We Keep Coding

Fastest way to count non spacing chars in Unicode text in Python

Given the Unicode non spacing marks list - https://www.fileformat.info/info/unicode/category/Mn/list.htm
UNICODE_NSM = ['\u0300', '\u0301', '\u0302', '\u0303', '\u0304', '\u0305', '\u0306', '\u0307', '\u0308', '\u0309', '\u030A', '\u030B', '\u030C', '\u030D', '\u030E', '\u030F', '\u0310', '\u0311', '\u0312', '\u0313', '\u0314', '\u0315', '\u0316', '\u0317', '\u0318', '\u0319', '\u031A', '\u031B', '\u031C', '\u031D', '\u031E', '\u031F', '\u0320', '\u0321', '\u0322', '\u0323', '\u0324', '\u0325', '\u0326', '\u0327', '\u0328', '\u0329', '\u032A', '\u032B', '\u032C', '\u032D', '\u032E', '\u032F', '\u0330', '\u0331', '\u0332', '\u0333', '\u0334', '\u0335', '\u0336', '\u0337', '\u0338', '\u0339', '\u033A', '\u033B', '\u033C', '\u033D', '\u033E', '\u033F', '\u0340', '\u0341', '\u0342', '\u0343', '\u0344', '\u0345', '\u0346', '\u0347', '\u0348', '\u0349', '\u034A', '\u034B', '\u034C', '\u034D', '\u034E', '\u034F', '\u0350', '\u0351', '\u0352', '\u0353', '\u0354', '\u0355', '\u0356', '\u0357', '\u0358', '\u0359', '\u035A', '\u035B', '\u035C', '\u035D', '\u035E', '\u035F', '\u0360', '\u0361', '\u0362', '\u0363', '\u0364', '\u0365', '\u0366', '\u0367', '\u0368', '\u0369', '\u036A', '\u036B', '\u036C', '\u036D', '\u036E', '\u036F', '\u0483', '\u0484', '\u0485', '\u0486', '\u0487', '\u0591', '\u0592', '\u0593', '\u0594', '\u0595', '\u0596', '\u0597', '\u0598', '\u0599', '\u059A', '\u059B', '\u059C', '\u059D', '\u059E', '\u059F', '\u05A0', '\u05A1', '\u05A2', '\u05A3', '\u05A4', '\u05A5', '\u05A6', '\u05A7', '\u05A8', '\u05A9', '\u05AA', '\u05AB', '\u05AC', '\u05AD', '\u05AE', '\u05AF', '\u05B0', '\u05B1', '\u05B2', '\u05B3', '\u05B4', '\u05B5', '\u05B6', '\u05B7', '\u05B8', '\u05B9', '\u05BA', '\u05BB', '\u05BC', '\u05BD', '\u05BF', '\u05C1', '\u05C2', '\u05C4', '\u05C5', '\u05C7', '\u0610', '\u0611', '\u0612', '\u0613', '\u0614', '\u0615', '\u0616', '\u0617', '\u0618', '\u0619', '\u061A', '\u064B', '\u064C', '\u064D', '\u064E', '\u064F', '\u0650', '\u0651', '\u0652', '\u0653', '\u0654', '\u0655', '\u0656', '\u0657', '\u0658', '\u0659', '\u065A', '\u065B', '\u065C', '\u065D', '\u065E', '\u065F', '\u0670', '\u06D6', '\u06D7', '\u06D8', '\u06D9', '\u06DA', '\u06DB', '\u06DC', '\u06DF', '\u06E0', '\u06E1', '\u06E2', '\u06E3', '\u06E4', '\u06E7', '\u06E8', '\u06EA', '\u06EB', '\u06EC', '\u06ED', '\u0711', '\u0730', '\u0731', '\u0732', '\u0733', '\u0734', '\u0735', '\u0736', '\u0737', '\u0738', '\u0739', '\u073A', '\u073B', '\u073C', '\u073D', '\u073E', '\u073F', '\u0740', '\u0741', '\u0742', '\u0743', '\u0744', '\u0745', '\u0746', '\u0747', '\u0748', '\u0749', '\u074A', '\u07A6', '\u07A7', '\u07A8', '\u07A9', '\u07AA', '\u07AB', '\u07AC', '\u07AD', '\u07AE', '\u07AF', '\u07B0', '\u07EB', '\u07EC', '\u07ED', '\u07EE', '\u07EF', '\u07F0', '\u07F1', '\u07F2', '\u07F3', '\u0816', '\u0817', '\u0818', '\u0819', '\u081B', '\u081C', '\u081D', '\u081E', '\u081F', '\u0820', '\u0821', '\u0822', '\u0823', '\u0825', '\u0826', '\u0827', '\u0829', '\u082A', '\u082B', '\u082C', '\u082D', '\u0859', '\u085A', '\u085B', '\u08E4', '\u08E5', '\u08E6', '\u08E7', '\u08E8', '\u08E9', '\u08EA', '\u08EB', '\u08EC', '\u08ED', '\u08EE', '\u08EF', '\u08F0', '\u08F1', '\u08F2', '\u08F3', '\u08F4', '\u08F5', '\u08F6', '\u08F7', '\u08F8', '\u08F9', '\u08FA', '\u08FB', '\u08FC', '\u08FD', '\u08FE', '\u0900', '\u0901', '\u0902', '\u093A', '\u093C', '\u093E', '\u0941', '\u0942', '\u0943', '\u0944', '\u0945', '\u0946', '\u0947', '\u0948', '\u094D', '\u0951', '\u0952', '\u0953', '\u0954', '\u0955', '\u0956', '\u0957', '\u0962', '\u0963', '\u0981', '\u09BC', '\u09C1', '\u09C2', '\u09C3', '\u09C4', '\u09CD', '\u09E2', '\u09E3', '\u0A01', '\u0A02', '\u0A3C', '\u0A41', '\u0A42', '\u0A47', '\u0A48', '\u0A4B', '\u0A4C', '\u0A4D', '\u0A51', '\u0A70', '\u0A71', '\u0A75', '\u0A81', '\u0A82', '\u0ABC', '\u0AC1', '\u0AC2', '\u0AC3', '\u0AC4', '\u0AC5', '\u0AC7', '\u0AC8', '\u0ACD', '\u0AE2', '\u0AE3', '\u0B01', '\u0B3C', '\u0B3F', '\u0B41', '\u0B42', '\u0B43', '\u0B44', '\u0B4D', '\u0B56', '\u0B62', '\u0B63', '\u0B82', '\u0BC0', '\u0BCD', '\u0C3E', '\u0C3F', '\u0C40', '\u0C46', '\u0C47', '\u0C48', '\u0C4A', '\u0C4B', '\u0C4C', '\u0C4D', '\u0C55', '\u0C56', '\u0C62', '\u0C63', '\u0CBC', '\u0CBF', '\u0CC6', '\u0CCC', '\u0CCD', '\u0CE2', '\u0CE3', '\u0D41', '\u0D42', '\u0D43', '\u0D44', '\u0D4D', '\u0D62', '\u0D63', '\u0DCA', '\u0DD2', '\u0DD3', '\u0DD4', '\u0DD6', '\u0E31', '\u0E34', '\u0E35', '\u0E36', '\u0E37', '\u0E38', '\u0E39', '\u0E3A', '\u0E47', '\u0E48', '\u0E49', '\u0E4A', '\u0E4B', '\u0E4C', '\u0E4D', '\u0E4E', '\u0EB1', '\u0EB4', '\u0EB5', '\u0EB6', '\u0EB7', '\u0EB8', '\u0EB9', '\u0EBB', '\u0EBC', '\u0EC8', '\u0EC9', '\u0ECA', '\u0ECB', '\u0ECC', '\u0ECD', '\u0F18', '\u0F19', '\u0F35', '\u0F37', '\u0F39', '\u0F71', '\u0F72', '\u0F73', '\u0F74', '\u0F75', '\u0F76', '\u0F77', '\u0F78', '\u0F79', '\u0F7A', '\u0F7B', '\u0F7C', '\u0F7D', '\u0F7E', '\u0F80', '\u0F81', '\u0F82', '\u0F83', '\u0F84', '\u0F86', '\u0F87', '\u0F8D', '\u0F8E', '\u0F8F', '\u0F90', '\u0F91', '\u0F92', '\u0F93', '\u0F94', '\u0F95', '\u0F96', '\u0F97', '\u0F99', '\u0F9A', '\u0F9B', '\u0F9C', '\u0F9D', '\u0F9E', '\u0F9F', '\u0FA0', '\u0FA1', '\u0FA2', '\u0FA3', '\u0FA4', '\u0FA5', '\u0FA6', '\u0FA7', '\u0FA8', '\u0FA9', '\u0FAA', '\u0FAB', '\u0FAC', '\u0FAD', '\u0FAE', '\u0FAF', '\u0FB0', '\u0FB1', '\u0FB2', '\u0FB3', '\u0FB4', '\u0FB5', '\u0FB6', '\u0FB7', '\u0FB8', '\u0FB9', '\u0FBA', '\u0FBB', '\u0FBC', '\u0FC6', '\u102D', '\u102E', '\u102F', '\u1030', '\u1032', '\u1033', '\u1034', '\u1035', '\u1036', '\u1037', '\u1039', '\u103A', '\u103D', '\u103E', '\u1058', '\u1059', '\u105E', '\u105F', '\u1060', '\u1071', '\u1072', '\u1073', '\u1074', '\u1082', '\u1085', '\u1086', '\u108D', '\u109D', '\u135D', '\u135E', '\u135F', '\u1712', '\u1713', '\u1714', '\u1732', '\u1733', '\u1734', '\u1752', '\u1753', '\u1772', '\u1773', '\u17B4', '\u17B5', '\u17B7', '\u17B8', '\u17B9', '\u17BA', '\u17BB', '\u17BC', '\u17BD', '\u17C6', '\u17C9', '\u17CA', '\u17CB', '\u17CC', '\u17CD', '\u17CE', '\u17CF', '\u17D0', '\u17D1', '\u17D2', '\u17D3', '\u17DD', '\u180B', '\u180C', '\u180D', '\u18A9', '\u1920', '\u1921', '\u1922', '\u1927', '\u1928', '\u1932', '\u1939', '\u193A', '\u193B', '\u1A17', '\u1A18', '\u1A56', '\u1A58', '\u1A59', '\u1A5A', '\u1A5B', '\u1A5C', '\u1A5D', '\u1A5E', '\u1A60', '\u1A62', '\u1A65', '\u1A66', '\u1A67', '\u1A68', '\u1A69', '\u1A6A', '\u1A6B', '\u1A6C', '\u1A73', '\u1A74', '\u1A75', '\u1A76', '\u1A77', '\u1A78', '\u1A79', '\u1A7A', '\u1A7B', '\u1A7C', '\u1A7F', '\u1B00', '\u1B01', '\u1B02', '\u1B03', '\u1B34', '\u1B36', '\u1B37', '\u1B38', '\u1B39', '\u1B3A', '\u1B3C', '\u1B42', '\u1B6B', '\u1B6C', '\u1B6D', '\u1B6E', '\u1B6F', '\u1B70', '\u1B71', '\u1B72', '\u1B73', '\u1B80', '\u1B81', '\u1BA2', '\u1BA3', '\u1BA4', '\u1BA5', '\u1BA8', '\u1BA9', '\u1BAB', '\u1BE6', '\u1BE8', '\u1BE9', '\u1BED', '\u1BEF', '\u1BF0', '\u1BF1', '\u1C2C', '\u1C2D', '\u1C2E', '\u1C2F', '\u1C30', '\u1C31', '\u1C32', '\u1C33', '\u1C36', '\u1C37', '\u1CD0', '\u1CD1', '\u1CD2', '\u1CD4', '\u1CD5', '\u1CD6', '\u1CD7', '\u1CD8', '\u1CD9', '\u1CDA', '\u1CDB', '\u1CDC', '\u1CDD', '\u1CDE', '\u1CDF', '\u1CE0', '\u1CE2', '\u1CE3', '\u1CE4', '\u1CE5', '\u1CE6', '\u1CE7', '\u1CE8', '\u1CED', '\u1CF4', '\u1DC0', '\u1DC1', '\u1DC2', '\u1DC3', '\u1DC4', '\u1DC5', '\u1DC6', '\u1DC7', '\u1DC8', '\u1DC9', '\u1DCA', '\u1DCB', '\u1DCC', '\u1DCD', '\u1DCE', '\u1DCF', '\u1DD0', '\u1DD1', '\u1DD2', '