summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--Documentation/git-update-index.txt6
-rw-r--r--Makefile4
-rw-r--r--apply.c316
-rw-r--r--base85.c140
-rw-r--r--cache.h4
-rw-r--r--delta.h73
-rw-r--r--diff-delta.c359
-rw-r--r--diff.c114
-rw-r--r--diff.h1
-rwxr-xr-xgit-clone.sh6
-rw-r--r--pack-objects.c74
-rw-r--r--patch-delta.c2
-rw-r--r--read-cache.c2
-rw-r--r--sha1_file.c178
-rw-r--r--sha1_name.c55
-rwxr-xr-xt/t2101-update-index-reupdate.sh82
-rwxr-xr-xt/t4012-diff-binary.sh85
-rwxr-xr-xt/t5710-info-alternate.sh105
-rw-r--r--t/test4012.pngbin0 -> 5660 bytes
-rw-r--r--update-index.c58
20 files changed, 1339 insertions, 325 deletions
diff --git a/Documentation/git-update-index.txt b/Documentation/git-update-index.txt
index 57177c7fb6..d043e86a77 100644
--- a/Documentation/git-update-index.txt
+++ b/Documentation/git-update-index.txt
@@ -15,7 +15,7 @@ SYNOPSIS
[--cacheinfo <mode> <object> <file>]\*
[--chmod=(+|-)x]
[--assume-unchanged | --no-assume-unchanged]
- [--really-refresh] [--unresolve]
+ [--really-refresh] [--unresolve] [--again]
[--info-only] [--index-info]
[-z] [--stdin]
[--verbose]
@@ -80,6 +80,10 @@ OPTIONS
filesystem that has very slow lstat(2) system call
(e.g. cifs).
+--again::
+ Runs `git-update-index` itself on the paths whose index
+ entries are different from those from the `HEAD` commit.
+
--unresolve::
Restores the 'unmerged' or 'needs updating' state of a
file during a merge if it was cleared by accident.
diff --git a/Makefile b/Makefile
index 45484fcd82..37fbe789d3 100644
--- a/Makefile
+++ b/Makefile
@@ -205,7 +205,7 @@ DIFF_OBJS = \
diffcore-delta.o log-tree.o
LIB_OBJS = \
- blob.o commit.o connect.o csum-file.o \
+ blob.o commit.o connect.o csum-file.o base85.o \
date.o diff-delta.o entry.o exec_cmd.o ident.o index.o \
object.o pack-check.o patch-delta.o path.o pkt-line.o \
quote.o read-cache.o refs.o run-command.o \
@@ -607,7 +607,7 @@ test-date$X: test-date.c date.o ctype.o
$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) test-date.c date.o ctype.o
test-delta$X: test-delta.c diff-delta.o patch-delta.o
- $(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $^ -lz
+ $(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $^
check:
for i in *.c; do sparse $(ALL_CFLAGS) $(SPARSE_FLAGS) $$i || exit; done
diff --git a/apply.c b/apply.c
index 269210a578..7c8146a7f3 100644
--- a/apply.c
+++ b/apply.c
@@ -10,6 +10,7 @@
#include "cache.h"
#include "quote.h"
#include "blob.h"
+#include "delta.h"
// --check turns on checking that the working tree matches the
// files that are being modified, but doesn't apply the patch
@@ -19,6 +20,7 @@
//
static const char *prefix;
static int prefix_length = -1;
+static int newfd = -1;
static int p_value = 1;
static int allow_binary_replacement = 0;
@@ -113,6 +115,9 @@ struct patch {
char *new_name, *old_name, *def_name;
unsigned int old_mode, new_mode;
int is_rename, is_copy, is_new, is_delete, is_binary;
+#define BINARY_DELTA_DEFLATED 1
+#define BINARY_LITERAL_DEFLATED 2
+ unsigned long deflate_origlen;
int lines_added, lines_deleted;
int score;
struct fragment *fragments;
@@ -966,6 +971,88 @@ static inline int metadata_changes(struct patch *patch)
patch->old_mode != patch->new_mode);
}
+static int parse_binary(char *buffer, unsigned long size, struct patch *patch)
+{
+ /* We have read "GIT binary patch\n"; what follows is a line
+ * that says the patch method (currently, either "deflated
+ * literal" or "deflated delta") and the length of data before
+ * deflating; a sequence of 'length-byte' followed by base-85
+ * encoded data follows.
+ *
+ * Each 5-byte sequence of base-85 encodes up to 4 bytes,
+ * and we would limit the patch line to 66 characters,
+ * so one line can fit up to 13 groups that would decode
+ * to 52 bytes max. The length byte 'A'-'Z' corresponds
+ * to 1-26 bytes, and 'a'-'z' corresponds to 27-52 bytes.
+ * The end of binary is signalled with an empty line.
+ */
+ int llen, used;
+ struct fragment *fragment;
+ char *data = NULL;
+
+ patch->fragments = fragment = xcalloc(1, sizeof(*fragment));
+
+ /* Grab the type of patch */
+ llen = linelen(buffer, size);
+ used = llen;
+ linenr++;
+
+ if (!strncmp(buffer, "delta ", 6)) {
+ patch->is_binary = BINARY_DELTA_DEFLATED;
+ patch->deflate_origlen = strtoul(buffer + 6, NULL, 10);
+ }
+ else if (!strncmp(buffer, "literal ", 8)) {
+ patch->is_binary = BINARY_LITERAL_DEFLATED;
+ patch->deflate_origlen = strtoul(buffer + 8, NULL, 10);
+ }
+ else
+ return error("unrecognized binary patch at line %d: %.*s",
+ linenr-1, llen-1, buffer);
+ buffer += llen;
+ while (1) {
+ int byte_length, max_byte_length, newsize;
+ llen = linelen(buffer, size);
+ used += llen;
+ linenr++;
+ if (llen == 1)
+ break;
+ /* Minimum line is "A00000\n" which is 7-byte long,
+ * and the line length must be multiple of 5 plus 2.
+ */
+ if ((llen < 7) || (llen-2) % 5)
+ goto corrupt;
+ max_byte_length = (llen - 2) / 5 * 4;
+ byte_length = *buffer;
+ if ('A' <= byte_length && byte_length <= 'Z')
+ byte_length = byte_length - 'A' + 1;
+ else if ('a' <= byte_length && byte_length <= 'z')
+ byte_length = byte_length - 'a' + 27;
+ else
+ goto corrupt;
+ /* if the input length was not multiple of 4, we would
+ * have filler at the end but the filler should never
+ * exceed 3 bytes
+ */
+ if (max_byte_length < byte_length ||
+ byte_length <= max_byte_length - 4)
+ goto corrupt;
+ newsize = fragment->size + byte_length;
+ data = xrealloc(data, newsize);
+ if (decode_85(data + fragment->size,
+ buffer + 1,
+ byte_length))
+ goto corrupt;
+ fragment->size = newsize;
+ buffer += llen;
+ size -= llen;
+ }
+ fragment->patch = data;
+ return used;
+ corrupt:
+ return error("corrupt binary patch at line %d: %.*s",
+ linenr-1, llen-1, buffer);
+}
+
static int parse_chunk(char *buffer, unsigned long size, struct patch *patch)
{
int hdrsize, patchsize;
@@ -982,19 +1069,34 @@ static int parse_chunk(char *buffer, unsigned long size, struct patch *patch)
"Files ",
NULL,
};
+ static const char git_binary[] = "GIT binary patch\n";
int i;
int hd = hdrsize + offset;
unsigned long llen = linelen(buffer + hd, size - hd);
- if (!memcmp(" differ\n", buffer + hd + llen - 8, 8))
+ if (llen == sizeof(git_binary) - 1 &&
+ !memcmp(git_binary, buffer + hd, llen)) {
+ int used;
+ linenr++;
+ used = parse_binary(buffer + hd + llen,
+ size - hd - llen, patch);
+ if (used)
+ patchsize = used + llen;
+ else
+ patchsize = 0;
+ }
+ else if (!memcmp(" differ\n", buffer + hd + llen - 8, 8)) {
for (i = 0; binhdr[i]; i++) {
int len = strlen(binhdr[i]);
if (len < size - hd &&
!memcmp(binhdr[i], buffer + hd, len)) {
+ linenr++;
patch->is_binary = 1;
+ patchsize = llen;
break;
}
}
+ }
/* Empty patch cannot be applied if:
* - it is a binary patch and we do not do binary_replace, or
@@ -1345,76 +1447,150 @@ static int apply_one_fragment(struct buffer_desc *desc, struct fragment *frag)
return offset;
}
-static int apply_fragments(struct buffer_desc *desc, struct patch *patch)
+static char *inflate_it(const void *data, unsigned long size,
+ unsigned long inflated_size)
+{
+ z_stream stream;
+ void *out;
+ int st;
+
+ memset(&stream, 0, sizeof(stream));
+
+ stream.next_in = (unsigned char *)data;
+ stream.avail_in = size;
+ stream.next_out = out = xmalloc(inflated_size);
+ stream.avail_out = inflated_size;
+ inflateInit(&stream);
+ st = inflate(&stream, Z_FINISH);
+ if ((st != Z_STREAM_END) || stream.total_out != inflated_size) {
+ free(out);
+ return NULL;
+ }
+ return out;
+}
+
+static int apply_binary_fragment(struct buffer_desc *desc, struct patch *patch)
+{
+ unsigned long dst_size;
+ struct fragment *fragment = patch->fragments;
+ void *data;
+ void *result;
+
+ data = inflate_it(fragment->patch, fragment->size,
+ patch->deflate_origlen);
+ if (!data)
+ return error("corrupt patch data");
+ switch (patch->is_binary) {
+ case BINARY_DELTA_DEFLATED:
+ result = patch_delta(desc->buffer, desc->size,
+ data,
+ patch->deflate_origlen,
+ &dst_size);
+ free(desc->buffer);
+ desc->buffer = result;
+ free(data);
+ break;
+ case BINARY_LITERAL_DEFLATED:
+ free(desc->buffer);
+ desc->buffer = data;
+ dst_size = patch->deflate_origlen;
+ break;
+ }
+ if (!desc->buffer)
+ return -1;
+ desc->size = desc->alloc = dst_size;
+ return 0;
+}
+
+static int apply_binary(struct buffer_desc *desc, struct patch *patch)
{
- struct fragment *frag = patch->fragments;
const char *name = patch->old_name ? patch->old_name : patch->new_name;
+ unsigned char sha1[20];
+ unsigned char hdr[50];
+ int hdrlen;
- if (patch->is_binary) {
- unsigned char sha1[20];
+ if (!allow_binary_replacement)
+ return error("cannot apply binary patch to '%s' "
+ "without --allow-binary-replacement",
+ name);
- if (!allow_binary_replacement)
- return error("cannot apply binary patch to '%s' "
- "without --allow-binary-replacement",
- name);
+ /* For safety, we require patch index line to contain
+ * full 40-byte textual SHA1 for old and new, at least for now.
