git/rerere.c

832 lines
21 KiB
C
Raw Normal View History

#include "cache.h"
#include "lockfile.h"
#include "string-list.h"
#include "rerere.h"
#include "xdiff-interface.h"
#include "dir.h"
#include "resolve-undo.h"
#include "ll-merge.h"
#include "attr.h"
#include "pathspec.h"
#define RESOLVED 0
#define PUNTED 1
#define THREE_STAGED 2
void *RERERE_RESOLVED = &RERERE_RESOLVED;
/* if rerere_enabled == -1, fall back to detection of .git/rr-cache */
static int rerere_enabled = -1;
/* automatically update cleanly resolved paths to the index */
static int rerere_autoupdate;
static char *merge_rr_path;
const char *rerere_path(const char *hex, const char *file)
{
return git_path("rr-cache/%s/%s", hex, file);
}
static int has_rerere_resolution(const char *hex)
{
struct stat st;
return !stat(rerere_path(hex, "postimage"), &st);
}
/*
* $GIT_DIR/MERGE_RR file is a collection of records, each of which is
* "conflict ID", a HT and pathname, terminated with a NUL, and is
* used to keep track of the set of paths that "rerere" may need to
* work on (i.e. what is left by the previous invocation of "git
* rerere" during the current conflict resolution session).
*/
static void read_rr(struct string_list *rr)
{
struct strbuf buf = STRBUF_INIT;
FILE *in = fopen(merge_rr_path, "r");
if (!in)
return;
while (!strbuf_getwholeline(&buf, in, '\0')) {
char *path;
unsigned char sha1[20];
/* There has to be the hash, tab, path and then NUL */
if (buf.len < 42 || get_sha1_hex(buf.buf, sha1))
die("corrupt MERGE_RR");
if (buf.buf[40] != '\t')
die("corrupt MERGE_RR");
buf.buf[40] = '\0';
path = buf.buf + 41;
string_list_insert(rr, path)->util = xstrdup(buf.buf);
}
strbuf_release(&buf);
fclose(in);
}
static struct lock_file write_lock;
static int write_rr(struct string_list *rr, int out_fd)
{
int i;
for (i = 0; i < rr->nr; i++) {
struct strbuf buf = STRBUF_INIT;
assert(rr->items[i].util != RERERE_RESOLVED);
if (!rr->items[i].util)
continue;
strbuf_addf(&buf, "%s\t%s%c",
(char *)rr->items[i].util,
rr->items[i].string, 0);
if (write_in_full(out_fd, buf.buf, buf.len) != buf.len)
die("unable to write rerere record");
strbuf_release(&buf);
}
if (commit_lock_file(&write_lock) != 0)
die("unable to write rerere record");
return 0;
}
/*
* "rerere" interacts with conflicted file contents using this I/O
* abstraction. It reads a conflicted contents from one place via
* "getline()" method, and optionally can write it out after
* normalizing the conflicted hunks to the "output". Subclasses of
* rerere_io embed this structure at the beginning of their own
* rerere_io object.
*/
struct rerere_io {
int (*getline)(struct strbuf *, struct rerere_io *);
FILE *output;
int wrerror;
/* some more stuff */
};
static void ferr_write(const void *p, size_t count, FILE *fp, int *err)
{
if (!count || *err)
return;
if (fwrite(p, count, 1, fp) != 1)
*err = errno;
}
static inline void ferr_puts(const char *s, FILE *fp, int *err)
{
ferr_write(s, strlen(s), fp, err);
}
static void rerere_io_putstr(const char *str, struct rerere_io *io)
{
if (io->output)
ferr_puts(str, io->output, &io->wrerror);
}
/*
* Write a conflict marker to io->output (if defined).
*/
static void rerere_io_putconflict(int ch, int size, struct rerere_io *io)
{
char buf[64];
while (size) {
if (size <= sizeof(buf) - 2) {
memset(buf, ch, size);
buf[size] = '\n';
buf[size + 1] = '\0';
size = 0;
} else {
int sz = sizeof(buf) - 1;
/*
* Make sure we will not write everything out
* in this round by leaving at least 1 byte
* for the next round, giving the next round
* a chance to add the terminating LF. Yuck.
*/
if (size <= sz)
sz -= (sz - size) + 1;
memset(buf, ch, sz);
buf[sz] = '\0';
size -= sz;
}
rerere_io_putstr(buf, io);
}
}
static void rerere_io_putmem(const char *mem, size_t sz, struct rerere_io *io)
{
if (io->output)
ferr_write(mem, sz, io->output, &io->wrerror);
}
/*
* Subclass of rerere_io that reads from an on-disk file
*/
struct rerere_io_file {
struct rerere_io io;
FILE *input;
};
/*
* ... and its getline() method implementation
*/
static int rerere_file_getline(struct strbuf *sb, struct rerere_io *io_)
{
struct rerere_io_file *io = (struct rerere_io_file *)io_;
return strbuf_getwholeline(sb, io->input, '\n');
}
/*
* Require the exact number of conflict marker letters, no more, no
* less, followed by SP or any whitespace
* (including LF).
