| 1 | /* Copyright (C) 1995,1996,1998 Free Software Foundation, Inc. |
| 2 | * |
| 3 | * This program is free software; you can redistribute it and/or modify |
| 4 | * it under the terms of the GNU General Public License as published by |
| 5 | * the Free Software Foundation; either version 2, or (at your option) |
| 6 | * any later version. |
| 7 | * |
| 8 | * This program is distributed in the hope that it will be useful, |
| 9 | * but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 10 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
| 11 | * GNU General Public License for more details. |
| 12 | * |
| 13 | * You should have received a copy of the GNU General Public License |
| 14 | * along with this software; see the file COPYING. If not, write to |
| 15 | * the Free Software Foundation, Inc., 59 Temple Place, Suite 330, |
| 16 | * Boston, MA 02111-1307 USA |
| 17 | * |
| 18 | * As a special exception, the Free Software Foundation gives permission |
| 19 | * for additional uses of the text contained in its release of GUILE. |
| 20 | * |
| 21 | * The exception is that, if you link the GUILE library with other files |
| 22 | * to produce an executable, this does not by itself cause the |
| 23 | * resulting executable to be covered by the GNU General Public License. |
| 24 | * Your use of that executable is in no way restricted on account of |
| 25 | * linking the GUILE library code into it. |
| 26 | * |
| 27 | * This exception does not however invalidate any other reasons why |
| 28 | * the executable file might be covered by the GNU General Public License. |
| 29 | * |
| 30 | * This exception applies only to the code released by the |
| 31 | * Free Software Foundation under the name GUILE. If you copy |
| 32 | * code from other Free Software Foundation releases into a copy of |
| 33 | * GUILE, as the General Public License permits, the exception does |
| 34 | * not apply to the code that you add in this way. To avoid misleading |
| 35 | * anyone as to the status of such modified files, you must delete |
| 36 | * this exception notice from them. |
| 37 | * |
| 38 | * If you write modifications of your own for GUILE, it is your choice |
| 39 | * whether to permit this exception to apply to your modifications. |
| 40 | * If you do not wish that, delete this exception notice. */ |
| 41 | |
| 42 | /* Software engineering face-lift by Greg J. Badros, 11-Dec-1999, |
| 43 | gjb@cs.washington.edu, http://www.cs.washington.edu/homes/gjb */ |
| 44 | |
| 45 | \f |
| 46 | |
| 47 | #include <stdio.h> |
| 48 | #include <ctype.h> |
| 49 | #include "_scm.h" |
| 50 | #include "scm_validate.h" |
| 51 | |
| 52 | #include "chars.h" |
| 53 | \f |
| 54 | |
| 55 | SCM_DEFINE (scm_char_p, "char?", 1, 0, 0, |
| 56 | (SCM x), |
| 57 | "Return #t iff X is a character, else #f.") |
| 58 | #define FUNC_NAME s_scm_char_p |
| 59 | { |
| 60 | return SCM_BOOL(SCM_CHARP(x)); |
| 61 | } |
| 62 | #undef FUNC_NAME |
| 63 | |
| 64 | SCM_DEFINE1 (scm_char_eq_p, "char=?", scm_tc7_rpsubr, |
| 65 | (SCM x, SCM y), |
