static int line_termination = '\n';
static unsigned long p_context = ULONG_MAX;
static const char apply_usage[] =
-"git-apply [--stat] [--numstat] [--summary] [--check] [--index] [--cached] [--apply] [--no-add] [--index-info] [--allow-binary-replacement] [--reverse] [--reject] [--verbose] [-z] [-pNUM] [-CNUM] [--whitespace=<nowarn|warn|
error|error-all|strip>] <patch>...";
-
-static enum whitespace_eol {
- nowarn_whitespace,
- warn_on_whitespace,
- error_on_whitespace,
- strip_whitespace,
-} new_whitespace = warn_on_whitespace;
+"git-apply [--stat] [--numstat] [--summary] [--check] [--index] [--cached] [--apply] [--no-add] [--index-info] [--allow-binary-replacement] [--reverse] [--reject] [--verbose] [-z] [-pNUM] [-CNUM] [--whitespace=<nowarn|warn|
fix|error|error-all>] <patch>...";
+
+static enum ws_error_action {
+ nowarn_ws_error,
+ warn_on_ws_error,
+ die_on_ws_error,
+ correct_ws_error,
+} ws_error_action = warn_on_ws_error;
static int whitespace_error;
static int squelch_whitespace_errors = 5;
static int applied_after_fixing_ws;
static void parse_whitespace_option(const char *option)
{
if (!option) {
- new_whitespace = warn_on_whitespace;
+ ws_error_action = warn_on_ws_error;
return;
}
if (!strcmp(option, "warn")) {
- new_whitespace = warn_on_whitespace;
+ ws_error_action = warn_on_ws_error;
return;
}
if (!strcmp(option, "nowarn")) {
- new_whitespace = nowarn_whitespace;
+ ws_error_action = nowarn_ws_error;
return;
}
if (!strcmp(option, "error")) {
- new_whitespace = error_on_whitespace;
+ ws_error_action = die_on_ws_error;
return;
}
if (!strcmp(option, "error-all")) {
- new_whitespace = error_on_whitespace;
+ ws_error_action = die_on_ws_error;
squelch_whitespace_errors = 0;
return;
}
- if (!strcmp(option, "strip")) {
- new_whitespace = strip_whitespace;
+ if (!strcmp(option, "strip") || !strcmp(option, "fix")) {
+ ws_error_action = correct_ws_error;
return;
}
die("unrecognized whitespace option '%s'", option);
static void set_default_whitespace_mode(const char *whitespace_option)
{
- if (!whitespace_option && !apply_default_whitespace) {
- new_whitespace = (apply
- ? warn_on_whitespace
- : nowarn_whitespace);
- }
+ if (!whitespace_option && !apply_default_whitespace)
+ ws_error_action = (apply ? warn_on_ws_error : nowarn_ws_error);
}
/*
#define BINARY_DELTA_DEFLATED 1
#define BINARY_LITERAL_DEFLATED 2
+/*
+ * This represents a "patch" to a file, both metainfo changes
+ * such as creation/deletion, filemode and content changes represented
+ * as a series of fragments.
+ */
struct patch {
char *new_name, *old_name, *def_name;
unsigned int old_mode, new_mode;
int is_new, is_delete; /* -1 = unknown, 0 = false, 1 = true */
int rejected;
+ unsigned ws_rule;
unsigned long deflate_origlen;
int lines_added, lines_deleted;
int score;
struct patch *next;
};
-static void say_patch_name(FILE *output, const char *pre, struct patch *patch, const char *post)
+/*
+ * A line in a file, len-bytes long (includes the terminating LF,
+ * except for an incomplete line at the end if the file ends with
+ * one), and its contents hashes to 'hash'.
+ */
+struct line {
+ size_t len;
+ unsigned hash : 24;
+ unsigned flag : 8;
+#define LINE_COMMON 1
+};
+
+/*
+ * This represents a "file", which is an array of "lines".
+ */
+struct image {
+ char *buf;
+ size_t len;
+ size_t nr;
+ size_t alloc;
+ struct line *line_allocated;
+ struct line *line;
+};
+
+static uint32_t hash_line(const char *cp, size_t len)
+{
+ size_t i;
+ uint32_t h;
+ for (i = 0, h = 0; i < len; i++) {
+ if (!isspace(cp[i])) {
+ h = h * 3 + (cp[i] & 0xff);
+ }
+ }
+ return h;
+}
+
+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);
+ img->line_allocated[img->nr].len = len;
+ img->line_allocated[img->nr].hash = hash_line(bol, len);
+ img->line_allocated[img->nr].flag = flag;
+ img->nr++;
+}
+
+static void prepare_image(struct image *image, char *buf, size_t len,
+ int prepare_linetable)
+{
+ const char *cp, *ep;
+
+ memset(image, 0, sizeof(*image));
+ image->buf = buf;
+ image->len = len;
+
+ if (!prepare_linetable)
+ return;
+
+ ep = image->buf + image->len;
+ cp = image->buf;
+ while (cp < ep) {
+ const char *next;
+ for (next = cp; next < ep && *next != '\n'; next++)
+ ;
+ if (next < ep)
+ next++;
+ add_line_info(image, cp, next - cp, 0);
+ cp = next;
+ }
+ image->line = image->line_allocated;
+}
+
+static void clear_image(struct image *image)
+{
+ free(image->buf);
+ image->buf = NULL;
+ image->len = 0;
+}
+
+static void say_patch_name(FILE *output, const char *pre,
+ struct patch *patch, const char *post)
{
fputs(pre, output);
if (patch->old_name && patch->new_name &&
if (*line == '"') {
struct strbuf name;
- /* Proposed "new-style" GNU patch/diff format; see
+ /*
+ * Proposed "new-style" GNU patch/diff format; see
* http://marc.theaimsgroup.com/?l=git&m=112927316408690&w=2
*/
strbuf_init(&name, 0);
static int gitdiff_index(const char *line, struct patch *patch)
{
- /* index line is N hexadecimal, "..", N hexadecimal,
+ /*
+ * index line is N hexadecimal, "..", N hexadecimal,
* and optional space with octal mode.
