icu4r 0.1.3.2006.01.26
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/MIT-LICENSE +20 -0
- data/README +153 -0
- data/calendar.c +576 -0
- data/docs/FORMATTING +131 -0
- data/docs/UNICODE_REGEXPS +204 -0
- data/extconf.rb +15 -0
- data/fmt.cpp +150 -0
- data/icu4r.c +14 -0
- data/icu_common.h +45 -0
- data/samples/demo_each.rb +23 -0
- data/samples/demo_locales.rb +16 -0
- data/samples/demo_regexp.rb +11 -0
- data/samples/resbundle/appmsg/root.res +0 -0
- data/samples/resbundle/appmsg/ru.res +0 -0
- data/samples/resbundle/demo_bundle.rb +4 -0
- data/samples/resbundle/mkres.sh +4 -0
- data/samples/resbundle/root.txt +10 -0
- data/samples/resbundle/ru.txt +4 -0
- data/test/test_calendar.rb +109 -0
- data/test/test_ustring.rb +381 -0
- data/tools/doc.sh +2 -0
- data/tools/km.rb +425 -0
- data/ubundle.c +209 -0
- data/ucore_ext.c +168 -0
- data/uregex.c +673 -0
- data/uregex.h +27 -0
- data/ustring.c +3042 -0
- metadata +81 -0
@@ -0,0 +1,204 @@
|
|
1
|
+
This is one-stop reference on Unicode regular expressions syntax, available in ICU.
|
2
|
+
This text is compiled from several sources in ICU userguide and code docs.
|
3
|
+
|
4
|
+
=== Regular Expression Metacharacters
|
5
|
+
|
6
|
+
Character Description
|
7
|
+
\a Match a BELL, \u0007
|
8
|
+
\A Match at the beginning of the input. Differs from ^ in that \A will not match after a new line within the input.
|
9
|
+
\b, outside of a [Set] Match if the current position is a word boundary. Boundaries occur
|
10
|
+
at the transitions between word (\w) and non-word (\W) characters,
|
11
|
+
with combining marks ignored. For better word boundaries, see ICU Boundary Analysis .
|
12
|
+
\b, within a [Set] Match a BACKSPACE, \u0008.
|
13
|
+
\B Match if the current position is not a word boundary.
|
14
|
+
\cX Match a control-X character.
|
15
|
+
\d Match any character with the Unicode General Category of Nd (Number, Decimal Digit.)
|
16
|
+
\D Match any character that is not a decimal digit.
|
17
|
+
\e Match an ESCAPE, \u001B.
|
18
|
+
\E Terminates a \Q ... \E quoted sequence.
|
19
|
+
\f Match a FORM FEED, \u000C.
|
20
|
+
\G Match if the current position is at the end of the previous match.
|
21
|
+
\n Match a LINE FEED, \u000A.
|
22
|
+
\N{UNICODE CHARACTER NAME} Match the named character.
|
23
|
+
\p{UNICODE PROPERTY NAME} Match any character with the specified Unicode Property.
|
24
|
+
\P{UNICODE PROPERTY NAME} Match any character not having the specified Unicode Property.
|
25
|
+
\Q Quotes all following characters until \E.
|
26
|
+
\r Match a CARRIAGE RETURN, \u000D.
|
27
|
+
\s Match a white space character. White space is defined as [\t\n\f\r\p{Z}].
|
28
|
+
\S Match a non-white space character.
|
29
|
+
\t Match a HORIZONTAL TABULATION, \u0009.
|
30
|
+
\uhhhh Match the character with the hex value hhhh.
|
31
|
+
\Uhhhhhhhh Match the character with the hex value hhhhhhhh. Exactly eight hex digits must be
|
32
|
+
provided, even though the largest Unicode code point is \U0010ffff.
|
33
|
+
\w Match a word character. Word characters are [\p{Ll}\p{Lu}\p{Lt}\p{Lo}\p{Nd}].
|
34
|
+
\W Match a non-word character.
|
35
|
+
\x{hhhh} Match the character with hex value hhhh. From one to six hex digits may be supplied.
|
36
|
+
\xhh Match the character with two digit hex value hh
|
37
|
+
\X Match a Grapheme Cluster .
|
38
|
+
\Z Match if the current position is at the end of input, but before the final line terminator, if one exists.
|
39
|
+
\z Match if the current position is at the end of input.
|
40
|
+
\n Back Reference. Match whatever the nth capturing group matched. n must be a number > 1 and < total number
|
41
|
+
of capture groups in the pattern. Note: Octal escapes, such as \012, are not supported in ICU regular expressions
|
42
|
+
[pattern] Match any one character from the set. See UnicodeSet for a full description of what may appear in the pattern
|
43
|
+
. Match any character.
|
44
|
+
^ Match at the beginning of a line.
