![[tokkee]](http://tokkee.org/images/avatar.png){kind=avatar}
index db58a29c2b508ecccc56a2cb17ce6ef98f6355ed..f492d267cc157d46f899c70d01ea707d737d27ae 100644 (file)
--- a/grep.c
+++ b/grep.c
{
const char *error;
int erroffset;
- int options = 0;
+ int options = PCRE_MULTILINE;
if (opt->ignore_case)
options |= PCRE_CASELESS;
#define grep_attr_unlock()
#endif
-static int match_funcname(struct grep_opt *opt, const char *name, char *bol, char *eol)
+static int match_funcname(struct grep_opt *opt, struct grep_source *gs, char *bol, char *eol)
{
xdemitconf_t *xecfg = opt->priv;
if (xecfg && !xecfg->find_func) {
- struct userdiff_driver *drv;
- grep_attr_lock();
- drv = userdiff_find_by_path(name);
- grep_attr_unlock();
- if (drv && drv->funcname.pattern) {
- const struct userdiff_funcname *pe = &drv->funcname;
+ grep_source_load_driver(gs);
+ if (gs->driver->funcname.pattern) {
+ const struct userdiff_funcname *pe = &gs->driver->funcname;
xdiff_set_find_func(xecfg, pe->pattern, pe->cflags);
} else {
xecfg = opt->priv = NULL;
@@ -866,33 +863,33 @@ static int match_funcname(struct grep_opt *opt, const char *name, char *bol, cha
return 0;
}
-static void show_funcname_line(struct grep_opt *opt, const char *name,
- char *buf, char *bol, unsigned lno)
+static void show_funcname_line(struct grep_opt *opt, struct grep_source *gs,
+ char *bol, unsigned lno)
{
- while (bol > buf) {
+ while (bol > gs->buf) {
char *eol = --bol;
- while (bol > buf && bol[-1] != '\n')
+ while (bol > gs->buf && bol[-1] != '\n')
bol--;
lno--;
if (lno <= opt->last_shown)
break;
- if (match_funcname(opt, name, bol, eol)) {
- show_line(opt, bol, eol, name, lno, '=');
+ if (match_funcname(opt, gs, bol, eol)) {
+ show_line(opt, bol, eol, gs->name, lno, '=');
break;
}
}
}
-static void show_pre_context(struct grep_opt *opt, const char *name, char *buf,
+static void show_pre_context(struct grep_opt *opt, struct grep_source *gs,
char *bol, char *end, unsigned lno)
{
unsigned cur = lno, from = 1, funcname_lno = 0;
int funcname_needed = !!opt->funcname;
- if (opt->funcbody && !match_funcname(opt, name, bol, end))
+ if (opt->funcbody && !match_funcname(opt, gs, bol, end))
funcname_needed = 2;
if (opt->pre_context < lno)
@@ -901,14 +898,14 @@ static void show_pre_context(struct grep_opt *opt, const char *name, char *buf,
from = opt->last_shown + 1;
/* Rewind. */
- while (bol > buf &&
+ while (bol > gs->buf &&
cur > (funcname_needed == 2 ? opt->last_shown + 1 : from)) {
char *eol = --bol;
- while (bol > buf && bol[-1] != '\n')
+ while (bol > gs->buf && bol[-1] != '\n')
bol--;
cur--;
- if (funcname_needed && match_funcname(opt, name, bol, eol)) {
+ if (funcname_needed && match_funcname(opt, gs, bol, eol)) {
funcname_lno = cur;
funcname_needed = 0;
}
/* We need to look even further back to find a function signature. */
if (opt->funcname && funcname_needed)
- show_funcname_line(opt, name, buf, bol, cur);
+ show_funcname_line(opt, gs, bol, cur);
/* Back forward. */
while (cur < lno) {
while (*eol != '\n')
eol++;
- show_line(opt, bol, eol, name, cur, sign);
