diff options
Diffstat (limited to 'Test/V07pcre.ztst')
| -rw-r--r-- | Test/V07pcre.ztst | 62 |
1 files changed, 47 insertions, 15 deletions
diff --git a/Test/V07pcre.ztst b/Test/V07pcre.ztst index c9c844d2a..b8cd31c96 100644 --- a/Test/V07pcre.ztst +++ b/Test/V07pcre.ztst @@ -6,20 +6,8 @@ return 0 fi setopt rematch_pcre -# Find a UTF-8 locale. - setopt multibyte -# Don't let LC_* override our choice of locale. - unset -m LC_\* - mb_ok= - langs=(en_{US,GB}.{UTF-,utf}8 en.UTF-8 - $(locale -a 2>/dev/null | egrep 'utf8|UTF-8')) - for LANG in $langs; do - if [[ é = ? ]]; then - mb_ok=1 - break; - fi - done - if [[ -z $mb_ok ]]; then + LANG=$(ZTST_find_UTF8) + if [[ -z $LANG ]]; then ZTST_unimplemented="no UTF-8 locale or multibyte mode is not implemented" else print -u $ZTST_fd Testing PCRE multibyte with locale $LANG @@ -120,6 +108,11 @@ >0 xo→t →t >0 Xo→t →t + [[ foo =~ (pre)?f(o*)(opt(i)onal)?(y)* ]] + typeset -p match +0:Empty string for optional captures that don't match +>typeset -g -a match=( '' oo '' '' '' ) + string="The following zip codes: 78884 90210 99513" pcre_compile -m "\d{5}" pcre_match -b -- $string && print "$MATCH; ZPCRE_OP: $ZPCRE_OP" @@ -129,12 +122,17 @@ >78884; ZPCRE_OP: 25 30 >90210; ZPCRE_OP: 31 36 -# Embedded NULs allowed in plaintext, but not in RE (although \0 as two-chars allowed) +# Embedded NULs allowed in plaintext, in RE, pcre supports \0 as two-chars [[ $'a\0bc\0d' =~ '^(a\0.)(.+)$' ]] print "${#MATCH}; ${#match[1]}; ${#match[2]}" 0:ensure ASCII NUL passes in and out of matched plaintext >6; 3; 3 +# PCRE2 supports NULs also in the RE + [[ $'a\0b\0c' =~ $'^(.\0)+' ]] && print "${#MATCH}; ${#match[1]}" +0:ensure ASCII NUL works also in the regex +>4; 2 + # Ensure the long-form infix operator works [[ foo -pcre-match ^f..$ ]] print $? @@ -174,3 +172,37 @@ echo $match[2] ) 0:regression for segmentation fault, workers/38307 >test + + LANG_SAVE=$LANG + [[ é =~ '^.\z' ]]; echo $? + LANG=C + [[ é =~ '^..\z' ]]; echo $? + LANG=$LANG_SAVE + [[ é =~ '^.\z' ]]; echo $? +0:switch between C/UTF-8 locales +>0 +>0 +>0 + + [[ abc =~ 'a(d*)bc' ]] && print "$#MATCH; $#match; ${#match[1]}" +0:empty capture +>3; 1; 0 + + [[ category/name-12345 =~ '(?x)^ + (?<category> [^/]* ) / + (?<package> + (?<name> \w+ ) - + (?<version> \d+ ))$' ]] + typeset -p1 .pcre.match +0:named captures +>typeset -g -A .pcre.match=( +> [category]=category +> [name]=name +> [package]=name-12345 +> [version]=12345 +>) + + pcre_compile 'cat(er(pillar)?)?' + pcre_match -d 'the caterpillar catchment' && print $match +0:pcre_match -d +>caterpillar cater cat |