mirror of
https://github.com/git/git.git
synced 2024-11-17 22:44:49 +01:00
Merge branch 'jc/grep' into next
* jc/grep: builtin-grep: do not use setup_revisions() builtin-grep: support '-l' option. builtin-grep: wildcard pathspec fixes
This commit is contained in:
commit
f476ce2061
1 changed files with 206 additions and 144 deletions
350
builtin-grep.c
350
builtin-grep.c
|
@ -8,37 +8,69 @@
|
|||
#include "tree.h"
|
||||
#include "commit.h"
|
||||
#include "tag.h"
|
||||
#include "diff.h"
|
||||
#include "revision.h"
|
||||
#include "tree-walk.h"
|
||||
#include "builtin.h"
|
||||
#include <regex.h>
|
||||
#include <fnmatch.h>
|
||||
|
||||
static int pathspec_matches(struct diff_options *opt, const char *name)
|
||||
/*
|
||||
* git grep pathspecs are somewhat different from diff-tree pathspecs;
|
||||
* pathname wildcards are allowed.
|
||||
*/
|
||||
static int pathspec_matches(const char **paths, const char *name)
|
||||
{
|
||||
int i, j;
|
||||
int namelen;
|
||||
if (!opt->nr_paths)
|
||||
int namelen, i;
|
||||
if (!paths || !*paths)
|
||||
return 1;
|
||||
namelen = strlen(name);
|
||||
for (i = 0; i < opt->nr_paths; i++) {
|
||||
const char *match = opt->paths[i];
|
||||
int matchlen = opt->pathlens[i];
|
||||
if (matchlen <= namelen) {
|
||||
if (!strncmp(name, match, matchlen))
|
||||
return 1;
|
||||
continue;
|
||||
}
|
||||
/* If name is "Documentation" and pathspec is
|
||||
* "Documentation/", they should match. Maybe
|
||||
* we would want to strip it in get_pathspec()???
|
||||
*/
|
||||
if (strncmp(name, match, namelen))
|
||||
continue;
|
||||
for (j = namelen; j < matchlen; j++)
|
||||
if (match[j] != '/')
|
||||
break;
|
||||
if (matchlen <= j)
|
||||
for (i = 0; paths[i]; i++) {
|
||||
const char *match = paths[i];
|
||||
int matchlen = strlen(match);
|
||||
const char *slash, *cp;
|
||||
|
||||
if ((matchlen <= namelen) &&
|
||||
!strncmp(name, match, matchlen) &&
|
||||
(match[matchlen-1] == '/' ||
|
||||
name[matchlen] == '\0' || name[matchlen] == '/'))
|
||||
return 1;
|
||||
if (!fnmatch(match, name, 0))
|
||||
return 1;
|
||||
if (name[namelen-1] != '/')
|
||||
continue;
|
||||
|
||||
/* We are being asked if the name directory is worth
|
||||
* descending into.
|
||||
*
|
||||
* Find the longest leading directory name that does
|
||||
* not have metacharacter in the pathspec; the name
|
||||
* we are looking at must overlap with that directory.
|
||||
*/
|
||||
for (cp = match, slash = NULL; cp - match < matchlen; cp++) {
|
||||
char ch = *cp;
|
||||
if (ch == '/')
|
||||
slash = cp;
|
||||
if (ch == '*' || ch == '[')
|
||||
break;
|
||||
}
|
||||
if (!slash)
|
||||
slash = match; /* toplevel */
|
||||
else
|
||||
slash++;
|
||||
if (namelen <= slash - match) {
|
||||
/* Looking at "Documentation/" and
|
||||
* the pattern says "Documentation/howto/", or
|
||||
* "Documentation/diff*.txt".
|
||||
*/
|
||||
if (!memcmp(match, name, namelen))
|
||||
return 1;
|
||||
}
|
||||
else {
|
||||
/* Looking at "Documentation/howto/" and
|
||||
* the pattern says "Documentation/h*".
