[Python-checkins] cpython: Added forgotten new files for issues #22681 and #22682.

serhiy.storchaka python-checkins at python.org
Tue May 12 23:35:16 CEST 2015


https://hg.python.org/cpython/rev/def3bab79c8f
changeset:   95993:def3bab79c8f
user:        Serhiy Storchaka <storchaka at gmail.com>
date:        Wed May 13 00:34:53 2015 +0300
summary:
  Added forgotten new files for issues #22681 and #22682.

files:
  Lib/encodings/koi8_r.py |  131 +++---
  Lib/encodings/cp1251.py |  534 ++++++++++++++--------------
  2 files changed, 333 insertions(+), 332 deletions(-)


diff --git a/Lib/encodings/koi8_r.py b/Lib/encodings/koi8_t.py
copy from Lib/encodings/koi8_r.py
copy to Lib/encodings/koi8_t.py
--- a/Lib/encodings/koi8_r.py
+++ b/Lib/encodings/koi8_t.py
@@ -1,6 +1,7 @@
-""" Python Character Mapping Codec koi8_r generated from 'MAPPINGS/VENDORS/MISC/KOI8-R.TXT' with gencodec.py.
-
-"""#"
+""" Python Character Mapping Codec koi8_t
+"""
+# http://ru.wikipedia.org/wiki/КОИ-8
+# http://www.opensource.apple.com/source/libiconv/libiconv-4/libiconv/tests/KOI8-T.TXT
 
 import codecs
 
@@ -32,7 +33,7 @@
 
 def getregentry():
     return codecs.CodecInfo(
-        name='koi8-r',
+        name='koi8-t',
         encode=Codec().encode,
         decode=Codec().decode,
         incrementalencoder=IncrementalEncoder,
@@ -173,69 +174,69 @@
     '}'        #  0x7D -> RIGHT CURLY BRACKET
     '~'        #  0x7E -> TILDE
     '\x7f'     #  0x7F -> DELETE
-    '\u2500'   #  0x80 -> BOX DRAWINGS LIGHT HORIZONTAL
-    '\u2502'   #  0x81 -> BOX DRAWINGS LIGHT VERTICAL
-    '\u250c'   #  0x82 -> BOX DRAWINGS LIGHT DOWN AND RIGHT
-    '\u2510'   #  0x83 -> BOX DRAWINGS LIGHT DOWN AND LEFT
-    '\u2514'   #  0x84 -> BOX DRAWINGS LIGHT UP AND RIGHT
-    '\u2518'   #  0x85 -> BOX DRAWINGS LIGHT UP AND LEFT
-    '\u251c'   #  0x86 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
-    '\u2524'   #  0x87 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
-    '\u252c'   #  0x88 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
-    '\u2534'   #  0x89 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
-    '\u253c'   #  0x8A -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
-    '\u2580'   #  0x8B -> UPPER HALF BLOCK
-    '\u2584'   #  0x8C -> LOWER HALF BLOCK
-    '\u2588'   #  0x8D -> FULL BLOCK
-    '\u258c'   #  0x8E -> LEFT HALF BLOCK
-    '\u2590'   #  0x8F -> RIGHT HALF BLOCK
-    '\u2591'   #  0x90 -> LIGHT SHADE
-    '\u2592'   #  0x91 -> MEDIUM SHADE
-    '\u2593'   #  0x92 -> DARK SHADE
-    '\u2320'   #  0x93 -> TOP HALF INTEGRAL
-    '\u25a0'   #  0x94 -> BLACK SQUARE
-    '\u2219'   #  0x95 -> BULLET OPERATOR
-    '\u221a'   #  0x96 -> SQUARE ROOT
-    '\u2248'   #  0x97 -> ALMOST EQUAL TO
-    '\u2264'   #  0x98 -> LESS-THAN OR EQUAL TO
-    '\u2265'   #  0x99 -> GREATER-THAN OR EQUAL TO
-    '\xa0'     #  0x9A -> NO-BREAK SPACE
-    '\u2321'   #  0x9B -> BOTTOM HALF INTEGRAL
-    '\xb0'     #  0x9C -> DEGREE SIGN
-    '\xb2'     #  0x9D -> SUPERSCRIPT TWO
-    '\xb7'     #  0x9E -> MIDDLE DOT
-    '\xf7'     #  0x9F -> DIVISION SIGN
-    '\u2550'   #  0xA0 -> BOX DRAWINGS DOUBLE HORIZONTAL
-    '\u2551'   #  0xA1 -> BOX DRAWINGS DOUBLE VERTICAL
-    '\u2552'   #  0xA2 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
+    '\u049b'   #  0x80 -> CYRILLIC SMALL LETTER KA WITH DESCENDER
+    '\u0493'   #  0x81 -> CYRILLIC SMALL LETTER GHE WITH STROKE
+    '\u201a'   #  0x82 -> SINGLE LOW-9 QUOTATION MARK
+    '\u0492'   #  0x83 -> CYRILLIC CAPITAL LETTER GHE WITH STROKE
+    '\u201e'   #  0x84 -> DOUBLE LOW-9 QUOTATION MARK
+    '\u2026'   #  0x85 -> HORIZONTAL ELLIPSIS
+    '\u2020'   #  0x86 -> DAGGER
+    '\u2021'   #  0x87 -> DOUBLE DAGGER
+    '\ufffe'   #  0x88 -> UNDEFINED
+    '\u2030'   #  0x89 -> PER MILLE SIGN
+    '\u04b3'   #  0x8A -> CYRILLIC SMALL LETTER HA WITH DESCENDER
+    '\u2039'   #  0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK
+    '\u04b2'   #  0x8C -> CYRILLIC CAPITAL LETTER HA WITH DESCENDER
+    '\u04b7'   #  0x8D -> CYRILLIC SMALL LETTER CHE WITH DESCENDER
+    '\u04b6'   #  0x8E -> CYRILLIC CAPITAL LETTER CHE WITH DESCENDER
+    '\ufffe'   #  0x8F -> UNDEFINED
+    '\u049a'   #  0x90 -> CYRILLIC CAPITAL LETTER KA WITH DESCENDER
+    '\u2018'   #  0x91 -> LEFT SINGLE QUOTATION MARK
+    '\u2019'   #  0x92 -> RIGHT SINGLE QUOTATION MARK
+    '\u201c'   #  0x93 -> LEFT DOUBLE QUOTATION MARK
+    '\u201d'   #  0x94 -> RIGHT DOUBLE QUOTATION MARK
+    '\u2022'   #  0x95 -> BULLET
+    '\u2013'   #  0x96 -> EN DASH
+    '\u2014'   #  0x97 -> EM DASH
+    '\ufffe'   #  0x98 -> UNDEFINED
+    '\u2122'   #  0x99 -> TRADE MARK SIGN
+    '\ufffe'   #  0x9A -> UNDEFINED
+    '\u203a'   #  0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
+    '\ufffe'   #  0x9C -> UNDEFINED
+    '\ufffe'   #  0x9D -> UNDEFINED
+    '\ufffe'   #  0x9E -> UNDEFINED
+    '\ufffe'   #  0x9F -> UNDEFINED
+    '\ufffe'   #  0xA0 -> UNDEFINED
+    '\u04ef'   #  0xA1 -> CYRILLIC SMALL LETTER U WITH MACRON
+    '\u04ee'   #  0xA2 -> CYRILLIC CAPITAL LETTER U WITH MACRON
     '\u0451'   #  0xA3 -> CYRILLIC SMALL LETTER IO
-    '\u2553'   #  0xA4 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
-    '\u2554'   #  0xA5 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
-    '\u2555'   #  0xA6 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
-    '\u2556'   #  0xA7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
-    '\u2557'   #  0xA8 -> BOX DRAWINGS DOUBLE DOWN AND LEFT
-    '\u2558'   #  0xA9 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
-    '\u2559'   #  0xAA -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
-    '\u255a'   #  0xAB -> BOX DRAWINGS DOUBLE UP AND RIGHT
-    '\u255b'   #  0xAC -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
-    '\u255c'   #  0xAD -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
-    '\u255d'   #  0xAE -> BOX DRAWINGS DOUBLE UP AND LEFT
-    '\u255e'   #  0xAF -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
-    '\u255f'   #  0xB0 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
-    '\u2560'   #  0xB1 -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
-    '\u2561'   #  0xB2 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
+    '\xa4'     #  0xA4 -> CURRENCY SIGN
+    '\u04e3'   #  0xA5 -> CYRILLIC SMALL LETTER I WITH MACRON
+    '\xa6'     #  0xA6 -> BROKEN BAR
+    '\xa7'     #  0xA7 -> SECTION SIGN
+    '\ufffe'   #  0xA8 -> UNDEFINED
+    '\ufffe'   #  0xA9 -> UNDEFINED
+    '\ufffe'   #  0xAA -> UNDEFINED
+    '\xab'     #  0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+    '\xac'     #  0xAC -> NOT SIGN
+    '\xad'     #  0xAD -> SOFT HYPHEN
+    '\xae'     #  0xAE -> REGISTERED SIGN
+    '\ufffe'   #  0xAF -> UNDEFINED
+    '\xb0'     #  0xB0 -> DEGREE SIGN
+    '\xb1'     #  0xB1 -> PLUS-MINUS SIGN
+    '\xb2'     #  0xB2 -> SUPERSCRIPT TWO
     '\u0401'   #  0xB3 -> CYRILLIC CAPITAL LETTER IO
-    '\u2562'   #  0xB4 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
-    '\u2563'   #  0xB5 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
-    '\u2564'   #  0xB6 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
-    '\u2565'   #  0xB7 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
-    '\u2566'   #  0xB8 -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
-    '\u2567'   #  0xB9 -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
-    '\u2568'   #  0xBA -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
-    '\u2569'   #  0xBB -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
-    '\u256a'   #  0xBC -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
-    '\u256b'   #  0xBD -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
-    '\u256c'   #  0xBE -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+    '\ufffe'   #  0xB4 -> UNDEFINED
+    '\u04e2'   #  0xB5 -> CYRILLIC CAPITAL LETTER I WITH MACRON
+    '\xb6'     #  0xB6 -> PILCROW SIGN
+    '\xb7'     #  0xB7 -> MIDDLE DOT
+    '\ufffe'   #  0xB8 -> UNDEFINED
+    '\u2116'   #  0xB9 -> NUMERO SIGN
+    '\ufffe'   #  0xBA -> UNDEFINED
+    '\xbb'     #  0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+    '\ufffe'   #  0xBC -> UNDEFINED
+    '\ufffe'   #  0xBD -> UNDEFINED
+    '\ufffe'   #  0xBE -> UNDEFINED
     '\xa9'     #  0xBF -> COPYRIGHT SIGN
     '\u044e'   #  0xC0 -> CYRILLIC SMALL LETTER YU
     '\u0430'   #  0xC1 -> CYRILLIC SMALL LETTER A
diff --git a/Lib/encodings/cp1251.py b/Lib/encodings/kz1048.py
copy from Lib/encodings/cp1251.py
copy to Lib/encodings/kz1048.py
--- a/Lib/encodings/cp1251.py
+++ b/Lib/encodings/kz1048.py
@@ -1,4 +1,4 @@
-""" Python Character Mapping Codec cp1251 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1251.TXT' with gencodec.py.
+""" Python Character Mapping Codec kz1048 generated from 'MAPPINGS/VENDORS/MISC/KZ1048.TXT' with gencodec.py.
 