\u1DD3', '\u1DD4', '\u1DD5', '\u1DD6', '\u1DD7', '\u1DD8', '\u1DD9', '\u1DDA', '\u1DDB', '\u1DDC', '\u1DDD', '\u1DDE', '\u1DDF', '\u1DE0', '\u1DE1', '\u1DE2', '\u1DE3', '\u1DE4', '\u1DE5', '\u1DE6', '\u1DFC', '\u1DFD', '\u1DFE', '\u1DFF', '\u20D0', '\u20D1', '\u20D2', '\u20D3', '\u20D4', '\u20D5', '\u20D6', '\u20D7', '\u20D8', '\u20D9', '\u20DA', '\u20DB', '\u20DC', '\u20E1', '\u20E5', '\u20E6', '\u20E7', '\u20E8', '\u20E9', '\u20EA', '\u20EB', '\u20EC', '\u20ED', '\u20EE', '\u20EF', '\u20F0', '\u2CEF', '\u2CF0', '\u2CF1', '\u2D7F', '\u2DE0', '\u2DE1', '\u2DE2', '\u2DE3', '\u2DE4', '\u2DE5', '\u2DE6', '\u2DE7', '\u2DE8', '\u2DE9', '\u2DEA', '\u2DEB', '\u2DEC', '\u2DED', '\u2DEE', '\u2DEF', '\u2DF0', '\u2DF1', '\u2DF2', '\u2DF3', '\u2DF4', '\u2DF5', '\u2DF6', '\u2DF7', '\u2DF8', '\u2DF9', '\u2DFA', '\u2DFB', '\u2DFC', '\u2DFD', '\u2DFE', '\u2DFF', '\u302A', '\u302B', '\u302C', '\u302D', '\u3099', '\u309A', '\uA66F', '\uA674', '\uA675', '\uA676', '\uA677', '\uA678', '\uA679', '\uA67A', '\uA67B', '\uA67C', '\uA67D', '\uA69F', '\uA6F0', '\uA6F1', '\uA802', '\uA806', '\uA80B', '\uA825', '\uA826', '\uA8C4', '\uA8E0', '\uA8E1', '\uA8E2', '\uA8E3', '\uA8E4', '\uA8E5', '\uA8E6', '\uA8E7', '\uA8E8', '\uA8E9', '\uA8EA', '\uA8EB', '\uA8EC', '\uA8ED', '\uA8EE', '\uA8EF', '\uA8F0', '\uA8F1', '\uA926', '\uA927', '\uA928', '\uA929', '\uA92A', '\uA92B', '\uA92C', '\uA92D', '\uA947', '\uA948', '\uA949', '\uA94A', '\uA94B', '\uA94C', '\uA94D', '\uA94E', '\uA94F', '\uA950', '\uA951', '\uA980', '\uA981', '\uA982', '\uA9B3', '\uA9B6', '\uA9B7', '\uA9B8', '\uA9B9', '\uA9BC', '\uAA29', '\uAA2A', '\uAA2B', '\uAA2C', '\uAA2D', '\uAA2E', '\uAA31', '\uAA32', '\uAA35', '\uAA36', '\uAA43', '\uAA4C', '\uAAB0', '\uAAB2', '\uAAB3', '\uAAB4', '\uAAB7', '\uAAB8', '\uAABE', '\uAABF', '\uAAC1', '\uAAEC', '\uAAED', '\uAAF6', '\uABE5', '\uABE8', '\uABED', '\uFB1E', '\uFE00', '\uFE01', '\uFE02', '\uFE03', '\uFE04', '\uFE05', '\uFE06', '\uFE07', '\uFE08', '\uFE09', '\uFE0A', '\uFE0B', '\uFE0C', '\uFE0D', '\uFE0E', '\uFE0F', '\uFE20', '\uFE21', '\uFE22', '\uFE23', '\uFE24', '\uFE25', '\uFE26', '\U000101FD', '\U00010A01', '\U00010A02', '\U00010A03', '\U00010A05', '\U00010A06', '\U00010A0C', '\U00010A0D', '\U00010A0E', '\U00010A0F', '\U00010A38', '\U00010A39', '\U00010A3A', '\U00010A3F', '\U00011001', '\U00011038', '\U00011039', '\U0001103A', '\U0001103B', '\U0001103C', '\U0001103D', '\U0001103E', '\U0001103F', '\U00011040', '\U00011041', '\U00011042', '\U00011043', '\U00011044', '\U00011045', '\U00011046', '\U00011080', '\U00011081', '\U000110B3', '\U000110B4', '\U000110B5', '\U000110B6', '\U000110B9', '\U000110BA', '\U00011100', '\U00011101', '\U00011102', '\U00011127', '\U00011128', '\U00011129', '\U0001112A', '\U0001112B', '\U0001112D', '\U0001112E', '\U0001112F', '\U00011130', '\U00011131', '\U00011132', '\U00011133', '\U00011134', '\U00011180', '\U00011181', '\U000111B6', '\U000111B7', '\U000111B8', '\U000111B9', '\U000111BA', '\U000111BB', '\U000111BC', '\U000111BD', '\U000111BE', '\U000116AB', '\U000116AD', '\U000116B0', '\U000116B1', '\U000116B2', '\U000116B3', '\U000116B4', '\U000116B5', '\U000116B7', '\U00016F8F', '\U00016F90', '\U00016F91', '\U00016F92', '\U0001D167', '\U0001D168', '\U0001D169', '\U0001D17B', '\U0001D17C', '\U0001D17D', '\U0001D17E', '\U0001D17F', '\U0001D180', '\U0001D181', '\U0001D182', '\U0001D185', '\U0001D186', '\U0001D187', '\U0001D188', '\U0001D189', '\U0001D18A', '\U0001D18B', '\U0001D1AA', '\U0001D1AB', '\U0001D1AC', '\U0001D1AD', '\U0001D242', '\U0001D243', '\U0001D244', '\U000E0100', '\U000E0101', '\U000E0102', '\U000E0103', '\U000E0104', '\U000E0105', '\U000E0106', '\U000E0107', '\U000E0108', '\U000E0109', '\U000E010A', '\U000E010B', '\U000E010C', '\U000E010D', '\U000E010E', '\U000E010F', '\U000E0110', '\U000E0111', '\U000E0112', '\U000E0113', '\U000E0114', '\U000E0115', '\U000E0116', '\U000E0117', '\U000E0118', '\U000E0119', '\U000E011A', '\U000E011B', '\U000E011C', '\U000E011D', '\U000E011E', '\U000E011F', '\U000E0120', '\U000E0121', '\U000E0122', '\U000E0123', '\U000E0124', '\U000E0125', '\U000E0126', '\U000E0127', '\U000E0128', '\U000E0129', '\U000E012A', '\U000E012B', '\uE012C', '\U000E012D', '\U000E012E', '\U000E012F', '\U000E0130', '\U000E0131', '\U000E0132', '\U000E0133', '\U000E0134', '\U000E0135', '\U000E0136', '\U000E0137', '\U000E0138', '\U000E0139', '\U000E013A', '\U000E013B', '\U000E013C', '\U000E013D', '\U000E013E', '\U000E013F', '\U000E0140', '\U000E0141', '\U000E0142', '\U000E0143', '\U000E0144', '\U000E0145', '\U000E0146', '\U000E0147', '\U000E0148', '\U000E0149', '\U000E014A', '\U000E014B', '\U000E014C', '\U000E014D', '\U000E014E', '\U000E014F', '\U000E0150', '\U000E0151', '\U000E0152', '\U000E0153', '\U000E0154', '\U000E0155', '\U000E0156', '\U000E0157', '\U000E0158', '\U000E0159', '\U000E015A', '\U000E015B', '\U000E015C', '\U000E015D', '\U000E015E', '\U000E015F', '\U000E0160', '\U000E0161', '\U000E0162', '\U000E0163', '\U000E0164', '\U000E0165', '\U000E0166', '\U000E0167', '\U000E0168', '\U000E0169', '\U000E016A', '\U000E016B', '\U000E016C', '\U000E016D', '\U000E016E', '\U000E016F', '\U000E0170', '\U000E0171', '\U000E0172', '\U000E0173', '\U000E0174', '\U000E0175', '\U000E0176', '\U000E0177', '\U000E0178', '\U000E0179', '\U000E017A', '\U000E017B', '\U000E017C', '\U000E017D', '\U000E017E', '\U000E017F', '\U000E0180', '\U000E0181', '\U000E0182', '\U000E0183', '\U000E0184', '\U000E0185', '\uE0186', '\U000E0187', '\U000E0188', '\U000E0189', '\U000E018A', '\U000E018B', '\U000E018C', '\U000E018D', '\U000E018E', '\U000E018F', '\U000E0190', '\U000E0191', '\U000E0192', '\U000E0193', '\U000E0194', '\U000E0195', '\U000E0196', '\U000E0197', '\U000E0198', '\U000E0199', '\U000E019A', '\U000E019B', '\U000E019C', '\U000E019D', '\U000E019E', '\U000E019F', '\U000E01A0', '\U000E01A1', '\U000E01A2', '\U000E01A3', '\U000E01A4', '\U000E01A5', '\U000E01A6', '\U000E01A7', '\U000E01A8', '\U000E01A9', '\U000E01AA', '\U000E01AB', '\U000E01AC', '\U000E01AD', '\U000E01AE', '\U000E01AF', '\U000E01B0', '\U000E01B1', '\U000E01B2', '\U000E01B3', '\U000E01B4', '\U000E01B5', '\U000E01B6', '\U000E01B7', '\U000E01B8', '\U000E01B9', '\U000E01BA', '\U000E01BB', '\U000E01BC', '\U000E01BD', '\U000E01BE', '\U000E01BF', '\U000E01C0', '\U000E01C1', '\U000E01C2', '\U000E01C3', '\U000E01C4', '\U000E01C5', '\U000E01C6', '\U000E01C7', '\U000E01C8', '\U000E01C9', '\U000E01CA', '\U000E01CB', '\U000E01CC', '\U000E01CD', '\U000E01CE', '\U000E01CF', '\U000E01D0', '\U000E01D1', '\U000E01D2', '\U000E01D3', '\U000E01D4', '\U000E01D5', '\U000E01D6', '\U000E01D7', '\U000E01D8', '\U000E01D9', '\U000E01DA', '\U000E01DB', '\U000E01DC', '\U000E01DD', '\U000E01DE', '\U000E01DF', '\U000E01E0', '\U000E01E1', '\U000E01E2', '\U000E01E3', '\U000E01E4', '\U000E01E5', '\U000E01E6', '\U000E01E7', '\U000E01E8', '\U000E01E9', '\U000E01EA', '\U000E01EB', '\U000E01EC', '\U000E01ED', '\U000E01EE', '\U000E01EF'];
NOTE.
Please note that we have both \U000XXXXX and \uXXXX representations here.
I want to count the Unicode input text like this Hindi string "अब यहां से कहा जाएँ हम" or just a token word like "समझा", excluding the non spacing characters.
My implementation looks like
def countNonSpacingCharString(str):
count = 0;
for char in str:
if char not in UNICODE_NSM:
count = count + 1
return count
Thanks to the help provided in the answers below I have put all together in this github. There is also a mark codepoints list ready to be used in JavaScript / Node.js - https://github.com/loretoparisi/unicode_marks

