From b449f4cfc972929b638b90d375b8960c37790618 Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Thu, 6 Sep 2007 13:20:05 +0200 Subject: Rework strbuf API and semantics. The gory details are explained in strbuf.h. The change of semantics this patch enforces is that the embeded buffer has always a '\0' character after its last byte, to always make it a C-string. The offs-by-one changes are all related to that very change. A strbuf can be used to store byte arrays, or as an extended string library. The `buf' member can be passed to any C legacy string function, because strbuf operations always ensure there is a terminating \0 at the end of the buffer, not accounted in the `len' field of the structure. A strbuf can be used to generate a string/buffer whose final size is not really known, and then "strbuf_detach" can be used to get the built buffer, and keep the wrapping "strbuf" structure usable for further work again. Other interesting feature: strbuf_grow(sb, size) ensure that there is enough allocated space in `sb' to put `size' new octets of data in the buffer. It helps avoiding reallocating data for nothing when the problem the strbuf helps to solve has a known typical size. Signed-off-by: Pierre Habouzit Signed-off-by: Junio C Hamano diff --git a/archive-tar.c b/archive-tar.c index 66fe3e3..a0763c5 100644 --- a/archive-tar.c +++ b/archive-tar.c @@ -166,7 +166,7 @@ static void write_entry(const unsigned char *sha1, struct strbuf *path, sprintf(header.name, "%s.paxheader", sha1_to_hex(sha1)); } else { if (verbose) - fprintf(stderr, "%.*s\n", path->len, path->buf); + fprintf(stderr, "%.*s\n", (int)path->len, path->buf); if (S_ISDIR(mode) || S_ISGITLINK(mode)) { *header.typeflag = TYPEFLAG_DIR; mode = (mode | 0777) & ~tar_umask; diff --git a/fast-import.c b/fast-import.c index 078079d..2f7baf4 100644 --- a/fast-import.c +++ b/fast-import.c @@ -1595,7 +1595,7 @@ static void read_next_command(void) } else { struct recent_command *rc; - command_buf.buf = NULL; + strbuf_detach(&command_buf); read_line(&command_buf, stdin, '\n'); if (command_buf.eof) return; @@ -1649,7 +1649,6 @@ static void *cmd_data (size_t *size) size_t sz = 8192, term_len = command_buf.len - 5 - 2; length = 0; buffer = xmalloc(sz); - command_buf.buf = NULL; for (;;) { read_line(&command_buf, stdin, '\n'); if (command_buf.eof) @@ -1657,11 +1656,11 @@ static void *cmd_data (size_t *size) if (term_len == command_buf.len && !strcmp(term, command_buf.buf)) break; - ALLOC_GROW(buffer, length + command_buf.len, sz); + ALLOC_GROW(buffer, length + command_buf.len + 1, sz); memcpy(buffer + length, command_buf.buf, - command_buf.len - 1); - length += command_buf.len - 1; + command_buf.len); + length += command_buf.len; buffer[length++] = '\n'; } free(term); @@ -2101,7 +2100,7 @@ static void cmd_new_commit(void) } /* file_change* */ - while (!command_buf.eof && command_buf.len > 1) { + while (!command_buf.eof && command_buf.len > 0) { if (!prefixcmp(command_buf.buf, "M ")) file_change_m(b); else if (!prefixcmp(command_buf.buf, "D ")) @@ -2256,7 +2255,7 @@ static void cmd_reset_branch(void) else b = new_branch(sp); read_next_command(); - if (!cmd_from(b) && command_buf.len > 1) + if (!cmd_from(b) && command_buf.len > 0) unread_command_buf = 1; } @@ -2273,7 +2272,7 @@ static void cmd_checkpoint(void) static void cmd_progress(void) { - fwrite(command_buf.buf, 1, command_buf.len - 1, stdout); + fwrite(command_buf.buf, 1, command_buf.len, stdout); fputc('\n', stdout); fflush(stdout); skip_optional_lf(); diff --git a/mktree.c b/mktree.c index d86dde8..86de5eb 100644 --- a/mktree.c +++ b/mktree.c @@ -92,7 +92,6 @@ int main(int ac, char **av) strbuf_init(&sb); while (1) { - int len; char *ptr, *ntr; unsigned mode; enum object_type type; @@ -101,7 +100,6 @@ int main(int ac, char **av) read_line(&sb, stdin, line_termination); if (sb.eof) break; - len = sb.len; ptr = sb.buf; /* Input is non-recursive ls-tree output format * mode SP type SP sha1 TAB name @@ -111,7 +109,7 @@ int main(int ac, char **av) die("input format error: %s", sb.buf); ptr = ntr + 1; /* type */ ntr = strchr(ptr, ' '); - if (!ntr || sb.buf + len <= ntr + 41 || + if (!ntr || sb.buf + sb.len <= ntr + 40 || ntr[41] != '\t' || get_sha1_hex(ntr + 1, sha1)) die("input format error: %s", sb.buf); diff --git a/strbuf.c b/strbuf.c index e33d06b..7136de1 100644 --- a/strbuf.c +++ b/strbuf.c @@ -2,40 +2,113 @@ #include "strbuf.h" void strbuf_init(struct strbuf *sb) { - sb->buf = NULL; - sb->eof = sb->alloc = sb->len = 0; + memset(sb, 0, sizeof(*sb)); } -static void strbuf_begin(struct strbuf *sb) { +void strbuf_release(struct strbuf *sb) { free(sb->buf); + memset(sb, 0, sizeof(*sb)); +} + +void strbuf_reset(struct strbuf *sb) { + if (sb->len) + strbuf_setlen(sb, 0); + sb->eof = 0; +} + +char *strbuf_detach(struct strbuf *sb) { + char *res = sb->buf; strbuf_init(sb); + return res; +} + +void strbuf_grow(struct strbuf *sb, size_t extra) { + if (sb->len + extra + 1 <= sb->len) + die("you want to use way too much memory"); + ALLOC_GROW(sb->buf, sb->len + extra + 1, sb->alloc); +} + +void strbuf_add(struct strbuf *sb, const void *data, size_t len) { + strbuf_grow(sb, len); + memcpy(sb->buf + sb->len, data, len); + strbuf_setlen(sb, sb->len + len); +} + +void strbuf_addf(struct strbuf *sb, const char *fmt, ...) { + int len; + va_list ap; + + va_start(ap, fmt); + len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap); + va_end(ap); + if (len < 0) { + len = 0; + } + if (len >= strbuf_avail(sb)) { + strbuf_grow(sb, len); + va_start(ap, fmt); + len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap); + va_end(ap); + if (len >= strbuf_avail(sb)) { + die("this should not happen, your snprintf is broken"); + } + } + strbuf_setlen(sb, sb->len + len); } -static void inline strbuf_add(struct strbuf *sb, int ch) { - if (sb->alloc <= sb->len) { - sb->alloc = sb->alloc * 3 / 2 + 16; - sb->buf = xrealloc(sb->buf, sb->alloc); +size_t strbuf_fread(struct strbuf *sb, size_t size, FILE *f) { + size_t res; + + strbuf_grow(sb, size); + res = fread(sb->buf + sb->len, 1, size, f); + if (res > 0) { + strbuf_setlen(sb, sb->len + res); } - sb->buf[sb->len++] = ch; + return res; } -static void strbuf_end(struct strbuf *sb) { - strbuf_add(sb, 0); +ssize_t strbuf_read(struct strbuf *sb, int fd) +{ + size_t oldlen = sb->len; + + for (;;) { + ssize_t cnt; + + strbuf_grow(sb, 8192); + cnt = xread(fd, sb->buf + sb->len, sb->alloc - sb->len - 1); + if (cnt < 0) { + strbuf_setlen(sb, oldlen); + return -1; + } + if (!cnt) + break; + sb->len += cnt; + } + + sb->buf[sb->len] = '\0'; + return sb->len - oldlen; } void read_line(struct strbuf *sb, FILE *fp, int term) { int ch; - strbuf_begin(sb); if (feof(fp)) { + strbuf_release(sb); sb->eof = 1; return; } + + strbuf_reset(sb); while ((ch = fgetc(fp)) != EOF) { if (ch == term) break; - strbuf_add(sb, ch); + strbuf_grow(sb, 1); + sb->buf[sb->len++] = ch; } - if (ch == EOF && sb->len == 0) + if (ch == EOF && sb->len == 0) { + strbuf_release(sb); sb->eof = 1; - strbuf_end(sb); + } + + strbuf_grow(sb, 1); + sb->buf[sb->len] = '\0'; } diff --git a/strbuf.h b/strbuf.h index 74cc012..b40dc99 100644 --- a/strbuf.h +++ b/strbuf.h @@ -1,13 +1,95 @@ #ifndef STRBUF_H #define STRBUF_H + +/* + * Strbuf's can be use in many ways: as a byte array, or to store arbitrary + * long, overflow safe strings. + * + * Strbufs has some invariants that are very important to keep in mind: + * + * 1. the ->buf member is always malloc-ed, hence strbuf's can be used to + * build complex strings/buffers whose final size isn't easily known. + * + * It is legal to copy the ->buf pointer away. Though if you want to reuse + * the strbuf after that, setting ->buf to NULL isn't legal. + * `strbuf_detach' is the operation that detachs a buffer from its shell + * while keeping the shell valid wrt its invariants. + * + * 2. the ->buf member is a byte array that has at least ->len + 1 bytes + * allocated. The extra byte is used to store a '\0', allowing the ->buf + * member to be a valid C-string. Every strbuf function ensure this + * invariant is preserved. + * + * Note that it is OK to "play" with the buffer directly if you work it + * that way: + * + * strbuf_grow(sb, SOME_SIZE); + * // ... here the memory areay starting at sb->buf, and of length + * // sb_avail(sb) is all yours, and you are sure that sb_avail(sb) is at + * // least SOME_SIZE + * strbuf_setlen(sb, sb->len + SOME_OTHER_SIZE); + * + * Of course, SOME_OTHER_SIZE must be smaller or equal to sb_avail(sb). + * + * Doing so is safe, though if it has to be done in many places, adding the + * missing API to the strbuf module is the way to go. + * + * XXX: do _not_ assume that the area that is yours is of size ->alloc - 1 + * even if it's true in the current implementation. Alloc is somehow a + * "private" member that should not be messed with. + */ + +#include + struct strbuf { - int alloc; - int len; + size_t alloc; + size_t len; int eof; char *buf; }; +#define STRBUF_INIT { 0, 0, 0, NULL } + +/*----- strbuf life cycle -----*/ extern void strbuf_init(struct strbuf *); +extern void strbuf_release(struct strbuf *); +extern void strbuf_reset(struct strbuf *); +extern char *strbuf_detach(struct strbuf *); + +/*----- strbuf size related -----*/ +static inline size_t strbuf_avail(struct strbuf *sb) { + return sb->alloc ? sb->alloc - sb->len - 1 : 0; +} +static inline void strbuf_setlen(struct strbuf *sb, size_t len) { + assert (len < sb->alloc); + sb->len = len; + sb->buf[len] = '\0'; +} + +extern void strbuf_grow(struct strbuf *, size_t); + +/*----- add data in your buffer -----*/ +static inline void strbuf_addch(struct strbuf *sb, int c) { + strbuf_grow(sb, 1); + sb->buf[sb->len++] = c; + sb->buf[sb->len] = '\0'; +} + +extern void strbuf_add(struct strbuf *, const void *, size_t); +static inline void strbuf_addstr(struct strbuf *sb, const char *s) { + strbuf_add(sb, s, strlen(s)); +} +static inline void strbuf_addbuf(struct strbuf *sb, struct strbuf *sb2) { + strbuf_add(sb, sb2->buf, sb2->len); +} + +__attribute__((format(printf,2,3))) +extern void strbuf_addf(struct strbuf *sb, const char *fmt, ...); + +extern size_t strbuf_fread(struct strbuf *, size_t, FILE *); +/* XXX: if read fails, any partial read is undone */ +extern ssize_t strbuf_read(struct strbuf *, int fd); + extern void read_line(struct strbuf *, FILE *, int); #endif /* STRBUF_H */ -- cgit v0.10.2-6-g49f6 From 7a604f16b71e3bfd1c6e30d400f05be918e5376e Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Thu, 6 Sep 2007 13:20:06 +0200 Subject: Simplify strbuf uses in archive-tar.c using strbuf API This is just cleaner way to deal with strbufs, using its API rather than reinventing it in the module (e.g. strbuf_append_string is just the plain strbuf_addstr function, and it was used to perform what strbuf_addch does anyways). Signed-off-by: Junio C Hamano diff --git a/archive-tar.c b/archive-tar.c index a0763c5..c84d7c0 100644 --- a/archive-tar.c +++ b/archive-tar.c @@ -78,19 +78,6 @@ static void write_trailer(void) } } -static void strbuf_append_string(struct strbuf *sb, const char *s) -{ - int slen = strlen(s); - int total = sb->len + slen; - if (total + 1 > sb->alloc) { - sb->buf = xrealloc(sb->buf, total + 1); - sb->alloc = total + 1; - } - memcpy(sb->buf + sb->len, s, slen); - sb->len = total; - sb->buf[total] = '\0'; -} - /* * pax extended header records have the format "%u %s=%s\n". %u contains * the size of the whole string (including the %u), the first %s is the @@ -100,26 +87,17 @@ static void strbuf_append_string(struct strbuf *sb, const char *s) static void strbuf_append_ext_header(struct strbuf *sb, const char *keyword, const char *value, unsigned int valuelen) { - char *p; - int len, total, tmp; + int len, tmp; /* "%u %s=%s\n" */ len = 1 + 1 + strlen(keyword) + 1 + valuelen + 1; for (tmp = len; tmp > 9; tmp /= 10) len++; - total = sb->len + len; - if (total > sb->alloc) { - sb->buf = xrealloc(sb->buf, total); - sb->alloc = total; - } - - p = sb->buf; - p += sprintf(p, "%u %s=", len, keyword); - memcpy(p, value, valuelen); - p += valuelen; - *p = '\n'; - sb->len = total; + strbuf_grow(sb, len); + strbuf_addf(sb, "%u %s=", len, keyword); + strbuf_add(sb, value, valuelen); + strbuf_addch(sb, '\n'); } static unsigned int ustar_header_chksum(const struct ustar_header *header) @@ -153,8 +131,7 @@ static void write_entry(const unsigned char *sha1, struct strbuf *path, struct strbuf ext_header; memset(&header, 0, sizeof(header)); - ext_header.buf = NULL; - ext_header.len = ext_header.alloc = 0; + strbuf_init(&ext_header); if (!sha1) { *header.typeflag = TYPEFLAG_GLOBAL_HEADER; @@ -225,8 +202,8 @@ static void write_entry(const unsigned char *sha1, struct strbuf *path, if (ext_header.len > 0) { write_entry(sha1, NULL, 0, ext_header.buf, ext_header.len); - free(ext_header.buf); } + strbuf_release(&ext_header); write_blocked(&header, sizeof(header)); if (S_ISREG(mode) && buffer && size > 0) write_blocked(buffer, size); @@ -235,11 +212,11 @@ static void write_entry(const unsigned char *sha1, struct strbuf *path, static void write_global_extended_header(const unsigned char *sha1) { struct strbuf ext_header; - ext_header.buf = NULL; - ext_header.len = ext_header.alloc = 0; + + strbuf_init(&ext_header); strbuf_append_ext_header(&ext_header, "comment", sha1_to_hex(sha1), 40); write_entry(NULL, NULL, 0, ext_header.buf, ext_header.len); - free(ext_header.buf); + strbuf_release(&ext_header); } static int git_tar_config(const char *var, const char *value) @@ -260,28 +237,18 @@ static int write_tar_entry(const unsigned char *sha1, const char *base, int baselen, const char *filename, unsigned mode, int stage) { - static struct strbuf path; + static struct strbuf path = STRBUF_INIT; int filenamelen = strlen(filename); void *buffer; enum object_type type; unsigned long size; - if (!path.alloc) { - path.buf = xmalloc(PATH_MAX); - path.alloc = PATH_MAX; - path.len = path.eof = 0; - } - if (path.alloc < baselen + filenamelen + 1) { - free(path.buf); - path.buf = xmalloc(baselen + filenamelen + 1); - path.alloc = baselen + filenamelen + 1; - } - memcpy(path.buf, base, baselen); - memcpy(path.buf + baselen, filename, filenamelen); - path.len = baselen + filenamelen; - path.buf[path.len] = '\0'; + strbuf_grow(&path, MAX(PATH_MAX, baselen + filenamelen + 1)); + strbuf_reset(&path); + strbuf_add(&path, base, baselen); + strbuf_add(&path, filename, filenamelen); if (S_ISDIR(mode) || S_ISGITLINK(mode)) { - strbuf_append_string(&path, "/"); + strbuf_addch(&path, '/'); buffer = NULL; size = 0; } else { -- cgit v0.10.2-6-g49f6 From 4a241d79c9020dcafb1f254774bcab200171ab46 Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Thu, 6 Sep 2007 13:20:07 +0200 Subject: fast-import: Use strbuf API, and simplify cmd_data() This patch features the use of strbuf_detach, and prevent the programmer to mess with allocation directly. The code is as efficent as before, just more concise and more straightforward. Signed-off-by: Junio C Hamano diff --git a/fast-import.c b/fast-import.c index 2f7baf4..74ff0fd 100644 --- a/fast-import.c +++ b/fast-import.c @@ -340,7 +340,7 @@ static struct tag *last_tag; /* Input stream parsing */ static whenspec_type whenspec = WHENSPEC_RAW; -static struct strbuf command_buf; +static struct strbuf command_buf = STRBUF_INIT; static int unread_command_buf; static struct recent_command cmd_hist = {&cmd_hist, &cmd_hist, NULL}; static struct recent_command *cmd_tail = &cmd_hist; @@ -1638,17 +1638,16 @@ static void cmd_mark(void) static void *cmd_data (size_t *size) { - size_t length; - char *buffer; + struct strbuf buffer; + strbuf_init(&buffer); if (prefixcmp(command_buf.buf, "data ")) die("Expected 'data n' command, found: %s", command_buf.buf); if (!prefixcmp(command_buf.buf + 5, "<<")) { char *term = xstrdup(command_buf.buf + 5 + 2); - size_t sz = 8192, term_len = command_buf.len - 5 - 2; - length = 0; - buffer = xmalloc(sz); + size_t term_len = command_buf.len - 5 - 2; + for (;;) { read_line(&command_buf, stdin, '\n'); if (command_buf.eof) @@ -1656,21 +1655,18 @@ static void *cmd_data (size_t *size) if (term_len == command_buf.len && !strcmp(term, command_buf.buf)) break; - ALLOC_GROW(buffer, length + command_buf.len + 1, sz); - memcpy(buffer + length, - command_buf.buf, - command_buf.len); - length += command_buf.len; - buffer[length++] = '\n'; + strbuf_addbuf(&buffer, &command_buf); + strbuf_addch(&buffer, '\n'); } free(term); } else { - size_t n = 0; + size_t n = 0, length; + length = strtoul(command_buf.buf + 5, NULL, 10); - buffer = xmalloc(length); + while (n < length) { - size_t s = fread(buffer + n, 1, length - n, stdin); + size_t s = strbuf_fread(&buffer, length - n, stdin); if (!s && feof(stdin)) die("EOF in data (%lu bytes remaining)", (unsigned long)(length - n)); @@ -1679,8 +1675,8 @@ static void *cmd_data (size_t *size) } skip_optional_lf(); - *size = length; - return buffer; + *size = buffer.len; + return strbuf_detach(&buffer); } static int validate_raw_date(const char *src, char *result, int maxlen) -- cgit v0.10.2-6-g49f6 From d52bc66152834dff3fb5f32a54f6ed57730f58c6 Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Thu, 6 Sep 2007 13:20:08 +0200 Subject: mktree: Simplify write_tree() using strbuf API Signed-off-by: Pierre Habouzit Signed-off-by: Junio C Hamano diff --git a/mktree.c b/mktree.c index 86de5eb..2e84889 100644 --- a/mktree.c +++ b/mktree.c @@ -44,30 +44,23 @@ static int ent_compare(const void *a_, const void *b_) static void write_tree(unsigned char *sha1) { - char *buffer; - unsigned long size, offset; + struct strbuf buf; + size_t size; int i; qsort(entries, used, sizeof(*entries), ent_compare); for (size = i = 0; i < used; i++) size += 32 + entries[i]->len; - buffer = xmalloc(size); - offset = 0; + strbuf_init(&buf); + strbuf_grow(&buf, size); for (i = 0; i < used; i++) { struct treeent *ent = entries[i]; - - if (offset + ent->len + 100 < size) { - size = alloc_nr(offset + ent->len + 100); - buffer = xrealloc(buffer, size); - } - offset += sprintf(buffer + offset, "%o ", ent->mode); - offset += sprintf(buffer + offset, "%s", ent->name); - buffer[offset++] = 0; - hashcpy((unsigned char*)buffer + offset, ent->sha1); - offset += 20; + strbuf_addf(&buf, "%o %s%c", ent->mode, ent->name, '\0'); + strbuf_add(&buf, ent->sha1, 20); } - write_sha1_file(buffer, offset, tree_type, sha1); + + write_sha1_file(buf.buf, buf.len, tree_type, sha1); } static const char mktree_usage[] = "git-mktree [-z]"; -- cgit v0.10.2-6-g49f6 From af6eb82262e35687aa8f00d688e327cb845973fa Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Thu, 6 Sep 2007 13:20:09 +0200 Subject: Use strbuf API in apply, blame, commit-tree and diff Signed-off-by: Pierre Habouzit Signed-off-by: Junio C Hamano diff --git a/builtin-apply.c b/builtin-apply.c index 976ec77..90e328e 100644 --- a/builtin-apply.c +++ b/builtin-apply.c @@ -12,6 +12,7 @@ #include "blob.h" #include "delta.h" #include "builtin.h" +#include "strbuf.h" /* * --check turns on checking that the working tree matches the @@ -181,34 +182,21 @@ static void say_patch_name(FILE *output, const char *pre, struct patch *patch, c static void *read_patch_file(int fd, unsigned long *sizep) { - unsigned long size = 0, alloc = CHUNKSIZE; - void *buffer = xmalloc(alloc); + struct strbuf buf; - for (;;) { - ssize_t nr = alloc - size; - if (nr < 1024) { - alloc += CHUNKSIZE; - buffer = xrealloc(buffer, alloc); - nr = alloc - size; - } - nr = xread(fd, (char *) buffer + size, nr); - if (!nr) - break; - if (nr < 0) - die("git-apply: read returned %s", strerror(errno)); - size += nr; - } - *sizep = size; + strbuf_init(&buf); + if (strbuf_read(&buf, fd) < 0) + die("git-apply: read returned %s", strerror(errno)); + *sizep = buf.len; /* * Make sure that we have some slop in the buffer * so that we can do speculative "memcmp" etc, and * see to it that it is NUL-filled. */ - if (alloc < size + SLOP) - buffer = xrealloc(buffer, size + SLOP); - memset((char *) buffer + size, 0, SLOP); - return buffer; + strbuf_grow(&buf, SLOP); + memset(buf.buf + buf.len, 0, SLOP); + return strbuf_detach(&buf); } static unsigned long linelen(const char *buffer, unsigned long size) diff --git a/builtin-blame.c b/builtin-blame.c index dc88a95..1b1e6da 100644 --- a/builtin-blame.c +++ b/builtin-blame.c @@ -18,6 +18,7 @@ #include "cache-tree.h" #include "path-list.h" #include "mailmap.h" +#include "strbuf.h" static char blame_usage[] = "git-blame [-c] [-b] [-l] [--root] [-t] [-f] [-n] [-s] [-p] [-w] [-L n,m] [-S ] [-M] [-C] [-C] [--contents ] [--incremental] [commit] [--] file\n" @@ -2001,11 +2002,10 @@ static struct commit *fake_working_tree_commit(const char *path, const char *con struct commit *commit; struct origin *origin; unsigned char head_sha1[20]; - char *buf; + struct strbuf buf; const char *ident; int fd; time_t now; - unsigned long fin_size; int size, len; struct cache_entry *ce; unsigned mode; @@ -2023,9 +2023,11 @@ static struct commit *fake_working_tree_commit(const char *path, const char *con origin = make_origin(commit, path); + strbuf_init(&buf); if (!contents_from || strcmp("-", contents_from)) { struct stat st; const char *read_from; + unsigned long fin_size; if (contents_from) { if (stat(contents_from, &st) < 0) @@ -2038,19 +2040,19 @@ static struct commit *fake_working_tree_commit(const char *path, const char *con read_from = path; } fin_size = xsize_t(st.st_size); - buf = xmalloc(fin_size+1); mode = canon_mode(st.st_mode); switch (st.st_mode & S_IFMT) { case S_IFREG: fd = open(read_from, O_RDONLY); if (fd < 0) die("cannot open %s", read_from); - if (read_in_full(fd, buf, fin_size) != fin_size) + if (strbuf_read(&buf, fd) != xsize_t(st.st_size)) die("cannot read %s", read_from); break; case S_IFLNK: - if (readlink(read_from, buf, fin_size+1) != fin_size) + if (readlink(read_from, buf.buf, buf.alloc) != fin_size) die("cannot readlink %s", read_from); + buf.len = fin_size; break; default: die("unsupported file type %s", read_from); @@ -2059,26 +2061,13 @@ static struct commit *fake_working_tree_commit(const char *path, const char *con else { /* Reading from stdin */ contents_from = "standard input"; - buf = NULL; - fin_size = 0; mode = 0; - while (1) { - ssize_t cnt = 8192; - buf = xrealloc(buf, fin_size + cnt); - cnt = xread(0, buf + fin_size, cnt); - if (cnt < 0) - die("read error %s from stdin", - strerror(errno)); - if (!cnt) - break; - fin_size += cnt; - } - buf = xrealloc(buf, fin_size + 1); + if (strbuf_read(&buf, 0) < 0) + die("read error %s from stdin", strerror(errno)); } - buf[fin_size] = 0; - origin->file.ptr = buf; - origin->file.size = fin_size; - pretend_sha1_file(buf, fin_size, OBJ_BLOB, origin->blob_sha1); + origin->file.ptr = buf.buf; + origin->file.size = buf.len; + pretend_sha1_file(buf.buf, buf.len, OBJ_BLOB, origin->blob_sha1); commit->util = origin; /* diff --git a/builtin-commit-tree.c b/builtin-commit-tree.c index ccbcbe3..bc9502c 100644 --- a/builtin-commit-tree.c +++ b/builtin-commit-tree.c @@ -8,42 +8,13 @@ #include "tree.h" #include "builtin.h" #include "utf8.h" +#include "strbuf.h" #define BLOCKING (1ul << 14) /* * FIXME! Share the code with "write-tree.c" */ -static void init_buffer(char **bufp, unsigned int *sizep) -{ - *bufp = xmalloc(BLOCKING); - *sizep = 0; -} - -static void add_buffer(char **bufp, unsigned int *sizep, const char *fmt, ...) -{ - char one_line[2048]; - va_list args; - int len; - unsigned long alloc, size, newsize; - char *buf; - - va_start(args, fmt); - len = vsnprintf(one_line, sizeof(one_line), fmt, args); - va_end(args); - size = *sizep; - newsize = size + len + 1; - alloc = (size + 32767) & ~32767; - buf = *bufp; - if (newsize > alloc) { - alloc = (newsize + 32767) & ~32767; - buf = xrealloc(buf, alloc); - *bufp = buf; - } - *sizep = newsize - 1; - memcpy(buf + size, one_line, len); -} - static void check_valid(unsigned char *sha1, enum object_type expect) { enum object_type type = sha1_object_info(sha1, NULL); @@ -87,9 +58,7 @@ int cmd_commit_tree(int argc, const char **argv, const char *prefix) int parents = 0; unsigned char tree_sha1[20]; unsigned char commit_sha1[20]; - char comment[1000]; - char *buffer; - unsigned int size; + struct strbuf buffer; int encoding_is_utf8; git_config(git_default_config); @@ -118,8 +87,9 @@ int cmd_commit_tree(int argc, const char **argv, const char *prefix) /* Not having i18n.commitencoding is the same as having utf-8 */ encoding_is_utf8 = is_encoding_utf8(git_commit_encoding); - init_buffer(&buffer, &size); - add_buffer(&buffer, &size, "tree %s\n", sha1_to_hex(tree_sha1)); + strbuf_init(&buffer); + strbuf_grow(&buffer, 8192); /* should avoid reallocs for the headers */ + strbuf_addf(&buffer, "tree %s\n", sha1_to_hex(tree_sha1)); /* * NOTE! This ordering means that the same exact tree merged with a @@ -127,26 +97,24 @@ int cmd_commit_tree(int argc, const char **argv, const char *prefix) * if everything else stays the same. */ for (i = 0; i < parents; i++) - add_buffer(&buffer, &size, "parent %s\n", sha1_to_hex(parent_sha1[i])); + strbuf_addf(&buffer, "parent %s\n", sha1_to_hex(parent_sha1[i])); /* Person/date information */ - add_buffer(&buffer, &size, "author %s\n", git_author_info(1)); - add_buffer(&buffer, &size, "committer %s\n", git_committer_info(1)); + strbuf_addf(&buffer, "author %s\n", git_author_info(1)); + strbuf_addf(&buffer, "committer %s\n", git_committer_info(1)); if (!encoding_is_utf8) - add_buffer(&buffer, &size, - "encoding %s\n", git_commit_encoding); - add_buffer(&buffer, &size, "\n"); + strbuf_addf(&buffer, "encoding %s\n", git_commit_encoding); + strbuf_addch(&buffer, '\n'); /* And add the comment */ - while (fgets(comment, sizeof(comment), stdin) != NULL) - add_buffer(&buffer, &size, "%s", comment); + if (strbuf_read(&buffer, 0) < 0) + die("git-commit-tree: read returned %s", strerror(errno)); /* And check the encoding */ - buffer[size] = '\0'; - if (encoding_is_utf8 && !is_utf8(buffer)) + if (encoding_is_utf8 && !is_utf8(buffer.buf)) fprintf(stderr, commit_utf8_warn); - if (!write_sha1_file(buffer, size, commit_type, commit_sha1)) { + if (!write_sha1_file(buffer.buf, buffer.len, commit_type, commit_sha1)) { printf("%s\n", sha1_to_hex(commit_sha1)); return 0; } diff --git a/diff.c b/diff.c index 0d30d05..c054b23 100644 --- a/diff.c +++ b/diff.c @@ -9,6 +9,7 @@ #include "xdiff-interface.h" #include "color.h" #include "attr.h" +#include "strbuf.h" #ifdef NO_FAST_WORKING_DIRECTORY #define FAST_WORKING_DIRECTORY 0 @@ -1545,26 +1546,16 @@ static int reuse_worktree_file(const char *name, const unsigned char *sha1, int static int populate_from_stdin(struct diff_filespec *s) { -#define INCREMENT 1024 - char *buf; - unsigned long size; - ssize_t got; - - size = 0; - buf = NULL; - while (1) { - buf = xrealloc(buf, size + INCREMENT); - got = xread(0, buf + size, INCREMENT); - if (!got) - break; /* EOF */ - if (got < 0) - return error("error while reading from stdin %s", + struct strbuf buf; + + strbuf_init(&buf); + if (strbuf_read(&buf, 0) < 0) + return error("error while reading from stdin %s", strerror(errno)); - size += got; - } + s->should_munmap = 0; - s->data = buf; - s->size = size; + s->size = buf.len; + s->data = strbuf_detach(&buf); s->should_free = 1; return 0; } -- cgit v0.10.2-6-g49f6 From 19b358e8daafdfe5a5d25ff7972e041493b05156 Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Thu, 6 Sep 2007 13:20:10 +0200 Subject: Use strbuf API in buitin-rerere.c Signed-off-by: Pierre Habouzit Signed-off-by: Junio C Hamano diff --git a/builtin-rerere.c b/builtin-rerere.c index 29d057c..98d7702 100644 --- a/builtin-rerere.c +++ b/builtin-rerere.c @@ -1,6 +1,7 @@ #include "builtin.h" #include "cache.h" #include "path-list.h" +#include "strbuf.h" #include "xdiff/xdiff.h" #include "xdiff-interface.h" @@ -66,41 +67,20 @@ static int write_rr(struct path_list *rr, int out_fd) return commit_lock_file(&write_lock); } -struct buffer { - char *ptr; - int nr, alloc; -}; - -static void append_line(struct buffer *buffer, const char *line) -{ - int len = strlen(line); - - if (buffer->nr + len > buffer->alloc) { - buffer->alloc = alloc_nr(buffer->nr + len); - buffer->ptr = xrealloc(buffer->ptr, buffer->alloc); - } - memcpy(buffer->ptr + buffer->nr, line, len); - buffer->nr += len; -} - -static void clear_buffer(struct buffer *buffer) -{ - free(buffer->ptr); - buffer->ptr = NULL; - buffer->nr = buffer->alloc = 0; -} - static int handle_file(const char *path, unsigned char *sha1, const char *output) { SHA_CTX ctx; char buf[1024]; int hunk = 0, hunk_no = 0; - struct buffer minus = { NULL, 0, 0 }, plus = { NULL, 0, 0 }; - struct buffer *one = &minus, *two = + + struct strbuf minus, plus; + struct strbuf *one = &minus, *two = + FILE *f = fopen(path, "r"); FILE *out; + strbuf_init(&minus); + strbuf_init(&plus); + if (!f) return error("Could not open %s", path); @@ -122,36 +102,36 @@ static int handle_file(const char *path, else if (!prefixcmp(buf, "=======")) hunk = 2; else if (!prefixcmp(buf, ">>>>>>> ")) { - int one_is_longer = (one->nr > two->nr); - int common_len = one_is_longer ? two->nr : one->nr; - int cmp = memcmp(one->ptr, two->ptr, common_len); + int one_is_longer = (one->len > two->len); + int common_len = one_is_longer ? two->len : one->len; + int cmp = memcmp(one->buf, two->buf, common_len); hunk_no++; hunk = 0; if ((cmp > 0) || ((cmp == 0) && one_is_longer)) { - struct buffer *swap = one; + struct strbuf *swap = one; one = two; two = swap; } if (out) { fputs("<<<<<<<\n", out); - fwrite(one->ptr, one->nr, 1, out); + fwrite(one->buf, one->len, 1, out); fputs("=======\n", out); - fwrite(two->ptr, two->nr, 1, out); + fwrite(two->buf, two->len, 1, out); fputs(">>>>>>>\n", out); } if (sha1) { - SHA1_Update(&ctx, one->ptr, one->nr); + SHA1_Update(&ctx, one->buf, one->len); SHA1_Update(&ctx, "\0", 1); - SHA1_Update(&ctx, two->ptr, two->nr); + SHA1_Update(&ctx, two->buf, two->len); SHA1_Update(&ctx, "\0", 1); } - clear_buffer(one); - clear_buffer(two); + strbuf_release(one); + strbuf_release(two); } else if (hunk == 1) - append_line(one, buf); + strbuf_addstr(one, buf); else if (hunk == 2) - append_line(two, buf); + strbuf_addstr(two, buf); else if (out) fputs(buf, out); } -- cgit v0.10.2-6-g49f6 From 5242bcbb638f031818e9ebd4467c8e55d5a06bfb Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Thu, 6 Sep 2007 13:20:11 +0200 Subject: Use strbuf API in cache-tree.c Should even be marginally faster. Signed-off-by: Pierre Habouzit Signed-off-by: Junio C Hamano diff --git a/cache-tree.c b/cache-tree.c index 077f034..76af6f5 100644 --- a/cache-tree.c +++ b/cache-tree.c @@ -1,4 +1,5 @@ #include "cache.h" +#include "strbuf.h" #include "tree.h" #include "cache-tree.h" @@ -235,8 +236,7 @@ static int update_one(struct cache_tree *it, int missing_ok, int dryrun) { - unsigned long size, offset; - char *buffer; + struct strbuf buffer; int i; if (0 <= it->entry_count && has_sha1_file(it->sha1)) @@ -293,9 +293,8 @@ static int update_one(struct cache_tree *it, /* * Then write out the tree object for this level. */ - size = 8192; - buffer = xmalloc(size); - offset = 0; + strbuf_init(&buffer); + strbuf_grow(&buffer, 8192); for (i = 0; i < entries; i++) { struct cache_entry *ce = cache[i]; @@ -332,15 +331,9 @@ static int update_one(struct cache_tree *it, if (!ce->ce_mode) continue; /* entry being removed */ - if (size < offset + entlen + 100) { - size = alloc_nr(offset + entlen + 100); - buffer = xrealloc(buffer, size); - } - offset += sprintf(buffer + offset, - "%o %.