xsvalUtils.py

Go to the documentation of this file.

#
# minixsv, Release 0.9.0
# file: xsvalUtils.py
#
# utility functions for XML schema validation
#
# history:
# 2008-02-13 rl   created
#
# Copyright (c) 2004-2008 by Roland Leuthe.  All rights reserved.
#
# --------------------------------------------------------------------
# The minixsv XML schema validator is
#
# Copyright (c) 2004-2008 by Roland Leuthe
#
# By obtaining, using, and/or copying this software and/or its
# associated documentation, you agree that you have read, understood,
# and will comply with the following terms and conditions:
#
# Permission to use, copy, modify, and distribute this software and
# its associated documentation for any purpose and without fee is
# hereby granted, provided that the above copyright notice appears in
# all copies, and that both that copyright notice and this permission
# notice appear in supporting documentation, and that the name of
# the author not be used in advertising or publicity
# pertaining to distribution of the software without specific, written
# prior permission.
#
# THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD
# TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANT-
# ABILITY AND FITNESS.  IN NO EVENT SHALL THE AUTHOR
# BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY
# DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
# WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
# ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
# OF THIS SOFTWARE.
# --------------------------------------------------------------------

import string
import re

creWithinSet = re.compile(r"(^|.*[^\\])(?P<obr>\[)[^\]]*\Z")

creMultiCharEscP = re.compile(r"(?P<pbs>\\*)(?P<escSeq>(?P<inv>[\^])?\\(?P<pP>[pP]){(?P<id>[^}]*)})")

substMultiCharEscPDict = {
     r"Cc" : ur"\x00-\x1f\x7f-\x9f",
     r"Cf" : ur"\u06dd\u070f\u180e\u200c-\u200f\u202a-\u202e\u2060-\u2063\u206a-\u206f\ufeff\ufff9-\ufffb",
     r"Co" : ur"\ue000-\uf8ff",
     r"Cn" : ur"\ufdd0-\ufdef\ufffe\uffff",
     r"Cs" : ur"\ud800-\udfff",
     r"C" : ur"\x00-\x1f\x7f-\x9f\u06dd\u070f\u180e\u200c-\u200f\u202a-\u202e\u2060-\u2063\u206a-\u206f\ud800-\uf8ff\ufeff\ufff9-\ufffb",
                                    
