Subversion Repositories Kolibri OS

Rev

Go to most recent revision | Blame | Last modification | View Log | Download | RSS feed

  1. /*
  2.  * Copyright 2010 John-Mark Bell <jmb@netsurf-browser.org>
  3.  *
  4.  * This file is part of NetSurf, http://www.netsurf-browser.org/
  5.  *
  6.  * NetSurf is free software; you can redistribute it and/or modify
  7.  * it under the terms of the GNU General Public License as published by
  8.  * the Free Software Foundation; version 2 of the License.
  9.  *
  10.  * NetSurf is distributed in the hope that it will be useful,
  11.  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  12.  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  13.  * GNU General Public License for more details.
  14.  *
  15.  * You should have received a copy of the GNU General Public License
  16.  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  17.  */
  18.  
  19. #include <inttypes.h>
  20. #include <stdbool.h>
  21. #include <stdlib.h>
  22. #include <string.h>
  23.  
  24. #include "utils/http/primitives.h"
  25.  
  26. /**
  27.  * Skip past linear whitespace in input
  28.  *
  29.  * \param input  Pointer to current input byte. Updated on exit.
  30.  */
  31. void http__skip_LWS(const char **input)
  32. {
  33.         const char *pos = *input;
  34.  
  35.         while (*pos == ' ' || *pos == '\t')
  36.                 pos++;
  37.  
  38.         *input = pos;
  39. }
  40.  
  41. /**
  42.  * Determine if a character is valid for an HTTP token
  43.  *
  44.  * \param c  Character to consider
  45.  * \return True if character is valid, false otherwise
  46.  */
  47. static bool http_is_token_char(uint8_t c)
  48. {
  49.         /* [ 32 - 126 ] except ()<>@,;:\"/[]?={} SP HT */
  50.  
  51.         if (c <= ' ' || 126 < c)
  52.                 return false;
  53.  
  54.         return (strchr("()<>@,;:\\\"/[]?={}", c) == NULL);
  55. }
  56.  
  57. /**
  58.  * Parse an HTTP token
  59.  *
  60.  * \param input  Pointer to current input byte. Updated on exit.
  61.  * \param value  Pointer to location to receive on-heap token value.
  62.  * \return NSERROR_OK on success,
  63.  *         NSERROR_NOMEM on memory exhaustion,
  64.  *         NSERROR_NOT_FOUND if no token could be parsed
  65.  *
  66.  * The returned value is owned by the caller
  67.  */
  68. nserror http__parse_token(const char **input, lwc_string **value)
  69. {
  70.         const uint8_t *start = (const uint8_t *) *input;
  71.         const uint8_t *end;
  72.         lwc_string *token;
  73.  
  74.         end = start;
  75.         while (http_is_token_char(*end))
  76.                 end++;
  77.  
  78.         if (end == start)
  79.                 return NSERROR_NOT_FOUND;
  80.  
  81.         if (lwc_intern_string((const char *) start,
  82.                         end - start, &token) != lwc_error_ok)
  83.                 return NSERROR_NOMEM;
  84.  
  85.         *value = token;
  86.         *input = (const char *) end;
  87.  
  88.         return NSERROR_OK;
  89. }
  90.  
  91. /**
  92.  * Parse an HTTP quoted-string
  93.  *
  94.  * \param input  Pointer to current input byte. Updated on exit.
  95.  * \param value  Pointer to location to receive on-heap string value.
  96.  * \return NSERROR_OK on success,
  97.  *         NSERROR_NOMEM on memory exhaustion,
  98.  *         NSERROR_NOT_FOUND if no string could be parsed
  99.  *
  100.  * The returned value is owned by the caller
  101.  */
  102. nserror http__parse_quoted_string(const char **input, lwc_string **value)
  103. {
  104.         const uint8_t *start = (const uint8_t *) *input;
  105.         const uint8_t *end;
  106.         uint8_t c;
  107.         lwc_string *string_value;
  108.  
  109.         /* <"> *( qdtext | quoted-pair ) <">
  110.          * qdtext = any TEXT except <">
  111.          * quoted-pair = "\" CHAR
  112.          * TEXT = [ HT, CR, LF, 32-126, 128-255 ]
  113.          * CHAR = [ 0 - 127 ]
  114.          *
  115.          * \todo TEXT may contain non 8859-1 chars encoded per RFC 2047
  116.          * \todo Support quoted-pairs
  117.          */
  118.  
  119.         if (*start != '"')
  120.                 return NSERROR_NOT_FOUND;
  121.  
  122.         end = start = start + 1;
  123.  
  124.         c = *end;
  125.         while (c == '\t' || c == '\r' || c == '\n' ||
  126.                         c == ' ' || c == '!' ||
  127.                         ('#' <= c && c <= 126) || c > 127) {
  128.                 end++;
  129.                 c = *end;
  130.         }
  131.  
  132.         if (*end != '"')
  133.                 return NSERROR_NOT_FOUND;
  134.  
  135.         if (lwc_intern_string((const char *) start, end - start,
  136.                         &string_value) != lwc_error_ok)
  137.                 return NSERROR_NOMEM;
  138.  
  139.         *value = string_value;
  140.  
  141.         *input = (const char *) end + 1;
  142.  
  143.         return NSERROR_OK;
  144. }
  145.  
  146.  
  147.