From 6973dcaee76ef7b7bfcabd2f26e76205aae07858 Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Fri, 21 Apr 2006 23:57:45 -0700 Subject: [PATCH] Libify diff-files. This is the first installment to libify diff brothers. The updated diff-files uses revision.c::setup_revisions() infrastructure to parse its command line arguments, which means the pathname arguments are checked more strictly than before. The tests are adjusted to separate possibly missing paths from the rest of arguments with double-dashes, to show the kosher way. As Linus pointed out, renaming diff.c to diff-lib.c was simply stupid, so I am renaming it back. The new diff-lib.c is to contain pieces extracted from diff brothers. Signed-off-by: Junio C Hamano --- Makefile | 2 +- diff-files.c | 212 +--- diff-lib.c | 1862 ++------------------------------- diff.c | 1795 +++++++++++++++++++++++++++++++ diff.h | 7 +- t/t1001-read-tree-m-2way.sh | 2 +- t/t1002-read-tree-m-u-2way.sh | 2 +- 7 files changed, 1929 insertions(+), 1953 deletions(-) create mode 100644 diff.c diff --git a/Makefile b/Makefile index d9a3a82fe..0924f84c4 100644 --- a/Makefile +++ b/Makefile @@ -199,7 +199,7 @@ LIB_H = \ tree-walk.h log-tree.h DIFF_OBJS = \ - diff-lib.o diffcore-break.o diffcore-order.o \ + diff.o diff-lib.o diffcore-break.o diffcore-order.o \ diffcore-pickaxe.o diffcore-rename.o tree-diff.o combine-diff.o \ diffcore-delta.o log-tree.o diff --git a/diff-files.c b/diff-files.c index ffbef48b2..b9d193d50 100644 --- a/diff-files.c +++ b/diff-files.c @@ -12,203 +12,43 @@ static const char diff_files_usage[] = "git-diff-files [-q] [-0/-1/2/3 |-c|--cc] [] [...]" COMMON_DIFF_OPTIONS_HELP; -static struct rev_info rev; -static int silent = 0; -static int diff_unmerged_stage = 2; -static int combine_merges = 0; -static int dense_combined_merges = 0; - -static void show_unmerge(const char *path) -{ - diff_unmerge(&rev.diffopt, path); -} - -static void show_file(int pfx, struct cache_entry *ce) -{ - diff_addremove(&rev.diffopt, pfx, ntohl(ce->ce_mode), - ce->sha1, ce->name, NULL); -} - -static void show_modified(int oldmode, int mode, - const unsigned char *old_sha1, const unsigned char *sha1, - char *path) -{ - diff_change(&rev.diffopt, oldmode, mode, old_sha1, sha1, path, NULL); -} - int main(int argc, const char **argv) { - const char **pathspec; - const char *prefix = setup_git_directory(); - int entries, i; + struct rev_info rev; + int silent = 0; git_config(git_diff_config); - diff_setup(&rev.diffopt); + init_revisions(&rev); + rev.abbrev = 0; + + argc = setup_revisions(argc, argv, &rev, NULL); while (1 < argc && argv[1][0] == '-') { - if (!strcmp(argv[1], "--")) { - argv++; - argc--; - break; - } - if (!strcmp(argv[1], "-0")) - diff_unmerged_stage = 0; - else if (!strcmp(argv[1], "-1")) - diff_unmerged_stage = 1; - else if (!strcmp(argv[1], "-2")) - diff_unmerged_stage = 2; - else if (!strcmp(argv[1], "-3")) - diff_unmerged_stage = 3; - else if (!strcmp(argv[1], "--base")) - diff_unmerged_stage = 1; + if (!strcmp(argv[1], "--base")) + rev.max_count = 1; else if (!strcmp(argv[1], "--ours")) - diff_unmerged_stage = 2; + rev.max_count = 2; else if (!strcmp(argv[1], "--theirs")) - diff_unmerged_stage = 3; + rev.max_count = 3; else if (!strcmp(argv[1], "-q")) silent = 1; - else if (!strcmp(argv[1], "-r")) - ; /* no-op */ - else if (!strcmp(argv[1], "-s")) - ; /* no-op */ - else if (!strcmp(argv[1], "-c")) - combine_merges = 1; - else if (!strcmp(argv[1], "--cc")) - dense_combined_merges = combine_merges = 1; - else { - int diff_opt_cnt; - diff_opt_cnt = diff_opt_parse(&rev.diffopt, - argv+1, argc-1); - if (diff_opt_cnt < 0) - usage(diff_files_usage); - else if (diff_opt_cnt) { - argv += diff_opt_cnt; - argc -= diff_opt_cnt; - continue; - } - else - usage(diff_files_usage); - } + else + usage(diff_files_usage); argv++; argc--; } - if (dense_combined_merges) - rev.diffopt.output_format = DIFF_FORMAT_PATCH; - - /* Find the directory, and set up the pathspec */ - pathspec = get_pathspec(prefix, argv + 1); - entries = read_cache(); - - if (diff_setup_done(&rev.diffopt) < 0) + /* + * Make sure there are NO revision (i.e. pending object) parameter, + * rev.max_count is reasonable (0 <= n <= 3), + * there is no other revision filtering parameters. + */ + if (rev.pending_objects || + rev.min_age != -1 || rev.max_age != -1) usage(diff_files_usage); - - /* At this point, if argc == 1, then we are doing everything. - * Otherwise argv[1] .. argv[argc-1] have the explicit paths. + /* + * Backward compatibility wart - "diff-files -s" used to + * defeat the common diff option "-s" which asked for + * DIFF_FORMAT_NO_OUTPUT. */ - if (entries < 0) { - perror("read_cache"); - exit(1); - } - - for (i = 0; i < entries; i++) { - struct stat st; - unsigned int oldmode, newmode; - struct cache_entry *ce = active_cache[i]; - int changed; - - if (!ce_path_match(ce, pathspec)) - continue; - - if (ce_stage(ce)) { - struct { - struct combine_diff_path p; - struct combine_diff_parent filler[5]; - } combine; - int num_compare_stages = 0; - - combine.p.next = NULL; - combine.p.len = ce_namelen(ce); - combine.p.path = xmalloc(combine.p.len + 1); - memcpy(combine.p.path, ce->name, combine.p.len); - combine.p.path[combine.p.len] = 0; - combine.p.mode = 0; - memset(combine.p.sha1, 0, 20); - memset(&combine.p.parent[0], 0, - sizeof(combine.filler)); - - while (i < entries) { - struct cache_entry *nce = active_cache[i]; - int stage; - - if (strcmp(ce->name, nce->name)) - break; - - /* Stage #2 (ours) is the first parent, - * stage #3 (theirs) is the second. - */ - stage = ce_stage(nce); - if (2 <= stage) { - int mode = ntohl(nce->ce_mode); - num_compare_stages++; - memcpy(combine.p.parent[stage-2].sha1, - nce->sha1, 20); - combine.p.parent[stage-2].mode = - canon_mode(mode); - combine.p.parent[stage-2].status = - DIFF_STATUS_MODIFIED; - } - - /* diff against the proper unmerged stage */ - if (stage == diff_unmerged_stage) - ce = nce; - i++; - } - /* - * Compensate for loop update - */ - i--; - - if (combine_merges && num_compare_stages == 2) { - show_combined_diff(&combine.p, 2, - dense_combined_merges, - &rev); - free(combine.p.path); - continue; - } - free(combine.p.path); - - /* - * Show the diff for the 'ce' if we found the one - * from the desired stage. - */ - show_unmerge(ce->name); - if (ce_stage(ce) != diff_unmerged_stage) - continue; - } - - if (lstat(ce->name, &st) < 0) { - if (errno != ENOENT && errno != ENOTDIR) { - perror(ce->name); - continue; - } - if (silent) - continue; - show_file('-', ce); - continue; - } - changed = ce_match_stat(ce, &st, 0); - if (!changed && !rev.diffopt.find_copies_harder) - continue; - oldmode = ntohl(ce->ce_mode); - - newmode = canon_mode(st.st_mode); - if (!trust_executable_bit && - S_ISREG(newmode) && S_ISREG(oldmode) && - ((newmode ^ oldmode) == 0111)) - newmode = oldmode; - show_modified(oldmode, newmode, - ce->sha1, (changed ? null_sha1 : ce->sha1), - ce->name); - } - diffcore_std(&rev.diffopt); - diff_flush(&rev.diffopt); - return 0; + if (rev.diffopt.output_format == DIFF_FORMAT_NO_OUTPUT) + rev.diffopt.output_format = DIFF_FORMAT_RAW; + return run_diff_files(&rev, silent); } diff --git a/diff-lib.c b/diff-lib.c index 13b216f27..a28dd3dca 100644 --- a/diff-lib.c +++ b/diff-lib.c @@ -1,1795 +1,133 @@ /* * Copyright (C) 2005 Junio C Hamano */ -#include -#include -#include #include "cache.h" #include "quote.h" +#include "commit.h" #include "diff.h" #include "diffcore.h" -#include "xdiff-interface.h" - -static int use_size_cache; - -int diff_rename_limit_default = -1; - -int git_diff_config(const char *var, const char *value) -{ - if (!strcmp(var, "diff.renamelimit")) { - diff_rename_limit_default = git_config_int(var, value); - return 0; - } - - return git_default_config(var, value); -} - -static char *quote_one(const char *str) -{ - int needlen; - char *xp; - - if (!str) - return NULL; - needlen = quote_c_style(str, NULL, NULL, 0); - if (!needlen) - return strdup(str); - xp = xmalloc(needlen + 1); - quote_c_style(str, xp, NULL, 0); - return xp; -} - -static char *quote_two(const char *one, const char *two) -{ - int need_one = quote_c_style(one, NULL, NULL, 1); - int need_two = quote_c_style(two, NULL, NULL, 1); - char *xp; - - if (need_one + need_two) { - if (!need_one) need_one = strlen(one); - if (!need_two) need_one = strlen(two); - - xp = xmalloc(need_one + need_two + 3); - xp[0] = '"'; - quote_c_style(one, xp + 1, NULL, 1); - quote_c_style(two, xp + need_one + 1, NULL, 1); - strcpy(xp + need_one + need_two + 1, "\""); - return xp; - } - need_one = strlen(one); - need_two = strlen(two); - xp = xmalloc(need_one + need_two + 1); - strcpy(xp, one); - strcpy(xp + need_one, two); - return xp; -} - -static const char *external_diff(void) -{ - static const char *external_diff_cmd = NULL; - static int done_preparing = 0; - - if (done_preparing) - return external_diff_cmd; - external_diff_cmd = getenv("GIT_EXTERNAL_DIFF"); - done_preparing = 1; - return external_diff_cmd; -} - -#define TEMPFILE_PATH_LEN 50 - -static struct diff_tempfile { - const char *name; /* filename external diff should read from */ - char hex[41]; - char mode[10]; - char tmp_path[TEMPFILE_PATH_LEN]; -} diff_temp[2]; - -static int count_lines(const char *data, int size) -{ - int count, ch, completely_empty = 1, nl_just_seen = 0; - count = 0; - while (0 < size--) { - ch = *data++; - if (ch == '\n') { - count++; - nl_just_seen = 1; - completely_empty = 0; - } - else { - nl_just_seen = 0; - completely_empty = 0; - } - } - if (completely_empty) - return 0; - if (!nl_just_seen) - count++; /* no trailing newline */ - return count; -} - -static void print_line_count(int count) -{ - switch (count) { - case 0: - printf("0,0"); - break; - case 1: - printf("1"); - break; - default: - printf("1,%d", count); - break; - } -} - -static void copy_file(int prefix, const char *data, int size) -{ - int ch, nl_just_seen = 1; - while (0 < size--) { - ch = *data++; - if (nl_just_seen) - putchar(prefix); - putchar(ch); - if (ch == '\n') - nl_just_seen = 1; - else - nl_just_seen = 0; - } - if (!nl_just_seen) - printf("\n\\ No newline at end of file\n"); -} - -static void emit_rewrite_diff(const char *name_a, - const char *name_b, - struct diff_filespec *one, - struct diff_filespec *two) -{ - int lc_a, lc_b; - diff_populate_filespec(one, 0); - diff_populate_filespec(two, 0); - lc_a = count_lines(one->data, one->size); - lc_b = count_lines(two->data, two->size); - printf("--- %s\n+++ %s\n@@ -", name_a, name_b); - print_line_count(lc_a); - printf(" +"); - print_line_count(lc_b); - printf(" @@\n"); - if (lc_a) - copy_file('-', one->data, one->size); - if (lc_b) - copy_file('+', two->data, two->size); -} - -static int fill_mmfile(mmfile_t *mf, struct diff_filespec *one) -{ - if (!DIFF_FILE_VALID(one)) { - mf->ptr = ""; /* does not matter */ - mf->size = 0; - return 0; - } - else if (diff_populate_filespec(one, 0)) - return -1; - mf->ptr = one->data; - mf->size = one->size; - return 0; -} - -struct emit_callback { - const char **label_path; -}; - -static int fn_out(void *priv, mmbuffer_t *mb, int nbuf) -{ - int i; - struct emit_callback *ecbdata = priv; - - if (ecbdata->label_path[0]) { - printf("--- %s\n", ecbdata->label_path[0]); - printf("+++ %s\n", ecbdata->label_path[1]); - ecbdata->label_path[0] = ecbdata->label_path[1] = NULL; - } - for (i = 0; i < nbuf; i++) - if (!fwrite(mb[i].ptr, mb[i].size, 1, stdout)) - return -1; - return 0; -} - -static char *pprint_rename(const char *a, const char *b) -{ - const char *old = a; - const char *new = b; - char *name = NULL; - int pfx_length, sfx_length; - int len_a = strlen(a); - int len_b = strlen(b); - - /* Find common prefix */ - pfx_length = 0; - while (*old && *new && *old == *new) { - if (*old == '/') - pfx_length = old - a + 1; - old++; - new++; - } - - /* Find common suffix */ - old = a + len_a; - new = b + len_b; - sfx_length = 0; - while (a <= old && b <= new && *old == *new) { - if (*old == '/') - sfx_length = len_a - (old - a); - old--; - new--; - } - - /* - * pfx{mid-a => mid-b}sfx - * {pfx-a => pfx-b}sfx - * pfx{sfx-a => sfx-b} - * name-a => name-b - */ - if (pfx_length + sfx_length) { - name = xmalloc(len_a + len_b - pfx_length - sfx_length + 7); - sprintf(name, "%.