*/
static int is_cmarker(char *buf, int marker_char, int marker_size)
{
int want_sp;
/*
* The beginning of our version and the end of their version
* always are labeled like "<<<<< ours" or ">>>>> theirs",
* hence we set want_sp for them. Note that the version from
* the common ancestor in diff3-style output is not always
* labelled (e.g. "||||| common" is often seen but "|||||"
* alone is also valid), so we do not set want_sp.
*/
want_sp = (marker_char == '<') || (marker_char == '>');
while (marker_size--)
if (*buf++ != marker_char)
return 0;
if (want_sp && *buf != ' ')
return 0;
return isspace(*buf);
}
static int handle_path(unsigned char *sha1, struct rerere_io *io, int marker_size)
{
fix openssl headers conflicting with custom SHA1 implementations On ARM I have the following compilation errors: CC fast-import.o In file included from cache.h:8, from builtin.h:6, from fast-import.c:142: arm/sha1.h:14: error: conflicting types for 'SHA_CTX' /usr/include/openssl/sha.h:105: error: previous declaration of 'SHA_CTX' was here arm/sha1.h:16: error: conflicting types for 'SHA1_Init' /usr/include/openssl/sha.h:115: error: previous declaration of 'SHA1_Init' was here arm/sha1.h:17: error: conflicting types for 'SHA1_Update' /usr/include/openssl/sha.h:116: error: previous declaration of 'SHA1_Update' was here arm/sha1.h:18: error: conflicting types for 'SHA1_Final' /usr/include/openssl/sha.h:117: error: previous declaration of 'SHA1_Final' was here make: *** [fast-import.o] Error 1 This is because openssl header files are always included in git-compat-util.h since commit 684ec6c63c whenever NO_OPENSSL is not set, which somehow brings in <openssl/sha1.h> clashing with the custom ARM version. Compilation of git is probably broken on PPC too for the same reason. Turns out that the only file requiring openssl/ssl.h and openssl/err.h is imap-send.c. But only moving those problematic includes there doesn't solve the issue as it also includes cache.h which brings in the conflicting local SHA1 header file. As suggested by Jeff King, the best solution is to rename our references to SHA1 functions and structure to something git specific, and define those according to the implementation used. Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Shawn O. Pearce <spearce@spearce.org>
2008-10-02 02:05:20 +08:00
git_SHA_CTX ctx;
int hunk_no = 0;
enum {
RR_CONTEXT = 0, RR_SIDE_1, RR_SIDE_2, RR_ORIGINAL
} hunk = RR_CONTEXT;
struct strbuf one = STRBUF_INIT, two = STRBUF_INIT;
struct strbuf buf = STRBUF_INIT;
if (sha1)
fix openssl headers conflicting with custom SHA1 implementations On ARM I have the following compilation errors: CC fast-import.o In file included from cache.h:8, from builtin.h:6, from fast-import.c:142: arm/sha1.h:14: error: conflicting types for 'SHA_CTX' /usr/include/openssl/sha.h:105: error: previous declaration of 'SHA_CTX' was here arm/sha1.h:16: error: conflicting types for 'SHA1_Init' /usr/include/openssl/sha.h:115: error: previous declaration of 'SHA1_Init' was here arm/sha1.h:17: error: conflicting types for 'SHA1_Update' /usr/include/openssl/sha.h:116: error: previous declaration of 'SHA1_Update' was here arm/sha1.h:18: error: conflicting types for 'SHA1_Final' /usr/include/openssl/sha.h:117: error: previous declaration of 'SHA1_Final' was here make: *** [fast-import.o] Error 1 This is because openssl header files are always included in git-compat-util.h since commit 684ec6c63c whenever NO_OPENSSL is not set, which somehow brings in <openssl/sha1.h> clashing with the custom ARM version. Compilation of git is probably broken on PPC too for the same reason. Turns out that the only file requiring openssl/ssl.h and openssl/err.h is imap-send.c. But only moving those problematic includes there doesn't solve the issue as it also includes cache.h which brings in the conflicting local SHA1 header file. As suggested by Jeff King, the best solution is to rename our references to SHA1 functions and structure to something git specific, and define those according to the implementation used. Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Shawn O. Pearce <spearce@spearce.org>
2008-10-02 02:05:20 +08:00
git_SHA1_Init(&ctx);
while (!io->getline(&buf, io)) {
if (is_cmarker(buf.buf, '<', marker_size)) {
if (hunk != RR_CONTEXT)
goto bad;
hunk = RR_SIDE_1;
} else if (is_cmarker(buf.buf, '|', marker_size)) {
if (hunk != RR_SIDE_1)
goto bad;
hunk = RR_ORIGINAL;
} else if (is_cmarker(buf.buf, '=', marker_size)) {
if (hunk != RR_SIDE_1 && hunk != RR_ORIGINAL)
goto bad;
hunk = RR_SIDE_2;
} else if (is_cmarker(buf.buf, '>', marker_size)) {
if (hunk != RR_SIDE_2)
goto bad;
if (strbuf_cmp(&one, &two) > 0)
strbuf_swap(&one, &two);
hunk_no++;
hunk = RR_CONTEXT;
rerere_io_putconflict('<', marker_size, io);
rerere_io_putmem(one.buf, one.len, io);
rerere_io_putconflict('=', marker_size, io);
rerere_io_putmem(two.buf, two.len, io);
rerere_io_putconflict('>', marker_size, io);
if (sha1) {