*/
const char *ptr, *eol;
return NULL;
}
-/* This is to extract the same name that appears on "diff --git"
+/*
+ * This is to extract the same name that appears on "diff --git"
* line. We do not find and return anything if it is a rename
* patch, and it is OK because we will find the name elsewhere.
* We need to reliably find name only when it is mode-change only,
goto free_and_fail1;
strbuf_remove(&first, 0, cp + 1 - first.buf);
- /* second points at one past closing dq of name.
+ /*
+ * second points at one past closing dq of name.
* find the second name.
*/
while ((second < line + llen) && isspace(*second))
return NULL;
name++;
- /* since the first name is unquoted, a dq if exists must be
+ /*
+ * since the first name is unquoted, a dq if exists must be
* the beginning of the second name.
*/
for (second = name; second < line + llen; second++) {
}
static int parse_range(const char *line, int len, int offset, const char *expect,
- unsigned long *p1, unsigned long *p2)
+ unsigned long *p1, unsigned long *p2)
{
int digits, ex;
return offset;
}
- /** --- followed by +++ ? */
+ /* --- followed by +++ ? */
if (memcmp("--- ", line, 4) || memcmp("+++ ", line + len, 4))
continue;
/*
* We only accept unified patches, so we want it to
* at least have "@@ -a,b +c,d @@\n", which is 14 chars
- * minimum
+ * minimum ("@@ -0,0 +1 @@\n" is the shortest).
*/
nextlen = linelen(line + len, size - len);
if (size < nextlen + 14 || memcmp("@@ -", line + len + nextlen, 4))
return -1;
}
-static void check_whitespace(const char *line, int len)
+static void check_whitespace(const char *line, int len, unsigned ws_rule)
{
- const char *err = "Adds trailing whitespace";
- int seen_space = 0;
- int i;
-
- /*
- * We know len is at least two, since we have a '+' and we
- * checked that the last character was a '\n' before calling
- * this function. That is, an addition of an empty line would
- * check the '+' here. Sneaky...
- */
- if (isspace(line[len-2]))
- goto error;
-
- /*
- * Make sure that there is no space followed by a tab in
- * indentation.
- */
- err = "Space in indent is followed by a tab";
- for (i = 1; i < len; i++) {
- if (line[i] == '\t') {
- if (seen_space)
- goto error;
- }
- else if (line[i] == ' ')
- seen_space = 1;
- else
- break;
- }
- return;
+ char *err;
+ unsigned result = check_and_emit_line(line + 1, len - 1, ws_rule,
+ NULL, NULL, NULL, NULL);
+ if (!result)
+ return;
- error:
whitespace_error++;
if (squelch_whitespace_errors &&
squelch_whitespace_errors < whitespace_error)
;
- else
- fprintf(stderr, "%s.\n%s:%d:%.*s\n",
- err, patch_input_file, linenr, len-2, line+1);
+ 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);
+ }
}
-
/*
* Parse a unified diff. Note that this really needs to parse each
* fragment separately, since the only way to know the difference
* between a "---" that is part of a patch, and a "---" that starts
* the next patch is to look at the line counts..
*/
-static int parse_fragment(char *line, unsigned long size, struct patch *patch, struct fragment *fragment)
+static int parse_fragment(char *line, unsigned long size,
+ struct patch *patch, struct fragment *fragment)
{
int added, deleted;
int len = linelen(line, size), offset;
break;
case '-':
if (apply_in_reverse &&
- new_whitespace != nowarn_whitespace)
- check_whitespace(line, len);
+ ws_error_action != nowarn_ws_error)
+ check_whitespace(line, len, patch->ws_rule);
deleted++;
oldlines--;
trailing = 0;
break;
case '+':
if (!apply_in_reverse &&
- new_whitespace != nowarn_whitespace)
- check_whitespace(line, len);
+ ws_error_action != nowarn_ws_error)
+ check_whitespace(line, len, patch->ws_rule);
added++;
newlines--;
trailing = 0;
break;
- /* We allow "\ No newline at end of file". Depending
+ /*
+ * We allow "\ No newline at end of file". Depending
* on locale settings when the patch was produced we
* don't know what this line looks like. The only
* thing we do know is that it begins with "\ ".
fragment->leading = leading;
fragment->trailing = trailing;
- /* If a fragment ends with an incomplete line, we failed to include
+ /*
+ * If a fragment ends with an incomplete line, we failed to include
* it in the above loop because we hit oldlines == newlines == 0
* before seeing it.
