code cleanup

extra/chardet/chardistribution.py

@@ -42,7 +42,7 @@ class CharDistributionAnalysis:
         self._mTableSize = None # Size of above table
         self._mTypicalDistributionRatio = None # This is a constant value which varies from language to language, used in calculating confidence.  See http://www.mozilla.org/projects/intl/UniversalCharsetDetection.html for further detail.
         self.reset()
-        
+
     def reset(self):
         """reset analyser, clear any state"""
         self._mDone = constants.False # If this flag is set to constants.True, detection is done and conclusion has been made
@@ -87,7 +87,7 @@ class CharDistributionAnalysis:
         # convert this encoding string to a number, here called order.
         # This allows multiple encodings of a language to share one frequency table.
         return -1
-    
+
 class EUCTWDistributionAnalysis(CharDistributionAnalysis):
     def __init__(self):
         CharDistributionAnalysis.__init__(self)

extra/chardet/charsetgroupprober.py

@@ -34,7 +34,7 @@ class CharSetGroupProber(CharSetProber):
         self._mActiveNum = 0
         self._mProbers = []
         self._mBestGuessProber = None
-        
+
     def reset(self):
         CharSetProber.reset(self)
         self._mActiveNum = 0

extra/chardet/charsetprober.py

@@ -31,10 +31,10 @@ import constants, re
 class CharSetProber:
     def __init__(self):
         pass
-        
+
     def reset(self):
         self._mState = constants.eDetecting
-    
+
     def get_charset_name(self):
         return None
 
@@ -50,11 +50,11 @@ class CharSetProber:
     def filter_high_bit_only(self, aBuf):
         aBuf = re.sub(r'([\x00-\x7F])+', ' ', aBuf)
         return aBuf
-    
+
     def filter_without_english_letters(self, aBuf):
         aBuf = re.sub(r'([A-Za-z])+', ' ', aBuf)
         return aBuf
-        
+
     def filter_with_english_letters(self, aBuf):
         # TODO
         return aBuf

extra/chardet/escprober.py

@@ -75,5 +75,5 @@ class EscCharSetProber(CharSetProber):
                     self._mState = constants.eFoundIt
                     self._mDetectedCharset = codingSM.get_coding_state_machine()
                     return self.get_state()
-                
+
         return self.get_state()

extra/chardet/eucjpprober.py

@@ -44,7 +44,7 @@ class EUCJPProber(MultiByteCharSetProber):
     def reset(self):
         MultiByteCharSetProber.reset(self)
         self._mContextAnalyzer.reset()
-        
+
     def get_charset_name(self):
         return "EUC-JP"
 
@@ -69,9 +69,9 @@ class EUCJPProber(MultiByteCharSetProber):
                 else:
                     self._mContextAnalyzer.feed(aBuf[i-1:i+1], charLen)
                     self._mDistributionAnalyzer.feed(aBuf[i-1:i+1], charLen)
-                    
+
         self._mLastChar[0] = aBuf[aLen - 1]
-        
+
         if self.get_state() == constants.eDetecting:
             if self._mContextAnalyzer.got_enough_data() and \
                    (self.get_confidence() > constants.SHORTCUT_THRESHOLD):

extra/chardet/hebrewprober.py

@@ -164,7 +164,7 @@ class HebrewProber(CharSetProber):
         self._mPrev = ' '
         self._mBeforePrev = ' '
         # These probers are owned by the group prober.
-        
+
     def set_model_probers(self, logicalProber, visualProber):
         self._mLogicalProber = logicalProber
         self._mVisualProber = visualProber
@@ -184,7 +184,7 @@ class HebrewProber(CharSetProber):
         # these letters as Non-Final letters outweighs the damage since these words 
         # are quite rare.
         return c in [NORMAL_KAF, NORMAL_MEM, NORMAL_NUN, NORMAL_PE]
-    
+
     def feed(self, aBuf):
         # Final letter analysis for logical-visual decision.
         # Look for evidence that the received buffer is either logical Hebrew or 
@@ -215,7 +215,7 @@ class HebrewProber(CharSetProber):
             return constants.eNotMe
 
         aBuf = self.filter_high_bit_only(aBuf)
-        
+
         for cur in aBuf:
             if cur == ' ':
                 # We stand on a space - a word just ended

