@ -2,6 +2,8 @@
#include "grep.h"
#include "grep.h"
#include "userdiff.h"
#include "userdiff.h"
#include "xdiff-interface.h"
#include "xdiff-interface.h"
#include "diff.h"
#include "diffcore.h"
static int grep_source_load(struct grep_source *gs);
static int grep_source_load(struct grep_source *gs);
static int grep_source_is_binary(struct grep_source *gs);
static int grep_source_is_binary(struct grep_source *gs);
@ -1322,6 +1324,58 @@ static void std_output(struct grep_opt *opt, const void *buf, size_t size)
fwrite(buf, size, 1, stdout);
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)
static int grep_source_1(struct grep_opt *opt, struct grep_source *gs, int collect_hits)
{
{
char *bol;
char *bol;
@ -1332,6 +1386,7 @@ static int grep_source_1(struct grep_opt *opt, struct grep_source *gs, int colle
unsigned count = 0;
unsigned count = 0;
int try_lookahead = 0;
int try_lookahead = 0;
int show_function = 0;
int show_function = 0;
struct userdiff_driver *textconv = NULL;
enum grep_context ctx = GREP_CONTEXT_HEAD;
enum grep_context ctx = GREP_CONTEXT_HEAD;
xdemitconf_t xecfg;
xdemitconf_t xecfg;
@ -1353,19 +1408,36 @@ static int grep_source_1(struct grep_opt *opt, struct grep_source *gs, int colle
}
}
opt->last_shown = 0;
opt->last_shown = 0;
switch (opt->binary) {
if (opt->allow_textconv) {
case GREP_BINARY_DEFAULT:
grep_source_load_driver(gs);
if (grep_source_is_binary(gs))
/*
binary_match_only = 1;
* We might set up the shared textconv cache data here, which
break;
* is not thread-safe.
case GREP_BINARY_NOMATCH:
*/
if (grep_source_is_binary(gs))
grep_attr_lock();
return 0; /* Assume unmatch */
textconv = userdiff_get_textconv(gs->driver);
break;
grep_attr_unlock();
case GREP_BINARY_TEXT:
}
break;
default:
/*
die("bug: unknown binary handling mode");
* 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));
memset(&xecfg, 0, sizeof(xecfg));
@ -1373,7 +1445,7 @@ static int grep_source_1(struct grep_opt *opt, struct grep_source *gs, int colle
try_lookahead = should_lookahead(opt);
try_lookahead = should_lookahead(opt);
if (grep_source_load(gs) < 0)
if (fill_textconv_grep(textconv, gs) < 0)
return 0;
return 0;
bol = gs->buf;
bol = gs->buf;