#include "run-command.h"
#include "utf8.h"
#include "userdiff.h"
+#include "sigchain.h"
#ifdef NO_FAST_WORKING_DIRECTORY
#define FAST_WORKING_DIRECTORY 0
static int diff_rename_limit_default = 200;
static int diff_suppress_blank_empty;
int diff_use_color_default = -1;
+static const char *diff_word_regex_cfg;
static const char *external_diff_cmd_cfg;
int diff_auto_refresh_index = 1;
static int diff_mnemonic_prefix;
static char diff_colors[][COLOR_MAXLEN] = {
- "\033[m", /* reset */
- "", /* PLAIN (normal) */
- "\033[1m", /* METAINFO (bold) */
- "\033[36m", /* FRAGINFO (cyan) */
- "\033[31m", /* OLD (red) */
- "\033[32m", /* NEW (green) */
- "\033[33m", /* COMMIT (yellow) */
- "\033[41m", /* WHITESPACE (red background) */
+ GIT_COLOR_RESET,
+ GIT_COLOR_NORMAL, /* PLAIN */
+ GIT_COLOR_BOLD, /* METAINFO */
+ GIT_COLOR_CYAN, /* FRAGINFO */
+ GIT_COLOR_RED, /* OLD */
+ GIT_COLOR_GREEN, /* NEW */
+ GIT_COLOR_YELLOW, /* COMMIT */
+ GIT_COLOR_BG_RED, /* WHITESPACE */
};
static void diff_filespec_load_driver(struct diff_filespec *one);
}
if (!strcmp(var, "diff.external"))
return git_config_string(&external_diff_cmd_cfg, var, value);
+ if (!strcmp(var, "diff.wordregex"))
+ return git_config_string(&diff_word_regex_cfg, var, value);
return git_diff_basic_config(var, value, cb);
}
char tmp_path[PATH_MAX];
} diff_temp[2];
+static struct diff_tempfile *claim_diff_tempfile(void) {
+ int i;
+ for (i = 0; i < ARRAY_SIZE(diff_temp); i++)
+ if (!diff_temp[i].name)
+ return diff_temp + i;
+ die("BUG: diff is failing to clean up its tempfiles");
+}
+
+static int remove_tempfile_installed;
+
+static void remove_tempfile(void)
+{
+ int i;
+ for (i = 0; i < ARRAY_SIZE(diff_temp); 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();
+ sigchain_pop(signo);
+ raise(signo);
+}
+
static int count_lines(const char *data, int size)
{
int count, ch, completely_empty = 1, nl_just_seen = 0;
struct diff_words_buffer {
mmfile_t text;
long alloc;
- long current; /* output pointer */
- int suppressed_newline;
+ struct diff_words_orig {
+ const char *begin, *end;
+ } *orig;
+ int orig_nr, orig_alloc;
};
static void diff_words_append(char *line, unsigned long len,
struct diff_words_buffer *buffer)
{
- if (buffer->text.size + len > buffer->alloc) {
- buffer->alloc = (buffer->text.size + len) * 3 / 2;
- buffer->text.ptr = xrealloc(buffer->text.ptr, buffer->alloc);
- }
+ ALLOC_GROW(buffer->text.ptr, buffer->text.size + len, buffer->alloc);
line++;
len--;
memcpy(buffer->text.ptr + buffer->text.size, line, len);
buffer->text.size += len;
+ buffer->text.ptr[buffer->text.size] = '\0';
}
struct diff_words_data {
struct diff_words_buffer minus, plus;
+ const char *current_plus;
FILE *file;
+ regex_t *word_regex;
};
-static void print_word(FILE *file, struct diff_words_buffer *buffer, int len, int color,
- int suppress_newline)
+static void fn_out_diff_words_aux(void *priv, char *line, unsigned long len)
{
- const char *ptr;
- int eol = 0;
+ struct diff_words_data *diff_words = priv;
+ int minus_first, minus_len, plus_first, plus_len;
+ const char *minus_begin, *minus_end, *plus_begin, *plus_end;
- if (len == 0)
+ if (line[0] != '@' || parse_hunk_header(line, len,
+ &minus_first, &minus_len, &plus_first, &plus_len))
return;
- ptr = buffer->text.ptr + buffer->current;
- buffer->current += len;
+ /* POSIX requires that first be decremented by one if len == 0... */
+ if (minus_len) {
+ minus_begin = diff_words->minus.orig[minus_first].begin;
+ minus_end =
+ diff_words->minus.orig[minus_first + minus_len - 1].end;
+ } else
+ minus_begin = minus_end =
+ diff_words->minus.orig[minus_first].end;
- if (ptr[len - 1] == '\n') {
- eol = 1;
- len--;
+ if (plus_len) {
+ plus_begin = diff_words->plus.orig[plus_first].begin;
+ plus_end = diff_words->plus.orig[plus_first + plus_len - 1].end;
