lh | 9ed821d | 2023-04-07 01:36:19 -0700 | [diff] [blame^] | 1 | /* Copyright (C) 1991-2015 Free Software Foundation, Inc. |
| 2 | This file is part of the GNU C Library. |
| 3 | |
| 4 | The GNU C Library is free software; you can redistribute it and/or |
| 5 | modify it under the terms of the GNU Lesser General Public |
| 6 | License as published by the Free Software Foundation; either |
| 7 | version 2.1 of the License, or (at your option) any later version. |
| 8 | |
| 9 | The GNU C Library 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 GNU |
| 12 | Lesser General Public License for more details. |
| 13 | |
| 14 | You should have received a copy of the GNU Lesser General Public |
| 15 | License along with the GNU C Library; if not, see |
| 16 | <http://www.gnu.org/licenses/>. */ |
| 17 | |
| 18 | #include <assert.h> |
| 19 | #include <errno.h> |
| 20 | #include <limits.h> |
| 21 | #include <ctype.h> |
| 22 | #include <stdarg.h> |
| 23 | #include <stdbool.h> |
| 24 | #include <stdio.h> |
| 25 | #include <stdint.h> |
| 26 | #include <stdlib.h> |
| 27 | #include <string.h> |
| 28 | #include <wchar.h> |
| 29 | #include <wctype.h> |
| 30 | #include <bits/libc-lock.h> |
| 31 | #include <locale/localeinfo.h> |
| 32 | |
| 33 | #ifdef __GNUC__ |
| 34 | # define HAVE_LONGLONG |
| 35 | # define LONGLONG long long |
| 36 | #else |
| 37 | # define LONGLONG long |
| 38 | #endif |
| 39 | |
| 40 | /* Determine whether we have to handle `long long' at all. */ |
| 41 | #if LONG_MAX == LONG_LONG_MAX |
| 42 | # define need_longlong 0 |
| 43 | #else |
| 44 | # define need_longlong 1 |
| 45 | #endif |
| 46 | |
| 47 | /* Determine whether we have to handle `long'. */ |
| 48 | #if INT_MAX == LONG_MAX |
| 49 | # define need_long 0 |
| 50 | #else |
| 51 | # define need_long 1 |
| 52 | #endif |
| 53 | |
| 54 | /* Those are flags in the conversion format. */ |
| 55 | #define LONG 0x0001 /* l: long or double */ |
| 56 | #define LONGDBL 0x0002 /* L: long long or long double */ |
| 57 | #define SHORT 0x0004 /* h: short */ |
| 58 | #define SUPPRESS 0x0008 /* *: suppress assignment */ |
| 59 | #define POINTER 0x0010 /* weird %p pointer (`fake hex') */ |
| 60 | #define NOSKIP 0x0020 /* do not skip blanks */ |
| 61 | #define NUMBER_SIGNED 0x0040 /* signed integer */ |
| 62 | #define GROUP 0x0080 /* ': group numbers */ |
| 63 | #define GNU_MALLOC 0x0100 /* a: malloc strings */ |
| 64 | #define CHAR 0x0200 /* hh: char */ |
| 65 | #define I18N 0x0400 /* I: use locale's digits */ |
| 66 | #define HEXA_FLOAT 0x0800 /* hexadecimal float */ |
| 67 | #define READ_POINTER 0x1000 /* this is a pointer value */ |
| 68 | #define POSIX_MALLOC 0x2000 /* m: malloc strings */ |
| 69 | #define MALLOC (GNU_MALLOC | POSIX_MALLOC) |
| 70 | |
| 71 | #include <locale/localeinfo.h> |
| 72 | #include <libioP.h> |
| 73 | #include <libio.h> |
| 74 | |
| 75 | #undef va_list |
| 76 | #define va_list _IO_va_list |
| 77 | |
| 78 | #ifdef COMPILE_WSCANF |
| 79 | # define ungetc(c, s) ((void) (c == WEOF \ |
| 80 | || (--read_in, \ |
| 81 | _IO_sputbackwc (s, c)))) |
| 82 | # define ungetc_not_eof(c, s) ((void) (--read_in, \ |
| 83 | _IO_sputbackwc (s, c))) |
| 84 | # define inchar() (c == WEOF ? ((errno = inchar_errno), WEOF) \ |
| 85 | : ((c = _IO_getwc_unlocked (s)), \ |
| 86 | (void) (c != WEOF \ |
| 87 | ? ++read_in \ |
| 88 | : (size_t) (inchar_errno = errno)), c)) |
| 89 | |
| 90 | # define MEMCPY(d, s, n) __wmemcpy (d, s, n) |
| 91 | # define ISSPACE(Ch) iswspace (Ch) |
| 92 | # define ISDIGIT(Ch) iswdigit (Ch) |
| 93 | # define ISXDIGIT(Ch) iswxdigit (Ch) |
| 94 | # define TOLOWER(Ch) towlower (Ch) |
| 95 | # define ORIENT if (_IO_fwide (s, 1) != 1) return WEOF |
| 96 | # define __strtoll_internal __wcstoll_internal |
| 97 | # define __strtoull_internal __wcstoull_internal |
| 98 | # define __strtol_internal __wcstol_internal |
| 99 | # define __strtoul_internal __wcstoul_internal |
| 100 | # define __strtold_internal __wcstold_internal |
| 101 | # define __strtod_internal __wcstod_internal |
| 102 | # define __strtof_internal __wcstof_internal |
| 103 | |
| 104 | # define L_(Str) L##Str |
| 105 | # define CHAR_T wchar_t |
| 106 | # define UCHAR_T unsigned int |
| 107 | # define WINT_T wint_t |
| 108 | # undef EOF |
| 109 | # define EOF WEOF |
| 110 | #else |
| 111 | # define ungetc(c, s) ((void) ((int) c == EOF \ |
| 112 | || (--read_in, \ |
| 113 | _IO_sputbackc (s, (unsigned char) c)))) |
| 114 | # define ungetc_not_eof(c, s) ((void) (--read_in, \ |
| 115 | _IO_sputbackc (s, (unsigned char) c))) |
| 116 | # define inchar() (c == EOF ? ((errno = inchar_errno), EOF) \ |
| 117 | : ((c = _IO_getc_unlocked (s)), \ |
| 118 | (void) (c != EOF \ |
| 119 | ? ++read_in \ |
| 120 | : (size_t) (inchar_errno = errno)), c)) |
| 121 | # define MEMCPY(d, s, n) memcpy (d, s, n) |
| 122 | # define ISSPACE(Ch) __isspace_l (Ch, loc) |
| 123 | # define ISDIGIT(Ch) __isdigit_l (Ch, loc) |
| 124 | # define ISXDIGIT(Ch) __isxdigit_l (Ch, loc) |
| 125 | # define TOLOWER(Ch) __tolower_l ((unsigned char) (Ch), loc) |
| 126 | # define ORIENT if (_IO_vtable_offset (s) == 0 \ |
| 127 | && _IO_fwide (s, -1) != -1) \ |
| 128 | return EOF |
| 129 | |
| 130 | # define L_(Str) Str |
| 131 | # define CHAR_T char |
| 132 | # define UCHAR_T unsigned char |
| 133 | # define WINT_T int |
| 134 | #endif |
| 135 | |
| 136 | #define encode_error() do { \ |
| 137 | errval = 4; \ |
| 138 | __set_errno (EILSEQ); \ |
| 139 | goto errout; \ |
| 140 | } while (0) |
| 141 | #define conv_error() do { \ |
| 142 | errval = 2; \ |
| 143 | goto errout; \ |
| 144 | } while (0) |
| 145 | #define input_error() do { \ |
| 146 | errval = 1; \ |
| 147 | if (done == 0) done = EOF; \ |
| 148 | goto errout; \ |
| 149 | } while (0) |
| 150 | #define add_ptr_to_free(ptr) \ |
| 151 | do \ |
| 152 | { \ |
| 153 | if (ptrs_to_free == NULL \ |
| 154 | || ptrs_to_free->count == (sizeof (ptrs_to_free->ptrs) \ |
| 155 | / sizeof (ptrs_to_free->ptrs[0]))) \ |
| 156 | { \ |
| 157 | struct ptrs_to_free *new_ptrs = alloca (sizeof (*ptrs_to_free)); \ |
| 158 | new_ptrs->count = 0; \ |
| 159 | new_ptrs->next = ptrs_to_free; \ |
| 160 | ptrs_to_free = new_ptrs; \ |
| 161 | } \ |
| 162 | ptrs_to_free->ptrs[ptrs_to_free->count++] = (ptr); \ |
| 163 | } \ |
| 164 | while (0) |
| 165 | #define ARGCHECK(s, format) \ |
| 166 | do \ |
| 167 | { \ |
| 168 | /* Check file argument for consistence. */ \ |
| 169 | CHECK_FILE (s, EOF); \ |
| 170 | if (s->_flags & _IO_NO_READS) \ |
| 171 | { \ |
| 172 | __set_errno (EBADF); \ |
| 173 | return EOF; \ |
| 174 | } \ |
| 175 | else if (format == NULL) \ |
| 176 | { \ |
| 177 | MAYBE_SET_EINVAL; \ |
| 178 | return EOF; \ |
| 179 | } \ |
| 180 | } while (0) |
| 181 | #define LOCK_STREAM(S) \ |
| 182 | __libc_cleanup_region_start (1, (void (*) (void *)) &_IO_funlockfile, (S)); \ |
| 183 | _IO_flockfile (S) |
| 184 | #define UNLOCK_STREAM(S) \ |
| 185 | _IO_funlockfile (S); \ |
| 186 | __libc_cleanup_region_end (0) |
| 187 | |
| 188 | struct ptrs_to_free |
| 189 | { |
| 190 | size_t count; |
| 191 | struct ptrs_to_free *next; |
| 192 | char **ptrs[32]; |
| 193 | }; |
| 194 | |
| 195 | /* Read formatted input from S according to the format string |
| 196 | FORMAT, using the argument list in ARG. |
| 197 | Return the number of assignments made, or -1 for an input error. */ |
| 198 | #ifdef COMPILE_WSCANF |
| 199 | int |
| 200 | _IO_vfwscanf (_IO_FILE *s, const wchar_t *format, _IO_va_list argptr, |
| 201 | int *errp) |
| 202 | #else |
| 203 | int |
| 204 | _IO_vfscanf_internal (_IO_FILE *s, const char *format, _IO_va_list argptr, |
| 205 | int *errp) |
| 206 | #endif |
| 207 | { |
| 208 | va_list arg; |
| 209 | const CHAR_T *f = format; |
| 210 | UCHAR_T fc; /* Current character of the format. */ |
| 211 | WINT_T done = 0; /* Assignments done. */ |
| 212 | size_t read_in = 0; /* Chars read in. */ |
| 213 | WINT_T c = 0; /* Last char read. */ |
| 214 | int width; /* Maximum field width. */ |
| 215 | int flags; /* Modifiers for current format element. */ |
| 216 | int errval = 0; |
| 217 | #ifndef COMPILE_WSCANF |
| 218 | __locale_t loc = _NL_CURRENT_LOCALE; |
| 219 | struct __locale_data *const curctype = loc->__locales[LC_CTYPE]; |
| 220 | #endif |
| 221 | |
| 222 | /* Errno of last failed inchar call. */ |
| 223 | int inchar_errno = 0; |
| 224 | /* Status for reading F-P nums. */ |
| 225 | char got_digit, got_dot, got_e, negative; |
| 226 | /* If a [...] is a [^...]. */ |
| 227 | CHAR_T not_in; |
| 228 | #define exp_char not_in |
| 229 | /* Base for integral numbers. */ |
| 230 | int base; |
| 231 | /* Decimal point character. */ |
| 232 | #ifdef COMPILE_WSCANF |
| 233 | wint_t decimal; |
| 234 | #else |
| 235 | const char *decimal; |
| 236 | #endif |
| 237 | /* The thousands character of the current locale. */ |
| 238 | #ifdef COMPILE_WSCANF |
| 239 | wint_t thousands; |
| 240 | #else |
| 241 | const char *thousands; |
| 242 | #endif |
| 243 | struct ptrs_to_free *ptrs_to_free = NULL; |
| 244 | /* State for the conversions. */ |
| 245 | mbstate_t state; |
| 246 | /* Integral holding variables. */ |
| 247 | union |
| 248 | { |
| 249 | long long int q; |
| 250 | unsigned long long int uq; |
| 251 | long int l; |
| 252 | unsigned long int ul; |
| 253 | } num; |
| 254 | /* Character-buffer pointer. */ |
| 255 | char *str = NULL; |
| 256 | wchar_t *wstr = NULL; |
| 257 | char **strptr = NULL; |
| 258 | ssize_t strsize = 0; |
| 259 | /* We must not react on white spaces immediately because they can |
| 260 | possibly be matched even if in the input stream no character is |
| 261 | available anymore. */ |
| 262 | int skip_space = 0; |
| 263 | /* Workspace. */ |
| 264 | CHAR_T *tw; /* Temporary pointer. */ |
| 265 | CHAR_T *wp = NULL; /* Workspace. */ |
| 266 | size_t wpmax = 0; /* Maximal size of workspace. */ |
| 267 | size_t wpsize; /* Currently used bytes in workspace. */ |
| 268 | bool use_malloc = false; |
| 269 | #define ADDW(Ch) \ |
| 270 | do \ |
| 271 | { \ |
| 272 | if (__glibc_unlikely (wpsize == wpmax)) \ |
| 273 | { \ |
| 274 | CHAR_T *old = wp; \ |
| 275 | bool fits = __glibc_likely (wpmax <= SIZE_MAX / sizeof (CHAR_T) / 2); \ |
| 276 | size_t wpneed = MAX (UCHAR_MAX + 1, 2 * wpmax); \ |
| 277 | size_t newsize = fits ? wpneed * sizeof (CHAR_T) : SIZE_MAX; \ |
| 278 | if (!__libc_use_alloca (newsize)) \ |
| 279 | { \ |
| 280 | wp = realloc (use_malloc ? wp : NULL, newsize); \ |
| 281 | if (wp == NULL) \ |
| 282 | { \ |
| 283 | if (use_malloc) \ |
| 284 | free (old); \ |
| 285 | done = EOF; \ |
| 286 | goto errout; \ |
| 287 | } \ |
| 288 | if (! use_malloc) \ |
| 289 | MEMCPY (wp, old, wpsize); \ |
| 290 | wpmax = wpneed; \ |
| 291 | use_malloc = true; \ |
| 292 | } \ |
| 293 | else \ |
| 294 | { \ |
| 295 | size_t s = wpmax * sizeof (CHAR_T); \ |
| 296 | wp = (CHAR_T *) extend_alloca (wp, s, newsize); \ |
| 297 | wpmax = s / sizeof (CHAR_T); \ |