*/
int *status_p,
int *used_p)
{
- /* Expect a line that begins with binary patch method ("literal"
+ /*
+ * Expect a line that begins with binary patch method ("literal"
* or "delta"), followed by the length of data before deflating.
* a sequence of 'length-byte' followed by base-85 encoded data
* should follow, terminated by a newline.
size--;
break;
}
- /* Minimum line is "A00000\n" which is 7-byte long,
+ /*
+ * Minimum line is "A00000\n" which is 7-byte long,
* and the line length must be multiple of 5 plus 2.
*/
if ((llen < 7) || (llen-2) % 5)
static int parse_binary(char *buffer, unsigned long size, struct patch *patch)
{
- /* We have read "GIT binary patch\n"; what follows is a line
+ /*
+ * We have read "GIT binary patch\n"; what follows is a line
* that says the patch method (currently, either "literal" or
* "delta") and the length of data before deflating; a
* sequence of 'length-byte' followed by base-85 encoded data
if (reverse)
used += used_1;
else if (status) {
- /* not having reverse hunk is not an error, but having
+ /*
+ * Not having reverse hunk is not an error, but having
* a corrupt reverse hunk is.
*/
free((void*) forward->patch);
if (offset < 0)
return offset;
- patchsize = parse_single_patch(buffer + offset + hdrsize, size - offset - hdrsize, patch);
+ patch->ws_rule = whitespace_rule(patch->new_name
+ ? patch->new_name
+ : patch->old_name);
+
+ patchsize = parse_single_patch(buffer + offset + hdrsize,
+ size - offset - hdrsize, patch);
if (!patchsize) {
static const char *binhdr[] = {
}
}
-static const char pluses[] = "++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++";
-static const char minuses[]= "----------------------------------------------------------------------";
+static const char pluses[] =
+"++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++";
+static const char minuses[]=
+"----------------------------------------------------------------------";
static void show_stats(struct patch *patch)
{
case S_IFREG:
if (strbuf_read_file(buf, path, st->st_size) != st->st_size)
return error("unable to open or read %s", path);
- convert_to_git(path, buf->buf, buf->len, buf);
+ convert_to_git(path, buf->buf, buf->len, buf, 0);
return 0;
default:
return -1;
}
}
-static int find_offset(const char *buf, unsigned long size, const char *fragment, unsigned long fragsize, int line, int *lines)
+static void update_pre_post_images(struct image *preimage,
+ struct image *postimage,
+ char *buf,
+ size_t len)
{
- int i;
- unsigned long start, backwards, forwards;
+ int i, ctx;
+ char *new, *old, *fixed;
+ struct image fixed_preimage;
- if (fragsize > size)
- return -1;
+ /*
+ * Update the preimage with whitespace fixes. Note that we
+ * are not losing preimage->buf -- apply_one_fragment() will
+ * free "oldlines".
+ */
+ prepare_image(&fixed_preimage, buf, len, 1);
+ assert(fixed_preimage.nr == preimage->nr);
+ for (i = 0; i < preimage->nr; i++)
+ fixed_preimage.line[i].flag = preimage->line[i].flag;
+ free(preimage->line_allocated);
+ *preimage = fixed_preimage;
- start = 0;
- if (line > 1) {
- unsigned long offset = 0;
- i = line-1;
- while (offset + fragsize <= size) {
- if (buf[offset++] == '\n') {
- start = offset;
- if (!--i)
- break;
- }
+ /*
+ * Adjust the common context lines in postimage, in place.
+ * This is possible because whitespace fixing does not make
+ * the string grow.
+ */
+ new = old = postimage->buf;
+ fixed = preimage->buf;
+ for (i = ctx = 0; i < postimage->nr; i++) {
+ size_t len = postimage->line[i].len;
+ if (!(postimage->line[i].flag & LINE_COMMON)) {
+ /* an added line -- no counterparts in preimage */
+ memmove(new, old, len);
+ old += len;
+ new += len;
+ continue;
+ }
+
+ /* a common context -- skip it in the original postimage */
+ old += len;
+
+ /* and find the corresponding one in the fixed preimage */
+ while (ctx < preimage->nr &&
+ !(preimage->line[ctx].flag & LINE_COMMON)) {
+ fixed += preimage->line[ctx].len;
+ ctx++;
}
+ if (preimage->nr <= ctx)
+ die("oops");
+
+ /* and copy it in, while fixing the line length */
+ len = preimage->line[ctx].len;
+ memcpy(new, fixed, len);
+ new += len;
+ fixed += len;
+ postimage->line[i].len = len;
+ ctx++;
+ }
+
+ /* Fix the length of the whole thing */
+ postimage->len = new - postimage->buf;
+}
+
+static int match_fragment(struct image *img,
+ struct image *preimage,
+ struct image *postimage,
+ unsigned long try,
+ int try_lno,
+ unsigned ws_rule,
+ int match_beginning, int match_end)
+{
+ int i;
+ char *fixed_buf, *buf, *orig, *target;
+
+ if (preimage->nr + try_lno > img->nr)
+ 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++)
+ if (preimage->line[i].hash != img->line[try_lno + i].hash)
+ 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.
