X-Git-Url: https://git.tokkee.org/?a=blobdiff_plain;ds=sidebyside;f=builtin-grep.c;h=ad7dc00cde4e8e08ef35b313525781c135357df3;hb=747fa12cef73b6ca04fffaddaad7326cf546cdea;hp=2e7986cecefc964f665b10d363569951c1f40293;hpb=b8ca3fbd462f94b980af828528c8f1fa59601b57;p=git.git

diff --git a/builtin-grep.c b/builtin-grep.c
index 2e7986cec..ad7dc00cd 100644
--- a/builtin-grep.c
+++ b/builtin-grep.c
@@ -11,6 +11,7 @@
 #include "tree-walk.h"
 #include "builtin.h"
 #include <regex.h>
+#include "grep.h"
 #include <fnmatch.h>
 #include <sys/wait.h>
 
@@ -82,301 +83,40 @@ static int pathspec_matches(const char **paths, const char *name)
 	return 0;
 }
 
-struct grep_pat {
-	struct grep_pat *next;
-	const char *origin;
-	int no;
-	const char *pattern;
-	regex_t regexp;
-};
-
-struct grep_opt {
-	struct grep_pat *pattern_list;
-	struct grep_pat **pattern_tail;
-	regex_t regexp;
-	unsigned linenum:1;
-	unsigned invert:1;
-	unsigned name_only:1;
-	unsigned unmatch_name_only:1;
-	unsigned count:1;
-	unsigned word_regexp:1;
-	unsigned fixed:1;
-#define GREP_BINARY_DEFAULT	0
-#define GREP_BINARY_NOMATCH	1
-#define GREP_BINARY_TEXT	2
-	unsigned binary:2;
-	int regflags;
-	unsigned pre_context;
-	unsigned post_context;
-};
-
-static void add_pattern(struct grep_opt *opt, const char *pat,
-			const char *origin, int no)
-{
-	struct grep_pat *p = xcalloc(1, sizeof(*p));
-	p->pattern = pat;
-	p->origin = origin;
-	p->no = no;
-	*opt->pattern_tail = p;
-	opt->pattern_tail = &p->next;
-	p->next = NULL;
-}
-
-static void compile_patterns(struct grep_opt *opt)
-{
-	struct grep_pat *p;
-	for (p = opt->pattern_list; p; p = p->next) {
-		int err = regcomp(&p->regexp, p->pattern, opt->regflags);
-		if (err) {
-			char errbuf[1024];
-			char where[1024];
-			if (p->no)
-				sprintf(where, "In '%s' at %d, ",
-					p->origin, p->no);
-			else if (p->origin)
-				sprintf(where, "%s, ", p->origin);
-			else
-				where[0] = 0;
-			regerror(err, &p->regexp, errbuf, 1024);
-			regfree(&p->regexp);
-			die("%s'%s': %s", where, p->pattern, errbuf);
-		}
-	}
-}
-
-static char *end_of_line(char *cp, unsigned long *left)
-{
-	unsigned long l = *left;
-	while (l && *cp != '\n') {
-		l--;
-		cp++;
-	}
-	*left = l;
-	return cp;
-}
-
-static int word_char(char ch)
-{
-	return isalnum(ch) || ch == '_';
-}
-
-static void show_line(struct grep_opt *opt, const char *bol, const char *eol,
-		      const char *name, unsigned lno, char sign)
-{
-	printf("%s%c", name, sign);
-	if (opt->linenum)
-		printf("%d%c", lno, sign);
-	printf("%.*s\n", (int)(eol-bol), bol);
-}
-
-/*
- * NEEDSWORK: share code with diff.c
- */
-#define FIRST_FEW_BYTES 8000
-static int buffer_is_binary(const char *ptr, unsigned long size)
-{
-	if (FIRST_FEW_BYTES < size)
-		size = FIRST_FEW_BYTES;
-	if (memchr(ptr, 0, size))
-		return 1;
-	return 0;
-}
-
-static int fixmatch(const char *pattern, char *line, regmatch_t *match)
-{
-	char *hit = strstr(line, pattern);
-	if (!hit) {
-		match->rm_so = match->rm_eo = -1;
-		return REG_NOMATCH;
-	}
-	else {
-		match->rm_so = hit - line;
-		match->rm_eo = match->rm_so + strlen(pattern);
-		return 0;
-	}
-}
-
-static int grep_buffer(struct grep_opt *opt, const char *name,
-		       char *buf, unsigned long size)
-{
-	char *bol = buf;
-	unsigned long left = size;
-	unsigned lno = 1;
-	struct pre_context_line {
-		char *bol;
-		char *eol;
-	} *prev = NULL, *pcl;
-	unsigned last_hit = 0;
-	unsigned last_shown = 0;
-	int binary_match_only = 0;
-	const char *hunk_mark = "";
-	unsigned count = 0;
-
-	if (buffer_is_binary(buf, size)) {
-		switch (opt->binary) {
-		case GREP_BINARY_DEFAULT:
-			binary_match_only = 1;
-			break;
-		case GREP_BINARY_NOMATCH:
-			return 0; /* Assume unmatch */
-			break;
-		default:
-			break;
-		}
-	}
-
-	if (opt->pre_context)
-		prev = xcalloc(opt->pre_context, sizeof(*prev));
-	if (opt->pre_context || opt->post_context)
-		hunk_mark = "--\n";
-
-	while (left) {
-		regmatch_t pmatch[10];
-		char *eol, ch;
-		int hit = 0;
-		struct grep_pat *p;
-
-		eol = end_of_line(bol, &left);
-		ch = *eol;
-		*eol = 0;
-
-		for (p = opt->pattern_list; p; p = p->next) {