| 298 | if (old != NULL) \ |
| 299 | MEMCPY (wp, old, wpsize); \ |
| 300 | } \ |
| 301 | } \ |
| 302 | wp[wpsize++] = (Ch); \ |
| 303 | } \ |
| 304 | while (0) |
| 305 | |
| 306 | #ifdef __va_copy |
| 307 | __va_copy (arg, argptr); |
| 308 | #else |
| 309 | arg = (va_list) argptr; |
| 310 | #endif |
| 311 | |
| 312 | #ifdef ORIENT |
| 313 | ORIENT; |
| 314 | #endif |
| 315 | |
| 316 | ARGCHECK (s, format); |
| 317 | |
| 318 | { |
| 319 | #ifndef COMPILE_WSCANF |
| 320 | struct __locale_data *const curnumeric = loc->__locales[LC_NUMERIC]; |
| 321 | #endif |
| 322 | |
| 323 | /* Figure out the decimal point character. */ |
| 324 | #ifdef COMPILE_WSCANF |
| 325 | decimal = _NL_CURRENT_WORD (LC_NUMERIC, _NL_NUMERIC_DECIMAL_POINT_WC); |
| 326 | #else |
| 327 | decimal = curnumeric->values[_NL_ITEM_INDEX (DECIMAL_POINT)].string; |
| 328 | #endif |
| 329 | /* Figure out the thousands separator character. */ |
| 330 | #ifdef COMPILE_WSCANF |
| 331 | thousands = _NL_CURRENT_WORD (LC_NUMERIC, _NL_NUMERIC_THOUSANDS_SEP_WC); |
| 332 | #else |
| 333 | thousands = curnumeric->values[_NL_ITEM_INDEX (THOUSANDS_SEP)].string; |
| 334 | if (*thousands == '\0') |
| 335 | thousands = NULL; |
| 336 | #endif |
| 337 | } |
| 338 | |
| 339 | /* Lock the stream. */ |
| 340 | LOCK_STREAM (s); |
| 341 | |
| 342 | |
| 343 | #ifndef COMPILE_WSCANF |
| 344 | /* From now on we use `state' to convert the format string. */ |
| 345 | memset (&state, '\0', sizeof (state)); |
| 346 | #endif |
| 347 | |
| 348 | /* Run through the format string. */ |
| 349 | while (*f != '\0') |
| 350 | { |
| 351 | unsigned int argpos; |
| 352 | /* Extract the next argument, which is of type TYPE. |
| 353 | For a %N$... spec, this is the Nth argument from the beginning; |
| 354 | otherwise it is the next argument after the state now in ARG. */ |
| 355 | #ifdef __va_copy |
| 356 | # define ARG(type) (argpos == 0 ? va_arg (arg, type) : \ |
| 357 | ({ unsigned int pos = argpos; \ |
| 358 | va_list arg; \ |
| 359 | __va_copy (arg, argptr); \ |
| 360 | while (--pos > 0) \ |
| 361 | (void) va_arg (arg, void *); \ |
| 362 | va_arg (arg, type); \ |
| 363 | })) |
| 364 | #else |
| 365 | # if 0 |
| 366 | /* XXX Possible optimization. */ |
| 367 | # define ARG(type) (argpos == 0 ? va_arg (arg, type) : \ |
| 368 | ({ va_list arg = (va_list) argptr; \ |
| 369 | arg = (va_list) ((char *) arg \ |
| 370 | + (argpos - 1) \ |
| 371 | * __va_rounded_size (void *)); \ |
| 372 | va_arg (arg, type); \ |
| 373 | })) |
| 374 | # else |
| 375 | # define ARG(type) (argpos == 0 ? va_arg (arg, type) : \ |
| 376 | ({ unsigned int pos = argpos; \ |
| 377 | va_list arg = (va_list) argptr; \ |
| 378 | while (--pos > 0) \ |
| 379 | (void) va_arg (arg, void *); \ |
| 380 | va_arg (arg, type); \ |
| 381 | })) |
| 382 | # endif |
| 383 | #endif |
| 384 | |
| 385 | #ifndef COMPILE_WSCANF |
| 386 | if (!isascii ((unsigned char) *f)) |
| 387 | { |
| 388 | /* Non-ASCII, may be a multibyte. */ |
| 389 | int len = __mbrlen (f, strlen (f), &state); |
| 390 | if (len > 0) |
| 391 | { |
| 392 | do |
| 393 | { |
| 394 | c = inchar (); |
| 395 | if (__glibc_unlikely (c == EOF)) |
| 396 | input_error (); |
| 397 | else if (c != (unsigned char) *f++) |
| 398 | { |
| 399 | ungetc_not_eof (c, s); |
| 400 | conv_error (); |
| 401 | } |
| 402 | } |
| 403 | while (--len > 0); |
| 404 | continue; |
| 405 | } |
| 406 | } |
| 407 | #endif |
| 408 | |
| 409 | fc = *f++; |
| 410 | if (fc != '%') |
| 411 | { |
| 412 | /* Remember to skip spaces. */ |
| 413 | if (ISSPACE (fc)) |
| 414 | { |
| 415 | skip_space = 1; |
| 416 | continue; |
| 417 | } |
| 418 | |
| 419 | /* Read a character. */ |
| 420 | c = inchar (); |
| 421 | |
| 422 | /* Characters other than format specs must just match. */ |
| 423 | if (__glibc_unlikely (c == EOF)) |
| 424 | input_error (); |
| 425 | |
| 426 | /* We saw white space char as the last character in the format |
| 427 | string. Now it's time to skip all leading white space. */ |
| 428 | if (skip_space) |
| 429 | { |
| 430 | while (ISSPACE (c)) |
| 431 | if (__glibc_unlikely (inchar () == EOF)) |
| 432 | input_error (); |
| 433 | skip_space = 0; |
| 434 | } |
| 435 | |
| 436 | if (__glibc_unlikely (c != fc)) |
| 437 | { |
| 438 | ungetc (c, s); |
| 439 | conv_error (); |
| 440 | } |
| 441 | |
| 442 | continue; |
| 443 | } |
| 444 | |
| 445 | /* This is the start of the conversion string. */ |
| 446 | flags = 0; |
| 447 | |
| 448 | /* Initialize state of modifiers. */ |
| 449 | argpos = 0; |
| 450 | |
| 451 | /* Prepare temporary buffer. */ |
| 452 | wpsize = 0; |
| 453 | |
| 454 | /* Check for a positional parameter specification. */ |
| 455 | if (ISDIGIT ((UCHAR_T) *f)) |
| 456 | { |
| 457 | argpos = (UCHAR_T) *f++ - L_('0'); |
| 458 | while (ISDIGIT ((UCHAR_T) *f)) |
| 459 | argpos = argpos * 10 + ((UCHAR_T) *f++ - L_('0')); |
| 460 | if (*f == L_('$')) |
| 461 | ++f; |
| 462 | else |
| 463 | { |
| 464 | /* Oops; that was actually the field width. */ |
| 465 | width = argpos; |
| 466 | argpos = 0; |
| 467 | goto got_width; |
| 468 | } |
| 469 | } |
| 470 | |
| 471 | /* Check for the assignment-suppressing, the number grouping flag, |
| 472 | and the signal to use the locale's digit representation. */ |
| 473 | while (*f == L_('*') || *f == L_('\'') || *f == L_('I')) |
| 474 | switch (*f++) |
| 475 | { |
| 476 | case L_('*'): |
| 477 | flags |= SUPPRESS; |
| 478 | break; |
| 479 | case L_('\''): |
| 480 | #ifdef COMPILE_WSCANF |
| 481 | if (thousands != L'\0') |
| 482 | #else |
| 483 | if (thousands != NULL) |
| 484 | #endif |
| 485 | flags |= GROUP; |
| 486 | break; |
| 487 | case L_('I'): |
| 488 | flags |= I18N; |
| 489 | break; |
| 490 | } |
| 491 | |
| 492 | /* Find the maximum field width. */ |
| 493 | width = 0; |
| 494 | while (ISDIGIT ((UCHAR_T) *f)) |
| 495 | { |
| 496 | width *= 10; |
| 497 | width += (UCHAR_T) *f++ - L_('0'); |
| 498 | } |
| 499 | got_width: |
| 500 | if (width == 0) |
| 501 | width = -1; |
| 502 | |
| 503 | /* Check for type modifiers. */ |
| 504 | switch (*f++) |
| 505 | { |
| 506 | case L_('h'): |
| 507 | /* ints are short ints or chars. */ |
| 508 | if (*f == L_('h')) |
| 509 | { |
| 510 | ++f; |
| 511 | flags |= CHAR; |
| 512 | } |
| 513 | else |
| 514 | flags |= SHORT; |
| 515 | break; |
| 516 | case L_('l'): |
| 517 | if (*f == L_('l')) |
| 518 | { |
| 519 | /* A double `l' is equivalent to an `L'. */ |
| 520 | ++f; |
| 521 | flags |= LONGDBL | LONG; |
| 522 | } |
| 523 | else |
| 524 | /* ints are long ints. */ |
| 525 | flags |= LONG; |
| 526 | break; |
| 527 | case L_('q'): |
| 528 | case L_('L'): |
| 529 | /* doubles are long doubles, and ints are long long ints. */ |
| 530 | flags |= LONGDBL | LONG; |
| 531 | break; |
| 532 | case L_('a'): |
| 533 | /* The `a' is used as a flag only if followed by `s', `S' or |
| 534 | `['. */ |
| 535 | if (*f != L_('s') && *f != L_('S') && *f != L_('[')) |
| 536 | { |
| 537 | --f; |
| 538 | break; |
| 539 | } |
| 540 | /* In __isoc99_*scanf %as, %aS and %a[ extension is not |
| 541 | supported at all. */ |
| 542 | if (s->_flags2 & _IO_FLAGS2_SCANF_STD) |
| 543 | { |
| 544 | --f; |
| 545 | break; |
| 546 | } |
| 547 | /* String conversions (%s, %[) take a `char **' |
| 548 | arg and fill it in with a malloc'd pointer. */ |
| 549 | flags |= GNU_MALLOC; |
| 550 | break; |
| 551 | case L_('m'): |
| 552 | flags |= POSIX_MALLOC; |
| 553 | if (*f == L_('l')) |
| 554 | { |
| 555 | ++f; |
| 556 | flags |= LONG; |
| 557 | } |
| 558 | break; |
| 559 | case L_('z'): |
| 560 | if (need_longlong && sizeof (size_t) > sizeof (unsigned long int)) |
| 561 | flags |= LONGDBL; |
| 562 | else if (sizeof (size_t) > sizeof (unsigned int)) |
| 563 | flags |= LONG; |
| 564 | break; |
| 565 | case L_('j'): |
| 566 | if (need_longlong && sizeof (uintmax_t) > sizeof (unsigned long int)) |
| 567 | flags |= LONGDBL; |
| 568 | else if (sizeof (uintmax_t) > sizeof (unsigned int)) |
| 569 | flags |= LONG; |
| 570 | break; |
| 571 | case L_('t'): |
| 572 | if (need_longlong && sizeof (ptrdiff_t) > sizeof (long int)) |
| 573 | flags |= LONGDBL; |
| 574 | else if (sizeof (ptrdiff_t) > sizeof (int)) |
| 575 | flags |= LONG; |
| 576 | break; |
| 577 | default: |
| 578 | /* Not a recognized modifier. Backup. */ |
| 579 | --f; |
| 580 | break; |
| 581 | } |
| 582 | |
| 583 | /* End of the format string? */ |
| 584 | if (__glibc_unlikely (*f == L_('\0'))) |
| 585 | conv_error (); |
| 586 | |
| 587 | /* Find the conversion specifier. */ |
| 588 | fc = *f++; |
| 589 | if (skip_space || (fc != L_('[') && fc != L_('c') |
| 590 | && fc != L_('C') && fc != L_('n'))) |
| 591 | { |
| 592 | /* Eat whitespace. */ |
| 593 | int save_errno = errno; |
| 594 | __set_errno (0); |
| 595 | do |
| 596 | /* We add the additional test for EOF here since otherwise |
| 597 | inchar will restore the old errno value which might be |
| 598 | EINTR but does not indicate an interrupt since nothing |
| 599 | was read at this time. */ |
| 600 | if (__builtin_expect ((c == EOF || inchar () == EOF) |
| 601 | && errno == EINTR, 0)) |
| 602 | input_error (); |
| 603 | while (ISSPACE (c)); |
| 604 | __set_errno (save_errno); |
| 605 | ungetc (c, s); |
| 606 | skip_space = 0; |
| 607 | } |
| 608 | |
| 609 | switch (fc) |
| 610 | { |
| 611 | case L_('%'): /* Must match a literal '%'. */ |
| 612 | c = inchar (); |
| 613 | if (__glibc_unlikely (c == EOF)) |
| 614 | input_error (); |
| 615 | if (__glibc_unlikely (c != fc)) |
| 616 | { |
| 617 | ungetc_not_eof (c, s); |
| 618 | conv_error (); |
| 619 | } |
| 620 | break; |
| 621 | |
| 622 | case L_('n'): /* Answer number of assignments done. */ |
| 623 | /* Corrigendum 1 to ISO C 1990 describes the allowed flags |
| 624 | with the 'n' conversion specifier. */ |
| 625 | if (!(flags & SUPPRESS)) |
| 626 | { |
| 627 | /* Don't count the read-ahead. */ |
| 628 | if (need_longlong && (flags & LONGDBL)) |
| 629 | *ARG (long long int *) = read_in; |
| 630 | else if (need_long && (flags & LONG)) |
| 631 | *ARG (long int *) = read_in; |
| 632 | else if (flags & SHORT) |
| 633 | *ARG (short int *) = read_in; |
| 634 | else if (!(flags & CHAR)) |
| 635 | *ARG (int *) = read_in; |
| 636 | else |
| 637 | *ARG (char *) = read_in; |
| 638 | |
| 639 | #ifdef NO_BUG_IN_ISO_C_CORRIGENDUM_1 |
| 640 | /* We have a severe problem here. The ISO C standard |
| 641 | contradicts itself in explaining the effect of the %n |
| 642 | format in `scanf'. While in ISO C:1990 and the ISO C |
| 643 | Amendement 1:1995 the result is described as |
| 644 | |
| 645 | Execution of a %n directive does not effect the |
| 646 | assignment count returned at the completion of |
| 647 | execution of the f(w)scanf function. |
| 648 | |
| 649 | in ISO C Corrigendum 1:1994 the following was added: |
| 650 | |
| 651 | Subclause 7.9.6.2 |
| 652 | Add the following fourth example: |
| 653 | In: |
| 654 | #include <stdio.h> |
| 655 | int d1, d2, n1, n2, i; |
