summaryrefslogtreecommitdiff
path: root/diff-lib.c
diff options
context:
space:
mode:
authorLibravatar Junio C Hamano <junkio@cox.net>2006-04-19 15:12:02 -0700
committerLibravatar Junio C Hamano <junkio@cox.net>2006-04-19 15:38:14 -0700
commitba580aeafb52921025de1efe1c50db34393f9907 (patch)
tree3bad2a681f7dcb5b04731280993de93fff968349 /diff-lib.c
parentgit log: don't do merge diffs by default (diff)
downloadtgif-ba580aeafb52921025de1efe1c50db34393f9907.tar.xz
diff: move diff.c to diff-lib.c to make room.
Now I am not doing any real "git-diff in C" yet, but this would help before doing so. Signed-off-by: Junio C Hamano <junkio@cox.net>
Diffstat (limited to 'diff-lib.c')
-rw-r--r--diff-lib.c1736
1 files changed, 1736 insertions, 0 deletions
diff --git a/diff-lib.c b/diff-lib.c
new file mode 100644
index 0000000000..0a832c3585
--- /dev/null
+++ b/diff-lib.c
@@ -0,0 +1,1736 @@
+/*
+ * Copyright (C) 2005 Junio C Hamano
+ */
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <signal.h>
+#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;
+}
+
+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 int added, deleted;
+ } **files;
+};
+
+static struct diffstat_file *diffstat_add(struct diffstat_t *diffstat,
+ const char *name)
+{
+ 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;
+ x->name = strdup(name);
+ 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 (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_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 <name, sha1> 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 = x