Fastest way I came up with. len was slightly faster than sum. I built a set of all combining mark types in the setup.
test.py:
import sys
from unicodedata import category
MARK_SET = set(chr(c) for c in range(sys.maxunicode + 1) if category(chr(c))[0] == 'M')
s = "अब यहां से कहा जाएँ हम"
def count_len(s):
return len([c for c in s if c not in MARK_SET])
def count_sum(s):
return sum([c not in MARK_SET for c in s])
if __name__ == '__main__':
print(len(s))
print(count_len(s))
print(count_sum(s))
Output:
22
16
16
Timings:
C:\>py -m timeit -s "from test import count_sum,s" "count_sum(s)"
50000 loops, best of 5: 4.62 usec per loop
C:\>py -m timeit -s "from test import count_len,s" "count_len(s)"
50000 loops, best of 5: 3.97 usec per loop
It's worth noting that there is a grapheme 3rd party library. grapheme.length(s) == 16, but it was much slower (118us). The full grapheme-detecting algorithm is more complicated than skipping the modifier category. Consider the combining emojis for families and skin colors.
See also Unicode Text Segmentation.

This might be a better alternative:
def countNonSpacingCharString(str):
return len([char for char in str if not(char in UNICODE_NSM)])

How about using a dictionary to look up the values and if not present, increment the count? It should be faster than the former approach because the time complexity to check the presence of the character reduces to O(1).
The implementation should look somewhat like this:
Create a dict and populate it:
lookup_dict = {}
for alpha in UNICODE_NSM:
lookup_dict[alpha] = 1
Look it up while looping through the string:
def countNonSpacingCharString(str):
count = 0;
for char in str:
start_time = time.time()
if not lookup_dict.get(char):
count = count + 1
print("--- %s seconds ---" % (time.time() - start_time))
return count

I must note that using str, as variable name in Python is bad idea, as it is name of built-in function. Anyway I would implement your function following way:
def countNonSpacingCharString(s):
return len(filter(lambda x:not x in UNICODE_NSM,s))
in Python 2
def countNonSpacingCharString(s):
return sum(1 for _ in filter(lambda x:not x in UNICODE_NSM,s))
in Python 3
Inspecting my function using dis.dis showed that it produced less bytecode than your version with count, thus suggesting it might be faster, though this need further investigation.
EDIT: I tested my code in Python 2, but not Python 3 - version for Python 3 added, using Mohammad Banisaeid answer from this topic.
EDIT 2: If you uses UNICODE_NSM only for that, you might try to use set instead of list, which should boost in operator, though again this need further investigation. For discussion about list vs set performance see this thread.

