Show modified files in git-ls-files

Add -m/--modified to show files that have been modified wrt. the index.

[jc: The original came from Brian Gerst on Sep 1st but it only checked
if the paths were cache dirty without actually checking the files were
modified.  I also added the usage string and a new test.]

Signed-off-by: Junio C Hamano <junkio@cox.net>

6 files changed, 140 insertions, 78 deletions

diff --git a/Documentation/git-ls-files.txt b/Documentation/git-ls-files.txt
index 628d424ec0..591f4ed462 100644
--- a/Documentation/git-ls-files.txt
+++ b/Documentation/git-ls-files.txt
@@ -1,6 +1,5 @@
 git-ls-files(1)
 ===============
-v0.1, May 2005
 
 NAME
 ----
@@ -10,8 +9,8 @@ git-ls-files - Information about files in the cache/working directory
 SYNOPSIS
 --------
 'git-ls-files' [-z] [-t]
-		(--[cached|deleted|others|ignored|stage|unmerged|killed])\*
-		(-[c|d|o|i|s|u|k])\*
+		(--[cached|deleted|others|ignored|stage|unmerged|killed|modified])\*
+		(-[c|d|o|i|s|u|k|m])\*
 		[-x <pattern>|--exclude=<pattern>]
 		[-X <file>|--exclude-from=<file>]
 		[--exclude-per-directory=<file>]
@@ -33,6 +32,9 @@ OPTIONS
 -d|--deleted::
 	Show deleted files in the output
 
+-m|--modified::
+	Show modified files in the output
+
 -o|--others::
 	Show other files in the output
 
@@ -71,6 +73,7 @@ OPTIONS
 	H	cached
 	M	unmerged
 	R	removed/deleted
+	C	modifed/changed
 	K	to be killed
 	?	other
 
diff --git a/cache.h b/cache.h
index 1d99d6817d..7f209794ba 100644
--- a/cache.h
+++ b/cache.h
@@ -161,6 +161,7 @@ extern int remove_cache_entry_at(int pos);
 extern int remove_file_from_cache(char *path);
 extern int ce_same_name(struct cache_entry *a, struct cache_entry *b);
 extern int ce_match_stat(struct cache_entry *ce, struct stat *st);
+extern int ce_modified(struct cache_entry *ce, struct stat *st);
 extern int ce_path_match(const struct cache_entry *ce, const char **pathspec);
 extern int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object, const char *type);
 extern void fill_stat_cache_info(struct cache_entry *ce, struct stat *st);
diff --git a/ls-files.c b/ls-files.c
index e53d245884..e3f43ecca1 100644
--- a/ls-files.c
+++ b/ls-files.c
@@ -16,6 +16,7 @@ static int show_others = 0;
 static int show_ignored = 0;
 static int show_stage = 0;
 static int show_unmerged = 0;
+static int show_modified = 0;
 static int show_killed = 0;
 static int line_terminator = '\n';
 
@@ -28,6 +29,7 @@ static const char *tag_unmerged = "";
 static const char *tag_removed = "";
 static const char *tag_other = "";
 static const char *tag_killed = "";
+static const char *tag_modified = "";
 
 static char *exclude_per_dir = NULL;
 
@@ -443,15 +445,18 @@ static void show_files(void)
 			show_ce_entry(ce_stage(ce) ? tag_unmerged : tag_cached, ce);
 		}
 	}
-	if (show_deleted) {
+	if (show_deleted | show_modified) {
 		for (i = 0; i < active_nr; i++) {
 			struct cache_entry *ce = active_cache[i];
 			struct stat st;
+			int err;
 			if (excluded(ce->name) != show_ignored)
 				continue;
-			if (!lstat(ce->name, &st))
-				continue;
-			show_ce_entry(tag_removed, ce);
+			err = lstat(ce->name, &st);
+			if (show_deleted && err)
+				show_ce_entry(tag_removed, ce);
+			if (show_modified && ce_modified(ce, &st))
+				show_ce_entry(tag_modified, ce);
 		}
 	}
 }
@@ -523,7 +528,7 @@ static void verify_pathspec(void)
 }
 
 static const char ls_files_usage[] =
-	"git-ls-files [-z] [-t] (--[cached|deleted|others|stage|unmerged|killed])* "
+	"git-ls-files [-z] [-t] (--[cached|deleted|others|stage|unmerged|killed|modified])* "
 	"[ --ignored ] [--exclude=<pattern>] [--exclude-from=<file>] "
 	"[ --exclude-per-directory=<filename> ]";
 
