csum-file: introduce checksum_valid()

Introduce a new function which checks the validity of a file's trailing
checksum. This is similar to hashfd_check(), but different since it is
intended to be used by callers who aren't writing the same data (like
`git index-pack --verify`), but who instead want to validate the
integrity of data that they are reading.

Rewrite the first of two callers which could benefit from this new
function in pack-check.c. Subsequent callers will be added in the
following patches.

Helped-by: Jeff King <peff@peff.net>
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Taylor Blau <me@ttaylorr.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/csum-file.c b/csum-file.c
index 7510950fa3e99dbbf147ffc5d444d4570a7be23c..60f58f662ae09ae84446c80b07efcae6340b863d 100644 (file)
--- a/csum-file.c
+++ b/csum-file.c
@@ -187,3 +187,19 @@ uint32_t crc32_end(struct hashfile *f)
        f->do_crc = 0;
        return f->crc32;
 }
+
+int hashfile_checksum_valid(const unsigned char *data, size_t total_len)
+{
+       unsigned char got[GIT_MAX_RAWSZ];
+       git_hash_ctx ctx;
+       size_t data_len = total_len - the_hash_algo->rawsz;
+
+       if (total_len < the_hash_algo->rawsz)
+               return 0; /* say "too short"? */
+
+       the_hash_algo->init_fn(&ctx);
+       the_hash_algo->update_fn(&ctx, data, data_len);
+       the_hash_algo->final_fn(got, &ctx);
+
+       return hasheq(got, data + data_len);
+}

diff --git a/csum-file.h b/csum-file.h
index e54d53d1d0b3537b4fb4b0f22f9699cf38a2c3cf..87e3879f1cc178a8988deff0c147d7252d7f549c 100644 (file)
--- a/csum-file.h
+++ b/csum-file.h
@@ -42,6 +42,9 @@ void hashflush(struct hashfile *f);
 void crc32_begin(struct hashfile *);
 uint32_t crc32_end(struct hashfile *);
 
+/* Verify checksum validity while reading. Returns non-zero on success. */
+int hashfile_checksum_valid(const unsigned char *data, size_t len);
+
 /*
  * Returns the total number of bytes fed to the hashfile so far (including ones
  * that have not been written out to the descriptor yet).

diff --git a/pack-check.c b/pack-check.c
index 4b089fe8ec051af05044225c283ee5ff3c1dac84..c8e560d71ab7e558da1a332d0640e6a71df5ac8c 100644 (file)
--- a/pack-check.c
+++ b/pack-check.c
@@ -164,22 +164,13 @@ static int verify_packfile(struct repository *r,
 
 int verify_pack_index(struct packed_git *p)
 {
-       size_t len;
-       const unsigned char *index_base;
-       git_hash_ctx ctx;
-       unsigned char hash[GIT_MAX_RAWSZ];
        int err = 0;
 
        if (open_pack_index(p))
                return error("packfile %s index not opened", p->pack_name);
-       index_base = p->index_data;
-       len = p->index_size - the_hash_algo->rawsz;
 
        /* Verify SHA1 sum of the index file */
-       the_hash_algo->init_fn(&ctx);
-       the_hash_algo->update_fn(&ctx, index_base, len);
-       the_hash_algo->final_fn(hash, &ctx);
-       if (!hasheq(hash, index_base + len))
+       if (!hashfile_checksum_valid(p->index_data, p->index_size))
                err = error("Packfile index for %s hash mismatch",
                            p->pack_name);
        return err;