fix openssl headers conflicting with custom SHA1 implementations On ARM I have the following compilation errors: CC fast-import.o In file included from cache.h:8, from builtin.h:6, from fast-import.c:142: arm/sha1.h:14: error: conflicting types for 'SHA_CTX' /usr/include/openssl/sha.h:105: error: previous declaration of 'SHA_CTX' was here arm/sha1.h:16: error: conflicting types for 'SHA1_Init' /usr/include/openssl/sha.h:115: error: previous declaration of 'SHA1_Init' was here arm/sha1.h:17: error: conflicting types for 'SHA1_Update' /usr/include/openssl/sha.h:116: error: previous declaration of 'SHA1_Update' was here arm/sha1.h:18: error: conflicting types for 'SHA1_Final' /usr/include/openssl/sha.h:117: error: previous declaration of 'SHA1_Final' was here make: *** [fast-import.o] Error 1 This is because openssl header files are always included in git-compat-util.h since commit 684ec6c63c whenever NO_OPENSSL is not set, which somehow brings in <openssl/sha1.h> clashing with the custom ARM version. Compilation of git is probably broken on PPC too for the same reason. Turns out that the only file requiring openssl/ssl.h and openssl/err.h is imap-send.c. But only moving those problematic includes there doesn't solve the issue as it also includes cache.h which brings in the conflicting local SHA1 header file. As suggested by Jeff King, the best solution is to rename our references to SHA1 functions and structure to something git specific, and define those according to the implementation used. Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Shawn O. Pearce <spearce@spearce.org>
2008-10-02 02:05:20 +08:00
git_SHA1_Update(&ctx, one.buf ? one.buf : "",
one.len + 1);
fix openssl headers conflicting with custom SHA1 implementations On ARM I have the following compilation errors: CC fast-import.o In file included from cache.h:8, from builtin.h:6, from fast-import.c:142: arm/sha1.h:14: error: conflicting types for 'SHA_CTX' /usr/include/openssl/sha.h:105: error: previous declaration of 'SHA_CTX' was here arm/sha1.h:16: error: conflicting types for 'SHA1_Init' /usr/include/openssl/sha.h:115: error: previous declaration of 'SHA1_Init' was here arm/sha1.h:17: error: conflicting types for 'SHA1_Update' /usr/include/openssl/sha.h:116: error: previous declaration of 'SHA1_Update' was here arm/sha1.h:18: error: conflicting types for 'SHA1_Final' /usr/include/openssl/sha.h:117: error: previous declaration of 'SHA1_Final' was here make: *** [fast-import.o] Error 1 This is because openssl header files are always included in git-compat-util.h since commit 684ec6c63c whenever NO_OPENSSL is not set, which somehow brings in <openssl/sha1.h> clashing with the custom ARM version. Compilation of git is probably broken on PPC too for the same reason. Turns out that the only file requiring openssl/ssl.h and openssl/err.h is imap-send.c. But only moving those problematic includes there doesn't solve the issue as it also includes cache.h which brings in the conflicting local SHA1 header file. As suggested by Jeff King, the best solution is to rename our references to SHA1 functions and structure to something git specific, and define those according to the implementation used. Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Shawn O. Pearce <spearce@spearce.org>
2008-10-02 02:05:20 +08:00
git_SHA1_Update(&ctx, two.buf ? two.buf : "",
two.len + 1);
}
strbuf_reset(&one);
strbuf_reset(&two);
} else if (hunk == RR_SIDE_1)
strbuf_addbuf(&one, &buf);
else if (hunk == RR_ORIGINAL)
; /* discard */
else if (hunk == RR_SIDE_2)
strbuf_addbuf(&two, &buf);
else
rerere_io_putstr(buf.buf, io);
continue;
bad:
hunk = 99; /* force error exit */
break;
}
strbuf_release(&one);
strbuf_release(&two);
strbuf_release(&buf);
if (sha1)
fix openssl headers conflicting with custom SHA1 implementations On ARM I have the following compilation errors: CC fast-import.o In file included from cache.h:8, from builtin.h:6, from fast-import.c:142: arm/sha1.h:14: error: conflicting types for 'SHA_CTX' /usr/include/openssl/sha.h:105: error: previous declaration of 'SHA_CTX' was here arm/sha1.h:16: error: conflicting types for 'SHA1_Init' /usr/include/openssl/sha.h:115: error: previous declaration of 'SHA1_Init' was here arm/sha1.h:17: error: conflicting types for 'SHA1_Update' /usr/include/openssl/sha.h:116: error: previous declaration of 'SHA1_Update' was here arm/sha1.h:18: error: conflicting types for 'SHA1_Final' /usr/include/openssl/sha.h:117: error: previous declaration of 'SHA1_Final' was here make: *** [fast-import.o] Error 1 This is because openssl header files are always included in git-compat-util.h since commit 684ec6c63c whenever NO_OPENSSL is not set, which somehow brings in <openssl/sha1.h> clashing with the custom ARM version. Compilation of git is probably broken on PPC too for the same reason. Turns out that the only file requiring openssl/ssl.h and openssl/err.h is imap-send.c. But only moving those problematic includes there doesn't solve the issue as it also includes cache.h which brings in the conflicting local SHA1 header file. As suggested by Jeff King, the best solution is to rename our references to SHA1 functions and structure to something git specific, and define those according to the implementation used. Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Shawn O. Pearce <spearce@spearce.org>
2008-10-02 02:05:20 +08:00
