[PATCH] delta check

This adds knowledge of delta objects to fsck-cache and various object
parsing code.  A new switch to git-fsck-cache is provided to display the
maximum delta depth found in a repository.

Signed-off-by: Nicolas Pitre <nico@cam.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

diff --git a/Makefile b/Makefile
index 5211edc4ba0999b87ce1aa899683bd495fe345dd..fc69a409aea200e5b4e1ddd6fe61821220a57955 100644 (file)
--- a/Makefile
+++ b/Makefile
@@ -36,7 +36,7 @@ install: $(PROG) $(SCRIPTS)
        $(INSTALL) $(PROG) $(SCRIPTS) $(dest)$(bin)
 
 LIB_OBJS=read-cache.o sha1_file.o usage.o object.o commit.o tree.o blob.o \
-        tag.o date.o index.o diff-delta.o patch-delta.o
+        tag.o delta.o date.o index.o diff-delta.o patch-delta.o
 LIB_FILE=libgit.a
 LIB_H=cache.h object.h blob.h tree.h commit.h tag.h delta.h
 

diff --git a/blob.c b/blob.c
index 280f5241577ac029e9d5a7eb5bf895642b342fc8..c800cd3905e2a4e97098064a588e15c0ae33a0b0 100644 (file)
--- a/blob.c
+++ b/blob.c
@@ -14,6 +14,8 @@ struct blob *lookup_blob(unsigned char *sha1)
                ret->object.type = blob_type;
                return ret;
        }
+       if (!obj->type)
+               obj->type = blob_type;
        if (obj->type != blob_type) {
                error("Object %s is a %s, not a blob", 
                      sha1_to_hex(sha1), obj->type);

diff --git a/commit.c b/commit.c
index e83056406f54495fe8a1090a816c425375858d4d..3f2235ecf87b63bc5d16342ebcf7f8faf098530a 100644 (file)
--- a/commit.c
+++ b/commit.c
@@ -37,6 +37,8 @@ struct commit *lookup_commit(unsigned char *sha1)
                ret->object.type = commit_type;
                return ret;
        }
+       if (!obj->type)
+               obj->type = commit_type;
        return check_commit(obj, sha1);
 }
 

diff --git a/delta.c b/delta.c
new file mode 100644 (file)
index 0000000..05ef7fd
--- /dev/null
+++ b/delta.c
@@ -0,0 +1,115 @@
+#include "object.h"
+#include "blob.h"
+#include "tree.h"
+#include "commit.h"
+#include "tag.h"
+#include "delta.h"
+#include "cache.h"
+#include <string.h>
+
+/* the delta object definition (it can alias any other object) */
+struct delta {
+       union {
+               struct object object;
+               struct blob blob;
+               struct tree tree;
+               struct commit commit;
+               struct tag tag;
+       } u;
+};
+
+struct delta *lookup_delta(unsigned char *sha1)
+{
+       struct object *obj = lookup_object(sha1);
+       if (!obj) {
+               struct delta *ret = xmalloc(sizeof(struct delta));
+               memset(ret, 0, sizeof(struct delta));
+               created_object(sha1, &ret->u.object);
+               return ret;
+       }
+       return (struct delta *) obj;
+}
+
+int parse_delta_buffer(struct delta *item, void *buffer, unsigned long size)
+{
+       struct object *reference;
+       struct object_list *p;
+
+       if (item->u.object.delta)
+               return 0;
+       item->u.object.delta = 1;
+       if (size <= 20)
+               return -1;
+       reference = lookup_object(buffer);
+       if (!reference) {
+               struct delta *ref = xmalloc(sizeof(struct delta));
+               memset(ref, 0, sizeof(struct delta));
+               created_object(buffer, &ref->u.object);
+               reference = &ref->u.object;
+       }
+
+       p = xmalloc(sizeof(*p));
+       p->item = &item->u.object;
+       p->next = reference->attached_deltas;
+       reference->attached_deltas = p;
+       return 0;
+}
+
+int process_deltas(void *src, unsigned long src_size, const char *src_type,
+                  struct object_list *delta_list)
+{
+       int deepest = 0;
+       do {
+               struct object *obj = delta_list->item;
+               static char type[10];
+               void *map, *delta, *buf;
+               unsigned long map_size, delta_size, buf_size;
+               map = map_sha1_file(obj->sha1, &map_size);
+               if (!map)
+                       continue;
+               delta = unpack_sha1_file(map, map_size, type, &delta_size);
+               munmap(map, map_size);
+               if (!delta)
+                       continue;
+               if (strcmp(type, "delta") || delta_size <= 20) {
+                       free(delta);
+                       continue;
+               }
+               buf = patch_delta(src, src_size,
+                                 delta+20, delta_size-20,
+                                 &buf_size);
+               free(delta);
+               if (!buf)
+                       continue;
+               if (check_sha1_signature(obj->sha1, buf, buf_size, src_type) < 0)
+                       printf("sha1 mismatch for delta %s\n", sha1_to_hex(obj->sha1));
+               if (obj->type && obj->type != src_type) {
+                       error("got %s when expecting %s for delta %s",
+                             src_type, obj->type, sha1_to_hex(obj->sha1));
+                       free(buf);
+                       continue;
+               }
+               obj->type = src_type;
+               if (src_type == blob_type) {
+                       parse_blob_buffer((struct blob *)obj, buf, buf_size);
+               } else if (src_type == tree_type) {
+                       parse_tree_buffer((struct tree *)obj, buf, buf_size);
+               } else if (src_type == commit_type) {
+                       parse_commit_buffer((struct commit *)obj, buf, buf_size);
+               } else if (src_type == tag_type) {
+                       parse_tag_buffer((struct tag *)obj, buf, buf_size);
+               } else {
+                       error("unknown object type %s", src_type);
+                       free(buf);
+                       continue;
+               }
+               if (obj->attached_deltas) {
+                       int depth = process_deltas(buf, buf_size, src_type,
+                                                  obj->attached_deltas);
+                       if (deepest < depth)
+                               deepest = depth;
+               }
+               free(buf);
+       } while ((delta_list = delta_list->next));
+       return deepest + 1;
+}

