2 files changed, 95 insertions, 5 deletions

diff --git a/sha1_file.c b/sha1_file.c
index 956422ba4a..c9ae7ec2ae 100644
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -2688,10 +2688,13 @@ static int index_core(unsigned char *sha1, int fd, size_t size,
  * This also bypasses the usual "convert-to-git" dance, and that is on
  * purpose. We could write a streaming version of the converting
  * functions and insert that before feeding the data to fast-import
- * (or equivalent in-core API described above), but the primary
- * motivation for trying to stream from the working tree file and to
- * avoid mmaping it in core is to deal with large binary blobs, and
- * by definition they do _not_ want to get any conversion.
+ * (or equivalent in-core API described above). However, that is
+ * somewhat complicated, as we do not know the size of the filter
+ * result, which we need to know beforehand when writing a git object.
+ * Since the primary motivation for trying to stream from the working
+ * tree file and to avoid mmaping it in core is to deal with large
+ * binary blobs, they generally do not want to get any conversion, and
+ * callers should avoid this code path when filters are requested.
  */
 static int index_stream(unsigned char *sha1, int fd, size_t size,
 			enum object_type type, const char *path,
@@ -2766,7 +2769,8 @@ int index_fd(unsigned char *sha1, int fd, struct stat *st,
 
 	if (!S_ISREG(st->st_mode))
 		ret = index_pipe(sha1, fd, type, path, flags);
-	else if (size <= big_file_threshold || type != OBJ_BLOB)
+	else if (size <= big_file_threshold || type != OBJ_BLOB ||
+		 (path && would_convert_to_git(path, NULL, 0, 0)))
 		ret = index_core(sha1, fd, size, type, path, flags);
 	else
 		ret = index_stream(sha1, fd, size, type, path, flags);
diff --git a/t/t1051-large-conversion.sh b/t/t1051-large-conversion.sh
new file mode 100755
index 0000000000..8b7640b3ba
--- /dev/null
+++ b/t/t1051-large-conversion.sh
@@ -0,0 +1,86 @@
+#!/bin/sh
+
+test_description='test conversion filters on large files'
+. ./test-lib.sh
+
+set_attr() {
+	test_when_finished 'rm -f .gitattributes' &&
+	echo "* $*" >.gitattributes
+}
+
+check_input() {
+	git read-tree --empty &&
+	git add small large &&
+	git cat-file blob :small >small.index &&
+	git cat-file blob :large | head -n 1 >large.index &&
+	test_cmp small.index large.index
+}
+
+check_output() {
+	rm -f small large &&
+	git checkout small large &&
+	head -n 1 large >large.head &&
+	test_cmp small large.head
+}
+
+test_expect_success 'setup input tests' '
+	printf "\$Id: foo\$\\r\\n" >small &&
+	cat small small >large &&
+	git config core.bigfilethreshold 20 &&
+	git config filter.test.clean "sed s/.*/CLEAN/"
+'
+
+test_expect_success 'autocrlf=true converts on input' '
+	test_config core.autocrlf true &&
+	check_input
+'
+
+test_expect_success 'eol=crlf converts on input' '
+	set_attr eol=crlf &&
+	check_input
+'
+
+test_expect_success 'ident converts on input' '
+	set_attr ident &&
+	check_input
+'
+
+test_expect_success 'user-defined filters convert on input' '
+	set_attr filter=test &&
+	check_input
+'
+
+test_expect_success 'setup output tests' '
+	echo "\$Id\$" >small &&
+	cat small small >large &&
+	git add small large &&
+	git config core.bigfilethreshold 7 &&
+	git config filter.test.smudge "sed s/.*/SMUDGE/"
+'
+
+test_expect_success 'autocrlf=true converts on output' '
+	test_config core.autocrlf true &&
+	check_output
+'
+
+test_expect_success 'eol=crlf converts on output' '
+	set_attr eol=crlf &&
+	check_output
+'
+
+test_expect_success 'user-defined filters convert on output' '
+	set_attr filter=test &&
+	check_output
+'
+
+test_expect_success 'ident converts on output' '
+	set_attr ident &&
+	rm -f small large &&
+	git checkout small large &&
+	sed -n "s/Id: .*/Id: SHA/p" <small >small.clean &&
+	head -n 1 large >large.head &&
+	sed -n "s/Id: .*/Id: SHA/p" <large.head >large.clean &&
+	test_cmp small.clean large.clean
+'
+
+test_done