*s{%.*s => %.*s}%s", - pfx_length, a, - len_a - pfx_length - sfx_length, a + pfx_length, - len_b - pfx_length - sfx_length, b + pfx_length, - a + len_a - sfx_length); - } - else { - name = xmalloc(len_a + len_b + 5); - sprintf(name, "%s => %s", a, b); - } - return name; -} - -struct diffstat_t { - struct xdiff_emit_state xm; - - int nr; - int alloc; - struct diffstat_file { - char *name; - unsigned is_unmerged:1; - unsigned is_binary:1; - unsigned is_renamed:1; - unsigned int added, deleted; - } **files; -}; - -static struct diffstat_file *diffstat_add(struct diffstat_t *diffstat, - const char *name_a, - const char *name_b) -{ - struct diffstat_file *x; - x = xcalloc(sizeof (*x), 1); - if (diffstat->nr == diffstat->alloc) { - diffstat->alloc = alloc_nr(diffstat->alloc); - diffstat->files = xrealloc(diffstat->files, - diffstat->alloc * sizeof(x)); - } - diffstat->files[diffstat->nr++] = x; - if (name_b) { - x->name = pprint_rename(name_a, name_b); - x->is_renamed = 1; - } - else - x->name = strdup(name_a); - return x; -} - -static void diffstat_consume(void *priv, char *line, unsigned long len) -{ - struct diffstat_t *diffstat = priv; - struct diffstat_file *x = diffstat->files[diffstat->nr - 1]; - - if (line[0] == '+') - x->added++; - else if (line[0] == '-') - x->deleted++; -} - -static const char pluses[] = "++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++"; -static const char minuses[]= "----------------------------------------------------------------------"; - -static void show_stats(struct diffstat_t* data) -{ - char *prefix = ""; - int i, len, add, del, total, adds = 0, dels = 0; - int max, max_change = 0, max_len = 0; - int total_files = data->nr; - - if (data->nr == 0) - return; - - for (i = 0; i < data->nr; i++) { - struct diffstat_file *file = data->files[i]; - - len = strlen(file->name); - if (max_len < len) - max_len = len; - - if (file->is_binary || file->is_unmerged) - continue; - if (max_change < file->added + file->deleted) - max_change = file->added + file->deleted; - } - - for (i = 0; i < data->nr; i++) { - char *name = data->files[i]->name; - int added = data->files[i]->added; - int deleted = data->files[i]->deleted; - - if (0 < (len = quote_c_style(name, NULL, NULL, 0))) { - char *qname = xmalloc(len + 1); - quote_c_style(name, qname, NULL, 0); - free(name); - data->files[i]->name = name = qname; - } - - /* - * "scale" the filename - */ - len = strlen(name); - max = max_len; - if (max > 50) - max = 50; - if (len > max) { - char *slash; - prefix = "..."; - max -= 3; - name += len - max; - slash = strchr(name, '/'); - if (slash) - name = slash; - } - len = max; - - /* - * scale the add/delete - */ - max = max_change; - if (max + len > 70) - max = 70 - len; - - if (data->files[i]->is_binary) { - printf(" %s%-*s | Bin\n", prefix, len, name); - goto free_diffstat_file; - } - else if (data->files[i]->is_unmerged) { - printf(" %s%-*s | Unmerged\n", prefix, len, name); - goto free_diffstat_file; - } - else if (!data->files[i]->is_renamed && - (added + deleted == 0)) { - total_files--; - goto free_diffstat_file; - } - - add = added; - del = deleted; - total = add + del; - adds += add; - dels += del; - - if (max_change > 0) { - total = (total * max + max_change / 2) / max_change; - add = (add * max + max_change / 2) / max_change; - del = total - add; - } - printf(" %s%-*s |%5d %.*s%.*s\n", prefix, - len, name, added + deleted, - add, pluses, del, minuses); - free_diffstat_file: - free(data->files[i]->name); - free(data->files[i]); - } - free(data->files); - printf(" %d files changed, %d insertions(+), %d deletions(-)\n", - total_files, adds, dels); -} - -#define FIRST_FEW_BYTES 8000 -static int mmfile_is_binary(mmfile_t *mf) -{ - long sz = mf->size; - if (FIRST_FEW_BYTES < sz) - sz = FIRST_FEW_BYTES; - if (memchr(mf->ptr, 0, sz)) - return 1; - return 0; -} - -static void builtin_diff(const char *name_a, - const char *name_b, - struct diff_filespec *one, - struct diff_filespec *two, - const char *xfrm_msg, - int complete_rewrite) -{ - mmfile_t mf1, mf2; - const char *lbl[2]; - char *a_one, *b_two; - - a_one = quote_two("a/", name_a); - b_two = quote_two("b/", name_b); - lbl[0] = DIFF_FILE_VALID(one) ? a_one : "/dev/null"; - lbl[1] = DIFF_FILE_VALID(two) ? b_two : "/dev/null"; - printf("diff --git %s %s\n", a_one, b_two); - if (lbl[0][0] == '/') { - /* /dev/null */ - printf("new file mode %06o\n", two->mode); - if (xfrm_msg && xfrm_msg[0]) - puts(xfrm_msg); - } - else if (lbl[1][0] == '/') { - printf("deleted file mode %06o\n", one->mode); - if (xfrm_msg && xfrm_msg[0]) - puts(xfrm_msg); - } - else { - if (one->mode != two->mode) { - printf("old mode %06o\n", one->mode); - printf("new mode %06o\n", two->mode); - } - if (xfrm_msg && xfrm_msg[0]) - puts(xfrm_msg); - /* - * we do not run diff between different kind - * of objects. - */ - if ((one->mode ^ two->mode) & S_IFMT) - goto free_ab_and_return; - if (complete_rewrite) { - emit_rewrite_diff(name_a, name_b, one, two); - goto free_ab_and_return; - } - } - - if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0) - die("unable to read files to diff"); - - if (mmfile_is_binary(&mf1) || mmfile_is_binary(&mf2)) - printf("Binary files %s and %s differ\n", lbl[0], lbl[1]); - else { - /* Crazy xdl interfaces.. */ - const char *diffopts = getenv("GIT_DIFF_OPTS"); - xpparam_t xpp; - xdemitconf_t xecfg; - xdemitcb_t ecb; - struct emit_callback ecbdata; - - ecbdata.label_path = lbl; - xpp.flags = XDF_NEED_MINIMAL; - xecfg.ctxlen = 3; - xecfg.flags = XDL_EMIT_FUNCNAMES; - if (!diffopts) - ; - else if (!strncmp(diffopts, "--unified=", 10)) - xecfg.ctxlen = strtoul(diffopts + 10, NULL, 10); - else if (!strncmp(diffopts, "-u", 2)) - xecfg.ctxlen = strtoul(diffopts + 2, NULL, 10); - ecb.outf = fn_out; - ecb.priv = &ecbdata; - xdl_diff(&mf1, &mf2, &xpp, &xecfg, &ecb); - } - - free_ab_and_return: - free(a_one); - free(b_two); - return; -} - -static void builtin_diffstat(const char *name_a, const char *name_b, - struct diff_filespec *one, - struct diff_filespec *two, - struct diffstat_t *diffstat) -{ - mmfile_t mf1, mf2; - struct diffstat_file *data; - - data = diffstat_add(diffstat, name_a, name_b); - - if (!one || !two) { - data->is_unmerged = 1; - return; - } - - if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0) - die("unable to read files to diff"); - - if (mmfile_is_binary(&mf1) || mmfile_is_binary(&mf2)) - data->is_binary = 1; - else { - /* Crazy xdl interfaces.. */ - xpparam_t xpp; - xdemitconf_t xecfg; - xdemitcb_t ecb; - - xpp.flags = XDF_NEED_MINIMAL; - xecfg.ctxlen = 0; - xecfg.flags = 0; - ecb.outf = xdiff_outf; - ecb.priv = diffstat; - xdl_diff(&mf1, &mf2, &xpp, &xecfg, &ecb); - } -} - -struct diff_filespec *alloc_filespec(const char *path) -{ - int namelen = strlen(path); - struct diff_filespec *spec = xmalloc(sizeof(*spec) + namelen + 1); - - memset(spec, 0, sizeof(*spec)); - spec->path = (char *)(spec + 1); - memcpy(spec->path, path, namelen+1); - return spec; -} - -void fill_filespec(struct diff_filespec *spec, const unsigned char *sha1, - unsigned short mode) -{ - if (mode) { - spec->mode = canon_mode(mode); - memcpy(spec->sha1, sha1, 20); - spec->sha1_valid = !!memcmp(sha1, null_sha1, 20); - } -} +#include "revision.h" /* - * 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 - * prepare_temp_file() does not have to inflate and extract. + * diff-files */ -static int work_tree_matches(const char *name, const unsigned char *sha1) -{ - struct cache_entry *ce; - struct stat st; - int pos, len; - - /* We do not read the cache ourselves here, because the - * benchmark with my previous version that always reads cache - * shows that it makes things worse for diff-tree comparing - * two linux-2.6 kernel trees in an already checked out work - * tree. This is because most diff-tree comparisons deal with - * only a small number of files, while reading the cache is - * expensive for a large project, and its cost outweighs the - * savings we get by not inflating the object to a temporary - * file. Practically, this code only helps when we are used - * by diff-cache --cached, which does read the cache before - * calling us. - */ - if (!active_cache) - return 0; - - len = strlen(name); - pos = cache_name_pos(name, len); - if (pos < 0) - return 0; - ce = active_cache[pos]; - if ((lstat(name, &st) < 0) || - !S_ISREG(st.st_mode) || /* careful! */ - ce_match_stat(ce, &st, 0) || - 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 pair. - */ - return 1; -} - -static struct sha1_size_cache { - unsigned char sha1[20]; - unsigned long size; -} **sha1_size_cache; -static int sha1_size_cache_nr, sha1_size_cache_alloc; -static struct sha1_size_cache *locate_size_cache(unsigned char *sha1, - int find_only, - unsigned long size) +int run_diff_files(struct rev_info *revs, int silent_on_removed) { - int first, last; - struct sha1_size_cache *e; + int entries, i; + int diff_unmerged_stage = revs->max_count; - first = 0; - last = sha1_size_cache_nr; - while (last > first) { - int cmp, next = (last + first) >> 1; - e = sha1_size_cache[next]; - cmp = memcmp(e->sha1, sha1, 20); - if (!cmp) - return e; - if (cmp < 0) { - last = next; - continue; - } - first = next+1; - } - /* not found */ - if (find_only) - return NULL; - /* insert to make it at "first" */ - if (sha1_size_cache_alloc <= sha1_size_cache_nr) { - sha1_size_cache_alloc = alloc_nr(sha1_size_cache_alloc); - sha1_size_cache = xrealloc(sha1_size_cache, - sha1_size_cache_alloc * - sizeof(*sha1_size_cache)); - } - sha1_size_cache_nr++; - if (first < sha1_size_cache_nr) - memmove(sha1_size_cache + first + 1, sha1_size_cache + first, - (sha1_size_cache_nr - first - 1) * - sizeof(*sha1_size_cache)); - e = xmalloc(sizeof(struct sha1_size_cache)); - sha1_size_cache[first] = e; - memcpy(e->sha1, sha1, 20); - e->size = size; - return e; -} - -/* - * 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 size_only) -{ - int err = 0; - if (!DIFF_FILE_VALID(s)) - die("internal error: asking to populate invalid file."); - if (S_ISDIR(s->mode)) + if (diff_unmerged_stage < 0) + diff_unmerged_stage = 2; + entries = read_cache(); + if (entries < 0) { + perror("read_cache"); return -1; - - if (!use_size_cache) - size_only = 0; - - 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 (size_only) - return 0; - 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); - close(fd); - if (s->data == MAP_FAILED) - goto err_empty; - s->should_munmap = 1; } - else { - char type[20]; - struct sha1_size_cache *e; - - if (size_only) { - e = locate_size_cache(s->sha1, 1, 0); - if (e) { - s->size = e->size; - return 0; - } - if (!sha1_object_info(s->sha1, type, &s->size)) - locate_size_cache(s->sha1, 0, s->size); - } - else { - 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 = NULL; - free(s->cnt_data); - s->cnt_data = NULL; -} - -static void prep_temp_blob(struct diff_tempfile *temp, - void *blob, - unsigned long size, - const unsigned char *sha1, - int mode) -{ - int fd; - - fd = git_mkstemp(temp->tmp_path, TEMPFILE_PATH_LEN, ".diff_XXXXXX"); - if (fd < 0) - die("unable to create temp-file"); - if (write(fd, blob, size) != size) - die("unable to write temp-file"); - close(fd); - temp->name = temp->tmp_path; - strcpy(temp->hex, sha1_to_hex(sha1)); - temp->hex[40] = 0; - sprintf(temp->mode, "%06o", mode); -} - -static void prepare_temp_file(const char *name, - struct diff_tempfile *temp, - struct diff_filespec *one) -{ - if (!DIFF_FILE_VALID(one)) { - not_a_valid_file: - /* A '-' entry produces this for file-2, and - * a '+' entry produces this for file-1. - */ - temp->name = "/dev/null"; - strcpy(temp->hex, "."); - strcpy(temp->mode, "."); - return; - } - - if (!one->sha1_valid || - work_tree_matches(name, one->sha1)) { + for (i = 0; i < entries; i++) { struct stat st; - if (lstat(name, &st) < 0) { - if (errno == ENOENT) - goto not_a_valid_file; - die("stat(%s): %s", name, strerror(errno)); - } - if (S_ISLNK(st.st_mode)) { - int ret; - char buf[PATH_MAX + 1]; /* ought to be SYMLINK_MAX */ - if (sizeof(buf) <= st.st_size) - die("symlink too long: %s", name); - ret = readlink(name, buf, st.st_size); - if (ret < 0) - die("readlink(%s)", name); - prep_temp_blob(temp, buf, st.st_size, - (one->sha1_valid ? - 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->sha1)); - /* Even though we may sometimes borrow the - * contents from the work tree, we always want - * one->mode. mode is trustworthy even when - * !