Perhaps the easiest way to do this is to use the unicodedata module. In part, because it will be more rigorously tested. Indeed, I found your list appeared to be including categories other than Mn. That is, it includes Unicode points from Mc (Mark, spacing combining) as well, but you said you only wanted to exclude Unicode points from Mn (Mark, Nonspacing).
eg.
import unicodedata
def countNonSpacingCharString(string):
category = unicodedata.category
return sum(category(char) != 'Mn' for char in string)
This appears to be about 60 times faster according to timeit.
You might get a TypeError, if your version of Python and therefore unicodedata is not up-to-date, and so not aware of recent additions to Unicode. You can get around this by installing unicodedata2 and using that instead.

From your comments it looks like you're really after counting "user perceived characters". This is a complicated process with a number of edge cases. If you can then you should to install regex on your environment (that would be micropython?). You can then do:
>>> parts = regex.findall(r'\X', 'अब यहां से कहा जाएँ हम')
>>> parts
['अ', 'ब', ' ', 'य', 'हां', ' ', 'से', ' ', 'क', 'हा', ' ', 'जा', 'एँ', ' ', 'ह', 'म']
>>> len(parts)
16
Which splits your string into "user perceived characters", and then you can work on this list of strings to get what you need.
Failing that, your current solution of just ignoring Mark code points is an 80/20 solution (gets you most of the way their for the least amount of effort). You will have to revise what your list of Unicode marks though. My tests showed that your list was missing 113 code points across all the Indo-European and Dravidian scripts in Unicode (Devanagari, Bengali, Gurmukhi, Gujarati, Oriya, Tamil, Telugu, Kannada, Malayalam, and Sinhala).
I extracted these characters by downloading and parsing: https://www.unicode.org/Public/11.0.0/ucd/UnicodeData.txt with the following code:
indian_script_range = range(0x0900, 0x0E00) # doesn't include all indic scripts (eg. Thai)
basic_multilingual_plane = range(0x0000, 0x10000)
# use the latter if you want to be more thorough and include all indic scripts and non-indic scripts
codepoint_range = indian_script_range
codepoints = []
with open('UnicodeData.txt') as f:
for line in f:
hex_string, name, category, *rest = line.strip().split(';')
codepoint_number = int(hex_string, base=16)
if (
category in ('Mn', 'Mc', 'Me')
and (
codepoint_number in codepoint_range
or name.startswith('VARIATION SELECTOR') # you seemed to want to include these
)
):
codepoints.append(chr(codepoint_number))
missing = set(codepoints) - set(UNICODE_NSM)