| 656 | i = sscanf("123", "%d%n%n%d", &d1, &n1, &n2, &d2); |
| 657 | the value 123 is assigned to d1 and the value3 to n1. |
| 658 | Because %n can never get an input failure the value |
| 659 | of 3 is also assigned to n2. The value of d2 is not |
| 660 | affected. The value 3 is assigned to i. |
| 661 | |
| 662 | We go for now with the historically correct code from ISO C, |
| 663 | i.e., we don't count the %n assignments. When it ever |
| 664 | should proof to be wrong just remove the #ifdef above. */ |
| 665 | ++done; |
| 666 | #endif |
| 667 | } |
| 668 | break; |
| 669 | |
| 670 | case L_('c'): /* Match characters. */ |
| 671 | if ((flags & LONG) == 0) |
| 672 | { |
| 673 | if (width == -1) |
| 674 | width = 1; |
| 675 | |
| 676 | #define STRING_ARG(Str, Type, Width) \ |
| 677 | do if (!(flags & SUPPRESS)) \ |
| 678 | { \ |
| 679 | if (flags & MALLOC) \ |
| 680 | { \ |
| 681 | /* The string is to be stored in a malloc'd buffer. */ \ |
| 682 | /* For %mS using char ** is actually wrong, but \ |
| 683 | shouldn't make a difference on any arch glibc \ |
| 684 | supports and would unnecessarily complicate \ |
| 685 | things. */ \ |
| 686 | strptr = ARG (char **); \ |
| 687 | if (strptr == NULL) \ |
| 688 | conv_error (); \ |
| 689 | /* Allocate an initial buffer. */ \ |
| 690 | strsize = Width; \ |
| 691 | *strptr = (char *) malloc (strsize * sizeof (Type)); \ |
| 692 | Str = (Type *) *strptr; \ |
| 693 | if (Str != NULL) \ |
| 694 | add_ptr_to_free (strptr); \ |
| 695 | else if (flags & POSIX_MALLOC) \ |
| 696 | { \ |
| 697 | done = EOF; \ |
| 698 | goto errout; \ |
| 699 | } \ |
| 700 | } \ |
| 701 | else \ |
| 702 | Str = ARG (Type *); \ |
| 703 | if (Str == NULL) \ |
| 704 | conv_error (); \ |
| 705 | } while (0) |
| 706 | #ifdef COMPILE_WSCANF |
| 707 | STRING_ARG (str, char, 100); |
| 708 | #else |
| 709 | STRING_ARG (str, char, (width > 1024 ? 1024 : width)); |
| 710 | #endif |
| 711 | |
| 712 | c = inchar (); |
| 713 | if (__glibc_unlikely (c == EOF)) |
| 714 | input_error (); |
| 715 | |
| 716 | #ifdef COMPILE_WSCANF |
| 717 | /* We have to convert the wide character(s) into multibyte |
| 718 | characters and store the result. */ |
| 719 | memset (&state, '\0', sizeof (state)); |
| 720 | |
| 721 | do |
| 722 | { |
| 723 | size_t n; |
| 724 | |
| 725 | if (!(flags & SUPPRESS) && (flags & POSIX_MALLOC) |
| 726 | && str + MB_CUR_MAX >= *strptr + strsize) |
| 727 | { |
| 728 | /* We have to enlarge the buffer if the `m' flag |
| 729 | was given. */ |
| 730 | size_t strleng = str - *strptr; |
| 731 | char *newstr; |
| 732 | |
| 733 | newstr = (char *) realloc (*strptr, strsize * 2); |
| 734 | if (newstr == NULL) |
| 735 | { |
| 736 | /* Can't allocate that much. Last-ditch effort. */ |
| 737 | newstr = (char *) realloc (*strptr, |
| 738 | strleng + MB_CUR_MAX); |
| 739 | if (newstr == NULL) |
| 740 | { |
| 741 | /* c can't have `a' flag, only `m'. */ |
| 742 | done = EOF; |
| 743 | goto errout; |
| 744 | } |
| 745 | else |
| 746 | { |
| 747 | *strptr = newstr; |
| 748 | str = newstr + strleng; |
| 749 | strsize = strleng + MB_CUR_MAX; |
| 750 | } |
| 751 | } |
| 752 | else |
| 753 | { |
| 754 | *strptr = newstr; |
| 755 | str = newstr + strleng; |
| 756 | strsize *= 2; |
| 757 | } |
| 758 | } |
| 759 | |
| 760 | n = __wcrtomb (!(flags & SUPPRESS) ? str : NULL, c, &state); |
| 761 | if (__glibc_unlikely (n == (size_t) -1)) |
| 762 | /* No valid wide character. */ |
| 763 | input_error (); |
| 764 | |
| 765 | /* Increment the output pointer. Even if we don't |
| 766 | write anything. */ |
| 767 | str += n; |
| 768 | } |
| 769 | while (--width > 0 && inchar () != EOF); |
| 770 | #else |
| 771 | if (!(flags & SUPPRESS)) |
| 772 | { |
| 773 | do |
| 774 | { |
| 775 | if ((flags & MALLOC) |
| 776 | && (char *) str == *strptr + strsize) |
| 777 | { |
| 778 | /* Enlarge the buffer. */ |
| 779 | size_t newsize |
| 780 | = strsize |
| 781 | + (strsize >= width ? width - 1 : strsize); |
| 782 | |
| 783 | str = (char *) realloc (*strptr, newsize); |
| 784 | if (str == NULL) |
| 785 | { |
| 786 | /* Can't allocate that much. Last-ditch |
| 787 | effort. */ |
| 788 | str = (char *) realloc (*strptr, strsize + 1); |
| 789 | if (str == NULL) |
| 790 | { |
| 791 | /* c can't have `a' flag, only `m'. */ |
| 792 | done = EOF; |
| 793 | goto errout; |
| 794 | } |
| 795 | else |
| 796 | { |
| 797 | *strptr = (char *) str; |
| 798 | str += strsize; |
| 799 | ++strsize; |
| 800 | } |
| 801 | } |
| 802 | else |
| 803 | { |
| 804 | *strptr = (char *) str; |
| 805 | str += strsize; |
| 806 | strsize = newsize; |
| 807 | } |
| 808 | } |
| 809 | *str++ = c; |
| 810 | } |
| 811 | while (--width > 0 && inchar () != EOF); |
| 812 | } |
| 813 | else |
| 814 | while (--width > 0 && inchar () != EOF); |
| 815 | #endif |
| 816 | |
| 817 | if (!(flags & SUPPRESS)) |
| 818 | { |
| 819 | if ((flags & MALLOC) && str - *strptr != strsize) |
| 820 | { |
| 821 | char *cp = (char *) realloc (*strptr, str - *strptr); |
| 822 | if (cp != NULL) |
| 823 | *strptr = cp; |
| 824 | } |
| 825 | strptr = NULL; |
| 826 | ++done; |
| 827 | } |
| 828 | |
| 829 | break; |
| 830 | } |
| 831 | /* FALLTHROUGH */ |
| 832 | case L_('C'): |
| 833 | if (width == -1) |
| 834 | width = 1; |
| 835 | |
| 836 | STRING_ARG (wstr, wchar_t, (width > 1024 ? 1024 : width)); |
| 837 | |
| 838 | c = inchar (); |
| 839 | if (__glibc_unlikely (c == EOF)) |
| 840 | input_error (); |
| 841 | |
| 842 | #ifdef COMPILE_WSCANF |
| 843 | /* Just store the incoming wide characters. */ |
| 844 | if (!(flags & SUPPRESS)) |
| 845 | { |
| 846 | do |
| 847 | { |
| 848 | if ((flags & MALLOC) |
| 849 | && wstr == (wchar_t *) *strptr + strsize) |
| 850 | { |
| 851 | size_t newsize |
| 852 | = strsize + (strsize > width ? width - 1 : strsize); |
| 853 | /* Enlarge the buffer. */ |
| 854 | wstr = (wchar_t *) realloc (*strptr, |
| 855 | newsize * sizeof (wchar_t)); |
| 856 | if (wstr == NULL) |
| 857 | { |
| 858 | /* Can't allocate that much. Last-ditch effort. */ |
| 859 | wstr = (wchar_t *) realloc (*strptr, |
| 860 | (strsize + 1) |
| 861 | * sizeof (wchar_t)); |
| 862 | if (wstr == NULL) |
| 863 | { |
| 864 | /* C or lc can't have `a' flag, only `m' |
| 865 | flag. */ |
| 866 | done = EOF; |
| 867 | goto errout; |
| 868 | } |
| 869 | else |
| 870 | { |
| 871 | *strptr = (char *) wstr; |
| 872 | wstr += strsize; |
| 873 | ++strsize; |
| 874 | } |
| 875 | } |
| 876 | else |
| 877 | { |
| 878 | *strptr = (char *) wstr; |
| 879 | wstr += strsize; |
| 880 | strsize = newsize; |
| 881 | } |
| 882 | } |
| 883 | *wstr++ = c; |
| 884 | } |
| 885 | while (--width > 0 && inchar () != EOF); |
| 886 | } |
| 887 | else |
| 888 | while (--width > 0 && inchar () != EOF); |
| 889 | #else |
| 890 | { |
| 891 | /* We have to convert the multibyte input sequence to wide |
| 892 | characters. */ |
| 893 | char buf[1]; |
| 894 | mbstate_t cstate; |
| 895 | |
| 896 | memset (&cstate, '\0', sizeof (cstate)); |
| 897 | |
| 898 | do |
| 899 | { |
| 900 | /* This is what we present the mbrtowc function first. */ |
| 901 | buf[0] = c; |
| 902 | |
| 903 | if (!(flags & SUPPRESS) && (flags & MALLOC) |
| 904 | && wstr == (wchar_t *) *strptr + strsize) |
| 905 | { |
| 906 | size_t newsize |
| 907 | = strsize + (strsize > width ? width - 1 : strsize); |
| 908 | /* Enlarge the buffer. */ |
| 909 | wstr = (wchar_t *) realloc (*strptr, |
| 910 | newsize * sizeof (wchar_t)); |
| 911 | if (wstr == NULL) |
| 912 | { |
| 913 | /* Can't allocate that much. Last-ditch effort. */ |
| 914 | wstr = (wchar_t *) realloc (*strptr, |
| 915 | ((strsize + 1) |
| 916 | * sizeof (wchar_t))); |
| 917 | if (wstr == NULL) |
| 918 | { |
| 919 | /* C or lc can't have `a' flag, only `m' flag. */ |
| 920 | done = EOF; |
| 921 | goto errout; |
| 922 | } |
| 923 | else |
| 924 | { |
| 925 | *strptr = (char *) wstr; |
| 926 | wstr += strsize; |
| 927 | ++strsize; |
| 928 | } |
| 929 | } |
| 930 | else |
| 931 | { |
| 932 | *strptr = (char *) wstr; |
| 933 | wstr += strsize; |
| 934 | strsize = newsize; |
| 935 | } |
| 936 | } |
| 937 | |
| 938 | while (1) |
| 939 | { |
| 940 | size_t n; |
| 941 | |
| 942 | n = __mbrtowc (!(flags & SUPPRESS) ? wstr : NULL, |
| 943 | buf, 1, &cstate); |
| 944 | |
| 945 | if (n == (size_t) -2) |
| 946 | { |
| 947 | /* Possibly correct character, just not enough |
| 948 | input. */ |
| 949 | if (__glibc_unlikely (inchar () == EOF)) |
| 950 | encode_error (); |
| 951 | |
| 952 | buf[0] = c; |
| 953 | continue; |
| 954 | } |
| 955 | |
| 956 | if (__glibc_unlikely (n != 1)) |
| 957 | encode_error (); |
| 958 | |
| 959 | /* We have a match. */ |
| 960 | break; |
| 961 | } |
| 962 | |
| 963 | /* Advance the result pointer. */ |
| 964 | ++wstr; |
| 965 | } |
| 966 | while (--width > 0 && inchar () != EOF); |
| 967 | } |
| 968 | #endif |
| 969 | |
| 970 | if (!(flags & SUPPRESS)) |
| 971 | { |
| 972 | if ((flags & MALLOC) && wstr - (wchar_t *) *strptr != strsize) |
| 973 | { |
| 974 | wchar_t *cp = (wchar_t *) realloc (*strptr, |
| 975 | ((wstr |
| 976 | - (wchar_t *) *strptr) |
| 977 | * sizeof (wchar_t))); |
| 978 | if (cp != NULL) |
| 979 | *strptr = (char *) cp; |
| 980 | } |
| 981 | strptr = NULL; |
| 982 | |
| 983 | ++done; |
| 984 | } |
| 985 | |
| 986 | break; |
| 987 | |
| 988 | case L_('s'): /* Read a string. */ |
| 989 | if (!(flags & LONG)) |
| 990 | { |
| 991 | STRING_ARG (str, char, 100); |
| 992 | |
| 993 | c = inchar (); |
| 994 | if (__glibc_unlikely (c == EOF)) |
| 995 | input_error (); |
| 996 | |
| 997 | #ifdef COMPILE_WSCANF |
| 998 | memset (&state, '\0', sizeof (state)); |
| 999 | #endif |
| 1000 | |
| 1001 | do |
| 1002 | { |
| 1003 | if (ISSPACE (c)) |
| 1004 | { |
| 1005 | ungetc_not_eof (c, s); |
| 1006 | break; |
| 1007 | } |
| 1008 | |
| 1009 | #ifdef COMPILE_WSCANF |
| 1010 | /* This is quite complicated. We have to convert the |
| 1011 | wide characters into multibyte characters and then |
| 1012 | store them. */ |
| 1013 | { |
| 1014 | size_t n; |
| 1015 | |
| 1016 | if (!(flags & SUPPRESS) && (flags & MALLOC) |
| 1017 | && str + MB_CUR_MAX >= *strptr + strsize) |
| 1018 | { |
| 1019 | /* We have to enlarge the buffer if the `a' or `m' |
| 1020 | flag was given. */ |
| 1021 | size_t strleng = str - *strptr; |
| 1022 | char *newstr; |
| 1023 | |
| 1024 | newstr = (char *) realloc (*strptr, strsize * 2); |
| 1025 | if (newstr == NULL) |
| 1026 | { |
| 1027 | /* Can't allocate that much. Last-ditch |
| 1028 | effort. */ |
| 1029 | newstr = (char *) realloc (*strptr, |
| 1030 | strleng + MB_CUR_MAX); |
| 1031 | if (newstr == NULL) |
| 1032 | { |
| 1033 | if (flags & POSIX_MALLOC) |
| 1034 | { |
| 1035 | done = EOF; |
| 1036 | goto errout; |
| 1037 | } |
| 1038 | /* We lose. Oh well. Terminate the |
| 1039 | string and stop converting, |
| 1040 | so at least we don't skip any input. */ |
| 1041 | ((char *) (*strptr))[strleng] = '\0'; |
| 1042 | strptr = NULL; |