|
45
|
+
$ Match at the end of a line.
|
46
|
+
\ Quotes the following character. Characters that must be quoted to be treated as literals are * ? + [ ( ) { } ^ $ | \ . /
|
47
|
+
|
48
|
+
=== Regular Expression Operators
|
49
|
+
|
50
|
+
Operator Description
|
51
|
+
| Alternation. A|B matches either A or B.
|
52
|
+
* Match 0 or more times. Match as many times as possible.
|
53
|
+
+ Match 1 or more times. Match as many times as possible.
|
54
|
+
? Match zero or one times. Prefer one.
|
55
|
+
{n} Match exactly n times
|
56
|
+
{n,} Match at least n times. Match as many times as possible.
|
57
|
+
{n,m} Match between n and m times. Match as many times as possible, but not more than m.
|
58
|
+
*? Match 0 or more times. Match as few times as possible.
|
59
|
+
+? Match 1 or more times. Match as few times as possible.
|
60
|
+
?? Match zero or one times. Prefer zero.
|
61
|
+
{n}? Match exactly n times
|
62
|
+
{n,}? Match at least n times, but no more than required for an overall pattern match
|
63
|
+
{n,m}? Match between n and m times. Match as few times as possible, but not less than n.
|
64
|
+
*+ Match 0 or more times. Match as many times as possible when first encountered, do not retry with
|
65
|
+
fewer even if overall match fails (Possessive Match)
|
66
|
+
++ Match 1 or more times. Possessive match.
|
67
|
+
?+ Match zero or one times. Possessive match.
|
68
|
+
{n}+ Match exactly n times
|
69
|
+
{n,}+ Match at least n times. Possessive Match.
|
70
|
+
{n,m}+ Match between n and m times. Possessive Match.
|
71
|
+
( ... ) Capturing parentheses. Range of input that matched the parenthesized subexpression is
|
72
|
+
available after the match.
|
73
|
+
(?: ... ) Non-capturing parentheses. Groups the included pattern, but does not provide
|
74
|
+
capturing of matching text. Somewhat more efficient than capturing parentheses.
|
75
|
+
(?> ... ) Atomic-match parentheses. First match of the parenthesized subexpression is the only
|
76
|
+
one tried; if it does not lead to an overall pattern match, back up the search for a
|
77
|
+
match to a position before the "(?>"
|
78
|
+
(?# ... ) Free-format comment (?# comment ).
|
79
|
+
(?= ... ) Look-ahead assertion. True if the parenthesized pattern matches at the current input position,
|
80
|
+
but does not advance the input position.
|
81
|
+
(?! ... ) Negative look-ahead assertion. True if the parenthesized pattern does not match at the current
|
82
|
+
input position. Does not advance the input position.
|
83
|
+
(?<= ... ) Look-behind assertion. True if the parenthesized pattern matches text preceding the current
|
84
|
+
input position, with the last character of the match being the input character just before
|
85
|
+
the current position. Does not alter the input position. The length of possible strings matched
|
86
|
+
by the look-behind pattern must not be unbounded (no * or + operators.)
|
87
|
+
(?<! ... ) Negative Look-behind assertion. True if the parenthesized pattern does not
|
88
|
+
match text preceding the current input position, with the last character of the
|
89
|
+
match being the input character just before the current position. Does not alter
|
90
|
+
the input position. The length of possible strings matched by the look-behind pattern
|
91
|
+
must not be unbounded (no * or + operators.)
|
92
|
+
(?ismx-ismx: ... ) Flag settings. Evaluate the parenthesized expression with the specified flags enabled or -disabled.
|
93
|
+
(?ismx-ismx) Flag settings. Change the flag settings. Changes apply to the portion of the pattern
|
94
|
+
following the setting. For example, (?i) changes to a case insensitive match.
|
95
|
+
|
96
|
+
=== Replacement Text
|
97
|
+
|
98
|
+
The replacement text for find-and-replace operations may contain references to capture-group text from the find. References are of the form $n, where n is the number of the capture group.
|
99
|
+
|
100
|
+
Character Descriptions
|
101
|
+
$n The text of capture group n will be substituted for $n. n must be >= 0 and not
|
102
|
+
greater than the number of capture groups. A $ not followed by a digit has no special meaning,
|
103
|
+
and will appear in the substitution text as itself, a $.
|
104
|
+
\ Treat the following character as a literal, suppressing any special meaning. Backslash escaping in
|
105
|
+
substitution text is only required for '$' and '\', but may be used on any other character without bad effects.
|
106
|
+
|
107
|
+
=== UnicodeSet Pattern syntax
|
108
|
+
|
109
|
+
These patterns follow a syntax similar to that employed by version 8 regular expression character classes.