| 66 | "Return #t iff X is the same character as Y, else #f.") |
| 67 | #define FUNC_NAME s_scm_char_eq_p |
| 68 | { |
| 69 | SCM_VALIDATE_CHAR (1,x); |
| 70 | SCM_VALIDATE_CHAR (2,y); |
| 71 | return SCM_BOOL(SCM_CHAR(x) == SCM_CHAR(y)); |
| 72 | } |
| 73 | #undef FUNC_NAME |
| 74 | |
| 75 | |
| 76 | SCM_DEFINE1 (scm_char_less_p, "char<?", scm_tc7_rpsubr, |
| 77 | (SCM x, SCM y), |
| 78 | "Return #t iff X is less than Y in the Ascii sequence, else #f.") |
| 79 | #define FUNC_NAME s_scm_char_less_p |
| 80 | { |
| 81 | SCM_VALIDATE_CHAR (1,x); |
| 82 | SCM_VALIDATE_CHAR (2,y); |
| 83 | return SCM_BOOL(SCM_CHAR(x) < SCM_CHAR(y)); |
| 84 | } |
| 85 | #undef FUNC_NAME |
| 86 | |
| 87 | SCM_DEFINE1 (scm_char_leq_p, "char<=?", scm_tc7_rpsubr, |
| 88 | (SCM x, SCM y), |
| 89 | "Return #t iff X is less than or equal to Y in the Ascii sequence, else #f.") |
| 90 | #define FUNC_NAME s_scm_char_leq_p |
| 91 | { |
| 92 | SCM_VALIDATE_CHAR (1,x); |
| 93 | SCM_VALIDATE_CHAR (2,y); |
| 94 | return SCM_BOOL(SCM_CHAR(x) <= SCM_CHAR(y)); |
| 95 | } |
| 96 | #undef FUNC_NAME |
| 97 | |
| 98 | SCM_DEFINE1 (scm_char_gr_p, "char>?", scm_tc7_rpsubr, |
| 99 | (SCM x, SCM y), |
| 100 | "Return #t iff X is greater than Y in the Ascii sequence, else #f.") |
| 101 | #define FUNC_NAME s_scm_char_gr_p |
| 102 | { |
| 103 | SCM_VALIDATE_CHAR (1,x); |
| 104 | SCM_VALIDATE_CHAR (2,y); |
| 105 | return SCM_BOOL(SCM_CHAR(x) > SCM_CHAR(y)); |
| 106 | } |
| 107 | #undef FUNC_NAME |
| 108 | |
| 109 | SCM_DEFINE1 (scm_char_geq_p, "char>=?", scm_tc7_rpsubr, |
| 110 | (SCM x, SCM y), |
| 111 | "Return #t iff X is greater than or equal to Y in the Ascii sequence, else #f.") |
| 112 | #define FUNC_NAME s_scm_char_geq_p |
| 113 | { |
| 114 | SCM_VALIDATE_CHAR (1,x); |
| 115 | SCM_VALIDATE_CHAR (2,y); |
| 116 | return SCM_BOOL(SCM_CHAR(x) >= SCM_CHAR(y)); |
| 117 | } |
| 118 | #undef FUNC_NAME |
| 119 | |
| 120 | SCM_DEFINE1 (scm_char_ci_eq_p, "char-ci=?", scm_tc7_rpsubr, |
| 121 | (SCM x, SCM y), |
| 122 | "Return #t iff X is the same character as Y ignoring case, else #f.") |
| 123 | #define FUNC_NAME s_scm_char_ci_eq_p |
| 124 | { |
| 125 | SCM_VALIDATE_CHAR (1,x); |
| 126 | SCM_VALIDATE_CHAR (2,y); |
| 127 | return SCM_BOOL(scm_upcase(SCM_CHAR(x))==scm_upcase(SCM_CHAR(y))); |
| 128 | } |
| 129 | #undef FUNC_NAME |
| 130 | |
| 131 | SCM_DEFINE1 (scm_char_ci_less_p, "char-ci<?", scm_tc7_rpsubr, |
| 132 | (SCM x, SCM y), |
| 133 | "Return #t iff X is less than Y in the Ascii sequence ignoring case, else #f.") |
| 134 | #define FUNC_NAME s_scm_char_ci_less_p |
| 135 | { |
| 136 | SCM_VALIDATE_CHAR (1,x); |
| 137 | SCM_VALIDATE_CHAR (2,y); |
| 138 | return SCM_BOOL((scm_upcase(SCM_CHAR(x))) < scm_upcase(SCM_CHAR(y))); |
| 139 | } |
| 140 | #undef FUNC_NAME |
| 141 | |
| 142 | SCM_DEFINE1 (scm_char_ci_leq_p, "char-ci<=?", scm_tc7_rpsubr, |
| 143 | (SCM x, SCM y), |
| 144 | "Return #t iff X is less than or equal to Y in the Ascii sequence ignoring case, else #f.") |
| 145 | #define FUNC_NAME s_scm_char_ci_leq_p |
| 146 | { |
| 147 | SCM_VALIDATE_CHAR (1,x); |
