rchardet 1.7.0 → 1.8.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 3cdc02a9943abeba846fd618a5ee9f04fe8ef506
-  data.tar.gz: edeeefd5700589aa5bb8cbc371a6cd580e2557fc
+SHA256:
+  metadata.gz: b03009ca37e41a17ddc0f4f62cd5889b11b59b1f2100998f191a0be7ede5d000
+  data.tar.gz: ea8473dc5f1b7c4d24f858de90c591f1dec66055cc05b30b475e8256fa0c7a41
 SHA512:
-  metadata.gz: facabfeae468c114f98ae3e6f38aedbf9c3a1f4393995b00d539903b67444a1124ed2a1307c56192263d6b28a9167766fd2fdd1c5eda2183379d37a679cb5a10
-  data.tar.gz: 374d62ffda808bfd64639de216087162d2f117fd78cbc87fc9bcd05162e00c0e311638a20748c8a7033b7ad5320ff2ab8d2011843e4400992c23548911fabc49
+  metadata.gz: 7829042566b227306274d03219456cda42b8cd3767a085bec2dd72e0d6d0d4fa78a165fd911768599c2c255f5879a7c25d2cde74bee2091a70e5fbf2ca77e586
+  data.tar.gz: 249b2027502f888713c57bcae850178adcdf60db9463a5357b396b3a2d9fd76a65d9a12247f8cddf8bf4e877d1c1a427c05b0c040c3f329b604106775af85f27

data/lib/rchardet.rb

@@ -33,8 +33,8 @@ require 'rchardet/euckrfreq'
 require 'rchardet/euckrprober'
 require 'rchardet/euctwfreq'
 require 'rchardet/euctwprober'
-require 'rchardet/gb2312freq'
-require 'rchardet/gb2312prober'
+require 'rchardet/gb18030freq'
+require 'rchardet/gb18030prober'
 require 'rchardet/hebrewprober'
 require 'rchardet/jisfreq'
 require 'rchardet/jpcntx'

data/lib/rchardet/chardistribution.rb

@@ -149,16 +149,16 @@ module CharDet
     end
   end
 
-  class GB2312DistributionAnalysis < CharDistributionAnalysis
+  class GB18030DistributionAnalysis < CharDistributionAnalysis
     def initialize
       super()
-      @charToFreqOrder = GB2312CharToFreqOrder
-      @tableSize = GB2312_TABLE_SIZE
-      @typicalDistributionRatio = GB2312_TYPICAL_DISTRIBUTION_RATIO
+      @charToFreqOrder = GB18030CharToFreqOrder
+      @tableSize = GB18030_TABLE_SIZE
+      @typicalDistributionRatio = GB18030_TYPICAL_DISTRIBUTION_RATIO
     end
 
     def get_order(aStr)
-      # for GB2312 encoding, we are interested 
+      # for GB18030 encoding, we are interested 
       #  first  byte range: 0xb0 -- 0xfe
       #  second byte range: 0xa1 -- 0xfe
       # no validation needed here. State machine has done that

data/lib/rchardet/{gb2312freq.rb → gb18030freq.rb}

@@ -26,7 +26,7 @@
 # 02110-1301  USA
 ######################### END LICENSE BLOCK #########################
 
-# GB2312 most frequently used character table
+# GB18030 most frequently used character table
 #
 # Char to FreqOrder table , from hz6763
 
@@ -41,11 +41,11 @@
 # Typical Distribution Ratio about 25% of Ideal one, still much higher that RDR
 
 module CharDet
-GB2312_TYPICAL_DISTRIBUTION_RATIO = 0.9
+GB18030_TYPICAL_DISTRIBUTION_RATIO = 0.9
 
-GB2312_TABLE_SIZE = 3760
+GB18030_TABLE_SIZE = 3760
 
-GB2312CharToFreqOrder = [
+GB18030CharToFreqOrder = [
 1671, 749,1443,2364,3924,3807,2330,3921,1704,3463,2691,1511,1515, 572,3191,2205,
 2361, 224,2558, 479,1711, 963,3162, 440,4060,1905,2966,2947,3580,2647,3961,3842,
 2204, 869,4207, 970,2678,5626,2944,2956,1479,4048, 514,3595, 588,1346,2820,3409,