| 1043 | ++done; |
| 1044 | conv_error (); |
| 1045 | } |
| 1046 | else |
| 1047 | { |
| 1048 | *strptr = newstr; |
| 1049 | str = newstr + strleng; |
| 1050 | strsize = strleng + MB_CUR_MAX; |
| 1051 | } |
| 1052 | } |
| 1053 | else |
| 1054 | { |
| 1055 | *strptr = newstr; |
| 1056 | str = newstr + strleng; |
| 1057 | strsize *= 2; |
| 1058 | } |
| 1059 | } |
| 1060 | |
| 1061 | n = __wcrtomb (!(flags & SUPPRESS) ? str : NULL, c, |
| 1062 | &state); |
| 1063 | if (__glibc_unlikely (n == (size_t) -1)) |
| 1064 | encode_error (); |
| 1065 | |
| 1066 | assert (n <= MB_CUR_MAX); |
| 1067 | str += n; |
| 1068 | } |
| 1069 | #else |
| 1070 | /* This is easy. */ |
| 1071 | if (!(flags & SUPPRESS)) |
| 1072 | { |
| 1073 | *str++ = c; |
| 1074 | if ((flags & MALLOC) |
| 1075 | && (char *) str == *strptr + strsize) |
| 1076 | { |
| 1077 | /* Enlarge the buffer. */ |
| 1078 | str = (char *) realloc (*strptr, 2 * strsize); |
| 1079 | if (str == NULL) |
| 1080 | { |
| 1081 | /* Can't allocate that much. Last-ditch |
| 1082 | effort. */ |
| 1083 | str = (char *) realloc (*strptr, strsize + 1); |
| 1084 | if (str == NULL) |
| 1085 | { |
| 1086 | if (flags & POSIX_MALLOC) |
| 1087 | { |
| 1088 | done = EOF; |
| 1089 | goto errout; |
| 1090 | } |
| 1091 | /* We lose. Oh well. Terminate the |
| 1092 | string and stop converting, |
| 1093 | so at least we don't skip any input. */ |
| 1094 | ((char *) (*strptr))[strsize - 1] = '\0'; |
| 1095 | strptr = NULL; |
| 1096 | ++done; |
| 1097 | conv_error (); |
| 1098 | } |
| 1099 | else |
| 1100 | { |
| 1101 | *strptr = (char *) str; |
| 1102 | str += strsize; |
| 1103 | ++strsize; |
| 1104 | } |
| 1105 | } |
| 1106 | else |
| 1107 | { |
| 1108 | *strptr = (char *) str; |
| 1109 | str += strsize; |
| 1110 | strsize *= 2; |
| 1111 | } |
| 1112 | } |
| 1113 | } |
| 1114 | #endif |
| 1115 | } |
| 1116 | while ((width <= 0 || --width > 0) && inchar () != EOF); |
| 1117 | |
| 1118 | if (!(flags & SUPPRESS)) |
| 1119 | { |
| 1120 | #ifdef COMPILE_WSCANF |
| 1121 | /* We have to emit the code to get into the initial |
| 1122 | state. */ |
| 1123 | char buf[MB_LEN_MAX]; |
| 1124 | size_t n = __wcrtomb (buf, L'\0', &state); |
| 1125 | if (n > 0 && (flags & MALLOC) |
| 1126 | && str + n >= *strptr + strsize) |
| 1127 | { |
| 1128 | /* Enlarge the buffer. */ |
| 1129 | size_t strleng = str - *strptr; |
| 1130 | char *newstr; |
| 1131 | |
| 1132 | newstr = (char *) realloc (*strptr, strleng + n + 1); |
| 1133 | if (newstr == NULL) |
| 1134 | { |
| 1135 | if (flags & POSIX_MALLOC) |
| 1136 | { |
| 1137 | done = EOF; |
| 1138 | goto errout; |
| 1139 | } |
| 1140 | /* We lose. Oh well. Terminate the string |
| 1141 | and stop converting, so at least we don't |
| 1142 | skip any input. */ |
| 1143 | ((char *) (*strptr))[strleng] = '\0'; |
| 1144 | strptr = NULL; |
| 1145 | ++done; |
| 1146 | conv_error (); |
| 1147 | } |
| 1148 | else |
| 1149 | { |
| 1150 | *strptr = newstr; |
| 1151 | str = newstr + strleng; |
| 1152 | strsize = strleng + n + 1; |
| 1153 | } |
| 1154 | } |
| 1155 | |
| 1156 | str = __mempcpy (str, buf, n); |
| 1157 | #endif |
| 1158 | *str++ = '\0'; |
| 1159 | |
| 1160 | if ((flags & MALLOC) && str - *strptr != strsize) |
| 1161 | { |
| 1162 | char *cp = (char *) realloc (*strptr, str - *strptr); |
| 1163 | if (cp != NULL) |
| 1164 | *strptr = cp; |
| 1165 | } |
| 1166 | strptr = NULL; |
| 1167 | |
| 1168 | ++done; |
| 1169 | } |
| 1170 | break; |
| 1171 | } |
| 1172 | /* FALLTHROUGH */ |
| 1173 | |
| 1174 | case L_('S'): |
| 1175 | { |
| 1176 | #ifndef COMPILE_WSCANF |
| 1177 | mbstate_t cstate; |
| 1178 | #endif |
| 1179 | |
| 1180 | /* Wide character string. */ |
| 1181 | STRING_ARG (wstr, wchar_t, 100); |
| 1182 | |
| 1183 | c = inchar (); |
| 1184 | if (__builtin_expect (c == EOF, 0)) |
| 1185 | input_error (); |
| 1186 | |
| 1187 | #ifndef COMPILE_WSCANF |
| 1188 | memset (&cstate, '\0', sizeof (cstate)); |
| 1189 | #endif |
| 1190 | |
| 1191 | do |
| 1192 | { |
| 1193 | if (ISSPACE (c)) |
| 1194 | { |
| 1195 | ungetc_not_eof (c, s); |
| 1196 | break; |
| 1197 | } |
| 1198 | |
| 1199 | #ifdef COMPILE_WSCANF |
| 1200 | /* This is easy. */ |
| 1201 | if (!(flags & SUPPRESS)) |
| 1202 | { |
| 1203 | *wstr++ = c; |
| 1204 | if ((flags & MALLOC) |
| 1205 | && wstr == (wchar_t *) *strptr + strsize) |
| 1206 | { |
| 1207 | /* Enlarge the buffer. */ |
| 1208 | wstr = (wchar_t *) realloc (*strptr, |
| 1209 | (2 * strsize) |
| 1210 | * sizeof (wchar_t)); |
| 1211 | if (wstr == NULL) |
| 1212 | { |
| 1213 | /* Can't allocate that much. Last-ditch |
| 1214 | effort. */ |
| 1215 | wstr = (wchar_t *) realloc (*strptr, |
| 1216 | (strsize + 1) |
| 1217 | * sizeof (wchar_t)); |
| 1218 | if (wstr == NULL) |
| 1219 | { |
| 1220 | if (flags & POSIX_MALLOC) |
| 1221 | { |
| 1222 | done = EOF; |
| 1223 | goto errout; |
| 1224 | } |
| 1225 | /* We lose. Oh well. Terminate the string |
| 1226 | and stop converting, so at least we don't |
| 1227 | skip any input. */ |
| 1228 | ((wchar_t *) (*strptr))[strsize - 1] = L'\0'; |
| 1229 | strptr = NULL; |
| 1230 | ++done; |
| 1231 | conv_error (); |
| 1232 | } |
| 1233 | else |
| 1234 | { |
| 1235 | *strptr = (char *) wstr; |
| 1236 | wstr += strsize; |
| 1237 | ++strsize; |
| 1238 | } |
| 1239 | } |
| 1240 | else |
| 1241 | { |
| 1242 | *strptr = (char *) wstr; |
| 1243 | wstr += strsize; |
| 1244 | strsize *= 2; |
| 1245 | } |
| 1246 | } |
| 1247 | } |
| 1248 | #else |
| 1249 | { |
| 1250 | char buf[1]; |
| 1251 | |
| 1252 | buf[0] = c; |
| 1253 | |
| 1254 | while (1) |
| 1255 | { |
| 1256 | size_t n; |
| 1257 | |
| 1258 | n = __mbrtowc (!(flags & SUPPRESS) ? wstr : NULL, |
| 1259 | buf, 1, &cstate); |
| 1260 | |
| 1261 | if (n == (size_t) -2) |
| 1262 | { |
| 1263 | /* Possibly correct character, just not enough |
| 1264 | input. */ |
| 1265 | if (__glibc_unlikely (inchar () == EOF)) |
| 1266 | encode_error (); |
| 1267 | |
| 1268 | buf[0] = c; |
| 1269 | continue; |
| 1270 | } |
| 1271 | |
| 1272 | if (__glibc_unlikely (n != 1)) |
| 1273 | encode_error (); |
| 1274 | |
| 1275 | /* We have a match. */ |
| 1276 | ++wstr; |
| 1277 | break; |
| 1278 | } |
| 1279 | |
| 1280 | if (!(flags & SUPPRESS) && (flags & MALLOC) |
| 1281 | && wstr == (wchar_t *) *strptr + strsize) |
| 1282 | { |
| 1283 | /* Enlarge the buffer. */ |
| 1284 | wstr = (wchar_t *) realloc (*strptr, |
| 1285 | (2 * strsize |
| 1286 | * sizeof (wchar_t))); |
| 1287 | if (wstr == NULL) |
| 1288 | { |
| 1289 | /* Can't allocate that much. Last-ditch effort. */ |
| 1290 | wstr = (wchar_t *) realloc (*strptr, |
| 1291 | ((strsize + 1) |
| 1292 | * sizeof (wchar_t))); |
| 1293 | if (wstr == NULL) |
| 1294 | { |
| 1295 | if (flags & POSIX_MALLOC) |
| 1296 | { |
| 1297 | done = EOF; |
| 1298 | goto errout; |
| 1299 | } |
| 1300 | /* We lose. Oh well. Terminate the |
| 1301 | string and stop converting, so at |
| 1302 | least we don't skip any input. */ |
| 1303 | ((wchar_t *) (*strptr))[strsize - 1] = L'\0'; |
| 1304 | strptr = NULL; |
| 1305 | ++done; |
| 1306 | conv_error (); |
| 1307 | } |
| 1308 | else |
| 1309 | { |
| 1310 | *strptr = (char *) wstr; |
| 1311 | wstr += strsize; |
| 1312 | ++strsize; |
| 1313 | } |
| 1314 | } |
| 1315 | else |
| 1316 | { |
| 1317 | *strptr = (char *) wstr; |
| 1318 | wstr += strsize; |
| 1319 | strsize *= 2; |
| 1320 | } |
| 1321 | } |
| 1322 | } |
| 1323 | #endif |
| 1324 | } |
| 1325 | while ((width <= 0 || --width > 0) && inchar () != EOF); |
| 1326 | |
| 1327 | if (!(flags & SUPPRESS)) |
| 1328 | { |
| 1329 | *wstr++ = L'\0'; |
| 1330 | |
| 1331 | if ((flags & MALLOC) && wstr - (wchar_t *) *strptr != strsize) |
| 1332 | { |
| 1333 | wchar_t *cp = (wchar_t *) realloc (*strptr, |
| 1334 | ((wstr |
| 1335 | - (wchar_t *) *strptr) |
| 1336 | * sizeof(wchar_t))); |
| 1337 | if (cp != NULL) |
| 1338 | *strptr = (char *) cp; |
| 1339 | } |
| 1340 | strptr = NULL; |
| 1341 | |
| 1342 | ++done; |
| 1343 | } |
| 1344 | } |
| 1345 | break; |
| 1346 | |
| 1347 | case L_('x'): /* Hexadecimal integer. */ |
| 1348 | case L_('X'): /* Ditto. */ |
| 1349 | base = 16; |
| 1350 | goto number; |
| 1351 | |
| 1352 | case L_('o'): /* Octal integer. */ |
| 1353 | base = 8; |
| 1354 | goto number; |
| 1355 | |
| 1356 | case L_('u'): /* Unsigned decimal integer. */ |
| 1357 | base = 10; |
| 1358 | goto number; |
| 1359 | |
| 1360 | case L_('d'): /* Signed decimal integer. */ |
| 1361 | base = 10; |
| 1362 | flags |= NUMBER_SIGNED; |
| 1363 | goto number; |
| 1364 | |
| 1365 | case L_('i'): /* Generic number. */ |
| 1366 | base = 0; |
| 1367 | flags |= NUMBER_SIGNED; |
| 1368 | |
| 1369 | number: |
| 1370 | c = inchar (); |
| 1371 | if (__glibc_unlikely (c == EOF)) |
| 1372 | input_error (); |
| 1373 | |
| 1374 | /* Check for a sign. */ |
| 1375 | if (c == L_('-') || c == L_('+')) |
| 1376 | { |
| 1377 | ADDW (c); |
| 1378 | if (width > 0) |
| 1379 | --width; |
| 1380 | c = inchar (); |
| 1381 | } |
| 1382 | |
| 1383 | /* Look for a leading indication of base. */ |
| 1384 | if (width != 0 && c == L_('0')) |
| 1385 | { |
| 1386 | if (width > 0) |
| 1387 | --width; |
| 1388 | |
| 1389 | ADDW (c); |
| 1390 | c = inchar (); |
| 1391 | |
| 1392 | if (width != 0 && TOLOWER (c) == L_('x')) |
| 1393 | { |
| 1394 | if (base == 0) |
| 1395 | base = 16; |
| 1396 | if (base == 16) |
| 1397 | { |
| 1398 | if (width > 0) |
| 1399 | --width; |
| 1400 | c = inchar (); |
| 1401 | } |
| 1402 | } |
| 1403 | else if (base == 0) |
| 1404 | base = 8; |
| 1405 | } |
| 1406 | |
| 1407 | if (base == 0) |
| 1408 | base = 10; |
| 1409 | |
| 1410 | if (base == 10 && __builtin_expect ((flags & I18N) != 0, 0)) |
| 1411 | { |
| 1412 | int from_level; |
| 1413 | int to_level; |
| 1414 | int level; |
| 1415 | #ifdef COMPILE_WSCANF |
| 1416 | const wchar_t *wcdigits[10]; |
| 1417 | const wchar_t *wcdigits_extended[10]; |
| 1418 | #else |
| 1419 | const char *mbdigits[10]; |
| 1420 | const char *mbdigits_extended[10]; |
| 1421 | #endif |
| 1422 | /* "to_inpunct" is a map from ASCII digits to their |
| 1423 | equivalent in locale. This is defined for locales |
| 1424 | which use an extra digits set. */ |
| 1425 | wctrans_t map = __wctrans ("to_inpunct"); |
| 1426 | int n; |
| 1427 | |
| 1428 | from_level = 0; |
| 1429 | #ifdef COMPILE_WSCANF |
| 1430 | to_level = _NL_CURRENT_WORD (LC_CTYPE, |
| 1431 | _NL_CTYPE_INDIGITS_WC_LEN) - 1; |
| 1432 | #else |
| 1433 | to_level = (uint32_t) curctype->values[_NL_ITEM_INDEX (_NL_CTYPE_INDIGITS_MB_LEN)].word - 1; |
| 1434 | #endif |
| 1435 | |
| 1436 | /* Get the alternative digit forms if there are any. */ |
| 1437 | if (__glibc_unlikely (map != NULL)) |
| 1438 | { |
| 1439 | /* Adding new level for extra digits set in locale file. */ |
| 1440 | ++to_level; |
| 1441 | |
| 1442 | for (n = 0; n < 10; ++n) |
| 1443 | { |
| 1444 | #ifdef COMPILE_WSCANF |
| 1445 | wcdigits[n] = (const wchar_t *) |
| 1446 | _NL_CURRENT (LC_CTYPE, _NL_CTYPE_INDIGITS0_WC + n); |
