static int whitespace_error;
static int squelch_whitespace_errors = 5;
static int applied_after_fixing_ws;
+
+static enum ws_ignore {
+ ignore_ws_none,
+ ignore_ws_change,
+} ws_ignore_action = ignore_ws_none;
+
+
static const char *patch_input_file;
static const char *root;
static int root_len;
die("unrecognized whitespace option '%s'", option);
}
+static void parse_ignorewhitespace_option(const char *option)
+{
+ if (!option || !strcmp(option, "no") ||
+ !strcmp(option, "false") || !strcmp(option, "never") ||
+ !strcmp(option, "none")) {
+ ws_ignore_action = ignore_ws_none;
+ return;
+ }
+ if (!strcmp(option, "change")) {
+ ws_ignore_action = ignore_ws_change;
+ return;
+ }
+ die("unrecognized whitespace ignore option '%s'", option);
+}
+
static void set_default_whitespace_mode(const char *whitespace_option)
{
if (!whitespace_option && !apply_default_whitespace)
const char *patch;
int size;
int rejected;
+ int linenr;
struct fragment *next;
};
return h;
}
+/*
+ * Compare lines s1 of length n1 and s2 of length n2, ignoring
+ * whitespace difference. Returns 1 if they match, 0 otherwise
+ */
+static int fuzzy_matchlines(const char *s1, size_t n1,
+ const char *s2, size_t n2)
+{
+ const char *last1 = s1 + n1 - 1;
+ const char *last2 = s2 + n2 - 1;
+ int result = 0;
+
+ if (n1 < 0 || n2 < 0)
+ return 0;
+
+ /* ignore line endings */
+ while ((*last1 == '\r') || (*last1 == '\n'))
+ last1--;
+ while ((*last2 == '\r') || (*last2 == '\n'))
+ last2--;
+
+ /* skip leading whitespace */
+ while (isspace(*s1) && (s1 <= last1))
+ s1++;
+ while (isspace(*s2) && (s2 <= last2))
+ s2++;
+ /* early return if both lines are empty */
+ if ((s1 > last1) && (s2 > last2))
+ return 1;
+ while (!result) {
+ result = *s1++ - *s2++;
+ /*
+ * Skip whitespace inside. We check for whitespace on
+ * both buffers because we don't want "a b" to match
+ * "ab"
+ */
+ if (isspace(*s1) && isspace(*s2)) {
+ while (isspace(*s1) && s1 <= last1)
+ s1++;
+ while (isspace(*s2) && s2 <= last2)
+ s2++;
+ }
+ /*
+ * If we reached the end on one side only,
+ * lines don't match
+ */
+ if (
+ ((s2 > last2) && (s1 <= last1)) ||
+ ((s1 > last1) && (s2 <= last2)))
+ return 0;
+ if ((s1 > last1) && (s2 > last2))
+ break;
+ }
+
+ return !result;
+}
+
static void add_line_info(struct image *img, const char *bol, size_t len, unsigned flag)
{
ALLOC_GROW(img->line_allocated, img->nr + 1, img->alloc);
{
int i = 0, j = 0;
+ if (!name)
+ return NULL;
+
while (name[i]) {
if ((name[j++] = name[i++]) == '/')
while (name[i] == '/')
static char *find_name(const char *line, char *def, int p_value, int terminate)
{
int len;
- const char *start = line;
+ const char *start = NULL;
+
+ if (p_value == 0)
+ start = line;
if (*line == '"') {
struct strbuf name = STRBUF_INIT;
return val;
}
+/*
+ * Does the ---/+++ line has the POSIX timestamp after the last HT?
+ * GNU diff puts epoch there to signal a creation/deletion event. Is
+ * this such a timestamp?
+ */
+static int has_epoch_timestamp(const char *nameline)
+{
+ /*
+ * We are only interested in epoch timestamp; any non-zero
+ * fraction cannot be one, hence "(\.0+)?" in the regexp below.
+ * For the same reason, the date must be either 1969-12-31 or
+ * 1970-01-01, and the seconds part must be "00".
+ */
+ const char stamp_regexp[] =
+ "^(1969-12-31|1970-01-01)"
+ " "
+ "[0-2][0-9]:[0-5][0-9]:00(\\.0+)?"