*s", mode, entlen, path + baselen); - buffer[offset++] = 0; - hashcpy((unsigned char*)buffer + offset, sha1); - offset += 20; + strbuf_grow(&buffer, entlen + 100); + strbuf_addf(&buffer, "%o %.*s%c", mode, entlen, path + baselen, '\0'); + strbuf_add(&buffer, sha1, 20); #if DEBUG fprintf(stderr, "cache-tree update-one %o %.*s\n", @@ -349,10 +342,10 @@ static int update_one(struct cache_tree *it, } if (dryrun) - hash_sha1_file(buffer, offset, tree_type, it->sha1); + hash_sha1_file(buffer.buf, buffer.len, tree_type, it->sha1); else - write_sha1_file(buffer, offset, tree_type, it->sha1); - free(buffer); + write_sha1_file(buffer.buf, buffer.len, tree_type, it->sha1); + strbuf_release(&buffer); it->entry_count = i; #if DEBUG fprintf(stderr, "cache-tree update-one (%d ent, %d subtree) %s\n", @@ -378,12 +371,10 @@ int cache_tree_update(struct cache_tree *it, return 0; } -static void *write_one(struct cache_tree *it, +static void write_one(struct cache_tree *it, char *path, int pathlen, - char *buffer, - unsigned long *size, - unsigned long *offset) + struct strbuf *buffer) { int i; @@ -393,13 +384,9 @@ static void *write_one(struct cache_tree *it, * tree-sha1 (missing if invalid) * subtree_nr "cache-tree" entries for subtrees. */ - if (*size < *offset + pathlen + 100) { - *size = alloc_nr(*offset + pathlen + 100); - buffer = xrealloc(buffer, *size); - } - *offset += sprintf(buffer + *offset, "%.*s%c%d %d\n", - pathlen, path, 0, - it->entry_count, it->subtree_nr); + strbuf_grow(buffer, pathlen + 100); + strbuf_add(buffer, path, pathlen); + strbuf_addf(buffer, "%c%d %d\n", 0, it->entry_count, it->subtree_nr); #if DEBUG if (0 <= it->entry_count) @@ -412,8 +399,7 @@ static void *write_one(struct cache_tree *it, #endif if (0 <= it->entry_count) { - hashcpy((unsigned char*)buffer + *offset, it->sha1); - *offset += 20; + strbuf_add(buffer, it->sha1, 20); } for (i = 0; i < it->subtree_nr; i++) { struct cache_tree_sub *down = it->down[i]; @@ -423,21 +409,20 @@ static void *write_one(struct cache_tree *it, prev->name, prev->namelen) <= 0) die("fatal - unsorted cache subtree"); } - buffer = write_one(down->cache_tree, down->name, down->namelen, - buffer, size, offset); + write_one(down->cache_tree, down->name, down->namelen, buffer); } - return buffer; } void *cache_tree_write(struct cache_tree *root, unsigned long *size_p) { char path[PATH_MAX]; - unsigned long size = 8192; - char *buffer = xmalloc(size); + struct strbuf buffer; - *size_p = 0; path[0] = 0; - return write_one(root, path, 0, buffer, &size, size_p); + strbuf_init(&buffer); + write_one(root, path, 0, &buffer); + *size_p = buffer.len; + return strbuf_detach(&buffer); } static struct cache_tree *read_one(const char **buffer, unsigned long *size_p) -- cgit v0.10.2-6-g49f6 From f1696ee398e92bcea3cdc7b3da85d8e0f77f6c50 Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Mon, 10 Sep 2007 12:35:04 +0200 Subject: Strbuf API extensions and fixes. * Add strbuf_rtrim to remove trailing spaces. * Add strbuf_insert to insert data at a given position. * Off-by one fix in strbuf_addf: strbuf_avail() does not counts the final \0 so the overflow test for snprintf is the strict comparison. This is not critical as the growth mechanism chosen will always allocate _more_ memory than asked, so the second test will not fail. It's some kind of miracle though. * Add size extension hints for strbuf_init and strbuf_read. If 0, default applies, else: + initial buffer has the given size for strbuf_init. + first growth checks it has at least this size rather than the default 8192. Signed-off-by: Pierre Habouzit Signed-off-by: Junio C Hamano diff --git a/archive-tar.c b/archive-tar.c index 0612bb6..cc94cf3 100644 --- a/archive-tar.c +++ b/archive-tar.c @@ -132,7 +132,7 @@ static void write_entry(const unsigned char *sha1, struct strbuf *path, struct strbuf ext_header; memset(&header, 0, sizeof(header)); - strbuf_init(&ext_header); + strbuf_init(&ext_header, 0); if (!sha1) { *header.typeflag = TYPEFLAG_GLOBAL_HEADER; @@ -214,7 +214,7 @@ static void write_global_extended_header(const unsigned char *sha1) { struct strbuf ext_header; - strbuf_init(&ext_header); + strbuf_init(&ext_header, 0); strbuf_append_ext_header(&ext_header, "comment", sha1_to_hex(sha1), 40); write_entry(NULL, NULL, 0, ext_header.buf, ext_header.len); strbuf_release(&ext_header); diff --git a/builtin-apply.c b/builtin-apply.c index 90e328e..988e85f 100644 --- a/builtin-apply.c +++ b/builtin-apply.c @@ -184,8 +184,8 @@ static void *read_patch_file(int fd, unsigned long *sizep) { struct strbuf buf; - strbuf_init(&buf); - if (strbuf_read(&buf, fd) < 0) + strbuf_init(&buf, 0); + if (strbuf_read(&buf, fd, 0) < 0) die("git-apply: read returned %s", strerror(errno)); *sizep = buf.len; diff --git a/builtin-blame.c b/builtin-blame.c index 1b1e6da..b004f06 100644 --- a/builtin-blame.c +++ b/builtin-blame.c @@ -2023,7 +2023,7 @@ static struct commit *fake_working_tree_commit(const char *path, const char *con origin = make_origin(commit, path); - strbuf_init(&buf); + strbuf_init(&buf, 0); if (!contents_from || strcmp("-", contents_from)) { struct stat st; const char *read_from; @@ -2046,7 +2046,7 @@ static struct commit *fake_working_tree_commit(const char *path, const char *con fd = open(read_from, O_RDONLY); if (fd < 0) die("cannot open %s", read_from); - if (strbuf_read(&buf, fd) != xsize_t(st.st_size)) + if (strbuf_read(&buf, fd, 0) != xsize_t(st.st_size)) die("cannot read %s", read_from); break; case S_IFLNK: @@ -2062,7 +2062,7 @@ static struct commit *fake_working_tree_commit(const char *path, const char *con /* Reading from stdin */ contents_from = "standard input"; mode = 0; - if (strbuf_read(&buf, 0) < 0) + if (strbuf_read(&buf, 0, 0) < 0) die("read error %s from stdin", strerror(errno)); } origin->file.ptr = buf.buf; diff --git a/builtin-checkout-index.c b/builtin-checkout-index.c index 75377b9..153ba7d 100644 --- a/builtin-checkout-index.c +++ b/builtin-checkout-index.c @@ -274,7 +274,7 @@ int cmd_checkout_index(int argc, const char **argv, const char *prefix) struct strbuf buf; if (all) die("git-checkout-index: don't mix '--all' and '--stdin'"); - strbuf_init(&buf); + strbuf_init(&buf, 0); while (1) { char *path_name; const char *p; diff --git a/builtin-commit-tree.c b/builtin-commit-tree.c index bc9502c..325334f 100644 --- a/builtin-commit-tree.c +++ b/builtin-commit-tree.c @@ -87,8 +87,7 @@ int cmd_commit_tree(int argc, const char **argv, const char *prefix) /* Not having i18n.commitencoding is the same as having utf-8 */ encoding_is_utf8 = is_encoding_utf8(git_commit_encoding); - strbuf_init(&buffer); - strbuf_grow(&buffer, 8192); /* should avoid reallocs for the headers */ + strbuf_init(&buffer, 8192); /* should avoid reallocs for the headers */ strbuf_addf(&buffer, "tree %s\n", sha1_to_hex(tree_sha1)); /* @@ -107,7 +106,7 @@ int cmd_commit_tree(int argc, const char **argv, const char *prefix) strbuf_addch(&buffer, '\n'); /* And add the comment */ - if (strbuf_read(&buffer, 0) < 0) + if (strbuf_read(&buffer, 0, 0) < 0) die("git-commit-tree: read returned %s", strerror(errno)); /* And check the encoding */ diff --git a/builtin-rerere.c b/builtin-rerere.c index 98d7702..826d346 100644 --- a/builtin-rerere.c +++ b/builtin-rerere.c @@ -78,8 +78,8 @@ static int handle_file(const char *path, FILE *f = fopen(path, "r"); FILE *out; - strbuf_init(&minus); - strbuf_init(&plus); + strbuf_init(&minus, 0); + strbuf_init(&plus, 0); if (!f) return error("Could not open %s", path); diff --git a/builtin-update-index.c b/builtin-update-index.c index a7a4574..9240a28 100644 --- a/builtin-update-index.c +++ b/builtin-update-index.c @@ -303,7 +303,7 @@ static void update_one(const char *path, const char *prefix, int prefix_length) static void read_index_info(int line_termination) { struct strbuf buf; - strbuf_init(&buf); + strbuf_init(&buf, 0); while (1) { char *ptr, *tab; char *path_name; @@ -716,7 +716,7 @@ int cmd_update_index(int argc, const char **argv, const char *prefix) } if (read_from_stdin) { struct strbuf buf; - strbuf_init(&buf); + strbuf_init(&buf, 0); while (1) { char *path_name; const char *p; diff --git a/cache-tree.c b/cache-tree.c index 76af6f5..8f53c99 100644 --- a/cache-tree.c +++ b/cache-tree.c @@ -293,8 +293,7 @@ static int update_one(struct cache_tree *it, /* * Then write out the tree object for this level. */ - strbuf_init(&buffer); - strbuf_grow(&buffer, 8192); + strbuf_init(&buffer, 8192); for (i = 0; i < entries; i++) { struct cache_entry *ce = cache[i]; @@ -419,7 +418,7 @@ void *cache_tree_write(struct cache_tree *root, unsigned long *size_p) struct strbuf buffer; path[0] = 0; - strbuf_init(&buffer); + strbuf_init(&buffer, 0); write_one(root, path, 0, &buffer); *size_p = buffer.len; return strbuf_detach(&buffer); diff --git a/diff.c b/diff.c index 26d7bb9..7290309 100644 --- a/diff.c +++ b/diff.c @@ -1548,8 +1548,8 @@ static int populate_from_stdin(struct diff_filespec *s) { struct strbuf buf; - strbuf_init(&buf); - if (strbuf_read(&buf, 0) < 0) + strbuf_init(&buf, 0); + if (strbuf_read(&buf, 0, 0) < 0) return error("error while reading from stdin %s", strerror(errno)); diff --git a/fast-import.c b/fast-import.c index 74ff0fd..2c0bfb9 100644 --- a/fast-import.c +++ b/fast-import.c @@ -1640,7 +1640,7 @@ static void *cmd_data (size_t *size) { struct strbuf buffer; - strbuf_init(&buffer); + strbuf_init(&buffer, 0); if (prefixcmp(command_buf.buf, "data ")) die("Expected 'data n' command, found: %s", command_buf.buf); @@ -2318,7 +2318,7 @@ int main(int argc, const char **argv) git_config(git_default_config); alloc_objects(object_entry_alloc); - strbuf_init(&command_buf); + strbuf_init(&command_buf, 0); atom_table = xcalloc(atom_table_sz, sizeof(struct atom_str*)); branch_table = xcalloc(branch_table_sz, sizeof(struct branch*)); avail_tree_table = xcalloc(avail_tree_table_sz, sizeof(struct avail_tree_content*)); diff --git a/fetch.c b/fetch.c index 811be87..dd6ed9e 100644 --- a/fetch.c +++ b/fetch.c @@ -218,7 +218,7 @@ int pull_targets_stdin(char ***target, const char ***write_ref) int targets = 0, targets_alloc = 0; struct strbuf buf; *target = NULL; *write_ref = NULL; - strbuf_init(&buf); + strbuf_init(&buf, 0); while (1) { char *rf_one = NULL; char *tg_one; diff --git a/mktree.c b/mktree.c index 2e84889..3891cd9 100644 --- a/mktree.c +++ b/mktree.c @@ -51,9 +51,8 @@ static void write_tree(unsigned char *sha1) qsort(entries, used, sizeof(*entries), ent_compare); for (size = i = 0; i < used; i++) size += 32 + entries[i]->len; - strbuf_init(&buf); - strbuf_grow(&buf, size); + strbuf_init(&buf, size); for (i = 0; i < used; i++) { struct treeent *ent = entries[i]; strbuf_addf(&buf, "%o %s%c", ent->mode, ent->name, '\0'); @@ -83,7 +82,7 @@ int main(int ac, char **av) av++; } - strbuf_init(&sb); + strbuf_init(&sb, 0); while (1) { char *ptr, *ntr; unsigned mode; diff --git a/strbuf.c b/strbuf.c index 7136de1..d919047 100644 --- a/strbuf.c +++ b/strbuf.c @@ -1,8 +1,10 @@ #include "cache.h" #include "strbuf.h" -void strbuf_init(struct strbuf *sb) { +void strbuf_init(struct strbuf *sb, size_t hint) { memset(sb, 0, sizeof(*sb)); + if (hint) + strbuf_grow(sb, hint); } void strbuf_release(struct strbuf *sb) { @@ -18,7 +20,7 @@ void strbuf_reset(struct strbuf *sb) { char *strbuf_detach(struct strbuf *sb) { char *res = sb->buf; - strbuf_init(sb); + strbuf_init(sb, 0); return res; } @@ -28,6 +30,24 @@ void strbuf_grow(struct strbuf *sb, size_t extra) { ALLOC_GROW(sb->buf, sb->len + extra + 1, sb->alloc); } +void strbuf_rtrim(struct strbuf *sb) +{ + while (sb->len > 0 && isspace((unsigned char)sb->buf[sb->len - 1])) + sb->len--; + sb->buf[sb->len] = '\0'; +} + +void strbuf_insert(struct strbuf *sb, size_t pos, const void *data, size_t len) { + strbuf_grow(sb, len); + if (pos >= sb->len) { + pos = sb->len; + } else { + memmove(sb->buf + pos + len, sb->buf + pos, sb->len - pos); + } + memcpy(sb->buf + pos, data, len); + strbuf_setlen(sb, sb->len + len); +} + void strbuf_add(struct strbuf *sb, const void *data, size_t len) { strbuf_grow(sb, len); memcpy(sb->buf + sb->len, data, len); @@ -44,12 +64,12 @@ void strbuf_addf(struct strbuf *sb, const char *fmt, ...) { if (len < 0) { len = 0; } - if (len >= strbuf_avail(sb)) { + if (len > strbuf_avail(sb)) { strbuf_grow(sb, len); va_start(ap, fmt); len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap); va_end(ap); - if (len >= strbuf_avail(sb)) { + if (len > strbuf_avail(sb)) { die("this should not happen, your snprintf is broken"); } } @@ -67,14 +87,14 @@ size_t strbuf_fread(struct strbuf *sb, size_t size, FILE *f) { return res; } -ssize_t strbuf_read(struct strbuf *sb, int fd) +ssize_t strbuf_read(struct strbuf *sb, int fd, size_t hint) { size_t oldlen = sb->len; + strbuf_grow(sb, hint ? hint : 8192); for (;;) { ssize_t cnt; - strbuf_grow(sb, 8192); cnt = xread(fd, sb->buf + sb->len, sb->alloc - sb->len - 1); if (cnt < 0) { strbuf_setlen(sb, oldlen); @@ -83,6 +103,7 @@ ssize_t strbuf_read(struct strbuf *sb, int fd) if (!cnt) break; sb->len += cnt; + strbuf_grow(sb, 8192); } sb->buf[sb->len] = '\0'; diff --git a/strbuf.h b/strbuf.h index b40dc99..21fc111 100644 --- a/strbuf.h +++ b/strbuf.h @@ -51,7 +51,7 @@ struct strbuf { #define STRBUF_INIT { 0, 0, 0, NULL } /*----- strbuf life cycle -----*/ -extern void strbuf_init(struct strbuf *); +extern void strbuf_init(struct strbuf *, size_t); extern void strbuf_release(struct strbuf *); extern void strbuf_reset(struct strbuf *); extern char *strbuf_detach(struct strbuf *); @@ -68,6 +68,9 @@ static inline void strbuf_setlen(struct strbuf *sb, size_t len) { extern void strbuf_grow(struct strbuf *, size_t); +/*----- content related -----*/ +extern void strbuf_rtrim(struct strbuf *); + /*----- add data in your buffer -----*/ static inline void strbuf_addch(struct strbuf *sb, int c) { strbuf_grow(sb, 1); @@ -75,6 +78,9 @@ static inline void strbuf_addch(struct strbuf *sb, int c) { sb->buf[sb->len] = '\0'; } +/* inserts after pos, or appends if pos >= sb->len */ +extern void strbuf_insert(struct strbuf *, size_t pos, const void *, size_t); + extern void strbuf_add(struct strbuf *, const void *, size_t); static inline void strbuf_addstr(struct strbuf *sb, const char *s) { strbuf_add(sb, s, strlen(s)); @@ -88,7 +94,7 @@ extern void strbuf_addf(struct strbuf *sb, const char *fmt, ...); extern size_t strbuf_fread(struct strbuf *, size_t, FILE *); /* XXX: if read fails, any partial read is undone */ -extern ssize_t strbuf_read(struct strbuf *, int fd); +extern ssize_t strbuf_read(struct strbuf *, int fd, size_t hint); extern void read_line(struct strbuf *, FILE *, int); -- cgit v0.10.2-6-g49f6 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 diff --git a/commit.c b/commit.c index 99f65ce..25781cc 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)); diff --git a/interpolate.c b/interpolate.c index 0082677..3de5832 100644 --- a/interpolate.c +++ b/interpolate.c @@ -44,9 +44,8 @@ void interp_clear_table(struct interp *table, int ninterps) * { "%%", "%"}, * } * - * Returns 0 on a successful substitution pass that fits in result, - * Returns a number of bytes needed to hold the full substituted - * string otherwise. + * Returns the length of the substituted string (not including the final \0). + * Like with snprintf, if the result is >= reslen, then it overflowed. */ unsigned long interpolate(char *result, unsigned long reslen, @@ -61,8 +60,6 @@ unsigned long interpolate(char *result, unsigned long reslen, int i; char c; - memset(result, 0, reslen); - while ((c = *src)) { if (c == '%') { /* Try to match an interpolation string. */ @@ -78,9 +75,9 @@ unsigned long interpolate(char *result, unsigned long reslen, value = interps[i].value; valuelen = strlen(value); - if (newlen + valuelen + 1 < reslen) { + if (newlen + valuelen < reslen) { /* Substitute. */ - strncpy(dest, value, valuelen); + memcpy(dest, value, valuelen); dest += valuelen; } newlen += valuelen; @@ -95,8 +92,9 @@ unsigned long interpolate(char *result, unsigned long reslen, newlen++; } - if (newlen + 1 < reslen) - return 0; - else - return newlen + 2; + /* XXX: the previous loop always keep room for the ending NUL, + we just need to check if there was room for a NUL in the first place */ + if (reslen > 0) + *dest = '\0'; + return newlen; } -- cgit v0.10.2-6-g49f6 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 diff --git a/builtin-archive.c b/builtin-archive.c index a90c65c..b50d5ad 100644 --- a/builtin-archive.c +++ b/builtin-archive.c @@ -84,14 +84,16 @@ static int run_remote_archiver(const char *remote, int argc, static void *format_subst(const struct commit *commit, const char *format, unsigned long *sizep) { - unsigned long len = *sizep, result_len = 0; + unsigned long len = *sizep; const char *a = format; - char *result = NULL; + struct strbuf result; + struct strbuf fmt; + + strbuf_init(&result, 0); + strbuf_init(&fmt, 0); for (;;) { const char *b, *c; - char *fmt, *formatted = NULL; - unsigned long a_len, fmt_len, formatted_len, allocated = 0; b = memmem(a, len, "$Format:", 8); if (!b || a + len < b + 9) @@ -100,32 +102,23 @@ static void *format_subst(const struct commit *commit, const char *format, if (!c) break; - a_len = b - a; - fmt_len = c - b - 8; - fmt = xmalloc(fmt_len + 1); - memcpy(fmt, b + 8, fmt_len); - fmt[fmt_len] = '\0'; - - formatted_len = format_commit_message(commit, fmt, &formatted, - &allocated); - free(fmt); - result = xrealloc(result, result_len + a_len + formatted_len); - memcpy(result + result_len, a, a_len); - memcpy(result + result_len + a_len, formatted, formatted_len); - result_len += a_len + formatted_len; + strbuf_reset(&fmt); + strbuf_add(&fmt, b + 8, c - b - 8); + + strbuf_add(&result, a, b - a); + format_commit_message(commit, fmt.buf, &result); len -= c + 1 - a; a = c + 1; } - if (result && len) { - result = xrealloc(result, result_len + len); - memcpy(result + result_len, a, len); - result_len += len; + if (result.len && len) { + strbuf_add(&result, a, len); } - *sizep = result_len; + *sizep = result.len; - return result; + strbuf_release(&fmt); + return strbuf_detach(&result); } static void *convert_to_archive(const char *path, diff --git a/builtin-branch.c b/builtin-branch.c index 5f5c182..3da8b55 100644 --- a/builtin-branch.c +++ b/builtin-branch.c @@ -268,23 +268,22 @@ static void print_ref_item(struct ref_item *item, int maxwidth, int verbose, } if (verbose) { - char *subject = NULL; - unsigned long subject_len = 0; + struct strbuf subject; const char *sub = " **** invalid ref ****"; + strbuf_init(&subject, 0); + commit = lookup_commit(item->sha1); if (commit && !parse_commit(commit)) { - pretty_print_commit(CMIT_FMT_ONELINE, commit, ~0, - &subject, &subject_len, 0, - NULL, NULL, 0); - sub = subject; + pretty_print_commit(CMIT_FMT_ONELINE, commit, + &subject, 0, NULL, NULL, 0); + sub = subject.buf; } 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), sub); - if (subject) - free(subject); + strbuf_release(&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 fa81c25..e1d3e7d 100644 --- a/builtin-log.c +++ b/builtin-log.c @@ -763,13 +763,13 @@ int cmd_cherry(int argc, const char **argv, const char *prefix) sign = '-'; if (verbose) { - char *buf = NULL; - unsigned long buflen = 0; - pretty_print_commit(CMIT_FMT_ONELINE, commit, ~0, - &buf, &buflen, 0, NULL, NULL, 0); + struct strbuf buf; + strbuf_init(&buf, 0); + pretty_print_commit(CMIT_FMT_ONELINE, commit, + &buf, 0, NULL, NULL, 0); printf("%c %s %s\n", sign, - sha1_to_hex(commit->object.sha1), buf); - free(buf); + sha1_to_hex(commit->object.sha1), buf.buf); + strbuf_release(&buf); } else { printf("%c %s\n", sign, diff --git a/builtin-rev-list.c b/builtin-rev-list.c index ac551d5..4fd4b6b 100644 --- a/builtin-rev-list.c +++ b/builtin-rev-list.c @@ -80,13 +80,12 @@ static void show_commit(struct commit *commit) putchar('\n'); if (revs.verbose_header) { - char *buf = NULL; - unsigned long buflen = 0; - pretty_print_commit(revs.commit_format, commit, ~0, - &buf, &buflen, - revs.abbrev, NULL, NULL, revs.date_mode); - printf("%s%c", buf, hdr_termination); - free(buf); + struct strbuf buf; + strbuf_init(&buf, 0); + pretty_print_commit(revs.commit_format, commit, + &buf, revs.abbrev, NULL, NULL, revs.date_mode); + printf("%s%c", buf.buf, hdr_termination); + strbuf_release(&buf); } maybe_flush_or_die(stdout, "stdout"); if (commit->parents) { diff --git a/builtin-show-branch.c b/builtin-show-branch.c index 4fa87f6..07a0c23 100644 --- a/builtin-show-branch.c +++ b/builtin-show-branch.c @@ -259,16 +259,15 @@ static void join_revs(struct commit_list **list_p, static void show_one_commit(struct commit *commit, int no_name) { - char *pretty = NULL; + struct strbuf pretty; const char *pretty_str = "(unavailable)"; - unsigned long pretty_len = 0; struct commit_name *name = commit->util; + strbuf_init(&pretty, 0); if (commit->object.parsed) { - pretty_print_commit(CMIT_FMT_ONELINE, commit, ~0, - &pretty, &pretty_len, - 0, NULL, NULL, 0); - pretty_str = pretty; + pretty_print_commit(CMIT_FMT_ONELINE, commit, + &pretty, 0, NULL, NULL, 0); + pretty_str = pretty.buf; } if (!prefixcmp(pretty_str, "[PATCH] ")) pretty_str += 8; @@ -289,7 +288,7 @@ static void show_one_commit(struct commit *commit, int no_name) find_unique_abbrev(commit->object.sha1, 7)); } puts(pretty_str); - free(pretty); + strbuf_release(&pretty); } static char *ref_name[MAX_REVS + 1]; diff --git a/commit.c b/commit.c index 25781cc..6602e2c 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; diff --git a/commit.h b/commit.h index a8d7661..b779de8 100644 --- a/commit.h +++ b/commit.h @@ -3,6 +3,7 @@ #include "object.h" #include "tree.h" +#include "strbuf.h" #include "decorate.h" struct commit_list { @@ -61,8 +62,12 @@ enum cmit_fmt { }; extern enum cmit_fmt get_commit_format(const char *arg); -extern long format_commit_message(const struct commit *commit, const void *template, char **buf_p, unsigned long *space_p); -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); +extern void format_commit_message(const struct commit *commit, + const void *format, struct strbuf *sb); +extern void pretty_print_commit(enum cmit_fmt fmt, const struct commit*, + struct strbuf *, + int abbrev, const char *subject, + const char *after_subject, enum date_mode); /** Removes the first commit from a list sorted by date, and adds all * of its parents. diff --git a/log-tree.c b/log-tree.c index a642371..3e5e6ac 100644 --- a/log-tree.c +++ b/log-tree.c @@ -79,25 +79,14 @@ static int detect_any_signoff(char *letter, int size) return seen_head && seen_name; } -static unsigned long append_signoff(char **buf_p, unsigned long *buf_sz_p, - unsigned long at, const char *signoff) +static void append_signoff(struct strbuf *sb, const char *signoff) { static const char signed_off_by[] = "Signed-off-by: "; size_t signoff_len = strlen(signoff); int has_signoff = 0; 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; + + cp = sb->buf; /* First see if we already have the sign-off by the signer */ while ((cp = strstr(cp, signed_off_by))) { @@ -105,29 +94,25 @@ static unsigned long append_signoff(char **buf_p, unsigned long *buf_sz_p, has_signoff = 1; cp += strlen(signed_off_by); - if (cp + signoff_len >= buf + at) + if (cp + signoff_len >= sb->buf + sb->len) break; if (strncmp(cp, signoff, signoff_len)) continue; if (!isspace(cp[signoff_len])) continue; /* we already have him */ - return at; + return; } if (!has_signoff) - has_signoff = detect_any_signoff(buf, at); + has_signoff = detect_any_signoff(sb->buf, sb->len); if (!has_signoff) - buf[at++] = '\n'; - - strcpy(buf + at, signed_off_by); - at += strlen(signed_off_by); - strcpy(buf + at, signoff); - at += signoff_len; - buf[at++] = '\n'; - buf[at] = 0; - return at; + strbuf_addch(sb, '\n'); + + strbuf_addstr(sb, signed_off_by); + strbuf_add(sb, signoff, signoff_len); + strbuf_addch(sb, '\n'); } static unsigned int digits_in_number(unsigned int number) @@ -142,14 +127,12 @@ static unsigned int digits_in_number(unsigned int number) void show_log(struct rev_info *opt, const char *sep) { - char *msgbuf = NULL; - unsigned long msgbuf_len = 0; + struct strbuf msgbuf; struct log_info *log = opt->loginfo; struct commit *commit = log->commit, *parent = log->parent; int abbrev = opt->diffopt.abbrev; int abbrev_commit = opt->abbrev_commit ? opt->abbrev : 40; const char *extra; - int len; const char *subject = NULL, *extra_headers = opt->extra_headers; opt->loginfo = NULL; @@ -288,18 +271,17 @@ 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, - &msgbuf, &msgbuf_len, abbrev, subject, - extra_headers, opt->date_mode); + strbuf_init(&msgbuf, 0); + pretty_print_commit(opt->commit_format, commit, &msgbuf, + abbrev, subject, extra_headers, opt->date_mode); if (opt->add_signoff) - len = append_signoff(&msgbuf, &msgbuf_len, len, - opt->add_signoff); + append_signoff(&msgbuf, opt->add_signoff); if (opt->show_log_size) - printf("log size %i\n", len); + printf("log size %i\n", (int)msgbuf.len); - printf("%s%s%s", msgbuf, extra, sep); - free(msgbuf); + printf("%s%s%s", msgbuf.buf, extra, sep); + strbuf_release(&msgbuf); } int log_tree_diff_flush(struct rev_info *opt) -- cgit v0.10.2-6-g49f6 From b655d46bb2d8aa12f3203f93c323b41df161fd26 Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Mon, 10 Sep 2007 12:35:07 +0200 Subject: Use strbuf_read in builtin-fetch-tool.c. xrealloc.use --; Signed-off-by: Pierre Habouzit Signed-off-by: Junio C Hamano diff --git a/builtin-fetch--tool.c b/builtin-fetch--tool.c index 24c7e6f..90bdc32 100644 --- a/builtin-fetch--tool.c +++ b/builtin-fetch--tool.c @@ -2,27 +2,16 @@ #include "cache.h" #include "refs.h" #include "commit.h" - -#define CHUNK_SIZE 1024 +#include "strbuf.h" static char *get_stdin(void) { - size_t offset = 0; - char *data = xmalloc(CHUNK_SIZE); - - while (1) { - ssize_t cnt = xread(0, data + offset, CHUNK_SIZE); - if (cnt < 0) - die("error reading standard input: %s", - strerror(errno)); - if (cnt == 0) { - data[offset] = 0; - break; - } - offset += cnt; - data = xrealloc(data, offset + CHUNK_SIZE); + struct strbuf buf; + strbuf_init(&buf, 0); + if (strbuf_read(&buf, 0, 1024) < 0) { + die("error reading standard input: %s", strerror(errno)); } - return data; + return strbuf_detach(&buf); } static void show_new(enum object_type type, unsigned char *sha1_new) -- cgit v0.10.2-6-g49f6 From 635d043f30c60f5ec8121bd94304e529f90407c7 Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Mon, 10 Sep 2007 12:35:08 +0200 Subject: Use strbufs to in read_message (imap-send.c), custom buffer--. Signed-off-by: Pierre Habouzit Signed-off-by: Junio C Hamano diff --git a/imap-send.c b/imap-send.c index a5a0696..ecd4216 100644 --- a/imap-send.c +++ b/imap-send.c @@ -23,6 +23,7 @@ */ #include "cache.h" +#include "strbuf.h" typedef struct store_conf { char *name; @@ -1160,28 +1161,18 @@ imap_store_msg( store_t *gctx, msg_data_t *data, int *uid ) static int read_message( FILE *f, msg_data_t *msg ) { - int len, r; + struct strbuf buf; - memset( msg, 0, sizeof *msg ); - len = CHUNKSIZE; - msg->data = xmalloc( len+1 ); - msg->data[0] = 0; - - while(!feof( f )) { - if (msg->len >= len) { - void *p; - len += CHUNKSIZE; - p = xrealloc(msg->data, len+1); - if (!p) - break; - msg->data = p; - } - r = fread( &msg->data[msg->len], 1, len - msg->len, f ); - if (r <= 0) + memset(msg, 0, sizeof(*msg)); + strbuf_init(&buf, 0); + + do { + if (strbuf_fread(&buf, CHUNKSIZE, f) <= 0) break; - msg->len += r; - } - msg->data[msg->len] = 0; + } while (!feof(f)); + + msg->len = buf.len; + msg->data = strbuf_detach(&buf); return msg->len; } -- cgit v0.10.2-6-g49f6 From fd17f5b5f77716bf90098c6e49e3cf7fd9f56306 Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Mon, 10 Sep 2007 12:35:09 +0200 Subject: Replace all read_fd use with strbuf_read, and get rid of it. This brings builtin-stripspace, builtin-tag and mktag to use strbufs. Signed-off-by: Pierre Habouzit Signed-off-by: Junio C Hamano diff --git a/builtin-stripspace.c b/builtin-stripspace.c index 916355c..c4cf2f0 100644 --- a/builtin-stripspace.c +++ b/builtin-stripspace.c @@ -1,5 +1,6 @@ #include "builtin.h" #include "cache.h" +#include "strbuf.h" /* * Returns the length of a line, without trailing spaces. @@ -74,26 +75,22 @@ size_t stripspace(char *buffer, size_t length, int skip_comments) int cmd_stripspace(int argc, const char **argv, const char *prefix) { - char *buffer; - unsigned long size; + struct strbuf buf; int strip_comments = 0; if (argc > 1 && (!strcmp(argv[1], "-s") || !strcmp(argv[1], "--strip-comments"))) strip_comments = 1; - size = 1024; - buffer = xmalloc(size); - if (read_fd(0, &buffer, &size)) { - free(buffer); + strbuf_init(&buf, 0); + if (strbuf_read(&buf, 0, 1024) < 0) die("could not read the input"); - } - size = stripspace(buffer, size, strip_comments); - write_or_die(1, buffer, size); - if (size) - putc('\n', stdout); + strbuf_setlen(&buf, stripspace(buf.buf, buf.len, strip_comments)); + if (buf.len) + strbuf_addch(&buf, '\n'); - free(buffer); + write_or_die(1, buf.buf, buf.len); + strbuf_release(&buf); return 0; } diff --git a/builtin-tag.c b/builtin-tag.c index 3a9d2ee..9f29342 100644 --- a/builtin-tag.c +++ b/builtin-tag.c @@ -8,6 +8,7 @@ #include "cache.h" #include "builtin.h" +#include "strbuf.h" #include "refs.h" #include "tag.h" #include "run-command.h" @@ -17,7 +18,7 @@ static const char builtin_tag_usage[] = static char signingkey[1000]; -static void launch_editor(const char *path, char **buffer, unsigned long *len) +static void launch_editor(const char *path, struct strbuf *buffer) { const char *editor, *terminal; struct child_process child; @@ -55,10 +56,8 @@ static void launch_editor(const char *path, char **buffer, unsigned long *len) fd = open(path, O_RDONLY); if (fd < 0) die("could not open '%s': %s", path, strerror(errno)); - if (read_fd(fd, buffer, len)) { - free(*buffer); - die("could not read message file '%s': %s", - path, strerror(errno)); + if (strbuf_read(buffer, fd, 0) < 0) { + die("could not read message file '%s': %s", path, strerror(errno)); } close(fd); } @@ -184,7 +183,7 @@ static int verify_tag(const char *name, const char *ref, return 0; } -static ssize_t do_sign(char *buffer, size_t size, size_t max) +static int do_sign(struct strbuf *buffer) { struct child_process gpg; const char *args[4]; @@ -216,22 +215,22 @@ static ssize_t do_sign(char *buffer, size_t size, size_t max) if (start_command(&gpg)) return error("could not run gpg."); - if (write_in_full(gpg.in, buffer, size) != size) { + if (write_in_full(gpg.in, buffer->buf, buffer->len) != buffer->len) { close(gpg.in); finish_command(&gpg); return error("gpg did not accept the tag data"); } close(gpg.in); gpg.close_in = 0; - len = read_in_full(gpg.out, buffer + size, max - size); + len = strbuf_read(buffer, gpg.out, 1024); if (finish_command(&gpg) || !len || len < 0) return error("gpg failed to sign the tag"); - if (len == max - size) + if (len < 0) return error("could not read the entire signature from gpg."); - return size + len; + return 0; } static const char tag_template[] = @@ -254,15 +253,13 @@ static int git_tag_config(const char *var, const char *value) return git_default_config(var, value); } -#define MAX_SIGNATURE_LENGTH 1024 -/* message must be NULL or allocated, it will be reallocated and freed */ static void create_tag(const unsigned char *object, const char *tag, - char *message, int sign, unsigned char *result) + struct strbuf *buf, int message, int sign, + unsigned char *result) { enum object_type type; - char header_buf[1024], *buffer = NULL; - int header_len, max_size; - unsigned long size = 0; + char header_buf[1024]; + int header_len; type = sha1_object_info(object, NULL); if (type <= OBJ_NONE) @@ -294,53 +291,40 @@ static void create_tag(const unsigned char *object, const char *tag, write_or_die(fd, tag_template, strlen(tag_template)); close(fd); - launch_editor(path, &buffer, &size); + launch_editor(path, buf); unlink(path); free(path); } - else { - buffer = message; - size = strlen(message); - } - size = stripspace(buffer, size, 1); + strbuf_setlen(buf, stripspace(buf->buf, buf->len, 1)); - if (!message && !size) + if (!message && !buf->len) die("no tag message?"); /* insert the header and add the '\n' if needed: */ - max_size = header_len + size + (sign ? MAX_SIGNATURE_LENGTH : 0) + 1; - buffer = xrealloc(buffer, max_size); - if (size) - buffer[size++] = '\n'; - memmove(buffer + header_len, buffer, size); - memcpy(buffer, header_buf, header_len); - size += header_len; - - if (sign) { - ssize_t r = do_sign(buffer, size, max_size); - if (r < 0) - die("unable to sign the tag"); - size = r; - } + if (buf->len) + strbuf_addch(buf, '\n'); + strbuf_insert(buf, 0, header_buf, header_len); - if (write_sha1_file(buffer, size, tag_type, result) < 0) + if (sign && do_sign(buf) < 0) + die("unable to sign the tag"); + if (write_sha1_file(buf->buf, buf->len, tag_type, result) < 0) die("unable to write tag file"); - free(buffer); } int cmd_tag(int argc, const char **argv, const char *prefix) { + struct strbuf buf; unsigned char object[20], prev[20]; - int annotate = 0, sign = 0, force = 0, lines = 0; - char *message = NULL; + int annotate = 0, sign = 0, force = 0, lines = 0, message = 0; char ref[PATH_MAX]; const char *object_ref, *tag; int i; struct ref_lock *lock; git_config(git_tag_config); + strbuf_init(&buf, 0); for (i = 1; i < argc; i++) { const char *arg = argv[i]; @@ -376,11 +360,11 @@ int cmd_tag(int argc, const char **argv, const char *prefix) die("option -m needs an argument."); if (message) die("only one -F or -m option is allowed."); - message = xstrdup(argv[i]); + strbuf_addstr(&buf, argv[i]); + message = 1; continue; } if (!strcmp(arg, "-F")) { - unsigned long len; int fd; annotate = 1; @@ -398,12 +382,10 @@ int cmd_tag(int argc, const char **argv, const char *prefix) die("could not open '%s': %s", argv[i], strerror(errno)); } - len = 1024; - message = xmalloc(len); - if (read_fd(fd, &message, &len)) { - free(message); + if (strbuf_read(&buf, fd, 1024) < 0) { die("cannot read %s", argv[i]); } + message = 1; continue; } if (!strcmp(arg, "-u")) { @@ -451,7 +433,7 @@ int cmd_tag(int argc, const char **argv, const char *prefix) die("tag '%s' already exists", tag); if (annotate) - create_tag(object, tag, message, sign, object); + create_tag(object, tag, &buf, message, sign, object); lock = lock_any_ref_for_update(ref, prev, 0); if (!lock) @@ -459,5 +441,6 @@ int cmd_tag(int argc, const char **argv, const char *prefix) if (write_ref_sha1(lock, object, NULL) < 0) die("%s: cannot update the ref", ref); + strbuf_release(&buf); return 0; } diff --git a/cache.h b/cache.h index 493983c..231f81d 100644 --- a/cache.h +++ b/cache.h @@ -269,7 +269,6 @@ extern int ie_match_stat(struct index_state *, struct cache_entry *, struct stat extern int ie_modified(struct index_state *, struct cache_entry *, struct stat *, int); extern int ce_path_match(const struct cache_entry *ce, const char **pathspec); extern int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object, enum object_type type, const char *path); -extern int read_fd(int fd, char **return_buf, unsigned long *return_size); extern int index_pipe(unsigned char *sha1, int fd, const char *type, int write_object); extern int index_path(unsigned char *sha1, const char *path, struct stat *st, int write_object); extern void fill_stat_cache_info(struct cache_entry *ce, struct stat *st); diff --git a/mktag.c b/mktag.c index 38acd5a..7567f9e 100644 --- a/mktag.c +++ b/mktag.c @@ -1,4 +1,5 @@ #include "cache.h" +#include "strbuf.h" #include "tag.h" /* @@ -111,8 +112,7 @@ static int verify_tag(char *buffer, unsigned long size) int main(int argc, char **argv) { - unsigned long size = 4096; - char *buffer = xmalloc(size); + struct strbuf buf; unsigned char result_sha1[20]; if (argc != 1) @@ -120,21 +120,20 @@ int main(int argc, char **argv) setup_git_directory(); - if (read_fd(0, &buffer, &size)) { - free(buffer); + strbuf_init(&buf, 0); + if (strbuf_read(&buf, 0, 4096) < 0) { die("could not read from stdin"); } /* Verify it for some basic sanity: it needs to start with "object \ntype\ntagger " */ - if (verify_tag(buffer, size) < 0) + if (verify_tag(buf.buf, buf.len) < 0) die("invalid tag signature file"); - if (write_sha1_file(buffer, size, tag_type, result_sha1) < 0) + if (write_sha1_file(buf.buf, buf.len, tag_type, result_sha1) < 0) die("unable to write tag file"); - free(buffer); - + strbuf_release(&buf); printf("%s\n", sha1_to_hex(result_sha1)); return 0; } diff --git a/sha1_file.c b/sha1_file.c index 9978a58..aea1096 100644 --- a/sha1_file.c +++ b/sha1_file.c @@ -14,6 +14,7 @@ #include "tag.h" #include "tree.h" #include "refs.h" +#include "strbuf.h" #ifndef O_NOATIME #if defined(__linux__) && (defined(__i386__) || defined(__PPC__)) @@ -2302,68 +2303,25 @@ int has_sha1_file(const unsigned char *sha1) return find_sha1_file(sha1, &st) ? 1 : 0; } -/* - * reads from fd as long as possible into a supplied buffer of size bytes. - * If necessary the buffer's size is increased using realloc() - * - * returns 0 if anything went fine and -1 otherwise - * - * The buffer is always NUL-terminated, not including it in returned size. - * - * NOTE: both buf and size may change, but even when -1 is returned - * you still have to free() it yourself. - */ -int read_fd(int fd, char **return_buf, unsigned long *return_size) -{ - char *buf = *return_buf; - unsigned long size = *return_size; - ssize_t iret; - unsigned long off = 0; - - if (!buf || size <= 1) { - size = 1024; - buf = xrealloc(buf, size); - } - - do { - iret = xread(fd, buf + off, (size - 1) - off); - if (iret > 0) { - off += iret; - if (off == size - 1) { - size = alloc_nr(size); - buf = xrealloc(buf, size); - } - } - } while (iret > 0); - - buf[off] = '\0'; - - *return_buf = buf; - *return_size = off; - - if (iret < 0) - return -1; - return 0; -} - int index_pipe(unsigned char *sha1, int fd, const char *type, int write_object) { - unsigned long size = 4096; - char *buf = xmalloc(size); + struct strbuf buf; int ret; - if (read_fd(fd, &buf, &size)) { - free(buf); + strbuf_init(&buf, 0); + if (strbuf_read(&buf, fd, 4096) < 0) { + strbuf_release(&buf); return -1; } if (!type) type = blob_type; if (write_object) - ret = write_sha1_file(buf, size, type, sha1); + ret = write_sha1_file(buf.buf, buf.len, type, sha1); else - ret = hash_sha1_file(buf, size, type, sha1); - free(buf); + ret = hash_sha1_file(buf.buf, buf.len, type, sha1); + strbuf_release(&buf); + return ret; } -- cgit v0.10.2-6-g49f6 From 760da9607ee08e9dd495dee993262bb857694ac9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ren=C3=A9=20Scharfe?= Date: Fri, 14 Sep 2007 00:13:06 +0200 Subject: archive: fix subst file generation Before the strbuf conversion, result was a char pointer. The if statement checked for it being not NULL, which meant that no "$Format:...$" string had been found and no replacement had to be made. format_subst() returned NULL in that case -- the caller then simply kept the original file content, as it was unaffected by the expansion. The length of the string being 0 is not the same as the string being NULL (expansion to an empty string vs. no expansion at all), so checking result.len != 0 is not a full replacement for the old NULL check. However, I doubt the subtle optimization explained above resulted in a notable speed-up anyway. Simplify the code and add the tail of the file to the expanded string unconditionally. [jc: added a test to expose the breakage this fixes] Signed-off-by: Rene Scharfe Signed-off-by: Junio C Hamano diff --git a/builtin-archive.c b/builtin-archive.c index b50d5ad..6fa424d 100644 --- a/builtin-archive.c +++ b/builtin-archive.c @@ -111,9 +111,7 @@ static void *format_subst(const struct commit *commit, const char *format, a = c + 1; } - if (result.len && len) { - strbuf_add(&result, a, len); - } + strbuf_add(&result, a, len); *sizep = result.len; diff --git a/t/t5000-tar-tree.sh b/t/t5000-tar-tree.sh index 42e28ab..dca2067 100755 --- a/t/t5000-tar-tree.sh +++ b/t/t5000-tar-tree.sh @@ -36,7 +36,8 @@ test_expect_success \ echo simple textfile >a/a && mkdir a/bin && cp /bin/sh a/bin && - printf "A\$Format:%s\$O" "$SUBSTFORMAT" >a/substfile && + printf "A\$Format:%s\$O" "$SUBSTFORMAT" >a/substfile1 && + printf "A not substituted O" >a/substfile2 && ln -s a a/l1 && (p=long_path_to_a_file && cd a && for depth in 1 2 3 4 5; do mkdir $p && cd $p; done && @@ -108,20 +109,22 @@ test_expect_success \ 'diff -r a c/prefix/a' test_expect_success \ - 'create an archive with a substfile' \ - 'echo substfile export-subst >a/.gitattributes && + 'create an archive with a substfiles' \ + 'echo "substfile?" export-subst >a/.gitattributes && git archive HEAD >f.tar && rm a/.gitattributes' test_expect_success \ - 'extract substfile' \ + 'extract substfiles' \ '(mkdir f && cd f && $TAR xf -) f/a/substfile.expected && - diff f/a/substfile.expected f/a/substfile' + >f/a/substfile1.expected && + diff f/a/substfile1.expected f/a/substfile1 && + diff a/substfile2 f/a/substfile2 +' test_expect_success \ 'git archive --format=zip' \ -- cgit v0.10.2-6-g49f6 From 917c9a713397b16671ed5b1f1c159515bcfa389e Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Sat, 15 Sep 2007 15:56:50 +0200 Subject: New strbuf APIs: splice and attach. * strbuf_splice replace a portion of the buffer with another. * strbuf_attach replace a strbuf buffer with the given one, that should be malloc'ed. Then it enforces strbuf's invariants. If alloc > len, then this function has negligible cost, else it will perform a realloc, possibly with a cost. Also some style issues are fixed now. Signed-off-by: Pierre Habouzit Acked-by: Linus Torvalds Signed-off-by: Junio C Hamano diff --git a/strbuf.c b/strbuf.c index d919047..ff551ac 100644 --- a/strbuf.c +++ b/strbuf.c @@ -1,30 +1,45 @@ #include "cache.h" #include "strbuf.h" -void strbuf_init(struct strbuf *sb, size_t hint) { +void strbuf_init(struct strbuf *sb, size_t hint) +{ memset(sb, 0, sizeof(*sb)); if (hint) strbuf_grow(sb, hint); } -void strbuf_release(struct strbuf *sb) { +void strbuf_release(struct strbuf *sb) +{ free(sb->buf); memset(sb, 0, sizeof(*sb)); } -void strbuf_reset(struct strbuf *sb) { +void strbuf_reset(struct strbuf *sb) +{ if (sb->len) strbuf_setlen(sb, 0); sb->eof = 0; } -char *strbuf_detach(struct strbuf *sb) { +char *strbuf_detach(struct strbuf *sb) +{ char *res = sb->buf; strbuf_init(sb, 0); return res; } -void strbuf_grow(struct strbuf *sb, size_t extra) { +void strbuf_attach(struct strbuf *sb, void *buf, size_t len, size_t alloc) +{ + strbuf_release(sb); + sb->buf = buf; + sb->len = len; + sb->alloc = alloc; + strbuf_grow(sb, 0); + sb->buf[sb->len] = '\0'; +} + +void strbuf_grow(struct strbuf *sb, size_t extra) +{ if (sb->len + extra + 1 <= sb->len) die("you want to use way too much memory"); ALLOC_GROW(sb->buf, sb->len + extra + 1, sb->alloc); @@ -37,24 +52,44 @@ void strbuf_rtrim(struct strbuf *sb) sb->buf[sb->len] = '\0'; } -void strbuf_insert(struct strbuf *sb, size_t pos, const void *data, size_t len) { +void strbuf_insert(struct strbuf *sb, size_t pos, const void *data, size_t len) +{ strbuf_grow(sb, len); - if (pos >= sb->len) { - pos = sb->len; - } else { - memmove(sb->buf + pos + len, sb->buf + pos, sb->len - pos); - } + if (pos > sb->len) + die("`pos' is too far after the end of the buffer"); + memmove(sb->buf + pos + len, sb->buf + pos, sb->len - pos); memcpy(sb->buf + pos, data, len); strbuf_setlen(sb, sb->len + len); } -void strbuf_add(struct strbuf *sb, const void *data, size_t len) { +void strbuf_splice(struct strbuf *sb, size_t pos, size_t len, + const void *data, size_t dlen) +{ + if (pos + len < pos) + die("you want to use way too much memory"); + if (pos > sb->len) + die("`pos' is too far after the end of the buffer"); + if (pos + len > sb->len) + die("`pos + len' is too far after the end of the buffer"); + + if (dlen >= len) + strbuf_grow(sb, dlen - len); + memmove(sb->buf + pos + dlen, + sb->buf + pos + len, + sb->len - pos - len); + memcpy(sb->buf + pos, data, dlen); + strbuf_setlen(sb, sb->len + dlen - len); +} + +void strbuf_add(struct strbuf *sb, const void *data, size_t len) +{ strbuf_grow(sb, len); memcpy(sb->buf + sb->len, data, len); strbuf_setlen(sb, sb->len + len); } -void strbuf_addf(struct strbuf *sb, const char *fmt, ...) { +void strbuf_addf(struct strbuf *sb, const char *fmt, ...) +{ int len; va_list ap; @@ -76,7 +111,8 @@ void strbuf_addf(struct strbuf *sb, const char *fmt, ...) { strbuf_setlen(sb, sb->len + len); } -size_t strbuf_fread(struct strbuf *sb, size_t size, FILE *f) { +size_t strbuf_fread(struct strbuf *sb, size_t size, FILE *f) +{ size_t res; strbuf_grow(sb, size); @@ -110,7 +146,8 @@ ssize_t strbuf_read(struct strbuf *sb, int fd, size_t hint) return sb->len - oldlen; } -void read_line(struct strbuf *sb, FILE *fp, int term) { +void read_line(struct strbuf *sb, FILE *fp, int term) +{ int ch; if (feof(fp)) { strbuf_release(sb); diff --git a/strbuf.h b/strbuf.h index 21fc111..f163c63 100644 --- a/strbuf.h +++ b/strbuf.h @@ -55,6 +55,7 @@ extern void strbuf_init(struct strbuf *, size_t); extern void strbuf_release(struct strbuf *); extern void strbuf_reset(struct strbuf *); extern char *strbuf_detach(struct strbuf *); +extern void strbuf_attach(struct strbuf *, void *, size_t, size_t); /*----- strbuf size related -----*/ static inline size_t strbuf_avail(struct strbuf *sb) { @@ -81,6 +82,10 @@ static inline void strbuf_addch(struct strbuf *sb, int c) { /* inserts after pos, or appends if pos >= sb->len */ extern void strbuf_insert(struct strbuf *, size_t pos, const void *, size_t); +/* splice pos..pos+len with given data */ +extern void strbuf_splice(struct strbuf *, size_t pos, size_t len, + const void *, size_t); + extern void strbuf_add(struct strbuf *, const void *, size_t); static inline void strbuf_addstr(struct strbuf *sb, const char *s) { strbuf_add(sb, s, strlen(s)); -- cgit v0.10.2-6-g49f6 From 5ecd293d1420bf641a927a015877950f4d79c067 Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Sun, 16 Sep 2007 15:51:04 +0200 Subject: Rewrite convert_to_{git,working_tree} to use strbuf's. * Now, those functions take an "out" strbuf argument, where they store their result if any. In that case, it also returns 1, else it returns 0. * those functions support "in place" editing, in the sense that it's OK to call them this way: convert_to_git(path, sb->buf, sb->len, sb); When doable, conversions are done in place for real, else the strbuf content is just replaced with the new one, transparentely for the caller. If you want to create a new filter working this way, being the accumulation of filter1, filter2, ... filtern, then your meta_filter would be: int meta_filter(..., const char *src, size_t len, struct strbuf *sb) { int ret = 0; ret |= filter1(...., src, len, sb); if (ret) { src = sb->buf; len = sb->len; } ret |= filter2(...., src, len, sb); if (ret) { src = sb->buf; len = sb->len; } .... return ret | filtern(..., src, len, sb); } That's why subfilters the convert_to_* functions called were also rewritten to work this way. Signed-off-by: Pierre Habouzit Acked-by: Linus Torvalds Signed-off-by: Junio C Hamano diff --git a/builtin-apply.c b/builtin-apply.c index 988e85f..e5c29eb 100644 --- a/builtin-apply.c +++ b/builtin-apply.c @@ -1446,8 +1446,7 @@ static int read_old_data(struct stat *st, const char *path, char **buf_p, unsign { int fd; unsigned long got; - unsigned long nsize; - char *nbuf; + struct strbuf nbuf; unsigned long size = *size_p; char *buf = *buf_p; @@ -1466,13 +1465,12 @@ static int read_old_data(struct stat *st, const char *path, char **buf_p, unsign got += ret; } close(fd); - nsize = got; - nbuf = convert_to_git(path, buf, &nsize); - if (nbuf) { + strbuf_init(&nbuf, 0); + if (convert_to_git(path, buf, size, &nbuf)) { free(buf); - *buf_p = nbuf; - *alloc_p = nsize; - *size_p = nsize; + *buf_p = nbuf.buf; + *alloc_p = nbuf.alloc; + *size_p = nbuf.len; } return got != size; default: @@ -2439,7 +2437,7 @@ static void add_index_file(const char *path, unsigned mode, void *buf, unsigned static int try_create_file(const char *path, unsigned int mode, const char *buf, unsigned long size) { int fd; - char *nbuf; + struct strbuf nbuf; if (S_ISGITLINK(mode)) { struct stat st; @@ -2458,9 +2456,11 @@ static int try_create_file(const char *path, unsigned int mode, const char *buf, if (fd < 0) return -1; - nbuf = convert_to_working_tree(path, buf, &size); - if (nbuf) - buf = nbuf; + strbuf_init(&nbuf, 0); + if (convert_to_working_tree(path, buf, size, &nbuf)) { + size = nbuf.len; + buf = nbuf.buf; + } while (size) { int written = xwrite(fd, buf, size); @@ -2473,8 +2473,7 @@ static int try_create_file(const char *path, unsigned int mode, const char *buf, } if (close(fd) < 0) die("closing file %s: %s", path, strerror(errno)); - if (nbuf) - free(nbuf); + strbuf_release(&nbuf); return 0; } diff --git a/builtin-archive.c b/builtin-archive.c index 6fa424d..843a9e3 100644 --- a/builtin-archive.c +++ b/builtin-archive.c @@ -81,22 +81,21 @@ static int run_remote_archiver(const char *remote, int argc, return !!rv; } -static void *format_subst(const struct commit *commit, const char *format, - unsigned long *sizep) +static void format_subst(const struct commit *commit, + const char *src, size_t len, + struct strbuf *buf) { - unsigned long len = *sizep; - const char *a = format; - struct strbuf result; + char *to_free = NULL; struct strbuf fmt; - strbuf_init(&result, 0); + if (src == buf->buf) + to_free = strbuf_detach(buf); strbuf_init(&fmt, 0); - for (;;) { const char *b, *c; - b = memmem(a, len, "$Format:", 8); - if (!b || a + len < b + 9) + b = memmem(src, len, "$Format:", 8); + if (!b || src + len < b + 9) break; c = memchr(b + 8, '$', len - 8); if (!c) @@ -105,62 +104,57 @@ static void *format_subst(const struct commit *commit, const char *format, strbuf_reset(&fmt); strbuf_add(&fmt, b + 8, c - b - 8); - strbuf_add(&result, a, b - a); - format_commit_message(commit, fmt.buf, &result); - len -= c + 1 - a; - a = c + 1; + strbuf_add(buf, src, b - src); + format_commit_message(commit, fmt.buf, buf); + len -= c + 1 - src; + src = c + 1; } - - strbuf_add(&result, a, len); - - *sizep = result.len; - + strbuf_add(buf, src, len); strbuf_release(&fmt); - return strbuf_detach(&result); + free(to_free); } -static void *convert_to_archive(const char *path, - const void *src, unsigned long *sizep, - const struct commit *commit) +static int convert_to_archive(const char *path, + const void *src, size_t len, + struct strbuf *buf, + const struct commit *commit) { static struct git_attr *attr_export_subst; struct git_attr_check check[1]; if (!commit) - return NULL; + return 0; - if (!attr_export_subst) - attr_export_subst = git_attr("export-subst", 12); + if (!attr_export_subst) + attr_export_subst = git_attr("export-subst", 12); check[0].attr = attr_export_subst; if (git_checkattr(path, ARRAY_SIZE(check), check)) - return NULL; + return 0; if (!ATTR_TRUE(check[0].value)) - return NULL; + return 0; - return format_subst(commit, src, sizep); + format_subst(commit, src, len, buf); + return 1; } void *sha1_file_to_archive(const char *path, const unsigned char *sha1, unsigned int mode, enum object_type *type, - unsigned long *size, + unsigned long *sizep, const struct commit *commit) { - void *buffer, *converted; + void *buffer; - buffer = read_sha1_file(sha1, type, size); + buffer = read_sha1_file(sha1, type, sizep); if (buffer && S_ISREG(mode)) { - converted = convert_to_working_tree(path, buffer, size); - if (converted) { - free(buffer); - buffer = converted; - } - - converted = convert_to_archive(path, buffer, size, commit); - if (converted) { - free(buffer); - buffer = converted; - } + struct strbuf buf; + + strbuf_init(&buf, 0); + strbuf_attach(&buf, buffer, *sizep, *sizep + 1); + convert_to_working_tree(path, buf.buf, buf.len, &buf); + convert_to_archive(path, buf.buf, buf.len, &buf, commit); + *sizep = buf.len; + buffer = buf.buf; } return buffer; diff --git a/cache.h b/cache.h index 231f81d..37eb57e 100644 --- a/cache.h +++ b/cache.h @@ -2,6 +2,7 @@ #define CACHE_H #include "git-compat-util.h" +#include "strbuf.h" #include SHA1_HEADER #include @@ -589,8 +590,9 @@ extern void trace_printf(const char *format, ...); extern void trace_argv_printf(const char **argv, int count, const char *format, ...); /* convert.c */ -extern char *convert_to_git(const char *path, const char *src, unsigned long *sizep); -extern char *convert_to_working_tree(const char *path, const char *src, unsigned long *sizep); +/* returns 1 if *dst was used */ +extern int convert_to_git(const char *path, const char *src, size_t len, struct strbuf *dst); +extern int convert_to_working_tree(const char *path, const char *src, size_t len, struct strbuf *dst); /* diff.c */ extern int diff_auto_refresh_index; diff --git a/convert.c b/convert.c index d77c8eb..00a341c 100644 --- a/convert.c +++ b/convert.c @@ -1,6 +1,7 @@ #include "cache.h" #include "attr.h" #include "run-command.h" +#include "strbuf.h" /* * convert.c - convert a file when checking it out and checking it in. @@ -80,24 +81,19 @@ 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 +102,17 @@ 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; + strbuf_grow(buf, len); + dst = buf->buf; if (action == CRLF_GUESS) { /* * If we guessed, we already know we rejected a file with @@ -134,71 +123,72 @@ 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); + + 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 +236,8 @@ 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 +245,19 @@ 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 +266,37 @@ 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 = error("read from external filter %s failed", cmd); + ret = 0; } - status = finish_command(&child_process); if (status) { - error("external filter %s failed %d", cmd, -status); - free(dst); - dst = NULL; + ret = error("external filter %s failed %d", cmd, -status); + ret = 0; } - if (dst) - *sizep = dstsize; - return dst; + if (ret) { + *dst = nbuf; + } else { + strbuf_release(&nbuf); + } + return ret; } static struct convert_driver { @@ -449,137 +420,104 @@ 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; + + strbuf_grow(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 == "$" - * - src[0] == "I" - */ + /* are we "faking" in place editing ? */ + if (src == buf->buf) + to_free = strbuf_detach(buf); + hash_sha1_file(src, len, "blob", sha1); - /* - * It's possible that an expanded Id has crept its way into the - * repository, we cope with that by stripping the expansion out - */ - if (src[2] == ':') { - /* Expanded keywords have "$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 +556,12 @@ 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 +573,25 @@ 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 +603,15 @@ 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); } diff --git a/diff.c b/diff.c index 7290309..f41bcd9 100644 --- a/diff.c +++ b/diff.c @@ -1600,10 +1600,9 @@ int diff_populate_filespec(struct diff_filespec *s, int size_only) if (!s->sha1_valid || reuse_worktree_file(s->path, s->sha1, 0)) { + struct strbuf buf; struct stat st; int fd; - char *buf; - unsigned long size; if (!strcmp(s->path, "-")) return populate_from_stdin(s); @@ -1644,13 +1643,12 @@ int diff_populate_filespec(struct diff_filespec *s, int size_only) /* * Convert from working tree format to canonical git format */ - size = s->size; - buf = convert_to_git(s->path, s->data, &size); - if (buf) { + strbuf_init(&buf, 0); + if (convert_to_git(s->path, s->data, s->size, &buf)) { munmap(s->data, s->size); s->should_munmap = 0; - s->data = buf; - s->size = size; + s->data = buf.buf; + s->size = buf.len; s->should_free = 1; } } diff --git a/entry.c b/entry.c index fc3a506..4a8c73b 100644 --- a/entry.c +++ b/entry.c @@ -104,7 +104,8 @@ static int write_entry(struct cache_entry *ce, char *path, const struct checkout long wrote; switch (ntohl(ce->ce_mode) & S_IFMT) { - char *buf, *new; + char *new; + struct strbuf buf; unsigned long size; case S_IFREG: @@ -116,10 +117,11 @@ static int write_entry(struct cache_entry *ce, char *path, const struct checkout /* * Convert from git internal format to working tree format */ - buf = convert_to_working_tree(ce->name, new, &size); - if (buf) { + strbuf_init(&buf, 0); + if (convert_to_working_tree(ce->name, new, size, &buf)) { free(new); - new = buf; + new = buf.buf; + size = buf.len; } if (to_tempfile) { diff --git a/sha1_file.c b/sha1_file.c index aea1096..64b5b46 100644 --- a/sha1_file.c +++ b/sha1_file.c @@ -2343,12 +2343,12 @@ int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object, * Convert blobs to git internal format */ if ((type == OBJ_BLOB) && S_ISREG(st->st_mode)) { - unsigned long nsize = size; - char *nbuf = convert_to_git(path, buf, &nsize); - if (nbuf) { + struct strbuf nbuf; + strbuf_init(&nbuf, 0); + if (convert_to_git(path, buf, size, &nbuf)) { munmap(buf, size); - size = nsize; - buf = nbuf; + size = nbuf.len; + buf = nbuf.buf; re_allocated = 1; } } -- cgit v0.10.2-6-g49f6 From ba3ed09728cb25e004d3b732de14fca8aeb602f6 Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Sat, 15 Sep 2007 15:56:50 +0200 Subject: Now that cache.h needs strbuf.h, remove useless includes. Signed-off-by: Pierre Habouzit Acked-by: Linus Torvalds Signed-off-by: Junio C Hamano diff --git a/archive-tar.c b/archive-tar.c index cc94cf3..a87bc4b 100644 --- a/archive-tar.c +++ b/archive-tar.c @@ -3,7 +3,6 @@ */ #include "cache.h" #include "commit.h" -#include "strbuf.h" #include "tar.h" #include "builtin.h" #include "archive.h" diff --git a/builtin-apply.c b/builtin-apply.c index e5c29eb..1256716 100644 --- a/builtin-apply.c +++ b/builtin-apply.c @@ -12,7 +12,6 @@ #include "blob.h" #include "delta.h" #include "builtin.h" -#include "strbuf.h" /* * --check turns on checking that the working tree matches the diff --git a/builtin-blame.c b/builtin-blame.c index b004f06..e364b6c 100644 --- a/builtin-blame.c +++ b/builtin-blame.c @@ -18,7 +18,6 @@ #include "cache-tree.h" #include "path-list.h" #include "mailmap.h" -#include "strbuf.h" static char blame_usage[] = "git-blame [-c] [-b] [-l] [--root] [-t] [-f] [-n] [-s] [-p] [-w] [-L n,m] [-S ] [-M] [-C] [-C] [--contents ] [--incremental] [commit] [--] file\n" diff --git a/builtin-checkout-index.c b/builtin-checkout-index.c index 153ba7d..85e8efe 100644 --- a/builtin-checkout-index.c +++ b/builtin-checkout-index.c @@ -38,7 +38,6 @@ */ #include "builtin.h" #include "cache.h" -#include "strbuf.h" #include "quote.h" #include "cache-tree.h" diff --git a/builtin-commit-tree.c b/builtin-commit-tree.c index 325334f..88b0ab3 100644 --- a/builtin-commit-tree.c +++ b/builtin-commit-tree.c @@ -8,7 +8,6 @@ #include "tree.h" #include "builtin.h" #include "utf8.h" -#include "strbuf.h" #define BLOCKING (1ul << 14) diff --git a/builtin-fetch--tool.c b/builtin-fetch--tool.c index 90bdc32..514a3cc 100644 --- a/builtin-fetch--tool.c +++ b/builtin-fetch--tool.c @@ -2,7 +2,6 @@ #include "cache.h" #include "refs.h" #include "commit.h" -#include "strbuf.h" static char *get_stdin(void) { diff --git a/builtin-rerere.c b/builtin-rerere.c index 826d346..58288f6 100644 --- a/builtin-rerere.c +++ b/builtin-rerere.c @@ -1,7 +1,6 @@ #include "builtin.h" #include "cache.h" #include "path-list.h" -#include "strbuf.h" #include "xdiff/xdiff.h" #include "xdiff-interface.h" diff --git a/builtin-stripspace.c b/builtin-stripspace.c index c4cf2f0..1ce2847 100644 --- a/builtin-stripspace.c +++ b/builtin-stripspace.c @@ -1,6 +1,5 @@ #include "builtin.h" #include "cache.h" -#include "strbuf.h" /* * Returns the length of a line, without trailing spaces. diff --git a/builtin-tag.c b/builtin-tag.c index 9f29342..82ebda1 100644 --- a/builtin-tag.c +++ b/builtin-tag.c @@ -8,7 +8,6 @@ #include "cache.h" #include "builtin.h" -#include "strbuf.h" #include "refs.h" #include "tag.h" #include "run-command.h" diff --git a/builtin-update-index.c b/builtin-update-index.c index 9240a28..1091f1b 100644 --- a/builtin-update-index.c +++ b/builtin-update-index.c @@ -4,7 +4,6 @@ * Copyright (C) Linus Torvalds, 2005 */ #include "cache.h" -#include "strbuf.h" #include "quote.h" #include "cache-tree.h" #include "tree-walk.h" diff --git a/cache-tree.c b/cache-tree.c index 8f53c99..5471844 100644 --- a/cache-tree.c +++ b/cache-tree.c @@ -1,5 +1,4 @@ #include "cache.h" -#include "strbuf.h" #include "tree.h" #include "cache-tree.h" diff --git a/convert.c b/convert.c index 00a341c..508d30b 100644 --- a/convert.c +++ b/convert.c @@ -1,7 +1,6 @@ #include "cache.h" #include "attr.h" #include "run-command.h" -#include "strbuf.h" /* * convert.c - convert a file when checking it out and checking it in. diff --git a/diff.c b/diff.c index f41bcd9..56b672c 100644 --- a/diff.c +++ b/diff.c @@ -9,7 +9,6 @@ #include "xdiff-interface.h" #include "color.h" #include "attr.h" -#include "strbuf.h" #ifdef NO_FAST_WORKING_DIRECTORY #define FAST_WORKING_DIRECTORY 0 diff --git a/fast-import.c b/fast-import.c index 2c0bfb9..1866d34 100644 --- a/fast-import.c +++ b/fast-import.c @@ -149,7 +149,6 @@ Format of STDIN stream: #include "pack.h" #include "refs.h" #include "csum-file.h" -#include "strbuf.h" #include "quote.h" #define PACK_ID_BITS 16 diff --git a/fetch.c b/fetch.c index dd6ed9e..c256e6f 100644 --- a/fetch.c +++ b/fetch.c @@ -6,7 +6,6 @@ #include "tag.h" #include "blob.h" #include "refs.h" -#include "strbuf.h" int get_tree = 0; int get_history = 0; diff --git a/imap-send.c b/imap-send.c index ecd4216..86e4a0f 100644 --- a/imap-send.c +++ b/imap-send.c @@ -23,7 +23,6 @@ */ #include "cache.h" -#include "strbuf.h" typedef struct store_conf { char *name; diff --git a/mktag.c b/mktag.c index 7567f9e..b05260c 100644 --- a/mktag.c +++ b/mktag.c @@ -1,5 +1,4 @@ #include "cache.h" -#include "strbuf.h" #include "tag.h" /* diff --git a/mktree.c b/mktree.c index 3891cd9..5dab4bd 100644 --- a/mktree.c +++ b/mktree.c @@ -4,7 +4,6 @@ * Copyright (c) Junio C Hamano, 2006 */ #include "cache.h" -#include "strbuf.h" #include "quote.h" #include "tree.h" diff --git a/sha1_file.c b/sha1_file.c index 64b5b46..59325d4 100644 --- a/sha1_file.c +++ b/sha1_file.c @@ -14,7 +14,6 @@ #include "tag.h" #include "tree.h" #include "refs.h" -#include "strbuf.h" #ifndef O_NOATIME #if defined(__linux__) && (defined(__i386__) || defined(__PPC__)) diff --git a/strbuf.c b/strbuf.c index ff551ac..c5f9e2a 100644 --- a/strbuf.c +++ b/strbuf.c @@ -1,5 +1,4 @@ #include "cache.h" -#include "strbuf.h" void strbuf_init(struct strbuf *sb, size_t hint) { -- cgit v0.10.2-6-g49f6 From c7f9cb14286fff23bfe65033d4ec63f84c77f554 Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Sun, 16 Sep 2007 18:54:42 +0200 Subject: builtin-apply: use strbuf's instead of buffer_desc's. Signed-off-by: Pierre Habouzit Acked-by: Linus Torvalds Signed-off-by: Junio C Hamano diff --git a/builtin-apply.c b/builtin-apply.c index 1256716..61b5131 100644 --- a/builtin-apply.c +++ b/builtin-apply.c @@ -1441,37 +1441,28 @@ static void show_stats(struct patch *patch) free(qname); } -static int read_old_data(struct stat *st, const char *path, char **buf_p, unsigned long *alloc_p, unsigned long *size_p) +static int read_old_data(struct stat *st, const char *path, struct strbuf *buf) { int fd; - unsigned long got; - struct strbuf nbuf; - unsigned long size = *size_p; - char *buf = *buf_p; switch (st->st_mode & S_IFMT) { case S_IFLNK: - return readlink(path, buf, size) != size; + strbuf_grow(buf, st->st_size); + if (readlink(path, buf->buf, st->st_size) != st->st_size) + return -1; + strbuf_setlen(buf, st->st_size); + return 0; case S_IFREG: fd = open(path, O_RDONLY); if (fd < 0) return error("unable to open %s", path); - got = 0; - for (;;) { - ssize_t ret = xread(fd, buf + got, size - got); - if (ret <= 0) - break; - got += ret; + if (strbuf_read(buf, fd, st->st_size) < 0) { + close(fd); + return -1; } close(fd); - strbuf_init(&nbuf, 0); - if (convert_to_git(path, buf, size, &nbuf)) { - free(buf); - *buf_p = nbuf.buf; - *alloc_p = nbuf.alloc; - *size_p = nbuf.len; - } - return got != size; + convert_to_git(path, buf->buf, buf->len, buf); + return 0; default: return -1; } @@ -1576,12 +1567,6 @@ static void remove_last_line(const char **rbuf, int *rsize) *rsize = offset + 1; } -struct buffer_desc { - char *buffer; - unsigned long size; - unsigned long alloc; -}; - static int apply_line(char *output, const char *patch, int plen) { /* plen is number of bytes to be copied from patch, @@ -1651,10 +1636,9 @@ static int apply_line(char *output, const char *patch, int plen) return output + plen - buf; } -static int apply_one_fragment(struct buffer_desc *desc, struct fragment *frag, int inaccurate_eof) +static int apply_one_fragment(struct strbuf *buf, struct fragment *frag, int inaccurate_eof) { int match_beginning, match_end; - char *buf = desc->buffer; const char *patch = frag->patch; int offset, size = frag->size; char *old = xmalloc(size); @@ -1765,24 +1749,17 @@ static int apply_one_fragment(struct buffer_desc *desc, struct fragment *frag, i lines = 0; pos = frag->newpos; for (;;) { - offset = find_offset(buf, desc->size, + offset = find_offset(buf->buf, buf->len, oldlines, oldsize, pos, &lines); - if (match_end && offset + oldsize != desc->size) + if (match_end && offset + oldsize != buf->len) offset = -1; if (match_beginning && offset) offset = -1; if (offset >= 0) { - int diff; - unsigned long size, alloc; - if (new_whitespace == strip_whitespace && - (desc->size - oldsize - offset == 0)) /* end of file? */ + (buf->len - oldsize - offset == 0)) /* end of file? */ newsize -= new_blank_lines_at_end; - diff = newsize - oldsize; - size = desc->size + diff; - alloc = desc->alloc; - /* Warn if it was necessary to reduce the number * of context lines. */ @@ -1792,19 +1769,8 @@ static int apply_one_fragment(struct buffer_desc *desc, struct fragment *frag, i " to apply fragment at %d\n", leading, trailing, pos + lines); - if (size > alloc) { - alloc = size + 8192; - desc->alloc = alloc; - buf = xrealloc(buf, alloc); - desc->buffer = buf; - } - desc->size = size; - memmove(buf + offset + newsize, - buf + offset + oldsize, - size - offset - newsize); - memcpy(buf + offset, newlines, newsize); + strbuf_splice(buf, offset, oldsize, newlines, newsize); offset = 0; - break; } @@ -1840,12 +1806,11 @@ static int apply_one_fragment(struct buffer_desc *desc, struct fragment *frag, i return offset; } -static int apply_binary_fragment(struct buffer_desc *desc, struct patch *patch) +static int apply_binary_fragment(struct strbuf *buf, struct patch *patch) { - unsigned long dst_size; struct fragment *fragment = patch->fragments; - void *data; - void *result; + unsigned long len; + void *dst; /* Binary patch is irreversible without the optional second hunk */ if (apply_in_reverse) { @@ -1856,29 +1821,24 @@ static int apply_binary_fragment(struct buffer_desc *desc, struct patch *patch) ? patch->new_name : patch->old_name); fragment = fragment->next; } - data = (void*) fragment->patch; switch (fragment->binary_patch_method) { case BINARY_DELTA_DEFLATED: - result = patch_delta(desc->buffer, desc->size, - data, - fragment->size, - &dst_size); - free(desc->buffer); - desc->buffer = result; - break; + dst = patch_delta(buf->buf, buf->len, fragment->patch, + fragment->size, &len); + if (!dst) + return -1; + /* XXX patch_delta NUL-terminates */ + strbuf_attach(buf, dst, len, len + 1); + return 0; case BINARY_LITERAL_DEFLATED: - free(desc->buffer); - desc->buffer = data; - dst_size = fragment->size; - break; + strbuf_reset(buf); + strbuf_add(buf, fragment->patch, fragment->size); + return 0; } - if (!desc->buffer) - return -1; - desc->size = desc->alloc = dst_size; - return 0; + return -1; } -static int apply_binary(struct buffer_desc *desc, struct patch *patch) +static int apply_binary(struct strbuf *buf, struct patch *patch) { const char *name = patch->old_name ? patch->old_name : patch->new_name; unsigned char sha1[20]; @@ -1897,7 +1857,7 @@ static int apply_binary(struct buffer_desc *desc, struct patch *patch) /* See if the old one matches what the patch * applies to. */ - hash_sha1_file(desc->buffer, desc->size, blob_type, sha1); + hash_sha1_file(buf->buf, buf->len, blob_type, sha1); if (strcmp(sha1_to_hex(sha1), patch->old_sha1_prefix)) return error("the patch applies to '%s' (%s), " "which does not match the " @@ -1906,16 +1866,14 @@ static int apply_binary(struct buffer_desc *desc, struct patch *patch) } else { /* Otherwise, the old one must be empty. */ - if (desc->size) + if (buf->len) return error("the patch applies to an empty " "'%s' but it is not empty", name); } get_sha1_hex(patch->new_sha1_prefix, sha1); if (is_null_sha1(sha1)) { - free(desc->buffer); - desc->alloc = desc->size = 0; - desc->buffer = NULL; + strbuf_release(buf); return 0; /* deletion patch */ } @@ -1923,43 +1881,44 @@ static int apply_binary(struct buffer_desc *desc, struct patch *patch) /* We already have the postimage */ enum object_type type; unsigned long size; + char *result; - free(desc->buffer); - desc->buffer = read_sha1_file(sha1, &type, &size); - if (!desc->buffer) + result = read_sha1_file(sha1, &type, &size); + if (!result) return error("the necessary postimage %s for " "'%s' cannot be read", patch->new_sha1_prefix, name); - desc->alloc = desc->size = size; - } - else { - /* We have verified desc matches the preimage; + /* XXX read_sha1_file NUL-terminates */ + strbuf_attach(buf, result, size, size + 1); + } else { + /* We have verified buf matches the preimage; * apply the patch data to it, which is stored * in the patch->fragments->{patch,size}. */ - if (apply_binary_fragment(desc, patch)) + if (apply_binary_fragment(buf, patch)) return error("binary patch does not apply to '%s'", name); /* verify that the result matches */ - hash_sha1_file(desc->buffer, desc->size, blob_type, sha1); + hash_sha1_file(buf->buf, buf->len, blob_type, sha1); if (strcmp(sha1_to_hex(sha1), patch->new_sha1_prefix)) - return error("binary patch to '%s' creates incorrect result (expecting %s, got %s)", name, patch->new_sha1_prefix, sha1_to_hex(sha1)); + return error("binary patch to '%s' creates incorrect result (expecting %s, got %s)", + name, patch->new_sha1_prefix, sha1_to_hex(sha1)); } return 0; } -static int apply_fragments(struct buffer_desc *desc, struct patch *patch) +static int apply_fragments(struct strbuf *buf, struct patch *patch) { struct fragment *frag = patch->fragments; const char *name = patch->old_name ? patch->old_name : patch->new_name; if (patch->is_binary) - return apply_binary(desc, patch); + return apply_binary(buf, patch); while (frag) { - if (apply_one_fragment(desc, frag, patch->inaccurate_eof)) { + if (apply_one_fragment(buf, frag, patch->inaccurate_eof)) { error("patch failed: %s:%ld", name, frag->oldpos); if (!apply_with_reject) return -1; @@ -1970,76 +1929,57 @@ static int apply_fragments(struct buffer_desc *desc, struct patch *patch) return 0; } -static int read_file_or_gitlink(struct cache_entry *ce, char **buf_p, - unsigned long *size_p) +static int read_file_or_gitlink(struct cache_entry *ce, struct strbuf *buf) { if (!ce) return 0; if (S_ISGITLINK(ntohl(ce->ce_mode))) { - *buf_p = xmalloc(100); - *size_p = snprintf(*buf_p, 100, - "Subproject commit %s\n", sha1_to_hex(ce->sha1)); + strbuf_grow(buf, 100); + strbuf_addf(buf, "Subproject commit %s\n", sha1_to_hex(ce->sha1)); } else { enum object_type type; - *buf_p = read_sha1_file(ce->sha1, &type, size_p); - if (!*buf_p) + unsigned long sz; + char *result; + + result = read_sha1_file(ce->sha1, &type, &sz); + if (!result) return -1; + /* XXX read_sha1_file NUL-terminates */ + strbuf_attach(buf, result, sz, sz + 1); } return 0; } static int apply_data(struct patch *patch, struct stat *st, struct cache_entry *ce) { - char *buf; - unsigned long size, alloc; - struct buffer_desc desc; + struct strbuf buf; - size = 0; - alloc = 0; - buf = NULL; + strbuf_init(&buf, 0); if (cached) { - if (read_file_or_gitlink(ce, &buf, &size)) + if (read_file_or_gitlink(ce, &buf)) return error("read of %s failed", patch->old_name); - alloc = size; } else if (patch->old_name) { if (S_ISGITLINK(patch->old_mode)) { - if (ce) - read_file_or_gitlink(ce, &buf, &size); - else { + if (ce) { + read_file_or_gitlink(ce, &buf); + } else { /* * There is no way to apply subproject * patch without looking at the index. */ patch->fragments = NULL; - size = 0; } - } - else { - size = xsize_t(st->st_size); - alloc = size + 8192; - buf = xmalloc(alloc); - if (read_old_data(st, patch->old_name, - &buf, &alloc, &size)) - return error("read of %s failed", - patch->old_name); + } else { + if (read_old_data(st, patch->old_name, &buf)) + return error("read of %s failed", patch->old_name); } } - desc.size = size; - desc.alloc = alloc; - desc.buffer = buf; - - if (apply_fragments(&desc, patch) < 0) + if (apply_fragments(&buf, patch) < 0) return -1; /* note with --reject this succeeds. */ - - /* NUL terminate the result */ - if (desc.alloc <= desc.size) - desc.buffer = xrealloc(desc.buffer, desc.size + 1); - desc.buffer[desc.size] = 0; - - patch->result = desc.buffer; - patch->resultsize = desc.size; + patch->result = buf.buf; + patch->resultsize = buf.len; if (0 < patch->is_delete && patch->resultsize) return error("removal patch leaves file contents"); @@ -2460,19 +2400,11 @@ static int try_create_file(const char *path, unsigned int mode, const char *buf, size = nbuf.len; buf = nbuf.buf; } + write_or_die(fd, buf, size); + strbuf_release(&nbuf); - while (size) { - int written = xwrite(fd, buf, size); - if (written < 0) - die("writing file %s: %s", path, strerror(errno)); - if (!written) - die("out of space writing file %s", path); - buf += written; - size -= written; - } if (close(fd) < 0) die("closing file %s: %s", path, strerror(errno)); - strbuf_release(&nbuf); return 0; } -- cgit v0.10.2-6-g49f6 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 diff --git a/commit.c b/commit.c index 6602e2c..13af933 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 v0.10.2-6-g49f6 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 diff --git a/commit.c b/commit.c index 13af933..85889f9 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 v0.10.2-6-g49f6 From e6c019d0b0140fae1cdfd661746cbe319b6c3670 Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Mon, 17 Sep 2007 11:19:04 +0200 Subject: Drop strbuf's 'eof' marker, and make read_line a first class citizen. read_line is now strbuf_getline, and is a first class citizen, it returns 0 when reading a line worked, EOF else. The ->eof marker was used non-locally by fast-import.c, mimic the same behaviour using a static int in "read_next_command", that now returns -1 on EOF, and avoids to call strbuf_getline when it's in EOF state. Also no longer automagically strbuf_release the buffer, it's counter intuitive and breaks fast-import in a very subtle way. Note: being at EOF implies that command_buf.len == 0. Signed-off-by: Pierre Habouzit Signed-off-by: Junio C Hamano diff --git a/builtin-checkout-index.c b/builtin-checkout-index.c index 85e8efe..a18ecc4 100644 --- a/builtin-checkout-index.c +++ b/builtin-checkout-index.c @@ -277,9 +277,7 @@ int cmd_checkout_index(int argc, const char **argv, const char *prefix) while (1) { char *path_name; const char *p; - - read_line(&buf, stdin, line_termination); - if (buf.eof) + if (strbuf_getline(&buf, stdin, line_termination) == EOF) break; if (line_termination && buf.buf[0] == '"') path_name = unquote_c_style(buf.buf, NULL); @@ -292,6 +290,7 @@ int cmd_checkout_index(int argc, const char **argv, const char *prefix) if (path_name != buf.buf) free(path_name); } + strbuf_release(&buf); } if (all) diff --git a/builtin-update-index.c b/builtin-update-index.c index 1091f1b..45e33f5 100644 --- a/builtin-update-index.c +++ b/builtin-update-index.c @@ -327,8 +327,7 @@ static void read_index_info(int line_termination) * This format is to put higher order stages into the * index file and matches git-ls-files --stage output. */ - read_line(&buf, stdin, line_termination); - if (buf.eof) + if (strbuf_getline(&buf, stdin, line_termination) == EOF) break; errno = 0; @@ -391,6 +390,7 @@ static void read_index_info(int line_termination) bad_line: die("malformed index info %s", buf.buf); } + strbuf_release(&buf); } static const char update_index_usage[] = @@ -719,8 +719,7 @@ int cmd_update_index(int argc, const char **argv, const char *prefix) while (1) { char *path_name; const char *p; - read_line(&buf, stdin, line_termination); - if (buf.eof) + if (strbuf_getline(&buf, stdin, line_termination) == EOF) break; if (line_termination && buf.buf[0] == '"') path_name = unquote_c_style(buf.buf, NULL); @@ -735,6 +734,7 @@ int cmd_update_index(int argc, const char **argv, const char *prefix) if (path_name != buf.buf) free(path_name); } + strbuf_release(&buf); } finish: diff --git a/fast-import.c b/fast-import.c index 1866d34..da04566 100644 --- a/fast-import.c +++ b/fast-import.c @@ -1584,20 +1584,25 @@ static void dump_marks(void) mark_file, strerror(errno)); } -static void read_next_command(void) +static int read_next_command(void) { + static int stdin_eof = 0; + + if (stdin_eof) { + unread_command_buf = 0; + return EOF; + } + do { if (unread_command_buf) { unread_command_buf = 0; - if (command_buf.eof) - return; } else { struct recent_command *rc; strbuf_detach(&command_buf); - read_line(&command_buf, stdin, '\n'); - if (command_buf.eof) - return; + stdin_eof = strbuf_getline(&command_buf, stdin, '\n'); + if (stdin_eof) + return EOF; rc = rc_free; if (rc) @@ -1616,6 +1621,8 @@ static void read_next_command(void) cmd_tail = rc; } } while (command_buf.buf[0] == '#'); + + return 0; } static void skip_optional_lf(void) @@ -1648,8 +1655,7 @@ static void *cmd_data (size_t *size) size_t term_len = command_buf.len - 5 - 2; for (;;) { - read_line(&command_buf, stdin, '\n'); - if (command_buf.eof) + if (strbuf_getline(&command_buf, stdin, '\n') == EOF) die("EOF in data (terminator '%s' not found)", term); if (term_len == command_buf.len && !strcmp(term, command_buf.buf)) @@ -2095,7 +2101,7 @@ static void cmd_new_commit(void) } /* file_change* */ - while (!command_buf.eof && command_buf.len > 0) { + while (command_buf.len > 0) { if (!prefixcmp(command_buf.buf, "M ")) file_change_m(b); else if (!prefixcmp(command_buf.buf, "D ")) @@ -2110,7 +2116,8 @@ static void cmd_new_commit(void) unread_command_buf = 1; break; } - read_next_command(); + if (read_next_command() == EOF) + break; } /* build the tree and the commit */ @@ -2375,11 +2382,8 @@ int main(int argc, const char **argv) prepare_packed_git(); start_packfile(); set_die_routine(die_nicely); - for (;;) { - read_next_command(); - if (command_buf.eof) - break; - else if (!strcmp("blob", command_buf.buf)) + while (read_next_command() != EOF) { + if (!strcmp("blob", command_buf.buf)) cmd_new_blob(); else if (!prefixcmp(command_buf.buf, "commit ")) cmd_new_commit(); diff --git a/fetch.c b/fetch.c index c256e6f..b1c1f07 100644 --- a/fetch.c +++ b/fetch.c @@ -222,8 +222,7 @@ int pull_targets_stdin(char ***target, const char ***write_ref) char *rf_one = NULL; char *tg_one; - read_line(&buf, stdin, '\n'); - if (buf.eof) + if (strbuf_getline(&buf, stdin, '\n') == EOF) break; tg_one = buf.buf; rf_one = strchr(tg_one, '\t'); @@ -239,6 +238,7 @@ int pull_targets_stdin(char ***target, const char ***write_ref) (*write_ref)[targets] = rf_one ? xstrdup(rf_one) : NULL; targets++; } + strbuf_release(&buf); return targets; } diff --git a/mktree.c b/mktree.c index 5dab4bd..9c137de 100644 --- a/mktree.c +++ b/mktree.c @@ -88,8 +88,7 @@ int main(int ac, char **av) enum object_type type; char *path; - read_line(&sb, stdin, line_termination); - if (sb.eof) + if (strbuf_getline(&sb, stdin, line_termination) == EOF) break; ptr = sb.buf; /* Input is non-recursive ls-tree output format @@ -121,6 +120,7 @@ int main(int ac, char **av) if (path != ntr) free(path); } + strbuf_release(&sb); write_tree(sha1); puts(sha1_to_hex(sha1)); exit(0); diff --git a/strbuf.c b/strbuf.c index c5f9e2a..59383ac 100644 --- a/strbuf.c +++ b/strbuf.c @@ -17,7 +17,6 @@ void strbuf_reset(struct strbuf *sb) { if (sb->len) strbuf_setlen(sb, 0); - sb->eof = 0; } char *strbuf_detach(struct strbuf *sb) @@ -145,14 +144,13 @@ ssize_t strbuf_read(struct strbuf *sb, int fd, size_t hint) return sb->len - oldlen; } -void read_line(struct strbuf *sb, FILE *fp, int term) +int strbuf_getline(struct strbuf *sb, FILE *fp, int term) { int ch; - if (feof(fp)) { - strbuf_release(sb); - sb->eof = 1; - return; - } + + strbuf_grow(sb, 0); + if (feof(fp)) + return EOF; strbuf_reset(sb); while ((ch = fgetc(fp)) != EOF) { @@ -161,11 +159,9 @@ void read_line(struct strbuf *sb, FILE *fp, int term) strbuf_grow(sb, 1); sb->buf[sb->len++] = ch; } - if (ch == EOF && sb->len == 0) { - strbuf_release(sb); - sb->eof = 1; - } + if (ch == EOF && sb->len == 0) + return EOF; - strbuf_grow(sb, 1); sb->buf[sb->len] = '\0'; + return 0; } diff --git a/strbuf.h b/strbuf.h index f163c63..b2cbd97 100644 --- a/strbuf.h +++ b/strbuf.h @@ -44,11 +44,10 @@ struct strbuf { size_t alloc; size_t len; - int eof; char *buf; }; -#define STRBUF_INIT { 0, 0, 0, NULL } +#define STRBUF_INIT { 0, 0, NULL } /*----- strbuf life cycle -----*/ extern void strbuf_init(struct strbuf *, size_t); @@ -101,6 +100,6 @@ extern size_t strbuf_fread(struct strbuf *, size_t, FILE *); /* XXX: if read fails, any partial read is undone */ extern ssize_t strbuf_read(struct strbuf *, int fd, size_t hint); -extern void read_line(struct strbuf *, FILE *, int); +extern int strbuf_getline(struct strbuf *, FILE *, int); #endif /* STRBUF_H */ -- cgit v0.10.2-6-g49f6 From eec813cfc6409a1b72399acf7ac08283faad7b8f Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Mon, 17 Sep 2007 13:48:17 +0200 Subject: fast-import was using dbuf's, replace them with strbuf's. Signed-off-by: Pierre Habouzit Signed-off-by: Junio C Hamano diff --git a/fast-import.c b/fast-import.c index da04566..e456eab 100644 --- a/fast-import.c +++ b/fast-import.c @@ -250,12 +250,6 @@ struct tag unsigned char sha1[20]; }; -struct dbuf -{ - void *buffer; - size_t capacity; -}; - struct hash_list { struct hash_list *next; @@ -323,8 +317,8 @@ static unsigned int tree_entry_alloc = 1000; static void *avail_tree_entry; static unsigned int avail_tree_table_sz = 100; static struct avail_tree_content **avail_tree_table; -static struct dbuf old_tree; -static struct dbuf new_tree; +static struct strbuf old_tree = STRBUF_INIT; +static struct strbuf new_tree = STRBUF_INIT; /* Branch data */ static unsigned long max_active_branches = 5; @@ -346,7 +340,7 @@ static struct recent_command *cmd_tail = &cmd_hist; static struct recent_command *rc_free; static unsigned int cmd_save = 100; static uintmax_t next_mark; -static struct dbuf new_data; +static struct strbuf new_data = STRBUF_INIT; static void write_branch_report(FILE *rpt, struct branch *b) { @@ -566,17 +560,6 @@ static char *pool_strdup(const char *s) return r; } -static void size_dbuf(struct dbuf *b, size_t maxlen) -{ - if (b->buffer) { - if (b->capacity >= maxlen) - return; - free(b->buffer); - } - b->capacity = ((maxlen / 1024) + 1) * 1024; - b->buffer = xmalloc(b->capacity); -} - static void insert_mark(uintmax_t idnum, struct object_entry *oe) { struct mark_set *s = marks; @@ -1005,8 +988,7 @@ static size_t encode_header( static int store_object( enum object_type type, - void *dat, - size_t datlen, + struct strbuf *dat, struct last_object *last, unsigned char *sha1out, uintmax_t mark) @@ -1020,10 +1002,10 @@ static int store_object( z_stream s; hdrlen = sprintf((char*)hdr,"%s %lu", typename(type), - (unsigned long)datlen) + 1; + (unsigned long)dat->len) + 1; SHA1_Init(&c); SHA1_Update(&c, hdr, hdrlen); - SHA1_Update(&c, dat, datlen); + SHA1_Update(&c, dat->buf, dat->len); SHA1_Final(sha1, &c); if (sha1out) hashcpy(sha1out, sha1); @@ -1044,9 +1026,9 @@ static int store_object( if (last && last->data && last->depth < max_depth) { delta = diff_delta(last->data, last->len, - dat, datlen, + dat->buf, dat->len, &deltalen, 0); - if (delta && deltalen >= datlen) { + if (delta && deltalen >= dat->len) { free(delta); delta = NULL; } @@ -1059,8 +1041,8 @@ static int store_object( s.next_in = delta; s.avail_in = deltalen; } else { - s.next_in = dat; - s.avail_in = datlen; + s.next_in = (void *)dat->buf; + s.avail_in = dat->len; } s.avail_out = deflateBound(&s, s.avail_in); s.next_out = out = xmalloc(s.avail_out); @@ -1083,8 +1065,8 @@ static int store_object( memset(&s, 0, sizeof(s)); deflateInit(&s, zlib_compression_level); - s.next_in = dat; - s.avail_in = datlen; + s.next_in = (void *)dat->buf; + s.avail_in = dat->len; s.avail_out = deflateBound(&s, s.avail_in); s.next_out = out = xrealloc(out, s.avail_out); while (deflate(&s, Z_FINISH) == Z_OK) @@ -1118,7 +1100,7 @@ static int store_object( } else { if (last) last->depth = 0; - hdrlen = encode_header(type, datlen, hdr); + hdrlen = encode_header(type, dat->len, hdr); write_or_die(pack_data->pack_fd, hdr, hdrlen); pack_size += hdrlen; } @@ -1131,9 +1113,9 @@ static int store_object( if (last) { if (!last->no_free) free(last->data); - last->data = dat; last->offset = e->offset; - last->len = datlen; + last->data = dat->buf; + last->len = dat->len; } return 0; } @@ -1229,14 +1211,10 @@ static int tecmp1 (const void *_a, const void *_b) b->name->str_dat, b->name->str_len, b->versions[1].mode); } -static void mktree(struct tree_content *t, - int v, - unsigned long *szp, - struct dbuf *b) +static void mktree(struct tree_content *t, int v, struct strbuf *b) { size_t maxlen = 0; unsigned int i; - char *c; if (!v) qsort(t->entries,t->entry_count,sizeof(t->entries[0]),tecmp0); @@ -1248,27 +1226,22 @@ static void mktree(struct tree_content *t, maxlen += t->entries[i]->name->str_len + 34; } - size_dbuf(b, maxlen); - c = b->buffer; + strbuf_reset(b); + strbuf_grow(b, maxlen); for (i = 0; i < t->entry_count; i++) { struct tree_entry *e = t->entries[i]; if (!e->versions[v].mode) continue; - c += sprintf(c, "%o", (unsigned int)e->versions[v].mode); - *c++ = ' '; - strcpy(c, e->name->str_dat); - c += e->name->str_len + 1; - hashcpy((unsigned char*)c, e->versions[v].sha1); - c += 20; + strbuf_addf(b, "%o %s%c", (unsigned int)e->versions[v].mode, + e->name->str_dat, '\0'); + strbuf_add(b, e->versions[v].sha1, 20); } - *szp = c - (char*)b->buffer; } static void store_tree(struct tree_entry *root) { struct tree_content *t = root->tree; unsigned int i, j, del; - unsigned long new_len; struct last_object lo; struct object_entry *le; @@ -1288,16 +1261,16 @@ static void store_tree(struct tree_entry *root) lo.depth = 0; lo.no_free = 0; } else { - mktree(t, 0, &lo.len, &old_tree); - lo.data = old_tree.buffer; + mktree(t, 0, &old_tree); + lo.len = old_tree.len; + lo.data = old_tree.buf; lo.offset = le->offset; lo.depth = t->delta_depth; lo.no_free = 1; } - mktree(t, 1, &new_len, &new_tree); - store_object(OBJ_TREE, new_tree.buffer, new_len, - &lo, root->versions[1].sha1, 0); + mktree(t, 1, &new_tree); + store_object(OBJ_TREE, &new_tree, &lo, root->versions[1].sha1, 0); t->delta_depth = lo.depth; for (i = 0, j = 0, del = 0; i < t->entry_count; i++) { @@ -1642,11 +1615,10 @@ static void cmd_mark(void) next_mark = 0; } -static void *cmd_data (size_t *size) +static void cmd_data(struct strbuf *sb) { - struct strbuf buffer; + strbuf_reset(sb); - strbuf_init(&buffer, 0); if (prefixcmp(command_buf.buf, "data ")) die("Expected 'data n' command, found: %s", command_buf.buf); @@ -1660,8 +1632,8 @@ static void *cmd_data (size_t *size) if (term_len == command_buf.len && !strcmp(term, command_buf.buf)) break; - strbuf_addbuf(&buffer, &command_buf); - strbuf_addch(&buffer, '\n'); + strbuf_addbuf(sb, &command_buf); + strbuf_addch(sb, '\n'); } free(term); } @@ -1671,7 +1643,7 @@ static void *cmd_data (size_t *size) length = strtoul(command_buf.buf + 5, NULL, 10); while (n < length) { - size_t s = strbuf_fread(&buffer, length - n, stdin); + size_t s = strbuf_fread(sb, length - n, stdin); if (!s && feof(stdin)) die("EOF in data (%lu bytes remaining)", (unsigned long)(length - n)); @@ -1680,8 +1652,6 @@ static void *cmd_data (size_t *size) } skip_optional_lf(); - *size = buffer.len; - return strbuf_detach(&buffer); } static int validate_raw_date(const char *src, char *result, int maxlen) @@ -1744,15 +1714,14 @@ static char *parse_ident(const char *buf) static void cmd_new_blob(void) { - size_t l; - void *d; + struct strbuf buf; read_next_command(); cmd_mark(); - d = cmd_data(&l); - - if (store_object(OBJ_BLOB, d, l, &last_blob, NULL, next_mark)) - free(d); + strbuf_init(&buf, 0); + cmd_data(&buf); + if (store_object(OBJ_BLOB, &buf, &last_blob, NULL, next_mark)) + strbuf_release(&buf); } static void unload_one_branch(void) @@ -1848,14 +1817,15 @@ static void file_change_m(struct branch *b) } if (inline_data) { - size_t l; - void *d; + struct strbuf buf; + if (!p_uq) p = p_uq = xstrdup(p); read_next_command(); - d = cmd_data(&l); - if (store_object(OBJ_BLOB, d, l, &last_blob, sha1, 0)) - free(d); + strbuf_init(&buf, 0); + cmd_data(&buf); + if (store_object(OBJ_BLOB, &buf, &last_blob, sha1, 0)) + strbuf_release(&buf); } else if (oe) { if (oe->type != OBJ_BLOB) die("Not a blob (actually a %s): %s", @@ -2062,9 +2032,8 @@ static struct hash_list *cmd_merge(unsigned int *count) static void cmd_new_commit(void) { + static struct strbuf msg = STRBUF_INIT; struct branch *b; - void *msg; - size_t msglen; char *sp; char *author = NULL; char *committer = NULL; @@ -2089,7 +2058,7 @@ static void cmd_new_commit(void) } if (!committer) die("Expected committer but didn't get one"); - msg = cmd_data(&msglen); + cmd_data(&msg); read_next_command(); cmd_from(b); merge_list = cmd_merge(&merge_count); @@ -2124,46 +2093,39 @@ static void cmd_new_commit(void) store_tree(&b->branch_tree); hashcpy(b->branch_tree.versions[0].sha1, b->branch_tree.versions[1].sha1); - size_dbuf(&new_data, 114 + msglen - + merge_count * 49 - + (author - ? strlen(author) + strlen(committer) - : 2 * strlen(committer))); - sp = new_data.buffer; - sp += sprintf(sp, "tree %s\n", + + strbuf_reset(&new_data); + strbuf_addf(&new_data, "tree %s\n", sha1_to_hex(b->branch_tree.versions[1].sha1)); if (!is_null_sha1(b->sha1)) - sp += sprintf(sp, "parent %s\n", sha1_to_hex(b->sha1)); + strbuf_addf(&new_data, "parent %s\n", sha1_to_hex(b->sha1)); while (merge_list) { struct hash_list *next = merge_list->next; - sp += sprintf(sp, "parent %s\n", sha1_to_hex(merge_list->sha1)); + strbuf_addf(&new_data, "parent %s\n", sha1_to_hex(merge_list->sha1)); free(merge_list); merge_list = next; } - sp += sprintf(sp, "author %s\n", author ? author : committer); - sp += sprintf(sp, "committer %s\n", committer); - *sp++ = '\n'; - memcpy(sp, msg, msglen); - sp += msglen; + strbuf_addf(&new_data, + "author %s\n" + "committer %s\n" + "\n", + author ? author : committer, committer); + strbuf_addbuf(&new_data, &msg); free(author); free(committer); - free(msg); - if (!store_object(OBJ_COMMIT, - new_data.buffer, sp - (char*)new_data.buffer, - NULL, b->sha1, next_mark)) + if (!store_object(OBJ_COMMIT, &new_data, NULL, b->sha1, next_mark)) b->pack_id = pack_id; b->last_commit = object_count_by_type[OBJ_COMMIT]; } static void cmd_new_tag(void) { + static struct strbuf msg = STRBUF_INIT; char *sp; const char *from; char *tagger; struct branch *s; - void *msg; - size_t msglen; struct tag *t; uintmax_t from_mark = 0; unsigned char sha1[20]; @@ -2214,24 +2176,21 @@ static void cmd_new_tag(void) /* tag payload/message */ read_next_command(); - msg = cmd_data(&msglen); + cmd_data(&msg); /* build the tag object */ - size_dbuf(&new_data, 67+strlen(t->name)+strlen(tagger)+msglen); - sp = new_data.buffer; - sp += sprintf(sp, "object %s\n", sha1_to_hex(sha1)); - sp += sprintf(sp, "type %s\n", commit_type); - sp += sprintf(sp, "tag %s\n", t->name); - sp += sprintf(sp, "tagger %s\n", tagger); - *sp++ = '\n'; - memcpy(sp, msg, msglen); - sp += msglen; + strbuf_reset(&new_data); + strbuf_addf(&new_data, + "object %s\n" + "type %s\n" + "tag %s\n" + "tagger %s\n" + "\n", + sha1_to_hex(sha1), commit_type, t->name, tagger); + strbuf_addbuf(&new_data, &msg); free(tagger); - free(msg); - if (store_object(OBJ_TAG, new_data.buffer, - sp - (char*)new_data.buffer, - NULL, t->sha1, 0)) + if (store_object(OBJ_TAG, &new_data, NULL, t->sha1, 0)) t->pack_id = MAX_PACK_ID; else t->pack_id = pack_id; -- cgit v0.10.2-6-g49f6 From 0557656930d41f10c90bccf90e3c5bd87bd53661 Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Mon, 17 Sep 2007 14:00:38 +0200 Subject: fast-import optimization: Now that cmd_data acts on a strbuf, make last_object stashed buffer be a strbuf as well. On new stash, don't free the last stashed buffer, rather swap it with the one you will stash, this way, callers of store_object can act on static strbufs, and at some point, fast-import won't allocate new memory for objects buffers. Signed-off-by: Junio C Hamano diff --git a/fast-import.c b/fast-import.c index e456eab..e2a4834 100644 --- a/fast-import.c +++ b/fast-import.c @@ -182,11 +182,10 @@ struct mark_set struct last_object { - void *data; - unsigned long len; + struct strbuf data; uint32_t offset; unsigned int depth; - unsigned no_free:1; + unsigned no_swap : 1; }; struct mem_pool @@ -310,7 +309,7 @@ static struct mark_set *marks; static const char* mark_file; /* Our last blob */ -static struct last_object last_blob; +static struct last_object last_blob = { STRBUF_INIT, 0, 0, 0 }; /* Tree management */ static unsigned int tree_entry_alloc = 1000; @@ -950,9 +949,7 @@ static void end_packfile(void) free(old_p); /* We can't carry a delta across packfiles. */ - free(last_blob.data); - last_blob.data = NULL; - last_blob.len = 0; + strbuf_release(&last_blob.data); last_blob.offset = 0; last_blob.depth = 0; } @@ -1024,8 +1021,8 @@ static int store_object( return 1; } - if (last && last->data && last->depth < max_depth) { - delta = diff_delta(last->data, last->len, + if (last && last->data.buf && last->depth < max_depth) { + delta = diff_delta(last->data.buf, last->data.len, dat->buf, dat->len, &deltalen, 0); if (delta && deltalen >= dat->len) { @@ -1111,11 +1108,14 @@ static int store_object( free(out); free(delta); if (last) { - if (!last->no_free) - free(last->data); + if (last->no_swap) { + last->data = *dat; + } else { + struct strbuf tmp = *dat; + *dat = last->data; + last->data = tmp; + } last->offset = e->offset; - last->data = dat->buf; - last->len = dat->len; } return 0; } @@ -1242,7 +1242,7 @@ static void store_tree(struct tree_entry *root) { struct tree_content *t = root->tree; unsigned int i, j, del; - struct last_object lo; + struct last_object lo = { STRBUF_INIT, 0, 0, /* no_swap */ 1 }; struct object_entry *le; if (!is_null_sha1(root->versions[1].sha1)) @@ -1254,19 +1254,11 @@ static void store_tree(struct tree_entry *root) } le = find_object(root->versions[0].sha1); - if (!S_ISDIR(root->versions[0].mode) - || !le - || le->pack_id != pack_id) { - lo.data = NULL; - lo.depth = 0; - lo.no_free = 0; - } else { + if (S_ISDIR(root->versions[0].mode) && le && le->pack_id == pack_id) { mktree(t, 0, &old_tree); - lo.len = old_tree.len; - lo.data = old_tree.buf; + lo.data = old_tree; lo.offset = le->offset; lo.depth = t->delta_depth; - lo.no_free = 1; } mktree(t, 1, &new_tree); @@ -1714,14 +1706,12 @@ static char *parse_ident(const char *buf) static void cmd_new_blob(void) { - struct strbuf buf; + static struct strbuf buf = STRBUF_INIT; read_next_command(); cmd_mark(); - strbuf_init(&buf, 0); cmd_data(&buf); - if (store_object(OBJ_BLOB, &buf, &last_blob, NULL, next_mark)) - strbuf_release(&buf); + store_object(OBJ_BLOB, &buf, &last_blob, NULL, next_mark); } static void unload_one_branch(void) @@ -1817,15 +1807,13 @@ static void file_change_m(struct branch *b) } if (inline_data) { - struct strbuf buf; + static struct strbuf buf = STRBUF_INIT; if (!p_uq) p = p_uq = xstrdup(p); read_next_command(); - strbuf_init(&buf, 0); cmd_data(&buf); - if (store_object(OBJ_BLOB, &buf, &last_blob, sha1, 0)) - strbuf_release(&buf); + store_object(OBJ_BLOB, &buf, &last_blob, sha1, 0); } else if (oe) { if (oe->type != OBJ_BLOB) die("Not a blob (actually a %s): %s", -- cgit v0.10.2-6-g49f6 From 68d3025a805097ec148ec6e9b0b54a5db1ef138e Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Sat, 15 Sep 2007 23:53:05 +0200 Subject: Add xmemdupz() that duplicates a block of memory, and NUL terminates it. A lot of places in git's code use code like: char *res; len = ... find length of an interesting segment in src ...; res = xmalloc(len + 1); memcpy(res, src, len); res[len] = '\0'; return res; A new function xmemdupz() captures the allocation, copy and NUL termination. Existing xstrndup() is reimplemented in terms of this new function. Signed-off-by: Pierre Habouzit Signed-off-by: Junio C Hamano diff --git a/git-compat-util.h b/git-compat-util.h index 1bfbdeb..f23d934 100644 --- a/git-compat-util.h +++ b/git-compat-util.h @@ -211,19 +211,20 @@ static inline void *xmalloc(size_t size) return ret; } -static inline char *xstrndup(const char *str, size_t len) +static inline void *xmemdupz(const void *data, size_t len) { - char *p; - - p = memchr(str, '\0', len); - if (p) - len = p - str; - p = xmalloc(len + 1); - memcpy(p, str, len); + char *p = xmalloc(len + 1); + memcpy(p, data, len); p[len] = '\0'; return p; } +static inline char *xstrndup(const char *str, size_t len) +{ + char *p = memchr(str, '\0', len); + return xmemdupz(str, p ? p - str : len); +} + static inline void *xrealloc(void *ptr, size_t size) { void *ret = realloc(ptr, size); -- cgit v0.10.2-6-g49f6 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 diff --git a/attr.c b/attr.c index 1293993..92704a3 100644 --- a/attr.c +++ b/attr.c @@ -160,12 +160,7 @@ static const char *parse_attr(const char *src, int lineno, const char *cp, else if (!equals) e->setto = ATTR__TRUE; else { - char *value; - int vallen = ep - equals; - value = xmalloc(vallen); - memcpy(value, equals+1, vallen-1); - value[vallen-1] = 0; - e->setto = value; + e->setto = xmemdupz(equals + 1, ep - equals - 1); } e->attr = git_attr(cp, len); } diff --git a/builtin-add.c b/builtin-add.c index 0d7d0ce..f9a6580 100644 --- a/builtin-add.c +++ b/builtin-add.c @@ -71,12 +71,8 @@ static void fill_directory(struct dir_struct *dir, const char **pathspec, baselen = common_prefix(pathspec); path = "."; base = ""; - if (baselen) { - char *common = xmalloc(baselen + 1); - memcpy(common, *pathspec, baselen); - common[baselen] = 0; - path = base = common; - } + if (baselen) + path = base = xmemdupz(*pathspec, baselen); /* Read the directory and prune it */ read_directory(dir, path, base, baselen, pathspec); diff --git a/builtin-apply.c b/builtin-apply.c index f953c5b..512c9b6 100644 --- a/builtin-apply.c +++ b/builtin-apply.c @@ -293,11 +293,7 @@ static char *find_name(const char *line, char *def, int p_value, int terminate) return def; } - name = xmalloc(len + 1); - memcpy(name, start, len); - name[len] = 0; - free(def); - return name; + return xmemdupz(start, len); } static int count_slashes(const char *cp) @@ -687,10 +683,7 @@ static char *git_header_name(char *line, int llen) break; } if (second[len] == '\n' && !memcmp(name, second, len)) { - char *ret = xmalloc(len + 1); - memcpy(ret, name, len); - ret[len] = 0; - return ret; + return xmemdupz(name, len); } } } diff --git a/builtin-fetch--tool.c b/builtin-fetch--tool.c index 514a3cc..349b59c 100644 --- a/builtin-fetch--tool.c +++ b/builtin-fetch--tool.c @@ -222,19 +222,15 @@ static char *find_local_name(const char *remote_name, const char *refs, } if (!strncmp(remote_name, ref, len) && ref[len] == ':') { const char *local_part = ref + len + 1; - char *ret; int retlen; if (!next) retlen = strlen(local_part); else retlen = next - local_part; - ret = xmalloc(retlen + 1); - memcpy(ret, local_part, retlen); - ret[retlen] = 0; *force_p = single_force; *not_for_merge_p = not_for_merge; - return ret; + return xmemdupz(local_part, retlen); } ref = next; } diff --git a/builtin-fmt-merge-msg.c b/builtin-fmt-merge-msg.c index ae60fcc..8a3c962 100644 --- a/builtin-fmt-merge-msg.c +++ b/builtin-fmt-merge-msg.c @@ -140,12 +140,10 @@ static int handle_line(char *line) if (!strcmp(".", src) || !strcmp(src, origin)) { int len = strlen(origin); if (origin[0] == '\'' && origin[len - 1] == '\'') { - char *new_origin = xmalloc(len - 1); - memcpy(new_origin, origin + 1, len - 2); - new_origin[len - 2] = 0; - origin = new_origin; - } else + origin = xmemdupz(origin + 1, len - 2); + } else { origin = xstrdup(origin); + } } else { char *new_origin = xmalloc(strlen(origin) + strlen(src) + 5); sprintf(new_origin, "%s of %s", origin, src); @@ -211,14 +209,11 @@ static void shortlog(const char *name, unsigned char *sha1, bol += 2; eol = strchr(bol, '\n'); - if (eol) { - int len = eol - bol; - oneline = xmalloc(len + 1); - memcpy(oneline, bol, len); - oneline[len] = 0; - } else + oneline = xmemdupz(bol, eol - bol); + } else { oneline = xstrdup(bol); + } append_to_list(&subjects, oneline, NULL); } diff --git a/builtin-for-each-ref.c b/builtin-for-each-ref.c index 0afa1c5..725c1df 100644 --- a/builtin-for-each-ref.c +++ b/builtin-for-each-ref.c @@ -87,7 +87,6 @@ static int used_atom_cnt, sort_atom_limit, need_tagged; static int parse_atom(const char *atom, const char *ep) { const char *sp; - char *n; int i, at; sp = atom; @@ -120,10 +119,7 @@ static int parse_atom(const char *atom, const char *ep) (sizeof *used_atom) * used_atom_cnt); used_atom_type = xrealloc(used_atom_type, (sizeof(*used_atom_type) * used_atom_cnt)); - n = xmalloc(ep - atom + 1); - memcpy(n, atom, ep - atom); - n[ep-atom] = 0; - used_atom[at] = n; + used_atom[at] = xmemdupz(atom, ep - atom); used_atom_type[at] = valid_atom[i].cmp_type; return at; } @@ -305,46 +301,28 @@ static const char *find_wholine(const char *who, int wholen, const char *buf, un static const char *copy_line(const char *buf) { const char *eol = strchr(buf, '\n'); - char *line; - int len; if (!eol) return ""; - len = eol - buf; - line = xmalloc(len + 1); - memcpy(line, buf, len); - line[len] = 0; - return line; + return xmemdupz(buf, eol - buf); } static const char *copy_name(const char *buf) { - const char *eol = strchr(buf, '\n'); - const char *eoname = strstr(buf, " <"); - char *line; - int len; - if (!(eoname && eol && eoname < eol)) - return ""; - len = eoname - buf; - line = xmalloc(len + 1); - memcpy(line, buf, len); - line[len] = 0; - return line; + const char *cp; + for (cp = buf; *cp != '\n'; cp++) { + if (!strncmp(cp, " <", 2)) + return xmemdupz(buf, cp - buf); + } + return ""; } static const char *copy_email(const char *buf) { const char *email = strchr(buf, '<'); const char *eoemail = strchr(email, '>'); - char *line; - int len; if (!email || !eoemail) return ""; - eoemail++; - len = eoemail - email; - line = xmalloc(len + 1); - memcpy(line, email, len); - line[len] = 0; - return line; + return xmemdupz(email, eoemail + 1 - email); } static void grab_date(const char *buf, struct atom_value *v) diff --git a/builtin-log.c b/builtin-log.c index 60819d1..e8b982d 100644 --- a/builtin-log.c +++ b/builtin-log.c @@ -441,8 +441,6 @@ static const char *clean_message_id(const char *msg_id) { char ch; const char *a, *z, *m; - char *n; - size_t len; m = msg_id; while ((ch = *m) && (isspace(ch) || (ch == '<'))) @@ -458,11 +456,7 @@ static const char *clean_message_id(const char *msg_id) die("insane in-reply-to: %s", msg_id); if (++z == m) return a; - len = z - a; - n = xmalloc(len + 1); - memcpy(n, a, len); - n[len] = 0; - return n; + return xmemdupz(a, z - a); } int cmd_format_patch(int argc, const char **argv, const char *prefix) @@ -541,9 +535,7 @@ int cmd_format_patch(int argc, const char **argv, const char *prefix) endpos = strchr(committer, '>'); if (!endpos) die("bogos committer info %s\n", committer); - add_signoff = xmalloc(endpos - committer + 2); - memcpy(add_signoff, committer, endpos - committer + 1); - add_signoff[endpos - committer + 1] = 0; + add_signoff = xmemdupz(committer, endpos - committer + 1); } else if (!strcmp(argv[i], "--attach")) { rev.mime_boundary = git_version_string; diff --git a/builtin-ls-files.c b/builtin-ls-files.c index 6c1db86..48dd3f7 100644 --- a/builtin-ls-files.c +++ b/builtin-ls-files.c @@ -299,7 +299,6 @@ static void prune_cache(const char *prefix) static const char *verify_pathspec(const char *prefix) { const char **p, *n, *prev; - char *real_prefix; unsigned long max; prev = NULL; @@ -326,14 +325,8 @@ static const char *verify_pathspec(const char *prefix) if (prefix_offset > max || memcmp(prev, prefix, prefix_offset)) die("git-ls-files: cannot generate relative filenames containing '..'"); - real_prefix = NULL; prefix_len = max; - if (max) { - real_prefix = xmalloc(max + 1); - memcpy(real_prefix, prev, max); - real_prefix[max] = 0; - } - return real_prefix; + return max ? xmemdupz(prev, max) : NULL; } /* diff --git a/builtin-mv.c b/builtin-mv.c index b95b7d2..b944651 100644 --- a/builtin-mv.c +++ b/builtin-mv.c @@ -22,10 +22,7 @@ static const char **copy_pathspec(const char *prefix, const char **pathspec, for (i = 0; i < count; i++) { int length = strlen(result[i]); if (length > 0 && result[i][length - 1] == '/') { - char *without_slash = xmalloc(length); - memcpy(without_slash, result[i], length - 1); - without_slash[length - 1] = '\0'; - result[i] = without_slash; + result[i] = xmemdupz(result[i], length - 1); } if (base_name) { const char *last_slash = strrchr(result[i], '/'); diff --git a/builtin-revert.c b/builtin-revert.c index 499bbe7..a655c8e 100644 --- a/builtin-revert.c +++ b/builtin-revert.c @@ -168,9 +168,7 @@ static void set_author_ident_env(const char *message) char *line, *pend, *email, *timestamp; p += 7; - line = xmalloc(eol + 1 - p); - memcpy(line, p, eol - p); - line[eol - p] = '\0'; + line = xmemdupz(p, eol - p); email = strchr(line, '<'); if (!email) die ("Could not extract author email from %s", diff --git a/builtin-shortlog.c b/builtin-shortlog.c index 16af619..3fe7546 100644 --- a/builtin-shortlog.c +++ b/builtin-shortlog.c @@ -39,10 +39,7 @@ static void insert_author_oneline(struct path_list *list, while (authorlen > 0 && isspace(author[authorlen - 1])) authorlen--; - buffer = xmalloc(authorlen + 1); - memcpy(buffer, author, authorlen); - buffer[authorlen] = '\0'; - + buffer = xmemdupz(author, authorlen); item = path_list_insert(buffer, list); if (item->util == NULL) item->util = xcalloc(1, sizeof(struct path_list)); @@ -66,13 +63,9 @@ static void insert_author_oneline(struct path_list *list, oneline++; onelinelen--; } - while (onelinelen > 0 && isspace(oneline[onelinelen - 1])) onelinelen--; - - buffer = xmalloc(onelinelen + 1); - memcpy(buffer, oneline, onelinelen); - buffer[onelinelen] = '\0'; + buffer = xmemdupz(oneline, onelinelen); if (dot3) { int dot3len = strlen(dot3); diff --git a/commit.c b/commit.c index 85889f9..f86fa77 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]) diff --git a/connect.c b/connect.c index 8b1e993..1653a0e 100644 --- a/connect.c +++ b/connect.c @@ -393,9 +393,7 @@ static int git_proxy_command_options(const char *var, const char *value) if (matchlen == 4 && !memcmp(value, "none", 4)) matchlen = 0; - git_proxy_command = xmalloc(matchlen + 1); - memcpy(git_proxy_command, value, matchlen); - git_proxy_command[matchlen] = 0; + git_proxy_command = xmemdupz(value, matchlen); } return 0; } diff --git a/convert.c b/convert.c index 508d30b..79c9df2 100644 --- a/convert.c +++ b/convert.c @@ -323,13 +323,8 @@ 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); } diff --git a/diff.c b/diff.c index a5b69ed..2216d75 100644 --- a/diff.c +++ b/diff.c @@ -83,13 +83,8 @@ static int parse_lldiff_command(const char *var, const char *ep, const char *val if (!strncmp(drv->name, name, namelen) && !drv->name[namelen]) break; if (!drv) { - char *namebuf; drv = xcalloc(1, sizeof(struct ll_diff_driver)); - namebuf = xmalloc(namelen + 1); - memcpy(namebuf, name, namelen); - namebuf[namelen] = 0; - drv->name = namebuf; - drv->next = NULL; + drv->name = xmemdupz(name, namelen); if (!user_diff_tail) user_diff_tail = &user_diff; *user_diff_tail = drv; @@ -126,12 +121,8 @@ static int parse_funcname_pattern(const char *var, const char *ep, const char *v if (!strncmp(pp->name, name, namelen) && !pp->name[namelen]) break; if (!pp) { - char *namebuf; pp = xcalloc(1, sizeof(*pp)); - namebuf = xmalloc(namelen + 1); - memcpy(namebuf, name, namelen); - namebuf[namelen] = 0; - pp->name = namebuf; + pp->name = xmemdupz(name, namelen); pp->next = funcname_pattern_list; funcname_pattern_list = pp; } diff --git a/diffcore-order.c b/diffcore-order.c index 2a4bd82..23e9385 100644 --- a/diffcore-order.c +++ b/diffcore-order.c @@ -48,11 +48,8 @@ static void prepare_order(const char *orderfile) if (*ep == '\n') { *ep = 0; order[cnt] = cp; - } - else { - order[cnt] = xmalloc(ep-cp+1); - memcpy(order[cnt], cp, ep-cp); - order[cnt][ep-cp] = 0; + } else { + order[cnt] = xmemdupz(cp, ep - cp); } cnt++; } diff --git a/fast-import.c b/fast-import.c index e2a4834..f990658 100644 --- a/fast-import.c +++ b/fast-import.c @@ -1864,9 +1864,7 @@ static void file_change_cr(struct branch *b, int rename) endp = strchr(s, ' '); if (!endp) die("Missing space after source: %s", command_buf.buf); - s_uq = xmalloc(endp - s + 1); - memcpy(s_uq, s, endp - s); - s_uq[endp - s] = 0; + s_uq = xmemdupz(s, endp - s); } s = s_uq; diff --git a/http-push.c b/http-push.c index 7c3720f..276e1eb 100644 --- a/http-push.c +++ b/http-push.c @@ -1271,10 +1271,7 @@ xml_cdata(void *userData, const XML_Char *s, int len) { struct xml_ctx *ctx = (struct xml_ctx *)userData; free(ctx->cdata); - ctx->cdata = xmalloc(len + 1); - /* NB: 's' is not null-terminated, can not use strlcpy here */ - memcpy(ctx->cdata, s, len); - ctx->cdata[len] = '\0'; + ctx->cdata = xmemdupz(s, len); } static struct remote_lock *lock_remote(const char *path, long timeout) @@ -2172,9 +2169,7 @@ static void fetch_symref(const char *path, char **symref, unsigned char *sha1) /* If it's a symref, set the refname; otherwise try for a sha1 */ if (!prefixcmp((char *)buffer.buffer, "ref: ")) { - *symref = xmalloc(buffer.posn - 5); - memcpy(*symref, (char *)buffer.buffer + 5, buffer.posn - 6); - (*symref)[buffer.posn - 6] = '\0'; + *symref = xmemdupz((char *)buffer.buffer + 5, buffer.posn - 6); } else { get_sha1_hex(buffer.buffer, sha1); } diff --git a/imap-send.c b/imap-send.c index 86e4a0f..905d097 100644 --- a/imap-send.c +++ b/imap-send.c @@ -623,9 +623,7 @@ parse_imap_list_l( imap_t *imap, char **sp, list_t **curp, int level ) goto bail; cur->len = s - p; s++; - cur->val = xmalloc( cur->len + 1 ); - memcpy( cur->val, p, cur->len ); - cur->val[cur->len] = 0; + cur->val = xmemdupz(p, cur->len); } else { /* atom */ p = s; @@ -633,12 +631,10 @@ parse_imap_list_l( imap_t *imap, char **sp, list_t **curp, int level ) if (level && *s == ')') break; cur->len = s - p; - if (cur->len == 3 && !memcmp ("NIL", p, 3)) + if (cur->len == 3 && !memcmp ("NIL", p, 3)) { cur->val = NIL; - else { - cur->val = xmalloc( cur->len + 1 ); - memcpy( cur->val, p, cur->len ); - cur->val[cur->len] = 0; + } else { + cur->val = xmemdupz(p, cur->len); } } @@ -1221,13 +1217,7 @@ split_msg( msg_data_t *all_msgs, msg_data_t *msg, int *ofs ) if (p) msg->len = &p[1] - data; - msg->data = xmalloc( msg->len + 1 ); - if (!msg->data) - return 0; - - memcpy( msg->data, data, msg->len ); - msg->data[ msg->len ] = 0; - + msg->data = xmemdupz(data, msg->len); *ofs += msg->len; return 1; } diff --git a/merge-recursive.c b/merge-recursive.c index 19d5f3b..14b56c2 100644 --- a/merge-recursive.c +++ b/merge-recursive.c @@ -432,19 +432,15 @@ static int update_stages(const char *path, struct diff_filespec *o, static int remove_path(const char *name) { - int ret, len; + int ret; char *slash, *dirs; ret = unlink(name); if (ret) return ret; - len = strlen(name); - dirs = xmalloc(len+1); - memcpy(dirs, name, len); - dirs[len] = '\0'; + dirs = xstrdup(name); while ((slash = strrchr(name, '/'))) { *slash = '\0'; - len = slash - name; if (rmdir(name) != 0) break; } @@ -578,9 +574,7 @@ static void update_file_flags(const unsigned char *sha, flush_buffer(fd, buf, size); close(fd); } else if (S_ISLNK(mode)) { - char *lnk = xmalloc(size + 1); - memcpy(lnk, buf, size); - lnk[size] = '\0'; + char *lnk = xmemdupz(buf, size); mkdir_p(path, 0777); unlink(path); symlink(lnk, path); @@ -872,14 +866,9 @@ static int read_merge_config(const char *var, const char *value) if (!strncmp(fn->name, name, namelen) && !fn->name[namelen]) break; if (!fn) { - char *namebuf; fn = xcalloc(1, sizeof(struct ll_merge_driver)); - namebuf = xmalloc(namelen + 1); - memcpy(namebuf, name, namelen); - namebuf[namelen] = 0; - fn->name = namebuf; + fn->name = xmemdupz(name, namelen); fn->fn = ll_ext_merge; - fn->next = NULL; *ll_user_merge_tail = fn; ll_user_merge_tail = &(fn->next); } diff --git a/refs.c b/refs.c index 7fb3350..07e260c 100644 --- a/refs.c +++ b/refs.c @@ -1246,15 +1246,11 @@ int create_symref(const char *ref_target, const char *refs_heads_master, static char *ref_msg(const char *line, const char *endp) { const char *ep; - char *msg; - line += 82; - for (ep = line; ep < endp && *ep != '\n'; ep++) - ; - msg = xmalloc(ep - line + 1); - memcpy(msg, line, ep - line); - msg[ep - line] = 0; - return msg; + ep = memchr(line, '\n', endp - line); + if (!ep) + ep = endp; + return xmemdupz(line, ep - line); } int read_ref_at(const char *ref, unsigned long at_time, int cnt, unsigned char *sha1, char **msg, unsigned long *cutoff_time, int *cutoff_tz, int *cutoff_cnt) diff --git a/sha1_file.c b/sha1_file.c index 59325d4..385c5d8 100644 --- a/sha1_file.c +++ b/sha1_file.c @@ -1491,11 +1491,8 @@ found_cache_entry: ent->lru.next->prev = ent->lru.prev; ent->lru.prev->next = ent->lru.next; delta_base_cached -= ent->size; - } - else { - ret = xmalloc(ent->size + 1); - memcpy(ret, ent->data, ent->size); - ((char *)ret)[ent->size] = 0; + } else { + ret = xmemdupz(ent->data, ent->size); } *type = ent->type; *base_size = ent->size; @@ -1872,12 +1869,9 @@ void *read_sha1_file(const unsigned char *sha1, enum object_type *type, co = find_cached_object(sha1); if (co) { - buf = xmalloc(co->size + 1); - memcpy(buf, co->buf, co->size); - ((char*)buf)[co->size] = 0; *type = co->type; *size = co->size; - return buf; + return xmemdupz(co->buf, co->size); } buf = read_packed_sha1(sha1, type, size); diff --git a/tag.c b/tag.c index bbacd59..f62bcdd 100644 --- a/tag.c +++ b/tag.c @@ -68,9 +68,7 @@ int parse_tag_buffer(struct tag *item, void *data, unsigned long size) memcpy(type, type_line + 5, typelen); type[typelen] = '\0'; taglen = sig_line - tag_line - strlen("tag \n"); - item->tag = xmalloc(taglen + 1); - memcpy(item->tag, tag_line + 4, taglen); - item->tag[taglen] = '\0'; + item->tag = xmemdupz(tag_line + 4, taglen); if (!strcmp(type, blob_type)) { item->tagged = &lookup_blob(sha1)->object; -- cgit v0.10.2-6-g49f6 From ca0328354afbf4ec6941cb4312bfc6908ab06d73 Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Wed, 19 Sep 2007 01:37:50 -0700 Subject: builtin-apply.c: fix a tiny leak introduced during xmemdupz() conversion. Signed-off-by: Junio C Hamano diff --git a/builtin-apply.c b/builtin-apply.c index 512c9b6..db337f1 100644 --- a/builtin-apply.c +++ b/builtin-apply.c @@ -291,6 +291,7 @@ static char *find_name(const char *line, char *def, int p_value, int terminate) int deflen = strlen(def); if (deflen < len && !strncmp(start, def, deflen)) return def; + free(def); } return xmemdupz(start, len); -- cgit v0.10.2-6-g49f6 From 6b30852ded5074652f4304a303521932235c62db Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Wed, 19 Sep 2007 01:52:59 -0700 Subject: builtin-for-each-ref.c::copy_name() - do not overstep the buffer. This was introduced during xmemdupz() conversion. Signed-off-by: Junio C Hamano diff --git a/builtin-for-each-ref.c b/builtin-for-each-ref.c index 725c1df..e868a4b 100644 --- a/builtin-for-each-ref.c +++ b/builtin-for-each-ref.c @@ -309,7 +309,7 @@ static const char *copy_line(const char *buf) static const char *copy_name(const char *buf) { const char *cp; - for (cp = buf; *cp != '\n'; cp++) { + for (cp = buf; *cp && *cp != '\n'; cp++) { if (!strncmp(cp, " <", 2)) return xmemdupz(buf, cp - buf); } -- cgit v0.10.2-6-g49f6 From e03e05ff73a6f6b4f32eb5cd13b4f1e43275e42f Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Thu, 20 Sep 2007 00:42:10 +0200 Subject: Fix the expansion pattern of the pseudo-static path buffer. Signed-off-by: Pierre Habouzit diff --git a/archive-tar.c b/archive-tar.c index a87bc4b..e1bced5 100644 --- a/archive-tar.c +++ b/archive-tar.c @@ -238,15 +238,14 @@ static int write_tar_entry(const unsigned char *sha1, const char *filename, unsigned mode, int stage) { static struct strbuf path = STRBUF_INIT; - int filenamelen = strlen(filename); void *buffer; enum object_type type; unsigned long size; - strbuf_grow(&path, MAX(PATH_MAX, baselen + filenamelen + 1)); strbuf_reset(&path); + strbuf_grow(&path, PATH_MAX); strbuf_add(&path, base, baselen); - strbuf_add(&path, filename, filenamelen); + strbuf_addstr(&path, filename); if (S_ISDIR(mode) || S_ISGITLINK(mode)) { strbuf_addch(&path, '/'); buffer = NULL; -- cgit v0.10.2-6-g49f6 From 19247e5510279f018f8358a72b38cc5aa62fac8a Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Thu, 20 Sep 2007 10:43:11 +0200 Subject: nfv?asprintf are broken without va_copy, workaround them. * drop nfasprintf. * move nfvasprintf into imap-send.c back, and let it work on a 8k buffer, and die() in case of overflow. It should be enough for imap commands, if someone cares about imap-send, he's welcomed to fix it properly. * replace nfvasprintf use in merge-recursive with a copy of the strbuf_addf logic, it's one place, we'll live with it. To ease the change, output_buffer string list is replaced with a strbuf ;) * rework trace.c to call vsnprintf itself. It's used to format strerror()s and git command names, it should never be more than a few octets long, let it work on a 8k static buffer with vsnprintf or die loudly. Signed-off-by: Pierre Habouzit diff --git a/cache.h b/cache.h index 8650d62..916ee51 100644 --- a/cache.h +++ b/cache.h @@ -585,8 +585,6 @@ extern void *alloc_object_node(void); extern void alloc_report(void); /* trace.c */ -extern int nfasprintf(char **str, const char *fmt, ...); -extern int nfvasprintf(char **str, const char *fmt, va_list va); extern void trace_printf(const char *format, ...); extern void trace_argv_printf(const char **argv, int count, const char *format, ...); diff --git a/imap-send.c b/imap-send.c index 905d097..e95cdde 100644 --- a/imap-send.c +++ b/imap-send.c @@ -105,6 +105,19 @@ static void free_generic_messages( message_t * ); static int nfsnprintf( char *buf, int blen, const char *fmt, ... ); +static int nfvasprintf(char **strp, const char *fmt, va_list ap) +{ + int len; + char tmp[8192]; + + len = vsnprintf(tmp, sizeof(tmp), fmt, ap); + if (len < 0) + die("Fatal: Out of memory\n"); + if (len >= sizeof(tmp)) + die("imap command overflow !\n"); + *strp = xmemdupz(tmp, len); + return len; +} static void arc4_init( void ); static unsigned char arc4_getbyte( void ); diff --git a/merge-recursive.c b/merge-recursive.c index 14b56c2..86767e6 100644 --- a/merge-recursive.c +++ b/merge-recursive.c @@ -85,63 +85,58 @@ struct stage_data unsigned processed:1; }; -struct output_buffer -{ - struct output_buffer *next; - char *str; -}; - static struct path_list current_file_set = {NULL, 0, 0, 1}; static struct path_list current_directory_set = {NULL, 0, 0, 1}; static int call_depth = 0; static int verbosity = 2; static int buffer_output = 1; -static struct output_buffer *output_list, *output_end; +static struct strbuf obuf = STRBUF_INIT; -static int show (int v) +static int show(int v) { return (!call_depth && verbosity >= v) || verbosity >= 5; } -static void output(int v, const char *fmt, ...) +static void flush_output(void) { - va_list args; - va_start(args, fmt); - if (buffer_output && show(v)) { - struct output_buffer *b = xmalloc(sizeof(*b)); - nfvasprintf(&b->str, fmt, args); - b->next = NULL; - if (output_end) - output_end->next = b; - else - output_list = b; - output_end = b; - } else if (show(v)) { - int i; - for (i = call_depth; i--;) - fputs(" ", stdout); - vfprintf(stdout, fmt, args); - fputc('\n', stdout); + if (obuf.len) { + fputs(obuf.buf, stdout); + strbuf_reset(&obuf); } - va_end(args); } -static void flush_output(void) +static void output(int v, const char *fmt, ...) { - struct output_buffer *b, *n; - for (b = output_list; b; b = n) { - int i; - for (i = call_depth; i--;) - fputs(" ", stdout); - fputs(b->str, stdout); - fputc('\n', stdout); - n = b->next; - free(b->str); - free(b); + int len; + va_list ap; + + if (!show(v)) + return; + + strbuf_grow(&obuf, call_depth * 2 + 2); + memset(obuf.buf + obuf.len, ' ', call_depth * 2); + strbuf_setlen(&obuf, obuf.len + call_depth * 2); + + va_start(ap, fmt); + len = vsnprintf(obuf.buf + obuf.len, strbuf_avail(&obuf), fmt, ap); + va_end(ap); + + if (len < 0) + len = 0; + if (len >= strbuf_avail(&obuf)) { + strbuf_grow(&obuf, len + 2); + va_start(ap, fmt); + len = vsnprintf(obuf.buf + obuf.len, strbuf_avail(&obuf), fmt, ap); + va_end(ap); + if (len >= strbuf_avail(&obuf)) { + die("this should not happen, your snprintf is broken"); + } } - output_list = NULL; - output_end = NULL; + strbuf_setlen(&obuf, obuf.len + len); + strbuf_add(&obuf, "\n", 1); + if (!buffer_output) + flush_output(); } static void output_commit_title(struct commit *commit) diff --git a/trace.c b/trace.c index 7961a27..91548a5 100644 --- a/trace.c +++ b/trace.c @@ -25,33 +25,6 @@ #include "cache.h" #include "quote.h" -/* Stolen from "imap-send.c". */ -int nfvasprintf(char **strp, const char *fmt, va_list ap) -{ - int len; - char tmp[1024]; - - if ((len = vsnprintf(tmp, sizeof(tmp), fmt, ap)) < 0 || - !