-			if (!opt->fixed) {
-				regex_t *exp = &p->regexp;
-				hit = !regexec(exp, bol, ARRAY_SIZE(pmatch),
-					       pmatch, 0);
-			}
-			else {
-				hit = !fixmatch(p->pattern, bol, pmatch);
-			}
-
-			if (hit && opt->word_regexp) {
-				/* Match beginning must be either
-				 * beginning of the line, or at word
-				 * boundary (i.e. the last char must
-				 * not be alnum or underscore).
-				 */
-				if ((pmatch[0].rm_so < 0) ||
-				    (eol - bol) <= pmatch[0].rm_so ||
-				    (pmatch[0].rm_eo < 0) ||
-				    (eol - bol) < pmatch[0].rm_eo)
-					die("regexp returned nonsense");
-				if (pmatch[0].rm_so != 0 &&
-				    word_char(bol[pmatch[0].rm_so-1]))
-					hit = 0;
-				if (pmatch[0].rm_eo != (eol-bol) &&
-				    word_char(bol[pmatch[0].rm_eo]))
-					hit = 0;
-			}
-			if (hit)
-				break;
-		}
-		/* "grep -v -e foo -e bla" should list lines
-		 * that do not have either, so inversion should
-		 * be done outside.
-		 */
-		if (opt->invert)
-			hit = !hit;
-		if (opt->unmatch_name_only) {
-			if (hit)
-				return 0;
-			goto next_line;
-		}
-		if (hit) {
-			count++;
-			if (binary_match_only) {
-				printf("Binary file %s matches\n", name);
-				return 1;
-			}
-			if (opt->name_only) {
-				printf("%s\n", name);
-				return 1;
-			}
-			/* Hit at this line.  If we haven't shown the
-			 * pre-context lines, we would need to show them.
-			 * When asked to do "count", this still show
-			 * the context which is nonsense, but the user
-			 * deserves to get that ;-).
-			 */
-			if (opt->pre_context) {
-				unsigned from;
-				if (opt->pre_context < lno)
-					from = lno - opt->pre_context;
-				else
-					from = 1;
-				if (from <= last_shown)
-					from = last_shown + 1;
-				if (last_shown && from != last_shown + 1)
-					printf(hunk_mark);
-				while (from < lno) {
-					pcl = &prev[lno-from-1];
-					show_line(opt, pcl->bol, pcl->eol,
-						  name, from, '-');
-					from++;
-				}
-				last_shown = lno-1;
-			}
-			if (last_shown && lno != last_shown + 1)
-				printf(hunk_mark);
-			if (!opt->count)
-				show_line(opt, bol, eol, name, lno, ':');
-			last_shown = last_hit = lno;
-		}
-		else if (last_hit &&
-			 lno <= last_hit + opt->post_context) {
-			/* If the last hit is within the post context,
-			 * we need to show this line.
-			 */
-			if (last_shown && lno != last_shown + 1)
-				printf(hunk_mark);
-			show_line(opt, bol, eol, name, lno, '-');
-			last_shown = lno;
-		}
-		if (opt->pre_context) {
-			memmove(prev+1, prev,
-				(opt->pre_context-1) * sizeof(*prev));
-			prev->bol = bol;
-			prev->eol = eol;
-		}
-
-	next_line:
-		*eol = ch;
-		bol = eol + 1;
-		if (!left)
-			break;
-		left--;
-		lno++;
-	}
-
-	if (opt->unmatch_name_only) {
-		/* We did not see any hit, so we want to show this */
-		printf("%s\n", name);
-		return 1;
-	}
-
-	/* NEEDSWORK:
-	 * The real "grep -c foo *.c" gives many "bar.c:0" lines,
-	 * which feels mostly useless but sometimes useful.  Maybe
-	 * make it another option?  For now suppress them.
-	 */
-	if (opt->count && count)
-		printf("%s:%u\n", name, count);
-	return !!last_hit;
-}
-
-static int grep_sha1(struct grep_opt *opt, const unsigned char *sha1, const char *name)
+static int grep_sha1(struct grep_opt *opt, const unsigned char *sha1, const char *name, int tree_name_len)
 {
 	unsigned long size;
 	char *data;
 	char type[20];
+	char *to_free = NULL;
 	int hit;
+
 	data = read_sha1_file(sha1, type, &size);
 	if (!data) {
 		error("'%s': unable to read %s", name, sha1_to_hex(sha1));
 		return 0;
 	}
+	if (opt->relative && opt->prefix_length) {
+		static char name_buf[PATH_MAX];
+		char *cp;
+		int name_len = strlen(name) - opt->prefix_length + 1;
+
+		if (!tree_name_len)
+			name += opt->prefix_length;
+		else {
+			if (ARRAY_SIZE(name_buf) <= name_len)
+				cp = to_free = xmalloc(name_len);
+			else
+				cp = name_buf;
+			memcpy(cp, name, tree_name_len);
+			strcpy(cp + tree_name_len,
+			       name + tree_name_len + opt->prefix_length);
+			name = cp;
+		}
+	}
 	hit = grep_buffer(opt, name, data, size);
 	free(data);
+	free(to_free);
 	return hit;
 }
 