|
110
|
+
|
111
|
+
Here are some simple examples:
|
112
|
+
|
113
|
+
[] No characters
|
114
|
+
[a] The character 'a'
|
115
|
+
[ae] The characters 'a' and 'e'
|
116
|
+
[a-e] The characters 'a' through 'e' inclusive, in Unicode code point order
|
117
|
+
[\u4E01] The character U+4E01
|
118
|
+
[a{ab}{ac}] The character 'a' and the multicharacter strings "ab" and "ac"
|
119
|
+
[\p{Lu}] All characters in the general category Uppercase Letter
|
120
|
+
|
121
|
+
Any character may be preceded by a backslash in order to remove any special meaning.
|
122
|
+
White space characters, are ignored, unless they are escaped.
|
123
|
+
|
124
|
+
Property patterns specify a set of characters having a certain property as defined by the
|
125
|
+
Unicode standard. Both the POSIX-like "[:Lu:]" and the Perl-like syntax "\\p{Lu}" are recognized.
|
126
|
+
|
127
|
+
Patterns specify individual characters, ranges of characters, and Unicode property sets.
|
128
|
+
When elements are concatenated, they specify their union. To complement a set, place a '^'
|
129
|
+
immediately after the opening '['. Property patterns are inverted by modifying their delimiters;
|
130
|
+
"[:^foo]" and "\\P{foo}". In any other location, '^' has no special meaning.
|
131
|
+
|
132
|
+
Ranges are indicated by placing two a '-' between two characters, as in "a-z".
|
133
|
+
This specifies the range of all characters from the left to the right, in Unicode order.
|
134
|
+
If the left character is greater than or equal to the right character it is a syntax error.
|
135
|
+
If a '-' occurs as the first character after the opening '[' or '[^', or if it occurs as the
|
136
|
+
last character before the closing ']', then it is taken as a literal. Thus "[a\-b]", "[-ab]",
|
137
|
+
and "[ab-]" all indicate the same set of three characters, 'a', 'b', and '-'.
|
138
|
+
|
139
|
+
Sets may be intersected using the '&' operator or the asymmetric set difference may be taken using
|
140
|
+
the '-' operator, for example, "[[:L:]&[\\u0000-\\u0FFF]]" indicates the set of all
|
141
|
+
Unicode letters with values less than 4096. Operators ('&' and '|') have equal precedence
|
142
|
+
and bind left-to-right. Thus "[[:L:]-[a-z]-[\\u0100-\\u01FF]]" is equivalent to
|
143
|
+
"[[[:L:]-[a-z]]-[\\u0100-\\u01FF]]". This only really matters for difference; intersection
|
144
|
+
is commutative.
|
145
|
+
|
146
|
+
[a] The set containing 'a'
|
147
|
+
[a-z] The set containing 'a' through 'z' and all letters in between, in Unicode order
|
148
|
+
[^a-z] The set containing all characters but 'a' through 'z', that is, U+0000 through 'a'-1
|
149
|
+
and 'z'+1 through U+10FFFF
|
150
|
+
[[pat1][pat2]] The union of sets specified by pat1 and pat2
|
151
|
+
[[pat1]&[pat2]] The intersection of sets specified by pat1 and pat2
|
152
|
+
[[pat1]-[pat2]] The asymmetric difference of sets specified by pat1 and pat2
|
153
|
+
[:Lu:] or \p{Lu} The set of characters having the specified Unicode property; in this case, Unicode uppercase letters
|
154
|
+
[:^Lu:] or \P{Lu} The set of characters not having the given Unicode property
|
155
|
+
|
156
|
+
Warning: you cannot add an empty string ("") to a UnicodeSet.
|
157
|
+
|
158
|
+
Formal syntax
|
159
|
+
|
160
|
+
pattern := ('[' '^'? item* ']') | property
|
161
|
+
item := char | (char '-' char) | pattern-expr
|
162
|
+
pattern-expr := pattern | pattern-expr pattern | pattern-expr op pattern
|
163
|
+
op := '&' | '-'
|
164
|
+
special := '[' | ']' | '-'
|
165
|
+
char := any character that is not special | ('\' any character) | ('\u' hex hex hex hex)
|
166
|
+
hex := any character for which Character.digit(c, 16) returns a non-negative result
|
167
|
+
property := a Unicode property set pattern
|
168
|
+
|
169
|
+
Legend:
|
170
|
+
a := b a may be replaced by b
|
171
|
+
a? zero or one instance of a
|
172
|
+
a* one or more instances of a
|
173
|
+
a | b either a or b
|
174
|
+
'a' the literal string between the quotes
|
175
|
+
|
176
|
+
The C/POSIX character classes are also available in UnicodeSet patterns, using patterns like [:graph:] or \p{graph}.