+ } else
+ plus_begin = plus_end = diff_words->plus.orig[plus_first].end;
+
+ if (diff_words->current_plus != plus_begin)
+ fwrite(diff_words->current_plus,
+ plus_begin - diff_words->current_plus, 1,
+ diff_words->file);
+ if (minus_begin != minus_end)
+ color_fwrite_lines(diff_words->file,
+ diff_get_color(1, DIFF_FILE_OLD),
+ minus_end - minus_begin, minus_begin);
+ if (plus_begin != plus_end)
+ color_fwrite_lines(diff_words->file,
+ diff_get_color(1, DIFF_FILE_NEW),
+ plus_end - plus_begin, plus_begin);
+
+ diff_words->current_plus = plus_end;
+}
+
+/* This function starts looking at *begin, and returns 0 iff a word was found. */
+static int find_word_boundaries(mmfile_t *buffer, regex_t *word_regex,
+ int *begin, int *end)
+{
+ if (word_regex && *begin < buffer->size) {
+ regmatch_t match[1];
+ if (!regexec(word_regex, buffer->ptr + *begin, 1, match, 0)) {
+ char *p = memchr(buffer->ptr + *begin + match[0].rm_so,
+ '\n', match[0].rm_eo - match[0].rm_so);
+ *end = p ? p - buffer->ptr : match[0].rm_eo + *begin;
+ *begin += match[0].rm_so;
+ return *begin >= *end;
+ }
+ return -1;
}
- fputs(diff_get_color(1, color), file);
- fwrite(ptr, len, 1, file);
- fputs(diff_get_color(1, DIFF_RESET), file);
+ /* find the next word */
+ while (*begin < buffer->size && isspace(buffer->ptr[*begin]))
+ (*begin)++;
+ if (*begin >= buffer->size)
+ return -1;
- if (eol) {
- if (suppress_newline)
- buffer->suppressed_newline = 1;
- else
- putc('\n', file);
- }
+ /* find the end of the word */
+ *end = *begin + 1;
+ while (*end < buffer->size && !isspace(buffer->ptr[*end]))
+ (*end)++;
+
+ return 0;
}
-static void fn_out_diff_words_aux(void *priv, char *line, unsigned long len)
+/*
+ * This function splits the words in buffer->text, stores the list with
+ * newline separator into out, and saves the offsets of the original words
+ * in buffer->orig.
+ */
+static void diff_words_fill(struct diff_words_buffer *buffer, mmfile_t *out,
+ regex_t *word_regex)
{
- struct diff_words_data *diff_words = priv;
+ int i, j;
+ long alloc = 0;
- if (diff_words->minus.suppressed_newline) {
- if (line[0] != '+')
- putc('\n', diff_words->file);
- diff_words->minus.suppressed_newline = 0;
- }
+ out->size = 0;
+ out->ptr = NULL;
- len--;
- switch (line[0]) {
- case '-':
- print_word(diff_words->file,
- &diff_words->minus, len, DIFF_FILE_OLD, 1);
- break;
- case '+':
- print_word(diff_words->file,
- &diff_words->plus, len, DIFF_FILE_NEW, 0);
- break;
- case ' ':
- print_word(diff_words->file,
- &diff_words->plus, len, DIFF_PLAIN, 0);
- diff_words->minus.current += len;
- break;
+ /* fake an empty "0th" word */
+ ALLOC_GROW(buffer->orig, 1, buffer->orig_alloc);
+ buffer->orig[0].begin = buffer->orig[0].end = buffer->text.ptr;
+ buffer->orig_nr = 1;
+
+ for (i = 0; i < buffer->text.size; i++) {
+ if (find_word_boundaries(&buffer->text, word_regex, &i, &j))
+ return;
+
+ /* store original boundaries */
+ ALLOC_GROW(buffer->orig, buffer->orig_nr + 1,
+ buffer->orig_alloc);
+ buffer->orig[buffer->orig_nr].begin = buffer->text.ptr + i;
+ buffer->orig[buffer->orig_nr].end = buffer->text.ptr + j;
+ buffer->orig_nr++;
+
+ /* store one word */
+ ALLOC_GROW(out->ptr, out->size + j - i + 1, alloc);
+ memcpy(out->ptr + out->size, buffer->text.ptr + i, j - i);
+ out->ptr[out->size + j - i] = '\n';
+ out->size += j - i + 1;
+
+ i = j - 1;
}
}
xdemitconf_t xecfg;
xdemitcb_t ecb;
mmfile_t minus, plus;
- int i;
+
+ /* special case: only removal */
+ if (!diff_words->plus.text.size) {
+ color_fwrite_lines(diff_words->file,
+ diff_get_color(1, DIFF_FILE_OLD),
+ diff_words->minus.text.size, diff_words->minus.text.ptr);
+ diff_words->minus.text.size = 0;
+ return;
+ }
+
+ diff_words->current_plus = diff_words->plus.text.ptr;
memset(&xpp, 0, sizeof(xpp));
memset(&xecfg, 0, sizeof(xecfg));
