundary, and every caller used ~0u (2) we check for final NUL no matter what, so it doesn't help for speed. As a result most of the pp_* function takes 3 arguments less, and we need a lot less local variables, this makes the code way more readable, and easier to extend if needed. This patch also fixes some spacing and cosmetic issues. This patch also fixes (as a side effect) a memory leak intoruced in builtin-archive.c at commit df4a394f (fmt was xmalloc'ed and not free'd) Signed-off-by: Pierre Habouzit Signed-off-by: Junio C Hamano --- commit.c | 333 ++++++++++++++++++++++++--------------------------------------- 1 file changed, 124 insertions(+), 209 deletions(-) (limited to 'commit.c') diff --git a/commit.c b/commit.c index 25781cc833..6602e2c72f 100644 --- a/commit.c +++ b/commit.c @@ -458,11 +458,11 @@ void clear_commit_marks(struct commit *commit, unsigned int mark) /* * Generic support for pretty-printing the header */ -static int get_one_line(const char *msg, unsigned long len) +static int get_one_line(const char *msg) { int ret = 0; - while (len--) { + for (;;) { char c = *msg++; if (!c) break; @@ -485,31 +485,24 @@ static int is_rfc2047_special(char ch) return (non_ascii(ch) || (ch == '=') || (ch == '?') || (ch == '_')); } -static int add_rfc2047(char *buf, const char *line, int len, +static void add_rfc2047(struct strbuf *sb, const char *line, int len, const char *encoding) { - char *bp = buf; - int i, needquote; - char q_encoding[128]; - const char *q_encoding_fmt = "=?%s?q?"; + int i, last; - for (i = needquote = 0; !needquote && i < len; i++) { + for (i = 0; i < len; i++) { int ch = line[i]; if (non_ascii(ch)) - needquote++; - if ((i + 1 < len) && - (ch == '=' && line[i+1] == '?')) - needquote++; + goto needquote; + if ((i + 1 < len) && (ch == '=' && line[i+1] == '?')) + goto needquote; } - if (!needquote) - return sprintf(buf, "%.*s", len, line); - - i = snprintf(q_encoding, sizeof(q_encoding), q_encoding_fmt, encoding); - if (sizeof(q_encoding) < i) - die("Insanely long encoding name %s", encoding); - memcpy(bp, q_encoding, i); - bp += i; - for (i = 0; i < len; i++) { + strbuf_add(sb, line, len); + return; + +needquote: + strbuf_addf(sb, "=?%s?q?", encoding); + for (i = last = 0; i < len; i++) { unsigned ch = line[i] & 0xFF; /* * We encode ' ' using '=20' even though rfc2047 @@ -518,15 +511,13 @@ static int add_rfc2047(char *buf, const char *line, int len, * leave the underscore in place. */ if (is_rfc2047_special(ch) || ch == ' ') { - sprintf(bp, "=%02X", ch); - bp += 3; + strbuf_add(sb, line + last, i - last); + strbuf_addf(sb, "=%02X", ch); + last = i + 1; } - else - *bp++ = ch; } - memcpy(bp, "?=", 2); - bp += 2; - return bp - buf; + strbuf_add(sb, line + last, len - last); + strbuf_addstr(sb, "?="); } static unsigned long bound_rfc2047(unsigned long len, const char *encoding) @@ -537,21 +528,21 @@ static unsigned long bound_rfc2047(unsigned long len, const char *encoding) return len * 3 + elen + 100; } -static int add_user_info(const char *what, enum cmit_fmt fmt, char *buf, +static void add_user_info(const char *what, enum cmit_fmt fmt, struct strbuf *sb, const char *line, enum date_mode dmode, const char *encoding) { char *date; int namelen; unsigned long time; - int tz, ret; + int tz; const char *filler = " "; if (fmt == CMIT_FMT_ONELINE) - return 0; + return; date = strchr(line, '>'); if (!date) - return 