From: Junio C Hamano Date: Mon, 8 Mar 2010 08:35:59 +0000 (-0800) Subject: Merge branch 'jc/grep-author-all-match-implicit' into maint X-Git-Tag: v1.7.0.3~31 X-Git-Url: https://git.lorimer.id.au/gitweb.git/diff_plain/1f54d693fda851a1df81e2b6c85f1c72f4633916?ds=inline;hp=-c Merge branch 'jc/grep-author-all-match-implicit' into maint * jc/grep-author-all-match-implicit: "log --author=me --grep=it" should find intersection, not union --- 1f54d693fda851a1df81e2b6c85f1c72f4633916 diff --combined builtin-grep.c index 26979577d3,d57c4d9bed..371db0aa9e --- a/builtin-grep.c +++ b/builtin-grep.c @@@ -15,9 -15,12 +15,9 @@@ #include "grep.h" #include "quote.h" -#ifndef NO_EXTERNAL_GREP -#ifdef __unix__ -#define NO_EXTERNAL_GREP 0 -#else -#define NO_EXTERNAL_GREP 1 -#endif +#ifndef NO_PTHREADS +#include "thread-utils.h" +#include #endif static char const * const grep_usage[] = { @@@ -25,266 -28,6 +25,266 @@@ NULL }; +static int use_threads = 1; + +#ifndef NO_PTHREADS +#define THREADS 8 +static pthread_t threads[THREADS]; + +static void *load_sha1(const unsigned char *sha1, unsigned long *size, + const char *name); +static void *load_file(const char *filename, size_t *sz); + +enum work_type {WORK_SHA1, WORK_FILE}; + +/* We use one producer thread and THREADS consumer + * threads. The producer adds struct work_items to 'todo' and the + * consumers pick work items from the same array. + */ +struct work_item +{ + enum work_type type; + char *name; + + /* if type == WORK_SHA1, then 'identifier' is a SHA1, + * otherwise type == WORK_FILE, and 'identifier' is a NUL + * terminated filename. + */ + void *identifier; + char done; + struct strbuf out; +}; + +/* In the range [todo_done, todo_start) in 'todo' we have work_items + * that have been or are processed by a consumer thread. We haven't + * written the result for these to stdout yet. + * + * The work_items in [todo_start, todo_end) are waiting to be picked + * up by a consumer thread. + * + * The ranges are modulo TODO_SIZE. + */ +#define TODO_SIZE 128 +static struct work_item todo[TODO_SIZE]; +static int todo_start; +static int todo_end; +static int todo_done; + +/* Has all work items been added? */ +static int all_work_added; + +/* This lock protects all the variables above. */ +static pthread_mutex_t grep_mutex; + +/* Used to serialize calls to read_sha1_file. */ +static pthread_mutex_t read_sha1_mutex; + +#define grep_lock() pthread_mutex_lock(&grep_mutex) +#define grep_unlock() pthread_mutex_unlock(&grep_mutex) +#define read_sha1_lock() pthread_mutex_lock(&read_sha1_mutex) +#define read_sha1_unlock() pthread_mutex_unlock(&read_sha1_mutex) + +/* Signalled when a new work_item is added to todo. */ +static pthread_cond_t cond_add; + +/* Signalled when the result from one work_item is written to + * stdout. + */ +static pthread_cond_t cond_write; + +/* Signalled when we are finished with everything. */ +static pthread_cond_t cond_result; + +static void add_work(enum work_type type, char *name, void *id) +{ + grep_lock(); + + while ((todo_end+1) % ARRAY_SIZE(todo) == todo_done) { + pthread_cond_wait(&cond_write, &grep_mutex); + } + + todo[todo_end].type = type; + todo[todo_end].name = name; + todo[todo_end].identifier = id; + todo[todo_end].done = 0; + strbuf_reset(&todo[todo_end].out); + todo_end = (todo_end + 1) % ARRAY_SIZE(todo); + + pthread_cond_signal(&cond_add); + grep_unlock(); +} + +static struct work_item *get_work(void) +{ + struct work_item *ret; + + grep_lock(); + while (todo_start == todo_end && !all_work_added) { + pthread_cond_wait(&cond_add, &grep_mutex); + } + + if (todo_start == todo_end && all_work_added) { + ret = NULL; + } else { + ret = &todo[todo_start]; + todo_start = (todo_start + 1) % ARRAY_SIZE(todo); + } + grep_unlock(); + return ret; +} + +static void grep_sha1_async(struct grep_opt *opt, char *name, + const unsigned char *sha1) +{ + unsigned char *s; + s = xmalloc(20); + memcpy(s, sha1, 20); + add_work(WORK_SHA1, name, s); +} + +static void grep_file_async(struct grep_opt *opt, char *name, + const char *filename) +{ + add_work(WORK_FILE, name, xstrdup(filename)); +} + +static void work_done(struct work_item *w) +{ + int old_done; + + grep_lock(); + w->done = 1; + old_done = todo_done; + for(; todo[todo_done].done && todo_done != todo_start; + todo_done = (todo_done+1) % ARRAY_SIZE(todo)) { + w = &todo[todo_done]; + write_or_die(1, w->out.buf, w->out.len); + free(w->name); + free(w->identifier); + } + + if (old_done != todo_done) + pthread_cond_signal(&cond_write); + + if (all_work_added && todo_done == todo_end) + pthread_cond_signal(&cond_result); + + grep_unlock(); +} + +static void *run(void *arg) +{ + int hit = 0; + struct grep_opt *opt = arg; + + while (1) { + struct work_item *w = get_work(); + if (!w) + break; + + opt->output_priv = w; + if (w->type == WORK_SHA1) { + unsigned long sz; + void* data = load_sha1(w->identifier, &sz, w->name); + + if (data) { + hit |= grep_buffer(opt, w->name, data, sz); + free(data); + } + } else if (w->type == WORK_FILE) { + size_t sz; + void* data = load_file(w->identifier, &sz); + if (data) { + hit |= grep_buffer(opt, w->name, data, sz); + free(data); + } + } else { + assert(0); + } + + work_done(w); + } + free_grep_patterns(arg); + free(arg); + + return (void*) (intptr_t) hit; +} + +static void strbuf_out(struct grep_opt *opt, const void *buf, size_t size) +{ + struct work_item *w = opt->output_priv; + strbuf_add(&w->out, buf, size); +} + +static void start_threads(struct grep_opt *opt) +{ + int i; + + pthread_mutex_init(&grep_mutex, NULL); + pthread_mutex_init(&read_sha1_mutex, NULL); + pthread_cond_init(&cond_add, NULL); + pthread_cond_init(&cond_write, NULL); + pthread_cond_init(&cond_result, NULL); + + for (i = 0; i < ARRAY_SIZE(todo); i++) { + strbuf_init(&todo[i].out, 0); + } + + for (i = 0; i < ARRAY_SIZE(threads); i++) { + int err; + struct grep_opt *o = grep_opt_dup(opt); + o->output = strbuf_out; + compile_grep_patterns(o); + err = pthread_create(&threads[i], NULL, run, o); + + if (err) + die("grep: failed to create thread: %s", + strerror(err)); + } +} + +static int wait_all(void) +{ + int hit = 0; + int i; + + grep_lock(); + all_work_added = 1; + + /* Wait until all work is done. */ + while (todo_done != todo_end) + pthread_cond_wait(&cond_result, &grep_mutex); + + /* Wake up all the consumer threads so they can see that there + * is no more work to do. + */ + pthread_cond_broadcast(&cond_add); + grep_unlock(); + + for (i = 0; i < ARRAY_SIZE(threads); i++) { + void *h; + pthread_join(threads[i], &h); + hit |= (int) (intptr_t) h; + } + + pthread_mutex_destroy(&grep_mutex); + pthread_mutex_destroy(&read_sha1_mutex); + pthread_cond_destroy(&cond_add); + pthread_cond_destroy(&cond_write); + pthread_cond_destroy(&cond_result); + + return hit; +} +#else /* !NO_PTHREADS */ +#define read_sha1_lock() +#define read_sha1_unlock() + +static int wait_all(void) +{ + return 0; +} +#endif + static int grep_config(const char *var, const char *value, void *cb) { struct grep_opt *opt = cb; @@@ -299,6 -42,8 +299,6 @@@ opt->color = git_config_colorbool(var, value, -1); return 0; } - if (!strcmp(var, "color.grep.external")) - return git_config_string(&(opt->color_external), var, value); if (!strcmp(var, "color.grep.match")) { if (!value) return config_error_nonbool(var); @@@ -408,74 -153,37 +408,74 @@@ static int pathspec_matches(const char return 0; } -static int grep_sha1(struct grep_opt *opt, const unsigned char *sha1, const char *name, int tree_name_len) +static void *lock_and_read_sha1_file(const unsigned char *sha1, enum object_type *type, unsigned long *size) +{ + void *data; + + if (use_threads) { + read_sha1_lock(); + data = read_sha1_file(sha1, type, size); + read_sha1_unlock(); + } else { + data = read_sha1_file(sha1, type, size); + } + return data; +} + +static void *load_sha1(const unsigned char *sha1, unsigned long *size, + const char *name) { - unsigned long size; - char *data; enum object_type type; - int hit; - struct strbuf pathbuf = STRBUF_INIT; + void *data = lock_and_read_sha1_file(sha1, &type, size); - data = read_sha1_file(sha1, &type, &size); - if (!data) { + if (!data) error("'%s': unable to read %s", name, sha1_to_hex(sha1)); - return 0; - } + + return data; +} + +static int grep_sha1(struct grep_opt *opt, const unsigned char *sha1, + const char *filename, int tree_name_len) +{ + struct strbuf pathbuf = STRBUF_INIT; + char *name; + if (opt->relative && opt->prefix_length) { - quote_path_relative(name + tree_name_len, -1, &pathbuf, opt->prefix); - strbuf_insert(&pathbuf, 0, name, tree_name_len); - name = pathbuf.buf; + quote_path_relative(filename + tree_name_len, -1, &pathbuf, + opt->prefix); + strbuf_insert(&pathbuf, 0, filename, tree_name_len); + } else { + strbuf_addstr(&pathbuf, filename); + } + + name = strbuf_detach(&pathbuf, NULL); + +#ifndef NO_PTHREADS + if (use_threads) { + grep_sha1_async(opt, name, sha1); + return 0; + } else +#endif + { + int hit; + unsigned long sz; + void *data = load_sha1(sha1, &sz, name); + if (!data) + hit = 0; + else + hit = grep_buffer(opt, name, data, sz); + + free(data); + free(name); + return hit; } - hit = grep_buffer(opt, name, data, size); - strbuf_release(&pathbuf); - free(data); - return hit; } -static int grep_file(struct grep_opt *opt, const char *filename) +static void *load_file(const char *filename, size_t *sz) { struct stat st; - int i; char *data; - size_t sz; - struct strbuf buf = STRBUF_INIT; + int i; if (lstat(filename, &st) < 0) { err_ret: @@@ -485,60 -193,329 +485,60 @@@ } if (!S_ISREG(st.st_mode)) return 0; - sz = xsize_t(st.st_size); + *sz = xsize_t(st.st_size); i = open(filename, O_RDONLY); if (i < 0) goto err_ret; - data = xmalloc(sz + 1); - if (st.st_size != read_in_full(i, data, sz)) { + data = xmalloc(*sz + 1); + if (st.st_size != read_in_full(i, data, *sz)) { error("'%s': short read %s", filename, strerror(errno)); close(i); free(data); return 0; } close(i); - if (opt->relative && opt->prefix_length) - filename = quote_path_relative(filename, -1, &buf, opt->prefix); - i = grep_buffer(opt, filename, data, sz); - strbuf_release(&buf); - free(data); - return