+ */
+ if (strlen(patch->old_sha1_prefix) != 40 ||
+ strlen(patch->new_sha1_prefix) != 40 ||
+ get_sha1_hex(patch->old_sha1_prefix, sha1) ||
+ get_sha1_hex(patch->new_sha1_prefix, sha1))
+ return error("cannot apply binary patch to '%s' "
+ "without full index line", name);
- /* For safety, we require patch index line to contain
- * full 40-byte textual SHA1 for old and new, at least for now.
+ if (patch->old_name) {
+ /* See if the old one matches what the patch
+ * applies to.
*/
- if (strlen(patch->old_sha1_prefix) != 40 ||
- strlen(patch->new_sha1_prefix) != 40 ||
- get_sha1_hex(patch->old_sha1_prefix, sha1) ||
- get_sha1_hex(patch->new_sha1_prefix, sha1))
- return error("cannot apply binary patch to '%s' "
- "without full index line", name);
-
- if (patch->old_name) {
- unsigned char hdr[50];
- int hdrlen;
-
- /* See if the old one matches what the patch
- * applies to.
- */
- write_sha1_file_prepare(desc->buffer, desc->size,
- blob_type, sha1, hdr, &hdrlen);
- if (strcmp(sha1_to_hex(sha1), patch->old_sha1_prefix))
- return error("the patch applies to '%s' (%s), "
- "which does not match the "
- "current contents.",
- name, sha1_to_hex(sha1));
- }
- else {
- /* Otherwise, the old one must be empty. */
- if (desc->size)
- return error("the patch applies to an empty "
- "'%s' but it is not empty", name);
- }
+ write_sha1_file_prepare(desc->buffer, desc->size,
+ blob_type, sha1, hdr, &hdrlen);
+ if (strcmp(sha1_to_hex(sha1), patch->old_sha1_prefix))
+ return error("the patch applies to '%s' (%s), "
+ "which does not match the "
+ "current contents.",
+ name, sha1_to_hex(sha1));
+ }
+ else {
+ /* Otherwise, the old one must be empty. */
+ if (desc->size)
+ return error("the patch applies to an empty "
+ "'%s' but it is not empty", name);
+ }
- /* For now, we do not record post-image data in the patch,
- * and require the object already present in the recipient's
- * object database.
+ get_sha1_hex(patch->new_sha1_prefix, sha1);
+ if (!memcmp(sha1, null_sha1, 20)) {
+ free(desc->buffer);
+ desc->alloc = desc->size = 0;
+ desc->buffer = NULL;
+ return 0; /* deletion patch */
+ }
+
+ if (has_sha1_file(sha1)) {
+ /* We already have the postimage */
+ char type[10];
+ unsigned long size;
+
+ free(desc->buffer);
+ desc->buffer = read_sha1_file(sha1, type, &size);
+ if (!desc->buffer)
+ return error("the necessary postimage %s for "
+ "'%s' cannot be read",
+ patch->new_sha1_prefix, name);
+ desc->alloc = desc->size = size;
+ }
+ else {
+ /* We have verified desc matches the preimage;
+ * apply the patch data to it, which is stored
+ * in the patch->fragments->{patch,size}.
*/
- if (desc->buffer) {
- free(desc->buffer);
- desc->alloc = desc->size = 0;
- }
- get_sha1_hex(patch->new_sha1_prefix, sha1);
-
- if (memcmp(sha1, null_sha1, 20)) {
- char type[10];
- unsigned long size;
-
- desc->buffer = read_sha1_file(sha1, type, &size);
- if (!desc->buffer)
- return error("the necessary postimage %s for "
- "'%s' does not exist",
- patch->new_sha1_prefix, name);
- desc->alloc = desc->size = size;
- }
+ if (apply_binary_fragment(desc, patch))
+ return error("binary patch does not apply to '%s'",
+ name);
- return 0;
+ /* verify that the result matches */
+ write_sha1_file_prepare(desc->buffer, desc->size, blob_type,
+ sha1, hdr, &hdrlen);
+ if (strcmp(sha1_to_hex(sha1), patch->new_sha1_prefix))
+ return error("binary patch to '%s' creates incorrect result", name);
}
+ return 0;
+}
+
+static int apply_fragments(struct buffer_desc *desc, struct patch *patch)
+{
+ struct fragment *frag = patch->fragments;
+ const char *name = patch->old_name ? patch->old_name : patch->new_name;
+
+ if (patch->is_binary)
+ return apply_binary(desc, patch);
+
while (frag) {
if (apply_one_fragment(desc, frag) < 0)
return error("patch failed: %s:%ld",
@@ -1873,7 +2049,6 @@ static int use_patch(struct patch *p)
static int apply_patch(int fd, const char *filename)
{
- int newfd;
unsigned long offset, size;
char *buffer = read_patch_file(fd, &size);
struct patch *list = NULL, **listp = &list;
@@ -1904,12 +2079,11 @@ static int apply_patch(int fd, const char *filename)
size -= nr;
}
- newfd = -1;
if (whitespace_error && (new_whitespace == error_on_whitespace))
apply = 0;
write_index = check_index && apply;
- if (write_index)
+ if (write_index && newfd < 0)
newfd = hold_index_file_for_update(&cache_file, get_index_file());
if (check_index) {
if (read_cache() < 0)
@@ -1922,12 +2096,6 @@ static int apply_patch(int fd, const char *filename)
if (apply)
write_out_results(list, skipped_patch);
- if (write_index) {
- if (write_cache(newfd, active_cache, active_nr) ||
- commit_index_file(&cache_file))
- die("Unable to write new cachefile");
- }
-
if (show_index_info)
show_index_list(list);
@@ -1990,7 +2158,8 @@ int main(int argc, char **argv)
diffstat = 1;
continue;
}
- if (!strcmp(arg, "--allow-binary-replacement")) {
+ if (!strcmp(arg, "--allow-binary-replacement") ||
+ !strcmp(arg, "--binary")) {
allow_binary_replacement = 1;
continue;
}
@@ -2085,5 +2254,12 @@ int main(int argc, char **argv)
whitespace_error == 1 ? "" : "s",
whitespace_error == 1 ? "s" : "");
}
+
+ if (write_index) {
+ if (write_cache(newfd, active_cache, active_nr) ||
+ commit_index_file(&cache_file))
+ die("Unable to write new cachefile");
+ }
+
return 0;
}
diff --git a/base85.c b/base85.c
new file mode 100644
index 0000000000..a9e97f89d9
--- /dev/null
+++ b/base85.c
@@ -0,0 +1,140 @@
+#include "cache.h"
+
+#undef DEBUG_85
+
+#ifdef DEBUG_85
+#define say(a) fprintf(stderr, a)
+#define say1(a,b) fprintf(stderr, a, b)
+#define say2(a,b,c) fprintf(stderr, a, b, c)
+#else
+#define say(a) do {} while(0)
+#define say1(a,b) do {} while(0)
+#define say2(a,b,c) do {} while(0)
+#endif
+
+static const char en85[] = {
+ '0', '1', '2', '3', '4', '5', '6', '7', '8', '9',
+ 'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J',
+ 'K', 'L', 'M', 'N', 'O', 'P', 'Q', 'R', 'S', 'T',
+ 'U', 'V', 'W', 'X', 'Y', 'Z',
+ 'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j',
+ 'k', 'l', 'm', 'n', 'o', 'p', 'q', 'r', 's', 't',
+ 'u', 'v', 'w', 'x', 'y', 'z',
+ '!', '#', '$', '%', '&', '(', ')', '*', '+', '-',
+ ';', '<', '=', '>', '?', '@', '^', '_', '`', '{',
+ '|', '}', '~'
+};
+
+static char de85[256];
+static void prep_base85(void)
+{
+ int i;
+ if (de85['Z'])
+ return;
+ for (i = 0; i < ARRAY_SIZE(en85); i++) {
+ int ch = en85[i];
+ de85[ch] = i + 1;
+ }
+}
+
+int decode_85(char *dst, char *buffer, int len)
+{
+ prep_base85();
+
+ say2("decode 85 <%.*s>", len/4*5, buffer);
+ while (len) {
+ unsigned acc = 0;
+ int de, cnt = 4;
+ unsigned char ch;
+ do {
+ ch = *buffer++;
+ de = de85[ch];
+ if (--de < 0)
+ return error("invalid base85 alphabet %c", ch);
+ acc = acc * 85 + de;
+ } while (--cnt);
+ ch = *buffer++;
+ de = de85[ch];
+ if (--de < 0)
+ return error("invalid base85 alphabet %c", ch);
+ /*
+ * Detect overflow. The largest
+ * 5-letter possible is "|NsC0" to
+ * encode 0xffffffff, and "|NsC" gives
+ * 0x03030303 at this point (i.e.
+ * 0xffffffff = 0x03030303 * 85).
+ */
+ if (0x03030303 < acc ||
+ 0xffffffff - de < (acc *= 85))
+ error("invalid base85 sequence %.5s", buffer-5);
+ acc += de;
+ say1(" %08x", acc);
+
+ cnt = (len < 4) ? len : 4;
+ len -= cnt;
+ do {
+ acc = (acc << 8) | (acc >> 24);
+ *dst++ = acc;
+ } while (--cnt);
+ }
+ say("\n");
+
+ return 0;
+}
+
+void encode_85(char *buf, unsigned char *data, int bytes)
+{
+ prep_base85();
+
+ say("encode 85");
+ while (bytes) {
+ unsigned acc = 0;
+ int cnt;
+ for (cnt = 24; cnt >= 0; cnt -= 8) {
+ int ch = *data++;
+ acc |= ch << cnt;
+ if (--bytes == 0)
+ break;
+ }
+ say1(" %08x", acc);
+ for (cnt = 4; cnt >= 0; cnt--) {
+ int val = acc % 85;
+ acc /= 85;
+ buf[cnt] = en85[val];
+ }
+ buf += 5;
+ }
+ say("\n");
+
+ *buf = 0;
+}
+
+#ifdef DEBUG_85
+int main(int ac, char **av)
+{
+ char buf[1024];
+
+ if (!strcmp(av[1], "-e")) {
+ int len = strlen(av[2]);
+ encode_85(buf, av[2], len);
+ if (len <= 26) len = len + 'A' - 1;
+ else len = len + 'a' - 26 + 1;
+ printf("encoded: %c%s\n", len, buf);
+ return 0;
+ }
+ if (!strcmp(av[1], "-d")) {
+ int len = *av[2];
+ if ('A' <= len && len <= 'Z') len = len - 'A' + 1;
+ else len = len - 'a' + 26 + 1;
+ decode_85(buf, av[2]+1, len);
+ printf("decoded: %.*s\n", len, buf);
+ return 0;
+ }
+ if (!strcmp(av[1], "-t")) {
+ char t[4] = { -1,-1,-1,-1 };
+ encode_85(buf, t, 4);
+ printf("encoded: D%s\n", buf);
+ return 0;
+ }
+}
+#endif
diff --git a/cache.h b/cache.h
index 9d0ddcff01..4b7a439253 100644
--- a/cache.h
+++ b/cache.h
@@ -363,4 +363,8 @@ extern int receive_keep_pack(int fd[2], const char *me, int quiet);
/* pager.c */
extern void setup_pager(void);
+/* base85 */
+int decode_85(char *dst, char *line, int linelen);
+void encode_85(char *buf, unsigned char *data, int bytes);
+
#endif /* CACHE_H */
diff --git a/delta.h b/delta.h
index 09b2e1eed5..727ae30e9e 100644
--- a/delta.h
+++ b/delta.h
@@ -1,11 +1,72 @@
#ifndef DELTA_H
#define DELTA_H
-/* handling of delta buffers */
-extern void *diff_delta(const void *from_buf, unsigned long from_size,
- const void *to_buf, unsigned long to_size,
- unsigned long *delta_size, unsigned long max_size);
-extern void *patch_delta(void *src_buf, unsigned long src_size,
+/* opaque object for delta index */
+struct delta_index;
+
+/*
+ * create_delta_index: compute index data from given buffer
+ *
+ * This returns a pointer to a struct delta_index that should be passed to
+ * subsequent create_delta() calls, or to free_delta_index(). A NULL pointer
+ * is returned on failure. The given buffer must not be freed nor altered
+ * before free_delta_index() is called. The returned pointer must be freed
+ * using free_delta_index().
