Handle . within content when extracting tags

2019-08-19 12:07:04 +01:00 · 2019-08-19 12:07:04 +01:00 · 68b2c7632a
parent 40805f2ae0
commit 68b2c7632a
1 changed files with 9 additions and 0 deletions
--- a/content.py
+++ b/content.py
@ -150,6 +150,15 @@ def addHtmlTags(baseDir: str,httpPrefix: str, \
    if content.startswith('<p>'):
        return content
    words=content.replace(',',' ').replace(';',' ')
+    # remove . for words which are not mentions
+    wordCtr=0
+    for wordIndex in range(0,len(words)-1):
+        wordStr=words[wordIndex]
+        if wordStr.endswith('.'):
+            if not wordStr.startswith('@'):
+                words[wordIndex]=words[wordIndex][:-1]
+        if wordStr.startsswith('.'):
+            words[wordIndex]=words[wordIndex][1:]
    replaceMentions={}
    replaceHashTags={}
    replaceEmoji={}