(one->sha1_valid), as long as - * DIFF_FILE_VALID(one). - */ - sprintf(temp->mode, "%06o", one->mode); - } - return; - } - else { - if (diff_populate_filespec(one, 0)) - die("cannot read data blob for %s", one->path); - prep_temp_blob(temp, one->data, one->size, - one->sha1, one->mode); - } -} - -static void remove_tempfile(void) -{ - int i; - - for (i = 0; i < 2; i++) - if (diff_temp[i].name == diff_temp[i].tmp_path) { - unlink(diff_temp[i].name); - diff_temp[i].name = NULL; - } -} - -static void remove_tempfile_on_signal(int signo) -{ - remove_tempfile(); - signal(SIGINT, SIG_DFL); - raise(signo); -} - -static int spawn_prog(const char *pgm, const char **arg) -{ - pid_t pid; - int status; + unsigned int oldmode, newmode; + struct cache_entry *ce = active_cache[i]; + int changed; - fflush(NULL); - pid = fork(); - if (pid < 0) - die("unable to fork"); - if (!pid) { - execvp(pgm, (char *const*) arg); - exit(255); - } - - while (waitpid(pid, &status, 0) < 0) { - if (errno == EINTR) + if (!ce_path_match(ce, revs->prune_data)) continue; - return -1; - } - - /* Earlier we did not check the exit status because - * diff exits non-zero if files are different, and - * we are not interested in knowing that. It was a - * mistake which made it harder to quit a diff-* - * session that uses the git-apply-patch-script as - * the GIT_EXTERNAL_DIFF. A custom GIT_EXTERNAL_DIFF - * should also exit non-zero only when it wants to - * abort the entire diff-* session. - */ - if (WIFEXITED(status) && !WEXITSTATUS(status)) - return 0; - return -1; -} - -/* An external diff command takes: - * - * diff-cmd name infile1 infile1-sha1 infile1-mode \ - * infile2 infile2-sha1 infile2-mode [ rename-to ] - * - */ -static void run_external_diff(const char *pgm, - const char *name, - const char *other, - struct diff_filespec *one, - struct diff_filespec *two, - const char *xfrm_msg, - int complete_rewrite) -{ - const char *spawn_arg[10]; - struct diff_tempfile *temp = diff_temp; - int retval; - static int atexit_asked = 0; - const char *othername; - const char **arg = &spawn_arg[0]; - - othername = (other? other : name); - if (one && two) { - prepare_temp_file(name, &temp[0], one); - prepare_temp_file(othername, &temp[1], two); - if (! atexit_asked && - (temp[0].name == temp[0].tmp_path || - temp[1].name == temp[1].tmp_path)) { - atexit_asked = 1; - atexit(remove_tempfile); - } - signal(SIGINT, remove_tempfile_on_signal); - } - if (one && two) { - *arg++ = pgm; - *arg++ = name; - *arg++ = temp[0].name; - *arg++ = temp[0].hex; - *arg++ = temp[0].mode; - *arg++ = temp[1].name; - *arg++ = temp[1].hex; - *arg++ = temp[1].mode; - if (other) { - *arg++ = other; - *arg++ = xfrm_msg; - } - } else { - *arg++ = pgm; - *arg++ = name; - } - *arg = NULL; - retval = spawn_prog(pgm, spawn_arg); - remove_tempfile(); - if (retval) { - fprintf(stderr, "external diff died, stopping at %s.\n", name); - exit(1); - } -} - -static void run_diff_cmd(const char *pgm, - const char *name, - const char *other, - struct diff_filespec *one, - struct diff_filespec *two, - const char *xfrm_msg, - int complete_rewrite) -{ - if (pgm) { - run_external_diff(pgm, name, other, one, two, xfrm_msg, - complete_rewrite); - return; - } - if (one && two) - builtin_diff(name, other ? other : name, - one, two, xfrm_msg, complete_rewrite); - else - printf("* Unmerged path %s\n", name); -} - -static void diff_fill_sha1_info(struct diff_filespec *one) -{ - if (DIFF_FILE_VALID(one)) { - if (!one->sha1_valid) { - struct stat st; - if (lstat(one->path, &st) < 0) - die("stat %s", one->path); - if (index_path(one->sha1, one->path, &st, 0)) - die("cannot hash %s\n", one->path); - } - } - else - memset(one->sha1, 0, 20); -} - -static void run_diff(struct diff_filepair *p, struct diff_options *o) -{ - const char *pgm = external_diff(); - char msg[PATH_MAX*2+300], *xfrm_msg; - struct diff_filespec *one; - struct diff_filespec *two; - const char *name; - const char *other; - char *name_munged, *other_munged; - int complete_rewrite = 0; - int len; - - if (DIFF_PAIR_UNMERGED(p)) { - /* unmerged */ - run_diff_cmd(pgm, p->one->path, NULL, NULL, NULL, NULL, 0); - return; - } - - name = p->one->path; - other = (strcmp(name, p->two->path) ? p->two->path : NULL); - name_munged = quote_one(name); - other_munged = quote_one(other); - one = p->one; two = p->two; - - diff_fill_sha1_info(one); - diff_fill_sha1_info(two); - - len = 0; - switch (p->status) { - case DIFF_STATUS_COPIED: - len += snprintf(msg + len, sizeof(msg) - len, - "similarity index %d%%\n" - "copy from %s\n" - "copy to %s\n", - (int)(0.5 + p->score * 100.0/MAX_SCORE), - name_munged, other_munged); - break; - case DIFF_STATUS_RENAMED: - len += snprintf(msg + len, sizeof(msg) - len, - "similarity index %d%%\n" - "rename from %s\n" - "rename to %s\n", - (int)(0.5 + p->score * 100.0/MAX_SCORE), - name_munged, other_munged); - break; - case DIFF_STATUS_MODIFIED: - if (p->score) { - len += snprintf(msg + len, sizeof(msg) - len, - "dissimilarity index %d%%\n", - (int)(0.5 + p->score * - 100.0/MAX_SCORE)); - complete_rewrite = 1; - break; - } - /* fallthru */ - default: - /* nothing */ - ; - } - - if (memcmp(one->sha1, two->sha1, 20)) { - char one_sha1[41]; - int abbrev = o->full_index ? 40 : DEFAULT_ABBREV; - memcpy(one_sha1, sha1_to_hex(one->sha1), 41); - - len += snprintf(msg + len, sizeof(msg) - len, - "index %.*s..%.*s", - abbrev, one_sha1, abbrev, - sha1_to_hex(two->sha1)); - if (one->mode == two->mode) - len += snprintf(msg + len, sizeof(msg) - len, - " %06o", one->mode); - len += snprintf(msg + len, sizeof(msg) - len, "\n"); - } - - if (len) - msg[--len] = 0; - xfrm_msg = len ? msg : NULL; - - if (!pgm && - DIFF_FILE_VALID(one) && DIFF_FILE_VALID(two) && - (S_IFMT & one->mode) != (S_IFMT & two->mode)) { - /* a filepair that changes between file and symlink - * needs to be split into deletion and creation. - */ - struct diff_filespec *null = alloc_filespec(two->path); - run_diff_cmd(NULL, name, other, one, null, xfrm_msg, 0); - free(null); - null = alloc_filespec(one->path); - run_diff_cmd(NULL, name, other, null, two, xfrm_msg, 0); - free(null); - } - else - run_diff_cmd(pgm, name, other, one, two, xfrm_msg, - complete_rewrite); - - free(name_munged); - free(other_munged); -} - -static void run_diffstat(struct diff_filepair *p, struct diff_options *o, - struct diffstat_t *diffstat) -{ - const char *name; - const char *other; - - if (DIFF_PAIR_UNMERGED(p)) { - /* unmerged */ - builtin_diffstat(p->one->path, NULL, NULL, NULL, diffstat); - return; - } - - name = p->one->path; - other = (strcmp(name, p->two->path) ? p->two->path : NULL); - - diff_fill_sha1_info(p->one); - diff_fill_sha1_info(p->two); - - builtin_diffstat(name, other, p->one, p->two, diffstat); -} - -void diff_setup(struct diff_options *options) -{ - memset(options, 0, sizeof(*options)); - options->output_format = DIFF_FORMAT_RAW; - options->line_termination = '\n'; - options->break_opt = -1; - options->rename_limit = -1; - - options->change = diff_change; - options->add_remove = diff_addremove; -} - -int diff_setup_done(struct diff_options *options) -{ - if ((options->find_copies_harder && - options->detect_rename != DIFF_DETECT_COPY) || - (0 <= options->rename_limit && !options->detect_rename)) - return -1; - - /* - * These cases always need recursive; we do not drop caller-supplied - * recursive bits for other formats here. - */ - if ((options->output_format == DIFF_FORMAT_PATCH) || - (options->output_format == DIFF_FORMAT_DIFFSTAT)) - options->recursive = 1; - - if (options->detect_rename && options->rename_limit < 0) - options->rename_limit = diff_rename_limit_default; - if (options->setup & DIFF_SETUP_USE_CACHE) { - if (!active_cache) - /* read-cache does not die even when it fails - * so it is safe for us to do this here. Also - * it does not smudge active_cache or active_nr - * when it fails, so we do not have to worry about - * cleaning it up ourselves either. + if (ce_stage(ce)) { + struct { + struct combine_diff_path p; + struct combine_diff_parent filler[5]; + } combine; + int num_compare_stages = 0; + + combine.p.next = NULL; + combine.p.len = ce_namelen(ce); + combine.p.path = xmalloc(combine.p.len + 1); + memcpy(combine.p.path, ce->name, combine.p.len); + combine.p.path[combine.p.len] = 0; + combine.p.mode = 0; + memset(combine.p.sha1, 0, 20); + memset(&combine.p.parent[0], 0, + sizeof(combine.filler)); + + while (i < entries) { + struct cache_entry *nce = active_cache[i]; + int stage; + + if (strcmp(ce->name, nce->name)) + break; + + /* Stage #2 (ours) is the first parent, + * stage #3 (theirs) is the second. + */ + stage = ce_stage(nce); + if (2 <= stage) { + int mode = ntohl(nce->ce_mode); + num_compare_stages++; + memcpy(combine.p.parent[stage-2].sha1, + nce->sha1, 20); + combine.p.parent[stage-2].mode = + canon_mode(mode); + combine.p.parent[stage-2].status = + DIFF_STATUS_MODIFIED; + } + + /* diff against the proper unmerged stage */ + if (stage == diff_unmerged_stage) + ce = nce; + i++; + } + /* + * Compensate for loop update */ - read_cache(); - } - if (options->setup & DIFF_SETUP_USE_SIZE_CACHE) - use_size_cache = 1; - if (options->abbrev <= 0 || 40 < options->abbrev) - options->abbrev = 40; /* full */ + i--; - return 0; -} - -int diff_opt_parse(struct diff_options *options, const char **av, int ac) -{ - const char *arg = av[0]; - if (!strcmp(arg, "-p") || !strcmp(arg, "-u")) - options->output_format = DIFF_FORMAT_PATCH; - else if (!strcmp(arg, "--patch-with-raw")) { - options->output_format = DIFF_FORMAT_PATCH; - options->with_raw = 1; - } - else if (!strcmp(arg, "--stat")) - options->output_format = DIFF_FORMAT_DIFFSTAT; - else if (!strcmp(arg, "--patch-with-stat")) { - options->output_format = DIFF_FORMAT_PATCH; - options->with_stat = 1; - } - else if (!strcmp(arg, "-z")) - options->line_termination = 0; - else if (!strncmp(arg, "-l", 2)) - options->rename_limit = strtoul(arg+2, NULL, 10); - else if (!strcmp(arg, "--full-index")) - options->full_index = 1; - else if (!strcmp(arg, "--name-only")) - options->output_format = DIFF_FORMAT_NAME; - else if (!strcmp(arg, "--name-status")) - options->output_format = DIFF_FORMAT_NAME_STATUS; - else if (!strcmp(arg, "-R")) - options->reverse_diff = 1; - else if (!strncmp(arg, "-S", 2)) - options->pickaxe = arg + 2; - else if (!strcmp(arg, "-s")) - options->output_format = DIFF_FORMAT_NO_OUTPUT; - else if (!strncmp(arg, "-O", 2)) - options->orderfile = arg + 2; - else if (!strncmp(arg, "--diff-filter=", 14)) - options->filter = arg + 14; - else if (!strcmp(arg, "--pickaxe-all")) - options->pickaxe_opts = DIFF_PICKAXE_ALL; - else if (!strcmp(arg, "--pickaxe-regex")) - options->pickaxe_opts = DIFF_PICKAXE_REGEX; - else if (!strncmp(arg, "-B", 2)) { - if ((options->break_opt = - diff_scoreopt_parse(arg)) == -1) - return -1; - } - else if (!strncmp(arg, "-M", 2)) { - if ((options->rename_score = - diff_scoreopt_parse(arg)) == -1) - return -1; - options->detect_rename = DIFF_DETECT_RENAME; - } - else if (!strncmp(arg, "-C", 2)) { - if ((options->rename_score = - diff_scoreopt_parse(arg)) == -1) - return -1; - options->detect_rename = DIFF_DETECT_COPY; - } - else if (!strcmp(arg, "--find-copies-harder")) - options->find_copies_harder = 1; - else if (!strcmp(arg, "--abbrev")) - options->abbrev = DEFAULT_ABBREV; - else if (!strncmp(arg, "--abbrev=", 9)) { - options->abbrev = strtoul(arg + 9, NULL, 10); - if (options->abbrev < MINIMUM_ABBREV) - options->abbrev = MINIMUM_ABBREV; - else if (40 < options->abbrev) - options->abbrev = 40; - } - else - return 0; - return 1; -} - -static int parse_num(const char **cp_p) -{ - unsigned long num, scale; - int ch, dot; - const char *cp = *cp_p; - - num = 0; - scale = 1; - dot = 0; - for(;;) { - ch = *cp; - if ( !dot && ch == '.' ) { - scale = 1; - dot = 1; - } else if ( ch == '%' ) { - scale = dot ? scale*100 : 100; - cp++; /* % is always at the end */ - break; - } else if ( ch >= '0' && ch <= '9' ) { - if ( scale < 100000 ) { - scale *= 10; - num = (num*10) + (ch-'0'); + if (revs->combine_merges && num_compare_stages == 2) { + show_combined_diff(&combine.p, 2, + revs->dense_combined_merges, + revs); + free(combine.p.path); + continue; } - } else { - break; - } - cp++; - } - *cp_p = cp; - - /* user says num divided by scale and we say internally that - * is MAX_SCORE * num / scale. - */ - return (num >= scale) ? MAX_SCORE : (MAX_SCORE * num / scale); -} - -int diff_scoreopt_parse(const char *opt) -{ - int opt1, opt2, cmd; + free(combine.p.path); - if (*opt++ != '-') - return -1; - cmd = *opt++; - if (cmd != 'M' && cmd != 'C' && cmd != 'B') - return -1; /* that is not a -M, -C nor -B option */ - - opt1 = parse_num(&opt); - if (cmd != 'B') - opt2 = 0; - else { - if (*opt == 0) - opt2 = 0; - else if (*opt != '/') - return -1; /* we expect -B80/99 or -B80 */ - else { - opt++; - opt2 = parse_num(&opt); + /* + * Show the diff for the 'ce' if we found the one + * from the desired stage. + */ + diff_unmerge(&revs->diffopt, ce->name); + if (ce_stage(ce) != diff_unmerged_stage) + continue; } - } - if (*opt != 0) - return -1; - return opt1 | (opt2 << 16); -} - -struct diff_queue_struct diff_queued_diff; -void diff_q(struct diff_queue_struct *queue, struct diff_filepair *dp) -{ - 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; -} - -struct diff_filepair *diff_queue(struct diff_queue_struct *queue, - struct diff_filespec *one, - struct diff_filespec *two) -{ - struct diff_filepair *dp = xmalloc(sizeof(*dp)); - dp->one = one; - dp->two = two; - dp->score = 0; - dp->status = 0; - dp->source_stays = 0; - dp->broken_pair = 0; - if (queue) - diff_q(queue, dp); - return dp; -} - -void diff_free_filepair(struct diff_filepair *p) -{ - diff_free_filespec_data(p->one); - diff_free_filespec_data(p->two); - free(p->one); - free(p->two); - free(p); -} - -/* This is different from find_unique_abbrev() in that - * it stuffs the result with dots for alignment. - */ -const char *diff_unique_abbrev(const unsigned char *sha1, int len) -{ - int abblen; - const char *abbrev; - if (len == 40) - return sha1_to_hex(sha1); - - abbrev = find_unique_abbrev(sha1, len); - if (!abbrev) - return sha1_to_hex(sha1); - abblen = strlen(abbrev); - if (abblen < 37) { - static char hex[41]; - if (len < abblen && abblen <= len + 2) - sprintf(hex, "%s%.*s", abbrev, len+3-abblen, ".."); - else - sprintf(hex, "%s...", abbrev); - return hex; - } - return sha1_to_hex(sha1); -} - -static void diff_flush_raw(struct diff_filepair *p, - int line_termination, - int inter_name_termination, - struct diff_options *options, - int output_format) -{ - int two_paths; - char status[10]; - int abbrev = options->abbrev; - const char *path_one, *path_two; - - path_one = p->one->path; - path_two = p->two->path; - if (line_termination) { - path_one = quote_one(path_one); - path_two = quote_one(path_two); - } - - if (p->score) - sprintf(status, "%c%03d", p->status, - (int)(0.5 + p->score * 100.0/MAX_SCORE)); - else { - status[0] = p->status; - status[1] = 0; - } - switch (p->status) { - case DIFF_STATUS_COPIED: - case DIFF_STATUS_RENAMED: - two_paths = 1; - break; - case DIFF_STATUS_ADDED: - case DIFF_STATUS_DELETED: - two_paths = 0; - break; - default: - two_paths = 0; - break; - } - if (output_format != DIFF_FORMAT_NAME_STATUS) { - printf(":%06o %06o %s ", - p->one->mode, p->two->mode, - diff_unique_abbrev(p->one->sha1, abbrev)); - printf("%s ", - diff_unique_abbrev(p->two->sha1, abbrev)); - } - printf("%s%c%s", status, inter_name_termination, path_one); - if (two_paths) - printf("%c%s", inter_name_termination, path_two); - putchar(line_termination); - if (path_one != p->one->path) - free((void*)path_one); - if (path_two != p->two->path) - free((void*)path_two); -} - -static void diff_flush_name(struct diff_filepair *p, - int inter_name_termination, - int line_termination) -{ - char *path = p->two->path; - - if (line_termination) - path = quote_one(p->two->path); - else - path = p->two->path; - printf("%s%c", path, line_termination); - if (p->two->path != path) - free(path); -} - -int diff_unmodified_pair(struct diff_filepair *p) -{ - /* This function is written stricter than necessary to support - * the currently implemented transformers, but the idea is to - * let transformers to produce diff_filepairs any way they want, - * and filter and clean them up here before producing the output. - */ - struct diff_filespec *one, *two; - - if (DIFF_PAIR_UNMERGED(p)) - return 0; /* unmerged is interesting */ - - one = p->one; - two = p->two; - - /* deletion, addition, mode or type change - * and rename are all interesting. - */ - if (DIFF_FILE_VALID(one) != DIFF_FILE_VALID(two) || - DIFF_PAIR_MODE_CHANGED(p) || - strcmp(one->path, two->path)) - return 0; - - /* both are valid and point at the same path. that is, we are - * dealing with a change. - */ - 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; -} - -static void diff_flush_patch(struct diff_filepair *p, struct diff_options *o) -{ - if (diff_unmodified_pair(p)) - return; - - if ((DIFF_FILE_VALID(p->one) && S_ISDIR(p->one->mode)) || - (DIFF_FILE_VALID(p->two) && S_ISDIR(p->two->mode))) - return; /* no tree diffs in patch format */ - - run_diff(p, o); -} - -static void diff_flush_stat(struct diff_filepair *p, struct diff_options *o, - struct diffstat_t *diffstat) -{ - if (diff_unmodified_pair(p)) - return; - - if ((DIFF_FILE_VALID(p->one) && S_ISDIR(p->one->mode)) || - (DIFF_FILE_VALID(p->two) && S_ISDIR(p->two->mode))) - return; /* no tree diffs in patch format */ - - run_diffstat(p, o, diffstat); -} - -int diff_queue_is_empty(void) -{ - struct diff_queue_struct *q = &diff_queued_diff; - int i; - for (i = 0; i < q->nr; i++) - if (!diff_unmodified_pair(q->queue[i])) - return 0; - return 1; -} - -#if DIFF_DEBUG -void diff_debug_filespec(struct diff_filespec *s, int x, const char *one) -{ - fprintf(stderr, "queue[%d] %s (%s) %s %06o %s\n", - x, one ? one : "", - s->path, - DIFF_FILE_VALID(s) ? "valid" : "invalid", - s->mode, - s->sha1_valid ? sha1_to_hex(s->sha1) : ""); - fprintf(stderr, "queue[%d] %s size %lu flags %d\n", - x, one ? one : "", - s->size, s->xfrm_flags); -} - -void diff_debug_filepair(const struct diff_filepair *p, int i) -{ - diff_debug_filespec(p->one, i, "one"); - diff_debug_filespec(p->two, i, "two"); - fprintf(stderr, "score %d, status %c stays %d broken %d\n", - p->score, p->status ? p->status : '?', - p->source_stays, p->broken_pair); -} - -void diff_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_filepair *p = q->queue[i]; - diff_debug_filepair(p, i); - } -} -#endif - -static void diff_resolve_rename_copy(void) -{ - int i, j; - struct diff_filepair *p, *pp; - struct diff_queue_struct *q = &diff_queued_diff; - - diff_debug_queue("resolve-rename-copy", q); - - for (i = 0; i < q->nr; i++) { - p = q->queue[i]; - p->status = 0; /* undecided */ - if (DIFF_PAIR_UNMERGED(p)) - p->status = DIFF_STATUS_UNMERGED; - else if (!DIFF_FILE_VALID(p->one)) - p->status = DIFF_STATUS_ADDED; - else if (!DIFF_FILE_VALID(p->two)) - p->status = DIFF_STATUS_DELETED; - else if (DIFF_PAIR_TYPE_CHANGED(p)) - p->status = DIFF_STATUS_TYPE_CHANGED; - - /* from this point on, we are dealing with a pair - * whose both sides are valid and of the same type, i.e. - * either in-place edit or rename/copy edit. - */ - else if (DIFF_PAIR_RENAME(p)) { - if (p->source_stays) { - p->status = DIFF_STATUS_COPIED; + if (lstat(ce->name, &st) < 0) { + if (errno != ENOENT && errno != ENOTDIR) { + perror(ce->name); continue; } - /* See if there is some other filepair that - * copies from the same source as us. If so - * we are a copy. Otherwise we are either a - * copy if the path stays, or a rename if it - * does not, but we already handled "stays" case. - */ - for (j = i + 1; j < q->nr; j++) { - pp = q->queue[j]; - if (strcmp(pp->one->path, p->one->path)) - continue; /* not us */ - if (!DIFF_PAIR_RENAME(pp)) - continue; /* not a rename/copy */ - /* pp is a rename/copy from the same source */ - p->status = DIFF_STATUS_COPIED; - break; - } - if (!p->status) - p->status = DIFF_STATUS_RENAMED; - } - else if (memcmp(p->one->sha1, p->two->sha1, 20) || - p->one->mode != p->two->mode) - p->status = DIFF_STATUS_MODIFIED; - else { - /* This is a "no-change" entry and should not - * happen anymore, but prepare for broken callers. - */ - error("feeding unmodified %s to diffcore", - p->one->path); - p->status = DIFF_STATUS_UNKNOWN; - } - } - diff_debug_queue("resolve-rename-copy done", q); -} - -static void flush_one_pair(struct diff_filepair *p, - int diff_output_format, - struct diff_options *options, - struct diffstat_t *diffstat) -{ - int inter_name_termination = '\t'; - int line_termination = options->line_termination; - if (!line_termination) - inter_name_termination = 0; - - switch (p->status) { - case DIFF_STATUS_UNKNOWN: - break; - case 0: - die("internal error in diff-resolve-rename-copy"); - break; - default: - switch (diff_output_format) { - case DIFF_FORMAT_DIFFSTAT: - diff_flush_stat(p, options, diffstat); - break; - case DIFF_FORMAT_PATCH: - diff_flush_patch(p, options); - break; - case DIFF_FORMAT_RAW: - case DIFF_FORMAT_NAME_STATUS: - diff_flush_raw(p, line_termination, - inter_name_termination, - options, diff_output_format); - break; - case DIFF_FORMAT_NAME: - diff_flush_name(p, - inter_name_termination, - line_termination); - break; - case DIFF_FORMAT_NO_OUTPUT: - break; - } - } -} - -void diff_flush(struct diff_options *options) -{ - struct diff_queue_struct *q = &diff_queued_diff; - int i; - int diff_output_format = options->output_format; - struct diffstat_t *diffstat = NULL; - - if (diff_output_format == DIFF_FORMAT_DIFFSTAT || options->with_stat) { - diffstat = xcalloc(sizeof (struct diffstat_t), 1); - diffstat->xm.consume = diffstat_consume; - } - - if (options->with_raw) { - for (i = 0; i < q->nr; i++) { - struct diff_filepair *p = q->queue[i]; - flush_one_pair(p, DIFF_FORMAT_RAW, options, NULL); - } - putchar(options->line_termination); - } - if (options->with_stat) { - for (i = 0; i < q->nr; i++) { - struct diff_filepair *p = q->queue[i]; - flush_one_pair(p, DIFF_FORMAT_DIFFSTAT, options, - diffstat); - } - show_stats(diffstat); - free(diffstat); - diffstat = NULL; - putchar(options->line_termination); - } - for (i = 0; i < q->nr; i++) { - struct diff_filepair *p = q->queue[i]; - flush_one_pair(p, diff_output_format, options, diffstat); - diff_free_filepair(p); - } - - if (diffstat) { - show_stats(diffstat); - free(diffstat); - } - - free(q->queue); - q->queue = NULL; - q->nr = q->alloc = 0; -} - -static void diffcore_apply_filter(const char *filter) -{ - int i; - struct diff_queue_struct *q = &diff_queued_diff; - struct diff_queue_struct outq; - outq.queue = NULL; - outq.nr = outq.alloc = 0; - - if (!filter) - return; - - if (strchr(filter, DIFF_STATUS_FILTER_AON)) { - int found; - for (i = found = 0; !found && i < q->nr; i++) { - struct diff_filepair *p = q->queue[i]; - if (((p->status == DIFF_STATUS_MODIFIED) && - ((p->score && - strchr(filter, DIFF_STATUS_FILTER_BROKEN)) || - (!p->score && - strchr(filter, DIFF_STATUS_MODIFIED)))) || - ((p->status != DIFF_STATUS_MODIFIED) && - strchr(filter, p->status))) - found++; - } - if (found) - return; - - /* otherwise we will clear the whole queue - * by copying the empty outq at the end of this - * function, but first clear the current entries - * in the queue. - */ - for (i = 0; i < q->nr; i++) - diff_free_filepair(q->queue[i]); - } - else { - /* Only the matching ones */ - for (i = 0; i < q->nr; i++) { - struct diff_filepair *p = q->queue[i]; - - if (((p->status == DIFF_STATUS_MODIFIED) && - ((p->score && - strchr(filter, DIFF_STATUS_FILTER_BROKEN)) || - (!p->score && - strchr(filter, DIFF_STATUS_MODIFIED)))) || - ((p->status != DIFF_STATUS_MODIFIED) && - strchr(filter, p->status))) - diff_q(&outq, p); - else - diff_free_filepair(p); + if (silent_on_removed) + continue; + diff_addremove(&revs->diffopt, '-', ntohl(ce->ce_mode), + ce->sha1, ce->name, NULL); + continue; } - } - free(q->queue); - *q = outq; -} - -void diffcore_std(struct diff_options *options) -{ - if (options->break_opt != -1) - diffcore_break(options->break_opt); - if (options->detect_rename) - diffcore_rename(options); - if (options->break_opt != -1) - diffcore_merge_broken(); - if (options->pickaxe) - diffcore_pickaxe(options->pickaxe, options->pickaxe_opts); - if (options->orderfile) - diffcore_order(options->orderfile); - diff_resolve_rename_copy(); - diffcore_apply_filter(options->filter); -} - - -void diffcore_std_no_resolve(struct diff_options *options) -{ - if (options->pickaxe) - diffcore_pickaxe(options->pickaxe, options->pickaxe_opts); - if (options->orderfile) - diffcore_order(options->orderfile); - diffcore_apply_filter(options->filter); -} - -void diff_addremove(struct diff_options *options, - int addremove, unsigned mode, - const unsigned char *sha1, - const char *base, const char *path) -{ - char concatpath[PATH_MAX]; - 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() - * also has the same effect. - * Before the final output happens, they are pruned after - * merged into rename/copy pairs as appropriate. - */ - if (options->reverse_diff) - addremove = (addremove == '+' ? '-' : - addremove == '-' ? '+' : addremove); - - if (!path) path = ""; - sprintf(concatpath, "%s%s", base, path); - one = alloc_filespec(concatpath); - two = alloc_filespec(concatpath); - - if (addremove != '+') - fill_filespec(one, sha1, mode); - if (addremove != '-') - fill_filespec(two, sha1, mode); - - diff_queue(&diff_queued_diff, one, two); -} + changed = ce_match_stat(ce, &st, 0); + if (!changed && !revs->diffopt.find_copies_harder) + continue; + oldmode = ntohl(ce->ce_mode); -void diff_change(struct diff_options *options, - unsigned old_mode, unsigned new_mode, - const unsigned char *old_sha1, - const unsigned char *new_sha1, - const char *base, const char *path) -{ - char concatpath[PATH_MAX]; - struct diff_filespec *one, *two; + newmode = canon_mode(st.st_mode); + if (!trust_executable_bit && + S_ISREG(newmode) && S_ISREG(oldmode) && + ((newmode ^ oldmode) == 0111)) + newmode = oldmode; + diff_change(&revs->diffopt, oldmode, newmode, + ce->sha1, (changed ? null_sha1 : ce->sha1), + ce->name, NULL); - if (options->reverse_diff) { - unsigned tmp; - const unsigned char *tmp_c; - tmp = old_mode; old_mode = new_mode; new_mode = tmp; - tmp_c = old_sha1; old_sha1 = new_sha1; new_sha1 = tmp_c; } - 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(&diff_queued_diff, one, two); + diffcore_std(&revs->diffopt); + diff_flush(&revs->diffopt); + return 0; } -void diff_unmerge(struct diff_options *options, - const char *path) -{ - struct diff_filespec *one, *two; - one = alloc_filespec(path); - two = alloc_filespec(path); - diff_queue(&diff_queued_diff, one, two); -} diff --git a/diff.c b/diff.c new file mode 100644 index 000000000..13b216f27 --- /dev/null +++ b/diff.c @@ -0,0 +1,1795 @@ +/* + * Copyright (C) 2005 Junio C Hamano + */ +#include +#include +#include +#include "cache.h" +#include "quote.h" +#include "diff.h" +#include "diffcore.h" +#include "xdiff-interface.h" + +static int use_size_cache; + +int diff_rename_limit_default = -1; + +int git_diff_config(const char *var, const char *value) +{ + if (!strcmp(var, "diff.renamelimit")) { + diff_rename_limit_default = git_config_int(var, value); + return 0; + } + + return git_default_config(var, value); +} + +static char *quote_one(const char *str) +{ + int needlen; + char *xp; + + if (!str) + return NULL; + needlen = quote_c_style(str, NULL, NULL, 0); + if (!needlen) + return strdup(str); + xp = xmalloc(needlen + 1); + quote_c_style(str, xp, NULL, 0); + return xp; +} + +static char *quote_two(const char *one, const char *two) +{ + int need_one = quote_c_style(one, NULL, NULL, 1); + int need_two = quote_c_style(two, NULL, NULL, 1); + char *xp; + + if (need_one + need_two) { + if (!need_one) need_one = strlen(one); + if (!need_two) need_one = strlen(two); + + xp = xmalloc(need_one + need_two + 3); + xp[0] = '"'; + quote_c_style(one, xp + 1, NULL, 1); + quote_c_style(two, xp + need_one + 1, NULL, 1); + strcpy(xp + need_one + need_two + 1, "\""); + return xp; + } + need_one = strlen(one); + need_two = strlen(two); + xp = xmalloc(need_one + need_two + 1); + strcpy(xp, one); + strcpy(xp + need_one, two); + return xp; +} + +static const char *external_diff(void) +{ + static const char *external_diff_cmd = NULL; + static int done_preparing = 0; + + if (done_preparing) + return external_diff_cmd; + external_diff_cmd = getenv("GIT_EXTERNAL_DIFF"); + done_preparing = 1; + return external_diff_cmd; +} + +#define TEMPFILE_PATH_LEN 50 + +static struct diff_tempfile { + const char *name; /* filename external diff should read from */ + char hex[41]; + char mode[10]; + char tmp_path[TEMPFILE_PATH_LEN]; +} diff_temp[2]; + +static int count_lines(const char *data, int size) +{ + int count, ch, completely_empty = 1, nl_just_seen = 0; + count = 0; + while (0 < size--) { + ch = *data++; + if (ch == '\n') { + count++; + nl_just_seen = 1; + completely_empty = 0; + } + else { + nl_just_seen = 0; + completely_empty = 0; + } + } + if (completely_empty) + return 0; + if (!nl_just_seen) + count++; /* no trailing newline */ + return count; +} + +static void print_line_count(int count) +{ + switch (count) { + case 0: + printf("0,0"); + break; + case 1: + printf("1"); + break; + default: + printf("1,%d", count); + break; + } +} + +static void copy_file(int prefix, const char *data, int size) +{ + int ch, nl_just_seen = 1; + while (0 < size--) { + ch = *data++; + if (nl_just_seen) + putchar(prefix); + putchar(ch); + if (ch == '\n') + nl_just_seen = 1; + else + nl_just_seen = 0; + } + if (!nl_just_seen) + printf("\n\\ No newline at end of file\n"); +} + +static void emit_rewrite_diff(const char *name_a, + const char *name_b, + struct diff_filespec *one, + struct diff_filespec *two) +{ + int lc_a, lc_b; + diff_populate_filespec(one, 0); + diff_populate_filespec(two, 0); + lc_a = count_lines(one->data, one->size); + lc_b = count_lines(two->data, two->size); + printf("--- %s\n+++ %s\n@@ -", name_a, name_b); + print_line_count(lc_a); + printf(" +"); + print_line_count(lc_b); + printf(" @@\n"); + if (lc_a) + copy_file('-', one->data, one->size); + if (lc_b) + copy_file('+', two->data, two->size); +} + +static int fill_mmfile(mmfile_t *mf, struct diff_filespec *one) +{ + if (!DIFF_FILE_VALID(one)) { + mf->ptr = ""; /* does not matter */ + mf->size = 0; + return 0; + } + else if (diff_populate_filespec(one, 0)) + return -1; + mf->ptr = one->data; + mf->size = one->size; + return 0; +} + +struct emit_callback { + const char **label_path; +}; + +static int fn_out(void *priv, mmbuffer_t *mb, int nbuf) +{ + int i; + struct emit_callback *ecbdata = priv; + + if (ecbdata->label_path[0]) { + printf("--- %s\n", ecbdata->label_path[0]); + printf("+++ %s\n", ecbdata->label_path[1]); + ecbdata->label_path[0] = ecbdata->label_path[1] = NULL; + } + for (i = 0; i < nbuf; i++) + if (!fwrite(mb[i].ptr, mb[i].size, 1, stdout)) + return -1; + return 0; +} + +static char *pprint_rename(const char *a, const char *b) +{ + const char *old = a; + const char *new = b; + char *name = NULL; + int pfx_length, sfx_length; + int len_a = strlen(a); + int len_b = strlen(b); + + /* Find common prefix */ + pfx_length = 0; + while (*old && *new && *old == *new) { + if (*old == '/') + pfx_length = old - a + 1; + old++; + new++; + } + + /* Find common suffix */ + old = a + len_a; + new = b + len_b; + sfx_length = 0; + while (a <= old && b <= new && *old == *new) { + if (*old == '/') + sfx_length = len_a - (old - a); + old--; + new--; + } + + /* + * pfx{mid-a => mid-b}sfx + * {pfx-a => pfx-b}sfx + * pfx{sfx-a => sfx-b} + * name-a => name-b + */ + if (pfx_length + sfx_length) { + name = xmalloc(len_a + len_b - pfx_length - sfx_length + 7); + sprintf(name, "%.*s{%.*s => %.*s}%s", + pfx_length, a, + len_a - pfx_length - sfx_length, a + pfx_length, + len_b - pfx_length - sfx_length, b + pfx_length, + a + len_a - sfx_length); + } + else { + name = xmalloc(len_a + len_b + 5); + sprintf(name, "%s => %s", a, b); + } + return name; +} + +struct diffstat_t { + struct xdiff_emit_state xm; + + int nr; + int alloc; + struct diffstat_file { + char *name; + unsigned is_unmerged:1; + unsigned is_binary:1; + unsigned is_renamed:1; + unsigned int added, deleted; + } **files; +}; + +static struct diffstat_file *diffstat_add(struct diffstat_t *diffstat, + const char *name_a, + const char *name_b) +{ + struct diffstat_file *x; + x = xcalloc(sizeof (*x), 1); + if (diffstat->nr == diffstat->alloc) { + diffstat->alloc = alloc_nr(diffstat->alloc); + diffstat->files = xrealloc(diffstat->files, + diffstat->alloc * sizeof(x)); + } + diffstat->files[diffstat->nr++] = x; + if (name_b) { + x->name = pprint_rename(name_a, name_b); + x->is_renamed = 1; + } + else + x->name = strdup(name_a); + return x; +} + +static void diffstat_consume(void *priv, char *line, unsigned long len) +{ + struct diffstat_t *diffstat = priv; + struct diffstat_file *x = diffstat->files[diffstat->nr - 1]; + + if (line[0] == '+') + x->added++; + else if (line[0] == '-') + x->deleted++; +} + +static const char pluses[] = "++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++"; +static const char minuses[]= "----------------------------------------------------------------------"; + +static void show_stats(struct diffstat_t* data) +{ + char *prefix = ""; + int i, len, add, del, total, adds = 0, dels = 0; + int max, max_change = 0, max_len = 0; + int total_files = data->nr; + + if (data->nr == 0) + return; + + for (i = 0; i < data->nr; i++) { + struct diffstat_file *file = data->files[i]; + + len = strlen(file->name); + if (max_len < len) + max_len = len; + + if (file->is_binary || file->is_unmerged) + continue; + if (max_change < file->added + file->deleted) + max_change = file->added + file->deleted; + } + + for (i = 0; i < data->nr; i++) { + char *name = data->files[i]->name; + int added = data->files[i]->added; + int deleted = data->files[i]->deleted; + + if (0 < (len = quote_c_style(name, NULL, NULL, 0))) { + char *qname = xmalloc(len + 1); + quote_c_style(name, qname, NULL, 0); + free(name); + data->files[i]->name = name = qname; + } + + /* + * "scale" the filename + */ + len = strlen(name); + max = max_len; + if (max > 50) + max = 50; + if (len > max) { + char *slash; + prefix = "..."; + max -= 3; + name += len - max; + slash = strchr(name, '/'); + if (slash) + name = slash; + } + len = max; + + /* + * scale the add/delete + */ + max = max_change; + if (max + len > 70) + max = 70 - len; + + if (data->files[i]->is_binary) { + printf(" %s%-*s | Bin\n", prefix, len, name); + goto free_diffstat_file; + } + else if (data->files[i]->is_unmerged) { + printf(" %s%-*s | Unmerged\n", prefix, len, name); + goto free_diffstat_file; + } + else if (!data->files[i]->is_renamed && + (added + deleted == 0)) { + total_files--; + goto free_diffstat_file; + } + + add = added; + del = deleted; + total = add + del; + adds += add; + dels += del; + + if (max_change > 0) { + total = (total * max + max_change / 2) / max_change; + add = (add * max + max_change / 2) / max_change; + del = total - add; + } + printf(" %s%-*s |%5d %.