git/list[1] front-page[2] threads[3] people[4] search[5] about
 

[PATCH 19/19] grep: drop pathspec_matches() in favor of tree_entry_interesting()

From
Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
Date
Dec 13, 2010, 09:46 UTC
Message-ID
<1292233616-27692-20-git-send-email-pclouds@gmail.com>
In-Reply-To
<1292233616-27692-1-git-send-email-pclouds@gmail.com>
Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
 builtin/grep.c |  130 ++++++-------------------------------------------------
 1 files changed, 15 insertions(+), 115 deletions(-)
diff --git a/builtin/grep.c b/builtin/grep.c
index 6bd5728..a56cdd6 100644
--- a/builtin/grep.c
+++ b/builtin/grep.c
@@ -333,106 +333,6 @@ static int grep_config(const char *var, const char *value, void *cb)
 	return 0;
 }
 
-/*
- * Return non-zero if max_depth is negative or path has no more then max_depth
- * slashes.
- */
-static int accept_subdir(const char *path, int max_depth)
-{
-	if (max_depth < 0)
-		return 1;
-
-	while ((path = strchr(path, '/')) != NULL) {
-		max_depth--;
-		if (max_depth < 0)
-			return 0;
-		path++;
-	}
-	return 1;
-}
-
-/*
- * Return non-zero if name is a subdirectory of match and is not too deep.
- */
-static int is_subdir(const char *name, int namelen,
-		const char *match, int matchlen, int max_depth)
-{
-	if (matchlen > namelen || strncmp(name, match, matchlen))
-		return 0;
-
-	if (name[matchlen] == '\0') /* exact match */
-		return 1;
-
-	if (!matchlen || match[matchlen-1] == '/' || name[matchlen] == '/')
-		return accept_subdir(name + matchlen + 1, max_depth);
-
-	return 0;
-}
-
-/*
- * git grep pathspecs are somewhat different from diff-tree pathspecs;
- * pathname wildcards are allowed.
- */
-static int pathspec_matches(const char **paths, const char *name, int max_depth)
-{
-	int namelen, i;
-	if (!paths || !*paths)
-		return accept_subdir(name, max_depth);
-	namelen = strlen(name);
-	for (i = 0; paths[i]; i++) {
-		const char *match = paths[i];
-		int matchlen = strlen(match);
-		const char *cp, *meta;
-
-		if (is_subdir(name, namelen, match, matchlen, max_depth))
-			return 1;
-		if (!fnmatch(match, name, 0))
-			return 1;
-		if (name[namelen-1] != '/')
-			continue;
-
-		/* We are being asked if the directory ("name") is worth
-		 * descending into.
-		 *
-		 * Find the longest leading directory name that does
-		 * not have metacharacter in the pathspec; the name
-		 * we are looking at must overlap with that directory.
-		 */
-		for (cp = match, meta = NULL; cp - match < matchlen; cp++) {
-			char ch = *cp;
-			if (ch == '*' || ch == '[' || ch == '?') {
-				meta = cp;
-				break;
-			}
-		}
-		if (!meta)
-			meta = cp; /* fully literal */
-
-		if (namelen <= meta - match) {
-			/* Looking at "Documentation/" and
-			 * the pattern says "Documentation/howto/", or
-			 * "Documentation/diff*.txt".  The name we
-			 * have should match prefix.
-			 */
-			if (!memcmp(match, name, namelen))
-				return 1;
-			continue;
-		}
-
-		if (meta - match < namelen) {
-			/* Looking at "Documentation/howto/" and
-			 * the pattern says "Documentation/h*";
-			 * match up to "Do.../h"; this avoids descending
-			 * into "Documentation/technical/".
-			 */
-			if (!memcmp(match, name, meta - match))
-				return 1;
-			continue;
-		}
-	}
-	return 0;
-}
-
 static void *lock_and_read_sha1_file(const unsigned char *sha1, enum object_type *type, unsigned long *size)
 {
 	void *data;
@@ -632,39 +532,37 @@ static int grep_tree(struct grep_opt *opt, const struct pathspec *pathspec,
 		     struct tree_desc *tree, char *base,
 		     int baselen, int tree_name_len)
 {
-	int hit = 0;
+	int hit = 0, matched = 0;
 	struct name_entry entry;
 
 	while (tree_entry(tree, &entry)) {
 		int te_len = tree_entry_len(entry.path, entry.sha1);
-		int len = baselen;
-		memcpy(base + baselen, entry.path, te_len+1);
 
-		len += te_len;
-		if (S_ISDIR(entry.mode)) {
-			/* Match "abc/" against pathspec to
-			 * decide if we want to descend into "abc"
-			 * directory.
-			 */
-			base[len++] = '/';
-			base[len] = 0;
+		if (matched != 2) {
+			matched = tree_entry_interesting(&entry, base, baselen, pathspec);
+			if (matched == -1)
+				break; /* no more matches */
+			if (!matched)
+				continue;
 		}
 