|
177
|
+
|
178
|
+
alpha , lower , upper , punct , digit , xdigit, alnum , space , blank , cntrl , graph , print
|
179
|
+
|
180
|
+
=== General Categories
|
181
|
+
|
182
|
+
Lu = Letter, uppercase Mn = Mark, nonspacing Nd = Number, decimal digit
|
183
|
+
Ll = Letter, lowercase Mc = Mark, spacing combining Nl = Number, letter
|
184
|
+
Lt = Letter, titlecase Me = Mark, enclosing No = Number, other
|
185
|
+
Lm = Letter, modifier
|
186
|
+
Lo = Letter, other
|
187
|
+
|
188
|
+
Zs = Separator, space Cc = Other, control
|
189
|
+
Zl = Separator, line Cf = Other, format
|
190
|
+
Zp = Separator, paragraph Cs = Other, surrogate
|
191
|
+
Co = Other, private use
|
192
|
+
Cn = Other, not assigned (including noncharacters)
|
193
|
+
|
194
|
+
Pc = Punctuation, connector Sm = Symbol, math
|
195
|
+
Pd = Punctuation, dash Sc = Symbol, currency
|
196
|
+
Ps = Punctuation, open Sk = Symbol, modifier
|
197
|
+
Pe = Punctuation, close So = Symbol, other
|
198
|
+
Pi = Punctuation, initial quote (may behave like Ps or Pe depending on usage)
|
199
|
+
Pf = Punctuation, final quote (may behave like Ps or Pe depending on usage)
|
200
|
+
Po = Punctuation, other
|
201
|
+
|
202
|
+
|
203
|
+
See also http://www.unicode.org/Public/UNIDATA/PropertyAliases.txt and
|
204
|
+
http://www.unicode.org/Public/UNIDATA/PropertyValueAliases.txt for additional info.
|
data/extconf.rb
ADDED
@@ -0,0 +1,15 @@
|
|
1
|
+
require 'mkmf'
|
2
|
+
$LDFLAGS = "-licuuc -licui18n -licudata -lstdc++ "
|
3
|
+
$CFLAGS = "-Wall"
|
4
|
+
if !have_library('icui18n', 'u_init_3_4')
|
5
|
+
puts "ICU v3.4 required -- not found."
|
6
|
+
exit 1
|
7
|
+
end
|
8
|
+
create_makefile('icu4r')
|
9
|
+
File.open("Makefile", "a") << <<-EOT
|
10
|
+
|
11
|
+
check: $(DLLIB)
|
12
|
+
@$(RUBY) $(srcdir)/test/test_ustring.rb
|
13
|
+
@$(RUBY) $(srcdir)/test/test_calendar.rb
|
14
|
+
|
15
|
+
EOT
|
data/fmt.cpp
ADDED
@@ -0,0 +1,150 @@
|
|
1
|
+
#include "ruby.h"
|
2
|
+
#include "icu_common.h"
|
3
|
+
#include <unicode/msgfmt.h>
|
4
|
+
#include <unicode/translit.h>
|
5
|
+
#include <unicode/smpdtfmt.h>
|
6
|
+
#include <unicode/calendar.h>
|
7
|
+
#include <unicode/ucal.h>
|
8
|
+
/* This file contains various C-C++ wrappers, to ease my life
|
9
|
+
*/
|
10
|
+
extern "C" {
|
11
|
+
extern VALUE rb_cUString;
|
12
|
+
extern VALUE rb_cUCalendar;
|
13
|
+
extern VALUE icu_ustr_new(const UChar * str, long len);
|
14
|
+
extern VALUE icu_ustr_new_set(const UChar * str, long len, long capa);
|
15
|
+
|
16
|
+
VALUE icu_format(UChar * pattern, int32_t len, VALUE args, int32_t arg_len, char * locale)
|
17
|
+
{
|
18
|
+
Formattable * arguments = new Formattable[arg_len];
|
19
|
+
int i, is_set;
|
20
|
+
VALUE obj;
|
21
|
+
for(i = 0; i < arg_len; i++){
|
22
|
+
obj = rb_ary_entry(args,i);
|
23
|
+
is_set = 0;
|
24
|
+
switch(TYPE(obj)){
|
25
|
+
case T_FIXNUM:
|
26
|
+
case T_FLOAT:
|
27
|
+
arguments[i].setDouble(rb_num2dbl(obj));
|
28
|
+
is_set = 1;
|
29
|
+
break;
|
30
|
+
}
|
31
|
+
if(! is_set) {
|
32
|
+
if (CLASS_OF(obj) == rb_cUString) {
|
33
|
+
arguments[i].setString(UnicodeString(ICU_PTR(obj), ICU_LEN(obj)));
|
34
|
+
} else
|
35
|
+
if (CLASS_OF(obj) == rb_cTime) {
|
36
|
+
// ICU expects milliseconds since 01.01.1970
|
37
|
+
