Removing long words from feed titles

merge-requests/8/head
Bob Mottram 2020-10-31 23:10:38 +00:00
parent ade3c0560b
commit cb49d90bb9
4 changed files with 15 additions and 9 deletions

View File

@ -639,7 +639,7 @@ def removeLongWords(content: str, maxWordLength: int,
wordStr[:maxWordLength]) wordStr[:maxWordLength])
if content.startswith('<p>'): if content.startswith('<p>'):
if not content.endswith('</p>'): if not content.endswith('</p>'):
content = content.strip()+'</p>' content = content.strip() + '</p>'
return content return content

View File

@ -22,7 +22,6 @@ from utils import removeHtml
from blocking import isBlockedDomain from blocking import isBlockedDomain
from blocking import isBlockedHashtag from blocking import isBlockedHashtag
from filters import isFiltered from filters import isFiltered
from content import removeLongWords
def rss2Header(httpPrefix: str, def rss2Header(httpPrefix: str,
@ -90,10 +89,6 @@ def addNewswireDictEntry(baseDir: str, domain: str,
tags=[], maxTags=32) -> None: tags=[], maxTags=32) -> None:
"""Update the newswire dictionary """Update the newswire dictionary
""" """
# remove any long words from the title, which can
# cause column overflows
title = removeLongWords(title, 30, [])
allText = removeHtml(title + ' ' + description) allText = removeHtml(title + ' ' + description)
# check that none of the text is filtered against # check that none of the text is filtered against

View File

@ -1674,6 +1674,15 @@ def testWebLinks():
resultText = removeLongWords(exampleText, 40, []) resultText = removeLongWords(exampleText, 40, [])
assert resultText == exampleText assert resultText == exampleText
exampleText = \
'some.incredibly.long.and.annoying.word.which.should.be.removed: ' + \
'The remaining text'
resultText = removeLongWords(exampleText, 40, [])
print('resultText: ' + resultText)
assert resultText == \
'some.incredibly.long.and.annoying.word.w\n' + \
'hich.should.be.removed: The remaining text'
exampleText = \ exampleText = \
'<p>Tox address is 88AB9DED6F9FBEF43E105FB72060A2D89F9B93C74' + \ '<p>Tox address is 88AB9DED6F9FBEF43E105FB72060A2D89F9B93C74' + \
'4E8C45AB3C5E42C361C837155AFCFD9D448</p>' '4E8C45AB3C5E42C361C837155AFCFD9D448</p>'

View File

@ -5707,9 +5707,10 @@ def htmlNewswire(newswire: {}, nickname: str, moderator: bool,
totalVotesStr = \ totalVotesStr = \
votesIndicator(totalVotes, positiveVoting) votesIndicator(totalVotes, positiveVoting)
title = removeLongWords(item[0], 30, []).replace('\n', '<br>')
htmlStr += '<p class="newswireItemVotedOn">' + \ htmlStr += '<p class="newswireItemVotedOn">' + \
'<a href="' + item[1] + '">' + \ '<a href="' + item[1] + '">' + \
'<span class="newswireItemVotedOn">' + item[0] + \ '<span class="newswireItemVotedOn">' + title + \
'</span></a>' + totalVotesStr '</span></a>' + totalVotesStr
if moderator: if moderator:
htmlStr += \ htmlStr += \
@ -5732,10 +5733,11 @@ def htmlNewswire(newswire: {}, nickname: str, moderator: bool,
totalVotesStr = \ totalVotesStr = \
votesIndicator(totalVotes, positiveVoting) votesIndicator(totalVotes, positiveVoting)
title = removeLongWords(item[0], 30, []).replace('\n', '<br>')
if moderator and moderatedItem: if moderator and moderatedItem:
htmlStr += '<p class="newswireItemModerated">' + \ htmlStr += '<p class="newswireItemModerated">' + \
'<a href="' + item[1] + '">' + \ '<a href="' + item[1] + '">' + \
item[0] + '</a>' + totalVotesStr title + '</a>' + totalVotesStr
htmlStr += ' ' + dateShown htmlStr += ' ' + dateShown
htmlStr += '<a href="/users/' + nickname + \ htmlStr += '<a href="/users/' + nickname + \
'/newswirevote=' + dateStrLink + '" ' + \ '/newswirevote=' + dateStrLink + '" ' + \
@ -5746,7 +5748,7 @@ def htmlNewswire(newswire: {}, nickname: str, moderator: bool,
else: else:
htmlStr += '<p class="newswireItem">' + \ htmlStr += '<p class="newswireItem">' + \
'<a href="' + item[1] + '">' + \ '<a href="' + item[1] + '">' + \
item[0] + '</a>' + \ title + '</a>' + \
totalVotesStr totalVotesStr
htmlStr += ' <span class="newswireDate">' htmlStr += ' <span class="newswireDate">'
htmlStr += dateShown + '</span></p>\n' htmlStr += dateShown + '</span></p>\n'