rchardet 1.3 → 1.3.1

data/lib/rchardet/chardistribution.rb

@@ -57,8 +57,8 @@ module CharDet
       if order >= 0
 	@_mTotalChars += 1
 	# order is valid
-	if order < @_mTableSize:
-	  if 512 > @_mCharToFreqOrder[order]:
+	if order < @_mTableSize
+	  if 512 > @_mCharToFreqOrder[order]
 	    @_mFreqChars += 1
 	  end
 	end
@@ -72,7 +72,7 @@ module CharDet
 	return SURE_NO
       end
 
-      if @_mTotalChars != @_mFreqChars:
+      if @_mTotalChars != @_mFreqChars
 	r = @_mFreqChars / ((@_mTotalChars - @_mFreqChars) * @_mTypicalDistributionRatio)
 	if r < SURE_YES
 	  return r
@@ -227,10 +227,10 @@ module CharDet
       #   first  byte range: 0xa0 -- 0xfe
       #   second byte range: 0xa1 -- 0xfe
       # no validation needed here. State machine has done that
-      if aStr[0..0] >= "\xA0":
-	return 94 * (aStr[0] - 0xA1) + aStr[1] - 0xa1
+      if aStr[0..0] >= "\xA0"
+        return 94 * (aStr[0] - 0xA1) + aStr[1] - 0xa1
       else
-	return -1
+        return -1
       end
     end
   end

data/lib/rchardet/charsetgroupprober.rb

@@ -40,7 +40,7 @@ module CharDet
       super
       @_mActiveNum = 0
 
-      for prober in @_mProbers:
+      for prober in @_mProbers
 	if prober
 	  prober.reset()
 	  prober.active = true

data/lib/rchardet/codingstatemachine.rb

@@ -28,6 +28,8 @@
 
 module CharDet
   class CodingStateMachine
+    attr_accessor :active
+
     def initialize(sm)
       @_mModel = sm
       @_mCurrentBytePos = 0

data/lib/rchardet/escprober.rb

@@ -41,7 +41,7 @@ module CharDet
 
     def reset
       super()
-      for codingSM in @_mCodingSM:
+      for codingSM in @_mCodingSM
 	next if not codingSM
 	codingSM.active = true
 	codingSM.reset()

data/lib/rchardet/eucjpprober.rb

@@ -56,7 +56,7 @@ module CharDet
 	elsif codingState == EItsMe
 	  @_mState = EFoundIt
 	  break
-	elsif codingState == EStart:
+	elsif codingState == EStart
 	  charLen = @_mCodingSM.get_current_charlen()
 	  if i == 0
 	    @_mLastChar[1] = aBuf[0..0]

data/lib/rchardet/jpcntx.rb

@@ -34,7 +34,7 @@ module CharDet
   MINIMUM_DATA_THRESHOLD = 4
 
   # This is hiragana 2-char sequence table, the number in each cell represents its frequency category
-  jp2CharContext = [
+  JP2_CHAR_CONTEXT = [
     [0,0,0,2,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,0,1,0,0,0,0,0,0,0,0,0,0,1],
     [2,4,0,4,0,3,0,4,0,3,4,4,4,2,4,3,3,4,3,2,3,3,4,2,3,3,3,2,4,1,4,3,3,1,5,4,3,4,3,4,3,5,3,0,3,5,4,2,0,3,1,0,3,3,0,3,3,0,1,1,0,4,3,0,3,3,0,4,0,2,0,3,5,5,5,5,4,0,4,1,0,3,4],
     [0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,2],
@@ -150,13 +150,13 @@ module CharDet
 	  @_mNeedToSkipCharNum = i - aLen
 	  @_mLastCharOrder = -1
 	else
-	  if (order != -1) and (@_mLastCharOrder != -1):
+	  if (order != -1) and (@_mLastCharOrder != -1)
 	    @_mTotalRel += 1
-	    if @_mTotalRel > MAX_REL_THRESHOLD:
+	    if @_mTotalRel > MAX_REL_THRESHOLD
 	      @_mDone = true
 	      break
 	    end
-	    @_mRelSample[jp2CharContext[@_mLastCharOrder][order]] += 1
+	    @_mRelSample[JP2_CHAR_CONTEXT[@_mLastCharOrder][order]] += 1
 	  end
 	  @_mLastCharOrder = order
 	end
@@ -169,7 +169,7 @@ module CharDet
 
