diff options
Diffstat (limited to 'mrbgems/mruby-string-ext')
| -rw-r--r-- | mrbgems/mruby-string-ext/mrblib/string.rb | 14 | ||||
| -rw-r--r-- | mrbgems/mruby-string-ext/src/string.c | 228 | ||||
| -rw-r--r-- | mrbgems/mruby-string-ext/test/numeric.rb | 29 | ||||
| -rw-r--r-- | mrbgems/mruby-string-ext/test/range.rb | 26 | ||||
| -rw-r--r-- | mrbgems/mruby-string-ext/test/string.rb | 155 |
5 files changed, 322 insertions, 130 deletions
diff --git a/mrbgems/mruby-string-ext/mrblib/string.rb b/mrbgems/mruby-string-ext/mrblib/string.rb index 2a323c858..e57d75355 100644 --- a/mrbgems/mruby-string-ext/mrblib/string.rb +++ b/mrbgems/mruby-string-ext/mrblib/string.rb @@ -93,7 +93,7 @@ class String # "hello".rstrip! #=> nil # def rstrip! - raise RuntimeError, "can't modify frozen String" if frozen? + raise FrozenError, "can't modify frozen String" if frozen? s = self.rstrip (s == self) ? nil : self.replace(s) end @@ -310,11 +310,15 @@ class String end end + ## + # Call the given block for each character of + # +self+. def each_char(&block) return to_enum :each_char unless block - - split('').each do |i| - block.call(i) + pos = 0 + while pos < self.size + block.call(self[pos]) + pos += 1 end self end @@ -410,7 +414,7 @@ class String e = max.ord while c <= e break if exclusive and c == e - yield c.chr + yield c.chr(__ENCODING__) c += 1 end return self diff --git a/mrbgems/mruby-string-ext/src/string.c b/mrbgems/mruby-string-ext/src/string.c index ba7e3c610..e3b8d9960 100644 --- a/mrbgems/mruby-string-ext/src/string.c +++ b/mrbgems/mruby-string-ext/src/string.c @@ -5,6 +5,91 @@ #include <mruby/string.h> #include <mruby/range.h> +#define ENC_ASCII_8BIT "ASCII-8BIT" +#define ENC_BINARY "BINARY" +#define ENC_UTF8 "UTF-8" + +#define ENC_COMP_P(enc, enc_lit) \ + str_casecmp_p(RSTRING_PTR(enc), RSTRING_LEN(enc), enc_lit, sizeof(enc_lit"")-1) + +#ifdef MRB_WITHOUT_FLOAT +# define mrb_float_p(o) FALSE +#endif + +static mrb_bool +str_casecmp_p(const char *s1, mrb_int len1, const char *s2, mrb_int len2) +{ + const char *e1, *e2; + + if (len1 != len2) return FALSE; + e1 = s1 + len1; + e2 = s2 + len2; + while (s1 < e1 && s2 < e2) { + if (*s1 != *s2 && TOUPPER(*s1) != TOUPPER(*s2)) return FALSE; + ++s1; + ++s2; + } + return TRUE; +} + +static mrb_value +int_chr_binary(mrb_state *mrb, mrb_value num) +{ + mrb_int cp = mrb_int(mrb, num); + char c; + mrb_value str; + + if (cp < 0 || 0xff < cp) { + mrb_raisef(mrb, E_RANGE_ERROR, "%v out of char range", num); + } + c = (char)cp; + str = mrb_str_new(mrb, &c, 1); + RSTR_SET_ASCII_FLAG(mrb_str_ptr(str)); + return str; +} + +#ifdef MRB_UTF8_STRING +static mrb_value +int_chr_utf8(mrb_state *mrb, mrb_value num) +{ + mrb_int cp = mrb_int(mrb, num); + char utf8[4]; + mrb_int len; + mrb_value str; + uint32_t ascii_flag = 0; + + if (cp < 0 || 0x10FFFF < cp) { + mrb_raisef(mrb, E_RANGE_ERROR, "%v out of char range", num); + } + if (cp < 0x80) { + utf8[0] = (char)cp; + len = 1; + ascii_flag = MRB_STR_ASCII; + } + else if (cp < 0x800) { + utf8[0] = (char)(0xC0 | (cp >> 6)); + utf8[1] = (char)(0x80 | (cp & 0x3F)); + len = 2; + } + else if (cp < 0x10000) { + utf8[0] = (char)(0xE0 | (cp >> 12)); + utf8[1] = (char)(0x80 | ((cp >> 6) & 