summaryrefslogtreecommitdiff
path: root/extensions/universalchardet/src/base/nsUniversalDetector.cpp
blob: d272827b815cbdb9e4e5b98324cc09f7f325d5a6 (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
/* -*- Mode: C++; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
/* This Source Code Form is subject to the terms of the Mozilla Public
 * License, v. 2.0. If a copy of the MPL was not distributed with this
 * file, You can obtain one at http://mozilla.org/MPL/2.0/. */

#include "nscore.h"

#include "nsUniversalDetector.h"

#include "nsMBCSGroupProber.h"
#include "nsEscCharsetProber.h"
#include "nsLatin1Prober.h"

nsUniversalDetector::nsUniversalDetector()
{
  mDone = false;
  mBestGuess = -1;   //illegal value as signal
  mInTag = false;
  mEscCharSetProber = nullptr;

  mStart = true;
  mDetectedCharset = nullptr;
  mGotData = false;
  mInputState = ePureAscii;
  mLastChar = '\0';

  uint32_t i;
  for (i = 0; i < NUM_OF_CHARSET_PROBERS; i++)
    mCharSetProbers[i] = nullptr;
}

nsUniversalDetector::~nsUniversalDetector() 
{
  for (int32_t i = 0; i < NUM_OF_CHARSET_PROBERS; i++)
    delete mCharSetProbers[i];

  delete mEscCharSetProber;
}

void 
nsUniversalDetector::Reset()
{
  mDone = false;
  mBestGuess = -1;   //illegal value as signal
  mInTag = false;

  mStart = true;
  mDetectedCharset = nullptr;
  mGotData = false;
  mInputState = ePureAscii;
  mLastChar = '\0';

  if (mEscCharSetProber)
    mEscCharSetProber->Reset();

  uint32_t i;
  for (i = 0; i < NUM_OF_CHARSET_PROBERS; i++)
    if (mCharSetProbers[i])
      mCharSetProbers[i]->Reset();
}

//---------------------------------------------------------------------
#define SHORTCUT_THRESHOLD      (float)0.95
#define MINIMUM_THRESHOLD      (float)0.20

nsresult nsUniversalDetector::HandleData(const char* aBuf, uint32_t aLen)
{
  if(mDone) 
    return NS_OK;

  if (aLen > 0)
    mGotData = true;

  //If the data starts with BOM, we know it is UTF
  if (mStart)
  {
    mStart = false;
    if (aLen >= 2) {
      switch (aBuf[0]) {
      case '\xEF':
        if ((aLen > 2) && ('\xBB' == aBuf[1]) && ('\xBF' == aBuf[2])) {
          // EF BB BF  UTF-8 encoded BOM
          mDetectedCharset = "UTF-8";
        }
        break;
      case '\xFE':
        if ('\xFF' == aBuf[1]) {
          // FE FF  UTF-16, big endian BOM
          mDetectedCharset = "UTF-16BE";
        }
        break;
      case '\xFF':
        if ('\xFE' == aBuf[1]) {
          // FF FE  UTF-16, little endian BOM
          mDetectedCharset = "UTF-16LE";
        }
        break;
      }  // switch
    }

    if (mDetectedCharset)
    {
      mDone = true;
      return NS_OK;
    }
  }
  
  uint32_t i;
  for (i = 0; i < aLen; i++)
  {
    //other than 0xa0, if every othe character is ascii, the page is ascii
    if (aBuf[i] & '\x80' && aBuf[i] != '\xA0')  //Since many Ascii only page contains NBSP 
    {
      //we got a non-ascii byte (high-byte)
      if (mInputState != eHighbyte)
      {
        //adjust state
        mInputState = eHighbyte;

        //kill mEscCharSetProber if it is active
        if (mEscCharSetProber) {
          delete mEscCharSetProber;
          mEscCharSetProber = nullptr;
        }

        //start multibyte and singlebyte charset prober
        if (nullptr == mCharSetProbers[0])
        {
          mCharSetProbers[0] = new nsMBCSGroupProber();
          if (nullptr == mCharSetProbers[0])
            return NS_ERROR_OUT_OF_MEMORY;
        }
        if (nullptr == mCharSetProbers[2])
        {
          mCharSetProbers[2] = new nsLatin1Prober; 
          if (nullptr == mCharSetProbers[2])
            return NS_ERROR_OUT_OF_MEMORY;
        }
      }
    }
    else
    {
      //ok, just pure ascii so far
      if ((ePureAscii == mInputState) && (aBuf[i] == '\033'))
      {
        //found escape character
        mInputState = eEscAscii;
      }
      mLastChar = aBuf[i];
    }
  }

  nsProbingState st;
  switch (mInputState)
  {
  case eEscAscii:
    if (nullptr == mEscCharSetProber) {
      mEscCharSetProber = new nsEscCharSetProber();
      if (nullptr == mEscCharSetProber)
        return NS_ERROR_OUT_OF_MEMORY;
    }
    st = mEscCharSetProber->HandleData(aBuf, aLen);
    if (st == eFoundIt)
    {
      mDone = true;
      mDetectedCharset = mEscCharSetProber->GetCharSetName();
    }
    break;
  case eHighbyte:
    for (i = 0; i < NUM_OF_CHARSET_PROBERS; i++)
    {
      if (mCharSetProbers[i])
      {
        st = mCharSetProbers[i]->HandleData(aBuf, aLen);
        if (st == eFoundIt) 
        {
          mDone = true;
          mDetectedCharset = mCharSetProbers[i]->GetCharSetName();
          return NS_OK;
        }
      } 
    }
    break;

  default:  //pure ascii
    ;//do nothing here
  }
  return NS_OK;
}


//---------------------------------------------------------------------
void nsUniversalDetector::DataEnd()
{
  if (!mGotData)
  {
    // we haven't got any data yet, return immediately 
    // caller program sometimes call DataEnd before anything has been sent to detector
    return;
  }

  if (mDetectedCharset)
  {
    mDone = true;
    Report(mDetectedCharset);
    return;
  }
  
  switch (mInputState)
  {
  case eHighbyte:
    {
      float proberConfidence;
      float maxProberConfidence = (float)0.0;
      int32_t maxProber = 0;

      for (int32_t i = 0; i < NUM_OF_CHARSET_PROBERS; i++)
      {
        if (mCharSetProbers[i])
        {
          proberConfidence = mCharSetProbers[i]->GetConfidence();
          if (proberConfidence > maxProberConfidence)
          {
            maxProberConfidence = proberConfidence;
            maxProber = i;
          }
        }
      }
      //do not report anything because we are not confident of it, that's in fact a negative answer
      if (maxProberConfidence > MINIMUM_THRESHOLD)
        Report(mCharSetProbers[maxProber]->GetCharSetName());
    }
    break;
  case eEscAscii:
    break;
  default:
    ;
  }
  return;
}