| 1447 | |
| 1448 | wchar_t *wc_extended = (wchar_t *) |
| 1449 | alloca ((to_level + 2) * sizeof (wchar_t)); |
| 1450 | __wmemcpy (wc_extended, wcdigits[n], to_level); |
| 1451 | wc_extended[to_level] = __towctrans (L'0' + n, map); |
| 1452 | wc_extended[to_level + 1] = '\0'; |
| 1453 | wcdigits_extended[n] = wc_extended; |
| 1454 | #else |
| 1455 | mbdigits[n] |
| 1456 | = curctype->values[_NL_CTYPE_INDIGITS0_MB + n].string; |
| 1457 | |
| 1458 | /* Get the equivalent wide char in map. */ |
| 1459 | wint_t extra_wcdigit = __towctrans (L'0' + n, map); |
| 1460 | |
| 1461 | /* Convert it to multibyte representation. */ |
| 1462 | mbstate_t state; |
| 1463 | memset (&state, '\0', sizeof (state)); |
| 1464 | |
| 1465 | char extra_mbdigit[MB_LEN_MAX]; |
| 1466 | size_t mblen |
| 1467 | = __wcrtomb (extra_mbdigit, extra_wcdigit, &state); |
| 1468 | |
| 1469 | if (mblen == (size_t) -1) |
| 1470 | { |
| 1471 | /* Ignore this new level. */ |
| 1472 | map = NULL; |
| 1473 | break; |
| 1474 | } |
| 1475 | |
| 1476 | /* Calculate the length of mbdigits[n]. */ |
| 1477 | const char *last_char = mbdigits[n]; |
| 1478 | for (level = 0; level < to_level; ++level) |
| 1479 | last_char = strchr (last_char, '\0') + 1; |
| 1480 | |
| 1481 | size_t mbdigits_len = last_char - mbdigits[n]; |
| 1482 | |
| 1483 | /* Allocate memory for extended multibyte digit. */ |
| 1484 | char *mb_extended; |
| 1485 | mb_extended = (char *) alloca (mbdigits_len + mblen + 1); |
| 1486 | |
| 1487 | /* And get the mbdigits + extra_digit string. */ |
| 1488 | *(char *) __mempcpy (__mempcpy (mb_extended, mbdigits[n], |
| 1489 | mbdigits_len), |
| 1490 | extra_mbdigit, mblen) = '\0'; |
| 1491 | mbdigits_extended[n] = mb_extended; |
| 1492 | #endif |
| 1493 | } |
| 1494 | } |
| 1495 | |
| 1496 | /* Read the number into workspace. */ |
| 1497 | while (c != EOF && width != 0) |
| 1498 | { |
| 1499 | /* In this round we get the pointer to the digit strings |
| 1500 | and also perform the first round of comparisons. */ |
| 1501 | for (n = 0; n < 10; ++n) |
| 1502 | { |
| 1503 | /* Get the string for the digits with value N. */ |
| 1504 | #ifdef COMPILE_WSCANF |
| 1505 | if (__glibc_unlikely (map != NULL)) |
| 1506 | wcdigits[n] = wcdigits_extended[n]; |
| 1507 | else |
| 1508 | wcdigits[n] = (const wchar_t *) |
| 1509 | _NL_CURRENT (LC_CTYPE, _NL_CTYPE_INDIGITS0_WC + n); |
| 1510 | wcdigits[n] += from_level; |
| 1511 | |
| 1512 | if (c == (wint_t) *wcdigits[n]) |
| 1513 | { |
| 1514 | to_level = from_level; |
| 1515 | break; |
| 1516 | } |
| 1517 | |
| 1518 | /* Advance the pointer to the next string. */ |
| 1519 | ++wcdigits[n]; |
| 1520 | #else |
| 1521 | const char *cmpp; |
| 1522 | int avail = width > 0 ? width : INT_MAX; |
| 1523 | |
| 1524 | if (__glibc_unlikely (map != NULL)) |
| 1525 | mbdigits[n] = mbdigits_extended[n]; |
| 1526 | else |
| 1527 | mbdigits[n] |
| 1528 | = curctype->values[_NL_CTYPE_INDIGITS0_MB + n].string; |
| 1529 | |
| 1530 | for (level = 0; level < from_level; level++) |
| 1531 | mbdigits[n] = strchr (mbdigits[n], '\0') + 1; |
| 1532 | |
| 1533 | cmpp = mbdigits[n]; |
| 1534 | while ((unsigned char) *cmpp == c && avail >= 0) |
| 1535 | { |
| 1536 | if (*++cmpp == '\0') |
| 1537 | break; |
| 1538 | else |
| 1539 | { |
| 1540 | if (avail == 0 || inchar () == EOF) |
| 1541 | break; |
| 1542 | --avail; |
| 1543 | } |
| 1544 | } |
| 1545 | |
| 1546 | if (*cmpp == '\0') |
| 1547 | { |
| 1548 | if (width > 0) |
| 1549 | width = avail; |
| 1550 | to_level = from_level; |
| 1551 | break; |
| 1552 | } |
| 1553 | |
| 1554 | /* We are pushing all read characters back. */ |
| 1555 | if (cmpp > mbdigits[n]) |
| 1556 | { |
| 1557 | ungetc (c, s); |
| 1558 | while (--cmpp > mbdigits[n]) |
| 1559 | ungetc_not_eof ((unsigned char) *cmpp, s); |
| 1560 | c = (unsigned char) *cmpp; |
| 1561 | } |
| 1562 | |
| 1563 | /* Advance the pointer to the next string. */ |
| 1564 | mbdigits[n] = strchr (mbdigits[n], '\0') + 1; |
| 1565 | #endif |
| 1566 | } |
| 1567 | |
| 1568 | if (n == 10) |
| 1569 | { |
| 1570 | /* Have not yet found the digit. */ |
| 1571 | for (level = from_level + 1; level <= to_level; ++level) |
| 1572 | { |
| 1573 | /* Search all ten digits of this level. */ |
| 1574 | for (n = 0; n < 10; ++n) |
| 1575 | { |
| 1576 | #ifdef COMPILE_WSCANF |
| 1577 | if (c == (wint_t) *wcdigits[n]) |
| 1578 | break; |
| 1579 | |
| 1580 | /* Advance the pointer to the next string. */ |
| 1581 | ++wcdigits[n]; |
| 1582 | #else |
| 1583 | const char *cmpp; |
| 1584 | int avail = width > 0 ? width : INT_MAX; |
| 1585 | |
| 1586 | cmpp = mbdigits[n]; |
| 1587 | while ((unsigned char) *cmpp == c && avail >= 0) |
| 1588 | { |
| 1589 | if (*++cmpp == '\0') |
| 1590 | break; |
| 1591 | else |
| 1592 | { |
| 1593 | if (avail == 0 || inchar () == EOF) |
| 1594 | break; |
| 1595 | --avail; |
| 1596 | } |
| 1597 | } |
| 1598 | |
| 1599 | if (*cmpp == '\0') |
| 1600 | { |
| 1601 | if (width > 0) |
| 1602 | width = avail; |
| 1603 | break; |
| 1604 | } |
| 1605 | |
| 1606 | /* We are pushing all read characters back. */ |
| 1607 | if (cmpp > mbdigits[n]) |
| 1608 | { |
| 1609 | ungetc (c, s); |
| 1610 | while (--cmpp > mbdigits[n]) |
| 1611 | ungetc_not_eof ((unsigned char) *cmpp, s); |
| 1612 | c = (unsigned char) *cmpp; |
| 1613 | } |
| 1614 | |
| 1615 | /* Advance the pointer to the next string. */ |
| 1616 | mbdigits[n] = strchr (mbdigits[n], '\0') + 1; |
| 1617 | #endif |
| 1618 | } |
| 1619 | |
| 1620 | if (n < 10) |
| 1621 | { |
| 1622 | /* Found it. */ |
| 1623 | from_level = level; |
| 1624 | to_level = level; |
| 1625 | break; |
| 1626 | } |
| 1627 | } |
| 1628 | } |
| 1629 | |
| 1630 | if (n < 10) |
| 1631 | c = L_('0') + n; |
| 1632 | else if (flags & GROUP) |
| 1633 | { |
| 1634 | /* Try matching against the thousands separator. */ |
| 1635 | #ifdef COMPILE_WSCANF |
| 1636 | if (c != thousands) |
| 1637 | break; |
| 1638 | #else |
| 1639 | const char *cmpp = thousands; |
| 1640 | int avail = width > 0 ? width : INT_MAX; |
| 1641 | |
| 1642 | while ((unsigned char) *cmpp == c && avail >= 0) |
| 1643 | { |
| 1644 | ADDW (c); |
| 1645 | if (*++cmpp == '\0') |
| 1646 | break; |
| 1647 | else |
| 1648 | { |
| 1649 | if (avail == 0 || inchar () == EOF) |
| 1650 | break; |
| 1651 | --avail; |
| 1652 | } |
| 1653 | } |
| 1654 | |
| 1655 | if (*cmpp != '\0') |
| 1656 | { |
| 1657 | /* We are pushing all read characters back. */ |
| 1658 | if (cmpp > thousands) |
| 1659 | { |
| 1660 | wpsize -= cmpp - thousands; |
| 1661 | ungetc (c, s); |
| 1662 | while (--cmpp > thousands) |
| 1663 | ungetc_not_eof ((unsigned char) *cmpp, s); |
| 1664 | c = (unsigned char) *cmpp; |
| 1665 | } |
| 1666 | break; |
| 1667 | } |
| 1668 | |
| 1669 | if (width > 0) |
| 1670 | width = avail; |
| 1671 | |
| 1672 | /* The last thousands character will be added back by |
| 1673 | the ADDW below. */ |
| 1674 | --wpsize; |
| 1675 | #endif |
| 1676 | } |
| 1677 | else |
| 1678 | break; |
| 1679 | |
| 1680 | ADDW (c); |
| 1681 | if (width > 0) |
| 1682 | --width; |
| 1683 | |
| 1684 | c = inchar (); |
| 1685 | } |
| 1686 | } |
| 1687 | else |
| 1688 | /* Read the number into workspace. */ |
| 1689 | while (c != EOF && width != 0) |
| 1690 | { |
| 1691 | if (base == 16) |
| 1692 | { |
| 1693 | if (!ISXDIGIT (c)) |
| 1694 | break; |
| 1695 | } |
| 1696 | else if (!ISDIGIT (c) || (int) (c - L_('0')) >= base) |
| 1697 | { |
| 1698 | if (base == 10 && (flags & GROUP)) |
| 1699 | { |
| 1700 | /* Try matching against the thousands separator. */ |
| 1701 | #ifdef COMPILE_WSCANF |
| 1702 | if (c != thousands) |
| 1703 | break; |
| 1704 | #else |
| 1705 | const char *cmpp = thousands; |
| 1706 | int avail = width > 0 ? width : INT_MAX; |
| 1707 | |
| 1708 | while ((unsigned char) *cmpp == c && avail >= 0) |
| 1709 | { |
| 1710 | ADDW (c); |
| 1711 | if (*++cmpp == '\0') |
| 1712 | break; |
| 1713 | else |
| 1714 | { |
| 1715 | if (avail == 0 || inchar () == EOF) |
| 1716 | break; |
| 1717 | --avail; |
| 1718 | } |
| 1719 | } |
| 1720 | |
| 1721 | if (*cmpp != '\0') |
| 1722 | { |
| 1723 | /* We are pushing all read characters back. */ |
| 1724 | if (cmpp > thousands) |
| 1725 | { |
| 1726 | wpsize -= cmpp - thousands; |
| 1727 | ungetc (c, s); |
| 1728 | while (--cmpp > thousands) |
| 1729 | ungetc_not_eof ((unsigned char) *cmpp, s); |
| 1730 | c = (unsigned char) *cmpp; |
| 1731 | } |
| 1732 | break; |
| 1733 | } |
| 1734 | |
| 1735 | if (width > 0) |
| 1736 | width = avail; |
| 1737 | |
| 1738 | /* The last thousands character will be added back by |
| 1739 | the ADDW below. */ |
| 1740 | --wpsize; |
| 1741 | #endif |
| 1742 | } |
| 1743 | else |
| 1744 | break; |
| 1745 | } |
| 1746 | ADDW (c); |
| 1747 | if (width > 0) |
| 1748 | --width; |
| 1749 | |
| 1750 | c = inchar (); |
| 1751 | } |
| 1752 | |
| 1753 | if (wpsize == 0 |
| 1754 | || (wpsize == 1 && (wp[0] == L_('+') || wp[0] == L_('-')))) |
| 1755 | { |
| 1756 | /* There was no number. If we are supposed to read a pointer |
| 1757 | we must recognize "(nil)" as well. */ |
| 1758 | if (__builtin_expect (wpsize == 0 |
| 1759 | && (flags & READ_POINTER) |
| 1760 | && (width < 0 || width >= 5) |
| 1761 | && c == '(' |
| 1762 | && TOLOWER (inchar ()) == L_('n') |
| 1763 | && TOLOWER (inchar ()) == L_('i') |
| 1764 | && TOLOWER (inchar ()) == L_('l') |
| 1765 | && inchar () == L_(')'), 1)) |
| 1766 | /* We must produce the value of a NULL pointer. A single |
| 1767 | '0' digit is enough. */ |
| 1768 | ADDW (L_('0')); |
| 1769 | else |
| 1770 | { |
| 1771 | /* The last read character is not part of the number |
| 1772 | anymore. */ |
| 1773 | ungetc (c, s); |
| 1774 | |
| 1775 | conv_error (); |
| 1776 | } |
| 1777 | } |
| 1778 | else |
| 1779 | /* The just read character is not part of the number anymore. */ |
| 1780 | ungetc (c, s); |
| 1781 | |
| 1782 | /* Convert the number. */ |
| 1783 | ADDW (L_('\0')); |
| 1784 | if (need_longlong && (flags & LONGDBL)) |
| 1785 | { |
| 1786 | if (flags & NUMBER_SIGNED) |
| 1787 | num.q = __strtoll_internal (wp, &tw, base, flags & GROUP); |
| 1788 | else |
| 1789 | num.uq = __strtoull_internal (wp, &tw, base, flags & GROUP); |
| 1790 | } |
| 1791 | else |
| 1792 | { |
| 1793 | if (flags & NUMBER_SIGNED) |
| 1794 | num.l = __strtol_internal (wp, &tw, base, flags & GROUP); |
| 1795 | else |
| 1796 | num.ul = __strtoul_internal (wp, &tw, base, flags & GROUP); |
| 1797 | } |
| 1798 | if (__glibc_unlikely (wp == tw)) |
| 1799 | conv_error (); |
| 1800 | |
| 1801 | if (!(flags & SUPPRESS)) |
| 1802 | { |
| 1803 | if (flags & NUMBER_SIGNED) |
| 1804 | { |
| 1805 | if (need_longlong && (flags & LONGDBL)) |
| 1806 | *ARG (LONGLONG int *) = num.q; |
| 1807 | else if (need_long && (flags & LONG)) |
| 1808 | *ARG (long int *) = num.l; |
| 1809 | else if (flags & SHORT) |
| 1810 | *ARG (short int *) = (short int) num.l; |
| 1811 | else if (!(flags & CHAR)) |
