def eh_linha_vazia(self, linha):
tester = VerEx().\
start_of_line().\
end_of_line()
teste_1 = tester.match(linha)
teste_2 = tester.match(VerEx().find(' ').replace(linha, ''))
teste_3 = linha == ''
return (teste_1 is not None) or (teste_2 is not None) or teste_3
def sentiment_words(self, filename):
"""
Parameters
----------
filename : str
file path for sentiment scores. Represented with a pos, neg, or both score. .
Returns
-------
Dictionary of sentiment scores for words.
"""
df = pd.read_table(filename, skiprows=26)
df['score'] = df['PosScore'] - df['NegScore']
df = df[['SynsetTerms', 'score']]
df.columns = ['words', 'score']
# remove neutral words
mask = df['score'] != 0
df = df[mask]
# Regex to find number
rx1 = re.compile('#([0-9])')
# Regex to find words
verEx = VerEx()
exp = verEx.range('a', 'z', 'A', 'Z')
rx2 = re.compile(exp.source())
sent_dict = {}
for i, row in df.iterrows():
w = row['words']
s = row['score']
nums = re.findall(rx1, w)
w = w.split(' ')
words = []
if len(w) == 1:
words = ''.join(re.findall(rx2, str(w)))
else:
words = [''.join(re.findall(rx2, str(string))) for string in w]
for nn, ww in zip(nums, words):
# only sentiment for the most common meaning of the word
if nn == '1':
sent_dict[ww] = s
return sent_dict
# mylist = []
# if mylist:
# print('zzzz')
# zzz = ['3'][0]
# zzz = str(zzz)
# print(zzz)
# website = '222222222222222222222'
# #
# # print(website.startswith('www'))
# # if website.startswith('www'):
# # project_performance
# # print('AAAAAAAAAAAAAAAAA')
from verbalexpressions import VerEx
verbal_expression = VerEx()
# Create a test string
replace_me = "Replace bird with a duck"
# Create an expression that looks for the word "bird"
expression = VerEx().find('bird')
# Execute the expression in VerEx
result_VerEx = expression.replace(replace_me, 'duck')
print(result_VerEx)
# Or we can compile and use the regular expression using re
import re
regexp = expression.compile()
result_re = regexp.sub('duck', replace_me)
def setUp(self):
self.v = VerEx()
#!/usr/bin/env python
# coding: utf-8
# In[198]:
from verbalexpressions import VerEx
# In[199]:
verEx = VerEx()
# In[200]:
strings = ['123Abdul233', '233Raja434', '223Ethan Hunt444']
# In[201]:
expression = verEx.range('a', 'z', 'A', 'Z', ' ')
# In[202]:
expression.source()
# In[204]:
import re
re_exp = expression.compile()
# In[205]:
import os
import subprocess
import sys
from mdx_gfm import GithubFlavoredMarkdownExtension
DEBUG_MODE = json.loads(sys.argv[1].lower())
def log(s: str):
print(" >> %s" % s)
url = 'file:///android_asset/'
# pre hyperlink fixer
re_disable_link = (VerEx().find("[").anything_but("]").find(
"](http").anything_but(")").find(")").regex())
to_disable_link = r'\2'
# pre hyperlink fixer
re_fix_innerlink = (VerEx().find("[").anything_but("]").find(
"](#").anything_but(")").find(")").regex())
# %s will be self markdown name
to_fix_innerlink = r'[\2](%s#\4)'
# fix hyperlink
re_fix_linkpath = (VerEx().find("[").anything_but("]").find("](").anything_but(
'#').maybe("#").anything_but(")").find(")").regex())
to_fix_linkpath = r'[\2](%s\4.html\5\6)' % url
# img-tag to a-tag
re_img2a = (VerEx().find("<img").anything().find(' src="').anything().find(
# -*- coding:utf-8 -*-
import re
from verbalexpressions import VerEx
# Create an example of how to test for correctly formed URLs
verbal_expression = VerEx()
# word = (verbal_expression.start_of_line('#').anything_but("#").end_of_line("#"))
# print(word.source())
verbal_expression = VerEx()
tester = (verbal_expression.
start_of_line().
find('http').
maybe('s').
find('://').
maybe('www.').
anything_but(' ').
end_of_line()
)
# Create an example URL
# test_url = "https://www.google.com"
# Test if the URL is valid
# if tester.match(test_url):
# print("Valid URL")
# Print the generated regex
print(tester.source()) # => ^(http)(s)?(\:\/\/)(www\.)?([^\ ]*)$
import markdown
import os
import subprocess
import sys
DEBUG_MODE = json.loads(sys.argv[1].lower())
def log(s: str):
print(" >> %s" % s)
url = 'file:///android_asset/'
# pre hyperlink fixer
re_disable_link = (VerEx().find("[").anything_but("]").find(
"](http").anything_but(")").find(")").regex())
to_disable_link = r'\2'
# pre hyperlink fixer
re_fix_innerlink = (VerEx().find("[").anything_but("]").find(
"](#").anything_but(")").find(")").regex())
# %s will be self markdown name
to_fix_innerlink = r'[\2](%s#\4)'
# fix hyperlink
re_fix_linkpath = (VerEx().find("[").anything_but("]").find("](").anything_but(
'#').maybe("#").anything_but(")").find(")").regex())
to_fix_linkpath = r'[\2](%s\4.html\5\6)' % url
# img-tag to a-tag
re_img2a = (VerEx().find("<img").anything().find(' src="').anything().find(