utf8proc

view ruby/utf8proc_native.c @ 2:aaad485d5335

find changesets by author, revision, files, or words in the commit message
Version 0.3

- changed normalization from NFC to NFKC for postgresql unifold function
- added support to mark the beginning of a grapheme cluster with 0xFF (option: CHARBOUND)
- added the ruby method String#chars, which is returning an array of UTF-8 encoded grapheme clusters
- added NLF2LF transformation in postgresql unifold function
- added the DECOMPOSE option, if you neither use COMPOSE or DECOMPOSE, no normalization will be performed (different from previous versions)
- using integer constants rather than C-strings for character properties
- fixed (hopefully) a problem with the ruby library on Mac OS X, which occured when compiler optimization was switched on
author jbe
date Fri Aug 04 12:00:00 2006 +0200 (2006-08-04)
parents 61a89ecc2fb9
children 4ee0d5f54af1
line source
1 /*
2 * Copyright (c) 2006, FlexiGuided GmbH, Berlin, Germany
3 * Author: Jan Behrens <jan.behrens@flexiguided.de>
4 * All rights reserved.
5 *
6 * Redistribution and use in source and binary forms, with or without
7 * modification, are permitted provided that the following conditions are
8 * met:
9 *
10 * 1. Redistributions of source code must retain the above copyright
11 * notice, this list of conditions and the following disclaimer.
12 * 2. Redistributions in binary form must reproduce the above copyright
13 * notice, this list of conditions and the following disclaimer in the
14 * documentation and/or other materials provided with the distribution.
15 * 3. Neither the name of the FlexiGuided GmbH nor the names of its
16 * contributors may be used to endorse or promote products derived from
17 * this software without specific prior written permission.
18 *
19 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
20 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
21 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
22 * PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER
23 * OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
24 * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
25 * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
26 * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
27 * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
28 * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
29 * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
30 *
31 */
32
33
34 /*
35 * File name: ruby/utf8proc_native.c
36 * Version: 0.3
37 * Last changed: 2006-08-04
38 *
39 * Description:
40 * Native part of the ruby wrapper for libutf8proc.
41 */
42
43
44 #include "../utf8proc.c"
45 #include "ruby.h"
46
47 typedef struct utf8proc_ruby_mapenv_struct {
48 int32_t *buffer;
49 } utf8proc_ruby_mapenv_t;
50
51 void utf8proc_ruby_mapenv_free(utf8proc_ruby_mapenv_t *env) {
52 free(env->buffer);
53 free(env);
54 }
55
56 VALUE utf8proc_ruby_module;
57 VALUE utf8proc_ruby_options;
58 VALUE utf8proc_ruby_eUnicodeError;
59 VALUE utf8proc_ruby_eInvalidUtf8Error;
60 VALUE utf8proc_ruby_eCodeNotAssignedError;
61
62 VALUE utf8proc_ruby_map_error(ssize_t result) {
63 VALUE excpt_class;
64 switch (result) {
65 case UTF8PROC_ERROR_NOMEM:
66 excpt_class = rb_eNoMemError; break;
67 case UTF8PROC_ERROR_OVERFLOW:
68 excpt_class = rb_eArgError; break;
69 case UTF8PROC_ERROR_INVALIDUTF8:
70 excpt_class = utf8proc_ruby_eInvalidUtf8Error; break;
71 case UTF8PROC_ERROR_NOTASSIGNED:
72 excpt_class = utf8proc_ruby_eCodeNotAssignedError; break;
73 default:
