X-Git-Url: https://git.octo.it/?a=blobdiff_plain;f=diff.c;h=a72029058e195c596ab958e26cc0176cb0dc6b1c;hb=f9714a4a0cd4ed0ccca3833743d98ea874a2232d;hp=bafbc09808d393ceddc0c0445d322568b2007853;hpb=be020332a152ef95e0e8435fb69d8c02d5da29bb;p=git.git diff --git a/diff.c b/diff.c index bafbc098..a7202905 100644 --- a/diff.c +++ b/diff.c @@ -12,6 +12,7 @@ static const char *diff_opts = "-pu"; static unsigned char null_sha1[20] = { 0, }; static int reverse_diff; +static int use_size_cache; static const char *external_diff(void) { @@ -82,10 +83,88 @@ static struct diff_tempfile { char tmp_path[50]; } diff_temp[2]; +static int count_lines(const char *filename) +{ + FILE *in; + int count, ch, completely_empty = 1, nl_just_seen = 0; + in = fopen(filename, "r"); + count = 0; + while ((ch = fgetc(in)) != EOF) + if (ch == '\n') { + count++; + nl_just_seen = 1; + completely_empty = 0; + } + else { + nl_just_seen = 0; + completely_empty = 0; + } + fclose(in); + if (completely_empty) + return 0; + if (!nl_just_seen) + count++; /* no trailing newline */ + return count; +} + +static void print_line_count(int count) +{ + switch (count) { + case 0: + printf("0,0"); + break; + case 1: + printf("1"); + break; + default: + printf("1,%d", count); + break; + } +} + +static void copy_file(int prefix, const char *filename) +{ + FILE *in; + int ch, nl_just_seen = 1; + in = fopen(filename, "r"); + while ((ch = fgetc(in)) != EOF) { + if (nl_just_seen) + putchar(prefix); + putchar(ch); + if (ch == '\n') + nl_just_seen = 1; + else + nl_just_seen = 0; + } + fclose(in); + if (!nl_just_seen) + printf("\n\\ No newline at end of file\n"); +} + +static void emit_rewrite_diff(const char *name_a, + const char *name_b, + struct diff_tempfile *temp) +{ + /* Use temp[i].name as input, name_a and name_b as labels */ + int lc_a, lc_b; + lc_a = count_lines(temp[0].name); + lc_b = count_lines(temp[1].name); + printf("--- %s\n+++ %s\n@@ -", name_a, name_b); + print_line_count(lc_a); + printf(" +"); + print_line_count(lc_b); + printf(" @@\n"); + if (lc_a) + copy_file('-', temp[0].name); + if (lc_b) + copy_file('+', temp[1].name); +} + static void builtin_diff(const char *name_a, const char *name_b, struct diff_tempfile *temp, - const char *xfrm_msg) + const char *xfrm_msg, + int complete_rewrite) { int i, next_at, cmd_size; const char *diff_cmd = "diff -L'%s%s' -L'%s%s'"; @@ -131,10 +210,16 @@ 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); @@ -142,12 +227,16 @@ static void builtin_diff(const char *name_a, } if (xfrm_msg && xfrm_msg[0]) puts(xfrm_msg); - if (strncmp(temp[0].mode, temp[1].mode, 3)) /* we do not run diff between different kind * of objects. */ exit(0); + if (complete_rewrite) { + fflush(NULL); + emit_rewrite_diff(name_a, name_b, temp); + exit(0); + } } fflush(NULL); execlp("/bin/sh","sh", "-c", cmd, NULL); @@ -222,12 +311,61 @@ 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)) @@ -235,6 +373,9 @@ 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 || @@ -254,6 +395,8 @@ 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); @@ -274,8 +417,21 @@ 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_object_info(s->sha1, type, &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; } @@ -355,13 +511,18 @@ 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); @@ -395,7 +556,8 @@ static void run_external_diff(const char *pgm, const char *other, struct diff_filespec *one, struct diff_filespec *two, - const char *xfrm_msg) + const char *xfrm_msg, + int complete_rewrite) { struct diff_tempfile *temp = diff_temp; pid_t pid; @@ -445,7 +607,8 @@ static void run_external_diff(const char *pgm, * otherwise we use the built-in one. */ if (one && two) - builtin_diff(name, other ? : name, temp, xfrm_msg); + builtin_diff(name, other ? : name, temp, xfrm_msg, + complete_rewrite); else printf("* Unmerged path %s\n", name); exit(0); @@ -468,13 +631,59 @@ static void run_external_diff(const char *pgm, remove_tempfile(); } -static void run_diff(const char *name, - const char *other, - struct diff_filespec *one, - struct diff_filespec *two, - const char *xfrm_msg) +static void run_diff(struct diff_filepair *p) { const char *pgm = external_diff(); + char msg_[PATH_MAX*2+200], *xfrm_msg; + struct diff_filespec *one; + struct diff_filespec *two; + const char *name; + const char *other; + int complete_rewrite = 0; + + if (DIFF_PAIR_UNMERGED(p)) { + /* unmerged */ + run_external_diff(pgm, p->one->path, NULL, NULL, NULL, NULL, + 0); + return; + } + + name = p->one->path; + other = (strcmp(name, p->two->path) ? p->two->path : NULL); + one = p->one; two = p->two; + switch (p->status) { + case 'C': + sprintf(msg_, + "similarity index %d%%\n" + "copy from %s\n" + "copy to %s", + (int)(0.5 + p->score * 100.0/MAX_SCORE), + name, other); + xfrm_msg = msg_; + break; + case 'R': + sprintf(msg_, + "similarity index %d%%\n" + "rename from %s\n" + "rename to %s", + (int)(0.5 + p->score * 100.0/MAX_SCORE), + name, other); + xfrm_msg = msg_; + break; + case 'M': + if (p->score) { + sprintf(msg_, + "dissimilarity index %d%%", + (int)(0.5 + p->score * 100.0/MAX_SCORE)); + xfrm_msg = msg_; + complete_rewrite = 1; + break; + } + /* fallthru */ + default: + xfrm_msg = NULL; + } + if (!pgm && DIFF_FILE_VALID(one) && DIFF_FILE_VALID(two) && (S_IFMT & one->mode) != (S_IFMT & two->mode)) { @@ -482,20 +691,85 @@ static void run_diff(const char *name, * 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); + run_external_diff(NULL, name, other, one, null, xfrm_msg, 0); free(null); null = alloc_filespec(one->path); - run_external_diff(NULL, name, other, null, two, xfrm_msg); + run_external_diff(NULL, name, other, null, two, xfrm_msg, 0); free(null); } else - run_external_diff(pgm, name, other, one, two, xfrm_msg); + run_external_diff(pgm, name, other, one, two, xfrm_msg, + complete_rewrite); } 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) +{ + 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; @@ -518,6 +792,9 @@ struct diff_filepair *diff_queue(struct diff_queue_struct *queue, dp->one = one; dp->two = two; dp->score = 0; + dp->status = 0; + dp->source_stays = 0; + dp->broken_pair = 0; diff_q(queue, dp); return dp; } @@ -546,16 +823,22 @@ static void diff_flush_raw(struct diff_filepair *p, die(err, p->two->path); } + 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; + } switch (p->status) { case 'C': case 'R': two_paths = 1; - sprintf(status, "%c%03d", p->status, - (int)(0.5 + p->score * 100.0/MAX_SCORE)); + break; + case 'N': case 'D': + two_paths = 0; break; default: two_paths = 0; - status[0] = p->status; - status[1] = 0; break; } printf(":%06o %06o %s ", @@ -606,45 +889,14 @@ int diff_unmodified_pair(struct diff_filepair *p) static void diff_flush_patch(struct diff_filepair *p) { - const char *name, *other; - char msg_[PATH_MAX*2+200], *msg; - 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 */ - switch (p->status) { - case 'C': - sprintf(msg_, - "similarity index %d%%\n" - "copy from %s\n" - "copy to %s", - (int)(0.5 + p->score * 100.0/MAX_SCORE), - p->one->path, p->two->path); - msg = msg_; - break; - case 'R': - sprintf(msg_, - "similarity index %d%%\n" - "rename old %s\n" - "rename new %s", - (int)(0.5 + p->score * 100.0/MAX_SCORE), - p->one->path, p->two->path); - msg = msg_; - break; - default: - msg = NULL; - } - - if (DIFF_PAIR_UNMERGED(p)) - run_diff(name, NULL, NULL, NULL, NULL); - else - run_diff(name, other, p->one, p->two, msg); + run_diff(p); } int diff_queue_is_empty(void) @@ -675,8 +927,9 @@ void diff_debug_filepair(const struct diff_filepair *p, int i) { diff_debug_filespec(p->one, i, "one"); diff_debug_filespec(p->two, i, "two"); - fprintf(stderr, "score %d, status %c\n", - p->score, p->status ? : '?'); + 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) @@ -698,8 +951,6 @@ static void diff_resolve_rename_copy(void) struct diff_filepair *p, *pp; struct diff_queue_struct *q = &diff_queued_diff; - /* This should not depend on the ordering of things. */ - diff_debug_queue("resolve-rename-copy", q); for (i = 0; i < q->nr; i++) { @@ -707,24 +958,10 @@ static void diff_resolve_rename_copy(void) p->status = 0; /* undecided */ if (DIFF_PAIR_UNMERGED(p)) p->status = 'U'; - else if (!DIFF_FILE_VALID((p)->one)) + else if (!DIFF_FILE_VALID(p->one)) p->status = 'N'; - else if (!DIFF_FILE_VALID((p)->two)) { - /* Deletion record should be omitted if there - * are rename/copy entries using this one as - * the source. Then we can say one of them - * is a rename and the rest are copies. - */ + else if (!DIFF_FILE_VALID(p->two)) p->status = 'D'; - for (j = 0; j < q->nr; j++) { - pp = q->queue[j]; - if (!strcmp(pp->one->path, p->one->path) && - strcmp(pp->one->path, pp->two->path)) { - p->status = 'X'; - break; - } - } - } else if (DIFF_PAIR_TYPE_CHANGED(p)) p->status = 'T'; @@ -732,33 +969,24 @@ static void diff_resolve_rename_copy(void) * whose both sides are valid and of the same type, i.e. * either in-place edit or rename/copy edit. */ - else if (strcmp(p->one->path, p->two->path)) { - /* See if there is somebody else anywhere that - * will keep the path (either modified or - * unmodified). If so, we have to be a copy, - * not a rename. In addition, if there is - * some other rename or copy that comes later - * than us that uses the same source, we - * have to be a copy, not a rename. + 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 = 0; j < q->nr; j++) { + for (j = i + 1; j < q->nr; j++) { pp = q->queue[j]; if (strcmp(pp->one->path, p->one->path)) - continue; - if (!strcmp(pp->one->path, pp->two->path)) { - if (DIFF_FILE_VALID(pp->two)) { - /* non-delete */ - p->status = 'C'; - break; - } - continue; - } - /* pp is a rename/copy ... */ - if (i < j) { - /* ... and comes later than us */ - p->status = 'C'; - break; - } + 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'; @@ -766,14 +994,19 @@ static void diff_resolve_rename_copy(void) 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 */ + 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) +void diff_flush(int diff_output_style) { struct diff_queue_struct *q = &diff_queued_diff; int i; @@ -782,8 +1015,6 @@ void diff_flush(int diff_output_style, int resolve_rename_copy) if (diff_output_style == DIFF_FORMAT_MACHINE) line_termination = inter_name_termination = 0; - if (resolve_rename_copy) - diff_resolve_rename_copy(); for (i = 0; i < q->nr; i++) { struct diff_filepair *p = q->queue[i]; @@ -810,6 +1041,94 @@ void diff_flush(int diff_output_style, int resolve_rename_copy) q->nr = q->alloc = 0; } +static void diffcore_apply_filter(const char *filter) +{ + int i; + struct diff_queue_struct *q = &diff_queued_diff; + struct diff_queue_struct outq; + outq.queue = NULL; + outq.nr = outq.alloc = 0; + + if (!filter) + return; + + if (strchr(filter, 'A')) { + /* All-or-none */ + int found; + for (i = found = 0; !found && i < q->nr; i++) { + struct diff_filepair *p = q->queue[i]; + if (((p->status == 'M') && + ((p->score && strchr(filter, 'B')) || + (!p->score && strchr(filter, 'M')))) || + ((p->status != 'M') && strchr(filter, p->status))) + found++; + } + if (found) + return; + + /* otherwise we will clear the whole queue + * by copying the empty outq at the end of this + * function, but first clear the current entries + * in the queue. + */ + for (i = 0; i < q->nr; i++) + diff_free_filepair(q->queue[i]); + } + else { + /* Only the matching ones */ + for (i = 0; i < q->nr; i++) { + struct diff_filepair *p = q->queue[i]; + if (((p->status == 'M') && + ((p->score && strchr(filter, 'B')) || + (!p->score && strchr(filter, 'M')))) || + ((p->status != 'M') && strchr(filter, p->status))) + diff_q(&outq, p); + else + diff_free_filepair(p); + } + } + free(q->queue); + *q = outq; +} + +void diffcore_std(const char **paths, + int detect_rename, int rename_score, + const char *pickaxe, int pickaxe_opts, + int break_opt, + const char *orderfile, + const char *filter) +{ + 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); + diff_resolve_rename_copy(); + diffcore_apply_filter(filter); +} + + +void diffcore_std_no_resolve(const char **paths, + const char *pickaxe, int pickaxe_opts, + const char *orderfile, + const char *filter) +{ + if (paths && paths[0]) + diffcore_pathspec(paths); + if (pickaxe) + diffcore_pickaxe(pickaxe, pickaxe_opts); + if (orderfile) + diffcore_order(orderfile); + diffcore_apply_filter(filter); +} + void diff_addremove(int addremove, unsigned mode, const unsigned char *sha1, const char *base, const char *path)