#include <limits.h>
#include "cache.h"
#include "diff.h"
-#include "delta.h"
+#include "diffcore.h"
static const char *diff_opts = "-pu";
static unsigned char null_sha1[20] = { 0, };
-#define MAX_SCORE 10000
-#define DEFAULT_MINIMUM_SCORE 5000
+
+static int detect_rename;
+static int reverse_diff;
+static int diff_raw_output = -1;
+static const char **pathspec;
+static int speccnt;
+static int minimum_score;
static const char *external_diff(void)
{
}
static struct diff_tempfile {
- const char *name;
+ const char *name; /* filename external diff should read from */
char hex[41];
char mode[10];
char tmp_path[50];
} diff_temp[2];
-struct diff_spec {
- unsigned char blob_sha1[20];
- unsigned short mode; /* file mode */
- unsigned sha1_valid : 1; /* if true, use blob_sha1 and trust mode;
- * if false, use the name and read from
- * the filesystem.
- */
- unsigned file_valid : 1; /* if false the file does not exist */
-};
-
static void builtin_diff(const char *name_a,
const char *name_b,
struct diff_tempfile *temp,
- int rename_score)
+ const char *xfrm_msg)
{
int i, next_at, cmd_size;
const char *diff_cmd = "diff -L'%s%s' -L'%s%s'";
printf("old mode %s\n", temp[0].mode);
printf("new mode %s\n", temp[1].mode);
}
- if (strcmp(name_a, name_b)) {
- if (0 < rename_score)
- printf("rename similarity index %d%%\n",
- (int)(0.5+
- rename_score*100.0/MAX_SCORE));
- printf("rename old %s\n", name_a);
- printf("rename new %s\n", name_b);
- }
+ if (xfrm_msg && xfrm_msg[0])
+ fputs(xfrm_msg, stdout);
+
if (strncmp(temp[0].mode, temp[1].mode, 3))
/* we do not run diff between different kind
* of objects.
execlp("/bin/sh","sh", "-c", cmd, NULL);
}
+struct diff_filespec *alloc_filespec(const char *path)
+{
+ int namelen = strlen(path);
+ struct diff_filespec *spec = xmalloc(sizeof(*spec) + namelen + 1);
+ spec->path = (char *)(spec + 1);
+ strcpy(spec->path, path);
+ spec->should_free = spec->should_munmap = spec->file_valid = 0;
+ spec->xfrm_flags = 0;
+ spec->size = 0;
+ spec->data = 0;
+ return spec;
+}
+
+void fill_filespec(struct diff_filespec *spec, const unsigned char *sha1,
+ unsigned short mode)
+{
+ spec->mode = mode;
+ memcpy(spec->sha1, sha1, 20);
+ spec->sha1_valid = !!memcmp(sha1, null_sha1, 20);
+ spec->file_valid = 1;
+}
+
/*
* Given a name and sha1 pair, if the dircache tells us the file in
* the work tree has that object contents, return true, so that
return 0;
ce = active_cache[pos];
if ((lstat(name, &st) < 0) ||
- !S_ISREG(st.st_mode) ||
+ !S_ISREG(st.st_mode) || /* careful! */
ce_match_stat(ce, &st) ||
memcmp(sha1, ce->sha1, 20))
return 0;
+ /* we return 1 only when we can stat, it is a regular file,
+ * stat information matches, and sha1 recorded in the cache
+ * matches. I.e. we know the file in the work tree really is
+ * the same as the <name, sha1> pair.
+ */
return 1;
}
+/*
+ * While doing rename detection and pickaxe operation, we may need to
+ * grab the data for the blob (or file) for our own in-core comparison.
+ * diff_filespec has data and size fields for this purpose.
+ */
+int diff_populate_filespec(struct diff_filespec *s)
+{
+ int err = 0;
+ if (!s->file_valid)
+ die("internal error: asking to populate invalid file.");
+ if (S_ISDIR(s->mode))
+ return -1;
+
+ if (s->data)
+ return err;
+ if (!s->sha1_valid ||
+ work_tree_matches(s->path, s->sha1)) {
+ struct stat st;
+ int fd;
+ if (lstat(s->path, &st) < 0) {
+ if (errno == ENOENT) {
+ err_empty:
+ err = -1;
+ empty:
+ s->data = "";
+ s->size = 0;
+ return err;
+ }
+ }
+ s->size = st.st_size;
+ if (!s->size)
+ goto empty;
+ if (S_ISLNK(st.st_mode)) {
+ int ret;
+ s->data = xmalloc(s->size);
+ s->should_free = 1;
+ ret = readlink(s->path, s->data, s->size);
+ if (ret < 0) {
+ free(s->data);
+ goto err_empty;
+ }
+ return 0;
+ }
+ fd = open(s->path, O_RDONLY);
+ if (fd < 0)
+ goto err_empty;
+ s->data = mmap(NULL, s->size, PROT_READ, MAP_PRIVATE, fd, 0);
+ s->should_munmap = 1;
+ close(fd);
+ }
+ else {
+ char type[20];
+ s->data = read_sha1_file(s->sha1, type, &s->size);
+ s->should_free = 1;
+ }
+ return 0;
+}
+
+void diff_free_filespec_data(struct diff_filespec *s)
+{
+ if (s->should_free)
+ free(s->data);
+ else if (s->should_munmap)
+ munmap(s->data, s->size);
+ s->should_free = s->should_munmap = 0;
+ s->data = 0;
+}
+
static void prep_temp_blob(struct diff_tempfile *temp,
void *blob,
unsigned long size,
static void prepare_temp_file(const char *name,
struct diff_tempfile *temp,
- struct diff_spec *one)
+ struct diff_filespec *one)
{
if (!one->file_valid) {
not_a_valid_file:
}
if (!one->sha1_valid ||
- work_tree_matches(name, one->blob_sha1)) {
+ work_tree_matches(name, one->sha1)) {
struct stat st;
- temp->name = name;
- if (lstat(temp->name, &st) < 0) {
+ if (lstat(name, &st) < 0) {
if (errno == ENOENT)
goto not_a_valid_file;
- die("stat(%s): %s", temp->name, strerror(errno));
+ die("stat(%s): %s", name, strerror(errno));
}
if (S_ISLNK(st.st_mode)) {
int ret;
die("readlink(%s)", name);
prep_temp_blob(temp, buf, st.st_size,
(one->sha1_valid ?
