cereme/baram.py

## baram.py
import re
lines = None
char_dict = {}
valid_regex = re.compile('[가-힣A-Za-z0-9]')
def char_filter(elem):
    return bool(valid_regex.match(elem[0]))

with open('./baram_email.txt', 'r') as f:
    lines = f.readlines()

for line in lines:
    for char in line:
        try:
            char_dict[char] += 1
        except KeyError:
            char_dict[char] = 1

print(sorted(filter(char_filter ,char_dict.items()), key=lambda x:x[1], reverse=True))

""" result
[('다', 81), ('스', 64), ('니', 63), ('는', 49), ('하', 47), ('트', 47), ('이', 44), ('리', 40), ('가', 39), ('을', 38), ('에', 38), ('프', 38), ('로', 34), ('고', 34),
('를', 32), ('해', 32), ('지', 30), ('일', 28), ('린', 27), ('기', 26), ('합', 26), ('개', 23), ('인', 23), ('크', 22), ('의', 22), ('럼', 21), ('시', 21), ('도', 21), (
'있', 21), ('자', 20), ('주', 20), ('그', 19), ('은', 18), ('서', 17), ('야', 17), ('한', 15), ('어', 15), ('정', 15), ('발', 15), ('습', 15), ('제', 15), ('행', 14), ('
완', 13), ('대', 12), ('으', 12), ('용', 12), ('할', 12), ('입', 11), ('드', 11), ('사', 11), ('적', 11), ('면', 11), ('팀', 11), ('요', 10), ('애', 10), ('변', 10), ('
게', 10), ('위', 10), ('료', 10), ('우', 9), ('방', 9), ('나', 9), ('선', 9), ('되', 9), ('포', 9), ('보', 9), ('들', 9), ('계', 9), ('루', 9), ('백', 9), ('아', 8), ('
라', 8), ('성', 8), ('과', 8), ('수', 8), ('치', 8), ('된', 8), ('데', 8), ('점', 7), ('전', 7), ('경', 7), ('실', 7), ('부', 7), ('문', 7), ('만', 7), ('작', 7), ('획',
 7), ('뷰', 7), ('회', 7), ('토', 7), ('안', 6), ('진', 6), ('었', 6), ('순', 6), ('품', 6), ('임', 6), ('내', 6), ('분', 6), ('마', 6), ('무', 6), ('달', 6), ('최', 6),
 ('밍', 6), ('비', 6), ('세', 5), ('바', 5), ('금', 5), ('법', 5), ('화', 5), ('빠', 5), ('른', 5), ('명', 5), ('산', 5), ('터', 5), ('매', 5), ('했', 5), ('젝', 5), ('
관', 5), ('유', 5), ('공', 5), ('더', 5), ('잘', 5), ('장', 5), ('히', 5), ('책', 5), ('답', 5), ('려', 5), ('목', 5), ('표', 5), ('슈', 5), ('조', 5), ('느', 4), ('4',
4), ('필', 4), ('립', 4), ('중', 4), ('생', 4), ('각', 4), ('와', 4), ('여', 4), ('않', 4), ('모', 4), ('엇', 4), ('력', 4), ('원', 4), ('거', 4), ('래', 4), ('많', 4),