     r"Ll" : ur"a-z\xaa\xb5\xba\xdf-\xf6\xf8-\xff\u0101\u0103\u0105\u0107\u0109\u010b\u010d\u010f\u0111\u0113\u0115\u0117\u0119\u011b\u011d\u011f\u0121\u0123\u0125\u0127\u0129\u012b\u012d\u012f\u0131\u0133\u0135\u0137-\u0138\u013a\u013c\u013e\u0140\u0142\u0144\u0146\u0148-\u0149\u014b\u014d\u014f\u0151\u0153\u0155\u0157\u0159\u015b\u015d\u015f\u0161\u0163\u0165\u0167\u0169\u016b\u016d\u016f\u0171\u0173\u0175\u0177\u017a\u017c\u017e-\u0180\u0183\u0185\u0188\u018c-\u018d\u0192\u0195\u0199-\u019b\u019e\u01a1\u01a3\u01a5\u01a8\u01aa-\u01ab\u01ad\u01b0\u01b4\u01b6\u01b9-\u01ba\u01bd-\u01bf\u01c6\u01c9\u01cc\u01ce\u01d0\u01d2\u01d4\u01d6\u01d8\u01da\u01dc-\u01dd\u01df\u01e1\u01e3\u01e5\u01e7\u01e9\u01eb\u01ed\u01ef-\u01f0\u01f3\u01f5\u01f9\u01fb\u01fd\u01ff\u0201\u0203\u0205\u0207\u0209\u020b\u020d\u020f\u0211\u0213\u0215\u0217\u0219\u021b\u021d\u021f\u0223\u0225\u0227\u0229\u022b\u022d\u022f\u0231\u0233\u0250-\u02ad\u0390\u03ac-\u03ce\u03d0-\u03d1\u03d5-\u03d7\u03d9\u03db\u03dd\u03df\u03e1\u03e3\u03e5\u03e7\u03e9\u03eb\u03ed\u03ef-\u03f3\u03f5\u0430-\u045f\u0461\u0463\u0465\u0467\u0469\u046b\u046d\u046f\u0471\u0473\u0475\u0477\u0479\u047b\u047d\u047f\u0481\u048b\u048d\u048f\u0491\u0493\u0495\u0497\u0499\u049b\u049d\u049f\u04a1\u04a3\u04a5\u04a7\u04a9\u04ab\u04ad\u04af\u04b1\u04b3\u04b5\u04b7\u04b9\u04bb\u04bd\u04bf\u04c2\u04c4\u04c6\u04c8\u04ca\u04cc\u04ce\u04d1\u04d3\u04d5\u04d7\u04d9\u04db\u04dd\u04df\u04e1\u04e3\u04e5\u04e7\u04e9\u04eb\u04ed\u04ef\u04f1\u04f3\u04f5\u04f9\u0501\u0503\u0505\u0507\u0509\u050b\u050d\u050f\u0561-\u0587\u1e01\u1e03\u1e05\u1e07\u1e09\u1e0b\u1e0d\u1e0f\u1e11\u1e13\u1e15\u1e17\u1e19\u1e1b\u1e1d\u1e1f\u1e21\u1e23\u1e25\u1e27\u1e29\u1e2b\u1e2d\u1e2f\u1e31\u1e33\u1e35\u1e37\u1e39\u1e3b\u1e3d\u1e3f\u1e41\u1e43\u1e45\u1e47\u1e49\u1e4b\u1e4d\u1e4f\u1e51\u1e53\u1e55\u1e57\u1e59\u1e5b\u1e5d\u1e5f\u1e61\u1e63\u1e65\u1e67\u1e69\u1e6b\u1e6d\u1e6f\u1e71\u1e73\u1e75\u1e77\u1e79\u1e7b\u1e7d\u1e7f\u1e81\u1e83\u1e85\u1e87\u1e89\u1e8b\u1e8d\u1e8f\u1e91\u1e93\u1e95-\u1e9b\u1ea1\u1ea3\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u1eb9\u1ebb\u1ebd\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u1ec9\u1ecb\u1ecd\u1ecf\u1ed1\u1ed3\u1ed5\u1ed7\u1ed9\u1edb\u1edd\u1edf\u1ee1\u1ee3\u1ee5\u1ee7\u1ee9\u1eeb\u1eed\u1eef\u1ef1\u1ef3\u1ef5\u1ef7\u1ef9\u1f00-\u1f07\u1f10-\u1f15\u1f20-\u1f27\u1f30-\u1f37\u1f40-\u1f45\u1f50-\u1f57\u1f60-\u1f67\u1f70-\u1f7d\u1f80-\u1f87\u1f90-\u1f97\u1fa0-\u1fa7\u1fb0-\u1fb4\u1fb6-\u1fb7\u1fbe\u1fc2-\u1fc4\u1fc6-\u1fc7\u1fd0-\u1fd3\u1fd6-\u1fd7\u1fe0-\u1fe7\u1ff2-\u1ff4\u1ff6-\u1ff7\u2071\u207f\u210a\u210e-\u210f\u2113\u212f\u2134\u2139\u213d\u2146-\u2149\ufb00-\ufb06\ufb13-\ufb17\uff41-\uff5a",
     r"Lm" : ur"\u02b0-\u02b8\u02bb-\u02c1\u02d0-\u02d1\u02e0-\u02e4\u02ee\u037a\u0559\u0640\u06e5-\u06e6\u0e46\u0ec6\u17d7\u1843\u3005\u3031-\u3035\u303b\u309d-\u309e\u30fc-\u30fe\uff70\uff9e-\uff9f",
     r"Lo" : ur"\u01bb\u01c0-\u01c3\u05d0-\u05ea\u05f0-\u05f2\u0621-\u063a\u0641-\u064a\u066e-\u066f\u0671-\u06d3\u06d5\u06fa-\u06fc\u0710\u0712-\u072c\u0780-\u07a5\u07b1\u0905-\u0939\u093d\u0950\u0958-\u0961\u0985-\u098c\u098f-\u0990\u0993-\u09a8\u09aa-\u09b0\u09b2\u09b6-\u09b9\u09dc-\u09dd\u09df-\u09e1\u09f0-\u09f1\u0a05-\u0a0a\u0a0f-\u0a10\u0a13-\u0a28\u0a2a-\u0a30\u0a32-\u0a33\u0a35-\u0a36\u0a38-\u0a39\u0a59-\u0a5c\u0a5e\u0a72-\u0a74\u0a85-\u0a8b\u0a8d\u0a8f-\u0a91\u0a93-\u0aa8\u0aaa-\u0ab0\u0ab2-\u0ab3\u0ab5-\u0ab9\u0abd\u0ad0\u0ae0\u0b05-\u0b0c\u0b0f-\u0b10\u0b13-\u0b28\u0b2a-\u0b30\u0b32-\u0b33\u0b36-\u0b39\u0b3d\u0b5c-\u0b5d\u0b5f-\u0b61\u0b83\u0b85-\u0b8a\u0b8e-\u0b90\u0b92-\u0b95\u0b99-\u0b9a\u0b9c\u0b9e-\u0b9f\u0ba3-\u0ba4\u0ba8-\u0baa\u0bae-\u0bb5\u0bb7-\u0bb9\u0c05-\u0c0c\u0c0e-\u0c10\u0c12-\u0c28\u0c2a-\u0c33\u0c35-\u0c39\u0c60-\u0c61\u0c85-\u0c8c\u0c8e-\u0c90\u0c92-\u0ca8\u0caa-\u0cb3\u0cb5-\u0cb9\u0cde\u0ce0-\u0ce1\u0d05-\u0d0c\u0d0e-\u0d10\u0d12-\u0d28\u0d2a-\u0d39\u0d60-\u0d61\u0d85-\u0d96\u0d9a-\u0db1\u0db3-\u0dbb\u0dbd\u0dc0-\u0dc6\u0e01-\u0e30\u0e32-\u0e33\u0e40-\u0e45\u0e81-\u0e82\u0e84\u0e87-\u0e88\u0e8a\u0e8d\u0e94-\u0e97\u0e99-\u0e9f\u0ea1-\u0ea3\u0ea5\u0ea7\u0eaa-\u0eab\u0ead-\u0eb0\u0eb2-\u0eb3\u0ebd\u0ec0-\u0ec4\u0edc-\u0edd\u0f00\u0f40-\u0f47\u0f49-\u0f6a\u0f88-\u0f8b\u1000-\u1021\u1023-\u1027\u1029-\u102a\u1050-\u1055\u10d0-\u10f8\u1100-\u1159\u115f-\u11a2\u11a8-\u11f9\u1200-\u1206\u1208-\u1246\u1248\u124a-\u124d\u1250-\u1256\u1258\u125a-\u125d\u1260-\u1286\u1288\u128a-\u128d\u1290-\u12ae\u12b0\u12b2-\u12b5\u12b8-\u12be\u12c0\u12c2-\u12c5\u12c8-\u12ce\u12d0-\u12d6\u12d8-\u12ee\u12f0-\u130e\u1310\u1312-\u1315\u1318-\u131e\u1320-\u1346\u1348-\u135a\u13a0-\u13f4\u1401-\u166c\u166f-\u1676\u1681-\u169a\u16a0-\u16ea\u1700-\u170c\u170e-\u1711\u1720-\u1731\u1740-\u1751\u1760-\u176c\u176e-\u1770\u1780-\u17b3\u17dc\u1820-\u1842\u1844-\u1877\u1880-\u18a8\u2135-\u2138\u3006\u303c\u3041-\u3096\u309f\u30a1-\u30fa\u30ff\u3105-\u312c\u3131-\u318e\u31a0-\u31b7\u31f0-\u31ff\u3400-\u4db5\u4e00-\u9fa5\ua000-\ua48c\uac00-\ud7a3\uf900-\ufa2d\ufa30-\ufa6a\ufb1d\ufb1f-\ufb28\ufb2a-\ufb36\ufb38-\ufb3c\ufb3e\ufb40-\ufb41\ufb43-\ufb44\ufb46-\ufbb1\ufbd3-\ufd3d\ufd50-\ufd8f\ufd92-\ufdc7\ufdf0-\ufdfb\ufe70-\ufe74\ufe76-\ufefc\uff66-\uff6f\uff71-\uff9d\uffa0-\uffbe\uffc2-\uffc7\uffca-\uffcf\uffd2-\uffd7\uffda-\uffdc",
     r"Lt" : ur"\u01c5\u01c8\u01cb\u01f2\u1f88-\u1f8f\u1f98-\u1f9f\u1fa8-\u1faf\u1fbc\u1fcc\u1ffc",
     r"Lu" : ur"A-Z\xc0-\xd6\xd8-\xde\u0100\u0102\u0104\u0106\u0108\u010a\u010c\u010e\u0110\u0112\u0114\u0116\u0118\u011a\u011c\u011e\u0120\u0122\u0124\u0126\u0128\u012a\u012c\u012e\u0130\u0132\u0134\u0136\u0139\u013b\u013d\u013f\u0141\u0143\u0145\u0147\u014a\u014c\u014e\u0150\u0152\u0154\u0156\u0158\u015a\u015c\u015e\u0160\u0162\u0164\u0166\u0168\u016a\u016c\u016e\u0170\u0172\u0174\u0176\u0178-\u0179\u017b\u017d\u0181-\u0182\u0184\u0186-\u0187\u0189-\u018b\u018e-\u0191\u0193-\u0194\u0196-\u0198\u019c-\u019d\u019f-\u01a0\u01a2\u01a4\u01a6-\u01a7\u01a9\u01ac\u01ae-\u01af\u01b1-\u01b3\u01b5\u01b7-\u01b8\u01bc\u01c4\u01c7\u01ca\u01cd\u01cf\u01d1\u01d3\u01d5\u01d7\u01d9\u01db\u01de\u01e0\u01e2\u01e4\u01e6\u01e8\u01ea\u01ec\u01ee\u01f1\u01f4\u01f6-\u01f8\u01fa\u01fc\u01fe\u0200\u0202\u0204\u0206\u0208\u020a\u020c\u020e\u0210\u0212\u0214\u0216\u0218\u021a\u021c\u021e\u0220\u0222\u0224\u0226\u0228\u022a\u022c\u022e\u0230\u0232\u0386\u0388-\u038a\u038c\u038e-\u038f\u0391-\u03a1\u03a3-\u03ab\u03d2-\u03d4\u03d8\u03da\u03dc\u03de\u03e0\u03e2\u03e4\u03e6\u03e8\u03ea\u03ec\u03ee\u03f4\u0400-\u042f\u0460\u0462\u0464\u0466\u0468\u046a\u046c\u046e\u0470\u0472\u0474\u0476\u0478\u047a\u047c\u047e\u0480\u048a\u048c\u048e\u0490\u0492\u0494\u0496\u0498\u049a\u049c\u049e\u04a0\u04a2\u04a4\u04a6\u04a8\u04aa\u04ac\u04ae\u04b0\u04b2\u04b4\u04b6\u04b8\u04ba\u04bc\u04be\u04c0-\u04c1\u04c3\u04c5\u04c7\u04c9\u04cb\u04cd\u04d0\u04d2\u04d4\u04d6\u04d8\u04da\u04dc\u04de\u04e0\u04e2\u04e4\u04e6\u04e8\u04ea\u04ec\u04ee\u04f0\u04f2\u04f4\u04f8\u0500\u0502\u0504\u0506\u0508\u050a\u050c\u050e\u0531-\u0556\u10a0-\u10c5\u1e00\u1e02\u1e04\u1e06\u1e08\u1e0a\u1e0c\u1e0e\u1e10\u1e12\u1e14\u1e16\u1e18\u1e1a\u1e1c\u1e1e\u1e20\u1e22\u1e24\u1e26\u1e28\u1e2a\u1e2c\u1e2e\u1e30\u1e32\u1e34\u1e36\u1e38\u1e3a\u1e3c\u1e3e\u1e40\u1e42\u1e44\u1e46\u1e48\u1e4a\u1e4c\u1e4e\u1e50\u1e52\u1e54\u1e56\u1e58\u1e5a\u1e5c\u1e5e\u1e60\u1e62\u1e64\u1e66\u1e68\u1e6a\u1e6c\u1e6e\u1e70\u1e72\u1e74\u1e76\u1e78\u1e7a\u1e7c\u1e7e\u1e80\u1e82\u1e84\u1e86\u1e88\u1e8a\u1e8c\u1e8e\u1e90\u1e92\u1e94\u1ea0\u1ea2\u1ea4\u1ea6\u1ea8\u1eaa\u1eac\u1eae\u1eb0\u1eb2\u1eb4\u1eb6\u1eb8\u1eba\u1ebc\u1ebe\u1ec0\u1ec2\u1ec4\u1ec6\u1ec8\u1eca\u1ecc\u1ece\u1ed0\u1ed2\u1ed4\u1ed6\u1ed8\u1eda\u1edc\u1ede\u1ee0\u1ee2\u1ee4\u1ee6\u1ee8\u1eea\u1eec\u1eee\u1ef0\u1ef2\u1ef4\u1ef6\u1ef8\u1f08-\u1f0f\u1f18-\u1f1d\u1f28-\u1f2f\u1f38-\u1f3f\u1f48-\u1f4d\u1f59\u1f5b\u1f5d\u1f5f\u1f68-\u1f6f\u1fb8-\u1fbb\u1fc8-\u1fcb\u1fd8-\u1fdb\u1fe8-\u1fec\u1ff8-\u1ffb\u2102\u2107\u210b-\u210d\u2110-\u2112\u2115\u2119-\u211d\u2124\u2126\u2128\u212a-\u212d\u2130-\u2131\u2133\u213e-\u213f\u2145\uff21-\uff3a",
     r"L" : ur"A-Za-z\xaa\xb5\xba\xc0-\xd6\xd8-\xf6\xf8-\u0220\u0222-\u0233\u0250-\u02ad\u02b0-\u02b8\u02bb-\u02c1\u02d0-\u02d1\u02e0-\u02e4\u02ee\u037a\u0386\u0388-\u038a\u038c\u038e-\u03a1\u03a3-\u03ce\u03d0-\u03f5\u0400-\u0481\u048a-\u04ce\u04d0-\u04f5\u04f8-\u04f9\u0500-\u050f\u0531-\u0556\u0559\u0561-\u0587\u05d0-\u05ea\u05f0-\u05f2\u0621-\u063a\u0640-\u064a\u066e-\u066f\u0671-\u06d3\u06d5\u06e5-\u06e6\u06fa-\u06fc\u0710\u0712-\u072c\u0780-\u07a5\u07b1\u0905-\u0939\u093d\u0950\u0958-\u0961\u0985-\u098c\u098f-\u0990\u0993-\u09a8\u09aa-\u09b0\u09b2\u09b6-\u09b9\u09dc-\u09dd\u09df-\u09e1\u09f0-\u09f1\u0a05-\u0a0a\u0a0f-\u0a10\u0a13-\u0a28\u0a2a-\u0a30\u0a32-\u0a33\u0a35-\u0a36\u0a38-\u0a39\u0a59-\u0a5c\u0a5e\u0a72-\u0a74\u0a85-\u0a8b\u0a8d\u0a8f-\u0a91\u0a93-\u0aa8\u0aaa-\u0ab0\u0ab2-\u0ab3\u0ab5-\u0ab9\u0abd\u0ad0\u0ae0\u0b05-\u0b0c\u0b0f-\u0b10\u0b13-\u0b28\u0b2a-\u0b30\u0b32-\u0b33\u0b36-\u0b39\u0b3d\u0b5c-\u0b5d\u0b5f-\u0b61\u0b83\u0b85-\u0b8a\u0b8e-\u0b90\u0b92-\u0b95\u0b99-\u0b9a\u0b9c\u0b9e-\u0b9f\u0ba3-\u0ba4\u0ba8-\u0baa\u0bae-\u0bb5\u0bb7-\u0bb9\u0c05-\u0c0c\u0c0e-\u0c10\u0c12-\u0c28\u0c2a-\u0c33\u0c35-\u0c39\u0c60-\u0c61\u0c85-\u0c8c\u0c8e-\u0c90\u0c92-\u0ca8\u0caa-\u0cb3\u0cb5-\u0cb9\u0cde\u0ce0-\u0ce1\u0d05-\u0d0c\u0d0e-\u0d10\u0d12-\u0d28\u0d2a-\u0d39\u0d60-\u0d61\u0d85-\u0d96\u0d9a-\u0db1\u0db3-\u0dbb\u0dbd\u0dc0-\u0dc6\u0e01-\u0e30\u0e32-\u0e33\u0e40-\u0e46\u0e81-\u0e82\u0e84\u0e87-\u0e88\u0e8a\u0e8d\u0e94-\u0e97\u0e99-\u0e9f\u0ea1-\u0ea3\u0ea5\u0ea7\u0eaa-\u0eab\u0ead-\u0eb0\u0eb2-\u0eb3\u0ebd\u0ec0-\u0ec4\u0ec6\u0edc-\u0edd\u0f00\u0f40-\u0f47\u0f49-\u0f6a\u0f88-\u0f8b\u1000-\u1021\u1023-\u1027\u1029-\u102a\u1050-\u1055\u10a0-\u10c5\u10d0-\u10f8\u1100-\u1159\u115f-\u11a2\u11a8-\u11f9\u1200-\u1206\u1208-\u1246\u1248\u124a-\u124d\u1250-\u1256\u1258\u125a-\u125d\u1260-\u1286\u1288\u128a-\u128d\u1290-\u12ae\u12b0\u12b2-\u12b5\u12b8-\u12be\u12c0\u12c2-\u12c5\u12c8-\u12ce\u12d0-\u12d6\u12d8-\u12ee\u12f0-\u130e\u1310\u1312-\u1315\u1318-\u131e\u1320-\u1346\u1348-\u135a\u13a0-\u13f4\u1401-\u166c\u166f-\u1676\u1681-\u169a\u16a0-\u16ea\u1700-\u170c\u170e-\u1711\u1720-\u1731\u1740-\u1751\u1760-\u176c\u176e-\u1770\u1780-\u17b3\u17d7\u17dc\u1820-\u1877\u1880-\u18a8\u1e00-\u1e9b\u1ea0-\u1ef9\u1f00-\u1f15\u1f18-\u1f1d\u1f20-\u1f45\u1f48-\u1f4d\u1f50-\u1f57\u1f59\u1f5b\u1f5d\u1f5f-\u1f7d\u1f80-\u1fb4\u1fb6-\u1fbc\u1fbe\u1fc2-\u1fc4\u1fc6-\u1fcc\u1fd0-\u1fd3\u1fd6-\u1fdb\u1fe0-\u1fec\u1ff2-\u1ff4\u1ff6-\u1ffc\u2071\u207f\u2102\u2107\u210a-\u2113\u2115\u2119-\u211d\u2124\u2126\u2128\u212a-\u212d\u212f-\u2131\u2133-\u2139\u213d-\u213f\u2145-\u2149\u3005-\u3006\u3031-\u3035\u303b-\u303c\u3041-\u3096\u309d-\u309f\u30a1-\u30fa\u30fc-\u30ff\u3105-\u312c\u3131-\u318e\u31a0-\u31b7\u31f0-\u31ff\u3400-\u4db5\u4e00-\u9fa5\ua000-\ua48c\uac00-\ud7a3\uf900-\ufa2d\ufa30-\ufa6a\ufb00-\ufb06\ufb13-\ufb17\ufb1d\ufb1f-\ufb28\ufb2a-\ufb36\ufb38-\ufb3c\ufb3e\ufb40-\ufb41\ufb43-\ufb44\ufb46-\ufbb1\ufbd3-\ufd3d\ufd50-\ufd8f\ufd92-\ufdc7\ufdf0-\ufdfb\ufe70-\ufe74\ufe76-\ufefc\uff21-\uff3a\uff41-\uff5a\uff66-\uffbe\uffc2-\uffc7\uffca-\uffcf\uffd2-\uffd7\uffda-\uffdc",
                                    