i; + data[*sz] = 0; + return data; } -#if !NO_EXTERNAL_GREP -static int exec_grep(int argc, const char **argv) +static int grep_file(struct grep_opt *opt, const char *filename) { - pid_t pid; - int status; + struct strbuf buf = STRBUF_INIT; + char *name; - argv[argc] = NULL; - trace_argv_printf(argv, "trace: grep:"); - pid = fork(); - if (pid < 0) - return pid; - if (!pid) { - execvp("grep", (char **) argv); - exit(255); - } - while (waitpid(pid, &status, 0) < 0) { - if (errno == EINTR) - continue; - return -1; - } - if (WIFEXITED(status)) { - if (!WEXITSTATUS(status)) - return 1; + if (opt->relative && opt->prefix_length) + quote_path_relative(filename, -1, &buf, opt->prefix); + else + strbuf_addstr(&buf, filename); + name = strbuf_detach(&buf, NULL); + +#ifndef NO_PTHREADS + if (use_threads) { + grep_file_async(opt, name, filename); return 0; - } - return -1; -} - -#define MAXARGS 1000 -#define ARGBUF 4096 -#define push_arg(a) do { \ - if (nr < MAXARGS) argv[nr++] = (a); \ - else die("maximum number of args exceeded"); \ - } while (0) - -/* - * If you send a singleton filename to grep, it does not give - * the name of the file. GNU grep has "-H" but we would want - * that behaviour in a portable way. - * - * So we keep two pathnames in argv buffer unsent to grep in - * the main loop if we need to do more than one grep. - */ -static int flush_grep(struct grep_opt *opt, - int argc, int arg0, const char **argv, int *kept) -{ - int status; - int count = argc - arg0; - const char *kept_0 = NULL; - - if (count <= 2) { - /* - * Because we keep at least 2 paths in the call from - * the main loop (i.e. kept != NULL), and MAXARGS is - * far greater than 2, this usually is a call to - * conclude the grep. However, the user could attempt - * to overflow the argv buffer by giving too many - * options to leave very small number of real - * arguments even for the call in the main loop. - */ - if (kept) - die("insanely many options to grep"); - - /* - * If we have two or more paths, we do not have to do - * anything special, but we need to push /dev/null to - * get "-H" behaviour of GNU grep portably but when we - * are not doing "-l" nor "-L" nor "-c". - */ - if (count == 1 && - !opt->name_only && - !opt->unmatch_name_only && - !opt->count) { - argv[argc++] = "/dev/null"; - argv[argc] = NULL; - } - } - - else if (kept) { - /* - * Called because we found many paths and haven't finished - * iterating over the cache yet. We keep two paths - * for the concluding call. argv[argc-2] and argv[argc-1] - * has the last two paths, so save the first one away, - * replace it with NULL while sending the list to grep, - * and recover them after we are done. - */ - *kept = 2; - kept_0 = argv[argc-2]; - argv[argc-2] = NULL; - argc -= 2; - } - - if (opt->pre_context || opt->post_context) { - /* - * grep handles hunk marks between files, but we need to - * do that ourselves between multiple calls. - */ - if (opt->show_hunk_mark) - write_or_die(1, "--\n", 3); + } else +#endif + { + int hit; + size_t sz; + void *data = load_file(filename, &sz); + if (!data) + hit = 0; else - opt->show_hunk_mark = 1; - } + hit = grep_buffer(opt, name, data, sz); - status = exec_grep(argc, argv); - - if (kept_0) { - /* - * Then recover them. Now the last arg is beyond the - * terminating NULL which is at argc, and the second - * from the last is what we saved away in kept_0 - */ - argv[arg0++] = kept_0; - argv[arg0] = argv[argc+1]; - } - return status; -} - -static void grep_add_color(struct strbuf *sb, const char *escape_seq) -{ - size_t orig_len = sb->len; - - while (*escape_seq) { - if (*escape_seq == 'm') - strbuf_addch(sb, ';'); - else if (*escape_seq != '\033' && *escape_seq != '[') - strbuf_addch(sb, *escape_seq); - escape_seq++; - } - if (sb->len > orig_len && sb->buf[sb->len - 1] == ';') - strbuf_setlen(sb, sb->len - 1); -} - -static int has_skip_worktree_entry(struct grep_opt *opt, const char **paths) -{ - int nr; - for (nr = 0; nr < active_nr; nr++) { - struct cache_entry *ce = active_cache[nr]; - if (!S_ISREG(ce->ce_mode)) - continue; - if (!pathspec_matches(paths, ce->name, opt->max_depth)) - continue; - if (ce_skip_worktree(ce)) - return 1; - } - return 0; -} - -static int external_grep(struct grep_opt *opt, const char **paths, int cached) -{ - int i, nr, argc, hit, len, status; - const char *argv[MAXARGS+1]; - char randarg[ARGBUF]; - char *argptr = randarg; - struct grep_pat *p; - - if (opt->extended || (opt->relative && opt->prefix_length) - || has_skip_worktree_entry(opt, paths)) - return -1; - len = nr = 0; - push_arg("grep"); - if (opt->fixed) - push_arg("-F"); - if (opt->linenum) - push_arg("-n"); - if (!opt->pathname) - push_arg("-h"); - if (opt->regflags & REG_EXTENDED) - push_arg("-E"); - if (opt->ignore_case) - push_arg("-i"); - if (opt->binary == GREP_BINARY_NOMATCH) - push_arg("-I"); - if (opt->word_regexp) - push_arg("-w"); - if (opt->name_only) - push_arg("-l"); - if (opt->unmatch_name_only) - push_arg("-L"); - if (opt->null_following_name) - /* in GNU grep git's "-z" translates