- minus.size = diff_words->minus.text.size;
- minus.ptr = xmalloc(minus.size);
- memcpy(minus.ptr, diff_words->minus.text.ptr, minus.size);
- for (i = 0; i < minus.size; i++)
- if (isspace(minus.ptr[i]))
- minus.ptr[i] = '\n';
- diff_words->minus.current = 0;
-
- plus.size = diff_words->plus.text.size;
- plus.ptr = xmalloc(plus.size);
- memcpy(plus.ptr, diff_words->plus.text.ptr, plus.size);
- for (i = 0; i < plus.size; i++)
- if (isspace(plus.ptr[i]))
- plus.ptr[i] = '\n';
- diff_words->plus.current = 0;
-
+ diff_words_fill(&diff_words->minus, &minus, diff_words->word_regex);
+ diff_words_fill(&diff_words->plus, &plus, diff_words->word_regex);
xpp.flags = XDF_NEED_MINIMAL;
- xecfg.ctxlen = diff_words->minus.alloc + diff_words->plus.alloc;
+ /* as only the hunk header will be parsed, we need a 0-context */
+ xecfg.ctxlen = 0;
xdi_diff_outf(&minus, &plus, fn_out_diff_words_aux, diff_words,
&xpp, &xecfg, &ecb);
free(minus.ptr);
free(plus.ptr);
+ if (diff_words->current_plus != diff_words->plus.text.ptr +
+ diff_words->plus.text.size)
+ fwrite(diff_words->current_plus,
+ diff_words->plus.text.ptr + diff_words->plus.text.size
+ - diff_words->current_plus, 1,
+ diff_words->file);
diff_words->minus.text.size = diff_words->plus.text.size = 0;
-
- if (diff_words->minus.suppressed_newline) {
- putc('\n', diff_words->file);
- diff_words->minus.suppressed_newline = 0;
- }
}
typedef unsigned long (*sane_truncate_fn)(char *line, unsigned long len);
diff_words_show(ecbdata->diff_words);
free (ecbdata->diff_words->minus.text.ptr);
+ free (ecbdata->diff_words->minus.orig);
free (ecbdata->diff_words->plus.text.ptr);
+ free (ecbdata->diff_words->plus.orig);
+ free(ecbdata->diff_words->word_regex);
free(ecbdata->diff_words);
ecbdata->diff_words = NULL;
}
static void show_stats(struct diffstat_t* data, struct diff_options *options)
{
- int i, len, add, del, total, adds = 0, dels = 0;
+ int i, len, add, del, adds = 0, dels = 0;
int max_change = 0, max_len = 0;
int total_files = data->nr;
int width, name_width;
*/
add = added;
del = deleted;
- total = add + del;
adds += add;
dels += del;
if (width <= max_change) {
add = scale_linear(add, width, max_change);
del = scale_linear(del, width, max_change);
- total = add + del;
}
show_name(options->file, prefix, name, len, reset, set);
fprintf(options->file, "%5d%s", added + deleted,
return one->driver->funcname.pattern ? &one->driver->funcname : NULL;
}
+static const char *userdiff_word_regex(struct diff_filespec *one)
+{
+ diff_filespec_load_driver(one);
+ return one->driver->word_regex;
+}
+
void diff_set_mnemonic_prefix(struct diff_options *options, const char *a, const char *b)
{
if (!options->a_prefix)
ecbdata.file = o->file;
xpp.flags = XDF_NEED_MINIMAL | o->xdl_opts;
xecfg.ctxlen = o->context;
+ xecfg.interhunkctxlen = o->interhunkcontext;
xecfg.flags = XDL_EMIT_FUNCNAMES;
if (pe)
xdiff_set_find_func(&xecfg, pe->pattern, pe->cflags);
ecbdata.diff_words =
xcalloc(1, sizeof(struct diff_words_data));
ecbdata.diff_words->file = o->file;
+ if (!o->word_regex)
+ o->word_regex = userdiff_word_regex(one);
+ if (!o->word_regex)
+ o->word_regex = userdiff_word_regex(two);
+ if (!o->word_regex)
+ o->word_regex = diff_word_regex_cfg;
+ if (o->word_regex) {
+ ecbdata.diff_words->word_regex = (regex_t *)
+ xmalloc(sizeof(regex_t));
+ if (regcomp(ecbdata.diff_words->word_regex,
+ o->word_regex,
+ REG_EXTENDED | REG_NEWLINE))
+ die ("Invalid regular expression: %s",
+ o->word_regex);
+ }
}
xdi_diff_outf(&mf1, &mf2, fn_out_consume, &ecbdata,
&xpp, &xecfg, &ecb);
struct stat st;
int pos, len;
- /* We do not read the cache ourselves here, because the
+ /*
+ * 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
* objects however would tend to be slower as they need
* to be individually opened and inflated.