     def get_confidence
       # This is just one way to calculate confidence. It works well for me.
-      if @_mTotalRel > MINIMUM_DATA_THRESHOLD:
+      if @_mTotalRel > MINIMUM_DATA_THRESHOLD
 	return (@_mTotalRel - @_mRelSample[0]) / @_mTotalRel
       else
 	return DONT_KNOW
@@ -208,7 +208,7 @@ module CharDet
       return -1, 1 unless aStr
       # find out current char's byte length
       aStr = aStr[0..1].join if aStr.class == Array
-      if (aStr[0..0] == "\x8E") or ((aStr[0..0] >= "\xA1") and (aStr[0..0] <= "\xFE")):
+      if (aStr[0..0] == "\x8E") or ((aStr[0..0] >= "\xA1") and (aStr[0..0] <= "\xFE"))
 	charLen = 2
       elsif aStr[0..0] == "\x8F"
 	charLen = 3

data/lib/rchardet/sjisprober.rb

@@ -71,7 +71,7 @@ module CharDet
 
       @_mLastChar[0] = aBuf[aLen - 1.. aLen-1]
 
-      if get_state() == EDetecting:
+      if get_state() == EDetecting
 	if @_mContextAnalyzer.got_enough_data() and (get_confidence() > SHORTCUT_THRESHOLD)
 	  @_mState = EFoundIt
 	end

data/lib/rchardet/universaldetector.rb

@@ -91,11 +91,11 @@ module CharDet
       end
 
       @_mGotData = true
-      if @result['encoding'] and (@result['confidence'] > 0.0):
+      if @result['encoding'] and (@result['confidence'] > 0.0)
 	@done = true
 	return
       end
-      if @_mInputState == EPureAscii:
+      if @_mInputState == EPureAscii
 	if @_highBitDetector =~ (aBuf)
 	  @_mInputState = EHighbyte
 	elsif (@_mInputState == EPureAscii) and @_escDetector =~ (@_mLastChar + aBuf)
@@ -109,7 +109,7 @@ module CharDet
 	  @_mEscCharSetProber = EscCharSetProber.new()
 	end
 	if @_mEscCharSetProber.feed(aBuf) == EFoundIt
-	  @result = {'encoding' =>  self._mEscCharSetProber.get_charset_name(),
+	  @result = {'encoding' =>  @_mEscCharSetProber.get_charset_name(),
 			       'confidence' =>  @_mEscCharSetProber.get_confidence()
 	  }
 	  @done = true
@@ -138,12 +138,12 @@ module CharDet
       end
       @done = true
 
-      if @_mInputState == EPureAscii:
+      if @_mInputState == EPureAscii
 	@result = {'encoding' => 'ascii', 'confidence' => 1.0}
 	return @result
       end
 
-      if @_mInputState == EHighbyte:
+      if @_mInputState == EHighbyte
 	confidences = {}
         @_mCharSetProbers.each{ |prober| confidences[prober] = prober.get_confidence }
 	maxProber = @_mCharSetProbers.max{ |a,b| confidences[a] <=> confidences[b] }

data/lib/rchardet/utf8prober.rb

@@ -63,7 +63,7 @@ module CharDet
 	end
       end
 
-      if get_state() == EDetecting:
+      if get_state() == EDetecting
 	if get_confidence() > SHORTCUT_THRESHOLD
 	  @_mState = EFoundIt
 	end

data/lib/rchardet.rb

@@ -56,7 +56,7 @@ require 'rchardet/universaldetector'
 require 'rchardet/utf8prober'
 
 module CharDet
-  VERSION = "1.3"
+  VERSION = "1.3.1"
   def CharDet.detect(aBuf)
     u = UniversalDetector.new
     u.reset

metadata

@@ -1,7 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: rchardet
 version: !ruby/object:Gem::Version 
-  version: "1.3"
+  hash: 25
+  prerelease: 
+  segments: 
+  - 1
+  - 3
+  - 1
+  version: 1.3.1
 platform: ruby
 authors: 
 - Jeff Hodges
@@ -9,8 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2009-07-19 00:00:00 -07:00
-default_executable: 
+date: 2012-12-02 00:00:00 Z
 dependencies: []
 
 description: 
@@ -60,7 +65,6 @@ files:
 - lib/rchardet.rb
 - README
 - COPYING
-has_rdoc: true
 homepage: http://github.com/jmhodges/rchardet/tree/master
 licenses: []
 
@@ -70,21 +74,27 @@ rdoc_options: []
 require_paths: 
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
       version: "0"
-  version: 
 required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
       version: "0"
-  version: 
 requirements: []
 
 rubyforge_project: rchardet
-rubygems_version: 1.3.4
+rubygems_version: 1.8.15
 signing_key: 
 specification_version: 3
 summary: Character encoding auto-detection in Ruby. As smart as your browser. Open source.