+ " "
+ "([-+][0-2][0-9][0-5][0-9])\n";
+ const char *timestamp = NULL, *cp;
+ static regex_t *stamp;
+ regmatch_t m[10];
+ int zoneoffset;
+ int hourminute;
+ int status;
+
+ for (cp = nameline; *cp != '\n'; cp++) {
+ if (*cp == '\t')
+ timestamp = cp + 1;
+ }
+ if (!timestamp)
+ return 0;
+ if (!stamp) {
+ stamp = xmalloc(sizeof(*stamp));
+ if (regcomp(stamp, stamp_regexp, REG_EXTENDED)) {
+ warning("Cannot prepare timestamp regexp %s",
+ stamp_regexp);
+ return 0;
+ }
+ }
+
+ status = regexec(stamp, timestamp, ARRAY_SIZE(m), m, 0);
+ if (status) {
+ if (status != REG_NOMATCH)
+ warning("regexec returned %d for input: %s",
+ status, timestamp);
+ return 0;
+ }
+
+ zoneoffset = strtol(timestamp + m[3].rm_so + 1, NULL, 10);
+ zoneoffset = (zoneoffset / 100) * 60 + (zoneoffset % 100);
+ if (timestamp[m[3].rm_so] == '-')
+ zoneoffset = -zoneoffset;
+
+ /*
+ * YYYY-MM-DD hh:mm:ss must be from either 1969-12-31
+ * (west of GMT) or 1970-01-01 (east of GMT)
+ */
+ if ((zoneoffset < 0 && memcmp(timestamp, "1969-12-31", 10)) ||
+ (0 <= zoneoffset && memcmp(timestamp, "1970-01-01", 10)))
+ return 0;
+
+ hourminute = (strtol(timestamp + 11, NULL, 10) * 60 +
+ strtol(timestamp + 14, NULL, 10) -
+ zoneoffset);
+
+ return ((zoneoffset < 0 && hourminute == 1440) ||
+ (0 <= zoneoffset && !hourminute));
+}
+
/*
* Get the name etc info from the ---/+++ lines of a traditional patch header
*
} else {
name = find_name(first, NULL, p_value, TERM_SPACE | TERM_TAB);
name = find_name(second, name, p_value, TERM_SPACE | TERM_TAB);
- patch->old_name = patch->new_name = name;
+ if (has_epoch_timestamp(first)) {
+ patch->is_new = 1;
+ patch->is_delete = 0;
+ patch->new_name = name;
+ } else if (has_epoch_timestamp(second)) {
+ patch->is_new = 0;
+ patch->is_delete = 1;
+ patch->old_name = name;
+ } else {
+ patch->old_name = patch->new_name = name;
+ }
}
if (!name)
die("unable to find filename in patch at line %d", linenr);
if (isnull)
die("git apply: bad git-diff - expected /dev/null, got %s on line %d", name, linenr);
another = find_name(line, NULL, p_value, TERM_TAB);
- if (!another || memcmp(another, name, len))
+ if (!another || memcmp(another, name, len + 1))
die("git apply: bad git-diff - inconsistent %s filename on line %d", oldnew, linenr);
free(another);
return orig_name;
static const char *stop_at_slash(const char *line, int llen)
{
+ int nslash = p_value;
int i;
for (i = 0; i < llen; i++) {
int ch = line[i];
- if (ch == '/')
- return line + i;
+ if (ch == '/' && --nslash <= 0)
+ return &line[i];
}
return NULL;
}
continue;
if (!patch->old_name && !patch->new_name) {
if (!patch->def_name)
- die("git diff header lacks filename information (line %d)", linenr);
+ die("git diff header lacks filename information when removing "
+ "%d leading pathname components (line %d)" , p_value, linenr);
patch->old_name = patch->new_name = patch->def_name;
}
patch->is_toplevel_relative = 1;
return -1;
}
-static void check_whitespace(const char *line, int len, unsigned ws_rule)
+static void record_ws_error(unsigned result, const char *line, int len, int linenr)
{
char *err;
- unsigned result = ws_check(line + 1, len - 1, ws_rule);
+
if (!result)
return;
whitespace_error++;
if (squelch_whitespace_errors &&
squelch_whitespace_errors < whitespace_error)
- ;
- else {
- err = whitespace_error_string(result);
- fprintf(stderr, "%s:%d: %s.\n%.*s\n",
- patch_input_file, linenr, err, len - 2, line + 1);
- free(err);
- }
+ return;
+
+ err = whitespace_error_string(result);