+ show_line(opt, bol, eol, gs->name, cur, sign);
bol = eol + 1;
cur++;
}
fwrite(buf, size, 1, stdout);
}
-static int grep_buffer_1(struct grep_opt *opt, const char *name,
- char *buf, unsigned long size, int collect_hits)
+static int grep_source_1(struct grep_opt *opt, struct grep_source *gs, int collect_hits)
{
- char *bol = buf;
- unsigned long left = size;
+ char *bol;
+ unsigned long left;
unsigned lno = 1;
unsigned last_hit = 0;
int binary_match_only = 0;
switch (opt->binary) {
case GREP_BINARY_DEFAULT:
- if (buffer_is_binary(buf, size))
+ if (grep_source_is_binary(gs))
binary_match_only = 1;
break;
case GREP_BINARY_NOMATCH:
- if (buffer_is_binary(buf, size))
+ if (grep_source_is_binary(gs))
return 0; /* Assume unmatch */
break;
case GREP_BINARY_TEXT:
try_lookahead = should_lookahead(opt);
+ if (grep_source_load(gs) < 0)
+ return 0;
+
+ bol = gs->buf;
+ left = gs->size;
while (left) {
char *eol, ch;
int hit;
if (opt->status_only)
return 1;
if (opt->name_only) {
- show_name(opt, name);
+ show_name(opt, gs->name);
return 1;
}
if (opt->count)
goto next_line;
if (binary_match_only) {
opt->output(opt, "Binary file ", 12);
- output_color(opt, name, strlen(name),
+ output_color(opt, gs->name, strlen(gs->name),
opt->color_filename);
opt->output(opt, " matches\n", 9);
return 1;
* pre-context lines, we would need to show them.
*/
if (opt->pre_context || opt->funcbody)
- show_pre_context(opt, name, buf, bol, eol, lno);
+ show_pre_context(opt, gs, bol, eol, lno);
else if (opt->funcname)
- show_funcname_line(opt, name, buf, bol, lno);
- show_line(opt, bol, eol, name, lno, ':');
+ show_funcname_line(opt, gs, bol, lno);
+ show_line(opt, bol, eol, gs->name, lno, ':');
last_hit = lno;
if (opt->funcbody)
show_function = 1;
goto next_line;
}
- if (show_function && match_funcname(opt, name, bol, eol))
+ if (show_function && match_funcname(opt, gs, bol, eol))
show_function = 0;
if (show_function ||
(last_hit && lno <= last_hit + opt->post_context)) {
/* If the last hit is within the post context,
* we need to show this line.
*/
- show_line(opt, bol, eol, name, lno, '-');
+ show_line(opt, bol, eol, gs->name, lno, '-');
}
next_line:
return 0;
if (opt->unmatch_name_only) {
/* We did not see any hit, so we want to show this */
- show_name(opt, name);
+ show_name(opt, gs->name);
return 1;
}
*/
if (opt->count && count) {
char buf[32];
- output_color(opt, name, strlen(name), opt->color_filename);
+ output_color(opt, gs->name, strlen(gs->name), opt->color_filename);
output_sep(opt, ':');
snprintf(buf, sizeof(buf), "%u\n", count);
opt->output(opt, buf, strlen(buf));
}
}
-int grep_buffer(struct grep_opt *opt, const char *name, char *buf, unsigned long size)
+int grep_source(struct grep_opt *opt, struct grep_source *gs)
{
/*
* we do not have to do the two-pass grep when we do not check
* buffer-wide "all-match".
*/
if (!opt->all_match)
- return grep_buffer_1(opt, name, buf, size, 0);
+ return grep_source_1(opt, gs, 0);
/* Otherwise the toplevel "or" terms hit a bit differently.
* We first clear hit markers from them.