|
||||
*/
|
||||
if (!memcmp(match, name, slash - match))
|
||||
return 1;
|
||||
}
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
|
@ -48,6 +80,7 @@ struct grep_opt {
|
|||
regex_t regexp;
|
||||
unsigned linenum:1;
|
||||
unsigned invert:1;
|
||||
unsigned name_only:1;
|
||||
int regflags;
|
||||
unsigned pre_context;
|
||||
unsigned post_context;
|
||||
|
@ -106,6 +139,10 @@ static int grep_buffer(struct grep_opt *opt, const char *name,
|
|||
if (opt->invert)
|
||||
hit = !hit;
|
||||
if (hit) {
|
||||
if (opt->name_only) {
|
||||
printf("%s\n", name);
|
||||
return 1;
|
||||
}
|
||||
/* Hit at this line. If we haven't shown the
|
||||
* pre-context lines, we would need to show them.
|
||||
*/
|
||||
|
@ -203,7 +240,7 @@ static int grep_file(struct grep_opt *opt, const char *filename)
|
|||
return i;
|
||||
}
|
||||
|
||||
static int grep_cache(struct grep_opt *opt, struct rev_info *revs, int cached)
|
||||
static int grep_cache(struct grep_opt *opt, const char **paths, int cached)
|
||||
{
|
||||
int hit = 0;
|
||||
int nr;
|
||||
|
@ -213,7 +250,7 @@ static int grep_cache(struct grep_opt *opt, struct rev_info *revs, int cached)
|
|||
struct cache_entry *ce = active_cache[nr];
|
||||
if (ce_stage(ce) || !S_ISREG(ntohl(ce->ce_mode)))
|
||||
continue;
|
||||
if (!pathspec_matches(&revs->diffopt, ce->name))
|
||||
if (!pathspec_matches(paths, ce->name))
|
||||
continue;
|
||||
if (cached)
|
||||
hit |= grep_sha1(opt, ce->sha1, ce->name);
|
||||
|
@ -223,7 +260,7 @@ static int grep_cache(struct grep_opt *opt, struct rev_info *revs, int cached)
|
|||
return hit;
|
||||
}
|
||||
|
||||
static int grep_tree(struct grep_opt *opt, struct rev_info *revs,
|
||||
static int grep_tree(struct grep_opt *opt, const char **paths,
|
||||
struct tree_desc *tree,
|
||||
const char *tree_name, const char *base)
|
||||
{
|
||||
|
@ -232,17 +269,17 @@ static int grep_tree(struct grep_opt *opt, struct rev_info *revs,
|
|||
int hit = 0;
|
||||
const char *path;
|
||||
const unsigned char *sha1;
|
||||
char *down_base;
|
||||
char *down;
|
||||
char *path_buf = xmalloc(PATH_MAX + strlen(tree_name) + 100);
|
||||
|
||||
if (tree_name[0]) {
|
||||
int offset = sprintf(path_buf, "%s:", tree_name);
|
||||
down_base = path_buf + offset;
|
||||
strcat(down_base, base);
|
||||
down = path_buf + offset;
|
||||
strcat(down, base);
|
||||
}
|
||||
else {
|
||||
down_base = path_buf;
|
||||
strcpy(down_base, base);
|
||||
down = path_buf;
|
||||
strcpy(down, base);
|
||||
}
|
||||
len = strlen(path_buf);
|
||||
|
||||
|
@ -252,7 +289,14 @@ static int grep_tree(struct grep_opt *opt, struct rev_info *revs,
|
|||
pathlen = strlen(path);
|
||||
strcpy(path_buf + len, path);
|
||||
|
||||
if (!pathspec_matches(&revs->diffopt, down_base))
|
||||
if (S_ISDIR(mode))
|
||||
/* Match "abc/" against pathspec to
|
||||
* decide if we want to descend into "abc"
|
||||
* directory.