*/
- if (!FAST_WORKING_DIRECTORY && !want_file && has_sha1_pack(sha1, NULL))
+ if (!FAST_WORKING_DIRECTORY && !want_file && has_sha1_pack(sha1))
return 0;
len = strlen(name);
if (hashcmp(sha1, ce->sha1) || !S_ISREG(ce->ce_mode))
return 0;
+ /*
+ * If ce is marked as "assume unchanged", there is no
+ * guarantee that work tree matches what we are looking for.
+ */
+ if (ce->ce_flags & CE_VALID)
+ return 0;
+
/*
* If ce matches the file in the work tree, we can reuse it.
*/
s->cnt_data = NULL;
}
-static void prep_temp_blob(struct diff_tempfile *temp,
+static void prep_temp_blob(const char *path, struct diff_tempfile *temp,
void *blob,
unsigned long size,
const unsigned char *sha1,
int mode)
{
int fd;
+ struct strbuf buf = STRBUF_INIT;
fd = git_mkstemp(temp->tmp_path, PATH_MAX, ".diff_XXXXXX");
if (fd < 0)
die("unable to create temp-file: %s", strerror(errno));
+ if (convert_to_working_tree(path,
+ (const char *)blob, (size_t)size, &buf)) {
+ blob = buf.buf;
+ size = buf.len;
+ }
if (write_in_full(fd, blob, size) != size)
die("unable to write temp-file");
close(fd);
strcpy(temp->hex, sha1_to_hex(sha1));
temp->hex[40] = 0;
sprintf(temp->mode, "%06o", mode);
+ strbuf_release(&buf);
}
-static void prepare_temp_file(const char *name,
- struct diff_tempfile *temp,
- struct diff_filespec *one)
+static struct diff_tempfile *prepare_temp_file(const char *name,
+ struct diff_filespec *one)
{
+ struct diff_tempfile *temp = claim_diff_tempfile();
+
if (!DIFF_FILE_VALID(one)) {
not_a_valid_file:
/* A '-' entry produces this for file-2, and
temp->name = "/dev/null";
strcpy(temp->hex, ".");
strcpy(temp->mode, ".");
- return;
+ return temp;
+ }
+
+ if (!remove_tempfile_installed) {
+ atexit(remove_tempfile);
+ sigchain_push_common(remove_tempfile_on_signal);
+ remove_tempfile_installed = 1;
}
if (!one->sha1_valid ||
die("readlink(%s)", name);
if (ret == sizeof(buf))
die("symlink too long: %s", name);
- prep_temp_blob(temp, buf, ret,
+ prep_temp_blob(name, temp, buf, ret,
(one->sha1_valid ?
one->sha1 : null_sha1),
(one->sha1_valid ?