(*strp = xmalloc(len + 1))) - die("Fatal: Out of memory\n"); - if (len >= (int)sizeof(tmp)) - vsprintf(*strp, fmt, ap); - else - memcpy(*strp, tmp, len + 1); - return len; -} - -int nfasprintf(char **str, const char *fmt, ...) -{ - int rc; - va_list args; - - va_start(args, fmt); - rc = nfvasprintf(str, fmt, args); - va_end(args); - return rc; -} - /* Get a trace file descriptor from GIT_TRACE env variable. */ static int get_trace_fd(int *need_close) { @@ -89,63 +62,54 @@ static int get_trace_fd(int *need_close) static const char err_msg[] = "Could not trace into fd given by " "GIT_TRACE environment variable"; -void trace_printf(const char *format, ...) +void trace_printf(const char *fmt, ...) { - char *trace_str; - va_list rest; - int need_close = 0; - int fd = get_trace_fd(&need_close); + char buf[8192]; + va_list ap; + int fd, len, need_close = 0; + fd = get_trace_fd(&need_close); if (!fd) return; - va_start(rest, format); - nfvasprintf(&trace_str, format, rest); - va_end(rest); - - write_or_whine_pipe(fd, trace_str, strlen(trace_str), err_msg); - - free(trace_str); + va_start(ap, fmt); + len = vsnprintf(buf, sizeof(buf), fmt, ap); + va_end(ap); + if (len >= sizeof(buf)) + die("unreasonnable trace length"); + write_or_whine_pipe(fd, buf, len, err_msg); if (need_close) close(fd); } -void trace_argv_printf(const char **argv, int count, const char *format, ...) +void trace_argv_printf(const char **argv, int count, const char *fmt, ...) { - char *argv_str, *format_str, *trace_str; - size_t argv_len, format_len, trace_len; - va_list rest; - int need_close = 0; - int fd = get_trace_fd(&need_close); + char buf[8192]; + va_list ap; + char *argv_str; + size_t argv_len; + int fd, len, need_close = 0; + fd = get_trace_fd(&need_close); if (!fd) return; + va_start(ap, fmt); + len = vsnprintf(buf, sizeof(buf), fmt, ap); + va_end(ap); + if (len >= sizeof(buf)) + die("unreasonnable trace length"); + /* Get the argv string. */ argv_str = sq_quote_argv(argv, count); argv_len = strlen(argv_str); - /* Get the formated string. */ - va_start(rest, format); - nfvasprintf(&format_str, format, rest); - va_end(rest); - - /* Allocate buffer for trace string. */ - format_len = strlen(format_str); - trace_len = argv_len + format_len + 1; /* + 1 for \n */ - trace_str = xmalloc(trace_len + 1); - - /* Copy everything into the trace string. */ - strncpy(trace_str, format_str, format_len); - strncpy(trace_str + format_len, argv_str, argv_len); - strcpy(trace_str + trace_len - 1, "\n"); - - write_or_whine_pipe(fd, trace_str, trace_len, err_msg); + write_or_whine_pipe(fd, buf, len, err_msg); + write_or_whine_pipe(fd, argv_str, argv_len, err_msg); + write_or_whine_pipe(fd, "\n", 1, err_msg); free(argv_str); - free(format_str); - free(trace_str); if (need_close) close(fd); -- cgit v0.10.2-6-g49f6 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 diff --git a/commit.c b/commit.c index f86fa77..55b08ec 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 "), diff --git a/fast-import.c b/fast-import.c index f990658..eddae22 100644 --- a/fast-import.c +++ b/fast-import.c @@ -1111,9 +1111,7 @@ static int store_object( if (last->no_swap) { last->data = *dat; } else { - struct strbuf tmp = *dat; - *dat = last->data; - last->data = tmp; + strbuf_swap(&last->data, dat); } last->offset = e->offset; } diff --git a/strbuf.c b/strbuf.c index 59383ac..dcb725d 100644 --- a/strbuf.c +++ b/strbuf.c @@ -50,16 +50,6 @@ void strbuf_rtrim(struct strbuf *sb) sb->buf[sb->len] = '\0'; } -void strbuf_insert(struct strbuf *sb, size_t pos, const void *data, size_t len) -{ - strbuf_grow(sb, len); - if (pos > sb->len) - die("`pos' is too far after the end of the buffer"); - memmove(sb->buf + pos + len, sb->buf + pos, sb->len - pos); - memcpy(sb->buf + pos, data, len); - strbuf_setlen(sb, sb->len + len); -} - void strbuf_splice(struct strbuf *sb, size_t pos, size_t len, const void *data, size_t dlen) { @@ -79,6 +69,16 @@ void strbuf_splice(struct strbuf *sb, size_t pos, size_t len, strbuf_setlen(sb, sb->len + dlen - len); } +void strbuf_insert(struct strbuf *sb, size_t pos, const void *data, size_t len) +{ + strbuf_splice(sb, pos, 0, data, len); +} + +void strbuf_remove(struct strbuf *sb, size_t pos, size_t len) +{ + strbuf_splice(sb, pos, len, NULL, 0); +} + void strbuf_add(struct strbuf *sb, const void *data, size_t len) { strbuf_grow(sb, len); diff --git a/strbuf.h b/strbuf.h index b2cbd97..567e2d1 100644 --- a/strbuf.h +++ b/strbuf.h @@ -55,15 +55,20 @@ extern void strbuf_release(struct strbuf *); extern void strbuf_reset(struct strbuf *); extern char *strbuf_detach(struct strbuf *); extern void strbuf_attach(struct strbuf *, void *, size_t, size_t); +static inline void strbuf_swap(struct strbuf *a, struct strbuf *b) { + struct strbuf tmp = *a; + *a = *b; + *b = tmp; +} /*----- strbuf size related -----*/ static inline size_t strbuf_avail(struct strbuf *sb) { - return sb->alloc ? sb->alloc - sb->len - 1 : 0; + return sb->alloc ? sb->alloc - sb->len - 1 : 0; } static inline void strbuf_setlen(struct strbuf *sb, size_t len) { - assert (len < sb->alloc); - sb->len = len; - sb->buf[len] = '\0'; + assert (len < sb->alloc); + sb->len = len; + sb->buf[len] = '\0'; } extern void strbuf_grow(struct strbuf *, size_t); @@ -78,12 +83,12 @@ static inline void strbuf_addch(struct strbuf *sb, int c) { sb->buf[sb->len] = '\0'; } -/* inserts after pos, or appends if pos >= sb->len */ extern void strbuf_insert(struct strbuf *, size_t pos, const void *, size_t); +extern void strbuf_remove(struct strbuf *, size_t pos, size_t len); /* splice pos..pos+len with given data */ extern void strbuf_splice(struct strbuf *, size_t pos, size_t len, - const void *, size_t); + const void *, size_t); extern void strbuf_add(struct strbuf *, const void *, size_t); static inline void strbuf_addstr(struct strbuf *sb, const char *s) { -- cgit v0.10.2-6-g49f6 From 7fb1011e610a28518959b1d2d48cea17ecc32048 Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Thu, 20 Sep 2007 00:42:14 +0200 Subject: Rework unquote_c_style to work on a strbuf. If the gain is not obvious in the diffstat, the resulting code is more readable, _and_ in checkout-index/update-index we now reuse the same buffer to unquote strings instead of always freeing/mallocing. This also is more coherent with the next patch that reworks quoting functions. The quoting function is also made more efficient scanning for backslashes and treating portions of strings without a backslash at once. Signed-off-by: Pierre Habouzit diff --git a/builtin-apply.c b/builtin-apply.c index db337f1..1cf68ed 100644 --- a/builtin-apply.c +++ b/builtin-apply.c @@ -231,35 +231,33 @@ static char *find_name(const char *line, char *def, int p_value, int terminate) { int len; const char *start = line; - char *name; if (*line == '"') { + struct strbuf name; + /* Proposed "new-style" GNU patch/diff format; see * http://marc.theaimsgroup.com/?l=git&m=112927316408690&w=2 */ - name = unquote_c_style(line, NULL); - if (name) { - char *cp = name; - while (p_value) { + strbuf_init(&name, 0); + if (!unquote_c_style(&name, line, NULL)) { + char *cp; + + for (cp = name.buf; p_value; p_value--) { cp = strchr(cp, '/'); if (!cp) break; cp++; - p_value--; } if (cp) { /* name can later be freed, so we need * to memmove, not just return cp */ - memmove(name, cp, strlen(cp) + 1); + strbuf_remove(&name, 0, cp - name.buf); free(def); - return name; - } - else { - free(name); - name = NULL; + return name.buf; } } + strbuf_release(&name); } for (;;) { @@ -567,29 +565,30 @@ static const char *stop_at_slash(const char *line, int llen) */ static char *git_header_name(char *line, int llen) { - int len; const char *name; const char *second = NULL; + size_t len; line += strlen("diff --git "); llen -= strlen("diff --git "); if (*line == '"') { const char *cp; - char *first = unquote_c_style(line, &second); - if (!first) - return NULL; + struct strbuf first; + struct strbuf sp; + + strbuf_init(&first, 0); + strbuf_init(&sp, 0); + + if (unquote_c_style(&first, line, &second)) + goto free_and_fail1; /* advance to the first slash */ - cp = stop_at_slash(first, strlen(first)); - if (!cp || cp == first) { - /* we do not accept absolute paths */ - free_first_and_fail: - free(first); - return NULL; - } - len = strlen(cp+1); - memmove(first, cp+1, len+1); /* including NUL */ + cp = stop_at_slash(first.buf, first.len); + /* we do not accept absolute paths */ + if (!cp || cp == first.buf) + goto free_and_fail1; + strbuf_remove(&first, 0, cp + 1 - first.buf); /* second points at one past closing dq of name. * find the second name. @@ -598,40 +597,40 @@ static char *git_header_name(char *line, int llen) second++; if (line + llen <= second) - goto free_first_and_fail; + goto free_and_fail1; if (*second == '"') { - char *sp = unquote_c_style(second, NULL); - if (!sp) - goto free_first_and_fail; - cp = stop_at_slash(sp, strlen(sp)); - if (!cp || cp == sp) { - free_both_and_fail: - free(sp); - goto free_first_and_fail; - } + if (unquote_c_style(&sp, second, NULL)) + goto free_and_fail1; + cp = stop_at_slash(sp.buf, sp.len); + if (!cp || cp == sp.buf) + goto free_and_fail1; /* They must match, otherwise ignore */ - if (strcmp(cp+1, first)) - goto free_both_and_fail; - free(sp); - return first; + if (strcmp(cp + 1, first.buf)) + goto free_and_fail1; + strbuf_release(&sp); + return first.buf; } /* unquoted second */ cp = stop_at_slash(second, line + llen - second); if (!cp || cp == second) - goto free_first_and_fail; + goto free_and_fail1; cp++; - if (line + llen - cp != len + 1 || - memcmp(first, cp, len)) - goto free_first_and_fail; - return first; + if (line + llen - cp != first.len + 1 || + memcmp(first.buf, cp, first.len)) + goto free_and_fail1; + return first.buf; + + free_and_fail1: + strbuf_release(&first); + strbuf_release(&sp); + return NULL; } /* unquoted first name */ name = stop_at_slash(line, llen); if (!name || name == line) return NULL; - name++; /* since the first name is unquoted, a dq if exists must be @@ -639,28 +638,30 @@ static char *git_header_name(char *line, int llen) */ for (second = name; second < line + llen; second++) { if (*second == '"') { - const char *cp = second; + struct strbuf sp; const char *np; - char *sp = unquote_c_style(second, NULL); - - if (!sp) - return NULL; - np = stop_at_slash(sp, strlen(sp)); - if (!np || np == sp) { - free_second_and_fail: - free(sp); - return NULL; - } + + strbuf_init(&sp, 0); + if (unquote_c_style(&sp, second, NULL)) + goto free_and_fail2; + + np = stop_at_slash(sp.buf, sp.len); + if (!np || np == sp.buf) + goto free_and_fail2; np++; - len = strlen(np); - if (len < cp - name && + + len = sp.buf + sp.len - np; + if (len < second - name && !strncmp(np, name, len) && isspace(name[len])) { /* Good */ - memmove(sp, np, len + 1); - return sp; + strbuf_remove(&sp, 0, np - sp.buf); + return sp.buf; } - goto free_second_and_fail; + + free_and_fail2: + strbuf_release(&sp); + return NULL; } } diff --git a/builtin-checkout-index.c b/builtin-checkout-index.c index a18ecc4..e6264c4 100644 --- a/builtin-checkout-index.c +++ b/builtin-checkout-index.c @@ -270,26 +270,27 @@ int cmd_checkout_index(int argc, const char **argv, const char *prefix) } if (read_from_stdin) { - struct strbuf buf; + struct strbuf buf, nbuf; + if (all) die("git-checkout-index: don't mix '--all' and '--stdin'"); + strbuf_init(&buf, 0); - while (1) { - char *path_name; + strbuf_init(&nbuf, 0); + while (strbuf_getline(&buf, stdin, line_termination) != EOF) { const char *p; - if (strbuf_getline(&buf, stdin, line_termination) == EOF) - break; - if (line_termination && buf.buf[0] == '"') - path_name = unquote_c_style(buf.buf, NULL); - else - path_name = buf.buf; - p = prefix_path(prefix, prefix_length, path_name); + if (line_termination && buf.buf[0] == '"') { + strbuf_reset(&nbuf); + if (unquote_c_style(&nbuf, buf.buf, NULL)) + die("line is badly quoted"); + strbuf_swap(&buf, &nbuf); + } + p = prefix_path(prefix, prefix_length, buf.buf); checkout_file(p, prefix_length); - if (p < path_name || p > path_name + strlen(path_name)) + if (p < buf.buf || p > buf.buf + buf.len) free((char *)p); - if (path_name != buf.buf) - free(path_name); } + strbuf_release(&nbuf); strbuf_release(&buf); } diff --git a/builtin-update-index.c b/builtin-update-index.c index acd5ab5..c76879e 100644 --- a/builtin-update-index.c +++ b/builtin-update-index.c @@ -295,8 +295,11 @@ static void update_one(const char *path, const char *prefix, int prefix_length) static void read_index_info(int line_termination) { struct strbuf buf; + struct strbuf uq; + strbuf_init(&buf, 0); - while (1) { + strbuf_init(&uq, 0); + while (strbuf_getline(&buf, stdin, line_termination) != EOF) { char *ptr, *tab; char *path_name; unsigned char sha1[20]; @@ -320,9 +323,6 @@ static void read_index_info(int line_termination) * This format is to put higher order stages into the * index file and matches git-ls-files --stage output. */ - if (strbuf_getline(&buf, stdin, line_termination) == EOF) - break; - errno = 0; ul = strtoul(buf.buf, &ptr, 8); if (ptr == buf.buf || *ptr != ' ' @@ -347,15 +347,17 @@ static void read_index_info(int line_termination) if (get_sha1_hex(tab - 40, sha1) || tab[-41] != ' ') goto bad_line; - if (line_termination && ptr[0] == '"') - path_name = unquote_c_style(ptr, NULL); - else - path_name = ptr; + path_name = ptr; + if (line_termination && path_name[0] == '"') { + strbuf_reset(&uq); + if (unquote_c_style(&uq, path_name, NULL)) { + die("git-update-index: bad quoting of path name"); + } + path_name = uq.buf; + } if (!verify_path(path_name)) { fprintf(stderr, "Ignoring path %s\n", path_name); - if (path_name != ptr) - free(path_name); continue; } @@ -383,6 +385,7 @@ static void read_index_info(int line_termination) die("malformed index info %s", buf.buf); } strbuf_release(&buf); + strbuf_release(&uq); } static const char update_index_usage[] = @@ -705,26 +708,26 @@ int cmd_update_index(int argc, const char **argv, const char *prefix) free((char*)p); } if (read_from_stdin) { - struct strbuf buf; + struct strbuf buf, nbuf; + strbuf_init(&buf, 0); - while (1) { - char *path_name; + strbuf_init(&nbuf, 0); + while (strbuf_getline(&buf, stdin, line_termination) != EOF) { const char *p; - if (strbuf_getline(&buf, stdin, line_termination) == EOF) - break; - if (line_termination && buf.buf[0] == '"') - path_name = unquote_c_style(buf.buf, NULL); - else - path_name = buf.buf; - p = prefix_path(prefix, prefix_length, path_name); + if (line_termination && buf.buf[0] == '"') { + strbuf_reset(&nbuf); + if (unquote_c_style(&nbuf, buf.buf, NULL)) + die("line is badly quoted"); + strbuf_swap(&buf, &nbuf); + } + p = prefix_path(prefix, prefix_length, buf.buf); update_one(p, NULL, 0); if (set_executable_bit) chmod_path(set_executable_bit, p); - if (p < path_name || p > path_name + strlen(path_name)) - free((char*) p); - if (path_name != buf.buf) - free(path_name); + if (p < buf.buf || p > buf.buf + buf.len) + free((char *)p); } + strbuf_release(&nbuf); strbuf_release(&buf); } diff --git a/fast-import.c b/fast-import.c index eddae22..a870a44 100644 --- a/fast-import.c +++ b/fast-import.c @@ -1759,7 +1759,7 @@ static void load_branch(struct branch *b) static void file_change_m(struct branch *b) { const char *p = command_buf.buf + 2; - char *p_uq; + static struct strbuf uq = STRBUF_INIT; const char *endp; struct object_entry *oe = oe; unsigned char sha1[20]; @@ -1797,18 +1797,20 @@ static void file_change_m(struct branch *b) if (*p++ != ' ') die("Missing space after SHA1: %s", command_buf.buf); - p_uq = unquote_c_style(p, &endp); - if (p_uq) { + strbuf_reset(&uq); + if (!unquote_c_style(&uq, p, &endp)) { if (*endp) die("Garbage after path in: %s", command_buf.buf); - p = p_uq; + p = uq.buf; } if (inline_data) { static struct strbuf buf = STRBUF_INIT; - if (!p_uq) - p = p_uq = xstrdup(p); + if (p != uq.buf) { + strbuf_addstr(&uq, p); + p = uq.buf; + } read_next_command(); cmd_data(&buf); store_object(OBJ_BLOB, &buf, &last_blob, sha1, 0); @@ -1826,56 +1828,54 @@ static void file_change_m(struct branch *b) } tree_content_set(&b->branch_tree, p, sha1, S_IFREG | mode, NULL); - free(p_uq); } static void file_change_d(struct branch *b) { const char *p = command_buf.buf + 2; - char *p_uq; + static struct strbuf uq = STRBUF_INIT; const char *endp; - p_uq = unquote_c_style(p, &endp); - if (p_uq) { + strbuf_reset(&uq); + if (!unquote_c_style(&uq, p, &endp)) { if (*endp) die("Garbage after path in: %s", command_buf.buf); - p = p_uq; + p = uq.buf; } tree_content_remove(&b->branch_tree, p, NULL); - free(p_uq); } static void file_change_cr(struct branch *b, int rename) { const char *s, *d; - char *s_uq, *d_uq; + static struct strbuf s_uq = STRBUF_INIT; + static struct strbuf d_uq = STRBUF_INIT; const char *endp; struct tree_entry leaf; s = command_buf.buf + 2; - s_uq = unquote_c_style(s, &endp); - if (s_uq) { + strbuf_reset(&s_uq); + if (!unquote_c_style(&s_uq, s, &endp)) { if (*endp != ' ') die("Missing space after source: %s", command_buf.buf); - } - else { + } else { endp = strchr(s, ' '); if (!endp) die("Missing space after source: %s", command_buf.buf); - s_uq = xmemdupz(s, endp - s); + strbuf_add(&s_uq, s, endp - s); } - s = s_uq; + s = s_uq.buf; endp++; if (!*endp) die("Missing dest: %s", command_buf.buf); d = endp; - d_uq = unquote_c_style(d, &endp); - if (d_uq) { + strbuf_reset(&d_uq); + if (!unquote_c_style(&d_uq, d, &endp)) { if (*endp) die("Garbage after dest in: %s", command_buf.buf); - d = d_uq; + d = d_uq.buf; } memset(&leaf, 0, sizeof(leaf)); @@ -1889,9 +1889,6 @@ static void file_change_cr(struct branch *b, int rename) leaf.versions[1].sha1, leaf.versions[1].mode, leaf.tree); - - free(s_uq); - free(d_uq); } static void file_change_deleteall(struct branch *b) diff --git a/mktree.c b/mktree.c index 9c137de..e0da110 100644 --- a/mktree.c +++ b/mktree.c @@ -66,6 +66,7 @@ static const char mktree_usage[] = "git-mktree [-z]"; int main(int ac, char **av) { struct strbuf sb; + struct strbuf p_uq; unsigned char sha1[20]; int line_termination = '\n'; @@ -82,14 +83,13 @@ int main(int ac, char **av) } strbuf_init(&sb, 0); - while (1) { + strbuf_init(&p_uq, 0); + while (strbuf_getline(&sb, stdin, line_termination) != EOF) { char *ptr, *ntr; unsigned mode; enum object_type type; char *path; - if (strbuf_getline(&sb, stdin, line_termination) == EOF) - break; ptr = sb.buf; /* Input is non-recursive ls-tree output format * mode SP type SP sha1 TAB name @@ -109,18 +109,21 @@ int main(int ac, char **av) *ntr++ = 0; /* now at the beginning of SHA1 */ if (type != type_from_string(ptr)) die("object type %s mismatch (%s)", ptr, typename(type)); - ntr += 41; /* at the beginning of name */ - if (line_termination && ntr[0] == '"') - path = unquote_c_style(ntr, NULL); - else - path = ntr; - append_to_tree(mode, sha1, path); + path = ntr + 41; /* at the beginning of name */ + if (line_termination && path[0] == '"') { + strbuf_reset(&p_uq); + if (unquote_c_style(&p_uq, path, NULL)) { + die("invalid quoting"); + } + path = p_uq.buf; + } - if (path != ntr) - free(path); + append_to_tree(mode, sha1, path); } + strbuf_release(&p_uq); strbuf_release(&sb); + write_tree(sha1); puts(sha1_to_hex(sha1)); exit(0); diff --git a/quote.c b/quote.c index d88bf75..7771c9c 100644 --- a/quote.c +++ b/quote.c @@ -239,73 +239,71 @@ int quote_c_style(const char *name, char *outbuf, FILE *outfp, int no_dq) /* * C-style name unquoting. * - * Quoted should point at the opening double quote. Returns - * an allocated memory that holds unquoted name, which the caller - * should free when done. Updates endp pointer to point at - * one past the ending double quote if given. + * Quoted should point at the opening double quote. + * + Returns 0 if it was able to unquote the string properly, and appends the + * result in the strbuf `sb'. + * + Returns -1 in case of error, and doesn't touch the strbuf. Though note + * that this function will allocate memory in the strbuf, so calling + * strbuf_release is mandatory whichever result unquote_c_style returns. + * + * Updates endp pointer to point at one past the ending double quote if given. */ - -char *unquote_c_style(const char *quoted, const char **endp) +int unquote_c_style(struct strbuf *sb, const char *quoted, const char **endp) { - const char *sp; - char *name = NULL, *outp = NULL; - int count = 0, ch, ac; - -#undef EMIT -#define EMIT(c) (outp ? (*outp++ = (c)) : (count++)) + size_t oldlen = sb->len, len; + int ch, ac; if (*quoted++ != '"') - return NULL; + return -1; + + for (;;) { + len = strcspn(quoted, "\"\\"); + strbuf_add(sb, quoted, len); + quoted += len; - while (1) { - /* first pass counts and allocates, second pass fills */ - for (sp = quoted; (ch = *sp++) != '"'; ) { - if (ch == '\\') { - switch (ch = *sp++) { - case 'a': ch = '\a'; break; - case 'b': ch = '\b'; break; - case 'f': ch = '\f'; break; - case 'n': ch = '\n'; break; - case 'r': ch = '\r'; break; - case 't': ch = '\t'; break; - case 'v': ch = '\v'; break; - - case '\\': case '"': - break; /* verbatim */ - - case '0': - case '1': - case '2': - case '3': - case '4': - case '5': - case '6': - case '7': - /* octal */ + switch (*quoted++) { + case '"': + if (endp) + *endp = quoted + 1; + return 0; + case '\\': + break; + default: + goto error; + } + + switch ((ch = *quoted++)) { + case 'a': ch = '\a'; break; + case 'b': ch = '\b'; break; + case 'f': ch = '\f'; break; + case 'n': ch = '\n'; break; + case 'r': ch = '\r'; break; + case 't': ch = '\t'; break; + case 'v': ch = '\v'; break; + + case '\\': case '"': + break; /* verbatim */ + + /* octal values with first digit over 4 overflow */ + case '0': case '1': case '2': case '3': ac = ((ch - '0') << 6); - if ((ch = *sp++) < '0' || '7' < ch) - return NULL; + if ((ch = *quoted++) < '0' || '7' < ch) + goto error; ac |= ((ch - '0') << 3); - if ((ch = *sp++) < '0' || '7' < ch) - return NULL; + if ((ch = *quoted++) < '0' || '7' < ch) + goto error; ac |= (ch - '0'); ch = ac; break; default: - return NULL; /* malformed */ - } + goto error; } - EMIT(ch); + strbuf_addch(sb, ch); } - if (name) { - *outp = 0; - if (endp) - *endp = sp; - return name; - } - outp = name = xmalloc(count + 1); - } + error: + strbuf_setlen(sb, oldlen); + return -1; } void write_name_quoted(const char *prefix, int prefix_len, diff --git a/quote.h b/quote.h index 8a59cc5..f48a3fc 100644 --- a/quote.h +++ b/quote.h @@ -43,9 +43,9 @@ extern int add_to_string(char **ptrp, int *sizep, const char *str, int quote); */ extern char *sq_dequote(char *); +extern int unquote_c_style(struct strbuf *, const char *quoted, const char **endp); extern int quote_c_style(const char *name, char *outbuf, FILE *outfp, int nodq); -extern char *unquote_c_style(const char *quoted, const char **endp); extern void write_name_quoted(const char *prefix, int prefix_len, const char *name, int quote, FILE *out); -- cgit v0.10.2-6-g49f6 From 663af3422a648e87945e4d8c0cc3e13671f2bbde Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Thu, 20 Sep 2007 00:42:15 +0200 Subject: Full rework of quote_c_style and write_name_quoted. * quote_c_style works on a strbuf instead of a wild buffer. * quote_c_style is now clever enough to not add double quotes if not needed. * write_name_quoted inherits those advantages, but also take a different set of arguments. Now instead of asking for quotes or not, you pass a "terminator". If it's \0 then we assume you don't want to escape, else C escaping is performed. In any case, the terminator is also appended to the stream. It also no longer takes the prefix/prefix_len arguments, as it's seldomly used, and makes some optimizations harder. * write_name_quotedpfx is created to work like write_name_quoted and take the prefix/prefix_len arguments. Thanks to those API changes, diff.c has somehow lost weight, thanks to the removal of functions that were wrappers around the old write_name_quoted trying to give it a semantics like the new one, but performing a lot of allocations for this goal. Now we always write directly to the stream, no intermediate allocation is performed. As a side effect of the refactor in builtin-apply.c, the length of the bar graphs in diffstats are not affected anymore by the fact that the path was clipped. Signed-off-by: Pierre Habouzit diff --git a/builtin-apply.c b/builtin-apply.c index 1cf68ed..01c9d60 100644 --- a/builtin-apply.c +++ b/builtin-apply.c @@ -163,15 +163,14 @@ static void say_patch_name(FILE *output, const char *pre, struct patch *patch, c fputs(pre, output); if (patch->old_name && patch->new_name && strcmp(patch->old_name, patch->new_name)) { - write_name_quoted(NULL, 0, patch->old_name, 1, output); + quote_c_style(patch->old_name, NULL, output, 0); fputs(" => ", output); - write_name_quoted(NULL, 0, patch->new_name, 1, output); - } - else { + quote_c_style(patch->new_name, NULL, output, 0); + } else { const char *n = patch->new_name; if (!n) n = patch->old_name; - write_name_quoted(NULL, 0, n, 1, output); + quote_c_style(n, NULL, output, 0); } fputs(post, output); } @@ -1379,61 +1378,50 @@ static const char minuses[]= "-------------------------------------------------- static void show_stats(struct patch *patch) { - const char *prefix = ""; - char *name = patch->new_name; - char *qname = NULL; - int len, max, add, del, total; - - if (!name) - name = patch->old_name; + struct strbuf qname; + char *cp = patch->new_name ? patch->new_name : patch->old_name; + int max, add, del; - if (0 < (len = quote_c_style(name, NULL, NULL, 0))) { - qname = xmalloc(len + 1); - quote_c_style(name, qname, NULL, 0); - name = qname; - } + strbuf_init(&qname, 0); + quote_c_style(cp, &qname, NULL, 0); /* * "scale" the filename */ - len = strlen(name); max = max_len; if (max > 50) max = 50; - if (len > max) { - char *slash; - prefix = "..."; - max -= 3; - name += len - max; - slash = strchr(name, '/'); - if (slash) - name = slash; + + if (qname.len > max) { + cp = strchr(qname.buf + qname.len + 3 - max, '/'); + if (!cp) + cp = qname.buf + qname.len + 3 - max; + strbuf_splice(&qname, 0, cp - qname.buf, "...", 3); + } + + if (patch->is_binary) { + printf(" %-*s | Bin\n", max, qname.buf); + strbuf_release(&qname); + return; } - len = max; + + printf(" %-*s |", max, qname.buf); + strbuf_release(&qname); /* * scale the add/delete */ - max = max_change; - if (max + len > 70) - max = 70 - len; - + max = max + max_change > 70 ? 70 - max : max_change; add = patch->lines_added; del = patch->lines_deleted; - total = add + del; if (max_change > 0) { - total = (total * max + max_change / 2) / max_change; + int total = ((add + del) * max + max_change / 2) / max_change; add = (add * max + max_change / 2) / max_change; del = total - add; } - if (patch->is_binary) - printf(" %s%-*s | Bin\n", prefix, len, name); - else - printf(" %s%-*s |%5d %.*s%.*s\n", prefix, - len, name, patch->lines_added + patch->lines_deleted, - add, pluses, del, minuses); - free(qname); + printf("%5d %.*s%.*s\n", patch->lines_added + patch->lines_deleted, + add, pluses, del, minuses); } static int read_old_data(struct stat *st, const char *path, struct strbuf *buf) @@ -2228,13 +2216,8 @@ static void numstat_patch_list(struct patch *patch) if (patch->is_binary) printf("-\t-\t"); else - printf("%d\t%d\t", - patch->lines_added, patch->lines_deleted); - if (line_termination && quote_c_style(name, NULL, NULL, 0)) - quote_c_style(name, NULL, stdout, 0); - else - fputs(name, stdout); - putchar(line_termination); + printf("%d\t%d\t", patch->lines_added, patch->lines_deleted); + write_name_quoted(name, stdout, line_termination); } } diff --git a/builtin-blame.c b/builtin-blame.c index e364b6c..16c0ca8 100644 --- a/builtin-blame.c +++ b/builtin-blame.c @@ -1430,8 +1430,7 @@ static void get_commit_info(struct commit *commit, static void write_filename_info(const char *path) { printf("filename "); - write_name_quoted(NULL, 0, path, 1, stdout); - putchar('\n'); + write_name_quoted(path, stdout, '\n'); } /* diff --git a/builtin-check-attr.c b/builtin-check-attr.c index d949733..6afdfa1 100644 --- a/builtin-check-attr.c +++ b/builtin-check-attr.c @@ -56,7 +56,7 @@ int cmd_check_attr(int argc, const char **argv, const char *prefix) else if (ATTR_UNSET(value)) value = "unspecified"; - write_name_quoted("", 0, argv[i], 1, stdout); + quote_c_style(argv[i], NULL, stdout, 0); printf(": %s: %s\n", argv[j+1], value); } } diff --git a/builtin-checkout-index.c b/builtin-checkout-index.c index e6264c4..70d619d 100644 --- a/builtin-checkout-index.c +++ b/builtin-checkout-index.c @@ -66,9 +66,7 @@ static void write_tempfile_record(const char *name, int prefix_length) fputs(topath[checkout_stage], stdout); putchar('\t'); - write_name_quoted("", 0, name + prefix_length, - line_termination, stdout); - putchar(line_termination); + write_name_quoted(name + prefix_length, stdout, line_termination); for (i = 0; i < 4; i++) { topath[i][0] = 0; diff --git a/builtin-ls-files.c b/builtin-ls-files.c index 48dd3f7..2e6f43b 100644 --- a/builtin-ls-files.c +++ b/builtin-ls-files.c @@ -84,8 +84,7 @@ static void show_dir_entry(const char *tag, struct dir_entry *ent) return; fputs(tag, stdout); - write_name_quoted("", 0, ent->name + offset, line_terminator, stdout); - putchar(line_terminator); + write_name_quoted(ent->name + offset, stdout, line_terminator); } static void show_other_files(struct dir_struct *dir) @@ -208,21 +207,15 @@ static void show_ce_entry(const char *tag, struct cache_entry *ce) if (!show_stage) { fputs(tag, stdout); - write_name_quoted("", 0, ce->name + offset, - line_terminator, stdout); - putchar(line_terminator); - } - else { + } else { printf("%s%06o %s %d\t", tag, ntohl(ce->ce_mode), abbrev ? find_unique_abbrev(ce->sha1,abbrev) : sha1_to_hex(ce->sha1), ce_stage(ce)); - write_name_quoted("", 0, ce->name + offset, - line_terminator, stdout); - putchar(line_terminator); } + write_name_quoted(ce->name + offset, stdout, line_terminator); } static void show_files(struct dir_struct *dir, const char *prefix) diff --git a/builtin-ls-tree.c b/builtin-ls-tree.c index cb4be4f..7abe333 100644 --- a/builtin-ls-tree.c +++ b/builtin-ls-tree.c @@ -112,10 +112,8 @@ static int show_tree(const unsigned char *sha1, const char *base, int baselen, abbrev ? find_unique_abbrev(sha1, abbrev) : sha1_to_hex(sha1)); } - write_name_quoted(base + chomp_prefix, baselen - chomp_prefix, - pathname, - line_termination, stdout); - putchar(line_termination); + write_name_quotedpfx(base + chomp_prefix, baselen - chomp_prefix, + pathname, stdout, line_termination); return retval; } diff --git a/combine-diff.c b/combine-diff.c index ef62234..fe5a2a1 100644 --- a/combine-diff.c +++ b/combine-diff.c @@ -650,10 +650,7 @@ static void dump_quoted_path(const char *prefix, const char *path, const char *c_meta, const char *c_reset) { printf("%s%s", c_meta, prefix); - if (quote_c_style(path, NULL, NULL, 0)) - quote_c_style(path, NULL, stdout, 0); - else - printf("%s", path); + quote_c_style(path, NULL, stdout, 0); printf("%s\n", c_reset); } @@ -900,16 +897,7 @@ static void show_raw_diff(struct combine_diff_path *p, int num_parent, struct re putchar(inter_name_termination); } - if (line_termination) { - if (quote_c_style(p->path, NULL, NULL, 0)) - quote_c_style(p->path, NULL, stdout, 0); - else - printf("%s", p->path); - putchar(line_termination); - } - else { - printf("%s%c", p->path, line_termination); - } + write_name_quoted(p->path, stdout, line_termination); } void show_combined_diff(struct combine_diff_path *p, diff --git a/diff.c b/diff.c index 2216d75..fb6d077 100644 --- a/diff.c +++ b/diff.c @@ -181,44 +181,23 @@ int git_diff_ui_config(const char *var, const char *value) return git_default_config(var, value); } -static char *quote_one(const char *str) -{ - int needlen; - char *xp; - - if (!str) - return NULL; - needlen = quote_c_style(str, NULL, NULL, 0); - if (!needlen) - return xstrdup(str); - xp = xmalloc(needlen + 1); - quote_c_style(str, xp, NULL, 0); - return xp; -} - static char *quote_two(const char *one, const char *two) { int need_one = quote_c_style(one, NULL, NULL, 1); int need_two = quote_c_style(two, NULL, NULL, 1); - char *xp; + struct strbuf res; + strbuf_init(&res, 0); if (need_one + need_two) { - if (!need_one) need_one = strlen(one); - if (!need_two) need_one = strlen(two); - - xp = xmalloc(need_one + need_two + 3); - xp[0] = '"'; - quote_c_style(one, xp + 1, NULL, 1); - quote_c_style(two, xp + need_one + 1, NULL, 1); - strcpy(xp + need_one + need_two + 1, "\""); - return xp; + strbuf_addch(&res, '"'); + quote_c_style(one, &res, NULL, 1); + quote_c_style(two, &res, NULL, 1); + strbuf_addch(&res, '"'); + } else { + strbuf_addstr(&res, one); + strbuf_addstr(&res, two); } - need_one = strlen(one); - need_two = strlen(two); - xp = xmalloc(need_one + need_two + 1); - strcpy(xp, one); - strcpy(xp + need_one, two); - return xp; + return res.buf; } static const char *external_diff(void) @@ -670,27 +649,20 @@ static char *pprint_rename(const char *a, const char *b) { const char *old = a; const char *new = b; - char *name = NULL; + struct strbuf name; int pfx_length, sfx_length; int len_a = strlen(a); int len_b = strlen(b); + int a_midlen, b_midlen; int qlen_a = quote_c_style(a, NULL, NULL, 0); int qlen_b = quote_c_style(b, NULL, NULL, 0); + strbuf_init(&name, 0); if (qlen_a || qlen_b) { - if (qlen_a) len_a = qlen_a; - if (qlen_b) len_b = qlen_b; - name = xmalloc( len_a + len_b + 5 ); - if (qlen_a) - quote_c_style(a, name, NULL, 0); - else - memcpy(name, a, len_a); - memcpy(name + len_a, " => ", 4); - if (qlen_b) - quote_c_style(b, name + len_a + 4, NULL, 0); - else - memcpy(name + len_a + 4, b, len_b + 1); - return name; + quote_c_style(a, &name, NULL, 0); + strbuf_addstr(&name, " => "); + quote_c_style(b, &name, NULL, 0); + return name.buf; } /* Find common prefix */ @@ -719,24 +691,26 @@ static char *pprint_rename(const char *a, const char *b) * pfx{sfx-a => sfx-b} * name-a => name-b */ + a_midlen = len_a - pfx_length - sfx_length; + b_midlen = len_b - pfx_length - sfx_length; + if (a_midlen < 0) + a_midlen = 0; + if (b_midlen < 0) + b_midlen = 0; + + strbuf_grow(&name, pfx_length + a_midlen + b_midlen + sfx_length + 7); if (pfx_length + sfx_length) { - int a_midlen = len_a - pfx_length - sfx_length; - int b_midlen = len_b - pfx_length - sfx_length; - if (a_midlen < 0) a_midlen = 0; - if (b_midlen < 0) b_midlen = 0; - - name = xmalloc(pfx_length + a_midlen + b_midlen + sfx_length + 7); - sprintf(name, "%.