Skip to content

Minor Typo candiate_words -> candidate_words #13

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
codelucas merged 1 commit into from
Jan 20, 2014
Merged

Minor Typo candiate_words -> candidate_words #13

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 7 additions & 7 deletions newspaper/text.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -75,18 +75,18 @@ def remove_punctuation(self, content):
content = content.encode('utf-8')
return content.translate(self.TRANS_TABLE, string.punctuation)

def candiate_words(self, stripped_input):
def candidate_words(self, stripped_input):
return stripped_input.split(' ')

def get_stopword_count(self, content):
if not content:
return WordStats()
ws = WordStats()
stripped_input = self.remove_punctuation(content)
candiate_words = self.candiate_words(stripped_input)
candidate_words = self.candidate_words(stripped_input)
overlapping_stopwords = []
c = 0
for w in candiate_words:
for w in candidate_words:
c += 1
if w.lower() in self.STOP_WORDS:
overlapping_stopwords.append(w.lower())
Expand All @@ -104,7 +104,7 @@ class StopWordsChinese(StopWords):
def __init__(self, language='zh'):
super(StopWordsChinese, self).__init__(language='zh')

def candiate_words(self, stripped_input):
def candidate_words(self, stripped_input):
# jieba builds a tree that takes a while. avoid building
# this tree if we don't use the chinese language
from .packages import jieba
Expand All @@ -122,7 +122,7 @@ def __init__(self, language='ar'):
def remove_punctuation(self, content):
return content

def candiate_words(self, stripped_input):
def candidate_words(self, stripped_input):
import nltk
s = nltk.stem.isri.ISRIStemmer()
words = []
Expand All @@ -143,10 +143,10 @@ def get_stopword_count(self, content):
return WordStats()
ws = WordStats()
stripped_input = self.remove_punctuation(content)
candiate_words = self.candiate_words(stripped_input)
candidate_words = self.candidate_words(stripped_input)
overlapping_stopwords = []
c = 0
for w in candiate_words:
for w in candidate_words:
c += 1
for stop_word in self.STOP_WORDS:
overlapping_stopwords.append(stop_word)
Expand Down