74 excpt_class = rb_eRuntimeError;
75 }
76 rb_raise(excpt_class, "%s", utf8proc_errmsg(result));
77 return Qnil;
78 }
79
80 VALUE utf8proc_ruby_map(VALUE self, VALUE str_param, VALUE options_param) {
81 VALUE str;
82 int options;
83 VALUE env_obj;
84 utf8proc_ruby_mapenv_t *env;
85 ssize_t result;
86 VALUE retval;
87 str = StringValue(str_param);
88 options = NUM2INT(options_param) & ~UTF8PROC_NULLTERM;
89 env_obj = Data_Make_Struct(rb_cObject, utf8proc_ruby_mapenv_t, NULL,
90 utf8proc_ruby_mapenv_free, env);
91 result = utf8proc_decompose(RSTRING(str)->ptr, RSTRING(str)->len,
92 NULL, 0, options);
93 if (result < 0) {
94 utf8proc_ruby_map_error(result);
95 return Qnil; // needed to prevent problems with optimization
96 }
97 env->buffer = ALLOC_N(int32_t, result+1);
98 result = utf8proc_decompose(RSTRING(str)->ptr, RSTRING(str)->len,
99 env->buffer, result, options);
100 if (result < 0) {
101 free(env->buffer);
102 env->buffer = 0;
103 utf8proc_ruby_map_error(result);
104 return Qnil; // needed to prevent problems with optimization
105 }
106 result = utf8proc_reencode(env->buffer, result, options);
107 if (result < 0) {
108 free(env->buffer);
109 env->buffer = 0;
110 utf8proc_ruby_map_error(result);
111 return Qnil; // needed to prevent problems with optimization
112 }
113 retval = rb_str_new((char *)env->buffer, result);
114 free(env->buffer);
115 env->buffer = 0;
116 return retval;
117 }
118
119 static VALUE utf8proc_ruby_char(VALUE self, VALUE code_param) {
120 char buffer[4];
121 ssize_t result;
122 int uc;
123 uc = NUM2INT(code_param);
124 if (uc < 0 || ((uc & 0xFFFF) >= 0xFFFE) || (uc >= 0xD800 && uc < 0xE000) ||
125 (uc >= 0xFDD0 && uc < 0xFDF0))
126 rb_raise(rb_eArgError, "Invalid Unicode code point");
127 result = utf8proc_encode_char(uc, buffer);
128 return rb_str_new(buffer, result);
129 }
130
131 #define register_utf8proc_option(sym, field) \
132 rb_hash_aset(utf8proc_ruby_options, ID2SYM(rb_intern(sym)), INT2FIX(field))
133
134 void Init_utf8proc_native() {
135 utf8proc_ruby_module = rb_define_module("Utf8Proc");
136 rb_define_module_function(utf8proc_ruby_module, "utf8map",
137 utf8proc_ruby_map, 2);
138 rb_define_module_function(utf8proc_ruby_module, "utf8char",
139 utf8proc_ruby_char, 1);
140 utf8proc_ruby_eUnicodeError = rb_define_class_under(utf8proc_ruby_module,
141 "UnicodeError", rb_eStandardError);
142 utf8proc_ruby_eInvalidUtf8Error = rb_define_class_under(
143 utf8proc_ruby_module, "InvalidUtf8Error", utf8proc_ruby_eUnicodeError);
144 utf8proc_ruby_eCodeNotAssignedError = rb_define_class_under(
145 utf8proc_ruby_module, "CodeNotAssignedError",
146 utf8proc_ruby_eUnicodeError);
147 utf8proc_ruby_options = rb_hash_new();
148 register_utf8proc_option("stable", UTF8PROC_STABLE);
149 register_utf8proc_option("compat", UTF8PROC_COMPAT);
150 register_utf8proc_option("compose", UTF8PROC_COMPOSE);
151 register_utf8proc_option("decompose", UTF8PROC_DECOMPOSE);
152 register_utf8proc_option("ignore", UTF8PROC_IGNORE);
153 register_utf8proc_option("rejectna", UTF8PROC_REJECTNA);
154 register_utf8proc_option("nlf2ls", UTF8PROC_NLF2LS);
155 register_utf8proc_option("nlf2ps", UTF8PROC_NLF2PS);
156 register_utf8proc_option("nlf2lf", UTF8PROC_NLF2LF);
157 register_utf8proc_option("stripcc", UTF8PROC_STRIPCC);
158 register_utf8proc_option("casefold", UTF8PROC_CASEFOLD);
159 register_utf8proc_option("charbound", UTF8PROC_CHARBOUND);
160 OBJ_FREEZE(utf8proc_ruby_options);
161 rb_define_const(utf8proc_ruby_module, "Options", utf8proc_ruby_options);
162 }
163
164

Impressum / About Us