+ fprintf(stderr, "%s:%d: %s.\n%.*s\n",
+ patch_input_file, linenr, err, len, line);
+ free(err);
+}
+
+static void check_whitespace(const char *line, int len, unsigned ws_rule)
+{
+ unsigned result = ws_check(line + 1, len - 1, ws_rule);
+
+ record_ws_error(result, line + 1, len - 2, linenr);
}
/*
int len;
fragment = xcalloc(1, sizeof(*fragment));
+ fragment->linenr = linenr;
len = parse_fragment(line, size, patch, fragment);
if (len <= 0)
die("corrupt patch at line %d", linenr);
}
}
+/*
+ * Update the preimage, and the common lines in postimage,
+ * from buffer buf of length len. If postlen is 0 the postimage
+ * is updated in place, otherwise it's updated on a new buffer
+ * of length postlen
+ */
+
static void update_pre_post_images(struct image *preimage,
struct image *postimage,
char *buf,
- size_t len)
+ size_t len, size_t postlen)
{
int i, ctx;
char *new, *old, *fixed;
*preimage = fixed_preimage;
/*
- * Adjust the common context lines in postimage, in place.
- * This is possible because whitespace fixing does not make
- * the string grow.
+ * Adjust the common context lines in postimage. This can be
+ * done in-place when we are just doing whitespace fixing,
+ * which does not make the string grow, but needs a new buffer
+ * when ignoring whitespace causes the update, since in this case
+ * we could have e.g. tabs converted to multiple spaces.
+ * We trust the caller to tell us if the update can be done
+ * in place (postlen==0) or not.
*/
- new = old = postimage->buf;
+ old = postimage->buf;
+ if (postlen)
+ new = postimage->buf = xmalloc(postlen);
+ else
+ new = old;
fixed = preimage->buf;
for (i = ctx = 0; i < postimage->nr; i++) {
size_t len = postimage->line[i].len;
{
int i;
char *fixed_buf, *buf, *orig, *target;
+ int preimage_limit;
- if (preimage->nr + try_lno > img->nr)
+ if (preimage->nr + try_lno <= img->nr) {
+ /*
+ * The hunk falls within the boundaries of img.
+ */
+ preimage_limit = preimage->nr;
+ if (match_end && (preimage->nr + try_lno != img->nr))
+ return 0;
+ } else if (ws_error_action == correct_ws_error &&
+ (ws_rule & WS_BLANK_AT_EOF) && match_end) {
+ /*
+ * This hunk that matches at the end extends beyond
+ * the end of img, and we are removing blank lines
+ * at the end of the file. This many lines from the
+ * beginning of the preimage must match with img, and
+ * the remainder of the preimage must be blank.
+ */
+ preimage_limit = img->nr - try_lno;
+ } else {
+ /*
+ * The hunk extends beyond the end of the img and
+ * we are not removing blanks at the end, so we
+ * should reject the hunk at this position.
+ */
return 0;
+ }
if (match_beginning && try_lno)
return 0;
- if (match_end && preimage->nr + try_lno != img->nr)
- return 0;
-
/* Quick hash check */
- for (i = 0; i < preimage->nr; i++)
+ for (i = 0; i < preimage_limit; i++)
if (preimage->line[i].hash != img->line[try_lno + i].hash)
return 0;
+ if (preimage_limit == preimage->nr) {
+ /*
+ * Do we have an exact match? If we were told to match
+ * at the end, size must be exactly at try+fragsize,
+ * otherwise try+fragsize must be still within the preimage,
+ * and either case, the old piece should match the preimage
+ * exactly.
+ */
+ if ((match_end
+ ? (try + preimage->len == img->len)
+ : (try + preimage->len <= img->len)) &&
+ !memcmp(img->buf + try, preimage->buf, preimage->len))
+ return 1;
+ } else {
+ /*
+ * The preimage extends beyond the end of img, so
+ * there cannot be an exact match.
