1 /*
2 * Copyright (C) 2008, 2009 Google Inc. 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
31 #include "config.h"
32 #include "TextEncodingDetector.h"
33
34 #include "TextEncoding.h"
35 #include <wtf/UnusedParam.h>
36
37 #include "unicode/ucnv.h"
38 #include "unicode/ucsdet.h"
39
40 namespace WebCore {
41
detectTextEncoding(const char * data,size_t len,const char * hintEncodingName,TextEncoding * detectedEncoding)42 bool detectTextEncoding(const char* data, size_t len,
43 const char* hintEncodingName,
44 TextEncoding* detectedEncoding)
45 {
46 *detectedEncoding = TextEncoding();
47 int matchesCount = 0;
48 UErrorCode status = U_ZERO_ERROR;
49 UCharsetDetector* detector = ucsdet_open(&status);
50 if (U_FAILURE(status))
51 return false;
52 ucsdet_enableInputFilter(detector, true);
53 ucsdet_setText(detector, data, static_cast<int32_t>(len), &status);
54 if (U_FAILURE(status))
55 return false;
56
57 // FIXME: A few things we can do other than improving
58 // the ICU detector itself.
59 // 1. Use ucsdet_detectAll and pick the most likely one given
60 // "the context" (parent-encoding, referrer encoding, etc).
61 // 2. 'Emulate' Firefox/IE's non-Universal detectors (e.g.
62 // Chinese, Japanese, Russian, Korean and Hebrew) by picking the
63 // encoding with a highest confidence among the detector-specific
64 // limited set of candidate encodings.
65 // Below is a partial implementation of the first part of what's outlined
66 // above.
67 const UCharsetMatch** matches = ucsdet_detectAll(detector, &matchesCount, &status);
68 if (U_FAILURE(status)) {
69 ucsdet_close(detector);
70 return false;
71 }
72
73 const char* encoding = 0;
74 if (hintEncodingName) {
75 TextEncoding hintEncoding(hintEncodingName);
76 // 10 is the minimum confidence value consistent with the codepoint
77 // allocation in a given encoding. The size of a chunk passed to
78 // us varies even for the same html file (apparently depending on
79 // the network load). When we're given a rather short chunk, we
80 // don't have a sufficiently reliable signal other than the fact that
81 // the chunk is consistent with a set of encodings. So, instead of
82 // setting an arbitrary threshold, we have to scan all the encodings
83 // consistent with the data.
84 const int32_t kThresold = 10;
85 for (int i = 0; i < matchesCount; ++i) {
86 int32_t confidence = ucsdet_getConfidence(matches[i], &status);
87 if (U_FAILURE(status)) {
88 status = U_ZERO_ERROR;
89 continue;
90 }
91 if (confidence < kThresold)
92 break;
93 const char* matchEncoding = ucsdet_getName(matches[i], &status);
94 if (U_FAILURE(status)) {
95 status = U_ZERO_ERROR;
96 continue;
97 }
98 if (TextEncoding(matchEncoding) == hintEncoding) {
99 encoding = hintEncodingName;
100 break;
101 }
102 }
103 }
104 // If no match is found so far, just pick the top match.
105 // This can happen, say, when a parent frame in EUC-JP refers to
106 // a child frame in Shift_JIS and both frames do NOT specify the encoding
107 // making us resort to auto-detection (when it IS turned on).
108 if (!encoding && matchesCount > 0)
109 encoding = ucsdet_getName(matches[0], &status);
110 if (U_SUCCESS(status)) {
111 *detectedEncoding = TextEncoding(encoding);
112 ucsdet_close(detector);
113 return true;
114 }
115 ucsdet_close(detector);
116 return false;
117 }
118
119 }
120