Mark Tolonens answer is the fastest, because it uses a set for comparison. If you have a text of length n and m whitespace-characters to compare with, then your worst-case runtime using two lists is O(nm). Using a set for the whitespace characters reduces that to O(n).
Using unicodedata.category is just nicer because it is shorter and less prone to human error.
Performance comparison
You can clearly see that the markset_count and the category_count are way faster than the generator_count and the loop_count. Also the speed of the latter two varies way more. Interestingly, the generator_count is slower than the loop_count.
The markset_count is a bit faster than the category_count. I think that is the case because looking up the category and doing the string comparison also takes a bit of time. The difference is way more clear when you only plot the two and increase the text length:
import timeit
import sys
import unicodedata
import numpy as np
UNICODE_NSM = ['\u0300', '\u0301', '\u0302', '\u0303', '\u0304', '\u0305', '\u0306', '\u0307', '\u0308', '\u0309', '\u030A', '\u030B', '\u030C', '\u030D', '\u030E', '\u030F', '\u0310', '\u0311', '\u0312', '\u0313', '\u0314', '\u0315', '\u0316', '\u0317', '\u0318', '\u0319', '\u031A', '\u031B', '\u031C', '\u031D', '\u031E', '\u031F', '\u0320', '\u0321', '\u0322', '\u0323', '\u0324', '\u0325', '\u0326', '\u0327', '\u0328', '\u0329', '\u032A', '\u032B', '\u032C', '\u032D', '\u032E', '\u032F', '\u0330', '\u0331', '\u0332', '\u0333', '\u0334', '\u0335', '\u0336', '\u0337', '\u0338', '\u0339', '\u033A', '\u033B', '\u033C', '\u033D', '\u033E', '\u033F', '\u0340', '\u0341', '\u0342', '\u0343', '\u0344', '\u0345', '\u0346', '\u0347', '\u0348', '\u0349', '\u034A', '\u034B', '\u034C', '\u034D', '\u034E', '\u034F', '\u0350', '\u0351', '\u0352', '\u0353', '\u0354', '\u0355', '\u0356', '\u0357', '\u0358', '\u0359', '\u035A', '\u035B', '\u035C', '\u035D', '\u035E', '\u035F', '\u0360', '\u0361', '\u0362', '\u0363', '\u0364', '\u0365', '\u0366', '\u0367', '\u0368', '\u0369', '\u036A', '\u036B', '\u036C', '\u036D', '\u036E', '\u036F', '\u0483', '\u0484', '\u0485', '\u0486', '\u0487', '\u0591', '\u0592', '\u0593', '\u0594', '\u0595', '\u0596', '\u0597', '\u0598', '\u0599', '\u059A', '\u059B', '\u059C', '\u059D', '\u059E', '\u059F', '\u05A0', '\u05A1', '\u05A2', '\u05A3', '\u05A4', '\u05A5', '\u05A6', '\u05A7', '\u05A8', '\u05A9', '\u05AA', '\u05AB', '\u05AC', '\u05AD', '\u05AE', '\u05AF', '\u05B0', '\u05B1', '\u05B2', '\u05B3', '\u05B4', '\u05B5', '\u05B6', '\u05B7', '\u05B8', '\u05B9', '\u05BA', '\u05BB', '\u05BC', '\u05BD', '\u05BF', '\u05C1', '\u05C2', '\u05C4', '\u05C5', '\u05C7', '\u0610', '\u0611', '\u0612', '\u0613', '\u0614', '\u0615', '\u0616', '\u0617', '\u0618', '\u0619', '\u061A', '\u064B', '\u064C', '\u064D', '\u064E', '\u064F', '\u0650', '\u0651', '\u0652', '\u0653', '\u0654', '\u0655', '\u0656', '\u0657', '\u0658', '\u0659', '\u065A', '\u065B', '\u065C', '\u065D', '\u065E', '\u065F', '\u0670', '\u06D6', '\u06D7', '\u06D8', '\u06D9', '\u06DA', '\u06DB', '\u06DC', '\u06DF', '\u06E0', '\u06E1', '\u06E2', '\u06E3', '\u06E4', '\u06E7', '\u06E8', '\u06EA', '\u06EB', '\u06EC', '\u06ED', '\u0711', '\u0730', '\u0731', '\u0732', '\u0733', '\u0734', '\u0735', '\u0736', '\u0737', '\u0738', '\u0739', '\u073A', '\u073B', '\u073C', '\u073D', '\u073E', '\u073F', '\u0740', '\u0741', '\u0742', '\u0743', '\u0744', '\u0745', '\u0746', '\u0747', '\u0748', '\u0749', '\u074A', '\u07A6', '\u07A7', '\u07A8', '\u07A9', '\u07AA', '\u07AB', '\u07AC', '\u07AD', '\u07AE', '\u07AF', '\u07B0', '\u07EB', '\u07EC', '\u07ED', '\u07EE', '\u07EF', '\u07F0', '\u07F1', '\u07F2', '\u07F3', '\u0816', '\u0817', '\u0818', '\u0819', '\u081B', '\u081C', '\u081D', '\u081E', '\u081F', '\u0820', '\u0821', '\u0822', '\u0823', '\u0825', '\u0826', '\u0827', '\u0829', '\u082A', '\u082B', '\u082C', '\u082D', '\u0859', '\u085A', '\u085B', '\u08E4', '\u08E5', '\u08E6', '\u08E7', '\u08E8', '\u08E9', '\u08EA', '\u08EB', '\u08EC', '\u08ED', '\u08EE', '\u08EF', '\u08F0', '\u08F1', '\u08F2', '\u08F3', '\u08F4', '\u08F5', '\u08F6', '\u08F7', '\u08F8', '\u08F9', '\u08FA', '\u08FB', '\u08FC', '\u08FD', '\u08FE', '\u0900', '\u0901', '\u0902', '\u093A', '\u093C', '\u093E', '\u0941', '\u0942', '\u0943', '\u0944', '\u0945', '\u0946', '\u0947', '\u0948', '\u094D', '\u0951', '\u0952', '\u0953', '\u0954', '\u0955', '\u0956', '\u0957', '\u0962', '\u0963', '\u0981', '\u09BC', '\u09C1', '\u09C2', '\u09C3', '\u09C4', '\u09CD', '\u09E2', '\u09E3', '\u0A01', '\u0A02', '\u0A3C', '\u0A41', '\u0A42', '\u0A47', '\u0A48', '\u0A4B', '\u0A4C', '\u0A4D', '\u0A51', '\u0A70', '\u0A71', '\u0A75', '\u0A81', '\u0A82', '\u0ABC', '\u0AC1', '\u0AC2', '\u0AC3', '\u0AC4', '\u0AC5', '\u0AC7', '\u0AC8', '\u0ACD', '\u0AE2', '\u0AE3', '\u0B01', '\u0B3C', '\u0B3F', '\u0B41', '\u0B42', '\u0B43', '\u0B44', '\u0B4D', '\u0B56', '\u0B62', '\u0B63', '\u0B82', '\u0BC0', '\u0BCD', '\u0C3E', '\u0C3F', '\u0C40', '\u0C46', '\u0C47', '\u0C48', '\u0C4A', '\u0C4B', '\u0C4C', '\u0C4D', '\u0C55', '\u0C56', '\u0C62', '\u0C63', '\u0CBC', '\u0CBF', '\u0CC6', '\u0CCC', '\u0CCD', '\u0CE2', '\u0CE3', '\u0D41', '\u0D42', '\u0D43', '\u0D44', '\u0D4D', '\u0D62', '\u0D63', '\u0DCA', '\u0DD2', '\u0DD3', '\u0DD4', '\u0DD6', '\u0E31', '\u0E34', '\u0E35', '\u0E36', '\u0E37', '\u0E38', '\u0E39', '\u0E3A', '\u0E47', '\u0E48', '\u0E49', '\u0E4A', '\u0E4B', '\u0E4C', '\u0E4D', '\u0E4E', '\u0EB1', '\u0EB4', '\u0EB5', '\u0EB6', '\u0EB7', '\u0EB8', '\u0EB9', '\u0EBB', '\u0EBC', '\u0EC8', '\u0EC9', '\u0ECA', '\u0ECB', '\u0ECC', '\u0ECD', '\u0F18', '\u0F19', '\u0F35', '\u0F37', '\u0F39', '\u0F71', '\u0F72', '\u0F73', '\u0F74', '\u0F75', '\u0F76', '\u0F77', '\u0F78', '\u0F79', '\u0F7A', '\u0F7B', '\u0F7C', '\u0F7D', '\u0F7E', '\u0F80', '\u0F81', '\u0F82', '\u0F83', '\u0F84', '\u0F86', '\u0F87', '\u0F8D', '\u0F8E', '\u0F8F', '\u0F90', '\u0F91', '\u0F92', '\u0F93', '\u0F94', '\u0F95', '\u0F96', '\u0F97', '\u0F99', '\u0F9A', '\u0F9B', '\u0F9C', '\u0F9D', '\u0F9E', '\u0F9F', '\u0FA0', '\u0FA1', '\u0FA2', '\u0FA3', '\u0FA4', '\u0FA5', '\u0FA6', '\u0FA7', '\u0FA8', '\u0FA9', '\u0FAA', '\u0FAB', '\u0FAC', '\u0FAD', '\u0FAE', '\u0FAF', '\u0FB0', '\u0FB1', '\u0FB2', '\u0FB3', '\u0FB4', '\u0FB5', '\u0FB6', '\u0FB7', '\u0FB8', '\u0FB9', '\u0FBA', '\u0FBB', '\u0FBC', '\u0FC6', '\u102D', '\u102E', '\u102F', '\u1030', '\u1032', '\u1033', '\u1034', '\u1035', '\u1036', '\u1037', '\u1039', '\u103A', '\u103D', '\u103E', '\u1058', '\u1059', '\u105E', '\u105F', '\u1060', '\u1071', '\u1072', '\u1073', '\u1074', '\u1082', '\u1085', '\u1086', '\u108D', '\u109D', '\u135D', '\u135E', '\u135F', '\u1712', '\u1713', '\u1714', '\u1732', '\u1733', '\u1734', '\u1752', '\u1753', '\u1772', '\u1773', '\u17B4', '\u17B5', '\u17B7', '\u17B8', '\u17B9', '\u17BA', '\u17BB', '\u17BC', '\u17BD', '\u17C6', '\u17C9', '\u17CA', '\u17CB', '\u17CC', '\u17CD', '\u17CE', '\u17CF', '\u17D0', '\u17D1', '\u17D2', '\u17D3', '\u17DD', '\u180B', '\u180C', '\u180D', '\u18A9', '\u1920', '\u1921', '\u1922', '\u1927', '\u1928', '\u1932', '\u1939', '\u193A', '\u193B', '\u1A17', '\u1A18', '\u1A56', '\u1A58', '\u1A59', '\u1A5A', '\u1A5B', '\u1A5C', '\u1A5D', '\u1A5E', '\u1A60', '\u1A62', '\u1A65', '\u1A66', '\u1A67', '\u1A68', '\u1A69', '\u1A6A', '\u1A6B', '\u1A6C', '\u1A73', '\u1A74', '\u1A75', '\u1A76', '\u1A77', '\u1A78', '\u1A79', '\u1A7A', '\u1A7B', '\u1A7C', '\u1A7F', '\u1B00', '\u1B01', '\u1B02', '\u1B03', '\u1B34', '\u1B36', '\u1B37', '\u1B38', '\u1B39', '\u1B3A', '\u1B3C', '\u1B42', '\u1B6B', '\u1B6C', '\u1B6D', '\u1B6E', '\u1B6F', '\u1B70', '\u1B71', '\u1B72', '\u1B73', '\u1B80', '\u1B81', '\u1BA2', '\u1BA3', '\u1BA4', '\u1BA5', '\u1BA8', '\u1BA9', '\u1BAB', '\u1BE6', '\u1BE8', '\u1BE9', '\u1BED', '\u1BEF', '\u1BF0', '\u1BF1', '\u1C2C', '\u1C2D', '\u1C2E', '\u1C2F', '\u1C30', '\u1C31', '\u1C32', '\u1C33', '\u1C36', '\u1C37', '\u1CD0', '\u1CD1', '\u1CD2', '\u1CD4', '\u1CD5', '\u1CD6', '\u1CD7', '\u1CD8', '\u1CD9', '\u1CDA', '\u1CDB', '\u1CDC', '\u1CDD', '\u1CDE', '\u1CDF', '\u1CE0', '\u1CE2', '\u1CE3', '\u1CE4', '\u1CE5', '\u1CE6', '\u1CE7', '\u1CE8', '\u1CED', '\u1CF4', '\u1DC0', '\u1DC1', '\u1DC2', '\u1DC3', '\u1DC4', '\u1DC5', '\u1DC6', '\u1DC7', '\u1DC8', '\u1DC9', '\u1DCA', '\u1DCB', '\u1DCC', '\u1DCD', '\u1DCE', '\u1DCF', '\u1DD0', '\u1DD1', '\u1DD2', '\u1DD3', '\u1DD4', '\u1DD5', '\u1DD6', '\u1DD7', '\u1DD8', '\u1DD9', '\u1DDA', '\u1DDB', '\u1DDC', '\u1DDD', '\u1DDE', '\u1DDF', '\u1DE0', '\u1DE1', '\u1DE2', '\u1DE3', '\u1DE4', '\u1DE5', '\u1DE6', '\u1DFC', '\u1DFD', '\u1DFE', '\u1DFF', '\u20D0', '\u20D1', '\u20D2', '\u20D3', '\u20D4', '\u20D5', '\u20D6