+ *
+ * There must be one non-blank context line that match
+ * a line before the end of img.
+ */
+ char *buf_end;
+
+ buf = preimage->buf;
+ buf_end = buf;
+ for (i = 0; i < preimage_limit; i++)
+ buf_end += preimage->line[i].len;
+
+ for ( ; buf < buf_end; buf++)
+ if (!isspace(*buf))
+ break;
+ if (buf == buf_end)
+ return 0;
+ }
+
/*
- * Do we have an exact match? If we were told to match
- * at the end, size must be exactly at try+fragsize,
- * otherwise try+fragsize must be still within the preimage,
- * and either case, the old piece should match the preimage
- * exactly.
+ * No exact match. If we are ignoring whitespace, run a line-by-line
+ * fuzzy matching. We collect all the line length information because
+ * we need it to adjust whitespace if we match.
*/
- if ((match_end
- ? (try + preimage->len == img->len)
- : (try + preimage->len <= img->len)) &&
- !memcmp(img->buf + try, preimage->buf, preimage->len))
+ if (ws_ignore_action == ignore_ws_change) {
+ size_t imgoff = 0;
+ size_t preoff = 0;
+ size_t postlen = postimage->len;
+ size_t extra_chars;
+ char *preimage_eof;
+ char *preimage_end;
+ for (i = 0; i < preimage_limit; i++) {
+ size_t prelen = preimage->line[i].len;
+ size_t imglen = img->line[try_lno+i].len;
+
+ if (!fuzzy_matchlines(img->buf + try + imgoff, imglen,
+ preimage->buf + preoff, prelen))
+ return 0;
+ if (preimage->line[i].flag & LINE_COMMON)
+ postlen += imglen - prelen;
+ imgoff += imglen;
+ preoff += prelen;
+ }
+
+ /*
+ * Ok, the preimage matches with whitespace fuzz.
+ *
+ * imgoff now holds the true length of the target that
+ * matches the preimage before the end of the file.
+ *
+ * Count the number of characters in the preimage that fall
+ * beyond the end of the file and make sure that all of them
+ * are whitespace characters. (This can only happen if
+ * we are removing blank lines at the end of the file.)
+ */
+ buf = preimage_eof = preimage->buf + preoff;
+ for ( ; i < preimage->nr; i++)
+ preoff += preimage->line[i].len;
+ preimage_end = preimage->buf + preoff;
+ for ( ; buf < preimage_end; buf++)
+ if (!isspace(*buf))
+ return 0;
+
+ /*
+ * Update the preimage and the common postimage context
+ * lines to use the same whitespace as the target.
+ * If whitespace is missing in the target (i.e.
+ * if the preimage extends beyond the end of the file),
+ * use the whitespace from the preimage.
+ */
+ extra_chars = preimage_end - preimage_eof;
+ fixed_buf = xmalloc(imgoff + extra_chars);
+ memcpy(fixed_buf, img->buf + try, imgoff);
+ memcpy(fixed_buf + imgoff, preimage_eof, extra_chars);
+ imgoff += extra_chars;
+ update_pre_post_images(preimage, postimage,
+ fixed_buf, imgoff, postlen);
return 1;
+ }
if (ws_error_action != correct_ws_error)
return 0;
/*
* The hunk does not apply byte-by-byte, but the hash says
- * it might with whitespace fuzz.
+ * it might with whitespace fuzz. We haven't been asked to
+ * ignore whitespace, we were asked to correct whitespace
+ * errors, so let's try matching after whitespace correction.
+ *
+ * The preimage may extend beyond the end of the file,
+ * but in this loop we will only handle the part of the
+ * preimage that falls within the file.
*/
fixed_buf = xmalloc(preimage->len + 1);
buf = fixed_buf;
orig = preimage->buf;
target = img->buf + try;
- for (i = 0; i < preimage->nr; i++) {
+ for (i = 0; i < preimage_limit; i++) {
size_t fixlen; /* length after fixing the preimage */
size_t oldlen = preimage->line[i].len;
size_t tgtlen = img->line[try_lno + i].len;
target += tgtlen;
}
+
+ /*
+ * Now handle the lines in the preimage that falls beyond the
+ * end of the file (if any). They will only match if they are
+ * empty or only contain whitespace (if WS_BLANK_AT_EOL is
+ * false).
