extract-msg 0.48.2__py3-none-any.whl

extract_msg/encoding/__init__.py

@@ -0,0 +1,277 @@
+"""
+File for handling specialized encoding tasks or information.
+"""
+
+__all__ = [
+    'lookupCodePage',
+]
+
+
+# This adds additional encodings to python.
+import ebcdic as _
+import codecs
+
+from ..exceptions import UnknownCodepageError, UnsupportedEncodingError
+
+
+# This is a dictionary matching the code page number to it's encoding name.
+# The list used to make this can be found here:
+# https://docs.microsoft.com/en-us/windows/win32/intl/code-page-identifiers
+### TODO:
+# Many of these code pages are not supported by Python. As such, we should
+# really implement them ourselves to make sure that if someone wants to use an
+# MSG file with one of those encodings, they are able to. Perhaps we should
+# create a seperate module for that?
+# Code pages that currently don't have a supported encoding will be preceded by
+# `# UNSUPPORTED`.
+# For some of these, it is also possible that the name we are trying to find
+# them with is not known to Python. I have already confirmed this for a few of
+# them, and adjusted their names to ones that python would recognize. It is
+# Possible I missed a few.
+_CODE_PAGES = {
+    37: 'IBM037', # IBM EBCDIC US-Canada
+    437: 'IBM437', # OEM United States
+    500: 'IBM500', # IBM EBCDIC International
+    708: 'ASMO-708', # Arabic (ASMO 708)
+    # UNSUPPORTED.
+    709: '', # Arabic (ASMO-449+, BCON V4)
+    # UNSUPPORTED.
+    710: '', # Arabic - Transparent Arabic
+    # UNSUPPORTED.
+    720: 'DOS-720', # Arabic (Transparent ASMO); Arabic (DOS)
+    737: 'cp737', # OEM Greek (formerly 437G); Greek (DOS)
+    775: 'ibm775', # OEM Baltic; Baltic (DOS)
+    850: 'ibm850', # OEM Multilingual Latin 1; Western European (DOS)
+    852: 'ibm852', # OEM Latin 2; Central European (DOS)
+    855: 'IBM855', # OEM Cyrillic (primarily Russian)
+    857: 'ibm857', # OEM Turkish; Turkish (DOS)
+    858: 'cp858', # OEM Multilingual Latin 1 + Euro symbol
+    860: 'IBM860', # OEM Portuguese; Portuguese (DOS)
+    861: 'ibm861', # OEM Icelandic; Icelandic (DOS)
+    862: 'cp862', # OEM Hebrew; Hebrew (DOS)
+    863: 'IBM863', # OEM French Canadian; French Canadian (DOS)
+    864: 'IBM864', # OEM Arabic; Arabic (864)
+    865: 'IBM865', # OEM Nordic; Nordic (DOS)
+    866: 'cp866', # OEM Russian; Cyrillic (DOS)
+    869: 'ibm869', # OEM Modern Greek; Greek, Modern (DOS)
+    870: 'cp870', # IBM870 # IBM EBCDIC Multilingual/ROECE (Latin 2); IBM EBCDIC Multilingual Latin 2
+    874: 'windows-874', # ANSI/OEM Thai (ISO 8859-11); Thai (Windows)
+    875: 'cp875', # IBM EBCDIC Greek Modern
+    932: 'shift_jis', # ANSI/OEM Japanese; Japanese (Shift-JIS)
+    936: 'gb2312', # ANSI/OEM Simplified Chinese (PRC, Singapore); Chinese Simplified (GB2312)
+    949: 'ks_c_5601-1987', # ANSI/OEM Korean (Unified Hangul Code)
+    # We *must* use a custom encoding because the Python implementation differs
+    # from the Microsoft implementation.
+    950: 'windows-950', # ANSI/OEM Traditional Chinese (Taiwan; Hong Kong SAR, PRC); Chinese Traditional (Big5)
+    1026: 'IBM1026', # IBM EBCDIC Turkish (Latin 5)
+    1047: 'cp1047', # IBM EBCDIC Latin 1/Open System
+    1140: 'cp1140', # IBM EBCDIC US-Canada (037 + Euro symbol); IBM EBCDIC (US-Canada-Euro)
+    1141: 'cp1141', # IBM EBCDIC Germany (20273 + Euro symbol); IBM EBCDIC (Germany-Euro)
+    1142: 'cp1142', # IBM EBCDIC Denmark-Norway (20277 + Euro symbol); IBM EBCDIC (Denmark-Norway-Euro)
+    1143: 'cp1143', # IBM EBCDIC Finland-Sweden (20278 + Euro symbol); IBM EBCDIC (Finland-Sweden-Euro)
+    1144: 'cp1144', # IBM EBCDIC Italy (20280 + Euro symbol); IBM EBCDIC (Italy-Euro)
+    1145: 'cp1145', # IBM EBCDIC Latin America-Spain (20284 + Euro symbol); IBM EBCDIC (Spain-Euro)
+    1146: 'cp1146', # IBM EBCDIC United Kingdom (20285 + Euro symbol); IBM EBCDIC (UK-Euro)
+    1147: 'cp1147', # IBM EBCDIC France (20297 + Euro symbol); IBM EBCDIC (France-Euro)
+    1148: 'cp1148ms', # IBM EBCDIC International (500 + Euro symbol); IBM EBCDIC (International-Euro)
+    1149: 'cp1149', # IBM EBCDIC Icelandic (20871 + Euro symbol); IBM EBCDIC (Icelandic-Euro)