| 148 | SCM_VALIDATE_CHAR (2,y); |
| 149 | return SCM_BOOL(scm_upcase(SCM_CHAR(x)) <= scm_upcase(SCM_CHAR(y))); |
| 150 | } |
| 151 | #undef FUNC_NAME |
| 152 | |
| 153 | SCM_DEFINE1 (scm_char_ci_gr_p, "char-ci>?", scm_tc7_rpsubr, |
| 154 | (SCM x, SCM y), |
| 155 | "Return #t iff X is greater than Y in the Ascii sequence ignoring case, else #f.") |
| 156 | #define FUNC_NAME s_scm_char_ci_gr_p |
| 157 | { |
| 158 | SCM_VALIDATE_CHAR (1,x); |
| 159 | SCM_VALIDATE_CHAR (2,y); |
| 160 | return SCM_BOOL(scm_upcase(SCM_CHAR(x)) > scm_upcase(SCM_CHAR(y))); |
| 161 | } |
| 162 | #undef FUNC_NAME |
| 163 | |
| 164 | SCM_DEFINE1 (scm_char_ci_geq_p, "char-ci>=?", scm_tc7_rpsubr, |
| 165 | (SCM x, SCM y), |
| 166 | "Return #t iff X is greater than or equal to Y in the Ascii sequence ignoring case, else #f.") |
| 167 | #define FUNC_NAME s_scm_char_ci_geq_p |
| 168 | { |
| 169 | SCM_VALIDATE_CHAR (1,x); |
| 170 | SCM_VALIDATE_CHAR (2,y); |
| 171 | return SCM_BOOL(scm_upcase(SCM_CHAR(x)) >= scm_upcase(SCM_CHAR(y))); |
| 172 | } |
| 173 | #undef FUNC_NAME |
| 174 | |
| 175 | |
| 176 | SCM_DEFINE (scm_char_alphabetic_p, "char-alphabetic?", 1, 0, 0, |
| 177 | (SCM chr), |
| 178 | "Return #t iff CHR is alphabetic, else #f.\n" |
| 179 | "Alphabetic means the same thing as the isalpha C library function.") |
| 180 | #define FUNC_NAME s_scm_char_alphabetic_p |
| 181 | { |
| 182 | SCM_VALIDATE_CHAR (1,chr); |
| 183 | return SCM_BOOL(isascii(SCM_CHAR(chr)) && isalpha(SCM_CHAR(chr))); |
| 184 | } |
| 185 | #undef FUNC_NAME |
| 186 | |
| 187 | SCM_DEFINE (scm_char_numeric_p, "char-numeric?", 1, 0, 0, |
| 188 | (SCM chr), |
| 189 | "Return #t iff CHR is numeric, else #f.\n" |
| 190 | "Numeric means the same thing as the isdigit C library function.") |
| 191 | #define FUNC_NAME s_scm_char_numeric_p |
| 192 | { |
| 193 | SCM_VALIDATE_CHAR (1,chr); |
| 194 | return SCM_BOOL(isascii(SCM_CHAR(chr)) && isdigit(SCM_CHAR(chr))); |
| 195 | } |
| 196 | #undef FUNC_NAME |
| 197 | |
| 198 | SCM_DEFINE (scm_char_whitespace_p, "char-whitespace?", 1, 0, 0, |
| 199 | (SCM chr), |
| 200 | "Return #t iff CHR is whitespace, else #f.\n" |
| 201 | "Whitespace means the same thing as the isspace C library function.") |
| 202 | #define FUNC_NAME s_scm_char_whitespace_p |
| 203 | { |
| 204 | SCM_VALIDATE_CHAR (1,chr); |
| 205 | return SCM_BOOL(isascii(SCM_CHAR(chr)) && isspace(SCM_CHAR(chr))); |
| 206 | } |
| 207 | #undef FUNC_NAME |
| 208 | |
| 209 | |
| 210 | |
| 211 | SCM_DEFINE (scm_char_upper_case_p, "char-upper-case?", 1, 0, 0, |
| 212 | (SCM chr), |
| 213 | "Return #t iff CHR is uppercase, else #f.\n" |
| 214 | "Uppercase means the same thing as the isupper C library function.") |
| 215 | #define FUNC_NAME s_scm_char_upper_case_p |
| 216 | { |
| 217 | SCM_VALIDATE_CHAR (1,chr); |
| 218 | return SCM_BOOL(isascii(SCM_CHAR(chr)) && isupper(SCM_CHAR(chr))); |
| 219 | } |
| 220 | #undef FUNC_NAME |
| 221 | |
| 222 | |
| 223 | SCM_DEFINE (scm_char_lower_case_p, "char-lower-case?", 1, 0, 0, |
| 224 | (SCM chr), |
| 225 | "Return #t iff CHR is lowercase, else #f.\n" |