@@ -406,6 +146,8 @@ static int grep_file(struct grep_opt *opt, const char *filename)
 		return 0;
 	}
 	close(i);
+	if (opt->relative && opt->prefix_length)
+		filename += opt->prefix_length;
 	i = grep_buffer(opt, filename, data, st.st_size);
 	free(data);
 	return i;
@@ -446,18 +188,22 @@ static int exec_grep(int argc, const char **argv)
 
 static int external_grep(struct grep_opt *opt, const char **paths, int cached)
 {
-	int i, nr, argc, hit, len;
+	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))
+		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->regflags & REG_ICASE)
@@ -536,12 +282,17 @@ static int external_grep(struct grep_opt *opt, const char **paths, int cached)
 		argv[argc++] = name;
 		if (argc < MAXARGS)
 			continue;
-		hit += exec_grep(argc, argv);
+		status = exec_grep(argc, argv);
+		if (0 < status)
+			hit = 1;
 		argc = nr;
 	}
-	if (argc > nr)
-		hit += exec_grep(argc, argv);
-	return 0;
+	if (argc > nr) {
+		status = exec_grep(argc, argv);
+		if (0 < status)
+			hit = 1;
+	}
+	return hit;
 }
 
 static int grep_cache(struct grep_opt *opt, const char **paths, int cached)
@@ -570,10 +321,11 @@ static int grep_cache(struct grep_opt *opt, const char **paths, int cached)
 		if (!pathspec_matches(paths, ce->name))
 			continue;
 		if (cached)
-			hit |= grep_sha1(opt, ce->sha1, ce->name);
+			hit |= grep_sha1(opt, ce->sha1, ce->name, 0);
 		else
 			hit |= grep_file(opt, ce->name);
 	}
+	free_grep_patterns(opt);
 	return hit;
 }
 
@@ -585,11 +337,12 @@ static int grep_tree(struct grep_opt *opt, const char **paths,
 	int hit = 0;
 	struct name_entry entry;
 	char *down;
-	char *path_buf = xmalloc(PATH_MAX + strlen(tree_name) + 100);
+	int tn_len = strlen(tree_name);
+	char *path_buf = xmalloc(PATH_MAX + tn_len + 100);
 
