#include "xdiff-interface.h"
#include "diff.h"
#include "diffcore.h"
+#include "commit.h"
+#include "quote.h"
static int grep_source_load(struct grep_source *gs);
static int grep_source_is_binary(struct grep_source *gs);
static struct grep_opt grep_defaults;
+static void std_output(struct grep_opt *opt, const void *buf, size_t size)
+{
+ fwrite(buf, size, 1, stdout);
+}
+
/*
* Initialize the grep_defaults template with hardcoded defaults.
* We could let the compiler do this, but without C99 initializers
color_set(opt->color_selected, "");
color_set(opt->color_sep, GIT_COLOR_CYAN);
opt->color = -1;
+ opt->output = std_output;
}
static int parse_pattern_type_arg(const char *opt, const char *arg)
opt->pathname = def->pathname;
opt->regflags = def->regflags;
opt->relative = def->relative;
+ opt->output = def->output;
color_set(opt->color_context, def->color_context);
color_set(opt->color_filename, def->color_filename);
color_set(opt->color_sep, def->color_sep);
}
-void grep_commit_pattern_type(enum grep_pattern_type pattern_type, struct grep_opt *opt)
-{
- if (pattern_type != GREP_PATTERN_TYPE_UNSPECIFIED)
- grep_set_pattern_type_option(pattern_type, opt);
- else if (opt->pattern_type_option != GREP_PATTERN_TYPE_UNSPECIFIED)
- grep_set_pattern_type_option(opt->pattern_type_option, opt);
- else if (opt->extended_regexp_option)
- grep_set_pattern_type_option(GREP_PATTERN_TYPE_ERE, opt);
-}
-
-void grep_set_pattern_type_option(enum grep_pattern_type pattern_type, struct grep_opt *opt)
+static void grep_set_pattern_type_option(enum grep_pattern_type pattern_type, struct grep_opt *opt)
{
switch (pattern_type) {
case GREP_PATTERN_TYPE_UNSPECIFIED:
}
}
+void grep_commit_pattern_type(enum grep_pattern_type pattern_type, struct grep_opt *opt)
+{
+ if (pattern_type != GREP_PATTERN_TYPE_UNSPECIFIED)
+ grep_set_pattern_type_option(pattern_type, opt);
+ else if (opt->pattern_type_option != GREP_PATTERN_TYPE_UNSPECIFIED)
+ grep_set_pattern_type_option(opt->pattern_type_option, opt);
+ else if (opt->extended_regexp_option)
+ grep_set_pattern_type_option(GREP_PATTERN_TYPE_ERE, opt);
+}
+
static struct grep_pat *create_grep_pat(const char *pat, size_t patlen,
const char *origin, int no,
enum grep_pat_token t,
int erroffset;
int options = PCRE_MULTILINE;
- if (opt->ignore_case)
+ if (opt->ignore_case) {
+ if (has_non_ascii(p->pattern))
+ p->pcre_tables = pcre_maketables();
options |= PCRE_CASELESS;
+ }
+ if (is_utf8_locale() && has_non_ascii(p->pattern))
+ options |= PCRE_UTF8;
p->pcre_regexp = pcre_compile(p->pattern, options, &error, &erroffset,
- NULL);
+ p->pcre_tables);
if (!p->pcre_regexp)
compile_regexp_failed(p, error);
{
pcre_free(p->pcre_regexp);
pcre_free(p->pcre_extra_info);
+ pcre_free((void *)p->pcre_tables);
}
#else /* !USE_LIBPCRE */
static void compile_pcre_regexp(struct grep_pat *p, const struct grep_opt *opt)
return 1;
}
+static void compile_fixed_regexp(struct grep_pat *p, struct grep_opt *opt)
+{
+ struct strbuf sb = STRBUF_INIT;
+ int err;
+ int regflags;
+
+ basic_regex_quote_buf(&sb, p->pattern);