- one->blob_sha1 : null_sha1),
+ one->sha1 : null_sha1),
(one->sha1_valid ?
one->mode : S_IFLNK));
}
else {
+ /* we can borrow from the file in the work tree */
+ temp->name = name;
if (!one->sha1_valid)
strcpy(temp->hex, sha1_to_hex(null_sha1));
else
- strcpy(temp->hex, sha1_to_hex(one->blob_sha1));
+ strcpy(temp->hex, sha1_to_hex(one->sha1));
sprintf(temp->mode, "%06o",
S_IFREG |ce_permissions(st.st_mode));
}
return;
}
else {
- void *blob;
- char type[20];
- unsigned long size;
-
- blob = read_sha1_file(one->blob_sha1, type, &size);
- if (!blob || strcmp(type, "blob"))
- die("unable to read blob object for %s (%s)",
- name, sha1_to_hex(one->blob_sha1));
- prep_temp_blob(temp, blob, size, one->blob_sha1, one->mode);
- free(blob);
+ if (diff_populate_filespec(one))
+ die("cannot read data blob for %s", one->path);
+ prep_temp_blob(temp, one->data, one->size,
+ one->sha1, one->mode);
}
}
remove_tempfile();
}
-static int detect_rename;
-static int reverse_diff;
-static int diff_raw_output = -1;
-static const char **pathspec;
-static int speccnt;
-static int minimum_score;
-
static int matches_pathspec(const char *name)
{
int i;
*/
static void run_external_diff(const char *name,
const char *other,
- struct diff_spec *one,
- struct diff_spec *two,
- int rename_score)
+ struct diff_filespec *one,
+ struct diff_filespec *two,
+ const char *xfrm_msg)
{
struct diff_tempfile *temp = diff_temp;
pid_t pid;
const char *pgm = external_diff();
if (pgm) {
if (one && two) {
- const char *exec_arg[9];
+ const char *exec_arg[10];
const char **arg = &exec_arg[0];
*arg++ = pgm;
*arg++ = name;
*arg++ = temp[1].name;
*arg++ = temp[1].hex;
*arg++ = temp[1].mode;
- if (other)
+ if (other) {
*arg++ = other;
- *arg = NULL;
+ *arg++ = xfrm_msg;
+ }
+ *arg = 0;
execvp(pgm, (char *const*) exec_arg);
}
else
* otherwise we use the built-in one.
*/
if (one && two)
- builtin_diff(name, other ? : name, temp, rename_score);
+ builtin_diff(name, other ? : name, temp, xfrm_msg);
else
printf("* Unmerged path %s\n", name);
exit(0);
remove_tempfile();
}
-/*
- * We do not detect circular renames. Just hold created and deleted
- * entries and later attempt to match them up. If they do not match,
- * then spit them out as deletes or creates as original.
- */
-
-static struct diff_spec_hold {
- struct diff_spec_hold *next;
- struct diff_spec it;
- unsigned long size;
- int flags;
-#define MATCHED 1
-#define SHOULD_FREE 2
-#define SHOULD_MUNMAP 4
- void *data;
- char path[1];
-} *createdfile, *deletedfile;
-
-static void hold_diff(const char *name,
- struct diff_spec *one,
- struct diff_spec *two)
+int diff_scoreopt_parse(const char *opt)
{
- struct diff_spec_hold **list, *elem;
-
- if (one->file_valid && two->file_valid)
- die("internal error");
+ int diglen, num, scale, i;
+ if (opt[0] != '-' || (opt[1] != 'M' && opt[1] != 'C'))
+ return -1; /* that is not a -M nor -C option */
+ diglen = strspn(opt+2, "0123456789");
+ if (diglen == 0 || strlen(opt+2) != diglen)
+ return 0; /* use default */
+ sscanf(opt+2, "%d", &num);
+ for (i = 0, scale = 1; i < diglen; i++)
+ scale *= 10;
- if (!detect_rename) {
- run_external_diff(name, NULL, one, two, -1);
- return;
- }
- elem = xmalloc(sizeof(*elem) + strlen(name));
- strcpy(elem->path, name);
- elem->size = 0;
- elem->data = NULL;
- elem->flags = 0;
- if (one->file_valid) {
- list = &deletedfile;
- elem->it = *one;
- }
- else {
- list = &createdfile;
- elem->it = *two;
- }
- elem->next = *list;
- *list = elem;
+ /* user says num divided by scale and we say internally that
+ * is MAX_SCORE * num / scale.