+ */
+extern struct delta_index *
+create_delta_index(const void *buf, unsigned long bufsize);
+
+/*
+ * free_delta_index: free the index created by create_delta_index()
+ */
+extern void free_delta_index(struct delta_index *index);
+
+/*
+ * create_delta: create a delta from given index for the given buffer
+ *
+ * This function may be called multiple times with different buffers using
+ * the same delta_index pointer. If max_delta_size is non-zero and the
+ * resulting delta is to be larger than max_delta_size then NULL is returned.
+ * On success, a non-NULL pointer to the buffer with the delta data is
+ * returned and *delta_size is updated with its size. The returned buffer
+ * must be freed by the caller.
+ */
+extern void *
+create_delta(const struct delta_index *index,
+ const void *buf, unsigned long bufsize,
+ unsigned long *delta_size, unsigned long max_delta_size);
+
+/*
+ * diff_delta: create a delta from source buffer to target buffer
+ *
+ * If max_delta_size is non-zero and the resulting delta is to be larger
+ * than max_delta_size then NULL is returned. On success, a non-NULL
+ * pointer to the buffer with the delta data is returned and *delta_size is
+ * updated with its size. The returned buffer must be freed by the caller.
+ */
+static inline void *
+diff_delta(const void *src_buf, unsigned long src_bufsize,
+ const void *trg_buf, unsigned long trg_bufsize,
+ unsigned long *delta_size, unsigned long max_delta_size)
+{
+ struct delta_index *index = create_delta_index(src_buf, src_bufsize);
+ if (index) {
+ void *delta = create_delta(index, trg_buf, trg_bufsize,
+ delta_size, max_delta_size);
+ free_delta_index(index);
+ return delta;
+ }
+ return NULL;
+}
+
+/*
+ * patch_delta: recreate target buffer given source buffer and delta data
+ *
+ * On success, a non-NULL pointer to the target buffer is returned and
+ * *trg_bufsize is updated with its size. On failure a NULL pointer is
+ * returned. The returned buffer must be freed by the caller.
+ */
+extern void *patch_delta(const void *src_buf, unsigned long src_size,
const void *delta_buf, unsigned long delta_size,
unsigned long *dst_size);
@@ -14,7 +75,7 @@ extern void *patch_delta(void *src_buf, unsigned long src_size,
/*
* This must be called twice on the delta data buffer, first to get the
- * expected reference buffer size, and again to get the result buffer size.
+ * expected source buffer size, and again to get the target buffer size.
*/
static inline unsigned long get_delta_hdr_size(const unsigned char **datap,
const unsigned char *top)
diff --git a/diff-delta.c b/diff-delta.c
index 5bc22047f8..c618875188 100644
--- a/diff-delta.c
+++ b/diff-delta.c
@@ -20,69 +20,188 @@
#include <stdlib.h>
#include <string.h>
-#include <zlib.h>
#include "delta.h"
-/* block size: min = 16, max = 64k, power of 2 */
-#define BLK_SIZE 16
-
-#define MIN(a, b) ((a) < (b) ? (a) : (b))
+/* maximum hash entry list for the same hash bucket */
+#define HASH_LIMIT 64
+
+#define RABIN_SHIFT 23
+#define RABIN_WINDOW 16
+
+static const unsigned int T[256] = {
+ 0x00000000, 0xab59b4d1, 0x56b369a2, 0xfdeadd73, 0x063f6795, 0xad66d344,
+ 0x508c0e37, 0xfbd5bae6, 0x0c7ecf2a, 0xa7277bfb, 0x5acda688, 0xf1941259,
+ 0x0a41a8bf, 0xa1181c6e, 0x5cf2c11d, 0xf7ab75cc, 0x18fd9e54, 0xb3a42a85,
+ 0x4e4ef7f6, 0xe5174327, 0x1ec2f9c1, 0xb59b4d10, 0x48719063, 0xe32824b2,
+ 0x1483517e, 0xbfdae5af, 0x423038dc, 0xe9698c0d, 0x12bc36eb, 0xb9e5823a,
+ 0x440f5f49, 0xef56eb98, 0x31fb3ca8, 0x9aa28879, 0x6748550a, 0xcc11e1db,
+ 0x37c45b3d, 0x9c9defec, 0x6177329f, 0xca2e864e, 0x3d85f382, 0x96dc4753,
+ 0x6b369a20, 0xc06f2ef1, 0x3bba9417, 0x90e320c6, 0x6d09fdb5, 0xc6504964,
+ 0x2906a2fc, 0x825f162d, 0x7fb5cb5e, 0xd4ec7f8f, 0x2f39c569, 0x846071b8,
+ 0x798aaccb, 0xd2d3181a, 0x25786dd6, 0x8e21d907, 0x73cb0474, 0xd892b0a5,
+ 0x23470a43, 0x881ebe92, 0x75f463e1, 0xdeadd730, 0x63f67950, 0xc8afcd81,
+ 0x354510f2, 0x9e1ca423, 0x65c91ec5, 0xce90aa14, 0x337a7767, 0x9823c3b6,
+ 0x6f88b67a, 0xc4d102ab, 0x393bdfd8, 0x92626b09, 0x69b7d1ef, 0xc2ee653e,
+ 0x3f04b84d, 0x945d0c9c, 0x7b0be704, 0xd05253d5, 0x2db88ea6, 0x86e13a77,
+ 0x7d348091, 0xd66d3440, 0x2b87e933, 0x80de5de2, 0x7775282e, 0xdc2c9cff,
+ 0x21c6418c, 0x8a9ff55d, 0x714a4fbb, 0xda13fb6a, 0x27f92619, 0x8ca092c8,
+ 0x520d45f8, 0xf954f129, 0x04be2c5a, 0xafe7988b, 0x5432226d, 0xff6b96bc,
+ 0x02814bcf, 0xa9d8ff1e, 0x5e738ad2, 0xf52a3e03, 0x08c0e370, 0xa39957a1,
+ 0x584ced47, 0xf3155996, 0x0eff84e5, 0xa5a63034, 0x4af0dbac, 0xe1a96f7d,
+ 0x1c43b20e, 0xb71a06df, 0x4ccfbc39, 0xe79608e8, 0x1a7cd59b, 0xb125614a,
+ 0x468e1486, 0xedd7a057, 0x103d7d24, 0xbb64c9f5, 0x40b17313, 0xebe8c7c2,
+ 0x16021ab1, 0xbd5bae60, 0x6cb54671, 0xc7ecf2a0, 0x3a062fd3, 0x915f9b02,
+ 0x6a8a21e4, 0xc1d39535, 0x3c394846, 0x9760fc97, 0x60cb895b, 0xcb923d8a,
+ 0x3678e0f9, 0x9d215428, 0x66f4eece, 0xcdad5a1f, 0x3047876c, 0x9b1e33bd,
+ 0x7448d825, 0xdf116cf4, 0x22fbb187, 0x89a20556, 0x7277bfb0, 0xd92e0b61,
+ 0x24c4d612, 0x8f9d62c3, 0x7836170f, 0xd36fa3de, 0x2e857ead, 0x85dcca7c,
+ 0x7e09709a, 0xd550c44b, 0x28ba1938, 0x83e3ade9, 0x5d4e7ad9, 0xf617ce08,
+ 0x0bfd137b, 0xa0a4a7aa, 0x5b711d4c, 0xf028a99d, 0x0dc274ee, 0xa69bc03f,
+ 0x5130b5f3, 0xfa690122, 0x0783dc51, 0xacda6880, 0x570fd266, 0xfc5666b7,
+ 0x01bcbbc4, 0xaae50f15, 0x45b3e48d, 0xeeea505c, 0x13008d2f, 0xb85939fe,
+ 0x438c8318, 0xe8d537c9, 0x153feaba, 0xbe665e6b, 0x49cd2ba7, 0xe2949f76,
+ 0x1f7e4205, 0xb427f6d4, 0x4ff24c32, 0xe4abf8e3, 0x19412590, 0xb2189141,
+ 0x0f433f21, 0xa41a8bf0, 0x59f05683, 0xf2a9e252, 0x097c58b4, 0xa225ec65,
+ 0x5fcf3116, 0xf49685c7, 0x033df00b, 0xa86444da, 0x558e99a9, 0xfed72d78,
+ 0x0502979e, 0xae5b234f, 0x53b1fe3c, 0xf8e84aed, 0x17bea175, 0xbce715a4,
+ 0x410dc8d7, 0xea547c06, 0x1181c6e0, 0xbad87231, 0x4732af42, 0xec6b1b93,
+ 0x1bc06e5f, 0xb099da8e, 0x4d7307fd, 0xe62ab32c, 0x1dff09ca, 0xb6a6bd1b,
+ 0x4b4c6068, 0xe015d4b9, 0x3eb80389, 0x95e1b758, 0x680b6a2b, 0xc352defa,
+ 0x3887641c, 0x93ded0cd, 0x6e340dbe, 0xc56db96f, 0x32c6cca3, 0x999f7872,
+ 0x6475a501, 0xcf2c11d0, 0x34f9ab36, 0x9fa01fe7, 0x624ac294, 0xc9137645,
+ 0x26459ddd, 0x8d1c290c, 0x70f6f47f, 0xdbaf40ae, 0x207afa48, 0x8b234e99,
+ 0x76c993ea, 0xdd90273b, 0x2a3b52f7, 0x8162e626, 0x7c883b55, 0xd7d18f84,
+ 0x2c043562, 0x875d81b3, 0x7ab75cc0, 0xd1eee811
+};
-#define GR_PRIME 0x9e370001
-#define HASH(v, shift) (((unsigned int)(v) * GR_PRIME) >> (shift))
+static const unsigned int U[256] = {
+ 0x00000000, 0x7eb5200d, 0x5633f4cb, 0x2886d4c6, 0x073e5d47, 0x798b7d4a,
+ 0x510da98c, 0x2fb88981, 0x0e7cba8e, 0x70c99a83, 0x584f4e45, 0x26fa6e48,
+ 0x0942e7c9, 0x77f7c7c4, 0x5f711302, 0x21c4330f, 0x1cf9751c, 0x624c5511,