arguments[i].setDate(rb_num2dbl(rb_funcall(obj, rb_intern("to_f"), 0))*1000);
|
38
|
+
}
|
39
|
+
else {
|
40
|
+
delete [] arguments;
|
41
|
+
rb_raise(rb_eArgError, "wrong arg type: %s", rb_class2name(CLASS_OF(obj)));
|
42
|
+
}
|
43
|
+
}
|
44
|
+
}
|
45
|
+
UnicodeString patString(pattern,len);
|
46
|
+
UErrorCode status = U_ZERO_ERROR;
|
47
|
+
UnicodeString resultStr;
|
48
|
+
FieldPosition fieldPosition(0);
|
49
|
+
MessageFormat * fmt= new MessageFormat(patString,Locale(locale), status);
|
50
|
+
if( U_FAILURE(status) ){
|
51
|
+
rb_raise(rb_eArgError, "Can't format: %s", u_errorName(status));
|
52
|
+
}
|
53
|
+
fmt->format(arguments,arg_len,resultStr,fieldPosition,status);
|
54
|
+
if( U_FAILURE(status) ){
|
55
|
+
rb_raise(rb_eArgError, "Can't format: %s", u_errorName(status));
|
56
|
+
}
|
57
|
+
int32_t blen = resultStr.length();
|
58
|
+
UChar * buf = ALLOC_N(UChar, blen + 1);
|
59
|
+
resultStr.extract(buf, blen, status);
|
60
|
+
VALUE ret = icu_ustr_new( buf, blen);
|
61
|
+
free(buf);
|
62
|
+
delete[] arguments;
|
63
|
+
delete fmt;
|
64
|
+
return ret;
|
65
|
+
}
|
66
|
+
VALUE icu_date_parse(UChar * str, int32_t str_len, char * locale, UChar * val, int32_t len)
|
67
|
+
{
|
68
|
+
UErrorCode status = U_ZERO_ERROR;
|
69
|
+
SimpleDateFormat formatter(UnicodeString(str, str_len), Locale(locale), status);
|
70
|
+
if( U_FAILURE(status) ) {
|
71
|
+
rb_raise(rb_eArgError, u_errorName(status));
|
72
|
+
}
|
73
|
+
status = U_ZERO_ERROR;
|
74
|
+
UDate p_time = formatter.parse(UnicodeString(val, len), status);
|
75
|
+
if( U_FAILURE(status) ) {
|
76
|
+
rb_raise(rb_eArgError, u_errorName(status));
|
77
|
+
}
|
78
|
+
return rb_time_new( (time_t) (p_time/1000.0), 0);
|
79
|
+
}
|
80
|
+
VALUE icu_transliterate(UChar * str, int32_t str_len, UChar * id, int32_t id_len, UChar * rules, int32_t rule_len)
|
81
|
+
{
|
82
|
+
UErrorCode status = U_ZERO_ERROR;
|
83
|
+
UParseError p_error;
|
84
|
+
Transliterator * t ;
|
85
|
+
if( rules != NULL) {
|
86
|
+
t = Transliterator::createFromRules(UnicodeString(id, id_len), UnicodeString(rules, rule_len),
|
87
|
+
UTRANS_FORWARD, p_error, status);
|
88
|
+
} else {
|
89
|
+
t = Transliterator::createInstance(UnicodeString(id, id_len), UTRANS_FORWARD, p_error, status);
|
90
|
+
}
|
91
|
+
if( U_FAILURE(status) )
|
92
|
+
{
|
93
|
+
rb_raise(rb_eRuntimeError, u_errorName(status));
|
94
|
+
}
|
95
|
+
UnicodeString * src = new UnicodeString(str, str_len);
|
96
|
+
t->transliterate(*src);
|
97
|
+
int32_t blen = src->length();
|
98
|
+
UChar * buf = ALLOC_N(UChar, blen + 1);
|
99
|
+
src->extract(buf, blen, status);
|
100
|
+
VALUE ret = icu_ustr_new_set( buf, blen, blen+1);
|
101
|
+
delete src;
|
102
|
+
delete t;
|
103
|
+
return ret;
|
104
|
+
}
|
105
|
+
extern void icu4r_cal_free(UCalendar *);
|
106
|
+
|
107
|
+
VALUE icu4r_cal_clone(VALUE cal)
|
108
|
+
{
|
109
|
+
Calendar * clon;
|
110
|
+
clon = ((Calendar *)(DATA_PTR(cal)))->clone();
|
111
|
+
return Data_Wrap_Struct(rb_cUCalendar, 0, icu4r_cal_free, clon);
|
112
|
+
}
|
113
|
+
#define CPP_CALENDAR(obj) ((Calendar*)DATA_PTR(obj))
|
114
|
+
VALUE icu4r_cal_before(VALUE cal, VALUE obj)
|
115
|
+
{
|
116
|
+
UErrorCode status = U_ZERO_ERROR;
|
117
|
+
UBool answer;
|
118
|
+
Check_Class( obj, rb_cUCalendar);
|
119
|
+
Calendar *other = CPP_CALENDAR(obj);