', '\u20D7', '\u20D8', '\u20D9', '\u20DA', '\u20DB', '\u20DC', '\u20E1', '\u20E5', '\u20E6', '\u20E7', '\u20E8', '\u20E9', '\u20EA', '\u20EB', '\u20EC', '\u20ED', '\u20EE', '\u20EF', '\u20F0', '\u2CEF', '\u2CF0', '\u2CF1', '\u2D7F', '\u2DE0', '\u2DE1', '\u2DE2', '\u2DE3', '\u2DE4', '\u2DE5', '\u2DE6', '\u2DE7', '\u2DE8', '\u2DE9', '\u2DEA', '\u2DEB', '\u2DEC', '\u2DED', '\u2DEE', '\u2DEF', '\u2DF0', '\u2DF1', '\u2DF2', '\u2DF3', '\u2DF4', '\u2DF5', '\u2DF6', '\u2DF7', '\u2DF8', '\u2DF9', '\u2DFA', '\u2DFB', '\u2DFC', '\u2DFD', '\u2DFE', '\u2DFF', '\u302A', '\u302B', '\u302C', '\u302D', '\u3099', '\u309A', '\uA66F', '\uA674', '\uA675', '\uA676', '\uA677', '\uA678', '\uA679', '\uA67A', '\uA67B', '\uA67C', '\uA67D', '\uA69F', '\uA6F0', '\uA6F1', '\uA802', '\uA806', '\uA80B', '\uA825', '\uA826', '\uA8C4', '\uA8E0', '\uA8E1', '\uA8E2', '\uA8E3', '\uA8E4', '\uA8E5', '\uA8E6', '\uA8E7', '\uA8E8', '\uA8E9', '\uA8EA', '\uA8EB', '\uA8EC', '\uA8ED', '\uA8EE', '\uA8EF', '\uA8F0', '\uA8F1', '\uA926', '\uA927', '\uA928', '\uA929', '\uA92A', '\uA92B', '\uA92C', '\uA92D', '\uA947', '\uA948', '\uA949', '\uA94A', '\uA94B', '\uA94C', '\uA94D', '\uA94E', '\uA94F', '\uA950', '\uA951', '\uA980', '\uA981', '\uA982', '\uA9B3', '\uA9B6', '\uA9B7', '\uA9B8', '\uA9B9', '\uA9BC', '\uAA29', '\uAA2A', '\uAA2B', '\uAA2C', '\uAA2D', '\uAA2E', '\uAA31', '\uAA32', '\uAA35', '\uAA36', '\uAA43', '\uAA4C', '\uAAB0', '\uAAB2', '\uAAB3', '\uAAB4', '\uAAB7', '\uAAB8', '\uAABE', '\uAABF', '\uAAC1', '\uAAEC', '\uAAED', '\uAAF6', '\uABE5', '\uABE8', '\uABED', '\uFB1E', '\uFE00', '\uFE01', '\uFE02', '\uFE03', '\uFE04', '\uFE05', '\uFE06', '\uFE07', '\uFE08', '\uFE09', '\uFE0A', '\uFE0B', '\uFE0C', '\uFE0D', '\uFE0E', '\uFE0F', '\uFE20', '\uFE21', '\uFE22', '\uFE23', '\uFE24', '\uFE25', '\uFE26', '\U000101FD', '\U00010A01', '\U00010A02', '\U00010A03', '\U00010A05', '\U00010A06', '\U00010A0C', '\U00010A0D', '\U00010A0E', '\U00010A0F', '\U00010A38', '\U00010A39', '\U00010A3A', '\U00010A3F', '\U00011001', '\U00011038', '\U00011039', '\U0001103A', '\U0001103B', '\U0001103C', '\U0001103D', '\U0001103E', '\U0001103F', '\U00011040', '\U00011041', '\U00011042', '\U00011043', '\U00011044', '\U00011045', '\U00011046', '\U00011080', '\U00011081', '\U000110B3', '\U000110B4', '\U000110B5', '\U000110B6', '\U000110B9', '\U000110BA', '\U00011100', '\U00011101', '\U00011102', '\U00011127', '\U00011128', '\U00011129', '\U0001112A', '\U0001112B', '\U0001112D', '\U0001112E', '\U0001112F', '\U00011130', '\U00011131', '\U00011132', '\U00011133', '\U00011134', '\U00011180', '\U00011181', '\U000111B6', '\U000111B7', '\U000111B8', '\U000111B9', '\U000111BA', '\U000111BB', '\U000111BC', '\U000111BD', '\U000111BE', '\U000116AB', '\U000116AD', '\U000116B0', '\U000116B1', '\U000116B2', '\U000116B3', '\U000116B4', '\U000116B5', '\U000116B7', '\U00016F8F', '\U00016F90', '\U00016F91', '\U00016F92', '\U0001D167', '\U0001D168', '\U0001D169', '\U0001D17B', '\U0001D17C', '\U0001D17D', '\U0001D17E', '\U0001D17F', '\U0001D180', '\U0001D181', '\U0001D182', '\U0001D185', '\U0001D186', '\U0001D187', '\U0001D188', '\U0001D189', '\U0001D18A', '\U0001D18B', '\U0001D1AA', '\U0001D1AB', '\U0001D1AC', '\U0001D1AD', '\U0001D242', '\U0001D243', '\U0001D244', '\U000E0100', '\U000E0101', '\U000E0102', '\U000E0103', '\U000E0104', '\U000E0105', '\U000E0106', '\U000E0107', '\U000E0108', '\U000E0109', '\U000E010A', '\U000E010B', '\U000E010C', '\U000E010D', '\U000E010E', '\U000E010F', '\U000E0110', '\U000E0111', '\U000E0112', '\U000E0113', '\U000E0114', '\U000E0115', '\U000E0116', '\U000E0117', '\U000E0118', '\U000E0119', '\U000E011A', '\U000E011B', '\U000E011C', '\U000E011D', '\U000E011E', '\U000E011F', '\U000E0120', '\U000E0121', '\U000E0122', '\U000E0123', '\U000E0124', '\U000E0125', '\U000E0126', '\U000E0127', '\U000E0128', '\U000E0129', '\U000E012A', '\U000E012B', '\uE012C', '\U000E012D', '\U000E012E', '\U000E012F', '\U000E0130', '\U000E0131', '\U000E0132', '\U000E0133', '\U000E0134', '\U000E0135', '\U000E0136', '\U000E0137', '\U000E0138', '\U000E0139', '\U000E013A', '\U000E013B', '\U000E013C', '\U000E013D', '\U000E013E', '\U000E013F', '\U000E0140', '\U000E0141', '\U000E0142', '\U000E0143', '\U000E0144', '\U000E0145', '\U000E0146', '\U000E0147', '\U000E0148', '\U000E0149', '\U000E014A', '\U000E014B', '\U000E014C', '\U000E014D', '\U000E014E', '\U000E014F', '\U000E0150', '\U000E0151', '\U000E0152', '\U000E0153', '\U000E0154', '\U000E0155', '\U000E0156', '\U000E0157', '\U000E0158', '\U000E0159', '\U000E015A', '\U000E015B', '\U000E015C', '\U000E015D', '\U000E015E', '\U000E015F', '\U000E0160', '\U000E0161', '\U000E0162', '\U000E0163', '\U000E0164', '\U000E0165', '\U000E0166', '\U000E0167', '\U000E0168', '\U000E0169', '\U000E016A', '\U000E016B', '\U000E016C', '\U000E016D', '\U000E016E', '\U000E016F', '\U000E0170', '\U000E0171', '\U000E0172', '\U000E0173', '\U000E0174', '\U000E0175', '\U000E0176', '\U000E0177', '\U000E0178', '\U000E0179', '\U000E017A', '\U000E017B', '\U000E017C', '\U000E017D', '\U000E017E', '\U000E017F', '\U000E0180', '\U000E0181', '\U000E0182', '\U000E0183', '\U000E0184', '\U000E0185', '\uE0186', '\U000E0187', '\U000E0188', '\U000E0189', '\U000E018A', '\U000E018B', '\U000E018C', '\U000E018D', '\U000E018E', '\U000E018F', '\U000E0190', '\U000E0191', '\U000E0192', '\U000E0193', '\U000E0194', '\U000E0195', '\U000E0196', '\U000E0197', '\U000E0198', '\U000E0199', '\U000E019A', '\U000E019B', '\U000E019C', '\U000E019D', '\U000E019E', '\U000E019F', '\U000E01A0', '\U000E01A1', '\U000E01A2', '\U000E01A3', '\U000E01A4', '\U000E01A5', '\U000E01A6', '\U000E01A7', '\U000E01A8', '\U000E01A9', '\U000E01AA', '\U000E01AB', '\U000E01AC', '\U000E01AD', '\U000E01AE', '\U000E01AF', '\U000E01B0', '\U000E01B1', '\U000E01B2', '\U000E01B3', '\U000E01B4', '\U000E01B5', '\U000E01B6', '\U000E01B7', '\U000E01B8', '\U000E01B9', '\U000E01BA', '\U000E01BB', '\U000E01BC', '\U000E01BD', '\U000E01BE', '\U000E01BF', '\U000E01C0', '\U000E01C1', '\U000E01C2', '\U000E01C3', '\U000E01C4', '\U000E01C5', '\U000E01C6', '\U000E01C7', '\U000E01C8', '\U000E01C9', '\U000E01CA', '\U000E01CB', '\U000E01CC', '\U000E01CD', '\U000E01CE', '\U000E01CF', '\U000E01D0', '\U000E01D1', '\U000E01D2', '\U000E01D3', '\U000E01D4', '\U000E01D5', '\U000E01D6', '\U000E01D7', '\U000E01D8', '\U000E01D9', '\U000E01DA', '\U000E01DB', '\U000E01DC', '\U000E01DD', '\U000E01DE', '\U000E01DF', '\U000E01E0', '\U000E01E1', '\U000E01E2', '\U000E01E3', '\U000E01E4', '\U000E01E5', '\U000E01E6', '\U000E01E7', '\U000E01E8', '\U000E01E9', '\U000E01EA', '\U000E01EB', '\U000E01EC', '\U000E01ED', '\U000E01EE', '\U000E01EF']
MARK_SET = set(chr(c) for c in range(sys.maxunicode + 1) if unicodedata.category(chr(c))[0] == 'M')
print('len(UNICODE_NSM) = {}'.format(len(UNICODE_NSM)))
print('len(MARK_SET) = {}'.format(len(MARK_SET)))
filepath = "UnicodeData.txt"
with open(filepath) as f:
text = f.read()
text = text[:1000]
def main():
ground_truth = loop_count(text)
functions = [(loop_count, 'loop_count'),
(generator_count, 'generator_count'),
(category_count, 'category_count'),
(markset_count, 'markset_count'),
]
functions = functions[::-1]
duration_list = {}
for func, name in functions:
is_correct = func(text) == ground_truth
durations = timeit.repeat(lambda: func(text), repeat=500, number=3)
if is_correct:
correctness = 'correct'
else:
correctness = 'NOT correct'
duration_list[name] = durations
print('{func:<20}: {correctness}, '
'min: {min:0.3f}s, mean: {mean:0.3f}s, max: {max:0.3f}s'
.format(func=name,
correctness=correctness,
min=min(durations),
mean=np.mean(durations),
max=max(durations),
))
create_boxplot(duration_list)
def create_boxplot(duration_list):
import seaborn as sns
import matplotlib.pyplot as plt
import operator
plt.figure(num=None, figsize=(8, 4), dpi=300,
facecolor='w', edgecolor='k')
sns.set(style="whitegrid")
sorted_keys, sorted_vals = zip(*sorted(duration_list.items(), key=operator.itemgetter(1)))
flierprops = dict(markerfacecolor='0.75', markersize=1,
linestyle='none')
ax = sns.boxplot(data=sorted_vals, width=.3, orient='h',
flierprops=flierprops,)
ax.set(xlabel="Time in s", ylabel="")
plt.yticks(plt.yticks()[0], sorted_keys)
plt.tight_layout()
plt.savefig("output.png")
def generator_count(text):
return sum(1 for char in text if char not in UNICODE_NSM)
def loop_count(text):
# 1769137
count = 0
for char in text:
if char not in UNICODE_NSM:
count += 1
return count
def markset_count(text):
return sum(char not in MARK_SET for char in text)
def category_count(text):
return sum(unicodedata.category(char) != 'Mn' for char in text)
if __name__ == '__main__':
main()

