X-Git-Url: https://git.octo.it/?a=blobdiff_plain;f=diff.c;h=ababcaa0e663254bf4d18adbb5fb0db3ac80f202;hb=f7c1512af8ff4f821c530f9a4bc8f8ff25733d51;hp=a237311d7a7358fca67633d648eaa5d257f87755;hpb=5d728c8411a092f80171f787b5409d98978690c7;p=git.git diff --git a/diff.c b/diff.c index a237311d..ababcaa0 100644 --- a/diff.c +++ b/diff.c @@ -4,11 +4,17 @@ #include #include #include -#include #include "cache.h" #include "diff.h" +#include "diffcore.h" static const char *diff_opts = "-pu"; +static unsigned char null_sha1[20] = { 0, }; + +static int reverse_diff; +static int generate_patch; +static int line_termination = '\n'; +static int inter_name_termination = '\t'; static const char *external_diff(void) { @@ -53,7 +59,7 @@ static char *sq_expand(const char *src) const char *cp; char *bp; - /* count bytes needed to store the quoted string. */ + /* count bytes needed to store the quoted string. */ for (cnt = 1, cp = src; *cp; cnt++, cp++) if (*cp == '\'') cnt += 3; @@ -73,31 +79,35 @@ static char *sq_expand(const char *src) } static struct diff_tempfile { - const char *name; + const char *name; /* filename external diff should read from */ char hex[41]; char mode[10]; char tmp_path[50]; } diff_temp[2]; -static void builtin_diff(const char *name, - struct diff_tempfile *temp) +static void builtin_diff(const char *name_a, + const char *name_b, + struct diff_tempfile *temp, + const char *xfrm_msg) { - int i, next_at; - const char *git_prefix = "# mode: "; + int i, next_at, cmd_size; const char *diff_cmd = "diff -L'%s%s' -L'%s%s'"; const char *diff_arg = "'%s' '%s'||:"; /* "||:" is to return 0 */ const char *input_name_sq[2]; const char *path0[2]; const char *path1[2]; - const char *name_sq = sq_expand(name); + const char *name_sq[2]; char *cmd; - + + name_sq[0] = sq_expand(name_a); + name_sq[1] = sq_expand(name_b); + /* diff_cmd and diff_arg have 6 %s in total which makes * the sum of these strings 12 bytes larger than required. * we use 2 spaces around diff-opts, and we need to count * terminating NUL, so we subtract 9 here. */ - int cmd_size = (strlen(diff_cmd) + strlen(diff_opts) + + cmd_size = (strlen(diff_cmd) + strlen(diff_opts) + strlen(diff_arg) - 9); for (i = 0; i < 2; i++) { input_name_sq[i] = sq_expand(temp[i].name); @@ -106,7 +116,7 @@ static void builtin_diff(const char *name, path1[i] = ""; } else { path0[i] = i ? "b/" : "a/"; - path1[i] = name_sq; + path1[i] = name_sq[i]; } cmd_size += (strlen(path0[i]) + strlen(path1[i]) + strlen(input_name_sq[i])); @@ -123,14 +133,18 @@ static void builtin_diff(const char *name, next_at += snprintf(cmd+next_at, cmd_size-next_at, diff_arg, input_name_sq[0], input_name_sq[1]); + printf("diff --git a/%s b/%s\n", name_a, name_b); if (!path1[0][0]) - printf("%s. %s %s\n", git_prefix, temp[1].mode, name); + printf("new file mode %s\n", temp[1].mode); else if (!path1[1][0]) - printf("%s%s . %s\n", git_prefix, temp[0].mode, name); + printf("deleted file mode %s\n", temp[0].mode); else { - if (strcmp(temp[0].mode, temp[1].mode)) - printf("%s%s %s %s\n", git_prefix, - temp[0].mode, temp[1].mode, name); + if (strcmp(temp[0].mode, temp[1].mode)) { + printf("old mode %s\n", temp[0].mode); + printf("new mode %s\n", temp[1].mode); + } + if (xfrm_msg && xfrm_msg[0]) + fputs(xfrm_msg, stdout); if (strncmp(temp[0].mode, temp[1].mode, 3)) /* we do not run diff between different kind @@ -142,6 +156,31 @@ static void builtin_diff(const char *name, execlp("/bin/sh","sh", "-c", cmd, NULL); } +struct