|
120
|
+
answer = CPP_CALENDAR(cal)->before(*other, status);
|
121
|
+
if( U_FAILURE(status) ) rb_raise(rb_eArgError, u_errorName(status));
|
122
|
+
return answer ? Qtrue : Qfalse;
|
123
|
+
}
|
124
|
+
|
125
|
+
VALUE icu4r_cal_time_equals(VALUE cal, VALUE obj)
|
126
|
+
{
|
127
|
+
UErrorCode status = U_ZERO_ERROR;
|
128
|
+
UBool answer;
|
129
|
+
Check_Class( obj, rb_cUCalendar);
|
130
|
+
Calendar *other = CPP_CALENDAR(obj);
|
131
|
+
answer = CPP_CALENDAR(cal)->equals(*other, status);
|
132
|
+
if( U_FAILURE(status) ) rb_raise(rb_eArgError, u_errorName(status));
|
133
|
+
return answer ? Qtrue : Qfalse;
|
134
|
+
}
|
135
|
+
|
136
|
+
VALUE icu4r_cal_after(VALUE cal, VALUE obj)
|
137
|
+
{
|
138
|
+
Check_Class( obj, rb_cUCalendar);
|
139
|
+
return icu4r_cal_before(obj, cal);
|
140
|
+
}
|
141
|
+
|
142
|
+
VALUE icu4r_cal_equal(VALUE cal, VALUE obj)
|
143
|
+
{
|
144
|
+
UBool answer;
|
145
|
+
Check_Class( obj, rb_cUCalendar);
|
146
|
+
answer = (*CPP_CALENDAR(cal)) == (*CPP_CALENDAR(obj));
|
147
|
+
return answer ? Qtrue : Qfalse;
|
148
|
+
}
|
149
|
+
}
|
150
|
+
|
data/icu4r.c
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
extern void initialize_ustring(void);
|
2
|
+
extern void initialize_calendar(void);
|
3
|
+
extern void initialize_uregexp(void);
|
4
|
+
extern void initialize_ucore_ext(void);
|
5
|
+
extern void initialize_ubundle(void);
|
6
|
+
void Init_icu4r (void) {
|
7
|
+
|
8
|
+
initialize_ustring();
|
9
|
+
initialize_uregexp();
|
10
|
+
initialize_ucore_ext();
|
11
|
+
initialize_ubundle();
|
12
|
+
initialize_calendar();
|
13
|
+
|
14
|
+
}
|
data/icu_common.h
ADDED
@@ -0,0 +1,45 @@
|
|
1
|
+
#include "ruby.h"
|
2
|
+
#include <unicode/utypes.h>
|
3
|
+
#include <unicode/ustring.h>
|
4
|
+
#include <unicode/ustdio.h>
|
5
|
+
#include <unicode/uchar.h>
|
6
|
+
#include <unicode/uclean.h>
|
7
|
+
#include <unicode/uregex.h>
|
8
|
+
#include <unicode/unorm.h>
|
9
|
+
#include <unicode/ubrk.h>
|
10
|
+
#include <unicode/ucnv.h>
|
11
|
+
#include <unicode/uset.h>
|
12
|
+
#include <unicode/uenum.h>
|
13
|
+
#include <unicode/utrans.h>
|
14
|
+
#include <unicode/ucol.h>
|
15
|
+
#include <unicode/usearch.h>
|
16
|
+
#include <unicode/ures.h>
|
17
|
+
#include <unicode/unum.h>
|
18
|
+
|
19
|
+
#ifdef HAVE_UNISTD_H
|
20
|
+
#include <unistd.h>
|
21
|
+
#endif
|
22
|
+
typedef struct {
|
23
|
+
long len;
|
24
|
+
long capa;
|
25
|
+
UChar *ptr;
|
26
|
+
char busy;
|
27
|
+
} ICUString ;
|
28
|
+
#define USTRING(obj) ((ICUString *)DATA_PTR(obj))
|
29
|
+
#define UREGEX(obj) ((ICURegexp *)DATA_PTR(obj))
|
30
|
+
#define ICU_PTR(str) USTRING(str)->ptr
|
31
|
+
#define ICU_LEN(str) USTRING(str)->len
|
32
|
+
#define ICU_CAPA(str) USTRING(str)->capa
|
33
|
+
#define ICU_RESIZE(str,capacity) REALLOC_N(ICU_PTR(str), UChar, (capacity)+1);
|
34
|
+
|
35
|
+
typedef struct {
|
36
|
+
URegularExpression *pattern;
|
37
|
+
int options;
|
38
|
+
} ICURegexp;
|
39
|
+
|
40
|
+
|
41
|
+
#define Check_Class(obj, klass) if(CLASS_OF(obj) != klass) rb_raise(rb_eTypeError, "Wrong type: expected %s, got %s", rb_class2name(klass), rb_class2name(rb_obj_class(obj)));
|
42
|
+
|
43
|
+
|
44
|
+
#define ICU_RAISE(status) if(U_FAILURE(status)) rb_raise(rb_eRuntimeError, u_errorName(status));
|
45
|
+