-	if (tree_name[0]) {
-		int offset = sprintf(path_buf, "%s:", tree_name);
-		down = path_buf + offset;
+	if (tn_len) {
+		tn_len = sprintf(path_buf, "%s:", tree_name);
+		down = path_buf + tn_len;
 		strcat(down, base);
 	}
 	else {
@@ -611,7 +364,7 @@ static int grep_tree(struct grep_opt *opt, const char **paths,
 		if (!pathspec_matches(paths, down))
 			;
 		else if (S_ISREG(entry.mode))
-			hit |= grep_sha1(opt, entry.sha1, path_buf);
+			hit |= grep_sha1(opt, entry.sha1, path_buf, tn_len);
 		else if (S_ISDIR(entry.mode)) {
 			char type[20];
 			struct tree_desc sub;
@@ -631,9 +384,9 @@ static int grep_tree(struct grep_opt *opt, const char **paths,
 static int grep_object(struct grep_opt *opt, const char **paths,
 		       struct object *obj, const char *name)
 {
-	if (obj->type == TYPE_BLOB)
-		return grep_sha1(opt, obj->sha1, name);
-	if (obj->type == TYPE_COMMIT || obj->type == TYPE_TREE) {
+	if (obj->type == OBJ_BLOB)
+		return grep_sha1(opt, obj->sha1, name, 0);
+	if (obj->type == OBJ_COMMIT || obj->type == OBJ_TREE) {
 		struct tree_desc tree;
 		void *data;
 		int hit;
@@ -652,18 +405,27 @@ static int grep_object(struct grep_opt *opt, const char **paths,
 static const char builtin_grep_usage[] =
 "git-grep <option>* <rev>* [-e] <pattern> [<path>...]";
 
-int cmd_grep(int argc, const char **argv, char **envp)
+static const char emsg_invalid_context_len[] =
+"%s: invalid context length argument";
+static const char emsg_missing_context_len[] =
+"missing context length argument";
+static const char emsg_missing_argument[] =
+"option requires an argument -%s";
+
+int cmd_grep(int argc, const char **argv, const char *prefix)
 {
 	int hit = 0;
 	int cached = 0;
 	int seen_dashdash = 0;
 	struct grep_opt opt;
 	struct object_array list = { 0, 0, NULL };
-	const char *prefix = setup_git_directory();
 	const char **paths = NULL;
 	int i;
 
 	memset(&opt, 0, sizeof(opt));
+	opt.prefix_length = (prefix && *prefix) ? strlen(prefix) : 0;
+	opt.relative = 1;
+	opt.pathname = 1;
 	opt.pattern_tail = &opt.pattern_list;
 	opt.regflags = REG_NEWLINE;
 
@@ -674,7 +436,7 @@ int cmd_grep(int argc, const char **argv, char **envp)
 	 * pattern, but then what follows it must be zero or more
 	 * valid refs up to the -- (if exists), and then existing
 	 * paths.  If there is an explicit pattern, then the first
-	 * unrecocnized non option is the beginning of the refs list
+	 * unrecognized non option is the beginning of the refs list
 	 * that continues up to the -- (if exists), and then paths.
 	 */
 
