Patch #1359618: Speed-up charmap encoder.

This commit is contained in:
Martin v. Löwis 2006-06-04 19:36:28 +00:00
parent 67966bed72
commit 3f767795f6
51 changed files with 510 additions and 11516 deletions

View file

@ -9,14 +9,14 @@ import codecs
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
return codecs.charmap_encode(input,errors,encoding_map)
return codecs.charmap_encode(input,errors,encoding_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_map)[0]
return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@ -303,256 +303,6 @@ decoding_table = (
u'\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS
)
### Encoding Map
### Encoding table
encoding_table=codecs.charmap_build(decoding_table)
encoding_map = {
0x0000: 0x00, # NULL
0x0001: 0x01, # START OF HEADING
0x0002: 0x02, # START OF TEXT
0x0003: 0x03, # END OF TEXT
0x0004: 0x04, # END OF TRANSMISSION
0x0005: 0x05, # ENQUIRY
0x0006: 0x06, # ACKNOWLEDGE
0x0007: 0x07, # BELL
0x0008: 0x08, # BACKSPACE
0x0009: 0x09, # HORIZONTAL TABULATION
0x000A: 0x0A, # LINE FEED
0x000B: 0x0B, # VERTICAL TABULATION
0x000C: 0x0C, # FORM FEED
0x000D: 0x0D, # CARRIAGE RETURN
0x000E: 0x0E, # SHIFT OUT
0x000F: 0x0F, # SHIFT IN
0x0010: 0x10, # DATA LINK ESCAPE
0x0011: 0x11, # DEVICE CONTROL ONE
0x0012: 0x12, # DEVICE CONTROL TWO
0x0013: 0x13, # DEVICE CONTROL THREE
0x0014: 0x14, # DEVICE CONTROL FOUR
0x0015: 0x15, # NEGATIVE ACKNOWLEDGE
0x0016: 0x16, # SYNCHRONOUS IDLE
0x0017: 0x17, # END OF TRANSMISSION BLOCK
0x0018: 0x18, # CANCEL
0x0019: 0x19, # END OF MEDIUM
0x001A: 0x1A, # SUBSTITUTE
0x001B: 0x1B, # ESCAPE
0x001C: 0x1C, # FILE SEPARATOR
0x001D: 0x1D, # GROUP SEPARATOR
0x001E: 0x1E, # RECORD SEPARATOR
0x001F: 0x1F, # UNIT SEPARATOR
0x0020: 0x20, # SPACE
0x0021: 0x21, # EXCLAMATION MARK
0x0022: 0x22, # QUOTATION MARK
0x0023: 0x23, # NUMBER SIGN
0x0024: 0x24, # DOLLAR SIGN
0x0025: 0x25, # PERCENT SIGN
0x0026: 0x26, # AMPERSAND
0x0027: 0x27, # APOSTROPHE
0x0028: 0x28, # LEFT PARENTHESIS
0x0029: 0x29, # RIGHT PARENTHESIS
0x002A: 0x2A, # ASTERISK
0x002B: 0x2B, # PLUS SIGN
0x002C: 0x2C, # COMMA
0x002D: 0x2D, # HYPHEN-MINUS
0x002E: 0x2E, # FULL STOP
0x002F: 0x2F, # SOLIDUS
0x0030: 0x30, # DIGIT ZERO
0x0031: 0x31, # DIGIT ONE
0x0032: 0x32, # DIGIT TWO
0x0033: 0x33, # DIGIT THREE
0x0034: 0x34, # DIGIT FOUR
0x0035: 0x35, # DIGIT FIVE
0x0036: 0x36, # DIGIT SIX
0x0037: 0x37, # DIGIT SEVEN
0x0038: 0x38, # DIGIT EIGHT
0x0039: 0x39, # DIGIT NINE
0x003A: 0x3A, # COLON
0x003B: 0x3B, # SEMICOLON
0x003C: 0x3C, # LESS-THAN SIGN
0x003D: 0x3D, # EQUALS SIGN
0x003E: 0x3E, # GREATER-THAN SIGN
