url/url_canon_icu.cc

   1 // Copyright 2011, Google Inc.
   2 // All rights reserved.
   3 //
   4 // Redistribution and use in source and binary forms, with or without
   5 // modification, are permitted provided that the following conditions are
   6 // met:
   7 //
   8 //     * Redistributions of source code must retain the above copyright
   9 // notice, this list of conditions and the following disclaimer.
  10 //     * Redistributions in binary form must reproduce the above
  11 // copyright notice, this list of conditions and the following disclaimer
  12 // in the documentation and/or other materials provided with the
  13 // distribution.
  14 //     * Neither the name of Google Inc. nor the names of its
  15 // contributors may be used to endorse or promote products derived from
  16 // this software without specific prior written permission.
  17 //
  18 // THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
  19 // "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
  20 // LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
  21 // A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
  22 // OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
  23 // SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
  24 // LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
  25 // DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
  26 // THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
  27 // (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
  28 // OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  29
  30 // ICU integration functions.
  31
  32 #include <stdlib.h>
  33 #include <string.h>
  34 #include <unicode/ucnv.h>
  35 #include <unicode/ucnv_cb.h>
  36 #include <unicode/uidna.h>
  37
  38 #include "base/logging.h"
  39 #include "url/url_canon_icu.h"
  40 #include "url/url_canon_internal.h"  // for _itoa_s
  41
  42 namespace url_canon {
  43
  44 namespace {
  45
  46 // Called when converting a character that can not be represented, this will
  47 // append an escaped version of the numerical character reference for that code
  48 // point. It is of the form "&#1234;" and we will escape the non-digits to
  49 // "%26%231234%3B". Why? This is what Netscape did back in the olden days.
  50 void appendURLEscapedChar(const void* context,
  51                           UConverterFromUnicodeArgs* from_args,
  52                           const UChar* code_units,
  53                           int32_t length,
  54                           UChar32 code_point,
  55                           UConverterCallbackReason reason,
  56                           UErrorCode* err) {
  57   if (reason == UCNV_UNASSIGNED) {
  58     *err = U_ZERO_ERROR;
  59
  60     const static int prefix_len = 6;
  61     const static char prefix[prefix_len + 1] = "%26%23";  // "&#" percent-escaped
  62     ucnv_cbFromUWriteBytes(from_args, prefix, prefix_len, 0, err);
  63
  64     DCHECK(code_point < 0x110000);
  65     char number[8];  // Max Unicode code point is 7 digits.
  66     _itoa_s(code_point, number, 10);
  67     int number_len = static_cast<int>(strlen(number));
  68     ucnv_cbFromUWriteBytes(from_args, number, number_len, 0, err);
  69
  70     const static int postfix_len = 3;
  71     const static char postfix[postfix_len + 1] = "%3B";   // ";" percent-escaped
  72     ucnv_cbFromUWriteBytes(from_args, postfix, postfix_len, 0, err);
  73   }
  74 }
  75
  76 // A class for scoping the installation of the invalid character callback.
  77 class AppendHandlerInstaller {
  78  public:
  79   // The owner of this object must ensure that the converter is alive for the
  80   // duration of this object's lifetime.
  81   AppendHandlerInstaller(UConverter* converter) : converter_(converter) {
  82     UErrorCode err = U_ZERO_ERROR;
  83     ucnv_setFromUCallBack(converter_, appendURLEscapedChar, 0,
  84                           &old_callback_, &old_context_, &err);
  85   }
  86
  87   ~AppendHandlerInstaller() {
  88     UErrorCode err = U_ZERO_ERROR;
  89     ucnv_setFromUCallBack(converter_, old_callback_, old_context_, 0, 0, &err);
  90   }
  91
  92  private:
  93   UConverter* converter_;
  94
  95   UConverterFromUCallback old_callback_;
  96   const void* old_context_;
  97 };
  98
  99 }  // namespace
 100
 101 ICUCharsetConverter::ICUCharsetConverter(UConverter* converter)
 102     : converter_(converter) {
 103 }
 104
 105 ICUCharsetConverter::~ICUCharsetConverter() {
 106 }
 107
 108 void ICUCharsetConverter::ConvertFromUTF16(const char16* input,
 109                                            int input_len,
 110                                            CanonOutput* output) {
 111   // Install our error handler. It will be called for character that can not
 112   // be represented in the destination character set.