*/
clr_hit_marker(opt->pattern_expression);
- grep_buffer_1(opt, name, buf, size, 1);
+ grep_source_1(opt, gs, 1);
if (!chk_hit_marker(opt->pattern_expression))
return 0;
- return grep_buffer_1(opt, name, buf, size, 0);
+ return grep_source_1(opt, gs, 0);
+}
+
+int grep_buffer(struct grep_opt *opt, char *buf, unsigned long size)
+{
+ struct grep_source gs;
+ int r;
+
+ grep_source_init(&gs, GREP_SOURCE_BUF, NULL, NULL);
+ gs.buf = buf;
+ gs.size = size;
+
+ r = grep_source(opt, &gs);
+
+ grep_source_clear(&gs);
+ return r;
+}
+
+void grep_source_init(struct grep_source *gs, enum grep_source_type type,
+ const char *name, const void *identifier)
+{
+ gs->type = type;
+ gs->name = name ? xstrdup(name) : NULL;
+ gs->buf = NULL;
+ gs->size = 0;
+ gs->driver = NULL;
+
+ switch (type) {
+ case GREP_SOURCE_FILE:
+ gs->identifier = xstrdup(identifier);
+ break;
+ case GREP_SOURCE_SHA1:
+ gs->identifier = xmalloc(20);
+ memcpy(gs->identifier, identifier, 20);
+ break;
+ case GREP_SOURCE_BUF:
+ gs->identifier = NULL;
+ }
+}
+
+void grep_source_clear(struct grep_source *gs)
+{
+ free(gs->name);
+ gs->name = NULL;
+ free(gs->identifier);
+ gs->identifier = NULL;
+ grep_source_clear_data(gs);
+}
+
+void grep_source_clear_data(struct grep_source *gs)
+{
+ switch (gs->type) {
+ case GREP_SOURCE_FILE:
+ case GREP_SOURCE_SHA1:
+ free(gs->buf);
+ gs->buf = NULL;
+ gs->size = 0;
+ break;
+ case GREP_SOURCE_BUF:
+ /* leave user-provided buf intact */
+ break;
+ }
+}
+
+static int grep_source_load_sha1(struct grep_source *gs)
+{
+ enum object_type type;
+
+ grep_read_lock();
+ gs->buf = read_sha1_file(gs->identifier, &type, &gs->size);
+ grep_read_unlock();
+
+ if (!gs->buf)
+ return error(_("'%s': unable to read %s"),
+ gs->name,
+ sha1_to_hex(gs->identifier));
+ return 0;
+}
+
+static int grep_source_load_file(struct grep_source *gs)
+{
+ const char *filename = gs->identifier;
+ struct stat st;
+ char *data;
+ size_t size;
+ int i;
+
+ if (lstat(filename, &st) < 0) {
+ err_ret:
+ if (errno != ENOENT)
+ error(_("'%s': %s"), filename, strerror(errno));
+ return -1;
+ }
+ if (!S_ISREG(st.st_mode))
+ return -1;
+ size = xsize_t(st.st_size);
+ i = open(filename, O_RDONLY);
+ if (i < 0)
+ goto err_ret;
+ data = xmalloc(size + 1);
+ if (st.st_size != read_in_full(i, data, size)) {
+ error(_("'%s': short read %s"), filename, strerror(errno));
+ close(i);
+ free(data);
+ return -1;
+ }
+ close(i);
+ data[size] = 0;
+
+ gs->buf = data;
+ gs->size = size;
+ return 0;
+}
+
+int grep_source_load(struct grep_source *gs)
+{
+ if (gs->buf)
+ return 0;
+
+ switch (gs->type) {
+ case GREP_SOURCE_FILE:
+ return grep_source_load_file(gs);
+ case GREP_SOURCE_SHA1:
+ return grep_source_load_sha1(gs);
+ case GREP_SOURCE_BUF:
+ return gs->buf ? 0 : -1;
+ }
+ die("BUG: invalid grep_source type");
+}
+
+void grep_source_load_driver(struct grep_source *gs)
+{
+ if (gs->driver)
+ return;
+
+ grep_attr_lock();
+ gs->driver = userdiff_find_by_path(gs->name);
+ if (!gs->driver)
+ gs->driver = userdiff_find_by_name("default");
+ grep_attr_unlock();
+}
+
+int grep_source_is_binary(struct grep_source *gs)
+{
+ grep_source_load_driver(gs);
+ if (gs->driver->binary != -1)
+ return gs->driver->binary;
+
+ if (!grep_source_load(gs))
+ return buffer_is_binary(gs->buf, gs->size);
+
+ return 0;
}