summaryrefslogtreecommitdiffstats
path: root/net/http/http_util.cc
blob: a56a4db7eb8fcd6d3824d2a3a95fdf1fc3fb30d4 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
// Copyright 2008, Google Inc.
// All rights reserved.
//
// Redistribution and use in source and binary forms, with or without
// modification, are permitted provided that the following conditions are
// met:
//
//    * Redistributions of source code must retain the above copyright
// notice, this list of conditions and the following disclaimer.
//    * Redistributions in binary form must reproduce the above
// copyright notice, this list of conditions and the following disclaimer
// in the documentation and/or other materials provided with the
// distribution.
//    * Neither the name of Google Inc. nor the names of its
// contributors may be used to endorse or promote products derived from
// this software without specific prior written permission.
//
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

// The rules for parsing content-types were borrowed from Firefox:
// http://lxr.mozilla.org/mozilla/source/netwerk/base/src/nsURLHelper.cpp#834

#include "net/http/http_util.h"

#include <algorithm>

#include "base/logging.h"
#include "base/string_util.h"

using std::string;

namespace net {

//-----------------------------------------------------------------------------

// Return the index of the closing quote of the string, if any.
static size_t FindStringEnd(const string& line, size_t start, char delim) {
  DCHECK(start < line.length() && line[start] == delim &&
         (delim == '"' || delim == '\''));

  const char set[] = { delim, '\\', '\0' };
  for (;;) {
    // start points to either the start quote or the last
    // escaped char (the char following a '\\')

    size_t end = line.find_first_of(set, start + 1);
    if (end == string::npos)
      return line.length();

    if (line[end] == '\\') {
      // Hit a backslash-escaped char.  Need to skip over it.
      start = end + 1;
      if (start == line.length())
        return start;

      // Go back to looking for the next escape or the string end
      continue;
    }

    return end;
  }

  NOTREACHED();
  return line.length();
}

//-----------------------------------------------------------------------------

// static
size_t HttpUtil::FindDelimiter(const string& line, size_t search_start,
                               char delimiter) {
  do {
    // search_start points to the spot from which we should start looking
    // for the delimiter.
    const char delim_str[] = { delimiter, '"', '\'', '\0' };
    size_t cur_delim_pos = line.find_first_of(delim_str, search_start);
    if (cur_delim_pos == string::npos)
      return line.length();

    char ch = line[cur_delim_pos];
    if (ch == delimiter) {
      // Found delimiter
      return cur_delim_pos;
    }

    // We hit the start of a quoted string.  Look for its end.
    search_start = FindStringEnd(line, cur_delim_pos, ch);
    if (search_start == line.length())
      return search_start;

    ++search_start;

    // search_start now points to the first char after the end of the
    // string, so just go back to the top of the loop and look for
    // |delimiter| again.
  } while (true);

  NOTREACHED();
  return line.length();
}

// static
void HttpUtil::ParseContentType(const string& content_type_str,
                                string* mime_type, string* charset,
                                bool *had_charset) {
  // Trim leading and trailing whitespace from type.  We include '(' in
  // the trailing trim set to catch media-type comments, which are not at all
  // standard, but may occur in rare cases.
  size_t type_val = content_type_str.find_first_not_of(HTTP_LWS);
  type_val = std::min(type_val, content_type_str.length());
  size_t type_end = content_type_str.find_first_of(HTTP_LWS ";(", type_val);
  if (string::npos == type_end)
    type_end = content_type_str.length();

  size_t charset_val = 0;
  size_t charset_end = 0;

  // Iterate over parameters
  bool type_has_charset = false;
  size_t param_start = content_type_str.find_first_of(';', type_end);
  if (param_start != string::npos) {
    // We have parameters.  Iterate over them.
    size_t cur_param_start = param_start + 1;
    do {
      size_t cur_param_end =
          FindDelimiter(content_type_str, cur_param_start, ';');

      size_t param_name_start = content_type_str.find_first_not_of(HTTP_LWS,
          cur_param_start);
      param_name_start = std::min(param_name_start, cur_param_end);

      static const char charset_str[] = "charset=";
      size_t charset_end_offset = std::min(param_name_start +
          sizeof(charset_str) - 1, cur_param_end);
      if (LowerCaseEqualsASCII(content_type_str.begin() + param_name_start,
          content_type_str.begin() + charset_end_offset, charset_str)) {
        charset_val = param_name_start + sizeof(charset_str) - 1;
        charset_end = cur_param_end;
        type_has_charset = true;
      }

      cur_param_start = cur_param_end + 1;
    } while (cur_param_start < content_type_str.length());
  }

  if (type_has_charset) {
    // Trim leading and trailing whitespace from charset_val.  We include
    // '(' in the trailing trim set to catch media-type comments, which are
    // not at all standard, but may occur in rare cases.
    charset_val = content_type_str.find_first_not_of(HTTP_LWS, charset_val);
    charset_val = std::min(charset_val, charset_end);
    char first_char = content_type_str[charset_val];
    if (first_char == '"' || first_char == '\'') {
      charset_end = FindStringEnd(content_type_str, charset_val, first_char);
      ++charset_val;
      DCHECK(charset_end >= charset_val);
    } else {
      charset_end = std::min(content_type_str.find_first_of(HTTP_LWS ";(",
                                                            charset_val),
                             charset_end);
    }
  }