+ */
+ if ((match_end
+ ? (try + preimage->len == img->len)
+ : (try + preimage->len <= img->len)) &&
+ !memcmp(img->buf + try, preimage->buf, preimage->len))
+ 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.
+ */
+ fixed_buf = xmalloc(preimage->len + 1);
+ buf = fixed_buf;
+ orig = preimage->buf;
+ target = img->buf + try;
+ for (i = 0; i < preimage->nr; 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;
+ size_t tgtfixlen; /* length after fixing the target line */
+ char tgtfixbuf[1024], *tgtfix;
+ int match;
+
+ /* Try fixing the line in the preimage */
+ fixlen = ws_fix_copy(buf, orig, oldlen, ws_rule, NULL);
+
+ /* Try fixing the line in the target */
+ if (sizeof(tgtfixbuf) < tgtlen)
+ tgtfix = tgtfixbuf;
+ else
+ tgtfix = xmalloc(tgtlen);
+ tgtfixlen = ws_fix_copy(tgtfix, target, tgtlen, ws_rule, NULL);
+
+ /*
+ * If they match, either the preimage was based on
+ * a version before our tree fixed whitespace breakage,
+ * or we are lacking a whitespace-fix patch the tree
+ * the preimage was based on already had (i.e. target
+ * has whitespace breakage, the preimage doesn't).
+ * In either case, we are fixing the whitespace breakages
+ * so we might as well take the fix together with their
+ * real change.
+ */
+ match = (tgtfixlen == fixlen && !memcmp(tgtfix, buf, fixlen));
+
+ if (tgtfix != tgtfixbuf)
+ free(tgtfix);
+ if (!match)
+ goto unmatch_exit;
+
+ orig += oldlen;
+ buf += fixlen;
+ target += tgtlen;
}
- /* Exact line number? */
- if ((start + fragsize <= size) &&
- !memcmp(buf + start, fragment, fragsize))
- return start;
+ /*
+ * 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);
+ return 1;
+
+ unmatch_exit:
+ free(fixed_buf);
+ return 0;
+}
+
+static int find_pos(struct image *img,
+ struct image *preimage,
+ struct image *postimage,
+ int line,
+ unsigned ws_rule,
+ int match_beginning, int match_end)
+{
+ int i;
+ 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
+ * point starting from a wrong line that will never match and
+ * wander around and wait for a match at the specified end.
+ */
+ if (match_beginning)
+ line = 0;
+ else if (match_end)
+ line = img->nr - preimage->nr;
+
+ if (line > img->nr)
+ line = img->nr;
+
+ try = 0;
+ for (i = 0; i < line; i++)
+ try += img->line[i].len;
/*
* There's probably some smart way to do this, but I'll leave
* that to the smart and beautiful people. I'm simple and stupid.
*/
- backwards = start;
- forwards = start;
+ backwards = try;
+ backwards_lno = line;
+ forwards = try;
+ forwards_lno = line;
+ try_lno = line;
+
for (i = 0; ; i++) {
- unsigned long try;
- int n;
+ if (match_fragment(img, preimage, postimage,
+ try, try_lno, ws_rule,
+ match_beginning, match_end))
+ return try_lno;
+
+ again:
+ if (backwards_lno == 0 && forwards_lno == img->nr)
+ break;
- /* "backward" */
if (i & 1) {
- if (!backwards) {
- if (forwards + fragsize > size)
- break;
- continue;
+ if (backwards_lno == 0) {
+ i++;
+ goto again;
}
- do {
- --backwards;
- } while (backwards && buf[backwards-1] != '\n');
+ backwards_lno--;
+ backwards -= img->line[backwards_lno].len;
try = backwards;
+ try_lno = backwards_lno;
} else {
- while (forwards + fragsize <= size) {
- if (buf[forwards++] == '\n')
- break;
+ if (forwards_lno == img->nr) {
+ i++;
+ goto again;
}
+ forwards += img->line[forwards_lno].len;
+ forwards_lno++;
try = forwards;
+ try_lno = forwards_lno;
}
- if (try + fragsize > size)
- continue;
- if (memcmp(buf + try, fragment, fragsize))
- continue;
- n = (i >> 1)+1;
- if (i & 1)
- n = -n;
- *lines = n;
- return try;
}
-
- /*
- * We should start searching forward and backward.
- */
return -1;
}
-static void remove_first_line(const char **rbuf, int *rsize)
+static void remove_first_line(struct image *img)
{
- const char *buf = *rbuf;
- int size = *rsize;
- unsigned long offset;
- offset = 0;
- while (offset <= size) {
- if (buf[offset++] == '\n')
- break;
- }
- *rsize = size - offset;
- *rbuf = buf + offset;
+ img->buf += img->line[0].len;
+ img->len -= img->line[0].len;
+ img->line++;
+ img->nr--;
}
-static void remove_last_line(const char **rbuf, int *rsize)
+static void remove_last_line(struct image *img)
{
- const char *buf = *rbuf;
- int size = *rsize;
- unsigned long offset;
- offset = size - 1;
- while (offset > 0) {
- if (buf[--offset] == '\n')
- break;
- }
- *rsize = offset + 1;
+ img->len -= img->line[--img->nr].len;
}
-static int apply_line(char *output, const char *patch, int plen)
+static void update_image(struct image *img,
+ int applied_pos,
+ struct image *preimage,
+ struct image *postimage)
{
- /* plen is number of bytes to be copied from patch,
- * starting at patch+1 (patch[0] is '+'). Typically
- * patch[plen] is '\n', unless this is the incomplete
- * last line.