diff_filespec *alloc_filespec(const char *path) +{ + int namelen = strlen(path); + struct diff_filespec *spec = xmalloc(sizeof(*spec) + namelen + 1); + spec->path = (char *)(spec + 1); + strcpy(spec->path, path); + spec->should_free = spec->should_munmap = 0; + spec->xfrm_flags = 0; + spec->size = 0; + spec->data = NULL; + spec->mode = 0; + memset(spec->sha1, 0, 20); + return spec; +} + +void fill_filespec(struct diff_filespec *spec, const unsigned char *sha1, + unsigned short mode) +{ + if (mode) { /* just playing defensive */ + spec->mode = mode; + memcpy(spec->sha1, sha1, 20); + spec->sha1_valid = !!memcmp(sha1, null_sha1, 20); + } +} + /* * Given a name and sha1 pair, if the dircache tells us the file in * the work tree has that object contents, return true, so that @@ -152,19 +191,19 @@ static int work_tree_matches(const char *name, const unsigned char *sha1) struct cache_entry *ce; struct stat st; int pos, len; - + /* We do not read the cache ourselves here, because the * benchmark with my previous version that always reads cache * shows that it makes things worse for diff-tree comparing * two linux-2.6 kernel trees in an already checked out work - * tree. This is because most diff-tree comparison deals with + * tree. This is because most diff-tree comparisons deal with * only a small number of files, while reading the cache is * expensive for a large project, and its cost outweighs the * savings we get by not inflating the object to a temporary * file. Practically, this code only helps when we are used * by diff-cache --cached, which does read the cache before * calling us. - */ + */ if (!active_cache) return 0; @@ -174,13 +213,86 @@ static int work_tree_matches(const char *name, const unsigned char *sha1) return 0; ce = active_cache[pos]; if ((lstat(name, &st) < 0) || - !S_ISREG(st.st_mode) || + !S_ISREG(st.st_mode) || /* careful! */ ce_match_stat(ce, &st) || memcmp(sha1, ce->sha1, 20)) return 0; + /* we return 1 only when we can stat, it is a regular file, + * stat information matches, and sha1 recorded in the cache + * matches. I.e. we know the file in the work tree really is + * the same as the pair. + */ return 1; } +/* + * While doing rename detection and pickaxe operation, we may need to + * grab the data for the blob (or file) for our own in-core comparison. + * diff_filespec has data and size fields for this purpose. + */ +int diff_populate_filespec(struct diff_filespec *s) +{ + int err = 0; + if (!DIFF_FILE_VALID(s)) + die("internal error: asking to populate invalid file."); + if (S_ISDIR(s->mode)) + return -1; + + if (s->data) + return err; + if (!s->sha1_valid || + work_tree_matches(s->path, s->sha1)) { + struct stat st; + int fd; + if (lstat(s->path, &st) < 0) { + if (errno == ENOENT) { + err_empty: + err = -1; + empty: + s->data = ""; + s->size = 0; + return err; + } + } + s->size = st.st_size; + if (!s->size) + goto empty; + if (S_ISLNK(st.st_mode)) { + int ret; + s->data = xmalloc(s->size); + s->should_free = 1; + ret = readlink(s->path, s->data, s->size); + if (ret < 0) { + free(s->data); + goto err_empty; + } + return 0; + } + fd = open(s->path, O_RDONLY); + if (fd < 0) + goto err_empty; + s->data = mmap(NULL, s->size, PROT_READ, MAP_PRIVATE, fd, 0); + s->should_munmap = 1; + close(fd); + } + else { + char type[20]; + s->data = read_sha1_file(s->sha1, type, &s->size); + s->should_free = 1; + } + return 0; +} + +void diff_free_filespec_data(struct diff_filespec *s) +{ + if (s->should_free) + free(s->data); + else if (s->should_munmap) + munmap(s->data, s->size); + s->should_free = s->should_munmap = 0; + s->data = NULL; +} + static void prep_temp_blob(struct diff_tempfile *temp, void *blob, unsigned long size, @@ -204,12 +316,9 @@ static void prep_temp_blob(struct diff_tempfile *temp, static void prepare_temp_file(const char *name, struct diff_tempfile *temp, - struct diff_spec *one) + struct diff_filespec *one) { - static unsigned char null_sha1[20] = { 0, }; - int use_work_tree = 0; - - if (!one->file_valid) { + if (!DIFF_FILE_VALID(one)) { not_a_valid_file: /* A '-' entry produces this for file-2, and * a '+' entry produces this for file-1. @@ -220,18 +329,13 @@ static void prepare_temp_file(const char *name, return; } - if (one->sha1_valid && - (!memcmp(one->blob_sha1, null_sha1, sizeof(null_sha1)) || - work_tree_matches(name, one->blob_sha1))) - use_work_tree = 1; - - if (!one->sha1_valid || use_work_tree) { + if (!one->sha1_valid || + work_tree_matches(name, one->sha1)) { struct stat st; - temp->name = name; - if (lstat(temp->name, &st) < 0) { + if (lstat(name, &st) < 0) { if (errno == ENOENT) goto not_a_valid_file; - die("stat(%s): %s", temp->name, strerror(errno)); + die("stat(%s): %s", name, strerror(errno)); } if (S_ISLNK(st.st_mode)) { int ret; @@ -243,31 +347,27 @@ static void prepare_temp_file(const char *name, die("readlink(%s)", name); prep_temp_blob(temp, buf, st.st_size, (one->sha1_valid ? - one->blob_sha1 : null_sha1), + one->sha1 : null_sha1), (one->sha1_valid ? one->mode : S_IFLNK)); } else { + /* we can borrow from the file in the work tree */ + temp->name = name; if (!one->sha1_valid) strcpy(temp->hex, sha1_to_hex(null_sha1)); else - strcpy(temp->hex, sha1_to_hex(one->blob_sha1)); + strcpy(temp->hex, sha1_to_hex(one->sha1)); sprintf(temp->mode, "%06o", S_IFREG |ce_permissions(st.st_mode)); } return; } else { - void *blob; - char type[20]; - unsigned long size; - - blob = read_sha1_file(one->blob_sha1, type, &size); - if (!blob || strcmp(type, "blob")) - die("unable to read blob object for %s (%s)", - name, sha1_to_hex(one->blob_sha1)); - prep_temp_blob(temp, blob, size, one->blob_sha1, one->mode); - free(blob); + if (diff_populate_filespec(one)) + die("cannot read data blob for %s", one->path); + prep_temp_blob(temp, one->data, one->size, + one->sha1, one->mode); } } @@ -290,12 +390,14 @@ static void remove_tempfile_on_signal(int signo) /* An external diff command takes: * * diff-cmd name infile1 infile1-sha1 infile1-mode \ - * infile2 infile2-sha1 infile2-mode. + * infile2 infile2-sha1 infile2-mode [ rename-to ] * */ -void run_external_diff(const char *name, - struct diff_spec *one, - struct diff_spec *two) +static void run_external_diff(const char *name, + const char *other, + struct diff_filespec *one, + struct diff_filespec *two, + const char *xfrm_msg) { struct diff_tempfile *temp = diff_temp; pid_t pid; @@ -304,7 +406,7 @@ void run_external_diff(const char *name, if (one && two) { prepare_temp_file(name, &temp[0], one); - prepare_temp_file(name, &temp[1], two); + prepare_temp_file(other ? : name, &temp[1], two); if (! atexit_asked && (temp[0].name == temp[0].tmp_path || temp[1].name == temp[1].tmp_path)) { @@ -321,12 +423,24 @@ void run_external_diff(const char *name, if (!pid) { const char *pgm = external_diff(); if (pgm) { - if (one && two) - execlp(pgm, pgm, - name, - temp[0].name, temp[0].hex, temp[0].mode, - temp[1].name, temp[1].hex, temp[1].mode, - NULL); + if (one && two) { + const char *exec_arg[10]; + const char **arg = &exec_arg[0]; + *arg++ = pgm; + *arg++ = name; + *arg++ = temp[0].name; + *arg++ = temp[0].hex; + *arg++ = temp[0].mode; + *arg++ = temp[1].name; + *arg++ = temp[1].hex; + *arg++ = temp[1].mode; + if (other) { + *arg++ = other; + *arg++ = xfrm_msg; + } + *arg = NULL; + execvp(pgm, (char *const*) exec_arg); + } else execlp(pgm, pgm, name, NULL); } @@ -334,7 +448,7 @@ void run_external_diff(const char *name, * otherwise we use the built-in one. */ if (one && two) - builtin_diff(name, temp); + builtin_diff(name, other ? : name, temp, xfrm_msg); else printf("* Unmerged path %s\n", name); exit(0); @@ -357,53 +471,334 @@ void run_external_diff(const char *name, remove_tempfile(); } +void diff_setup(int reverse_diff_) +{ + reverse_diff = reverse_diff_; +} + +struct diff_queue_struct diff_queued_diff; + +void diff_q(struct diff_queue_struct *queue, struct diff_filepair *dp) +{ + if (queue->alloc <= queue->nr) { + queue->alloc = alloc_nr(queue->alloc); + queue->queue = xrealloc(queue->queue, + sizeof(dp) * queue->alloc); + } + queue->queue[queue->nr++] = dp; +} + +struct diff_filepair *diff_queue(struct diff_queue_struct *queue, + struct diff_filespec *one, + struct diff_filespec *two) +{ + struct diff_filepair *dp = xmalloc(sizeof(*dp)); + dp->one = one; + dp->two = two; + dp->score = 0; + dp->orig_order = queue->nr; + dp->rename_rank = 0; + diff_q(queue, dp); + return dp; +} + +static void diff_flush_raw(struct diff_filepair *p) +{ + if (DIFF_PAIR_UNMERGED(p)) { + printf("U %s%c", p->one->path, line_termination); + return; + } + printf(":%06o %06o %s ", + p->one->mode, p->two->mode, sha1_to_hex(p->one->sha1)); + printf("%s%c%s%c%s%c", + sha1_to_hex(p->two->sha1), inter_name_termination, + p->one->path, inter_name_termination, + p->two->path, line_termination); +} + +int diff_unmodified_pair(struct diff_filepair *p) +{ + /* This function is written stricter than necessary to support + * the currently implemented transformers, but the idea is to + * 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; + + if (DIFF_PAIR_UNMERGED(p)) + return 0; /* unmerged is interesting */ + + one = p->one; + two = p->two; + + /* deletion, addition, mode change and renames are all interesting. */ + if (DIFF_FILE_VALID(one) != DIFF_FILE_VALID(two) || + (one->mode != two->mode) || + strcmp(one->path, two->path)) + return 0; + + /* both are valid and point at the same path. that is, we are + * dealing with a change. + */ + if (one->sha1_valid && two->sha1_valid && + !memcmp(one->sha1, two->sha1, sizeof(one->sha1))) + return 1; /* no change */ + if (!one->sha1_valid && !two->sha1_valid) + return 1; /* both look at the same file on the filesystem. */ + return 0; +} + +static void diff_flush_patch(struct diff_filepair *p, const char *msg) +{ + const char *name, *other; + + /* diffcore_prune() keeps "stay" entries for diff-raw + * copy/rename detection, but when we are generating + * patches we do not need them. + */ + if (diff_unmodified_pair(p)) + return; + + name = p->one->path; + other = (strcmp(name, p->two->path) ? p->two->path : NULL); + if ((DIFF_FILE_VALID(p->one) && S_ISDIR(p->one->mode)) || + (DIFF_FILE_VALID(p->two) && S_ISDIR(p->two->mode))) + return; /* no tree diffs in patch format */ + + if (DIFF_PAIR_UNMERGED(p)) + run_external_diff(name, NULL, NULL, NULL, NULL); + else + run_external_diff(name, other, p->one, p->two, msg); +} + +int