From 3c65ea532f745a2bc619ed1aa32b9c26155329c3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Carlo=20Marcelo=20Arenas=20Bel=C3=B3n?= Date: Fri, 6 Jan 2023 20:40:07 -0800 Subject: [PATCH] pcre: only use UTF when available in the library Before this change, if linked with a PCRE library without unicode any invocations of grep when using an UTF locale will error with: grep: this version of PCRE2 does not have Unicode support * src/pcresearch.c: Check if Unicode was compiled in. * tests/pcre-utf8-w: Add check to skip test. * tests/pcre-utf8: Update check. --- src/pcresearch.c | 4 +++- tests/pcre-utf8 | 2 +- tests/pcre-utf8-w | 5 ++++- 3 files changed, 8 insertions(+), 3 deletions(-) diff --git a/src/pcresearch.c b/src/pcresearch.c index 45b67ee..ac70a20 100644 --- a/src/pcresearch.c +++ b/src/pcresearch.c @@ -140,12 +140,14 @@ Pcompile (char *pattern, idx_t size, reg_syntax_t ignored, bool exact) int ec; int flags = PCRE2_DOLLAR_ENDONLY | (match_icase ? PCRE2_CASELESS : 0); char *patlim = pattern + size; + int unicode = 1; struct pcre_comp *pc = ximalloc (sizeof *pc); pcre2_general_context *gcontext = pc->gcontext = pcre2_general_context_create (private_malloc, private_free, NULL); pcre2_compile_context *ccontext = pcre2_compile_context_create (gcontext); - if (localeinfo.multibyte) + pcre2_config (PCRE2_CONFIG_UNICODE, &unicode); + if (unicode && localeinfo.multibyte) { if (! localeinfo.using_utf8) die (EXIT_TROUBLE, 0, _("-P supports only unibyte and UTF-8 locales")); diff --git a/tests/pcre-utf8 b/tests/pcre-utf8 index 1b3b2d3..4d97e69 100755 --- a/tests/pcre-utf8 +++ b/tests/pcre-utf8 @@ -14,7 +14,7 @@ LC_ALL=en_US.UTF-8 require_pcre_ fail=0 echo '$' | LC_ALL=en_US.UTF-8 grep -qP '\p{S}' \ - || skip_ 'PCRE support is compiled out, or it does not support properties' + || skip_ 'PCRE unicode support is compiled out' euro='\342\202\254 euro' printf "$euro\\n" > in || framework_failure_ diff --git a/tests/pcre-utf8-w b/tests/pcre-utf8-w index 4cd7db6..81ac9ff 100755 --- a/tests/pcre-utf8-w +++ b/tests/pcre-utf8-w @@ -13,9 +13,12 @@ LC_ALL=en_US.UTF-8 export LC_ALL require_pcre_ +echo . | grep -qP '(*UTF).' 2>/dev/null \ + || skip_ 'PCRE unicode support is compiled out' + fail=0 -echo 'Perú'> in || framework_failure_ +echo 'Perú' > in || framework_failure_ echo 'ú' > exp || framework_failure_ grep -Po '.\b' in > out || fail=1 -- 2.37.1 (Apple Git-137.1)