+ /*
+ * remove the copy of preimage at offset in img
+ * and replace it with postimage
*/
- int i;
- int add_nl_to_tail = 0;
- int fixed = 0;
- int last_tab_in_indent = -1;
- int last_space_in_indent = -1;
- int need_fix_leading_space = 0;
- char *buf;
-
- if ((new_whitespace != strip_whitespace) || !whitespace_error ||
- *patch != '+') {
- memcpy(output, patch + 1, plen);
- return plen;
- }
-
- if (1 < plen && isspace(patch[plen-1])) {
- if (patch[plen] == '\n')
- add_nl_to_tail = 1;
- plen--;
- while (0 < plen && isspace(patch[plen]))
- plen--;
- fixed = 1;
- }
-
- for (i = 1; i < plen; i++) {
- char ch = patch[i];
- if (ch == '\t') {
- last_tab_in_indent = i;
- if (0 <= last_space_in_indent)
- need_fix_leading_space = 1;
- }
- else if (ch == ' ')
- last_space_in_indent = i;
- else
- break;
- }
+ int i, nr;
+ size_t remove_count, insert_count, applied_at = 0;
+ char *result;
- buf = output;
- if (need_fix_leading_space) {
- int consecutive_spaces = 0;
- /* between patch[1..last_tab_in_indent] strip the
- * funny spaces, updating them to tab as needed.
+ for (i = 0; i < applied_pos; i++)
+ applied_at += img->line[i].len;
+
+ remove_count = 0;
+ for (i = 0; i < preimage->nr; i++)
+ remove_count += img->line[applied_pos + i].len;
+ insert_count = postimage->len;
+
+ /* Adjust the contents */
+ result = xmalloc(img->len + insert_count - remove_count + 1);
+ memcpy(result, img->buf, applied_at);
+ memcpy(result + applied_at, postimage->buf, postimage->len);
+ memcpy(result + applied_at + postimage->len,
+ img->buf + (applied_at + remove_count),
+ img->len - (applied_at + remove_count));
+ free(img->buf);
+ img->buf = result;
+ img->len += insert_count - remove_count;
+ result[img->len] = '\0';
+
+ /* Adjust the line table */
+ nr = img->nr + postimage->nr - preimage->nr;
+ if (preimage->nr < postimage->nr) {
+ /*
+ * NOTE: this knows that we never call remove_first_line()
+ * on anything other than pre/post image.
*/
- for (i = 1; i < last_tab_in_indent; i++, plen--) {
- char ch = patch[i];
- if (ch != ' ') {
- consecutive_spaces = 0;
- *output++ = ch;
- } else {
- consecutive_spaces++;
- if (consecutive_spaces == 8) {
- *output++ = '\t';
- consecutive_spaces = 0;
- }
- }
- }
- fixed = 1;
- i = last_tab_in_indent;
+ img->line = xrealloc(img->line, nr * sizeof(*img->line));
+ img->line_allocated = img->line;
}
- else
- i = 1;
-
- memcpy(output, patch + i, plen);
- if (add_nl_to_tail)
- output[plen++] = '\n';
- if (fixed)
- applied_after_fixing_ws++;
- return output + plen - buf;
+ if (preimage->nr != postimage->nr)
+ memmove(img->line + applied_pos + postimage->nr,
+ img->line + applied_pos + preimage->nr,
+ (img->nr - (applied_pos + preimage->nr)) *
+ sizeof(*img->line));
+ memcpy(img->line + applied_pos,
+ postimage->line,
+ postimage->nr * sizeof(*img->line));
+ img->nr = nr;
}
-static int apply_one_fragment(struct strbuf *buf, struct fragment *frag, int inaccurate_eof)
+static int apply_one_fragment(struct image *img, struct fragment *frag,
+ int inaccurate_eof, unsigned ws_rule)
{
int match_beginning, match_end;
const char *patch = frag->patch;
- int offset, size = frag->size;
- char *old = xmalloc(size);
- char *new = xmalloc(size);
- const char *oldlines, *newlines;
- int oldsize = 0, newsize = 0;
+ int size = frag->size;
+ char *old, *new, *oldlines, *newlines;
int new_blank_lines_at_end = 0;
unsigned long leading, trailing;
- int pos, lines;
+ int pos, applied_pos;
+ struct image preimage;
+ struct image postimage;
+
+ memset(&preimage, 0, sizeof(preimage));
+ memset(&postimage, 0, sizeof(postimage));
+ oldlines = xmalloc(size);
+ newlines = xmalloc(size);
+ old = oldlines;
+ new = newlines;
while (size > 0) {
char first;
int len = linelen(patch, size);
- int plen;
+ int plen, added;
int added_blank_line = 0;
if (!len)
* followed by "\ No newline", then we also remove the
* last one (which is the newline, of course).
