Merge branch 'fg/autocrlf'

* fg/autocrlf:
  autocrlf: Make it work also for un-normalized repositories

2 files changed, 101 insertions, 0 deletions

diff --git a/convert.c b/convert.c
index 824bd047a5..64dce3ff57 100644
--- a/convert.c
+++ b/convert.c
@@ -120,6 +120,43 @@ static void check_safe_crlf(const char *path, int action,
 	}
 }
 
+static int has_cr_in_index(const char *path)
+{
+	int pos, len;
+	unsigned long sz;
+	enum object_type type;
+	void *data;
+	int has_cr;
+	struct index_state *istate = &the_index;
+
+	len = strlen(path);
+	pos = index_name_pos(istate, path, len);
+	if (pos < 0) {
+		/*
+		 * We might be in the middle of a merge, in which
+		 * case we would read stage #2 (ours).
+		 */
+		int i;
+		for (i = -pos - 1;
+		     (pos < 0 && i < istate->cache_nr &&
+		      !strcmp(istate->cache[i]->name, path));
+		     i++)
+			if (ce_stage(istate->cache[i]) == 2)
+				pos = i;
+	}
+	if (pos < 0)
+		return 0;
+	data = read_sha1_file(istate->cache[pos]->sha1, &type, &sz);
+	if (!data || type != OBJ_BLOB) {
+		free(data);
+		return 0;
+	}
+
+	has_cr = memchr(data, '\r', sz) != NULL;
+	free(data);
+	return has_cr;
+}
+
 static int crlf_to_git(const char *path, const char *src, size_t len,
                        struct strbuf *buf, int action, enum safe_crlf checksafe)
 {
@@ -145,6 +182,13 @@ static int crlf_to_git(const char *path, const char *src, size_t len,
 		 */
 		if (is_binary(len, &stats))
 			return 0;
+
+		/*
+		 * If the file in the index has any CR in it, do not convert.
+		 * This is the new safer autocrlf handling.
+		 */
+		if (has_cr_in_index(path))
+			return 0;
 	}
 
 	check_safe_crlf(path, action, &stats, checksafe);
@@ -203,6 +247,11 @@ static int crlf_to_worktree(const char *path, const char *src, size_t len,
 		return 0;
 
 	if (action == CRLF_GUESS) {
+		/* If we have any CR or CRLF line endings, we do not touch it */
+		/* This is the new safer autocrlf-handling */
+		if (stats.cr > 0 || stats.crlf > 0)
+			return 0;
+
 		/* If we have any bare CR characters, we're not going to touch it */
 		if (stats.cr != stats.crlf)
 			return 0;
diff --git a/t/t0020-crlf.sh b/t/t0020-crlf.sh
index c3e7e322a8..234a94f3e6 100755
--- a/t/t0020-crlf.sh
+++ b/t/t0020-crlf.sh
@@ -453,5 +453,57 @@ test_expect_success 'invalid .gitattributes (must not crash)' '
 	git diff
 
 '
+# Some more tests here to add new autocrlf functionality.
+# We want to have a known state here, so start a bit from scratch
+
+test_expect_success 'setting up for new autocrlf tests' '
+	git config core.autocrlf false &&
+	git config core.safecrlf false &&
+	rm -rf .????* * &&
+	for w in I am all LF; do echo $w; done >alllf &&
+	for w in Oh here is CRLFQ in text; do echo $w; done | q_to_cr >mixed &&
+	for w in I am all CRLF; do echo $w; done | append_cr >allcrlf &&
+	git add -A . &&
+	git commit -m "alllf, allcrlf and mixed only" &&
+	git tag -a -m "message" autocrlf-checkpoint
+'
+
+test_expect_success 'report no change after setting autocrlf' '
+	git config core.autocrlf true &&
+	touch * &&
+	git diff --exit-code
+'
+
+test_expect_success 'files are clean after checkout' '
+	rm * &&
+	git checkout -f &&
+	git diff --exit-code
+'
+
+cr_to_Q_no_NL () {
+    tr '\015' Q | tr -d '\012'
+}
+
+test_expect_success 'LF only file gets CRLF with autocrlf' '
+	test "$(cr_to_Q_no_NL < alllf)" = "IQamQallQLFQ"
+'
+
+test_expect_success 'Mixed file is still mixed with autocrlf' '
+	test "$(cr_to_Q_no_NL < mixed)" = "OhhereisCRLFQintext"
+'
+
+test_expect_success 'CRLF only file has CRLF with autocrlf' '
+	test "$(cr_to_Q_no_NL < allcrlf)" = "IQamQallQCRLFQ"
+'
+
+test_expect_success 'New CRLF file gets LF in repo' '
+	tr -d "\015" < alllf | append_cr > alllf2 &&
+	git add alllf2 &&
+	git commit -m "alllf2 added" &&
+	git config core.autocrlf false &&
+	rm * &&
+	git checkout -f &&
+	test_cmp alllf alllf2
+'
 
 test_done