SYNOPSIS
--------
[verse]
-'git grep' [-a | --text] [-I] [-i | --ignore-case] [-w | --word-regexp]
+'git grep' [-a | --text] [-I] [--textconv] [-i | --ignore-case] [-w | --word-regexp]
[-v | --invert-match] [-h|-H] [--full-name]
[-E | --extended-regexp] [-G | --basic-regexp]
[-P | --perl-regexp]
--text::
Process binary files as if they were text.
+--textconv::
+ Honor textconv filter settings.
+
+--no-textconv::
+ Do not honor textconv filter settings.
+ This is the default.
+
-i::
--ignore-case::
Ignore case differences between the patterns and the
* Call `diff_setup_done()`; this inspects the options set up so far for
internal consistency and make necessary tweaking to it (e.g. if
- textual patch output was asked, recursive behaviour is turned on).
+ textual patch output was asked, recursive behaviour is turned on);
+ the callback set_default in diff_options can be used to tweak this more.
* As you find different pairs of files, call `diff_change()` to feed
modified files, `diff_addremove()` to feed created or deleted files,
operation, but some do not have anything to do with the diffcore
library.
+`touched_flags`::
+ Records whether a flag has been changed due to user request
+ (rather than just set/unset by default).
+
+`set_default`::
+ Callback which allows tweaking the options in diff_setup_done().
+
BINARY, TEXT;;
Affects the way how a file that is seemingly binary is treated.
case 'e':
return !has_sha1_file(sha1);
+ case 'c':
+ if (!obj_context.path[0])
+ die("git cat-file --textconv %s: <object> must be <sha1:path>",
+ obj_name);
+
+ if (textconv_object(obj_context.path, obj_context.mode, sha1, 1, &buf, &size))
+ break;
+
case 'p':
type = sha1_object_info(sha1, NULL);
if (type < 0)
/* otherwise just spit out the data */
break;
- case 'c':
- if (!obj_context.path[0])
- die("git cat-file --textconv %s: <object> must be <sha1:path>",
- obj_name);
-
- if (!textconv_object(obj_context.path, obj_context.mode, sha1, 1, &buf, &size))
- die("git cat-file --textconv: unable to run textconv on %s",
- obj_name);
- break;
-
case 0:
if (type_from_string(exp_type) == OBJ_BLOB) {
unsigned char blob_sha1[20];
}
static int grep_object(struct grep_opt *opt, const struct pathspec *pathspec,
- struct object *obj, const char *name)
+ struct object *obj, const char *name, struct object_context *oc)
{
if (obj->type == OBJ_BLOB)
- return grep_sha1(opt, obj->sha1, name, 0, NULL);
+ return grep_sha1(opt, obj->sha1, name, 0, oc ? oc->path : NULL);
if (obj->type == OBJ_COMMIT || obj->type == OBJ_TREE) {
struct tree_desc tree;
void *data;
for (i = 0; i < nr; i++) {
struct object *real_obj;
real_obj = deref_tag(list->objects[i].item, NULL, 0);
- if (grep_object(opt, pathspec, real_obj, list->objects[i].name)) {
+ if (grep_object(opt, pathspec, real_obj, list->objects[i].name, list->objects[i].context)) {
hit = 1;
if (opt->status_only)
break;
OPT_SET_INT('I', NULL, &opt.binary,
N_("don't match patterns in binary files"),
GREP_BINARY_NOMATCH),
+ OPT_BOOL(0, "textconv", &opt.allow_textconv,
+ N_("process binary files with textconv filters")),
{ OPTION_INTEGER, 0, "max-depth", &opt.max_depth, N_("depth"),
N_("descend at most <depth> levels"), PARSE_OPT_NONEG,
NULL, 1 },
for (i = 0; i < argc; i++) {
const char *arg = argv[i];
unsigned char sha1[20];
+ struct object_context oc;
/* Is it a rev? */
- if (!get_sha1(arg, sha1)) {
+ if (!get_sha1_with_context(arg, 0, sha1, &oc)) {
struct object *object = parse_object_or_die(sha1, arg);
if (!seen_dashdash)
