diff options
Diffstat (limited to 'diff.c')
| -rw-r--r-- | diff.c | 192 |
1 files changed, 117 insertions, 75 deletions
@@ -26,6 +26,7 @@ #endif static int diff_detect_rename_default; +static int diff_compaction_heuristic; /* experimental */ static int diff_rename_limit_default = 400; static int diff_suppress_blank_empty; static int diff_use_color_default = -1; @@ -189,6 +190,10 @@ int git_diff_ui_config(const char *var, const char *value, void *cb) diff_detect_rename_default = git_config_rename(var, value); return 0; } + if (!strcmp(var, "diff.compactionheuristic")) { + diff_compaction_heuristic = git_config_bool(var, value); + return 0; + } if (!strcmp(var, "diff.autorefreshindex")) { diff_auto_refresh_index = git_config_bool(var, value); return 0; @@ -349,7 +354,6 @@ struct emit_callback { const char **label_path; struct diff_words_data *diff_words; struct diff_options *opt; - int *found_changesp; struct strbuf *header; }; @@ -717,7 +721,6 @@ static void emit_rewrite_diff(const char *name_a, memset(&ecbdata, 0, sizeof(ecbdata)); ecbdata.color_diff = want_color(o->use_color); - ecbdata.found_changesp = &o->found_changes; ecbdata.ws_rule = whitespace_rule(name_b); ecbdata.opt = o; if (ecbdata.ws_rule & WS_BLANK_AT_EOF) { @@ -946,7 +949,8 @@ static int find_word_boundaries(mmfile_t *buffer, regex_t *word_regex, { if (word_regex && *begin < buffer->size) { regmatch_t match[1]; - if (!regexec(word_regex, buffer->ptr + *begin, 1, match, 0)) { + if (!regexec_buf(word_regex, buffer->ptr + *begin, + buffer->size - *begin, 1, match, 0)) { char *p = memchr(buffer->ptr + *begin + match[0].rm_so, '\n', match[0].rm_eo - match[0].rm_so); *end = p ? p - buffer->ptr : match[0].rm_eo + *begin; @@ -1211,12 +1215,13 @@ static void fn_out_consume(void *priv, char *line, unsigned long len) struct diff_options *o = ecbdata->opt; const char *line_prefix = diff_line_prefix(o); + o->found_changes = 1; + if (ecbdata->header) { - fprintf(ecbdata->opt->file, "%s", ecbdata->header->buf); + fprintf(o->file, "%s", ecbdata->header->buf); strbuf_reset(ecbdata->header); ecbdata->header = NULL; } - *(ecbdata->found_changesp) = 1; if (ecbdata->label_path[0]) { const char *name_a_tab, *name_b_tab; @@ -1224,9 +1229,9 @@ static void fn_out_consume(void *priv, char *line, unsigned long len) name_a_tab = strchr(ecbdata->label_path[0], ' ') ? "\t" : ""; name_b_tab = strchr(ecbdata->label_path[1], ' ') ? "\t" : ""; - fprintf(ecbdata->opt->file, "%s%s--- %s%s%s\n", + fprintf(o->file, "%s%s--- %s%s%s\n", line_prefix, meta, ecbdata->label_path[0], reset, name_a_tab); - fprintf(ecbdata->opt->file, "%s%s+++ %s%s%s\n", + fprintf(o->file, "%s%s+++ %s%s%s\n", line_prefix, meta, ecbdata->label_path[1], reset, name_b_tab); ecbdata->label_path[0] = ecbdata->label_path[1] = NULL; } @@ -1244,15 +1249,7 @@ static void fn_out_consume(void *priv, char *line, unsigned long len) find_lno(line, ecbdata); emit_hunk_header(ecbdata, line, len); if (line[len-1] != '\n') - putc('\n', ecbdata->opt->file); - return; - } - - if (len < 1) { - emit_line(ecbdata->opt, reset, reset, line, len); - if (ecbdata->diff_words - && ecbdata->diff_words->type == DIFF_WORDS_PORCELAIN) - fputs("~\n", ecbdata->opt->file); + putc('\n', o->file); return; } @@ -1277,8 +1274,8 @@ static void fn_out_consume(void *priv, char *line, unsigned long len) } diff_words_flush(ecbdata); if (ecbdata->diff_words->type == DIFF_WORDS_PORCELAIN) { - emit_line(ecbdata->opt, context, reset, line, len); - fputs("~\n", ecbdata->opt->file); + emit_line(o, context, reset, line, len); + fputs("~\n", o->file); } else { /* * Skip the prefix character, if any. With @@ -1289,7 +1286,7 @@ static void fn_out_consume(void *priv, char *line, unsigned long len) line++; len--; } - emit_line(ecbdata->opt, context, reset, line, len); + emit_line(o, context, reset, line, len); } return; } @@ -1311,8 +1308,7 @@ static void fn_out_consume(void *priv, char *line, unsigned long len) default: /* incomplete line at the end */ ecbdata->lno_in_preimage++; - emit_line(ecbdata->opt, - diff_get_color(ecbdata->color_diff, DIFF_CONTEXT), + emit_line(o, diff_get_color(ecbdata->color_diff, DIFF_CONTEXT), reset, line, len); break; } @@ -1928,8 +1924,8 @@ static void show_dirstat(struct diff_options *options) name = p->two->path ? p->two->path : p->one->path; - if (p->one->sha1_valid && p->two->sha1_valid) - content_changed = hashcmp(p->one->sha1, p->two->sha1); + if (p->one->oid_valid && p->two->oid_valid) + content_changed = oidcmp(&p->one->oid, &p->two->oid); else content_changed = 1; @@ -2301,7 +2297,8 @@ static void builtin_diff(const char *name_a, const char *add = diff_get_color_opt(o, DIFF_FILE_NEW); show_submodule_summary(o->file, one->path ? one->path : two->path, line_prefix, - one->sha1, two->sha1, two->dirty_submodule, + one->oid.hash, two->oid.hash, + two->dirty_submodule, meta, del, add, reset); return; } @@ -2379,7 +2376,7 @@ static void builtin_diff(const char *name_a, if (!one->data && !two->data && S_ISREG(one->mode) && S_ISREG(two->mode) && !DIFF_OPT_TST(o, BINARY)) { - if (!hashcmp(one->sha1, two->sha1)) { + if (!oidcmp(&one->oid, &two->oid)) { if (must_show_header) fprintf(o->file, "%s", header.buf); goto free_ab_and_return; @@ -2432,7 +2429,6 @@ static void builtin_diff(const char *name_a, memset(&ecbdata, 0, sizeof(ecbdata)); ecbdata.label_path = lbl; ecbdata.color_diff = want_color(o->use_color); - ecbdata.found_changesp = &o->found_changes; ecbdata.ws_rule = whitespace_rule(name_b); if (ecbdata.ws_rule & WS_BLANK_AT_EOF) check_blank_at_eof(&mf1, &mf2, &ecbdata); @@ -2500,7 +2496,7 @@ static void builtin_diffstat(const char *name_a, const char *name_b, return; } - same_contents = !hashcmp(one->sha1, two->sha1); + same_contents = !oidcmp(&one->oid, &two->oid); if (diff_filespec_is_binary(one) || diff_filespec_is_binary(two)) { data->is_binary = 1; @@ -2633,8 +2629,8 @@ void fill_filespec(struct diff_filespec *spec, const unsigned char *sha1, { if (mode) { spec->mode = canon_mode(mode); - hashcpy(spec->sha1, sha1); - spec->sha1_valid = sha1_valid; + hashcpy(spec->oid.hash, sha1); + spec->oid_valid = sha1_valid; } } @@ -2677,6 +2673,13 @@ static int reuse_worktree_file(const char *name, const unsigned char *sha1, int if (!FAST_WORKING_DIRECTORY && !want_file && has_sha1_pack(sha1)) return 0; + /* + * Similarly, if we'd have to convert the file contents anyway, that + * makes the optimization not worthwhile. + */ + if (!want_file && would_convert_to_git(name)) + return 0; + len = strlen(name); pos = cache_name_pos(name, len); if (pos < 0) @@ -2716,7 +2719,8 @@ static int diff_populate_gitlink(struct diff_filespec *s, int size_only) if (s->dirty_submodule) dirty = "-dirty"; - strbuf_addf(&buf, "Subproject commit %s%s\n", sha1_to_hex(s->sha1), dirty); + strbuf_addf(&buf, "Subproject commit %s%s\n", + oid_to_hex(&s->oid), dirty); s->size = buf.len; if (size_only) { s->data = NULL; @@ -2759,8 +2763,8 @@ int diff_populate_filespec(struct diff_filespec *s, unsigned int flags) if (S_ISGITLINK(s->mode)) return diff_populate_gitlink(s, size_only); - if (!s->sha1_valid || - reuse_worktree_file(s->path, s->sha1, 0)) { + if (!s->oid_valid || + reuse_worktree_file(s->path, s->oid.hash, 0)) { struct strbuf buf = STRBUF_INIT; struct stat st; int fd; @@ -2817,9 +2821,10 @@ int diff_populate_filespec(struct diff_filespec *s, unsigned int flags) else { enum object_type type; if (size_only || (flags & CHECK_BINARY)) { - type = sha1_object_info(s->sha1, &s->size); + type = sha1_object_info(s->oid.hash, &s->size); if (type < 0) - die("unable to read %s", sha1_to_hex(s->sha1)); + die("unable to read %s", + oid_to_hex(&s->oid)); if (size_only) return 0; if (s->size > big_file_threshold && s->is_binary == -1) { @@ -2827,9 +2832,9 @@ int diff_populate_filespec(struct diff_filespec *s, unsigned int flags) return 0; } } - s->data = read_sha1_file(s->sha1, &type, &s->size); + s->data = read_sha1_file(s->oid.hash, &type, &s->size); if (!s->data) - die("unable to read %s", sha1_to_hex(s->sha1)); + die("unable to read %s", oid_to_hex(&s->oid)); s->should_free = 1; } return 0; @@ -2858,7 +2863,7 @@ void diff_free_filespec_data(struct diff_filespec *s) static void prep_temp_blob(const char *path, struct diff_tempfile *temp, void *blob, unsigned long size, - const unsigned char *sha1, + const struct object_id *oid, int mode) { int fd; @@ -2883,7 +2888,7 @@ static void prep_temp_blob(const char *path, struct diff_tempfile *temp, die_errno("unable to write temp-file"); close_tempfile(&temp->tempfile); temp->name = get_tempfile_path(&temp->tempfile); - sha1_to_hex_r(temp->hex, sha1); + oid_to_hex_r(temp->hex, oid); xsnprintf(temp->mode, sizeof(temp->mode), "%06o", mode); strbuf_release(&buf); strbuf_release(&template); @@ -2907,8 +2912,8 @@ static struct diff_tempfile *prepare_temp_file(const char *name, } if (!S_ISGITLINK(one->mode) && - (!one->sha1_valid || - reuse_worktree_file(name, one->sha1, 1))) { + (!one->oid_valid || + reuse_worktree_file(name, one->oid.hash, 1))) { struct stat st; if (lstat(name, &st) < 0) { if (errno == ENOENT) @@ -2920,19 +2925,19 @@ static struct diff_tempfile *prepare_temp_file(const char *name, if (strbuf_readlink(&sb, name, st.st_size) < 0) die_errno("readlink(%s)", name); prep_temp_blob(name, temp, sb.buf, sb.len, - (one->sha1_valid ? - one->sha1 : null_sha1), - (one->sha1_valid ? + (one->oid_valid ? + &one->oid : &null_oid), + (one->oid_valid ? one->mode : S_IFLNK)); strbuf_release(&sb); } else { /* we can borrow from the file in the work tree */ temp->name = name; - if (!one->sha1_valid) + if (!one->oid_valid) sha1_to_hex_r(temp->hex, null_sha1); else - sha1_to_hex_r(temp->hex, one->sha1); + sha1_to_hex_r(temp->hex, one->oid.hash); /* Even though we may