0x003F: 0x3F, # QUESTION MARK
0x0040: 0x40, # COMMERCIAL AT
0x0041: 0x41, # LATIN CAPITAL LETTER A
0x0042: 0x42, # LATIN CAPITAL LETTER B
0x0043: 0x43, # LATIN CAPITAL LETTER C
0x0044: 0x44, # LATIN CAPITAL LETTER D
0x0045: 0x45, # LATIN CAPITAL LETTER E
0x0046: 0x46, # LATIN CAPITAL LETTER F
0x0047: 0x47, # LATIN CAPITAL LETTER G
0x0048: 0x48, # LATIN CAPITAL LETTER H
0x0049: 0x49, # LATIN CAPITAL LETTER I
0x004A: 0x4A, # LATIN CAPITAL LETTER J
0x004B: 0x4B, # LATIN CAPITAL LETTER K
0x004C: 0x4C, # LATIN CAPITAL LETTER L
0x004D: 0x4D, # LATIN CAPITAL LETTER M
0x004E: 0x4E, # LATIN CAPITAL LETTER N
0x004F: 0x4F, # LATIN CAPITAL LETTER O
0x0050: 0x50, # LATIN CAPITAL LETTER P
0x0051: 0x51, # LATIN CAPITAL LETTER Q
0x0052: 0x52, # LATIN CAPITAL LETTER R
0x0053: 0x53, # LATIN CAPITAL LETTER S
0x0054: 0x54, # LATIN CAPITAL LETTER T
0x0055: 0x55, # LATIN CAPITAL LETTER U
0x0056: 0x56, # LATIN CAPITAL LETTER V
0x0057: 0x57, # LATIN CAPITAL LETTER W
0x0058: 0x58, # LATIN CAPITAL LETTER X
0x0059: 0x59, # LATIN CAPITAL LETTER Y
0x005A: 0x5A, # LATIN CAPITAL LETTER Z
0x005B: 0x5B, # LEFT SQUARE BRACKET
0x005C: 0x5C, # REVERSE SOLIDUS
0x005D: 0x5D, # RIGHT SQUARE BRACKET
0x005E: 0x5E, # CIRCUMFLEX ACCENT
0x005F: 0x5F, # LOW LINE
0x0060: 0x60, # GRAVE ACCENT
0x0061: 0x61, # LATIN SMALL LETTER A
0x0062: 0x62, # LATIN SMALL LETTER B
0x0063: 0x63, # LATIN SMALL LETTER C
0x0064: 0x64, # LATIN SMALL LETTER D
0x0065: 0x65, # LATIN SMALL LETTER E
0x0066: 0x66, # LATIN SMALL LETTER F
0x0067: 0x67, # LATIN SMALL LETTER G
0x0068: 0x68, # LATIN SMALL LETTER H
0x0069: 0x69, # LATIN SMALL LETTER I
0x006A: 0x6A, # LATIN SMALL LETTER J
0x006B: 0x6B, # LATIN SMALL LETTER K
0x006C: 0x6C, # LATIN SMALL LETTER L
0x006D: 0x6D, # LATIN SMALL LETTER M
0x006E: 0x6E, # LATIN SMALL LETTER N
0x006F: 0x6F, # LATIN SMALL LETTER O
0x0070: 0x70, # LATIN SMALL LETTER P
0x0071: 0x71, # LATIN SMALL LETTER Q
0x0072: 0x72, # LATIN SMALL LETTER R
0x0073: 0x73, # LATIN SMALL LETTER S
0x0074: 0x74, # LATIN SMALL LETTER T
0x0075: 0x75, # LATIN SMALL LETTER U
0x0076: 0x76, # LATIN SMALL LETTER V
0x0077: 0x77, # LATIN SMALL LETTER W
0x0078: 0x78, # LATIN SMALL LETTER X
0x0079: 0x79, # LATIN SMALL LETTER Y
0x007A: 0x7A, # LATIN SMALL LETTER Z
0x007B: 0x7B, # LEFT CURLY BRACKET
0x007C: 0x7C, # VERTICAL LINE
0x007D: 0x7D, # RIGHT CURLY BRACKET
0x007E: 0x7E, # TILDE
0x007F: 0x7F, # DELETE
0x00A0: 0xA0, # NO-BREAK SPACE
0x00A1: 0xA1, # INVERTED EXCLAMATION MARK
0x00A2: 0xA2, # CENT SIGN
0x00A3: 0xA3, # POUND SIGN
0x00A4: 0xA4, # CURRENCY SIGN
0x00A5: 0xA5, # YEN SIGN
0x00A6: 0xA6, # BROKEN BAR