diff --git a/delta.h b/delta.h
index e073dff831ab5062638ddc33e32a7c7aae807c39..8e4efdf4acb568a4bd439884911d0ee947bd7f92 100644 (file)
--- a/delta.h
+++ b/delta.h
@@ -1,6 +1,21 @@
+#ifndef DELTA_H
+#define DELTA_H
+
+/* handling of delta buffers */
 extern void *diff_delta(void *from_buf, unsigned long from_size,
                        void *to_buf, unsigned long to_size,
                        unsigned long *delta_size);
 extern void *patch_delta(void *src_buf, unsigned long src_size,
                         void *delta_buf, unsigned long delta_size,
                         unsigned long *dst_size);
+
+/* handling of delta objects */
+struct delta;
+struct object_list;
+extern struct delta *lookup_delta(unsigned char *sha1);
+extern int parse_delta_buffer(struct delta *item, void *buffer, unsigned long size);
+extern int parse_delta(struct delta *item, unsigned char sha1);
+extern int process_deltas(void *src, unsigned long src_size,
+                         const char *src_type, struct object_list *delta);
+
+#endif

diff --git a/fsck-cache.c b/fsck-cache.c
index 6c65f2bb2262f378e17fc75600a32abeaf4e1ed6..6ac122b71cf9a5eec298a003032c5724d47f306d 100644 (file)
--- a/fsck-cache.c
+++ b/fsck-cache.c
@@ -6,15 +6,46 @@
 #include "tree.h"
 #include "blob.h"
 #include "tag.h"
+#include "delta.h"
 
 #define REACHABLE 0x0001
 
 static int show_root = 0;
 static int show_tags = 0;
 static int show_unreachable = 0;
+static int show_max_delta_depth = 0;
 static int keep_cache_objects = 0; 
 static unsigned char head_sha1[20];
 
+static void expand_deltas(void)
+{
+       int i, max_depth = 0;
+
+       /*
+        * To be as efficient as possible we look for delta heads and
+        * recursively process them going backward, and parsing
+        * resulting objects along the way.  This allows for processing
+        * each delta objects only once regardless of the delta depth.
+        */
+       for (i = 0; i < nr_objs; i++) {
+               struct object *obj = objs[i];
+               if (obj->parsed && !obj->delta && obj->attached_deltas) {
+                       int depth = 0;
+                       char type[10];
+                       unsigned long size;
+                       void *buf = read_sha1_file(obj->sha1, type, &size);
+                       if (!buf)
+                               continue;
+                       depth = process_deltas(buf, size, obj->type,
+                                              obj->attached_deltas);
+                       if (max_depth < depth)
+                               max_depth = depth;
+               }
+       }
+       if (show_max_delta_depth)
+               printf("maximum delta depth = %d\n", max_depth);
+}
+                                                                                                                       
 static void check_connectivity(void)
 {
        int i;
@@ -25,7 +56,12 @@ static void check_connectivity(void)
                struct object_list *refs;
 
                if (!obj->parsed) {
-                       printf("missing %s %s\n", obj->type, sha1_to_hex(obj->sha1));
+                       if (obj->delta)
+                               printf("unresolved delta %s\n",
+                                      sha1_to_hex(obj->sha1));
+                       else
+                               printf("missing %s %s\n",
+                                      obj->type, sha1_to_hex(obj->sha1));
                        continue;
                }
 
