summaryrefslogtreecommitdiff
path: root/grep.c
diff options
context:
space:
mode:
Diffstat (limited to 'grep.c')
-rw-r--r--grep.c122
1 files changed, 93 insertions, 29 deletions
diff --git a/grep.c b/grep.c
index 82eb7da..ac34bfe 100644
--- a/grep.c
+++ b/grep.c
@@ -1,12 +1,14 @@
-#include "cache.h"
+#include "git-compat-util.h"
#include "config.h"
+#include "gettext.h"
#include "grep.h"
-#include "object-store.h"
+#include "hex.h"
+#include "object-store-ll.h"
+#include "pretty.h"
#include "userdiff.h"
#include "xdiff-interface.h"
#include "diff.h"
#include "diffcore.h"
-#include "commit.h"
#include "quote.h"
#include "help.h"
@@ -14,7 +16,7 @@ static int grep_source_load(struct grep_source *gs);
static int grep_source_is_binary(struct grep_source *gs,
struct index_state *istate);
-static void std_output(struct grep_opt *opt, const void *buf, size_t size)
+static void std_output(struct grep_opt *opt UNUSED, const void *buf, size_t size)
{
fwrite(buf, size, 1, stdout);
}
@@ -52,7 +54,8 @@ define_list_config_array_extra(color_grep_slots, {"match"});
* Read the configuration file once and store it in
* the grep_defaults template.
*/
-int grep_config(const char *var, const char *value, void *cb)
+int grep_config(const char *var, const char *value,
+ const struct config_context *ctx, void *cb)
{
struct grep_opt *opt = cb;
const char *slot;
@@ -87,9 +90,9 @@ int grep_config(const char *var, const char *value, void *cb)
if (!strcmp(var, "color.grep"))
opt->color = git_config_colorbool(var, value);
if (!strcmp(var, "color.grep.match")) {
- if (grep_config("color.grep.matchcontext", value, cb) < 0)
+ if (grep_config("color.grep.matchcontext", value, ctx, cb) < 0)
return -1;
- if (grep_config("color.grep.matchselected", value, cb) < 0)
+ if (grep_config("color.grep.matchselected", value, ctx, cb) < 0)
return -1;
} else if (skip_prefix(var, "color.grep.", &slot)) {
int i = LOOKUP_CONFIG(color_grep_slots, slot);
@@ -262,6 +265,31 @@ static void pcre2_free(void *pointer, MAYBE_UNUSED void *memory_data)
free(pointer);
}
+static int pcre2_jit_functional(void)
+{
+ static int jit_working = -1;
+ pcre2_code *code;
+ size_t off;
+ int err;
+
+ if (jit_working != -1)
+ return jit_working;
+
+ /*
+ * Try to JIT compile a simple pattern to probe if the JIT is
+ * working in general. It might fail for systems where creating
+ * memory mappings for runtime code generation is restricted.
+ */
+ code = pcre2_compile((PCRE2_SPTR)".", 1, 0, &err, &off, NULL);
+ if (!code)
+ return 0;
+
+ jit_working = pcre2_jit_compile(code, PCRE2_JIT_COMPLETE) == 0;
+ pcre2_code_free(code);
+
+ return jit_working;
+}
+
static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_opt *opt)
{
int error;
@@ -293,7 +321,16 @@ static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_opt *opt
options |= PCRE2_CASELESS;
}
if (!opt->ignore_locale && is_utf8_locale() && !literal)
- options |= (PCRE2_UTF | PCRE2_MATCH_INVALID_UTF);
+ options |= (PCRE2_UTF | PCRE2_UCP | PCRE2_MATCH_INVALID_UTF);
+
+#ifndef GIT_PCRE2_VERSION_10_35_OR_HIGHER
+ /*
+ * Work around a JIT bug related to invalid Unicode character handling
+ * fixed in 10.35:
+ * https://github.com/PCRE2Project/pcre2/commit/c21bd977547d
+ */
+ options &= ~PCRE2_UCP;
+#endif
#ifndef GIT_PCRE2_VERSION_10_36_OR_HIGHER
/* Work around https://bugs.exim.org/show_bug.cgi?id=2642 fixed in 10.36 */
@@ -317,8 +354,29 @@ static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_opt *opt
pcre2_config(PCRE2_CONFIG_JIT, &p->pcre2_jit_on);
if (p->pcre2_jit_on) {
jitret = pcre2_jit_compile(p->pcre2_pattern, PCRE2_JIT_COMPLETE);
- if (jitret)
- die("Couldn't JIT the PCRE2 pattern '%s', got '%d'\n", p->pattern, jitret);
+ if (jitret == PCRE2_ERROR_NOMEMORY && !pcre2_jit_functional()) {
+ /*
+ * Even though pcre2_config(PCRE2_CONFIG_JIT, ...)
+ * indicated JIT support, the library might still
+ * fail to generate JIT code for various reasons,
+ * e.g. when SELinux's 'deny_execmem' or PaX's
+ * MPROTECT prevent creating W|X memory mappings.
+ *
+ * Instead of faling hard, fall back to interpreter
+ * mode, just as if the pattern was prefixed with
+ * '(*NO_JIT)'.
