Do SHA1 hash _before_ compression.

And add a "convert-cache" program to convert from old-style
to new-style.

5 files changed, 158 insertions, 13 deletions

diff --git a/Makefile b/Makefile
index 0d07b9a..cd299f8 100644
--- a/Makefile
+++ b/Makefile
@@ -16,7 +16,7 @@ AR=ar
 PROG=   update-cache show-diff init-db write-tree read-tree commit-tree \
 	cat-file fsck-cache checkout-cache diff-tree rev-tree show-files \
 	check-files ls-tree merge-base merge-cache unpack-file git-export \
-	diff-cache
+	diff-cache convert-cache
 
 all: $(PROG)
 
@@ -88,12 +88,16 @@ git-export: git-export.o $(LIB_FILE)
 diff-cache: diff-cache.o $(LIB_FILE)
 	$(CC) $(CFLAGS) -o diff-cache diff-cache.o $(LIBS)
 
+convert-cache: convert-cache.o $(LIB_FILE)
+	$(CC) $(CFLAGS) -o convert-cache convert-cache.o $(LIBS)
+
 blob.o: $(LIB_H)
 cat-file.o: $(LIB_H)
 check-files.o: $(LIB_H)
 checkout-cache.o: $(LIB_H)
 commit.o: $(LIB_H)
 commit-tree.o: $(LIB_H)
+convert-cache.o: $(LIB_H)
 diff-cache.o: $(LIB_H)
 diff-tree.o: $(LIB_H)
 fsck-cache.o: $(LIB_H)
diff --git a/cache.h b/cache.h
index efeb82b..dd91a71 100644
--- a/cache.h
+++ b/cache.h
@@ -112,7 +112,7 @@ extern void * map_sha1_file(const unsigned char *sha1, unsigned long *size);
 extern void * unpack_sha1_file(void *map, unsigned long mapsize, char *type, unsigned long *size);
 extern void * read_sha1_file(const unsigned char *sha1, char *type, unsigned long *size);
 extern int write_sha1_file(char *buf, unsigned len, unsigned char *return_sha1);
-extern int check_sha1_signature(unsigned char *sha1, void *buf, unsigned long size);
+extern int check_sha1_signature(unsigned char *sha1, void *buf, unsigned long size, const char *type);
 