 """#"
 
@@ -8,31 +8,31 @@
 
 class Codec(codecs.Codec):
 
-    def encode(self,input,errors='strict'):
-        return codecs.charmap_encode(input,errors,encoding_table)
+    def encode(self, input, errors='strict'):
+        return codecs.charmap_encode(input, errors, encoding_table)
 
-    def decode(self,input,errors='strict'):
-        return codecs.charmap_decode(input,errors,decoding_table)
+    def decode(self, input, errors='strict'):
+        return codecs.charmap_decode(input, errors, decoding_table)
 
 class IncrementalEncoder(codecs.IncrementalEncoder):
     def encode(self, input, final=False):
-        return codecs.charmap_encode(input,self.errors,encoding_table)[0]
+        return codecs.charmap_encode(input, self.errors, encoding_table)[0]
 
 class IncrementalDecoder(codecs.IncrementalDecoder):
     def decode(self, input, final=False):
-        return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+        return codecs.charmap_decode(input, self.errors, decoding_table)[0]
 
-class StreamWriter(Codec,codecs.StreamWriter):
+class StreamWriter(Codec, codecs.StreamWriter):
     pass
 
-class StreamReader(Codec,codecs.StreamReader):
+class StreamReader(Codec, codecs.StreamReader):
     pass
 
