diff options
author | jilles <jilles@FreeBSD.org> | 2011-05-07 14:32:16 +0000 |
---|---|---|
committer | jilles <jilles@FreeBSD.org> | 2011-05-07 14:32:16 +0000 |
commit | 8bbce85526c337676cfa1f717dac02d86742cf0a (patch) | |
tree | 56cf1ceba22fd77045407a8fa8188f0feeecf4b6 | |
parent | 11604ee85b5b347285de99920d04978997c18508 (diff) | |
download | FreeBSD-src-8bbce85526c337676cfa1f717dac02d86742cf0a.zip FreeBSD-src-8bbce85526c337676cfa1f717dac02d86742cf0a.tar.gz |
sh: Add UTF-8 support to ${#var}.
If the current locale uses UTF-8, ${#var} counts codepoints (more precisely,
bytes b with (b & 0xc0) != 0x80).
-rw-r--r-- | bin/sh/expand.c | 16 | ||||
-rw-r--r-- | tools/regression/bin/sh/expansion/length7.0 | 14 | ||||
-rw-r--r-- | tools/regression/bin/sh/expansion/length8.0 | 14 |
3 files changed, 41 insertions, 3 deletions
diff --git a/bin/sh/expand.c b/bin/sh/expand.c index c343977..dcef74e 100644 --- a/bin/sh/expand.c +++ b/bin/sh/expand.c @@ -665,6 +665,7 @@ evalvar(char *p, int flag) int special; int startloc; int varlen; + int varlenb; int easy; int quotes = flag & (EXP_FULL | EXP_CASE | EXP_REDIR); @@ -712,8 +713,15 @@ again: /* jump here after setting a variable with ${var=text} */ if (special) { varvalue(var, varflags & VSQUOTE, subtype, flag); if (subtype == VSLENGTH) { - varlen = expdest - stackblock() - startloc; - STADJUST(-varlen, expdest); + varlenb = expdest - stackblock() - startloc; + varlen = varlenb; + if (localeisutf8) { + val = stackblock() + startloc; + for (;val != expdest; val++) + if ((*val & 0xC0) == 0x80) + varlen--; + } + STADJUST(-varlenb, expdest); } } else { char const *syntax = (varflags & VSQUOTE) ? DQSYNTAX @@ -721,7 +729,9 @@ again: /* jump here after setting a variable with ${var=text} */ if (subtype == VSLENGTH) { for (;*val; val++) - varlen++; + if (!localeisutf8 || + (*val & 0xC0) != 0x80) + varlen++; } else { if (quotes) diff --git a/tools/regression/bin/sh/expansion/length7.0 b/tools/regression/bin/sh/expansion/length7.0 new file mode 100644 index 0000000..b79b116 --- /dev/null +++ b/tools/regression/bin/sh/expansion/length7.0 @@ -0,0 +1,14 @@ +# $FreeBSD$ + +unset LC_ALL +LC_CTYPE=en_US.UTF-8 +export LC_CTYPE + +# a umlaut +s=$(printf '\303\244') +# euro sign +s=$s$(printf '\342\202\254') +# some sort of 't' outside BMP +s=$s$(printf '\360\235\225\245') +set -- "$s" +[ ${#s} = 3 ] && [ ${#1} = 3 ] diff --git a/tools/regression/bin/sh/expansion/length8.0 b/tools/regression/bin/sh/expansion/length8.0 new file mode 100644 index 0000000..3cc6c15 --- /dev/null +++ b/tools/regression/bin/sh/expansion/length8.0 @@ -0,0 +1,14 @@ +# $FreeBSD$ + +unset LC_ALL +LC_CTYPE=en_US.ISO8859-1 +export LC_CTYPE + +# a umlaut +s=$(printf '\303\244') +# euro sign +s=$s$(printf '\342\202\254') +# some sort of 't' outside BMP +s=$s$(printf '\360\235\225\245') +set -- "$s" +[ ${#s} = 9 ] && [ ${#1} = 9 ] |