git_SHA1_Final(sha1, &ctx);
if (hunk != RR_CONTEXT)
return -1;
return hunk_no;
}
static int handle_file(const char *path, unsigned char *sha1, const char *output)
{
int hunk_no = 0;
struct rerere_io_file io;
int marker_size = ll_merge_marker_size(path);
memset(&io, 0, sizeof(io));
io.io.getline = rerere_file_getline;
io.input = fopen(path, "r");
io.io.wrerror = 0;
if (!io.input)
return error("Could not open %s", path);
if (output) {
io.io.output = fopen(output, "w");
if (!io.io.output) {
fclose(io.input);
return error("Could not write %s", output);
}
}
hunk_no = handle_path(sha1, (struct rerere_io *)&io, marker_size);
fclose(io.input);
if (io.io.wrerror)
error("There were errors while writing %s (%s)",
path, strerror(io.io.wrerror));
if (io.io.output && fclose(io.io.output))
io.io.wrerror = error("Failed to flush %s: %s",
path, strerror(errno));
if (hunk_no < 0) {
if (output)
unlink_or_warn(output);
return error("Could not parse conflict hunks in %s", path);
}
if (io.io.wrerror)
return -1;
return hunk_no;
}
/*
* Subclass of rerere_io that reads from an in-core buffer that is a
* strbuf
*/
struct rerere_io_mem {
struct rerere_io io;
struct strbuf input;
};
/*
* ... and its getline() method implementation
*/
static int rerere_mem_getline(struct strbuf *sb, struct rerere_io *io_)
{
struct rerere_io_mem *io = (struct rerere_io_mem *)io_;
char *ep;
size_t len;
strbuf_release(sb);
if (!io->input.len)
return -1;
ep = memchr(io->input.buf, '\n', io->input.len);
if (!ep)
ep = io->input.buf + io->input.len;
else if (*ep == '\n')
ep++;
len = ep - io->input.buf;
strbuf_add(sb, io->input.buf, len);
strbuf_remove(&io->input, 0, len);
return 0;
}
static int handle_cache(const char *path, unsigned char *sha1, const char *output)
{
mmfile_t mmfile[3] = {{NULL}};
mmbuffer_t result = {NULL, 0};
Convert "struct cache_entry *" to "const ..." wherever possible I attempted to make index_state->cache[] a "const struct cache_entry **" to find out how existing entries in index are modified and where. The question I have is what do we do if we really need to keep track of on-disk changes in the index. The result is - diff-lib.c: setting CE_UPTODATE - name-hash.c: setting CE_HASHED - preload-index.c, read-cache.c, unpack-trees.c and builtin/update-index: obvious - entry.c: write_entry() may refresh the checked out entry via fill_stat_cache_info(). This causes "non-const struct cache_entry *" in builtin/apply.c, builtin/checkout-index.c and builtin/checkout.c - builtin/ls-files.c: --with-tree changes stagemask and may set CE_UPDATE Of these, write_entry() and its call sites are probably most interesting because it modifies on-disk info. But this is stat info and can be retrieved via refresh, at least for porcelain commands. Other just uses ce_flags for local purposes. So, keeping track of "dirty" entries is just a matter of setting a flag in index modification functions exposed by read-cache.c. Except unpack-trees, the rest of the code base does not do anything funny behind read-cache's back. The actual patch is less valueable than the summary above. But if anyone wants to re-identify the above sites. Applying this patch, then this: diff --git a/cache.h b/cache.h index 430d021..1692891 100644 --- a/cache.h +++ b/cache.h @@ -267,7 +267,7 @@ static inline unsigned int canon_mode(unsigned int mode) #define cache_entry_size(len) (offsetof(struct cache_entry,name) + (len) + 1) struct index_state { - struct cache_entry **cache; + const struct cache_entry **cache; unsigned int version; unsigned int cache_nr, cache_alloc, cache_changed; struct string_list *resolve_undo; will help quickly identify them without bogus warnings. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-07-09 23:29:00 +08:00
const struct cache_entry *ce;
int pos, len, i, hunk_no;
struct rerere_io_mem io;
int marker_size = ll_merge_marker_size(path);
/*
* Reproduce the conflicted merge in-core
*/
len = strlen(path);
pos = cache_name_pos(path, len);
if (0 <= pos)
return -1;
pos = -pos - 1;
while (pos < active_nr) {
enum object_type type;
unsigned long size;
ce = active_cache[pos++];
if (ce_namelen(ce) != len || memcmp(ce->name, path, len))
break;
i = ce_stage(ce) - 1;
if (!mmfile[i].ptr) {
mmfile[i].ptr = read_sha1_file(ce->sha1, &type, &size);
mmfile[i].size = size;
}
}
for (i = 0; i < 3; i++)
if (!mmfile[i].ptr && !mmfile[i].size)
mmfile[i].ptr = xstrdup("");
/*
* NEEDSWORK: handle conflicts from merges with
* merge.renormalize set, too
*/
ll_merge(&result, path, &mmfile[0], NULL,
&mmfile[1], "ours",
&mmfile[2], "theirs", NULL);
for (i = 0; i < 3; i++)
free(mmfile[i].ptr);
memset(&io, 0, sizeof(io));
io.io.getline = rerere_mem_getline;
if (output)
io.io.output = fopen(output, "w");
else
io.io.output = NULL;
strbuf_init(&io.input, 0);
strbuf_attach(&io.input, result.ptr, result.size, result.size);
hunk_no = handle_path(sha1, (struct rerere_io *)&io, marker_size);
strbuf_release(&io.input);
if (io.io.output)
fclose(io.io.output);
return hunk_no;
}
/*
* Look at a cache entry at "i" and see if it is not conflicting,
* conflicting and we are willing to handle, or conflicting and
* we are unable to handle, and return the determination in *type.
* Return the cache index to be looked at next, by skipping the
* stages we have already looked at in this invocation of this
* function.
*/
static int check_one_conflict(int i, int *type)
{
Convert "struct cache_entry *" to "const ..." wherever possible I attempted to make index_state->cache[] a "const struct cache_entry **" to find out how existing entries in index are modified and where. The question I have is what do we do if we really need to keep track of on-disk changes in the index. The result is - diff-lib.c: setting CE_UPTODATE - name-hash.c: setting CE_HASHED - preload-index.c, read-cache.c, unpack-trees.c and builtin/update-index: obvious - entry.c: write_entry() may refresh the checked out entry via fill_stat_cache_info(). This causes "non-const struct cache_entry *" in builtin/apply.c, builtin/checkout-index.c and builtin/checkout.c - builtin/ls-files.c: --with-tree changes stagemask and may set CE_UPDATE Of these, write_entry() and its call sites are probably most interesting because it modifies on-disk info. But this is stat info and can be retrieved via refresh, at least for porcelain commands. Other just uses ce_flags for local purposes. So, keeping track of "dirty" entries is just a matter of setting a flag in index modification functions exposed by read-cache.c. Except unpack-trees, the rest of the code base does not do anything funny behind read-cache's back. The actual patch is less valueable than the summary above. But if anyone wants to re-identify the above sites. Applying this patch, then this: diff --git a/cache.h b/cache.h index 430d021..1692891 100644 --- a/cache.h +++ b/cache.h @@ -267,7 +267,7 @@ static inline unsigned int canon_mode(unsigned int mode) #define cache_entry_size(len) (offsetof(struct cache_entry,name) + (len) + 1) struct index_state { - struct cache_entry **cache; + const struct cache_entry **cache; unsigned int version; unsigned int cache_nr, cache_alloc, cache_changed; struct string_list *resolve_undo; will help quickly identify them without bogus warnings. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-07-09 23:29:00 +08:00
const struct cache_entry *e = active_cache[i];
if (!ce_stage(e)) {
*type = RESOLVED;
return i + 1;
}
*type = PUNTED;
while (ce_stage(active_cache[i]) == 1)
i++;
/* Only handle regular files with both stages #2 and #3 */
if (i + 1 < active_nr) {
Convert "struct cache_entry *" to "const ..." wherever possible I attempted to make index_state->cache[] a "const struct cache_entry **" to find out how existing entries in index are modified and where. The question I have is what do we do if we really need to keep track of on-disk changes in the index. The result is - diff-lib.c: setting CE_UPTODATE - name-hash.c: setting CE_HASHED - preload-index.c, read-cache.c, unpack-trees.c and builtin/update-index: obvious - entry.c: write_entry() may refresh the checked out entry via fill_stat_cache_info(). This causes "non-const struct cache_entry *" in builtin/apply.c, builtin/checkout-index.c and builtin/checkout.c - builtin/ls-files.c: --with-tree changes stagemask and may set CE_UPDATE Of these, write_entry() and its call sites are probably most interesting because it modifies on-disk info. But this is stat info and can be retrieved via refresh, at least for porcelain commands. Other just uses ce_flags for local purposes. So, keeping track of "dirty" entries is just a matter of setting a flag in index modification functions exposed by read-cache.c. Except unpack-trees, the rest of the code base does not do anything funny behind read-cache's back. The actual patch is less valueable than the summary above. But if anyone wants to re-identify the above sites. Applying this patch, then this: diff --git a/cache.h b/cache.h index 430d021..1692891 100644 --- a/cache.h +++ b/cache.h @@ -267,7 +267,7 @@ static inline unsigned int canon_mode(unsigned int mode) #define cache_entry_size(len) (offsetof(struct cache_entry,name) + (len) + 1) struct index_state { - struct cache_entry **cache; + const struct cache_entry **cache; unsigned int version; unsigned int cache_nr, cache_alloc, cache_changed; struct string_list *resolve_undo; will help quickly identify them without bogus warnings. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-07-09 23:29:00 +08:00
const struct cache_entry *e2 = active_cache[i];
const struct cache_entry *e3 = active_cache[i + 1];
if (ce_stage(e2) == 2 &&
ce_stage(e3) == 3 &&
ce_same_name(e, e3) &&
S_ISREG(e2->ce_mode) &&
S_ISREG(e3->ce_mode))
*type = THREE_STAGED;
}
/* Skip the entries with the same name */
while (i < active_nr && ce_same_name(e, active_cache[i]))
i++;
return i;
}
/*
* Scan the index and find paths that have conflicts that rerere can
* handle, i.e. the ones that has both stages #2 and #3.