+    1200: 'utf-16-le', # Unicode UTF-16, little endian byte order (BMP of ISO 10646);
+    1201: 'utf-16-be', # Unicode UTF-16, big endian byte order;
+    1250: 'windows-1250', # ANSI Central European; Central European (Windows)
+    1251: 'windows-1251', # ANSI Cyrillic; Cyrillic (Windows)
+    1252: 'windows-1252', # ANSI Latin 1; Western European (Windows)
+    1253: 'windows-1253', # ANSI Greek; Greek (Windows)
+    1254: 'windows-1254', # ANSI Turkish; Turkish (Windows)
+    1255: 'windows-1255', # ANSI Hebrew; Hebrew (Windows)
+    1256: 'windows-1256', # ANSI Arabic; Arabic (Windows)
+    1257: 'windows-1257', # ANSI Baltic; Baltic (Windows)
+    1258: 'windows-1258', # ANSI/OEM Vietnamese; Vietnamese (Windows)
+    1361: 'Johab', # Korean (Johab)
+    10000: 'macintosh', # MAC Roman; Western European (Mac)
+    10001: 'x-mac-japanese', # Japanese (Mac)
+    # UNSUPPORTED.
+    10002: 'x-mac-chinesetrad', # MAC Traditional Chinese (Big5); Chinese Traditional (Mac)
+    10003: 'x-mac-korean', # Korean (Mac)
+    # UNSUPPORTED.
+    10004: 'x-mac-arabic', # Arabic (Mac)
+    # UNSUPPORTED.
+    10005: 'x-mac-hebrew', # Hebrew (Mac)
+    10006: 'x-mac-greek', # Greek (Mac)
+    10007: 'x-mac-cyrillic', # Cyrillic (Mac)
+    # UNSUPPORTED.
+    10008: 'x-mac-chinesesimp', # MAC Simplified Chinese (GB 2312); Chinese Simplified (Mac)
+    # UNSUPPORTED.
+    10010: 'x-mac-romanian', # Romanian (Mac)
+    # UNSUPPORTED.
+    10017: 'x-mac-ukrainian', # Ukrainian (Mac)
+    # UNSUPPORTED.
+    10021: 'x-mac-thai', # Thai (Mac)
+    10029: 'x-mac-ce', # MAC Latin 2; Central European (Mac)
+    10079: 'x-mac-icelandic', # Icelandic (Mac)
+    10081: 'x-mac-turkish', # Turkish (Mac)
+    # UNSUPPORTED.
+    10082: 'x-mac-croatian', # Croatian (Mac)
+    12000: 'utf-32', # Unicode UTF-32, little endian byte order
+    12001: 'utf-32BE', # Unicode UTF-32, big endian byte order
+    # UNSUPPORTED.
+    20000: 'x-Chinese_CNS', # CNS Taiwan; Chinese Traditional (CNS)
+    # UNSUPPORTED.
+    20001: 'x-cp20001', # TCA Taiwan
+    # UNSUPPORTED.
+    20002: 'x_Chinese-Eten', # Eten Taiwan; Chinese Traditional (Eten)
+    # UNSUPPORTED.
+    20003: 'x-cp20003', # IBM5550 Taiwan
+    # UNSUPPORTED.
+    20004: 'x-cp20004', # TeleText Taiwan
+    # UNSUPPORTED.
+    20005: 'x-cp20005', # Wang Taiwan
+    # UNSUPPORTED.
+    20105: 'x-IA5', # IA5 (IRV International Alphabet No. 5, 7-bit); Western European (IA5)
+    # UNSUPPORTED.
+    20106: 'x-IA5-German', # IA5 German (7-bit)
+    # UNSUPPORTED.
+    20107: 'x-IA5-Swedish', # IA5 Swedish (7-bit)
+    # UNSUPPORTED.
+    20108: 'x-IA5-Norwegian', # IA5 Norwegian (7-bit)
+    20127: 'us-ascii', # US-ASCII (7-bit)
+    # UNSUPPORTED.
+    20261: 'x-cp20261', # T.61
+    # UNSUPPORTED.
+    20269: 'x-cp20269', # ISO 6937 Non-Spacing Accent
+    20273: 'IBM273', # IBM EBCDIC Germany
+    20277: 'cp277', # IBM EBCDIC Denmark-Norway
+    20278: 'cp278', # IBM EBCDIC Finland-Sweden
+    20280: 'cp280', # IBM EBCDIC Italy
+    20284: 'cp284', # IBM EBCDIC Latin America-Spain
+    20285: 'cp285', # IBM EBCDIC United Kingdom
+    20290: 'cp290', # IBM EBCDIC Japanese Katakana Extended
+    20297: 'cp297', # IBM EBCDIC France
+    20420: 'cp420', # IBM EBCDIC Arabic
+    # UNSUPPORTED.
+    20423: 'IBM423', # IBM EBCDIC Greek
+    20424: 'IBM424', # IBM EBCDIC Hebrew
+    20833: 'cp833', # IBM EBCDIC Korean Extended
+    20838: 'cp838', # IBM EBCDIC Thai
+    20866: 'koi8-r', # Russian (KOI8-R); Cyrillic (KOI8-R)
+    20871: 'cp871', # IBM EBCDIC Icelandic
+    # UNSUPPORTED.
+    20880: 'IBM880', # IBM EBCDIC Cyrillic Russian
+    # UNSUPPORTED.
+    20905: 'IBM905', # IBM EBCDIC Turkish
+    # UNSUPPORTED.
+    20924: 'IBM00924', # IBM EBCDIC Latin 1/Open System (1047 + Euro symbol)
+    20932: 'EUC-JP', # Japanese (JIS 0208-1990 and 0212-1990)
+    # UNSUPPORTED.
+    20936: 'x-cp20936', # Simplified Chinese (GB2312); Chinese Simplified (GB2312-80)
+    # UNSUPPORTED.
+    20949: 'x-cp20949', # Korean Wansung
+    21025: 'cp1025', # IBM EBCDIC Cyrillic Serbian-Bulgarian
+    # UNSUPPORTED.
+    21027: '', # (deprecated)
+    21866: 'koi8-u', # Ukrainian (KOI8-U); Cyrillic (KOI8-U)
+    28591: 'iso-8859-1', # ISO 8859-1 Latin 1; Western European (ISO)
