On Fri, Jul 26 2019, Junio C Hamano wrote:
> Ævar Arnfjörð Bjarmason <avarab@xxxxxxxxx> writes:
>
>> diff --git a/Makefile b/Makefile
>> index bd246f2989..dd38d5e527 100644
>> --- a/Makefile
>> +++ b/Makefile
>> @@ -726,6 +726,7 @@ TEST_BUILTINS_OBJS += test-oidmap.o
>> TEST_BUILTINS_OBJS += test-online-cpus.o
>> TEST_BUILTINS_OBJS += test-parse-options.o
>> TEST_BUILTINS_OBJS += test-path-utils.o
>> +TEST_BUILTINS_OBJS += test-pcre2-config.o
>
> This won't even build with any released pcre version; shouldn't we
> make it at least conditionally compiled code? Specifically...
>
>> TEST_BUILTINS_OBJS += test-pkt-line.o
>> TEST_BUILTINS_OBJS += test-prio-queue.o
>> TEST_BUILTINS_OBJS += test-reach.o
>> diff --git a/grep.c b/grep.c
>> index c7c06ae08d..8b8b9efe12 100644
>> --- a/grep.c
>> +++ b/grep.c
>> @@ -474,7 +474,7 @@ static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_opt *opt
>> }
>> if (!opt->ignore_locale && is_utf8_locale() && has_non_ascii(p->pattern) &&
>> !(!opt->ignore_case && (p->fixed || p->is_fixed)))
>> - options |= PCRE2_UTF;
>> + options |= (PCRE2_UTF | PCRE2_MATCH_INVALID_UTF);
>>
>> p->pcre2_pattern = pcre2_compile((PCRE2_SPTR)p->pattern,
>> p->patternlen, options, &error, &erroffset,
>> diff --git a/grep.h b/grep.h
>> index c0c71eb4a9..506f05b97b 100644
>> --- a/grep.h
>> +++ b/grep.h
>> @@ -21,6 +21,9 @@ typedef int pcre_extra;
>> #ifdef USE_LIBPCRE2
>> #define PCRE2_CODE_UNIT_WIDTH 8
>> #include <pcre2.h>
>> +#ifndef PCRE2_MATCH_INVALID_UTF
>> +#define PCRE2_MATCH_INVALID_UTF 0
>> +#endif
>
> ... unlike this piece of code ...
>
>> #else
>> typedef int pcre2_code;
>> typedef int pcre2_match_data;
>> diff --git a/t/helper/test-pcre2-config.c b/t/helper/test-pcre2-config.c
>> new file mode 100644
>> index 0000000000..5258fdddba
>> --- /dev/null
>> +++ b/t/helper/test-pcre2-config.c
>> @@ -0,0 +1,12 @@
>> +#include "test-tool.h"
>> +#include "cache.h"
>> +#include "grep.h"
>> +
>> +int cmd__pcre2_config(int argc, const char **argv)
>> +{
>> + if (argc == 2 && !strcmp(argv[1], "has-PCRE2_MATCH_INVALID_UTF")) {
>> + int value = PCRE2_MATCH_INVALID_UTF;
>
> ... this part does not have any fallback definition.
It works because we include grep.h, which'll define
PCRE2_MATCH_INVALID_UTF=0 if pcre2.h doesn't give it to us. I've tested
this on PCRE versions with/without PCRE2_MATCH_INVALID_UTF and it works
& runs/skips the appropriate tests.