 ### encodings module API
 
 def getregentry():
     return codecs.CodecInfo(
-        name='cp1251',
+        name='kz1048',
         encode=Codec().encode,
         decode=Codec().decode,
         incrementalencoder=IncrementalEncoder,
@@ -45,263 +45,263 @@
 ### Decoding Table
 
 decoding_table = (
-    '\x00'     #  0x00 -> NULL
-    '\x01'     #  0x01 -> START OF HEADING
-    '\x02'     #  0x02 -> START OF TEXT
-    '\x03'     #  0x03 -> END OF TEXT
-    '\x04'     #  0x04 -> END OF TRANSMISSION
-    '\x05'     #  0x05 -> ENQUIRY
-    '\x06'     #  0x06 -> ACKNOWLEDGE
-    '\x07'     #  0x07 -> BELL
-    '\x08'     #  0x08 -> BACKSPACE
-    '\t'       #  0x09 -> HORIZONTAL TABULATION
-    '\n'       #  0x0A -> LINE FEED
-    '\x0b'     #  0x0B -> VERTICAL TABULATION
-    '\x0c'     #  0x0C -> FORM FEED
-    '\r'       #  0x0D -> CARRIAGE RETURN
-    '\x0e'     #  0x0E -> SHIFT OUT
-    '\x0f'     #  0x0F -> SHIFT IN
-    '\x10'     #  0x10 -> DATA LINK ESCAPE
-    '\x11'     #  0x11 -> DEVICE CONTROL ONE
-    '\x12'     #  0x12 -> DEVICE CONTROL TWO
-    '\x13'     #  0x13 -> DEVICE CONTROL THREE
-    '\x14'     #  0x14 -> DEVICE CONTROL FOUR
-    '\x15'     #  0x15 -> NEGATIVE ACKNOWLEDGE
-    '\x16'     #  0x16 -> SYNCHRONOUS IDLE
-    '\x17'     #  0x17 -> END OF TRANSMISSION BLOCK
-    '\x18'     #  0x18 -> CANCEL
-    '\x19'     #  0x19 -> END OF MEDIUM
-    '\x1a'     #  0x1A -> SUBSTITUTE
-    '\x1b'     #  0x1B -> ESCAPE
-    '\x1c'     #  0x1C -> FILE SEPARATOR
-    '\x1d'     #  0x1D -> GROUP SEPARATOR
-    '\x1e'     #  0x1E -> RECORD SEPARATOR
-    '\x1f'     #  0x1F -> UNIT SEPARATOR
-    ' '        #  0x20 -> SPACE
-    '!'        #  0x21 -> EXCLAMATION MARK
-    '"'        #  0x22 -> QUOTATION MARK
-    '#'        #  0x23 -> NUMBER SIGN
-    '$'        #  0x24 -> DOLLAR SIGN
-    '%'        #  0x25 -> PERCENT SIGN
-    '&'        #  0x26 -> AMPERSAND
-    "'"        #  0x27 -> APOSTROPHE
-    '('        #  0x28 -> LEFT PARENTHESIS
-    ')'        #  0x29 -> RIGHT PARENTHESIS
-    '*'        #  0x2A -> ASTERISK
-    '+'        #  0x2B -> PLUS SIGN
-    ','        #  0x2C -> COMMA
-    '-'        #  0x2D -> HYPHEN-MINUS
-    '.'        #  0x2E -> FULL STOP
-    '/'        #  0x2F -> SOLIDUS
-    '0'        #  0x30 -> DIGIT ZERO
-    '1'        #  0x31 -> DIGIT ONE
-    '2'        #  0x32 -> DIGIT TWO
-    '3'        #  0x33 -> DIGIT THREE
-    '4'        #  0x34 -> DIGIT FOUR
-    '5'        #  0x35 -> DIGIT FIVE
-    '6'        #  0x36 -> DIGIT SIX
-    '7'        #  0x37 -> DIGIT SEVEN
-    '8'        #  0x38 -> DIGIT EIGHT
-    '9'        #  0x39 -> DIGIT NINE
-    ':'        #  0x3A -> COLON
-    ';'        #  0x3B -> SEMICOLON
-    '<'        #  0x3C -> LESS-THAN SIGN
-    '='        #  0x3D -> EQUALS SIGN
-    '>'        #  0x3E -> GREATER-THAN SIGN
-    '?'        #  0x3F -> QUESTION MARK
-    '@'        #  0x40 -> COMMERCIAL AT
-    'A'        #  0x41 -> LATIN CAPITAL LETTER A
-    'B'        #  0x42 -> LATIN CAPITAL LETTER B
-    'C'        #  0x43 -> LATIN CAPITAL LETTER C
-    'D'        #  0x44 -> LATIN CAPITAL LETTER D
-    'E'        #  0x45 -> LATIN CAPITAL LETTER E
-    'F'        #  0x46 -> LATIN CAPITAL LETTER F
-    'G'        #  0x47 -> LATIN CAPITAL LETTER G
-    'H'        #  0x48 -> LATIN CAPITAL LETTER H
-    'I'        #  0x49 -> LATIN CAPITAL LETTER I
-    'J'        #  0x4A -> LATIN CAPITAL LETTER J
-    'K'        #  0x4B -> LATIN CAPITAL LETTER K
-    'L'        #  0x4C -> LATIN CAPITAL LETTER L
-    'M'        #  0x4D -> LATIN CAPITAL LETTER M
-    'N'        #  0x4E -> LATIN CAPITAL LETTER N
-    'O'        #  0x4F -> LATIN CAPITAL LETTER O
-    'P'        #  0x50 -> LATIN CAPITAL LETTER P
-    'Q'        #  0x51 -> LATIN CAPITAL LETTER Q
-    'R'        #  0x52 -> LATIN CAPITAL LETTER R
-    'S'        #  0x53 -> LATIN CAPITAL LETTER S
-    'T'        #  0x54 -> LATIN CAPITAL LETTER T
-    'U'        #  0x55 -> LATIN CAPITAL LETTER U
-    'V'        #  0x56 -> LATIN CAPITAL LETTER V
-    'W'        #  0x57 -> LATIN CAPITAL LETTER W
-    'X'        #  0x58 -> LATIN CAPITAL LETTER X
-    'Y'        #  0x59 -> LATIN CAPITAL LETTER Y
-    'Z'        #  0x5A -> LATIN CAPITAL LETTER Z
-    '['        #  0x5B -> LEFT SQUARE BRACKET