@@ -547,6 +552,7 @@ int main(int argc, char **argv)
 			tag_cached = "H ";
 			tag_unmerged = "M ";
 			tag_removed = "R ";
+			tag_modified = "C ";
 			tag_other = "? ";
 			tag_killed = "K ";
 			continue;
@@ -559,6 +565,10 @@ int main(int argc, char **argv)
 			show_deleted = 1;
 			continue;
 		}
+		if (!strcmp(arg, "-m") || !strcmp(arg, "--modified")) {
+			show_modified = 1;
+			continue;
+		}
 		if (!strcmp(arg, "-o") || !strcmp(arg, "--others")) {
 			show_others = 1;
 			continue;
@@ -630,7 +640,8 @@ int main(int argc, char **argv)
 	}
 
 	/* With no flags, we default to showing the cached files */
-	if (!(show_stage | show_deleted | show_others | show_unmerged | show_killed))
+	if (!(show_stage | show_deleted | show_others | show_unmerged |
+	      show_killed | show_modified))
 		show_cached = 1;
 
 	read_cache();
diff --git a/read-cache.c b/read-cache.c
index 6eff4c8401..ef6fd79e20 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -83,6 +83,83 @@ int ce_match_stat(struct cache_entry *ce, struct stat *st)
 	return changed;
 }
 
+static int ce_compare_data(struct cache_entry *ce, struct stat *st)
+{
+	int match = -1;
+	int fd = open(ce->name, O_RDONLY);
+
+	if (fd >= 0) {
+		unsigned char sha1[20];
+		if (!index_fd(sha1, fd, st, 0, NULL))
+			match = memcmp(sha1, ce->sha1, 20);
+		close(fd);
+	}
+	return match;
+}
+
+static int ce_compare_link(struct cache_entry *ce, unsigned long expected_size)
+{
+	int match = -1;
+	char *target;
+	void *buffer;
+	unsigned long size;
+	char type[10];
+	int len;
+
+	target = xmalloc(expected_size);
+	len = readlink(ce->name, target, expected_size);
+	if (len != expected_size) {
+		free(target);
+		return -1;
+	}
+	buffer = read_sha1_file(ce->sha1, type, &size);
+	if (!buffer) {
+		free(target);
+		return -1;
+	}
+	if (size == expected_size)
+		match = memcmp(buffer, target, size);
+	free(buffer);
+	free(target);
+	return match;
+}
+
+int ce_modified(struct cache_entry *ce, struct stat *st)
+{
+	int changed;
+	changed = ce_match_stat(ce, st);
+	if (!changed)
+		return 0;
+
+	/*
+	 * If the mode or type has changed, there's no point in trying
+	 * to refresh the entry - it's not going to match
+	 */
+	if (changed & (MODE_CHANGED | TYPE_CHANGED))
+		return changed;
+
+	/* Immediately after read-tree or update-index --cacheinfo,
+	 * the length field is zero.  For other cases the ce_size
+	 * should match the SHA1 recorded in the index entry.
+	 */
+	if ((changed & DATA_CHANGED) && ce->ce_size != htonl(0))
+		return changed;
+
+	switch (st->st_mode & S_IFMT) {
+	case S_IFREG:
+		if (ce_compare_data(ce, st))
+			return changed | DATA_CHANGED;
+		break;
+	case S_IFLNK:
+		if (ce_compare_link(ce, st->st_size))
+			return changed | DATA_CHANGED;
+		break;
+	default:
+		return changed | TYPE_CHANGED;
+	}
+	return 0;
+}
+
 int base_name_compare(const char *name1, int len1, int mode1,
 		      const char *name2, int len2, int mode2)
 {
diff --git a/t/t3010-ls-files-killed.sh b/t/t3010-ls-files-killed-modified.sh
index 2e18baae5a..5fc1976711 100755
--- a/t/t3010-ls-files-killed.sh
+++ b/t/t3010-ls-files-killed-modified.sh
@@ -3,7 +3,7 @@
 # Copyright (c) 2005 Junio C Hamano
 #
 
-test_description='git-ls-files -k flag test.
+test_description='git-ls-files -k and -m flags test.
 