 /* Convert to/from hex/sha1 representation */
 extern int get_sha1_hex(const char *hex, unsigned char *sha1);
diff --git a/convert-cache.c b/convert-cache.c
new file mode 100644
index 0000000..97e9952
--- /dev/null
+++ b/convert-cache.c
@@ -0,0 +1,138 @@
+#include "cache.h"
+
+struct entry {
+	unsigned char old_sha1[20];
+	unsigned char new_sha1[20];
+	int converted;
+};
+
+#define MAXOBJECTS (1000000)
+
+static struct entry *convert[MAXOBJECTS];
+static int nr_convert;
+
+static struct entry * convert_entry(unsigned char *sha1);
+
+static struct entry *insert_new(unsigned char *sha1, int pos)
+{
+	struct entry *new = malloc(sizeof(struct entry));
+
+	memset(new, 0, sizeof(*new));
+	memcpy(new->old_sha1, sha1, 20);
+	memmove(convert + pos + 1, convert + pos, (nr_convert - pos) * sizeof(struct entry *));
+	convert[pos] = new;
+	nr_convert++;
+	if (nr_convert == MAXOBJECTS)
+		die("you're kidding me - hit maximum object limit");
+	return new;
+}
+
+static struct entry *lookup_entry(unsigned char *sha1)
+{
+	int low = 0, high = nr_convert;
+
+	while (low < high) {
+		int next = (low + high) / 2;
+		struct entry *n = convert[next];
+		int cmp = memcmp(sha1, n->old_sha1, 20);
+		if (!cmp)
+			return n;
+		if (cmp < 0) {
+			high = next;
+			continue;
+		}
+		low = next+1;
+	}
+	return insert_new(sha1, low);
+}
+
+static void convert_blob(void *buffer, unsigned long size)
+{
+	/* Nothing to do */
+}
+
+static void convert_binary_sha1(void *buffer)
+{
+	struct entry *entry = convert_entry(buffer);
+	memcpy(buffer, entry->new_sha1, 20);
+}
+
+static void convert_ascii_sha1(void *buffer)
+{
+	unsigned char sha1[20];
+	struct entry *entry;
+
+	if (get_sha1_hex(buffer, sha1))
+		die("bad sha1");
+	entry = convert_entry(sha1);
+	memcpy(buffer, sha1_to_hex(entry->new_sha1), 40);
+}
+
+static void convert_tree(void *buffer, unsigned long size)
+{
+	while (size) {
+		int len = 1+strlen(buffer);
+
+		convert_binary_sha1(buffer + len);
+
+		len += 20;
+		if (len > size)
+			die("corrupt tree object");
+		size -= len;
+		buffer += len;
+	}
+}
+
+static void convert_commit(void *buffer, unsigned long size)
+{
+	convert_ascii_sha1(buffer+5);
+	buffer += 46;    /* "tree " + "hex sha1" + "\n" */
+	while (!memcmp(buffer, "parent ", 7)) {
+		convert_ascii_sha1(buffer+7);
+		buffer += 48;
+	}
+}
+
+static struct entry * convert_entry(unsigned char *sha1)
+{
+	struct entry *entry = lookup_entry(sha1);
+	char type[20];
+	void *buffer, *data;
+	unsigned long size, offset;
+
+	if (entry->converted)
+		return entry;
+	data = read_sha1_file(sha1, type, &size);
+	if (!data)
+		die("unable to read object %s", sha1_to_hex(sha1));
+
+	buffer = malloc(size + 100);
+	offset = sprintf(buffer, "%s %lu", type, size)+1;
+	memcpy(buffer + offset, data, size);
+	
+	if (!strcmp(type, "blob"))
+		convert_blob(buffer + offset, size);
+	else if (!strcmp(type, "tree"))
+		convert_tree(buffer + offset, size);
+	else if (!strcmp(type, "commit"))
+		convert_commit(buffer + offset, size);
+	else
+		die("unknown object type '%s' in %s", type, sha1_to_hex(sha1));
+	write_sha1_file(buffer, size + offset, entry->new_sha1);
+	entry->converted = 1;
+	free(buffer);
+	return entry;
+}
+
+int main(int argc, char **argv)
+{
+	unsigned char sha1[20];
+	struct entry *entry;
+
+	if (argc != 2 || get_sha1_hex(argv[1], sha1))
+		usage("convert-cache <sha1>");
+
+	entry = convert_entry(sha1);
+	printf("new sha1: %s\n", sha1_to_hex(entry->new_sha1));
+	return 0;
+}
diff --git a/fsck-cache.c b/fsck-cache.c
index 952d413..96b8eb1 100644
--- a/fsck-cache.c
+++ b/fsck-cache.c
@@ -85,12 +85,13 @@ static int fsck_name(char *hex)
 		if (map) {
 			char type[100];
 			unsigned long size;
-			void *buffer = NULL;
-			if (!check_sha1_signature(sha1, map, mapsize))
-				buffer = unpack_sha1_file(map, mapsize, type,
-							  &size);
+			void *buffer = unpack_sha1_file(map, mapsize, type, &size);
+			if (!buffer)
+				return -1;
+			if (check_sha1_signature(sha1, buffer, size, type) < 0)
+				printf("sha1 mismatch %s\n", sha1_to_hex(sha1));
 			munmap(map, mapsize);
-			if (buffer && !fsck_entry(sha1, type, buffer, size))
+			if (!fsck_entry(sha1, type, buffer, size))
 				return 0;
 		}
 	}
diff --git a/sha1_file.c b/sha1_file.c
index bb44a01..40c00b7 100644
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -80,12 +80,14 @@ char *sha1_file_name(const unsigned char *sha1)
 	return base;
 }
 
-int check_sha1_signature(unsigned char *sha1, void *map, unsigned long size)
+int check_sha1_signature(unsigned char *sha1, void *map, unsigned long size, const char *type)
 {
+	char header[100];
 	unsigned char real_sha1[20];
 	SHA_CTX c;
 
 	SHA1_Init(&c);
+	SHA1_Update(&c, header, 1+sprintf(header, "%s %lu", type, size));
 	SHA1_Update(&c, map, size);
 	SHA1_Final(real_sha1, &c);
 	return memcmp(sha1, real_sha1, 20) ? -1 : 0;
@@ -172,6 +174,11 @@ int write_sha1_file(char *buf, unsigned len, unsigned char *returnsha1)
 	unsigned char sha1[20];
 	SHA_CTX c;
 
+	/* Sha1.. */
+	SHA1_Init(&c);
+	SHA1_Update(&c, buf, len);
+	SHA1_Final(sha1, &c);
+
 	/* Set it up */
 	memset(&stream, 0, sizeof(stream));
 	deflateInit(&stream, Z_BEST_COMPRESSION);
@@ -188,11 +195,6 @@ int write_sha1_file(char *buf, unsigned len, unsigned char *returnsha1)
 	deflateEnd(&stream);
 	size = stream.total_out;
 
-	/* Sha1.. */
-	SHA1_Init(&c);
-	SHA1_Update(&c, compressed, size);
-	SHA1_Final(sha1, &c);
-
 	if (write_sha1_buffer(sha1, compressed, size) < 0)
 		return -1;
 	if (returnsha1)