+ */
+ return MAX_SCORE * num / scale;
}
-static int populate_data(struct diff_spec_hold *s)
+void diff_setup(int detect_rename_, int minimum_score_, int reverse_diff_,
+ int diff_raw_output_,
+ const char **pathspec_, int speccnt_)
{
- char type[20];
-
- if (s->data)
- return 0;
- if (s->it.sha1_valid) {
- s->data = read_sha1_file(s->it.blob_sha1, type, &s->size);
- s->flags |= SHOULD_FREE;
- }
- else {
- struct stat st;
- int fd;
- fd = open(s->path, O_RDONLY);
- if (fd < 0)
- return -1;
- if (fstat(fd, &st)) {
- close(fd);
- return -1;
- }
- s->size = st.st_size;
- s->data = mmap(NULL, s->size, PROT_READ, MAP_PRIVATE, fd, 0);
- close(fd);
- if (!s->size)
- s->data = "";
- else
- s->flags |= SHOULD_MUNMAP;
- }
- return 0;
+ detect_rename = detect_rename_;
+ reverse_diff = reverse_diff_;
+ pathspec = pathspec_;
+ diff_raw_output = diff_raw_output_;
+ speccnt = speccnt_;
+ minimum_score = minimum_score_ ? : DEFAULT_MINIMUM_SCORE;
}
-static void free_data(struct diff_spec_hold *s)
-{
- if (s->flags & SHOULD_FREE)
- free(s->data);
- else if (s->flags & SHOULD_MUNMAP)
- munmap(s->data, s->size);
- s->flags &= ~(SHOULD_FREE|SHOULD_MUNMAP);
- s->data = NULL;
-}
+static struct diff_queue_struct queued_diff;
-static void flush_remaining_diff(struct diff_spec_hold *elem,
- int on_created_list)
+struct diff_file_pair *diff_queue(struct diff_queue_struct *queue,
+ struct diff_filespec *one,
+ struct diff_filespec *two)
{
- static struct diff_spec null_file_spec;
-
- null_file_spec.file_valid = 0;
- for ( ; elem ; elem = elem->next) {
- free_data(elem);
- if (elem->flags & MATCHED)
- continue;
- if (on_created_list)
- run_external_diff(elem->path, NULL,
- &null_file_spec, &elem->it, -1);
- else
- run_external_diff(elem->path, NULL,
- &elem->it, &null_file_spec, -1);
+ struct diff_file_pair *dp = xmalloc(sizeof(*dp));
+ dp->one = one;
+ dp->two = two;
+ dp->xfrm_msg = 0;
+ dp->orig_order = queue->nr;
+ dp->xfrm_work = 0;
+ if (queue->alloc <= queue->nr) {
+ queue->alloc = alloc_nr(queue->alloc);
+ queue->queue = xrealloc(queue->queue,
+ sizeof(dp) * queue->alloc);
}
+ queue->queue[queue->nr++] = dp;
+ return dp;
}
-static int is_exact_match(struct diff_spec_hold *src,
- struct diff_spec_hold *dst)
+static const char *git_object_type(unsigned mode)
{
- if (src->it.sha1_valid && dst->it.sha1_valid &&
- !memcmp(src->it.blob_sha1, dst->it.blob_sha1, 20))
- return 1;
- if (populate_data(src) || populate_data(dst))
- /* this is an error but will be caught downstream */
- return 0;
- if (src->size == dst->size &&
- !memcmp(src->data, dst->data, src->size))
- return 1;
- return 0;
+ return S_ISDIR(mode) ? "tree" : "blob";
}
-static int estimate_similarity(struct diff_spec_hold *src, struct diff_spec_hold *dst)
+static void diff_flush_raw(struct diff_file_pair *p)
{
- /* src points at a deleted file and dst points at a created
- * file. They may be quite similar, in which case we want to
- * say src is renamed to dst.
- *
- * Compare them and return how similar they are, representing
- * the score as an integer between 0 and 10000, except
- * where they match exactly it is considered better than anything
- * else.
- */
- void *delta;
- unsigned long delta_size;
- int score;
-
- delta_size = ((src->size < dst->size) ?
- (dst->size - src->size) : (src->size - dst->size));
+ struct diff_filespec *it;
+ int addremove;
- /* We would not consider rename followed by more than
- * minimum_score/MAX_SCORE edits; that is, delta_size must be smaller
- * than (src->size + dst->size)/2 * minimum_score/MAX_SCORE,
- * which means...
- */
+ /* raw output does not have a way to express rename nor copy */
+ if (strcmp(p->one->path, p->two->path))
+ return;
- if ((src->size+dst->size)*minimum_score < delta_size*MAX_SCORE*2)
- return 0;
+ if (p->one->file_valid && p->two->file_valid) {
+ char hex[41];
+ strcpy(hex, sha1_to_hex(p->one->sha1));
+ printf("*%06o->%06o %s %s->%s %s%c",
+ p->one->mode, p->two->mode,
+ git_object_type(p->one->mode),
+ hex, sha1_to_hex(p->two->sha1),
+ p->one->path, diff_raw_output);
+ return;
+ }
- delta = diff_delta(src->data, src->size,
- dst->data, dst->size,
- &delta_size);
- free(delta);
+ if (p->one->file_valid) {
+ it = p->one;
+ addremove = '-';
+ } else {
+ it = p->two;
+ addremove = '+';
+ }
- /* This "delta" is really xdiff with adler32 and all the
- * overheads but it is a quick and dirty approximation.