diff_needs_to_stay(struct diff_queue_struct *q, int i, + struct diff_filespec *it) +{ + /* If it will be used in later entry (either stay or used + * as the source of rename/copy), we need to copy, not rename. + */ + while (i < q->nr) { + struct diff_filepair *p = q->queue[i++]; + if (!DIFF_FILE_VALID(p->two)) + continue; /* removed is fine */ + if (strcmp(p->one->path, it->path)) + continue; /* not relevant */ + + /* p has its src set to *it and it is not a delete; + * it will be used for in-place change, rename/copy, + * or just stays there. We cannot rename it out. + */ + return 1; + } + return 0; +} + +static int diff_used_as_source(struct diff_queue_struct *q, int lim, + struct diff_filespec *it) +{ + int i; + for (i = 0; i < lim; i++) { + struct diff_filepair *p = q->queue[i++]; + if (!strcmp(p->one->path, it->path)) + return 1; + } + return 0; +} + +void diffcore_prune(void) +{ + /* + * Although rename/copy detection wants to have "no-change" + * entries fed into them, the downstream do not need to see + * them, unless we had rename/copy for the same path earlier. + * This function removes such entries. + * + * The applications that use rename/copy should: + * + * (1) feed change and "no-change" entries via diff_queue(). + * (2) call diffcore_rename, and any other future diffcore_xxx + * that would benefit by still having "no-change" entries. + * (3) call diffcore_prune + * (4) call other diffcore_xxx that do not need to see + * "no-change" entries. + * (5) call diff_flush(). + */ + struct diff_queue_struct *q = &diff_queued_diff; + struct diff_queue_struct outq; + int i; + + outq.queue = NULL; + outq.nr = outq.alloc = 0; + + for (i = 0; i < q->nr; i++) { + struct diff_filepair *p = q->queue[i]; + if (!diff_unmodified_pair(p) || + diff_used_as_source(q, i, p->one)) + diff_q(&outq, p); + else + free(p); + } + free(q->queue); + *q = outq; + return; +} + +static void diff_flush_one(struct diff_filepair *p, const char *msg) +{ + if (generate_patch) + diff_flush_patch(p, msg); + else + diff_flush_raw(p); +} + +int diff_queue_is_empty(void) +{ + struct diff_queue_struct *q = &diff_queued_diff; + return q->nr == 0; +} + +void diff_flush(int diff_output_style) +{ + struct diff_queue_struct *q = &diff_queued_diff; + int i; + + generate_patch = 0; + switch (diff_output_style) { + case DIFF_FORMAT_HUMAN: + line_termination = '\n'; + inter_name_termination = '\t'; + break; + case DIFF_FORMAT_MACHINE: + line_termination = inter_name_termination = 0; + break; + case DIFF_FORMAT_PATCH: + generate_patch = 1; + break; + } + for (i = 0; i < q->nr; i++) { + char msg_[PATH_MAX*2+200], *msg = NULL; + struct diff_filepair *p = q->queue[i]; + if (strcmp(p->one->path, p->two->path)) { + /* This is rename or copy. Which one is it? */ + if (diff_needs_to_stay(q, i+1, p->one)) { + sprintf(msg_, + "similarity index %d%%\n" + "copy from %s\n" + "copy to %s\n", + (int)(0.5 + p->score * 100/MAX_SCORE), + p->one->path, p->two->path); + } + else + sprintf(msg_, + "similarity index %d%%\n" + "rename old %s\n" + "rename new %s\n", + (int)(0.5 + p->score * 100/MAX_SCORE), + p->one->path, p->two->path); + msg = msg_; + } + diff_flush_one(p, msg); + } + + for (i = 0; i < q->nr; i++) { + struct diff_filepair *p = q->queue[i]; + diff_free_filespec_data(p->one); + diff_free_filespec_data(p->two); + free(p); + } + free(q->queue); + q->queue = NULL; + q->nr = q->alloc = 0; +} + void diff_addremove(int addremove, unsigned