void grep_source_load_driver(struct grep_source *gs)
{
if (gs->driver)
return;
grep_attr_lock();
if (gs->path)
gs->driver = userdiff_find_by_path(gs->path);
if (!gs->driver)
gs->driver = userdiff_find_by_name("default");
grep_attr_unlock();
}
static const char *parse_range_funcname(const char *arg, nth_line_fn_t nth_line_cb,
void *cb_data, long lines, long *begin, long *end,
const char *path)
{
char *pattern;
const char *term;
struct userdiff_driver *drv;
xdemitconf_t *xecfg = NULL;
const char *start;
const char *p;
int reg_error;
regex_t regexp;
assert(*arg == ':');
term = arg+1;
while (*term && *term != ':') {
if (*term == '\\' && *(term+1))
term++;
term++;
}
if (term == arg+1)
return NULL;
if (!begin) /* skip_range_arg case */
return term;
pattern = xstrndup(arg+1, term-(arg+1));
start = nth_line_cb(cb_data, 0);
drv = userdiff_find_by_path(path);
if (drv && drv->funcname.pattern) {
const struct userdiff_funcname *pe = &drv->funcname;
xecfg = xcalloc(1, sizeof(*xecfg));
xdiff_set_find_func(xecfg, pe->pattern, pe->cflags);
}
reg_error = regcomp(®exp, pattern, REG_NEWLINE);
if (reg_error) {
char errbuf[1024];
regerror(reg_error, ®exp, errbuf, 1024);
die("-L parameter '%s': %s", pattern, errbuf);
}
p = find_funcname_matching_regexp(xecfg, (char*) start, ®exp);
if (!p)
die("-L parameter '%s': no match", pattern);
*begin = 0;
while (p > nth_line_cb(cb_data, *begin))
(*begin)++;
if (*begin >= lines)
die("-L parameter '%s' matches at EOF", pattern);
*end = *begin+1;
while (*end < lines) {
const char *bol = nth_line_cb(cb_data, *end);
const char *eol = nth_line_cb(cb_data, *end+1);
if (match_funcname(xecfg, bol, eol))
break;
(*end)++;
}
regfree(®exp);
free(xecfg);
free(pattern);
/* compensate for 1-based numbering */
(*begin)++;
return term;
}
static int grep_buffer_1(struct grep_opt *opt, const char *name,
char *buf, unsigned long size, int collect_hits)
{
char *bol = buf;
unsigned long left = size;
unsigned lno = 1;
unsigned last_hit = 0;
int binary_match_only = 0;
unsigned count = 0;
int try_lookahead = 0;
enum grep_context ctx = GREP_CONTEXT_HEAD;
xdemitconf_t xecfg;
opt->last_shown = 0;
if (!opt->output)
opt->output = std_output;
if (buffer_is_binary(buf, size)) {
switch (opt->binary) {
case GREP_BINARY_DEFAULT:
binary_match_only = 1;
break;
case GREP_BINARY_NOMATCH:
return 0; /* Assume unmatch */
break;
default:
break;
}
}
memset(&xecfg, 0, sizeof(xecfg));
if (opt->funcname && !opt->unmatch_name_only && !opt->status_only &&
!opt->name_only && !binary_match_only && !collect_hits) {
struct userdiff_driver *drv = userdiff_find_by_path(name);
if (drv && drv->funcname.pattern) {
const struct userdiff_funcname *pe = &drv->funcname;
xdiff_set_find_func(&xecfg, pe->pattern, pe->cflags);
opt->priv = &xecfg;
}
}
try_lookahead = should_lookahead(opt);
while (left) {
char *eol, ch;
int hit;
/*
* look_ahead() skips quicly to the line that possibly
* has the next hit; don't call it if we need to do
* something more than just skipping the current line
* in response to an unmatch for the current line. E.g.
* inside a post-context window, we will show the current
* line as a context around the previous hit when it
* doesn't hit.
*/
if (try_lookahead
&& !(last_hit
&& lno <= last_hit + opt->post_context)
&& look_ahead(opt, &left, &lno, &bol))
break;
eol = end_of_line(bol, &left);
ch = *eol;
*eol = 0;
if ((ctx == GREP_CONTEXT_HEAD) && (eol == bol))
ctx = GREP_CONTEXT_BODY;
hit = match_line(opt, bol, eol, ctx, collect_hits);
*eol = ch;
if (collect_hits)
goto next_line;
/* "grep -v -e foo -e bla" should list lines
* that do not have either, so inversion should
* be done outside.