*/
sprintf(temp->mode, "%06o", one->mode);
}
- return;
+ return temp;
}
else {
if (diff_populate_filespec(one, 0))
die("cannot read data blob for %s", one->path);
- prep_temp_blob(temp, one->data, one->size,
+ prep_temp_blob(name, 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);
+ return temp;
}
/* An external diff command takes:
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) {
+ struct diff_tempfile *temp_one, *temp_two;
+ const char *othername = (other ? other : name);
+ temp_one = prepare_temp_file(name, one);
+ temp_two = prepare_temp_file(othername, 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;
+ *arg++ = temp_one->name;
+ *arg++ = temp_one->hex;
+ *arg++ = temp_one->mode;
+ *arg++ = temp_two->name;
+ *arg++ = temp_two->hex;
+ *arg++ = temp_two->mode;
if (other) {
*arg++ = other;
*arg++ = xfrm_msg;
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);
+ die("cannot hash %s", one->path);
}
}
else
options->break_opt = -1;
options->rename_limit = -1;
options->dirstat_percent = 3;
- DIFF_OPT_CLR(options, DIRSTAT_CUMULATIVE);
options->context = 3;
options->change = diff_change;
options->add_remove = diff_addremove;
if (diff_use_color_default > 0)
DIFF_OPT_SET(options, COLOR_DIFF);
- else
- DIFF_OPT_CLR(options, COLOR_DIFF);
options->detect_rename = diff_detect_rename_default;
if (!diff_mnemonic_prefix) {
/* xdiff options */
else if (!strcmp(arg, "-w") || !strcmp(arg, "--ignore-all-space"))
- options->xdl_opts |= XDF_IGNORE_WHITESPACE;
+ DIFF_XDL_SET(options, IGNORE_WHITESPACE);
else if (!strcmp(arg, "-b") || !strcmp(arg, "--ignore-space-change"))
- options->xdl_opts |= XDF_IGNORE_WHITESPACE_CHANGE;
+ DIFF_XDL_SET(options, IGNORE_WHITESPACE_CHANGE);
else if (!strcmp(arg, "--ignore-space-at-eol"))
- options->xdl_opts |= XDF_IGNORE_WHITESPACE_AT_EOL;
+ DIFF_XDL_SET(options, IGNORE_WHITESPACE_AT_EOL);
+ else if (!strcmp(arg, "--patience"))
+ DIFF_XDL_SET(options, PATIENCE_DIFF);
/* flags options */
else if (!strcmp(arg, "--binary")) {
DIFF_OPT_SET(options, COLOR_DIFF);
else if (!strcmp(arg, "--no-color"))
DIFF_OPT_CLR(options, COLOR_DIFF);
- else if (!strcmp(arg, "--color-words"))
- options->flags |= DIFF_OPT_COLOR_DIFF | DIFF_OPT_COLOR_DIFF_WORDS;
+ else if (!strcmp(arg, "--color-words")) {
+ DIFF_OPT_SET(options, COLOR_DIFF);
+ DIFF_OPT_SET(options, COLOR_DIFF_WORDS);
+ }
+ else if (!prefixcmp(arg, "--color-words=")) {
+ DIFF_OPT_SET(options, COLOR_DIFF);
+ DIFF_OPT_SET(options, COLOR_DIFF_WORDS);
+ options->word_regex = arg + 14;
+ }
else if (!strcmp(arg, "--exit-code"))
DIFF_OPT_SET(options, EXIT_WITH_STATUS);
else if (!strcmp(arg, "--quiet"))
options->b_prefix = arg + 13;
else if (!strcmp(arg, "--no-prefix"))
options->a_prefix = options->b_prefix = "";
+ else if (opt_arg(arg, '\0', "inter-hunk-context",
+ &options->interhunkcontext))
+ ;
else if (!prefixcmp(arg, "--output=")) {
options->file = fopen(arg + strlen("--output="), "w");
options->close_file = 1;
static char *run_textconv(const char *pgm, struct diff_filespec *spec,
size_t *outsize)
{
- struct diff_tempfile temp;
+ struct diff_tempfile *temp;
const char *argv[3];
const char **arg = argv;
struct child_process child;
struct strbuf buf = STRBUF_INIT;
- prepare_temp_file(spec->path, &temp, spec);
+ temp = prepare_temp_file(spec->path, spec);
*arg++ = pgm;
- *arg++ = temp.name;
+ *arg++ = temp->name;
*arg = NULL;
memset(&child, 0, sizeof(child));
if (start_command(&child) != 0 ||
strbuf_read(&buf, child.out, 0) < 0 ||
finish_command(&child) != 0) {
- if (temp.name == temp.tmp_path)
- unlink(temp.name);
+ remove_tempfile();
error("error running textconv command '%s'", pgm);
return NULL;
}
- if (temp.name == temp.tmp_path)
- unlink(temp.name);
+ remove_tempfile();
return strbuf_detach(&buf, outsize);
}