     r"Mc" : ur"\u0903\u093e-\u0940\u0949-\u094c\u0982-\u0983\u09be-\u09c0\u09c7-\u09c8\u09cb-\u09cc\u09d7\u0a3e-\u0a40\u0a83\u0abe-\u0ac0\u0ac9\u0acb-\u0acc\u0b02-\u0b03\u0b3e\u0b40\u0b47-\u0b48\u0b4b-\u0b4c\u0b57\u0bbe-\u0bbf\u0bc1-\u0bc2\u0bc6-\u0bc8\u0bca-\u0bcc\u0bd7\u0c01-\u0c03\u0c41-\u0c44\u0c82-\u0c83\u0cbe\u0cc0-\u0cc4\u0cc7-\u0cc8\u0cca-\u0ccb\u0cd5-\u0cd6\u0d02-\u0d03\u0d3e-\u0d40\u0d46-\u0d48\u0d4a-\u0d4c\u0d57\u0d82-\u0d83\u0dcf-\u0dd1\u0dd8-\u0ddf\u0df2-\u0df3\u0f3e-\u0f3f\u0f7f\u102c\u1031\u1038\u1056-\u1057\u17b4-\u17b6\u17be-\u17c5\u17c7-\u17c8",
     r"Me" : ur"\u0488-\u0489\u06de\u20dd-\u20e0\u20e2-\u20e4",
     r"Mn" : ur"\u0300-\u034f\u0360-\u036f\u0483-\u0486\u0591-\u05a1\u05a3-\u05b9\u05bb-\u05bd\u05bf\u05c1-\u05c2\u05c4\u064b-\u0655\u0670\u06d6-\u06dc\u06df-\u06e4\u06e7-\u06e8\u06ea-\u06ed\u0711\u0730-\u074a\u07a6-\u07b0\u0901-\u0902\u093c\u0941-\u0948\u094d\u0951-\u0954\u0962-\u0963\u0981\u09bc\u09c1-\u09c4\u09cd\u09e2-\u09e3\u0a02\u0a3c\u0a41-\u0a42\u0a47-\u0a48\u0a4b-\u0a4d\u0a70-\u0a71\u0a81-\u0a82\u0abc\u0ac1-\u0ac5\u0ac7-\u0ac8\u0acd\u0b01\u0b3c\u0b3f\u0b41-\u0b43\u0b4d\u0b56\u0b82\u0bc0\u0bcd\u0c3e-\u0c40\u0c46-\u0c48\u0c4a-\u0c4d\u0c55-\u0c56\u0cbf\u0cc6\u0ccc-\u0ccd\u0d41-\u0d43\u0d4d\u0dca\u0dd2-\u0dd4\u0dd6\u0e31\u0e34-\u0e3a\u0e47-\u0e4e\u0eb1\u0eb4-\u0eb9\u0ebb-\u0ebc\u0ec8-\u0ecd\u0f18-\u0f19\u0f35\u0f37\u0f39\u0f71-\u0f7e\u0f80-\u0f84\u0f86-\u0f87\u0f90-\u0f97\u0f99-\u0fbc\u0fc6\u102d-\u1030\u1032\u1036-\u1037\u1039\u1058-\u1059\u1712-\u1714\u1732-\u1734\u1752-\u1753\u1772-\u1773\u17b7-\u17bd\u17c6\u17c9-\u17d3\u180b-\u180d\u18a9\u20d0-\u20dc\u20e1\u20e5-\u20ea\u302a-\u302f\u3099-\u309a\ufb1e\ufe00-\ufe0f\ufe20-\ufe23",
     r"M" : ur"\u0300-\u034f\u0360-\u036f\u0483-\u0486\u0488-\u0489\u0591-\u05a1\u05a3-\u05b9\u05bb-\u05bd\u05bf\u05c1-\u05c2\u05c4\u064b-\u0655\u0670\u06d6-\u06dc\u06de-\u06e4\u06e7-\u06e8\u06ea-\u06ed\u0711\u0730-\u074a\u07a6-\u07b0\u0901-\u0903\u093c\u093e-\u094d\u0951-\u0954\u0962-\u0963\u0981-\u0983\u09bc\u09be-\u09c4\u09c7-\u09c8\u09cb-\u09cd\u09d7\u09e2-\u09e3\u0a02\u0a3c\u0a3e-\u0a42\u0a47-\u0a48\u0a4b-\u0a4d\u0a70-\u0a71\u0a81-\u0a83\u0abc\u0abe-\u0ac5\u0ac7-\u0ac9\u0acb-\u0acd\u0b01-\u0b03\u0b3c\u0b3e-\u0b43\u0b47-\u0b48\u0b4b-\u0b4d\u0b56-\u0b57\u0b82\u0bbe-\u0bc2\u0bc6-\u0bc8\u0bca-\u0bcd\u0bd7\u0c01-\u0c03\u0c3e-\u0c44\u0c46-\u0c48\u0c4a-\u0c4d\u0c55-\u0c56\u0c82-\u0c83\u0cbe-\u0cc4\u0cc6-\u0cc8\u0cca-\u0ccd\u0cd5-\u0cd6\u0d02-\u0d03\u0d3e-\u0d43\u0d46-\u0d48\u0d4a-\u0d4d\u0d57\u0d82-\u0d83\u0dca\u0dcf-\u0dd4\u0dd6\u0dd8-\u0ddf\u0df2-\u0df3\u0e31\u0e34-\u0e3a\u0e47-\u0e4e\u0eb1\u0eb4-\u0eb9\u0ebb-\u0ebc\u0ec8-\u0ecd\u0f18-\u0f19\u0f35\u0f37\u0f39\u0f3e-\u0f3f\u0f71-\u0f84\u0f86-\u0f87\u0f90-\u0f97\u0f99-\u0fbc\u0fc6\u102c-\u1032\u1036-\u1039\u1056-\u1059\u1712-\u1714\u1732-\u1734\u1752-\u1753\u1772-\u1773\u17b4-\u17d3\u180b-\u180d\u18a9\u20d0-\u20ea\u302a-\u302f\u3099-\u309a\ufb1e\ufe00-\ufe0f\ufe20-\ufe23",
                                    
     r"Nd" : ur"0-9\u0660-\u0669\u06f0-\u06f9\u0966-\u096f\u09e6-\u09ef\u0a66-\u0a6f\u0ae6-\u0aef\u0b66-\u0b6f\u0be7-\u0bef\u0c66-\u0c6f\u0ce6-\u0cef\u0d66-\u0d6f\u0e50-\u0e59\u0ed0-\u0ed9\u0f20-\u0f29\u1040-\u1049\u1369-\u1371\u17e0-\u17e9\u1810-\u1819\uff10-\uff19",
     r"Nl" : ur"\u16ee-\u16f0\u2160-\u2183\u3007\u3021-\u3029\u3038-\u303a",
     r"No" : ur"\xb2-\xb3\xb9\xbc-\xbe\u09f4-\u09f9\u0bf0-\u0bf2\u0f2a-\u0f33\u1372-\u137c\u2070\u2074-\u2079\u2080-\u2089\u2153-\u215f\u2460-\u249b\u24ea-\u24fe\u2776-\u2793\u3192-\u3195\u3220-\u3229\u3251-\u325f\u3280-\u3289\u32b1-\u32bf",
     r"N" : ur"0-9\xb2-\xb3\xb9\xbc-\xbe\u0660-\u0669\u06f0-\u06f9\u0966-\u096f\u09e6-\u09ef\u09f4-\u09f9\u0a66-\u0a6f\u0ae6-\u0aef\u0b66-\u0b6f\u0be7-\u0bf2\u0c66-\u0c6f\u0ce6-\u0cef\u0d66-\u0d6f\u0e50-\u0e59\u0ed0-\u0ed9\u0f20-\u0f33\u1040-\u1049\u1369-\u137c\u16ee-\u16f0\u17e0-\u17e9\u1810-\u1819\u2070\u2074-\u2079\u2080-\u2089\u2153-\u2183\u2460-\u249b\u24ea-\u24fe\u2776-\u2793\u3007\u3021-\u3029\u3038-\u303a\u3192-\u3195\u3220-\u3229\u3251-\u325f\u3280-\u3289\u32b1-\u32bf\uff10-\uff19",
                                    