@@ -43,7 +79,12 @@ static void check_connectivity(void)
                        continue;
 
                if (show_unreachable && !(obj->flags & REACHABLE)) {
-                       printf("unreachable %s %s\n", obj->type, sha1_to_hex(obj->sha1));
+                       if (obj->attached_deltas)
+                               printf("foreign delta reference %s\n", 
+                                      sha1_to_hex(obj->sha1));
+                       else
+                               printf("unreachable %s %s\n",
+                                      obj->type, sha1_to_hex(obj->sha1));
                        continue;
                }
 
@@ -201,6 +242,8 @@ static int fsck_sha1(unsigned char *sha1)
                return fsck_commit((struct commit *) obj);
        if (obj->type == tag_type)
                return fsck_tag((struct tag *) obj);
+       if (!obj->type && obj->delta)
+               return 0;
        return -1;
 }
 
@@ -384,6 +427,10 @@ int main(int argc, char **argv)
                        show_root = 1;
                        continue;
                }
+               if (!strcmp(arg, "--delta-depth")) {
+                       show_max_delta_depth = 1;
+                       continue;
+               }
                if (!strcmp(arg, "--cache")) {
                        keep_cache_objects = 1;
                        continue;
@@ -400,6 +447,8 @@ int main(int argc, char **argv)
        }
        fsck_sha1_list();
 
+       expand_deltas();
+
        heads = 0;
        for (i = 1; i < argc; i++) {
                const char *arg = argv[i]; 
@@ -423,7 +472,7 @@ int main(int argc, char **argv)
        }
 
        /*
-        * If we've not been gived any explicit head information, do the
+        * If we've not been given any explicit head information, do the
         * default ones from .git/refs. We also consider the index file
         * in this case (ie this implies --cache).
         */

diff --git a/object.c b/object.c
index b5a62e7f87f24c2ab0ea83f3c445d81bcbff027a..deb683076d7e1a91e913398ff905085230014a4f 100644 (file)
--- a/object.c
+++ b/object.c
@@ -4,6 +4,7 @@
 #include "commit.h"
 #include "cache.h"
 #include "tag.h"
+#include "delta.h"
 #include <stdlib.h>
 #include <string.h>
 
@@ -104,6 +105,7 @@ struct object *parse_object(unsigned char *sha1)
        unsigned long mapsize;
        void *map = map_sha1_file(sha1, &mapsize);
        if (map) {
+               int is_delta;
                struct object *obj;
                char type[100];
                unsigned long size;
@@ -111,9 +113,14 @@ struct object *parse_object(unsigned char *sha1)
                munmap(map, mapsize);
                if (!buffer)
                        return NULL;
-               if (check_sha1_signature(sha1, buffer, size, type) < 0)
+               is_delta = !strcmp(type, "delta");
+               if (!is_delta && check_sha1_signature(sha1, buffer, size, type) < 0)
                        printf("sha1 mismatch %s\n", sha1_to_hex(sha1));
-               if (!strcmp(type, "blob")) {
+               if (is_delta) {
+                       struct delta *delta = lookup_delta(sha1);
+                       parse_delta_buffer(delta, buffer, size);
+                       obj = (struct object *) delta;
+               } else if (!strcmp(type, "blob")) {
                        struct blob *blob = lookup_blob(sha1);
                        parse_blob_buffer(blob, buffer, size);
                        obj = &blob->object;

diff --git a/object.h b/object.h
index 09700d376077b2d6136620faf6efb77ee679deeb..464bb0a292c11515ecb074de37daa7fa5536d8e5 100644 (file)
--- a/object.h
+++ b/object.h
@@ -9,10 +9,12 @@ struct object_list {
 struct object {
        unsigned parsed : 1;
        unsigned used : 1;
+       unsigned delta : 1;
        unsigned int flags;
        unsigned char sha1[20];
        const char *type;
        struct object_list *refs;
+       struct object_list *attached_deltas;
 };
 
 extern int nr_objs;

diff --git a/tag.c b/tag.c
index 22deb243ad58b2c57fb8652fe2d08c571ee3e781..26494ca9695fdd2e81952378f64bbc361698117d 100644 (file)
--- a/tag.c
+++ b/tag.c
@@ -13,6 +13,8 @@ struct tag *lookup_tag(unsigned char *sha1)
                 ret->object.type = tag_type;
                 return ret;
         }
+       if (!obj->type)
+               obj->type = tag_type;
         if (obj->type != tag_type) {
                 error("Object %s is a %s, not a tree", 
                       sha1_to_hex(sha1), obj->type);

diff --git a/tree.c b/tree.c
index ca800a85f771be1bd10d6575d93ca05bd3fc381c..d448daeab172a2a8b1a1c0624319f3f0096d40c0 100644 (file)
--- a/tree.c
+++ b/tree.c
@@ -83,6 +83,8 @@ struct tree *lookup_tree(unsigned char *sha1)
                ret->object.type = tree_type;
                return ret;
        }
+       if (!obj->type)
+               obj->type = tree_type;
        if (obj->type != tree_type) {
                error("Object %s is a %s, not a tree", 
                      sha1_to_hex(sha1), obj->type);