*/
- plen = len-1;
+ plen = len - 1;
if (len < size && patch[len] == '\\')
plen--;
first = *patch;
if (plen < 0)
/* ... followed by '\No newline'; nothing */
break;
- old[oldsize++] = '\n';
- new[newsize++] = '\n';
+ *old++ = '\n';
+ *new++ = '\n';
+ add_line_info(&preimage, "\n", 1, LINE_COMMON);
+ add_line_info(&postimage, "\n", 1, LINE_COMMON);
break;
case ' ':
case '-':
- memcpy(old + oldsize, patch + 1, plen);
- oldsize += plen;
+ memcpy(old, patch + 1, plen);
+ add_line_info(&preimage, old, plen,
+ (first == ' ' ? LINE_COMMON : 0));
+ old += plen;
if (first == '-')
break;
/* Fall-through for ' ' */
case '+':
- if (first != '+' || !no_add) {
- int added = apply_line(new + newsize, patch,
- plen);
- newsize += added;
- if (first == '+' &&
- added == 1 && new[newsize-1] == '\n')
- added_blank_line = 1;
+ /* --no-add does not add new lines */
+ if (first == '+' && no_add)
+ break;
+
+ if (first != '+' ||
+ !whitespace_error ||
+ ws_error_action != correct_ws_error) {
+ memcpy(new, patch + 1, plen);
+ added = plen;
+ }
+ else {
+ added = ws_fix_copy(new, patch + 1, plen, ws_rule, &applied_after_fixing_ws);
}
+ add_line_info(&postimage, new, added,
+ (first == '+' ? 0 : LINE_COMMON));
+ new += added;
+ if (first == '+' &&
+ added == 1 && new[-1] == '\n')
+ added_blank_line = 1;
break;
case '@': case '\\':
/* Ignore it, we already handled it */
patch += len;
size -= len;
}
-
- if (inaccurate_eof && oldsize > 0 && old[oldsize - 1] == '\n' &&
- newsize > 0 && new[newsize - 1] == '\n') {
- oldsize--;
- newsize--;
+ if (inaccurate_eof &&
+ old > oldlines && old[-1] == '\n' &&
+ new > newlines && new[-1] == '\n') {
+ old--;
+ new--;
}
- oldlines = old;
- newlines = new;
leading = frag->leading;
trailing = frag->trailing;
/*
- * If we don't have any leading/trailing data in the patch,
- * we want it to match at the beginning/end of the file.
+ * A hunk to change lines at the beginning would begin with
+ * @@ -1,L +N,M @@
+ *
+ * And a hunk to add to an empty file would begin with
+ * @@ -0,0 +N,M @@
*
- * But that would break if the patch is generated with
- * --unified=0; sane people wouldn't do that to cause us
- * trouble, but we try to please not so sane ones as well.
+ * In other words, a hunk that is (frag->oldpos <= 1) with or
+ * without leading context must match at the beginning.
*/
- if (unidiff_zero) {
- match_beginning = (!leading && !frag->oldpos);
- match_end = 0;
- }
- else {
- match_beginning = !leading && (frag->oldpos == 1);
- match_end = !trailing;
- }
+ match_beginning = frag->oldpos <= 1;
+
+ /*
+ * A hunk without trailing lines must match at the end.
+ * However, we simply cannot tell if a hunk must match end
+ * from the lack of trailing lines if the patch was generated
+ * with unidiff without any context.
+ */
+ match_end = !unidiff_zero && !trailing;
+
+ pos = frag->newpos ? (frag->newpos - 1) : 0;
+ preimage.buf = oldlines;
+ preimage.len = old - oldlines;
+ postimage.buf = newlines;
+ postimage.len = new - newlines;
+ preimage.line = preimage.line_allocated;
+ postimage.line = postimage.line_allocated;
- lines = 0;
- pos = frag->newpos;
for (;;) {
- offset = find_offset(buf->buf, buf->len,
- oldlines, oldsize, pos, &lines);
- if (match_end && offset + oldsize != buf->len)
- offset = -1;
- if (match_beginning && offset)
- offset = -1;
- if (offset >= 0) {
- if (new_whitespace == strip_whitespace &&
- (buf->len - oldsize - offset == 0)) /* end of file? */
- newsize -= new_blank_lines_at_end;
-
- /* Warn if it was necessary to reduce the number
- * of context lines.
- */
- if ((leading != frag->leading) ||
- (trailing != frag->trailing))
- fprintf(stderr, "Context reduced to (%ld/%ld)"
- " to apply fragment at %d\n",
- leading, trailing, pos + lines);
-
- strbuf_splice(buf, offset, oldsize, newlines, newsize);
- offset = 0;
+
+ applied_pos = find_pos(img, &preimage, &postimage, pos,
+ ws_rule, match_beginning, match_end);
+
+ if (applied_pos >= 0)
break;
- }
/* Am I at my context limits? */
if ((leading <= p_context) && (trailing <= p_context))
match_beginning = match_end = 0;
continue;
}
- /* Reduce the number of context lines
- * Reduce both leading and trailing if they are equal
- * otherwise just reduce the larger context.
