Merge pull request isso-comments#903 from projectgus/bugfix/migrate_wordpress_paragraphs

migrate: Handle single newlines in WordPress comments as line breaks

Author: ix5

CHANGES.rst

@@ -17,8 +17,10 @@ Breaking Changes
 Bugfixes & Improvements
 ^^^^^^^^^^^^^^^^^^^^^^^
 
-- TBD
+- When importing from WordPress single newlines are now converted to line breaks
+  (`#903`_, projectgus)
 
+.. _#903: https://github.com/posativ/isso/pull/903
 
 0.13.0.beta1 (2022-06-05)
 -------------------------

isso/migrate.py

@@ -225,9 +225,18 @@ def migrate(self):
         progress.finish("{0} threads, {1} comments".format(
             len(items) - skip, self.count))
 
+    def _process_comment_content(self, text):
+        # WordPress comment text renders a single newline between two blocks of
+        # text as a <br> tag, so add an explicit Markdown line break on import
+        # (Otherwise multiple blocks of text separated by single newlines are
+        # all shown as one long line.)
+        text = re.sub(r'(?!^\n)\n(?!^\n)', '  \n', text, 0)
+
+        return strip(text)
+
     def Comment(self, el):
         return {
-            "text": strip(el.find(self.ns + "comment_content").text),
+            "text": self._process_comment_content(el.find(self.ns + "comment_content").text),
             "author": strip(el.find(self.ns + "comment_author").text),
             "email": strip(el.find(self.ns + "comment_author_email").text),
             "website": strip(el.find(self.ns + "comment_author_url").text),

isso/tests/test_migration.py

@@ -87,7 +87,7 @@ def test_wordpress(self):
         self.assertEqual(
             len(db.execute("SELECT id FROM threads").fetchall()), 2)
         self.assertEqual(
-            len(db.execute("SELECT id FROM comments").fetchall()), 7)
+            len(db.execute("SELECT id FROM comments").fetchall()), 8)
 
         first = db.comments.get(1)
         self.assertEqual(first["author"], "Ohai")
@@ -101,7 +101,11 @@ def test_wordpress(self):
         for i in (3, 4, 5):
             self.assertEqual(db.comments.get(i)["parent"], second["id"])
 
-        last = db.comments.get(6)
+        # Ensure newlines in wordpress translate to two newlines in isso, to render the same
+        multiline = db.comments.get(6)
+        self.assertIn("multiple lines:  \nWordPress", multiline["text"])
+
+        last = db.comments.get(7)
         self.assertEqual(last["author"], "Letzter :/")
         self.assertEqual(last["parent"], None)
 

isso/tests/wordpress.xml

@@ -101,13 +101,29 @@
             </wp:comment>
             <wp:comment>
                 <wp:comment_id>10</wp:comment_id>
+                <wp:comment_author><![CDATA[Multiline Author]]></wp:comment_author>
+                <wp:comment_author_email>[email protected]
+                </wp:comment_author_email>
+                <wp:comment_author_url></wp:comment_author_url>
+                <wp:comment_author_IP>::ffff:86.52.1.0</wp:comment_author_IP>
+                <wp:comment_date>2022-06-06 12:13:14</wp:comment_date>
+                <wp:comment_date_gmt>2022-06-06 02:13:14</wp:comment_date_gmt>
+                <wp:comment_content><![CDATA[When you have a comment with multiple lines:
+WordPress exports it like this.]]></wp:comment_content>
+                <wp:comment_approved>1</wp:comment_approved>
+                <wp:comment_type></wp:comment_type>
+                <wp:comment_parent>0</wp:comment_parent>
+                <wp:comment_user_id>1</wp:comment_user_id>
+            </wp:comment>
+            <wp:comment>
+                <wp:comment_id>11</wp:comment_id>
                 <wp:comment_author><![CDATA[Letzter :/]]></wp:comment_author>
                 <wp:comment_author_email>[email protected]
                 </wp:comment_author_email>
                 <wp:comment_author_url></wp:comment_author_url>
                 <wp:comment_author_IP>::ffff:86.56.63.0</wp:comment_author_IP>
-                <wp:comment_date>2014-04-29 15:21:56</wp:comment_date>
-                <wp:comment_date_gmt>2014-04-29 15:21:56</wp:comment_date_gmt>
+                <wp:comment_date>2022-06-07 15:21:56</wp:comment_date>
+                <wp:comment_date_gmt>2022-06-07 15:21:56</wp:comment_date_gmt>
                 <wp:comment_content><![CDATA[...]]></wp:comment_content>
                 <wp:comment_approved>1</wp:comment_approved>
                 <wp:comment_type></wp:comment_type>