1 | /* Character handling in C locale. |
2 | |
3 | These functions work like the corresponding functions in <ctype.h>, |
4 | except that they have the C (POSIX) locale hardwired, whereas the |
5 | <ctype.h> functions' behaviour depends on the current locale set via |
6 | setlocale. |
7 | |
8 | Copyright (C) 2000-2003, 2006, 2008-2019 Free Software Foundation, Inc. |
9 | |
10 | This program is free software; you can redistribute it and/or modify |
11 | it under the terms of the GNU General Public License as published by |
12 | the Free Software Foundation; either version 3 of the License, or |
13 | (at your option) any later version. |
14 | |
15 | This program is distributed in the hope that it will be useful, |
16 | but WITHOUT ANY WARRANTY; without even the implied warranty of |
17 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
18 | GNU General Public License for more details. |
19 | |
20 | You should have received a copy of the GNU General Public License |
21 | along with this program; if not, see <https://www.gnu.org/licenses/>. */ |
22 | |
23 | #ifndef C_CTYPE_H |
24 | #define C_CTYPE_H |
25 | |
26 | #include <stdbool.h> |
27 | |
28 | #ifndef _GL_INLINE_HEADER_BEGIN |
29 | #error "Please include config.h first." |
30 | #endif |
31 | _GL_INLINE_HEADER_BEGIN |
32 | #ifndef C_CTYPE_INLINE |
33 | # define C_CTYPE_INLINE _GL_INLINE |
34 | #endif |
35 | |
36 | #ifdef __cplusplus |
37 | extern "C" { |
38 | #endif |
39 | |
40 | |
41 | /* The functions defined in this file assume the "C" locale and a character |
42 | set without diacritics (ASCII-US or EBCDIC-US or something like that). |
43 | Even if the "C" locale on a particular system is an extension of the ASCII |
44 | character set (like on BeOS, where it is UTF-8, or on AmigaOS, where it |
45 | is ISO-8859-1), the functions in this file recognize only the ASCII |
46 | characters. */ |
47 | |
48 | |
49 | #if (' ' == 32) && ('!' == 33) && ('"' == 34) && ('#' == 35) \ |
50 | && ('%' == 37) && ('&' == 38) && ('\'' == 39) && ('(' == 40) \ |
51 | && (')' == 41) && ('*' == 42) && ('+' == 43) && (',' == 44) \ |
52 | && ('-' == 45) && ('.' == 46) && ('/' == 47) && ('0' == 48) \ |
53 | && ('1' == 49) && ('2' == 50) && ('3' == 51) && ('4' == 52) \ |
54 | && ('5' == 53) && ('6' == 54) && ('7' == 55) && ('8' == 56) \ |
55 | && ('9' == 57) && (':' == 58) && (';' == 59) && ('<' == 60) \ |
56 | && ('=' == 61) && ('>' == 62) && ('?' == 63) && ('A' == 65) \ |
57 | && ('B' == 66) && ('C' == 67) && ('D' == 68) && ('E' == 69) \ |
58 | && ('F' == 70) && ('G' == 71) && ('H' == 72) && ('I' == 73) \ |
59 | && ('J' == 74) && ('K' == 75) && ('L' == 76) && ('M' == 77) \ |
60 | && ('N' == 78) && ('O' == 79) && ('P' == 80) && ('Q' == 81) \ |
61 | && ('R' == 82) && ('S' == 83) && ('T' == 84) && ('U' == 85) \ |
62 | && ('V' == 86) && ('W' == 87) && ('X' == 88) && ('Y' == 89) \ |