     r"Pc" : ur"_\u203f-\u2040\u30fb\ufe33-\ufe34\ufe4d-\ufe4f\uff3f\uff65",
     r"Pd" : ur"-\xad\u058a\u1806\u2010-\u2015\u301c\u3030\u30a0\ufe31-\ufe32\ufe58\ufe63\uff0d",
     r"Pe" : ur")\]}\u0f3b\u0f3d\u169c\u2046\u207e\u208e\u232a\u23b5\u2769\u276b\u276d\u276f\u2771\u2773\u2775\u27e7\u27e9\u27eb\u2984\u2986\u2988\u298a\u298c\u298e\u2990\u2992\u2994\u2996\u2998\u29d9\u29db\u29fd\u3009\u300b\u300d\u300f\u3011\u3015\u3017\u3019\u301b\u301e-\u301f\ufd3f\ufe36\ufe38\ufe3a\ufe3c\ufe3e\ufe40\ufe42\ufe44\ufe5a\ufe5c\ufe5e\uff09\uff3d\uff5d\uff60\uff63",
     r"Pf" : ur"\xbb\u2019\u201d\u203a",
     r"Pi" : ur"\xab\u2018\u201b-\u201c\u201f\u2039",
     r"Po" : ur"!\"#%&'*,./:;?@\\\xa1\xb7\xbf\u037e\u0387\u055a-\u055f\u0589\u05be\u05c0\u05c3\u05f3-\u05f4\u060c\u061b\u061f\u066a-\u066d\u06d4\u0700-\u070d\u0964-\u0965\u0970\u0df4\u0e4f\u0e5a-\u0e5b\u0f04-\u0f12\u0f85\u104a-\u104f\u10fb\u1361-\u1368\u166d-\u166e\u16eb-\u16ed\u1735-\u1736\u17d4-\u17d6\u17d8-\u17da\u1800-\u1805\u1807-\u180a\u2016-\u2017\u2020-\u2027\u2030-\u2038\u203b-\u203e\u2041-\u2043\u2047-\u2051\u2057\u23b6\u3001-\u3003\u303d\ufe30\ufe45-\ufe46\ufe49-\ufe4c\ufe50-\ufe52\ufe54-\ufe57\ufe5f-\ufe61\ufe68\ufe6a-\ufe6b\uff01-\uff03\uff05-\uff07\uff0a\uff0c\uff0e-\uff0f\uff1a-\uff1b\uff1f-\uff20\uff3c\uff61\uff64",
     r"Ps" : ur"(\[{\u0f3a\u0f3c\u169b\u201a\u201e\u2045\u207d\u208d\u2329\u23b4\u2768\u276a\u276c\u276e\u2770\u2772\u2774\u27e6\u27e8\u27ea\u2983\u2985\u2987\u2989\u298b\u298d\u298f\u2991\u2993\u2995\u2997\u29d8\u29da\u29fc\u3008\u300a\u300c\u300e\u3010\u3014\u3016\u3018\u301a\u301d\ufd3e\ufe35\ufe37\ufe39\ufe3b\ufe3d\ufe3f\ufe41\ufe43\ufe59\ufe5b\ufe5d\uff08\uff3b\uff5b\uff5f\uff62",
     r"P" : ur"!\"#%&'()*,\-./:;?@\[\\\]_{}\xa1\xab\xad\xb7\xbb\xbf\u037e\u0387\u055a-\u055f\u0589-\u058a\u05be\u05c0\u05c3\u05f3-\u05f4\u060c\u061b\u061f\u066a-\u066d\u06d4\u0700-\u070d\u0964-\u0965\u0970\u0df4\u0e4f\u0e5a-\u0e5b\u0f04-\u0f12\u0f3a-\u0f3d\u0f85\u104a-\u104f\u10fb\u1361-\u1368\u166d-\u166e\u169b-\u169c\u16eb-\u16ed\u1735-\u1736\u17d4-\u17d6\u17d8-\u17da\u1800-\u180a\u2010-\u2027\u2030-\u2043\u2045-\u2051\u2057\u207d-\u207e\u208d-\u208e\u2329-\u232a\u23b4-\u23b6\u2768-\u2775\u27e6-\u27eb\u2983-\u2998\u29d8-\u29db\u29fc-\u29fd\u3001-\u3003\u3008-\u3011\u3014-\u301f\u3030\u303d\u30a0\u30fb\ufd3e-\ufd3f\ufe30-\ufe46\ufe49-\ufe52\ufe54-\ufe61\ufe63\ufe68\ufe6a-\ufe6b\uff01-\uff03\uff05-\uff0a\uff0c-\uff0f\uff1a-\uff1b\uff1f-\uff20\uff3b-\uff3d\uff3f\uff5b\uff5d\uff5f-\uff65",
                                    
     r"Sc" : ur"$\xa2-\xa5\u09f2-\u09f3\u0e3f\u17db\u20a0-\u20b1\ufdfc\ufe69\uff04\uffe0-\uffe1\uffe5-\uffe6",
     r"Sk" : ur"\^`\xa8\xaf\xb4\xb8\u02b9-\u02ba\u02c2-\u02cf\u02d2-\u02df\u02e5-\u02ed\u0374-\u0375\u0384-\u0385\u1fbd\u1fbf-\u1fc1\u1fcd-\u1fcf\u1fdd-\u1fdf\u1fed-\u1fef\u1ffd-\u1ffe\u309b-\u309c\uff3e\uff40\uffe3",
     r"Sm" : ur"+<=>|~\xac\xb1\xd7\xf7\u03f6\u2044\u2052\u207a-\u207c\u208a-\u208c\u2140-\u2144\u214b\u2190-\u2194\u219a-\u219b\u21a0\u21a3\u21a6\u21ae\u21ce-\u21cf\u21d2\u21d4\u21f4-\u22ff\u2308-\u230b\u2320-\u2321\u237c\u239b-\u23b3\u25b7\u25c1\u25f8-\u25ff\u266f\u27d0-\u27e5\u27f0-\u27ff\u2900-\u2982\u2999-\u29d7\u29dc-\u29fb\u29fe-\u2aff\ufb29\ufe62\ufe64-\ufe66\uff0b\uff1c-\uff1e\uff5c\uff5e\uffe2\uffe9-\uffec",
     r"So" : ur"\xa6-\xa7\xa9\xae\xb0\xb6\u0482\u06e9\u06fd-\u06fe\u09fa\u0b70\u0f01-\u0f03\u0f13-\u0f17\u0f1a-\u0f1f\u0f34\u0f36\u0f38\u0fbe-\u0fc5\u0fc7-\u0fcc\u0fcf\u2100-\u2101\u2103-\u2106\u2108-\u2109\u2114\u2116-\u2118\u211e-\u2123\u2125\u2127\u2129\u212e\u2132\u213a\u214a\u2195-\u2199\u219c-\u219f\u21a1-\u21a2\u21a4-\u21a5\u21a7-\u21ad\u21af-\u21cd\u21d0-\u21d1\u21d3\u21d5-\u21f3\u2300-\u2307\u230c-\u231f\u2322-\u2328\u232b-\u237b\u237d-\u239a\u23b7-\u23ce\u2400-\u2426\u2440-\u244a\u249c-\u24e9\u2500-\u25b6\u25b8-\u25c0\u25c2-\u25f7\u2600-\u2613\u2616-\u2617\u2619-\u266e\u2670-\u267d\u2680-\u2689\u2701-\u2704\u2706-\u2709\u270c-\u2727\u2729-\u274b\u274d\u274f-\u2752\u2756\u2758-\u275e\u2761-\u2767\u2794\u2798-\u27af\u27b1-\u27be\u2800-\u28ff\u2e80-\u2e99\u2e9b-\u2ef3\u2f00-\u2fd5\u2ff0-\u2ffb\u3004\u3012-\u3013\u3020\u3036-\u3037\u303e-\u303f\u3190-\u3191\u3196-\u319f\u3200-\u321c\u322a-\u3243\u3260-\u327b\u327f\u328a-\u32b0\u32c0-\u32cb\u32d0-\u32fe\u3300-\u3376\u337b-\u33dd\u33e0-\u33fe\ua490-\ua4c6\uffe4\uffe8\uffed-\uffee\ufffc-\ufffd",
     r"S" : ur"$+<=>\^`|~\xa2-\xa9\xac\xae-\xb1\xb4\xb6\xb8\xd7\xf7\u02b9-\u02ba\u02c2-\u02cf\u02d2-\u02df\u02e5-\u02ed\u0374-\u0375\u0384-\u0385\u03f6\u0482\u06e9\u06fd-\u06fe\u09f2-\u09f3\u09fa\u0b70\u0e3f\u0f01-\u0f03\u0f13-\u0f17\u0f1a-\u0f1f\u0f34\u0f36\u0f38\u0fbe-\u0fc5\u0fc7-\u0fcc\u0fcf\u17db\u1fbd\u1fbf-\u1fc1\u1fcd-\u1fcf\u1fdd-\u1fdf\u1fed-\u1fef\u1ffd-\u1ffe\u2044\u2052\u207a-\u207c\u208a-\u208c\u20a0-\u20b1\u2100-\u2101\u2103-\u2106\u2108-\u2109\u2114\u2116-\u2118\u211e-\u2123\u2125\u2127\u2129\u212e\u2132\u213a\u2140-\u2144\u214a-\u214b\u2190-\u2328\u232b-\u23b3\u23b7-\u23ce\u2400-\u2426\u2440-\u244a\u249c-\u24e9\u2500-\u2613\u2616-\u2617\u2619-\u267d\u2680-\u2689\u2701-\u2704\u2706-\u2709\u270c-\u2727\u2729-\u274b\u274d\u274f-\u2752\u2756\u2758-\u275e\u2761-\u2767\u2794\u2798-\u27af\u27b1-\u27be\u27d0-\u27e5\u27f0-\u2982\u2999-\u29d7\u29dc-\u29fb\u29fe-\u2aff\u2e80-\u2e99\u2e9b-\u2ef3\u2f00-\u2fd5\u2ff0-\u2ffb\u3004\u3012-\u3013\u3020\u3036-\u3037\u303e-\u303f\u309b-\u309c\u3190-\u3191\u3196-\u319f\u3200-\u321c\u322a-\u3243\u3260-\u327b\u327f\u328a-\u32b0\u32c0-\u32cb\u32d0-\u32fe\u3300-\u3376\u337b-\u33dd\u33e0-\u33fe\ua490-\ua4c6\ufb29\ufdfc\ufe62\ufe64-\ufe66\ufe69\uff04\uff0b\uff1c-\uff1e\uff3e\uff40\uff5c\uff5e\uffe0-\uffe6\uffe8-\uffee\ufffc-\ufffd",

     r"Zl" : ur"\u2028",
     r"Zp" : ur"\u2029",
     r"Zs" : ur" \xa0\u1680\u2000-\u200b\u202f\u205f\u3000",
     r"Z" : ur" \xa0\u1680\u2000-\u200b\u2028-\u2029\u202f\u205f\u3000",