+ 0x4aca81d7, 0x347fa1da, 0x1bc7285b, 0x65720856, 0x4df4dc90, 0x3341fc9d,
+ 0x1285cf92, 0x6c30ef9f, 0x44b63b59, 0x3a031b54, 0x15bb92d5, 0x6b0eb2d8,
+ 0x4388661e, 0x3d3d4613, 0x39f2ea38, 0x4747ca35, 0x6fc11ef3, 0x11743efe,
+ 0x3eccb77f, 0x40799772, 0x68ff43b4, 0x164a63b9, 0x378e50b6, 0x493b70bb,
+ 0x61bda47d, 0x1f088470, 0x30b00df1, 0x4e052dfc, 0x6683f93a, 0x1836d937,
+ 0x250b9f24, 0x5bbebf29, 0x73386bef, 0x0d8d4be2, 0x2235c263, 0x5c80e26e,
+ 0x740636a8, 0x0ab316a5, 0x2b7725aa, 0x55c205a7, 0x7d44d161, 0x03f1f16c,
+ 0x2c4978ed, 0x52fc58e0, 0x7a7a8c26, 0x04cfac2b, 0x73e5d470, 0x0d50f47d,
+ 0x25d620bb, 0x5b6300b6, 0x74db8937, 0x0a6ea93a, 0x22e87dfc, 0x5c5d5df1,
+ 0x7d996efe, 0x032c4ef3, 0x2baa9a35, 0x551fba38, 0x7aa733b9, 0x041213b4,
+ 0x2c94c772, 0x5221e77f, 0x6f1ca16c, 0x11a98161, 0x392f55a7, 0x479a75aa,
+ 0x6822fc2b, 0x1697dc26, 0x3e1108e0, 0x40a428ed, 0x61601be2, 0x1fd53bef,
+ 0x3753ef29, 0x49e6cf24, 0x665e46a5, 0x18eb66a8, 0x306db26e, 0x4ed89263,
+ 0x4a173e48, 0x34a21e45, 0x1c24ca83, 0x6291ea8e, 0x4d29630f, 0x339c4302,
+ 0x1b1a97c4, 0x65afb7c9, 0x446b84c6, 0x3adea4cb, 0x1258700d, 0x6ced5000,
+ 0x4355d981, 0x3de0f98c, 0x15662d4a, 0x6bd30d47, 0x56ee4b54, 0x285b6b59,
+ 0x00ddbf9f, 0x7e689f92, 0x51d01613, 0x2f65361e, 0x07e3e2d8, 0x7956c2d5,
+ 0x5892f1da, 0x2627d1d7, 0x0ea10511, 0x7014251c, 0x5facac9d, 0x21198c90,
+ 0x099f5856, 0x772a785b, 0x4c921c31, 0x32273c3c, 0x1aa1e8fa, 0x6414c8f7,
+ 0x4bac4176, 0x3519617b, 0x1d9fb5bd, 0x632a95b0, 0x42eea6bf, 0x3c5b86b2,
+ 0x14dd5274, 0x6a687279, 0x45d0fbf8, 0x3b65dbf5, 0x13e30f33, 0x6d562f3e,
+ 0x506b692d, 0x2ede4920, 0x06589de6, 0x78edbdeb, 0x5755346a, 0x29e01467,
+ 0x0166c0a1, 0x7fd3e0ac, 0x5e17d3a3, 0x20a2f3ae, 0x08242768, 0x76910765,
+ 0x59298ee4, 0x279caee9, 0x0f1a7a2f, 0x71af5a22, 0x7560f609, 0x0bd5d604,
+ 0x235302c2, 0x5de622cf, 0x725eab4e, 0x0ceb8b43, 0x246d5f85, 0x5ad87f88,
+ 0x7b1c4c87, 0x05a96c8a, 0x2d2fb84c, 0x539a9841, 0x7c2211c0, 0x029731cd,
+ 0x2a11e50b, 0x54a4c506, 0x69998315, 0x172ca318, 0x3faa77de, 0x411f57d3,
+ 0x6ea7de52, 0x1012fe5f, 0x38942a99, 0x46210a94, 0x67e5399b, 0x19501996,
+ 0x31d6cd50, 0x4f63ed5d, 0x60db64dc, 0x1e6e44d1, 0x36e89017, 0x485db01a,
+ 0x3f77c841, 0x41c2e84c, 0x69443c8a, 0x17f11c87, 0x38499506, 0x46fcb50b,
+ 0x6e7a61cd, 0x10cf41c0, 0x310b72cf, 0x4fbe52c2, 0x67388604, 0x198da609,
+ 0x36352f88, 0x48800f85, 0x6006db43, 0x1eb3fb4e, 0x238ebd5d, 0x5d3b9d50,
+ 0x75bd4996, 0x0b08699b, 0x24b0e01a, 0x5a05c017, 0x728314d1, 0x0c3634dc,
+ 0x2df207d3, 0x534727de, 0x7bc1f318, 0x0574d315, 0x2acc5a94, 0x54797a99,
+ 0x7cffae5f, 0x024a8e52, 0x06852279, 0x78300274, 0x50b6d6b2, 0x2e03f6bf,
+ 0x01bb7f3e, 0x7f0e5f33, 0x57888bf5, 0x293dabf8, 0x08f998f7, 0x764cb8fa,
+ 0x5eca6c3c, 0x207f4c31, 0x0fc7c5b0, 0x7172e5bd, 0x59f4317b, 0x27411176,
+ 0x1a7c5765, 0x64c97768, 0x4c4fa3ae, 0x32fa83a3, 0x1d420a22, 0x63f72a2f,
+ 0x4b71fee9, 0x35c4dee4, 0x1400edeb, 0x6ab5cde6, 0x42331920, 0x3c86392d,
+ 0x133eb0ac, 0x6d8b90a1, 0x450d4467, 0x3bb8646a
+};
-struct index {
+struct index_entry {
const unsigned char *ptr;
unsigned int val;
- struct index *next;
+ struct index_entry *next;
+};
+
+struct delta_index {
+ const void *src_buf;
+ unsigned long src_size;
+ unsigned int hash_mask;
+ struct index_entry *hash[0];
};
-static struct index ** delta_index(const unsigned char *buf,
- unsigned long bufsize,
- unsigned long trg_bufsize,
- unsigned int *hash_shift)
+struct delta_index * create_delta_index(const void *buf, unsigned long bufsize)
{
- unsigned int i, hsize, hshift, hlimit, entries, *hash_count;
- const unsigned char *data;
- struct index *entry, **hash;
+ unsigned int i, hsize, hmask, entries, prev_val, *hash_count;
+ const unsigned char *data, *buffer = buf;
+ struct delta_index *index;
+ struct index_entry *entry, **hash;
void *mem;
+ unsigned long memsize;
+
+ if (!buf || !bufsize)
+ return NULL;
- /* determine index hash size */
- entries = bufsize / BLK_SIZE;
+ /* Determine index hash size. Note that indexing skips the
+ first byte to allow for optimizing the rabin polynomial
+ initialization in create_delta(). */
+ entries = (bufsize - 1) / RABIN_WINDOW;
hsize = entries / 4;
for (i = 4; (1 << i) < hsize && i < 31; i++);
hsize = 1 << i;
- hshift = 32 - i;
- *hash_shift = hshift;
+ hmask = hsize - 1;
/* allocate lookup index */
- mem = malloc(hsize * sizeof(*hash) + entries * sizeof(*entry));
+ memsize = sizeof(*index) +
+ sizeof(*hash) * hsize +
+ sizeof(*entry) * entries;
+ mem = malloc(memsize);
if (!mem)
return NULL;
+ index = mem;
+ mem = index + 1;
hash = mem;
- entry = mem + hsize * sizeof(*hash);
+ mem = hash + hsize;
+ entry = mem;
+
+ index->src_buf = buf;
+ index->src_size = bufsize;
+ index->hash_mask = hmask;
memset(hash, 0, hsize * sizeof(*hash));
/* allocate an array to count hash entries */
hash_count = calloc(hsize, sizeof(*hash_count));
if (!hash_count) {
- free(hash);
+ free(index);
return NULL;
}
/* then populate the index */
- data = buf + entries * BLK_SIZE - BLK_SIZE;
- while (data >= buf) {
- unsigned int val = adler32(0, data, BLK_SIZE);
- i = HASH(val, hshift);
- entry->ptr = data;
- entry->val = val;
- entry->next = hash[i];
- hash[i] = entry++;
- hash_count[i]++;
- data -= BLK_SIZE;
- }
+ prev_val = ~0;
+ for (data = buffer + entries * RABIN_WINDOW - RABIN_WINDOW;
+ data >= buffer;
+ data -= RABIN_WINDOW) {
+ unsigned int val = 0;
+ for (i = 1; i <= RABIN_WINDOW; i++)
+ val = ((val << 8) | data[i]) ^ T[val >> RABIN_SHIFT];
+ if (val == prev_val) {
+ /* keep the lowest of consecutive identical blocks */
+ entry[-1].ptr = data + RABIN_WINDOW;
+ } else {
+ prev_val = val;
+ i = val & hmask;
+ entry->ptr = data + RABIN_WINDOW;
+ entry->val = val;
+ entry->next = hash[i];
+ hash[i] = entry++;
+ hash_count[i]++;
+ entries--;
+ }
+ }
/*
* Determine a limit on the number of entries in the same hash
@@ -91,27 +210,18 @@ static struct index ** delta_index(const unsigned char *buf,
* bucket that would bring us to O(m*n) computing costs (m and n
* corresponding to reference and target buffer sizes).
*
- * The more the target buffer is large, the more it is important to
- * have small entry lists for each hash buckets. With such a limit
- * the cost is bounded to something more like O(m+n).
- */
- hlimit = (1 << 26) / trg_bufsize;
- if (hlimit < 4*BLK_SIZE)
- hlimit = 4*BLK_SIZE;
-
- /*
- * Now make sure none of the hash buckets has more entries than
+ * Make sure none of the hash buckets has more entries than
* we're willing to test. Otherwise we cull the entry list
* uniformly to still preserve a good repartition across
* the reference buffer.