| 226 | "Lowercase means the same thing as the islower C library function.") |
| 227 | #define FUNC_NAME s_scm_char_lower_case_p |
| 228 | { |
| 229 | SCM_VALIDATE_CHAR (1,chr); |
| 230 | return SCM_BOOL(isascii(SCM_CHAR(chr)) && islower(SCM_CHAR(chr))); |
| 231 | } |
| 232 | #undef FUNC_NAME |
| 233 | |
| 234 | |
| 235 | |
| 236 | SCM_DEFINE (scm_char_is_both_p, "char-is-both?", 1, 0, 0, |
| 237 | (SCM chr), |
| 238 | "Return #t iff CHR is either uppercase or lowercase, else #f.\n" |
| 239 | "Uppercase and lowercase are as defined by the isupper and islower\n" |
| 240 | "C library functions.") |
| 241 | #define FUNC_NAME s_scm_char_is_both_p |
| 242 | { |
| 243 | SCM_VALIDATE_CHAR (1,chr); |
| 244 | return SCM_BOOL(isascii(SCM_CHAR(chr)) && (isupper(SCM_CHAR(chr)) || islower(SCM_CHAR(chr)))); |
| 245 | } |
| 246 | #undef FUNC_NAME |
| 247 | |
| 248 | |
| 249 | |
| 250 | |
| 251 | SCM_DEFINE (scm_char_to_integer, "char->integer", 1, 0, 0, |
| 252 | (SCM chr), |
| 253 | "Return the number corresponding to ordinal position of CHR in the Ascii sequence.") |
| 254 | #define FUNC_NAME s_scm_char_to_integer |
| 255 | { |
| 256 | SCM_VALIDATE_CHAR (1,chr); |
| 257 | return scm_ulong2num((unsigned long)SCM_CHAR(chr)); |
| 258 | } |
| 259 | #undef FUNC_NAME |
| 260 | |
| 261 | |
| 262 | |
| 263 | SCM_DEFINE (scm_integer_to_char, "integer->char", 1, 0, 0, |
| 264 | (SCM n), |
| 265 | "Return the character at position N in the Ascii sequence.") |
| 266 | #define FUNC_NAME s_scm_integer_to_char |
| 267 | { |
| 268 | SCM_VALIDATE_INUM_RANGE (1, n, 0, 256); |
| 269 | return SCM_MAKE_CHAR (SCM_INUM (n)); |
| 270 | } |
| 271 | #undef FUNC_NAME |
| 272 | |
| 273 | |
| 274 | SCM_DEFINE (scm_char_upcase, "char-upcase", 1, 0, 0, |
| 275 | (SCM chr), |
| 276 | "Return the uppercase character version of CHR.") |
| 277 | #define FUNC_NAME s_scm_char_upcase |
| 278 | { |
| 279 | SCM_VALIDATE_CHAR (1,chr); |
| 280 | return SCM_MAKE_CHAR(scm_upcase(SCM_CHAR(chr))); |
| 281 | } |
| 282 | #undef FUNC_NAME |
| 283 | |
| 284 | |
| 285 | SCM_DEFINE (scm_char_downcase, "char-downcase", 1, 0, 0, |
| 286 | (SCM chr), |
| 287 | "Return the lowercase character version of CHR.") |
| 288 | #define FUNC_NAME s_scm_char_downcase |
| 289 | { |
| 290 | SCM_VALIDATE_CHAR (1,chr); |
| 291 | return SCM_MAKE_CHAR(scm_downcase(SCM_CHAR(chr))); |
| 292 | } |
| 293 | #undef FUNC_NAME |
| 294 | |
| 295 | \f |
| 296 | |
| 297 | |
| 298 | |
| 299 | static unsigned char scm_upcase_table[SCM_CHAR_CODE_LIMIT]; |
| 300 | static unsigned char scm_downcase_table[SCM_CHAR_CODE_LIMIT]; |
| 301 | static const unsigned char scm_lowers[] = "abcdefghijklmnopqrstuvwxyz"; |
| 302 | static const unsigned char scm_uppers[] = "ABCDEFGHIJKLMNOPQRSTUVWXYZ"; |
| 303 | |
| 304 | |
| 305 | void |
| 306 | scm_tables_prehistory () |
| 307 | { |
| 308 | int i; |
| 309 | for (i = 0; i < SCM_CHAR_CODE_LIMIT; i++) |
| 310 | scm_upcase_table[i] = scm_downcase_table[i] = i; |
| 311 | for (i = 0; i < (int) (sizeof scm_lowers / sizeof (scm_lowers[0])); i++) |
| 312 | { |