sometimes borrow the * contents from the work tree, we always want * one->mode. mode is trustworthy even when @@ -2947,7 +2952,7 @@ static struct diff_tempfile *prepare_temp_file(const char *name, if (diff_populate_filespec(one, 0)) die("cannot read data blob for %s", one->path); prep_temp_blob(name, temp, one->data, one->size, - one->sha1, one->mode); + &one->oid, one->mode); } return temp; } @@ -3060,7 +3065,7 @@ static void fill_metainfo(struct strbuf *msg, default: *must_show_header = 0; } - if (one && two && hashcmp(one->sha1, two->sha1)) { + if (one && two && oidcmp(&one->oid, &two->oid)) { int abbrev = DIFF_OPT_TST(o, FULL_INDEX) ? 40 : DEFAULT_ABBREV; if (DIFF_OPT_TST(o, BINARY)) { @@ -3070,8 +3075,8 @@ static void fill_metainfo(struct strbuf *msg, abbrev = 40; } strbuf_addf(msg, "%s%sindex %s..", line_prefix, set, - find_unique_abbrev(one->sha1, abbrev)); - strbuf_addstr(msg, find_unique_abbrev(two->sha1, abbrev)); + find_unique_abbrev(one->oid.hash, abbrev)); + strbuf_add_unique_abbrev(msg, two->oid.hash, abbrev); if (one->mode == two->mode) strbuf_addf(msg, " %06o", one->mode); strbuf_addf(msg, "%s\n", reset); @@ -3126,20 +3131,20 @@ static void run_diff_cmd(const char *pgm, static void diff_fill_sha1_info(struct diff_filespec *one) { if (DIFF_FILE_VALID(one)) { - if (!one->sha1_valid) { + if (!one->oid_valid) { struct stat st; if (one->is_stdin) { - hashcpy(one->sha1, null_sha1); + oidclr(&one->oid); return; } if (lstat(one->path, &st) < 0) die_errno("stat '%s'", one->path); - if (index_path(one->sha1, one->path, &st, 0)) + if (index_path(one->oid.hash, one->path, &st, 0)) die("cannot hash %s", one->path); } } else - hashclr(one->sha1); + oidclr(&one->oid); } static void strip_prefix(int prefix_length, const char **namep, const char **otherp) @@ -3278,6 +3283,8 @@ void diff_setup(struct diff_options *options) options->use_color = diff_use_color_default; options->detect_rename = diff_detect_rename_default; options->xdl_opts |= diff_algorithm; + if (diff_compaction_heuristic) + DIFF_XDL_SET(options, COMPACTION_HEURISTIC); options->orderfile = diff_order_file_cfg; @@ -3798,6 +3805,10 @@ int diff_opt_parse(struct diff_options *options, DIFF_XDL_SET(options, IGNORE_WHITESPACE_AT_EOL); else if (!strcmp(arg, "--ignore-blank-lines")) DIFF_XDL_SET(options, IGNORE_BLANK_LINES); + else if (!strcmp(arg, "--compaction-heuristic")) + DIFF_XDL_SET(options, COMPACTION_HEURISTIC); + else if (!strcmp(arg, "--no-compaction-heuristic")) + DIFF_XDL_CLR(options, COMPACTION_HEURISTIC); else if (!strcmp(arg, "--patience")) options->xdl_opts = DIFF_WITH_ALG(options, PATIENCE_DIFF); else if (!strcmp(arg, "--histogram")) @@ -3966,6 +3977,8 @@ int diff_opt_parse(struct diff_options *options, if (!options->file) die_errno("Could not open '%s'", path); options->close_file = 1; + if (options->use_color != GIT_COLOR_ALWAYS) + options->use_color = GIT_COLOR_NEVER; return argcount; } else return 0; @@ -4076,7 +4089,8 @@ void diff_free_filepair(struct diff_filepair *p) free(p); } -/* This is different from find_unique_abbrev() in that +/* + * This is different from find_unique_abbrev() in that * it stuffs the result with dots for alignment. */ const char *diff_unique_abbrev(const unsigned char *sha1, int