*/
for (i = 0; i < hsize; i++) {
- if (hash_count[i] < hlimit)
+ if (hash_count[i] < HASH_LIMIT)
continue;
entry = hash[i];
do {
- struct index *keep = entry;
- int skip = hash_count[i] / hlimit / 2;
+ struct index_entry *keep = entry;
+ int skip = hash_count[i] / HASH_LIMIT / 2;
do {
entry = entry->next;
} while(--skip && entry);
@@ -120,32 +230,35 @@ static struct index ** delta_index(const unsigned char *buf,
}
free(hash_count);
- return hash;
+ /* If we didn't use all hash entries, free the unused memory. */
+ if (entries)
+ index = realloc(index, memsize - entries * sizeof(*entry));
+
+ return index;
}
-/* provide the size of the copy opcode given the block offset and size */
-#define COPYOP_SIZE(o, s) \
- (!!(o & 0xff) + !!(o & 0xff00) + !!(o & 0xff0000) + !!(o & 0xff000000) + \
- !!(s & 0xff) + !!(s & 0xff00) + 1)
+void free_delta_index(struct delta_index *index)
+{
+ free(index);
+}
-/* the maximum size for any opcode */
-#define MAX_OP_SIZE COPYOP_SIZE(0xffffffff, 0xffffffff)
+/*
+ * The maximum size for any opcode sequence, including the initial header
+ * plus rabin window plus biggest copy.
+ */
+#define MAX_OP_SIZE (5 + 5 + 1 + RABIN_WINDOW + 7)
-void *diff_delta(const void *from_buf, unsigned long from_size,
- const void *to_buf, unsigned long to_size,
- unsigned long *delta_size,
- unsigned long max_size)
+void *
+create_delta(const struct delta_index *index,
+ const void *trg_buf, unsigned long trg_size,
+ unsigned long *delta_size, unsigned long max_size)
{
- unsigned int i, outpos, outsize, hash_shift;
+ unsigned int i, outpos, outsize, val;
int inscnt;
const unsigned char *ref_data, *ref_top, *data, *top;
unsigned char *out;
- struct index *entry, **hash;
- if (!from_size || !to_size)
- return NULL;
- hash = delta_index(from_buf, from_size, to_size, &hash_shift);
- if (!hash)
+ if (!trg_buf || !trg_size)
return NULL;
outpos = 0;
@@ -153,64 +266,66 @@ void *diff_delta(const void *from_buf, unsigned long from_size,
if (max_size && outsize >= max_size)
outsize = max_size + MAX_OP_SIZE + 1;
out = malloc(outsize);
- if (!out) {
- free(hash);
+ if (!out)
return NULL;
- }
-
- ref_data = from_buf;
- ref_top = from_buf + from_size;
- data = to_buf;
- top = to_buf + to_size;
/* store reference buffer size */
- out[outpos++] = from_size;
- from_size >>= 7;
- while (from_size) {
- out[outpos - 1] |= 0x80;
- out[outpos++] = from_size;
- from_size >>= 7;
+ i = index->src_size;
+ while (i >= 0x80) {
+ out[outpos++] = i | 0x80;
+ i >>= 7;
}
+ out[outpos++] = i;
/* store target buffer size */
- out[outpos++] = to_size;
- to_size >>= 7;
- while (to_size) {
- out[outpos - 1] |= 0x80;
- out[outpos++] = to_size;
- to_size >>= 7;
+ i = trg_size;
+ while (i >= 0x80) {
+ out[outpos++] = i | 0x80;
+ i >>= 7;
}
-
- inscnt = 0;
+ out[outpos++] = i;
+
+ ref_data = index->src_buf;
+ ref_top = ref_data + index->src_size;
+ data = trg_buf;
+ top = trg_buf + trg_size;
+
+ outpos++;
+ val = 0;
+ for (i = 0; i < RABIN_WINDOW && data < top; i++, data++) {
+ out[outpos++] = *data;
+ val = ((val << 8) | *data) ^ T[val >> RABIN_SHIFT];
+ }
+ inscnt = i;
while (data < top) {
unsigned int moff = 0, msize = 0;
- if (data + BLK_SIZE <= top) {
- unsigned int val = adler32(0, data, BLK_SIZE);
- i = HASH(val, hash_shift);
- for (entry = hash[i]; entry; entry = entry->next) {
- const unsigned char *ref = entry->ptr;
- const unsigned char *src = data;
- unsigned int ref_size = ref_top - ref;
- if (entry->val != val)
- continue;
- if (ref_size > top - src)
- ref_size = top - src;
- if (ref_size > 0x10000)
- ref_size = 0x10000;
- if (ref_size <= msize)
- break;
- while (ref_size-- && *src++ == *ref)
- ref++;
- if (msize < ref - entry->ptr) {
- /* this is our best match so far */
- msize = ref - entry->ptr;
- moff = entry->ptr - ref_data;
- }
+ struct index_entry *entry;
+ val ^= U[data[-RABIN_WINDOW]];
+ val = ((val << 8) | *data) ^ T[val >> RABIN_SHIFT];
+ i = val & index->hash_mask;
+ for (entry = index->hash[i]; entry; entry = entry->next) {
+ const unsigned char *ref = entry->ptr;
+ const unsigned char *src = data;
+ unsigned int ref_size = ref_top - ref;
+ if (entry->val != val)
+ continue;
+ if (ref_size > top - src)
+ ref_size = top - src;
+ if (ref_size > 0x10000)
+ ref_size = 0x10000;
+ if (ref_size <= msize)
+ break;
+ while (ref_size-- && *src++ == *ref)
+ ref++;
+ if (msize < ref - entry->ptr) {
+ /* this is our best match so far */
+ msize = ref - entry->ptr;
+ moff = entry->ptr - ref_data;
}
}
- if (!msize || msize < COPYOP_SIZE(moff, msize)) {
+ if (msize < 4) {
if (!inscnt)
outpos++;
out[outpos++] = *data++;
@@ -222,6 +337,20 @@ void *diff_delta(const void *from_buf, unsigned long from_size,
} else {
unsigned char *op;
+ if (msize >= RABIN_WINDOW) {
+ const unsigned char *sk;
+ sk = data + msize - RABIN_WINDOW;
+ val = 0;
+ for (i = 0; i < RABIN_WINDOW; i++)
+ val = ((val << 8) | *sk++) ^ T[val >> RABIN_SHIFT];
+ } else {
+ const unsigned char *sk = data + 1;
+ for (i = 1; i < msize; i++) {
+ val ^= U[sk[-RABIN_WINDOW]];
+ val = ((val << 8) | *sk++) ^ T[val >> RABIN_SHIFT];
+ }
+ }
+
if (inscnt) {
while (moff && ref_data[moff-1] == data[-1]) {
if (msize == 0x10000)
@@ -266,12 +395,10 @@ void *diff_delta(const void *from_buf, unsigned long from_size,
if (max_size && outsize >= max_size)
outsize = max_size + MAX_OP_SIZE + 1;
if (max_size && outpos > max_size)
- out = NULL;
- else
- out = realloc(out, outsize);
+ break;
+ out = realloc(out, outsize);
if (!out) {
free(tmp);
- free(hash);
return NULL;
}
}
@@ -280,7 +407,11 @@ void *diff_delta(const void *from_buf, unsigned long from_size,
if (inscnt)
out[outpos - inscnt - 1] = inscnt;
- free(hash);
+ if (max_size && outpos > max_size) {
+ free(out);
+ return NULL;
+ }
+
*delta_size = outpos;
return out;
}
diff --git a/diff.c b/diff.c
index 5315270601..7a7b839e56 100644
--- a/diff.c
+++ b/diff.c
@@ -8,6 +8,7 @@
#include "quote.h"
#include "diff.h"
#include "diffcore.h"
+#include "delta.h"
#include "xdiff-interface.h"
static int use_size_cache;
@@ -391,6 +392,90 @@ static void show_stats(struct diffstat_t* data)
total_files, adds, dels);
}
+static unsigned char *deflate_it(char *data,
+ unsigned long size,
+ unsigned long *result_size)
+{
+ int bound;
+ unsigned char *deflated;
+ z_stream stream;
+
+ memset(&stream, 0, sizeof(stream));
+ deflateInit(&stream, Z_BEST_COMPRESSION);
+ bound = deflateBound(&stream, size);
+ deflated = xmalloc(bound);
+ stream.next_out = deflated;
+ stream.avail_out = bound;
+
+ stream.next_in = (unsigned char *)data;
+ stream.avail_in = size;
+ while (deflate(&stream, Z_FINISH) == Z_OK)
+ ; /* nothing */
+ deflateEnd(&stream);
+ *result_size = stream.total_out;
+ return deflated;
+}
+
+static void emit_binary_diff(mmfile_t *one, mmfile_t *two)
+{
+ void *cp;
+ void *delta;
+ void *deflated;
+ void *data;
+ unsigned long orig_size;
+ unsigned long delta_size;
+ unsigned long deflate_size;
+ unsigned long data_size;
+
+ printf("GIT binary patch\n");
+ /* We could do deflated delta, or we could do just deflated two,
+ * whichever is smaller.
+ */
+ delta = NULL;
+ deflated = deflate_it(two->ptr, two->size, &deflate_size);
+ if (one->size && two->size) {
+ delta = diff_delta(one->ptr, one->size,
+ two->ptr, two->size,
+ &delta_size, deflate_size);
+ if (delta) {
+ void *to_free = delta;
+ orig_size = delta_size;
+ delta = deflate_it(delta, delta_size, &delta_size);
+ free(to_free);
+ }
+ }
+
+ if (delta && delta_size < deflate_size) {
+ printf("delta %lu\n", orig_size);
+ free(deflated);
+ data = delta;
+ data_size = delta_size;
+ }
+ else {
+ printf("literal %lu\n", two->size);
+ free(delta);
+ data = deflated;
+ data_size = deflate_size;
+ }
+
+ /* emit data encoded in base85 */
+ cp = data;
+ while (data_size) {
+ int bytes = (52 < data_size) ? 52 : data_size;
+ char line[70];
+ data_size -= bytes;
+ if (bytes <= 26)
+ line[0] = bytes + 'A' - 1;
+ else
+ line[0] = bytes - 26 + 'a' - 1;
+ encode_85(line + 1, cp, bytes);
+ cp += bytes;
+ puts(line);
+ }
+ printf("\n");
+ free(data);
+}
+
#define FIRST_FEW_BYTES 8000
static int mmfile_is_binary(mmfile_t *mf)
{
@@ -407,6 +492,7 @@ static void builtin_diff(const char *name_a,
struct diff_filespec *one,
struct diff_filespec *two,
const char *xfrm_msg,
+ struct diff_options *o,
int complete_rewrite)
{
mmfile_t mf1, mf2;
@@ -451,8 +537,17 @@ static void builtin_diff(const char *name_a,
if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0)
die("unable to read files to diff");
- if (mmfile_is_binary(&mf1) || mmfile_is_binary(&mf2))
- printf("Binary files %s and %s differ\n", lbl[0], lbl[1]);
+ if (mmfile_is_binary(&mf1) || mmfile_is_binary(&mf2)) {
+ /* Quite common confusing case */
+ if (mf1.size == mf2.size &&
+ !memcmp(mf1.ptr, mf2.ptr, mf1.size))
+ goto free_ab_and_return;
+ if (o->binary)
+ emit_binary_diff(&mf1, &mf2);
+ else
+ printf("Binary files %s and %s differ\n",
+ lbl[0], lbl[1]);
+ }
else {
/* Crazy xdl interfaces.. */
const char *diffopts = getenv("GIT_DIFF_OPTS");
@@ -928,6 +1023,7 @@ static void run_diff_cmd(const char *pgm,
struct diff_filespec *one,
struct diff_filespec *two,
const char *xfrm_msg,
+ struct diff_options *o,
int complete_rewrite)
{
if (pgm) {
@@ -937,7 +1033,7 @@ static void run_diff_cmd(const char *pgm,
}
if (one && two)
builtin_diff(name, other ? other : name,
- one, two, xfrm_msg, complete_rewrite);
+ one, two, xfrm_msg, o, complete_rewrite);
else
printf("* Unmerged path %s\n", name);
}
@@ -971,7 +1067,7 @@ static void run_diff(struct diff_filepair *p, struct diff_options *o)
if (DIFF_PAIR_UNMERGED(p)) {
/* unmerged */
- run_diff_cmd(pgm, p->one->path, NULL, NULL, NULL, NULL, 0);
+ run_diff_cmd(pgm, p->one->path, NULL, NULL, NULL, NULL, o, 0);
return;
}
@@ -1041,14 +1137,14 @@ static void run_diff(struct diff_filepair *p, struct diff_options *o)
* needs to be split into deletion and creation.