*/
if (opt->invert)
hit = !hit;
if (opt->unmatch_name_only) {
if (hit)
return 0;
goto next_line;
}
if (hit) {
count++;
if (opt->status_only)
return 1;
if (binary_match_only) {
opt->output(opt, "Binary file ", 12);
output_color(opt, name, strlen(name),
opt->color_filename);
opt->output(opt, " matches\n", 9);
return 1;
}
if (opt->name_only) {
show_name(opt, name);
return 1;
}
/* Hit at this line. If we haven't shown the
* pre-context lines, we would need to show them.
* When asked to do "count", this still show
* the context which is nonsense, but the user
* deserves to get that ;-).
*/
if (opt->pre_context)
show_pre_context(opt, name, buf, bol, lno);
else if (opt->funcname)
show_funcname_line(opt, name, buf, bol, lno);
if (!opt->count)
show_line(opt, bol, eol, name, lno, ':');
last_hit = lno;
}
else if (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, '-');
}
next_line:
bol = eol + 1;
if (!left)
break;
left--;
lno++;
}
if (collect_hits)
return 0;
if (opt->status_only)
return 0;
if (opt->unmatch_name_only) {
/* We did not see any hit, so we want to show this */
show_name(opt, name);
return 1;
}
xdiff_clear_find_func(&xecfg);
opt->priv = NULL;
/* NEEDSWORK:
* The real "grep -c foo *.c" gives many "bar.c:0" lines,
* which feels mostly useless but sometimes useful. Maybe
* make it another option? For now suppress them.
*/
if (opt->count && count) {
char buf[32];
output_color(opt, name, strlen(name), opt->color_filename);
output_sep(opt, ':');
snprintf(buf, sizeof(buf), "%u\n", count);
opt->output(opt, buf, strlen(buf));
}
return !!last_hit;
}
static int grep_buffer_1(struct grep_opt *opt, const char *name,
char *buf, unsigned long size, int collect_hits)
{
char *bol = buf;
unsigned long left = size;
unsigned lno = 1;
unsigned last_hit = 0;
int binary_match_only = 0;
unsigned count = 0;
enum grep_context ctx = GREP_CONTEXT_HEAD;
xdemitconf_t xecfg;
opt->last_shown = 0;
if (buffer_is_binary(buf, size)) {
switch (opt->binary) {
case GREP_BINARY_DEFAULT:
binary_match_only = 1;
break;
case GREP_BINARY_NOMATCH:
return 0; /* Assume unmatch */
break;
default:
break;
}
}
memset(&xecfg, 0, sizeof(xecfg));
if (opt->funcname && !opt->unmatch_name_only && !opt->status_only &&
!opt->name_only && !binary_match_only && !collect_hits) {
struct userdiff_driver *drv = userdiff_find_by_path(name);
if (drv && drv->funcname.pattern) {
const struct userdiff_funcname *pe = &drv->funcname;
xdiff_set_find_func(&xecfg, pe->pattern, pe->cflags);
opt->priv = &xecfg;
}
}
while (left) {
char *eol, ch;
int hit;
eol = end_of_line(bol, &left);
ch = *eol;
*eol = 0;
if ((ctx == GREP_CONTEXT_HEAD) && (eol == bol))
ctx = GREP_CONTEXT_BODY;
hit = match_line(opt, bol, eol, ctx, collect_hits);
*eol = ch;
if (collect_hits)
goto next_line;
/* "grep -v -e foo -e bla" should list lines
* that do not have either, so inversion should
* be done outside.
*/
if (opt->invert)
hit = !hit;
if (opt->unmatch_name_only) {
if (hit)
return 0;
goto next_line;
}
if (hit) {
count++;
if (opt->status_only)
return 1;
if (binary_match_only) {
printf("Binary file %s matches\n", name);
return 1;
}
if (opt->name_only) {
show_name(opt, name);
return 1;
}
/* Hit at this line. If we haven't shown the
* pre-context lines, we would need to show them.
* When asked to do "count", this still show
* the context which is nonsense, but the user
* deserves to get that ;-).
*/
if (opt->pre_context)
show_pre_context(opt, name, buf, bol, lno);
else if (opt->funcname)
show_funcname_line(opt, name, buf, bol, lno);
if (!opt->count)
show_line(opt, bol, eol, name, lno, ':');
last_hit = lno;
}
else if (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, '-');
}
next_line:
bol = eol + 1;
if (!left)
break;
left--;
lno++;
}
if (collect_hits)
return 0;
if (opt->status_only)
return 0;
if (opt->unmatch_name_only) {
/* We did not see any hit, so we want to show this */
show_name(opt, name);
return 1;
}
xdiff_clear_find_func(&xecfg);
opt->priv = NULL;
/* NEEDSWORK:
* The real "grep -c foo *.c" gives many "bar.c:0" lines,
* which feels mostly useless but sometimes useful. Maybe
* make it another option? For now suppress them.
*/
if (opt->count && count)
printf("%s%c%u\n", name,
opt->null_following_name ? '\0' : ':', count);
return !!last_hit;
}