-		if (!pathspec_matches(pathspec->raw, base, opt->max_depth))
-			;
-		else if (S_ISREG(entry.mode)) {
+		memcpy(base + baselen, entry.path, te_len+1);
+		if (S_ISREG(entry.mode))
 			hit |= grep_sha1(opt, entry.sha1, base-tree_name_len, tree_name_len);
-		}
 		else if (S_ISDIR(entry.mode)) {
 			enum object_type type;
 			struct tree_desc sub;
 			void *data;
 			unsigned long size;
+			int len = baselen + te_len;
 
 			data = lock_and_read_sha1_file(entry.sha1, &type, &size);
 			if (!data)
 				die("unable to read tree (%s)",
 				    sha1_to_hex(entry.sha1));
+
+			base[len++] = '/';
+			base[len] = 0;
 			init_tree_desc(&sub, data, size);
 			hit |= grep_tree(opt, pathspec, &sub, base, len, tree_name_len);
 			free(data);
@@ -1069,6 +967,8 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 		paths[1] = NULL;
 	}
 	init_pathspec(&pathspec, paths);
+	pathspec.max_depth = opt.max_depth;
+	pathspec.recursive = 1;
 
 	if (show_in_pager && (cached || list.nr))
 		die("--open-files-in-pager only works on the worktree");
-- 
1.7.3.3.476.g10a82
Previous: Nguyễn Thái Ngọc Duy
Message 45 of 45 in “nd/struct-pathspec (or pathspec unification [1])”
  1. 00/19 nd/struct-pathspec (or pathspec unification [1])Nguyễn Thái Ngọc Duy, Dec 13, 2010
  2. 01/19 Add struct pathspecNguyễn Thái Ngọc Duy, Dec 13, 2010
  3. Thiago FarinaDec 13, 2010
  4. Nguyen Thai Ngoc DuyDec 14, 2010
  5. 02/19 diff-no-index: use diff_tree_setup_paths()Nguyễn Thái Ngọc Duy, Dec 13, 2010
  6. 03/19 pathspec: cache string length when initializing pathspecNguyễn Thái Ngọc Duy, Dec 13, 2010
  7. 04/19 Convert struct diff_options to use struct pathspecNguyễn Thái Ngọc Duy, Dec 13, 2010
  8. Junio C HamanoDec 13, 2010
  9. Nguyen Thai Ngoc DuyDec 14, 2010
  10. 05/19 tree_entry_interesting(): remove dependency on struct diff_optionsNguyễn Thái Ngọc Duy, Dec 13, 2010
  11. Junio C HamanoDec 13, 2010
  12. 06/19 Move tree_entry_interesting() to tree-walk.c and export itNguyễn Thái Ngọc Duy, Dec 13, 2010
  13. 07/19 glossary: define pathspecNguyễn Thái Ngọc Duy, Dec 13, 2010
  14. 08/19 pathspec: mark wildcard pathspecs from the beginningNguyễn Thái Ngọc Duy, Dec 13, 2010
  15. Junio C HamanoDec 13, 2010
  16. 09/19 tree-diff.c: reserve space in "base" for pathname concatenationNguyễn Thái Ngọc Duy, Dec 13, 2010
  17. Junio C HamanoDec 13, 2010
  18. Nguyen Thai Ngoc DuyDec 14, 2010
  19. Junio C HamanoDec 14, 2010
  20. Nguyen Thai Ngoc DuyDec 14, 2010
  21. Johannes SixtDec 14, 2010
  22. Nguyen Thai Ngoc DuyDec 14, 2010
  23. Johannes SixtDec 14, 2010
  24. Nguyen Thai Ngoc DuyDec 14, 2010
  25. Junio C HamanoDec 14, 2010
  26. 10/19 tree_entry_interesting(): factor out most matching logicNguyễn Thái Ngọc Duy, Dec 13, 2010
  27. Junio C HamanoDec 13, 2010
  28. 11/19 tree_entry_interesting: support depth limitNguyễn Thái Ngọc Duy, Dec 13, 2010
  29. Junio C HamanoDec 13, 2010
  30. Nguyen Thai Ngoc DuyDec 14, 2010
  31. 12/19 tree_entry_interesting(): support wildcard matchingNguyễn Thái Ngọc Duy, Dec 13, 2010
  32. Junio C HamanoDec 13, 2010
  33. Nguyen Thai Ngoc DuyDec 14, 2010
  34. 13/19 tree_entry_interesting(): optimize fnmatch when base is matchedNguyễn Thái Ngọc Duy, Dec 13, 2010
  35. Junio C HamanoDec 13, 2010
  36. 14/19 Convert ce_path_match() use to match_pathspec()Nguyễn Thái Ngọc Duy, Dec 13, 2010
  37. Junio C HamanoDec 13, 2010
  38. Nguyen Thai Ngoc DuyDec 14, 2010
  39. 15/19 pathspec: add match_pathspec_depth()Nguyễn Thái Ngọc Duy, Dec 13, 2010
  40. Junio C HamanoDec 13, 2010
  41. Nguyen Thai Ngoc DuyDec 14, 2010
  42. 16/19 grep: convert to use struct pathspecNguyễn Thái Ngọc Duy, Dec 13, 2010
  43. 17/19 grep: use match_pathspec_depth() for cache/worktree greppingNguyễn Thái Ngọc Duy, Dec 13, 2010
  44. 18/19 grep: use preallocated buffer for grep_tree()Nguyễn Thái Ngọc Duy, Dec 13, 2010
  45. 19/19 grep: drop pathspec_matches() in favor of tree_entry_interesting()Nguyễn Thái Ngọc Duy, Dec 13, 2010

Read the whole thread, see it on lore, or plain text.

$ cat FOOTERMessages come from the public archive at lore.kernel.org/git, fetched every hour. The front page is chosen and written each morning by an AI editor and can be wrong; the threads themselves are the record. About and API. For agents: an MCP server at https://gitlist.dev/mcp, and any thread, story or person page as Markdown by adding .md to its URL (or sending Accept: text/markdown). Details in /llms.txt.