*s%.*s\n", prefix, + len, name, added + deleted, + add, pluses, del, minuses); + free_diffstat_file: + free(data->files[i]->name); + free(data->files[i]); + } + free(data->files); + printf(" %d files changed, %d insertions(+), %d deletions(-)\n", + total_files, adds, dels); +} + +#define FIRST_FEW_BYTES 8000 +static int mmfile_is_binary(mmfile_t *mf) +{ + long sz = mf->size; + if (FIRST_FEW_BYTES < sz) + sz = FIRST_FEW_BYTES; + if (memchr(mf->ptr, 0, sz)) + return 1; + return 0; +} + +static void builtin_diff(const char *name_a, + const char *name_b, + struct diff_filespec *one, + struct diff_filespec *two, + const char *xfrm_msg, + int complete_rewrite) +{ + mmfile_t mf1, mf2; + const char *lbl[2]; + char *a_one, *b_two; + + a_one = quote_two("a/", name_a); + b_two = quote_two("b/", name_b); + lbl[0] = DIFF_FILE_VALID(one) ? a_one : "/dev/null"; + lbl[1] = DIFF_FILE_VALID(two) ? b_two : "/dev/null"; + printf("diff --git %s %s\n", a_one, b_two); + if (lbl[0][0] == '/') { + /* /dev/null */ + printf("new file mode %06o\n", two->mode); + if (xfrm_msg && xfrm_msg[0]) + puts(xfrm_msg); + } + else if (lbl[1][0] == '/') { + printf("deleted file mode %06o\n", one->mode); + if (xfrm_msg && xfrm_msg[0]) + puts(xfrm_msg); + } + else { + if (one->mode != two->mode) { + printf("old mode %06o\n", one->mode); + printf("new mode %06o\n", two->mode); + } + if (xfrm_msg && xfrm_msg[0]) + puts(xfrm_msg); + /* + * we do not run diff between different kind + * of objects. + */ + if ((one->mode ^ two->mode) & S_IFMT) + goto free_ab_and_return; + if (complete_rewrite) { + emit_rewrite_diff(name_a, name_b, one, two); + goto free_ab_and_return; + } + } + + if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0) + die("unable to read files to diff"); + + if (mmfile_is_binary(&mf1) || mmfile_is_binary(&mf2)) + printf("Binary files %s and %s differ\n", lbl[0], lbl[1]); + else { + /* Crazy xdl interfaces.. */ + const char *diffopts = getenv("GIT_DIFF_OPTS"); + xpparam_t xpp; + xdemitconf_t xecfg; + xdemitcb_t ecb; + struct emit_callback ecbdata; + + ecbdata.label_path = lbl; + xpp.flags = XDF_NEED_MINIMAL; + xecfg.ctxlen = 3; + xecfg.flags = XDL_EMIT_FUNCNAMES; + if (!diffopts) + ; + else if (!strncmp(diffopts, "--unified=", 10)) + xecfg.ctxlen = strtoul(diffopts + 10, NULL, 10); + else if (!strncmp(diffopts, "-u", 2)) + xecfg.ctxlen = strtoul(diffopts + 2, NULL, 10); + ecb.outf = fn_out; + ecb.priv = &ecbdata; + xdl_diff(&mf1, &mf2, &xpp, &xecfg, &ecb); + } + + free_ab_and_return: + free(a_one); + free(b_two); + return; +} + +static void builtin_diffstat(const char *name_a, const char *name_b, + struct diff_filespec *one, + struct diff_filespec *two, + struct diffstat_t *diffstat) +{ + mmfile_t mf1, mf2; + struct diffstat_file *data; + + data = diffstat_add(diffstat, name_a, name_b); + + if (!one || !two) { + data->is_unmerged = 1; + return; + } + + if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0) + die("unable to read files to diff"); + + if (mmfile_is_binary(&mf1) || mmfile_is_binary(&mf2)) + data->is_binary = 1; + else { + /* Crazy xdl interfaces.. */ + xpparam_t xpp; + xdemitconf_t xecfg; + xdemitcb_t ecb; + + xpp.flags = XDF_NEED_MINIMAL; + xecfg.ctxlen = 0; + xecfg.flags = 0; + ecb.outf = xdiff_outf; + ecb.priv = diffstat; + xdl_diff(&mf1, &mf2, &xpp, &xecfg, &ecb); + } +} + +struct diff_filespec *alloc_filespec(const char *path) +{ + int namelen = strlen(path); + struct diff_filespec *spec = xmalloc(sizeof(*spec) + namelen + 1); + + memset(spec, 0, sizeof(*spec)); + spec->path = (char *)(spec + 1); + memcpy(spec->path, path, namelen+1); + return spec; +} + +void fill_filespec(struct diff_filespec *spec, const unsigned char *sha1, + unsigned short mode) +{ + if (mode) { + spec->mode = canon_mode(mode); + memcpy(spec->sha1, sha1, 20); + spec->sha1_valid = !!memcmp(sha1, null_sha1, 20); + } +} + +/* + * 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 + * prepare_temp_file() does not have to inflate and extract. + */ +static int work_tree_matches(const char *name, const unsigned char *sha1) +{ + struct cache_entry *ce; + struct stat st; + int pos, len; + + /* We do not read the cache ourselves here, because the + * benchmark with my previous version that always reads cache + * shows that it makes things worse for diff-tree comparing + * two linux-2.6 kernel trees in an already checked out work + * tree. This is because most diff-tree comparisons deal with + * only a small number of files, while reading the cache is + * expensive for a large project, and its cost outweighs the + * savings we get by not inflating the object to a temporary + * file. Practically, this code only helps when we are used + * by diff-cache --cached, which does read the cache before + * calling us. + */ + if (!active_cache) + return 0; + + len = strlen(name); + pos = cache_name_pos(name, len); + if (pos < 0) + return 0; + ce = active_cache[pos]; + if ((lstat(name, &st) < 0) || + !S_ISREG(st.st_mode) || /* careful! */ + ce_match_stat(ce, &st, 0) || + 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 pair. + */ + return 1; +} + +static struct sha1_size_cache { + unsigned char sha1[20]; + unsigned long size; +} **sha1_size_cache; +static int sha1_size_cache_nr, sha1_size_cache_alloc; + +static struct sha1_size_cache *locate_size_cache(unsigned char *sha1, + int find_only, + unsigned long size) +{ + int first, last; + struct sha1_size_cache *e; + + first = 0; + last = sha1_size_cache_nr; + while (last > first) { + int cmp, next = (last + first) >> 1; + e = sha1_size_cache[next]; + cmp = memcmp(e->sha1, sha1, 20); + if (!cmp) + return e; + if (cmp < 0) { + last = next; + continue; + } + first = next+1; + } + /* not found */ + if (find_only) + return NULL; + /* insert to make it at "first" */ + if (sha1_size_cache_alloc <= sha1_size_cache_nr) { + sha1_size_cache_alloc = alloc_nr(sha1_size_cache_alloc); + sha1_size_cache = xrealloc(sha1_size_cache, + sha1_size_cache_alloc * + sizeof(*sha1_size_cache)); + } + sha1_size_cache_nr++; + if (first < sha1_size_cache_nr) + memmove(sha1_size_cache + first + 1, sha1_size_cache + first, + (sha1_size_cache_nr - first - 1) * + sizeof(*sha1_size_cache)); + e = xmalloc(sizeof(struct sha1_size_cache)); + sha1_size_cache[first] = e; + memcpy(e->sha1, sha1, 20); + e->size = size; + return e; +} + +/* + * 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 size_only) +{ + int err = 0; + if (!DIFF_FILE_VALID(s)) + die("internal error: asking to populate invalid file."); + if (S_ISDIR(s->mode)) + return -1; + + if (!use_size_cache) + size_only = 0; + + 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 (size_only) + return 0; + 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); + close(fd); + if (s->data == MAP_FAILED) + goto err_empty; + s->should_munmap = 1; + } + else { + char type[20]; + struct sha1_size_cache *e; + + if (size_only) { + e = locate_size_cache(s->sha1, 1, 0); + if (e) { + s->size = e->size; + return 0; + } + if (!sha1_object_info(s->sha1, type, &s->size)) + locate_size_cache(s->sha1, 0, s->size); + } + else { + 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 = NULL; + free(s->cnt_data); + s->cnt_data = NULL; +} + +static void prep_temp_blob(struct diff_tempfile *temp, + void *blob, + unsigned long size, + const unsigned char *sha1, + int mode) +{ + int fd; + + fd = git_mkstemp(temp->tmp_path, TEMPFILE_PATH_LEN, ".diff_XXXXXX"); + if (fd < 0) + die("unable to create temp-file"); + if (write(fd, blob, size) != size) + die("unable to write temp-file"); + close(fd); + temp->name = temp->tmp_path; + strcpy(temp->hex, sha1_to_hex(sha1)); + temp->hex[40] = 0; + sprintf(temp->mode, "%06o", mode); +} + +static void prepare_temp_file(const char *name, + struct diff_tempfile *temp, + struct diff_filespec *one) +{ + if (!DIFF_FILE_VALID(one)) { + not_a_valid_file: + /* A '-' entry produces this for file-2, and + * a '+' entry produces this for file-1. + */ + temp->name = "/dev/null"; + strcpy(temp->hex, "."); + strcpy(temp->mode, "."); + return; + } + + if (!one->sha1_valid || + work_tree_matches(name, one->sha1)) { + struct stat st; + if (lstat(name, &st) < 0) { + if (errno == ENOENT) + goto not_a_valid_file; + die("stat(%s): %s", name, strerror(errno)); + } + if (S_ISLNK(st.st_mode)) { + int ret; + char buf[PATH_MAX + 1]; /* ought to be SYMLINK_MAX */ + if (sizeof(buf) <= st.st_size) + die("symlink too long: %s", name); + ret = readlink(name, buf, st.st_size); + if (ret < 0) + die("readlink(%s)", name); + prep_temp_blob(temp, buf, st.st_size, + (one->sha1_valid ? + 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->sha1)); + /* Even though we may sometimes borrow the + * contents from the work tree, we always want + * one->mode. mode is trustworthy even when + * !(one->sha1_valid), as long as + * DIFF_FILE_VALID(one). + */ + sprintf(temp->mode, "%06o", one->mode); + } + return; + } + else { + if (diff_populate_filespec(one, 0)) + die("cannot read data blob for %s", one->path); + prep_temp_blob(temp, one->data, one->size, + one->sha1, one->mode); + } +} + +static void remove_tempfile(void) +{ + int i; + + for (i = 0; i < 2; i++) + if (diff_temp[i].name == diff_temp[i].tmp_path) { + unlink(diff_temp[i].name); + diff_temp[i].name = NULL; + } +} + +static void remove_tempfile_on_signal(int signo) +{ + remove_tempfile(); + signal(SIGINT, SIG_DFL); + raise(signo); +} + +static int spawn_prog(const char *pgm, const char **arg) +{ + pid_t pid; + int status; + + fflush(NULL); + pid = fork(); + if (pid < 0) + die("unable to fork"); + if (!pid) { + execvp(pgm, (char *const*) arg); + exit(255); + } + + while (waitpid(pid, &status, 0) < 0) { + if (errno == EINTR) + continue; + return -1; + } + + /* Earlier we did not check the exit status because + * diff exits non-zero if files are different, and + * we are not interested in knowing that. It was a + * mistake which made it harder to quit a diff-* + * session that uses the git-apply-patch-script as + * the GIT_EXTERNAL_DIFF. A custom GIT_EXTERNAL_DIFF + * should also exit non-zero only when it wants to + * abort the entire diff-* session. + */ + if (WIFEXITED(status) && !WEXITSTATUS(status)) + return 0; + return -1; +} + +/* An external diff command takes: + * + * diff-cmd name infile1 infile1-sha1 infile1-mode \ + * infile2 infile2-sha1 infile2-mode [ rename-to ] + * + */ +static void run_external_diff(const char *pgm, + const char *name, + const char *other, + struct diff_filespec *one, + struct diff_filespec *two, + const char *xfrm_msg, + int complete_rewrite) +{ + const char *spawn_arg[10]; + struct diff_tempfile *temp = diff_temp; + int retval; + static int atexit_asked = 0; + const char *othername; + const char **arg = &spawn_arg[0]; + + othername = (other? other : name); + if (one && two) { + prepare_temp_file(name, &temp[0], one); + prepare_temp_file(othername, &temp[1], two); + if (! atexit_asked && + (temp[0].name == temp[0].tmp_path || + temp[1].name == temp[1].tmp_path)) { + atexit_asked = 1; + atexit(remove_tempfile); + } + signal(SIGINT, remove_tempfile_on_signal); + } + + if (one && two) { + *arg++ = pgm; + *arg++ = name; + *arg++ = temp[0].name; + *arg++ = temp[0].hex; + *arg++ = temp[0].mode; + *arg++ = temp[1].name; + *arg++ = temp[1].hex; + *arg++ = temp[1].mode; + if (other) { + *arg++ = other; + *arg++ = xfrm_msg; + } + } else { + *arg++ = pgm; + *arg++ = name; + } + *arg = NULL; + retval = spawn_prog(pgm, spawn_arg); + remove_tempfile(); + if (retval) { + fprintf(stderr, "external diff died, stopping at %s.