*/
struct diff_filespec *null = alloc_filespec(two->path);
- run_diff_cmd(NULL, name, other, one, null, xfrm_msg, 0);
+ run_diff_cmd(NULL, name, other, one, null, xfrm_msg, o, 0);
free(null);
null = alloc_filespec(one->path);
- run_diff_cmd(NULL, name, other, null, two, xfrm_msg, 0);
+ run_diff_cmd(NULL, name, other, null, two, xfrm_msg, o, 0);
free(null);
}
else
- run_diff_cmd(pgm, name, other, one, two, xfrm_msg,
+ run_diff_cmd(pgm, name, other, one, two, xfrm_msg, o,
complete_rewrite);
free(name_munged);
@@ -1147,6 +1243,10 @@ int diff_opt_parse(struct diff_options *options, const char **av, int ac)
options->rename_limit = strtoul(arg+2, NULL, 10);
else if (!strcmp(arg, "--full-index"))
options->full_index = 1;
+ else if (!strcmp(arg, "--binary")) {
+ options->output_format = DIFF_FORMAT_PATCH;
+ options->full_index = options->binary = 1;
+ }
else if (!strcmp(arg, "--name-only"))
options->output_format = DIFF_FORMAT_NAME;
else if (!strcmp(arg, "--name-status"))
diff --git a/diff.h b/diff.h
index b3b2c4dd28..d052608404 100644
--- a/diff.h
+++ b/diff.h
@@ -28,6 +28,7 @@ struct diff_options {
with_raw:1,
with_stat:1,
tree_in_recursive:1,
+ binary:1,
full_index:1,
silent_on_remove:1,
find_copies_harder:1;
diff --git a/git-clone.sh b/git-clone.sh
index b78524767c..227245c865 100755
--- a/git-clone.sh
+++ b/git-clone.sh
@@ -261,11 +261,7 @@ yes,yes)
;;
yes)
mkdir -p "$GIT_DIR/objects/info"
- {
- test -f "$repo/objects/info/alternates" &&
- cat "$repo/objects/info/alternates";
- echo "$repo/objects"
- } >>"$GIT_DIR/objects/info/alternates"
+ echo "$repo/objects" >> "$GIT_DIR/objects/info/alternates"
;;
esac
git-ls-remote "$repo" >"$GIT_DIR/CLONE_HEAD"
diff --git a/pack-objects.c b/pack-objects.c
index 53caed42dd..523a1c7da8 100644
--- a/pack-objects.c
+++ b/pack-objects.c
@@ -994,6 +994,7 @@ static int type_size_sort(const struct object_entry *a, const struct object_entr
struct unpacked {
struct object_entry *entry;
void *data;
+ struct delta_index *index;
};
/*
@@ -1004,61 +1005,56 @@ struct unpacked {
* more importantly, the bigger file is likely the more recent
* one.
*/
-static int try_delta(struct unpacked *cur, struct unpacked *old, unsigned max_depth)
+static int try_delta(struct unpacked *trg, struct unpacked *src,
+ struct delta_index *src_index, unsigned max_depth)
{
- struct object_entry *cur_entry = cur->entry;
- struct object_entry *old_entry = old->entry;
- unsigned long size, oldsize, delta_size, sizediff;
- long max_size;
+ struct object_entry *trg_entry = trg->entry;
+ struct object_entry *src_entry = src->entry;
+ unsigned long size, src_size, delta_size, sizediff, max_size;
void *delta_buf;
/* Don't bother doing diffs between different types */
- if (cur_entry->type != old_entry->type)
+ if (trg_entry->type != src_entry->type)
return -1;
/* We do not compute delta to *create* objects we are not
* going to pack.
*/
- if (cur_entry->preferred_base)
+ if (trg_entry->preferred_base)
return -1;
- /* If the current object is at pack edge, take the depth the
+ /*
+ * If the current object is at pack edge, take the depth the
* objects that depend on the current object into account --
* otherwise they would become too deep.
*/
- if (cur_entry->delta_child) {
- if (max_depth <= cur_entry->delta_limit)
+ if (trg_entry->delta_child) {
+ if (max_depth <= trg_entry->delta_limit)
return 0;
- max_depth -= cur_entry->delta_limit;
+ max_depth -= trg_entry->delta_limit;
}
-
- if (old_entry->depth >= max_depth)
+ if (src_entry->depth >= max_depth)
return 0;
- /*
- * NOTE!
- *
- * We always delta from the bigger to the smaller, since that's
- * more space-efficient (deletes don't have to say _what_ they
- * delete).
- */
- size = cur_entry->size;
+ /* Now some size filtering euristics. */
+ size = trg_entry->size;
max_size = size / 2 - 20;
- if (cur_entry->delta)
- max_size = cur_entry->delta_size-1;
- oldsize = old_entry->size;
- sizediff = oldsize < size ? size - oldsize : 0;
+ if (trg_entry->delta)
+ max_size = trg_entry->delta_size-1;
+ src_size = src_entry->size;
+ sizediff = src_size < size ? size - src_size : 0;
if (sizediff >= max_size)
return 0;
- delta_buf = diff_delta(old->data, oldsize,
- cur->data, size, &delta_size, max_size);
+
+ delta_buf = create_delta(src_index, trg->data, size, &delta_size, max_size);
if (!delta_buf)
return 0;
- cur_entry->delta = old_entry;
- cur_entry->delta_size = delta_size;
- cur_entry->depth = old_entry->depth + 1;
+
+ trg_entry->delta = src_entry;
+ trg_entry->delta_size = delta_size;
+ trg_entry->depth = src_entry->depth + 1;
free(delta_buf);
- return 0;
+ return 1;
}
static void progress_interval(int signum)
@@ -1108,12 +1104,17 @@ static void find_deltas(struct object_entry **list, int window, int depth)
if (entry->size < 50)
continue;
-
+ if (n->index)
+ free_delta_index(n->index);
free(n->data);
n->entry = entry;
n->data = read_sha1_file(entry->sha1, type, &size);
if (size != entry->size)
- die("object %s inconsistent object length (%lu vs %lu)", sha1_to_hex(entry->sha1), size, entry->size);
+ die("object %s inconsistent object length (%lu vs %lu)",
+ sha1_to_hex(entry->sha1), size, entry->size);
+ n->index = create_delta_index(n->data, size);
+ if (!n->index)
+ die("out of memory");
j = window;
while (--j > 0) {
@@ -1124,7 +1125,7 @@ static void find_deltas(struct object_entry **list, int window, int depth)
m = array + other_idx;
if (!m->entry)
break;
- if (try_delta(n, m, depth) < 0)
+ if (try_delta(n, m, m->index, depth) < 0)
break;
}
#if 0
@@ -1144,8 +1145,11 @@ static void find_deltas(struct object_entry **list, int window, int depth)
if (progress)
fputc('\n', stderr);
- for (i = 0; i < window; ++i)
+ for (i = 0; i < window; ++i) {
+ if (array[i].index)
+ free_delta_index(array[i].index);
free(array[i].data);
+ }
free(array);
}
diff --git a/patch-delta.c b/patch-delta.c
index affd4f673d..8f318ed8aa 100644
--- a/patch-delta.c
+++ b/patch-delta.c
@@ -13,7 +13,7 @@
#include <string.h>
#include "delta.h"
-void *patch_delta(void *src_buf, unsigned long src_size,
+void *patch_delta(const void *src_buf, unsigned long src_size,
const void *delta_buf, unsigned long delta_size,
unsigned long *dst_size)
{
diff --git a/read-cache.c b/read-cache.c
index f97f92d90a..a917ab0cfe 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -552,7 +552,7 @@ int read_cache(void)
active_nr = ntohl(hdr->hdr_entries);
active_alloc = alloc_nr(active_nr);
- active_cache = calloc(active_alloc, sizeof(struct cache_entry *));
+ active_cache = xcalloc(active_alloc, sizeof(struct cache_entry *));
offset = sizeof(*hdr);
for (i = 0; i < active_nr; i++) {
diff --git a/sha1_file.c b/sha1_file.c
index 5464828259..b62d0e3dcd 100644
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -217,6 +217,8 @@ char *sha1_pack_index_name(const unsigned char *sha1)
struct alternate_object_database *alt_odb_list;
static struct alternate_object_database **alt_odb_tail;
+static void read_info_alternates(const char * alternates, int depth);
+
/*
* Prepare alternate object database registry.
*
@@ -232,14 +234,85 @@ static struct alternate_object_database **alt_odb_tail;
* SHA1, an extra slash for the first level indirection, and the
* terminating NUL.
