Allow empty strings

Improved rule
Adding browser_steps json schema rule for API
2025-02-09 22:24:29 +01:00 · 2025-02-09 22:14:17 +01:00 · 2025-02-09 22:12:41 +01:00 · 2025-02-08 18:01:26 +01:00 · 2025-02-08 10:14:19 +01:00 · 2025-02-08 00:23:20 +01:00
6 changed files with 51 additions and 5 deletions
--- a/changedetectionio/init.py
+++ b/changedetectionio/init.py
@@ -2,7 +2,7 @@

 # Read more https://github.com/dgtlmoon/changedetection.io/wiki

-__version__ = '0.49.0'
+__version__ = '0.49.1'

 from changedetectionio.strtobool import strtobool
 from json.decoder import JSONDecodeError
--- a/changedetectionio/api/api_schema.py
+++ b/changedetectionio/api/api_schema.py
@@ -112,6 +112,35 @@ def build_watch_json_schema(d):

    schema['properties']['time_between_check'] = build_time_between_check_json_schema()

+    schema['properties']['browser_steps'] = {
+        "anyOf": [
+            {
+                "type": "array",
+                "items": {
+                    "type": "object",
+                    "properties": {
+                        "operation": {
+                            "type": ["string", "null"],
+                            "maxLength": 5000  # Allows null and any string up to 5000 chars (including "")
+                        },
+                        "selector": {
+                            "type": ["string", "null"],
+                            "maxLength": 5000
+                        },
+                        "optional_value": {
+                            "type": ["string", "null"],
+                            "maxLength": 5000
+                        }
+                    },
+                    "required": ["operation", "selector", "optional_value"],
+                    "additionalProperties": False  # No extra keys allowed
+                }
+            },
+            {"type": "null"},  # Allows null for `browser_steps`
+            {"type": "array", "maxItems": 0}  # Allows empty array []
+        ]
+    }
+
    # headers ?
    return schema

--- a/changedetectionio/content_fetchers/res/stock-not-in-stock.js
+++ b/changedetectionio/content_fetchers/res/stock-not-in-stock.js
@@ -52,6 +52,7 @@ function isItemInStock() {
        'niet leverbaar',
        'niet op voorraad',
        'no disponible',
+        'non disponibile',
        'no longer in stock',
        'no tickets available',
        'not available',
--- a/changedetectionio/html_tools.py
+++ b/changedetectionio/html_tools.py
@@ -1,5 +1,6 @@
-from typing import List
+from loguru import logger
 from lxml import etree
+from typing import List
 import json
 import re

@@ -298,8 +299,10 @@ def extract_json_as_string(content, json_filter, ensure_is_ldjson_info_type=None
 # https://github.com/dgtlmoon/changedetection.io/pull/2041#issuecomment-1848397161w
    # Try to parse/filter out the JSON, if we get some parser error, then maybe it's embedded within HTML tags
    try:
-        stripped_text_from_html = _parse_json(json.loads(content), json_filter)
-    except json.JSONDecodeError:
+        # .lstrip("\ufeff") strings ByteOrderMark from UTF8 and still lets the UTF work
+        stripped_text_from_html = _parse_json(json.loads(content.lstrip("\ufeff") ), json_filter)
+    except json.JSONDecodeError as e:
+        logger.warning(str(e))

        # Foreach <script json></script> blob.. just return the first that matches json_filter
        # As a last resort, try to parse the whole <body>
--- a/changedetectionio/templates/watch-overview.html
+++ b/changedetectionio/templates/watch-overview.html
@@ -108,7 +108,8 @@
                    {% else %}
                    <a class="state-on" href="{{url_for('index', op='pause', uuid=watch.uuid, tag=active_tag_uuid)}}"><img src="{{url_for('static_content', group='images', filename='play.svg')}}" alt="UnPause checks" title="UnPause checks" class="icon icon-unpause" ></a>
                    {% endif %}
-                    <a class="link-mute state-{{'on' if watch.notification_muted else 'off'}}" href="{{url_for('index', op='mute', uuid=watch.uuid, tag=active_tag_uuid)}}"><img src="{{url_for('static_content', group='images', filename='bell-off.svg')}}" alt="Mute notifications" title="Mute notifications" class="icon icon-mute" ></a>
+                    {% set mute_label = 'UnMute notification' if watch.notification_muted else 'Mute notification' %}
+                    <a class="link-mute state-{{'on' if watch.notification_muted else 'off'}}" href="{{url_for('index', op='mute', uuid=watch.uuid, tag=active_tag_uuid)}}"><img src="{{url_for('static_content', group='images', filename='bell-off.svg')}}" alt="{{ mute_label }}" title="{{ mute_label }}" class="icon icon-mute" ></a>
                </td>
                <td class="title-col inline">{{watch.title if watch.title is not none and watch.title|length > 0 else watch.url}}
                    <a class="external" target="_blank" rel="noopener" href="{{ watch.link.replace('source:','') }}"></a>
--- a/changedetectionio/tests/test_jsonpath_jq_selector.py
+++ b/changedetectionio/tests/test_jsonpath_jq_selector.py
@@ -514,3 +514,15 @@ def test_check_jq_ext_filter(client, live_server, measure_memory_usage):
 def test_check_jqraw_ext_filter(client, live_server, measure_memory_usage):
    if jq_support:
        check_json_ext_filter('jq:.[] | select(.status | contains("Sold"))', client, live_server)
+
+def test_jsonpath_BOM_utf8(client, live_server, measure_memory_usage):
+    from .. import html_tools
+
+    # JSON string with BOM and correct double-quoted keys
+    json_str = '\ufeff{"name": "José", "emoji": "😊", "language": "中文", "greeting": "Привет"}'
+
+    # See that we can find the second <script> one, which is not broken, and matches our filter
+    text = html_tools.extract_json_as_string(json_str, "json:$.name")
+    assert text == '"José"'
+
+
Author	SHA1	Message	Date
dgtlmoon	8cac46467e	Allow empty strings	2025-02-09 22:24:29 +01:00
dgtlmoon	5c63f346ac	Improved rule	2025-02-09 22:14:17 +01:00
dgtlmoon	b15c9632c8	Adding `browser_steps` json schema rule for API	2025-02-09 22:12:41 +01:00
dgtlmoon	09ebc6ec63	UI - Fix mute/unmute alt/title label alt/title text in watch overview (#2951 )	2025-02-08 18:01:26 +01:00
dgtlmoon	6b1065502e	0.49.1	2025-02-08 10:14:19 +01:00
vin86	d4c470984a	Update stock-not-in-stock.js - Italian (#2948 )	2025-02-08 00:23:20 +01:00
dgtlmoon	55da48f719	Re #2945 - Handle/Strip UTF-8 ByteOrderMark in JSON strings correctly (fixes `"Exception: No parsable JSON found in this document"` error) (#2947 )	2025-02-07 22:19:23 +01:00