\n", name); + exit(1); + } +} + +static void run_diff_cmd(const char *pgm, + const char *name, + const char *other, + struct diff_filespec *one, + struct diff_filespec *two, + const char *xfrm_msg, + int complete_rewrite) +{ + if (pgm) { + run_external_diff(pgm, name, other, one, two, xfrm_msg, + complete_rewrite); + return; + } + if (one && two) + builtin_diff(name, other ? other : name, + one, two, xfrm_msg, complete_rewrite); + else + printf("* Unmerged path %s\n", name); +} + +static void diff_fill_sha1_info(struct diff_filespec *one) +{ + if (DIFF_FILE_VALID(one)) { + if (!one->sha1_valid) { + struct stat st; + if (lstat(one->path, &st) < 0) + die("stat %s", one->path); + if (index_path(one->sha1, one->path, &st, 0)) + die("cannot hash %s\n", one->path); + } + } + else + memset(one->sha1, 0, 20); +} + +static void run_diff(struct diff_filepair *p, struct diff_options *o) +{ + const char *pgm = external_diff(); + char msg[PATH_MAX*2+300], *xfrm_msg; + struct diff_filespec *one; + struct diff_filespec *two; + const char *name; + const char *other; + char *name_munged, *other_munged; + int complete_rewrite = 0; + int len; + + if (DIFF_PAIR_UNMERGED(p)) { + /* unmerged */ + run_diff_cmd(pgm, p->one->path, NULL, NULL, NULL, NULL, 0); + return; + } + + name = p->one->path; + other = (strcmp(name, p->two->path) ? p->two->path : NULL); + name_munged = quote_one(name); + other_munged = quote_one(other); + one = p->one; two = p->two; + + diff_fill_sha1_info(one); + diff_fill_sha1_info(two); + + len = 0; + switch (p->status) { + case DIFF_STATUS_COPIED: + len += snprintf(msg + len, sizeof(msg) - len, + "similarity index %d%%\n" + "copy from %s\n" + "copy to %s\n", + (int)(0.5 + p->score * 100.0/MAX_SCORE), + name_munged, other_munged); + break; + case DIFF_STATUS_RENAMED: + len += snprintf(msg + len, sizeof(msg) - len, + "similarity index %d%%\n" + "rename from %s\n" + "rename to %s\n", + (int)(0.5 + p->score * 100.0/MAX_SCORE), + name_munged, other_munged); + break; + case DIFF_STATUS_MODIFIED: + if (p->score) { + len += snprintf(msg + len, sizeof(msg) - len, + "dissimilarity index %d%%\n", + (int)(0.5 + p->score * + 100.0/MAX_SCORE)); + complete_rewrite = 1; + break; + } + /* fallthru */ + default: + /* nothing */ + ; + } + + if (memcmp(one->sha1, two->sha1, 20)) { + char one_sha1[41]; + int abbrev = o->full_index ? 40 : DEFAULT_ABBREV; + memcpy(one_sha1, sha1_to_hex(one->sha1), 41); + + len += snprintf(msg + len, sizeof(msg) - len, + "index %.*s..%.*s", + abbrev, one_sha1, abbrev, + sha1_to_hex(two->sha1)); + if (one->mode == two->mode) + len += snprintf(msg + len, sizeof(msg) - len, + " %06o", one->mode); + len += snprintf(msg + len, sizeof(msg) - len, "\n"); + } + + if (len) + msg[--len] = 0; + xfrm_msg = len ? msg : NULL; + + if (!pgm && + DIFF_FILE_VALID(one) && DIFF_FILE_VALID(two) && + (S_IFMT & one->mode) != (S_IFMT & two->mode)) { + /* a filepair that changes between file and symlink + * needs to be split into deletion and creation. + */ + struct diff_filespec *null = alloc_filespec(two->path); + run_diff_cmd(NULL, name, other, one, null, xfrm_msg, 0); + free(null); + null = alloc_filespec(one->path); + run_diff_cmd(NULL, name, other, null, two, xfrm_msg, 0); + free(null); + } + else + run_diff_cmd(pgm, name, other, one, two, xfrm_msg, + complete_rewrite); + + free(name_munged); + free(other_munged); +} + +static void run_diffstat(struct diff_filepair *p, struct diff_options *o, + struct diffstat_t *diffstat) +{ + const char *name; + const char *other; + + if (DIFF_PAIR_UNMERGED(p)) { + /* unmerged */ + builtin_diffstat(p->one->path, NULL, NULL, NULL, diffstat); + return; + } + + name = p->one->path; + other = (strcmp(name, p->two->path) ? p->two->path : NULL); + + diff_fill_sha1_info(p->one); + diff_fill_sha1_info(p->two); + + builtin_diffstat(name, other, p->one, p->two, diffstat); +} + +void diff_setup(struct diff_options *options) +{ + memset(options, 0, sizeof(*options)); + options->output_format = DIFF_FORMAT_RAW; + options->line_termination = '\n'; + options->break_opt = -1; + options->rename_limit = -1; + + options->change = diff_change; + options->add_remove = diff_addremove; +} + +int diff_setup_done(struct diff_options *options) +{ + if ((options->find_copies_harder && + options->detect_rename != DIFF_DETECT_COPY) || + (0 <= options->rename_limit && !options->detect_rename)) + return -1; + + /* + * These cases always need recursive; we do not drop caller-supplied + * recursive bits for other formats here. + */ + if ((options->output_format == DIFF_FORMAT_PATCH) || + (options->output_format == DIFF_FORMAT_DIFFSTAT)) + options->recursive = 1; + + if (options->detect_rename && options->rename_limit < 0) + options->rename_limit = diff_rename_limit_default; + if (options->setup & DIFF_SETUP_USE_CACHE) { + if (!active_cache) + /* read-cache does not die even when it fails + * so it is safe for us to do this here. Also + * it does not smudge active_cache or active_nr + * when it fails, so we do not have to worry about + * cleaning it up ourselves either. + */ + read_cache(); + } + if (options->setup & DIFF_SETUP_USE_SIZE_CACHE) + use_size_cache = 1; + if (options->abbrev <= 0 || 40 < options->abbrev) + options->abbrev = 40; /* full */ + + return 0; +} + +int diff_opt_parse(struct diff_options *options, const char **av, int ac) +{ + const char *arg = av[0]; + if (!strcmp(arg, "-p") || !strcmp(arg, "-u")) + options->output_format = DIFF_FORMAT_PATCH; + else if (!strcmp(arg, "--patch-with-raw")) { + options->output_format = DIFF_FORMAT_PATCH; + options->with_raw = 1; + } + else if (!strcmp(arg, "--stat")) + options->output_format = DIFF_FORMAT_DIFFSTAT; + else if (!strcmp(arg, "--patch-with-stat")) { + options->output_format = DIFF_FORMAT_PATCH; + options->with_stat = 1; + } + else if (!strcmp(arg, "-z")) + options->line_termination = 0; + else if (!strncmp(arg, "-l", 2)) + options->rename_limit = strtoul(arg+2, NULL, 10); + else if (!strcmp(arg, "--full-index")) + options->full_index = 1; + else if (!strcmp(arg, "--name-only")) + options->output_format = DIFF_FORMAT_NAME; + else if (!strcmp(arg, "--name-status")) + options->output_format = DIFF_FORMAT_NAME_STATUS; + else if (!strcmp(arg, "-R")) + options->reverse_diff = 1; + else if (!strncmp(arg, "-S", 2)) + options->pickaxe = arg + 2; + else if (!strcmp(arg, "-s")) + options->output_format = DIFF_FORMAT_NO_OUTPUT; + else if (!strncmp(arg, "-O", 2)) + options->orderfile = arg + 2; + else if (!strncmp(arg, "--diff-filter=", 14)) + options->filter = arg + 14; + else if (!strcmp(arg, "--pickaxe-all")) + options->pickaxe_opts = DIFF_PICKAXE_ALL; + else if (!strcmp(arg, "--pickaxe-regex")) + options->pickaxe_opts = DIFF_PICKAXE_REGEX; + else if (!strncmp(arg, "-B", 2)) { + if ((options->break_opt = + diff_scoreopt_parse(arg)) == -1) + return -1; + } + else if (!strncmp(arg, "-M", 2)) { + if ((options->rename_score = + diff_scoreopt_parse(arg)) == -1) + return -1; + options->detect_rename = DIFF_DETECT_RENAME; + } + else if (!strncmp(arg, "-C", 2)) { + if ((options->rename_score = + diff_scoreopt_parse(arg)) == -1) + return -1; + options->detect_rename = DIFF_DETECT_COPY; + } + else if (!strcmp(arg, "--find-copies-harder")) + options->find_copies_harder = 1; + else if (!strcmp(arg, "--abbrev")) + options->abbrev = DEFAULT_ABBREV; + else if (!strncmp(arg, "--abbrev=", 9)) { + options->abbrev = strtoul(arg + 9, NULL, 10); + if (options->abbrev < MINIMUM_ABBREV) + options->abbrev = MINIMUM_ABBREV; + else if (40 < options->abbrev) + options->abbrev = 40; + } + else + return 0; + return 1; +} + +static int parse_num(const char **cp_p) +{ + unsigned long num, scale; + int ch, dot; + const char *cp = *cp_p; + + num = 0; + scale = 1; + dot = 0; + for(;;) { + ch = *cp; + if ( !dot && ch == '.' ) { + scale = 1; + dot = 1; + } else if ( ch == '%' ) { + scale = dot ? scale*100 : 100; + cp++; /* % is always at the end */ + break; + } else if ( ch >= '0' && ch <= '9' ) { + if ( scale < 100000 ) { + scale *= 10; + num = (num*10) + (ch-'0'); + } + } else { + break; + } + cp++; + } + *cp_p = cp; + + /* user says num divided by scale and we say internally that + * is MAX_SCORE * num / scale. + */ + return (num >= scale) ? MAX_SCORE : (MAX_SCORE * num / scale); +} + +int diff_scoreopt_parse(const char *opt) +{ + int opt1, opt2, cmd; + + if (*opt++ != '-') + return -1; + cmd = *opt++; + if (cmd != 'M' && cmd != 'C' && cmd != 'B') + return -1; /* that is not a -M, -C nor -B option */ + + opt1 = parse_num(&opt); + if (cmd != 'B') + opt2 = 0; + else { + if (*opt == 0) + opt2 = 0; + else if (*opt != '/') + return -1; /* we expect -B80/99 or -B80 */ + else { + opt++; + opt2 = parse_num(&opt); + } + } + if (*opt != 0) + return -1; + return opt1 | (opt2 << 16); +} + +struct diff_queue_struct diff_queued_diff; + +void diff_q(struct diff_queue_struct *queue, struct diff_filepair *dp) +{ + 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; +} + +struct diff_filepair *diff_queue(struct diff_queue_struct *queue, + struct diff_filespec *one, + struct diff_filespec *two) +{ + struct diff_filepair *dp = xmalloc(sizeof(*dp)); + dp->one = one; + dp->two = two; + dp->score = 0; + dp->status = 0; + dp->source_stays = 0; + dp->broken_pair = 0; + if (queue) + diff_q(queue, dp); + return dp; +} + +void diff_free_filepair(struct diff_filepair *p) +{ + diff_free_filespec_data(p->one); + diff_free_filespec_data(p->two); + free(p->one); + free(p->two); + free(p); +} + +/* This is different from find_unique_abbrev() in that + * it stuffs the result with dots for alignment. + */ +const char *diff_unique_abbrev(const unsigned char *sha1, int len) +{ + int abblen; + const char *abbrev; + if (len == 40) + return sha1_to_hex(sha1); + + abbrev = find_unique_abbrev(sha1, len); + if (!abbrev) + return sha1_to_hex(sha1); + abblen = strlen(abbrev); + if (abblen < 37) { + static char hex[41]; + if (len < abblen && abblen <= len + 2) + sprintf(hex, "%s%.