     r"IsBasicLatin" : ur"\u0000-\u007f",
     r"IsLatin-1Supplement" : ur"\u0080-\u00ff",
     r"IsLatinExtended-A" : ur"\u0100-\u017f",
     r"IsLatinExtended-B" : ur"\u0180-\u024f",
     r"IsIPAExtensions" : ur"\u0250-\u02af",
     r"IsSpacingModifierLetters" : ur"\u02b0-\u02ff",
     r"IsCombiningDiacriticalMarks" : ur"\u0300-\u036f",
     r"IsGreek" : ur"\u0370-\u03ff",
     r"IsCyrillic" : ur"\u0400-\u04ff",
     r"IsArmenian" : ur"\u0530-\u058f",
     r"IsHebrew" : ur"\u0590-\u05ff",
     r"IsArabic" : ur"\u0600-\u06ff",
     r"IsSyriac" : ur"\u0700-\u074f",
     r"IsThaana" : ur"\u0780-\u07bf",
     r"IsDevanagari" : ur"\u0900-\u097f",
     r"IsBengali" : ur"\u0980-\u09ff",
     r"IsGurmukhi" : ur"\u0a00-\u0a7f",
     r"IsGujarati" : ur"\u0a80-\u0aff",
     r"IsOriya" : ur"\u0b00-\u0b7f",
     r"IsTamil" : ur"\u0b80-\u0bff",
     r"IsTelugu" : ur"\u0C00-\u0C7F",    
     r"IsKannada" : ur"\u0C80-\u0CFF",
     r"IsMalayalam" : ur"\u0D00-\u0D7F",
     r"IsSinhala" : ur"\u0D80-\u0DFF",
     r"IsThai" : ur"\u0E00-\u0E7F",
     r"IsLao" : ur"\u0E80-\u0EFF",
     r"IsTibetan" : ur"\u0F00-\u0FFF",
     r"IsMyanmar" : ur"\u1000-\u109F",
     r"IsGeorgian" : ur"\u10A0-\u10FF",
     r"IsHangulJamo" : ur"\u1100-\u11FF",
     r"IsEthiopic" : ur"\u1200-\u137F",
     r"IsCherokee" : ur"\u13A0-\u13FF",
     r"IsUnifiedCanadianAboriginalSyllabics" : ur"\u1400-\u167F",
     r"IsOgham" : ur"\u1680-\u169F",
     r"IsRunic" : ur"\u16A0-\u16FF",
     r"IsKhmer" : ur"\u1780-\u17FF",
     r"IsMongolian" : ur"\u1800-\u18AF",
     r"IsLatinExtendedAdditional" : ur"\u1E00-\u1EFF",
     r"IsGreekExtended" : ur"\u1F00-\u1FFF",
     r"IsGeneralPunctuation" : ur"\u2000-\u206F",
     r"IsSuperscriptsandSubscripts" : ur"\u2070-\u209F",
     r"IsCurrencySymbols" : ur"\u20A0-\u20CF",
     r"IsCombiningMarksforSymbols" : ur"\u20D0-\u20FF",
     r"IsLetterlikeSymbols" : ur"\u2100-\u214F",
     r"IsNumberForms" : ur"\u2150-\u218F",
     r"IsArrows" : ur"\u2190-\u21FF",
     r"IsMathematicalOperators" : ur"\u2200-\u22FF",
     r"IsMiscellaneousTechnical" : ur"\u2300-\u23FF",
     r"IsControlPictures" : ur"\u2400-\u243F",
     r"IsOpticalCharacterRecognition" : ur"\u2440-\u245F",
     r"IsEnclosedAlphanumerics" : ur"\u2460-\u24FF",
     r"IsBoxDrawing" : ur"\u2500-\u257F",
     r"IsBlockElements" : ur"\u2580-\u259F",
     r"IsGeometricShapes" : ur"\u25A0-\u25FF",
     r"IsMiscellaneousSymbols" : ur"\u2600-\u26FF",
     r"IsDingbats" : ur"\u2700-\u27BF",
     r"IsBraillePatterns" : ur"\u2800-\u28FF",
     r"IsCJKRadicalsSupplement" : ur"\u2E80-\u2EFF",
     r"IsKangxiRadicals" : ur"\u2F00-\u2FDF",
     r"IsIdeographicDescriptionCharacters" : ur"\u2FF0-\u2FFF",
     r"IsCJKSymbolsandPunctuation" : ur"\u3000-\u303F",
     r"IsHiragana" : ur"\u3040-\u309F",
     r"IsKatakana" : ur"\u30A0-\u30FF",
     r"IsBopomofo" : ur"\u3100-\u312F",
     r"IsHangulCompatibilityJamo" : ur"\u3130-\u318F",
     r"IsKanbun" : ur"\u3190-\u319F",
     r"IsBopomofoExtended" : ur"\u31A0-\u31BF",
     r"IsEnclosedCJKLettersandMonths" : ur"\u3200-\u32FF",
     r"IsCJKCompatibility" : ur"\u3300-\u33FF",
     r"IsCJKUnifiedIdeographsExtensionA" : ur"\u3400-\u4DB5",
     r"IsCJKUnifiedIdeographs" : ur"\u4E00-\u9FFF",
     r"IsYiSyllables" : ur"\uA000-\uA48F",
     r"IsYiRadicals" : ur"\uA490-\uA4CF",
     r"IsHangulSyllables" : ur"\uAC00-\uD7A3",
     r"IsHighSurrogates" : ur"\uD800-\uDB7F",
     r"IsHighPrivateUseSurrogates" : ur"\uDB80-\uDBFF",
     r"IsLowSurrogates" : ur"\uDC00-\uDFFF",
     r"IsPrivateUse" : ur"\uE000-\uF8FF",
     r"IsCJKCompatibilityIdeographs" : ur"\uF900-\uFAFF",
     r"IsAlphabeticPresentationForms" : ur"\uFB00-\uFB4F",
     r"IsArabicPresentationForms-A" : ur"\uFB50-\uFDFF",
     r"IsCombiningHalfMarks" : ur"\uFE20-\uFE2F",
     r"IsCJKCompatibilityForms" : ur"\uFE30-\uFE4F",
     r"IsSmallFormVariants" : ur"\uFE50-\uFE6F",
     r"IsArabicPresentationForms-B" : ur"\uFE70-\uFEFE",
     r"IsSpecials" : ur"\uFEFF-\uFEFF\uFFF0-\uFFFD",
     r"IsHalfwidthandFullwidthForms" : ur"\uFF00-\uFFEF",
# TODO: wide unicode characters are currently not supported!     
#     r"IsOldItalic" : ur"\U00010300-\U0001032F",
#     r"IsGothic" : ur"\U00010330-\U0001034F",
#     r"IsDeseret" : ur"\U00010400-\U0001044F",
#     r"IsByzantineMusicalSymbols" : ur"\U0001D000-\U0001D0FF",
#     r"IsMusicalSymbols" : ur"\U0001D100-\U0001D1FF",
#     r"IsMathematicalAlphanumericSymbols" : ur"\U0001D400-\U0001D7FF",
#     r"IsCJKUnifiedIdeographsExtensionB" : ur"\U00020000-\U0002A6D6",
#     r"IsCJKCompatibilityIdeographsSupplement" : ur"\U0002F800-\U0002FA1F",
#     r"IsTags" : ur"\U000E0000-\U000E007F",
#     r"IsPrivateUse" : ur"\U000F0000-\U000FFFFD\U00100000-\U0010FFFD",
     }


creSingleCharEsc = re.compile(r"(?P<pbs>\\*)(?P<escChar>\\[iIcC])")
                                      