data/lib/rchardet/{gb2312prober.rb → gb18030prober.rb}

@@ -27,16 +27,16 @@
 ######################### END LICENSE BLOCK #########################
 
 module CharDet
-  class GB2312Prober < MultiByteCharSetProber
+  class GB18030Prober < MultiByteCharSetProber
     def initialize
       super
-      @codingSM = CodingStateMachine.new(GB2312SMModel)
-      @distributionAnalyzer = GB2312DistributionAnalysis.new()
+      @codingSM = CodingStateMachine.new(GB18030SMModel)
+      @distributionAnalyzer = GB18030DistributionAnalysis.new()
       reset()
     end
 
     def get_charset_name
-      return "GB2312"
+      return "GB18030"
     end
   end
 end

data/lib/rchardet/mbcsgroupprober.rb

@@ -36,7 +36,7 @@ module CharDet
                     UTF8Prober.new,
                     SJISProber.new,
                     EUCJPProber.new,
-                    GB2312Prober.new,
+                    GB18030Prober.new,
                     EUCKRProber.new,
                     Big5Prober.new,
                     EUCTWProber.new

data/lib/rchardet/mbcssm.rb

@@ -239,9 +239,9 @@ module CharDet
     'name' =>  'x-euc-tw'
   }.freeze
 
-  # GB2312
+  # GB18030
 
-  GB2312_cls = [
+  GB18030_cls = [
     1,1,1,1,1,1,1,1,  # 00 - 07 
     1,1,1,1,1,1,0,0,  # 08 - 0f 
     1,1,1,1,1,1,1,1,  # 10 - 17 
@@ -276,7 +276,7 @@ module CharDet
     6,6,6,6,6,6,6,0  # f8 - ff 
   ].freeze
 
-  GB2312_st = [
+  GB18030_st = [
     EError,EStart,EStart,EStart,EStart,EStart,     3,EError,#00-07 
     EError,EError,EError,EError,EError,EError,EItsMe,EItsMe,#08-0f 
     EItsMe,EItsMe,EItsMe,EItsMe,EItsMe,EError,EError,EStart,#10-17 
@@ -290,13 +290,13 @@ module CharDet
   # it is used for frequency analysis only, and we are validing 
   # each code range there as well. So it is safe to set it to be 
   # 2 here. 
-  GB2312CharLenTable = [0, 1, 1, 1, 1, 1, 2].freeze
+  GB18030CharLenTable = [0, 1, 1, 1, 1, 1, 2].freeze
 
-  GB2312SMModel = {'classTable' =>  GB2312_cls,
+  GB18030SMModel = {'classTable' =>  GB18030_cls,
     'classFactor' =>  7,
-    'stateTable' =>  GB2312_st,
-    'charLenTable' =>  GB2312CharLenTable,
-    'name' =>  'GB2312'
+    'stateTable' =>  GB18030_st,
+    'charLenTable' =>  GB18030CharLenTable,
+    'name' =>  'GB18030'
   }.freeze
 
   # Shift_JIS

data/lib/rchardet/version.rb

@@ -1,3 +1,3 @@
 module CharDet
-  VERSION = "1.7.0"
+  VERSION = "1.8.0"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: rchardet
 version: !ruby/object:Gem::Version
-  version: 1.7.0
+  version: 1.8.0
 platform: ruby
 authors:
 - Michael Grosser
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-01-07 00:00:00.000000000 Z
+date: 2018-06-01 00:00:00.000000000 Z
 dependencies: []
 description: 
 email:
@@ -34,8 +34,8 @@ files:
 - lib/rchardet/euckrprober.rb
 - lib/rchardet/euctwfreq.rb
 - lib/rchardet/euctwprober.rb
-- lib/rchardet/gb2312freq.rb
-- lib/rchardet/gb2312prober.rb
+- lib/rchardet/gb18030freq.rb
+- lib/rchardet/gb18030prober.rb
 - lib/rchardet/hebrewprober.rb
 - lib/rchardet/jisfreq.rb
 - lib/rchardet/jpcntx.rb
@@ -75,7 +75,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.6.14
+rubygems_version: 2.7.6
 signing_key: 
 specification_version: 4
 summary: Character encoding auto-detection in Ruby. As smart as your browser. Open