+    28592: 'iso-8859-2', # ISO 8859-2 Central European; Central European (ISO)
+    28593: 'iso-8859-3', # ISO 8859-3 Latin 3
+    28594: 'iso-8859-4', # ISO 8859-4 Baltic
+    28595: 'iso-8859-5', # ISO 8859-5 Cyrillic
+    28596: 'iso-8859-6', # ISO 8859-6 Arabic
+    28597: 'iso-8859-7', # ISO 8859-7 Greek
+    28598: 'iso-8859-8', # ISO 8859-8 Hebrew; Hebrew (ISO-Visual)
+    28599: 'iso-8859-9', # ISO 8859-9 Turkish
+    28603: 'iso-8859-13', # ISO 8859-13 Estonian
+    28605: 'iso-8859-15', # ISO 8859-15 Latin 9
+    # UNSUPPORTED.
+    29001: 'x-Europa', # Europa 3
+    # UNSUPPORTED.
+    38598: 'iso-8859-8-i', # ISO 8859-8 Hebrew; Hebrew (ISO-Logical)
+    50220: 'iso-2022-jp', # ISO 2022 Japanese with no halfwidth Katakana; Japanese (JIS)
+    50221: 'csISO2022JP', # ISO 2022 Japanese with halfwidth Katakana; Japanese (JIS-Allow 1 byte Kana)
+    50222: 'iso-2022-jp', # ISO 2022 Japanese JIS X 0201-1989; Japanese (JIS-Allow 1 byte Kana - SO/SI)
+    50225: 'iso-2022-kr', # ISO 2022 Korean
+    # UNSUPPORTED.
+    50227: 'x-cp50227', # ISO 2022 Simplified Chinese; Chinese Simplified (ISO 2022)
+    # UNSUPPORTED.
+    50229: '', # ISO 2022 Traditional Chinese
+    # UNSUPPORTED.
+    50930: '', # EBCDIC Japanese (Katakana) Extended
+    # UNSUPPORTED.
+    50931: '', # EBCDIC US-Canada and Japanese
+    # UNSUPPORTED.
+    50933: '', # EBCDIC Korean Extended and Korean
+    # UNSUPPORTED.
+    50935: '', # EBCDIC Simplified Chinese Extended and Simplified Chinese
+    # UNSUPPORTED.
+    50936: '', # EBCDIC Simplified Chinese
+    # UNSUPPORTED.
+    50937: '', # EBCDIC US-Canada and Traditional Chinese
+    # UNSUPPORTED.
+    50939: '', # EBCDIC Japanese (Latin) Extended and Japanese
+    51932: 'euc-jp', # EUC Japanese
+    51936: 'EUC-CN', # EUC Simplified Chinese; Chinese Simplified (EUC)
+    51949: 'euc-kr', # EUC Korean
+    # UNSUPPORTED.
+    51950: '', # EUC Traditional Chinese
+    52936: 'hz-gb-2312', # HZ-GB2312 Simplified Chinese; Chinese Simplified (HZ)
+    54936: 'GB18030', # Windows XP and later: GB18030 Simplified Chinese (4 byte); Chinese Simplified (GB18030)
+    # UNSUPPORTED.
+    57002: 'x-iscii-de', # ISCII Devanagari
+    # UNSUPPORTED.
+    57003: 'x-iscii-be', # ISCII Bangla
+    # UNSUPPORTED.
+    57004: 'x-iscii-ta', # ISCII Tamil
+    # UNSUPPORTED.
+    57005: 'x-iscii-te', # ISCII Telugu
+    # UNSUPPORTED.
+    57006: 'x-iscii-as', # ISCII Assamese
+    # UNSUPPORTED.
+    57007: 'x-iscii-or', # ISCII Odia
+    # UNSUPPORTED.
+    57008: 'x-iscii-ka', # ISCII Kannada
+    # UNSUPPORTED.
+    57009: 'x-iscii-ma', # ISCII Malayalam
+    # UNSUPPORTED.
+    57010: 'x-iscii-gu', # ISCII Gujarati
+    # UNSUPPORTED.
+    57011: 'x-iscii-pa', # ISCII Punjabi
+    65000: 'utf-7', # Unicode (UTF-7)
+    65001: 'utf-8', # Unicode (UTF-8)
+}
+
+# Register new encodings.
+
+def lookupCodePage(id_: int) -> str:
+    """
+    Converts an encoding id into it's name.
+
+    :raises UnknownCodepageError: The code page was not recognized.
+    :raises UnsupportedEncodingError: The code page was recognized, but no
+        encoding exists in the environment with support for it.
+    """
+    if id_ in _CODE_PAGES:
+        if (page := _CODE_PAGES[id_]):
+            return page
+        else:
+            raise UnsupportedEncodingError(f'Code page {id_} is unsupported.')
+    else:
+        raise UnknownCodepageError(f'Unknown code page {id_}.')
+
+def _lookupEncoding(name):
+    return _codecsInfo.get(name)
+
+from .utils import createSBEncoding as _sb, createVBEncoding as _vb
+from ._dt import (
+        _mac_ce, _mac_cyrillic, _mac_greek, _mac_iceland, _mac_turkish,
+        _win874_dec, _win950_dec
+    )
+
+_codecsInfo = {
+    'x_mac_ce': _sb('x-mac-ce', _mac_ce.decodingTable),
+    'x_mac_cyrillic': _sb('x-mac-cyrillic', _mac_cyrillic.decodingTable),
+    'x_mac_greek': _sb('x-mac-greek', _mac_greek.decodingTable),
+    'x_mac_icelandic': _sb('x-mac-icelandic', _mac_iceland.decodingTable),
+    'x_mac_turkish': _sb('x-mac-turkish', _mac_turkish.decodingTable),
+    'windows_950': _vb('windows-950', _win950_dec.decodingTable),
+    'windows_874': _sb('windows-874', _win874_dec.decodingTable),
+}
+
+codecs.register(_lookupEncoding)