substSingleCharEscDict = {             
     r"\i": ur"_:\u0041-\u005A\u0061-\u007A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u0131\u0134-\u013E\u0141-\u0148\u014A-\u017E\u0180-\u01C3\u01CD-\u01F0\u01F4-\u01F5\u01FA-\u0217\u0250-\u02A8\u02BB-\u02C1\u0386\u0388-\u038A\u038C\u038E-\u03A1\u03A3-\u03CE\u03D0-\u03D6\u03DA\u03DC\u03DE\u03E0\u03E2-\u03F3\u0401-\u040C\u040E-\u044F\u0451-\u045C\u045E-\u0481\u0490-\u04C4\u04C7-\u04C8\u04CB-\u04CC\u04D0-\u04EB\u04EE-\u04F5\u04F8-\u04F9\u0531-\u0556\u0559\u0561-\u0586\u05D0-\u05EA\u05F0-\u05F2\u0621-\u063A\u0641-\u064A\u0671-\u06B7\u06BA-\u06BE\u06C0-\u06CE\u06D0-\u06D3\u06D5\u06E5-\u06E6\u0905-\u0939\u093D\u0958-\u0961\u0985-\u098C\u098F-\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09DC-\u09DD\u09DF-\u09E1\u09F0-\u09F1\u0A05-\u0A0A\u0A0F-\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32-\u0A33\u0A35-\u0A36\u0A38-\u0A39\u0A59-\u0A5C\u0A5E\u0A72-\u0A74\u0A85-\u0A8B\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2-\u0AB3\u0AB5-\u0AB9\u0ABD\u0AE0\u0B05-\u0B0C\u0B0F-\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32-\u0B33\u0B36-\u0B39\u0B3D\u0B5C-\u0B5D\u0B5F-\u0B61\u0B85-\u0B8A\u0B8E-\u0B90\u0B92-\u0B95\u0B99-\u0B9A\u0B9C\u0B9E-\u0B9F\u0BA3-\u0BA4\u0BA8-\u0BAA\u0BAE-\u0BB5\u0BB7-\u0BB9\u0C05-\u0C0C\u0C0E-\u0C10\u0C12-\u0C28\u0C2A-\u0C33\u0C35-\u0C39\u0C60-\u0C61\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CDE\u0CE0-\u0CE1\u0D05-\u0D0C\u0D0E-\u0D10\u0D12-\u0D28\u0D2A-\u0D39\u0D60-\u0D61\u0E01-\u0E2E\u0E30\u0E32-\u0E33\u0E40-\u0E45\u0E81-\u0E82\u0E84\u0E87-\u0E88\u0E8A\u0E8D\u0E94-\u0E97\u0E99-\u0E9F\u0EA1-\u0EA3\u0EA5\u0EA7\u0EAA-\u0EAB\u0EAD-\u0EAE\u0EB0\u0EB2-\u0EB3\u0EBD\u0EC0-\u0EC4\u0F40-\u0F47\u0F49-\u0F69\u10A0-\u10C5\u10D0-\u10F6\u1100\u1102-\u1103\u1105-\u1107\u1109\u110B-\u110C\u110E-\u1112\u113C\u113E\u1140\u114C\u114E\u1150\u1154-\u1155\u1159\u115F-\u1161\u1163\u1165\u1167\u1169\u116D-\u116E\u1172-\u1173\u1175\u119E\u11A8\u11AB\u11AE-\u11AF\u11B7-\u11B8\u11BA\u11BC-\u11C2\u11EB\u11F0\u11F9\u1E00-\u1E9B\u1EA0-\u1EF9\u1F00-\u1F15\u1F18-\u1F1D\u1F20-\u1F45\u1F48-\u1F4D\u1F50-\u1F57\u1F59\u1F5B\u1F5D\u1F5F-\u1F7D\u1F80-\u1FB4\u1FB6-\u1FBC\u1FBE\u1FC2-\u1FC4\u1FC6-\u1FCC\u1FD0-\u1FD3\u1FD6-\u1FDB\u1FE0-\u1FEC\u1FF2-\u1FF4\u1FF6-\u1FFC\u2126\u212A-\u212B\u212E\u2180-\u2182\u3007\u3021-\u3029\u3041-\u3094\u30A1-\u30FA\u3105-\u312C\u4E00-\u9FA5\uAC00-\uD7A3",           
     r"\I": ur"^_:\u0041-\u005A\u0061-\u007A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u0131\u0134-\u013E\u0141-\u0148\u014A-\u017E\u0180-\u01C3\u01CD-\u01F0\u01F4-\u01F5\u01FA-\u0217\u0250-\u02A8\u02BB-\u02C1\u0386\u0388-\u038A\u038C\u038E-\u03A1\u03A3-\u03CE\u03D0-\u03D6\u03DA\u03DC\u03DE\u03E0\u03E2-\u03F3\u0401-\u040C\u040E-\u044F\u0451-\u045C\u045E-\u0481\u0490-\u04C4\u04C7-\u04C8\u04CB-\u04CC\u04D0-\u04EB\u04EE-\u04F5\u04F8-\u04F9\u0531-\u0556\u0559\u0561-\u0586\u05D0-\u05EA\u05F0-\u05F2\u0621-\u063A\u0641-\u064A\u0671-\u06B7\u06BA-\u06BE\u06C0-\u06CE\u06D0-\u06D3\u06D5\u06E5-\u06E6\u0905-\u0939\u093D\u0958-\u0961\u0985-\u098C\u098F-\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09DC-\u09DD\u09DF-\u09E1\u09F0-\u09F1\u0A05-\u0A0A\u0A0F-\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32-\u0A33\u0A35-\u0A36\u0A38-\u0A39\u0A59-\u0A5C\u0A5E\u0A72-\u0A74\u0A85-\u0A8B\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2-\u0AB3\u0AB5-\u0AB9\u0ABD\u0AE0\u0B05-\u0B0C\u0B0F-\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32-\u0B33\u0B36-\u0B39\u0B3D\u0B5C-\u0B5D\u0B5F-\u0B61\u0B85-\u0B8A\u0B8E-\u0B90\u0B92-\u0B95\u0B99-\u0B9A\u0B9C\u0B9E-\u0B9F\u0BA3-\u0BA4\u0BA8-\u0BAA\u0BAE-\u0BB5\u0BB7-\u0BB9\u0C05-\u0C0C\u0C0E-\u0C10\u0C12-\u0C28\u0C2A-\u0C33\u0C35-\u0C39\u0C60-\u0C61\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CDE\u0CE0-\u0CE1\u0D05-\u0D0C\u0D0E-\u0D10\u0D12-\u0D28\u0D2A-\u0D39\u0D60-\u0D61\u0E01-\u0E2E\u0E30\u0E32-\u0E33\u0E40-\u0E45\u0E81-\u0E82\u0E84\u0E87-\u0E88\u0E8A\u0E8D\u0E94-\u0E97\u0E99-\u0E9F\u0EA1-\u0EA3\u0EA5\u0EA7\u0EAA-\u0EAB\u0EAD-\u0EAE\u0EB0\u0EB2-\u0EB3\u0EBD\u0EC0-\u0EC4\u0F40-\u0F47\u0F49-\u0F69\u10A0-\u10C5\u10D0-\u10F6\u1100\u1102-\u1103\u1105-\u1107\u1109\u110B-\u110C\u110E-\u1112\u113C\u113E\u1140\u114C\u114E\u1150\u1154-\u1155\u1159\u115F-\u1161\u1163\u1165\u1167\u1169\u116D-\u116E\u1172-\u1173\u1175\u119E\u11A8\u11AB\u11AE-\u11AF\u11B7-\u11B8\u11BA\u11BC-\u11C2\u11EB\u11F0\u11F9\u1E00-\u1E9B\u1EA0-\u1EF9\u1F00-\u1F15\u1F18-\u1F1D\u1F20-\u1F45\u1F48-\u1F4D\u1F50-\u1F57\u1F59\u1F5B\u1F5D\u1F5F-\u1F7D\u1F80-\u1FB4\u1FB6-\u1FBC\u1FBE\u1FC2-\u1FC4\u1FC6-\u1FCC\u1FD0-\u1FD3\u1FD6-\u1FDB\u1FE0-\u1FEC\u1FF2-\u1FF4\u1FF6-\u1FFC\u2126\u212A-\u212B\u212E\u2180-\u2182\u3007\u3021-\u3029\u3041-\u3094\u30A1-\u30FA\u3105-\u312C\u4E00-\u9FA5\uAC00-\uD7A3",          
     r"\c": ur"_:\-.\u0041-\u005A\u0061-\u007A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u0131\u0134-\u013E\u0141-\u0148\u014A-\u017E\u0180-\u01C3\u01CD-\u01F0\u01F4-\u01F5\u01FA-\u0217\u0250-\u02A8\u02BB-\u02C1\u0386\u0388-\u038A\u038C\u038E-\u03A1\u03A3-\u03CE\u03D0-\u03D6\u03DA\u03DC\u03DE\u03E0\u03E2-\u03F3\u0401-\u040C\u040E-\u044F\u0451-\u045C\u045E-\u0481\u0490-\u04C4\u04C7-\u04C8\u04CB-\u04CC\u04D0-\u04EB\u04EE-\u04F5\u04F8-\u04F9\u0531-\u0556\u0559\u0561-\u0586\u05D0-\u05EA\u05F0-\u05F2\u0621-\u063A\u0641-\u064A\u0671-\u06B7\u06BA-\u06BE\u06C0-\u06CE\u06D0-\u06D3\u06D5\u06E5-\u06E6\u0905-\u0939\u093D\u0958-\u0961\u0985-\u098C\u098F-\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09DC-\u09DD\u09DF-\u09E1\u09F0-\u09F1\u0A05-\u0A0A\u0A0F-\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32-\u0A33\u0A35-\u0A36\u0A38-\u0A39\u0A59-\u0A5C\u0A5E\u0A72-\u0A74\u0A85-\u0A8B\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2-\u0AB3\u0AB5-\u0AB9\u0ABD\u0AE0\u0B05-\u0B0C\u0B0F-\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32-\u0B33\u0B36-\u0B39\u0B3D\u0B5C-\u0B5D\u0B5F-\u0B61\u0B85-\u0B8A\u0B8E-\u0B90\u0B92-\u0B95\u0B99-\u0B9A\u0B9C\u0B9E-\u0B9F\u0BA3-\u0BA4\u0BA8-\u0BAA\u0BAE-\u0BB5\u0BB7-\u0BB9\u0C05-\u0C0C\u0C0E-\u0C10\u0C12-\u0C28\u0C2A-\u0C33\u0C35-\u0C39\u0C60-\u0C61\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CDE\u0CE0-\u0CE1\u0D05-\u0D0C\u0D0E-\u0D10\u0D12-\u0D28\u0D2A-\u0D39\u0D60-\u0D61\u0E01-\u0E2E\u0E30\u0E32-\u0E33\u0E40-\u0E45\u0E81-\u0E82\u0E84\u0E87-\u0E88\u0E8A\u0E8D\u0E94-\u0E97\u0E99-\u0E9F\u0EA1-\u0EA3\u0EA5\u0EA7\u0EAA-\u0EAB\u0EAD-\u0EAE\u0EB0\u0EB2-\u0EB3\u0EBD\u0EC0-\u0EC4\u0F40-\u0F47\u0F49-\u0F69\u10A0-\u10C5\u10D0-\u10F6\u1100\u1102-\u1103\u1105-\u1107\u1109\u110B-\u110C\u110E-\u1112\u113C\u113E\u1140\u114C\u114E\u1150\u1154-\u1155\u1159\u115F-\u1161\u1163\u1165\u1167\u1169\u116D-\u116E\u1172-\u1173\u1175\u119E\u11A8\u11AB\u11AE-\u11AF\u11B7-\u11B8\u11BA\u11BC-\u11C2\u11EB\u11F0\u11F9\u1E00-\u1E9B\u1EA0-\u1EF9\u1F00-\u1F15\u1F18-\u1F1D\u1F20-\u1F45\u1F48-\u1F4D\u1F50-\u1F57\u1F59\u1F5B\u1F5D\u1F5F-\u1F7D\u1F80-\u1FB4\u1FB6-\u1FBC\u1FBE\u1FC2-\u1FC4\u1FC6-\u1FCC\u1FD0-\u1FD3\u1FD6-\u1FDB\u1FE0-\u1FEC\u1FF2-\u1FF4\u1FF6-\u1FFC\u2126\u212A-\u212B\u212E\u2180-\u2182\u3041-\u3094\u30A1-\u30FA\u3105-\u312C\uAC00-\uD7A3\u4E00-\u9FA5\u3007\u3021-\u3029\u0300-\u0345\u0360-\u0361\u0483-\u0486\u0591-\u05A1\u05A3-\u05B9\u05BB-\u05BD\u05BF\u05C1-\u05C2\u05C4\u064B-\u0652\u0670\u06D6-\u06DC\u06DD-\u06DF\u06E0-\u06E4\u06E7-\u06E8\u06EA-\u06ED\u0901-\u0903\u093C\u093E-\u094C\u094D\u0951-\u0954\u0962-\u0963\u0981-\u0983\u09BC\u09BE\u09BF\u09C0-\u09C4\u09C7-\u09C8\u09CB-\u09CD\u09D7\u09E2-\u09E3\u0A02\u0A3C\u0A3E\u0A3F\u0A40-\u0A42\u0A47-\u0A48\u0A4B-\u0A4D\u0A70-\u0A71\u0A81-\u0A83\u0ABC\u0ABE-\u0AC5\u0AC7-\u0AC9\u0ACB-\u0ACD\u0B01-\u0B03\u0B3C\u0B3E-\u0B43\u0B47-\u0B48\u0B4B-\u0B4D\u0B56-\u0B57\u0B82-\u0B83\u0BBE-\u0BC2\u0BC6-\u0BC8\u0BCA-\u0BCD\u0BD7\u0C01-\u0C03\u0C3E-\u0C44\u0C46-\u0C48\u0C4A-\u0C4D\u0C55-\u0C56\u0C82-\u0C83\u0CBE-\u0CC4\u0CC6-\u0CC8\u0CCA-\u0CCD\u0CD5-\u0CD6\u0D02-\u0D03\u0D3E-\u0D43\u0D46-\u0D48\u0D4A-\u0D4D\u0D57\u0E31\u0E34-\u0E3A\u0E47-\u0E4E\u0EB1\u0EB4-\u0EB9\u0EBB-\u0EBC\u0EC8-\u0ECD\u0F18-\u0F19\u0F35\u0F37\u0F39\u0F3E\u0F3F\u0F71-\u0F84\u0F86-\u0F8B\u0F90-\u0F95\u0F97\u0F99-\u0FAD\u0FB1-\u0FB7\u0FB9\u20D0-\u20DC\u20E1\u302A-\u302F\u3099\u309A\u0030-\u0039\u0660-\u0669\u06F0-\u06F9\u0966-\u096F\u09E6-\u09EF\u0A66-\u0A6F\u0AE6-\u0AEF\u0B66-\u0B6F\u0BE7-\u0BEF\u0C66-\u0C6F\u0CE6-\u0CEF\u0D66-\u0D6F\u0E50-\u0E59\u0ED0-\u0ED9\u0F20-\u0F29\u00B7\u02D0\u02D1\u0387\u0640\u0E46\u0EC6\u3005\u3031-\u3035\u309D-\u309E\u30FC-\u30FE",             
     r"\C": ur"^_:\-.\u0041-\u005A\u0061-\u007A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u0131\u0134-\u013E\u0141-\u0148\u014A-\u017E\u0180-\u01C3\u01CD-\u01F0\u01F4-\u01F5\u01FA-\u0217\u0250-\u02A8\u02BB-\u02C1\u0386\u0388-\u038A\u038C\u038E-\u03A1\u03A3-\u03CE\u03D0-\u03D6\u03DA\u03DC\u03DE\u03E0\u03E2-\u03F3\u0401-\u040C\u040E-\u044F\u0451-\u045C\u045E-\u0481\u0490-\u04C4\u04C7-\u04C8\u04CB-\u04CC\u04D0-\u04EB\u04EE-\u04F5\u04F8-\u04F9\u0531-\u0556\u0559\u0561-\u0586\u05D0-\u05EA\u05F0-\u05F2\u0621-\u063A\u0641-\u064A\u0671-\u06B7\u06BA-\u06BE\u06C0-\u06CE\u06D0-\u06D3\u06D5\u06E5-\u06E6\u0905-\u0939\u093D\u0958-\u0961\u0985-\u098C\u098F-\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09DC-\u09DD\u09DF-\u09E1\u09F0-\u09F1\u0A05-\u0A0A\u0A0F-\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32-\u0A33\u0A35-\u0A36\u0A38-\u0A39\u0A59-\u0A5C\u0A5E\u0A72-\u0A74\u0A85-\u0A8B\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2-\u0AB3\u0AB5-\u0AB9\u0ABD\u0AE0\u0B05-\u0B0C\u0B0F-\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32-\u0B33\u0B36-\u0B39\u0B3D\u0B5C-\u0B5D\u0B5F-\u0B61\u0B85-\u0B8A\u0B8E-\u0B90\u0B92-\u0B95\u0B99-\u0B9A\u0B9C\u0B9E-\u0B9F\u0BA3-\u0BA4\u0BA8-\u0BAA\u0BAE-\u0BB5\u0BB7-\u0BB9\u0C05-\u0C0C\u0C0E-\u0C10\u0C12-\u0C28\u0C2A-\u0C33\u0C35-\u0C39\u0C60-\u0C61\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CDE\u0CE0-\u0CE1\u0D05-\u0D0C\u0D0E-\u0D10\u0D12-\u0D28\u0D2A-\u0D39\u0D60-\u0D61\u0E01-\u0E2E\u0E30\u0E32-\u0E33\u0E40-\u0E45\u0E81-\u0E82\u0E84\u0E87-\u0E88\u0E8A\u0E8D\u0E94-\u0E97\u0E99-\u0E9F\u0EA1-\u0EA3\u0EA5\u0EA7\u0EAA-\u0EAB\u0EAD-\u0EAE\u0EB0\u0EB2-\u0EB3\u0EBD\u0EC0-\u0EC4\u0F40-\u0F47\u0F49-\u0F69\u10A0-\u10C5\u10D0-\u10F6\u1100\u1102-\u1103\u1105-\u1107\u1109\u110B-\u110C\u110E-\u1112\u113C\u113E\u1140\u114C\u114E\u1150\u1154-\u1155\u1159\u115F-\u1161\u1163\u1165\u1167\u1169\u116D-\u116E\u1172-\u1173\u1175\u119E\u11A8\u11AB\u11AE-\u11AF\u11B7-\u11B8\u11BA\u11BC-\u11C2\u11EB\u11F0\u11F9\u1E00-\u1E9B\u1EA0-\u1EF9\u1F00-\u1F15\u1F18-\u1F1D\u1F20-\u1F45\u1F48-\u1F4D\u1F50-\u1F57\u1F59\u1F5B\u1F5D\u1F5F-\u1F7D\u1F80-\u1FB4\u1FB6-\u1FBC\u1FBE\u1FC2-\u1FC4\u1FC6-\u1FCC\u1FD0-\u1FD3\u1FD6-\u1FDB\u1FE0-\u1FEC\u1FF2-\u1FF4\u1FF6-\u1FFC\u2126\u212A-\u212B\u212E\u2180-\u2182\u3041-\u3094\u30A1-\u30FA\u3105-\u312C\uAC00-\uD7A3\u4E00-\u9FA5\u3007\u3021-\u3029\u0300-\u0345\u0360-\u0361\u0483-\u0486\u0591-\u05A1\u05A3-\u05B9\u05BB-\u05BD\u05BF\u05C1-\u05C2\u05C4\u064B-\u0652\u0670\u06D6-\u06DC\u06DD-\u06DF\u06E0-\u06E4\u06E7-\u06E8\u06EA-\u06ED\u0901-\u0903\u093C\u093E-\u094C\u094D\u0951-\u0954\u0962-\u0963\u0981-\u0983\u09BC\u09BE\u09BF\u09C0-\u09C4\u09C7-\u09C8\u09CB-\u09CD\u09D7\u09E2-\u09E3\u0A02\u0A3C\u0A3E\u0A3F\u0A40-\u0A42\u0A47-\u0A48\u0A4B-\u0A4D\u0A70-\u0A71\u0A81-\u0A83\u0ABC\u0ABE-\u0AC5\u0AC7-\u0AC9\u0ACB-\u0ACD\u0B01-\u0B03\u0B3C\u0B3E-\u0B43\u0B47-\u0B48\u0B4B-\u0B4D\u0B56-\u0B57\u0B82-\u0B83\u0BBE-\u0BC2\u0BC6-\u0BC8\u0BCA-\u0BCD\u0BD7\u0C01-\u0C03\u0C3E-\u0C44\u0C46-\u0C48\u0C4A-\u0C4D\u0C55-\u0C56\u0C82-\u0C83\u0CBE-\u0CC4\u0CC6-\u0CC8\u0CCA-\u0CCD\u0CD5-\u0CD6\u0D02-\u0D03\u0D3E-\u0D43\u0D46-\u0D48\u0D4A-\u0D4D\u0D57\u0E31\u0E34-\u0E3A\u0E47-\u0E4E\u0EB1\u0EB4-\u0EB9\u0EBB-\u0EBC\u0EC8-\u0ECD\u0F18-\u0F19\u0F35\u0F37\u0F39\u0F3E\u0F3F\u0F71-\u0F84\u0F86-\u0F8B\u0F90-\u0F95\u0F97\u0F99-\u0FAD\u0FB1-\u0FB7\u0FB9\u20D0-\u20DC\u20E1\u302A-\u302F\u3099\u309A\u0030-\u0039\u0660-\u0669\u06F0-\u06F9\u0966-\u096F\u09E6-\u09EF\u0A66-\u0A6F\u0AE6-\u0AEF\u0B66-\u0B6F\u0BE7-\u0BEF\u0C66-\u0C6F\u0CE6-\u0CEF\u0D66-\u0D6F\u0E50-\u0E59\u0ED0-\u0ED9\u0F20-\u0F29\u00B7\u02D0\u02D1\u0387\u0640\u0E46\u0EC6\u3005\u3031-\u3035\u309D-\u309E\u30FC-\u30FE",            
      }