*/
-static void link_alt_odb_entries(const char *alt, const char *ep, int sep,
- const char *relative_base)
+static int link_alt_odb_entry(const char * entry, int len, const char * relative_base, int depth)
{
- const char *cp, *last;
- struct alternate_object_database *ent;
+ struct stat st;
const char *objdir = get_object_directory();
+ struct alternate_object_database *ent;
+ struct alternate_object_database *alt;
+ /* 43 = 40-byte + 2 '/' + terminating NUL */
+ int pfxlen = len;
+ int entlen = pfxlen + 43;
int base_len = -1;
+ if (*entry != '/' && relative_base) {
+ /* Relative alt-odb */
+ if (base_len < 0)
+ base_len = strlen(relative_base) + 1;
+ entlen += base_len;
+ pfxlen += base_len;
+ }
+ ent = xmalloc(sizeof(*ent) + entlen);
+
+ if (*entry != '/' && relative_base) {
+ memcpy(ent->base, relative_base, base_len - 1);
+ ent->base[base_len - 1] = '/';
+ memcpy(ent->base + base_len, entry, len);
+ }
+ else
+ memcpy(ent->base, entry, pfxlen);
+
+ ent->name = ent->base + pfxlen + 1;
+ ent->base[pfxlen + 3] = '/';
+ ent->base[pfxlen] = ent->base[entlen-1] = 0;
+
+ /* Detect cases where alternate disappeared */
+ if (stat(ent->base, &st) || !S_ISDIR(st.st_mode)) {
+ error("object directory %s does not exist; "
+ "check .git/objects/info/alternates.",
+ ent->base);
+ free(ent);
+ return -1;
+ }
+
+ /* Prevent the common mistake of listing the same
+ * thing twice, or object directory itself.
+ */
+ for (alt = alt_odb_list; alt; alt = alt->next) {
+ if (!memcmp(ent->base, alt->base, pfxlen)) {
+ free(ent);
+ return -1;
+ }
+ }
+ if (!memcmp(ent->base, objdir, pfxlen)) {
+ free(ent);
+ return -1;
+ }
+
+ /* add the alternate entry */
+ *alt_odb_tail = ent;
+ alt_odb_tail = &(ent->next);
+ ent->next = NULL;
+
+ /* recursively add alternates */
+ read_info_alternates(ent->base, depth + 1);
+
+ ent->base[pfxlen] = '/';
+
+ return 0;
+}
+
+static void link_alt_odb_entries(const char *alt, const char *ep, int sep,
+ const char *relative_base, int depth)
+{
+ const char *cp, *last;
+
+ if (depth > 5) {
+ error("%s: ignoring alternate object stores, nesting too deep.",
+ relative_base);
+ return;
+ }
+
last = alt;
while (last < ep) {
cp = last;
@@ -249,60 +322,15 @@ static void link_alt_odb_entries(const char *alt, const char *ep, int sep,
last = cp + 1;
continue;
}
- for ( ; cp < ep && *cp != sep; cp++)
- ;
+ while (cp < ep && *cp != sep)
+ cp++;
if (last != cp) {
- struct stat st;
- struct alternate_object_database *alt;
- /* 43 = 40-byte + 2 '/' + terminating NUL */
- int pfxlen = cp - last;
- int entlen = pfxlen + 43;
-
- if (*last != '/' && relative_base) {
- /* Relative alt-odb */
- if (base_len < 0)
- base_len = strlen(relative_base) + 1;
- entlen += base_len;
- pfxlen += base_len;
- }
- ent = xmalloc(sizeof(*ent) + entlen);
-
- if (*last != '/' && relative_base) {
- memcpy(ent->base, relative_base, base_len - 1);
- ent->base[base_len - 1] = '/';
- memcpy(ent->base + base_len,
- last, cp - last);
- }
- else
- memcpy(ent->base, last, pfxlen);
-
- ent->name = ent->base + pfxlen + 1;
- ent->base[pfxlen + 3] = '/';
- ent->base[pfxlen] = ent->base[entlen-1] = 0;
-
- /* Detect cases where alternate disappeared */
- if (stat(ent->base, &st) || !S_ISDIR(st.st_mode)) {
- error("object directory %s does not exist; "
- "check .git/objects/info/alternates.",
- ent->base);
- goto bad;
- }
- ent->base[pfxlen] = '/';
-
- /* Prevent the common mistake of listing the same
- * thing twice, or object directory itself.
- */
- for (alt = alt_odb_list; alt; alt = alt->next)
- if (!memcmp(ent->base, alt->base, pfxlen))
- goto bad;
- if (!memcmp(ent->base, objdir, pfxlen)) {
- bad:
- free(ent);
- }
- else {
- *alt_odb_tail = ent;
- alt_odb_tail = &(ent->next);
- ent->next = NULL;
+ if ((*last != '/') && depth) {
+ error("%s: ignoring relative alternate object store %s",
+ relative_base, last);
+ } else {
+ link_alt_odb_entry(last, cp - last,
+ relative_base, depth);
}
}
while (cp < ep && *cp == sep)
@@ -311,23 +339,14 @@ static void link_alt_odb_entries(const char *alt, const char *ep, int sep,
}
}
-void prepare_alt_odb(void)
+static void read_info_alternates(const char * relative_base, int depth)
{
- char path[PATH_MAX];
char *map;
- int fd;
struct stat st;
- char *alt;
-
- alt = getenv(ALTERNATE_DB_ENVIRONMENT);
- if (!alt) alt = "";
-
- if (alt_odb_tail)
- return;
- alt_odb_tail = &alt_odb_list;
- link_alt_odb_entries(alt, alt + strlen(alt), ':', NULL);
+ char path[PATH_MAX];
+ int fd;
- sprintf(path, "%s/info/alternates", get_object_directory());
+ sprintf(path, "%s/info/alternates", relative_base);
fd = open(path, O_RDONLY);
if (fd < 0)
return;
@@ -340,11 +359,26 @@ void prepare_alt_odb(void)
if (map == MAP_FAILED)
return;
- link_alt_odb_entries(map, map + st.st_size, '\n',
- get_object_directory());
+ link_alt_odb_entries(map, map + st.st_size, '\n', relative_base, depth);
+
munmap(map, st.st_size);
}
+void prepare_alt_odb(void)
+{
+ char *alt;
+
+ alt = getenv(ALTERNATE_DB_ENVIRONMENT);
+ if (!alt) alt = "";
+
+ if (alt_odb_tail)
+ return;
+ alt_odb_tail = &alt_odb_list;
+ link_alt_odb_entries(alt, alt + strlen(alt), ':', NULL, 0);
+
+ read_info_alternates(get_object_directory(), 0);
+}
+
static char *find_sha1_file(const unsigned char *sha1, struct stat *st)
{
char *name = sha1_file_name(sha1);
diff --git a/sha1_name.c b/sha1_name.c
index 345935bb2b..dc6835520c 100644
--- a/sha1_name.c
+++ b/sha1_name.c
@@ -458,17 +458,56 @@ int get_sha1(const char *name, unsigned char *sha1)
{
int ret;
unsigned unused;
+ int namelen = strlen(name);
+ const char *cp;
prepare_alt_odb();
- ret = get_sha1_1(name, strlen(name), sha1);
- if (ret < 0) {
- const char *cp = strchr(name, ':');
- if (cp) {
- unsigned char tree_sha1[20];
- if (!get_sha1_1(name, cp-name, tree_sha1))
- return get_tree_entry(tree_sha1, cp+1, sha1,
- &unused);
+ ret = get_sha1_1(name, namelen, sha1);
+ if (!ret)
+ return ret;
+ /* sha1:path --> object name of path in ent sha1
+ * :path -> object name of path in index
+ * :[0-3]:path -> object name of path in index at stage
+ */
+ if (name[0] == ':') {
+ int stage = 0;
+ struct cache_entry *ce;
+ int pos;
+ if (namelen < 3 ||
+ name[2] != ':' ||
+ name[1] < '0' || '3' < name[1])
+ cp = name + 1;
+ else {
+ stage = name[1] - '0';
+ cp = name + 3;
}
+ namelen = namelen - (cp - name);
+ if (!active_cache)
+ read_cache();
+ if (active_nr < 0)
+ return -1;
+ pos = cache_name_pos(cp, namelen);
+ if (pos < 0)
+ pos = -pos - 1;
+ while (pos < active_nr) {
+ ce = active_cache[pos];
+ if (ce_namelen(ce) != namelen ||
+ memcmp(ce->name, cp, namelen))
+ break;
+ if (ce_stage(ce) == stage) {
+ memcpy(sha1, ce->sha1, 20);
+ return 0;
+ }
+ pos++;
+ }
+ return -1;
+ }
+ cp = strchr(name, ':');
+ if (cp) {
+ unsigned char tree_sha1[20];
+ if (!get_sha1_1(name, cp-name, tree_sha1))
+ return get_tree_entry(tree_sha1, cp+1, sha1,
+ &unused);
}
return ret;
}
diff --git a/t/t2101-update-index-reupdate.sh b/t/t2101-update-index-reupdate.sh
new file mode 100755
index 0000000000..77aed8d800
--- /dev/null
+++ b/t/t2101-update-index-reupdate.sh
@@ -0,0 +1,82 @@
+#!/bin/sh
+#
+# Copyright (c) 2006 Junio C Hamano
+#
+
+test_description='git-update-index --again test.
+'
+
+. ./test-lib.sh
+
+test_expect_success 'update-index --add' \
+ 'echo hello world >file1 &&
+ echo goodbye people >file2 &&
+ git-update-index --add file1 file2 &&
+ git-ls-files -s >current &&
+ cmp current - <<\EOF
+100644 3b18e512dba79e4c8300dd08aeb37f8e728b8dad 0 file1
+100644 9db8893856a8a02eaa73470054b7c1c5a7c82e47 0 file2
+EOF'
+
+test_expect_success 'update-index --again' \
+ 'rm -f file1 &&
+ echo hello everybody >file2 &&
+ if git-update-index --again
+ then
+ echo should have refused to remove file1
+ exit 1
+ else
+ echo happy - failed as expected
+ fi &&
+ git-ls-files -s >current &&
+ cmp current - <<\EOF
+100644 3b18e512dba79e4c8300dd08aeb37f8e728b8dad 0 file1
+100644 9db8893856a8a02eaa73470054b7c1c5a7c82e47 0 file2
+EOF'
+
+test_expect_success 'update-index --remove --again' \
+ 'git-update-index --remove --again &&
+ git-ls-files -s >current &&
+ cmp current - <<\EOF
+100644 0f1ae1422c2bf43f117d3dbd715c988a9ed2103f 0 file2
+EOF'
+
+test_expect_success 'first commit' 'git-commit -m initial'
+
+test_expect_success 'update-index again' \
+ 'mkdir -p dir1 &&
+ echo hello world >dir1/file3 &&
+ echo goodbye people >file2 &&
+ git-update-index --add file2 dir1/file3 &&
+ echo hello everybody >file2
+ echo happy >dir1/file3 &&
+ git-update-index --again &&
+ git-ls-files -s >current &&
+ cmp current - <<\EOF
+100644 53ab446c3f4e42ce9bb728a0ccb283a101be4979 0 dir1/file3
+100644 0f1ae1422c2bf43f117d3dbd715c988a9ed2103f 0 file2
+EOF'
+
+test_expect_success 'update-index --update from subdir' \
+ 'echo not so happy >file2 &&
+ cd dir1 &&
+ cat ../file2 >file3 &&
+ git-update-index --again &&
+ cd .. &&
+ git-ls-files -s >current &&
+ cmp current - <<\EOF
+100644 d7fb3f695f06c759dbf3ab00046e7cc2da22d10f 0 dir1/file3
+100644 0f1ae1422c2bf43f117d3dbd715c988a9ed2103f 0 file2
+EOF'
+
+test_expect_success 'update-index --update with pathspec' \
+ 'echo very happy >file2 &&
+ cat file2 >dir1/file3 &&
+ git-update-index --again dir1/ &&
+ git-ls-files -s >current &&
+ cmp current - <<\EOF
+100644 594fb5bb1759d90998e2bf2a38261ae8e243c760 0 dir1/file3
+100644 0f1ae1422c2bf43f117d3dbd715c988a9ed2103f 0 file2
+EOF'
+
+test_done
diff --git a/t/t4012-diff-binary.sh b/t/t4012-diff-binary.sh
new file mode 100755
index 0000000000..bdd95c0d3d
--- /dev/null
+++ b/t/t4012-diff-binary.sh
@@ -0,0 +1,85 @@
+#!/bin/sh
+#
+# Copyright (c) 2006 Junio C Hamano
+#
+
+test_description='Binary diff and apply
+'
+
+. ./test-lib.sh
+
+test_expect_success 'prepare repository' \
+ 'echo AIT >a && echo BIT >b && echo CIT >c && echo DIT >d &&
+ git-update-index --add a b c d &&
+ echo git >a &&
+ cat ../test4012.png >b &&
+ echo git >c &&
+ cat b b >d'
+
+test_expect_success 'diff without --binary' \
+ 'git-diff | git-apply --stat --summary >current &&
+ cmp current - <<\EOF
+ a | 2 +-
+ b | Bin
+ c | 2 +-
+ d | Bin
+ 4 files changed, 2 insertions(+), 2 deletions(-)
+EOF'
+
+test_expect_success 'diff with --binary' \
+ 'git-diff --binary | git-apply --stat --summary >current &&
+ cmp current - <<\EOF
+ a | 2 +-
+ b | Bin
+ c | 2 +-
+ d | Bin
+ 4 files changed, 2 insertions(+), 2 deletions(-)
+EOF'
+
+# apply needs to be able to skip the binary material correctly
+# in order to report the line number of a corrupt patch.