| 1812 | *ARG (int *) = (int) num.l; |
| 1813 | else |
| 1814 | *ARG (signed char *) = (signed char) num.ul; |
| 1815 | } |
| 1816 | else |
| 1817 | { |
| 1818 | if (need_longlong && (flags & LONGDBL)) |
| 1819 | *ARG (unsigned LONGLONG int *) = num.uq; |
| 1820 | else if (need_long && (flags & LONG)) |
| 1821 | *ARG (unsigned long int *) = num.ul; |
| 1822 | else if (flags & SHORT) |
| 1823 | *ARG (unsigned short int *) |
| 1824 | = (unsigned short int) num.ul; |
| 1825 | else if (!(flags & CHAR)) |
| 1826 | *ARG (unsigned int *) = (unsigned int) num.ul; |
| 1827 | else |
| 1828 | *ARG (unsigned char *) = (unsigned char) num.ul; |
| 1829 | } |
| 1830 | ++done; |
| 1831 | } |
| 1832 | break; |
| 1833 | |
| 1834 | case L_('e'): /* Floating-point numbers. */ |
| 1835 | case L_('E'): |
| 1836 | case L_('f'): |
| 1837 | case L_('F'): |
| 1838 | case L_('g'): |
| 1839 | case L_('G'): |
| 1840 | case L_('a'): |
| 1841 | case L_('A'): |
| 1842 | c = inchar (); |
| 1843 | if (width > 0) |
| 1844 | --width; |
| 1845 | if (__glibc_unlikely (c == EOF)) |
| 1846 | input_error (); |
| 1847 | |
| 1848 | got_digit = got_dot = got_e = 0; |
| 1849 | |
| 1850 | /* Check for a sign. */ |
| 1851 | if (c == L_('-') || c == L_('+')) |
| 1852 | { |
| 1853 | negative = c == L_('-'); |
| 1854 | if (__glibc_unlikely (width == 0 || inchar () == EOF)) |
| 1855 | /* EOF is only an input error before we read any chars. */ |
| 1856 | conv_error (); |
| 1857 | if (width > 0) |
| 1858 | --width; |
| 1859 | } |
| 1860 | else |
| 1861 | negative = 0; |
| 1862 | |
| 1863 | /* Take care for the special arguments "nan" and "inf". */ |
| 1864 | if (TOLOWER (c) == L_('n')) |
| 1865 | { |
| 1866 | /* Maybe "nan". */ |
| 1867 | ADDW (c); |
| 1868 | if (__builtin_expect (width == 0 |
| 1869 | || inchar () == EOF |
| 1870 | || TOLOWER (c) != L_('a'), 0)) |
| 1871 | conv_error (); |
| 1872 | if (width > 0) |
| 1873 | --width; |
| 1874 | ADDW (c); |
| 1875 | if (__builtin_expect (width == 0 |
| 1876 | || inchar () == EOF |
| 1877 | || TOLOWER (c) != L_('n'), 0)) |
| 1878 | conv_error (); |
| 1879 | if (width > 0) |
| 1880 | --width; |
| 1881 | ADDW (c); |
| 1882 | /* It is "nan". */ |
| 1883 | goto scan_float; |
| 1884 | } |
| 1885 | else if (TOLOWER (c) == L_('i')) |
| 1886 | { |
| 1887 | /* Maybe "inf" or "infinity". */ |
| 1888 | ADDW (c); |
| 1889 | if (__builtin_expect (width == 0 |
| 1890 | || inchar () == EOF |
| 1891 | || TOLOWER (c) != L_('n'), 0)) |
| 1892 | conv_error (); |
| 1893 | if (width > 0) |
| 1894 | --width; |
| 1895 | ADDW (c); |
| 1896 | if (__builtin_expect (width == 0 |
| 1897 | || inchar () == EOF |
| 1898 | || TOLOWER (c) != L_('f'), 0)) |
| 1899 | conv_error (); |
| 1900 | if (width > 0) |
| 1901 | --width; |
| 1902 | ADDW (c); |
| 1903 | /* It is as least "inf". */ |
| 1904 | if (width != 0 && inchar () != EOF) |
| 1905 | { |
| 1906 | if (TOLOWER (c) == L_('i')) |
| 1907 | { |
| 1908 | if (width > 0) |
| 1909 | --width; |
| 1910 | /* Now we have to read the rest as well. */ |
| 1911 | ADDW (c); |
| 1912 | if (__builtin_expect (width == 0 |
| 1913 | || inchar () == EOF |
| 1914 | || TOLOWER (c) != L_('n'), 0)) |
| 1915 | conv_error (); |
| 1916 | if (width > 0) |
| 1917 | --width; |
| 1918 | ADDW (c); |
| 1919 | if (__builtin_expect (width == 0 |
| 1920 | || inchar () == EOF |
| 1921 | || TOLOWER (c) != L_('i'), 0)) |
| 1922 | conv_error (); |
| 1923 | if (width > 0) |
| 1924 | --width; |
| 1925 | ADDW (c); |
| 1926 | if (__builtin_expect (width == 0 |
| 1927 | || inchar () == EOF |
| 1928 | || TOLOWER (c) != L_('t'), 0)) |
| 1929 | conv_error (); |
| 1930 | if (width > 0) |
| 1931 | --width; |
| 1932 | ADDW (c); |
| 1933 | if (__builtin_expect (width == 0 |
| 1934 | || inchar () == EOF |
| 1935 | || TOLOWER (c) != L_('y'), 0)) |
| 1936 | conv_error (); |
| 1937 | if (width > 0) |
| 1938 | --width; |
| 1939 | ADDW (c); |
| 1940 | } |
| 1941 | else |
| 1942 | /* Never mind. */ |
| 1943 | ungetc (c, s); |
| 1944 | } |
| 1945 | goto scan_float; |
| 1946 | } |
| 1947 | |
| 1948 | exp_char = L_('e'); |
| 1949 | if (width != 0 && c == L_('0')) |
| 1950 | { |
| 1951 | ADDW (c); |
| 1952 | c = inchar (); |
| 1953 | if (width > 0) |
| 1954 | --width; |
| 1955 | if (width != 0 && TOLOWER (c) == L_('x')) |
| 1956 | { |
| 1957 | /* It is a number in hexadecimal format. */ |
| 1958 | ADDW (c); |
| 1959 | |
| 1960 | flags |= HEXA_FLOAT; |
| 1961 | exp_char = L_('p'); |
| 1962 | |
| 1963 | /* Grouping is not allowed. */ |
| 1964 | flags &= ~GROUP; |
| 1965 | c = inchar (); |
| 1966 | if (width > 0) |
| 1967 | --width; |
| 1968 | } |
| 1969 | else |
| 1970 | got_digit = 1; |
| 1971 | } |
| 1972 | |
| 1973 | while (1) |
| 1974 | { |
| 1975 | if (ISDIGIT (c)) |
| 1976 | { |
| 1977 | ADDW (c); |
| 1978 | got_digit = 1; |
| 1979 | } |
| 1980 | else if (!got_e && (flags & HEXA_FLOAT) && ISXDIGIT (c)) |
| 1981 | { |
| 1982 | ADDW (c); |
| 1983 | got_digit = 1; |
| 1984 | } |
| 1985 | else if (got_e && wp[wpsize - 1] == exp_char |
| 1986 | && (c == L_('-') || c == L_('+'))) |
| 1987 | ADDW (c); |
| 1988 | else if (got_digit && !got_e |
| 1989 | && (CHAR_T) TOLOWER (c) == exp_char) |
| 1990 | { |
| 1991 | ADDW (exp_char); |
| 1992 | got_e = got_dot = 1; |
| 1993 | } |
| 1994 | else |
| 1995 | { |
| 1996 | #ifdef COMPILE_WSCANF |
| 1997 | if (! got_dot && c == decimal) |
| 1998 | { |
| 1999 | ADDW (c); |
| 2000 | got_dot = 1; |
| 2001 | } |
| 2002 | else if ((flags & GROUP) != 0 && ! got_dot && c == thousands) |
| 2003 | ADDW (c); |
| 2004 | else |
| 2005 | { |
| 2006 | /* The last read character is not part of the number |
| 2007 | anymore. */ |
| 2008 | ungetc (c, s); |
| 2009 | break; |
| 2010 | } |
| 2011 | #else |
| 2012 | const char *cmpp = decimal; |
| 2013 | int avail = width > 0 ? width : INT_MAX; |
| 2014 | |
| 2015 | if (! got_dot) |
| 2016 | { |
| 2017 | while ((unsigned char) *cmpp == c && avail >= 0) |
| 2018 | if (*++cmpp == '\0') |
| 2019 | break; |
| 2020 | else |
| 2021 | { |
| 2022 | if (avail == 0 || inchar () == EOF) |
| 2023 | break; |
| 2024 | --avail; |
| 2025 | } |
| 2026 | } |
| 2027 | |
| 2028 | if (*cmpp == '\0') |
| 2029 | { |
| 2030 | /* Add all the characters. */ |
| 2031 | for (cmpp = decimal; *cmpp != '\0'; ++cmpp) |
| 2032 | ADDW ((unsigned char) *cmpp); |
| 2033 | if (width > 0) |
| 2034 | width = avail; |
| 2035 | got_dot = 1; |
| 2036 | } |
| 2037 | else |
| 2038 | { |
| 2039 | /* Figure out whether it is a thousands separator. |
| 2040 | There is one problem: we possibly read more than |
| 2041 | one character. We cannot push them back but since |
| 2042 | we know that parts of the `decimal' string matched, |
| 2043 | we can compare against it. */ |
| 2044 | const char *cmp2p = thousands; |
| 2045 | |
| 2046 | if ((flags & GROUP) != 0 && ! got_dot) |
| 2047 | { |
| 2048 | while (cmp2p - thousands < cmpp - decimal |
| 2049 | && *cmp2p == decimal[cmp2p - thousands]) |
| 2050 | ++cmp2p; |
| 2051 | if (cmp2p - thousands == cmpp - decimal) |
| 2052 | { |
| 2053 | while ((unsigned char) *cmp2p == c && avail >= 0) |
| 2054 | if (*++cmp2p == '\0') |
| 2055 | break; |
| 2056 | else |
| 2057 | { |
| 2058 | if (avail == 0 || inchar () == EOF) |
| 2059 | break; |
| 2060 | --avail; |
| 2061 | } |
| 2062 | } |
| 2063 | } |
| 2064 | |
| 2065 | if (cmp2p != NULL && *cmp2p == '\0') |
| 2066 | { |
| 2067 | /* Add all the characters. */ |
| 2068 | for (cmpp = thousands; *cmpp != '\0'; ++cmpp) |
| 2069 | ADDW ((unsigned char) *cmpp); |
| 2070 | if (width > 0) |
| 2071 | width = avail; |
| 2072 | } |
| 2073 | else |
| 2074 | { |
| 2075 | /* The last read character is not part of the number |
| 2076 | anymore. */ |
| 2077 | ungetc (c, s); |
| 2078 | break; |
| 2079 | } |
| 2080 | } |
| 2081 | #endif |
| 2082 | } |
| 2083 | |
| 2084 | if (width == 0 || inchar () == EOF) |
| 2085 | break; |
| 2086 | |
| 2087 | if (width > 0) |
| 2088 | --width; |
| 2089 | } |
| 2090 | |
| 2091 | wctrans_t map; |
| 2092 | if (__builtin_expect ((flags & I18N) != 0, 0) |
| 2093 | /* Hexadecimal floats make no sense, fixing localized |
| 2094 | digits with ASCII letters. */ |
| 2095 | && !(flags & HEXA_FLOAT) |
| 2096 | /* Minimum requirement. */ |
| 2097 | && (wpsize == 0 || got_dot) |
| 2098 | && (map = __wctrans ("to_inpunct")) != NULL) |
| 2099 | { |
| 2100 | /* Reget the first character. */ |
| 2101 | inchar (); |
| 2102 | |
| 2103 | /* Localized digits, decimal points, and thousands |
| 2104 | separator. */ |
| 2105 | wint_t wcdigits[12]; |
| 2106 | |
| 2107 | /* First get decimal equivalent to check if we read it |
| 2108 | or not. */ |
| 2109 | wcdigits[11] = __towctrans (L'.', map); |
| 2110 | |
| 2111 | /* If we have not read any character or have just read |
| 2112 | locale decimal point which matches the decimal point |
| 2113 | for localized FP numbers, then we may have localized |
| 2114 | digits. Note, we test GOT_DOT above. */ |
| 2115 | #ifdef COMPILE_WSCANF |
| 2116 | if (wpsize == 0 || (wpsize == 1 && wcdigits[11] == decimal)) |
| 2117 | #else |
| 2118 | char mbdigits[12][MB_LEN_MAX + 1]; |
| 2119 | |
| 2120 | mbstate_t state; |
| 2121 | memset (&state, '\0', sizeof (state)); |
| 2122 | |
| 2123 | bool match_so_far = wpsize == 0; |
| 2124 | size_t mblen = __wcrtomb (mbdigits[11], wcdigits[11], &state); |
| 2125 | if (mblen != (size_t) -1) |
| 2126 | { |
| 2127 | mbdigits[11][mblen] = '\0'; |
| 2128 | match_so_far |= (wpsize == strlen (decimal) |
| 2129 | && strcmp (decimal, mbdigits[11]) == 0); |
| 2130 | } |
| 2131 | else |
| 2132 | { |
| 2133 | size_t decimal_len = strlen (decimal); |
| 2134 | /* This should always be the case but the data comes |
| 2135 | from a file. */ |
| 2136 | if (decimal_len <= MB_LEN_MAX) |
| 2137 | { |
| 2138 | match_so_far |= wpsize == decimal_len; |
| 2139 | memcpy (mbdigits[11], decimal, decimal_len + 1); |
| 2140 | } |
| 2141 | else |
| 2142 | match_so_far = false; |
| 2143 | } |
| 2144 | |
| 2145 | if (match_so_far) |
| 2146 | #endif |
| 2147 | { |
| 2148 | bool have_locthousands = (flags & GROUP) != 0; |
| 2149 | |
| 2150 | /* Now get the digits and the thousands-sep equivalents. */ |
| 2151 | for (int n = 0; n < 11; ++n) |
| 2152 | { |
| 2153 | if (n < 10) |
| 2154 | wcdigits[n] = __towctrans (L'0' + n, map); |
| 2155 | else if (n == 10) |
| 2156 | { |
| 2157 | wcdigits[10] = __towctrans (L',', map); |
| 2158 | have_locthousands &= wcdigits[10] != L'\0'; |
| 2159 | } |
| 2160 | |
| 2161 | #ifndef COMPILE_WSCANF |
| 2162 | memset (&state, '\0', sizeof (state)); |
| 2163 | |
| 2164 | size_t mblen = __wcrtomb (mbdigits[n], wcdigits[n], |
| 2165 | &state); |
| 2166 | if (mblen == (size_t) -1) |
| 2167 | { |
| 2168 | if (n == 10) |
| 2169 | { |
| 2170 | if (have_locthousands) |
| 2171 | { |
| 2172 | size_t thousands_len = strlen (thousands); |
| 2173 | if (thousands_len <= MB_LEN_MAX) |
| 2174 | memcpy (mbdigits[10], thousands, |
| 2175 | thousands_len + 1); |