63 | && ('Z' == 90) && ('[' == 91) && ('\\' == 92) && (']' == 93) \ |
64 | && ('^' == 94) && ('_' == 95) && ('a' == 97) && ('b' == 98) \ |
65 | && ('c' == 99) && ('d' == 100) && ('e' == 101) && ('f' == 102) \ |
66 | && ('g' == 103) && ('h' == 104) && ('i' == 105) && ('j' == 106) \ |
67 | && ('k' == 107) && ('l' == 108) && ('m' == 109) && ('n' == 110) \ |
68 | && ('o' == 111) && ('p' == 112) && ('q' == 113) && ('r' == 114) \ |
69 | && ('s' == 115) && ('t' == 116) && ('u' == 117) && ('v' == 118) \ |
70 | && ('w' == 119) && ('x' == 120) && ('y' == 121) && ('z' == 122) \ |
71 | && ('{' == 123) && ('|' == 124) && ('}' == 125) && ('~' == 126) |
72 | /* The character set is ASCII or one of its variants or extensions, not EBCDIC. |
73 | Testing the value of '\n' and '\r' is not relevant. */ |
74 | # define C_CTYPE_ASCII 1 |
75 | #elif ! (' ' == '\x40' && '0' == '\xf0' \ |
76 | && 'A' == '\xc1' && 'J' == '\xd1' && 'S' == '\xe2' \ |
77 | && 'a' == '\x81' && 'j' == '\x91' && 's' == '\xa2') |
78 | # error "Only ASCII and EBCDIC are supported" |
79 | #endif |
80 | |
81 | #if 'A' < 0 |
82 | # error "EBCDIC and char is signed -- not supported" |
83 | #endif |
84 | |
85 | /* Cases for control characters. */ |
86 | |
87 | #define _C_CTYPE_CNTRL \ |
88 | case '\a': case '\b': case '\f': case '\n': \ |
89 | case '\r': case '\t': case '\v': \ |
90 | _C_CTYPE_OTHER_CNTRL |
91 | |
92 | /* ASCII control characters other than those with \-letter escapes. */ |
93 | |
94 | #if C_CTYPE_ASCII |
95 | # define _C_CTYPE_OTHER_CNTRL \ |
96 | case '\x00': case '\x01': case '\x02': case '\x03': \ |
97 | case '\x04': case '\x05': case '\x06': case '\x0e': \ |
98 | case '\x0f': case '\x10': case '\x11': case '\x12': \ |
99 | case '\x13': case '\x14': case '\x15': case '\x16': \ |
100 | case '\x17': case '\x18': case '\x19': case '\x1a': \ |
101 | case '\x1b': case '\x1c': case '\x1d': case '\x1e': \ |
102 | case '\x1f': case '\x7f' |
103 | #else |
104 | /* Use EBCDIC code page 1047's assignments for ASCII control chars; |
105 | assume all EBCDIC code pages agree about these assignments. */ |
106 | # define _C_CTYPE_OTHER_CNTRL \ |
107 | case '\x00': case '\x01': case '\x02': case '\x03': \ |
108 | case '\x07': case '\x0e': case '\x0f': case '\x10': \ |
109 | case '\x11': case '\x12': case '\x13': case '\x18': \ |
110 | case '\x19': case '\x1c': case '\x1d': case '\x1e': \ |
111 | case '\x1f': case '\x26': case '\x27': case '\x2d': \ |
112 | case '\x2e': case '\x32': case '\x37': case '\x3c': \ |
113 | case '\x3d': case '\x3f' |
114 | #endif |
115 | |
116 | /* Cases for lowercase hex letters, and lowercase letters, all offset by N. */ |
117 | |
118 | #define _C_CTYPE_LOWER_A_THRU_F_N(N) \ |
119 | case 'a' + (N): case 'b' + (N): case 'c' + (N): case 'd' + (N): \ |
120 | case 'e' + (N): case 'f' + (N) |