+ */
+ p->pcre2_jit_on = 0;
+ return;
+ } else if (jitret) {
+ int need_clip = p->patternlen > 64;
+ int clip_len = need_clip ? 64 : p->patternlen;
+ die("Couldn't JIT the PCRE2 pattern '%.*s'%s, got '%d'%s",
+ clip_len, p->pattern, need_clip ? "..." : "", jitret,
+ pcre2_jit_functional()
+ ? "\nPerhaps prefix (*NO_JIT) to your pattern?"
+ : "");
+ }
/*
* The pcre2_config(PCRE2_CONFIG_JIT, ...) call just
@@ -393,18 +451,20 @@ static void free_pcre2_pattern(struct grep_pat *p)
pcre2_general_context_free(p->pcre2_general_context);
}
#else /* !USE_LIBPCRE2 */
-static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_opt *opt)
+static void compile_pcre2_pattern(struct grep_pat *p UNUSED,
+ const struct grep_opt *opt UNUSED)
{
die("cannot use Perl-compatible regexes when not compiled with USE_LIBPCRE");
}
-static int pcre2match(struct grep_pat *p, const char *line, const char *eol,
- regmatch_t *match, int eflags)
+static int pcre2match(struct grep_pat *p UNUSED, const char *line UNUSED,
+ const char *eol UNUSED, regmatch_t *match UNUSED,
+ int eflags UNUSED)
{
return 1;
}
-static void free_pcre2_pattern(struct grep_pat *p)
+static void free_pcre2_pattern(struct grep_pat *p UNUSED)
{
}
@@ -561,7 +621,7 @@ static struct grep_expr *compile_pattern_atom(struct grep_pat **list)
*list = p->next;
x = compile_pattern_or(list);
if (!*list || (*list)->token != GREP_CLOSE_PAREN)
- die("unmatched parenthesis");
+ die("unmatched ( for expression group");
*list = (*list)->next;
return x;
default:
@@ -708,6 +768,7 @@ void compile_grep_patterns(struct grep_opt *opt)
{
struct grep_pat *p;
struct grep_expr *header_expr = prep_header_patterns(opt);
+ int extended = 0;
for (p = opt->pattern_list; p; p = p->next) {
switch (p->token) {
@@ -717,21 +778,21 @@ void compile_grep_patterns(struct grep_opt *opt)
compile_regexp(p, opt);
break;
default:
- opt->extended = 1;
+ extended = 1;
break;
}
}
if (opt->all_match || opt->no_body_match || header_expr)
- opt->extended = 1;
- else if (!opt->extended)
+ extended = 1;
+ else if (!extended)
return;
p = opt->pattern_list;
if (p)
opt->pattern_expression = compile_pattern_expr(&p);
if (p)
- die("incomplete pattern expression: %s", p->pattern);
+ die("incomplete pattern expression group: %s", p->pattern);
if (opt->no_body_match && opt->pattern_expression)
opt->pattern_expression = grep_not_expr(opt->pattern_expression);
@@ -768,11 +829,11 @@ static void free_pattern_expr(struct grep_expr *x)
free(x);
}
-void free_grep_patterns(struct grep_opt *opt)
+static void free_grep_pat(struct grep_pat *pattern)
{
struct grep_pat *p, *n;
- for (p = opt->pattern_list; p; p = n) {
+ for (p = pattern; p; p = n) {
n = p->next;
switch (p->token) {
case GREP_PATTERN: /* atom */
@@ -789,10 +850,15 @@ void free_grep_patterns(struct grep_opt *opt)
}
free(p);
}
+}
- if (!opt->extended)
- return;
- free_pattern_expr(opt->pattern_expression);
+void free_grep_patterns(struct grep_opt *opt)
+{
+ free_grep_pat(opt->pattern_list);
+ free_grep_pat(opt->header_list);
+
+ if (opt->pattern_expression)
+ free_pattern_expr(opt->pattern_expression);
}
static const char *end_of_line(const char *cp, unsigned long *left)
@@ -971,8 +1037,6 @@ static int match_expr_eval(struct grep_opt *opt, struct grep_expr *x,
{
int h = 0;
- if (!x)
- die("Not a valid grep expression");
switch (x->node) {
case GREP_NODE_TRUE:
h = 1;
@@ -1052,7 +1116,7 @@ static int match_line(struct grep_opt *opt,
struct grep_pat *p;
int hit = 0;
- if (opt->extended)
+ if (opt->pattern_expression)
return match_expr(opt, bol, eol, ctx, col, icol,
collect_hits);
@@ -1370,7 +1434,7 @@ static int should_lookahead(struct grep_opt *opt)
{
struct grep_pat *p;
- if (opt->extended)
+ if (opt->pattern_expression)
return 0; /* punt for too complex stuff */
if (opt->invert)
return 0;
@@ -1615,7 +1679,7 @@ static int grep_source_1(struct grep_opt *opt, struct grep_source *gs, int colle
return 0;
goto next_line;
}
- if (hit) {
+ if (hit && (opt->max_count < 0 || count < opt->max_count)) {
count++;
if (opt->status_only)
return 1;
generated by cgit v0.10.2-6-g49f6 at 2024-04-19 07:14:44 (GMT)