0x3F)); + utf8[2] = (char)(0x80 | ( cp & 0x3F)); + len = 3; + } + else { + utf8[0] = (char)(0xF0 | (cp >> 18)); + utf8[1] = (char)(0x80 | ((cp >> 12) & 0x3F)); + utf8[2] = (char)(0x80 | ((cp >> 6) & 0x3F)); + utf8[3] = (char)(0x80 | ( cp & 0x3F)); + len = 4; + } + str = mrb_str_new(mrb, utf8, len); + mrb_str_ptr(str)->flags |= ascii_flag; + return str; +} +#endif + static mrb_value mrb_str_getbyte(mrb_state *mrb, mrb_value str) { @@ -29,7 +114,7 @@ mrb_str_setbyte(mrb_state *mrb, mrb_value str) len = RSTRING_LEN(str); if (pos < -len || len <= pos) - mrb_raisef(mrb, E_INDEX_ERROR, "index %S is out of array", mrb_fixnum_value(pos)); + mrb_raisef(mrb, E_INDEX_ERROR, "index %i out of string", pos); if (pos < 0) pos += len; @@ -42,44 +127,31 @@ mrb_str_setbyte(mrb_state *mrb, mrb_value str) static mrb_value mrb_str_byteslice(mrb_state *mrb, mrb_value str) { - mrb_value a1; - mrb_int len; + mrb_value a1, a2; + mrb_int str_len = RSTRING_LEN(str), beg, len; + mrb_bool empty = TRUE; - if (mrb_get_argc(mrb) == 2) { - mrb_int pos; - mrb_get_args(mrb, "ii", &pos, &len); - return mrb_str_substr(mrb, str, pos, len); + if (mrb_get_args(mrb, "o|o", &a1, &a2) == 2) { + beg = mrb_fixnum(mrb_to_int(mrb, a1)); + len = mrb_fixnum(mrb_to_int(mrb, a2)); } - mrb_get_args(mrb, "o|i", &a1, &len); - switch (mrb_type(a1)) { - case MRB_TT_RANGE: - { - mrb_int beg; - - len = RSTRING_LEN(str); - switch (mrb_range_beg_len(mrb, a1, &beg, &len, len, TRUE)) { - case 0: /* not range */ - break; - case 1: /* range */ - return mrb_str_substr(mrb, str, beg, len); - case 2: /* out of range */ - mrb_raisef(mrb, E_RANGE_ERROR, "%S out of range", a1); - break; - } + else if (mrb_type(a1) == MRB_TT_RANGE) { + if (mrb_range_beg_len(mrb, a1, &beg, &len, str_len, TRUE) != MRB_RANGE_OK) { return mrb_nil_value(); } -#ifndef MRB_WITHOUT_FLOAT - case MRB_TT_FLOAT: - a1 = mrb_fixnum_value((mrb_int)mrb_float(a1)); - /* fall through */ -#endif - case MRB_TT_FIXNUM: - return mrb_str_substr(mrb, str, mrb_fixnum(a1), 1); - default: - mrb_raise(mrb, E_TYPE_ERROR, "wrong type of argument"); } - /* not reached */ - return mrb_nil_value(); + else { + beg = mrb_fixnum(mrb_to_int(mrb, a1)); + len = 1; + empty = FALSE; + } + + if (mrb_str_beg_len(str_len, &beg, &len) && (empty || len != 0)) { + return mrb_str_byte_subseq(mrb, str, beg, len); + } + else { + return mrb_nil_value(); + } } /* @@ -137,8 +209,6 @@ mrb_str_swapcase(mrb_state *mrb, mrb_value self) return str; } -static mrb_value mrb_fixnum_chr(mrb_state *mrb, mrb_value num); - /* * call-seq: * str << integer -> str @@ -148,7 +218,8 @@ static mrb_value mrb_fixnum_chr(mrb_state *mrb, mrb_value num); * * Append---Concatenates the given object to <i>str</i>. If the object is a * <code>Integer</code>, it is considered as a codepoint, and is converted - * to a character before concatenation. + * to a character before concatenation + * (equivalent to <code>str.concat(integer.chr(__ENCODING__))</code>). * * a = "hello " * a << "world" #=> "hello world" @@ -160,8 +231,12 @@ mrb_str_concat_m(mrb_state *mrb, mrb_value self) mrb_value str; mrb_get_args(mrb, "o", &str); - if (mrb_fixnum_p(str)) - str = mrb_fixnum_chr(mrb, str); + if (mrb_fixnum_p(str) || mrb_float_p(str)) +#ifdef