fix(ipnews format) match the paragraph markers

superdesk · Jun 30, 2016 · 3509e36 · 3509e36
1 parent 94efa1f
commit 3509e36
Show file tree

Hide file tree

Showing 2 changed files with 9 additions and 9 deletions.
diff --git a/server/aap/publish/formatters/aap_ipnews_formatter.py b/server/aap/publish/formatters/aap_ipnews_formatter.py
@@ -41,19 +41,20 @@ def format(self, article, subscriber, codes=None):
                 elif article.get(FORMAT, FORMATS.HTML) == FORMATS.HTML:
                     text = StringIO()
                     for p in soup.findAll('p'):
-                        text.write('\x19\r\n')
+                        text.write('   ')
                         ptext = p.get_text('\n')
                         for l in ptext.split('\n'):
                             if len(l) > 80:
                                 text.write(textwrap.fill(l, 80).replace('\n', ' \r\n'))
                             else:
                                 text.write(l + ' \r\n')
+                        text.write('\x19\r\n')
                     body = text.getvalue().replace('\'', '\'\'')
                     # if this is the first take and we have a dateline inject it
                     if self.is_first_part(article) and 'dateline' in article and 'text' in article.get('dateline', {}):
-                        if body.startswith('\x19\r\n'):
-                            body = '\x19\r\n{} {}'.format(article.get('dateline').get('text').replace('\'', '\'\''),
-                                                          body[3:])
+                        if body.startswith('   '):
+                            body = '   {} {}'.format(article.get('dateline').get('text').replace('\'', '\'\''),
+                                                     body[3:])
 
                     odbc_item['article_text'] = body
                     odbc_item['texttab'] = 'x'

diff --git a/server/aap/publish/formatters/aap_ipnews_formatter_test.py b/server/aap/publish/formatters/aap_ipnews_formatter_test.py
@@ -117,8 +117,8 @@ def testIPNewsHtmlToText(self):
         seq, item = f.format(article, subscriber)[0]
         item = json.loads(item)
 
-        expected = '\r\nThe story body line 1 \r\nLine 2 \r\n\r\nabcdefghi abcdefghi abcdefghi abcdefghi ' \
-                   'abcdefghi abcdefghi abcdefghi abcdefghi \r\n\r\nMORE'
+        expected = '   The story body line 1 \r\nLine 2 \r\n\r\n   abcdefghi abcdefghi abcdefghi abcdefghi ' \
+                   'abcdefghi abcdefghi abcdefghi abcdefghi \r\n\r\n\r\nMORE'
         self.assertEqual(item['article_text'], expected)
 
     def testLastTake(self):
@@ -150,9 +150,8 @@ def testLastTake(self):
         f = AAPIpNewsFormatter()
         seq, item = f.format(article, subscriber)[0]
         item = json.loads(item)
-
-        expected = '\r\nThe story body line 1 \r\nLine 2 \r\n\r\nabcdefghi abcdefghi abcdefghi abcdefghi ' \
-                   'abcdefghi abcdefghi abcdefghi abcdefghi \r\n\r\nAAP'
+        expected = '   The story body line 1 \r\nLine 2 \r\n\r\n   abcdefghi abcdefghi abcdefghi abcdefghi ' \
+                   'abcdefghi abcdefghi abcdefghi abcdefghi \r\n\r\n\r\nAAP'
         self.assertEqual(item['article_text'], expected)
 
     def testMultipleCategories(self):