-    '\\'       #  0x5C -> REVERSE SOLIDUS
-    ']'        #  0x5D -> RIGHT SQUARE BRACKET
-    '^'        #  0x5E -> CIRCUMFLEX ACCENT
-    '_'        #  0x5F -> LOW LINE
-    '`'        #  0x60 -> GRAVE ACCENT
-    'a'        #  0x61 -> LATIN SMALL LETTER A
-    'b'        #  0x62 -> LATIN SMALL LETTER B
-    'c'        #  0x63 -> LATIN SMALL LETTER C
-    'd'        #  0x64 -> LATIN SMALL LETTER D
-    'e'        #  0x65 -> LATIN SMALL LETTER E
-    'f'        #  0x66 -> LATIN SMALL LETTER F
-    'g'        #  0x67 -> LATIN SMALL LETTER G
-    'h'        #  0x68 -> LATIN SMALL LETTER H
-    'i'        #  0x69 -> LATIN SMALL LETTER I
-    'j'        #  0x6A -> LATIN SMALL LETTER J
-    'k'        #  0x6B -> LATIN SMALL LETTER K
-    'l'        #  0x6C -> LATIN SMALL LETTER L
-    'm'        #  0x6D -> LATIN SMALL LETTER M
-    'n'        #  0x6E -> LATIN SMALL LETTER N
-    'o'        #  0x6F -> LATIN SMALL LETTER O
-    'p'        #  0x70 -> LATIN SMALL LETTER P
-    'q'        #  0x71 -> LATIN SMALL LETTER Q
-    'r'        #  0x72 -> LATIN SMALL LETTER R
-    's'        #  0x73 -> LATIN SMALL LETTER S
-    't'        #  0x74 -> LATIN SMALL LETTER T
-    'u'        #  0x75 -> LATIN SMALL LETTER U
-    'v'        #  0x76 -> LATIN SMALL LETTER V
-    'w'        #  0x77 -> LATIN SMALL LETTER W
-    'x'        #  0x78 -> LATIN SMALL LETTER X
-    'y'        #  0x79 -> LATIN SMALL LETTER Y
-    'z'        #  0x7A -> LATIN SMALL LETTER Z
-    '{'        #  0x7B -> LEFT CURLY BRACKET
-    '|'        #  0x7C -> VERTICAL LINE
-    '}'        #  0x7D -> RIGHT CURLY BRACKET
-    '~'        #  0x7E -> TILDE
-    '\x7f'     #  0x7F -> DELETE
-    '\u0402'   #  0x80 -> CYRILLIC CAPITAL LETTER DJE
-    '\u0403'   #  0x81 -> CYRILLIC CAPITAL LETTER GJE
-    '\u201a'   #  0x82 -> SINGLE LOW-9 QUOTATION MARK
-    '\u0453'   #  0x83 -> CYRILLIC SMALL LETTER GJE
-    '\u201e'   #  0x84 -> DOUBLE LOW-9 QUOTATION MARK
-    '\u2026'   #  0x85 -> HORIZONTAL ELLIPSIS
-    '\u2020'   #  0x86 -> DAGGER
-    '\u2021'   #  0x87 -> DOUBLE DAGGER
-    '\u20ac'   #  0x88 -> EURO SIGN
-    '\u2030'   #  0x89 -> PER MILLE SIGN
-    '\u0409'   #  0x8A -> CYRILLIC CAPITAL LETTER LJE
-    '\u2039'   #  0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK
-    '\u040a'   #  0x8C -> CYRILLIC CAPITAL LETTER NJE
-    '\u040c'   #  0x8D -> CYRILLIC CAPITAL LETTER KJE
-    '\u040b'   #  0x8E -> CYRILLIC CAPITAL LETTER TSHE
-    '\u040f'   #  0x8F -> CYRILLIC CAPITAL LETTER DZHE
-    '\u0452'   #  0x90 -> CYRILLIC SMALL LETTER DJE
-    '\u2018'   #  0x91 -> LEFT SINGLE QUOTATION MARK
-    '\u2019'   #  0x92 -> RIGHT SINGLE QUOTATION MARK
-    '\u201c'   #  0x93 -> LEFT DOUBLE QUOTATION MARK
-    '\u201d'   #  0x94 -> RIGHT DOUBLE QUOTATION MARK
-    '\u2022'   #  0x95 -> BULLET
-    '\u2013'   #  0x96 -> EN DASH
-    '\u2014'   #  0x97 -> EM DASH
-    '\ufffe'   #  0x98 -> UNDEFINED
-    '\u2122'   #  0x99 -> TRADE MARK SIGN
-    '\u0459'   #  0x9A -> CYRILLIC SMALL LETTER LJE
-    '\u203a'   #  0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
-    '\u045a'   #  0x9C -> CYRILLIC SMALL LETTER NJE
-    '\u045c'   #  0x9D -> CYRILLIC SMALL LETTER KJE
-    '\u045b'   #  0x9E -> CYRILLIC SMALL LETTER TSHE
-    '\u045f'   #  0x9F -> CYRILLIC SMALL LETTER DZHE
-    '\xa0'     #  0xA0 -> NO-BREAK SPACE
-    '\u040e'   #  0xA1 -> CYRILLIC CAPITAL LETTER SHORT U
-    '\u045e'   #  0xA2 -> CYRILLIC SMALL LETTER SHORT U
-    '\u0408'   #  0xA3 -> CYRILLIC CAPITAL LETTER JE
-    '\xa4'     #  0xA4 -> CURRENCY SIGN
-    '\u0490'   #  0xA5 -> CYRILLIC CAPITAL LETTER GHE WITH UPTURN
-    '\xa6'     #  0xA6 -> BROKEN BAR
-    '\xa7'     #  0xA7 -> SECTION SIGN
-    '\u0401'   #  0xA8 -> CYRILLIC CAPITAL LETTER IO
-    '\xa9'     #  0xA9 -> COPYRIGHT SIGN
-    '\u0404'   #  0xAA -> CYRILLIC CAPITAL LETTER UKRAINIAN IE
-    '\xab'     #  0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
-    '\xac'     #  0xAC -> NOT SIGN
-    '\xad'     #  0xAD -> SOFT HYPHEN
-    '\xae'     #  0xAE -> REGISTERED SIGN
-    '\u0407'   #  0xAF -> CYRILLIC CAPITAL LETTER YI
-    '\xb0'     #  0xB0 -> DEGREE SIGN
-    '\xb1'     #  0xB1 -> PLUS-MINUS SIGN
-    '\u0406'   #  0xB2 -> CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