|
@@ -0,0 +1,23 @@
|
|
1
|
+
require 'icu4r'
|
2
|
+
res = {}
|
3
|
+
src = <<-EOT
|
4
|
+
外国語の勉強と教え
|
5
|
+
Изучение и обучение иностранных языков
|
6
|
+
Enseñanza y estudio de idiomas
|
7
|
+
'læŋɡwidʒ 'lɘr:niŋ ænd 'ti:ʃiŋ
|
8
|
+
ללמוד וללמד את השֵפה
|
9
|
+
L'enseignement et l'étude des langues
|
10
|
+
Γλωσσική Εκμὰθηση και Διδασκαλία
|
11
|
+
เรียนและสอนภาษา
|
12
|
+
EOT
|
13
|
+
src = src.u
|
14
|
+
["line_break", "char", "sentence", "word"].each do |brk|
|
15
|
+
res[brk] = {}
|
16
|
+
["ja", "en", "th"].each do |loc|
|
17
|
+
out = []
|
18
|
+
src.send("each_#{brk}".to_sym, loc) { |s| out << s }
|
19
|
+
res[brk][loc] = out.join("|")
|
20
|
+
puts "---------#{brk}-------#{loc}---------"
|
21
|
+
puts out.join("|")
|
22
|
+
end
|
23
|
+
end
|
@@ -0,0 +1,16 @@
|
|
1
|
+
require 'icu4r'
|
2
|
+
root = UResourceBundle.open(nil, "en")
|
3
|
+
today = Time.now
|
4
|
+
UString::list_locales.each do |locale|
|
5
|
+
b = UResourceBundle.open(nil, locale)
|
6
|
+
lang, ctry, var = locale.split '_', 3
|
7
|
+
ctry = var ? var : ctry
|
8
|
+
puts [
|
9
|
+
locale,
|
10
|
+
"("+root["Countries"][ctry].to_s + " : " + root["Languages"][lang].to_s+")",
|
11
|
+
"("+b["Countries"][ctry].to_s + " : " + b["Languages"][lang].to_s+")",
|
12
|
+
"[{0,date,long}]({1,number,currency})".u.fmt(locale, today, 123.45),
|
13
|
+
b["ExemplarCharacters"]
|
14
|
+
].join("\t")
|
15
|
+
|
16
|
+
end
|
@@ -0,0 +1,11 @@
|
|
1
|
+
require 'icu4r'
|
2
|
+
str = " abcあいうえおアイウエオアイウエオ漢字,0123スクリプト".u
|
3
|
+
puts str.inspect_names
|
4
|
+
p str=~ ure('[\p{Script=Latin}]+')
|
5
|
+
p str=~ ure('[\p{Script=Hiragana}]+')
|
6
|
+
p str=~ ure('[\p{Script=Katakana}]+')
|
7
|
+
p str=~ ure('[\p{Script=Hiragana}\p{Script=Katakana}]+')
|
8
|
+
p str=~ ure('[\p{blk=CJKUnifiedIdeographs}]+')
|
9
|
+
p str=~ ure('[\p{L}]+')
|
10
|
+
p str=~ ure('\u3042') # あ
|
11
|
+
p str.scan(ure('[\p{N}]'))
|
Binary file
|
Binary file
|
@@ -0,0 +1,109 @@
|
|
1
|
+
require './icu4r'
|
2
|
+
require 'test/unit'
|
3
|
+
# these tests are ICU 3.4 dependent
|
4
|
+
class UCalendarTest < Test::Unit::TestCase
|
5
|
+
|
6
|
+
def test_time_zones
|
7
|
+
v = UCalendar.time_zones
|
8
|
+
assert_equal(v.size, 577)
|
9
|
+
assert_equal( UString, v[0].class)
|
10
|
+
assert_equal("ACT".u, v[0] )
|
11
|
+
end
|
12
|
+
|
13
|
+
def test_default
|
14
|
+
v = UCalendar.default_tz
|
15
|
+
UCalendar.default_tz ="Europe/Paris".u
|
16
|
+
assert_equal( "Europe/Paris".u, UCalendar.default_tz)
|
17
|
+
c = UCalendar.new
|
18
|
+
assert_equal( "GMT+01:00".u, c.time_zone)
|
19
|
+
end
|
20
|
+
|
21
|
+
def test_dst
|
22
|
+
assert_equal(UCalendar.dst_savings("America/Detroit".u), 3600000)
|
23
|
+
assert_equal(UCalendar.dst_savings("Australia/Lord_Howe".u), 1800000)
|
24
|
+
end
|
25
|
+
|
26
|
+
def test_tz_for_country
|
27
|
+
zones = %w{Europe/Kiev Europe/Simferopol Europe/Uzhgorod Europe/Zaporozhye}.collect {|s| s.to_u}
|
28
|
+
assert_equal(zones, UCalendar.tz_for_country("UA"))
|
29
|
+
end
|
30
|
+
|
31
|
+
def test_time_now
|
32
|
+
assert_equal(Time.now.to_i/100, UCalendar.now.to_i/100000)
|
33
|
+
end
|
34
|
+
|
35
|
+
def test_in_daylight
|
36
|
+
t = UCalendar.new
|
37
|
+
t.set_date(2006, 8, 22)
|
38
|
+
t.time_zone = "US/Hawaii".u
|
39
|
+
assert_equal(false, t.in_daylight_time?)
