[PATCH v5 0/6] recursively grep across submodules

[Brandon Williams <bmwill@google.com>]

Major change in v5 is to use tree_is_interesting api instead of the vanilla
pathspec code for submodules.  This is to fix the issue in the last seires
where I mix the two types.  More tests were also added to ensure that the
changes to the pathspec code functioned properly.

Brandon Williams (6):
  submodules: add helper functions to determine presence of submodules
  submodules: load gitmodules file from commit sha1
  grep: add submodules as a grep source type
  grep: optionally recurse into submodules
  grep: enable recurse-submodules to work on <tree> objects
  grep: search history of moved submodules

 Documentation/git-grep.txt         |  14 ++
 builtin/grep.c                     | 386 ++++++++++++++++++++++++++++++++++---
 cache.h                            |   2 +
 config.c                           |   8 +-
 git.c                              |   2 +-
 grep.c                             |  16 +-
 grep.h                             |   1 +
 submodule-config.c                 |   6 +-
 submodule-config.h                 |   3 +
 submodule.c                        |  50 +++++
 submodule.h                        |   3 +
 t/t7814-grep-recurse-submodules.sh | 241 +++++++++++++++++++++++
 tree-walk.c                        |  28 +++
 13 files changed, 729 insertions(+), 31 deletions(-)
 create mode 100755 t/t7814-grep-recurse-submodules.sh

-- interdiff based on 'bw/grep-recurse-submodules'

diff --git a/builtin/grep.c b/builtin/grep.c
index 052f605..2c727ef 100644
--- a/builtin/grep.c
+++ b/builtin/grep.c
@@ -698,6 +698,8 @@ static int grep_cache(struct grep_opt *opt, const struct pathspec *pathspec,
 		} else if (recurse_submodules && S_ISGITLINK(ce->ce_mode) &&
 			   submodule_path_match(pathspec, name.buf, NULL)) {
 			hit |= grep_submodule(opt, NULL, ce->name, ce->name);
+		} else {
+			continue;
 		}
 
 		if (ce_stage(ce)) {
@@ -734,17 +736,10 @@ static int grep_tree(struct grep_opt *opt, const struct pathspec *pathspec,
 		int te_len = tree_entry_len(&entry);
 
 		if (match != all_entries_interesting) {
-			strbuf_setlen(&name, name_base_len);
 			strbuf_addstr(&name, base->buf + tn_len);
-
-			if (recurse_submodules && S_ISGITLINK(entry.mode)) {
-				strbuf_addstr(&name, entry.path);
-				match = submodule_path_match(pathspec, name.buf,
-							     NULL);
-			} else {
-				match = tree_entry_interesting(&entry, &name,
-							       0, pathspec);
-			}
+			match = tree_entry_interesting(&entry, &name,
+						       0, pathspec);
+			strbuf_setlen(&name, name_base_len);
 
 			if (match == all_entries_not_interesting)
 				break;
diff --git a/t/t7814-grep-recurse-submodules.sh b/t/t7814-grep-recurse-submodules.sh
index 7d66716..0507771 100755
--- a/t/t7814-grep-recurse-submodules.sh
+++ b/t/t7814-grep-recurse-submodules.sh
@@ -127,6 +127,34 @@ test_expect_success 'grep tree and pathspecs' '
 	test_cmp expect actual
 '
 
+test_expect_success 'grep tree and pathspecs' '
+	cat >expect <<-\EOF &&
+	HEAD:submodule/a:foobar
+	HEAD:submodule/sub/a:foobar
+	EOF
+
+	git grep -e "bar" --recurse-submodules HEAD -- "submodule*a" >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'grep tree and more pathspecs' '
+	cat >expect <<-\EOF &&
+	HEAD:submodule/a:foobar
+	EOF
+
+	git grep -e "bar" --recurse-submodules HEAD -- "submodul?/a" >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'grep tree and more pathspecs' '
+	cat >expect <<-\EOF &&
+	HEAD:submodule/sub/a:foobar
+	EOF
+
+	git grep -e "bar" --recurse-submodules HEAD -- "submodul*/sub/a" >actual &&
+	test_cmp expect actual
+'
+
 test_expect_success 'grep recurse submodule colon in name' '
 	git init parent &&
 	test_when_finished "rm -rf parent" &&
diff --git a/tree-walk.c b/tree-walk.c
index 828f435..ff77605 100644
--- a/tree-walk.c
+++ b/tree-walk.c
@@ -1004,6 +1004,19 @@ static enum interesting do_match(const struct name_entry *entry,
 				 */
 				if (ps->recursive && S_ISDIR(entry->mode))
 					return entry_interesting;
+
+				/*
+				 * When matching against submodules with
+				 * wildcard characters, ensure that the entry
+				 * at least matches up to the first wild
+				 * character.  More accurate matching can then
+				 * be performed in the submodule itself.
+				 */
+				if (ps->recursive && S_ISGITLINK(entry->mode) &&
+				    !ps_strncmp(item, match + baselen,
+						entry->path,
+						item->nowildcard_len - baselen))
+					return entry_interesting;
 			}
 
 			continue;
@@ -1040,6 +1053,21 @@ static enum interesting do_match(const struct name_entry *entry,
 			strbuf_setlen(base, base_offset + baselen);
 			return entry_interesting;
 		}
+
+		/*
+		 * When matching against submodules with
+		 * wildcard characters, ensure that the entry
+		 * at least matches up to the first wild
+		 * character.  More accurate matching can then
+		 * be performed in the submodule itself.
+		 */
+		if (ps->recursive && S_ISGITLINK(entry->mode) &&
+		    !ps_strncmp(item, match, base->buf + base_offset,
+				item->nowildcard_len)) {
+			strbuf_setlen(base, base_offset + baselen);
+			return entry_interesting;
+		}
+
 		strbuf_setlen(base, base_offset + baselen);
 
 		/*

-- 
2.8.0.rc3.226.g39d4020