Misc fixes - juggling utf-8 not needed

(its utf-16 by default python string)

changedetectionio/blueprint/tags/templates/edit-tag.html

@@ -17,7 +17,6 @@
 </script>
 
 <script src="{{url_for('static_content', group='js', filename='watch-settings.js')}}" defer></script>
-<!--<script src="{{url_for('static_content', group='js', filename='limit.js')}}" defer></script>-->
 <script src="{{url_for('static_content', group='js', filename='notifications.js')}}" defer></script>
 
 <div class="edit-form monospaced-textarea">

changedetectionio/html_tools.py

@@ -357,7 +357,7 @@ def strip_ignore_text(content, wordlist, mode="content"):
 
             if not got_match:
                 # Not ignored
-                output.append(line.encode('utf8'))
+                output.append(line)
             else:
                 ignored_line_numbers.append(i)
 
@@ -366,7 +366,7 @@ def strip_ignore_text(content, wordlist, mode="content"):
     if mode == "line numbers":
         return ignored_line_numbers
 
-    return "\n".encode('utf8').join(output)
+    return "\n".join(output)
 
 def cdata_in_document_to_text(html_content: str, render_anchor_tag_content=False) -> str:
     from xml.sax.saxutils import escape as xml_escape

changedetectionio/model/Watch.py

@@ -312,13 +312,13 @@ class model(watch_base):
             dest = os.path.join(self.watch_data_dir, snapshot_fname)
             if not os.path.exists(dest):
                 with open(dest, 'wb') as f:
-                    f.write(brotli.compress(contents, mode=brotli.MODE_TEXT))
+                    f.write(brotli.compress(contents.encode('utf-8'), mode=brotli.MODE_TEXT))
         else:
             snapshot_fname = f"{snapshot_id}.txt"
             dest = os.path.join(self.watch_data_dir, snapshot_fname)
             if not os.path.exists(dest):
                 with open(dest, 'wb') as f:
-                    f.write(contents)
+                    f.write(contents.encode('utf-8'))
 
         # Append to index
         # @todo check last char was \n

changedetectionio/processors/restock_diff/processor.py

@@ -307,4 +307,4 @@ class perform_site_check(difference_detection_processor):
         # Always record the new checksum
         update_obj["previous_md5"] = fetched_md5
 
-        return changed_detected, update_obj, snapshot_content.encode('utf-8').strip()
+        return changed_detected, update_obj, snapshot_content.strip()

changedetectionio/processors/text_json_diff/__init__.py

@@ -72,7 +72,7 @@ def prepare_filter_prevew(datastore, watch_uuid):
                                                                  )
             # Use the last loaded HTML as the input
             update_handler.datastore = datastore
-            update_handler.fetcher.content = decompressed_data
+            update_handler.fetcher.content = str(decompressed_data) # str() because playwright/puppeteer/requests return string
             update_handler.fetcher.headers['content-type'] = tmp_watch.get('content-type')
 
             # Process our watch with filters and the HTML from disk, and also a blank watch with no filters but also with the same HTML from disk

changedetectionio/processors/text_json_diff/processor.py

@@ -205,18 +205,9 @@ class perform_site_check(difference_detection_processor):
         if watch.get('trim_text_whitespace'):
             stripped_text_from_html = '\n'.join(line.strip() for line in stripped_text_from_html.replace("\n\n", "\n").splitlines())
 
-        if watch.get('remove_duplicate_lines'):
-            stripped_text_from_html = '\n'.join(dict.fromkeys(line for line in stripped_text_from_html.replace("\n\n", "\n").splitlines()))
-
-        if watch.get('sort_text_alphabetically'):
-            # Note: Because a <p>something</p> will add an extra line feed to signify the paragraph gap
-            # we end up with 'Some text\n\n', sorting will add all those extra \n at the start, so we remove them here.
-            stripped_text_from_html = stripped_text_from_html.replace("\n\n", "\n")
-            stripped_text_from_html = '\n'.join(sorted(stripped_text_from_html.splitlines(), key=lambda x: x.lower()))
-
         # Re #340 - return the content before the 'ignore text' was applied
         # Also used to calculate/show what was removed
-        text_content_before_ignored_filter = stripped_text_from_html.encode('utf-8')
+        text_content_before_ignored_filter = stripped_text_from_html
 
         # @todo whitespace coming from missing rtrim()?
         # stripped_text_from_html could be based on their preferences, replace the processed text with only that which they want to know about.
@@ -235,12 +226,12 @@ class perform_site_check(difference_detection_processor):
                                              line_feed_sep="\n",
                                              include_change_type_prefix=False)
 
