git-archive: convert archive entries like checkouts do

As noted by Johan Herland, git-archive is a kind of checkout and needs
to apply any checkout filters that might be configured.

This patch adds the convenience function convert_sha1_file which returns
a buffer containing the object's contents, after converting, if necessary
(i.e. it's a combination of read_sha1_file and convert_to_working_tree).
Direct calls to read_sha1_file in git-archive are then replaced by calls
to convert_sha1_file.

Since convert_sha1_file expects its path argument to be NUL-terminated --
a convention it inherits from convert_to_working_tree -- the patch also
changes the path handling in archive-tar.c to always NUL-terminate the
string.  It used to solely rely on the len field of struct strbuf before.

archive-zip.c already NUL-terminates the path and thus needs no such
change.

Signed-off-by: Rene Scharfe <rene.scharfe@lsrfire.ath.cx>
Signed-off-by: Junio C Hamano <junkio@cox.net>

4 files changed, 26 insertions, 8 deletions

diff --git a/archive-tar.c b/archive-tar.c
index 56ff356966..33e76576f1 100644
--- a/archive-tar.c
+++ b/archive-tar.c
@@ -82,12 +82,13 @@ static void strbuf_append_string(struct strbuf *sb, const char *s)
 {
 	int slen = strlen(s);
 	int total = sb->len + slen;
-	if (total > sb->alloc) {
-		sb->buf = xrealloc(sb->buf, total);
-		sb->alloc = total;
+	if (total + 1 > sb->alloc) {
+		sb->buf = xrealloc(sb->buf, total + 1);
+		sb->alloc = total + 1;
 	}
 	memcpy(sb->buf + sb->len, s, slen);
 	sb->len = total;
+	sb->buf[total] = '\0';
 }
 
 /*
@@ -270,20 +271,21 @@ static int write_tar_entry(const unsigned char *sha1,
 		path.alloc = PATH_MAX;
 		path.len = path.eof = 0;
 	}
-	if (path.alloc < baselen + filenamelen) {
+	if (path.alloc < baselen + filenamelen + 1) {
 		free(path.buf);
-		path.buf = xmalloc(baselen + filenamelen);
-		path.alloc = baselen + filenamelen;
+		path.buf = xmalloc(baselen + filenamelen + 1);
+		path.alloc = baselen + filenamelen + 1;
 	}
 	memcpy(path.buf, base, baselen);
 	memcpy(path.buf + baselen, filename, filenamelen);
 	path.len = baselen + filenamelen;
+	path.buf[path.len] = '\0';
 	if (S_ISDIR(mode) || S_ISDIRLNK(mode)) {
 		strbuf_append_string(&path, "/");
 		buffer = NULL;
 		size = 0;
 	} else {
-		buffer = read_sha1_file(sha1, &type, &size);
+		buffer = convert_sha1_file(path.buf, sha1, mode, &type, &size);
 		if (!buffer)
 			die("cannot read %s", sha1_to_hex(sha1));
 	}
diff --git a/archive-zip.c b/archive-zip.c
index 1eaf262b74..3cbf6bb8ac 100644
--- a/archive-zip.c
+++ b/archive-zip.c
@@ -195,7 +195,7 @@ static int write_zip_entry(const unsigned char *sha1,
 		if (S_ISREG(mode) && zlib_compression_level != 0)
 			method = 8;
 		result = 0;
-		buffer = read_sha1_file(sha1, &type, &size);
+		buffer = convert_sha1_file(path, sha1, mode, &type, &size);
 		if (!buffer)
 			die("cannot read %s", sha1_to_hex(sha1));
 		crc = crc32(crc, buffer, size);
diff --git a/cache.h b/cache.h
index aaeb04a1b9..4204bc168c 100644
--- a/cache.h
+++ b/cache.h
@@ -548,6 +548,7 @@ extern void trace_argv_printf(const char **argv, int count, const char *format,
 /* convert.c */
 extern char *convert_to_git(const char *path, const char *src, unsigned long *sizep);
 extern char *convert_to_working_tree(const char *path, const char *src, unsigned long *sizep);
+extern void *convert_sha1_file(const char *path, const unsigned char *sha1, unsigned int mode, enum object_type *type, unsigned long *size);
 
 /* match-trees.c */
 void shift_tree(const unsigned char *, const unsigned char *, unsigned char *, int);
diff --git a/convert.c b/convert.c
index 12abdaf2a5..c64880bdf5 100644
--- a/convert.c
+++ b/convert.c
@@ -652,3 +652,18 @@ char *convert_to_working_tree(const char *path, const char *src, unsigned long *
 
 	return buf;
 }
+
+void *convert_sha1_file(const char *path, const unsigned char *sha1,
+                        unsigned int mode, enum object_type *type,
+                        unsigned long *size)
+{
+	void *buffer = read_sha1_file(sha1, type, size);
+	if (S_ISREG(mode) && buffer) {
+		void *converted = convert_to_working_tree(path, buffer, size);
+		if (converted) {
+			free(buffer);
+			buffer = converted;
+		}
+	}
+	return buffer;
+}