diff options
-rw-r--r-- | Documentation/git-diff-cache.txt | 5 | ||||
-rw-r--r-- | Documentation/git-diff-files.txt | 5 | ||||
-rw-r--r-- | Documentation/git-diff-helper.txt | 4 | ||||
-rw-r--r-- | Documentation/git-diff-tree.txt | 6 | ||||
-rw-r--r-- | Makefile | 5 | ||||
-rw-r--r-- | diff-cache.c | 8 | ||||
-rw-r--r-- | diff-files.c | 7 | ||||
-rw-r--r-- | diff-helper.c | 25 | ||||
-rw-r--r-- | diff-tree.c | 8 | ||||
-rw-r--r-- | diff.c | 699 | ||||
-rw-r--r-- | diffcore-rename.c | 443 | ||||
-rw-r--r-- | diffcore.h | 60 | ||||
-rwxr-xr-x | git-apply-patch-script | 2 | ||||
-rwxr-xr-x | t/t0000-basic.sh | 2 | ||||
-rwxr-xr-x | t/t4001-diff-rename.sh | 4 | ||||
-rw-r--r-- | t/t4003-diff-rename-1.sh | 93 |
16 files changed, 944 insertions, 432 deletions
diff --git a/Documentation/git-diff-cache.txt b/Documentation/git-diff-cache.txt index bd8a6e5c5e..e3ed7131a4 100644 --- a/Documentation/git-diff-cache.txt +++ b/Documentation/git-diff-cache.txt @@ -9,7 +9,7 @@ git-diff-cache - Compares content and mode of blobs between the cache and reposi SYNOPSIS -------- -'git-diff-cache' [-p] [-r] [-z] [-m] [-M] [-R] [--cached] <tree-ish> +'git-diff-cache' [-p] [-r] [-z] [-m] [-M] [-R] [-C] [--cached] <tree-ish> DESCRIPTION ----------- @@ -36,6 +36,9 @@ OPTIONS -M:: Detect renames; implies -p. +-C:: + Detect copies as well as renames; implies -p. + -R:: Output diff in reverse. diff --git a/Documentation/git-diff-files.txt b/Documentation/git-diff-files.txt index f79820a65c..1eae3d0333 100644 --- a/Documentation/git-diff-files.txt +++ b/Documentation/git-diff-files.txt @@ -9,7 +9,7 @@ git-diff-files - Compares files in the working tree and the cache SYNOPSIS -------- -'git-diff-files' [-p] [-q] [-r] [-z] [-M] [-R] [<pattern>...] +'git-diff-files' [-p] [-q] [-r] [-z] [-M] [-C] [-R] [<pattern>...] DESCRIPTION ----------- @@ -32,6 +32,9 @@ OPTIONS -M:: Detect renames; implies -p. +-C:: + Detect copies as well as renames; implies -p. + -r:: This flag does not mean anything. It is there only to match git-diff-tree. Unlike git-diff-tree, git-diff-files always looks diff --git a/Documentation/git-diff-helper.txt b/Documentation/git-diff-helper.txt index 800d71a386..302789e9d1 100644 --- a/Documentation/git-diff-helper.txt +++ b/Documentation/git-diff-helper.txt @@ -9,7 +9,7 @@ git-diff-helper - Generates patch format output for git-diff-* SYNOPSIS -------- -'git-diff-helper' [-z] [-R] [-M] +'git-diff-helper' [-z] [-R] [-M] [-C] DESCRIPTION ----------- @@ -34,6 +34,8 @@ OPTIONS -M:: Detect renames. +-C:: + Detect copies as well as renames. See Also -------- diff --git a/Documentation/git-diff-tree.txt b/Documentation/git-diff-tree.txt index 244f285137..f4e95a97c3 100644 --- a/Documentation/git-diff-tree.txt +++ b/Documentation/git-diff-tree.txt @@ -9,7 +9,7 @@ git-diff-tree - Compares the content and mode of blobs found via two tree object SYNOPSIS -------- -'git-diff-tree' [-p] [-r] [-z] [--stdin] [-M] [-R] [-m] [-s] [-v] <tree-ish> <tree-ish> [<pattern>]\* +'git-diff-tree' [-p] [-r] [-z] [--stdin] [-M] [-R] [-C] [-m] [-s] [-v] <tree-ish> <tree-ish> [<pattern>]\* DESCRIPTION ----------- @@ -36,6 +36,10 @@ OPTIONS -M:: Detect renames; implies -p, in turn implying also '-r'. +-C:: + Detect copies as well as renames; implies -p, in turn + implying also '-r'. + -R:: Output diff in reverse. @@ -45,7 +45,7 @@ LIB_H += strbuf.h LIB_OBJS += strbuf.o LIB_H += diff.h -LIB_OBJS += diff.o +LIB_OBJS += diff.o diffcore-rename.o LIB_OBJS += gitenv.o @@ -121,9 +121,10 @@ object.o: $(LIB_H) read-cache.o: $(LIB_H) sha1_file.o: $(LIB_H) usage.o: $(LIB_H) -diff.o: $(LIB_H) strbuf.o: $(LIB_H) gitenv.o: $(LIB_H) +diff.o: $(LIB_H) +diffcore-rename.o : $(LIB_H) test: all make -C t/ all diff --git a/diff-cache.c b/diff-cache.c index ff310ab357..383302abbc 100644 --- a/diff-cache.c +++ b/diff-cache.c @@ -153,7 +153,7 @@ static void mark_merge_entries(void) } static char *diff_cache_usage = -"git-diff-cache [-p] [-r] [-z] [-m] [-M] [-R] [--cached] <tree-ish>"; +"git-diff-cache [-p] [-r] [-z] [-m] [-M] [-C] [-R] [--cached] <tree-ish>"; int main(int argc, char **argv) { @@ -180,6 +180,12 @@ int main(int argc, char **argv) diff_score_opt = diff_scoreopt_parse(arg); continue; } + if (!strncmp(arg, "-C", 2)) { + generate_patch = 1; + detect_rename = 2; + diff_score_opt = diff_scoreopt_parse(arg); + continue; + } if (!strcmp(arg, "-z")) { line_termination = '\0'; continue; diff --git a/diff-files.c b/diff-files.c index c36bcf25bc..d020254922 100644 --- a/diff-files.c +++ b/diff-files.c @@ -7,7 +7,7 @@ #include "diff.h" static const char *diff_files_usage = -"git-diff-files [-p] [-q] [-r] [-z] [-M] [-R] [paths...]"; +"git-diff-files [-p] [-q] [-r] [-z] [-M] [-C] [-R] [paths...]"; static int generate_patch = 0; static int line_termination = '\n'; @@ -71,6 +71,11 @@ int main(int argc, char **argv) diff_score_opt = diff_scoreopt_parse(argv[1]); detect_rename = generate_patch = 1; } + else if (!strncmp(argv[1], "-C", 2)) { + diff_score_opt = diff_scoreopt_parse(argv[1]); + detect_rename = 2; + generate_patch = 1; + } else usage(diff_files_usage); argv++; argc--; diff --git a/diff-helper.c b/diff-helper.c index ea9aefab28..4e966db769 100644 --- a/diff-helper.c +++ b/diff-helper.c @@ -8,6 +8,7 @@ static int detect_rename = 0; static int diff_score_opt = 0; +static int generate_patch = 1; static int parse_oneside_change(const char *cp, int *mode, unsigned char *sha1, char *path) @@ -20,7 +21,8 @@ static int parse_oneside_change(const char *cp, int *mode, cp++; } *mode = m; - if (strncmp(cp, "\tblob\t", 6) && strncmp(cp, " blob ", 6)) + if (strncmp(cp, "\tblob\t", 6) && strncmp(cp, " blob ", 6) && + strncmp(cp, "\ttree\t", 6) && strncmp(cp, " tree ", 6)) return -1; cp += 6; if (get_sha1_hex(cp, sha1)) @@ -44,11 +46,13 @@ static int parse_diff_raw_output(const char *buf) diff_unmerge(cp + 1); break; case '+': - parse_oneside_change(cp, &new_mode, new_sha1, path); + if (parse_oneside_change(cp, &new_mode, new_sha1, path)) + return -1; diff_addremove('+', new_mode, new_sha1, path, NULL); break; case '-': - parse_oneside_change(cp, &old_mode, old_sha1, path); + if (parse_oneside_change(cp, &old_mode, old_sha1, path)) + return -1; diff_addremove('-', old_mode, old_sha1, path, NULL); break; case '*': @@ -64,7 +68,8 @@ static int parse_diff_raw_output(const char *buf) new_mode = (new_mode << 3) | (ch - '0'); cp++; } - if (strncmp(cp, "\tblob\t", 6) && strncmp(cp, " blob ", 6)) + if (strncmp(cp, "\tblob\t", 6) && strncmp(cp, " blob ", 6) && + strncmp(cp, "\ttree\t", 6) && strncmp(cp, " tree ", 6)) return -1; cp += 6; if (get_sha1_hex(cp, old_sha1)) @@ -88,7 +93,7 @@ static int parse_diff_raw_output(const char *buf) } static const char *diff_helper_usage = - "git-diff-helper [-z] [-R] [-M] paths..."; + "git-diff-helper [-z] [-R] [-M] [-C] paths..."; int main(int ac, const char **av) { struct strbuf sb; @@ -102,17 +107,25 @@ int main(int ac, const char **av) { reverse = 1; else if (av[1][1] == 'z') line_termination = 0; + else if (av[1][1] == 'p') /* hidden from the help */ + generate_patch = 0; else if (av[1][1] == 'M') { detect_rename = 1; diff_score_opt = diff_scoreopt_parse(av[1]); } + else if (av[1][1] == 'C') { + detect_rename = 2; + diff_score_opt = diff_scoreopt_parse(av[1]); + } else usage(diff_helper_usage); ac--; av++; } /* the remaining parameters are paths patterns */ - diff_setup(detect_rename, diff_score_opt, reverse, -1, av+1, ac-1); + diff_setup(detect_rename, diff_score_opt, reverse, + (generate_patch ? -1 : line_termination), + av+1, ac-1); while (1) { int status; diff --git a/diff-tree.c b/diff-tree.c index 5aa0d5e942..aa4944686b 100644 --- a/diff-tree.c +++ b/diff-tree.c @@ -430,7 +430,7 @@ static int diff_tree_stdin(char *line) } static char *diff_tree_usage = -"git-diff-tree [-p] [-r] [-z] [--stdin] [-M] [-R] [-m] [-s] [-v] <tree-ish> <tree-ish>"; +"git-diff-tree [-p] [-r] [-z] [--stdin] [-M] [-C] [-R] [-m] [-s] [-v] <tree-ish> <tree-ish>"; int main(int argc, char **argv) { @@ -478,6 +478,12 @@ int main(int argc, char **argv) diff_score_opt = diff_scoreopt_parse(arg); continue; } + if (!strncmp(arg, "-C", 2)) { + detect_rename = 2; + recursive = generate_patch = 1; + diff_score_opt = diff_scoreopt_parse(arg); + continue; + } if (!strcmp(arg, "-z")) { line_termination = '\0'; continue; @@ -7,12 +7,17 @@ #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) { @@ -77,26 +82,16 @@ static char *sq_expand(const char *src) } 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'"; @@ -151,14 +146,9 @@ static void builtin_diff(const char *name_a, 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. @@ -169,6 +159,28 @@ static void builtin_diff(const char *name_a, 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 @@ -201,13 +213,86 @@ static int work_tree_matches(const char *name, const unsigned char *sha1) 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, @@ -231,7 +316,7 @@ static void prep_temp_blob(struct diff_tempfile *temp, 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: @@ -245,13 +330,12 @@ static void prepare_temp_file(const char *name, } 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; @@ -263,31 +347,27 @@ static void prepare_temp_file(const char *name, 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); } } @@ -307,13 +387,6 @@ static void remove_tempfile_on_signal(int signo) 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; @@ -341,9 +414,9 @@ static int matches_pathspec(const char *name) */ 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; @@ -373,7 +446,7 @@ static void run_external_diff(const char *name, 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; @@ -383,9 +456,11 @@ static void run_external_diff(const char *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 @@ -395,7 +470,7 @@ static void run_external_diff(const char *name, * 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); @@ -418,335 +493,166 @@ static void run_external_diff(const char *name, 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 |