- *
- * Now we will give some score to it. 100% edit gets
- * 0 points and 0% edit gets MAX_SCORE points. That is, every
- * 1/MAX_SCORE edit gets 1 point penalty. The amount of penalty is:
- *
- * (delta_size * 2 / (src->size + dst->size)) * MAX_SCORE
- *
- */
- score = MAX_SCORE-(MAX_SCORE*2*delta_size/(src->size+dst->size));
- if (score < 0) return 0;
- if (MAX_SCORE < score) return MAX_SCORE;
- return score;
+ printf("%c%06o %s %s %s%c",
+ addremove,
+ it->mode, git_object_type(it->mode),
+ sha1_to_hex(it->sha1), it->path, diff_raw_output);
}
-struct diff_score {
- struct diff_spec_hold *src;
- struct diff_spec_hold *dst;
- int score;
-};
-
-static int score_compare(const void *a_, const void *b_)
+static void diff_flush_patch(struct diff_file_pair *p)
{
- const struct diff_score *a = a_, *b = b_;
- return b->score - a->score;
-}
+ const char *name, *other;
-static void flush_rename_pair(struct diff_spec_hold *src,
- struct diff_spec_hold *dst,
- int rename_score)
-{
- src->flags |= MATCHED;
- dst->flags |= MATCHED;
- free_data(src);
- free_data(dst);
- run_external_diff(src->path, dst->path,
- &src->it, &dst->it, rename_score);
-}
+ name = p->one->path;
+ other = (strcmp(name, p->two->path) ? p->two->path : NULL);
+ if ((p->one->file_valid && S_ISDIR(p->one->mode)) ||
+ (p->two->file_valid && S_ISDIR(p->two->mode)))
+ return; /* no tree diffs in patch format */
-static void free_held_diff(struct diff_spec_hold *list)
-{
- struct diff_spec_hold *h;
- for (h = list; list; list = h) {
- h = list->next;
- free_data(list);
- free(list);
- }
+ run_external_diff(name, other, p->one, p->two, p->xfrm_msg);
}
-void diff_flush(void)
+static int identical(struct diff_filespec *one, struct diff_filespec *two)
{
- int num_create, num_delete, c, d;
- struct diff_spec_hold *elem, *src, *dst;
- struct diff_score *mx;
-
- /* We really want to cull the candidates list early
- * with cheap tests in order to avoid doing deltas.
- *
- * With the current callers, we should not have already
- * matched entries at this point, but it is nonetheless
- * checked for sanity.
+ /* This function is written stricter than necessary to support
+ * the currently implemented transformers, but the idea is to
+ * let transformers to produce diff_file_pairs any way they want,
+ * and filter and clean them up here before producing the output.
*/
- for (dst = createdfile; dst; dst = dst->next) {
- if (dst->flags & MATCHED)
- continue;
- for (src = deletedfile; src; src = src->next) {
- if (src->flags & MATCHED)
- continue;
- if (! is_exact_match(src, dst))
- continue;
- flush_rename_pair(src, dst, MAX_SCORE);
- break;
- }
- }
- /* Count surviving candidates */
- for (num_create = 0, elem = createdfile; elem; elem = elem->next)
- if (!(elem->flags & MATCHED))
- num_create++;
-
- for (num_delete = 0, elem = deletedfile; elem; elem = elem->next)
- if (!(elem->flags & MATCHED))
- num_delete++;
-
- if (num_create == 0 || num_delete == 0)
- goto exit_path;
-
- mx = xmalloc(sizeof(*mx) * num_create * num_delete);
- for (c = 0, dst = createdfile; dst; dst = dst->next) {
- int base = c * num_delete;
- if (dst->flags & MATCHED)
- continue;
- for (d = 0, src = deletedfile; src; src = src->next) {
- struct diff_score *m = &mx[base+d];
- if (src->flags & MATCHED)
- continue;
- m->src = src;
- m->dst = dst;
- m->score = estimate_similarity(src, dst);
- d++;
- }
- c++;
- }
- qsort(mx, num_create*num_delete, sizeof(*mx), score_compare);
-
-#if 0
- for (c = 0; c < num_create * num_delete; c++) {
- src = mx[c].src;
- dst = mx[c].dst;
- if ((src->flags & MATCHED) || (dst->flags & MATCHED))
- continue;
- fprintf(stderr,
- "**score ** %d %s %s\n",
- mx[c].score, src->path, dst->path);
- }
-#endif
-
- for (c = 0; c < num_create * num_delete; c++) {
- src = mx[c].src;
- dst = mx[c].dst;
- if ((src->flags & MATCHED) || (dst->flags & MATCHED))
- continue;
- if (mx[c].score < minimum_score)
- break;
- flush_rename_pair(src, dst, mx[c].score);
- }
- free(mx);
-
- exit_path:
- flush_remaining_diff(createdfile, 1);
- flush_remaining_diff(deletedfile, 0);
- free_held_diff(createdfile);
- free_held_diff(deletedfile);
- createdfile = deletedfile = NULL;
-}
+ if (!one->file_valid && !two->file_valid)
+ return 1; /* not interesting */
-int diff_scoreopt_parse(const char *opt)
-{
- int diglen, num, scale, i;
- if (opt[0] != '-' || opt[1] != 'M')
- return -1; /* that is not -M option */
- diglen = strspn(opt+2, "0123456789");
- if (diglen == 0 || strlen(opt+2) != diglen)
- return 0; /* use default */
- sscanf(opt+2, "%d", &num);
- for (i = 0, scale = 1; i < diglen; i++)
- scale *= 10;
+ /* deletion, addition, mode change and renames are all interesting. */
+ if ((one->file_valid != two->file_valid) || (one->mode != two->mode) ||
+ strcmp(one->path, two->path))
+ return 0;
- /* user says num divided by scale and we say internally that
- * is MAX_SCORE * num / scale.
+ /* both are valid and point at the same path. that is, we are
+ * dealing with a change.
