X-Git-Url: https://git.octo.it/?a=blobdiff_plain;f=diff.c;h=2762905b56a6a247f661a12d1573f1877d29a959;hb=4a1332d04b676a226eba5a7c1247db199d463570;hp=5a2aee7acc0b54e6be8d6a884895098e0a739127;hpb=b6d8f309d9bbd8193d9b73eb41c6fcdaa8001298;p=git.git diff --git a/diff.c b/diff.c index 5a2aee7a..2762905b 100644 --- a/diff.c +++ b/diff.c @@ -12,9 +12,7 @@ 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 int use_size_cache; static const char *external_diff(void) { @@ -134,17 +132,23 @@ static void builtin_diff(const char *name_a, 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]) + if (!path1[0][0]) { printf("new file mode %s\n", temp[1].mode); - else if (!path1[1][0]) + if (xfrm_msg && xfrm_msg[0]) + puts(xfrm_msg); + } + else if (!path1[1][0]) { printf("deleted file mode %s\n", temp[0].mode); + if (xfrm_msg && xfrm_msg[0]) + puts(xfrm_msg); + } else { 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); + puts(xfrm_msg); if (strncmp(temp[0].mode, temp[1].mode, 3)) /* we do not run diff between different kind @@ -174,8 +178,8 @@ struct diff_filespec *alloc_filespec(const char *path) void fill_filespec(struct diff_filespec *spec, const unsigned char *sha1, unsigned short mode) { - if (mode) { /* just playing defensive */ - spec->mode = mode; + if (mode) { + spec->mode = DIFF_FILE_CANON_MODE(mode); memcpy(spec->sha1, sha1, 20); spec->sha1_valid = !!memcmp(sha1, null_sha1, 20); } @@ -225,12 +229,61 @@ static int work_tree_matches(const char *name, const unsigned char *sha1) return 1; } +static struct sha1_size_cache { + unsigned char sha1[20]; + unsigned long size; +} **sha1_size_cache; +static int sha1_size_cache_nr, sha1_size_cache_alloc; + +static struct sha1_size_cache *locate_size_cache(unsigned char *sha1, + int find_only, + unsigned long size) +{ + int first, last; + struct sha1_size_cache *e; + + first = 0; + last = sha1_size_cache_nr; + while (last > first) { + int cmp, next = (last + first) >> 1; + e = sha1_size_cache[next]; + cmp = memcmp(e->sha1, sha1, 20); + if (!cmp) + return e; + if (cmp < 0) { + last = next; + continue; + } + first = next+1; + } + /* not found */ + if (find_only) + return NULL; + /* insert to make it at "first" */ + if (sha1_size_cache_alloc <= sha1_size_cache_nr) { + sha1_size_cache_alloc = alloc_nr(sha1_size_cache_alloc); + sha1_size_cache = xrealloc(sha1_size_cache, + sha1_size_cache_alloc * + sizeof(*sha1_size_cache)); + } + sha1_size_cache_nr++; + if (first < sha1_size_cache_nr) + memmove(sha1_size_cache + first + 1, sha1_size_cache + first, + (sha1_size_cache_nr - first - 1) * + sizeof(*sha1_size_cache)); + e = xmalloc(sizeof(struct sha1_size_cache)); + sha1_size_cache[first] = e; + memcpy(e->sha1, sha1, 20); + e->size = size; + return e; +} + /* * 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 diff_populate_filespec(struct diff_filespec *s, int size_only) { int err = 0; if (!DIFF_FILE_VALID(s)) @@ -238,6 +291,9 @@ int diff_populate_filespec(struct diff_filespec *s) if (S_ISDIR(s->mode)) return -1; + if (!use_size_cache) + size_only = 0; + if (s->data) return err; if (!s->sha1_valid || @@ -257,6 +313,8 @@ int diff_populate_filespec(struct diff_filespec *s) s->size = st.st_size; if (!s->size) goto empty; + if (size_only) + return 0; if (S_ISLNK(st.st_mode)) { int ret; s->data = xmalloc(s->size); @@ -277,8 +335,21 @@ int diff_populate_filespec(struct diff_filespec *s) } else { char type[20]; - s->data = read_sha1_file(s->sha1, type, &s->size); - s->should_free = 1; + struct sha1_size_cache *e; + + if (size_only) { + e = locate_size_cache(s->sha1, 1, 0); + if (e) { + s->size = e->size; + return 0; + } + if (!sha1_file_size(s->sha1, &s->size)) + locate_size_cache(s->sha1, 0, s->size); + } + else { + s->data = read_sha1_file(s->sha1, type, &s->size); + s->should_free = 1; + } } return 0; } @@ -358,13 +429,18 @@ static void prepare_temp_file(const char *name, strcpy(temp->hex, sha1_to_hex(null_sha1)); else strcpy(temp->hex, sha1_to_hex(one->sha1)); - sprintf(temp->mode, "%06o", - S_IFREG |ce_permissions(st.st_mode)); + /* Even though we may sometimes borrow the + * contents from the work tree, we always want + * one->mode. mode is trustworthy even when + * !