  // if the server sent "*/*", it is meaningless, so do not store it.
  // also, if type_val is the same as mime_type, then just update the
  // charset.  however, if charset is empty and mime_type hasn't
  // changed, then don't wipe-out an existing charset.  We
  // also want to reject a mime-type if it does not include a slash.
  // some servers give junk after the charset parameter, which may
  // include a comma, so this check makes us a bit more tolerant.
  if (content_type_str.length() != 0 &&
      content_type_str != "*/*" &&
      content_type_str.find_first_of('/') != string::npos) {
    // Common case here is that mime_type is empty
    bool eq = !mime_type->empty() &&
        LowerCaseEqualsASCII(content_type_str.begin() + type_val,
                             content_type_str.begin() + type_end,
                             mime_type->data());
    if (!eq) {
      mime_type->assign(content_type_str.begin() + type_val,
                        content_type_str.begin() + type_end);
      StringToLowerASCII(mime_type);
    }
    if ((!eq && *had_charset) || type_has_charset) {
      *had_charset = true;
      charset->assign(content_type_str.begin() + charset_val,
                      content_type_str.begin() + charset_end);
      StringToLowerASCII(charset);
    }
  }
}

// static
bool HttpUtil::HasHeader(const std::string& headers, const char* name) {
  size_t name_len = strlen(name);
  string::const_iterator it =
      std::search(headers.begin(),
                  headers.end(),
                  name,
                  name + name_len,
                  CaseInsensitiveCompareASCII<char>());
  if (it == headers.end())
    return false;

  // ensure match is prefixed by newline
  if (it != headers.begin() && it[-1] != '\n')
    return false;

  // ensure match is suffixed by colon
  if (it + name_len >= headers.end() || it[name_len] != ':')
    return false;

  return true;
}

// static
bool HttpUtil::IsNonCoalescingHeader(string::const_iterator name_begin,
                                     string::const_iterator name_end) {
  // NOTE: "set-cookie2" headers do not support expires attributes, so we don't
  // have to list them here.
  const char* kNonCoalescingHeaders[] = {
    "date",
    "expires",
    "last-modified",
    "location",  // See bug 1050541 for details
    "retry-after",
    "set-cookie"
  };
  for (size_t i = 0; i < arraysize(kNonCoalescingHeaders); ++i) {
    if (LowerCaseEqualsASCII(name_begin, name_end, kNonCoalescingHeaders[i]))
      return true;
  }
  return false;
}

void HttpUtil::TrimLWS(string::const_iterator* begin,
                       string::const_iterator* end) {
  // leading whitespace
  while (*begin < *end && strchr(HTTP_LWS, (*begin)[0]))
    ++(*begin);

  // trailing whitespace
  while (*begin < *end && strchr(HTTP_LWS, (*end)[-1]))
    --(*end);
}

int HttpUtil::LocateEndOfHeaders(const char* buf, int buf_len) {
  bool was_lf = false;
  char last_c = '\0';
  for (int i = 0; i < buf_len; ++i) {
    char c = buf[i];
    if (c == '\n') {
      if (was_lf)
        return i + 1;
      was_lf = true;
    } else if (c != '\r' || last_c != '\n') {
      was_lf = false;
    }
    last_c = c;
  }
  return -1;
}

std::string HttpUtil::AssembleRawHeaders(const char* buf, int buf_len) {
  std::string raw_headers;

  // TODO(darin):
  //   - Handle header line continuations.
  //   - Be careful about CRs that appear spuriously mid header line.

  int line_start = 0;
  for (int i = 0; i < buf_len; ++i) {
    char c = buf[i];
    if (c == '\r' || c == '\n') {
      if (line_start != i) {
        // (line_start,i) is a header line.
        raw_headers.append(buf + line_start, buf + i);
        raw_headers.push_back('\0');
      }
      line_start = i + 1;
    }
  }
  raw_headers.push_back('\0');

  return raw_headers;
}

// BNF from section 4.2 of RFC 2616:
//
//   message-header = field-name ":" [ field-value ]
//   field-name     = token
//   field-value    = *( field-content | LWS )
//   field-content  = <the OCTETs making up the field-value
//                     and consisting of either *TEXT or combinations
//                     of token, separators, and quoted-string>
//

HttpUtil::HeadersIterator::HeadersIterator(string::const_iterator headers_begin,
                                           string::const_iterator headers_end,
                                           const std::string& line_delimiter)
    : lines_(headers_begin, headers_end, line_delimiter) {
}

bool HttpUtil::HeadersIterator::GetNext() {
  while (lines_.GetNext()) {
    name_begin_ = lines_.token_begin();
    values_end_ = lines_.token_end();

    string::const_iterator colon = find(name_begin_, values_end_, ':');
    if (colon == values_end_)
      continue;  // skip malformed header

    name_end_ = colon;
    TrimLWS(&name_begin_, &name_end_);
    if (name_begin_ == name_end_)
      continue;  // skip malformed header

    values_begin_ = colon + 1;
    TrimLWS(&values_begin_, &values_end_);

    // if we got a header name, then we are done.
    return true;
  }
  return false;
}

HttpUtil::ValuesIterator::ValuesIterator(
    string::const_iterator values_begin,
    string::const_iterator values_end,
    char delimiter)
    : values_(values_begin, values_end, string(1, delimiter)) {
  values_.set_quote_chars("\'\"");
}

bool HttpUtil::ValuesIterator::GetNext() {
  while (values_.GetNext()) {
    value_begin_ = values_.token_begin();
    value_end_ = values_.token_end();
    TrimLWS(&value_begin_, &value_end_);

    // bypass empty values.
    if (value_begin_ != value_end_)
      return true;
  }
  return false;
}

}  // namespace net