Text filters - Adding filters "Trim whitespace" and "Remove duplicate lines"

changedetectionio/forms.py

@@ -480,8 +480,10 @@ class processor_text_json_diff_form(commonSettingsForm):
     body = TextAreaField('Request body', [validators.Optional()])
     method = SelectField('Request method', choices=valid_method, default=default_method)
     ignore_status_codes = BooleanField('Ignore status codes (process non-2xx status codes as normal)', default=False)
-    check_unique_lines = BooleanField('Only trigger when unique lines appear', default=False)
+    check_unique_lines = BooleanField('Only trigger when unique lines appear in all history', default=False)
+    remove_duplicate_lines = BooleanField('Remove duplicate lines of text', default=False)
     sort_text_alphabetically =  BooleanField('Sort text alphabetically', default=False)
+    trim_text_whitespace = BooleanField('Trim whitespace before and after text', default=False)
 
     filter_text_added = BooleanField('Added lines', default=True)
     filter_text_replaced = BooleanField('Replaced/changed lines', default=True)

changedetectionio/model/__init__.py

@@ -60,6 +60,8 @@ class watch_base(dict):
             'time_between_check_use_default': True,
             'title': None,
             'track_ldjson_price_data': None,
+            'trim_text_whitespace': False,
+            'remove_duplicate_lines': False,
             'trigger_text': [],  # List of text or regex to wait for until a change is detected
             'url': '',
             'uuid': str(uuid.uuid4()),

changedetectionio/processors/text_json_diff/processor.py

@@ -218,11 +218,19 @@ class perform_site_check(difference_detection_processor):
                             is_rss=is_rss)) #1874 activate the <title workaround hack
                         stripped_text_from_html = future.result()
 
-        if watch.get('sort_text_alphabetically') and stripped_text_from_html:
+
+        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.strip() 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 = 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() ))
+            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
         text_content_before_ignored_filter = stripped_text_from_html.encode('utf-8')
@@ -304,7 +312,7 @@ class perform_site_check(difference_detection_processor):
                         for match in res:
                             regex_matched_output += [match] + [b'\n']
 
-            # Now we will only show what the regex matched
+            ##########################################################
             stripped_text_from_html = b''
             text_content_before_ignored_filter = b''
             if regex_matched_output:
@@ -312,6 +320,8 @@ class perform_site_check(difference_detection_processor):
                 stripped_text_from_html = b''.join(regex_matched_output)
                 text_content_before_ignored_filter = stripped_text_from_html
 
+
+
         # 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()

changedetectionio/templates/edit.html

@@ -331,11 +331,22 @@ nav
                     <span class="pure-form-message-inline">So it's always better to select <strong>Added</strong>+<strong>Replaced</strong> when you're interested in new content.</span><br>
                     <span class="pure-form-message-inline">When content is merely moved in a list, it will also trigger an <strong>addition</strong>, consider enabling <code><strong>Only trigger when unique lines appear</strong></code></span>
                 </fieldset>
-
+                <fieldset class="pure-control-group">
+                    {{ render_checkbox_field(form.check_unique_lines) }}
+                    <span class="pure-form-message-inline">Good for websites that just move the content around, and you want to know when NEW content is added, compares new lines against all history for this watch.</span>
+                </fieldset>
+                <fieldset class="pure-control-group">
+                    {{ render_checkbox_field(form.remove_duplicate_lines) }}
+                    <span class="pure-form-message-inline">Remove duplicate lines of text</span>
+                </fieldset>
                 <fieldset class="pure-control-group">
                     {{ render_checkbox_field(form.sort_text_alphabetically) }}
                     <span class="pure-form-message-inline">Helps reduce changes detected caused by sites shuffling lines around, combine with <i>check unique lines</i> below.</span>
                 </fieldset>
+                <fieldset class="pure-control-group">
+                    {{ render_checkbox_field(form.trim_text_whitespace) }}
+                    <span class="pure-form-message-inline">Remove any whitespace before and after each line of text</span>
+                </fieldset>
                 <fieldset class="pure-control-group">
                     {{ render_checkbox_field(form.check_unique_lines) }}
                     <span class="pure-form-message-inline">Good for websites that just move the content around, and you want to know when NEW content is added, compares new lines against all history for this watch.</span>

changedetectionio/tests/test_unique_lines.py

@@ -11,6 +11,8 @@ def set_original_ignore_response():
      <p>Some initial text</p>
      <p>Which is across multiple lines</p>
      <p>So let's see what happens.</p>
+     <p>&nbsp;  So let's see what happens.   <br> </p>
+     <p>A - sortable line</p> 
      </body>
      </html>
     """
@@ -166,3 +168,50 @@ def test_sort_lines_functionality(client, live_server, measure_memory_usage):
     
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
     assert b'Deleted' in res.data
+
+
+def test_extra_filters(client, live_server, measure_memory_usage):
+    #live_server_setup(live_server)
+
+    set_original_ignore_response()
+
+    # 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
+    wait_for_all_checks(client)
+
+    # Add our URL to the import page
+    res = client.post(
+        url_for("edit_page", uuid="first"),
+        data={"remove_duplicate_lines": "y",
+              "trim_text_whitespace": "y",
+              "sort_text_alphabetically": "",  # leave this OFF for testing
+              "url": test_url,
+              "fetch_backend": "html_requests"},
+        follow_redirects=True
+    )
+    assert b"Updated watch." in res.data
+    # Give the thread time to pick it up
+    wait_for_all_checks(client)
+    # Trigger a check
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+
+    # Give the thread time to pick it up
+    wait_for_all_checks(client)
+
+    res = client.get(
+        url_for("preview_page", uuid="first")
+    )
+
+    assert res.data.count(b"see what happens.") == 1
+
+    # still should remain unsorted ('A - sortable line') stays at the end
+    assert res.data.find(b'A - sortable line') > res.data.find(b'Which is across multiple lines')
+
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data