PyParsing: parseaction called multiple

I am a beginner with pyparsing but have experience with other parsing environments.
On my first small demo project I encountered a strange behavior of parsing actions: Parse action of base token (ident_simple) is called twice for each token of ident_simple.
import io, sys
from pyparsing import *
def pa_ident_simple(s, l, t):
print('ident_simple: ' + str(t))
def pa_ident_combined(s, l, t):
print('ident_combined: ' + str(t))
def make_grammar():
number = Word(nums)
ident_simple = Word( alphas, alphanums + "_" )
ident_simple.setParseAction(pa_ident_simple)
ident_combined = Combine(ident_simple + Literal('.') + ident_simple)
ident_combined.setParseAction(pa_ident_combined)
integer = number
elems = ( ident_combined | ident_simple | integer)
grammar = OneOrMore(elems) + StringEnd()
return grammar
if __name__ == "__main__":
inp_str = "UUU FFF.XXX GGG"
grammar = make_grammar()
print (inp_str, "--->", grammar.parseString( inp_str ))
For 'ident_combined' token it looks good: Parseaction is called once for each sub token 'ident_simple' and once for combined token.
I believe that the combined token is the problem: Parseaction of 'ident_simple' is called only once if 'ident_combined' is removed.
Can anybody give me a hint how to combine tokens correctly?
Thanks for any help
Update: When playing around I took the class "Or" instead of "MatchFirst".
elems = ( ident_combined ^ ident_simple ^ integer)
This showed a better behavior (in my opinion).
Output of original grammar (using "MatchFirst"):
ident_simple: ['UUU']
ident_simple: ['UUU']
ident_simple: ['FFF']
ident_simple: ['XXX']
ident_combined: ['FFF.XXX']
ident_simple: ['GGG']
ident_simple: ['GGG']
UUU FFF.XXX GGG ---> ['UUU', 'FFF.XXX', 'GGG']
Output of modified grammar (using "Or"):
ident_simple: ['UUU']
ident_simple: ['FFF']
ident_simple: ['XXX']
ident_combined: ['FFF.XXX']
ident_simple: ['GGG']
UUU FFF.XXX GGG ---> ['UUU', 'FFF.XXX', 'GGG']

pretty-printing OrderedDicts using pprint

I'm using pprint to nicely print a dict and it's working fine. Now I switch to using an OrderedDict from module collections. Unfortunately, the pprint routing does not seem to recognize that such objects are more or less dicts as well and falls back to printing that as a long line.
>>> d = { i:'*'*i for i in range(8) }
>>> pprint.pprint(d)
{0: '',
1: '*',
2: '**',
3: '***',
4: '****',
5: '*****',
6: '******',
7: '*******'}
>>> pprint.pprint(collections.OrderedDict(d))
OrderedDict([(0, ''), (1, '*'), (2, '**'), (3, '***'), (4, '****'), (5, '*****'), (6, '******'), (7, '*******')])
Any way to get a nicer representation of OrderedDicts as well? Maybe even if they are nested inside a normal dict or list?

I found a relatively simple solution for this, but it includes the risk of making the output for your ordered dictionary appear exactly as if it were a regular dict object.
The original solution for using a context manager to prevent pprint from sorting dictionary keys comes from this answer.
#contextlib.contextmanager
def pprint_OrderedDict():
pp_orig = pprint._sorted
od_orig = OrderedDict.__repr__
try:
pprint._sorted = lambda x:x
OrderedDict.__repr__ = dict.__repr__
yield
finally:
pprint._sorted = pp_orig
OrderedDict.__repr__ = od_orig
(You could also just patch the OrderedDict.__repr__ method with dict.__repr__, but please don't.)
Example:
>>> foo = [('Roger', 'Owner'), ('Diane', 'Manager'), ('Bob', 'Manager'),
... ('Ian', 'Associate'), ('Bill', 'Associate'), ('Melinda', 'Associate')]
>>> d = OrderedDict(foo)
>>> pprint.pprint(d)
OrderedDict([('Roger', 'Owner'), ('Diane', 'Manager'), ('Bob', 'Manager'), ('Ian', 'Associate'), ('Bill', 'Associate'), ('Melinda', 'Associate')])
>>> pprint.pprint(dict(d))
{'Bill': 'Associate',
'Bob': 'Manager',
'Diane': 'Manager',
'Ian': 'Associate',
'Melinda': 'Associate',
'Roger': 'Owner'}
>>> with pprint_OrderedDict():
... pprint.pprint(d)
...
{'Roger': 'Owner',
'Diane': 'Manager',
'Bob': 'Manager',
'Ian': 'Associate',
'Bill': 'Associate',
'Melinda': 'Associate'}

Try this on:
d = collections.OrderedDict({ i:'*'*i for i in range(8) })
EDIT
pprint.pprint(list(d.items()))

If you are specifically targeting CPython* 3.6 or later, then you can just use regular dictionaries instead of OrderedDict. You'll miss out on a few methods exclusive to OrderedDict, and this is not (yet) guaranteed to be portable to other Python implementations,** but it is probably the simplest way to accomplish what you are trying to do.
* CPython is the reference implementation of Python which may be downloaded from python.org.
** CPython stole this idea from PyPy, so you can probably depend on it working there too.

I realize this is sort of necroposting, but I thought I'd post what I use. Its main virtue is that its aoutput can be read back into python, thus allowing, for instance, to shutlle between representations (which I use, for instance, on JSON files). Of course it breaks pprint encapsulation, by ripping some code off its inner _format function.
#!/bin/env python
from __future__ import print_function
import pprint;
from collections import OrderedDict
import json
import sys
class MyPP (pprint.PrettyPrinter):
def _format(self, object, stream, indent, allowance, context, level):
if not isinstance(object, OrderedDict) :
return pprint.PrettyPrinter._format(self, object, stream, indent, allowance, context, level)
level = level + 1
objid = id(object)
if objid in context:
stream.write(_recursion(object))
self._recursive = True
self._readable = False
return
write = stream.write
_len=len
rep = self._repr(object, context, level - 1)
typ = type(object)
sepLines = _len(rep) > (self._width - 1 - indent - allowance)
if self._depth and level > self._depth:
write(rep)
return
write('OrderedDict([\n%s'%(' '*(indent+1),))
if self._indent_per_level > 1:
write((self._indent_per_level - 1) * ' ')
length = _len(object)
#import pdb; pdb.set_trace()
if length:
context[objid] = 1
indent = indent + self._indent_per_level
items = object.items()
key, ent = items[0]
rep = self._repr(key, context, level)
write('( ')
write(rep)
write(', ')
self._format(ent, stream, indent + _len(rep) + 2,
allowance + 1, context, level)
write(' )')
if length > 1:
for key, ent in items[1:]:
rep = self._repr(key, context, level)
if sepLines:
write(',\n%s( %s , ' % (' '*indent, rep))
else:
write(', ( %s , ' % rep)
self._format(ent, stream, indent + _len(rep) + 2,
allowance + 1, context, level)
write(' )')
indent = indent - self._indent_per_level
del context[objid]
write('])')
return
pp = MyPP(indent=1)
handle=open(sys.argv[1],"r")
values=json.loads(handle.read(),object_pairs_hook=OrderedDict)
pp.pprint(values)