|
||||
*/
|
||||
strcpy(path_buf + len + pathlen, "/");
|
||||
|
||||
if (!pathspec_matches(paths, down))
|
||||
;
|
||||
else if (S_ISREG(mode))
|
||||
hit |= grep_sha1(opt, sha1, path_buf);
|
||||
|
@ -264,9 +308,8 @@ static int grep_tree(struct grep_opt *opt, struct rev_info *revs,
|
|||
if (!data)
|
||||
die("unable to read tree (%s)",
|
||||
sha1_to_hex(sha1));
|
||||
strcpy(path_buf + len + pathlen, "/");
|
||||
sub.buf = data;
|
||||
hit = grep_tree(opt, revs, &sub, tree_name, down_base);
|
||||
hit |= grep_tree(opt, paths, &sub, tree_name, down);
|
||||
free(data);
|
||||
}
|
||||
update_tree_entry(tree);
|
||||
|
@ -274,7 +317,7 @@ static int grep_tree(struct grep_opt *opt, struct rev_info *revs,
|
|||
return hit;
|
||||
}
|
||||
|
||||
static int grep_object(struct grep_opt *opt, struct rev_info *revs,
|
||||
static int grep_object(struct grep_opt *opt, const char **paths,
|
||||
struct object *obj, const char *name)
|
||||
{
|
||||
if (!strcmp(obj->type, blob_type))
|
||||
|
@ -289,7 +332,7 @@ static int grep_object(struct grep_opt *opt, struct rev_info *revs,
|
|||
if (!data)
|
||||
die("unable to read tree (%s)", sha1_to_hex(obj->sha1));
|
||||
tree.buf = data;
|
||||
hit = grep_tree(opt, revs, &tree, name, "");
|
||||
hit = grep_tree(opt, paths, &tree, name, "");
|
||||
free(data);
|
||||
return hit;
|
||||
}
|
||||
|
@ -301,97 +344,119 @@ static const char builtin_grep_usage[] =
|
|||
|
||||
int cmd_grep(int argc, const char **argv, char **envp)
|
||||
{
|
||||
struct rev_info rev;
|
||||
const char **dst, **src;
|
||||
int err;
|
||||
int hit = 0;
|
||||
int no_more_arg = 0;
|
||||
int seen_range = 0;
|
||||
int no_more_flags = 0;
|
||||
int seen_noncommit = 0;
|
||||
int cached = 0;
|
||||
struct grep_opt opt;
|
||||
struct object_list *list;
|
||||
struct object_list *list, **tail, *object_list = NULL;
|
||||
const char *prefix = setup_git_directory();
|
||||
const char **paths = NULL;
|
||||
|
||||
memset(&opt, 0, sizeof(opt));
|
||||
opt.regflags = REG_NEWLINE;
|
||||
|
||||
/*
|
||||
* Interpret and remove the grep options upfront. Sigh...
|
||||
* No point using rev_info, really.
|
||||
*/
|
||||
for (dst = src = &argv[1]; src < argc + argv; ) {
|
||||
const char *arg = *src++;
|
||||
if (!no_more_arg) {
|
||||
if (!strcmp("--", arg)) {
|
||||
no_more_arg = 1;
|
||||
*dst++ = arg;
|
||||
continue;
|
||||
}
|
||||
if (!strcmp("--cached", arg)) {
|
||||
cached = 1;
|
||||
continue;
|
||||
}
|
||||
if (!strcmp("-i", arg) ||
|
||||
!strcmp("--ignore-case", arg)) {
|
||||
opt.regflags |= REG_ICASE;
|
||||
continue;
|
||||
}
|
||||
if (!strcmp("-v", arg) ||
|
||||
!strcmp("--invert-match", arg)) {
|
||||
opt.invert = 1;
|
||||
continue;
|
||||
}
|
||||
if (!strcmp("-E", arg) ||
|
||||
!strcmp("--extended-regexp", arg)) {
|
||||
opt.regflags |= REG_EXTENDED;
|
||||
continue;
|
||||
}
|
||||
if (!strcmp("-G", arg) ||
|
||||
!strcmp("--basic-regexp", arg)) {
|
||||
opt.regflags &= ~REG_EXTENDED;
|
||||
continue;
|
||||
}
|
||||
if (!strcmp("-e", arg)) {
|
||||
if (src < argc + argv) {
|
||||
opt.pattern = *src++;
|
||||
continue;
|
||||
}
|
||||
usage(builtin_grep_usage);
|
||||
}
|
||||
if (!strcmp("-n", arg)) {
|
||||
opt.linenum = 1;
|
||||
continue;
|
||||
}
|
||||
if (!strcmp("-H", arg)) {
|
||||
/* We always show the pathname, so this
|
||||
* is a noop.