+
+ /*
+ * Reduce the number of context lines; reduce both
+ * leading and trailing if they are equal otherwise
+ * just reduce the larger context.
*/
if (leading >= trailing) {
- remove_first_line(&oldlines, &oldsize);
- remove_first_line(&newlines, &newsize);
+ remove_first_line(&preimage);
+ remove_first_line(&postimage);
pos--;
leading--;
}
if (trailing > leading) {
- remove_last_line(&oldlines, &oldsize);
- remove_last_line(&newlines, &newsize);
+ remove_last_line(&preimage);
+ remove_last_line(&postimage);
trailing--;
}
}
- if (offset && apply_verbosely)
- error("while searching for:\n%.*s", oldsize, oldlines);
+ if (applied_pos >= 0) {
+ if (ws_error_action == correct_ws_error &&
+ new_blank_lines_at_end &&
+ postimage.nr + applied_pos == img->nr) {
+ /*
+ * 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.
+ */
+ while (new_blank_lines_at_end--)
+ remove_last_line(&postimage);
+ }
- free(old);
- free(new);
- return offset;
+ /*
+ * Warn if it was necessary to reduce the number
+ * of context lines.
+ */
+ if ((leading != frag->leading) ||
+ (trailing != frag->trailing))
+ fprintf(stderr, "Context reduced to (%ld/%ld)"
+ " to apply fragment at %d\n",
+ leading, trailing, applied_pos+1);
+ update_image(img, applied_pos, &preimage, &postimage);
+ } else {
+ if (apply_verbosely)
+ error("while searching for:\n%.*s",
+ (int)(old - oldlines), oldlines);
+ }
+
+ free(oldlines);
+ free(newlines);
+ free(preimage.line_allocated);
+ free(postimage.line_allocated);
+
+ return (applied_pos < 0);
}
-static int apply_binary_fragment(struct strbuf *buf, struct patch *patch)
+static int apply_binary_fragment(struct image *img, struct patch *patch)
{
struct fragment *fragment = patch->fragments;
unsigned long len;
}
switch (fragment->binary_patch_method) {
case BINARY_DELTA_DEFLATED:
- dst = patch_delta(buf->buf, buf->len, fragment->patch,
+ dst = patch_delta(img->buf, img->len, fragment->patch,
fragment->size, &len);
if (!dst)
return -1;
- /* XXX patch_delta NUL-terminates */
- strbuf_attach(buf, dst, len, len + 1);
+ clear_image(img);
+ img->buf = dst;
+ img->len = len;
return 0;
case BINARY_LITERAL_DEFLATED:
- strbuf_reset(buf);
- strbuf_add(buf, fragment->patch, fragment->size);
+ clear_image(img);
+ img->len = fragment->size;
+ img->buf = xmalloc(img->len+1);
+ memcpy(img->buf, fragment->patch, img->len);
+ img->buf[img->len] = '\0';
return 0;
}
return -1;
}
-static int apply_binary(struct strbuf *buf, struct patch *patch)
+static int apply_binary(struct image *img, struct patch *patch)
{
const char *name = patch->old_name ? patch->old_name : patch->new_name;
unsigned char sha1[20];
- /* For safety, we require patch index line to contain
+ /*
+ * For safety, we require patch index line to contain
* full 40-byte textual SHA1 for old and new, at least for now.
*/
if (strlen(patch->old_sha1_prefix) != 40 ||
"without full index line", name);
if (patch->old_name) {
- /* See if the old one matches what the patch
+ /*
+ * See if the old one matches what the patch
* applies to.
*/
- hash_sha1_file(buf->buf, buf->len, blob_type, sha1);
+ hash_sha1_file(img->buf, img->len, blob_type, sha1);
if (strcmp(sha1_to_hex(sha1), patch->old_sha1_prefix))
return error("the patch applies to '%s' (%s), "
"which does not match the "
}
else {
/* Otherwise, the old one must be empty. */
- if (buf->len)
+ if (img->len)
return error("the patch applies to an empty "
"'%s' but it is not empty", name);
}
get_sha1_hex(patch->new_sha1_prefix, sha1);
if (is_null_sha1(sha1)) {
- strbuf_release(buf);
+ clear_image(img);
return 0; /* deletion patch */
}
return error("the necessary postimage %s for "
"'%s' cannot be read",
patch->new_sha1_prefix, name);
- /* XXX read_sha1_file NUL-terminates */
- strbuf_attach(buf, result, size, size + 1);
+ clear_image(img);
+ img->buf = result;
+ img->len = size;
} else {
- /* We have verified buf matches the preimage;
+ /*
+ * We have verified buf matches the preimage;
* apply the patch data to it, which is stored
* in the patch->fragments->{patch,size}.
