Merge branch 'ab/pcre2-grep'

"git grep" compiled with libpcre2 sometimes triggered a segfault,
which is being fixed.

* ab/pcre2-grep:
grep: fix segfault under -P + PCRE2 <=10.30 + (*NO_JIT)
test-lib: add LIBPCRE1 & LIBPCRE2 prerequisites

diff --git a/grep.c b/grep.c
index a69c05edc2e4fc6787076531b43a49c7ccdc1113..3d7cd0e96f1ee160a66dd500c58d4026bf24e34c 100644 (file)
--- a/grep.c
+++ b/grep.c
@@ -477,6 +477,8 @@ static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_opt *opt
        int options = PCRE2_MULTILINE;
        const uint8_t *character_tables = NULL;
        int jitret;
+       int patinforet;
+       size_t jitsizearg;
 
        assert(opt->pcre2);
 
@@ -511,6 +513,30 @@ static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_opt *opt
                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);
+
+               /*
+                * The pcre2_config(PCRE2_CONFIG_JIT, ...) call just
+                * tells us whether the library itself supports JIT,
+                * but to see whether we're going to be actually using
+                * JIT we need to extract PCRE2_INFO_JITSIZE from the
+                * pattern *after* we do pcre2_jit_compile() above.
+                *
+                * This is because if the pattern contains the
+                * (*NO_JIT) verb (see pcre2syntax(3))
+                * pcre2_jit_compile() will exit early with 0. If we
+                * then proceed to call pcre2_jit_match() further down
+                * the line instead of pcre2_match() we'll either
+                * segfault (pre PCRE 10.31) or run into a fatal error
+                * (post PCRE2 10.31)
+                */
+               patinforet = pcre2_pattern_info(p->pcre2_pattern, PCRE2_INFO_JITSIZE, &jitsizearg);
+               if (patinforet)
+                       BUG("pcre2_pattern_info() failed: %d", patinforet);
+               if (jitsizearg == 0) {
+                       p->pcre2_jit_on = 0;
+                       return;
+               }
+
                p->pcre2_jit_stack = pcre2_jit_stack_create(1, 1024 * 1024, NULL);
                if (!p->pcre2_jit_stack)
                        die("Couldn't allocate PCRE2 JIT stack");

diff --git a/t/README b/t/README
index 4b079e4494d9324f0b03dfe8f714b3717292c0b6..599cd9808c553e281a0093c0853eeb1b9df36740 100644 (file)
--- a/t/README
+++ b/t/README
@@ -808,6 +808,18 @@ use these, and "test_set_prereq" for how to define your own.
    Git was compiled with support for PCRE. Wrap any tests
    that use git-grep --perl-regexp or git-grep -P in these.
 
+ - LIBPCRE1
+
+   Git was compiled with PCRE v1 support via
+   USE_LIBPCRE1=YesPlease. Wrap any PCRE using tests that for some
+   reason need v1 of the PCRE library instead of v2 in these.
+
+ - LIBPCRE2
+
+   Git was compiled with PCRE v2 support via
+   USE_LIBPCRE2=YesPlease. Wrap any PCRE using tests that for some
+   reason need v2 of the PCRE library instead of v1 in these.
+
  - CASE_INSENSITIVE_FS
 
    Test is run on a case insensitive file system.

diff --git a/t/t7810-grep.sh b/t/t7810-grep.sh
index c02ca735b9e31952811bfbb19048081dc546bd8e..1797f632a388d16f23a47c7693c7a3f0f0deabf6 100755 (executable)
--- a/t/t7810-grep.sh
+++ b/t/t7810-grep.sh
@@ -1131,6 +1131,12 @@ test_expect_success PCRE 'grep -P pattern' '
        test_cmp expected actual
 '
 
+test_expect_success LIBPCRE2 "grep -P with (*NO_JIT) doesn't error out" '
+       git grep -P "(*NO_JIT)\p{Ps}.*?\p{Pe}" hello.c >actual &&
+       test_cmp expected actual
+
+'
+
 test_expect_success !PCRE 'grep -P pattern errors without PCRE' '
        test_must_fail git grep -P "foo.*bar"
 '

diff --git a/t/test-lib.sh b/t/test-lib.sh
index 116bd6a70cf727f8dff496b9340b85146208e778..e7065df2bb028aff76f3169d84873a1a3d789571 100644 (file)
--- a/t/test-lib.sh
+++ b/t/test-lib.sh
@@ -1028,6 +1028,8 @@ test -z "$NO_PERL" && test_set_prereq PERL
 test -z "$NO_PTHREADS" && test_set_prereq PTHREADS
 test -z "$NO_PYTHON" && test_set_prereq PYTHON
 test -n "$USE_LIBPCRE1$USE_LIBPCRE2" && test_set_prereq PCRE
+test -n "$USE_LIBPCRE1" && test_set_prereq LIBPCRE1
+test -n "$USE_LIBPCRE2" && test_set_prereq LIBPCRE2
 test -z "$NO_GETTEXT" && test_set_prereq GETTEXT
 
 # Can we rely on git's output in the C locale?