-    '\u0456'   #  0xB3 -> CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
-    '\u0491'   #  0xB4 -> CYRILLIC SMALL LETTER GHE WITH UPTURN
-    '\xb5'     #  0xB5 -> MICRO SIGN
-    '\xb6'     #  0xB6 -> PILCROW SIGN
-    '\xb7'     #  0xB7 -> MIDDLE DOT
-    '\u0451'   #  0xB8 -> CYRILLIC SMALL LETTER IO
-    '\u2116'   #  0xB9 -> NUMERO SIGN
-    '\u0454'   #  0xBA -> CYRILLIC SMALL LETTER UKRAINIAN IE
-    '\xbb'     #  0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
-    '\u0458'   #  0xBC -> CYRILLIC SMALL LETTER JE
-    '\u0405'   #  0xBD -> CYRILLIC CAPITAL LETTER DZE
-    '\u0455'   #  0xBE -> CYRILLIC SMALL LETTER DZE
-    '\u0457'   #  0xBF -> CYRILLIC SMALL LETTER YI
-    '\u0410'   #  0xC0 -> CYRILLIC CAPITAL LETTER A
-    '\u0411'   #  0xC1 -> CYRILLIC CAPITAL LETTER BE
-    '\u0412'   #  0xC2 -> CYRILLIC CAPITAL LETTER VE
-    '\u0413'   #  0xC3 -> CYRILLIC CAPITAL LETTER GHE
-    '\u0414'   #  0xC4 -> CYRILLIC CAPITAL LETTER DE
-    '\u0415'   #  0xC5 -> CYRILLIC CAPITAL LETTER IE
-    '\u0416'   #  0xC6 -> CYRILLIC CAPITAL LETTER ZHE
-    '\u0417'   #  0xC7 -> CYRILLIC CAPITAL LETTER ZE
-    '\u0418'   #  0xC8 -> CYRILLIC CAPITAL LETTER I
-    '\u0419'   #  0xC9 -> CYRILLIC CAPITAL LETTER SHORT I
-    '\u041a'   #  0xCA -> CYRILLIC CAPITAL LETTER KA
-    '\u041b'   #  0xCB -> CYRILLIC CAPITAL LETTER EL
-    '\u041c'   #  0xCC -> CYRILLIC CAPITAL LETTER EM
-    '\u041d'   #  0xCD -> CYRILLIC CAPITAL LETTER EN
-    '\u041e'   #  0xCE -> CYRILLIC CAPITAL LETTER O
-    '\u041f'   #  0xCF -> CYRILLIC CAPITAL LETTER PE
-    '\u0420'   #  0xD0 -> CYRILLIC CAPITAL LETTER ER
-    '\u0421'   #  0xD1 -> CYRILLIC CAPITAL LETTER ES
-    '\u0422'   #  0xD2 -> CYRILLIC CAPITAL LETTER TE
-    '\u0423'   #  0xD3 -> CYRILLIC CAPITAL LETTER U
-    '\u0424'   #  0xD4 -> CYRILLIC CAPITAL LETTER EF
-    '\u0425'   #  0xD5 -> CYRILLIC CAPITAL LETTER HA
-    '\u0426'   #  0xD6 -> CYRILLIC CAPITAL LETTER TSE
-    '\u0427'   #  0xD7 -> CYRILLIC CAPITAL LETTER CHE
-    '\u0428'   #  0xD8 -> CYRILLIC CAPITAL LETTER SHA
-    '\u0429'   #  0xD9 -> CYRILLIC CAPITAL LETTER SHCHA
-    '\u042a'   #  0xDA -> CYRILLIC CAPITAL LETTER HARD SIGN
-    '\u042b'   #  0xDB -> CYRILLIC CAPITAL LETTER YERU
-    '\u042c'   #  0xDC -> CYRILLIC CAPITAL LETTER SOFT SIGN
-    '\u042d'   #  0xDD -> CYRILLIC CAPITAL LETTER E
-    '\u042e'   #  0xDE -> CYRILLIC CAPITAL LETTER YU
-    '\u042f'   #  0xDF -> CYRILLIC CAPITAL LETTER YA
-    '\u0430'   #  0xE0 -> CYRILLIC SMALL LETTER A
-    '\u0431'   #  0xE1 -> CYRILLIC SMALL LETTER BE
-    '\u0432'   #  0xE2 -> CYRILLIC SMALL LETTER VE
-    '\u0433'   #  0xE3 -> CYRILLIC SMALL LETTER GHE
-    '\u0434'   #  0xE4 -> CYRILLIC SMALL LETTER DE
-    '\u0435'   #  0xE5 -> CYRILLIC SMALL LETTER IE
-    '\u0436'   #  0xE6 -> CYRILLIC SMALL LETTER ZHE
-    '\u0437'   #  0xE7 -> CYRILLIC SMALL LETTER ZE
-    '\u0438'   #  0xE8 -> CYRILLIC SMALL LETTER I
-    '\u0439'   #  0xE9 -> CYRILLIC SMALL LETTER SHORT I
-    '\u043a'   #  0xEA -> CYRILLIC SMALL LETTER KA
-    '\u043b'   #  0xEB -> CYRILLIC SMALL LETTER EL
-    '\u043c'   #  0xEC -> CYRILLIC SMALL LETTER EM
-    '\u043d'   #  0xED -> CYRILLIC SMALL LETTER EN
-    '\u043e'   #  0xEE -> CYRILLIC SMALL LETTER O
-    '\u043f'   #  0xEF -> CYRILLIC SMALL LETTER PE
-    '\u0440'   #  0xF0 -> CYRILLIC SMALL LETTER ER
-    '\u0441'   #  0xF1 -> CYRILLIC SMALL LETTER ES
-    '\u0442'   #  0xF2 -> CYRILLIC SMALL LETTER TE
-    '\u0443'   #  0xF3 -> CYRILLIC SMALL LETTER U
-    '\u0444'   #  0xF4 -> CYRILLIC SMALL LETTER EF
-    '\u0445'   #  0xF5 -> CYRILLIC SMALL LETTER HA
-    '\u0446'   #  0xF6 -> CYRILLIC SMALL LETTER TSE
-    '\u0447'   #  0xF7 -> CYRILLIC SMALL LETTER CHE
-    '\u0448'   #  0xF8 -> CYRILLIC SMALL LETTER SHA
-    '\u0449'   #  0xF9 -> CYRILLIC SMALL LETTER SHCHA
-    '\u044a'   #  0xFA -> CYRILLIC SMALL LETTER HARD SIGN
-    '\u044b'   #  0xFB -> CYRILLIC SMALL LETTER YERU
-    '\u044c'   #  0xFC -> CYRILLIC SMALL LETTER SOFT SIGN
-    '\u044d'   #  0xFD -> CYRILLIC SMALL LETTER E
-    '\u044e'   #  0xFE -> CYRILLIC SMALL LETTER YU
-    '\u044f'   #  0xFF -> CYRILLIC SMALL LETTER YA
+    '\x00'      #  0x00 -> NULL
+    '\x01'      #  0x01 -> START OF HEADING
+    '\x02'      #  0x02 -> START OF TEXT
+    '\x03'      #  0x03 -> END OF TEXT