+test_expect_success 'apply detecting corrupt patch correctly' \
+ 'git-diff | sed -e 's/-CIT/xCIT/' >broken &&
+ if git-apply --stat --summary broken 2>detected
+ then
+ echo unhappy - should have detected an error
+ (exit 1)
+ else
+ echo happy
+ fi &&
+ detected=`cat detected` &&
+ detected=`expr "$detected" : "fatal.*at line \\([0-9]*\\)\$"` &&
+ detected=`sed -ne "${detected}p" broken` &&
+ test "$detected" = xCIT'
+
+test_expect_success 'apply detecting corrupt patch correctly' \
+ 'git-diff --binary | sed -e 's/-CIT/xCIT/' >broken &&
+ if git-apply --stat --summary broken 2>detected
+ then
+ echo unhappy - should have detected an error
+ (exit 1)
+ else
+ echo happy
+ fi &&
+ detected=`cat detected` &&
+ detected=`expr "$detected" : "fatal.*at line \\([0-9]*\\)\$"` &&
+ detected=`sed -ne "${detected}p" broken` &&
+ test "$detected" = xCIT'
+
+test_expect_success 'initial commit' 'git-commit -a -m initial'
+
+# Try removal (b), modification (d), and creation (e).
+test_expect_success 'diff-index with --binary' \
+ 'echo AIT >a && mv b e && echo CIT >c && cat e >d &&
+ git-update-index --add --remove a b c d e &&
+ tree0=`git-write-tree` &&
+ git-diff --cached --binary >current &&
+ git-apply --stat --summary current'
+
+test_expect_success 'apply binary patch' \
+ 'git-reset --hard &&
+ git-apply --binary --index <current &&
+ tree1=`git-write-tree` &&
+ test "$tree1" = "$tree0"'
+
+test_done
diff --git a/t/t5710-info-alternate.sh b/t/t5710-info-alternate.sh
new file mode 100755
index 0000000000..097d037f5d
--- /dev/null
+++ b/t/t5710-info-alternate.sh
@@ -0,0 +1,105 @@
+#!/bin/sh
+#
+# Copyright (C) 2006 Martin Waitz <tali@admingilde.org>
+#
+
+test_description='test transitive info/alternate entries'
+. ./test-lib.sh
+
+# test that a file is not reachable in the current repository
+# but that it is after creating a info/alternate entry
+reachable_via() {
+ alternate="$1"
+ file="$2"
+ if git cat-file -e "HEAD:$file"; then return 1; fi
+ echo "$alternate" >> .git/objects/info/alternate
+ git cat-file -e "HEAD:$file"
+}
+
+test_valid_repo() {
+ git fsck-objects --full > fsck.log &&
+ test `wc -l < fsck.log` = 0
+}
+
+base_dir=`pwd`
+
+test_expect_success 'preparing first repository' \
+'test_create_repo A && cd A &&
+echo "Hello World" > file1 &&
+git add file1 &&
+git commit -m "Initial commit" file1 &&
+git repack -a -d &&
+git prune'
+
+cd "$base_dir"
+
+test_expect_success 'preparing second repository' \
+'git clone -l -s A B && cd B &&
+echo "foo bar" > file2 &&
+git add file2 &&
+git commit -m "next commit" file2 &&
+git repack -a -d -l &&
+git prune'
+
+cd "$base_dir"
+
+test_expect_success 'preparing third repository' \
+'git clone -l -s B C && cd C &&
+echo "Goodbye, cruel world" > file3 &&
+git add file3 &&
+git commit -m "one more" file3 &&
+git repack -a -d -l &&
+git prune'
+
+cd "$base_dir"
+
+test_expect_failure 'creating too deep nesting' \
+'git clone -l -s C D &&
+git clone -l -s D E &&
+git clone -l -s E F &&
+git clone -l -s F G &&
+test_valid_repo'
+
+cd "$base_dir"
+
+test_expect_success 'validity of third repository' \
+'cd C &&
+test_valid_repo'
+
+cd "$base_dir"
+
+test_expect_success 'validity of fourth repository' \
+'cd D &&
+test_valid_repo'
+
+cd "$base_dir"
+
+test_expect_success 'breaking of loops' \
+"echo '$base_dir/B/.git/objects' >> '$base_dir'/A/.git/objects/info/alternates&&
+cd C &&
+test_valid_repo"
+
+cd "$base_dir"
+
+test_expect_failure 'that info/alternates is neccessary' \
+'cd C &&
+rm .git/objects/info/alternates &&
+test_valid_repo'
+
+cd "$base_dir"
+
+test_expect_success 'that relative alternate is possible for current dir' \
+'cd C &&
+echo "../../../B/.git/objects" > .git/objects/info/alternates &&
+test_valid_repo'
+
+cd "$base_dir"
+
+test_expect_failure 'that relative alternate is only possible for current dir' \
+'cd D &&
+test_valid_repo'
+
+cd "$base_dir"
+
+test_done
+
diff --git a/t/test4012.png b/t/test4012.png
new file mode 100644
index 0000000000..7b181d15ce
--- /dev/null
+++ b/t/test4012.png
Binary files differ
diff --git a/update-index.c b/update-index.c
index 00cde70645..3d7e02db2c 100644
--- a/update-index.c
+++ b/update-index.c
@@ -476,7 +476,7 @@ static void read_index_info(int line_termination)
}
static const char update_index_usage[] =
-"git-update-index [-q] [--add] [--replace] [--remove] [--unmerged] [--refresh] [--really-refresh] [--cacheinfo] [--chmod=(+|-)x] [--assume-unchanged] [--info-only] [--force-remove] [--stdin] [--index-info] [--unresolve] [--ignore-missing] [-z] [--verbose] [--] <file>...";
+"git-update-index [-q] [--add] [--replace] [--remove] [--unmerged] [--refresh] [--really-refresh] [--cacheinfo] [--chmod=(+|-)x] [--assume-unchanged] [--info-only] [--force-remove] [--stdin] [--index-info] [--unresolve] [--again] [--ignore-missing] [-z] [--verbose] [--] <file>...";
static unsigned char head_sha1[20];
static unsigned char merge_head_sha1[20];
@@ -491,11 +491,13 @@ static struct cache_entry *read_one_ent(const char *which,
struct cache_entry *ce;
if (get_tree_entry(ent, path, sha1, &mode)) {
- error("%s: not in %s branch.", path, which);
+ if (which)
+ error("%s: not in %s branch.", path, which);
return NULL;
}
if (mode == S_IFDIR) {
- error("%s: not a blob in %s branch.", path, which);
+ if (which)
+ error("%s: not a blob in %s branch.", path, which);
return NULL;
}
size = cache_entry_size(namelen);
@@ -600,6 +602,49 @@ static int do_unresolve(int ac, const char **av,
return err;
}
+static int do_reupdate(int ac, const char **av,
+ const char *prefix, int prefix_length)
+{
+ /* Read HEAD and run update-index on paths that are
+ * merged and already different between index and HEAD.
+ */
+ int pos;
+ int has_head = 1;
+ const char **pathspec = get_pathspec(prefix, av + 1);
+
+ if (read_ref(git_path("HEAD"), head_sha1))
+ /* If there is no HEAD, that means it is an initial
+ * commit. Update everything in the index.
+ */
+ has_head = 0;
+ redo:
+ for (pos = 0; pos < active_nr; pos++) {
+ struct cache_entry *ce = active_cache[pos];
+ struct cache_entry *old = NULL;
+ int save_nr;
+
+ if (ce_stage(ce) || !ce_path_match(ce, pathspec))
+ continue;
+ if (has_head)
+ old = read_one_ent(NULL, head_sha1,
+ ce->name, ce_namelen(ce), 0);
+ if (old && ce->ce_mode == old->ce_mode &&
+ !memcmp(ce->sha1, old->sha1, 20)) {
+ free(old);
+ continue; /* unchanged */
+ }
+ /* Be careful. The working tree may not have the
+ * path anymore, in which case, under 'allow_remove',
+ * or worse yet 'allow_replace', active_nr may decrease.
+ */
+ save_nr = active_nr;
+ update_one(ce->name + prefix_length, prefix, prefix_length);
+ if (save_nr != active_nr)
+ goto redo;
+ }
+ return 0;
+}
+
int main(int argc, const char **argv)
{
int i, newfd, entries, has_errors = 0, line_termination = '\n';
@@ -717,6 +762,13 @@ int main(int argc, const char **argv)
active_cache_changed = 0;
goto finish;
}
+ if (!strcmp(path, "--again")) {
+ has_errors = do_reupdate(argc - i, argv + i,
+ prefix, prefix_length);
+ if (has_errors)
+ active_cache_changed = 0;
+ goto finish;
+ }
if (!strcmp(path, "--ignore-missing")) {
not_new = 1;
continue;
generated by cgit v1.2.3 (git 2.25.1) at 2024-12-11 15:43:52 +0000