Merge branch 'jc/hash-object' into maint

"hash-object --literally" introduced in v2.2 was not prepared to
take a really long object type name.

* jc/hash-object:
  write_sha1_file(): do not use a separate sha1[] array
  t1007: add hash-object --literally tests
  hash-object --literally: fix buffer overrun with extra-long object type
  git-hash-object.txt: document --literally option

5 files changed, 43 insertions, 9 deletions

diff --git a/Documentation/git-hash-object.txt b/Documentation/git-hash-object.txt
index 02c1f12685..0c75f3b610 100644
--- a/Documentation/git-hash-object.txt
+++ b/Documentation/git-hash-object.txt
@@ -9,7 +9,7 @@ git-hash-object - Compute object ID and optionally creates a blob from a file
 SYNOPSIS
 --------
 [verse]
-'git hash-object' [-t <type>] [-w] [--path=<file>|--no-filters] [--stdin] [--] <file>...
+'git hash-object' [-t <type>] [-w] [--path=<file>|--no-filters] [--stdin [--literally]] [--] <file>...
 'git hash-object' [-t <type>] [-w] --stdin-paths [--no-filters] < <list-of-paths>
 
 DESCRIPTION
@@ -51,7 +51,13 @@ OPTIONS
 	Hash the contents as is, ignoring any input filter that would
 	have been chosen by the attributes mechanism, including the end-of-line
 	conversion. If the file is read from standard input then this
-	is always implied, unless the --path option is given.
+	is always implied, unless the `--path` option is given.
+
+--literally::
+	Allow `--stdin` to hash any garbage into a loose object which might not
+	otherwise pass standard object parsing or git-fsck checks. Useful for
+	stress-testing Git itself or reproducing characteristics of corrupt or
+	bogus objects encountered in the wild.
 
 GIT
 ---
diff --git a/builtin/hash-object.c b/builtin/hash-object.c
index 207b90c7b1..07fef3cc6b 100644
--- a/builtin/hash-object.c
+++ b/builtin/hash-object.c
@@ -22,10 +22,8 @@ static int hash_literally(unsigned char *sha1, int fd, const char *type, unsigne
 
 	if (strbuf_read(&buf, fd, 4096) < 0)
 		ret = -1;
-	else if (flags & HASH_WRITE_OBJECT)
-		ret = write_sha1_file(buf.buf, buf.len, type, sha1);
 	else
-		ret = hash_sha1_file(buf.buf, buf.len, type, sha1);
+		ret = hash_sha1_file_literally(buf.buf, buf.len, type, sha1, flags);
 	strbuf_release(&buf);
 	return ret;
 }
diff --git a/cache.h b/cache.h
index eabde3828c..e42be4b11b 100644
--- a/cache.h
+++ b/cache.h
@@ -874,6 +874,7 @@ static inline const unsigned char *lookup_replace_object_extended(const unsigned
 extern int sha1_object_info(const unsigned char *, unsigned long *);
 extern int hash_sha1_file(const void *buf, unsigned long len, const char *type, unsigned char *sha1);
 extern int write_sha1_file(const void *buf, unsigned long len, const char *type, unsigned char *return_sha1);
+extern int hash_sha1_file_literally(const void *buf, unsigned long len, const char *type, unsigned char *sha1, unsigned flags);
 extern int pretend_sha1_file(void *, unsigned long, enum object_type, unsigned char *);
 extern int force_object_loose(const unsigned char *sha1, time_t mtime);
 extern int git_open_noatime(const char *name);
diff --git a/sha1_file.c b/sha1_file.c
index f860d67744..47f56f2e89 100644
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -3009,9 +3009,8 @@ static int freshen_packed_object(const unsigned char *sha1)
 	return 1;
 }
 
-int write_sha1_file(const void *buf, unsigned long len, const char *type, unsigned char *returnsha1)
+int write_sha1_file(const void *buf, unsigned long len, const char *type, unsigned char *sha1)
 {
-	unsigned char sha1[20];
 	char hdr[32];
 	int hdrlen;
 
@@ -3019,13 +3018,32 @@ int write_sha1_file(const void *buf, unsigned long len, const char *type, unsign
 	 * it out into .git/objects/??/?{38} file.
 	 */
 	write_sha1_file_prepare(buf, len, type, sha1, hdr, &hdrlen);
-	if (returnsha1)
-		hashcpy(returnsha1, sha1);
 	if (freshen_packed_object(sha1) || freshen_loose_object(sha1))
 		return 0;
 	return write_loose_object(sha1, hdr, hdrlen, buf, len, 0);
 }
 
+int hash_sha1_file_literally(const void *buf, unsigned long len, const char *type,
+			     unsigned char *sha1, unsigned flags)
+{
+	char *header;
+	int hdrlen, status = 0;
+
+	/* type string, SP, %lu of the length plus NUL must fit this */
+	header = xmalloc(strlen(type) + 32);
+	write_sha1_file_prepare(buf, len, type, sha1, header, &hdrlen);
+
+	if (!(flags & HASH_WRITE_OBJECT))
+		goto cleanup;
+	if (freshen_packed_object(sha1) || freshen_loose_object(sha1))
+		goto cleanup;
+	status = write_loose_object(sha1, header, hdrlen, buf, len, 0);
+
+cleanup:
+	free(header);
+	return status;
+}
+
 int force_object_loose(const unsigned char *sha1, time_t mtime)
 {
 	void *buf;
diff --git a/t/t1007-hash-object.sh b/t/t1007-hash-object.sh
index ebb3a69c8c..7d2baa15bb 100755
--- a/t/t1007-hash-object.sh
+++ b/t/t1007-hash-object.sh
@@ -209,4 +209,15 @@ test_expect_success 'hash-object complains about truncated type name' '
 	test_must_fail git hash-object -t bl --stdin </dev/null
 '
 
+test_expect_success '--literally' '
+	t=1234567890 &&
+	echo example | git hash-object -t $t --literally --stdin
+'
+
+test_expect_success '--literally with extra-long type' '
+	t=12345678901234567890123456789012345678901234567890 &&
+	t="$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t" &&
+	echo example | git hash-object -t $t --literally --stdin
+'
+
 test_done