 113   AppendHandlerInstaller handler(converter_);
 114
 115   int begin_offset = output->length();
 116   int dest_capacity = output->capacity() - begin_offset;
 117   output->set_length(output->length());
 118
 119   do {
 120     UErrorCode err = U_ZERO_ERROR;
 121     char* dest = &output->data()[begin_offset];
 122     int required_capacity = ucnv_fromUChars(converter_, dest, dest_capacity,
 123                                             input, input_len, &err);
 124     if (err != U_BUFFER_OVERFLOW_ERROR) {
 125       output->set_length(begin_offset + required_capacity);
 126       return;
 127     }
 128
 129     // Output didn't fit, expand
 130     dest_capacity = required_capacity;
 131     output->Resize(begin_offset + dest_capacity);
 132   } while (true);
 133 }
 134
 135 // Converts the Unicode input representing a hostname to ASCII using IDN rules.
 136 // The output must be ASCII, but is represented as wide characters.
 137 //
 138 // On success, the output will be filled with the ASCII host name and it will
 139 // return true. Unlike most other canonicalization functions, this assumes that
 140 // the output is empty. The beginning of the host will be at offset 0, and
 141 // the length of the output will be set to the length of the new host name.
 142 //
 143 // On error, this will return false. The output in this case is undefined.
 144 bool IDNToASCII(const char16* src, int src_len, CanonOutputW* output) {
 145   DCHECK(output->length() == 0);  // Output buffer is assumed empty.
 146   while (true) {
 147     // Use ALLOW_UNASSIGNED to be more tolerant of hostnames that violate
 148     // the spec (which do exist). This does not present any risk and is a
 149     // little more future proof.
 150     UErrorCode err = U_ZERO_ERROR;
 151     int num_converted = uidna_IDNToASCII(src, src_len, output->data(),
 152                                          output->capacity(),
 153                                          UIDNA_ALLOW_UNASSIGNED, NULL, &err);
 154     if (err == U_ZERO_ERROR) {
 155       output->set_length(num_converted);
 156       return true;
 157     }
 158     if (err != U_BUFFER_OVERFLOW_ERROR)
 159       return false;  // Unknown error, give up.
 160
 161     // Not enough room in our buffer, expand.
 162     output->Resize(output->capacity() * 2);
 163   }
 164 }
 165
 166 bool ReadUTFChar(const char* str, int* begin, int length,
 167                  unsigned* code_point_out) {
 168   int code_point;  // Avoids warning when U8_NEXT writes -1 to it.
 169   U8_NEXT(str, *begin, length, code_point);
 170   *code_point_out = static_cast<unsigned>(code_point);
 171
 172   // The ICU macro above moves to the next char, we want to point to the last
 173   // char consumed.
 174   (*begin)--;
 175
 176   // Validate the decoded value.
 177   if (U_IS_UNICODE_CHAR(code_point))
 178     return true;
 179   *code_point_out = kUnicodeReplacementCharacter;
 180   return false;
 181 }
 182
 183 bool ReadUTFChar(const char16* str, int* begin, int length,
 184                  unsigned* code_point) {
 185   if (U16_IS_SURROGATE(str[*begin])) {
 186     if (!U16_IS_SURROGATE_LEAD(str[*begin]) || *begin + 1 >= length ||
 187         !U16_IS_TRAIL(str[*begin + 1])) {
 188       // Invalid surrogate pair.
 189       *code_point = kUnicodeReplacementCharacter;
 190       return false;
 191     } else {
 192       // Valid surrogate pair.
 193       *code_point = U16_GET_SUPPLEMENTARY(str[*begin], str[*begin + 1]);
 194       (*begin)++;
 195     }
 196   } else {
 197     // Not a surrogate, just one 16-bit word.
 198     *code_point = str[*begin];
 199   }
 200
 201   if (U_IS_UNICODE_CHAR(*code_point))
 202     return true;
 203
 204   // Invalid code point.
 205   *code_point = kUnicodeReplacementCharacter;
 206   return false;
 207 }
 208
 209 }  // namespace url_canon