summaryrefslogtreecommitdiff
path: root/fast-import.c
diff options
context:
space:
mode:
authorShawn O. Pearce <spearce@spearce.org>2008-01-20 23:37:01 -0500
committerJunio C Hamano <gitster@pobox.com>2008-01-21 01:04:12 -0800
commit7422bac441d6e00cfb8302600ae64512837ab4e3 (patch)
tree3c8c27b2558e2aa4a610d060c251910145547aff /fast-import.c
parentbb23fdfa6c13b7f9cd5e1dbe0ca2fea31a627c5c (diff)
downloadgit-7422bac441d6e00cfb8302600ae64512837ab4e3.tar.gz
Document the hairy gfi_unpack_entry part of fast-import
Junio pointed out this part of fast-import wasn't very clear on initial read, and it took some time for someone who was new to fast-import's "dirty little tricks" to understand how this was even working. So a little bit of commentary in the proper place may help future readers. Signed-off-by: Shawn O. Pearce <spearce@spearce.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Diffstat (limited to 'fast-import.c')
-rw-r--r--fast-import.c33
1 files changed, 33 insertions, 0 deletions
diff --git a/fast-import.c b/fast-import.c
index f6872fe23d..a523b171e2 100644
--- a/fast-import.c
+++ b/fast-import.c
@@ -1125,6 +1125,24 @@ static int store_object(
return 0;
}
+/* All calls must be guarded by find_object() or find_mark() to
+ * ensure the 'struct object_entry' passed was written by this
+ * process instance. We unpack the entry by the offset, avoiding
+ * the need for the corresponding .idx file. This unpacking rule
+ * works because we only use OBJ_REF_DELTA within the packfiles
+ * created by fast-import.
+ *
+ * oe must not be NULL. Such an oe usually comes from giving
+ * an unknown SHA-1 to find_object() or an undefined mark to
+ * find_mark(). Callers must test for this condition and use
+ * the standard read_sha1_file() when it happens.
+ *
+ * oe->pack_id must not be MAX_PACK_ID. Such an oe is usually from
+ * find_mark(), where the mark was reloaded from an existing marks
+ * file and is referencing an object that this fast-import process
+ * instance did not write out to a packfile. Callers must test for
+ * this condition and use read_sha1_file() instead.
+ */
static void *gfi_unpack_entry(
struct object_entry *oe,
unsigned long *sizep)
@@ -1132,7 +1150,22 @@ static void *gfi_unpack_entry(
enum object_type type;
struct packed_git *p = all_packs[oe->pack_id];
if (p == pack_data && p->pack_size < (pack_size + 20)) {
+ /* The object is stored in the packfile we are writing to
+ * and we have modified it since the last time we scanned
+ * back to read a previously written object. If an old
+ * window covered [p->pack_size, p->pack_size + 20) its
+ * data is stale and is not valid. Closing all windows
+ * and updating the packfile length ensures we can read
+ * the newly written data.
+ */
close_pack_windows(p);
+
+ /* We have to offer 20 bytes additional on the end of
+ * the packfile as the core unpacker code assumes the
+ * footer is present at the file end and must promise
+ * at least 20 bytes within any window it maps. But
+ * we don't actually create the footer here.
+ */
p->pack_size = pack_size + 20;
}
return unpack_entry(p, oe->offset, &type, sizep);