0; + return; namelen = ++date - line; time = strtoul(date, &date, 10); tz = strtol(date, NULL, 10); @@ -560,42 +551,35 @@ static int add_user_info(const char *what, enum cmit_fmt fmt, char *buf, char *name_tail = strchr(line, '<'); int display_name_length; if (!name_tail) - return 0; + return; while (line < name_tail && isspace(name_tail[-1])) name_tail--; display_name_length = name_tail - line; filler = ""; - strcpy(buf, "From: "); - ret = strlen(buf); - ret += add_rfc2047(buf + ret, line, display_name_length, - encoding); - memcpy(buf + ret, name_tail, namelen - display_name_length); - ret += namelen - display_name_length; - buf[ret++] = '\n'; + strbuf_addstr(sb, "From: "); + add_rfc2047(sb, line, display_name_length, encoding); + strbuf_add(sb, name_tail, namelen - display_name_length); + strbuf_addch(sb, '\n'); } else { - ret = sprintf(buf, "%s: %.*s%.*s\n", what, + strbuf_addf(sb, "%s: %.*s%.*s\n", what, (fmt == CMIT_FMT_FULLER) ? 4 : 0, filler, namelen, line); } switch (fmt) { case CMIT_FMT_MEDIUM: - ret += sprintf(buf + ret, "Date: %s\n", - show_date(time, tz, dmode)); + strbuf_addf(sb, "Date: %s\n", show_date(time, tz, dmode)); break; case CMIT_FMT_EMAIL: - ret += sprintf(buf + ret, "Date: %s\n", - show_date(time, tz, DATE_RFC2822)); + strbuf_addf(sb, "Date: %s\n", show_date(time, tz, DATE_RFC2822)); break; case CMIT_FMT_FULLER: - ret += sprintf(buf + ret, "%sDate: %s\n", what, - show_date(time, tz, dmode)); + strbuf_addf(sb, "%sDate: %s\n", what, show_date(time, tz, dmode)); break; default: /* notin' */ break; } - return ret; } static int is_empty_line(const char *line, int *len_p) @@ -607,16 +591,16 @@ static int is_empty_line(const char *line, int *len_p) return !len; } -static int add_merge_info(enum cmit_fmt fmt, char *buf, const struct commit *commit, int abbrev) +static void add_merge_info(enum cmit_fmt fmt, struct strbuf *sb, + const struct commit *commit, int abbrev) { struct commit_list *parent = commit->parents; - int offset; if ((fmt == CMIT_FMT_ONELINE) || (fmt == CMIT_FMT_EMAIL) || !parent || !parent->next) - return 0; + return; - offset = sprintf(buf, "Merge:"); + strbuf_addstr(sb, "Merge:"); while (parent) { struct commit *p = parent->item; @@ -629,10 +613,9 @@ static int add_merge_info(enum cmit_fmt fmt, char *buf, const struct commit *com dots = (abbrev && strlen(hex) != 40) ? "..." : ""; parent = parent->next; - offset += sprintf(buf + offset, " %s%s", hex, dots); + strbuf_addf(sb, " %s%s", hex, dots); } - buf[offset++] = '\n'; - return offset; + strbuf_addch(sb, '\n'); } static char *get_header(const struct commit *commit, const char *key) @@ -787,8 +770,8 @@ static void fill_person(struct interp *table, const char *msg, int len) interp_set_entry(table, 6, show_date(date, tz, DATE_ISO8601)); } -long format_commit_message(const struct commit *commit, const void *format, - char **buf_p, unsigned long *space_p) +void format_commit_message(const struct commit *commit, + const void *format, struct strbuf *sb) { struct interp table[] = { { "%H" }, /* commit hash */ @@ -841,6 +824,7 @@ long format_commit_message(const struct commit *commit, const void *format, }; struct commit_list *p; char parents[1024]; + unsigned long len; int i; enum { HEADER, SUBJECT, BODY } state; const char *msg = commit->buffer; @@ -921,20 +905,15 @@ long format_commit_message(const struct commit *commit, const void *format, if (!table[i].value) interp_set_entry(table, i, ""); - do { - char *buf = *buf_p; - unsigned long len; - - len = interpolate(buf, *space_p, format, - table, ARRAY_SIZE(table)); - if (len < *space_p) - break; - ALLOC_GROW(buf, len + 1, *space_p); - *buf_p = buf; - } while (1); + len = interpolate(sb->buf + sb->len, strbuf_avail(sb), + format, table, ARRAY_SIZE(table)); + if (len > strbuf_avail(sb)) { + strbuf_grow(sb, len); + interpolate(sb->buf + sb->len, strbuf_avail(sb) + 1, + format, table, ARRAY_SIZE(table)); + } + strbuf_setlen(sb, sb->len + len); interp_clear_table(table, ARRAY_SIZE(table)); - - return strlen(*buf_p); } static void pp_header(enum cmit_fmt fmt, @@ -943,34 +922,24 @@ static void pp_header(enum cmit_fmt fmt, 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) + struct strbuf *sb) { int parents_shown = 0; for (;;) { const char *line = *msg_p; - char *dst; - int linelen = get_one_line(*msg_p, *len_p); - unsigned long len; + int linelen = get_one_line(*msg_p); 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; + strbuf_add(sb, line, linelen); continue; } @@ -988,10 +957,8 @@ static void pp_header(enum cmit_fmt fmt, 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); + strbuf_grow(sb, num * 50 + 20); + add_merge_info(fmt, sb, commit, abbrev); parents_shown = 1; } @@ -1001,129 +968,99 @@ static void pp_header(enum cmit_fmt fmt, * FULLER shows both authors and dates. */ if (!memcmp(line, "author ", 7)) { - len = linelen; + unsigned long len = linelen; if (fmt == CMIT_FMT_EMAIL) len = bound_rfc2047(linelen, encoding); - ALLOC_GROW(*buf_p, *ofs_p + len + 80, *space_p); - dst = *buf_p + *ofs_p; - *ofs_p += add_user_info("Author", fmt, dst, - line + 7, dmode, encoding); + strbuf_grow(sb, len + 80); + add_user_info("Author", fmt, sb, line + 7, dmode, encoding); } if (!memcmp(line, "committer ", 10) && (fmt == CMIT_FMT_FULL || fmt == CMIT_FMT_FULLER)) { - len = linelen; + unsigned long len = linelen; if (fmt == CMIT_FMT_EMAIL) len = bound_rfc2047(linelen, encoding); - ALLOC_GROW(*buf_p, *ofs_p + len + 80, *space_p); - dst = *buf_p + *ofs_p; - *ofs_p += add_user_info("Commit", fmt, dst, - line + 10, dmode, encoding); + strbuf_grow(sb, len + 80); + add_user_info("Commit", fmt, sb, 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, + struct strbuf *sb, const char *subject, const char *after_subject, const char *encoding, int plain_non_ascii) { - char *title; - unsigned long title_alloc, title_len; + struct strbuf title; unsigned long len; - title_len = 0; - title_alloc = 80; - title = xmalloc(title_alloc); + strbuf_init(&title, 80); + for (;;) { const char *line = *msg_p; - int linelen = get_one_line(line, *len_p); - *msg_p += linelen; - *len_p -= linelen; + int linelen = get_one_line(line); + *msg_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) { + strbuf_grow(&title, linelen + 2); + if (title.len) { if (fmt == CMIT_FMT_EMAIL) { - len++; - title[title_len++] = '\n'; + strbuf_addch(&title, '\n'); } - len++; - title[title_len++] = ' '; + strbuf_addch(&title, ' '); } - memcpy(title + title_len, line, linelen); - title_len += linelen; + strbuf_add(&title, line, linelen); } /* Enough slop for the MIME header and rfc2047 */ - len = bound_rfc2047(title_len, encoding)+ 1000; + 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); + strbuf_grow(sb, title.len + len); 