| 2176 | else |
| 2177 | have_locthousands = false; |
| 2178 | } |
| 2179 | } |
| 2180 | else |
| 2181 | /* Ignore checking against localized digits. */ |
| 2182 | goto no_i18nflt; |
| 2183 | } |
| 2184 | else |
| 2185 | mbdigits[n][mblen] = '\0'; |
| 2186 | #endif |
| 2187 | } |
| 2188 | |
| 2189 | /* Start checking against localized digits, if |
| 2190 | conversion is done correctly. */ |
| 2191 | while (1) |
| 2192 | { |
| 2193 | if (got_e && wp[wpsize - 1] == exp_char |
| 2194 | && (c == L_('-') || c == L_('+'))) |
| 2195 | ADDW (c); |
| 2196 | else if (wpsize > 0 && !got_e |
| 2197 | && (CHAR_T) TOLOWER (c) == exp_char) |
| 2198 | { |
| 2199 | ADDW (exp_char); |
| 2200 | got_e = got_dot = 1; |
| 2201 | } |
| 2202 | else |
| 2203 | { |
| 2204 | /* Check against localized digits, decimal point, |
| 2205 | and thousands separator. */ |
| 2206 | int n; |
| 2207 | for (n = 0; n < 12; ++n) |
| 2208 | { |
| 2209 | #ifdef COMPILE_WSCANF |
| 2210 | if (c == wcdigits[n]) |
| 2211 | { |
| 2212 | if (n < 10) |
| 2213 | ADDW (L_('0') + n); |
| 2214 | else if (n == 11 && !got_dot) |
| 2215 | { |
| 2216 | ADDW (decimal); |
| 2217 | got_dot = 1; |
| 2218 | } |
| 2219 | else if (n == 10 && have_locthousands |
| 2220 | && ! got_dot) |
| 2221 | ADDW (thousands); |
| 2222 | else |
| 2223 | /* The last read character is not part |
| 2224 | of the number anymore. */ |
| 2225 | n = 12; |
| 2226 | |
| 2227 | break; |
| 2228 | } |
| 2229 | #else |
| 2230 | const char *cmpp = mbdigits[n]; |
| 2231 | int avail = width > 0 ? width : INT_MAX; |
| 2232 | |
| 2233 | while ((unsigned char) *cmpp == c && avail >= 0) |
| 2234 | if (*++cmpp == '\0') |
| 2235 | break; |
| 2236 | else |
| 2237 | { |
| 2238 | if (avail == 0 || inchar () == EOF) |
| 2239 | break; |
| 2240 | --avail; |
| 2241 | } |
| 2242 | if (*cmpp == '\0') |
| 2243 | { |
| 2244 | if (width > 0) |
| 2245 | width = avail; |
| 2246 | |
| 2247 | if (n < 10) |
| 2248 | ADDW (L_('0') + n); |
| 2249 | else if (n == 11 && !got_dot) |
| 2250 | { |
| 2251 | /* Add all the characters. */ |
| 2252 | for (cmpp = decimal; *cmpp != '\0'; |
| 2253 | ++cmpp) |
| 2254 | ADDW ((unsigned char) *cmpp); |
| 2255 | |
| 2256 | got_dot = 1; |
| 2257 | } |
| 2258 | else if (n == 10 && (flags & GROUP) != 0 |
| 2259 | && ! got_dot) |
| 2260 | { |
| 2261 | /* Add all the characters. */ |
| 2262 | for (cmpp = thousands; *cmpp != '\0'; |
| 2263 | ++cmpp) |
| 2264 | ADDW ((unsigned char) *cmpp); |
| 2265 | } |
| 2266 | else |
| 2267 | /* The last read character is not part |
| 2268 | of the number anymore. */ |
| 2269 | n = 12; |
| 2270 | |
| 2271 | break; |
| 2272 | } |
| 2273 | |
| 2274 | /* We are pushing all read characters back. */ |
| 2275 | if (cmpp > mbdigits[n]) |
| 2276 | { |
| 2277 | ungetc (c, s); |
| 2278 | while (--cmpp > mbdigits[n]) |
| 2279 | ungetc_not_eof ((unsigned char) *cmpp, s); |
| 2280 | c = (unsigned char) *cmpp; |
| 2281 | } |
| 2282 | #endif |
| 2283 | } |
| 2284 | |
| 2285 | if (n >= 12) |
| 2286 | { |
| 2287 | /* The last read character is not part |
| 2288 | of the number anymore. */ |
| 2289 | ungetc (c, s); |
| 2290 | break; |
| 2291 | } |
| 2292 | } |
| 2293 | |
| 2294 | if (width == 0 || inchar () == EOF) |
| 2295 | break; |
| 2296 | |
| 2297 | if (width > 0) |
| 2298 | --width; |
| 2299 | } |
| 2300 | } |
| 2301 | |
| 2302 | #ifndef COMPILE_WSCANF |
| 2303 | no_i18nflt: |
| 2304 | ; |
| 2305 | #endif |
| 2306 | } |
| 2307 | |
| 2308 | /* Have we read any character? If we try to read a number |
| 2309 | in hexadecimal notation and we have read only the `0x' |
| 2310 | prefix this is an error. */ |
| 2311 | if (__builtin_expect (wpsize == 0 |
| 2312 | || ((flags & HEXA_FLOAT) && wpsize == 2), 0)) |
| 2313 | conv_error (); |
| 2314 | |
| 2315 | scan_float: |
| 2316 | /* Convert the number. */ |
| 2317 | ADDW (L_('\0')); |
| 2318 | if ((flags & LONGDBL) && !__ldbl_is_dbl) |
| 2319 | { |
| 2320 | long double d = __strtold_internal (wp, &tw, flags & GROUP); |
| 2321 | if (!(flags & SUPPRESS) && tw != wp) |
| 2322 | *ARG (long double *) = negative ? -d : d; |
| 2323 | } |
| 2324 | else if (flags & (LONG | LONGDBL)) |
| 2325 | { |
| 2326 | double d = __strtod_internal (wp, &tw, flags & GROUP); |
| 2327 | if (!(flags & SUPPRESS) && tw != wp) |
| 2328 | *ARG (double *) = negative ? -d : d; |
| 2329 | } |
| 2330 | else |
| 2331 | { |
| 2332 | float d = __strtof_internal (wp, &tw, flags & GROUP); |
| 2333 | if (!(flags & SUPPRESS) && tw != wp) |
| 2334 | *ARG (float *) = negative ? -d : d; |
| 2335 | } |
| 2336 | |
| 2337 | if (__glibc_unlikely (tw == wp)) |
| 2338 | conv_error (); |
| 2339 | |
| 2340 | if (!(flags & SUPPRESS)) |
| 2341 | ++done; |
| 2342 | break; |
| 2343 | |
| 2344 | case L_('['): /* Character class. */ |
| 2345 | if (flags & LONG) |
| 2346 | STRING_ARG (wstr, wchar_t, 100); |
| 2347 | else |
| 2348 | STRING_ARG (str, char, 100); |
| 2349 | |
| 2350 | if (*f == L_('^')) |
| 2351 | { |
| 2352 | ++f; |
| 2353 | not_in = 1; |
| 2354 | } |
| 2355 | else |
| 2356 | not_in = 0; |
| 2357 | |
| 2358 | if (width < 0) |
| 2359 | /* There is no width given so there is also no limit on the |
| 2360 | number of characters we read. Therefore we set width to |
| 2361 | a very high value to make the algorithm easier. */ |
| 2362 | width = INT_MAX; |
| 2363 | |
| 2364 | #ifdef COMPILE_WSCANF |
| 2365 | /* Find the beginning and the end of the scanlist. We are not |
| 2366 | creating a lookup table since it would have to be too large. |
| 2367 | Instead we search each time through the string. This is not |
| 2368 | a constant lookup time but who uses this feature deserves to |
| 2369 | be punished. */ |
| 2370 | tw = (wchar_t *) f; /* Marks the beginning. */ |
| 2371 | |
| 2372 | if (*f == L']') |
| 2373 | ++f; |
| 2374 | |
| 2375 | while ((fc = *f++) != L'\0' && fc != L']'); |
| 2376 | |
| 2377 | if (__glibc_unlikely (fc == L'\0')) |
| 2378 | conv_error (); |
| 2379 | wchar_t *twend = (wchar_t *) f - 1; |
| 2380 | #else |
| 2381 | /* Fill WP with byte flags indexed by character. |
| 2382 | We will use this flag map for matching input characters. */ |
| 2383 | if (wpmax < UCHAR_MAX + 1) |
| 2384 | { |
| 2385 | wpmax = UCHAR_MAX + 1; |
| 2386 | wp = (char *) alloca (wpmax); |
| 2387 | } |
| 2388 | memset (wp, '\0', UCHAR_MAX + 1); |
| 2389 | |
| 2390 | fc = *f; |
| 2391 | if (fc == ']' || fc == '-') |
| 2392 | { |
| 2393 | /* If ] or - appears before any char in the set, it is not |
| 2394 | the terminator or separator, but the first char in the |
| 2395 | set. */ |
| 2396 | wp[fc] = 1; |
| 2397 | ++f; |
| 2398 | } |
| 2399 | |
| 2400 | while ((fc = *f++) != '\0' && fc != ']') |
| 2401 | if (fc == '-' && *f != '\0' && *f != ']' |
| 2402 | && (unsigned char) f[-2] <= (unsigned char) *f) |
| 2403 | { |
| 2404 | /* Add all characters from the one before the '-' |
| 2405 | up to (but not including) the next format char. */ |
| 2406 | for (fc = (unsigned char) f[-2]; fc < (unsigned char) *f; ++fc) |
| 2407 | wp[fc] = 1; |
| 2408 | } |
| 2409 | else |
| 2410 | /* Add the character to the flag map. */ |
| 2411 | wp[fc] = 1; |
| 2412 | |
| 2413 | if (__glibc_unlikely (fc == '\0')) |
| 2414 | conv_error(); |
| 2415 | #endif |
| 2416 | |
| 2417 | if (flags & LONG) |
| 2418 | { |
| 2419 | size_t now = read_in; |
| 2420 | #ifdef COMPILE_WSCANF |
| 2421 | if (__glibc_unlikely (inchar () == WEOF)) |
| 2422 | input_error (); |
| 2423 | |
| 2424 | do |
| 2425 | { |
| 2426 | wchar_t *runp; |
| 2427 | |
| 2428 | /* Test whether it's in the scanlist. */ |
| 2429 | runp = tw; |
| 2430 | while (runp < twend) |
| 2431 | { |
| 2432 | if (runp[0] == L'-' && runp[1] != '\0' |
| 2433 | && runp + 1 != twend |
| 2434 | && runp != tw |
| 2435 | && (unsigned int) runp[-1] <= (unsigned int) runp[1]) |
| 2436 | { |
| 2437 | /* Match against all characters in between the |
| 2438 | first and last character of the sequence. */ |
| 2439 | wchar_t wc; |
| 2440 | |
| 2441 | for (wc = runp[-1] + 1; wc <= runp[1]; ++wc) |
| 2442 | if ((wint_t) wc == c) |
| 2443 | break; |
| 2444 | |
| 2445 | if (wc <= runp[1] && !not_in) |
| 2446 | break; |
| 2447 | if (wc <= runp[1] && not_in) |
| 2448 | { |
| 2449 | /* The current character is not in the |
| 2450 | scanset. */ |
| 2451 | ungetc (c, s); |
| 2452 | goto out; |
| 2453 | } |
| 2454 | |
| 2455 | runp += 2; |
| 2456 | } |
| 2457 | else |
| 2458 | { |
| 2459 | if ((wint_t) *runp == c && !not_in) |
| 2460 | break; |
| 2461 | if ((wint_t) *runp == c && not_in) |
| 2462 | { |
| 2463 | ungetc (c, s); |
| 2464 | goto out; |
| 2465 | } |
| 2466 | |
| 2467 | ++runp; |
| 2468 | } |
| 2469 | } |
| 2470 | |
| 2471 | if (runp == twend && !not_in) |
| 2472 | { |
| 2473 | ungetc (c, s); |
| 2474 | goto out; |
| 2475 | } |
| 2476 | |
| 2477 | if (!(flags & SUPPRESS)) |
| 2478 | { |
| 2479 | *wstr++ = c; |
| 2480 | |
| 2481 | if ((flags & MALLOC) |
| 2482 | && wstr == (wchar_t *) *strptr + strsize) |
| 2483 | { |
| 2484 | /* Enlarge the buffer. */ |
| 2485 | wstr = (wchar_t *) realloc (*strptr, |
| 2486 | (2 * strsize) |
| 2487 | * sizeof (wchar_t)); |
| 2488 | if (wstr == NULL) |
| 2489 | { |
| 2490 | /* Can't allocate that much. Last-ditch |
| 2491 | effort. */ |
| 2492 | wstr = (wchar_t *) |
| 2493 | realloc (*strptr, (strsize + 1) |
| 2494 | * sizeof (wchar_t)); |
| 2495 | if (wstr == NULL) |
| 2496 | { |
| 2497 | if (flags & POSIX_MALLOC) |
| 2498 | { |
| 2499 | done = EOF; |
| 2500 | goto errout; |
| 2501 | } |
| 2502 | /* We lose. Oh well. Terminate the string |
| 2503 | and stop converting, so at least we don't |
| 2504 | skip any input. */ |
| 2505 | ((wchar_t *) (*strptr))[strsize - 1] = L'\0'; |
| 2506 | strptr = NULL; |
| 2507 | ++done; |
| 2508 | conv_error (); |
| 2509 | } |
| 2510 | else |
| 2511 | { |
| 2512 | *strptr = (char *) wstr; |
| 2513 | wstr += strsize; |
| 2514 | ++strsize; |
| 2515 | } |
| 2516 | } |
| 2517 | else |
| 2518 | { |
| 2519 | *strptr = (char *) wstr; |
| 2520 | wstr += strsize; |
| 2521 | strsize *= 2; |
| 2522 | } |
| 2523 | } |
| 2524 | } |
| 2525 | } |
| 2526 | while (--width > 0 && inchar () != WEOF); |
| 2527 | out: |
| 2528 | #else |
| 2529 | char buf[MB_LEN_MAX]; |
| 2530 | size_t cnt = 0; |
| 2531 | mbstate_t cstate; |
| 2532 | |
| 2533 | if (__glibc_unlikely (inchar () == EOF)) |
| 2534 | input_error (); |
| 2535 | |
| 2536 | memset (&cstate, '\0', sizeof (cstate)); |
| 2537 | |
| 2538 | do |
| 2539 | { |
| 2540 | if (wp[c] == not_in) |
| 2541 | { |
| 2542 | ungetc_not_eof (c, s); |
| 2543 | break; |
| 2544 | } |
| 2545 | |
| 2546 | /* This is easy. */ |
| 2547 | if (!(flags & SUPPRESS)) |
| 2548 | { |
| 2549 | size_t n; |
| 2550 | |
| 2551 | /* Convert it into a wide character. */ |
| 2552 | buf[0] = c; |
| 2553 | n = __mbrtowc (wstr, buf, 1, &cstate); |
| 2554 | |
| 2555 | if (n == (size_t) -2) |
| 2556 | { |
| 2557 | /* Possibly correct character, just not enough |
| 2558 | input. */ |
| 2559 | ++cnt; |