substSpecialEscList = (             
     (r"[\i-[:]]", ur"[_\u0041-\u005A\u0061-\u007A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u0131\u0134-\u013E\u0141-\u0148\u014A-\u017E\u0180-\u01C3\u01CD-\u01F0\u01F4-\u01F5\u01FA-\u0217\u0250-\u02A8\u02BB-\u02C1\u0386\u0388-\u038A\u038C\u038E-\u03A1\u03A3-\u03CE\u03D0-\u03D6\u03DA\u03DC\u03DE\u03E0\u03E2-\u03F3\u0401-\u040C\u040E-\u044F\u0451-\u045C\u045E-\u0481\u0490-\u04C4\u04C7-\u04C8\u04CB-\u04CC\u04D0-\u04EB\u04EE-\u04F5\u04F8-\u04F9\u0531-\u0556\u0559\u0561-\u0586\u05D0-\u05EA\u05F0-\u05F2\u0621-\u063A\u0641-\u064A\u0671-\u06B7\u06BA-\u06BE\u06C0-\u06CE\u06D0-\u06D3\u06D5\u06E5-\u06E6\u0905-\u0939\u093D\u0958-\u0961\u0985-\u098C\u098F-\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09DC-\u09DD\u09DF-\u09E1\u09F0-\u09F1\u0A05-\u0A0A\u0A0F-\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32-\u0A33\u0A35-\u0A36\u0A38-\u0A39\u0A59-\u0A5C\u0A5E\u0A72-\u0A74\u0A85-\u0A8B\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2-\u0AB3\u0AB5-\u0AB9\u0ABD\u0AE0\u0B05-\u0B0C\u0B0F-\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32-\u0B33\u0B36-\u0B39\u0B3D\u0B5C-\u0B5D\u0B5F-\u0B61\u0B85-\u0B8A\u0B8E-\u0B90\u0B92-\u0B95\u0B99-\u0B9A\u0B9C\u0B9E-\u0B9F\u0BA3-\u0BA4\u0BA8-\u0BAA\u0BAE-\u0BB5\u0BB7-\u0BB9\u0C05-\u0C0C\u0C0E-\u0C10\u0C12-\u0C28\u0C2A-\u0C33\u0C35-\u0C39\u0C60-\u0C61\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CDE\u0CE0-\u0CE1\u0D05-\u0D0C\u0D0E-\u0D10\u0D12-\u0D28\u0D2A-\u0D39\u0D60-\u0D61\u0E01-\u0E2E\u0E30\u0E32-\u0E33\u0E40-\u0E45\u0E81-\u0E82\u0E84\u0E87-\u0E88\u0E8A\u0E8D\u0E94-\u0E97\u0E99-\u0E9F\u0EA1-\u0EA3\u0EA5\u0EA7\u0EAA-\u0EAB\u0EAD-\u0EAE\u0EB0\u0EB2-\u0EB3\u0EBD\u0EC0-\u0EC4\u0F40-\u0F47\u0F49-\u0F69\u10A0-\u10C5\u10D0-\u10F6\u1100\u1102-\u1103\u1105-\u1107\u1109\u110B-\u110C\u110E-\u1112\u113C\u113E\u1140\u114C\u114E\u1150\u1154-\u1155\u1159\u115F-\u1161\u1163\u1165\u1167\u1169\u116D-\u116E\u1172-\u1173\u1175\u119E\u11A8\u11AB\u11AE-\u11AF\u11B7-\u11B8\u11BA\u11BC-\u11C2\u11EB\u11F0\u11F9\u1E00-\u1E9B\u1EA0-\u1EF9\u1F00-\u1F15\u1F18-\u1F1D\u1F20-\u1F45\u1F48-\u1F4D\u1F50-\u1F57\u1F59\u1F5B\u1F5D\u1F5F-\u1F7D\u1F80-\u1FB4\u1FB6-\u1FBC\u1FBE\u1FC2-\u1FC4\u1FC6-\u1FCC\u1FD0-\u1FD3\u1FD6-\u1FDB\u1FE0-\u1FEC\u1FF2-\u1FF4\u1FF6-\u1FFC\u2126\u212A-\u212B\u212E\u2180-\u2182\u3007\u3021-\u3029\u3041-\u3094\u30A1-\u30FA\u3105-\u312C\u4E00-\u9FA5\uAC00-\uD7A3]"),           
     (r"[\c-[:]]", ur"[_\-.\u0041-\u005A\u0061-\u007A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u0131\u0134-\u013E\u0141-\u0148\u014A-\u017E\u0180-\u01C3\u01CD-\u01F0\u01F4-\u01F5\u01FA-\u0217\u0250-\u02A8\u02BB-\u02C1\u0386\u0388-\u038A\u038C\u038E-\u03A1\u03A3-\u03CE\u03D0-\u03D6\u03DA\u03DC\u03DE\u03E0\u03E2-\u03F3\u0401-\u040C\u040E-\u044F\u0451-\u045C\u045E-\u0481\u0490-\u04C4\u04C7-\u04C8\u04CB-\u04CC\u04D0-\u04EB\u04EE-\u04F5\u04F8-\u04F9\u0531-\u0556\u0559\u0561-\u0586\u05D0-\u05EA\u05F0-\u05F2\u0621-\u063A\u0641-\u064A\u0671-\u06B7\u06BA-\u06BE\u06C0-\u06CE\u06D0-\u06D3\u06D5\u06E5-\u06E6\u0905-\u0939\u093D\u0958-\u0961\u0985-\u098C\u098F-\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09DC-\u09DD\u09DF-\u09E1\u09F0-\u09F1\u0A05-\u0A0A\u0A0F-\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32-\u0A33\u0A35-\u0A36\u0A38-\u0A39\u0A59-\u0A5C\u0A5E\u0A72-\u0A74\u0A85-\u0A8B\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2-\u0AB3\u0AB5-\u0AB9\u0ABD\u0AE0\u0B05-\u0B0C\u0B0F-\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32-\u0B33\u0B36-\u0B39\u0B3D\u0B5C-\u0B5D\u0B5F-\u0B61\u0B85-\u0B8A\u0B8E-\u0B90\u0B92-\u0B95\u0B99-\u0B9A\u0B9C\u0B9E-\u0B9F\u0BA3-\u0BA4\u0BA8-\u0BAA\u0BAE-\u0BB5\u0BB7-\u0BB9\u0C05-\u0C0C\u0C0E-\u0C10\u0C12-\u0C28\u0C2A-\u0C33\u0C35-\u0C39\u0C60-\u0C61\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CDE\u0CE0-\u0CE1\u0D05-\u0D0C\u0D0E-\u0D10\u0D12-\u0D28\u0D2A-\u0D39\u0D60-\u0D61\u0E01-\u0E2E\u0E30\u0E32-\u0E33\u0E40-\u0E45\u0E81-\u0E82\u0E84\u0E87-\u0E88\u0E8A\u0E8D\u0E94-\u0E97\u0E99-\u0E9F\u0EA1-\u0EA3\u0EA5\u0EA7\u0EAA-\u0EAB\u0EAD-\u0EAE\u0EB0\u0EB2-\u0EB3\u0EBD\u0EC0-\u0EC4\u0F40-\u0F47\u0F49-\u0F69\u10A0-\u10C5\u10D0-\u10F6\u1100\u1102-\u1103\u1105-\u1107\u1109\u110B-\u110C\u110E-\u1112\u113C\u113E\u1140\u114C\u114E\u1150\u1154-\u1155\u1159\u115F-\u1161\u1163\u1165\u1167\u1169\u116D-\u116E\u1172-\u1173\u1175\u119E\u11A8\u11AB\u11AE-\u11AF\u11B7-\u11B8\u11BA\u11BC-\u11C2\u11EB\u11F0\u11F9\u1E00-\u1E9B\u1EA0-\u1EF9\u1F00-\u1F15\u1F18-\u1F1D\u1F20-\u1F45\u1F48-\u1F4D\u1F50-\u1F57\u1F59\u1F5B\u1F5D\u1F5F-\u1F7D\u1F80-\u1FB4\u1FB6-\u1FBC\u1FBE\u1FC2-\u1FC4\u1FC6-\u1FCC\u1FD0-\u1FD3\u1FD6-\u1FDB\u1FE0-\u1FEC\u1FF2-\u1FF4\u1FF6-\u1FFC\u2126\u212A-\u212B\u212E\u2180-\u2182\u3041-\u3094\u30A1-\u30FA\u3105-\u312C\uAC00-\uD7A3\u4E00-\u9FA5\u3007\u3021-\u3029\u0300-\u0345\u0360-\u0361\u0483-\u0486\u0591-\u05A1\u05A3-\u05B9\u05BB-\u05BD\u05BF\u05C1-\u05C2\u05C4\u064B-\u0652\u0670\u06D6-\u06DC\u06DD-\u06DF\u06E0-\u06E4\u06E7-\u06E8\u06EA-\u06ED\u0901-\u0903\u093C\u093E-\u094C\u094D\u0951-\u0954\u0962-\u0963\u0981-\u0983\u09BC\u09BE\u09BF\u09C0-\u09C4\u09C7-\u09C8\u09CB-\u09CD\u09D7\u09E2-\u09E3\u0A02\u0A3C\u0A3E\u0A3F\u0A40-\u0A42\u0A47-\u0A48\u0A4B-\u0A4D\u0A70-\u0A71\u0A81-\u0A83\u0ABC\u0ABE-\u0AC5\u0AC7-\u0AC9\u0ACB-\u0ACD\u0B01-\u0B03\u0B3C\u0B3E-\u0B43\u0B47-\u0B48\u0B4B-\u0B4D\u0B56-\u0B57\u0B82-\u0B83\u0BBE-\u0BC2\u0BC6-\u0BC8\u0BCA-\u0BCD\u0BD7\u0C01-\u0C03\u0C3E-\u0C44\u0C46-\u0C48\u0C4A-\u0C4D\u0C55-\u0C56\u0C82-\u0C83\u0CBE-\u0CC4\u0CC6-\u0CC8\u0CCA-\u0CCD\u0CD5-\u0CD6\u0D02-\u0D03\u0D3E-\u0D43\u0D46-\u0D48\u0D4A-\u0D4D\u0D57\u0E31\u0E34-\u0E3A\u0E47-\u0E4E\u0EB1\u0EB4-\u0EB9\u0EBB-\u0EBC\u0EC8-\u0ECD\u0F18-\u0F19\u0F35\u0F37\u0F39\u0F3E\u0F3F\u0F71-\u0F84\u0F86-\u0F8B\u0F90-\u0F95\u0F97\u0F99-\u0FAD\u0FB1-\u0FB7\u0FB9\u20D0-\u20DC\u20E1\u302A-\u302F\u3099\u309A\u0030-\u0039\u0660-\u0669\u06F0-\u06F9\u0966-\u096F\u09E6-\u09EF\u0A66-\u0A6F\u0AE6-\u0AEF\u0B66-\u0B6F\u0BE7-\u0BEF\u0C66-\u0C6F\u0CE6-\u0CEF\u0D66-\u0D6F\u0E50-\u0E59\u0ED0-\u0ED9\u0F20-\u0F29\u00B7\u02D0\u02D1\u0387\u0640\u0E46\u0EC6\u3005\u3031-\u3035\u309D-\u309E\u30FC-\u30FE]"),
     )