+    '\x04'      #  0x04 -> END OF TRANSMISSION
+    '\x05'      #  0x05 -> ENQUIRY
+    '\x06'      #  0x06 -> ACKNOWLEDGE
+    '\x07'      #  0x07 -> BELL
+    '\x08'      #  0x08 -> BACKSPACE
+    '\t'        #  0x09 -> HORIZONTAL TABULATION
+    '\n'        #  0x0A -> LINE FEED
+    '\x0b'      #  0x0B -> VERTICAL TABULATION
+    '\x0c'      #  0x0C -> FORM FEED
+    '\r'        #  0x0D -> CARRIAGE RETURN
+    '\x0e'      #  0x0E -> SHIFT OUT
+    '\x0f'      #  0x0F -> SHIFT IN
+    '\x10'      #  0x10 -> DATA LINK ESCAPE
+    '\x11'      #  0x11 -> DEVICE CONTROL ONE
+    '\x12'      #  0x12 -> DEVICE CONTROL TWO
+    '\x13'      #  0x13 -> DEVICE CONTROL THREE
+    '\x14'      #  0x14 -> DEVICE CONTROL FOUR
+    '\x15'      #  0x15 -> NEGATIVE ACKNOWLEDGE
+    '\x16'      #  0x16 -> SYNCHRONOUS IDLE
+    '\x17'      #  0x17 -> END OF TRANSMISSION BLOCK
+    '\x18'      #  0x18 -> CANCEL
+    '\x19'      #  0x19 -> END OF MEDIUM
+    '\x1a'      #  0x1A -> SUBSTITUTE
+    '\x1b'      #  0x1B -> ESCAPE
+    '\x1c'      #  0x1C -> FILE SEPARATOR
+    '\x1d'      #  0x1D -> GROUP SEPARATOR
+    '\x1e'      #  0x1E -> RECORD SEPARATOR
+    '\x1f'      #  0x1F -> UNIT SEPARATOR
+    ' '         #  0x20 -> SPACE
+    '!'         #  0x21 -> EXCLAMATION MARK
+    '"'         #  0x22 -> QUOTATION MARK
+    '#'         #  0x23 -> NUMBER SIGN
+    '$'         #  0x24 -> DOLLAR SIGN
+    '%'         #  0x25 -> PERCENT SIGN
+    '&'         #  0x26 -> AMPERSAND
+    "'"         #  0x27 -> APOSTROPHE
+    '('         #  0x28 -> LEFT PARENTHESIS
+    ')'         #  0x29 -> RIGHT PARENTHESIS
+    '*'         #  0x2A -> ASTERISK
+    '+'         #  0x2B -> PLUS SIGN
+    ','         #  0x2C -> COMMA
+    '-'         #  0x2D -> HYPHEN-MINUS
+    '.'         #  0x2E -> FULL STOP
+    '/'         #  0x2F -> SOLIDUS
+    '0'         #  0x30 -> DIGIT ZERO
+    '1'         #  0x31 -> DIGIT ONE
+    '2'         #  0x32 -> DIGIT TWO
+    '3'         #  0x33 -> DIGIT THREE
+    '4'         #  0x34 -> DIGIT FOUR
+    '5'         #  0x35 -> DIGIT FIVE
+    '6'         #  0x36 -> DIGIT SIX
+    '7'         #  0x37 -> DIGIT SEVEN
+    '8'         #  0x38 -> DIGIT EIGHT
+    '9'         #  0x39 -> DIGIT NINE
+    ':'         #  0x3A -> COLON
+    ';'         #  0x3B -> SEMICOLON
+    '<'         #  0x3C -> LESS-THAN SIGN
+    '='         #  0x3D -> EQUALS SIGN
+    '>'         #  0x3E -> GREATER-THAN SIGN
+    '?'         #  0x3F -> QUESTION MARK
+    '@'         #  0x40 -> COMMERCIAL AT
+    'A'         #  0x41 -> LATIN CAPITAL LETTER A
+    'B'         #  0x42 -> LATIN CAPITAL LETTER B
+    'C'         #  0x43 -> LATIN CAPITAL LETTER C
+    'D'         #  0x44 -> LATIN CAPITAL LETTER D
+    'E'         #  0x45 -> LATIN CAPITAL LETTER E
+    'F'         #  0x46 -> LATIN CAPITAL LETTER F
+    'G'         #  0x47 -> LATIN CAPITAL LETTER G
+    'H'         #  0x48 -> LATIN CAPITAL LETTER H
+    'I'         #  0x49 -> LATIN CAPITAL LETTER I
+    'J'         #  0x4A -> LATIN CAPITAL LETTER J
+    'K'         #  0x4B -> LATIN CAPITAL LETTER K
+    'L'         #  0x4C -> LATIN CAPITAL LETTER L
+    'M'         #  0x4D -> LATIN CAPITAL LETTER M
+    'N'         #  0x4E -> LATIN CAPITAL LETTER N
+    'O'         #  0x4F -> LATIN CAPITAL LETTER O
+    'P'         #  0x50 -> LATIN CAPITAL LETTER P
+    'Q'         #  0x51 -> LATIN CAPITAL LETTER Q
+    'R'         #  0x52 -> LATIN CAPITAL LETTER R
+    'S'         #  0x53 -> LATIN CAPITAL LETTER S
+    'T'         #  0x54 -> LATIN CAPITAL LETTER T
+    'U'         #  0x55 -> LATIN CAPITAL LETTER U
+    'V'         #  0x56 -> LATIN CAPITAL LETTER V
+    'W'         #  0x57 -> LATIN CAPITAL LETTER W
+    'X'         #  0x58 -> LATIN CAPITAL LETTER X
+    'Y'         #  0x59 -> LATIN CAPITAL LETTER Y
+    'Z'         #  0x5A -> LATIN CAPITAL LETTER Z
+    '['         #  0x5B -> LEFT SQUARE BRACKET
+    '\\'        #  0x5C -> REVERSE SOLIDUS
+    ']'         #  0x5D -> RIGHT SQUARE BRACKET
+    '^'         #  0x5E -> CIRCUMFLEX ACCENT
+    '_'         #  0x5F -> LOW LINE
+    '`'         #  0x60 -> GRAVE ACCENT
+    'a'         #  0x61 -> LATIN SMALL LETTER A
+    'b'         #  0x62 -> LATIN SMALL LETTER B
+    'c'         #  0x63 -> LATIN SMALL LETTER C