121 | #define _C_CTYPE_LOWER_N(N) \ |
122 | _C_CTYPE_LOWER_A_THRU_F_N(N): \ |
123 | case 'g' + (N): case 'h' + (N): case 'i' + (N): case 'j' + (N): \ |
124 | case 'k' + (N): case 'l' + (N): case 'm' + (N): case 'n' + (N): \ |
125 | case 'o' + (N): case 'p' + (N): case 'q' + (N): case 'r' + (N): \ |
126 | case 's' + (N): case 't' + (N): case 'u' + (N): case 'v' + (N): \ |
127 | case 'w' + (N): case 'x' + (N): case 'y' + (N): case 'z' + (N) |
128 | |
129 | /* Cases for hex letters, digits, lower, punct, and upper. */ |
130 | |
131 | #define _C_CTYPE_A_THRU_F \ |
132 | _C_CTYPE_LOWER_A_THRU_F_N (0): \ |
133 | _C_CTYPE_LOWER_A_THRU_F_N ('A' - 'a') |
134 | #define _C_CTYPE_DIGIT \ |
135 | case '0': case '1': case '2': case '3': \ |
136 | case '4': case '5': case '6': case '7': \ |
137 | case '8': case '9' |
138 | #define _C_CTYPE_LOWER _C_CTYPE_LOWER_N (0) |
139 | #define _C_CTYPE_PUNCT \ |
140 | case '!': case '"': case '#': case '$': \ |
141 | case '%': case '&': case '\'': case '(': \ |
142 | case ')': case '*': case '+': case ',': \ |
143 | case '-': case '.': case '/': case ':': \ |
144 | case ';': case '<': case '=': case '>': \ |
145 | case '?': case '@': case '[': case '\\': \ |
146 | case ']': case '^': case '_': case '`': \ |
147 | case '{': case '|': case '}': case '~' |
148 | #define _C_CTYPE_UPPER _C_CTYPE_LOWER_N ('A' - 'a') |
149 | |
150 | |
151 | /* Function definitions. */ |
152 | |
153 | /* Unlike the functions in <ctype.h>, which require an argument in the range |
154 | of the 'unsigned char' type, the functions here operate on values that are |
155 | in the 'unsigned char' range or in the 'char' range. In other words, |
156 | when you have a 'char' value, you need to cast it before using it as |
157 | argument to a <ctype.h> function: |
158 | |
159 | const char *s = ...; |
160 | if (isalpha ((unsigned char) *s)) ... |
161 | |
162 | but you don't need to cast it for the functions defined in this file: |
163 | |
164 | const char *s = ...; |
165 | if (c_isalpha (*s)) ... |
166 | */ |
167 | |
168 | C_CTYPE_INLINE bool |
169 | c_isalnum (int c) |
170 | { |
171 | switch (c) |
172 | { |
173 | _C_CTYPE_DIGIT: |
174 | _C_CTYPE_LOWER: |
175 | _C_CTYPE_UPPER: |
176 | return true; |
177 | default: |
178 | return false; |
179 | } |
180 | } |
181 | |
182 | C_CTYPE_INLINE bool |
183 | c_isalpha (int c) |
184 | { |
185 | switch (c) |
186 | { |
187 | _C_CTYPE_LOWER: |
188 | _C_CTYPE_UPPER: |
189 | return true; |
190 | default: |
191 | return false; |
192 | } |
193 | } |
194 | |
195 | /* The function isascii is not locale dependent. |
196 | Its use in EBCDIC is questionable. */ |
197 | C_CTYPE_INLINE bool |
198 | c_isascii (int c) |
199 | { |
200 | switch (c) |
201 | { |
202 | case ' ': |
203 | _C_CTYPE_CNTRL: |
204 | _C_CTYPE_DIGIT: |
205 | _C_CTYPE_LOWER: |
206 | _C_CTYPE_PUNCT: |
207 | _C_CTYPE_UPPER: |
