diff options
author | duerst <duerst@b2dd03c8-39d4-4d8f-98ff-823fe69b080e> | 2016-06-05 05:46:37 +0000 |
---|---|---|
committer | duerst <duerst@b2dd03c8-39d4-4d8f-98ff-823fe69b080e> | 2016-06-05 05:46:37 +0000 |
commit | c5ea268264b006dbdeebbf66c847e4e3c778310b (patch) | |
tree | 386ea33f5a327e9c8569fbe25d6a595277811c2c /string.c | |
parent | ed6ab036d96c479ee6f6d0299e6cfbf599732f26 (diff) | |
download | ruby-c5ea268264b006dbdeebbf66c847e4e3c778310b.tar.gz |
* string.c: Remove :lithuanian guard for Unicode case mapping.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@55277 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
Diffstat (limited to 'string.c')
-rw-r--r-- | string.c | 38 |
1 files changed, 21 insertions, 17 deletions
@@ -5869,7 +5869,7 @@ rb_str_upcase_bang(int argc, VALUE *argv, VALUE str) enc = STR_ENC_GET(str); rb_str_check_dummy_enc(enc); s = RSTRING_PTR(str); send = RSTRING_END(str); - if (enc==rb_utf8_encoding() && argc>0) { /* :lithuanian can temporarily be used for new functionality without options */ + if (enc==rb_utf8_encoding()) { str_shared_replace(str, rb_str_casemap(str, &flags, enc)); modify = ONIGENC_CASE_MODIFIED & flags; } @@ -5959,7 +5959,7 @@ rb_str_downcase_bang(int argc, VALUE *argv, VALUE str) enc = STR_ENC_GET(str); rb_str_check_dummy_enc(enc); s = RSTRING_PTR(str); send = RSTRING_END(str); - if (enc==rb_utf8_encoding() && argc>0) { /* :lithuanian can temporarily be used for new functionality without options */ + if (enc==rb_utf8_encoding()) { str_shared_replace(str, rb_str_casemap(str, &flags, enc)); modify = ONIGENC_CASE_MODIFIED & flags; } @@ -6018,11 +6018,13 @@ rb_str_downcase_bang(int argc, VALUE *argv, VALUE str) * The meaning of the +options+ is as follows: * * No option :: - * Currently, old behavior (only the ASCII region, i.e. characters - * ``A'' to ``Z'', and/or ``a'' to ``z'', are affected). - * This will change very soon to full Unicode case mapping. + * Full Unicode case mapping, suitable for most languages + * (see :turkic and :lithuanian options below for exceptions). + * Context-dependent case mapping as described in Table 3-14 of the + * Unicode standard is currently not supported. * :ascii :: - * Only the ASCII region, i.e. the characters ``A'' to ``Z'', are affected. + * Only the ASCII region, i.e. the characters ``A'' to ``Z'' and + * ``a'' to ``z'', are affected. * This option cannot be combined with any other option. * :turkic :: * Full Unicode case mapping, adapted for Turkic languages @@ -6031,21 +6033,23 @@ rb_str_downcase_bang(int argc, VALUE *argv, VALUE str) * :lithuanian :: * Currently, just full Unicode case mapping. In the future, full Unicode * case mapping adapted for Lithuanian (keeping the dot on the lower case - * i even if there's an accent on top). + * i even if there is an accent on top). * :fold :: - * Only available on +downcase+ and +downcase!+. Unicode case folding, which - * is more far-reaching than Unicode case mapping. This option currently - * cannot be combined with any other option (i.e. we do not currenty - * implement a variant for turkic languages). + * Only available on +downcase+ and +downcase!+. Unicode case <b>folding</b>, + * which is more far-reaching than Unicode case mapping. + * This option currently cannot be combined with any other option + * (i.e. there is currenty no variant for turkic languages). * * Please note that several assumptions that are valid for ASCII-only case * conversions do not hold for more general case conversions. For example, * the length of the result may not be the same as the length of the input - * (neither in characters nor in bytes), and some roundtrip assumptions - * (e.g. str.downcase == str.downcase.upcase.downcase) may not apply. + * (neither in characters nor in bytes), some roundtrip assumptions + * (e.g. str.downcase == str.upcase.downcase) may not apply, and Unicode + * normalization (i.e. String#unicode_normalize) is not necessarily maintained + * by case mapping operations. * - * Non-ASCII case mapping/folding is currently only supported for UTF-8 Strings, - * but this support will be extended to other encodings in the future. + * Non-ASCII case mapping/folding is currently only supported for UTF-8 + * Strings/Symbols, but this support will be extended to other encodings. * * "hEllO".downcase #=> "hello" */ @@ -6090,7 +6094,7 @@ rb_str_capitalize_bang(int argc, VALUE *argv, VALUE str) enc = STR_ENC_GET(str); rb_str_check_dummy_enc(enc); if (RSTRING_LEN(str) == 0 || !RSTRING_PTR(str)) return Qnil; - if (enc==rb_utf8_encoding() && argc>0) { /* :lithuanian can temporarily be used for new functionality without options */ + if (enc==rb_utf8_encoding()) { str_shared_replace(str, rb_str_casemap(str, &flags, enc)); modify = ONIGENC_CASE_MODIFIED & flags; } @@ -6166,7 +6170,7 @@ rb_str_swapcase_bang(int argc, VALUE *argv, VALUE str) enc = STR_ENC_GET(str); rb_str_check_dummy_enc(enc); s = RSTRING_PTR(str); send = RSTRING_END(str); - if (enc==rb_utf8_encoding() && argc>0) { /* :lithuanian can temporarily be used for new functionality without options */ + if (enc==rb_utf8_encoding()) { str_shared_replace(str, rb_str_casemap(str, &flags, enc)); modify = ONIGENC_CASE_MODIFIED & flags; } |