('람', 3), ('란', 3), ('미', 3), ('민', 3), ('함', 3), ('소', 3), ('업', 3), ('통', 3), ('까', 3), ('능', 3), ('출', 3), ('러', 3), ('것', 3), ('1', 3), ('3', 3), ('든',
 3), ('말', 3), ('떤', 3), ('견', 3), ('벽', 3), ('음', 3), ('역', 3), ('됩', 3), ('록', 3), ('협', 3), ('질', 3), ('코', 3), ('불', 3), ('될', 3), ('틴', 3), ('현', 3),
 ('티', 3), ('차', 3), ('후', 3), ('못', 3), ('번', 3), ('0', 3), ('피', 3), ('월', 2), ('타', 2), ('난', 2), ('르', 2), ('첩', 2), ('론', 2), ('웨', 2), ('언', 2), ('a'
, 2), ('e', 2), ('l', 2), ('웠', 2), ('즈', 2), ('높', 2), ('때', 2), ('같', 2), ('워', 2), ('던', 2), ('2', 2), ('신', 2), ('걸', 2), ('외', 2), ('설', 2), ('동', 2), (
'반', 2), ('허', 2), ('규', 2), ('칙', 2), ('련', 2), ('앞', 2), ('간', 2), ('재', 2), ('등', 2), ('켓', 2), ('열', 2), ('검', 2), ('항', 2), ('두', 2), ('또', 2), ('막'
, 2), ('별', 2), ('운', 2), ('키', 2), ('담', 2), ('당', 2), ('Q', 2), ('A', 2), ('없', 2), ('랍', 2), ('글', 2), ('누', 2), ('감', 2), ('녕', 1), ('름', 1), ('덧', 1),
('8', 1), ('파', 1), ('앳', 1), ('플', 1), ('껴', 1), ('메', 1), ('접', 1), ('근', 1), ('환', 1), ('응', 1), ('뜻', 1), ('젠', 1), ('택', 1), ('닌', 1), ('폭', 1), ('w', 1), ('t', 1), ('r', 1), ('f', 1), ('객', 1), ('레', 1), ('효', 1), ('뢰', 1), ('벤', 1), ('투', 1), ('결', 1), ('국', 1), ('끼', 1), ('엔', 1), ('확', 1), ('구', 1), ('권', 1), ('체', 1), ('심', 1), ('극', 1), ('웁', 1), ('알', 1), ('헤', 1), ('쳐', 1), ('호', 1), ('테', 1), ('복', 1), ('뀌', 1), ('종', 1), ('즉', 1), ('킴', 1), ('써', 1), ('속', 1), ('집', 1), ('약', 1), ('단', 1), ('준', 1), ('겠', 1), ('떻', 1), ('찾', 1), ('추', 1), ('노', 1), ('너', 1), ('5', 1), ('탠', 1), ('멤', 1), ('버', 1), ('물', 1), ('씀', 1), ('렸', 1), ('y', 1), ('축', 1), ('P', 1), ('R', 1), ('상', 1), ('족', 1), ('큼', 1), ('처', 1), ('영', 1), ('였', 1), ('직', 1), ('듭', 1), ('희', 1), ('망', 1), ('좋', 1), ('퀴', 1), ('본', 1), ('몇', 1), ('특', 1), ('띄', 1), ('쓰', 1), ('x', 1), ('님', 1), ('맞', 1), ('머', 1), ('므', 1), ('먼', 1), ('저', 1), ('킨', 1), ('콘', 1), ('림', 1)]
"""
	import re
	lines = None
	char_dict = {}
	valid_regex = re.compile('[가-힣A-Za-z0-9]')
	def char_filter(elem):
	return bool(valid_regex.match(elem[0]))