*s", abbrev, len+3-abblen, ".."); + else + sprintf(hex, "%s...", abbrev); + return hex; + } + return sha1_to_hex(sha1); +} + +static void diff_flush_raw(struct diff_filepair *p, + int line_termination, + int inter_name_termination, + struct diff_options *options, + int output_format) +{ + int two_paths; + char status[10]; + int abbrev = options->abbrev; + const char *path_one, *path_two; + + path_one = p->one->path; + path_two = p->two->path; + if (line_termination) { + path_one = quote_one(path_one); + path_two = quote_one(path_two); + } + + if (p->score) + sprintf(status, "%c%03d", p->status, + (int)(0.5 + p->score * 100.0/MAX_SCORE)); + else { + status[0] = p->status; + status[1] = 0; + } + switch (p->status) { + case DIFF_STATUS_COPIED: + case DIFF_STATUS_RENAMED: + two_paths = 1; + break; + case DIFF_STATUS_ADDED: + case DIFF_STATUS_DELETED: + two_paths = 0; + break; + default: + two_paths = 0; + break; + } + if (output_format != DIFF_FORMAT_NAME_STATUS) { + printf(":%06o %06o %s ", + p->one->mode, p->two->mode, + diff_unique_abbrev(p->one->sha1, abbrev)); + printf("%s ", + diff_unique_abbrev(p->two->sha1, abbrev)); + } + printf("%s%c%s", status, inter_name_termination, path_one); + if (two_paths) + printf("%c%s", inter_name_termination, path_two); + putchar(line_termination); + if (path_one != p->one->path) + free((void*)path_one); + if (path_two != p->two->path) + free((void*)path_two); +} + +static void diff_flush_name(struct diff_filepair *p, + int inter_name_termination, + int line_termination) +{ + char *path = p->two->path; + + if (line_termination) + path = quote_one(p->two->path); + else + path = p->two->path; + printf("%s%c", path, line_termination); + if (p->two->path != path) + free(path); +} + +int diff_unmodified_pair(struct diff_filepair *p) +{ + /* This function is written stricter than necessary to support + * the currently implemented transformers, but the idea is to + * let transformers to produce diff_filepairs any way they want, + * and filter and clean them up here before producing the output. + */ + struct diff_filespec *one, *two; + + if (DIFF_PAIR_UNMERGED(p)) + return 0; /* unmerged is interesting */ + + one = p->one; + two = p->two; + + /* deletion, addition, mode or type change + * and rename are all interesting. + */ + if (DIFF_FILE_VALID(one) != DIFF_FILE_VALID(two) || + DIFF_PAIR_MODE_CHANGED(p) || + strcmp(one->path, two->path)) + return 0; + + /* both are valid and point at the same path. that is, we are + * dealing with a change. + */ + 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; +} + +static void diff_flush_patch(struct diff_filepair *p, struct diff_options *o) +{ + if (diff_unmodified_pair(p)) + return; + + if ((DIFF_FILE_VALID(p->one) && S_ISDIR(p->one->mode)) || + (DIFF_FILE_VALID(p->two) && S_ISDIR(p->two->mode))) + return; /* no tree diffs in patch format */ + + run_diff(p, o); +} + +static void diff_flush_stat(struct diff_filepair *p, struct diff_options *o, + struct diffstat_t *diffstat) +{ + if (diff_unmodified_pair(p)) + return; + + if ((DIFF_FILE_VALID(p->one) && S_ISDIR(p->one->mode)) || + (DIFF_FILE_VALID(p->two) && S_ISDIR(p->two->mode))) + return; /* no tree diffs in patch format */ + + run_diffstat(p, o, diffstat); +} + +int diff_queue_is_empty(void) +{ + struct diff_queue_struct *q = &diff_queued_diff; + int i; + for (i = 0; i < q->nr; i++) + if (!diff_unmodified_pair(q->queue[i])) + return 0; + return 1; +} + +#if DIFF_DEBUG +void diff_debug_filespec(struct diff_filespec *s, int x, const char *one) +{ + fprintf(stderr, "queue[%d] %s (%s) %s %06o %s\n", + x, one ? one : "", + s->path, + DIFF_FILE_VALID(s) ? "valid" : "invalid", + s->mode, + s->sha1_valid ? sha1_to_hex(s->sha1) : ""); + fprintf(stderr, "queue[%d] %s size %lu flags %d\n", + x, one ? one : "", + s->size, s->xfrm_flags); +} + +void diff_debug_filepair(const struct diff_filepair *p, int i) +{ + diff_debug_filespec(p->one, i, "one"); + diff_debug_filespec(p->two, i, "two"); + fprintf(stderr, "score %d, status %c stays %d broken %d\n", + p->score, p->status ? p->status : '?', + p->source_stays, p->broken_pair); +} + +void diff_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_filepair *p = q->queue[i]; + diff_debug_filepair(p, i); + } +} +#endif + +static void diff_resolve_rename_copy(void) +{ + int i, j; + struct diff_filepair *p, *pp; + struct diff_queue_struct *q = &diff_queued_diff; + + diff_debug_queue("resolve-rename-copy", q); + + for (i = 0; i < q->nr; i++) { + p = q->queue[i]; + p->status = 0; /* undecided */ + if (DIFF_PAIR_UNMERGED(p)) + p->status = DIFF_STATUS_UNMERGED; + else if (!DIFF_FILE_VALID(p->one)) + p->status = DIFF_STATUS_ADDED; + else if (!DIFF_FILE_VALID(p->two)) + p->status = DIFF_STATUS_DELETED; + else if (DIFF_PAIR_TYPE_CHANGED(p)) + p->status = DIFF_STATUS_TYPE_CHANGED; + + /* from this point on, we are dealing with a pair + * whose both sides are valid and of the same type, i.e. + * either in-place edit or rename/copy edit. + */ + else if (DIFF_PAIR_RENAME(p)) { + if (p->source_stays) { + p->status = DIFF_STATUS_COPIED; + continue; + } + /* See if there is some other filepair that + * copies from the same source as us. If so + * we are a copy. Otherwise we are either a + * copy if the path stays, or a rename if it + * does not, but we already handled "stays" case. + */ + for (j = i + 1; j < q->nr; j++) { + pp = q->queue[j]; + if (strcmp(pp->one->path, p->one->path)) + continue; /* not us */ + if (!DIFF_PAIR_RENAME(pp)) + continue; /* not a rename/copy */ + /* pp is a rename/copy from the same source */ + p->status = DIFF_STATUS_COPIED; + break; + } + if (!p->status) + p->status = DIFF_STATUS_RENAMED; + } + else if (memcmp(p->one->sha1, p->two->sha1, 20) || + p->one->mode != p->two->mode) + p->status = DIFF_STATUS_MODIFIED; + else { + /* This is a "no-change" entry and should not + * happen anymore, but prepare for broken callers. + */ + error("feeding unmodified %s to diffcore", + p->one->path); + p->status = DIFF_STATUS_UNKNOWN; + } + } + diff_debug_queue("resolve-rename-copy done", q); +} + +static void flush_one_pair(struct diff_filepair *p, + int diff_output_format, + struct diff_options *options, + struct diffstat_t *diffstat) +{ + int inter_name_termination = '\t'; + int line_termination = options->line_termination; + if (!line_termination) + inter_name_termination = 0; + + switch (p->status) { + case DIFF_STATUS_UNKNOWN: + break; + case 0: + die("internal error in diff-resolve-rename-copy"); + break; + default: + switch (diff_output_format) { + case DIFF_FORMAT_DIFFSTAT: + diff_flush_stat(p, options, diffstat); + break; + case DIFF_FORMAT_PATCH: + diff_flush_patch(p, options); + break; + case DIFF_FORMAT_RAW: + case DIFF_FORMAT_NAME_STATUS: + diff_flush_raw(p, line_termination, + inter_name_termination, + options, diff_output_format); + break; + case DIFF_FORMAT_NAME: + diff_flush_name(p, + inter_name_termination, + line_termination); + break; + case DIFF_FORMAT_NO_OUTPUT: + break; + } + } +} + +void diff_flush(struct diff_options *options) +{ + struct diff_queue_struct *q = &diff_queued_diff; + int i; + int diff_output_format = options->output_format; + struct diffstat_t *diffstat = NULL; + + if (diff_output_format == DIFF_FORMAT_DIFFSTAT || options->with_stat) { + diffstat = xcalloc(sizeof (struct diffstat_t), 1); + diffstat->xm.consume = diffstat_consume; + } + + if (options->with_raw) { + for (i = 0; i < q->nr; i++) { + struct diff_filepair *p = q->queue[i]; + flush_one_pair(p, DIFF_FORMAT_RAW, options, NULL); + } + putchar(options->line_termination); + } + if (options->with_stat) { + for (i = 0; i < q->nr; i++) { + struct diff_filepair *p = q->queue[i]; + flush_one_pair(p, DIFF_FORMAT_DIFFSTAT, options, + diffstat); + } + show_stats(diffstat); + free(diffstat); + diffstat = NULL; + putchar(options->line_termination); + } + for (i = 0; i < q->nr; i++) { + struct diff_filepair *p = q->queue[i]; + flush_one_pair(p, diff_output_format, options, diffstat); + diff_free_filepair(p); + } + + if (diffstat) { + show_stats(diffstat); + free(diffstat); + } + + free(q->queue); + q->queue = NULL; + q->nr = q->alloc = 0; +} + +static void diffcore_apply_filter(const char *filter) +{ + int i; + struct diff_queue_struct *q = &diff_queued_diff; + struct diff_queue_struct outq; + outq.queue = NULL; + outq.nr = outq.alloc = 0; + + if (!filter) + return; + + if (strchr(filter, DIFF_STATUS_FILTER_AON)) { + int found; + for (i = found = 0; !found && i < q->nr; i++) { + struct diff_filepair *p = q->queue[i]; + if (((p->status == DIFF_STATUS_MODIFIED) && + ((p->score && + strchr(filter, DIFF_STATUS_FILTER_BROKEN)) || + (!p->score && + strchr(filter, DIFF_STATUS_MODIFIED)))) || + ((p->status != DIFF_STATUS_MODIFIED) && + strchr(filter, p->status))) + found++; + } + if (found) + return; + + /* otherwise we will clear the whole queue + * by copying the empty outq at the end of this + * function, but first clear the current entries + * in the queue. + */ + for (i = 0; i < q->nr; i++) + diff_free_filepair(q->queue[i]); + } + else { + /* Only the matching ones */ + for (i = 0; i < q->nr; i++) { + struct diff_filepair *p = q->queue[i]; + + if (((p->status == DIFF_STATUS_MODIFIED) && + ((p->score && + strchr(filter, DIFF_STATUS_FILTER_BROKEN)) || + (!p->score && + strchr(filter, DIFF_STATUS_MODIFIED)))) || + ((p->status != DIFF_STATUS_MODIFIED) && + strchr(filter, p->status))) + diff_q(&outq, p); + else + diff_free_filepair(p); + } + } + free(q->queue); + *q = outq; +} + +void diffcore_std(struct diff_options *options) +{ + if (options->break_opt != -1) + diffcore_break(options->break_opt); + if (options->detect_rename) + diffcore_rename(options); + if (options->break_opt != -1) + diffcore_merge_broken(); + if (options->pickaxe) + diffcore_pickaxe(options->pickaxe, options->pickaxe_opts); + if (options->orderfile) + diffcore_order(options->orderfile); + diff_resolve_rename_copy(); + diffcore_apply_filter(options->filter); +} + + +void diffcore_std_no_resolve(struct diff_options *options) +{ + if (options->pickaxe) + diffcore_pickaxe(options->pickaxe, options->pickaxe_opts); + if (options->orderfile) + diffcore_order(options->orderfile); + diffcore_apply_filter(options->filter); +} + +void diff_addremove(struct diff_options *options, + int addremove, unsigned mode, + const unsigned char *sha1, + const char *base, const char *path) +{ + char concatpath[PATH_MAX]; + 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() + * also has the same effect. + * Before the final output happens, they are pruned after + * merged into rename/copy pairs as appropriate. + */ + if (options->reverse_diff) + addremove = (addremove == '+' ? '-' : + addremove == '-' ? '+' : addremove); + + if (!path) path = ""; + sprintf(concatpath, "%s%s", base, path); + one = alloc_filespec(concatpath); + two = alloc_filespec(concatpath); + + if (addremove != '+') + fill_filespec(one, sha1, mode); + if (addremove != '-') + fill_filespec(two, sha1, mode); + + diff_queue(&diff_queued_diff, one, two); +} + +void diff_change(struct diff_options *options, + unsigned old_mode, unsigned new_mode, + const unsigned char *old_sha1, + const unsigned char *new_sha1, + const char *base, const char *path) +{ + char concatpath[PATH_MAX]; + struct diff_filespec *one, *two; + + if (options->reverse_diff) { + unsigned tmp; + const unsigned char *tmp_c; + tmp = old_mode; old_mode = new_mode; new_mode = tmp; + tmp_c = old_sha1; old_sha1 = new_sha1; new_sha1 = tmp_c; + } + 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(&diff_queued_diff, one, two); +} + +void diff_unmerge(struct diff_options *options, + const char *path) +{ + struct diff_filespec *one, *two; + one = alloc_filespec(path); + two = alloc_filespec(path); + diff_queue(&diff_queued_diff, one, two); +} diff --git a/diff.h b/diff.h index 52fff6643..da4bd421f 100644 --- a/diff.h +++ b/diff.h @@ -28,10 +28,11 @@ struct diff_options { with_raw:1, with_stat:1, tree_in_recursive:1, - full_index:1; + full_index:1, + silent_on_remove:1, + find_copies_harder:1; int break_opt; int detect_rename; - int find_copies_harder; int line_termination; int output_format; int pickaxe_opts; @@ -168,4 +169,6 @@ extern void diff_flush(struct diff_options*); extern const char *diff_unique_abbrev(const unsigned char *, int); +extern int run_diff_files(struct rev_info *revs, int silent_on_removed); + #endif /* DIFF_H */ diff --git a/t/t1001-read-tree-m-2way.sh b/t/t1001-read-tree-m-2way.sh index d0ed24275..75e4c9a88 100755 --- a/t/t1001-read-tree-m-2way.sh +++ b/t/t1001-read-tree-m-2way.sh @@ -37,7 +37,7 @@ compare_change () { } check_cache_at () { - clean_if_empty=`git-diff-files "$1"` + clean_if_empty=`git-diff-files -- "$1"` case "$clean_if_empty" in '') echo "$1: clean" ;; ?*) echo "$1: dirty" ;; diff --git a/t/t1002-read-tree-m-u-2way.sh b/t/t1002-read-tree-m-u-2way.sh index 861ef4c0c..4d175d8ea 100755 --- a/t/t1002-read-tree-m-u-2way.sh +++ b/t/t1002-read-tree-m-u-2way.sh @@ -20,7 +20,7 @@ compare_change () { } check_cache_at () { - clean_if_empty=`git-diff-files "$1"` + clean_if_empty=`git-diff-files -- "$1"` case "$clean_if_empty" in '') echo "$1: clean" ;; ?*) echo "$1: dirty" ;; -- 2.26.2