+ */
+ for ( ; i < preimage->nr; i++) {
+ size_t fixlen; /* length after fixing the preimage */
+ size_t oldlen = preimage->line[i].len;
+ int j;
+
+ /* Try fixing the line in the preimage */
+ fixlen = ws_fix_copy(buf, orig, oldlen, ws_rule, NULL);
+
+ for (j = 0; j < fixlen; j++)
+ if (!isspace(buf[j]))
+ goto unmatch_exit;
+
+ orig += oldlen;
+ buf += fixlen;
+ }
+
/*
* Yes, the preimage is based on an older version that still
* has whitespace breakages unfixed, and fixing them makes the
* hunk match. Update the context lines in the postimage.
*/
update_pre_post_images(preimage, postimage,
- fixed_buf, buf - fixed_buf);
+ fixed_buf, buf - fixed_buf, 0);
return 1;
unmatch_exit:
unsigned long backwards, forwards, try;
int backwards_lno, forwards_lno, try_lno;
- if (preimage->nr > img->nr)
- return -1;
-
/*
- * If match_begining or match_end is specified, there is no
+ * If match_beginning or match_end is specified, there is no
* point starting from a wrong line that will never match and
* wander around and wait for a match at the specified end.
*/
else if (match_end)
line = img->nr - preimage->nr;
- if (line > img->nr)
+ /*
+ * Because the comparison is unsigned, the following test
+ * will also take care of a negative line number that can
+ * result when match_end and preimage is larger than the target.
+ */
+ if ((size_t) line > img->nr)
line = img->nr;
try = 0;
int i, nr;
size_t remove_count, insert_count, applied_at = 0;
char *result;
+ int preimage_limit;
+
+ /*
+ * If we are removing blank lines at the end of img,
+ * the preimage may extend beyond the end.
+ * If that is the case, we must be careful only to
+ * remove the part of the preimage that falls within
+ * the boundaries of img. Initialize preimage_limit
+ * to the number of lines in the preimage that falls
+ * within the boundaries.
+ */
+ preimage_limit = preimage->nr;
+ if (preimage_limit > img->nr - applied_pos)
+ preimage_limit = img->nr - applied_pos;
for (i = 0; i < applied_pos; i++)
applied_at += img->line[i].len;
remove_count = 0;
- for (i = 0; i < preimage->nr; i++)
+ for (i = 0; i < preimage_limit; i++)
remove_count += img->line[applied_pos + i].len;
insert_count = postimage->len;
result[img->len] = '\0';
/* Adjust the line table */
- nr = img->nr + postimage->nr - preimage->nr;
- if (preimage->nr < postimage->nr) {
+ nr = img->nr + postimage->nr - preimage_limit;
+ if (preimage_limit < postimage->nr) {
/*
* NOTE: this knows that we never call remove_first_line()
* on anything other than pre/post image.
