1 /* PSPP - a program for statistical analysis.
2 Copyright (C) 2006, 2010, 2011, 2012 Free Software Foundation, Inc.
4 This program is free software: you can redistribute it and/or modify
5 it under the terms of the GNU General Public License as published by
6 the Free Software Foundation, either version 3 of the License, or
7 (at your option) any later version.
9 This program is distributed in the hope that it will be useful,
10 but WITHOUT ANY WARRANTY; without even the implied warranty of
11 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
12 GNU General Public License for more details.
14 You should have received a copy of the GNU General Public License
15 along with this program. If not, see <http://www.gnu.org/licenses/>. */
23 void i18n_done (void);
24 void i18n_init (void);
28 /* The encoding of literal strings in PSPP source code, as seen at execution
29 time. In fact this is likely to be some extended ASCII encoding, such as
30 UTF-8 or ISO-8859-1, but ASCII is adequate for our purposes. */
31 #define C_ENCODING "ASCII"
35 char recode_byte (const char *to, const char *from, char);
37 char *recode_string (const char *to, const char *from,
38 const char *text, int len);
39 char *recode_string_pool (const char *to, const char *from,
40 const char *text, int length, struct pool *);
41 struct substring recode_substring_pool (const char *to, const char *from,
42 struct substring text, struct pool *);
44 size_t recode_string_len (const char *to, const char *from,
45 const char *text, int len);
47 char *utf8_encoding_trunc (const char *, const char *encoding,
49 size_t utf8_encoding_trunc_len (const char *, const char *encoding,
52 char *utf8_encoding_concat (const char *head, const char *tail,
53 const char *encoding, size_t max_len);
54 size_t utf8_encoding_concat_len (const char *head, const char *tail,
55 const char *encoding, size_t max_len);
57 char *utf8_to_filename (const char *filename);
58 char *filename_to_utf8 (const char *filename);
60 bool valid_encoding (const char *enc);
62 char get_system_decimal (void);
64 const char * get_default_encoding (void);
65 void set_default_encoding (const char *enc);
67 bool set_encoding_from_locale (const char *loc);
69 const char *uc_name (ucs4_t uc, char buffer[16]);
71 unsigned int utf8_hash_case_bytes (const char *, size_t n, unsigned int basis);
72 unsigned int utf8_hash_case_string (const char *, unsigned int basis);
73 int utf8_strcasecmp (const char *, const char *);
74 int utf8_strncasecmp (const char *, size_t, const char *, size_t);
75 char *utf8_to_upper (const char *);
76 char *utf8_to_lower (const char *);
78 /* Information about character encodings. */
80 /* ISO C defines a set of characters that a C implementation must support at
81 runtime, called the C basic execution character set, which consists of the
84 A B C D E F G H I J K L M
85 N O P Q R S T U V W X Y Z
86 a b c d e f g h i j k l m
87 n o p q r s t u v w x y z
89 ! " # % & ' ( ) * + , - . / :
90 ; < = > ? [ \ ] ^ _ { | } ~
91 space \a \b \r \n \t \v \f \0
93 The following is true of every member of the C basic execution character
94 set in all "reasonable" encodings:
96 1. Every member of the C basic character set is encoded.
98 2. Every member of the C basic character set has the same width in
99 bytes, called the "unit width". Most encodings have a unit width of
100 1 byte, but UCS-2 and UTF-16 have a unit width of 2 bytes and UCS-4
101 and UTF-32 have a unit width of 4 bytes.
103 3. In a stateful encoding, the encoding of members of the C basic
104 character set does not vary with shift state.
106 4. When a string is read unit-by-unit, a unit that has the encoded value
107 of a member of the C basic character set, EXCEPT FOR THE DECIMAL
108 DIGITS, always represents that member. That is, if the encoding has
109 multi-unit characters, the units that encode the C basic character
110 set are never part of a multi-unit character.
112 The exception for decimal digits is due to GB18030, which uses
113 decimal digits as part of multi-byte encodings.
115 All 8-bit and wider encodings that I have been able to find follow these
116 rules. 7-bit and narrower encodings (e.g. UTF-7) do not. I'm not too
117 concerned about that. */
121 /* Maximum width of a unit, in bytes. UTF-32 with 4-byte units is the widest
122 that I am aware of. */
125 /* Information about an encoding. */
128 /* Encoding name. IANA says character set names may be up to 40 US-ASCII
132 /* True if this encoding has a unit width of 1 byte, and every character
133 used in ASCII text files has the same value in this encoding. */
134 bool is_ascii_compatible;
136 /* True if this encoding has a unit width of 1 byte and appears to be
138 bool is_ebcdic_compatible;
140 /* Character information. */
141 int unit; /* Unit width, in bytes. */
142 char cr[MAX_UNIT]; /* \r in encoding, 'unit' bytes long. */
143 char lf[MAX_UNIT]; /* \n in encoding, 'unit' bytes long. */
144 char space[MAX_UNIT]; /* ' ' in encoding, 'unit' bytes long. */
147 bool get_encoding_info (struct encoding_info *, const char *name);
148 bool is_encoding_ascii_compatible (const char *encoding);
149 bool is_encoding_ebcdic_compatible (const char *encoding);
150 bool is_encoding_supported (const char *encoding);
152 bool is_encoding_utf8 (const char *encoding);
154 /* Database of encodings, by language or region. */
156 struct encoding_category
158 const char *category; /* e.g. "Arabic" or "Western European". */
159 const char **encodings; /* Encodings within the category. */
160 size_t n_encodings; /* Number of encodings in category. */
163 struct encoding_category *get_encoding_categories (void);
164 size_t get_n_encoding_categories (void);