extract_msg/encoding/_dt/__init__.py

@@ -0,0 +1,4 @@
+"""
+Decoding tables for the various encodings implemented. This allows the encoding
+definitions to be neater.
+"""

extract_msg/encoding/_dt/_mac_ce.py

@@ -0,0 +1,8 @@
+# Based on https://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/MAC/LATIN2.TXT
+
+__all__ = [
+    'decodingTable',
+]
+
+
+decodingTable={0:'\x00',1:'\x01',2:'\x02',3:'\x03',4:'\x04',5:'\x05',6:'\x06',7:'\x07',8:'\x08',9:'\t',10:'\n',11:'\x0b',12:'\x0c',13:'\r',14:'\x0e',15:'\x0f',16:'\x10',17:'\x11',18:'\x12',19:'\x13',20:'\x14',21:'\x15',22:'\x16',23:'\x17',24:'\x18',25:'\x19',26:'\x1a',27:'\x1b',28:'\x1c',29:'\x1d',30:'\x1e',31:'\x1f',32:' ',33:'!',34:'"',35:'#',36:'$',37:'%',38:'&',39:"'",40:'(',41:')',42:'*',43:'+',44:',',45:'-',46:'.',47:'/',48:'0',49:'1',50:'2',51:'3',52:'4',53:'5',54:'6',55:'7',56:'8',57:'9',58:':',59:';',60:'<',61:'=',62:'>',63:'?',64:'@',65:'A',66:'B',67:'C',68:'D',69:'E',70:'F',71:'G',72:'H',73:'I',74:'J',75:'K',76:'L',77:'M',78:'N',79:'O',80:'P',81:'Q',82:'R',83:'S',84:'T',85:'U',86:'V',87:'W',88:'X',89:'Y',90:'Z',91:'[',92:'\\',93:']',94:'^',95:'_',96:'`',97:'a',98:'b',99:'c',100:'d',101:'e',102:'f',103:'g',104:'h',105:'i',106:'j',107:'k',108:'l',109:'m',110:'n',111:'o',112:'p',113:'q',114:'r',115:'s',116:'t',117:'u',118:'v',119:'w',120:'x',121:'y',122:'z',123:'{',124:'|',125:'}',126:'~',127:'\x7f',128:'\xC4',129:'\u0100',130:'\u0101',131:'\xC9',132:'\u0104',133:'\xD6',134:'\xDC',135:'\xE1',136:'\u0105',137:'\u010C',138:'\xE4',139:'\u010D',140:'\u0106',141:'\u0107',142:'\xE9',143:'\u0179',144:'\u017A',145:'\u010E',146:'\xED',147:'\u010F',148:'\u0112',149:'\u0113',150:'\u0116',151:'\xF3',152:'\u0117',153:'\xF4',154:'\xF6',155:'\xF5',156:'\xFA',157:'\u011A',158:'\u011B',159:'\xFC',160:'\u2020',161:'\xB0',162:'\u0118',163:'\xA3',164:'\xA7',165:'\u2022',166:'\xB6',167:'\xDF',168:'\xAE',169:'\xA9',170:'\u2122',171:'\u0119',172:'\xA8',173:'\u2260',174:'\u0123',175:'\u012E',176:'\u012F',177:'\u012A',178:'\u2264',179:'\u2265',180:'\u012B',181:'\u0136',182:'\u2202',183:'\u2211',184:'\u0142',185:'\u013B',186:'\u013C',187:'\u013D',188:'\u013E',189:'\u0139',190:'\u013A',191:'\u0145',192:'\u0146',193:'\u0143',194:'\xAC',195:'\u221A',196:'\u0144',197:'\u0147',198:'\u2206',199:'\xAB',200:'\xBB',201:'\u2026',202:'\xA0',203:'\u0148',204:'\u0150',205:'\xD5',206:'\u0151',207:'\u014C',208:'\u2013',209:'\u2014',210:'\u201C',211:'\u201D',212:'\u2018',213:'\u2019',214:'\xF7',215:'\u25CA',216:'\u014D',217:'\u0154',218:'\u0155',219:'\u0158',220:'\u2039',221:'\u203A',222:'\u0159',223:'\u0156',224:'\u0157',225:'\u0160',226:'\u201A',227:'\u201E',228:'\u0161',229:'\u015A',230:'\u015B',231:'\xC1',232:'\u0164',233:'\u0165',234:'\xCD',235:'\u017D',236:'\u017E',237:'\u016A',238:'\xD3',239:'\xD4',240:'\u016B',241:'\u016E',242:'\xDA',243:'\u016F',244:'\u0170',245:'\u0171',246:'\u0172',247:'\u0173',248:'\xDD',249:'\xFD',250:'\u0137',251:'\u017B',252:'\u0141',253:'\u017C',254:'\u0122',255:'\u02C7'}

extract_msg/encoding/_dt/_mac_cyrillic.py

@@ -0,0 +1,8 @@
+# Based on https://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/MAC/CYRILLIC.TXT
+
+__all__ = [
+    'decodingTable',
+]
+
+
+decodingTable={0:'\x00',1:'\x01',2:'\x02',3:'\x03',4:'\x04',5:'\x05',6:'\x06',7:'\x07',8:'\x08',9:'\t',10:'\n',11:'\x0b',12:'\x0c',13:'\r',14:'\x0e',15:'\x0f',16:'\x10',17:'\x11',18:'\x12',19:'\x13',20:'\x14',21:'\x15',22:'\x16',23:'\x17',24:'\x18',25:'\x19',26:'\x1a',27:'\x1b',28:'\x1c',29:'\x1d',30:'\x1e',31:'\x1f',32:' ',33:'!',34:'"',35:'#',36:'$',37:'%',38:'&',39:"'",40:'(',41:')',42:'*',43:'+',44:',',45:'-',46:'.',47:'/',48:'0',49:'1',50:'2',51:'3',52:'4',53:'5',54:'6',55:'7',56:'8',57:'9',58:':',59:';',60:'<',61:'=',62:'>',63:'?',64:'@',65:'A',66:'B',67:'C',68:'D',69:'E',70:'F',71:'G',72:'H',73:'I',74:'J',75:'K',76:'L',77:'M',78:'N',79:'O',80:'P',81:'Q',82:'R',83:'S',84:'T',85:'U',86:'V',87:'W',88:'X',89:'Y',90:'Z',91:'[',92:'\\',93:']',94:'^',95:'_',96:'`',97:'a',98:'b',99:'c',100:'d',101:'e',102:'f',103:'g',104:'h',105:'i',106:'j',107:'k',108:'l',109:'m',110:'n',111:'o',112:'p',113:'q',114:'r',115:'s',116:'t',117:'u',118:'v',119:'w',120:'x',121:'y',122:'z',123:'{',124:'|',125:'}',126:'~',127:'\x7f',128:'\u0410',129:'\u0411',130:'\u0412',131:'\u0413',132:'\u0414',133:'\u0415',134:'\u0416',135:'\u0417',136:'\u0418',137:'\u0419',138:'\u041A',139:'\u041B',140:'\u041C',141:'\u041D',142:'\u041E',143:'\u041F',144:'\u0420',145:'\u0421',146:'\u0422',147:'\u0423',148:'\u0424',149:'\u0425',150:'\u0426',151:'\u0427',152:'\u0428',153:'\u0429',154:'\u042A',155:'\u042B',156:'\u042C',157:'\u042D',158:'\u042E',159:'\u042F',160:'\u2020',161:'\xB0',162:'\xA2',163:'\xA3',164:'\xA7',165:'\u2022',166:'\xB6',167:'\u0406',168:'\xAE',169:'\xA9',170:'\u2122',171:'\u0402',172:'\u0452',173:'\u2260',174:'\u0403',175:'\u0453',176:'\u221E',177:'\xB1',178:'\u2264',179:'\u2265',180:'\u0456',181:'\xB5',182:'\u2202',183:'\u0408',184:'\u0404',185:'\u0454',186:'\u0407',187:'\u0457',188:'\u0409',189:'\u0459',190:'\u040A',191:'\u045A',192:'\u0458',193:'\u0405',194:'\xAC',195:'\u221A',196:'\u0192',197:'\u2248',198:'\u2206',199:'\xAB',200:'\xBB',201:'\u2026',202:'\xA0',203:'\u040B',204:'\u045B',205:'\u040C',206:'\u045C',207:'\u0455',208:'\u2013',209:'\u2014',210:'\u201C',211:'\u201D',212:'\u2018',213:'\u2019',214:'\xF7',215:'\u201E',216:'\u040E',217:'\u045E',218:'\u040F',219:'\u045F',220:'\u2116',221:'\u0401',222:'\u0451',223:'\u044F',224:'\u0430',225:'\u0431',226:'\u0432',227:'\u0433',228:'\u0434',229:'\u0435',230:'\u0436',231:'\u0437',232:'\u0438',233:'\u0439',234:'\u043A',235:'\u043B',236:'\u043C',237:'\u043D',238:'\u043E',239:'\u043F',240:'\u0440',241:'\u0441',242:'\u0442',243:'\u0443',244:'\u0444',245:'\u0445',246:'\u0446',247:'\u0447',248:'\u0448',249:'\u0449',250:'\u044A',251:'\u044B',252:'\u044C',253:'\u044D',254:'\u044E',255:'\xA4'}

extract_msg/encoding/_dt/_mac_greek.py

@@ -0,0 +1,8 @@
+# Based on https://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/MAC/GREEK.TXT
+
+__all__ = [
+    'decodingTable',
+]
+
+
+decodingTable={0:'\x00',1:'\x01',2:'\x02',3:'\x03',4:'\x04',5:'\x05',6:'\x06',7:'\x07',8:'\x08',9:'\t',10:'\n',11:'\x0b',12:'\x0c',13:'\r',14:'\x0e',15:'\x0f',16:'\x10',17:'\x11',18:'\x12',19:'\x13',20:'\x14',21:'\x15',22:'\x16',23:'\x17',24:'\x18',25:'\x19',26:'\x1a',27:'\x1b',28:'\x1c',29:'\x1d',30:'\x1e',31:'\x1f',32:' ',33:'!',34:'"',35:'#',36:'$',37:'%',38:'&',39:"'",40:'(',41:')',42:'*',43:'+',44:',',45:'-',46:'.',47:'/',48:'0',49:'1',50:'2',51:'3',52:'4',53:'5',54:'6',55:'7',56:'8',57:'9',58:':',59:';',60:'<',61:'=',62:'>',63:'?',64:'@',65:'A',66:'B',67:'C',68:'D',69:'E',70:'F',71:'G',72:'H',73:'I',74:'J',75:'K',76:'L',77:'M',78:'N',79:'O',80:'P',81:'Q',82:'R',83:'S',84:'T',85:'U',86:'V',87:'W',88:'X',89:'Y',90:'Z',91:'[',92:'\\',93:']',94:'^',95:'_',96:'`',97:'a',98:'b',99:'c',100:'d',101:'e',102:'f',103:'g',104:'h',105:'i',106:'j',107:'k',108:'l',109:'m',110:'n',111:'o',112:'p',113:'q',114:'r',115:'s',116:'t',117:'u',118:'v',119:'w',120:'x',121:'y',122:'z',123:'{',124:'|',125:'}',126:'~',127:'\x7f',128:'\xC4',129:'\xB9',130:'\xB2',131:'\xC9',132:'\xB3',133:'\xD6',134:'\xDC',135:'\u0385',136:'\xE0',137:'\xE2',138:'\xE4',139:'\u0384',140:'\xA8',141:'\xE7',142:'\xE9',143:'\xE8',144:'\xEA',145:'\xEB',146:'\xA3',147:'\u2122',148:'\xEE',149:'\xEF',150:'\u2022',151:'\xBD',152:'\u2030',153:'\xF4',154:'\xF6',155:'\xA6',156:'\xAD',157:'\xF9',158:'\xFB',159:'\xFC',160:'\u2020',161:'\u0393',162:'\u0394',163:'\u0398',164:'\u039B',165:'\u039E',166:'\u03A0',167:'\xDF',168:'\xAE',169:'\xA9',170:'\u03A3',171:'\u03AA',172:'\xA7',173:'\u2260',174:'\xB0',175:'\u0387',176:'\u0391',177:'\xB1',178:'\u2264',179:'\u2265',180:'\xA5',181:'\u0392',182:'\u0395',183:'\u0396',184:'\u0397',185:'\u0399',186:'\u039A',187:'\u039C',188:'\u03A6',189:'\u03AB',190:'\u03A8',191:'\u03A9',192:'\u03AC',193:'\u039D',194:'\xAC',195:'\u039F',196:'\u03A1',197:'\u2248',198:'\u03A4',199:'\xAB',200:'\xBB',201:'\u2026',202:'\xA0',203:'\u03A5',204:'\u03A7',205:'\u0386',206:'\u0388',207:'\u0153',208:'\u2013',209:'\u2015',210:'\u201C',211:'\u201D',212:'\u2018',213:'\u2019',214:'\xF7',215:'\u0389',216:'\u038A',217:'\u038C',218:'\u038E',219:'\u03AD',220:'\u03AE',221:'\u03AF',222:'\u03CC',223:'\u038F',224:'\u03CD',225:'\u03B1',226:'\u03B2',227:'\u03C8',228:'\u03B4',229:'\u03B5',230:'\u03C6',231:'\u03B3',232:'\u03B7',233:'\u03B9',234:'\u03BE',235:'\u03BA',236:'\u03BB',237:'\u03BC',238:'\u03BD',239:'\u03BF',240:'\u03C0',241:'\u03CE',242:'\u03C1',243:'\u03C3',244:'\u03C4',245:'\u03B8',246:'\u03C9',247:'\u03C2',248:'\u03C7',249:'\u03C5',250:'\u03B6',251:'\u03CA',252:'\u03CB',253:'\u0390',254:'\u03B0'}

extract_msg/encoding/_dt/_mac_iceland.py

@@ -0,0 +1,8 @@
+# Based on https://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/MAC/ICELAND.TXT
+
+__all__ = [
+    'decodingTable',
+]
+
+
+decodingTable={0:'\x00',1:'\x01',2:'\x02',3:'\x03',4:'\x04',5:'\x05',6:'\x06',7:'\x07',8:'\x08',9:'\t',10:'\n',11:'\x0b',12:'\x0c',13:'\r',14:'\x0e',15:'\x0f',16:'\x10',17:'\x11',18:'\x12',19:'\x13',20:'\x14',21:'\x15',22:'\x16',23:'\x17',24:'\x18',25:'\x19',26:'\x1a',27:'\x1b',28:'\x1c',29:'\x1d',30:'\x1e',31:'\x1f',32:' ',33:'!',34:'"',35:'#',36:'$',37:'%',38:'&',39:"'",40:'(',41:')',42:'*',43:'+',44:',',45:'-',46:'.',47:'/',48:'0',49:'1',50:'2',51:'3',52:'4',53:'5',54:'6',55:'7',56:'8',57:'9',58:':',59:';',60:'<',61:'=',62:'>',63:'?',64:'@',65:'A',66:'B',67:'C',68:'D',69:'E',70:'F',71:'G',72:'H',73:'I',74:'J',75:'K',76:'L',77:'M',78:'N',79:'O',80:'P',81:'Q',82:'R',83:'S',84:'T',85:'U',86:'V',87:'W',88:'X',89:'Y',90:'Z',91:'[',92:'\\',93:']',94:'^',95:'_',96:'`',97:'a',98:'b',99:'c',100:'d',101:'e',102:'f',103:'g',104:'h',105:'i',106:'j',107:'k',108:'l',109:'m',110:'n',111:'o',112:'p',113:'q',114:'r',115:'s',116:'t',117:'u',118:'v',119:'w',120:'x',121:'y',122:'z',123:'{',124:'|',125:'}',126:'~',127:'\x7f',128:'\xC4',129:'\xC5',130:'\xC7',131:'\xC9',132:'\xD1',133:'\xD6',134:'\xDC',135:'\xE1',136:'\xE0',137:'\xE2',138:'\xE4',139:'\xE3',140:'\xE5',141:'\xE7',142:'\xE9',143:'\xE8',144:'\xEA',145:'\xEB',146:'\xED',147:'\xEC',148:'\xEE',149:'\xEF',150:'\xF1',151:'\xF3',152:'\xF2',153:'\xF4',154:'\xF6',155:'\xF5',156:'\xFA',157:'\xF9',158:'\xFB',159:'\xFC',160:'\xDD',161:'\xB0',162:'\xA2',163:'\xA3',164:'\xA7',165:'\u2022',166:'\xB6',167:'\xDF',168:'\xAE',169:'\xA9',170:'\u2122',171:'\xB4',172:'\xA8',173:'\u2260',174:'\xC6',175:'\xD8',176:'\u221E',177:'\xB1',178:'\u2264',179:'\u2265',180:'\xA5',181:'\xB5',182:'\u2202',183:'\u2211',184:'\u220F',185:'\u03C0',186:'\u222B',187:'\xAA',188:'\xBA',189:'\u2126',190:'\xE6',191:'\xF8',192:'\xBF',193:'\xA1',194:'\xAC',195:'\u221A',196:'\u0192',197:'\u2248',198:'\u2206',199:'\xAB',200:'\xBB',201:'\u2026',202:'\xA0',203:'\xC0',204:'\xC3',205:'\xD5',206:'\u0152',207:'\u0153',208:'\u2013',209:'\u2014',210:'\u201C',211:'\u201D',212:'\u2018',213:'\u2019',214:'\xF7',215:'\u25CA',216:'\xFF',217:'\u0178',218:'\u2044',219:'\xA4',220:'\xD0',221:'\xF0',222:'\xDE',223:'\xFE',224:'\xFD',225:'\xB7',226:'\u201A',227:'\u201E',228:'\u2030',229:'\xC2',230:'\xCA',231:'\xC1',232:'\xCB',233:'\xC8',234:'\xCD',235:'\xCE',236:'\xCF',237:'\xCC',238:'\xD3',239:'\xD4',241:'\xD2',242:'\xDA',243:'\xDB',244:'\xD9',245:'\u0131',246:'\u02C6',247:'\u02DC',248:'\xAF',249:'\u02D8',250:'\u02D9',251:'\u02DA',252:'\xB8',253:'\u02DD',254:'\u02DB',255:'\u02C7'}

extract_msg/encoding/_dt/_mac_turkish.py

@@ -0,0 +1,8 @@
+# Based on https://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/MAC/TURKISH.TXT
+
+__all__ = [
+    'decodingTable',
+]
+
+
+decodingTable={0:'\x00',1:'\x01',2:'\x02',3:'\x03',4:'\x04',5:'\x05',6:'\x06',7:'\x07',8:'\x08',9:'\t',10:'\n',11:'\x0b',12:'\x0c',13:'\r',14:'\x0e',15:'\x0f',16:'\x10',17:'\x11',18:'\x12',19:'\x13',20:'\x14',21:'\x15',22:'\x16',23:'\x17',24:'\x18',25:'\x19',26:'\x1a',27:'\x1b',28:'\x1c',29:'\x1d',30:'\x1e',31:'\x1f',32:' ',33:'!',34:'"',35:'#',36:'$',37:'%',38:'&',39:"'",40:'(',41:')',42:'*',43:'+',44:',',45:'-',46:'.',47:'/',48:'0',49:'1',50:'2',51:'3',52:'4',53:'5',54:'6',55:'7',56:'8',57:'9',58:':',59:';',60:'<',61:'=',62:'>',63:'?',64:'@',65:'A',66:'B',67:'C',68:'D',69:'E',70:'F',71:'G',72:'H',73:'I',74:'J',75:'K',76:'L',77:'M',78:'N',79:'O',80:'P',81:'Q',82:'R',83:'S',84:'T',85:'U',86:'V',87:'W',88:'X',89:'Y',90:'Z',91:'[',92:'\\',93:']',94:'^',95:'_',96:'`',97:'a',98:'b',99:'c',100:'d',101:'e',102:'f',103:'g',104:'h',105:'i',106:'j',107:'k',108:'l',109:'m',110:'n',111:'o',112:'p',113:'q',114:'r',115:'s',116:'t',117:'u',118:'v',119:'w',120:'x',121:'y',122:'z',123:'{',124:'|',125:'}',126:'~',127:'\x7f',128:'\xC4',129:'\xC5',130:'\xC7',131:'\xC9',132:'\xD1',133:'\xD6',134:'\xDC',135:'\xE1',136:'\xE0',137:'\xE2',138:'\xE4',139:'\xE3',140:'\xE5',141:'\xE7',142:'\xE9',143:'\xE8',144:'\xEA',145:'\xEB',146:'\xED',147:'\xEC',148:'\xEE',149:'\xEF',150:'\xF1',151:'\xF3',152:'\xF2',153:'\xF4',154:'\xF6',155:'\xF5',156:'\xFA',157:'\xF9',158:'\xFB',159:'\xFC',160:'\u2020',161:'\xB0',162:'\xA2',163:'\xA3',164:'\xA7',165:'\u2022',166:'\xB6',167:'\xDF',168:'\xAE',169:'\xA9',170:'\u2122',171:'\xB4',172:'\xA8',173:'\u2260',174:'\xC6',175:'\xD8',176:'\u221E',177:'\xB1',178:'\u2264',179:'\u2265',180:'\xA5',181:'\xB5',182:'\u2202',183:'\u2211',184:'\u220F',185:'\u03C0',186:'\u222B',187:'\xAA',188:'\xBA',189:'\u2126',190:'\xE6',191:'\xF8',192:'\xBF',193:'\xA1',194:'\xAC',195:'\u221A',196:'\u0192',197:'\u2248',198:'\u2206',199:'\xAB',200:'\xBB',201:'\u2026',202:'\xA0',203:'\xC0',204:'\xC3',205:'\xD5',206:'\u0152',207:'\u0153',208:'\u2013',209:'\u2014',210:'\u201C',211:'\u201D',212:'\u2018',213:'\u2019',214:'\xF7',215:'\u25CA',216:'\xFF',217:'\u0178',218:'\u011E',219:'\u011F',220:'\u0130',221:'\u0131',222:'\u015E',223:'\u015F',224:'\u2021',225:'\xB7',226:'\u201A',227:'\u201E',228:'\u2030',229:'\xC2',230:'\xCA',231:'\xC1',232:'\xCB',233:'\xC8',234:'\xCD',235:'\xCE',236:'\xCF',237:'\xCC',238:'\xD3',239:'\xD4',241:'\xD2',242:'\xDA',243:'\xDB',244:'\xD9',246:'\u02C6',247:'\u02DC',248:'\xAF',249:'\u02D8',250:'\u02D9',251:'\u02DA',252:'\xB8',253:'\u02DD',254:'\u02DB',255:'\u02C7'}