verify_non_filename(prefix, arg);
- add_object_array(object, arg, &list);
+ add_object_array_with_context(object, arg, &list, xmemdupz(&oc, sizeof(struct object_context)));
continue;
}
if (!strcmp(arg, "--")) {
if (default_date_mode)
rev->date_mode = parse_date_format(default_date_mode);
+ rev->diffopt.touched_flags = 0;
}
static void cmd_log_init_finish(int argc, const char **argv, const char *prefix,
strbuf_release(&out);
}
-static int show_blob_object(const unsigned char *sha1, struct rev_info *rev)
+static int show_blob_object(const unsigned char *sha1, struct rev_info *rev, const char *obj_name)
{
+ unsigned char sha1c[20];
+ struct object_context obj_context;
+ char *buf;
+ unsigned long size;
+
fflush(stdout);
- return stream_blob_to_fd(1, sha1, NULL, 0);
+ if (!DIFF_OPT_TOUCHED(&rev->diffopt, ALLOW_TEXTCONV) ||
+ !DIFF_OPT_TST(&rev->diffopt, ALLOW_TEXTCONV))
+ return stream_blob_to_fd(1, sha1, NULL, 0);
+
+ if (get_sha1_with_context(obj_name, 0, sha1c, &obj_context))
+ die("Not a valid object name %s", obj_name);
+ if (!obj_context.path[0] ||
+ !textconv_object(obj_context.path, obj_context.mode, sha1c, 1, &buf, &size))
+ return stream_blob_to_fd(1, sha1, NULL, 0);
+
+ if (!buf)
+ die("git show %s: bad file", obj_name);
+
+ write_or_die(1, buf, size);
+ return 0;
}
static int show_tag_object(const unsigned char *sha1, struct rev_info *rev)
const char *name = objects[i].name;
switch (o->type) {
case OBJ_BLOB:
- ret = show_blob_object(o->sha1, NULL);
+ ret = show_blob_object(o->sha1, &rev, name);
break;
case OBJ_TAG: {
struct tag *t = (struct tag *)o;
{
int count = 0;
+ if (options->set_default)
+ options->set_default(options);
+
if (options->output_format & DIFF_FORMAT_NAME)
count++;
if (options->output_format & DIFF_FORMAT_NAME_STATUS)
#define DIFF_OPT_PICKAXE_IGNORE_CASE (1 << 30)
#define DIFF_OPT_TST(opts, flag) ((opts)->flags & DIFF_OPT_##flag)
-#define DIFF_OPT_SET(opts, flag) ((opts)->flags |= DIFF_OPT_##flag)
-#define DIFF_OPT_CLR(opts, flag) ((opts)->flags &= ~DIFF_OPT_##flag)
+#define DIFF_OPT_TOUCHED(opts, flag) ((opts)->touched_flags & DIFF_OPT_##flag)
+#define DIFF_OPT_SET(opts, flag) (((opts)->flags |= DIFF_OPT_##flag),((opts)->touched_flags |= DIFF_OPT_##flag))
+#define DIFF_OPT_CLR(opts, flag) (((opts)->flags &= ~DIFF_OPT_##flag),((opts)->touched_flags |= DIFF_OPT_##flag))
#define DIFF_XDL_TST(opts, flag) ((opts)->xdl_opts & XDF_##flag)
#define DIFF_XDL_SET(opts, flag) ((opts)->xdl_opts |= XDF_##flag)
#define DIFF_XDL_CLR(opts, flag) ((opts)->xdl_opts &= ~XDF_##flag)
const char *single_follow;
const char *a_prefix, *b_prefix;
unsigned flags;
+ unsigned touched_flags;
/* diff-filter bits */
unsigned int filter;
/* to support internal diff recursion by --follow hack*/
int found_follow;
+ void (*set_default)(struct diff_options *);
+
FILE *file;
int close_file;
#include "grep.h"
#include "userdiff.h"
#include "xdiff-interface.h"
+#include "diff.h"
+#include "diffcore.h"
static int grep_source_load(struct grep_source *gs);
static int grep_source_is_binary(struct grep_source *gs);
fwrite(buf, size, 1, stdout);
}
+static int fill_textconv_grep(struct userdiff_driver *driver,
+ struct grep_source *gs)
+{
+ struct diff_filespec *df;
+ char *buf;
+ size_t size;
+
+ if (!driver || !driver->textconv)
+ return grep_source_load(gs);
+
+ /*
+ * The textconv interface is intimately tied to diff_filespecs, so we
+ * have to pretend to be one. If we could unify the grep_source
+ * and diff_filespec structs, this mess could just go away.