to "-Z" */ - push_arg("-Z"); - if (opt->count) - push_arg("-c"); - if (opt->post_context || opt->pre_context) { - if (opt->post_context != opt->pre_context) { - if (opt->pre_context) { - push_arg("-B"); - len += snprintf(argptr, sizeof(randarg)-len, - "%u", opt->pre_context) + 1; - if (sizeof(randarg) <= len) - die("maximum length of args exceeded"); - push_arg(argptr); - argptr += len; - } - if (opt->post_context) { - push_arg("-A"); - len += snprintf(argptr, sizeof(randarg)-len, - "%u", opt->post_context) + 1; - if (sizeof(randarg) <= len) - die("maximum length of args exceeded"); - push_arg(argptr); - argptr += len; - } - } - else { - push_arg("-C"); - len += snprintf(argptr, sizeof(randarg)-len, - "%u", opt->post_context) + 1; - if (sizeof(randarg) <= len) - die("maximum length of args exceeded"); - push_arg(argptr); - argptr += len; - } - } - for (p = opt->pattern_list; p; p = p->next) { - push_arg("-e"); - push_arg(p->pattern); - } - if (opt->color) { - struct strbuf sb = STRBUF_INIT; - - grep_add_color(&sb, opt->color_match); - setenv("GREP_COLOR", sb.buf, 1); - - strbuf_reset(&sb); - strbuf_addstr(&sb, "mt="); - grep_add_color(&sb, opt->color_match); - strbuf_addstr(&sb, ":sl=:cx=:fn=:ln=:bn=:se="); - setenv("GREP_COLORS", sb.buf, 1); - - strbuf_release(&sb); - - if (opt->color_external && strlen(opt->color_external) > 0) - push_arg(opt->color_external); - } else { - unsetenv("GREP_COLOR"); - unsetenv("GREP_COLORS"); - } - unsetenv("GREP_OPTIONS"); - - hit = 0; - argc = nr; - for (i = 0; i < active_nr; i++) { - struct cache_entry *ce = active_cache[i]; - char *name; - int kept; - if (!S_ISREG(ce->ce_mode)) - continue; - if (!pathspec_matches(paths, ce->name, opt->max_depth)) - continue; - name = ce->name; - if (name[0] == '-') { - int len = ce_namelen(ce); - name = xmalloc(len + 3); - memcpy(name, "./", 2); - memcpy(name + 2, ce->name, len + 1); - } - argv[argc++] = name; - if (MAXARGS <= argc) { - status = flush_grep(opt, argc, nr, argv, &kept); - if (0 < status) - hit = 1; - argc = nr + kept; - } - if (ce_stage(ce)) { - do { - i++; - } while (i < active_nr && - !strcmp(ce->name, active_cache[i]->name)); - i--; /* compensate for loop control */ - } - } - if (argc > nr) { - status = flush_grep(opt, argc, nr, argv, NULL); - if (0 < status) - hit = 1; + free(data); + free(name); + return hit; } - return hit; } -#endif -static int grep_cache(struct grep_opt *opt, const char **paths, int cached, - int external_grep_allowed) +static int grep_cache(struct grep_opt *opt, const char **paths, int cached) { int hit = 0; int nr; read_cache(); -#if !NO_EXTERNAL_GREP - /* - * Use the external "grep" command for the case where - * we grep through the checked-out files. It tends to - * be a lot more optimized - */ - if (!cached && external_grep_allowed) { - hit = external_grep(opt, paths, cached); - if (hit >= 0) - return hit; - hit = 0; - } -#endif - for (nr = 0; nr < active_nr; nr++) { struct cache_entry *ce = active_cache[nr]; if (!S_ISREG(ce->ce_mode)) @@@ -564,8 -541,6 +564,8 @@@ !strcmp(ce->name, active_cache[nr]->name)); nr--; /* compensate for loop control */ } + if (hit && opt->status_only) + break; } free_grep_patterns(opt); return hit; @@@ -615,7 -590,7 +615,7 @@@ static int grep_tree(struct grep_opt *o void *data; unsigned long size; - data = read_sha1_file(entry.sha1, &type, &size); + data = lock_and_read_sha1_file(entry.sha1, &type, &size); if (!data) die("unable to read tree (%s)", sha1_to_hex(entry.sha1)); @@@ -623,8 -598,6 +623,8 @@@ hit |= grep_tree(opt, paths, &sub, tree_name, down); free(data); } + if (hit && opt->status_only) + break; } strbuf_release(&pathbuf); return hit; @@@ -739,8 -712,8 +739,8 @@@ int cmd_grep(int argc, const char **arg { int hit = 0; int cached = 0; - int external_grep_allowed = 1; int seen_dashdash = 0; + int external_grep_allowed__ignored; struct grep_opt opt; struct object_array list = { 0, 0, NULL }; const char **paths = NULL; @@@ -819,13 -792,16 +819,13 @@@ { OPTION_CALLBACK, ')', NULL, &opt, NULL, "", PARSE_OPT_NOARG | PARSE_OPT_NONEG | PARSE_OPT_NODASH, close_callback }, + OPT_BOOLEAN('q', "quiet", &opt.status_only, + "indicate hit with exit status without output"), OPT_BOOLEAN(0, "all-match", &opt.all_match, "show only matches from files that match all patterns"), OPT_GROUP(""), -#if NO_EXTERNAL_GREP - OPT_BOOLEAN(0, "ext-grep", &external_grep_allowed, - "allow calling of grep(1) (ignored by this build)"), -#else - OPT_BOOLEAN(0, "ext-grep", &external_grep_allowed, - "allow calling of grep(1) (default)"), -#endif + OPT_BOOLEAN(0, "ext-grep", &external_grep_allowed__ignored, + "allow calling of grep(1) (ignored by this build)"), { OPTION_CALLBACK, 0, "help-all", &options, NULL, "show usage", PARSE_OPT_HIDDEN | PARSE_OPT_NOARG, help_callback }, OPT_END() @@@ -844,6 -820,7 +844,7 @@@ opt.relative = 1; opt.pathname = 1; opt.pattern_tail = &opt.pattern_list; + opt.header_tail = &opt.header_list; opt.regflags = REG_NEWLINE; opt.max_depth = -1; @@@ -868,16 -845,6 +869,16 @@@ PARSE_OPT_STOP_AT_NON_OPTION | PARSE_OPT_NO_INTERNAL_HELP); + /* + * skip a -- separator; we know it cannot be + * separating revisions from pathnames if + * we haven't even had any patterns yet + */ + if (argc > 0 && !opt.pattern_list && !strcmp(argv[0], "--")) { + argv++; + argc--; + } + /* First unrecognized non-option token */ if (argc > 0 && !opt.pattern_list) { append_grep_pattern(&opt, argv[0], "command line", 0, @@@ -886,23 -853,14 +887,23 @@@ argc--; } - if ((opt.color && !opt.color_external) || opt.funcname) - external_grep_allowed = 0; if (!opt.pattern_list) die("no pattern given."); if (!opt.fixed && opt.ignore_case) opt.regflags |= REG_ICASE; if ((opt.regflags != REG_NEWLINE) && opt.fixed) die("cannot mix --fixed-strings and regexp"); + +#ifndef NO_PTHREADS + if (online_cpus() == 1 || !grep_threads_ok(&opt)) + use_threads = 0; + + if (use_threads) + start_threads(&opt); +#else + use_threads = 0; +#endif + compile_grep_patterns(&opt); /* Check revs and then paths */ @@@ -940,14 -898,9 +941,14 @@@ } if (!list.nr) { + int hit; if (!cached) setup_work_tree(); - return !grep_cache(&opt, paths, cached, external_grep_allowed); + + hit = grep_cache(&opt, paths, cached); + if (use_threads) + hit |= wait_all(); + return !hit; } if (cached) @@@ -956,15 -909,9 +957,15 @@@ for (i = 0; i < list.nr; i++) { struct object *real_obj; real_obj = deref_tag(list.objects[i].item, NULL, 0); - if (grep_object(&opt, paths, real_obj, list.objects[i].name)) + if (grep_object(&opt, paths, real_obj, list.objects[i].name)) { hit = 1; + if (opt.status_only) + break; + } } + + if (use_threads) + hit |= wait_all(); free_grep_patterns(&opt); return !hit; } diff --combined builtin-rev-list.c index c924b3a2c7,c53ad9fa08..5679170e82 --- a/builtin-rev-list.c +++ b/builtin-rev-list.c @@@ -253,7 -253,7 +253,7 @@@ static void print_var_int(const char *v printf("%s=%d\n", var, val); } -int show_bisect_vars(struct rev_list_info *info, int reaches, int all) +static int show_bisect_vars(struct rev_list_info *info, int reaches, int all) { int cnt, flags = info->bisect_show_flags; char hex[41] = ""; @@@ -371,8 -371,9 +371,9 @@@ int cmd_rev_list(int argc, const char * revs.diff) usage(rev_list_usage); - save_commit_buffer = revs.verbose_header || - revs.grep_filter.pattern_list; + save_commit_buffer = (revs.verbose_header || + revs.grep_filter.pattern_list || + revs.grep_filter.header_list); if (bisect_list) revs.limited = 1; diff --combined grep.c index a0864f1cbb,eee99f31f1..90a063a985 --- a/grep.c +++ b/grep.c @@@ -11,8 -11,8 +11,8 @@@ void append_header_grep_pattern(struct p->no = 0; p->token = GREP_PATTERN_HEAD; p->field = field; - *opt->pattern_tail = p; - opt->pattern_tail = &p->next; + *opt->header_tail = p; + opt->header_tail = &p->next; p->next = NULL; } @@@ -29,26 -29,11 +29,26 @@@ void append_grep_pattern(struct grep_op p->next = NULL; } -static int is_fixed(const char *s) +struct grep_opt *grep_opt_dup(const struct grep_opt *opt) { - while (*s && !is_regex_special(*s)) - s++; - return !*s; + struct grep_pat *pat; + struct grep_opt *ret = xmalloc(sizeof(struct grep_opt)); + *ret = *opt; + + ret->pattern_list = NULL; + ret->pattern_tail = &ret->pattern_list; + + for(pat = opt->pattern_list; pat != NULL; pat = pat->next) + { + if(pat->token == GREP_PATTERN_HEAD) + append_header_grep_pattern(ret, pat->field, + pat->pattern); + else + append_grep_pattern(ret, pat->pattern, pat->origin, + pat->no, pat->token); + } + + return ret; } static void compile_regexp(struct grep_pat *p, struct grep_opt *opt) @@@ -57,8 -42,11 +57,8 @@@ p->word_regexp = opt->word_regexp; p->ignore_case = opt->ignore_case; + p->fixed = opt->fixed; - if (opt->fixed || is_fixed(p->pattern)) - p->fixed = 1; - if (opt->regflags & REG_ICASE) - p->fixed = 0; if (p->fixed) return; @@@ -184,9 -172,26 +184,26 @@@ static struct grep_expr *compile_patter void compile_grep_patterns(struct grep_opt *opt) { struct grep_pat *p; + struct grep_expr *header_expr = NULL; - if (opt->all_match) - opt->extended = 1; + if (opt->header_list) { + p = opt->header_list; + header_expr = compile_pattern_expr(&p); + if (p) + die("incomplete pattern expression: %s", p->pattern); + for (p = opt->header_list; p; p = p->next) { + switch (p->token) { + case GREP_PATTERN: /* atom */ + case GREP_PATTERN_HEAD: + case GREP_PATTERN_BODY: + compile_regexp(p, opt); + break; + default: + opt->extended = 1; + break; + } + } + } for (p = opt->pattern_list; p; p = p->next) { switch (p->token) { @@@ -201,7 -206,9 +218,9 @@@ } } - if (!opt->extended) + if (opt->all_match || header_expr) + opt->extended = 1; + else if (!opt->extended) return; /* Then bundle them up in an expression. @@@ -212,6 -219,21 +231,21 @@@ opt->pattern_expression = compile_pattern_expr(&p); if (p) die("incomplete pattern expression: %s", p->pattern); + + if (!header_expr) + return; + + if (opt->pattern_expression) { + struct grep_expr *z; + z = xcalloc(1, sizeof(*z)); + z->node = GREP_NODE_OR; + z->u.binary.left = opt->pattern_expression; + z->u.binary.right = header_expr; + opt->pattern_expression = z; + } else { + opt->pattern_expression = header_expr; + } + opt->all_match = 1; } static void free_pattern_expr(struct grep_expr *x) @@@ -272,8 -294,7 +306,8 @@@ static int word_char(char ch static void show_name(struct grep_opt *opt, const char *name) { - printf("%s%c", name, opt->null_following_name ? '\0' : '\n'); + opt->output(opt, name, strlen(name)); + opt->output(opt, opt->null_following_name ? "\0" : "\n", 1); } @@@ -510,32 -531,24 +544,32 @@@ static void show_line(struct grep_opt * const char *name, unsigned lno, char sign) { int rest = eol - bol; + char sign_str[1]; + sign_str[0] = sign; if (opt->pre_context || opt->post_context) { if (opt->last_shown == 0) { if (opt->show_hunk_mark) - fputs("--\n", stdout); + opt->output(opt, "--\n", 3); else opt->show_hunk_mark = 1; } else if (lno > opt->last_shown + 1) - fputs("--\n", stdout); + opt->output(opt, "--\n", 3); } opt->last_shown = lno; if (opt->null_following_name) - sign = '\0'; - if (opt->pathname) - printf("%s%c", name, sign); - if (opt->linenum) - printf("%d%c", lno, sign); + sign_str[0] = '\0'; + if (opt->pathname) { + opt->output(opt, name, strlen(name)); + opt->output(opt, sign_str, 1); + } + if (opt->linenum) { + char buf[32]; + snprintf(buf, sizeof(buf), "%d", lno); + opt->output(opt, buf, strlen(buf)); + opt->output(opt, sign_str, 1); + } if (opt->color) { regmatch_t match; enum grep_context ctx = GREP_CONTEXT_BODY; @@@ -546,22 -559,18 +580,22 @@@ while (next_match(opt, bol, eol, ctx, &match, eflags)) { if (match.rm_so == match.rm_eo) break; - printf("%.*s%s%.*s%s", - (int)match.rm_so, bol, - opt->color_match, - (int)(match.rm_eo - match.rm_so), bol + match.rm_so, - GIT_COLOR_RESET); + + opt->output(opt, bol, match.rm_so); + opt->output(opt, opt->color_match, + strlen(opt->color_match)); + opt->output(opt, bol + match.rm_so, + (int)(match.rm_eo - match.rm_so)); + opt->output(opt, GIT_COLOR_RESET, + strlen(GIT_COLOR_RESET)); bol += match.rm_eo; rest -= match.rm_eo; eflags = REG_NOTBOL; } *eol = ch; } - printf("%.*s\n", rest, bol); + opt->output(opt, bol, rest); + opt->output(opt, "\n", 1); } static int match_funcname(struct grep_opt *opt, char *bol, char *eol) @@@ -640,98 -649,6 +674,98 @@@ static void show_pre_context(struct gre } } +static int should_lookahead(struct grep_opt *opt) +{ + struct grep_pat *p; + + if (opt->extended) + return 0; /* punt for too complex stuff */ + if (opt->invert) + return 0; + for (p = opt->pattern_list; p; p = p->next) { + if (p->token != GREP_PATTERN) + return 0; /* punt for "header only" and stuff */ + } + return 1; +} + +static int look_ahead(struct grep_opt *opt, + unsigned long *left_p, + unsigned *lno_p, + char **bol_p) +{ + unsigned lno = *lno_p; + char *bol = *bol_p; + struct grep_pat *p; + char *sp, *last_bol; + regoff_t earliest = -1; + + for (p = opt->pattern_list; p; p = p->next) { + int hit; + regmatch_t m; + + if (p->fixed) + hit = !fixmatch(p->pattern, bol, p->ignore_case, &m); + else { +#ifdef REG_STARTEND + m.rm_so = 0; + m.rm_eo = *left_p; + hit = !regexec(&p->regexp, bol, 1, &m, REG_STARTEND); +#else + hit = !regexec(&p->regexp, bol, 1, &m, 0); +#endif + } + if (!hit || m.rm_so < 0 || m.rm_eo < 0) + continue; + if (earliest < 0 || m.rm_so < earliest) + earliest = m.rm_so; + } + + if (earliest < 0) { + *bol_p = bol + *left_p; + *left_p = 0; + return 1; + } + for (sp = bol + earliest; bol < sp && sp[-1] != '\n'; sp--) + ; /* find the beginning of the line */ + last_bol = sp; + + for (sp = bol; sp < last_bol; sp++) { + if (*sp == '\n') + lno++; + } + *left_p -= last_bol - bol; + *bol_p = last_bol; + *lno_p = lno; + return 0; +} + +int grep_threads_ok(const struct grep_opt *opt) +{ + /* If this condition is true, then we may use the attribute + * machinery in grep_buffer_1. The attribute code is not + * thread safe, so we disable the use of threads. + */ + if (opt->funcname && !opt->unmatch_name_only && !opt->status_only && + !opt->name_only) + return 0; + + /* If we are showing hunk marks, we should not do it for the + * first match. The synchronization problem we get for this + * constraint is not yet solved, so we disable threading in + * this case. + */ + if (opt->pre_context || opt->post_context) + return 0; + + return 1; +} + +static void std_output(struct grep_opt *opt, const void *buf, size_t size) +{ + fwrite(buf, size, 1, stdout); +} + static int grep_buffer_1(struct grep_opt *opt, const char *name, char *buf, unsigned long size, int collect_hits) { @@@ -741,15 -658,11 +775,15 @@@ unsigned last_hit = 0; int binary_match_only = 0; unsigned count = 0; + int try_lookahead = 0; enum grep_context ctx = GREP_CONTEXT_HEAD; xdemitconf_t xecfg; opt->last_shown = 0; + if (!opt->output) + opt->output = std_output; + if (buffer_is_binary(buf, size)) { switch (opt->binary) { case GREP_BINARY_DEFAULT: @@@ -773,26 -686,11 +807,26 @@@ opt->priv = &xecfg; } } + try_lookahead = should_lookahead(opt); while (left) { char *eol, ch; int hit; + /* + * look_ahead() skips quicly to the line that possibly + * has the next hit; don't call it if we need to do + * something more than just skipping the current line + * in response to an unmatch for the current line. E.g. + * inside a post-context window, we will show the current + * line as a context around the previous hit when it + * doesn't hit. + */ + if (try_lookahead + && !