MRB_UTF8_STRING + str = int_chr_utf8(mrb, str); +#else + str = int_chr_binary(mrb, str); +#endif else str = mrb_ensure_string_type(mrb, str); mrb_str_concat(mrb, self, str); @@ -507,8 +582,7 @@ str_tr(mrb_state *mrb, mrb_value str, mrb_value p1, mrb_value p2, mrb_bool squee continue; } if (c > 0x80) { - mrb_raisef(mrb, E_ARGUMENT_ERROR, "character (%S) out of range", - mrb_fixnum_value((mrb_int)c)); + mrb_raisef(mrb, E_ARGUMENT_ERROR, "character (%i) out of range", c); } lastch = c; s[i] = (char)c; @@ -812,7 +886,7 @@ mrb_str_count(mrb_state *mrb, mrb_value str) tr_parse_pattern(mrb, &pat, v_pat, TRUE); tr_compile_pattern(&pat, v_pat, bitmap); tr_free_pattern(mrb, &pat); - + s = RSTRING_PTR(str); len = RSTRING_LEN(str); for (i = 0; i < len; i++) { @@ -848,49 +922,42 @@ mrb_str_chr(mrb_state *mrb, mrb_value self) return mrb_str_substr(mrb, self, 0, 1); } +/* + * call-seq: + * int.chr([encoding]) -> string + * + * Returns a string containing the character represented by the +int+'s value + * according to +encoding+. +"ASCII-8BIT"+ (+"BINARY"+) and +"UTF-8"+ (only + * with +MRB_UTF8_STRING+) can be specified as +encoding+ (default is + * +"ASCII-8BIT"+). + * + * 65.chr #=> "A" + * 230.chr #=> "\xE6" + * 230.chr("ASCII-8BIT") #=> "\xE6" + * 230.chr("UTF-8") #=> "\u00E6" + */ static mrb_value -mrb_fixnum_chr(mrb_state *mrb, mrb_value num) +mrb_int_chr(mrb_state *mrb, mrb_value num) { - mrb_int cp = mrb_fixnum(num); -#ifdef MRB_UTF8_STRING - char utf8[4]; - mrb_int len; - - if (cp < 0 || 0x10FFFF < cp) { - mrb_raisef(mrb, E_RANGE_ERROR, "%S out of char range", num); - } - if (cp < 0x80) { - utf8[0] = (char)cp; - len = 1; - } - else if (cp < 0x800) { - utf8[0] = (char)(0xC0 | (cp >> 6)); - utf8[1] = (char)(0x80 | (cp & 0x3F)); - len = 2; + mrb_value enc; + mrb_bool enc_given; + + mrb_get_args(mrb, "|S?", &enc, &enc_given); + if (!enc_given || + ENC_COMP_P(enc, ENC_ASCII_8BIT) || + ENC_COMP_P(enc, ENC_BINARY)) { + return int_chr_binary(mrb, num); } - else if (cp < 0x10000) { - utf8[0] = (char)(0xE0 | (cp >> 12)); - utf8[1] = (char)(0x80 | ((cp >> 6) & 0x3F)); - utf8[2] = (char)(0x80 | ( cp & 0x3F)); - len = 3; +#ifdef MRB_UTF8_STRING + else if (ENC_COMP_P(enc, ENC_UTF8)) { + return int_chr_utf8(mrb, num); } +#endif else { - utf8[0] = (char)(0xF0 | (cp >> 18)); - utf8[1] = (char)(0x80 | ((cp >> 12) & 0x3F)); - utf8[2] = (char)(0x80 | ((cp >> 6) & 0x3F)); - utf8[3] = (char)(0x80 | ( cp & 0x3F)); - len = 4; - } - return mrb_str_new(mrb, utf8, len); -#else - char c; - - if (cp < 0 || 0xff < cp) { - mrb_raisef(mrb, E_RANGE_ERROR, "%S out of char range", num); + mrb_raisef(mrb, E_ARGUMENT_ERROR, "unknown encoding name - %v", enc); } - c = (char)cp; - return mrb_str_new(mrb, &c, 1); -#endif + /* not reached */ + return mrb_nil_value(); } /* @@ -1231,7 +1298,8 @@ mrb_mruby_string_ext_gem_init(mrb_state* mrb) mrb_define_method(mrb, s, "delete_suffix", mrb_str_del_suffix, MRB_ARGS_REQ(1)); mrb_define_method(mrb, s, "__lines", mrb_str_lines, MRB_ARGS_NONE()); - mrb_define_method(mrb, mrb->fixnum_class, "chr", mrb_fixnum_chr, MRB_ARGS_NONE()); + + mrb_define_method(mrb, mrb_module_get(mrb, "Integral"), "chr", mrb_int_chr, MRB_ARGS_OPT(1)); } void diff --git