+ */
+ df = alloc_filespec(gs->path);
+ switch (gs->type) {
+ case GREP_SOURCE_SHA1:
+ fill_filespec(df, gs->identifier, 1, 0100644);
+ break;
+ case GREP_SOURCE_FILE:
+ fill_filespec(df, null_sha1, 0, 0100644);
+ break;
+ default:
+ die("BUG: attempt to textconv something without a path?");
+ }
+
+ /*
+ * fill_textconv is not remotely thread-safe; it may load objects
+ * behind the scenes, and it modifies the global diff tempfile
+ * structure.
+ */
+ grep_read_lock();
+ size = fill_textconv(driver, df, &buf);
+ grep_read_unlock();
+ free_filespec(df);
+
+ /*
+ * The normal fill_textconv usage by the diff machinery would just keep
+ * the textconv'd buf separate from the diff_filespec. But much of the
+ * grep code passes around a grep_source and assumes that its "buf"
+ * pointer is the beginning of the thing we are searching. So let's
+ * install our textconv'd version into the grep_source, taking care not
+ * to leak any existing buffer.
+ */
+ grep_source_clear_data(gs);
+ gs->buf = buf;
+ gs->size = size;
+
+ return 0;
+}
+
static int grep_source_1(struct grep_opt *opt, struct grep_source *gs, int collect_hits)
{
char *bol;
unsigned count = 0;
int try_lookahead = 0;
int show_function = 0;
+ struct userdiff_driver *textconv = NULL;
enum grep_context ctx = GREP_CONTEXT_HEAD;
xdemitconf_t xecfg;
}
opt->last_shown = 0;
- switch (opt->binary) {
- case GREP_BINARY_DEFAULT:
- if (grep_source_is_binary(gs))
- binary_match_only = 1;
- break;
- case GREP_BINARY_NOMATCH:
- if (grep_source_is_binary(gs))
- return 0; /* Assume unmatch */
- break;
- case GREP_BINARY_TEXT:
- break;
- default:
- die("bug: unknown binary handling mode");
+ if (opt->allow_textconv) {
+ grep_source_load_driver(gs);
+ /*
+ * We might set up the shared textconv cache data here, which
+ * is not thread-safe.
+ */
+ grep_attr_lock();
+ textconv = userdiff_get_textconv(gs->driver);
+ grep_attr_unlock();
+ }
+
+ /*
+ * We know the result of a textconv is text, so we only have to care
+ * about binary handling if we are not using it.
+ */
+ if (!textconv) {
+ switch (opt->binary) {
+ case GREP_BINARY_DEFAULT:
+ if (grep_source_is_binary(gs))
+ binary_match_only = 1;
+ break;
+ case GREP_BINARY_NOMATCH:
+ if (grep_source_is_binary(gs))
+ return 0; /* Assume unmatch */
+ break;
+ case GREP_BINARY_TEXT:
+ break;
+ default:
+ die("bug: unknown binary handling mode");
+ }
}
memset(&xecfg, 0, sizeof(xecfg));
try_lookahead = should_lookahead(opt);
- if (grep_source_load(gs) < 0)
+ if (fill_textconv_grep(textconv, gs) < 0)
return 0;
bol = gs->buf;
#define GREP_BINARY_NOMATCH 1
#define GREP_BINARY_TEXT 2
int binary;
+ int allow_textconv;
int extended;
int use_reflog_filter;
int pcre;
return 0;
}
-void add_object_array(struct object *obj, const char *name, struct object_array *array)
-{
- add_object_array_with_mode(obj, name, array, S_IFINVALID);
-}
-
/*
* A zero-length string to which object_array_entry::name can be
* initialized without requiring a malloc/free.
