From 9765d56a23b499a91ee6b94e27805371521648d8 Mon Sep 17 00:00:00 2001
From: dgtlmoon <dgtlmoon@gmail.com>
Date: Thu, 26 Oct 2023 20:19:59 +0200
Subject: [PATCH] Text Filters - "Extract Text" filter was not being error
 checked properly when using a RegEx (#1902)

---
 changedetectionio/forms.py                    | 10 +++---
 changedetectionio/tests/test_extract_regex.py | 32 +++++++++++++++++++
 2 files changed, 37 insertions(+), 5 deletions(-)

diff --git a/changedetectionio/forms.py b/changedetectionio/forms.py
index e5ee6751..4177ed80 100644
--- a/changedetectionio/forms.py
+++ b/changedetectionio/forms.py
@@ -22,7 +22,8 @@ from wtforms.validators import ValidationError
 # each select <option data-enabled="enabled-0-0"
 from changedetectionio.blueprint.browser_steps.browser_steps import browser_step_ui_config
 
-from changedetectionio import content_fetcher
+from changedetectionio import content_fetcher, html_tools
+
 from changedetectionio.notification import (
     valid_notification_formats,
 )
@@ -284,11 +285,10 @@ class ValidateListRegex(object):
     def __call__(self, form, field):
 
         for line in field.data:
-            if line[0] == '/' and line[-1] == '/':
-                # Because internally we dont wrap in /
-                line = line.strip('/')
+            if re.search(html_tools.PERL_STYLE_REGEX, line, re.IGNORECASE):
                 try:
-                    re.compile(line)
+                    regex = html_tools.perl_style_slash_enclosed_regex_to_options(line)
+                    re.compile(regex)
                 except re.error:
                     message = field.gettext('RegEx \'%s\' is not a valid regular expression.')
                     raise ValidationError(message % (line))
diff --git a/changedetectionio/tests/test_extract_regex.py b/changedetectionio/tests/test_extract_regex.py
index a96b443f..7ff8f3a7 100644
--- a/changedetectionio/tests/test_extract_regex.py
+++ b/changedetectionio/tests/test_extract_regex.py
@@ -202,3 +202,35 @@ def test_check_filter_and_regex_extract(client, live_server):
 
     # Should not be here
     assert b'Some text that did change' not in res.data
+
+
+
+def test_regex_error_handling(client, live_server):
+
+    #live_server_setup(live_server)
+
+    # Add our URL to the import page
+    test_url = url_for('test_endpoint', _external=True)
+    res = client.post(
+        url_for("import_page"),
+        data={"urls": test_url},
+        follow_redirects=True
+    )
+    assert b"1 Imported" in res.data
+
+    ### test regex error handling
+    res = client.post(
+        url_for("edit_page", uuid="first"),
+        data={"extract_text": '/something bad\d{3/XYZ',
+              "url": test_url,
+              "fetch_backend": "html_requests"},
+        follow_redirects=True
+    )
+
+    with open('/tmp/fuck.html', 'wb') as f:
+        f.write(res.data)
+
+    assert b'is not a valid regular expression.' in res.data
+
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data