convert: stream from fd to required clean filter to reduce used address space

diff --git a/sha1_file.c b/sha1_file.c
index d9b51578ccd3b5e487b3ad31fefbe1f8b3e7e99e..423ec64e8732687afbd5c118885a6864927e2db6 100644 (file)
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -3090,6 +3090,29 @@ static int index_mem(unsigned char *sha1, void *buf, size_t size,
        return ret;
 }
 
+static int index_stream_convert_blob(unsigned char *sha1, int fd,
+                                    const char *path, unsigned flags)
+{
+       int ret;
+       const int write_object = flags & HASH_WRITE_OBJECT;
+       struct strbuf sbuf = STRBUF_INIT;
+
+       assert(path);
+       assert(would_convert_to_git_filter_fd(path));
+
+       convert_to_git_filter_fd(path, fd, &sbuf,
+                                write_object ? safe_crlf : SAFE_CRLF_FALSE);
+
+       if (write_object)
+               ret = write_sha1_file(sbuf.buf, sbuf.len, typename(OBJ_BLOB),
+                                     sha1);
+       else
+               ret = hash_sha1_file(sbuf.buf, sbuf.len, typename(OBJ_BLOB),
+                                    sha1);
+       strbuf_release(&sbuf);
+       return ret;
+}
+
 static int index_pipe(unsigned char *sha1, int fd, enum object_type type,
                      const char *path, unsigned flags)
 {
@@ -3157,7 +3180,9 @@ int index_fd(unsigned char *sha1, int fd, struct stat *st,
        int ret;
        size_t size = xsize_t(st->st_size);
 
-       if (!S_ISREG(st->st_mode))
+       if (type == OBJ_BLOB && path && would_convert_to_git_filter_fd(path))
+               ret = index_stream_convert_blob(sha1, fd, path, flags);
+       else if (!S_ISREG(st->st_mode))
                ret = index_pipe(sha1, fd, type, path, flags);
        else if (size <= big_file_threshold || type != OBJ_BLOB ||
                 (path && would_convert_to_git(path)))