*/
static char object_array_slopbuf[1];
-void add_object_array_with_mode(struct object *obj, const char *name, struct object_array *array, unsigned mode)
+static void add_object_array_with_mode_context(struct object *obj, const char *name,
+ struct object_array *array,
+ unsigned mode,
+ struct object_context *context)
{
unsigned nr = array->nr;
unsigned alloc = array->alloc;
else
entry->name = xstrdup(name);
entry->mode = mode;
+ entry->context = context;
array->nr = ++nr;
}
+void add_object_array(struct object *obj, const char *name, struct object_array *array)
+{
+ add_object_array_with_mode(obj, name, array, S_IFINVALID);
+}
+
+void add_object_array_with_mode(struct object *obj, const char *name, struct object_array *array, unsigned mode)
+{
+ add_object_array_with_mode_context(obj, name, array, mode, NULL);
+}
+
+void add_object_array_with_context(struct object *obj, const char *name, struct object_array *array, struct object_context *context)
+{
+ if (context)
+ add_object_array_with_mode_context(obj, name, array, context->mode, context);
+ else
+ add_object_array_with_mode_context(obj, name, array, S_IFINVALID, context);
+}
+
void object_array_filter(struct object_array *array,
object_array_each_func_t want, void *cb_data)
{
*/
char *name;
unsigned mode;
+ struct object_context *context;
} *objects;
};
/* Object array handling .. */
void add_object_array(struct object *obj, const char *name, struct object_array *array);
void add_object_array_with_mode(struct object *obj, const char *name, struct object_array *array, unsigned mode);
+void add_object_array_with_context(struct object *obj, const char *name, struct object_array *array, struct object_context *context);
typedef int (*object_array_each_func_t)(struct object_array_entry *, void *);
test_cmp expect.text actual
'
+test_expect_success 'show commit produces text' '
+ git show HEAD >diff &&
+ find_diff <diff >actual &&
+ test_cmp expect.text actual
+'
+
test_expect_success 'diff-tree produces binary' '
git diff-tree -p HEAD^ HEAD >diff &&
find_diff <diff >actual &&
git reset --soft HEAD@{1}
'
+test_expect_success 'show blob produces binary' '
+ git show HEAD:file >actual &&
+ printf "\\0\\n\\01\\n" >expect &&
+ test_cmp expect actual
+'
+
+test_expect_success 'show --textconv blob produces text' '
+ git show --textconv HEAD:file >actual &&
+ printf "0\\n1\\n" >expect &&
+ test_cmp expect actual
+'
+
+test_expect_success 'show --no-textconv blob produces binary' '
+ git show --no-textconv HEAD:file >actual &&
+ printf "\\0\\n\\01\\n" >expect &&
+ test_cmp expect actual
+'
+
test_expect_success 'grep-diff (-G) operates on textconv data (add)' '
echo one >expect &&
git log --root --format=%s -G0 >actual &&
test_cmp expect actual
'
+cat >nul_to_q_textconv <<'EOF'
+#!/bin/sh
+"$PERL_PATH" -pe 'y/\000/Q/' < "$1"
+EOF
+chmod +x nul_to_q_textconv
+
+test_expect_success 'setup textconv filters' '
+ echo a diff=foo >.gitattributes &&
+ git config diff.foo.textconv "\"$(pwd)\""/nul_to_q_textconv
+'
+
+test_expect_success 'grep does not honor textconv' '
+ test_must_fail git grep Qfile
+'
+
+test_expect_success 'grep --textconv honors textconv' '
+ echo "a:binaryQfile" >expect &&
+ git grep --textconv Qfile >actual &&
+ test_cmp expect actual
+'
+
+test_expect_success 'grep --no-textconv does not honor textconv' '
+ test_must_fail git grep --no-textconv Qfile
+'
+
+test_expect_success 'grep --textconv blob honors textconv' '
+ echo "HEAD:a:binaryQfile" >expect &&
+ git grep --textconv Qfile HEAD:a >actual &&
+ test_cmp expect actual
+'
+
test_done
'
cat >expected <<EOF
-fatal: git cat-file --textconv: unable to run textconv on :one.bin
+bin: test version 2
EOF
test_expect_success 'no filter specified' '
- git cat-file --textconv :one.bin 2>result
+ git cat-file --textconv :one.bin >result &&
test_cmp expected result
'
git config diff.test.cachetextconv false
'
-cat >expected <<EOF
-bin: test version 2
-EOF
-
test_expect_success 'cat-file without --textconv' '
git cat-file blob :one.bin >result &&
test_cmp expected result
'
test_expect_success 'cat-file without --textconv (symlink)' '
+ printf "%s" "one.bin" >expected &&
git cat-file blob :symlink.bin >result &&
- printf "%s" "one.bin" >expected
test_cmp expected result
'
test_expect_success 'cat-file --textconv on index (symlink)' '
- ! git cat-file --textconv :symlink.bin 2>result &&
- cat >expected <<\EOF &&
-fatal: git cat-file --textconv: unable to run textconv on :symlink.bin
-EOF
+ git cat-file --textconv :symlink.bin >result &&
test_cmp expected result
'
test_expect_success 'cat-file --textconv on HEAD (symlink)' '
- ! git cat-file --textconv HEAD:symlink.bin 2>result &&
- cat >expected <<EOF &&
-fatal: git cat-file --textconv: unable to run textconv on HEAD:symlink.bin
-EOF
+ git cat-file --textconv HEAD:symlink.bin >result &&
test_cmp expected result
'