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); + strbuf_addstr(sb, subject); + add_rfc2047(sb, title.buf, title.len, encoding); } else { - memcpy(*buf_p + *ofs_p, title, title_len); - *ofs_p += title_len; + strbuf_addbuf(sb, &title); } - (*buf_p)[(*ofs_p)++] = '\n'; + strbuf_addch(sb, '\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); + strbuf_addf(sb, header_fmt, encoding); } if (after_subject) { - len = strlen(after_subject); - memcpy(*buf_p + *ofs_p, after_subject, len); - *ofs_p += len; + strbuf_addstr(sb, after_subject); } - free(title); if (fmt == CMIT_FMT_EMAIL) { - ALLOC_GROW(*buf_p, *ofs_p + 20, *space_p); - (*buf_p)[(*ofs_p)++] = '\n'; + strbuf_addch(sb, '\n'); } + strbuf_release(&title); } 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, + struct strbuf *sb, int indent) { int first = 1; for (;;) { const char *line = *msg_p; - int linelen = get_one_line(line, *len_p); + int linelen = get_one_line(line); *msg_p += linelen; - *len_p -= linelen; if (!linelen) break; @@ -1136,36 +1073,32 @@ static void pp_remainder(enum cmit_fmt fmt, } first = 0; - ALLOC_GROW(*buf_p, *ofs_p + linelen + indent + 20, *space_p); + strbuf_grow(sb, linelen + indent + 20); if (indent) { - memset(*buf_p + *ofs_p, ' ', indent); - *ofs_p += indent; + memset(sb->buf + sb->len, ' ', indent); + strbuf_setlen(sb, sb->len + indent); } - memcpy(*buf_p + *ofs_p, line, linelen); - *ofs_p += linelen; - (*buf_p)[(*ofs_p)++] = '\n'; + strbuf_add(sb, line, linelen); + strbuf_addch(sb, '\n'); } } -unsigned long pretty_print_commit(enum cmit_fmt fmt, - const struct commit *commit, - unsigned long len, - char **buf_p, unsigned long *space_p, - int abbrev, const char *subject, - const char *after_subject, +void pretty_print_commit(enum cmit_fmt fmt, const struct commit *commit, + struct strbuf *sb, int abbrev, + const char *subject, const char *after_subject, enum date_mode dmode) { - unsigned long offset = 0; unsigned long beginning_of_body; int indent = 4; const char *msg = commit->buffer; int plain_non_ascii = 0; char *reencoded; const char *encoding; - char *buf; - if (fmt == CMIT_FMT_USERFORMAT) - return format_commit_message(commit, user_format, buf_p, space_p); + if (fmt == CMIT_FMT_USERFORMAT) { + format_commit_message(commit, user_format, sb); + return; + } encoding = (git_log_output_encoding ? git_log_output_encoding @@ -1175,7 +1108,6 @@ unsigned long pretty_print_commit(enum cmit_fmt fmt, reencoded = logmsg_reencode(commit, encoding); if (reencoded) { msg = reencoded; - len = strlen(reencoded); } if (fmt == CMIT_FMT_ONELINE || fmt == CMIT_FMT_EMAIL) @@ -1190,14 +1122,13 @@ unsigned long pretty_print_commit(enum cmit_fmt fmt, if (fmt == CMIT_FMT_EMAIL && !after_subject) { int i, ch, in_body; - for (in_body = i = 0; (ch = msg[i]) && i < len; i++) { + for (in_body = i = 0; (ch = msg[i]); i++) { if (!in_body) { /* author could be non 7-bit ASCII but * the log may be so; skip over the * header part first. */ - if (ch == '\n' && - i + 1 < len && msg[i+1] == '\n') + if (ch == '\n' && msg[i+1] == '\n') in_body = 1; } else if (non_ascii(ch)) { @@ -1207,59 +1138,44 @@ unsigned long pretty_print_commit(enum cmit_fmt fmt, } } - pp_header(fmt, abbrev, dmode, encoding, - commit, &msg, &len, - &offset, buf_p, space_p); + pp_header(fmt, abbrev, dmode, encoding, commit, &msg, sb); if (fmt != CMIT_FMT_ONELINE && !subject) { - ALLOC_GROW(*buf_p, offset + 20, *space_p); - (*buf_p)[offset++] = '\n'; + strbuf_addch(sb, '\n'); } /* Skip