0x00A7: 0xA7, # SECTION SIGN
0x00A8: 0xA8, # DIAERESIS
0x00A9: 0xA9, # COPYRIGHT SIGN
0x00AA: 0xAA, # FEMININE ORDINAL INDICATOR
0x00AB: 0xAB, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0x00AC: 0xAC, # NOT SIGN
0x00AD: 0xAD, # SOFT HYPHEN
0x00AE: 0xAE, # REGISTERED SIGN
0x00AF: 0xAF, # MACRON
0x00B0: 0xB0, # DEGREE SIGN
0x00B1: 0xB1, # PLUS-MINUS SIGN
0x00B2: 0xB2, # SUPERSCRIPT TWO
0x00B3: 0xB3, # SUPERSCRIPT THREE
0x00B4: 0xB4, # ACUTE ACCENT
0x00B5: 0xB5, # MICRO SIGN
0x00B6: 0xB6, # PILCROW SIGN
0x00B7: 0xB7, # MIDDLE DOT
0x00B8: 0xB8, # CEDILLA
0x00B9: 0xB9, # SUPERSCRIPT ONE
0x00BA: 0xBA, # MASCULINE ORDINAL INDICATOR
0x00BB: 0xBB, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0x00BC: 0xBC, # VULGAR FRACTION ONE QUARTER
0x00BD: 0xBD, # VULGAR FRACTION ONE HALF
0x00BE: 0xBE, # VULGAR FRACTION THREE QUARTERS
0x00BF: 0xBF, # INVERTED QUESTION MARK
0x00C0: 0xC0, # LATIN CAPITAL LETTER A WITH GRAVE
0x00C1: 0xC1, # LATIN CAPITAL LETTER A WITH ACUTE
0x00C2: 0xC2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
0x00C3: 0xC3, # LATIN CAPITAL LETTER A WITH TILDE
0x00C4: 0xC4, # LATIN CAPITAL LETTER A WITH DIAERESIS
0x00C5: 0xC5, # LATIN CAPITAL LETTER A WITH RING ABOVE
0x00C6: 0xC6, # LATIN CAPITAL LETTER AE
0x00C7: 0xC7, # LATIN CAPITAL LETTER C WITH CEDILLA
0x00C8: 0xC8, # LATIN CAPITAL LETTER E WITH GRAVE
0x00C9: 0xC9, # LATIN CAPITAL LETTER E WITH ACUTE
0x00CA: 0xCA, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
0x00CB: 0xCB, # LATIN CAPITAL LETTER E WITH DIAERESIS
0x00CC: 0xCC, # LATIN CAPITAL LETTER I WITH GRAVE
0x00CD: 0xCD, # LATIN CAPITAL LETTER I WITH ACUTE
0x00CE: 0xCE, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
0x00CF: 0xCF, # LATIN CAPITAL LETTER I WITH DIAERESIS
0x00D1: 0xD1, # LATIN CAPITAL LETTER N WITH TILDE
0x00D2: 0xD2, # LATIN CAPITAL LETTER O WITH GRAVE
0x00D3: 0xD3, # LATIN CAPITAL LETTER O WITH ACUTE
0x00D4: 0xD4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
0x00D5: 0xD5, # LATIN CAPITAL LETTER O WITH TILDE
0x00D6: 0xD6, # LATIN CAPITAL LETTER O WITH DIAERESIS
0x00D7: 0xD7, # MULTIPLICATION SIGN
0x00D8: 0xD8, # LATIN CAPITAL LETTER O WITH STROKE
0x00D9: 0xD9, # LATIN CAPITAL LETTER U WITH GRAVE
0x00DA: 0xDA, # LATIN CAPITAL LETTER U WITH ACUTE
0x00DB: 0xDB, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
0x00DC: 0xDC, # LATIN CAPITAL LETTER U WITH DIAERESIS
0x00DF: 0xDF, # LATIN SMALL LETTER SHARP S
0x00E0: 0xE0, # LATIN SMALL LETTER A WITH GRAVE
0x00E1: 0xE1, # LATIN SMALL LETTER A WITH ACUTE
0x00E2: 0xE2, # LATIN SMALL LETTER A WITH CIRCUMFLEX