+ regflags = opt->regflags & ~REG_EXTENDED;
+ if (opt->ignore_case)
+ regflags |= REG_ICASE;
+ err = regcomp(&p->regexp, sb.buf, regflags);
+ if (opt->debug)
+ fprintf(stderr, "fixed %s\n", sb.buf);
+ strbuf_release(&sb);
+ if (err) {
+ char errbuf[1024];
+ regerror(err, &p->regexp, errbuf, sizeof(errbuf));
+ regfree(&p->regexp);
+ compile_regexp_failed(p, errbuf);
+ }
+}
+
static void compile_regexp(struct grep_pat *p, struct grep_opt *opt)
{
+ int icase, ascii_only;
int err;
p->word_regexp = opt->word_regexp;
p->ignore_case = opt->ignore_case;
+ icase = opt->regflags & REG_ICASE || p->ignore_case;
+ ascii_only = !has_non_ascii(p->pattern);
+ /*
+ * Even when -F (fixed) asks us to do a non-regexp search, we
+ * may not be able to correctly case-fold when -i
+ * (ignore-case) is asked (in which case, we'll synthesize a
+ * regexp to match the pattern that matches regexp special
+ * characters literally, while ignoring case differences). On
+ * the other hand, even without -F, if the pattern does not
+ * have any regexp special characters and there is no need for
+ * case-folding search, we can internally turn it into a
+ * simple string match using kws. p->fixed tells us if we
+ * want to use kws.
+ */
if (opt->fixed || is_fixed(p->pattern, p->patternlen))
- p->fixed = 1;
+ p->fixed = !icase || ascii_only;
else
p->fixed = 0;
if (p->fixed) {
- if (opt->regflags & REG_ICASE || p->ignore_case)
- p->kws = kwsalloc(tolower_trans_tbl);
- else
- p->kws = kwsalloc(NULL);
+ p->kws = kwsalloc(icase ? tolower_trans_tbl : NULL);
kwsincr(p->kws, p->pattern, p->patternlen);
kwsprep(p->kws);
return;
+ } else if (opt->fixed) {
+ /*
+ * We come here when the pattern has the non-ascii
+ * characters we cannot case-fold, and asked to
+ * ignore-case.
+ */
+ compile_fixed_regexp(p, opt);
+ return;
}
if (opt->pcre) {
for (p = opt->header_list; p; p = p->next) {
if (p->token != GREP_PATTERN_HEAD)
- die("bug: a non-header pattern in grep header list.");
+ die("BUG: a non-header pattern in grep header list.");
if (p->field < GREP_HEADER_FIELD_MIN ||
GREP_HEADER_FIELD_MAX <= p->field)
- die("bug: unknown header field %d", p->field);
+ die("BUG: unknown header field %d", p->field);
compile_regexp(p, opt);
}
h = compile_pattern_atom(&pp);
if (!h || pp != p->next)
- die("bug: malformed header expr");
+ die("BUG: malformed header expr");
if (!header_group[p->field]) {
header_group[p->field] = h;
continue;
}
}
-static int regmatch(const regex_t *preg, char *line, char *eol,
- regmatch_t *match, int eflags)
-{
-#ifdef REG_STARTEND
- match->rm_so = 0;
- match->rm_eo = eol - line;
- eflags |= REG_STARTEND;
-#endif
- return regexec(preg, line, 1, match, eflags);
-}
-
static int patmatch(struct grep_pat *p, char *line, char *eol,
regmatch_t *match, int eflags)
{
else if (p->pcre_regexp)
hit = !pcrematch(p, line, eol, match, eflags);
else
- hit = !regmatch(&p->regexp, line, eol, match, eflags);
+ hit = !regexec_buf(&p->regexp, line, eol - line, 1, match,
+ eflags);
return hit;
}
}
if (opt->linenum) {