*/
- return MAX_SCORE * num / scale;
+ if (one->sha1_valid && two->sha1_valid &&
+ !memcmp(one->sha1, two->sha1, sizeof(one->sha1)))
+ return 1; /* no change */
+ if (!one->sha1_valid && !two->sha1_valid)
+ return 1; /* both look at the same file on the filesystem. */
+ return 0;
}
-void diff_setup(int detect_rename_, int minimum_score_, int reverse_diff_,
- int diff_raw_output_,
- const char **pathspec_, int speccnt_)
+static void diff_flush_one(struct diff_file_pair *p)
{
- free_held_diff(createdfile);
- free_held_diff(deletedfile);
- createdfile = deletedfile = NULL;
-
- detect_rename = detect_rename_;
- reverse_diff = reverse_diff_;
- pathspec = pathspec_;
- diff_raw_output = diff_raw_output_;
- speccnt = speccnt_;
- minimum_score = minimum_score_ ? : DEFAULT_MINIMUM_SCORE;
+ if (identical(p->one, p->two))
+ return;
+ if (0 <= diff_raw_output)
+ diff_flush_raw(p);
+ else
+ diff_flush_patch(p);
}
-static const char *git_object_type(unsigned mode)
+void diff_flush(void)
{
- return S_ISDIR(mode) ? "tree" : "blob";
+ struct diff_queue_struct *q = &queued_diff;
+ int i;
+
+ if (detect_rename)
+ diff_detect_rename(q, detect_rename, minimum_score);
+ for (i = 0; i < q->nr; i++)
+ diff_flush_one(q->queue[i]);
+
+ for (i = 0; i < q->nr; i++) {
+ struct diff_file_pair *p = q->queue[i];
+ diff_free_filespec_data(p->one);
+ diff_free_filespec_data(p->two);
+ free(p->xfrm_msg);
+ free(p);
+ }
+ free(q->queue);
+ q->queue = NULL;
+ q->nr = q->alloc = 0;
}
void diff_addremove(int addremove, unsigned mode,
const char *base, const char *path)
{
char concatpath[PATH_MAX];
- struct diff_spec spec[2], *one, *two;
-
+ struct diff_filespec *one, *two;
+
+ /* This may look odd, but it is a preparation for
+ * feeding "there are unchanged files which should
+ * not produce diffs, but when you are doing copy
+ * detection you would need them, so here they are"
+ * entries to the diff-core. They will be prefixed
+ * with something like '=' or '*' (I haven't decided
+ * which but should not make any difference).
+ * Feeding the same new and old to diff_change() should
+ * also have the same effect. diff_flush() should
+ * filter the identical ones out at the final output
+ * stage.
+ */
if (reverse_diff)
- addremove = (addremove == '+' ? '-' : '+');
+ addremove = (addremove == '+' ? '-' :
+ addremove == '-' ? '+' : addremove);
- if (0 <= diff_raw_output) {
- if (!path)
- path = "";
- printf("%c%06o %s %s %s%s%c",
- addremove,
- mode,
- git_object_type(mode), sha1_to_hex(sha1),
- base, path, diff_raw_output);
- return;
- }
- if (S_ISDIR(mode))
- return;
-
- memcpy(spec[0].blob_sha1, sha1, 20);
- spec[0].mode = mode;
- spec[0].sha1_valid = !!memcmp(sha1, null_sha1, 20);
- spec[0].file_valid = 1;
- spec[1].file_valid = 0;
+ if (!path) path = "";
+ sprintf(concatpath, "%s%s", base, path);
+ one = alloc_filespec(concatpath);
+ two = alloc_filespec(concatpath);
- if (addremove == '+') {
- one = spec + 1; two = spec;
- } else {
- one = spec; two = one + 1;
- }
+ if (addremove != '+')
+ fill_filespec(one, sha1, mode);
+ if (addremove != '-')
+ fill_filespec(two, sha1, mode);
- if (path) {
- strcpy(concatpath, base);
- strcat(concatpath, path);
- }
- hold_diff(path ? concatpath : base, one, two);
+ diff_queue(&queued_diff, one, two);
}
void diff_change(unsigned old_mode, unsigned new_mode,
const unsigned char *new_sha1,
const char *base, const char *path) {
char concatpath[PATH_MAX];
- struct diff_spec spec[2];
+ struct diff_filespec *one, *two;
if (reverse_diff) {
unsigned tmp;
tmp = old_mode; old_mode = new_mode; new_mode = tmp;
tmp_c = old_sha1; old_sha1 = new_sha1; new_sha1 = tmp_c;
}
-
- if (0 <= diff_raw_output) {
- char old_hex[41];
- strcpy(old_hex, sha1_to_hex(old_sha1));
-
- if (!path)
- path = "";
- printf("*%06o->%06o %s %s->%s %s%s%c",
- old_mode, new_mode,
- git_object_type(new_mode),
- old_hex, sha1_to_hex(new_sha1),
- base, path, diff_raw_output);
- return;
- }
- if (S_ISDIR(new_mode))
- return;
-
- if (path) {
- strcpy(concatpath, base);
- strcat(concatpath, path);
- }
-
- memcpy(spec[0].blob_sha1, old_sha1, 20);
- spec[0].mode = old_mode;
- memcpy(spec[1].blob_sha1, new_sha1, 20);
- spec[1].mode = new_mode;
- spec[0].sha1_valid = !!memcmp(old_sha1, null_sha1, 20);
- spec[1].sha1_valid = !!memcmp(new_sha1, null_sha1, 20);
- spec[1].file_valid = spec[0].file_valid = 1;
-
- /* We do not look at changed files as candidate for
- * rename detection ever.