0x00E3: 0xE3, # LATIN SMALL LETTER A WITH TILDE
0x00E4: 0xE4, # LATIN SMALL LETTER A WITH DIAERESIS
0x00E5: 0xE5, # LATIN SMALL LETTER A WITH RING ABOVE
0x00E6: 0xE6, # LATIN SMALL LETTER AE
0x00E7: 0xE7, # LATIN SMALL LETTER C WITH CEDILLA
0x00E8: 0xE8, # LATIN SMALL LETTER E WITH GRAVE
0x00E9: 0xE9, # LATIN SMALL LETTER E WITH ACUTE
0x00EA: 0xEA, # LATIN SMALL LETTER E WITH CIRCUMFLEX
0x00EB: 0xEB, # LATIN SMALL LETTER E WITH DIAERESIS
0x00EC: 0xEC, # LATIN SMALL LETTER I WITH GRAVE
0x00ED: 0xED, # LATIN SMALL LETTER I WITH ACUTE
0x00EE: 0xEE, # LATIN SMALL LETTER I WITH CIRCUMFLEX
0x00EF: 0xEF, # LATIN SMALL LETTER I WITH DIAERESIS
0x00F1: 0xF1, # LATIN SMALL LETTER N WITH TILDE
0x00F2: 0xF2, # LATIN SMALL LETTER O WITH GRAVE
0x00F3: 0xF3, # LATIN SMALL LETTER O WITH ACUTE
0x00F4: 0xF4, # LATIN SMALL LETTER O WITH CIRCUMFLEX
0x00F5: 0xF5, # LATIN SMALL LETTER O WITH TILDE
0x00F6: 0xF6, # LATIN SMALL LETTER O WITH DIAERESIS
0x00F7: 0xF7, # DIVISION SIGN
0x00F8: 0xF8, # LATIN SMALL LETTER O WITH STROKE
0x00F9: 0xF9, # LATIN SMALL LETTER U WITH GRAVE
0x00FA: 0xFA, # LATIN SMALL LETTER U WITH ACUTE
0x00FB: 0xFB, # LATIN SMALL LETTER U WITH CIRCUMFLEX
0x00FC: 0xFC, # LATIN SMALL LETTER U WITH DIAERESIS
0x00FF: 0xFF, # LATIN SMALL LETTER Y WITH DIAERESIS
0x011E: 0xD0, # LATIN CAPITAL LETTER G WITH BREVE
0x011F: 0xF0, # LATIN SMALL LETTER G WITH BREVE
0x0130: 0xDD, # LATIN CAPITAL LETTER I WITH DOT ABOVE
0x0131: 0xFD, # LATIN SMALL LETTER DOTLESS I
0x0152: 0x8C, # LATIN CAPITAL LIGATURE OE
0x0153: 0x9C, # LATIN SMALL LIGATURE OE
0x015E: 0xDE, # LATIN CAPITAL LETTER S WITH CEDILLA
0x015F: 0xFE, # LATIN SMALL LETTER S WITH CEDILLA
0x0160: 0x8A, # LATIN CAPITAL LETTER S WITH CARON
0x0161: 0x9A, # LATIN SMALL LETTER S WITH CARON
0x0178: 0x9F, # LATIN CAPITAL LETTER Y WITH DIAERESIS
0x0192: 0x83, # LATIN SMALL LETTER F WITH HOOK
0x02C6: 0x88, # MODIFIER LETTER CIRCUMFLEX ACCENT
0x02DC: 0x98, # SMALL TILDE
0x2013: 0x96, # EN DASH
0x2014: 0x97, # EM DASH
0x2018: 0x91, # LEFT SINGLE QUOTATION MARK
0x2019: 0x92, # RIGHT SINGLE QUOTATION MARK
0x201A: 0x82, # SINGLE LOW-9 QUOTATION MARK
0x201C: 0x93, # LEFT DOUBLE QUOTATION MARK
0x201D: 0x94, # RIGHT DOUBLE QUOTATION MARK
0x201E: 0x84, # DOUBLE LOW-9 QUOTATION MARK
0x2020: 0x86, # DAGGER
0x2021: 0x87, # DOUBLE DAGGER
0x2022: 0x95, # BULLET
0x2026: 0x85, # HORIZONTAL ELLIPSIS
0x2030: 0x89, # PER MILLE SIGN
0x2039: 0x8B, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK
0x203A: 0x9B, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
0x20AC: 0x80, # EURO SIGN
0x2122: 0x99, # TRADE MARK SIGN
}