diff options
-rw-r--r-- | ChangeLog | 8 | ||||
-rw-r--r-- | string.c | 36 | ||||
-rw-r--r-- | test/ruby/enc/test_case_comprehensive.rb | 8 |
3 files changed, 21 insertions, 31 deletions
@@ -1,11 +1,3 @@ -Tue May 31 10:10:03 2016 Martin Duerst <duerst@it.aoyama.ac.jp> - - * string.c: Activate full Unicode case mapping for UTF-8 by removing - the protective check for the presence of an option. - Update documentation. - - * test/ruby/enc/test_case_comprehensive.rb: Adjust tests for above change. - Tue May 31 00:30:11 2016 NAKAMURA Usaku <usa@ruby-lang.org> * ext/socket/raddrinfo.c (host_str, port_str): Use StringValueCStr @@ -5850,7 +5850,7 @@ 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()) { + if (enc==rb_utf8_encoding() && argc>0) { /* :lithuanian can temporarily be used for new functionality without options */ str_shared_replace(str, rb_str_casemap(str, &flags, enc)); modify = ONIGENC_CASE_MODIFIED & flags; } @@ -5940,7 +5940,7 @@ 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()) { + if (enc==rb_utf8_encoding() && argc>0) { /* :lithuanian can temporarily be used for new functionality without options */ str_shared_replace(str, rb_str_casemap(str, &flags, enc)); modify = ONIGENC_CASE_MODIFIED & flags; } @@ -5999,11 +5999,11 @@ rb_str_downcase_bang(int argc, VALUE *argv, VALUE str) * The meaning of the +options+ is as follows: * * No option :: - * Full Unicode case mapping, suitable for most languages - * (see :turkic and :lithuanian options below for exceptions) + * 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. * :ascii :: - * Only the ASCII region, i.e. the characters ``A'' to ``Z'' and - * ``a'' to ``z'', are affected. + * Only the ASCII region, i.e. the characters ``A'' to ``Z'', are affected. * This option cannot be combined with any other option. * :turkic :: * Full Unicode case mapping, adapted for Turkic languages @@ -6012,23 +6012,21 @@ 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 is an accent on top). + * i even if there's an accent on top). * :fold :: - * 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. we do not currenty implement a variant for turkic languages). + * 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). * * 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), 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. + * (neither in characters nor in bytes), and some roundtrip assumptions + * (e.g. str.downcase == str.downcase.upcase.downcase) may not apply. * - * Non-ASCII case mapping/folding is currently only supported for UTF-8 - * Strings/Symbols, but this support will be extended to other encodings. + * 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. * * "hEllO".downcase #=> "hello" */ @@ -6073,7 +6071,7 @@ 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()) { + if (enc==rb_utf8_encoding() && argc>0) { /* :lithuanian can temporarily be used for new functionality without options */ str_shared_replace(str, rb_str_casemap(str, &flags, enc)); modify = ONIGENC_CASE_MODIFIED & flags; } @@ -6149,7 +6147,7 @@ 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()) { + if (enc==rb_utf8_encoding() && argc>0) { /* :lithuanian can temporarily be used for new functionality without options */ str_shared_replace(str, rb_str_casemap(str, &flags, enc)); modify = ONIGENC_CASE_MODIFIED & flags; } diff --git a/test/ruby/enc/test_case_comprehensive.rb b/test/ruby/enc/test_case_comprehensive.rb index 7f7a2d10b9..da2354f4b9 100644 --- a/test/ruby/enc/test_case_comprehensive.rb +++ b/test/ruby/enc/test_case_comprehensive.rb @@ -78,10 +78,10 @@ class TestComprehensiveCaseFold < Test::Unit::TestCase end tests = [ - CaseTest.new(:downcase, [], downcase), - CaseTest.new(:upcase, [], upcase), - CaseTest.new(:capitalize, [], titlecase, downcase), - # @@@@ TODO: figure out how to test swapcase + CaseTest.new(:downcase, [:lithuanian], downcase), + CaseTest.new(:upcase, [:lithuanian], upcase), + CaseTest.new(:capitalize, [:lithuanian], titlecase, downcase), + # swapcase?????!!!!! CaseTest.new(:downcase, [:fold], casefold), CaseTest.new(:upcase, [:turkic], turkic_upcase), CaseTest.new(:downcase, [:turkic], turkic_downcase), |