*s{%.*s => %.*s}%s", - pfx_length, a, - a_midlen, a + pfx_length, - b_midlen, b + pfx_length, - a + len_a - sfx_length); + strbuf_add(&name, a, pfx_length); + strbuf_addch(&name, '{'); } - else { - name = xmalloc(len_a + len_b + 5); - sprintf(name, "%s => %s", a, b); + strbuf_add(&name, a + pfx_length, a_midlen); + strbuf_addstr(&name, " => "); + strbuf_add(&name, b + pfx_length, b_midlen); + if (pfx_length + sfx_length) { + strbuf_addch(&name, '}'); + strbuf_add(&name, a + len_a - sfx_length, sfx_length); } - return name; + return name.buf; } struct diffstat_t { @@ -849,12 +823,13 @@ static void show_stats(struct diffstat_t* data, struct diff_options *options) int change = file->added + file->deleted; if (!file->is_renamed) { /* renames are already quoted by pprint_rename */ - len = quote_c_style(file->name, NULL, NULL, 0); - if (len) { - char *qname = xmalloc(len + 1); - quote_c_style(file->name, qname, NULL, 0); + struct strbuf buf; + strbuf_init(&buf, 0); + if (quote_c_style(file->name, &buf, NULL, 0)) { free(file->name); - file->name = qname; + file->name = buf.buf; + } else { + strbuf_release(&buf); } } @@ -992,12 +967,12 @@ static void show_numstat(struct diffstat_t* data, struct diff_options *options) printf("-\t-\t"); else printf("%d\t%d\t", file->added, file->deleted); - if (options->line_termination && !file->is_renamed && - quote_c_style(file->name, NULL, NULL, 0)) - quote_c_style(file->name, NULL, stdout, 0); - else + if (!file->is_renamed) { + write_name_quoted(file->name, stdout, options->line_termination); + } else { fputs(file->name, stdout); - putchar(options->line_termination); + putchar(options->line_termination); + } } } @@ -1941,50 +1916,46 @@ static int similarity_index(struct diff_filepair *p) static void run_diff(struct diff_filepair *p, struct diff_options *o) { const char *pgm = external_diff(); - char msg[PATH_MAX*2+300], *xfrm_msg; - struct diff_filespec *one; - struct diff_filespec *two; + struct strbuf msg; + char *xfrm_msg; + struct diff_filespec *one = p->one; + struct diff_filespec *two = p->two; const char *name; const char *other; - char *name_munged, *other_munged; int complete_rewrite = 0; - int len; + if (DIFF_PAIR_UNMERGED(p)) { - /* unmerged */ run_diff_cmd(pgm, p->one->path, NULL, NULL, NULL, NULL, o, 0); return; } - name = p->one->path; + name = p->one->path; other = (strcmp(name, p->two->path) ? p->two->path : NULL); - name_munged = quote_one(name); - other_munged = quote_one(other); - one = p->one; two = p->two; - diff_fill_sha1_info(one); diff_fill_sha1_info(two); - len = 0; + strbuf_init(&msg, PATH_MAX * 2 + 300); switch (p->status) { case DIFF_STATUS_COPIED: - len += snprintf(msg + len, sizeof(msg) - len, - "similarity index %d%%\n" - "copy from %s\n" - "copy to %s\n", - similarity_index(p), name_munged, other_munged); + strbuf_addf(&msg, "similarity index %d%%", similarity_index(p)); + strbuf_addstr(&msg, "\ncopy from "); + quote_c_style(name, &msg, NULL, 0); + strbuf_addstr(&msg, "\ncopy to "); + quote_c_style(other, &msg, NULL, 0); + strbuf_addch(&msg, '\n'); break; case DIFF_STATUS_RENAMED: - len += snprintf(msg + len, sizeof(msg) - len, - "similarity index %d%%\n" - "rename from %s\n" - "rename to %s\n", - similarity_index(p), name_munged, other_munged); + strbuf_addf(&msg, "similarity index %d%%", similarity_index(p)); + strbuf_addstr(&msg, "\nrename from "); + quote_c_style(name, &msg, NULL, 0); + strbuf_addstr(&msg, "\nrename to "); + quote_c_style(other, &msg, NULL, 0); + strbuf_addch(&msg, '\n'); break; case DIFF_STATUS_MODIFIED: if (p->score) { - len += snprintf(msg + len, sizeof(msg) - len, - "dissimilarity index %d%%\n", + strbuf_addf(&msg, "dissimilarity index %d%%\n", similarity_index(p)); complete_rewrite = 1; break; @@ -2004,19 +1975,17 @@ static void run_diff(struct diff_filepair *p, struct diff_options *o) (!fill_mmfile(&mf, two) && diff_filespec_is_binary(two))) abbrev = 40; } - len += snprintf(msg + len, sizeof(msg) - len, - "index %.*s..%.*s", + strbuf_addf(&msg, "index %.*s..%.*s", abbrev, sha1_to_hex(one->sha1), abbrev, sha1_to_hex(two->sha1)); if (one->mode == two->mode) - len += snprintf(msg + len, sizeof(msg) - len, - " %06o", one->mode); - len += snprintf(msg + len, sizeof(msg) - len, "\n"); + strbuf_addf(&msg, " %06o", one->mode); + strbuf_addch(&msg, '\n'); } - if (len) - msg[--len] = 0; - xfrm_msg = len ? msg : NULL; + if (msg.len) + strbuf_setlen(&msg, msg.len - 1); + xfrm_msg = msg.len ? msg.buf : NULL; if (!pgm && DIFF_FILE_VALID(one) && DIFF_FILE_VALID(two) && @@ -2035,8 +2004,7 @@ static void run_diff(struct diff_filepair *p, struct diff_options *o) run_diff_cmd(pgm, name, other, one, two, xfrm_msg, o, complete_rewrite); - free(name_munged); - free(other_munged); + strbuf_release(&msg); } static void run_diffstat(struct diff_filepair *p, struct diff_options *o, @@ -2492,72 +2460,30 @@ const char *diff_unique_abbrev(const unsigned char *sha1, int len) return sha1_to_hex(sha1); } -static void diff_flush_raw(struct diff_filepair *p, - struct diff_options *options) +static void diff_flush_raw(struct diff_filepair *p, struct diff_options *opt) { - int two_paths; - char status[10]; - int abbrev = options->abbrev; - const char *path_one, *path_two; - int inter_name_termination = '\t'; - int line_termination = options->line_termination; - - if (!line_termination) - inter_name_termination = 0; + int line_termination = opt->line_termination; + int inter_name_termination = line_termination ? '\t' : '\0'; - path_one = p->one->path; - path_two = p->two->path; - if (line_termination) { - path_one = quote_one(path_one); - path_two = quote_one(path_two); + if (!(opt->output_format & DIFF_FORMAT_NAME_STATUS)) { + printf(":%06o %06o %s ", p->one->mode, p->two->mode, + diff_unique_abbrev(p->one->sha1, opt->abbrev)); + printf("%s ", diff_unique_abbrev(p->two->sha1, opt->abbrev)); } - - if (p->score) - sprintf(status, "%c%03d", p->status, similarity_index(p)); - else { - status[0] = p->status; - status[1] = 0; - } - switch (p->status) { - case DIFF_STATUS_COPIED: - case DIFF_STATUS_RENAMED: - two_paths = 1; - break; - case DIFF_STATUS_ADDED: - case DIFF_STATUS_DELETED: - two_paths = 0; - break; - default: - two_paths = 0; - break; - } - if (!(options->output_format & DIFF_FORMAT_NAME_STATUS)) { - printf(":%06o %06o %s ", - p->one->mode, p->two->mode, - diff_unique_abbrev(p->one->sha1, abbrev)); - printf("%s ", - diff_unique_abbrev(p->two->sha1, abbrev)); + if (p->score) { + printf("%c%03d%c", p->status, similarity_index(p), + inter_name_termination); + } else { + printf("%c%c", p->status, inter_name_termination); } - printf("%s%c%s", status, inter_name_termination, - two_paths || p->one->mode ? path_one : path_two); - if (two_paths) - printf("%c%s", inter_name_termination, path_two); - putchar(line_termination); - if (path_one != p->one->path) - free((void*)path_one); - if (path_two != p->two->path) - free((void*)path_two); -} -static void diff_flush_name(struct diff_filepair *p, struct diff_options *opt) -{ - char *path = p->two->path; - - if (opt->line_termination) - path = quote_one(p->two->path); - printf("%s%c", path, opt->line_termination); - if (p->two->path != path) - free(path); + if (p->status == DIFF_STATUS_COPIED || p->status == DIFF_STATUS_RENAMED) { + write_name_quoted(p->one->path, stdout, inter_name_termination); + write_name_quoted(p->two->path, stdout, line_termination); + } else { + const char *path = p->one->mode ? p->one->path : p->two->path; + write_name_quoted(path, stdout, line_termination); + } } int diff_unmodified_pair(struct diff_filepair *p) @@ -2567,14 +2493,11 @@ int diff_unmodified_pair(struct diff_filepair *p) * let transformers to produce diff_filepairs any way they want, * and filter and clean them up here before producing the output. */ - struct diff_filespec *one, *two; + struct diff_filespec *one = p->one, *two = p->two; if (DIFF_PAIR_UNMERGED(p)) return 0; /* unmerged is interesting */ - one = p->one; - two = p->two; - /* deletion, addition, mode or type change * and rename are all interesting. */ @@ -2763,32 +2686,27 @@ static void flush_one_pair(struct diff_filepair *p, struct diff_options *opt) else if (fmt & (DIFF_FORMAT_RAW | DIFF_FORMAT_NAME_STATUS)) diff_flush_raw(p, opt); else if (fmt & DIFF_FORMAT_NAME) - diff_flush_name(p, opt); + write_name_quoted(p->two->path, stdout, opt->line_termination); } static void show_file_mode_name(const char *newdelete, struct diff_filespec *fs) { - char *name = quote_one(fs->path); if (fs->mode) - printf(" %s mode %06o %s\n", newdelete, fs->mode, name); + printf(" %s mode %06o ", newdelete, fs->mode); else - printf(" %s %s\n", newdelete, name); - free(name); + printf(" %s ", newdelete); + write_name_quoted(fs->path, stdout, '\n'); } static void show_mode_change(struct diff_filepair *p, int show_name) { if (p->one->mode && p->two->mode && p->one->mode != p->two->mode) { + printf(" mode change %06o => %06o%c", p->one->mode, p->two->mode, + show_name ? ' ' : '\n'); if (show_name) { - char *name = quote_one(p->two->path); - printf(" mode change %06o => %06o %s\n", - p->one->mode, p->two->mode, name); - free(name); + write_name_quoted(p->two->path, stdout, '\n'); } - else - printf(" mode change %06o => %06o\n", - p->one->mode, p->two->mode); } } @@ -2818,12 +2736,11 @@ static void diff_summary(struct diff_filepair *p) break; default: if (p->score) { - char *name = quote_one(p->two->path); - printf(" rewrite %s (%d%%)\n", name, - similarity_index(p)); - free(name); - show_mode_change(p, 0); - } else show_mode_change(p, 1); + puts(" rewrite "); + write_name_quoted(p->two->path, stdout, ' '); + printf("(%d%%)\n", similarity_index(p)); + } + show_mode_change(p, !p->score); break; } } @@ -2837,14 +2754,14 @@ struct patch_id_t { static int remove_space(char *line, int len) { int i; - char *dst = line; - unsigned char c; + char *dst = line; + unsigned char c; - for (i = 0; i < len; i++) - if (!isspace((c = line[i]))) - *dst++ = c; + for (i = 0; i < len; i++) + if (!isspace((c = line[i]))) + *dst++ = c; - return dst - line; + return dst - line; } static void patch_id_consume(void *priv, char *line, unsigned long len) diff --git a/quote.c b/quote.c index 7771c9c..b1efe18 100644 --- a/quote.c +++ b/quote.c @@ -157,83 +157,143 @@ char *sq_dequote(char *arg) } } +/* 1 means: quote as octal + * 0 means: quote as octal if (quote_path_fully) + * -1 means: never quote + * c: quote as "\\c" + */ +#define X8(x) x, x, x, x, x, x, x, x +#define X16(x) X8(x), X8(x) +static signed char const sq_lookup[256] = { + /* 0 1 2 3 4 5 6 7 */ + /* 0x00 */ 1, 1, 1, 1, 1, 1, 1, 'a', + /* 0x08 */ 'b', 't', 'n', 'v', 'f', 'r', 1, 1, + /* 0x10 */ X16(1), + /* 0x20 */ -1, -1, '"', -1, -1, -1, -1, -1, + /* 0x28 */ X16(-1), X16(-1), X16(-1), + /* 0x58 */ -1, -1, -1, -1,'\\', -1, -1, -1, + /* 0x60 */ X16(-1), X8(-1), + /* 0x78 */ -1, -1, -1, -1, -1, -1, -1, 1, + /* 0x80 */ /* set to 0 */ +}; + +static inline int sq_must_quote(char c) { + return sq_lookup[(unsigned char)c] + quote_path_fully > 0; +} + +/* returns the longest prefix not needing a quote up to maxlen if positive. + This stops at the first \0 because it's marked as a character needing an + escape */ +static size_t next_quote_pos(const char *s, ssize_t maxlen) +{ + size_t len; + if (maxlen < 0) { + for (len = 0; !sq_must_quote(s[len]); len++); + } else { + for (len = 0; len < maxlen && !sq_must_quote(s[len]); len++); + } + return len; +} + /* * C-style name quoting. * - * Does one of three things: - * - * (1) if outbuf and outfp are both NULL, inspect the input name and - * counts the number of bytes that are needed to hold c_style - * quoted version of name, counting the double quotes around - * it but not terminating NUL, and returns it. However, if name - * does not need c_style quoting, it returns 0. - * - * (2) if outbuf is not NULL, it must point at a buffer large enough - * to hold the c_style quoted version of name, enclosing double - * quotes, and terminating NUL. Fills outbuf with c_style quoted - * version of name enclosed in double-quote pair. Return value - * is undefined. + * (1) if sb and fp are both NULL, inspect the input name and counts the + * number of bytes that are needed to hold c_style quoted version of name, + * counting the double quotes around it but not terminating NUL, and + * returns it. + * However, if name does not need c_style quoting, it returns 0. * - * (3) if outfp is not NULL, outputs c_style quoted version of name, - * but not enclosed in double-quote pair. Return value is undefined. + * (2) if sb or fp are not NULL, it emits the c_style quoted version + * of name, enclosed with double quotes if asked and needed only. + * Return value is the same as in (1). */ - -static int quote_c_style_counted(const char *name, int namelen, - char *outbuf, FILE *outfp, int no_dq) +static size_t quote_c_style_counted(const char *name, ssize_t maxlen, + struct strbuf *sb, FILE *fp, int no_dq) { #undef EMIT -#define EMIT(c) \ - (outbuf ? (*outbuf++ = (c)) : outfp ? fputc(c, outfp) : (count++)) - -#define EMITQ() EMIT('\\') +#define EMIT(c) \ + do { \ + if (sb) strbuf_addch(sb, (c)); \ + if (fp) fputc((c), fp); \ + count++; \ + } while (0) +#define EMITBUF(s, l) \ + do { \ + if (sb) strbuf_add(sb, (s), (l)); \ + if (fp) fwrite((s), (l), 1, fp); \ + count += (l); \ + } while (0) + + size_t len, count = 0; + const char *p = name; - const char *sp; - unsigned char ch; - int count = 0, needquote = 0; + for (;;) { + int ch; - if (!no_dq) - EMIT('"'); - for (sp = name; sp < name + namelen; sp++) { - ch = *sp; - if (!ch) + len = next_quote_pos(p, maxlen); + if (len == maxlen || !p[len]) break; - if ((ch < ' ') || (ch == '"') || (ch == '\\') || - (quote_path_fully && (ch >= 0177))) { - needquote = 1; - switch (ch) { - case '\a': EMITQ(); ch = 'a'; break; - case '\b': EMITQ(); ch = 'b'; break; - case '\f': EMITQ(); ch = 'f'; break; - case '\n': EMITQ(); ch = 'n'; break; - case '\r': EMITQ(); ch = 'r'; break; - case '\t': EMITQ(); ch = 't'; break; - case '\v': EMITQ(); ch = 'v'; break; - - case '\\': /* fallthru */ - case '"': EMITQ(); break; - default: - /* octal */ - EMITQ(); - EMIT(((ch >> 6) & 03) + '0'); - EMIT(((ch >> 3) & 07) + '0'); - ch = (ch & 07) + '0'; - break; - } + + if (!no_dq && p == name) + EMIT('"'); + + EMITBUF(p, len); + EMIT('\\'); + p += len; + ch = (unsigned char)*p++; + if (sq_lookup[ch] >= ' ') { + EMIT(sq_lookup[ch]); + } else { + EMIT(((ch >> 6) & 03) + '0'); + EMIT(((ch >> 3) & 07) + '0'); + EMIT(((ch >> 0) & 07) + '0'); } - EMIT(ch); } + + EMITBUF(p, len); + if (p == name) /* no ending quote needed */ + return 0; + if (!no_dq) EMIT('"'); - if (outbuf) - *outbuf = 0; + return count; +} - return needquote ? count : 0; +size_t quote_c_style(const char *name, struct strbuf *sb, FILE *fp, int nodq) +{ + return quote_c_style_counted(name, -1, sb, fp, nodq); } -int quote_c_style(const char *name, char *outbuf, FILE *outfp, int no_dq) +void write_name_quoted(const char *name, FILE *fp, int terminator) { - int cnt = strlen(name); - return quote_c_style_counted(name, cnt, outbuf, outfp, no_dq); + if (terminator) { + quote_c_style(name, NULL, fp, 0); + } else { + fputs(name, fp); + } + fputc(terminator, fp); +} + +extern void write_name_quotedpfx(const char *pfx, size_t pfxlen, + const char *name, FILE *fp, int terminator) +{ + int needquote = 0; + + if (terminator) { + needquote = next_quote_pos(pfx, pfxlen) < pfxlen + || name[next_quote_pos(name, -1)]; + } + if (needquote) { + fputc('"', fp); + quote_c_style_counted(pfx, pfxlen, NULL, fp, 1); + quote_c_style(name, NULL, fp, 1); + fputc('"', fp); + } else { + fwrite(pfx, pfxlen, 1, fp); + fputs(name, fp); + } + fputc(terminator, fp); } /* @@ -306,37 +366,6 @@ int unquote_c_style(struct strbuf *sb, const char *quoted, const char **endp) return -1; } -void write_name_quoted(const char *prefix, int prefix_len, - const char *name, int quote, FILE *out) -{ - int needquote; - - if (!quote) { - no_quote: - if (prefix_len) - fprintf(out, "%.*s", prefix_len, prefix); - fputs(name, out); - return; - } - - needquote = 0; - if (prefix_len) - needquote = quote_c_style_counted(prefix, prefix_len, - NULL, NULL, 0); - if (!needquote) - needquote = quote_c_style(name, NULL, NULL, 0); - if (needquote) { - fputc('"', out); - if (prefix_len) - quote_c_style_counted(prefix, prefix_len, - NULL, out, 1); - quote_c_style(name, NULL, out, 1); - fputc('"', out); - } - else - goto no_quote; -} - /* quoting as a string literal for other languages */ void perl_quote_print(FILE *stream, const char *src) diff --git a/quote.h b/quote.h index f48a3fc..2769f71 100644 --- a/quote.h +++ b/quote.h @@ -44,11 +44,11 @@ extern int add_to_string(char **ptrp, int *sizep, const char *str, int quote); extern char *sq_dequote(char *); extern int unquote_c_style(struct strbuf *, const char *quoted, const char **endp); -extern int quote_c_style(const char *name, char *outbuf, FILE *outfp, - int nodq); +extern size_t quote_c_style(const char *name, struct strbuf *, FILE *, int no_dq); -extern void write_name_quoted(const char *prefix, int prefix_len, - const char *name, int quote, FILE *out); +extern void write_name_quoted(const char *name, FILE *, int terminator); +extern void write_name_quotedpfx(const char *pfx, size_t pfxlen, + const char *name, FILE *, int terminator); /* quoting as a string literal for other languages */ extern void perl_quote_print(FILE *stream, const char *src); -- cgit v0.10.2-6-g49f6 From 7a33bcbe802080f3a926e93d66b65ff7c5e8c5ed Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Thu, 20 Sep 2007 00:42:13 +0200 Subject: sq_quote_argv and add_to_string rework with strbuf's. * sq_quote_buf is made public, and works on a strbuf. * sq_quote_argv also works on a strbuf. * make sq_quote_argv take a "maxlen" argument to check the buffer won't grow too big. Signed-off-by: Pierre Habouzit Signed-off-by: Junio C Hamano diff --git a/connect.c b/connect.c index 1653a0e..06d279e 100644 --- a/connect.c +++ b/connect.c @@ -577,16 +577,13 @@ pid_t git_connect(int fd[2], char *url, const char *prog, int flags) if (pid < 0) die("unable to fork"); if (!pid) { - char command[MAX_CMD_LEN]; - char *posn = command; - int size = MAX_CMD_LEN; - int of = 0; + struct strbuf cmd; - of |= add_to_string(&posn, &size, prog, 0); - of |= add_to_string(&posn, &size, " ", 0); - of |= add_to_string(&posn, &size, path, 1); - - if (of) + strbuf_init(&cmd, MAX_CMD_LEN); + strbuf_addstr(&cmd, prog); + strbuf_addch(&cmd, ' '); + sq_quote_buf(&cmd, path); + if (cmd.len >= MAX_CMD_LEN) die("command line too long"); dup2(pipefd[1][0], 0); @@ -606,10 +603,10 @@ pid_t git_connect(int fd[2], char *url, const char *prog, int flags) ssh_basename++; if (!port) - execlp(ssh, ssh_basename, host, command, NULL); + execlp(ssh, ssh_basename, host, cmd.buf, NULL); else execlp(ssh, ssh_basename, "-p", port, host, - command, NULL); + cmd.buf, NULL); } else { unsetenv(ALTERNATE_DB_ENVIRONMENT); @@ -618,7 +615,7 @@ pid_t git_connect(int fd[2], char *url, const char *prog, int flags) unsetenv(GIT_WORK_TREE_ENVIRONMENT); unsetenv(GRAFT_ENVIRONMENT); unsetenv(INDEX_ENVIRONMENT); - execlp("sh", "sh", "-c", command, NULL); + execlp("sh", "sh", "-c", cmd.buf, NULL); } die("exec failed"); } diff --git a/git.c b/git.c index 56ae8cc..9eaca1d 100644 --- a/git.c +++ b/git.c @@ -187,19 +187,13 @@ static int handle_alias(int *argcp, const char ***argv) if (alias_string) { if (alias_string[0] == '!') { if (*argcp > 1) { - int i, sz = PATH_MAX; - char *s = xmalloc(sz), *new_alias = s; + struct strbuf buf; - add_to_string(&s, &sz, alias_string, 0); + strbuf_init(&buf, PATH_MAX); + strbuf_addstr(&buf, alias_string); + sq_quote_argv(&buf, (*argv) + 1, *argcp - 1, PATH_MAX); free(alias_string); - alias_string = new_alias; - for (i = 1; i < *argcp && - !add_to_string(&s, &sz, " ", 0) && - !add_to_string(&s, &sz, (*argv)[i], 1) - ; i++) - ; /* do nothing */ - if (!sz) - die("Too many or long arguments"); + alias_string = buf.buf; } trace_printf("trace: alias to shell cmd: %s => %s\n", alias_command, alias_string + 1); diff --git a/quote.c b/quote.c index b1efe18..800fd88 100644 --- a/quote.c +++ b/quote.c @@ -12,37 +12,31 @@ * a'b ==> a'\''b ==> 'a'\''b' * a!b ==> a'\!'b ==> 'a'\!'b' */ -#undef EMIT -#define EMIT(x) do { if (++len < n) *bp++ = (x); } while(0) - static inline int need_bs_quote(char c) { return (c == '\'' || c == '!'); } -static size_t sq_quote_buf(char *dst, size_t n, const char *src) +void sq_quote_buf(struct strbuf *dst, const char *src) { - char c; - char *bp = dst; - size_t len = 0; - - EMIT('\''); - while ((c = *src++)) { - if (need_bs_quote(c)) { - EMIT('\''); - EMIT('\\'); - EMIT(c); - EMIT('\''); - } else { - EMIT(c); + char *to_free = NULL; + + if (dst->buf == src) + to_free = strbuf_detach(dst); + + strbuf_addch(dst, '\''); + while (*src) { + size_t len = strcspn(src, "'\\"); + strbuf_add(dst, src, len); + src += len; + while (need_bs_quote(*src)) { + strbuf_addstr(dst, "'\\"); + strbuf_addch(dst, *src++); + strbuf_addch(dst, '\''); } } - EMIT('\''); - - if ( n ) - *bp = 0; - - return len; + strbuf_addch(dst, '\''); + free(to_free); } void sq_quote_print(FILE *stream, const char *src) @@ -62,11 +56,10 @@ void sq_quote_print(FILE *stream, const char *src) fputc('\'', stream); } -char *sq_quote_argv(const char** argv, int count) +void sq_quote_argv(struct strbuf *dst, const char** argv, int count, + size_t maxlen) { - char *buf, *to; int i; - size_t len = 0; /* Count argv if needed. */ if (count < 0) { @@ -74,53 +67,14 @@ char *sq_quote_argv(const char** argv, int count) ; /* just counting */ } - /* Special case: no argv. */ - if (!count) - return xcalloc(1,1); - - /* Get destination buffer length. */ - for (i = 0; i < count; i++) - len += sq_quote_buf(NULL, 0, argv[i]) + 1; - - /* Alloc destination buffer. */ - to = buf = xmalloc(len + 1); - /* Copy into destination buffer. */ + strbuf_grow(dst, 32 * count); for (i = 0; i < count; ++i) { - *to++ = ' '; - to += sq_quote_buf(to, len, argv[i]); + strbuf_addch(dst, ' '); + sq_quote_buf(dst, argv[i]); + if (maxlen && dst->len > maxlen) + die("Too many or long arguments"); } - - return buf; -} - -/* - * Append a string to a string buffer, with or without shell quoting. - * Return true if the buffer overflowed. - */ -int add_to_string(char **ptrp, int *sizep, const char *str, int quote) -{ - char *p = *ptrp; - int size = *sizep; - int oc; - int err = 0; - - if (quote) - oc = sq_quote_buf(p, size, str); - else { - oc = strlen(str); - memcpy(p, str, (size <= oc) ? size - 1 : oc); - } - - if (size <= oc) { - err = 1; - oc = size - 1; - } - - *ptrp += oc; - **ptrp = '\0'; - *sizep -= oc; - return err; } char *sq_dequote(char *arg) diff --git a/quote.h b/quote.h index 2769f71..4287990 100644 --- a/quote.h +++ b/quote.h @@ -29,13 +29,10 @@ */ extern void sq_quote_print(FILE *stream, const char *src); -extern char *sq_quote_argv(const char** argv, int count); -/* - * Append a string to a string buffer, with or without shell quoting. - * Return true if the buffer overflowed. - */ -extern int add_to_string(char **ptrp, int *sizep, const char *str, int quote); +extern void sq_quote_buf(struct strbuf *, const char *src); +extern void sq_quote_argv(struct strbuf *, const char **argv, int count, + size_t maxlen); /* This unwraps what sq_quote() produces in place, but returns * NULL if the input does not look like what sq_quote would have diff --git a/rsh.c b/rsh.c index 5754a23..016d72e 100644 --- a/rsh.c +++ b/rsh.c @@ -10,12 +10,9 @@ int setup_connection(int *fd_in, int *fd_out, const char *remote_prog, char *host; char *path; int sv[2]; - char command[COMMAND_SIZE]; - char *posn; - int sizen; - int of; int i; pid_t pid; + struct strbuf cmd; if (!strcmp(url, "-")) { *fd_in = 0; @@ -36,24 +33,23 @@ int setup_connection(int *fd_in, int *fd_out, const char *remote_prog, if (!path) { return error("Bad URL: %s", url); } + /* $GIT_RSH "env GIT_DIR= " */ - sizen = COMMAND_SIZE; - posn = command; - of = 0; - of |= add_to_string(&posn, &sizen, "env ", 0); - of |= add_to_string(&posn, &sizen, GIT_DIR_ENVIRONMENT "=", 0); - of |= add_to_string(&posn, &sizen, path, 1); - of |= add_to_string(&posn, &sizen, " ", 0); - of |= add_to_string(&posn, &sizen, remote_prog, 1); + strbuf_init(&cmd, COMMAND_SIZE); + strbuf_addstr(&cmd, "env "); + strbuf_addstr(&cmd, GIT_DIR_ENVIRONMENT "="); + sq_quote_buf(&cmd, path); + strbuf_addch(&cmd, ' '); + sq_quote_buf(&cmd, remote_prog); - for ( i = 0 ; i < rmt_argc ; i++ ) { - of |= add_to_string(&posn, &sizen, " ", 0); - of |= add_to_string(&posn, &sizen, rmt_argv[i], 1); + for (i = 0 ; i < rmt_argc ; i++) { + strbuf_addch(&cmd, ' '); + sq_quote_buf(&cmd, rmt_argv[i]); } - of |= add_to_string(&posn, &sizen, " -", 0); + strbuf_addstr(&cmd, " -"); - if ( of ) + if (cmd.len >= COMMAND_SIZE) return error("Command line too long"); if (socketpair(AF_UNIX, SOCK_STREAM, 0, sv)) @@ -74,7 +70,7 @@ int setup_connection(int *fd_in, int *fd_out, const char *remote_prog, close(sv[1]); dup2(sv[0], 0); dup2(sv[0], 1); - execlp(ssh, ssh_basename, host, command, NULL); + execlp(ssh, ssh_basename, host, cmd.buf, NULL); } close(sv[0]); *fd_in = sv[1]; diff --git a/trace.c b/trace.c index 91548a5..69fa05e 100644 --- a/trace.c +++ b/trace.c @@ -64,7 +64,7 @@ static const char err_msg[] = "Could not trace into fd given by " void trace_printf(const char *fmt, ...) { - char buf[8192]; + struct strbuf buf; va_list ap; int fd, len, need_close = 0; @@ -72,12 +72,22 @@ void trace_printf(const char *fmt, ...) if (!fd) return; + strbuf_init(&buf, 0); va_start(ap, fmt); - len = vsnprintf(buf, sizeof(buf), fmt, ap); + len = vsnprintf(buf.buf, strbuf_avail(&buf), fmt, ap); va_end(ap); - if (len >= sizeof(buf)) - die("unreasonnable trace length"); - write_or_whine_pipe(fd, buf, len, err_msg); + if (len >= strbuf_avail(&buf)) { + strbuf_grow(&buf, len - strbuf_avail(&buf) + 128); + va_start(ap, fmt); + len = vsnprintf(buf.buf, strbuf_avail(&buf), fmt, ap); + va_end(ap); + if (len >= strbuf_avail(&buf)) + die("broken vsnprintf"); + } + strbuf_setlen(&buf, len); + + write_or_whine_pipe(fd, buf.buf, buf.len, err_msg); + strbuf_release(&buf); if (need_close) close(fd); @@ -85,31 +95,32 @@ void trace_printf(const char *fmt, ...) void trace_argv_printf(const char **argv, int count, const char *fmt, ...) { - char buf[8192]; + struct strbuf buf; va_list ap; - char *argv_str; - size_t argv_len; int fd, len, need_close = 0; fd = get_trace_fd(&need_close); if (!fd) return; + strbuf_init(&buf, 0); va_start(ap, fmt); - len = vsnprintf(buf, sizeof(buf), fmt, ap); + len = vsnprintf(buf.buf, strbuf_avail(&buf), fmt, ap); va_end(ap); - if (len >= sizeof(buf)) - die("unreasonnable trace length"); - - /* Get the argv string. */ - argv_str = sq_quote_argv(argv, count); - argv_len = strlen(argv_str); - - write_or_whine_pipe(fd, buf, len, err_msg); - write_or_whine_pipe(fd, argv_str, argv_len, err_msg); - write_or_whine_pipe(fd, "\n", 1, err_msg); + if (len >= strbuf_avail(&buf)) { + strbuf_grow(&buf, len - strbuf_avail(&buf) + 128); + va_start(ap, fmt); + len = vsnprintf(buf.buf, strbuf_avail(&buf), fmt, ap); + va_end(ap); + if (len >= strbuf_avail(&buf)) + die("broken vsnprintf"); + } + strbuf_setlen(&buf, len); - free(argv_str); + sq_quote_argv(&buf, argv, count, 0); + strbuf_addch(&buf, '\n'); + write_or_whine_pipe(fd, buf.buf, buf.len, err_msg); + strbuf_release(&buf); if (need_close) close(fd); -- cgit v0.10.2-6-g49f6 From a8f3e2219c237661a30b54fe23d58e055f0b548c Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Wed, 26 Sep 2007 02:26:06 -0700 Subject: strbuf_setlen(): do not barf on setting length of an empty buffer to 0 strbuf_setlen() expect to be able to NUL terminate the buffer, but a completely empty strbuf could have an empty buffer with 0 allocation; both the assert() and the assignment for NUL termination would fail. Signed-off-by: Junio C Hamano diff --git a/strbuf.h b/strbuf.h index 567e2d1..3b19de3 100644 --- a/strbuf.h +++ b/strbuf.h @@ -65,14 +65,17 @@ static inline void strbuf_swap(struct strbuf *a, struct strbuf *b) { static inline size_t strbuf_avail(struct strbuf *sb) { return sb->alloc ? sb->alloc - sb->len - 1 : 0; } + +extern void strbuf_grow(struct strbuf *, size_t); + static inline void strbuf_setlen(struct strbuf *sb, size_t len) { - assert (len < sb->alloc); + if (!sb->alloc) + strbuf_grow(sb, 0); + assert(len < sb->alloc); sb->len = len; sb->buf[len] = '\0'; } -extern void strbuf_grow(struct strbuf *, size_t); - /*----- content related -----*/ extern void strbuf_rtrim(struct strbuf *); -- cgit v0.10.2-6-g49f6 From 45f66f64636350b67eaf6832b0c424592be6ddda Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Mon, 24 Sep 2007 11:25:03 +0200 Subject: Add strbuf_cmp. Signed-off-by: Junio C Hamano diff --git a/strbuf.c b/strbuf.c index dcb725d..d5e92ee 100644 --- a/strbuf.c +++ b/strbuf.c @@ -50,6 +50,18 @@ void strbuf_rtrim(struct strbuf *sb) sb->buf[sb->len] = '\0'; } +int