########################################
# substitute some multichar escape characters
# which are not handled by the standard python re module
#
def substituteSpecialEscChars (intRePattern):
    for specialEsc, repl in substSpecialEscList:
        intRePattern = string.replace(intRePattern, specialEsc, repl)

    substituteDict = {}
    for regexObj in creMultiCharEscP.finditer(intRePattern):
        if not (len(regexObj.group('pbs')) & 1): # even number of preceding backslashes
            id = regexObj.group('id')
            pP = regexObj.group('pP')
            if not substMultiCharEscPDict.has_key(id):
                raise SyntaxError, r"Unknown MultiCharEscape sequence '\%s{%s}' found!" %(pP, id)
            else:
                inv = 0
                invstr = ""
                if pP == "P": inv ^= 1
                if regexObj.group('inv') == '^': 
                    inv ^= 1
                if inv: invstr = "^"
                if creWithinSet.match(intRePattern[:regexObj.start("escSeq")]):
                    substituteDict[(regexObj.start("escSeq"), regexObj.end("escSeq"))] = ur"%s%s" %(invstr, substMultiCharEscPDict[id])
                else:
                    substituteDict[(regexObj.start("escSeq"), regexObj.end("escSeq"))] = ur"[%s%s]" %(invstr, substMultiCharEscPDict[id])

    for regexObj in creSingleCharEsc.finditer(intRePattern):
        if not (len(regexObj.group('pbs')) & 1): # even number of preceding backslashes
            foundStr = regexObj.group("escChar")
            if not substSingleCharEscDict.has_key(foundStr):
                raise SyntaxError, "Unknown SingleCharEscape sequence '%s' found!" %(foundStr)
            else:
                regexObjWithinSet = creWithinSet.match(intRePattern[:regexObj.start("escChar")])
                if regexObjWithinSet:
                    substituteDict[(regexObj.start("escChar"), regexObj.end("escChar"))] = ur"%s" %substSingleCharEscDict[foundStr]
                else:
                    substituteDict[(regexObj.start("escChar"), regexObj.end("escChar"))] = ur"[%s]" %substSingleCharEscDict[foundStr]

    if substituteDict != {}:
        strFragList = []
        lastPos = 0
        keyList = substituteDict.keys()
        keyList.sort()
        for startPos, endPos in keyList:
            strFragList.append(intRePattern[lastPos:startPos])
            strFragList.append(substituteDict[(startPos,endPos)])
            lastPos = endPos
        strFragList.append(intRePattern[lastPos:])
        expandedPattern = "".join(strFragList)
    else:
        expandedPattern = intRePattern
        
    return expandedPattern