+    'd'         #  0x64 -> LATIN SMALL LETTER D
+    'e'         #  0x65 -> LATIN SMALL LETTER E
+    'f'         #  0x66 -> LATIN SMALL LETTER F
+    'g'         #  0x67 -> LATIN SMALL LETTER G
+    'h'         #  0x68 -> LATIN SMALL LETTER H
+    'i'         #  0x69 -> LATIN SMALL LETTER I
+    'j'         #  0x6A -> LATIN SMALL LETTER J
+    'k'         #  0x6B -> LATIN SMALL LETTER K
+    'l'         #  0x6C -> LATIN SMALL LETTER L
+    'm'         #  0x6D -> LATIN SMALL LETTER M
+    'n'         #  0x6E -> LATIN SMALL LETTER N
+    'o'         #  0x6F -> LATIN SMALL LETTER O
+    'p'         #  0x70 -> LATIN SMALL LETTER P
+    'q'         #  0x71 -> LATIN SMALL LETTER Q
+    'r'         #  0x72 -> LATIN SMALL LETTER R
+    's'         #  0x73 -> LATIN SMALL LETTER S
+    't'         #  0x74 -> LATIN SMALL LETTER T
+    'u'         #  0x75 -> LATIN SMALL LETTER U
+    'v'         #  0x76 -> LATIN SMALL LETTER V
+    'w'         #  0x77 -> LATIN SMALL LETTER W
+    'x'         #  0x78 -> LATIN SMALL LETTER X
+    'y'         #  0x79 -> LATIN SMALL LETTER Y
+    'z'         #  0x7A -> LATIN SMALL LETTER Z
+    '{'         #  0x7B -> LEFT CURLY BRACKET
+    '|'         #  0x7C -> VERTICAL LINE
+    '}'         #  0x7D -> RIGHT CURLY BRACKET
+    '~'         #  0x7E -> TILDE
+    '\x7f'      #  0x7F -> DELETE
+    '\u0402'    #  0x80 -> CYRILLIC CAPITAL LETTER DJE
+    '\u0403'    #  0x81 -> CYRILLIC CAPITAL LETTER GJE
+    '\u201a'    #  0x82 -> SINGLE LOW-9 QUOTATION MARK
+    '\u0453'    #  0x83 -> CYRILLIC SMALL LETTER GJE
+    '\u201e'    #  0x84 -> DOUBLE LOW-9 QUOTATION MARK
+    '\u2026'    #  0x85 -> HORIZONTAL ELLIPSIS
+    '\u2020'    #  0x86 -> DAGGER
+    '\u2021'    #  0x87 -> DOUBLE DAGGER
+    '\u20ac'    #  0x88 -> EURO SIGN
+    '\u2030'    #  0x89 -> PER MILLE SIGN
+    '\u0409'    #  0x8A -> CYRILLIC CAPITAL LETTER LJE
+    '\u2039'    #  0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK
+    '\u040a'    #  0x8C -> CYRILLIC CAPITAL LETTER NJE
+    '\u049a'    #  0x8D -> CYRILLIC CAPITAL LETTER KA WITH DESCENDER
+    '\u04ba'    #  0x8E -> CYRILLIC CAPITAL LETTER SHHA
+    '\u040f'    #  0x8F -> CYRILLIC CAPITAL LETTER DZHE
+    '\u0452'    #  0x90 -> CYRILLIC SMALL LETTER DJE
+    '\u2018'    #  0x91 -> LEFT SINGLE QUOTATION MARK
+    '\u2019'    #  0x92 -> RIGHT SINGLE QUOTATION MARK
+    '\u201c'    #  0x93 -> LEFT DOUBLE QUOTATION MARK
+    '\u201d'    #  0x94 -> RIGHT DOUBLE QUOTATION MARK
+    '\u2022'    #  0x95 -> BULLET
+    '\u2013'    #  0x96 -> EN DASH
+    '\u2014'    #  0x97 -> EM DASH
+    '\ufffe'    #  0x98 -> UNDEFINED
+    '\u2122'    #  0x99 -> TRADE MARK SIGN
+    '\u0459'    #  0x9A -> CYRILLIC SMALL LETTER LJE
+    '\u203a'    #  0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
+    '\u045a'    #  0x9C -> CYRILLIC SMALL LETTER NJE
+    '\u049b'    #  0x9D -> CYRILLIC SMALL LETTER KA WITH DESCENDER
+    '\u04bb'    #  0x9E -> CYRILLIC SMALL LETTER SHHA
+    '\u045f'    #  0x9F -> CYRILLIC SMALL LETTER DZHE
+    '\xa0'      #  0xA0 -> NO-BREAK SPACE
+    '\u04b0'    #  0xA1 -> CYRILLIC CAPITAL LETTER STRAIGHT U WITH STROKE
+    '\u04b1'    #  0xA2 -> CYRILLIC SMALL LETTER STRAIGHT U WITH STROKE
+    '\u04d8'    #  0xA3 -> CYRILLIC CAPITAL LETTER SCHWA
+    '\xa4'      #  0xA4 -> CURRENCY SIGN
+    '\u04e8'    #  0xA5 -> CYRILLIC CAPITAL LETTER BARRED O
+    '\xa6'      #  0xA6 -> BROKEN BAR
+    '\xa7'      #  0xA7 -> SECTION SIGN
+    '\u0401'    #  0xA8 -> CYRILLIC CAPITAL LETTER IO
+    '\xa9'      #  0xA9 -> COPYRIGHT SIGN
+    '\u0492'    #  0xAA -> CYRILLIC CAPITAL LETTER GHE WITH STROKE
+    '\xab'      #  0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+    '\xac'      #  0xAC -> NOT SIGN
+    '\xad'      #  0xAD -> SOFT HYPHEN
+    '\xae'      #  0xAE -> REGISTERED SIGN
+    '\u04ae'    #  0xAF -> CYRILLIC CAPITAL LETTER STRAIGHT U
+    '\xb0'      #  0xB0 -> DEGREE SIGN
+    '\xb1'      #  0xB1 -> PLUS-MINUS SIGN
+    '\u0406'    #  0xB2 -> CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
+    '\u0456'    #  0xB3 -> CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
+    '\u04e9'    #  0xB4 -> CYRILLIC SMALL LETTER BARRED O
+    '\xb5'      #  0xB5 -> MICRO SIGN
+    '\xb6'      #  0xB6 -> PILCROW SIGN