a/mrbgems/mruby-string-ext/test/numeric.rb b/mrbgems/mruby-string-ext/test/numeric.rb new file mode 100644 index 000000000..dfcb9ebf4 --- /dev/null +++ b/mrbgems/mruby-string-ext/test/numeric.rb @@ -0,0 +1,29 @@ +# coding: utf-8 + +assert('Integer#chr') do + assert_equal("A", 65.chr) + assert_equal("B", 0x42.chr) + assert_equal("\xab", 171.chr) + assert_raise(RangeError) { -1.chr } + assert_raise(RangeError) { 256.chr } + + assert_equal("A", 65.chr("ASCII-8BIT")) + assert_equal("B", 0x42.chr("BINARY")) + assert_equal("\xab", 171.chr("ascii-8bit")) + assert_raise(RangeError) { -1.chr("binary") } + assert_raise(RangeError) { 256.chr("Ascii-8bit") } + assert_raise(ArgumentError) { 65.chr("ASCII") } + assert_raise(ArgumentError) { 65.chr("ASCII-8BIT", 2) } + assert_raise(TypeError) { 65.chr(:BINARY) } + + if __ENCODING__ == "ASCII-8BIT" + assert_raise(ArgumentError) { 65.chr("UTF-8") } + else + assert_equal("A", 65.chr("UTF-8")) + assert_equal("B", 0x42.chr("UTF-8")) + assert_equal("«", 171.chr("utf-8")) + assert_equal("あ", 12354.chr("Utf-8")) + assert_raise(RangeError) { -1.chr("utf-8") } + assert_raise(RangeError) { 0x110000.chr.chr("UTF-8") } + end +end diff --git a/mrbgems/mruby-string-ext/test/range.rb b/mrbgems/mruby-string-ext/test/range.rb new file mode 100644 index 000000000..80c286850 --- /dev/null +++ b/mrbgems/mruby-string-ext/test/range.rb @@ -0,0 +1,26 @@ +assert('Range#max') do + # returns the maximum value in the range when called with no arguments + assert_equal 'l', ('f'..'l').max + assert_equal 'e', ('a'...'f').max + + # returns nil when the endpoint is less than the start point + assert_equal nil, ('z'..'l').max +end + +assert('Range#max given a block') do + # returns nil when the endpoint is less than the start point + assert_equal nil, (('z'..'l').max { |x, y| x <=> y }) +end + +assert('Range#min') do + # returns the minimum value in the range when called with no arguments + assert_equal 'f', ('f'..'l').min + + # returns nil when the start point is greater than the endpoint + assert_equal nil, ('z'..'l').min +end + +assert('Range#min given a block') do + # returns nil when the start point is greater than the endpoint + assert_equal nil, (('z'..'l').min { |x, y| x <=> y }) +end diff --git a/mrbgems/mruby-string-ext/test/string.rb b/mrbgems/mruby-string-ext/test/string.rb index 7c96ab694..8f1d25f29 100644 --- a/mrbgems/mruby-string-ext/test/string.rb +++ b/mrbgems/mruby-string-ext/test/string.rb @@ -2,7 +2,7 @@ ## # String(Ext) Test -UTF8STRING = ("\343\201\202".size == 1) +UTF8STRING = __ENCODING__ == "UTF-8" assert('String#getbyte') do str1 = "hello" @@ -26,69 +26,130 @@ end assert('String#byteslice') do str1 = "hello" + str2 = "\u3042ab" # "\xE3\x81\x82ab" + + assert_equal("h", str1.byteslice(0)) assert_equal("e", str1.byteslice(1)) + assert_equal(nil, str1.byteslice(5)) assert_equal("o", str1.byteslice(-1)) + assert_equal(nil, str1.byteslice(-6)) + assert_equal("\xE3", str2.byteslice(0)) + assert_equal("\x81", str2.byteslice(1)) + assert_equal(nil, str2.byteslice(5)) + assert_equal("b", str2.byteslice(-1)) + assert_equal(nil, str2.byteslice(-6)) + + assert_equal("", str1.byteslice(0, 0)) + assert_equal(str1, str1.byteslice(0, 6)) + assert_equal("el", str1.byteslice(1, 2)) + assert_equal("", str1.byteslice(5, 1)) + assert_equal("o", str1.byteslice(-1, 6)) + assert_equal(nil, str1.byteslice(-6, 1)) + assert_equal(nil, str1.byteslice(0, -1)) + assert_equal("", str2.byteslice(0, 0)) + assert_equal(str2, str2.byteslice(0, 6)) + assert_equal("\x81\x82", str2.byteslice(1, 2)) + assert_equal("", str2.byteslice(5, 1)) + assert_equal("b", str2.byteslice(-1, 6)) + assert_equal(nil, str2.byteslice(-6, 1)) + assert_equal(nil, str2.byteslice(0, -1)) + assert_equal("ell", str1.byteslice(1..3)) assert_equal("el", str1.byteslice(1...3)) + assert_equal("h", str1.byteslice(0..0)) + assert_equal("", str1.byteslice(5..0)) + assert_equal("o", str1.byteslice(4..5)) + assert_equal(nil, str1.byteslice(6..0)) + assert_equal("", str1.byteslice(-1..0)) + assert_equal("llo", str1.byteslice(-3..5)) + assert_equal("\x81\x82a", str2.byteslice(1..3)) + assert_equal("\x81\x82", str2.byteslice(1...3)) + assert_equal("\xE3", str2.byteslice(0..0)) + assert_equal("", str2.byteslice(5..0)) + assert_equal("b", str2.byteslice(4..5)) + assert_equal(nil, str2.byteslice(6..0)) + assert_equal("", str2.byteslice(-1..0)) + assert_equal("\x82ab", str2.byteslice(-3..5)) + + assert_raise(ArgumentError) { str1.byteslice } + assert_raise(ArgumentError) { str1.byteslice(1, 2, 3) } + assert_raise(TypeError) { str1.byteslice("1") } + assert_raise(TypeError) { str1.byteslice("1", 2) } + assert_raise(TypeError) { str1.byteslice(1, "2") } + assert_raise(TypeError) { str1.byteslice(1..2, 3) } + + skip unless Object.const_defined?(:Float) + assert_equal("o", str1.byteslice(4.0)) + assert_equal("\x82ab", str2.byteslice(2.0, 3.0)) end assert('String#dump') do - ("\1" * 100).dump # should not raise an exception - regress #1210 - "\0".inspect == "\"\\000\"" and - "foo".dump == "\"foo\"" + assert_equal("\"\\x00\"", "\0".dump) + assert_equal("\"foo\"", "foo".dump) + assert_nothing_raised { ("\1" * 100).dump } # regress #1210 end assert('String#strip') do s = " abc " - "".strip == "" and " \t\r\n\f\v".strip == "" and - "\0a\0".strip == "\0a" and - "abc".strip == "abc" and - " abc".strip == "abc" and - "abc ".strip == "abc" and - " abc ".strip == "abc" and - s == " abc " + assert_equal("abc", s.strip) + assert_equal(" abc ", s) + assert_equal("", "".strip) + assert_equal("", " \t\r\n\f\v".strip) + assert_equal("\0a", "\0a\0".strip) + assert_equal("abc", "abc".strip) + assert_equal("abc", " abc".strip) + assert_equal("abc", "abc ".strip) end assert('String#lstrip') do s = " abc " - s.lstrip - "".lstrip == "" and " \t\r\n\f\v".lstrip == "" and - "\0a\0".lstrip == "\0a\0" and - "abc".lstrip == "abc" and - " abc".lstrip == "abc" and - "abc ".lstrip == "abc " and - " abc ".lstrip == "abc " and - s == " abc " + assert_equal("abc ", s.lstrip) + assert_equal(" abc ", s) + assert_equal("", "".lstrip) + assert_equal("", " \t\r\n\f\v".lstrip) + assert_equal("\0a\0", "\0a\0".lstrip) + assert_equal("abc", "abc".lstrip) + assert_equal("abc", " abc".lstrip) + assert_equal("abc ", "abc ".lstrip) end assert('String#rstrip') do s = " abc " - s.rstrip - "".rstrip == "" and " \t\r\n\f\v".rstrip == "" and - "\0a\0".rstrip == "\0a" and - "abc".rstrip == "abc" and - " abc".rstrip == " abc" and - "abc ".rstrip == "abc" and - " abc ".rstrip == " abc" and - s == " abc " + assert_equal(" abc", s.rstrip) + assert_equal(" abc ", s) + assert_equal("", "".rstrip) + assert_equal("", " \t\r\n\f\v".rstrip) + assert_equal("\0a", "\0a\0".rstrip) + assert_equal("abc", "abc".rstrip) + assert_equal(" abc", " abc".rstrip) + assert_equal("abc", "abc ".rstrip) end assert('String#strip!') do s = " abc " t = "abc" - s.strip! == "abc" and s == "abc" and t.strip! == nil + assert_equal("abc", s.strip!) + assert_equal("abc", s) + assert_nil(t.strip!) + assert_equal("abc", t) end assert('String#lstrip!') do s = " abc " t = "abc " - s.lstrip! == "abc " and s == "abc " and t.lstrip! == nil + assert_equal("abc ", s.lstrip!) + assert_equal("abc ", s) + assert_nil(t.lstrip!) + assert_equal("abc ", t) end assert('String#rstrip!') do s = " abc " t = " abc" - s.rstrip! == " abc" and s == " abc" and t.rstrip! == nil + assert_equal(" abc", s.rstrip!) + assert_equal(" abc", s) + assert_nil(t.rstrip!) + assert_equal(" abc", t) end assert('String#swapcase') do @@ -106,8 +167,15 @@ end assert('String#concat') do assert_equal "Hello World!", "Hello " << "World" << 33 assert_equal "Hello World!", "Hello ".concat("World").concat(33) - assert_raise(TypeError) { "".concat(Object.new) } + + if UTF8STRING + assert_equal "H«", "H" << 0xab + assert_equal "Hは", "H" << 12399 + else + assert_equal "H\xab", "H" << 0xab + assert_raise(RangeError) { "H" << 12399 } + end end assert('String#casecmp') do @@ -127,7 +195,7 @@ assert('String#count') do assert_equal 4, s.count("a0-9") end -assert('String#tr') do +assert('String#tr') do assert_equal "ABC", "abc".tr('a-z', 'A-Z') assert_equal "hippo", "hello".tr('el', 'ip') assert_equal "Ruby", "Lisp".tr("Lisp", "Ruby") @@ -141,7 +209,7 @@ assert('String#tr!') do assert_equal "ab12222hijklmnopqR", s end -assert('String#tr_s') do +assert('String#tr_s') do assert_equal "hero", "hello".tr_s('l', 'r') assert_equal "h*o", "hello".tr_s('el', '*') assert_equal "hhxo", "hello".tr_s('el', 'hx') @@ -237,12 +305,6 @@ assert('String#oct') do assert_equal (-8), "-10".oct end -assert('String#chr') do - assert_equal "a", "abcde".chr - # test Fixnum#chr as well - assert_equal "a", 97.chr -end - assert('String#lines') do assert_equal ["Hel\n", "lo\n", "World!"], "Hel\nlo\nWorld!".lines assert_equal ["Hel\n", "lo\n", "World!\n"], "Hel\nlo\nWorld!\n".lines @@ -620,8 +682,11 @@ assert('String#ord(UTF-8)') do end if UTF8STRING assert('String#chr') do + assert_equal "a", "abcde".chr assert_equal "h", "hello!".chr + assert_equal "", "".chr end + assert('String#chr(UTF-8)') do assert_equal "こ", "こんにちは世界!".chr end if UTF8STRING @@ -647,19 +712,19 @@ assert('String#chars(UTF-8)') do end if UTF8STRING assert('String#each_char') do - s = "" + chars = [] "hello!".each_char do |x| - s += x + chars << x end - assert_equal "hello!", s + assert_equal ["h", "e", "l", "l", "o", "!"], chars end assert('String#each_char(UTF-8)') do - s = "" + chars = [] "こんにちは世界!".each_char do |x| - s += x + chars << x end - assert_equal "こんにちは世界!", s + assert_equal ["こ", "ん", "に", "ち", "は", "世", "界", "!"], chars end if UTF8STRING assert('String#codepoints') do |