|
||||
*/
|
||||
continue;
|
||||
}
|
||||
if (!strcmp("-A", arg) ||
|
||||
!strcmp("-B", arg) ||
|
||||
!strcmp("-C", arg)) {
|
||||
unsigned num;
|
||||
if ((argc + argv <= src) ||
|
||||
sscanf(*src++, "%u", &num) != 1)
|
||||
usage(builtin_grep_usage);
|
||||
switch (arg[1]) {
|
||||
case 'A':
|
||||
opt.post_context = num;
|
||||
break;
|
||||
case 'C':
|
||||
opt.post_context = num;
|
||||
case 'B':
|
||||
opt.pre_context = num;
|
||||
break;
|
||||
}
|
||||
continue;
|
||||
}
|
||||
while (1 < argc) {
|
||||
const char *arg = argv[1];
|
||||
argc--; argv++;
|
||||
if (!strcmp("--cached", arg)) {
|
||||
cached = 1;
|
||||
continue;
|
||||
}
|
||||
if (!strcmp("-i", arg) ||
|
||||
!strcmp("--ignore-case", arg)) {
|
||||
opt.regflags |= REG_ICASE;
|
||||
continue;
|
||||
}
|
||||
if (!strcmp("-v", arg) ||
|
||||
!strcmp("--invert-match", arg)) {
|
||||
opt.invert = 1;
|
||||
continue;
|
||||
}
|
||||
if (!strcmp("-E", arg) ||
|
||||
!strcmp("--extended-regexp", arg)) {
|
||||
opt.regflags |= REG_EXTENDED;
|
||||
continue;
|
||||
}
|
||||
if (!strcmp("-G", arg) ||
|
||||
!strcmp("--basic-regexp", arg)) {
|
||||
opt.regflags &= ~REG_EXTENDED;
|
||||
continue;
|
||||
}
|
||||
if (!strcmp("-n", arg)) {
|
||||
opt.linenum = 1;
|
||||
continue;
|
||||
}
|
||||
if (!strcmp("-H", arg)) {
|
||||
/* We always show the pathname, so this
|
||||
* is a noop.
|
||||
*/
|
||||
continue;
|
||||
}
|
||||
if (!strcmp("-l", arg) ||
|
||||
!strcmp("--files-with-matches", arg)) {
|
||||
opt.name_only = 1;
|
||||
continue;
|
||||
}
|
||||
if (!strcmp("-A", arg) ||
|
||||
!strcmp("-B", arg) ||
|
||||
!strcmp("-C", arg)) {
|
||||
unsigned num;
|
||||
if (argc <= 1 ||
|
||||
sscanf(*++argv, "%u", &num) != 1)
|
||||
usage(builtin_grep_usage);
|
||||
argc--;
|
||||
switch (arg[1]) {
|
||||
case 'A':
|
||||
opt.post_context = num;
|
||||
break;
|
||||
case 'C':
|
||||
opt.post_context = num;
|
||||
case 'B':
|
||||
opt.pre_context = num;
|
||||
break;
|
||||
}
|
||||
continue;
|
||||
}
|
||||
if (!strcmp("-e", arg)) {
|
||||
if (1 < argc) {
|
||||
/* We probably would want to do
|
||||
* -e pat1 -e pat2 as well later...
|
||||
*/
|
||||
if (opt.pattern)
|
||||
die("more than one pattern?");
|
||||
opt.pattern = *++argv;
|
||||
argc--;
|
||||
continue;
|
||||
}
|
||||
usage(builtin_grep_usage);
|
||||
}
|
||||
if (!strcmp("--", arg)) {
|
||||
no_more_flags = 1;
|
||||
continue;
|
||||
}
|
||||
/* Either unrecognized option or a single pattern */
|
||||
if (!no_more_flags && *arg == '-')
|
||||
usage(builtin_grep_usage);
|
||||
if (!opt.pattern) {
|
||||
opt.pattern = arg;
|
||||
break;
|
||||
}
|
||||
else {
|
||||
/* We are looking at the first path or rev;
|
||||
* it is found at argv[0] after leaving the
|
||||
* loop.