extract_msg/encoding/_dt/_win874_dec.py

@@ -0,0 +1,8 @@
+# Based on https://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP874.TXT
+
+__all__ = [
+    'decodingTable',
+]
+
+
+decodingTable={0:'\x00',1:'\x01',2:'\x02',3:'\x03',4:'\x04',5:'\x05',6:'\x06',7:'\x07',8:'\x08',9:'\t',10:'\n',11:'\x0B',12:'\x0C',13:'\r',14:'\x0E',15:'\x0F',16:'\x10',17:'\x11',18:'\x12',19:'\x13',20:'\x14',21:'\x15',22:'\x16',23:'\x17',24:'\x18',25:'\x19',26:'\x1A',27:'\x1B',28:'\x1C',29:'\x1D',30:'\x1E',31:'\x1F',32:' ',33:'!',34:'"',35:'#',36:'$',37:'%',38:'&',39:"'",40:'(',41:')',42:'*',43:'+',44:',',45:'-',46:'.',47:'/',48:'0',49:'1',50:'2',51:'3',52:'4',53:'5',54:'6',55:'7',56:'8',57:'9',58:':',59:';',60:'<',61:'=',62:'>',63:'?',64:'@',65:'A',66:'B',67:'C',68:'D',69:'E',70:'F',71:'G',72:'H',73:'I',74:'J',75:'K',76:'L',77:'M',78:'N',79:'O',80:'P',81:'Q',82:'R',83:'S',84:'T',85:'U',86:'V',87:'W',88:'X',89:'Y',90:'Z',91:'[',92:'\\',93:']',94:'^',95:'_',96:'`',97:'a',98:'b',99:'c',100:'d',101:'e',102:'f',103:'g',104:'h',105:'i',106:'j',107:'k',108:'l',109:'m',110:'n',111:'o',112:'p',113:'q',114:'r',115:'s',116:'t',117:'u',118:'v',119:'w',120:'x',121:'y',122:'z',123:'{',124:'|',125:'}',126:'~',127:'\x7F',128:'\x80',129:'\u20AC',133:'\u2026',145:'\u2018',146:'\u2019',147:'\u201C',148:'\u201D',149:'\u2022',150:'\u2013',151:'\u2014',160:'\xA0',161:'\u0E01',162:'\u0E02',163:'\u0E03',164:'\u0E04',165:'\u0E05',166:'\u0E06',167:'\u0E07',168:'\u0E08',169:'\u0E09',170:'\u0E0A',171:'\u0E0B',172:'\u0E0C',173:'\u0E0D',174:'\u0E0E',175:'\u0E0F',176:'\u0E10',177:'\u0E11',178:'\u0E12',179:'\u0E13',180:'\u0E14',181:'\u0E15',182:'\u0E16',183:'\u0E17',184:'\u0E18',185:'\u0E19',186:'\u0E1A',187:'\u0E1B',188:'\u0E1C',189:'\u0E1D',190:'\u0E1E',191:'\u0E1F',192:'\u0E20',193:'\u0E21',194:'\u0E22',195:'\u0E23',196:'\u0E24',197:'\u0E25',198:'\u0E26',199:'\u0E27',200:'\u0E28',201:'\u0E29',202:'\u0E2A',203:'\u0E2B',204:'\u0E2C',205:'\u0E2D',206:'\u0E2E',207:'\u0E2F',208:'\u0E30',209:'\u0E31',210:'\u0E32',211:'\u0E33',212:'\u0E34',213:'\u0E35',214:'\u0E36',215:'\u0E37',216:'\u0E38',217:'\u0E39',218:'\u0E3A',224:'\u0E3F',225:'\u0E40',226:'\u0E41',227:'\u0E42',228:'\u0E43',229:'\u0E44',230:'\u0E45',231:'\u0E46',232:'\u0E47',233:'\u0E48',234:'\u0E49',235:'\u0E4A',236:'\u0E4B',237:'\u0E4C',238:'\u0E4D',239:'\u0E4E',240:'\u0E4F',241:'\u0E50',242:'\u0E51',243:'\u0E52',244:'\u0E53',245:'\u0E54',246:'\u0E55',247:'\u0E56',248:'\u0E57',249:'\u0E58',250:'\u0E59',251:'\u0E5A',252:'\u0E5B'}