(last_hit + && lno <= last_hit + opt->post_context) + && look_ahead(opt, &left, &lno, &bol)) + break; eol = end_of_line(bol, &left); ch = *eol; *eol = 0; @@@ -822,9 -720,7 +856,9 @@@ if (opt->status_only) return 1; if (binary_match_only) { - printf("Binary file %s matches\n", name); + opt->output(opt, "Binary file ", 12); + opt->output(opt, name, strlen(name)); + opt->output(opt, " matches\n", 9); return 1; } if (opt->name_only) { @@@ -880,13 -776,9 +914,13 @@@ * which feels mostly useless but sometimes useful. Maybe * make it another option? For now suppress them. */ - if (opt->count && count) - printf("%s%c%u\n", name, - opt->null_following_name ? '\0' : ':', count); + if (opt->count && count) { + char buf[32]; + opt->output(opt, name, strlen(name)); + snprintf(buf, sizeof(buf), "%c%u\n", + opt->null_following_name ? '\0' : ':', count); + opt->output(opt, buf, strlen(buf)); + } return !!last_hit; } diff --combined grep.h index 9703087996,e39e5146d8..d35bc29bfd --- a/grep.h +++ b/grep.h @@@ -59,6 -59,8 +59,8 @@@ struct grep_expr struct grep_opt { struct grep_pat *pattern_list; struct grep_pat **pattern_tail; + struct grep_pat *header_list; + struct grep_pat **header_tail; struct grep_expr *pattern_expression; const char *prefix; int prefix_length; @@@ -85,15 -87,13 +87,15 @@@ int max_depth; int funcname; char color_match[COLOR_MAXLEN]; - const char *color_external; int regflags; unsigned pre_context; unsigned post_context; unsigned last_shown; int show_hunk_mark; void *priv; + + void (*output)(struct grep_opt *opt, const void *data, size_t size); + void *output_priv; }; extern void append_grep_pattern(struct grep_opt *opt, const char *pat, const char *origin, int no, enum grep_pat_token t); @@@ -102,7 -102,4 +104,7 @@@ extern void compile_grep_patterns(struc extern void free_grep_patterns(struct grep_opt *opt); extern int grep_buffer(struct grep_opt *opt, const char *name, char *buf, unsigned long size); +extern struct grep_opt *grep_opt_dup(const struct grep_opt *opt); +extern int grep_threads_ok(const struct grep_opt *opt); + #endif diff --combined revision.c index a8f0aa4c67,c84243d7bb..29721ecf84 --- a/revision.c +++ b/revision.c @@@ -134,20 -134,10 +134,20 @@@ static void add_pending_object_with_mod { if (revs->no_walk && (obj->flags & UNINTERESTING)) revs->no_walk = 0; - if (revs->reflog_info && obj->type == OBJ_COMMIT && - add_reflog_for_walk(revs->reflog_info, - (struct commit *)obj, name)) - return; + if (revs->reflog_info && obj->type == OBJ_COMMIT) { + struct strbuf buf = STRBUF_INIT; + int len = interpret_branch_name(name, &buf); + int st; + + if (0 < len && name[len] && buf.len) + strbuf_addstr(&buf, name + len); + st = add_reflog_for_walk(revs->reflog_info, + (struct commit *)obj, + buf.buf[0] ? buf.buf: name); + strbuf_release(&buf); + if (st) + return; + } add_object_array_with_mode(obj, name, &revs->pending, mode); } @@@ -278,7 -268,7 +278,7 @@@ static int tree_difference = REV_TREE_S static void file_add_remove(struct diff_options *options, int addremove, unsigned mode, const unsigned char *sha1, - const char *fullpath) + const char *fullpath, unsigned dirty_submodule) { int diff = addremove == '+' ? REV_TREE_NEW : REV_TREE_OLD; @@@ -291,8 -281,7 +291,8 @@@ static void file_change(struct diff_opt unsigned old_mode, unsigned new_mode, const unsigned char *old_sha1, const unsigned char *new_sha1, - const char *fullpath) + const char *fullpath, + unsigned old_dirty_submodule, unsigned new_dirty_submodule) { tree_difference = REV_TREE_DIFFERENT; DIFF_OPT_SET(options, HAS_CHANGES); @@@ -547,9 -536,6 +547,9 @@@ static void cherry_pick_list(struct com right_count++; } + if (!left_count || !right_count) + return; + left_first = left_count < right_count; init_patch_ids(&ids); if (revs->diffopt.nr_paths) { @@@ -713,18 -699,12 +713,18 @@@ static int handle_one_ref(const char *p return 0; } +static void init_all_refs_cb(struct all_refs_cb *cb, struct rev_info *revs, + unsigned flags) +{ + cb->all_revs = revs; + cb->all_flags = flags; +} + static void handle_refs(struct rev_info *revs, unsigned flags, int (*for_each)(each_ref_fn, void *)) { struct all_refs_cb cb; - cb.all_revs = revs; - cb.all_flags = flags; + init_all_refs_cb(&cb, revs, flags); for_each(handle_one_ref, &cb); } @@@ -826,6 -806,7 +826,7 @@@ void init_revisions(struct rev_info *re revs->grep_filter.status_only = 1; revs->grep_filter.pattern_tail = &(revs->grep_filter.pattern_list); + revs->grep_filter.header_tail = &(revs->grep_filter.header_list); revs->grep_filter.regflags = REG_NEWLINE; diff_setup(&revs->diffopt); @@@ -1181,22 -1162,13 +1182,22 @@@ static int handle_revision_opt(struct r revs->verbose_header = 1; } else if (!strcmp(arg, "--pretty")) { revs->verbose_header = 1; + revs->pretty_given = 1; get_commit_format(arg+8, revs); } else if (!prefixcmp(arg, "--pretty=") || !prefixcmp(arg, "--format=")) { revs->verbose_header = 1; + revs->pretty_given = 1; get_commit_format(arg+9, revs); + } else if (!strcmp(arg, "--show-notes")) { + revs->show_notes = 1; + revs->show_notes_given = 1; + } else if (!strcmp(arg, "--no-notes")) { + revs->show_notes = 0; + revs->show_notes_given = 1; } else if (!strcmp(arg, "--oneline")) { revs->verbose_header = 1; get_commit_format("oneline", revs); + revs->pretty_given = 1; revs->abbrev_commit = 1; } else if (!strcmp(arg, "--graph")) { revs->topo_order = 1; @@@ -1381,30 -1353,6 +1382,30 @@@ int setup_revisions(int argc, const cha handle_refs(revs, flags, for_each_remote_ref); continue; } + if (!prefixcmp(arg, "--glob=")) { + struct all_refs_cb cb; + init_all_refs_cb(&cb, revs, flags); + for_each_glob_ref(handle_one_ref, arg + 7, &cb); + continue; + } + if (!prefixcmp(arg, "--branches=")) { + struct all_refs_cb cb; + init_all_refs_cb(&cb, revs, flags); + for_each_glob_ref_in(handle_one_ref, arg + 11, "refs/heads/", &cb); + continue; + } + if (!prefixcmp(arg, "--tags=")) { + struct all_refs_cb cb; + init_all_refs_cb(&cb, revs, flags); + for_each_glob_ref_in(handle_one_ref, arg + 7, "refs/tags/", &cb); + continue; + } + if (!prefixcmp(arg, "--remotes=")) { + struct all_refs_cb cb; + init_all_refs_cb(&cb, revs, flags); + for_each_glob_ref_in(handle_one_ref, arg + 10, "refs/remotes/", &cb); + continue; + } if (!strcmp(arg, "--reflog")) { handle_reflog(revs, flags); continue; @@@ -1804,7 -1752,7 +1805,7 @@@ static int rewrite_parents(struct rev_i static int commit_match(struct commit *commit, struct rev_info *opt) { - if (!opt->grep_filter.pattern_list) + if (!opt->grep_filter.pattern_list && !opt->grep_filter.header_list) return 1; return grep_buffer(&opt->grep_filter, NULL, /* we say nothing, not even filename */ diff --combined t/t7002-grep.sh index 0b583cbfc1,6baa4461f7..af63d6ec6d --- a/t/t7002-grep.sh +++ b/t/t7002-grep.sh @@@ -8,6 -8,18 +8,6 @@@ test_description='git grep various . ./test-lib.sh -test_expect_success 'Check for external grep support' ' - case "$(git grep -h 2>&1|grep ext-grep)" in - *"(default)"*) - test_set_prereq EXTGREP - true;; - *"(ignored by this build)"*) - true;; - *) - false;; - esac -' - cat >hello.c < int main(int argc, const char **argv) @@@ -291,14 -303,6 +291,14 @@@ y:y y z:zzz EOF +test_expect_success 'grep -q, silently report matches' ' + >empty && + git grep -q mmap >actual && + test_cmp empty actual && + test_must_fail git grep -q qfwfq >actual && + test_cmp empty actual +' + # Create 1024 file names that sort between "y" and "z" to make sure # the two files are handled by different calls to an external grep. # This depends on MAXARGS in builtin-grep.c being 1024 or less. @@@ -310,8 -314,8 +310,8 @@@ test_expect_success 'grep -C1, hunk mar test_cmp expected actual ' -test_expect_success 'grep -C1 --no-ext-grep, hunk mark between files' ' - git grep -C1 --no-ext-grep "^[yz]" >actual && +test_expect_success 'grep -C1 hunk mark between files' ' + git grep -C1 "^[yz]" >actual && test_cmp expected actual ' @@@ -353,7 -357,7 +353,7 @@@ test_expect_success 'log grep (4)' ' test_expect_success 'log grep (5)' ' - git log --author=Thor -F --grep=Thu --pretty=tformat:%s >actual && + git log --author=Thor -F --pretty=tformat:%s >actual && ( echo third ; echo initial ) >expect && test_cmp expect actual ' @@@ -364,10 -368,18 +364,18 @@@ test_expect_success 'log grep (6)' test_cmp expect actual ' + test_expect_success 'log --grep --author implicitly uses all-match' ' + # grep matches initial and second but not third + # author matches only initial and third + git log --author="A U Thor" --grep=s --grep=l --format=%s >actual && + echo initial >expect && + test_cmp expect actual + ' + test_expect_success 'grep with CE_VALID file' ' git update-index --assume-unchanged t/t && rm t/t && - test "$(git grep --no-ext-grep test)" = "t/t:test" && + test "$(git grep test)" = "t/t:test" && git update-index --no-assume-unchanged t/t && git checkout t/t ' @@@ -434,37 -446,16 +442,37 @@@ test_expect_success 'grep -Fi' test_cmp expected actual ' -test_expect_success EXTGREP 'external grep is called' ' - GIT_TRACE=2 git grep foo >/dev/null 2>actual && - grep "trace: grep:.*foo" actual >/dev/null +test_expect_success 'setup double-dash tests' ' +cat >double-dash < +other +EOF +git add double-dash +' + +cat >expected < +EOF +test_expect_success 'grep -- pattern' ' + git grep -- "->" >actual && + test_cmp expected actual +' +test_expect_success 'grep -- pattern -- pathspec' ' + git grep -- "->" -- double-dash >actual && + test_cmp expected actual +' +test_expect_success 'grep -e pattern -- path' ' + git grep -e "->" -- double-dash >actual && + test_cmp expected actual ' -test_expect_success EXTGREP 'no external grep when skip-worktree entries exist' ' - git update-index --skip-worktree file && - GIT_TRACE=2 git grep foo >/dev/null 2>actual && - ! grep "trace: grep:" actual >/dev/null && - git update-index --no-skip-worktree file +cat >expected <actual && + test_cmp expected actual ' test_done