Added a few more encodings

Author: TheElementalOfDestruction

CHANGELOG.md

@@ -6,7 +6,11 @@
     * Added infrastructure to make it easy to add variable-byte (up to two bytes) encodings and single-byte encodings.
     * Added the following encodings:
         * windows-874
+        * x-mac-ce
         * x-mac-cyrillic
+        * x-mac-greek
+        * x-mac-icelandic
+        * x-mac-turkish
 * Fixed an issue in the save functions that left the possibility for the zip files to not end up closing if the save function created it and then had an exception.
 * Added new property `AttachmentBase.clsid` which returns the listed CLSID value of the data stream/storage of the attachment.
 * Changed internal behavior of `MSGFile.attachments`. This should not cause any noticeable changes to the output.

extract_msg/encoding/__init__.py

@@ -96,7 +96,6 @@
     10004: 'x-mac-arabic', # Arabic (Mac)
     # UNSUPPORTED.
     10005: 'x-mac-hebrew', # Hebrew (Mac)
-    # UNSUPPORTED.
     10006: 'x-mac-greek', # Greek (Mac)
     10007: 'x-mac-cyrillic', # Cyrillic (Mac)
     # UNSUPPORTED.
@@ -107,11 +106,8 @@
     10017: 'x-mac-ukrainian', # Ukrainian (Mac)
     # UNSUPPORTED.
     10021: 'x-mac-thai', # Thai (Mac)
-    # UNSUPPORTED.
     10029: 'x-mac-ce', # MAC Latin 2; Central European (Mac)
-    # UNSUPPORTED.
     10079: 'x-mac-icelandic', # Icelandic (Mac)
-    # UNSUPPORTED.
     10081: 'x-mac-turkish', # Turkish (Mac)
     # UNSUPPORTED.
     10082: 'x-mac-croatian', # Croatian (Mac)
@@ -264,11 +260,16 @@ def _lookupEncoding(name):
 
 from .utils import createSBEncoding as _sb, createVBEncoding as _vb
 from ._dt import (
-        _mac_cyrillic, _win874_dec, _win950_dec
+        _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),
 }

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_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'}