excess blank lines at the beginning of body, if any... */ for (;;) { - int linelen = get_one_line(msg, len); + int linelen = get_one_line(msg); int ll = linelen; if (!linelen) break; if (!is_empty_line(msg, &ll)) break; msg += linelen; - len -= linelen; } /* 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); - - beginning_of_body = offset; - if (fmt != CMIT_FMT_ONELINE) - pp_remainder(fmt, &msg, &len, &offset, - buf_p, space_p, indent); - - while (offset && isspace((*buf_p)[offset-1])) - offset--; + if (fmt == CMIT_FMT_ONELINE || fmt == CMIT_FMT_EMAIL) + pp_title_line(fmt, &msg, sb, subject, + after_subject, encoding, plain_non_ascii); - ALLOC_GROW(*buf_p, offset + 20, *space_p); - buf = *buf_p; + beginning_of_body = sb->len; + if (fmt != CMIT_FMT_ONELINE) + pp_remainder(fmt, &msg, sb, indent); + strbuf_rtrim(sb); /* Make sure there is an EOLN for the non-oneline case */ if (fmt != CMIT_FMT_ONELINE) - buf[offset++] = '\n'; + strbuf_addch(sb, '\n'); /* * 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 && offset <= beginning_of_body) - buf[offset++] = '\n'; - buf[offset] = '\0'; + if (fmt == CMIT_FMT_EMAIL && sb->len <= beginning_of_body) + strbuf_addch(sb, '\n'); free(reencoded); - return offset; } struct commit *pop_commit(struct commit_list **stack) @@ -1338,12 +1254,12 @@ void sort_in_topological_order_fn(struct commit_list ** list, int lifo, next=next->next; } /* - * find the tips - * - * tips are nodes not reachable from any other node in the list - * - * the tips serve as a starting set for the work queue. - */ + * find the tips + * + * tips are nodes not reachable from any other node in the list + * + * the tips serve as a starting set for the work queue. + */ next=*list; insert = &work; while (next) { @@ -1370,9 +1286,9 @@ void sort_in_topological_order_fn(struct commit_list ** list, int lifo, if (pn) { /* * parents are only enqueued for emission - * when all their children have been emitted thereby - * guaranteeing topological order. - */ + * when all their children have been emitted thereby + * guaranteeing topological order. + */ pn->indegree--; if (!pn->indegree) { if (!lifo) @@ -1384,9 +1300,9 @@ void sort_in_topological_order_fn(struct commit_list ** list, int lifo, parents=parents->next; } /* - * work_item is a commit all of whose children - * have already been emitted. we can emit it now. - */ + * work_item is a commit all of whose children + * have already been emitted. we can emit it now. + */ *pptr = work_node->list_item; pptr = &(*pptr)->next; *pptr = NULL; @@ -1482,8 +1398,7 @@ static struct commit_list *merge_bases(struct commit *one, struct commit *two) } struct commit_list *get_merge_bases(struct commit *one, - struct commit *two, - int cleanup) + struct commit *two, int cleanup) { struct commit_list *list; struct commit **rslt; -- cgit v1.2.1 From a08f23ab3eab67aac7163a284038f45fa99ef66f Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Sat, 15 Sep 2007 23:50:12 +0200 Subject: Refactor replace_encoding_header. * Be more clever in how we search for "encoding ...