-            watch.save_last_text_fetched_before_filters(text_content_before_ignored_filter)
+            watch.save_last_text_fetched_before_filters(text_content_before_ignored_filter.encode('utf-8'))
 
             if not rendered_diff and stripped_text_from_html:
                 # We had some content, but no differences were found
                 # Store our new file as the MD5 so it will trigger in the future
-                c = hashlib.md5(stripped_text_from_html.encode('utf-8').translate(None, b'\r\n\t ')).hexdigest()
+                c = hashlib.md5(stripped_text_from_html.translate(b'\r\n\t ').encode('utf-8')).hexdigest()
                 return False, {'previous_md5': c}, stripped_text_from_html.encode('utf-8')
             else:
                 stripped_text_from_html = rendered_diff
@@ -264,10 +255,8 @@ class perform_site_check(difference_detection_processor):
         # If there's text to skip
         # @todo we could abstract out the get_text() to handle this cleaner
         text_to_ignore = watch.get('ignore_text', []) + self.datastore.data['settings']['application'].get('global_ignore_text', [])
-        if len(text_to_ignore):
+        if text_to_ignore:
             stripped_text_from_html = html_tools.strip_ignore_text(stripped_text_from_html, text_to_ignore)
-        else:
-            stripped_text_from_html = stripped_text_from_html.encode('utf8')
 
         # 615 Extract text by regex
         extract_text = watch.get('extract_text', [])
@@ -301,15 +290,22 @@ class perform_site_check(difference_detection_processor):
             if regex_matched_output:
                 # @todo some formatter for presentation?
                 stripped_text_from_html = b''.join(regex_matched_output)
-                text_content_before_ignored_filter = stripped_text_from_html
 
+        if watch.get('remove_duplicate_lines'):
+            stripped_text_from_html = '\n'.join(dict.fromkeys(line for line in stripped_text_from_html.replace("\n\n", "\n").splitlines()))
 
 
+        if watch.get('sort_text_alphabetically'):
+            # Note: Because a <p>something</p> will add an extra line feed to signify the paragraph gap
+            # we end up with 'Some text\n\n', sorting will add all those extra \n at the start, so we remove them here.
+            stripped_text_from_html = stripped_text_from_html.replace("\n\n", "\n")
+            stripped_text_from_html = '\n'.join(sorted(stripped_text_from_html.splitlines(), key=lambda x: x.lower()))
+
         # Re #133 - if we should strip whitespaces from triggering the change detected comparison
         if self.datastore.data['settings']['application'].get('ignore_whitespace', False):
-            fetched_md5 = hashlib.md5(stripped_text_from_html.translate(None, b'\r\n\t ')).hexdigest()
+            fetched_md5 = hashlib.md5(stripped_text_from_html.translate(b'\r\n\t ').encode('utf-8')).hexdigest()
         else:
-            fetched_md5 = hashlib.md5(stripped_text_from_html).hexdigest()
+            fetched_md5 = hashlib.md5(stripped_text_from_html.encode('utf-8')).hexdigest()
 
         ############ Blocking rules, after checksum #################
         blocked = False

changedetectionio/templates/edit.html

@@ -26,7 +26,6 @@
 </script>
 <script src="{{url_for('static_content', group='js', filename='plugins.js')}}" defer></script>
 <script src="{{url_for('static_content', group='js', filename='watch-settings.js')}}" defer></script>
-<script src="{{url_for('static_content', group='js', filename='limit.js')}}" defer></script>
 <script src="{{url_for('static_content', group='js', filename='notifications.js')}}" defer></script>
 <script src="{{url_for('static_content', group='js', filename='visual-selector.js')}}" defer></script>
 {% if playwright_enabled %}

changedetectionio/update_worker.py

@@ -286,8 +286,8 @@ class update_worker(threading.Thread):
                         # Re #342
                         # In Python 3, all strings are sequences of Unicode characters. There is a bytes type that holds raw bytes.
                         # We then convert/.decode('utf-8') for the notification etc
-                        if not isinstance(contents, (bytes, bytearray)):
-                            raise Exception("Error - returned data from the fetch handler SHOULD be bytes")
+#                        if not isinstance(contents, (bytes, bytearray)):
+#                            raise Exception("Error - returned data from the fetch handler SHOULD be bytes")
                     except PermissionError as e:
                         logger.critical(f"File permission error updating file, watch: {uuid}")
                         logger.critical(str(e))