extra/chardet/jpcntx.py

@@ -123,7 +123,7 @@ jp2CharContext = ( \
 class JapaneseContextAnalysis:
     def __init__(self):
         self.reset()
-        
+
     def reset(self):
         self._mTotalRel = 0 # total sequence received
         self._mRelSample = [0] * NUM_OF_CATEGORY # category counters, each interger counts sequence in its category
@@ -133,7 +133,7 @@ class JapaneseContextAnalysis:
 
     def feed(self, aBuf, aLen):
         if self._mDone: return
-        
+
         # The buffer we got is byte oriented, and a character may span in more than one
         # buffers. In case the last one or two byte in last buffer is not complete, we 
         # record how many byte needed to complete that character and skip these bytes here.
@@ -158,7 +158,7 @@ class JapaneseContextAnalysis:
 
     def got_enough_data(self):
         return self._mTotalRel > ENOUGH_REL_THRESHOLD
-    
+
     def get_confidence(self):
         # This is just one way to calculate confidence. It works well for me.
         if self._mTotalRel > MINIMUM_DATA_THRESHOLD:
@@ -168,7 +168,7 @@ class JapaneseContextAnalysis:
 
     def get_order(self, aStr):
         return -1, 1
-        
+
 class SJISContextAnalysis(JapaneseContextAnalysis):
     def get_order(self, aStr):
         if not aStr: return -1, 1

extra/chardet/latin1prober.py

@@ -122,7 +122,7 @@ class Latin1Prober(CharSetProber):
     def get_confidence(self):
         if self.get_state() == constants.eNotMe:
             return 0.01
-  
+
         total = reduce(operator.add, self._mFreqCounter)
         if total < 0.01:
             confidence = 0.0

extra/chardet/mbcharsetprober.py

@@ -68,9 +68,9 @@ class MultiByteCharSetProber(CharSetProber):
                     self._mDistributionAnalyzer.feed(self._mLastChar, charLen)
                 else:
                     self._mDistributionAnalyzer.feed(aBuf[i-1:i+1], charLen)
-                    
+
         self._mLastChar[0] = aBuf[aLen - 1]
-        
+
         if self.get_state() == constants.eDetecting:
             if self._mDistributionAnalyzer.got_enough_data() and \
                (self.get_confidence() > constants.SHORTCUT_THRESHOLD):

extra/chardet/sbcharsetprober.py

@@ -37,7 +37,7 @@ SYMBOL_CAT_ORDER = 250
 NUMBER_OF_SEQ_CAT = 4
 POSITIVE_CAT = NUMBER_OF_SEQ_CAT - 1
 #NEGATIVE_CAT = 0
- 
+
 class SingleByteCharSetProber(CharSetProber):
     def __init__(self, model, reversed=constants.False, nameProber=None):
         CharSetProber.__init__(self)

extra/chardet/sjisprober.py

@@ -44,7 +44,7 @@ class SJISProber(MultiByteCharSetProber):
     def reset(self):
         MultiByteCharSetProber.reset(self)
         self._mContextAnalyzer.reset()
-        
+
     def get_charset_name(self):
         return "SHIFT_JIS"
 
@@ -69,9 +69,9 @@ class SJISProber(MultiByteCharSetProber):
                 else:
                     self._mContextAnalyzer.feed(aBuf[i + 1 - charLen : i + 3 - charLen], charLen)
                     self._mDistributionAnalyzer.feed(aBuf[i - 1 : i + 1], charLen)
-                    
+
         self._mLastChar[0] = aBuf[aLen - 1]
-        
+
         if self.get_state() == constants.eDetecting:
             if self._mContextAnalyzer.got_enough_data() and \
                    (self.get_confidence() > constants.SHORTCUT_THRESHOLD):

extra/chardet/universaldetector.py

@@ -63,7 +63,7 @@ class UniversalDetector:
 
         aLen = len(aBuf)
         if not aLen: return
-        
+
         if not self._mGotData:
             # If the data starts with BOM, we know it is UTF
             if aBuf[:3] == '\xEF\xBB\xBF':
@@ -125,7 +125,7 @@ class UniversalDetector:
                 sys.stderr.write('no data received!\n')
             return
         self.done = constants.True
-        
+
         if self._mInputState == ePureAscii:
             self.result = {'encoding': 'ascii', 'confidence': 1.0}
             return self.result