|
||||
*/
|
||||
argc++; argv--;
|
||||
break;
|
||||
}
|
||||
*dst++ = arg;
|
||||
}
|
||||
if (!opt.pattern)
|
||||
die("no pattern given.");
|
||||
|
||||
err = regcomp(&opt.regexp, opt.pattern, opt.regflags);
|
||||
if (err) {
|
||||
char errbuf[1024];
|
||||
|
@ -399,11 +464,32 @@ int cmd_grep(int argc, const char **argv, char **envp)
|
|||
regfree(&opt.regexp);
|
||||
die("'%s': %s", opt.pattern, errbuf);
|
||||
}
|
||||
tail = &object_list;
|
||||
while (1 < argc) {
|
||||
struct object *object;
|
||||
struct object_list *elem;
|
||||
const char *arg = argv[1];
|
||||
unsigned char sha1[20];
|
||||
if (get_sha1(arg, sha1) < 0)
|
||||
break;
|
||||
object = parse_object(sha1);
|
||||
if (!object)
|
||||
die("bad object %s", arg);
|
||||
elem = object_list_insert(object, tail);
|
||||
elem->name = arg;
|
||||
tail = &elem->next;
|
||||
argc--; argv++;
|
||||
}
|
||||
if (1 < argc)
|
||||
paths = get_pathspec(prefix, argv + 1);
|
||||
else if (prefix) {
|
||||
paths = xcalloc(2, sizeof(const char *));
|
||||
paths[0] = prefix;
|
||||
paths[1] = NULL;
|
||||
}
|
||||
|
||||
init_revisions(&rev);
|
||||
*dst = NULL;
|
||||
argc = setup_revisions(dst - argv, argv, &rev, NULL);
|
||||
|
||||
if (!object_list)
|
||||
return !grep_cache(&opt, paths, cached);
|
||||
/*
|
||||
* Do not walk "grep -e foo master next pu -- Documentation/"
|
||||
* but do walk "grep -e foo master..next -- Documentation/".
|
||||
|
@ -411,43 +497,19 @@ int cmd_grep(int argc, const char **argv, char **envp)
|
|||
* "grep -e foo v1.0.0:Documentation/ master..next"
|
||||
* so detect that and complain.
|
||||
*/
|
||||
for (list = rev.pending_objects; list; list = list->next) {
|
||||
for (list = object_list; list; list = list->next) {
|
||||
struct object *real_obj;
|
||||
if (list->item->flags & UNINTERESTING)
|
||||
seen_range = 1;
|
||||
real_obj = deref_tag(list->item, NULL, 0);
|
||||
if (strcmp(real_obj->type, commit_type))
|
||||
seen_noncommit = 1;
|
||||
}
|
||||
if (!rev.pending_objects)
|
||||
return !grep_cache(&opt, &rev, cached);
|
||||
if (cached)
|
||||
die("both --cached and revisions given.");
|
||||
|
||||
if (seen_range && seen_noncommit)
|
||||
die("both A..B and non commit are given.");
|
||||
if (seen_range) {
|
||||
struct commit *commit;
|
||||
prepare_revision_walk(&rev);
|
||||
while ((commit = get_revision(&rev)) != NULL) {
|
||||
unsigned char *sha1 = commit->object.sha1;
|
||||
const char *n = find_unique_abbrev(sha1, rev.abbrev);
|
||||
char rev_name[41];
|
||||
strcpy(rev_name, n);
|
||||
if (grep_object(&opt, &rev, &commit->object, rev_name))
|
||||
hit = 1;
|
||||
commit->buffer = NULL;
|
||||
}
|
||||
return !hit;
|
||||
}
|
||||
|
||||
/* all of them are non-commit; do not walk, and
|
||||
* do not lose their names.
|
||||
*/
|
||||
for (list = rev.pending_objects; list; list = list->next) {
|
||||
for (list = object_list; list; list = list->next) {
|
||||
struct object *real_obj;
|
||||
real_obj = deref_tag(list->item, NULL, 0);
|
||||
if (grep_object(&opt, &rev, real_obj, list->name))
|
||||
if (grep_object(&opt, paths, real_obj, list->name))
|
||||
hit = 1;
|
||||
}
|
||||
return !hit;
|
||||
|
|
Loading…
Reference in a new issue