*
* NEEDSWORK: we do not record or replay a previous "resolve by
* deletion" for a delete-modify conflict, as that is inherently risky
* without knowing what modification is being discarded. The only
* safe case, i.e. both side doing the deletion and modification that
* are identical to the previous round, might want to be handled,
* though.
*/
static int find_conflict(struct string_list *conflict)
{
int i;
if (read_cache() < 0)
return error("Could not read index");
for (i = 0; i < active_nr;) {
int conflict_type;
Convert "struct cache_entry *" to "const ..." wherever possible I attempted to make index_state->cache[] a "const struct cache_entry **" to find out how existing entries in index are modified and where. The question I have is what do we do if we really need to keep track of on-disk changes in the index. The result is - diff-lib.c: setting CE_UPTODATE - name-hash.c: setting CE_HASHED - preload-index.c, read-cache.c, unpack-trees.c and builtin/update-index: obvious - entry.c: write_entry() may refresh the checked out entry via fill_stat_cache_info(). This causes "non-const struct cache_entry *" in builtin/apply.c, builtin/checkout-index.c and builtin/checkout.c - builtin/ls-files.c: --with-tree changes stagemask and may set CE_UPDATE Of these, write_entry() and its call sites are probably most interesting because it modifies on-disk info. But this is stat info and can be retrieved via refresh, at least for porcelain commands. Other just uses ce_flags for local purposes. So, keeping track of "dirty" entries is just a matter of setting a flag in index modification functions exposed by read-cache.c. Except unpack-trees, the rest of the code base does not do anything funny behind read-cache's back. The actual patch is less valueable than the summary above. But if anyone wants to re-identify the above sites. Applying this patch, then this: diff --git a/cache.h b/cache.h index 430d021..1692891 100644 --- a/cache.h +++ b/cache.h @@ -267,7 +267,7 @@ static inline unsigned int canon_mode(unsigned int mode) #define cache_entry_size(len) (offsetof(struct cache_entry,name) + (len) + 1) struct index_state { - struct cache_entry **cache; + const struct cache_entry **cache; unsigned int version; unsigned int cache_nr, cache_alloc, cache_changed; struct string_list *resolve_undo; will help quickly identify them without bogus warnings. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-07-09 23:29:00 +08:00
const struct cache_entry *e = active_cache[i];
i = check_one_conflict(i, &conflict_type);
if (conflict_type == THREE_STAGED)
string_list_insert(conflict, (const char *)e->name);
}
return 0;
}
/*
* The merge_rr list is meant to hold outstanding conflicted paths
* that rerere could handle. Abuse the list by adding other types of
* entries to allow the caller to show "rerere remaining".
*
* - Conflicted paths that rerere does not handle are added
* - Conflicted paths that have been resolved are marked as such
* by storing RERERE_RESOLVED to .util field (where conflict ID
* is expected to be stored).
*
* Do *not* write MERGE_RR file out after calling this function.
*
* NEEDSWORK: we may want to fix the caller that implements "rerere
* remaining" to do this without abusing merge_rr.
*/
int rerere_remaining(struct string_list *merge_rr)
{
int i;
if (read_cache() < 0)
return error("Could not read index");
for (i = 0; i < active_nr;) {
int conflict_type;
Convert "struct cache_entry *" to "const ..." wherever possible I attempted to make index_state->cache[] a "const struct cache_entry **" to find out how existing entries in index are modified and where. The question I have is what do we do if we really need to keep track of on-disk changes in the index. The result is - diff-lib.c: setting CE_UPTODATE - name-hash.c: setting CE_HASHED - preload-index.c, read-cache.c, unpack-trees.c and builtin/update-index: obvious - entry.c: write_entry() may refresh the checked out entry via fill_stat_cache_info(). This causes "non-const struct cache_entry *" in builtin/apply.c, builtin/checkout-index.c and builtin/checkout.c - builtin/ls-files.c: --with-tree changes stagemask and may set CE_UPDATE Of these, write_entry() and its call sites are probably most interesting because it modifies on-disk info. But this is stat info and can be retrieved via refresh, at least for porcelain commands. Other just uses ce_flags for local purposes. So, keeping track of "dirty" entries is just a matter of setting a flag in index modification functions exposed by read-cache.c. Except unpack-trees, the rest of the code base does not do anything funny behind read-cache's back. The actual patch is less valueable than the summary above. But if anyone wants to re-identify the above sites. Applying this patch, then this: diff --git a/cache.h b/cache.h index 430d021..1692891 100644 --- a/cache.h +++ b/cache.h @@ -267,7 +267,7 @@ static inline unsigned int canon_mode(unsigned int mode) #define cache_entry_size(len) (offsetof(struct cache_entry,name) + (len) + 1) struct index_state { - struct cache_entry **cache; + const struct cache_entry **cache; unsigned int version; unsigned int cache_nr, cache_alloc, cache_changed; struct string_list *resolve_undo; will help quickly identify them without bogus warnings. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-07-09 23:29:00 +08:00