len) @@ -4088,6 +4102,26 @@ const char *diff_unique_abbrev(const unsigned char *sha1, int len) abbrev = find_unique_abbrev(sha1, len); abblen = strlen(abbrev); + + /* + * In well-behaved cases, where the abbbreviated result is the + * same as the requested length, append three dots after the + * abbreviation (hence the whole logic is limited to the case + * where abblen < 37); when the actual abbreviated result is a + * bit longer than the requested length, we reduce the number + * of dots so that they match the well-behaved ones. However, + * if the actual abbreviation is longer than the requested + * length by more than three, we give up on aligning, and add + * three dots anyway, to indicate that the output is not the + * full object name. Yes, this may be suboptimal, but this + * appears only in "diff --raw --abbrev" output and it is not + * worth the effort to change it now. Note that this would + * likely to work fine when the automatic sizing of default + * abbreviation length is used--we would be fed -1 in "len" in + * that case, and will end up always appending three-dots, but + * the automatic sizing is supposed to give abblen that ensures + * uniqueness across all objects (statistically speaking). + */ if (abblen < 37) { static char hex[41]; if (len < abblen && abblen <= len + 2) @@ -4107,8 +4141,9 @@ static void diff_flush_raw(struct diff_filepair *p, struct diff_options *opt) fprintf(opt->file, "%s", diff_line_prefix(opt)); if (!(opt->output_format & DIFF_FORMAT_NAME_STATUS)) { fprintf(opt->file, ":%06o %06o %s ", p->one->mode, p->two->mode, - diff_unique_abbrev(p->one->sha1, opt->abbrev)); - fprintf(opt->file, "%s ", diff_unique_abbrev(p->two->sha1, opt->abbrev)); + diff_unique_abbrev(p->one->oid.hash, opt->abbrev)); + fprintf(opt->file, "%s ", + diff_unique_abbrev(p->two->oid.hash, opt->abbrev)); } if (p->score) { fprintf(opt->file, "%c%03d%c", p->status, similarity_index(p), @@ -4157,11 +4192,11 @@ int diff_unmodified_pair(struct diff_filepair *p) /* both are valid and point at the same path. that is, we are * dealing with a change. */ - if (one->sha1_valid && two->sha1_valid && - !hashcmp(one->sha1, two->sha1) && + if (one->oid_valid && two->oid_valid && + !oidcmp(&one->oid, &two->oid) && !one->dirty_submodule && !two->dirty_submodule) return 1; /* no change */ - if (!one->sha1_valid && !two->sha1_valid) + if (!one->oid_valid && !two->oid_valid) return 1; /* both look at the same file on the filesystem. */ return 0; } @@ -4222,7 +4257,7 @@ void diff_debug_filespec(struct diff_filespec *s, int x, const char *one) s->path, DIFF_FILE_VALID(s) ? "valid" : "invalid", s->mode, - s->sha1_valid ? sha1_to_hex(s->sha1) : ""); + s->oid_valid ? oid_to_hex(&s->oid) : ""); fprintf(stderr, "queue[%d] %s size %lu\n", x, one ? one : "", s->size); @@ -4292,11 +4327,11 @@ static void diff_resolve_rename_copy(void) else p->status = DIFF_STATUS_RENAMED; } - else if (hashcmp(p->one->sha1, p->two->sha1) || + else if (oidcmp(&p->one->oid, &p->two->oid) || p->one->mode != p->two->mode || p->one->dirty_submodule || p->two->dirty_submodule || - is_null_sha1(p->one->sha1)) + is_null_oid(&p->one->oid)) p->status = DIFF_STATUS_MODIFIED; else { /* This is a "no-change" entry and should not @@ -4438,7 +4473,7 @@ static void patch_id_consume(void *priv, char *line, unsigned long len) } /* returns 0 upon success, and writes result into sha1 */ -static int diff_get_patch_id(struct diff_options *options, unsigned char *sha1) +static int diff_get_patch_id(struct diff_options *options, unsigned char *sha1, int diff_header_only) { struct diff_queue_struct *q = &diff_queued_diff; int i; @@ -4473,9 +4508,6 @@ static int diff_get_patch_id(struct diff_options *options, unsigned char *sha1) diff_fill_sha1_info(p->one); diff_fill_sha1_info(p->two); - if (fill_mmfile(&mf1, p->one) < 0 || - fill_mmfile(&mf2, p->two) < 0) - return error("unable to read files to diff"); len1 = remove_space(p->one->path, strlen(p->one->path)); len2 = remove_space(p->two->path, strlen(p->two->path)); @@ -4510,10 +4542,19 @@ static int diff_get_patch_id(struct diff_options *options, unsigned char *sha1) len2, p->two->path); git_SHA1_Update(&ctx, buffer, len1); + if (diff_header_only) + continue; + + if (fill_mmfile(&mf1, p->one) < 0 || + fill_mmfile(&mf2, p->two) < 0) + return error("unable to read files to diff"); + if (diff_filespec_is_binary(p->one) || diff_filespec_is_binary(p->two)) { - git_SHA1_Update(&ctx, sha1_to_hex(p->one->sha1), 40); - git_SHA1_Update(&ctx, sha1_to_hex(p->two->sha1), 40); + git_SHA1_Update(&ctx, oid_to_hex(&p->one->oid), + 40); + git_SHA1_Update(&ctx, oid_to_hex(&p->two->oid), + 40); continue; } @@ -4530,11 +4571,11 @@ static int diff_get_patch_id(struct diff_options *options, unsigned char *sha1) return 0; } -int diff_flush_patch_id(struct diff_options *options, unsigned char *sha1) +int diff_flush_patch_id(struct diff_options *options, unsigned char *sha1, int diff_header_only) { struct diff_queue_struct *q = &diff_queued_diff; int i; - int result = diff_get_patch_id(options, sha1); + int result = diff_get_patch_id(options, sha1, diff_header_only); for (i = 0; i < q->nr; i++) diff_free_filepair(q->queue[i]); @@ -4805,7 +4846,7 @@ static int diff_filespec_check_stat_unmatch(struct diff_filepair *p) */ if (!DIFF_FILE_VALID(p->one) || /* (1) */ !DIFF_FILE_VALID(p->two) || - (p->one->sha1_valid && p->two->sha1_valid) || + (p->one->oid_valid && p->two->oid_valid) || (p->one->mode != p->two->mode) || diff_populate_filespec(p->one, CHECK_SIZE_ONLY) || diff_populate_filespec(p->two, CHECK_SIZE_ONLY) || @@ -5101,8 +5142,9 @@ size_t fill_textconv(struct userdiff_driver *driver, if (!driver->textconv) die("BUG: fill_textconv called with non-textconv driver"); - if (driver->textconv_cache && df->sha1_valid) { - *outbuf = notes_cache_get(driver->textconv_cache, df->sha1, + if (driver->textconv_cache && df->oid_valid) { + *outbuf = notes_cache_get(driver->textconv_cache, + df->oid.hash, &size); if (*outbuf) return size; @@ -5112,9 +5154,9 @@ size_t fill_textconv(struct userdiff_driver *driver, if (!*outbuf) die("unable to read files to diff"); - if (driver->textconv_cache && df->sha1_valid) { + if (driver->textconv_cache && df->oid_valid) { /* ignore errors, as we might be in a readonly repository */ - notes_cache_put(driver->textconv_cache, df->sha1, *outbuf, + notes_cache_put(driver->textconv_cache, df->oid.hash, *outbuf, size); /* * we could save up changes and flush them all at the end, |