| 313 | scm_upcase_table[scm_lowers[i]] = scm_uppers[i]; |
| 314 | scm_downcase_table[scm_uppers[i]] = scm_lowers[i]; |
| 315 | } |
| 316 | } |
| 317 | |
| 318 | |
| 319 | int |
| 320 | scm_upcase (unsigned int c) |
| 321 | { |
| 322 | if (c < sizeof (scm_upcase_table)) |
| 323 | return scm_upcase_table[c]; |
| 324 | else |
| 325 | return c; |
| 326 | } |
| 327 | |
| 328 | |
| 329 | int |
| 330 | scm_downcase (unsigned int c) |
| 331 | { |
| 332 | if (c < sizeof (scm_downcase_table)) |
| 333 | return scm_downcase_table[c]; |
| 334 | else |
| 335 | return c; |
| 336 | } |
| 337 | |
| 338 | |
| 339 | #ifdef _DCC |
| 340 | # define ASCII |
| 341 | #else |
| 342 | # if (('\n'=='\025') && (' '=='\100') && ('a'=='\201') && ('A'=='\301')) |
| 343 | # define EBCDIC |
| 344 | # endif /* (('\n'=='\025') && (' '=='\100') && ('a'=='\201') && ('A'=='\301')) */ |
| 345 | # if (('\n'=='\012') && (' '=='\040') && ('a'=='\141') && ('A'=='\101')) |
| 346 | # define ASCII |
| 347 | # endif /* (('\n'=='\012') && (' '=='\040') && ('a'=='\141') && ('A'=='\101')) */ |
| 348 | #endif /* def _DCC */ |
| 349 | |
| 350 | |
| 351 | #ifdef EBCDIC |
| 352 | char *const scm_charnames[] = |
| 353 | { |
| 354 | "nul","soh","stx","etx", "pf", "ht", "lc","del", |
| 355 | 0 , 0 ,"smm", "vt", "ff", "cr", "so", "si", |
| 356 | "dle","dc1","dc2","dc3","res", "nl", "bs", "il", |
| 357 | "can", "em", "cc", 0 ,"ifs","igs","irs","ius", |
| 358 | "ds","sos", "fs", 0 ,"byp", "lf","eob","pre", |
| 359 | 0 , 0 , "sm", 0 , 0 ,"enq","ack","bel", |
| 360 | 0 , 0 ,"syn", 0 , "pn", "rs", "uc","eot", |
| 361 | 0 , 0 , 0 , 0 ,"dc4","nak", 0 ,"sub", |
| 362 | "space", scm_s_newline, "tab", "backspace", "return", "page", "null"}; |
| 363 | |
| 364 | const char scm_charnums[] = |
| 365 | "\000\001\002\003\004\005\006\007\ |
| 366 | \010\011\012\013\014\015\016\017\ |
| 367 | \020\021\022\023\024\025\026\027\ |
| 368 | \030\031\032\033\034\035\036\037\ |
| 369 | \040\041\042\043\044\045\046\047\ |
| 370 | \050\051\052\053\054\055\056\057\ |
| 371 | \060\061\062\063\064\065\066\067\ |
| 372 | \070\071\072\073\074\075\076\077\ |
| 373 | \n\t\b\r\f\0"; |
| 374 | #endif /* def EBCDIC */ |
| 375 | #ifdef ASCII |
| 376 | char *const scm_charnames[] = |
| 377 | { |
| 378 | "nul","soh","stx","etx","eot","enq","ack","bel", |
| 379 | "bs", "ht", "newline", "vt", "np", "cr", "so", "si", |
| 380 | "dle","dc1","dc2","dc3","dc4","nak","syn","etb", |
| 381 | "can", "em","sub","esc", "fs", "gs", "rs", "us", |
| 382 | "space", "nl", "tab", "backspace", "return", "page", "null", "del"}; |
| 383 | const char scm_charnums[] = |
| 384 | "\000\001\002\003\004\005\006\007\ |
| 385 | \010\011\012\013\014\015\016\017\ |
| 386 | \020\021\022\023\024\025\026\027\ |
| 387 | \030\031\032\033\034\035\036\037\ |
| 388 | \n\t\b\r\f\0\177"; |
| 389 | #endif /* def ASCII */ |
| 390 | |
| 391 | int scm_n_charnames = sizeof (scm_charnames) / sizeof (char *); |
| 392 | |
| 393 | |
| 394 | \f |
| 395 | |
| 396 | |
| 397 | void |
| 398 | scm_init_chars () |
| 399 | { |
| 400 | #include "chars.x" |
| 401 | } |
| 402 | |