\n": parse for real instead of the sloppy strstr's. * use strbuf_splice to do the substring replacements. Signed-off-by: Pierre Habouzit Acked-by: Linus Torvalds Signed-off-by: Junio C Hamano --- commit.c | 59 +++++++++++++++++++++++------------------------------------ 1 file changed, 23 insertions(+), 36 deletions(-) (limited to 'commit.c') diff --git a/commit.c b/commit.c index 6602e2c72f..13af93363e 100644 --- a/commit.c +++ b/commit.c @@ -648,47 +648,34 @@ static char *get_header(const struct commit *commit, const char *key) static char *replace_encoding_header(char *buf, const char *encoding) { - char *encoding_header = strstr(buf, "\nencoding "); - char *header_end = strstr(buf, "\n\n"); - char *end_of_encoding_header; - int encoding_header_pos; - int encoding_header_len; - int new_len; - int need_len; - int buflen = strlen(buf) + 1; - - if (!header_end) - header_end = buf + buflen; - if (!encoding_header || encoding_header >= header_end) - return buf; - encoding_header++; - end_of_encoding_header = strchr(encoding_header, '\n'); - if (!end_of_encoding_header) + struct strbuf tmp; + size_t start, len; + char *cp = buf; + + /* guess if there is an encoding header before a \n\n */ + while (strncmp(cp, "encoding ", strlen("encoding "))) { + cp = strchr(cp, '\n'); + if (!cp || *++cp == '\n') + return buf; + } + start = cp - buf; + cp = strchr(cp, '\n'); + if (!cp) return buf; /* should not happen but be defensive */ - end_of_encoding_header++; - - encoding_header_len = end_of_encoding_header - encoding_header; - encoding_header_pos = encoding_header - buf; + len = cp + 1 - (buf + start); + strbuf_init(&tmp, 0); + strbuf_attach(&tmp, buf, strlen(buf), strlen(buf) + 1); if (is_encoding_utf8(encoding)) { /* we have re-coded to UTF-8; drop the header */ - memmove(encoding_header, end_of_encoding_header, - buflen - (encoding_header_pos + encoding_header_len)); - return buf; - } - new_len = strlen(encoding); - need_len = new_len + strlen("encoding \n"); - if (encoding_header_len < need_len) { - buf = xrealloc(buf, buflen + (need_len - encoding_header_len)); - encoding_header = buf + encoding_header_pos; - end_of_encoding_header = encoding_header + encoding_header_len; + strbuf_splice(&tmp, start, len, NULL, 0); + } else { + /* just replaces XXXX in 'encoding XXXX\n' */ + strbuf_splice(&tmp, start + strlen("encoding "), + len - strlen("encoding \n"), + encoding, strlen(encoding)); } - memmove(end_of_encoding_header + (need_len - encoding_header_len), - end_of_encoding_header, - buflen - (encoding_header_pos + encoding_header_len)); - memcpy(encoding_header + 9, encoding, strlen(encoding)); - encoding_header[9 + new_len] = '\n'; - return buf; + return tmp.buf; } static char *logmsg_reencode(const struct commit *commit, -- cgit v1.2.1 From 8b6087fb25068d6af927f112a93dc056930f3108 Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Sun, 16 Sep 2007 10:19:01 +0200 Subject: Remove preemptive allocations. Careful profiling shows that we spend more time guessing what pattern allocation will have, whereas we can delay it only at the point where add_rfc2047 will be used and don't allocate huge memory area for the many cases where it's not. Signed-off-by: Pierre Habouzit Acked-by: Linus Torvalds Signed-off-by: Junio C Hamano --- commit.c | 35 +++++------------------------------ 1 file changed, 5 insertions(+), 30 deletions(-) (limited to 'commit.c') diff --git a/commit.c b/commit.c index 13af93363e..85889f9664 100644 --- a/commit.c +++ b/commit.c @@ -501,6 +501,7 @@ static void add_rfc2047(struct strbuf *sb, const char *line, int len, return; needquote: + strbuf_grow(sb, len * 3 + strlen(encoding) + 100); strbuf_addf(sb, "=?