strbuf_cmp(struct strbuf *a, struct strbuf *b) +{ + int cmp; + if (a->len < b->len) { + cmp = memcmp(a->buf, b->buf, a->len); + return cmp ? cmp : -1; + } else { + cmp = memcmp(a->buf, b->buf, b->len); + return cmp ? cmp : a->len != b->len; + } +} + void strbuf_splice(struct strbuf *sb, size_t pos, size_t len, const void *data, size_t dlen) { diff --git a/strbuf.h b/strbuf.h index 3b19de3..fd68389 100644 --- a/strbuf.h +++ b/strbuf.h @@ -78,6 +78,7 @@ static inline void strbuf_setlen(struct strbuf *sb, size_t len) { /*----- content related -----*/ extern void strbuf_rtrim(struct strbuf *); +extern int strbuf_cmp(struct strbuf *, struct strbuf *); /*----- add data in your buffer -----*/ static inline void strbuf_addch(struct strbuf *sb, int c) { -- cgit v0.10.2-6-g49f6 From 8289b6209552a57c255561a2585d0edbe96d62d3 Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Mon, 24 Sep 2007 11:25:04 +0200 Subject: Make builtin-rerere use of strbuf nicer and more efficient. memory is now reused across hunks. Signed-off-by: Junio C Hamano diff --git a/builtin-rerere.c b/builtin-rerere.c index 58288f6..d331772 100644 --- a/builtin-rerere.c +++ b/builtin-rerere.c @@ -72,13 +72,9 @@ static int handle_file(const char *path, SHA_CTX ctx; char buf[1024]; int hunk = 0, hunk_no = 0; - struct strbuf minus, plus; - struct strbuf *one = &minus, *two = + + struct strbuf one, two; FILE *f = fopen(path, "r"); - FILE *out; - - strbuf_init(&minus, 0); - strbuf_init(&plus, 0); + FILE *out = NULL; if (!f) return error("Could not open %s", path); @@ -89,51 +85,48 @@ static int handle_file(const char *path, fclose(f); return error("Could not write %s", output); } - } else - out = NULL; + } if (sha1) SHA1_Init(&ctx); + strbuf_init(&one, 0); + strbuf_init(&two, 0); while (fgets(buf, sizeof(buf), f)) { if (!prefixcmp(buf, "<<<<<<< ")) hunk = 1; else if (!prefixcmp(buf, "=======")) hunk = 2; else if (!prefixcmp(buf, ">>>>>>> ")) { - int one_is_longer = (one->len > two->len); - int common_len = one_is_longer ? two->len : one->len; - int cmp = memcmp(one->buf, two->buf, common_len); + int cmp = strbuf_cmp(&one, &two); hunk_no++; hunk = 0; - if ((cmp > 0) || ((cmp == 0) && one_is_longer)) { - struct strbuf *swap = one; - one = two; - two = swap; + if (cmp > 0) { + strbuf_swap(&one, &two); } if (out) { fputs("<<<<<<<\n", out); - fwrite(one->buf, one->len, 1, out); + fwrite(one.buf, one.len, 1, out); fputs("=======\n", out); - fwrite(two->buf, two->len, 1, out); + fwrite(two.buf, two.len, 1, out); fputs(">>>>>>>\n", out); } if (sha1) { - SHA1_Update(&ctx, one->buf, one->len); - SHA1_Update(&ctx, "\0", 1); - SHA1_Update(&ctx, two->buf, two->len); - SHA1_Update(&ctx, "\0", 1); + SHA1_Update(&ctx, one.buf, one.len + 1); + SHA1_Update(&ctx, two.buf, two.len + 1); } - strbuf_release(one); - strbuf_release(two); + strbuf_reset(&one); + strbuf_reset(&two); } else if (hunk == 1) - strbuf_addstr(one, buf); + strbuf_addstr(&one, buf); else if (hunk == 2) - strbuf_addstr(two, buf); + strbuf_addstr(&two, buf); else if (out) fputs(buf, out); } + strbuf_release(&one); + strbuf_release(&two); fclose(f); if (out) -- cgit v0.10.2-6-g49f6 From 1dffb8fa8056860e769f3a0c6e232d436f5a5c17 Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Tue, 25 Sep 2007 10:22:44 +0200 Subject: Small cache_tree_write refactor. This function cannot fail, make it void. Also make write_one act on a const char* instead of a char*. Signed-off-by: Pierre Habouzit Signed-off-by: Junio C Hamano diff --git a/cache-tree.c b/cache-tree.c index 5471844..50b3526 100644 --- a/cache-tree.c +++ b/cache-tree.c @@ -369,10 +369,8 @@ int cache_tree_update(struct cache_tree *it, return 0; } -static void write_one(struct cache_tree *it, - char *path, - int pathlen, - struct strbuf *buffer) +static void write_one(struct strbuf *buffer, struct cache_tree *it, + const char *path, int pathlen) { int i; @@ -407,20 +405,13 @@ static void write_one(struct cache_tree *it, prev->name, prev->namelen) <= 0) die("fatal - unsorted cache subtree"); } - write_one(down->cache_tree, down->name, down->namelen, buffer); + write_one(buffer, down->cache_tree, down->name, down->namelen); } } -void *cache_tree_write(struct cache_tree *root, unsigned long *size_p) +void cache_tree_write(struct strbuf *sb, struct cache_tree *root) { - char path[PATH_MAX]; - struct strbuf buffer; - - path[0] = 0; - strbuf_init(&buffer, 0); - write_one(root, path, 0, &buffer); - *size_p = buffer.len; - return strbuf_detach(&buffer); + write_one(sb, root, "", 0); } static struct cache_tree *read_one(const char **buffer, unsigned long *size_p) diff --git a/cache-tree.h b/cache-tree.h index 119407e..8243228 100644 --- a/cache-tree.h +++ b/cache-tree.h @@ -22,7 +22,7 @@ void cache_tree_free(struct cache_tree **); void cache_tree_invalidate_path(struct cache_tree *, const char *); struct cache_tree_sub *cache_tree_sub(struct cache_tree *, const char *); -void *cache_tree_write(struct cache_tree *root, unsigned long *size_p); +void cache_tree_write(struct strbuf *, struct cache_tree *root); struct cache_tree *cache_tree_read(const char *buffer, unsigned long size); int cache_tree_fully_valid(struct cache_tree *); diff --git a/read-cache.c b/read-cache.c index 2e40a34..56202d1 100644 --- a/read-cache.c +++ b/read-cache.c @@ -1136,7 +1136,7 @@ int write_index(struct index_state *istate, int newfd) { SHA_CTX c; struct cache_header hdr; - int i, removed; + int i, err, removed; struct cache_entry **cache = istate->cache; int entries = istate->cache_nr; @@ -1165,16 +1165,15 @@ int write_index(struct index_state *istate, int newfd) /* Write extension data here */ if (istate->cache_tree) { - unsigned long sz; - void *data = cache_tree_write(istate->cache_tree, &sz); - if (data && - !write_index_ext_header(&c, newfd, CACHE_EXT_TREE, sz) && - !ce_write(&c, newfd, data, sz)) - free(data); - else { - free(data); + struct strbuf sb; + + strbuf_init(&sb, 0); + cache_tree_write(&sb, istate->cache_tree); + err = write_index_ext_header(&c, newfd, CACHE_EXT_TREE, sb.len) < 0 + || ce_write(&c, newfd, sb.buf, sb.len) < 0; + strbuf_release(&sb); + if (err) return -1; - } } return ce_flush(&c, newfd); } -- cgit v0.10.2-6-g49f6 From b4833a2c62578bdbfd300e296702214cb1b9a601 Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Wed, 26 Sep 2007 23:34:01 -0700 Subject: rerere: Fix use of an empty strbuf.buf The code incorrectly assumed that strbuf.buf is always an allocated piece of memory that has NUL at offset strbuf.len. That assumption does not hold for a freshly initialized empty strbuf. Signed-off-by: Junio C Hamano diff --git a/builtin-rerere.c b/builtin-rerere.c index d331772..b820674 100644 --- a/builtin-rerere.c +++ b/builtin-rerere.c @@ -113,8 +113,10 @@ static int handle_file(const char *path, fputs(">>>>>>>\n", out); } if (sha1) { - SHA1_Update(&ctx, one.buf, one.len + 1); - SHA1_Update(&ctx, two.buf, two.len + 1); + SHA1_Update(&ctx, one.buf ? one.buf : "", + one.len + 1); + SHA1_Update(&ctx, two.buf ? two.buf : "", + two.len + 1); } strbuf_reset(&one); strbuf_reset(&two); -- cgit v0.10.2-6-g49f6 From a9390b9fcefb18c4ccdb521086a051bc9112e03d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Kristian=20H=C3=B8gsberg?= Date: Mon, 17 Sep 2007 20:06:46 -0400 Subject: Add strbuf_read_file(). MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Kristian Høgsberg Signed-off-by: Junio C Hamano diff --git a/builtin-tag.c b/builtin-tag.c index 82ebda1..fcbf9bb 100644 --- a/builtin-tag.c +++ b/builtin-tag.c @@ -22,7 +22,6 @@ static void launch_editor(const char *path, struct strbuf *buffer) const char *editor, *terminal; struct child_process child; const char *args[3]; - int fd; editor = getenv("GIT_EDITOR"); if (!editor && editor_program) @@ -52,13 +51,9 @@ static void launch_editor(const char *path, struct strbuf *buffer) if (run_command(&child)) die("There was a problem with the editor %s.", editor); - fd = open(path, O_RDONLY); - if (fd < 0) - die("could not open '%s': %s", path, strerror(errno)); - if (strbuf_read(buffer, fd, 0) < 0) { - die("could not read message file '%s': %s", path, strerror(errno)); - } - close(fd); + if (strbuf_read_file(buffer, path) < 0) + die("could not read message file '%s': %s", + path, strerror(errno)); } struct tag_filter { diff --git a/strbuf.c b/strbuf.c index d5e92ee..d1e338b 100644 --- a/strbuf.c +++ b/strbuf.c @@ -177,3 +177,18 @@ int strbuf_getline(struct strbuf *sb, FILE *fp, int term) sb->buf[sb->len] = '\0'; return 0; } + +int strbuf_read_file(struct strbuf *sb, const char *path) +{ + int fd, len; + + fd = open(path, O_RDONLY); + if (fd < 0) + return -1; + len = strbuf_read(sb, fd, 0); + close(fd); + if (len < 0) + return -1; + + return len; +} diff --git a/strbuf.h b/strbuf.h index fd68389..d4d9e56 100644 --- a/strbuf.h +++ b/strbuf.h @@ -108,6 +108,7 @@ extern void strbuf_addf(struct strbuf *sb, const char *fmt, ...); extern size_t strbuf_fread(struct strbuf *, size_t, FILE *); /* XXX: if read fails, any partial read is undone */ extern ssize_t strbuf_read(struct strbuf *, int fd, size_t hint); +extern int strbuf_read_file(struct strbuf *sb, const char *path); extern int strbuf_getline(struct strbuf *, FILE *, int); -- cgit v0.10.2-6-g49f6 From 6d69b6f6ac27ab6f71a10da34b813ca25fd2a358 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Kristian=20H=C3=B8gsberg?= Date: Mon, 17 Sep 2007 20:06:45 -0400 Subject: Clean up stripspace a bit, use strbuf even more. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Kristian Høgsberg Signed-off-by: Junio C Hamano diff --git a/builtin-stripspace.c b/builtin-stripspace.c index 1ce2847..c0b2130 100644 --- a/builtin-stripspace.c +++ b/builtin-stripspace.c @@ -8,17 +8,13 @@ */ static size_t cleanup(char *line, size_t len) { - if (len) { - if (line[len - 1] == '\n') - len--; - - while (len) { - unsigned char c = line[len - 1]; - if (!isspace(c)) - break; - len--; - } + while (len) { + unsigned char c = line[len - 1]; + if (!isspace(c)) + break; + len--; } + return len; } @@ -34,42 +30,42 @@ static size_t cleanup(char *line, size_t len) * If the input has only empty lines and spaces, * no output will be produced. * - * If last line has a newline at the end, it will be removed. + * If last line does not have a newline at the end, one is added. * * Enable skip_comments to skip every line starting with "#". */ -size_t stripspace(char *buffer, size_t length, int skip_comments) +void stripspace(struct strbuf *sb, int skip_comments) { - int empties = -1; + int empties = 0; size_t i, j, len, newlen; char *eol; - for (i = j = 0; i < length; i += len, j += newlen) { - eol = memchr(buffer + i, '\n', length - i); - len = eol ? eol - (buffer + i) + 1 : length - i; + /* We may have to add a newline. */ + strbuf_grow(sb, 1); - if (skip_comments && len && buffer[i] == '#') { + for (i = j = 0; i < sb->len; i += len, j += newlen) { + eol = memchr(sb->buf + i, '\n', sb->len - i); + len = eol ? eol - (sb->buf + i) + 1 : sb->len - i; + + if (skip_comments && len && sb->buf[i] == '#') { newlen = 0; continue; } - newlen = cleanup(buffer + i, len); + newlen = cleanup(sb->buf + i, len); /* Not just an empty line? */ if (newlen) { - if (empties != -1) - buffer[j++] = '\n'; - if (empties > 0) - buffer[j++] = '\n'; + if (empties > 0 && j > 0) + sb->buf[j++] = '\n'; empties = 0; - memmove(buffer + j, buffer + i, newlen); - continue; + memmove(sb->buf + j, sb->buf + i, newlen); + sb->buf[newlen + j++] = '\n'; + } else { + empties++; } - if (empties < 0) - continue; - empties++; } - return j; + strbuf_setlen(sb, j); } int cmd_stripspace(int argc, const char **argv, const char *prefix) @@ -85,9 +81,7 @@ int cmd_stripspace(int argc, const char **argv, const char *prefix) if (strbuf_read(&buf, 0, 1024) < 0) die("could not read the input"); - strbuf_setlen(&buf, stripspace(buf.buf, buf.len, strip_comments)); - if (buf.len) - strbuf_addch(&buf, '\n'); + stripspace(&buf, strip_comments); write_or_die(1, buf.buf, buf.len); strbuf_release(&buf); diff --git a/builtin-tag.c b/builtin-tag.c index fcbf9bb..6132cac 100644 --- a/builtin-tag.c +++ b/builtin-tag.c @@ -291,14 +291,11 @@ static void create_tag(const unsigned char *object, const char *tag, free(path); } - strbuf_setlen(buf, stripspace(buf->buf, buf->len, 1)); + stripspace(buf, 1); if (!message && !buf->len) die("no tag message?"); - /* insert the header and add the '\n' if needed: */ - if (buf->len) - strbuf_addch(buf, '\n'); strbuf_insert(buf, 0, header_buf, header_len); if (sign && do_sign(buf) < 0) diff --git a/builtin.h b/builtin.h index 03ee7bf..d6f2c76 100644 --- a/builtin.h +++ b/builtin.h @@ -7,7 +7,6 @@ extern const char git_version_string[]; extern const char git_usage_string[]; extern void help_unknown_cmd(const char *cmd); -extern size_t stripspace(char *buffer, size_t length, int skip_comments); extern int write_tree(unsigned char *sha1, int missing_ok, const char *prefix); extern void prune_packed_objects(int); diff --git a/strbuf.h b/strbuf.h index d4d9e56..5657e3d 100644 --- a/strbuf.h +++ b/strbuf.h @@ -112,4 +112,6 @@ extern int strbuf_read_file(struct strbuf *sb, const char *path); extern int strbuf_getline(struct strbuf *, FILE *, int); +extern void stripspace(struct strbuf *buf, int skip_comments); + #endif /* STRBUF_H */ -- cgit v0.10.2-6-g49f6 From 690b61f5f13db05aa4ad0efc422bd01aef3c1367 Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Thu, 27 Sep 2007 12:51:18 +0200 Subject: double free in builtin-update-index.c path_name is either ptr that should not be freed, or a pointer to a strbuf buffer that is deallocated when exiting the loop. Don't do that ! Signed-off-by: Pierre Habouzit Signed-off-by: Junio C Hamano diff --git a/builtin-update-index.c b/builtin-update-index.c index c76879e..e1a938d 100644 --- a/builtin-update-index.c +++ b/builtin-update-index.c @@ -377,8 +377,6 @@ static void read_index_info(int line_termination) die("git-update-index: unable to update %s", path_name); } - if (path_name != ptr) - free(path_name); continue; bad_line: -- cgit v0.10.2-6-g49f6 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 diff --git a/builtin-apply.c b/builtin-apply.c index 01c9d60..740623e 100644 --- a/builtin-apply.c +++ b/builtin-apply.c @@ -178,14 +178,13 @@ static void say_patch_name(FILE *output, const char *pre, struct patch *patch, c #define CHUNKSIZE (8192) #define SLOP (16) -static void *read_patch_file(int fd, unsigned long *sizep) +static void *read_patch_file(int fd, size_t *sizep) { struct strbuf buf; strbuf_init(&buf, 0); if (strbuf_read(&buf, fd, 0) < 0) die("git-apply: read returned %s", strerror(errno)); - *sizep = buf.len; /* * Make sure that we have some slop in the buffer @@ -194,7 +193,7 @@ static void *read_patch_file(int fd, unsigned long *sizep) */ strbuf_grow(&buf, SLOP); memset(buf.buf + buf.len, 0, SLOP); - return strbuf_detach(&buf); + return strbuf_detach(&buf, sizep); } static unsigned long linelen(const char *buffer, unsigned long size) @@ -253,7 +252,7 @@ static char *find_name(const char *line, char *def, int p_value, int terminate) */ strbuf_remove(&name, 0, cp - name.buf); free(def); - return name.buf; + return strbuf_detach(&name, NULL); } } strbuf_release(&name); @@ -607,7 +606,7 @@ static char *git_header_name(char *line, int llen) if (strcmp(cp + 1, first.buf)) goto free_and_fail1; strbuf_release(&sp); - return first.buf; + return strbuf_detach(&first, NULL); } /* unquoted second */ @@ -618,7 +617,7 @@ static char *git_header_name(char *line, int llen) if (line + llen - cp != first.len + 1 || memcmp(first.buf, cp, first.len)) goto free_and_fail1; - return first.buf; + return strbuf_detach(&first, NULL); free_and_fail1: strbuf_release(&first); @@ -655,7 +654,7 @@ static char *git_header_name(char *line, int llen) isspace(name[len])) { /* Good */ strbuf_remove(&sp, 0, np - sp.buf); - return sp.buf; + return strbuf_detach(&sp, NULL); } free_and_fail2: @@ -1968,8 +1967,7 @@ static int apply_data(struct patch *patch, struct stat *st, struct cache_entry * if (apply_fragments(&buf, patch) < 0) return -1; /* note with --reject this succeeds. */ - patch->result = buf.buf; - patch->resultsize = buf.len; + patch->result = strbuf_detach(&buf, &patch->resultsize); if (0 < patch->is_delete && patch->resultsize) return error("removal patch leaves file contents"); diff --git a/builtin-archive.c b/builtin-archive.c index 843a9e3..04385de 100644 --- a/builtin-archive.c +++ b/builtin-archive.c @@ -89,7 +89,7 @@ static void format_subst(const struct commit *commit, struct strbuf fmt; if (src == buf->buf) - to_free = strbuf_detach(buf); + to_free = strbuf_detach(buf, NULL); strbuf_init(&fmt, 0); for (;;) { const char *b, *c; @@ -153,8 +153,7 @@ void *sha1_file_to_archive(const char *path, const unsigned char *sha1, strbuf_attach(&buf, buffer, *sizep, *sizep + 1); convert_to_working_tree(path, buf.buf, buf.len, &buf); convert_to_archive(path, buf.buf, buf.len, &buf, commit); - *sizep = buf.len; - buffer = buf.buf; + buffer = strbuf_detach(&buf, sizep); } return buffer; diff --git a/builtin-fetch--tool.c b/builtin-fetch--tool.c index 349b59c..1e43d79 100644 --- a/builtin-fetch--tool.c +++ b/builtin-fetch--tool.c @@ -10,7 +10,7 @@ static char *get_stdin(void) if (strbuf_read(&buf, 0, 1024) < 0) { die("error reading standard input: %s", strerror(errno)); } - return strbuf_detach(&buf); + return strbuf_detach(&buf, NULL); } static void show_new(enum object_type type, unsigned char *sha1_new) diff --git a/commit.c b/commit.c index 55b08ec..62cc74d 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, diff --git a/convert.c b/convert.c index 79c9df2..0d5e909 100644 --- a/convert.c +++ b/convert.c @@ -168,7 +168,7 @@ static int crlf_to_worktree(const char *path, const char *src, size_t len, /* are we "faking" in place editing ? */ if (src == buf->buf) - to_free = strbuf_detach(buf); + to_free = strbuf_detach(buf, NULL); strbuf_grow(buf, len + stats.lf - stats.crlf); for (;;) { @@ -464,7 +464,7 @@ static int ident_to_worktree(const char *path, const char *src, size_t len, /* are we "faking" in place editing ? */ if (src == buf->buf) - to_free = strbuf_detach(buf); + to_free = strbuf_detach(buf, NULL); hash_sha1_file(src, len, "blob", sha1); strbuf_grow(buf, len + cnt * 43); diff --git a/diff.c b/diff.c index fb6d077..ab57519 100644 --- a/diff.c +++ b/diff.c @@ -197,7 +197,7 @@ static char *quote_two(const char *one, const char *two) strbuf_addstr(&res, one); strbuf_addstr(&res, two); } - return res.buf; + return strbuf_detach(&res, NULL); } static const char *external_diff(void) @@ -662,7 +662,7 @@ static char *pprint_rename(const char *a, const char *b) quote_c_style(a, &name, NULL, 0); strbuf_addstr(&name, " => "); quote_c_style(b, &name, NULL, 0); - return name.buf; + return strbuf_detach(&name, NULL); } /* Find common prefix */ @@ -710,7 +710,7 @@ static char *pprint_rename(const char *a, const char *b) strbuf_addch(&name, '}'); strbuf_add(&name, a + len_a - sfx_length, sfx_length); } - return name.buf; + return strbuf_detach(&name, NULL); } struct diffstat_t { @@ -827,7 +827,7 @@ static void show_stats(struct diffstat_t* data, struct diff_options *options) strbuf_init(&buf, 0); if (quote_c_style(file->name, &buf, NULL, 0)) { free(file->name); - file->name = buf.buf; + file->name = strbuf_detach(&buf, NULL); } else { strbuf_release(&buf); } @@ -1519,8 +1519,7 @@ static int populate_from_stdin(struct diff_filespec *s) strerror(errno)); s->should_munmap = 0; - s->size = buf.len; - s->data = strbuf_detach(&buf); + s->data = strbuf_detach(&buf, &s->size); s->should_free = 1; return 0; } @@ -1612,8 +1611,7 @@ int diff_populate_filespec(struct diff_filespec *s, int size_only) if (convert_to_git(s->path, s->data, s->size, &buf)) { munmap(s->data, s->size); s->should_munmap = 0; - s->data = buf.buf; - s->size = buf.len; + s->data = strbuf_detach(&buf, &s->size); s->should_free = 1; } } diff --git a/entry.c b/entry.c index 4a8c73b..98f5f6d 100644 --- a/entry.c +++ b/entry.c @@ -120,8 +120,7 @@ static int write_entry(struct cache_entry *ce, char *path, const struct checkout strbuf_init(&buf, 0); if (convert_to_working_tree(ce->name, new, size, &buf)) { free(new); - new = buf.buf; - size = buf.len; + new = strbuf_detach(&buf, &size); } if (to_tempfile) { diff --git a/fast-import.c b/fast-import.c index a870a44..e9c80be 100644 --- a/fast-import.c +++ b/fast-import.c @@ -1562,7 +1562,7 @@ static int read_next_command(void) } else { struct recent_command *rc; - strbuf_detach(&command_buf); + strbuf_detach(&command_buf, NULL); stdin_eof = strbuf_getline(&command_buf, stdin, '\n'); if (stdin_eof) return EOF; diff --git a/imap-send.c b/imap-send.c index e95cdde..a429a76 100644 --- a/imap-send.c +++ b/imap-send.c @@ -1180,7 +1180,7 @@ read_message( FILE *f, msg_data_t *msg ) } while (!feof(f)); msg->len = buf.len; - msg->data = strbuf_detach(&buf); + msg->data = strbuf_detach(&buf, NULL); return msg->len; } diff --git a/quote.c b/quote.c index 800fd88..482be05 100644 --- a/quote.c +++ b/quote.c @@ -22,7 +22,7 @@ void sq_quote_buf(struct strbuf *dst, const char *src) char *to_free = NULL; if (dst->buf == src) - to_free = strbuf_detach(dst); + to_free = strbuf_detach(dst, NULL); strbuf_addch(dst, '\''); while (*src) { diff --git a/sha1_file.c b/sha1_file.c index 385c5d8..753742a 100644 --- a/sha1_file.c +++ b/sha1_file.c @@ -2340,8 +2340,7 @@ int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object, strbuf_init(&nbuf, 0); if (convert_to_git(path, buf, size, &nbuf)) { munmap(buf, size); - size = nbuf.len; - buf = nbuf.buf; + buf = strbuf_detach(&nbuf, &size); re_allocated = 1; } } diff --git a/strbuf.c b/strbuf.c index d1e338b..0e431da 100644 --- a/strbuf.c +++ b/strbuf.c @@ -1,27 +1,33 @@ #include "cache.h" +/* + * 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 + * initialized strbuf. + */ +char strbuf_slopbuf[1]; + void strbuf_init(struct strbuf *sb, size_t hint) { - memset(sb, 0, sizeof(*sb)); + sb->alloc = sb->len = 0; + sb->buf = strbuf_slopbuf; if (hint) strbuf_grow(sb, hint); } void strbuf_release(struct strbuf *sb) { - free(sb->buf); - memset(sb, 0, sizeof(*sb)); -} - -void strbuf_reset(struct strbuf *sb) -{ - if (sb->len) - strbuf_setlen(sb, 0); + if (sb->alloc) { + free(sb->buf); + strbuf_init(sb, 0); + } } -char *strbuf_detach(struct strbuf *sb) +char *strbuf_detach(struct strbuf *sb, size_t *sz) { - char *res = sb->buf; + char *res = sb->alloc ? sb->buf : NULL; + if (sz) + *sz = sb->len; strbuf_init(sb, 0); return res; } @@ -40,6 +46,8 @@ void strbuf_grow(struct strbuf *sb, size_t extra) { if (sb->len + extra + 1 <= sb->len) die("you want to use way too much memory"); + if (!sb->alloc) + sb->buf = NULL; ALLOC_GROW(sb->buf, sb->len + extra + 1, sb->alloc); } diff --git a/strbuf.h b/strbuf.h index 5657e3d..6deec78 100644 --- a/strbuf.h +++ b/strbuf.h @@ -10,8 +10,7 @@ * 1. the ->buf member is always malloc-ed, hence strbuf's can be used to * build complex strings/buffers whose final size isn't easily known. * - * It is legal to copy the ->buf pointer away. Though if you want to reuse - * the strbuf after that, setting ->buf to NULL isn't legal. + * It is NOT legal to copy the ->buf pointer away. * `strbuf_detach' is the operation that detachs a buffer from its shell * while keeping the shell valid wrt its invariants. * @@ -41,19 +40,19 @@ #include +extern char strbuf_slopbuf[]; struct strbuf { size_t alloc; size_t len; char *buf; }; -#define STRBUF_INIT { 0, 0, NULL } +#define STRBUF_INIT { 0, 0, strbuf_slopbuf } /*----- strbuf life cycle -----*/ extern void strbuf_init(struct strbuf *, size_t); extern void strbuf_release(struct strbuf *); -extern void strbuf_reset(struct strbuf *); -extern char *strbuf_detach(struct strbuf *); +extern char *strbuf_detach(struct strbuf *, size_t *); extern void strbuf_attach(struct strbuf *, void *, size_t, size_t); static inline void strbuf_swap(struct strbuf *a, struct strbuf *b) { struct strbuf tmp = *a; @@ -75,6 +74,7 @@ static inline void strbuf_setlen(struct strbuf *sb, size_t len) { sb->len = len; sb->buf[len] = '\0'; } +#define strbuf_reset(sb) strbuf_setlen(sb, 0) /*----- content related -----*/ extern void strbuf_rtrim(struct strbuf *); -- cgit v0.10.2-6-g49f6 From 387e7e19d7eb5444be8da8e99ed7491989dc1cbb Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Thu, 27 Sep 2007 15:25:55 +0200 Subject: strbuf_read_file enhancement, and use it. * make strbuf_read_file take a size hint (works like strbuf_read) * use it in a couple of places. Signed-off-by: Pierre Habouzit Signed-off-by: Junio C Hamano diff --git a/builtin-apply.c b/builtin-apply.c index 740623e..fec96a8 100644 --- a/builtin-apply.c +++ b/builtin-apply.c @@ -1425,8 +1425,6 @@ static void show_stats(struct patch *patch) static int read_old_data(struct stat *st, const char *path, struct strbuf *buf) { - int fd; - switch (st->st_mode & S_IFMT) { case S_IFLNK: strbuf_grow(buf, st->st_size); @@ -1435,14 +1433,8 @@ static int read_old_data(struct stat *st, const char *path, struct strbuf *buf) strbuf_setlen(buf, st->st_size); return 0; case S_IFREG: - fd = open(path, O_RDONLY); - if (fd < 0) - return error("unable to open %s", path); - if (strbuf_read(buf, fd, st->st_size) < 0) { - close(fd); - return -1; - } - close(fd); + if (strbuf_read_file(buf, path, st->st_size) != st->st_size) + return error("unable to open or read %s", path); convert_to_git(path, buf->buf, buf->len, buf); return 0; default: diff --git a/builtin-blame.c b/builtin-blame.c index 16c0ca8..e3112a2 100644 --- a/builtin-blame.c +++ b/builtin-blame.c @@ -2002,7 +2002,6 @@ static struct commit *fake_working_tree_commit(const char *path, const char *con unsigned char head_sha1[20]; struct strbuf buf; const char *ident; - int fd; time_t now; int size, len; struct cache_entry *ce; @@ -2041,11 +2040,8 @@ static struct commit *fake_working_tree_commit(const char *path, const char *con mode = canon_mode(st.st_mode); switch (st.st_mode & S_IFMT) { case S_IFREG: - fd = open(read_from, O_RDONLY); - if (fd < 0) - die("cannot open %s", read_from); - if (strbuf_read(&buf, fd, 0) != xsize_t(st.st_size)) - die("cannot read %s", read_from); + if (strbuf_read_file(&buf, read_from, st.st_size) != st.st_size) + die("cannot open or read %s", read_from); break; case S_IFLNK: if (readlink(read_from, buf.buf, buf.alloc) != fin_size) diff --git a/builtin-tag.c b/builtin-tag.c index 6132cac..66e5a58 100644 --- a/builtin-tag.c +++ b/builtin-tag.c @@ -51,7 +51,7 @@ static void launch_editor(const char *path, struct strbuf *buffer) if (run_command(&child)) die("There was a problem with the editor %s.", editor); - if (strbuf_read_file(buffer, path) < 0) + if (strbuf_read_file(buffer, path, 0) < 0) die("could not read message file '%s': %s", path, strerror(errno)); } @@ -356,8 +356,6 @@ int cmd_tag(int argc, const char **argv, const char *prefix) continue; } if (!strcmp(arg, "-F")) { - int fd; - annotate = 1; i++; if (i == argc) @@ -365,17 +363,14 @@ int cmd_tag(int argc, const char **argv, const char *prefix) if (message) die("only one -F or -m option is allowed."); - if (!strcmp(argv[i], "-")) - fd = 0; - else { - fd = open(argv[i], O_RDONLY); - if (fd < 0) - die("could not open '%s': %s", + if (!strcmp(argv[i], "-")) { + if (strbuf_read(&buf, 0, 1024) < 0) + die("cannot read %s", argv[i]); + } else { + if (strbuf_read_file(&buf, argv[i], 1024) < 0) + die("could not open or read '%s': %s", argv[i], strerror(errno)); } - if (strbuf_read(&buf, fd, 1024) < 0) { - die("cannot read %s", argv[i]); - } message = 1; continue; } diff --git a/strbuf.c b/strbuf.c index 0e431da..f4201e1 100644 --- a/strbuf.c +++ b/strbuf.c @@ -186,14 +186,14 @@ int strbuf_getline(struct strbuf *sb, FILE *fp, int term) return 0; } -int strbuf_read_file(struct strbuf *sb, const char *path) +int strbuf_read_file(struct strbuf *sb, const char *path, size_t hint) { int fd, len; fd = open(path, O_RDONLY); if (fd < 0) return -1; - len = strbuf_read(sb, fd, 0); + len = strbuf_read(sb, fd, hint); close(fd); if (len < 0) return -1; diff --git a/strbuf.h b/strbuf.h index 6deec78..9b9e861 100644 --- a/strbuf.h +++ b/strbuf.h @@ -108,7 +108,7 @@ extern void strbuf_addf(struct strbuf *sb, const char *fmt, ...); extern size_t strbuf_fread(struct strbuf *, size_t, FILE *); /* XXX: if read fails, any partial read is undone */ extern ssize_t strbuf_read(struct strbuf *, int fd, size_t hint); -extern int strbuf_read_file(struct strbuf *sb, const char *path); +extern int strbuf_read_file(struct strbuf *sb, const char *path, size_t hint); extern int strbuf_getline(struct strbuf *, FILE *, int); -- cgit v0.10.2-6-g49f6 From 9a76adebd6dfe144c3643e7e877fff2b41be5c8e Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Thu, 27 Sep 2007 13:33:19 +0200 Subject: Make read_patch_file work on a strbuf. So that we don't need to use strbuf_detach. Signed-off-by: Pierre Habouzit Signed-off-by: Junio C Hamano diff --git a/builtin-apply.c b/builtin-apply.c index fec96a8..4113d66 100644 --- a/builtin-apply.c +++ b/builtin-apply.c @@ -178,12 +178,9 @@ static void say_patch_name(FILE *output, const char *pre, struct patch *patch, c #define CHUNKSIZE (8192) #define SLOP (16) -static void *read_patch_file(int fd, size_t *sizep) +static void read_patch_file(struct strbuf *sb, int fd) { - struct strbuf buf; - - strbuf_init(&buf, 0); - if (strbuf_read(&buf, fd, 0) < 0) + if (strbuf_read(sb, fd, 0) < 0) die("git-apply: read returned %s", strerror(errno)); /* @@ -191,9 +188,8 @@ static void *read_patch_file(int fd, size_t *sizep) * so that we can do speculative "memcmp" etc, and * see to it that it is NUL-filled. */ - strbuf_grow(&buf, SLOP); - memset(buf.buf + buf.len, 0, SLOP); - return strbuf_detach(&buf, sizep); + strbuf_grow(sb, SLOP); + memset(sb->buf + sb->len, 0, SLOP); } static unsigned long linelen(const char *buffer, unsigned long size) @@ -2633,22 +2629,22 @@ static void prefix_patches(struct patch *p) static int apply_patch(int fd, const char *filename, int inaccurate_eof) { - unsigned long offset, size; - char *buffer = read_patch_file(fd, &size); + size_t offset; + struct strbuf buf; struct patch *list = NULL, **listp = &list; int skipped_patch = 0; + strbuf_init(&buf, 0); patch_input_file = filename; - if (!buffer) - return -1; + read_patch_file(&buf, fd); offset = 0; - while (size > 0) { + while (offset < buf.len) { struct patch *patch; int nr; patch = xcalloc(1, sizeof(*patch)); patch->inaccurate_eof = inaccurate_eof; - nr = parse_chunk(buffer + offset, size, patch); + nr = parse_chunk(buf.buf + offset, buf.len, patch); if (nr < 0) break; if (apply_in_reverse) @@ -2666,7 +2662,6 @@ static int apply_patch(int fd, const char *filename, int inaccurate_eof) skipped_patch++; } offset += nr; - size -= nr; } if (whitespace_error && (new_whitespace == error_on_whitespace)) @@ -2701,7 +2696,7 @@ static int apply_patch(int fd, const char *filename, int inaccurate_eof) if (summary) summary_patch_list(list); - free(buffer); + strbuf_release(&buf); return 0; } -- cgit v0.10.2-6-g49f6