- */
- run_external_diff(path ? concatpath : base, NULL,
- &spec[0], &spec[1], -1);
+ if (!path) path = "";
+ sprintf(concatpath, "%s%s", base, path);
+ one = alloc_filespec(concatpath);
+ two = alloc_filespec(concatpath);
+ fill_filespec(one, old_sha1, old_mode);
+ fill_filespec(two, new_sha1, new_mode);
+
+ diff_queue(&queued_diff, one, two);
}
void diff_unmerge(const char *path)
printf("U %s%c", path, diff_raw_output);
return;
}
- run_external_diff(path, NULL, NULL, NULL, -1);
+ run_external_diff(path, NULL, NULL, NULL, NULL);
}
--- /dev/null
+/*
+ * Copyright (C) 2005 Junio C Hamano
+ */
+#include "cache.h"
+#include "diff.h"
+#include "diffcore.h"
+#include "delta.h"
+
+struct diff_rename_pool {
+ struct diff_filespec **s;
+ int nr, alloc;
+};
+
+static void diff_rename_pool_clear(struct diff_rename_pool *pool)
+{
+ pool->s = NULL; pool->nr = pool->alloc = 0;
+}
+
+static void diff_rename_pool_add(struct diff_rename_pool *pool,
+ struct diff_filespec *s)
+{
+ if (S_ISDIR(s->mode))
+ return; /* rename/copy patch for tree does not make sense. */
+
+ if (pool->alloc <= pool->nr) {
+ pool->alloc = alloc_nr(pool->alloc);
+ pool->s = xrealloc(pool->s,
+ sizeof(*(pool->s)) * pool->alloc);
+ }
+ pool->s[pool->nr] = s;
+ pool->nr++;
+}
+
+static int is_exact_match(struct diff_filespec *src, struct diff_filespec *dst)
+{
+ if (src->sha1_valid && dst->sha1_valid &&
+ !memcmp(src->sha1, dst->sha1, 20))
+ return 1;
+ if (diff_populate_filespec(src) || diff_populate_filespec(dst))
+ /* this is an error but will be caught downstream */
+ return 0;
+ if (src->size == dst->size &&
+ !memcmp(src->data, dst->data, src->size))
+ return 1;
+ return 0;
+}
+
+struct diff_score {
+ struct diff_filespec *src;
+ struct diff_filespec *dst;
+ int score;
+ int rank;
+};
+
+static int estimate_similarity(struct diff_filespec *src,
+ struct diff_filespec *dst,
+ int minimum_score)
+{
+ /* src points at a file that existed in the original tree (or
+ * optionally a file in the destination tree) and dst points
+ * at a newly created file. They may be quite similar, in which
+ * case we want to say src is renamed to dst or src is copied into
+ * dst, and then some edit has been applied to dst.
+ *
+ * Compare them and return how similar they are, representing
+ * the score as an integer between 0 and 10000, except
+ * where they match exactly it is considered better than anything
+ * else.
+ */
+ void *delta;
+ unsigned long delta_size;
+ int score;
+
+ delta_size = ((src->size < dst->size) ?
+ (dst->size - src->size) : (src->size - dst->size));
+
+ /* We would not consider rename followed by more than
+ * minimum_score/MAX_SCORE edits; that is, delta_size must be smaller
+ * than (src->size + dst->size)/2 * minimum_score/MAX_SCORE,
+ * which means...
+ */
+
+ if ((src->size+dst->size)*minimum_score < delta_size*MAX_SCORE*2)
+ return 0;
+
+ delta = diff_delta(src->data, src->size,
+ dst->data, dst->size,
+ &delta_size);
+ free(delta);
+
+ /* This "delta" is really xdiff with adler32 and all the
+ * overheads but it is a quick and dirty approximation.
+ *
+ * Now we will give some score to it. 100% edit gets
+ * 0 points and 0% edit gets MAX_SCORE points. That is, every
+ * 1/MAX_SCORE edit gets 1 point penalty. The amount of penalty is:
+ *
+ * (delta_size * 2 / (src->size + dst->size)) * MAX_SCORE
+ *
+ */
+ score = MAX_SCORE-(MAX_SCORE*2*delta_size/(src->size+dst->size));
+ if (score < 0) return 0;
+ if (MAX_SCORE < score) return MAX_SCORE;
+ return score;
+}
+
+static void record_rename_pair(struct diff_queue_struct *outq,
+ struct diff_filespec *src,
+ struct diff_filespec *dst,
+ int rank,
+ int score)
+{
+ /* The rank is used to sort the final output, because there
+ * are certain dependencies.
+ *
+ * - rank #0 depends on deleted ones.
+ * - rank #1 depends on kept files before they are modified.
+ * - rank #2 depends on kept files after they are modified;
+ * currently not used.
+ *
+ * Therefore, the final output order should be:
+ *
+ * 1. rank #0 rename/copy diffs.
+ * 2. deletions in the original.
+ * 3. rank #1 rename/copy diffs.
+ * 4. additions and modifications in the original.
+ * 5. rank #2 rename/copy diffs; currently not used.
+ *
+ * To achieve this sort order, we give xform_work the number
+ * above.