(one->sha1_valid), as long as + * DIFF_FILE_VALID(one). + */ + sprintf(temp->mode, "%06o", one->mode); } return; } else { - if (diff_populate_filespec(one)) + if (diff_populate_filespec(one, 0)) die("cannot read data blob for %s", one->path); prep_temp_blob(temp, one->data, one->size, one->sha1, one->mode); @@ -393,7 +469,8 @@ static void remove_tempfile_on_signal(int signo) * infile2 infile2-sha1 infile2-mode [ rename-to ] * */ -static void run_external_diff(const char *name, +static void run_external_diff(const char *pgm, + const char *name, const char *other, struct diff_filespec *one, struct diff_filespec *two, @@ -421,7 +498,6 @@ static void run_external_diff(const char *name, if (pid < 0) die("unable to fork"); if (!pid) { - const char *pgm = external_diff(); if (pgm) { if (one && two) { const char *exec_arg[10]; @@ -471,9 +547,98 @@ static void run_external_diff(const char *name, remove_tempfile(); } -void diff_setup(int reverse_diff_) +static void run_diff(const char *name, + const char *other, + struct diff_filespec *one, + struct diff_filespec *two, + const char *xfrm_msg) +{ + const char *pgm = external_diff(); + if (!pgm && + DIFF_FILE_VALID(one) && DIFF_FILE_VALID(two) && + (S_IFMT & one->mode) != (S_IFMT & two->mode)) { + /* a filepair that changes between file and symlink + * needs to be split into deletion and creation. + */ + struct diff_filespec *null = alloc_filespec(two->path); + run_external_diff(NULL, name, other, one, null, xfrm_msg); + free(null); + null = alloc_filespec(one->path); + run_external_diff(NULL, name, other, null, two, xfrm_msg); + free(null); + } + else + run_external_diff(pgm, name, other, one, two, xfrm_msg); +} + +void diff_setup(int flags) +{ + if (flags & DIFF_SETUP_REVERSE) + reverse_diff = 1; + if (flags & DIFF_SETUP_USE_CACHE) { + if (!active_cache) + /* read-cache does not die even when it fails + * so it is safe for us to do this here. Also + * it does not smudge active_cache or active_nr + * when it fails, so we do not have to worry about + * cleaning it up oufselves either. + */ + read_cache(); + } + if (flags & DIFF_SETUP_USE_SIZE_CACHE) + use_size_cache = 1; + +} + +static int parse_num(const char **cp_p) { - reverse_diff = reverse_diff_; + int num, scale, ch, cnt; + const char *cp = *cp_p; + + cnt = num = 0; + scale = 1; + while ('0' <= (ch = *cp) && ch <= '9') { + if (cnt++ < 5) { + /* We simply ignore more than 5 digits precision. */ + scale *= 10; + num = num * 10 + ch - '0'; + } + *cp++; + } + *cp_p = cp; + + /* user says num divided by scale and we say internally that + * is MAX_SCORE * num / scale. + */ + return (MAX_SCORE * num / scale); +} + +int diff_scoreopt_parse(const char *opt) +{ + int opt1, opt2, cmd; + + if (*opt++ != '-') + return -1; + cmd = *opt++; + if (cmd != 'M' && cmd != 'C' && cmd != 'B') + return -1; /* that is not a -M, -C nor -B option */ + + opt1 = parse_num(&opt); + if (cmd != 'B') + opt2 = 0; + else { + if (*opt == 0) + opt2 = 0; + else if (*opt != '/') + return -1; /* we expect -B80/99 or -B80 */ + else { + opt++; + opt2 = parse_num(&opt); + } + } + if (*opt != 0) + return -1; + return opt1 | (opt2 << 16); } struct diff_queue_struct diff_queued_diff; @@ -496,20 +661,51 @@ struct diff_filepair *diff_queue(struct diff_queue_struct *queue, dp->one = one; dp->two = two; dp->score = 0; - dp->orig_order = queue->nr; - dp->rename_rank = 0; + dp->source_stays = 0; + dp->broken_pair = 0; diff_q(queue, dp); return dp; } -static void diff_flush_raw(struct diff_filepair *p) +void diff_free_filepair(struct diff_filepair *p) +{ + diff_free_filespec_data(p->one); + diff_free_filespec_data(p->two); + free(p); +} + +static void diff_flush_raw(struct diff_filepair *p, + int line_termination, + int inter_name_termination) { int two_paths; char status[10]; + + if (line_termination) { + const char *err = "path %s cannot be expressed without -z"; + if (strchr(p->one->path, line_termination) || + strchr(p->one->path, inter_name_termination)) + die(err, p->one->path); + if (strchr(p->two->path, line_termination) || + strchr(p->two->path, inter_name_termination)) + die(err, p->two->path); + } + switch (p->status) { case 'C': case 'R': two_paths = 1; - sprintf(status, "%c%1d", p->status, p->score); + sprintf(status, "%c%03d", p->status, + (int)(0.5 + p->score * 100.0/MAX_SCORE)); + break; + case 'N': case 'D': + two_paths = 0; + if (p->score) + sprintf(status, "%c%03d", p->status, + (int)(0.5 + p->score * 100.0/MAX_SCORE)); + else { + status[0] = p->status; + status[1] = 0; + } break; default: two_paths = 0; @@ -544,9 +740,11 @@ int diff_unmodified_pair(struct diff_filepair *p) one = p->one; two = p->two; - /* deletion, addition, mode change and renames are all interesting. */ + /* deletion, addition, mode or type change + * and rename are all interesting. + */ if (DIFF_FILE_VALID(one) != DIFF_FILE_VALID(two) || - (one->mode != two->mode) || + DIFF_PAIR_MODE_CHANGED(p) || strcmp(one->path, two->path)) return 0; @@ -566,10 +764,6 @@ static void diff_flush_patch(struct diff_filepair *p) const char *name, *other; char msg_[PATH_MAX*2+200], *msg; - /* 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; @@ -584,8 +778,8 @@ static void diff_flush_patch(struct diff_filepair *p) sprintf(msg_, "similarity index %d%%\n" "copy from %s\n" - "copy to %s\n", - (int)(0.5 + p->score * 100/MAX_SCORE), + "copy to %s", + (int)(0.5 + p->score * 100.0/MAX_SCORE), p->one->path, p->two->path); msg = msg_; break; @@ -593,153 +787,195 @@ static void diff_flush_patch(struct diff_filepair *p) sprintf(msg_, "similarity index %d%%\n" "rename old %s\n" - "rename new %s\n", - (int)(0.5 + p->score * 100/MAX_SCORE), + "rename new %s", + (int)(0.5 + p->score * 100.0/MAX_SCORE), p->one->path, p->two->path); msg = msg_; break; + case 'D': case 'N': + if (DIFF_PAIR_BROKEN(p)) { + sprintf(msg_, + "dissimilarity index %d%%", + (int)(0.5 + p->score * 100.0/MAX_SCORE)); + msg = msg_; + } + else + msg = NULL; + break; default: msg = NULL; } if (DIFF_PAIR_UNMERGED(p)) - run_external_diff(name, NULL, NULL, NULL, NULL); + run_diff(name, NULL, NULL, NULL, NULL); else - run_external_diff(name, other, p->one, p->two, msg); + run_diff(name, other, p->one, p->two, msg); } -int diff_needs_to_stay(struct diff_queue_struct *q, int i, - struct diff_filespec *it) +int diff_queue_is_empty(void) { - /* 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; + struct diff_queue_struct *q = &diff_queued_diff; + int i; + for (i = 0; i < q->nr; i++) + if (!diff_unmodified_pair(q->queue[i])) + return 0; + return 1; } -static int diff_used_as_source(struct diff_queue_struct *q, int lim, - struct diff_filespec *it) +#if DIFF_DEBUG +void diff_debug_filespec(struct diff_filespec *s, int x, const char *one) { - 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; + fprintf(stderr, "queue[%d] %s (%s) %s %06o %s\n", + x, one ? : "", + s->path, + DIFF_FILE_VALID(s) ? "valid" : "invalid", + s->mode, + s->sha1_valid ? sha1_to_hex(s->sha1) : ""); + fprintf(stderr, "queue[%d] %s size %lu flags %d\n", + x, one ? : "", + s->size, s->xfrm_flags); } -void diffcore_prune(void) +void diff_debug_filepair(const struct diff_filepair *p, int i) { - /* - * 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; + diff_debug_filespec(p->one, i, "one"); + diff_debug_filespec(p->two, i, "two"); + fprintf(stderr, "score %d, status %c stays %d broken %d\n", + p->score, p->status ? : '?', + p->source_stays, p->broken_pair); +} +void diff_debug_queue(const char *msg, struct diff_queue_struct *q) +{ + int i; + if (msg) + fprintf(stderr, "%s\n", msg); + fprintf(stderr, "q->nr = %d\n", q->nr); 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); + diff_debug_filepair(p, i); } - free(q->queue); - *q = outq; - return; } +#endif -int diff_queue_is_empty(void) +static void diff_resolve_rename_copy(void) { + int i, j; + struct diff_filepair *p, *pp; struct diff_queue_struct *q = &diff_queued_diff; - return q->nr == 0; + + diff_debug_queue("resolve-rename-copy", q); + + for (i = 0; i < q->nr; i++) { + p = q->queue[i]; + p->status = 0; /* undecided */ + if (DIFF_PAIR_UNMERGED(p)) + p->status = 'U'; + else if (!DIFF_FILE_VALID(p->one)) + p->status = 'N'; + else if (!DIFF_FILE_VALID(p->two)) + p->status = 'D'; + else if (DIFF_PAIR_TYPE_CHANGED(p)) + p->status = 'T'; + + /* from this point on, we are dealing with a pair + * whose both sides are valid and of the same type, i.e. + * either in-place edit or rename/copy edit. + */ + else if (DIFF_PAIR_RENAME(p)) { + if (p->source_stays) { + p->status = 'C'; + continue; + } + /* See if there is some other filepair that + * copies from the same source as us. If so + * we are a copy. Otherwise we are a rename. + */ + for (j = i + 1; j < q->nr; j++) { + pp = q->queue[j]; + if (strcmp(pp->one->path, p->one->path)) + continue; /* not us */ + if (!DIFF_PAIR_RENAME(pp)) + continue; /* not a rename/copy */ + /* pp is a rename/copy from the same source */ + p->status = 'C'; + break; + } + if (!p->status) + p->status = 'R'; + } + else if (memcmp(p->one->sha1, p->two->sha1, 20) || + p->one->mode != p->two->mode) + p->status = 'M'; + else { + /* This is a "no-change" entry and should not + * happen anymore, but prepare for broken callers. + */ + error("feeding unmodified %s to diffcore", + p->one->path); + p->status = 'X'; + } + } + diff_debug_queue("resolve-rename-copy done", q); } void diff_flush(int diff_output_style, int resolve_rename_copy) { struct diff_queue_struct *q = &diff_queued_diff; int i; + int line_termination = '\n'; + int inter_name_termination = '\t'; - generate_patch = 0; - switch (diff_output_style) { - case DIFF_FORMAT_HUMAN: - line_termination = '\n'; - inter_name_termination = '\t'; - break; - case DIFF_FORMAT_MACHINE: + if (diff_output_style == 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++) { - struct diff_filepair *p = q->queue[i]; - if (resolve_rename_copy) { - if (DIFF_PAIR_UNMERGED(p)) - p->status = 'U'; - else if (!DIFF_FILE_VALID((p)->one)) - p->status = 'N'; - else if (!DIFF_FILE_VALID((p)->two)) - p->status = 'D'; - else 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)) - p->status = 'C'; - else - p->status = 'R'; - } - else - p->status = 'M'; - } - if (generate_patch) - diff_flush_patch(p); - else - diff_flush_raw(p); - } + if (resolve_rename_copy) + diff_resolve_rename_copy(); 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); + if ((diff_output_style == DIFF_FORMAT_NO_OUTPUT) || + (p->status == 'X')) + continue; + if (p->status == 0) + die("internal error in diff-resolve-rename-copy"); + switch (diff_output_style) { + case DIFF_FORMAT_PATCH: + diff_flush_patch(p); + break; + case DIFF_FORMAT_HUMAN: + case DIFF_FORMAT_MACHINE: + diff_flush_raw(p, line_termination, + inter_name_termination); + break; + } } + for (i = 0; i < q->nr; i++) + diff_free_filepair(q->queue[i]); free(q->queue); q->queue = NULL; q->nr = q->alloc = 0; } +void diffcore_std(const char **paths, + int detect_rename, int rename_score, + const char *pickaxe, int pickaxe_opts, + int break_opt, + const char *orderfile) +{ + if (paths && paths[0]) + diffcore_pathspec(paths); + if (break_opt != -1) + diffcore_break(break_opt); + if (detect_rename) + diffcore_rename(detect_rename, rename_score); + if (break_opt != -1) + diffcore_merge_broken(); + if (pickaxe) + diffcore_pickaxe(pickaxe, pickaxe_opts); + if (orderfile) + diffcore_order(orderfile); +} + void diff_addremove(int addremove, unsigned mode, const unsigned char *sha1, const char *base, const char *path) @@ -755,9 +991,9 @@ void diff_addremove(int addremove, unsigned mode, * 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. + * also has the same effect. + * Before the final output happens, they are pruned after + * merged into rename/copy pairs as appropriate. */ if (reverse_diff) addremove = (addremove == '+' ? '-' : @@ -795,7 +1031,7 @@ void diff_helper_input(unsigned old_mode, if (new_mode) fill_filespec(two, new_sha1, new_mode); dp = diff_queue(&diff_queued_diff, one, two); - dp->score = score; + dp->score = score * MAX_SCORE / 100; dp->status = status; }