char buf[32];
- snprintf(buf, sizeof(buf), "%d", lno);
+ xsnprintf(buf, sizeof(buf), "%d", lno);
output_color(opt, buf, strlen(buf), opt->color_lineno);
output_sep(opt, sign);
}
return 0;
}
-static void std_output(struct grep_opt *opt, const void *buf, size_t size)
-{
- fwrite(buf, size, 1, stdout);
-}
-
static int fill_textconv_grep(struct userdiff_driver *driver,
struct grep_source *gs)
{
return 0;
}
+static int is_empty_line(const char *bol, const char *eol)
+{
+ while (bol < eol && isspace(*bol))
+ bol++;
+ return bol == eol;
+}
+
static int grep_source_1(struct grep_opt *opt, struct grep_source *gs, int collect_hits)
{
char *bol;
+ char *peek_bol = NULL;
unsigned long left;
unsigned lno = 1;
unsigned last_hit = 0;
case GREP_BINARY_TEXT:
break;
default:
- die("bug: unknown binary handling mode");
+ die("BUG: unknown binary handling mode");
}
}
show_function = 1;
goto next_line;
}
- if (show_function && match_funcname(opt, gs, bol, eol))
- show_function = 0;
+ if (show_function && (!peek_bol || peek_bol < bol)) {
+ unsigned long peek_left = left;
+ char *peek_eol = eol;
+
+ /*
+ * Trailing empty lines are not interesting.
+ * Peek past them to see if they belong to the
+ * body of the current function.
+ */
+ peek_bol = bol;
+ while (is_empty_line(peek_bol, peek_eol)) {
+ peek_bol = peek_eol + 1;
+ peek_eol = end_of_line(peek_bol, &peek_left);
+ }
+
+ if (match_funcname(opt, gs, peek_bol, peek_eol))
+ show_function = 0;
+ }
if (show_function ||
(last_hit && lno <= last_hit + opt->post_context)) {
/* If the last hit is within the post context,
opt->color_filename);
output_sep(opt, ':');
}
- snprintf(buf, sizeof(buf), "%u\n", count);
+ xsnprintf(buf, sizeof(buf), "%u\n", count);
opt->output(opt, buf, strlen(buf));
return 1;
}
case GREP_SOURCE_FILE:
gs->identifier = xstrdup(identifier);
break;
+ case GREP_SOURCE_SUBMODULE:
+ if (!identifier) {
+ gs->identifier = NULL;
+ break;
+ }
+ /*
+ * FALL THROUGH
+ * If the identifier is non-NULL (in the submodule case) it
+ * will be a SHA1 that needs to be copied.
+ */
case GREP_SOURCE_SHA1:
gs->identifier = xmalloc(20);
hashcpy(gs->identifier, identifier);
break;
case GREP_SOURCE_BUF:
gs->identifier = NULL;
+ break;
}
}
switch (gs->type) {
case GREP_SOURCE_FILE:
case GREP_SOURCE_SHA1:
+ case GREP_SOURCE_SUBMODULE:
free(gs->buf);
gs->buf = NULL;
gs->size = 0;
if (lstat(filename, &st) < 0) {
err_ret:
if (errno != ENOENT)
- error(_("'%s': %s"), filename, strerror(errno));
+ error_errno(_("failed to stat '%s'"), filename);
return -1;
}
if (!S_ISREG(st.st_mode))
goto err_ret;
data = xmallocz(size);
if (st.st_size != read_in_full(i, data, size)) {
- error(_("'%s': short read %s"), filename, strerror(errno));
+ error_errno(_("'%s': short read"), filename);
close(i);
free(data);
return -1;
return grep_source_load_sha1(gs);
case GREP_SOURCE_BUF:
return gs->buf ? 0 : -1;
+ case GREP_SOURCE_SUBMODULE:
+ break;
}
- die("BUG: invalid grep_source type");
+ die("BUG: invalid grep_source type to load");
}
void grep_source_load_driver(struct grep_source *gs)