	with open('./baram_email.txt', 'r') as f:
	lines = f.readlines()

	for line in lines:
	for char in line:
	try:
	char_dict[char] += 1
	except KeyError:
	char_dict[char] = 1

	print(sorted(filter(char_filter ,char_dict.items()), key=lambda x:x[1], reverse=True))

	""" result
	[('다', 81), ('스', 64), ('니', 63), ('는', 49), ('하', 47), ('트', 47), ('이', 44), ('리', 40), ('가', 39), ('을', 38), ('에', 38), ('프', 38), ('로', 34), ('고', 34),
	('를', 32), ('해', 32), ('지', 30), ('일', 28), ('린', 27), ('기', 26), ('합', 26), ('개', 23), ('인', 23), ('크', 22), ('의', 22), ('럼', 21), ('시', 21), ('도', 21), (
	'있', 21), ('자', 20), ('주', 20), ('그', 19), ('은', 18), ('서', 17), ('야', 17), ('한', 15), ('어', 15), ('정', 15), ('발', 15), ('습', 15), ('제', 15), ('행', 14), ('
	완', 13), ('대', 12), ('으', 12), ('용', 12), ('할', 12), ('입', 11), ('드', 11), ('사', 11), ('적', 11), ('면', 11), ('팀', 11), ('요', 10), ('애', 10), ('변', 10), ('
	게', 10), ('위', 10), ('료', 10), ('우', 9), ('방', 9), ('나', 9), ('선', 9), ('되', 9), ('포', 9), ('보', 9), ('들', 9), ('계', 9), ('루', 9), ('백', 9), ('아', 8), ('
	라', 8), ('성', 8), ('과', 8), ('수', 8), ('치', 8), ('된', 8), ('데', 8), ('점', 7), ('전', 7), ('경', 7), ('실', 7), ('부', 7), ('문', 7), ('만', 7), ('작', 7), ('획',
	7), ('뷰', 7), ('회', 7), ('토', 7), ('안', 6), ('진', 6), ('었', 6), ('순', 6), ('품', 6), ('임', 6), ('내', 6), ('분', 6), ('마', 6), ('무', 6), ('달', 6), ('최', 6),
	('밍', 6), ('비', 6), ('세', 5), ('바', 5), ('금', 5), ('법', 5), ('화', 5), ('빠', 5), ('른', 5), ('명', 5), ('산', 5), ('터', 5), ('매', 5), ('했', 5), ('젝', 5), ('
	관', 5), ('유', 5), ('공', 5), ('더', 5), ('잘', 5), ('장', 5), ('히', 5), ('책', 5), ('답', 5), ('려', 5), ('목', 5), ('표', 5), ('슈', 5), ('조', 5), ('느', 4), ('4',
	4), ('필', 4), ('립', 4), ('중', 4), ('생', 4), ('각', 4), ('와', 4), ('여', 4), ('않', 4), ('모', 4), ('엇', 4), ('력', 4), ('원', 4), ('거', 4), ('래', 4), ('많', 4),
	('람', 3), ('란', 3), ('미', 3), ('민', 3), ('함', 3), ('소', 3), ('업', 3), ('통', 3), ('까', 3), ('능', 3), ('출', 3), ('러', 3), ('것', 3), ('1', 3), ('3', 3), ('든',
	3), ('말', 3), ('떤', 3), ('견', 3), ('벽', 3), ('음', 3), ('역', 3), ('됩', 3), ('록', 3), ('협', 3), ('질', 3), ('코', 3), ('불', 3), ('될', 3), ('틴', 3), ('현', 3),
	('티', 3), ('차', 3), ('후', 3), ('못', 3), ('번', 3), ('0', 3), ('피', 3), ('월', 2), ('타', 2), ('난', 2), ('르', 2), ('첩', 2), ('론', 2), ('웨', 2), ('언', 2), ('a'
	, 2), ('e', 2), ('l', 2), ('웠', 2), ('즈', 2), ('높', 2), ('때', 2), ('같', 2), ('워', 2), ('던', 2), ('2', 2), ('신', 2), ('걸', 2), ('외', 2), ('설', 2), ('동', 2), (
	'반', 2), ('허', 2), ('규', 2), ('칙', 2), ('련', 2), ('앞', 2), ('간', 2), ('재', 2), ('등', 2), ('켓', 2), ('열', 2), ('검', 2), ('항', 2), ('두', 2), ('또', 2), ('막'
	, 2), ('별', 2), ('운', 2), ('키', 2), ('담', 2), ('당', 2), ('Q', 2), ('A', 2), ('없', 2), ('랍', 2), ('글', 2), ('누', 2), ('감', 2), ('녕', 1), ('름', 1), ('덧', 1),
	('8', 1), ('파', 1), ('앳', 1), ('플', 1), ('껴', 1), ('메', 1), ('접', 1), ('근', 1), ('환', 1), ('응', 1), ('뜻', 1), ('젠', 1), ('택', 1), ('닌', 1), ('폭', 1), ('w', 1), ('t', 1), ('r', 1), ('f', 1), ('객', 1), ('레', 1), ('효', 1), ('뢰', 1), ('벤', 1), ('투', 1), ('결', 1), ('국', 1), ('끼', 1), ('엔', 1), ('확', 1), ('구', 1), ('권', 1), ('체', 1), ('심', 1), ('극', 1), ('웁', 1), ('알', 1), ('헤', 1), ('쳐', 1), ('호', 1), ('테', 1), ('복', 1), ('뀌', 1), ('종', 1), ('즉', 1), ('킴', 1), ('써', 1), ('속', 1), ('집', 1), ('약', 1), ('단', 1), ('준', 1), ('겠', 1), ('떻', 1), ('찾', 1), ('추', 1), ('노', 1), ('너', 1), ('5', 1), ('탠', 1), ('멤', 1), ('버', 1), ('물', 1), ('씀', 1), ('렸', 1), ('y', 1), ('축', 1), ('P', 1), ('R', 1), ('상', 1), ('족', 1), ('큼', 1), ('처', 1), ('영', 1), ('였', 1), ('직', 1), ('듭', 1), ('희', 1), ('망', 1), ('좋', 1), ('퀴', 1), ('본', 1), ('몇', 1), ('특', 1), ('띄', 1), ('쓰', 1), ('x', 1), ('님', 1), ('맞', 1), ('머', 1), ('므', 1), ('먼', 1), ('저', 1), ('킨', 1), ('콘', 1), ('림', 1)]
	"""