encoding-codepage 0.3 → 0.4

data/README.md

@@ -78,7 +78,8 @@ After installing this gem, you'll be able to access the following Code Pages fro
     CP936   => GB2312         # ANSI/OEM Simplified Chinese (PRC, Singapore); Chinese Simplified (GB2312)
     CP949   => KS_C_5601-1987 # ANSI/OEM Korean (Unified Hangul Code)
     CP950   => BIG5           # ANSI/OEM Traditional Chinese (Taiwan; Hong Kong SAR, PRC); Chinese Traditional (Big5)
-    CP1200  => UTF-16         # Unicode UTF-16, little endian byte order (BMP of ISO 10646); available only to managed applications
+    CP1200  => UTF-16LE       # Unicode UTF-16, little endian byte order (BMP of ISO 10646); available only to managed applications
+    CP1201  => UTF-16BE       # Unicode UTF-16, big endian byte order; available only to managed applications
     CP1250  => WINDOWS-1250   # ANSI Central European; Central European (Windows)
     CP1251  => WINDOWS-1251   # ANSI Cyrillic; Cyrillic (Windows)
     CP1252  => WINDOWS-1252   # ANSI Latin 1; Western European (Windows)
@@ -88,7 +89,7 @@ After installing this gem, you'll be able to access the following Code Pages fro
     CP1256  => WINDOWS-1256   # ANSI Arabic; Arabic (Windows)
     CP1257  => WINDOWS-1257   # ANSI Baltic; Baltic (Windows)
     CP1258  => WINDOWS-1258   # ANSI/OEM Vietnamese; Vietnamese (Windows)
-    CP12000 => UTF-32         # Unicode UTF-32, little endian byte order; available only to managed applications
+    CP12000 => UTF-32LE       # Unicode UTF-32, little endian byte order; available only to managed applications
     CP12001 => UTF-32BE       # Unicode UTF-32, big endian byte order; available only to managed applications
     CP20127 => US-ASCII       # US-ASCII (7-bit)
     CP20866 => KOI8-R         # Russian (KOI8-R); Cyrillic (KOI8-R)
@@ -105,14 +106,10 @@ After installing this gem, you'll be able to access the following Code Pages fro
     CP28599 => ISO-8859-9     # ISO 8859-9 Turkish
     CP28603 => ISO-8859-13    # ISO 8859-13 Estonian
     CP28605 => ISO-8859-15    # ISO 8859-15 Latin 9
-    CP50220 => ISO-2022-JP    # ISO 2022 Japanese with no halfwidth Katakana; Japanese (JIS)
-    CP50221 => CSISO2022JP    # ISO 2022 Japanese with halfwidth Katakana; Japanese (JIS-Allow 1 byte Kana)
-    CP50222 => ISO-2022-JP    # ISO 2022 Japanese JIS X 0201-1989; Japanese (JIS-Allow 1 byte Kana - SO/SI)
     CP51932 => EUC-JP         # EUC Japanese
     CP51936 => EUC-CN         # EUC Simplified Chinese; Chinese Simplified (EUC)
     CP51949 => EUC-KR         # EUC Korean
     CP54936 => GB18030        # Windows XP and later: GB18030 Simplified Chinese (4 byte); Chinese Simplified (GB18030)
-    CP65000 => UTF-7          # Unicode (UTF-7)
     CP65001 => UTF-8          # Unicode (UTF-8)
 
 The following code pages are known not to be supported:
@@ -138,7 +135,6 @@ The following code pages are known not to be supported:
     CP1147  => IBM01147                # IBM EBCDIC France (20297 + Euro symbol); IBM EBCDIC (France-Euro)
     CP1148  => IBM01148                # IBM EBCDIC International (500 + Euro symbol); IBM EBCDIC (International-Euro)
     CP1149  => IBM01149                # IBM EBCDIC Icelandic (20871 + Euro symbol); IBM EBCDIC (Icelandic-Euro)
-    CP1201  => UNICODEFFFE             # Unicode UTF-16, big endian byte order; available only to managed applications
     CP1361  => JOHAB                   # Korean (Johab)
     CP10000 => MACINTOSH               # MAC Roman; Western European (Mac)
     CP10001 => X-MAC-JAPANESE          # Japanese (Mac)
@@ -191,6 +187,9 @@ The following code pages are known not to be supported:
     CP21027 =>                         # (deprecated)
     CP29001 => X-EUROPA                # Europa 3
     CP38598 => ISO-8859-8-I            # ISO 8859-8 Hebrew; Hebrew (ISO-Logical)
+    CP50220 => ISO-2022-JP             # ISO 2022 Japanese with no halfwidth Katakana; Japanese (JIS)
+    CP50221 => CSISO2022JP             # ISO 2022 Japanese with halfwidth Katakana; Japanese (JIS-Allow 1 byte Kana)
+    CP50222 => ISO-2022-JP             # ISO 2022 Japanese JIS X 0201-1989; Japanese (JIS-Allow 1 byte Kana - SO/SI)
     CP50225 => ISO-2022-KR             # ISO 2022 Korean
     CP50227 => X-CP50227               # ISO 2022 Simplified Chinese; Chinese Simplified (ISO 2022)
     CP50229 =>                         # ISO 2022 Traditional Chinese
@@ -213,6 +212,7 @@ The following code pages are known not to be supported:
     CP57009 => X-ISCII-MA              # ISCII Malayalam
     CP57010 => X-ISCII-GU              # ISCII Gujarati
     CP57011 => X-ISCII-PA              # ISCII Punjabi
+    CP65000 => UTF-7                   # Unicode (UTF-7)
 
 Original list from: http://msdn.microsoft.com/en-us/library/dd317756(VS.85).aspx
 

data/lib/codepages.tsv

@@ -69,7 +69,7 @@
 10079	x-mac-icelandic	Icelandic (Mac)
 10081	x-mac-turkish	Turkish (Mac)
 10082	x-mac-croatian	Croatian (Mac)
-12000	utf-32	Unicode UTF-32, little endian byte order; available only to managed applications
+12000	utf-32LE	Unicode UTF-32, little endian byte order; available only to managed applications
 12001	utf-32BE	Unicode UTF-32, big endian byte order; available only to managed applications
 20000	x-Chinese_CNS	CNS Taiwan; Chinese Traditional (CNS)
 20001	x-cp20001	TCA Taiwan

data/lib/encoding-codepage.rb

@@ -54,7 +54,7 @@ class Encoding
         number, original, comment = line.split("\t", 3)
         number = Integer(number, 10)
 
-        if encoding = exist?(original.upcase)
+        if encoding = exist?(original.upcase) && !encoding.dummy?
           encoding.replicate "CP#{number}" unless codepage?(number)
 
           CodePage.reverse_lookup[encoding] = codepage(number)

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: encoding-codepage
 version: !ruby/object:Gem::Version
-  version: '0.3'
+  version: '0.4'
   prerelease: 
 platform: ruby
 authors: