OLD | NEW |
| (Empty) |
1 ######################## BEGIN LICENSE BLOCK ######################## | |
2 # The Original Code is Mozilla Universal charset detector code. | |
3 # | |
4 # The Initial Developer of the Original Code is | |
5 # Netscape Communications Corporation. | |
6 # Portions created by the Initial Developer are Copyright (C) 2001 | |
7 # the Initial Developer. All Rights Reserved. | |
8 # | |
9 # Contributor(s): | |
10 # Mark Pilgrim - port to Python | |
11 # Shy Shalom - original C code | |
12 # Proofpoint, Inc. | |
13 # | |
14 # This library is free software; you can redistribute it and/or | |
15 # modify it under the terms of the GNU Lesser General Public | |
16 # License as published by the Free Software Foundation; either | |
17 # version 2.1 of the License, or (at your option) any later version. | |
18 # | |
19 # This library is distributed in the hope that it will be useful, | |
20 # but WITHOUT ANY WARRANTY; without even the implied warranty of | |
21 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU | |
22 # Lesser General Public License for more details. | |
23 # | |
24 # You should have received a copy of the GNU Lesser General Public | |
25 # License along with this library; if not, write to the Free Software | |
26 # Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA | |
27 # 02110-1301 USA | |
28 ######################### END LICENSE BLOCK ######################### | |
29 | |
30 import sys | |
31 from . import constants | |
32 from .charsetprober import CharSetProber | |
33 | |
34 | |
35 class MultiByteCharSetProber(CharSetProber): | |
36 def __init__(self): | |
37 CharSetProber.__init__(self) | |
38 self._mDistributionAnalyzer = None | |
39 self._mCodingSM = None | |
40 self._mLastChar = [0, 0] | |
41 | |
42 def reset(self): | |
43 CharSetProber.reset(self) | |
44 if self._mCodingSM: | |
45 self._mCodingSM.reset() | |
46 if self._mDistributionAnalyzer: | |
47 self._mDistributionAnalyzer.reset() | |
48 self._mLastChar = [0, 0] | |
49 | |
50 def get_charset_name(self): | |
51 pass | |
52 | |
53 def feed(self, aBuf): | |
54 aLen = len(aBuf) | |
55 for i in range(0, aLen): | |
56 codingState = self._mCodingSM.next_state(aBuf[i]) | |
57 if codingState == constants.eError: | |
58 if constants._debug: | |
59 sys.stderr.write(self.get_charset_name() | |
60 + ' prober hit error at byte ' + str(i) | |
61 + '\n') | |
62 self._mState = constants.eNotMe | |
63 break | |
64 elif codingState == constants.eItsMe: | |
65 self._mState = constants.eFoundIt | |
66 break | |
67 elif codingState == constants.eStart: | |
68 charLen = self._mCodingSM.get_current_charlen() | |
69 if i == 0: | |
70 self._mLastChar[1] = aBuf[0] | |
71 self._mDistributionAnalyzer.feed(self._mLastChar, charLen) | |
72 else: | |
73 self._mDistributionAnalyzer.feed(aBuf[i - 1:i + 1], | |
74 charLen) | |
75 | |
76 self._mLastChar[0] = aBuf[aLen - 1] | |
77 | |
78 if self.get_state() == constants.eDetecting: | |
79 if (self._mDistributionAnalyzer.got_enough_data() and | |
80 (self.get_confidence() > constants.SHORTCUT_THRESHOLD)): | |
81 self._mState = constants.eFoundIt | |
82 | |
83 return self.get_state() | |
84 | |
85 def get_confidence(self): | |
86 return self._mDistributionAnalyzer.get_confidence() | |
OLD | NEW |