 This test prepares the following in the cache:
 
@@ -24,6 +24,16 @@ and the following on the filesystem:
 
 git-ls-files -k should report that existing filesystem
 objects except path4, path5 and path6/file6 to be killed.
+
+Also for modification test, the cache and working tree have:
+
+    path7       - an empty file, modified to a non-empty file.
+    path8       - a non-empty file, modified to an empty file.
+    path9	- an empty file, cache dirtied.
+    path10	- a non-empty file, cache dirtied.
+
+We should report path0, path1, path2/file2, path3/file3, path7 and path8
+modified without reporting path9 and path10.
 '
 . ./test-lib.sh
 
@@ -32,11 +42,15 @@ ln -s xyzzy path1
 mkdir path2 path3
 date >path2/file2
 date >path3/file3
+: >path7
+date >path8
+: >path9
+date >path10
 test_expect_success \
     'git-update-index --add to add various paths.' \
-    "git-update-index --add -- path0 path1 path?/file?"
+    "git-update-index --add -- path0 path1 path?/file? path7 path8 path9 path10"
 
-rm -fr path?
+rm -fr path? ;# leave path10 alone
 date >path2
 ln -s frotz path3
 ln -s nitfol path5
@@ -44,6 +58,10 @@ mkdir path0 path1 path6
 date >path0/file0
 date >path1/file1
 date >path6/file6
+date >path7
+: >path8
+: >path9
+touch path10
 
 test_expect_success \
     'git-ls-files -k to show killed files.' \
@@ -58,4 +76,21 @@ EOF
 test_expect_success \
     'validate git-ls-files -k output.' \
     'diff .output .expected'
+
+test_expect_success \
+    'git-ls-files -m to show modified files.' \
+    'git-ls-files -m >.output'
+cat >.expected <<EOF
+path0
+path1
+path2/file2
+path3/file3
+path7
+path8
+EOF
+
+test_expect_success \
+    'validate git-ls-files -m output.' \
+    'diff .output .expected'
+
 test_done
diff --git a/update-index.c b/update-index.c
index 60c8417496..cb0265bdf7 100644
--- a/update-index.c
+++ b/update-index.c
@@ -112,47 +112,6 @@ static int add_file_to_cache(char *path)
 	return 0;
 }
 
-static int compare_data(struct cache_entry *ce, struct stat *st)
-{
-	int match = -1;
-	int fd = open(ce->name, O_RDONLY);
-
-	if (fd >= 0) {
-		unsigned char sha1[20];
-		if (!index_fd(sha1, fd, st, 0, NULL))
-			match = memcmp(sha1, ce->sha1, 20);
-		close(fd);
-	}
-	return match;
-}
-
-static int compare_link(struct cache_entry *ce, unsigned long expected_size)
-{
-	int match = -1;
-	char *target;
-	void *buffer;
-	unsigned long size;
-	char type[10];
-	int len;
-
-	target = xmalloc(expected_size);
-	len = readlink(ce->name, target, expected_size);
-	if (len != expected_size) {
-		free(target);
-		return -1;
-	}
-	buffer = read_sha1_file(ce->sha1, type, &size);
-	if (!buffer) {
-		free(target);
-		return -1;
-	}
-	if (size == expected_size)
-		match = memcmp(buffer, target, size);
-	free(buffer);
-	free(target);
-	return match;
-}
-
 /*
  * "refresh" does not calculate a new sha1 file or bring the
  * cache up-to-date for mode/content changes. But what it
@@ -177,33 +136,9 @@ static struct cache_entry *refresh_entry(struct cache_entry *ce)
 	if (!changed)
 		return ce;
 
-	/*
-	 * If the mode or type has changed, there's no point in trying
-	 * to refresh the entry - it's not going to match
-	 */
-	if (changed & (MODE_CHANGED | TYPE_CHANGED))
-		return ERR_PTR(-EINVAL);
-
-	/* Immediately after read-tree or update-index --cacheinfo,
-	 * the length field is zero.  For other cases the ce_size
-	 * should match the SHA1 recorded in the index entry.
-	 */
-	if ((changed & DATA_CHANGED) && ce->ce_size != htonl(0))
+	if (ce_modified(ce, &st))
 		return ERR_PTR(-EINVAL);
 
-	switch (st.st_mode & S_IFMT) {
-	case S_IFREG:
-		if (compare_data(ce, &st))
-			return ERR_PTR(-EINVAL);
-		break;
-	case S_IFLNK:
-		if (compare_link(ce, st.st_size))
-			return ERR_PTR(-EINVAL);
-		break;
-	default:
-		return ERR_PTR(-EINVAL);
-	}
-
 	size = ce_size(ce);
 	updated = xmalloc(size);
 	memcpy(updated, ce, size);