| 2560 | assert (cnt < MB_CUR_MAX); |
| 2561 | continue; |
| 2562 | } |
| 2563 | cnt = 0; |
| 2564 | |
| 2565 | ++wstr; |
| 2566 | if ((flags & MALLOC) |
| 2567 | && wstr == (wchar_t *) *strptr + strsize) |
| 2568 | { |
| 2569 | /* Enlarge the buffer. */ |
| 2570 | wstr = (wchar_t *) realloc (*strptr, |
| 2571 | (2 * strsize |
| 2572 | * sizeof (wchar_t))); |
| 2573 | if (wstr == NULL) |
| 2574 | { |
| 2575 | /* Can't allocate that much. Last-ditch |
| 2576 | effort. */ |
| 2577 | wstr = (wchar_t *) |
| 2578 | realloc (*strptr, ((strsize + 1) |
| 2579 | * sizeof (wchar_t))); |
| 2580 | if (wstr == NULL) |
| 2581 | { |
| 2582 | if (flags & POSIX_MALLOC) |
| 2583 | { |
| 2584 | done = EOF; |
| 2585 | goto errout; |
| 2586 | } |
| 2587 | /* We lose. Oh well. Terminate the |
| 2588 | string and stop converting, |
| 2589 | so at least we don't skip any input. */ |
| 2590 | ((wchar_t *) (*strptr))[strsize - 1] = L'\0'; |
| 2591 | strptr = NULL; |
| 2592 | ++done; |
| 2593 | conv_error (); |
| 2594 | } |
| 2595 | else |
| 2596 | { |
| 2597 | *strptr = (char *) wstr; |
| 2598 | wstr += strsize; |
| 2599 | ++strsize; |
| 2600 | } |
| 2601 | } |
| 2602 | else |
| 2603 | { |
| 2604 | *strptr = (char *) wstr; |
| 2605 | wstr += strsize; |
| 2606 | strsize *= 2; |
| 2607 | } |
| 2608 | } |
| 2609 | } |
| 2610 | |
| 2611 | if (--width <= 0) |
| 2612 | break; |
| 2613 | } |
| 2614 | while (inchar () != EOF); |
| 2615 | |
| 2616 | if (__glibc_unlikely (cnt != 0)) |
| 2617 | /* We stopped in the middle of recognizing another |
| 2618 | character. That's a problem. */ |
| 2619 | encode_error (); |
| 2620 | #endif |
| 2621 | |
| 2622 | if (__glibc_unlikely (now == read_in)) |
| 2623 | /* We haven't succesfully read any character. */ |
| 2624 | conv_error (); |
| 2625 | |
| 2626 | if (!(flags & SUPPRESS)) |
| 2627 | { |
| 2628 | *wstr++ = L'\0'; |
| 2629 | |
| 2630 | if ((flags & MALLOC) |
| 2631 | && wstr - (wchar_t *) *strptr != strsize) |
| 2632 | { |
| 2633 | wchar_t *cp = (wchar_t *) |
| 2634 | realloc (*strptr, ((wstr - (wchar_t *) *strptr) |
| 2635 | * sizeof(wchar_t))); |
| 2636 | if (cp != NULL) |
| 2637 | *strptr = (char *) cp; |
| 2638 | } |
| 2639 | strptr = NULL; |
| 2640 | |
| 2641 | ++done; |
| 2642 | } |
| 2643 | } |
| 2644 | else |
| 2645 | { |
| 2646 | size_t now = read_in; |
| 2647 | |
| 2648 | if (__glibc_unlikely (inchar () == EOF)) |
| 2649 | input_error (); |
| 2650 | |
| 2651 | #ifdef COMPILE_WSCANF |
| 2652 | |
| 2653 | memset (&state, '\0', sizeof (state)); |
| 2654 | |
| 2655 | do |
| 2656 | { |
| 2657 | wchar_t *runp; |
| 2658 | size_t n; |
| 2659 | |
| 2660 | /* Test whether it's in the scanlist. */ |
| 2661 | runp = tw; |
| 2662 | while (runp < twend) |
| 2663 | { |
| 2664 | if (runp[0] == L'-' && runp[1] != '\0' |
| 2665 | && runp + 1 != twend |
| 2666 | && runp != tw |
| 2667 | && (unsigned int) runp[-1] <= (unsigned int) runp[1]) |
| 2668 | { |
| 2669 | /* Match against all characters in between the |
| 2670 | first and last character of the sequence. */ |
| 2671 | wchar_t wc; |
| 2672 | |
| 2673 | for (wc = runp[-1] + 1; wc <= runp[1]; ++wc) |
| 2674 | if ((wint_t) wc == c) |
| 2675 | break; |
| 2676 | |
| 2677 | if (wc <= runp[1] && !not_in) |
| 2678 | break; |
| 2679 | if (wc <= runp[1] && not_in) |
| 2680 | { |
| 2681 | /* The current character is not in the |
| 2682 | scanset. */ |
| 2683 | ungetc (c, s); |
| 2684 | goto out2; |
| 2685 | } |
| 2686 | |
| 2687 | runp += 2; |
| 2688 | } |
| 2689 | else |
| 2690 | { |
| 2691 | if ((wint_t) *runp == c && !not_in) |
| 2692 | break; |
| 2693 | if ((wint_t) *runp == c && not_in) |
| 2694 | { |
| 2695 | ungetc (c, s); |
| 2696 | goto out2; |
| 2697 | } |
| 2698 | |
| 2699 | ++runp; |
| 2700 | } |
| 2701 | } |
| 2702 | |
| 2703 | if (runp == twend && !not_in) |
| 2704 | { |
| 2705 | ungetc (c, s); |
| 2706 | goto out2; |
| 2707 | } |
| 2708 | |
| 2709 | if (!(flags & SUPPRESS)) |
| 2710 | { |
| 2711 | if ((flags & MALLOC) |
| 2712 | && str + MB_CUR_MAX >= *strptr + strsize) |
| 2713 | { |
| 2714 | /* Enlarge the buffer. */ |
| 2715 | size_t strleng = str - *strptr; |
| 2716 | char *newstr; |
| 2717 | |
| 2718 | newstr = (char *) realloc (*strptr, 2 * strsize); |
| 2719 | if (newstr == NULL) |
| 2720 | { |
| 2721 | /* Can't allocate that much. Last-ditch |
| 2722 | effort. */ |
| 2723 | newstr = (char *) realloc (*strptr, |
| 2724 | strleng + MB_CUR_MAX); |
| 2725 | if (newstr == NULL) |
| 2726 | { |
| 2727 | if (flags & POSIX_MALLOC) |
| 2728 | { |
| 2729 | done = EOF; |
| 2730 | goto errout; |
| 2731 | } |
| 2732 | /* We lose. Oh well. Terminate the string |
| 2733 | and stop converting, so at least we don't |
| 2734 | skip any input. */ |
| 2735 | ((char *) (*strptr))[strleng] = '\0'; |
| 2736 | strptr = NULL; |
| 2737 | ++done; |
| 2738 | conv_error (); |
| 2739 | } |
| 2740 | else |
| 2741 | { |
| 2742 | *strptr = newstr; |
| 2743 | str = newstr + strleng; |
| 2744 | strsize = strleng + MB_CUR_MAX; |
| 2745 | } |
| 2746 | } |
| 2747 | else |
| 2748 | { |
| 2749 | *strptr = newstr; |
| 2750 | str = newstr + strleng; |
| 2751 | strsize *= 2; |
| 2752 | } |
| 2753 | } |
| 2754 | } |
| 2755 | |
| 2756 | n = __wcrtomb (!(flags & SUPPRESS) ? str : NULL, c, &state); |
| 2757 | if (__glibc_unlikely (n == (size_t) -1)) |
| 2758 | encode_error (); |
| 2759 | |
| 2760 | assert (n <= MB_CUR_MAX); |
| 2761 | str += n; |
| 2762 | } |
| 2763 | while (--width > 0 && inchar () != WEOF); |
| 2764 | out2: |
| 2765 | #else |
| 2766 | do |
| 2767 | { |
| 2768 | if (wp[c] == not_in) |
| 2769 | { |
| 2770 | ungetc_not_eof (c, s); |
| 2771 | break; |
| 2772 | } |
| 2773 | |
| 2774 | /* This is easy. */ |
| 2775 | if (!(flags & SUPPRESS)) |
| 2776 | { |
| 2777 | *str++ = c; |
| 2778 | if ((flags & MALLOC) |
| 2779 | && (char *) str == *strptr + strsize) |
| 2780 | { |
| 2781 | /* Enlarge the buffer. */ |
| 2782 | size_t newsize = 2 * strsize; |
| 2783 | |
| 2784 | allocagain: |
| 2785 | str = (char *) realloc (*strptr, newsize); |
| 2786 | if (str == NULL) |
| 2787 | { |
| 2788 | /* Can't allocate that much. Last-ditch |
| 2789 | effort. */ |
| 2790 | if (newsize > strsize + 1) |
| 2791 | { |
| 2792 | newsize = strsize + 1; |
| 2793 | goto allocagain; |
| 2794 | } |
| 2795 | if (flags & POSIX_MALLOC) |
| 2796 | { |
| 2797 | done = EOF; |
| 2798 | goto errout; |
| 2799 | } |
| 2800 | /* We lose. Oh well. Terminate the |
| 2801 | string and stop converting, |
| 2802 | so at least we don't skip any input. */ |
| 2803 | ((char *) (*strptr))[strsize - 1] = '\0'; |
| 2804 | strptr = NULL; |
| 2805 | ++done; |
| 2806 | conv_error (); |
| 2807 | } |
| 2808 | else |
| 2809 | { |
| 2810 | *strptr = (char *) str; |
| 2811 | str += strsize; |
| 2812 | strsize = newsize; |
| 2813 | } |
| 2814 | } |
| 2815 | } |
| 2816 | } |
| 2817 | while (--width > 0 && inchar () != EOF); |
| 2818 | #endif |
| 2819 | |
| 2820 | if (__glibc_unlikely (now == read_in)) |
| 2821 | /* We haven't succesfully read any character. */ |
| 2822 | conv_error (); |
| 2823 | |
| 2824 | if (!(flags & SUPPRESS)) |
| 2825 | { |
| 2826 | #ifdef COMPILE_WSCANF |
| 2827 | /* We have to emit the code to get into the initial |
| 2828 | state. */ |
| 2829 | char buf[MB_LEN_MAX]; |
| 2830 | size_t n = __wcrtomb (buf, L'\0', &state); |
| 2831 | if (n > 0 && (flags & MALLOC) |
| 2832 | && str + n >= *strptr + strsize) |
| 2833 | { |
| 2834 | /* Enlarge the buffer. */ |
| 2835 | size_t strleng = str - *strptr; |
| 2836 | char *newstr; |
| 2837 | |
| 2838 | newstr = (char *) realloc (*strptr, strleng + n + 1); |
| 2839 | if (newstr == NULL) |
| 2840 | { |
| 2841 | if (flags & POSIX_MALLOC) |
| 2842 | { |
| 2843 | done = EOF; |
| 2844 | goto errout; |
| 2845 | } |
| 2846 | /* We lose. Oh well. Terminate the string |
| 2847 | and stop converting, so at least we don't |
| 2848 | skip any input. */ |
| 2849 | ((char *) (*strptr))[strleng] = '\0'; |
| 2850 | strptr = NULL; |
| 2851 | ++done; |
| 2852 | conv_error (); |
| 2853 | } |
| 2854 | else |
| 2855 | { |
| 2856 | *strptr = newstr; |
| 2857 | str = newstr + strleng; |
| 2858 | strsize = strleng + n + 1; |
| 2859 | } |
| 2860 | } |
| 2861 | |
| 2862 | str = __mempcpy (str, buf, n); |
| 2863 | #endif |
| 2864 | *str++ = '\0'; |
| 2865 | |
| 2866 | if ((flags & MALLOC) && str - *strptr != strsize) |
| 2867 | { |
| 2868 | char *cp = (char *) realloc (*strptr, str - *strptr); |
| 2869 | if (cp != NULL) |
| 2870 | *strptr = cp; |
| 2871 | } |
| 2872 | strptr = NULL; |
| 2873 | |
| 2874 | ++done; |
| 2875 | } |
| 2876 | } |
| 2877 | break; |
| 2878 | |
| 2879 | case L_('p'): /* Generic pointer. */ |
| 2880 | base = 16; |
| 2881 | /* A PTR must be the same size as a `long int'. */ |
| 2882 | flags &= ~(SHORT|LONGDBL); |
| 2883 | if (need_long) |
| 2884 | flags |= LONG; |
| 2885 | flags |= READ_POINTER; |
| 2886 | goto number; |
| 2887 | |
| 2888 | default: |
| 2889 | /* If this is an unknown format character punt. */ |
| 2890 | conv_error (); |
| 2891 | } |
| 2892 | } |
| 2893 | |
| 2894 | /* The last thing we saw int the format string was a white space. |
| 2895 | Consume the last white spaces. */ |
| 2896 | if (skip_space) |
| 2897 | { |
| 2898 | do |
| 2899 | c = inchar (); |
| 2900 | while (ISSPACE (c)); |
| 2901 | ungetc (c, s); |
| 2902 | } |
| 2903 | |
| 2904 | errout: |
| 2905 | /* Unlock stream. */ |
| 2906 | UNLOCK_STREAM (s); |
| 2907 | |
| 2908 | if (use_malloc) |
| 2909 | free (wp); |
| 2910 | |
| 2911 | if (errp != NULL) |
| 2912 | *errp |= errval; |
| 2913 | |
| 2914 | if (__glibc_unlikely (done == EOF)) |
| 2915 | { |
| 2916 | if (__glibc_unlikely (ptrs_to_free != NULL)) |
| 2917 | { |
| 2918 | struct ptrs_to_free *p = ptrs_to_free; |
| 2919 | while (p != NULL) |
| 2920 | { |
| 2921 | for (size_t cnt = 0; cnt < p->count; ++cnt) |
| 2922 | { |
| 2923 | free (*p->ptrs[cnt]); |
| 2924 | *p->ptrs[cnt] = NULL; |
| 2925 | } |
| 2926 | p = p->next; |
| 2927 | ptrs_to_free = p; |
| 2928 | } |
| 2929 | } |
| 2930 | } |
| 2931 | else if (__glibc_unlikely (strptr != NULL)) |
| 2932 | { |
| 2933 | free (*strptr); |
| 2934 | *strptr = NULL; |
| 2935 | } |
| 2936 | return done; |
| 2937 | } |
| 2938 | |
| 2939 | #ifdef COMPILE_WSCANF |
| 2940 | int |
| 2941 | __vfwscanf (FILE *s, const wchar_t *format, va_list argptr) |
| 2942 | { |
| 2943 | return _IO_vfwscanf (s, format, argptr, NULL); |
| 2944 | } |
| 2945 | ldbl_weak_alias (__vfwscanf, vfwscanf) |
| 2946 | #else |
| 2947 | int |
| 2948 | ___vfscanf (FILE *s, const char *format, va_list argptr) |
| 2949 | { |
| 2950 | return _IO_vfscanf_internal (s, format, argptr, NULL); |
| 2951 | } |
| 2952 | ldbl_strong_alias (_IO_vfscanf_internal, _IO_vfscanf) |
| 2953 | ldbl_hidden_def (_IO_vfscanf_internal, _IO_vfscanf) |
| 2954 | ldbl_strong_alias (___vfscanf, __vfscanf) |
| 2955 | ldbl_hidden_def (___vfscanf, __vfscanf) |
| 2956 | ldbl_weak_alias (___vfscanf, vfscanf) |
| 2957 | #endif |