+ */
+ struct diff_file_pair *dp = diff_queue(outq, src, dst);
+ dp->xfrm_work = (rank * 2 + 1) | (score<<RENAME_SCORE_SHIFT);
+ dst->xfrm_flags |= RENAME_DST_MATCHED;
+}
+
+#if 0
+static void debug_filespec(struct diff_filespec *s, int x, const char *one)
+{
+ fprintf(stderr, "queue[%d] %s (%s) %s %06o %s\n",
+ x, one,
+ s->path,
+ s->file_valid ? "valid" : "invalid",
+ s->mode,
+ s->sha1_valid ? sha1_to_hex(s->sha1) : "");
+ fprintf(stderr, "queue[%d] %s size %lu flags %d\n",
+ x, one,
+ s->size, s->xfrm_flags);
+}
+
+static void debug_filepair(const struct diff_file_pair *p, int i)
+{
+ debug_filespec(p->one, i, "one");
+ debug_filespec(p->two, i, "two");
+ fprintf(stderr, "pair flags %d, orig order %d, score %d\n",
+ (p->xfrm_work & ((1<<RENAME_SCORE_SHIFT) - 1)),
+ p->orig_order,
+ (p->xfrm_work >> RENAME_SCORE_SHIFT));
+}
+
+static void debug_queue(const char *msg, struct diff_queue_struct *q)
+{
+ int i;
+ if (msg)
+ fprintf(stderr, "%s\n", msg);
+ fprintf(stderr, "q->nr = %d\n", q->nr);
+ for (i = 0; i < q->nr; i++) {
+ struct diff_file_pair *p = q->queue[i];
+ debug_filepair(p, i);
+ }
+}
+#else
+#define debug_queue(a,b) do { ; /*nothing*/ } while(0)
+#endif
+
+/*
+ * We sort the outstanding diff entries according to the rank (see
+ * comment at the beginning of record_rename_pair) and tiebreak with
+ * the order in the original input.
+ */
+static int rank_compare(const void *a_, const void *b_)
+{
+ const struct diff_file_pair *a = *(const struct diff_file_pair **)a_;
+ const struct diff_file_pair *b = *(const struct diff_file_pair **)b_;
+ int a_rank = a->xfrm_work & ((1<<RENAME_SCORE_SHIFT) - 1);
+ int b_rank = b->xfrm_work & ((1<<RENAME_SCORE_SHIFT) - 1);
+
+ if (a_rank != b_rank)
+ return a_rank - b_rank;
+ return a->orig_order - b->orig_order;
+}
+
+/*
+ * We sort the rename similarity matrix with the score, in descending
+ * order (more similar first).
+ */
+static int score_compare(const void *a_, const void *b_)
+{
+ const struct diff_score *a = a_, *b = b_;
+ return b->score - a->score;
+}
+
+static int needs_to_stay(struct diff_queue_struct *q, int i,
+ struct diff_filespec *it)
+{
+ /* If it will be used in later entry (either stay or used
+ * as the source of rename/copy), we need to copy, not rename.
+ */
+ while (i < q->nr) {
+ struct diff_file_pair *p = q->queue[i++];
+ if (!p->two->file_valid)
+ continue; /* removed is fine */
+ if (strcmp(p->one->path, it->path))
+ continue; /* not relevant */
+
+ /* p has its src set to *it and it is not a delete;
+ * it will be used for in-place change or rename/copy,
+ * so we cannot rename it out.
+ */
+ return 1;
+ }
+ return 0;
+}
+
+void diff_detect_rename(struct diff_queue_struct *q,
+ int detect_rename,
+ int minimum_score)
+{
+ struct diff_queue_struct outq;
+ struct diff_rename_pool created, deleted, stay;
+ struct diff_rename_pool *(srcs[2]);
+ struct diff_score *mx;
+ int h, i, j;
+ int num_create, num_src, dst_cnt, src_cnt;
+
+ outq.queue = NULL;
+ outq.nr = outq.alloc = 0;
+
+ diff_rename_pool_clear(&created);
+ diff_rename_pool_clear(&deleted);
+ diff_rename_pool_clear(&stay);
+
+ srcs[0] = &deleted;
+ srcs[1] = &stay;
+
+ /* NEEDSWORK:
+ * (1) make sure we properly ignore but pass trees.
+ *
+ * (2) make sure we do right thing on the same path deleted
+ * and created in the same patch.
+ */
+
+ for (i = 0; i < q->nr; i++) {
+ struct diff_file_pair *p = q->queue[i];
+ if (!p->one->file_valid)
+ if (!p->two->file_valid)
+ continue; /* ignore nonsense */
+ else
+ diff_rename_pool_add(&created, p->two);
+ else if (!p->two->file_valid)
+ diff_rename_pool_add(&deleted, p->one);
+ else if (1 < detect_rename) /* find copy, too */
+ diff_rename_pool_add(&stay, p->one);
+ }
+ if (created.nr == 0)
+ goto cleanup; /* nothing to do */
+
+ /* We really want to cull the candidates list early
+ * with cheap tests in order to avoid doing deltas.
+ *
+ * With the current callers, we should not have already
+ * matched entries at this point, but it is nonetheless
+ * checked for sanity.
+ */
+ for (i = 0; i < created.nr; i++) {
+ if (created.s[i]->xfrm_flags & RENAME_DST_MATCHED)
+ continue; /* we have matched exactly already */
+ for (h = 0; h < sizeof(srcs)/sizeof(srcs[0]); h++) {
+ struct diff_rename_pool *p = srcs[h];
+ for (j = 0; j < p->nr; j++) {
+ if (!is_exact_match(p->s[j], created.s[i]))
+ continue;
+ record_rename_pair(&outq,
+ p->s[j], created.s[i], h,
+ MAX_SCORE);
+ break; /* we are done with this entry */
+ }
+ }
+ }
+ debug_queue("done detecting exact", &outq);
+
+ /* Have we run out the created file pool? If so we can avoid
+ * doing the delta matrix altogether.