const struct cache_entry *e = active_cache[i];
i = check_one_conflict(i, &conflict_type);
if (conflict_type == PUNTED)
string_list_insert(merge_rr, (const char *)e->name);
else if (conflict_type == RESOLVED) {
struct string_list_item *it;
it = string_list_lookup(merge_rr, (const char *)e->name);
if (it != NULL) {
free(it->util);
it->util = RERERE_RESOLVED;
}
}
}
return 0;
}
static int merge(const char *name, const char *path)
{
int ret;
mmfile_t cur = {NULL, 0}, base = {NULL, 0}, other = {NULL, 0};
mmbuffer_t result = {NULL, 0};
if (handle_file(path, NULL, rerere_path(name, "thisimage")) < 0)
return 1;
if (read_mmfile(&cur, rerere_path(name, "thisimage")) ||
read_mmfile(&base, rerere_path(name, "preimage")) ||
read_mmfile(&other, rerere_path(name, "postimage"))) {
ret = 1;
goto out;
}
ret = ll_merge(&result, path, &base, NULL, &cur, "", &other, "", NULL);
if (!ret) {
FILE *f;
if (utime(rerere_path(name, "postimage"), NULL) < 0)
warning("failed utime() on %s: %s",
rerere_path(name, "postimage"),
strerror(errno));
f = fopen(path, "w");
if (!f)
return error("Could not open %s: %s", path,
strerror(errno));
if (fwrite(result.ptr, result.size, 1, f) != 1)
error("Could not write %s: %s", path, strerror(errno));
if (fclose(f))
return error("Writing %s failed: %s", path,
strerror(errno));
}
out:
free(cur.ptr);
free(base.ptr);
free(other.ptr);
free(result.ptr);
return ret;
}
static struct lock_file index_lock;
static void update_paths(struct string_list *update)
{
int i;
hold_locked_index(&index_lock, 1);
for (i = 0; i < update->nr; i++) {
struct string_list_item *item = &update->items[i];
if (add_file_to_cache(item->string, 0))
exit(128);
fprintf(stderr, "Staged '%s' using previous resolution.\n",
item->string);
}
if (active_cache_changed) {
if (write_locked_index(&the_index, &index_lock, COMMIT_LOCK))
die("Unable to write new index file");
} else
rollback_lock_file(&index_lock);
}
static int do_plain_rerere(struct string_list *rr, int fd)
{
struct string_list conflict = STRING_LIST_INIT_DUP;
struct string_list update = STRING_LIST_INIT_DUP;
int i;
find_conflict(&conflict);
/*
* MERGE_RR records paths with conflicts immediately after merge
* failed. Some of the conflicted paths might have been hand resolved
* in the working tree since then, but the initial run would catch all
* and register their preimages.
*/
for (i = 0; i < conflict.nr; i++) {
const char *path = conflict.items[i].string;
if (!string_list_has_string(rr, path)) {
unsigned char sha1[20];
char *hex;
int ret;
ret = handle_file(path, sha1, NULL);
if (ret < 1)
continue;
hex = xstrdup(sha1_to_hex(sha1));
string_list_insert(rr, path)->util = hex;
if (mkdir_in_gitdir(git_path("rr-cache/%s", hex)))
continue;
handle_file(path, NULL, rerere_path(hex, "preimage"));
fprintf(stderr, "Recorded preimage for '%s'\n", path);
}
}
/*
* Now some of the paths that had conflicts earlier might have been
* hand resolved. Others may be similar to a conflict already that
* was resolved before.
*/
for (i = 0; i < rr->nr; i++) {
int ret;
const char *path = rr->items[i].string;
const char *name = (const char *)rr->items[i].util;
if (has_rerere_resolution(name)) {
if (merge(name, path))
continue;
if (rerere_autoupdate)
string_list_insert(&update, path);
else
fprintf(stderr,
"Resolved '%s' using previous resolution.\n",
path);
goto mark_resolved;
}
/* Let's see if we have resolved it. */
ret = handle_file(path, NULL, NULL);
if (ret)
continue;
fprintf(stderr, "Recorded resolution for '%s'.\n", path);
copy_file(rerere_path(name, "postimage"), path, 0666);
mark_resolved:
free(rr->items[i].util);
rr->items[i].util = NULL;
}
if (update.nr)
update_paths(&update);
return write_rr(rr, fd);
}
static void git_rerere_config(void)
{
git_config_get_bool("rerere.enabled", &rerere_enabled);
git_config_get_bool("rerere.autoupdate", &rerere_autoupdate);
git_config(git_default_config, NULL);
}
static int is_rerere_enabled(void)
{
const char *rr_cache;
int rr_cache_exists;
if (!rerere_enabled)
return 0;
rr_cache = git_path("rr-cache");
rr_cache_exists = is_directory(rr_cache);
if (rerere_enabled < 0)
return rr_cache_exists;