|
40
|
+
t.time_zone = "Europe/Berlin".u
|
41
|
+
assert_equal(true, t.in_daylight_time?)
|
42
|
+
end
|
43
|
+
def test_set_date
|
44
|
+
t = UCalendar.new
|
45
|
+
t.set_date(2006, 0, 22)
|
46
|
+
assert_equal(2006, t[:year])
|
47
|
+
assert_equal(0, t[:month])
|
48
|
+
assert_equal(22, t[:date])
|
49
|
+
t[:year] = 2007
|
50
|
+
t[:month] = 2
|
51
|
+
t[:date] = 23
|
52
|
+
assert_equal(2007, t[:year])
|
53
|
+
assert_equal(2, t[:month])
|
54
|
+
assert_equal(23, t[:date])
|
55
|
+
|
56
|
+
end
|
57
|
+
|
58
|
+
def test_set_date_time
|
59
|
+
t = UCalendar.new
|
60
|
+
t.set_date_time(2006, 0, 22, 11, 22, 33)
|
61
|
+
assert_equal(11, t[:hour])
|
62
|
+
assert_equal(22, t[:minute])
|
63
|
+
assert_equal(33, t[:second])
|
64
|
+
end
|
65
|
+
|
66
|
+
def test_millis
|
67
|
+
m = UCalendar.now
|
68
|
+
t = UCalendar.new
|
69
|
+
assert(m <= t.millis)
|
70
|
+
n = Time.now.to_i
|
71
|
+
t.millis = n * 1000.0
|
72
|
+
assert_equal(n*1000.0, t.millis)
|
73
|
+
end
|
74
|
+
|
75
|
+
def test_add_time
|
76
|
+
t = UCalendar.new
|
77
|
+
t.set_date_time(2006, 0, 22, 11, 22, 33)
|
78
|
+
t.add(:week_of_year, 1)
|
79
|
+
assert_equal(29, t[:date])
|
80
|
+
t.add(:hour, 48)
|
81
|
+
assert_equal(31, t[:date])
|
82
|
+
end
|
83
|
+
|
84
|
+
def test_format
|
85
|
+
t = UCalendar.new
|
86
|
+
t.set_date_time(2006, 0, 22, 11, 22, 33)
|
87
|
+
t.time_zone = "Europe/London".u
|
88
|
+
assert_equal("2006/01/22 11:22:33 GMT AD".u, t.format("yyyy/MM/dd HH:mm:ss z G".u, "en"))
|
89
|
+
end
|
90
|
+
|
91
|
+
def test_clone_and_compare
|
92
|
+
c = UCalendar.new
|
93
|
+
d = c.clone
|
94
|
+
assert(c == d)
|
95
|
+
assert(! (c < d) )
|
96
|
+
assert(! (c > d) )
|
97
|
+
assert(c.eql?(d))
|
98
|
+
c.add(:date, 1)
|
99
|
+
assert(c != d)
|
100
|
+
assert(! (c < d) )
|
101
|
+
assert( (c > d) )
|
102
|
+
assert(!c.eql?(d))
|
103
|
+
d.add(:date, 1)
|
104
|
+
assert(c.eql?(d))
|
105
|
+
d.time_zone = "Europe/Kiev".u
|
106
|
+
assert(!c.eql?(d))
|
107
|
+
assert(c == d)
|
108
|
+
end
|
109
|
+
end
|