Regex with unicode and str

I have a list of regex and a replace function.
regex function
replacement_patterns = [(ur'\\u20ac', ur' euros'),(ur'\xe2\x82\xac', r' euros'),(ur'\b[eE]?[uU]?[rR]\b', r' euros'), (ur'\b([0-9]+)[eE][uU]?[rR]?[oO]?[sS]?\b',ur' \1 euros')]
class RegexpReplacer(object):
def __init__(self, patterns=replacement_patterns):
self.patterns = [(re.compile(regex, re.UNICODE | re.IGNORECASE), repl) for (regex, repl) in patterns]
def replace(self, text):
s = text
for (pattern, repl) in self.patterns:
(s, count) = re.subn(pattern, repl, s)
return s
If I write the string as bellow:
string='730\u20ac.\r\n\n ropa surf ... 5,10 muy buen estado..... 170 \u20ac\r\n\nPack 850\u20ac, reparaci\u00f3n. \r\n\n'
replacer = RegexpReplacer()
texto= replacer.replace(string)
I get perfect results.
But if I call the function when iterating over a JSON file I have just loaded, it does not work (no error but no replacement)
What seems to happen is that when I call the function over the typed variable the function receives a STR, and when I call it from the JSON iteration it receives a unicode.
My question is why my regex is not working on the unicode, wouldnt it be supposed to?

Maybe you need something like this
import re
regex = re.compile("^http://.+", re.UNICODE)
And if you need more than one, you can do like this
regex = re.compile("^http://.+", re.UNICODE | re.IGNORECASE)
Get the example
>>> r = re.compile("^http://.+", re.UNICODE | re.IGNORECASE)
>>> r.match('HTTP://ыыы')
<_sre.SRE_Match object at 0x7f572455d648>
Does it correct result?
>>> class RegexpReplacer(object):
... def __init__(self, patterns=replacement_patterns):
... self.patterns = [(re.compile(regex, re.UNICODE | re.IGNORECASE), repl) for (regex, repl) in patterns]
... def replace(self, text):
... s = text
... for (pattern, repl) in self.patterns:
... (s, count) = re.subn(pattern, repl, s)
... return s
...
>>> string='730\u20ac.\r\n\n ropa surf ... 5,10 muy buen estado..... 170 \u20ac\r\n\nPack 850\u20ac, reparaci\u00f3n. \r\n\n'
>>> replacer = RegexpReplacer()
>>> texto= replacer.replace(string)
>>> texto
u'730 euros.\r\n\n ropa surf ... 5,10 muy buen estado..... 170 euros\r\n\nPack 850 euros, reparaci\\u00f3n. \r\n\n'

If you want Unicode replacement patterns, you need also be operating on Unicode strings. JSON should be returning Unicode as well.
Change the following by removing \\ and removing UTF-8 (won't see in a Unicode string). Also you compile with IGNORE_CASE so no need for [eE], etc.:
replacement_patterns = [(ur'\u20ac', ur' euros'),(ur'\be?u?r\b', r' euros'), (ur'\b([0-9]+)eu?r?o?s?\b',ur' \1 euros')]
Make the following a Unicode string (add u):
string = u'730\u20ac.\r\n\n ropa surf ... 5,10 muy buen estado..... 170 \u20ac\r\n\nPack 850\u20ac, reparaci\u00f3n. \r\n\n'
Then it should operator on Unicode JSON as well.

Disassemble Python code to dictionary

I'd like to develop a small debugging tool for Python programs. For the "Dynamic Slicing" feature, I need to find the variables that are accessed in a statement, and find the type of access (read or write) for those variables.
But the only disassembly feature that's built into Python is dis.disassemble, and that just prints the disassembly to standard output:
>>> dis.disassemble(compile('x = a + b', '', 'single'))
1 0 LOAD_NAME 0 (a)
3 LOAD_NAME 1 (b)
6 BINARY_ADD
7 STORE_NAME 2 (x)
10 LOAD_CONST 0 (None)
13 RETURN_VALUE
I'd like to be able to transform the disassembly into a dictionary of sets describing which variables are used by each instruction, like this:
>>> my_disassemble('x = a + b')
{'LOAD_NAME': set(['a', 'b']), 'STORE_NAME': set(['x'])}
How can I do this?

Read the source code for the dis module and you'll see that it's easy to do your own disassembly and generate whatever output format you like. Here's some code that generates the sequence of instructions in a code object, together with their arguments:
from opcode import *
def disassemble(co):
"""
Disassemble a code object and generate its instructions.
"""
code = co.co_code
n = len(code)
extended_arg = 0
i = 0
free = None
while i < n:
c = code[i]
op = ord(c)
i = i+1
if op < HAVE_ARGUMENT:
yield opname[op],
else:
oparg = ord(code[i]) + ord(code[i+1])*256 + extended_arg
extended_arg = 0
i = i+2
if op == EXTENDED_ARG:
extended_arg = oparg*65536L
if op in hasconst:
arg = co.co_consts[oparg]
elif op in hasname:
arg = co.co_names[oparg]
elif op in hasjrel:
arg = repr(i + oparg)
elif op in haslocal:
arg = co.co_varnames[oparg]
elif op in hascompare:
arg = cmp_op[oparg]
elif op in hasfree:
if free is None:
free = co.co_cellvars + co.co_freevars
arg = free[oparg]
else:
arg = oparg
yield opname[op], arg
And here's an example disassembly.
>>> def f(x):
... return x + 1
...
>>> list(disassemble(f.func_code))
[('LOAD_FAST', 'x'), ('LOAD_CONST', 1), ('BINARY_ADD',), ('RETURN_VALUE',)]
You can easily transform this into the dictionary-of-sets data structure you want:
>>> from collections import defaultdict
>>> d = defaultdict(set)
>>> for op in disassemble(f.func_code):
... if len(op) == 2:
... d[op[0]].add(op[1])
...
>>> d
defaultdict(<type 'set'>, {'LOAD_FAST': set(['x']), 'LOAD_CONST': set([1])})
(Or you could generate the dictionary-of-sets data structure directly.)
Note that in your application you probably don't actually need look up the name for each opcode. Instead, you could look up the opcodes you need in the opcode.opmap dictionary and create named constants, perhaps like this:
LOAD_FAST = opmap['LOAD_FAST'] # actual value is 124
...
for var in disassembly[LOAD_FAST]:
...
Update: in Python 3.4 you can use the new dis.get_instructions:
>>> def f(x):
... return x + 1
>>> import dis
>>> list(dis.get_instructions(f))
[Instruction(opname='LOAD_FAST', opcode=124, arg=0, argval='x',
argrepr='x', offset=0, starts_line=1, is_jump_target=False),
Instruction(opname='LOAD_CONST', opcode=100, arg=1, argval=1,
argrepr='1', offset=3, starts_line=None, is_jump_target=False),
Instruction(opname='BINARY_ADD', opcode=23, arg=None, argval=None,
argrepr='', offset=6, starts_line=None, is_jump_target=False),
Instruction(opname='RETURN_VALUE', opcode=83, arg=None, argval=None,
argrepr='', offset=7, starts_line=None, is_jump_target=False)]

I think the challenge here is to capture the output of a dis rather than parsing the output and create a dictionary. The reason I will not cover the second part is, the format and the fields (key, value) of the dictionary is not mentioned and its trivial.
As I mentioned, the reason its a challenge to capture the OP of dis is, its a print rather than a return, but this can be captured through context manager
def foo(co):
import sys
from contextlib import contextmanager
from cStringIO import StringIO
#contextmanager
def captureStdOut(output):
stdout = sys.stdout
sys.stdout = output
yield
sys.stdout = stdout
out = StringIO()
with captureStdOut(out):
dis.disassemble(co.func_code)
return out.getvalue()
import dis
import re
dict(re.findall("^.*?([A-Z_]+)\s+(.*)$", line)[0] for line in foo(foo).splitlines()
if line.strip())
{'LOAD_CONST': '0 (None)', 'WITH_CLEANUP': '', 'SETUP_WITH': '21 (to 107)', 'STORE_DEREF': '0 (sys)', 'POP_TOP': '', 'LOAD_FAST': '4 (out)', 'MAKE_CLOSURE': '0', 'STORE_FAST': '4 (out)', 'IMPORT_FROM': '4 (StringIO)', 'LOAD_GLOBAL': '5 (dis)', 'END_FINALLY': '', 'RETURN_VALUE': '', 'LOAD_CLOSURE': '0 (sys)', 'BUILD_TUPLE': '1', 'CALL_FUNCTION': '0', 'LOAD_ATTR': '8 (getvalue)', 'IMPORT_NAME': '3 (cStringIO)', 'POP_BLOCK': ''}
>>>