+    '\xb7'      #  0xB7 -> MIDDLE DOT
+    '\u0451'    #  0xB8 -> CYRILLIC SMALL LETTER IO
+    '\u2116'    #  0xB9 -> NUMERO SIGN
+    '\u0493'    #  0xBA -> CYRILLIC SMALL LETTER GHE WITH STROKE
+    '\xbb'      #  0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+    '\u04d9'    #  0xBC -> CYRILLIC SMALL LETTER SCHWA
+    '\u04a2'    #  0xBD -> CYRILLIC CAPITAL LETTER EN WITH DESCENDER
+    '\u04a3'    #  0xBE -> CYRILLIC SMALL LETTER EN WITH DESCENDER
+    '\u04af'    #  0xBF -> CYRILLIC SMALL LETTER STRAIGHT U
+    '\u0410'    #  0xC0 -> CYRILLIC CAPITAL LETTER A
+    '\u0411'    #  0xC1 -> CYRILLIC CAPITAL LETTER BE
+    '\u0412'    #  0xC2 -> CYRILLIC CAPITAL LETTER VE
+    '\u0413'    #  0xC3 -> CYRILLIC CAPITAL LETTER GHE
+    '\u0414'    #  0xC4 -> CYRILLIC CAPITAL LETTER DE
+    '\u0415'    #  0xC5 -> CYRILLIC CAPITAL LETTER IE
+    '\u0416'    #  0xC6 -> CYRILLIC CAPITAL LETTER ZHE
+    '\u0417'    #  0xC7 -> CYRILLIC CAPITAL LETTER ZE
+    '\u0418'    #  0xC8 -> CYRILLIC CAPITAL LETTER I
+    '\u0419'    #  0xC9 -> CYRILLIC CAPITAL LETTER SHORT I
+    '\u041a'    #  0xCA -> CYRILLIC CAPITAL LETTER KA
+    '\u041b'    #  0xCB -> CYRILLIC CAPITAL LETTER EL
+    '\u041c'    #  0xCC -> CYRILLIC CAPITAL LETTER EM
+    '\u041d'    #  0xCD -> CYRILLIC CAPITAL LETTER EN
+    '\u041e'    #  0xCE -> CYRILLIC CAPITAL LETTER O
+    '\u041f'    #  0xCF -> CYRILLIC CAPITAL LETTER PE
+    '\u0420'    #  0xD0 -> CYRILLIC CAPITAL LETTER ER
+    '\u0421'    #  0xD1 -> CYRILLIC CAPITAL LETTER ES
+    '\u0422'    #  0xD2 -> CYRILLIC CAPITAL LETTER TE
+    '\u0423'    #  0xD3 -> CYRILLIC CAPITAL LETTER U
+    '\u0424'    #  0xD4 -> CYRILLIC CAPITAL LETTER EF
+    '\u0425'    #  0xD5 -> CYRILLIC CAPITAL LETTER HA
+    '\u0426'    #  0xD6 -> CYRILLIC CAPITAL LETTER TSE
+    '\u0427'    #  0xD7 -> CYRILLIC CAPITAL LETTER CHE
+    '\u0428'    #  0xD8 -> CYRILLIC CAPITAL LETTER SHA
+    '\u0429'    #  0xD9 -> CYRILLIC CAPITAL LETTER SHCHA
+    '\u042a'    #  0xDA -> CYRILLIC CAPITAL LETTER HARD SIGN
+    '\u042b'    #  0xDB -> CYRILLIC CAPITAL LETTER YERU
+    '\u042c'    #  0xDC -> CYRILLIC CAPITAL LETTER SOFT SIGN
+    '\u042d'    #  0xDD -> CYRILLIC CAPITAL LETTER E
+    '\u042e'    #  0xDE -> CYRILLIC CAPITAL LETTER YU
+    '\u042f'    #  0xDF -> CYRILLIC CAPITAL LETTER YA
+    '\u0430'    #  0xE0 -> CYRILLIC SMALL LETTER A
+    '\u0431'    #  0xE1 -> CYRILLIC SMALL LETTER BE
+    '\u0432'    #  0xE2 -> CYRILLIC SMALL LETTER VE
+    '\u0433'    #  0xE3 -> CYRILLIC SMALL LETTER GHE
+    '\u0434'    #  0xE4 -> CYRILLIC SMALL LETTER DE
+    '\u0435'    #  0xE5 -> CYRILLIC SMALL LETTER IE
+    '\u0436'    #  0xE6 -> CYRILLIC SMALL LETTER ZHE
+    '\u0437'    #  0xE7 -> CYRILLIC SMALL LETTER ZE
+    '\u0438'    #  0xE8 -> CYRILLIC SMALL LETTER I
+    '\u0439'    #  0xE9 -> CYRILLIC SMALL LETTER SHORT I
+    '\u043a'    #  0xEA -> CYRILLIC SMALL LETTER KA
+    '\u043b'    #  0xEB -> CYRILLIC SMALL LETTER EL
+    '\u043c'    #  0xEC -> CYRILLIC SMALL LETTER EM
+    '\u043d'    #  0xED -> CYRILLIC SMALL LETTER EN
+    '\u043e'    #  0xEE -> CYRILLIC SMALL LETTER O
+    '\u043f'    #  0xEF -> CYRILLIC SMALL LETTER PE
+    '\u0440'    #  0xF0 -> CYRILLIC SMALL LETTER ER
+    '\u0441'    #  0xF1 -> CYRILLIC SMALL LETTER ES
+    '\u0442'    #  0xF2 -> CYRILLIC SMALL LETTER TE
+    '\u0443'    #  0xF3 -> CYRILLIC SMALL LETTER U
+    '\u0444'    #  0xF4 -> CYRILLIC SMALL LETTER EF
+    '\u0445'    #  0xF5 -> CYRILLIC SMALL LETTER HA
+    '\u0446'    #  0xF6 -> CYRILLIC SMALL LETTER TSE
+    '\u0447'    #  0xF7 -> CYRILLIC SMALL LETTER CHE
+    '\u0448'    #  0xF8 -> CYRILLIC SMALL LETTER SHA
+    '\u0449'    #  0xF9 -> CYRILLIC SMALL LETTER SHCHA
+    '\u044a'    #  0xFA -> CYRILLIC SMALL LETTER HARD SIGN
+    '\u044b'    #  0xFB -> CYRILLIC SMALL LETTER YERU
+    '\u044c'    #  0xFC -> CYRILLIC SMALL LETTER SOFT SIGN
+    '\u044d'    #  0xFD -> CYRILLIC SMALL LETTER E
+    '\u044e'    #  0xFE -> CYRILLIC SMALL LETTER YU
+    '\u044f'    #  0xFF -> CYRILLIC SMALL LETTER YA
 )
 
 ### Encoding table
-encoding_table=codecs.charmap_build(decoding_table)
+encoding_table = codecs.charmap_build(decoding_table)

-- 
Repository URL: https://hg.python.org/cpython


More information about the Python-checkins mailing list