+ */
+ if (outq.nr == created.nr)
+ goto flush_rest;
+
+ num_create = (created.nr - outq.nr);
+ num_src = deleted.nr + stay.nr;
+ mx = xmalloc(sizeof(*mx) * num_create * num_src);
+ for (dst_cnt = i = 0; i < created.nr; i++) {
+ int base = dst_cnt * num_src;
+ if (created.s[i]->xfrm_flags & RENAME_DST_MATCHED)
+ continue; /* dealt with exact match already. */
+ for (src_cnt = h = 0; h < sizeof(srcs)/sizeof(srcs[0]); h++) {
+ struct diff_rename_pool *p = srcs[h];
+ for (j = 0; j < p->nr; j++, src_cnt++) {
+ struct diff_score *m = &mx[base + src_cnt];
+ m->src = p->s[j];
+ m->dst = created.s[i];
+ m->score = estimate_similarity(m->src, m->dst,
+ minimum_score);
+ m->rank = h;
+ }
+ }
+ dst_cnt++;
+ }
+ /* cost matrix sorted by most to least similar pair */
+ qsort(mx, num_create * num_src, sizeof(*mx), score_compare);
+ for (i = 0; i < num_create * num_src; i++) {
+ if (mx[i].dst->xfrm_flags & RENAME_DST_MATCHED)
+ continue; /* alreayd done, either exact or fuzzy. */
+ if (mx[i].score < minimum_score)
+ continue;
+ record_rename_pair(&outq,
+ mx[i].src, mx[i].dst, mx[i].rank,
+ mx[i].score);
+ }
+ free(mx);
+ debug_queue("done detecting fuzzy", &outq);
+
+ flush_rest:
+ /* At this point, we have found some renames and copies and they
+ * are kept in outq. The original list is still in *q.
+ *
+ * Scan the original list and move them into the outq; we will sort
+ * outq and swap it into the queue supplied to pass that to
+ * downstream, so we assign the sort keys in this loop.
+ *
+ * See comments at the top of record_rename_pair for numbers used
+ * to assign xfrm_work.
+ *
+ * Note that we have not annotated the diff_file_pair with any comment
+ * so there is nothing other than p to free.
+ */
+ for (i = 0; i < q->nr; i++) {
+ struct diff_file_pair *dp, *p = q->queue[i];
+ if (!p->one->file_valid) {
+ if (p->two->file_valid) {
+ /* creation */
+ dp = diff_queue(&outq, p->one, p->two);
+ dp->xfrm_work = 4;
+ }
+ /* otherwise it is a nonsense; just ignore it */
+ }
+ else if (!p->two->file_valid) {
+ /* deletion */
+ dp = diff_queue(&outq, p->one, p->two);
+ dp->xfrm_work = 2;
+ }
+ else {
+ /* modification, or stay as is */
+ dp = diff_queue(&outq, p->one, p->two);
+ dp->xfrm_work = 4;
+ }
+ free(p);
+ }
+ debug_queue("done copying original", &outq);
+
+ /* Sort outq */
+ qsort(outq.queue, outq.nr, sizeof(outq.queue[0]), rank_compare);
+
+ debug_queue("done sorting", &outq);
+
+ free(q->queue);
+ q->nr = q->alloc = 0;
+ q->queue = NULL;
+
+ /* Copy it out to q, removing duplicates. */
+ for (i = 0; i < outq.nr; i++) {
+ struct diff_file_pair *p = outq.queue[i];
+ if (!p->one->file_valid) {
+ /* created */
+ if (p->two->xfrm_flags & RENAME_DST_MATCHED)
+ ; /* rename/copy created it already */
+ else
+ diff_queue(q, p->one, p->two);
+ }
+ else if (!p->two->file_valid) {
+ /* deleted */
+ if (p->one->xfrm_flags & RENAME_SRC_GONE)
+ ; /* rename/copy deleted it already */
+ else
+ diff_queue(q, p->one, p->two);
+ }
+ else if (strcmp(p->one->path, p->two->path)) {
+ /* rename or copy */
+ struct diff_file_pair *dp =
+ diff_queue(q, p->one, p->two);
+ int msglen = (strlen(p->one->path) +
+ strlen(p->two->path) + 100);
+ int score = (p->xfrm_work >> RENAME_SCORE_SHIFT);
+ dp->xfrm_msg = xmalloc(msglen);
+
+ /* if we have a later entry that is a rename/copy
+ * that depends on p->one, then we copy here.
+ * otherwise we rename it.
+ */
+ if (needs_to_stay(&outq, i+1, p->one)) {
+ /* copy it */
+ sprintf(dp->xfrm_msg,
+ "similarity index %d%%\n"
+ "copy from %s\n"
+ "copy to %s\n",
+ (int)(0.5 + score * 100 / MAX_SCORE),
+ p->one->path, p->two->path);
+ }
+ else {
+ /* rename it, and mark it as gone. */
+ p->one->xfrm_flags |= RENAME_SRC_GONE;
+ sprintf(dp->xfrm_msg,
+ "similarity index %d%%\n"
+ "rename old %s\n"
+ "rename new %s\n",
+ (int)(0.5 + score * 100 / MAX_SCORE),
+ p->one->path, p->two->path);
+ }
+ }
+ else
+ /* otherwise it is a modified (or stayed) entry */
+ diff_queue(q, p->one, p->two);
+ free(p);
+ }
+
+ free(outq.queue);
+ debug_queue("done collapsing", q);
+
+ cleanup:
+ free(created.s);
+ free(deleted.s);
+ free(stay.s);
+ return;
+}
projects / git.git / commitdiff