From bdc52a1fceba0b6ca2301128e6978c85bf771a4a Mon Sep 17 00:00:00 2001
From: Bob Mottram <bob@libreserver.org>
Date: Sat, 21 Sep 2024 21:52:13 +0100
Subject: [PATCH] Fix for removing long words

---
 content.py | 20 ++++++++++++++++++++
 tests.py   | 55 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 75 insertions(+)

diff --git a/content.py b/content.py
index 8d0d7edbb..5fa6e136e 100644
--- a/content.py
+++ b/content.py
@@ -1088,6 +1088,16 @@ def remove_long_words(content: str, max_word_length: int,
     if is_pgp_encrypted(content) or contains_pgp_public_key(content):
         return content
     content = replace_content_duplicates(content)
+
+    non_html_list = False
+    if '\n\n' in content and '<p>' not in content:
+        content = '<p>' + content.replace('\n\n', '</p> <p>') + '</p>'
+        non_html_list = True
+    non_html_list2 = False
+    if '\n' in content and '<p>' not in content:
+        content = '<p>' + content.replace('\n', '</p> <p>') + '</p>'
+        non_html_list2 = True
+
     if ' ' not in content and '</p><p>' not in content:
         # handle a single very long string with no spaces
         content_str = content.replace('<p>', '').replace(r'<\p>', '')
@@ -1166,6 +1176,16 @@ def remove_long_words(content: str, max_word_length: int,
         if not content.endswith('</p>'):
             content = content.strip() + '</p>'
     content = content.replace('<p> </p>', '<p></p>')
+    if non_html_list:
+        content = content.replace('</p> <p>', '\n\n')
+        content = content.replace('<p>', '')
+        content = content.replace('</p>', '')
+    if non_html_list2:
+        content = content.replace('</p> <p>', '\n')
+        content = content.replace('<p>', '')
+        content = content.replace('</p>', '')
+    content = content.replace('</p> <p>', '</p><p>')
+
     return content
 
 
diff --git a/tests.py b/tests.py
index 1862cac39..8b8e6241f 100644
--- a/tests.py
+++ b/tests.py
@@ -8855,6 +8855,61 @@ def _test_uninvert2():
 
 def _test_check_individual_post_content():
     print('check_individual_post_content')
+
+    content = "Unenshitification?\n\n" + \
+        "Counter-enshitification?\n\n" + \
+        "Anti-enshitification?"
+    content2 = remove_style_within_html(content)
+    if content2 != content:
+        print(content)
+        print(content2)
+    assert content2 == content
+
+    content3 = remove_long_words(content, 40, [])
+    if content3 != content:
+        print(content)
+        print(content3)
+    assert content3 == content
+
+    content4 = remove_text_formatting(content, False)
+    if content4 != content:
+        print(content)
+        print(content4)
+    assert content4 == content
+
+    content5 = limit_repeated_words(content, 6)
+    if content5 != content:
+        print(content)
+        print(content5)
+    assert content5 == content
+
+    content = "Unenshitification?\n" + \
+        "Counter-enshitification?\n" + \
+        "Anti-enshitification?"
+    content2 = remove_style_within_html(content)
+    if content2 != content:
+        print(content)
+        print(content2)
+    assert content2 == content
+
+    content3 = remove_long_words(content, 40, [])
+    if content3 != content:
+        print(content)
+        print(content3)
+    assert content3 == content
+
+    content4 = remove_text_formatting(content, False)
+    if content4 != content:
+        print(content)
+        print(content4)
+    assert content4 == content
+
+    content5 = limit_repeated_words(content, 6)
+    if content5 != content:
+        print(content)
+        print(content5)
+    assert content5 == content
+
     content = "<p>Unenshitification?</p><p></p><p>" + \
         "Counter-enshitification?</p><p></p>" + \
         "<p>Anti-enshitification?</p><p></p><p>Nonshitification?</p>"