img->line = xrealloc(img->line, nr * sizeof(*img->line));
img->line_allocated = img->line;
}
- if (preimage->nr != postimage->nr)
+ if (preimage_limit != postimage->nr)
memmove(img->line + applied_pos + postimage->nr,
- img->line + applied_pos + preimage->nr,
- (img->nr - (applied_pos + preimage->nr)) *
+ img->line + applied_pos + preimage_limit,
+ (img->nr - (applied_pos + preimage_limit)) *
sizeof(*img->line));
memcpy(img->line + applied_pos,
postimage->line,
int len = linelen(patch, size);
int plen, added;
int added_blank_line = 0;
+ int is_blank_context = 0;
if (!len)
break;
*new++ = '\n';
add_line_info(&preimage, "\n", 1, LINE_COMMON);
add_line_info(&postimage, "\n", 1, LINE_COMMON);
+ is_blank_context = 1;
break;
case ' ':
+ if (plen && (ws_rule & WS_BLANK_AT_EOF) &&
+ ws_blank_line(patch + 1, plen, ws_rule))
+ is_blank_context = 1;
case '-':
memcpy(old, patch + 1, plen);
add_line_info(&preimage, old, plen,
(first == '+' ? 0 : LINE_COMMON));
new += added;
if (first == '+' &&
- added == 1 && new[-1] == '\n')
+ (ws_rule & WS_BLANK_AT_EOF) &&
+ ws_blank_line(patch + 1, plen, ws_rule))
added_blank_line = 1;
break;
case '@': case '\\':
}
if (added_blank_line)
new_blank_lines_at_end++;
+ else if (is_blank_context)
+ ;
else
new_blank_lines_at_end = 0;
patch += len;
}
if (applied_pos >= 0) {
- if (ws_error_action == correct_ws_error &&
- new_blank_lines_at_end &&
- postimage.nr + applied_pos == img->nr) {
+ if (new_blank_lines_at_end &&
+ preimage.nr + applied_pos >= img->nr &&
+ (ws_rule & WS_BLANK_AT_EOF) &&
+ ws_error_action != nowarn_ws_error) {
+ record_ws_error(WS_BLANK_AT_EOF, "+", 1, frag->linenr);
+ if (ws_error_action == correct_ws_error) {
+ while (new_blank_lines_at_end--)
+ remove_last_line(&postimage);
+ }
/*
- * If the patch application adds blank lines
- * at the end, and if the patch applies at the
- * end of the image, remove those added blank
- * lines.
+ * We would want to prevent write_out_results()
+ * from taking place in apply_patch() that follows
+ * the callchain led us here, which is:
+ * apply_patch->check_patch_list->check_patch->
+ * apply_data->apply_fragments->apply_one_fragment
*/
- while (new_blank_lines_at_end--)
- remove_last_line(&postimage);
+ if (ws_error_action == die_on_ws_error)
+ apply = 0;
}
/*
return -1;
return 0;
}
- return ce_match_stat(ce, st, CE_MATCH_IGNORE_VALID);
+ return ce_match_stat(ce, st, CE_MATCH_IGNORE_VALID|CE_MATCH_IGNORE_SKIP_WORKTREE);
}
static int check_preimage(struct patch *patch, struct cache_entry **ce, struct stat *st)
if (stat_ret < 0) {
struct checkout costate;
/* checkout */
+ memset(&costate, 0, sizeof(costate));
costate.base_dir = "";
- costate.base_dir_len = 0;
- costate.force = 0;
- costate.quiet = 0;
- costate.not_new = 0;
costate.refresh_cache = 1;
if (checkout_entry(*ce, &costate, NULL) ||
lstat(old_name, st))
{
if (!strcmp(var, "apply.whitespace"))
return git_config_string(&apply_default_whitespace, var, value);
+ else if (!strcmp(var, "apply.ignorewhitespace"))
+ return git_config_string(&apply_default_ignorewhitespace, var, value);
return git_default_config(var, value, cb);
}
return 0;
}
+static int option_parse_space_change(const struct option *opt,
+ const char *arg, int unset)
+{
+ if (unset)
+ ws_ignore_action = ignore_ws_none;
+ else
+ ws_ignore_action = ignore_ws_change;
+ return 0;
+}
+
static int option_parse_whitespace(const struct option *opt,
const char *arg, int unset)
{
{ OPTION_CALLBACK, 0, "whitespace", &whitespace_option, "action",
"detect new or modified lines that have whitespace errors",
0, option_parse_whitespace },
+ { OPTION_CALLBACK, 0, "ignore-space-change", NULL, NULL,
+ "ignore changes in whitespace when finding context",
+ PARSE_OPT_NOARG, option_parse_space_change },
+ { OPTION_CALLBACK, 0, "ignore-whitespace", NULL, NULL,
+ "ignore changes in whitespace when finding context",
+ PARSE_OPT_NOARG, option_parse_space_change },
OPT_BOOLEAN('R', "reverse", &apply_in_reverse,
"apply the patch in reverse"),
OPT_BOOLEAN(0, "unidiff-zero", &unidiff_zero,
git_config(git_apply_config, NULL);
if (apply_default_whitespace)
parse_whitespace_option(apply_default_whitespace);
+ if (apply_default_ignorewhitespace)
+ parse_ignorewhitespace_option(apply_default_ignorewhitespace);
argc = parse_options(argc, argv, prefix, builtin_apply_options,
apply_usage, 0);