@@ -723,10 +485,12 @@ int cmd_grep(int argc, const char **argv, char **envp)
 			opt.linenum = 1;
 			continue;
 		}
+		if (!strcmp("-h", arg)) {
+			opt.pathname = 0;
+			continue;
+		}
 		if (!strcmp("-H", arg)) {
-			/* We always show the pathname, so this
-			 * is a noop.
-			 */
+			opt.pathname = 1;
 			continue;
 		}
 		if (!strcmp("-l", arg) ||
@@ -759,7 +523,7 @@ int cmd_grep(int argc, const char **argv, char **envp)
 			case 'A': case 'B': case 'C':
 				if (!arg[2]) {
 					if (argc <= 1)
-						usage(builtin_grep_usage);
+						die(emsg_missing_context_len);
 					scan = *++argv;
 					argc--;
 				}
@@ -771,7 +535,7 @@ int cmd_grep(int argc, const char **argv, char **envp)
 				break;
 			}
 			if (sscanf(scan, "%u", &num) != 1)
-				usage(builtin_grep_usage);
+				die(emsg_invalid_context_len, scan);
 			switch (arg[1]) {
 			case 'A':
 				opt.post_context = num;
@@ -790,7 +554,7 @@ int cmd_grep(int argc, const char **argv, char **envp)
 			int lno = 0;
 			char buf[1024];
 			if (argc <= 1)
-				usage(builtin_grep_usage);
+				die(emsg_missing_argument, arg);
 			patterns = fopen(argv[1], "r");
 			if (!patterns)
 				die("'%s': %s", argv[1], strerror(errno));
@@ -801,30 +565,69 @@ int cmd_grep(int argc, const char **argv, char **envp)
 				/* ignore empty line like grep does */
 				if (!buf[0])
 					continue;
-				add_pattern(&opt, strdup(buf), argv[1], ++lno);
+				append_grep_pattern(&opt, xstrdup(buf),
+						    argv[1], ++lno,
+						    GREP_PATTERN);
 			}
 			fclose(patterns);
 			argv++;
 			argc--;
 			continue;
 		}
+		if (!strcmp("--not", arg)) {
+			append_grep_pattern(&opt, arg, "command line", 0,
+					    GREP_NOT);
+			continue;
+		}
+		if (!strcmp("--and", arg)) {
+			append_grep_pattern(&opt, arg, "command line", 0,
+					    GREP_AND);
+			continue;
+		}
+		if (!strcmp("--or", arg))
+			continue; /* no-op */
+		if (!strcmp("(", arg)) {
+			append_grep_pattern(&opt, arg, "command line", 0,
+					    GREP_OPEN_PAREN);
+			continue;
+		}
+		if (!strcmp(")", arg)) {
+			append_grep_pattern(&opt, arg, "command line", 0,
+					    GREP_CLOSE_PAREN);
+			continue;
+		}
+		if (!strcmp("--all-match", arg)) {
+			opt.all_match = 1;
+			continue;
+		}
 		if (!strcmp("-e", arg)) {
 			if (1 < argc) {
-				add_pattern(&opt, argv[1], "-e option", 0);
+				append_grep_pattern(&opt, argv[1],
+						    "-e option", 0,
+						    GREP_PATTERN);
 				argv++;
 				argc--;
 				continue;
 			}
-			usage(builtin_grep_usage);
+			die(emsg_missing_argument, arg);
+		}
+		if (!strcmp("--full-name", arg)) {
+			opt.relative = 0;
+			continue;
 		}
-		if (!strcmp("--", arg))
+		if (!strcmp("--", arg)) {
+			/* later processing wants to have this at argv[1] */
+			argv--;
+			argc++;
 			break;
+		}
 		if (*arg == '-')
 			usage(builtin_grep_usage);
 
 		/* First unrecognized non-option token */
 		if (!opt.pattern_list) {
-			add_pattern(&opt, arg, "command line", 0);
+			append_grep_pattern(&opt, arg, "command line", 0,
+					    GREP_PATTERN);
 			break;
 		}
 		else {
@@ -841,8 +644,7 @@ int cmd_grep(int argc, const char **argv, char **envp)
 		die("no pattern given.");
 	if ((opt.regflags != REG_NEWLINE) && opt.fixed)
 		die("cannot mix --fixed-strings and regexp");
-	if (!opt.fixed)
-		compile_patterns(&opt);
+	compile_grep_patterns(&opt);
 
 	/* Check revs and then paths */
 	for (i = 1; i < argc; i++) {
@@ -870,8 +672,15 @@ int cmd_grep(int argc, const char **argv, char **envp)
 			verify_filename(prefix, argv[j]);
 	}
 
-	if (i < argc)
+	if (i < argc) {
 		paths = get_pathspec(prefix, argv + i);
+		if (opt.prefix_length && opt.relative) {
+			/* Make sure we do not get outside of paths */
+			for (i = 0; paths[i]; i++)
+				if (strncmp(prefix, paths[i], opt.prefix_length))
+					die("git-grep: cannot generate relative filenames containing '..'");
+		}
+	}
 	else if (prefix) {
 		paths = xcalloc(2, sizeof(const char *));
 		paths[0] = prefix;
@@ -890,5 +699,6 @@ int cmd_grep(int argc, const char **argv, char **envp)
 		if (grep_object(&opt, paths, real_obj, list.objects[i].name))
 			hit = 1;
 	}
+	free_grep_patterns(&opt);
 	return !hit;
 }