*/
- if (apply_binary_fragment(buf, patch))
+ if (apply_binary_fragment(img, patch))
return error("binary patch does not apply to '%s'",
name);
/* verify that the result matches */
- hash_sha1_file(buf->buf, buf->len, blob_type, sha1);
+ hash_sha1_file(img->buf, img->len, blob_type, sha1);
if (strcmp(sha1_to_hex(sha1), patch->new_sha1_prefix))
return error("binary patch to '%s' creates incorrect result (expecting %s, got %s)",
name, patch->new_sha1_prefix, sha1_to_hex(sha1));
return 0;
}
-static int apply_fragments(struct strbuf *buf, struct patch *patch)
+static int apply_fragments(struct image *img, struct patch *patch)
{
struct fragment *frag = patch->fragments;
const char *name = patch->old_name ? patch->old_name : patch->new_name;
+ unsigned ws_rule = patch->ws_rule;
+ unsigned inaccurate_eof = patch->inaccurate_eof;
if (patch->is_binary)
- return apply_binary(buf, patch);
+ return apply_binary(img, patch);
while (frag) {
- if (apply_one_fragment(buf, frag, patch->inaccurate_eof)) {
+ if (apply_one_fragment(img, frag, inaccurate_eof, ws_rule)) {
error("patch failed: %s:%ld", name, frag->oldpos);
if (!apply_with_reject)
return -1;
if (!ce)
return 0;
- if (S_ISGITLINK(ntohl(ce->ce_mode))) {
+ if (S_ISGITLINK(ce->ce_mode)) {
strbuf_grow(buf, 100);
strbuf_addf(buf, "Subproject commit %s\n", sha1_to_hex(ce->sha1));
} else {
static int apply_data(struct patch *patch, struct stat *st, struct cache_entry *ce)
{
struct strbuf buf;
+ struct image image;
+ size_t len;
+ char *img;
strbuf_init(&buf, 0);
if (cached) {
}
}
- if (apply_fragments(&buf, patch) < 0)
+ img = strbuf_detach(&buf, &len);
+ prepare_image(&image, img, len, !patch->is_binary);
+
+ if (apply_fragments(&image, patch) < 0)
return -1; /* note with --reject this succeeds. */
- patch->result = strbuf_detach(&buf, &patch->resultsize);
+ patch->result = image.buf;
+ patch->resultsize = image.len;
+ free(image.line_allocated);
if (0 < patch->is_delete && patch->resultsize)
return error("removal patch leaves file contents");
static int verify_index_match(struct cache_entry *ce, struct stat *st)
{
- if (S_ISGITLINK(ntohl(ce->ce_mode))) {
+ if (S_ISGITLINK(ce->ce_mode)) {
if (!S_ISDIR(st->st_mode))
return -1;
return 0;
return error("%s: does not match index",
old_name);
if (cached)
- st_mode = ntohl(ce->ce_mode);
+ st_mode = ce->ce_mode;
} else if (stat_ret < 0)
return error("%s: %s", old_name, strerror(errno));
if (!cached)
- st_mode = ntohl(ce_mode_from_stat(ce, st.st_mode));
+ st_mode = ce_mode_from_stat(ce, st.st_mode);
if (patch->is_new < 0)
patch->is_new = 0;
if (new_name && prev_patch && 0 < prev_patch->is_delete &&
!strcmp(prev_patch->old_name, new_name))
- /* A type-change diff is always split into a patch to
+ /*
+ * A type-change diff is always split into a patch to
* delete old, immediately followed by a patch to
* create new (see diff.c::run_diff()); in such a case
* it is Ok that the entry to be deleted by the
ce = xcalloc(1, ce_size);
memcpy(ce->name, path, namelen);
ce->ce_mode = create_ce_mode(mode);
- ce->ce_flags = htons(namelen);
+ ce->ce_flags = namelen;
if (S_ISGITLINK(mode)) {
const char *s = buf;
offset += nr;
}
- if (whitespace_error && (new_whitespace == error_on_whitespace))
+ if (whitespace_error && (ws_error_action == die_on_ws_error))
apply = 0;
update_index = check_index && apply;
static int git_apply_config(const char *var, const char *value)
{
if (!strcmp(var, "apply.whitespace")) {
+ if (!value)
+ return config_error_nonbool(var);
apply_default_whitespace = xstrdup(value);
return 0;
}
int read_stdin = 1;
int inaccurate_eof = 0;
int errs = 0;
- int is_not_gitdir = 0;
+ int is_not_gitdir;
const char *whitespace_option = NULL;
fd = open(arg, O_RDONLY);
if (fd < 0)
- usage(apply_usage);
+ die("can't open patch '%s': %s", arg, strerror(errno));
read_stdin = 0;
set_default_whitespace_mode(whitespace_option);
errs |= apply_patch(fd, arg, inaccurate_eof);
squelched,
squelched == 1 ? "" : "s");
}
- if (new_whitespace == error_on_whitespace)
+ if (ws_error_action == die_on_ws_error)
die("%d line%s add%s whitespace errors.",
whitespace_error,
whitespace_error == 1 ? "" : "s",
whitespace_error == 1 ? "s" : "");
- if (applied_after_fixing_ws)
+ if (applied_after_fixing_ws && apply)
fprintf(stderr, "warning: %d line%s applied after"
" fixing whitespace errors.\n",
applied_after_fixing_ws,
if (update_index) {
if (write_cache(newfd, active_cache, active_nr) ||
- close(newfd) || commit_locked_index(&lock_file))
+ commit_locked_index(&lock_file))
die("Unable to write new index file");
}