mode, const unsigned char *sha1, const char *base, const char *path) { char concatpath[PATH_MAX]; - struct diff_spec spec[2], *one, *two; + struct diff_filespec *one, *two; + + /* This may look odd, but it is a preparation for + * feeding "there are unchanged files which should + * not produce diffs, but when you are doing copy + * detection you would need them, so here they are" + * entries to the diff-core. They will be prefixed + * with something like '=' or '*' (I haven't decided + * which but should not make any difference). + * Feeding the same new and old to diff_change() + * also has the same effect. diffcore_prune() should + * be used to filter uninteresting ones out before the + * final output happens. + */ + if (reverse_diff) + addremove = (addremove == '+' ? '-' : + addremove == '-' ? '+' : addremove); - memcpy(spec[0].blob_sha1, sha1, 20); - spec[0].mode = mode; - spec[0].sha1_valid = spec[0].file_valid = 1; - spec[1].file_valid = 0; + if (!path) path = ""; + sprintf(concatpath, "%s%s", base, path); + one = alloc_filespec(concatpath); + two = alloc_filespec(concatpath); - if (addremove == '+') { - one = spec + 1; two = spec; - } else { - one = spec; two = one + 1; - } - - if (path) { - strcpy(concatpath, base); - strcat(concatpath, path); + if (addremove != '+') + fill_filespec(one, sha1, mode); + if (addremove != '-') + fill_filespec(two, sha1, mode); + + diff_queue(&diff_queued_diff, one, two); +} + +void diff_guif(unsigned old_mode, + unsigned new_mode, + const unsigned char *old_sha1, + const unsigned char *new_sha1, + const char *old_path, + const char *new_path) +{ + struct diff_filespec *one, *two; + + if (reverse_diff) { + unsigned tmp; + const unsigned char *tmp_c; + tmp = old_mode; old_mode = new_mode; new_mode = tmp; + tmp_c = old_sha1; old_sha1 = new_sha1; new_sha1 = tmp_c; } - run_external_diff(path ? concatpath : base, one, two); + one = alloc_filespec(old_path); + two = alloc_filespec(new_path); + if (old_mode) + fill_filespec(one, old_sha1, old_mode); + if (new_mode) + fill_filespec(two, new_sha1, new_mode); + diff_queue(&diff_queued_diff, one, two); } void diff_change(unsigned old_mode, unsigned new_mode, const unsigned char *old_sha1, const unsigned char *new_sha1, - const char *base, const char *path) { + const char *base, const char *path) +{ char concatpath[PATH_MAX]; - struct diff_spec spec[2]; - - memcpy(spec[0].blob_sha1, old_sha1, 20); - spec[0].mode = old_mode; - memcpy(spec[1].blob_sha1, new_sha1, 20); - spec[1].mode = new_mode; - spec[0].sha1_valid = spec[0].file_valid = 1; - spec[1].sha1_valid = spec[1].file_valid = 1; - - if (path) { - strcpy(concatpath, base); - strcat(concatpath, path); + struct diff_filespec *one, *two; + + if (reverse_diff) { + unsigned tmp; + const unsigned char *tmp_c; + tmp = old_mode; old_mode = new_mode; new_mode = tmp; + tmp_c = old_sha1; old_sha1 = new_sha1; new_sha1 = tmp_c; } - run_external_diff(path ? concatpath : base, &spec[0], &spec[1]); + if (!path) path = ""; + sprintf(concatpath, "%s%s", base, path); + one = alloc_filespec(concatpath); + two = alloc_filespec(concatpath); + fill_filespec(one, old_sha1, old_mode); + fill_filespec(two, new_sha1, new_mode); + + diff_queue(&diff_queued_diff, one, two); } void diff_unmerge(const char *path) { - run_external_diff(path, NULL, NULL); + struct diff_filespec *one, *two; + one = alloc_filespec(path); + two = alloc_filespec(path); + diff_queue(&diff_queued_diff, one, two); }