208 | return true; |
209 | default: |
210 | return false; |
211 | } |
212 | } |
213 | |
214 | C_CTYPE_INLINE bool |
215 | c_isblank (int c) |
216 | { |
217 | return c == ' ' || c == '\t'; |
218 | } |
219 | |
220 | C_CTYPE_INLINE bool |
221 | c_iscntrl (int c) |
222 | { |
223 | switch (c) |
224 | { |
225 | _C_CTYPE_CNTRL: |
226 | return true; |
227 | default: |
228 | return false; |
229 | } |
230 | } |
231 | |
232 | C_CTYPE_INLINE bool |
233 | c_isdigit (int c) |
234 | { |
235 | switch (c) |
236 | { |
237 | _C_CTYPE_DIGIT: |
238 | return true; |
239 | default: |
240 | return false; |
241 | } |
242 | } |
243 | |
244 | C_CTYPE_INLINE bool |
245 | c_isgraph (int c) |
246 | { |
247 | switch (c) |
248 | { |
249 | _C_CTYPE_DIGIT: |
250 | _C_CTYPE_LOWER: |
251 | _C_CTYPE_PUNCT: |
252 | _C_CTYPE_UPPER: |
253 | return true; |
254 | default: |
255 | return false; |
256 | } |
257 | } |
258 | |
259 | C_CTYPE_INLINE bool |
260 | c_islower (int c) |
261 | { |
262 | switch (c) |
263 | { |
264 | _C_CTYPE_LOWER: |
265 | return true; |
266 | default: |
267 | return false; |
268 | } |
269 | } |
270 | |
271 | C_CTYPE_INLINE bool |
272 | c_isprint (int c) |
273 | { |
274 | switch (c) |
275 | { |
276 | case ' ': |
277 | _C_CTYPE_DIGIT: |
278 | _C_CTYPE_LOWER: |
279 | _C_CTYPE_PUNCT: |
280 | _C_CTYPE_UPPER: |
281 | return true; |
282 | default: |
283 | return false; |
284 | } |
285 | } |
286 | |
287 | C_CTYPE_INLINE bool |
288 | c_ispunct (int c) |
289 | { |
290 | switch (c) |
291 | { |
292 | _C_CTYPE_PUNCT: |
293 | return true; |
294 | default: |
295 | return false; |
296 | } |
297 | } |
298 | |
299 | C_CTYPE_INLINE bool |
300 | c_isspace (int c) |
301 | { |
302 | switch (c) |
303 | { |
304 | case ' ': case '\t': case '\n': case '\v': case '\f': case '\r': |
305 | return true; |
306 | default: |
307 | return false; |
308 | } |
309 | } |
310 | |
311 | C_CTYPE_INLINE bool |
312 | c_isupper (int c) |
313 | { |
314 | switch (c) |
315 | { |
316 | _C_CTYPE_UPPER: |
317 | return true; |
318 | default: |
319 | return false; |
320 | } |
321 | } |
322 | |
323 | C_CTYPE_INLINE bool |
324 | c_isxdigit (int c) |
325 | { |
326 | switch (c) |
327 | { |
328 | _C_CTYPE_DIGIT: |
329 | _C_CTYPE_A_THRU_F: |
330 | return true; |
331 | default: |
332 | return false; |
333 | } |
334 | } |
335 | |
336 | C_CTYPE_INLINE int |
337 | c_tolower (int c) |
338 | { |
339 | switch (c) |
340 | { |
341 | _C_CTYPE_UPPER: |
342 | return c - 'A' + 'a'; |
343 | default: |
344 | return c; |
345 | } |
346 | } |
347 | |
348 | C_CTYPE_INLINE int |
349 | c_toupper (int c) |
350 | { |
351 | switch (c) |
352 | { |
353 | _C_CTYPE_LOWER: |
354 | return c - 'a' + 'A'; |
355 | default: |
356 | return c; |
357 | } |
358 | } |
359 | |
360 | #ifdef __cplusplus |
361 | } |
362 | #endif |
363 | |
364 | _GL_INLINE_HEADER_END |
365 | |
366 | #endif /* C_CTYPE_H */ |
367 | |