jules/PushingScores
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

new changes to textedit

Browse Source
This commit is contained in:
Cristina Cochior 2019-05-31 09:43:04 +02:00
parent 9fc5375862
commit 0af0e230c7
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
textedit.py
View File

@ -10,7 +10,7 @@ PART 1
We create the dictionary and save it. We create the dictionary and save it.
""" """
stopws = [",", ".", "?","!",":","(",")",">","<","@","#","``","/","–","''","‘","-","’", "DOCTYPE", "html", "!", "'", "<br>", "<br />", "/body", "/html", "/head", "h2", "/h2", "h1", "/h1","”","“"] stopws = [",", ".", "?","!",":","(",")",">","<","@","#","``","/","–","''","‘","-","’", "DOCTYPE", "html", "!", "'", "<br>", "<br />", "/body", "/html", "/head", "h2", "/h2", "h1", "/h1","”","“", "o", "Ca", "/"]
path = "static/files/" path = "static/files/"
for path, subdirs, files in os.walk(path): for path, subdirs, files in os.walk(path):
@ -55,7 +55,7 @@ def analysis(the_word, file_name):
# print(re_word) # print(re_word)
# print(the_word) # print(the_word)
for sent_token in sent_tokens: for sent_token in sent_tokens:
if re.search(re_word, sent_token): if re.search(re_word, sent_token, re.IGNORECASE):
new_sent_tokens.append({'id': id, 'sentence': sent_token.replace('\n', ' ').strip("'<>()“”")}) new_sent_tokens.append({'id': id, 'sentence': sent_token.replace('\n', ' ').strip("'<>()“”")})
if the_word in sentences_w_word: # if this is not the first iteration if the_word in sentences_w_word: # if this is not the first iteration
previous_sent_tokens = sentences_w_word[the_word] previous_sent_tokens = sentences_w_word[the_word]