%s?q?", encoding); for (i = last = 0; i < len; i++) { unsigned ch = line[i] & 0xFF; @@ -520,14 +521,6 @@ needquote: strbuf_addstr(sb, "?="); } -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 void add_user_info(const char *what, enum cmit_fmt fmt, struct strbuf *sb, const char *line, enum date_mode dmode, const char *encoding) @@ -560,8 +553,7 @@ static void add_user_info(const char *what, enum cmit_fmt fmt, struct strbuf *sb add_rfc2047(sb, line, display_name_length, encoding); strbuf_add(sb, name_tail, namelen - display_name_length); strbuf_addch(sb, '\n'); - } - else { + } else { strbuf_addf(sb, "%s: %.*s%.*s\n", what, (fmt == CMIT_FMT_FULLER) ? 4 : 0, filler, namelen, line); @@ -955,19 +947,12 @@ static void pp_header(enum cmit_fmt fmt, * FULLER shows both authors and dates. */ if (!memcmp(line, "author ", 7)) { - unsigned long len = linelen; - if (fmt == CMIT_FMT_EMAIL) - len = bound_rfc2047(linelen, encoding); - strbuf_grow(sb, len + 80); + strbuf_grow(sb, linelen + 80); add_user_info("Author", fmt, sb, line + 7, dmode, encoding); } - if (!memcmp(line, "committer ", 10) && (fmt == CMIT_FMT_FULL || fmt == CMIT_FMT_FULLER)) { - unsigned long len = linelen; - if (fmt == CMIT_FMT_EMAIL) - len = bound_rfc2047(linelen, encoding); - strbuf_grow(sb, len + 80); + strbuf_grow(sb, linelen + 80); add_user_info("Commit", fmt, sb, line + 10, dmode, encoding); } } @@ -982,7 +967,6 @@ static void pp_title_line(enum cmit_fmt fmt, int plain_non_ascii) { struct strbuf title; - unsigned long len; strbuf_init(&title, 80); @@ -1004,16 +988,7 @@ static void pp_title_line(enum cmit_fmt fmt, strbuf_add(&title, line, 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); - - strbuf_grow(sb, title.len + len); + strbuf_grow(sb, title.len + 1024); if (subject) { strbuf_addstr(sb, subject); add_rfc2047(sb, title.buf, title.len, encoding); -- cgit v1.2.1 From 182af8343c307436bb5364309aa6d4d46fa5911d Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Sun, 16 Sep 2007 00:32:36 +0200 Subject: Use xmemdupz() in many places. Signed-off-by: Pierre Habouzit Signed-off-by: Junio C Hamano --- commit.c | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) (limited to 'commit.c') diff --git a/commit.c b/commit.c index 85889f9664..f86fa776c0 100644 --- a/commit.c +++ b/commit.c @@ -628,11 +628,7 @@ static char *get_header(const struct commit *commit, const char *key) if (eol - line > key_len && !strncmp(line, key, key_len) && line[key_len] == ' ') { - int len = eol - line - key_len; - char *ret = xmalloc(len); - memcpy(ret, line + key_len + 1, len - 1); - ret[len - 1] = '\0'; - return ret; + return xmemdupz(line + key_len + 1, eol - line - key_len - 1); } line = next; } @@ -709,7 +705,7 @@ static void fill_person(struct interp *table, const char *msg, int len) start = end + 1; while (end > 0 && isspace(msg[end - 1])) end--; - table[0].value = xstrndup(msg, end); + table[0].value = xmemdupz(msg, end); if (start >= len) return; @@ -721,7 +717,7 @@ static void fill_person(struct interp *table, const char *msg, int len) if (end >= len) return; - table[1].value = xstrndup(msg + start, end - start); + table[1].value = xmemdupz(msg + start, end - start); /* parse date */ for (start = end + 1; start < len && isspace(msg[start]); start++) @@ -732,7 +728,7 @@ static void fill_person(struct interp *table, const char *msg, int len) if (msg + start == ep) return; - table[5].value = xstrndup(msg + start, ep - (msg + start)); + table[5].value = xmemdupz(msg + start, ep - (msg + start)); /* parse tz */ for (start = ep - msg + 1; start < len && isspace(msg[start]); start++) @@ -859,7 +855,7 @@ void format_commit_message(const struct commit *commit, ; /* do nothing */ if (state == SUBJECT) { - table[ISUBJECT].value = xstrndup(msg + i, eol - i); + table[ISUBJECT].value = xmemdupz(msg + i, eol - i); i = eol; } if (i == eol) { @@ -875,7 +871,7 @@ void format_commit_message(const struct commit *commit, msg + i + 10, eol - i - 10); else if (!prefixcmp(msg + i, "encoding ")) table[IENCODING].value = - xstrndup(msg + i + 9, eol - i - 9); + xmemdupz(msg + i + 9, eol - i - 9); i = eol; } if (msg[i]) -- cgit v1.2.1 From c76689df6c64a1e987bd779bd71a2042b5131fb9 Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Thu, 20 Sep 2007 00:42:12 +0200 Subject: strbuf API additions and enhancements. Add strbuf_remove, change strbuf_insert: As both are special cases of strbuf_splice, implement them as such. gcc is able to do the math and generate almost optimal code this way. Add strbuf_swap: Exchange the values of its arguments. Use it in fast-import.c Also fix spacing issues in strbuf.h Signed-off-by: Pierre Habouzit --- commit.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'commit.c') diff --git a/commit.c b/commit.c index f86fa776c0..55b08ec0b9 100644 --- a/commit.c +++ b/commit.c @@ -656,7 +656,7 @@ static char *replace_encoding_header(char *buf, const char *encoding) strbuf_attach(&tmp, buf, strlen(buf), strlen(buf) + 1); if (is_encoding_utf8(encoding)) { /* we have re-coded to UTF-8; drop the header */ - strbuf_splice(&tmp, start, len, NULL, 0); + strbuf_remove(&tmp, start, len); } else { /* just replaces XXXX in 'encoding XXXX\n' */ strbuf_splice(&tmp, start + strlen("encoding "), -- cgit v1.2.1 From b315c5c08139c0d3c1e4867a305334e29da01d07 Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Thu, 27 Sep 2007 12:58:23 +0200 Subject: strbuf change: be sure ->buf is never ever NULL. For that purpose, the ->buf is always initialized with a char * buf living in the strbuf module. It is made a char * so that we can sloppily accept things that perform: sb->buf[0] = '\0', and because you can't pass "" as an initializer for ->buf without making gcc unhappy for very good reasons. strbuf_init/_detach/_grow have been fixed to trust ->alloc and not ->buf anymore. as a consequence strbuf_detach is _mandatory_ to detach a buffer, copying ->buf isn't an option anymore, if ->buf is going to escape from the scope, and eventually be free'd. API changes: * strbuf_setlen now always works, so just make strbuf_reset a convenience macro. * strbuf_detatch takes a size_t* optional argument (meaning it can be NULL) to copy the buffer's len, as it was needed for this refactor to make the code more readable, and working like the callers. Signed-off-by: Pierre Habouzit Signed-off-by: Junio C Hamano --- commit.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'commit.c') diff --git a/commit.c b/commit.c index 55b08ec0b9..62cc74d7a9 100644 --- a/commit.c +++ b/commit.c @@ -663,7 +663,7 @@ static char *replace_encoding_header(char *buf, const char *encoding) len - strlen("encoding \n"), encoding, strlen(encoding)); } - return tmp.buf; + return strbuf_detach(&tmp, NULL); } static char *logmsg_reencode(const struct commit *commit, -- cgit v1.2.1