rerere: make sure it works even in a workdir attached to a young repository The git-new-workdir script in contrib/ makes a new work tree by sharing many subdirectories of the .git directory with the original repository. When rerere.enabled is set in the original repository, but the user has not encountered any conflicts yet, the original repository may not yet have .git/rr-cache directory. When rerere wants to run in a new work tree created from such a young original repository, it fails to mkdir(2) .git/rr-cache that is a symlink to a yet-to-be-created directory. There are three possible approaches to this: - A naive solution is not to create a symlink in the git-new-workdir script to a directory the original does not have (yet). This is not a solution, as we tend to lazily create subdirectories of .git/, and having rerere.enabled configuration set is a strong indication that the user _wants_ to have this lazy creation to happen; - We could always create .git/rr-cache upon repository creation. This is tempting but will not help people with existing repositories. - Detect this case by seeing that mkdir(2) failed with EEXIST, checking that the path is a symlink, and try running mkdir(2) on the link target. This patch solves the issue by doing the third one. Strictly speaking, this is incomplete. It does not attempt to handle relative symbolic link that points into the original repository, but this is good enough to help people who use contrib/workdir/git-new-workdir script. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-03-11 08:02:50 +08:00
if (!rr_cache_exists && mkdir_in_gitdir(rr_cache))
die("Could not create directory %s", rr_cache);
return 1;
}
int setup_rerere(struct string_list *merge_rr, int flags)
{
int fd;
git_rerere_config();
if (!is_rerere_enabled())
return -1;
if (flags & (RERERE_AUTOUPDATE|RERERE_NOAUTOUPDATE))
rerere_autoupdate = !!(flags & RERERE_AUTOUPDATE);
merge_rr_path = git_pathdup("MERGE_RR");
fd = hold_lock_file_for_update(&write_lock, merge_rr_path,
LOCK_DIE_ON_ERROR);
read_rr(merge_rr);
return fd;
}
int rerere(int flags)
{
struct string_list merge_rr = STRING_LIST_INIT_DUP;
int fd;
fd = setup_rerere(&merge_rr, flags);
if (fd < 0)
return 0;
return do_plain_rerere(&merge_rr, fd);
}
static int rerere_forget_one_path(const char *path, struct string_list *rr)
{
const char *filename;
char *hex;
unsigned char sha1[20];
int ret;
struct string_list_item *item;
ret = handle_cache(path, sha1, NULL);
if (ret < 1)
return error("Could not parse conflict hunks in '%s'", path);
hex = xstrdup(sha1_to_hex(sha1));
filename = rerere_path(hex, "postimage");
if (unlink(filename))
return (errno == ENOENT
? error("no remembered resolution for %s", path)
: error("cannot unlink %s: %s", filename, strerror(errno)));
handle_cache(path, sha1, rerere_path(hex, "preimage"));
fprintf(stderr, "Updated preimage for '%s'\n", path);
item = string_list_insert(rr, path);
free(item->util);
item->util = hex;
fprintf(stderr, "Forgot resolution for %s\n", path);
return 0;
}
int rerere_forget(struct pathspec *pathspec)
{
int i, fd;
struct string_list conflict = STRING_LIST_INIT_DUP;
struct string_list merge_rr = STRING_LIST_INIT_DUP;
if (read_cache() < 0)
return error("Could not read index");
fd = setup_rerere(&merge_rr, RERERE_NOAUTOUPDATE);
unmerge_cache(pathspec);
find_conflict(&conflict);
for (i = 0; i < conflict.nr; i++) {
struct string_list_item *it = &conflict.items[i];
if (!match_pathspec(pathspec, it->string,
strlen(it->string), 0, NULL, 0))
continue;
rerere_forget_one_path(it->string, &merge_rr);
}
return write_rr(&merge_rr, fd);
}
static time_t rerere_created_at(const char *name)
{
struct stat st;
return stat(rerere_path(name, "preimage"), &st) ? (time_t) 0 : st.st_mtime;
}
static time_t rerere_last_used_at(const char *name)
{
struct stat st;
return stat(rerere_path(name, "postimage"), &st) ? (time_t) 0 : st.st_mtime;
}
static void unlink_rr_item(const char *name)
{
unlink(rerere_path(name, "thisimage"));
unlink(rerere_path(name, "preimage"));
unlink(rerere_path(name, "postimage"));
rmdir(git_path("rr-cache/%s", name));
}
void rerere_gc(struct string_list *rr)
{
struct string_list to_remove = STRING_LIST_INIT_DUP;
DIR *dir;
struct dirent *e;
int i, cutoff;
time_t now = time(NULL), then;
int cutoff_noresolve = 15;
int cutoff_resolve = 60;
git_config_get_int("gc.rerereresolved", &cutoff_resolve);
git_config_get_int("gc.rerereunresolved", &cutoff_noresolve);
git_config(git_default_config, NULL);
dir = opendir(git_path("rr-cache"));
if (!dir)
die_errno("unable to open rr-cache directory");
while ((e = readdir(dir))) {
if (is_dot_or_dotdot(e->d_name))
continue;
then = rerere_last_used_at(e->d_name);
if (then) {
cutoff = cutoff_resolve;
} else {
then = rerere_created_at(e->d_name);
if (!then)
continue;
cutoff = cutoff_noresolve;
}
if (then < now - cutoff * 86400)
string_list_append(&to_remove, e->d_name);
}
closedir(dir);
for (i = 0; i < to_remove.nr; i++)
unlink_rr_item(to_remove.items[i].string);
string_list_clear(&to_remove, 0);
}
void rerere_clear(struct string_list *merge_rr)
{
int i;
for (i = 0; i < merge_rr->nr; i++) {
const char *name = (const char *)merge_rr->items[i].util;
if (!has_rerere_resolution(name))
unlink_rr_item(name);
}
unlink_or_warn(git_path("MERGE_RR"));
}