Restock & Price detection - Fix decimal-comma prices ("39,99") being read as 3999 (#4493) (#4494), Warning: Could change previous values that were wrongly stored as 4999 -> 49.99 for example

The extractors stripped everything but [\d.] before converting, so the
decimal comma was thrown away before Restock.parse_currency(), which
already understands it, ever saw the value. Route the values through
parse_currency() instead, and teach it that a lone "1,299" is a
thousands separator so that case does not regress.

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>

changedetectionio/processors/restock_diff/__init__.py

@@ -26,6 +26,9 @@ class Restock(dict):
                 standardized_value = standardized_value.replace(',', '')
             else:
                 standardized_value = standardized_value.replace('.', '').replace(',', '.')
+        elif re.fullmatch(r'\D*\d{1,3}(,\d{3})+\D*', standardized_value):
+            # Only thousands separators ie "1,299"
+            standardized_value = standardized_value.replace(',', '')
         else:
             standardized_value = standardized_value.replace(',', '.')
 

changedetectionio/processors/restock_diff/processor.py

@@ -47,12 +47,14 @@ def _deduplicate_prices(data):
 
         if isinstance(datum.value, list):
             # Process each item in the list
-            normalized_value = set([float(re.sub(r'[^\d.]', '', str(item))) for item in datum.value if str(item).strip()])
-            unique_data.update(normalized_value)
+            # parse_currency() understands decimal commas ("39,99"), stripping to [^\d.] first would turn that into 3999
+            normalized_value = set([Restock().parse_currency(str(item)) for item in datum.value if str(item).strip()])
+            unique_data.update(v for v in normalized_value if v is not None)
         else:
             # Process single value
-            v = float(re.sub(r'[^\d.]', '', str(datum.value)))
-            unique_data.add(v)
+            v = Restock().parse_currency(str(datum.value))
+            if v is not None:
+                unique_data.add(v)
 
     return list(unique_data)
 

changedetectionio/processors/restock_diff/pure_python_extractor.py

@@ -16,6 +16,7 @@ from html.parser import HTMLParser
 import json
 import re
 from loguru import logger
+from . import Restock
 
 
 class JSONLDExtractor(HTMLParser):
@@ -135,9 +136,9 @@ class MicrodataExtractor(HTMLParser):
         if self.current_itemprop == 'price':
             # Try to extract numeric price from text
             try:
-                price_text = re.sub(r'[^\d.]', '', data.strip())
-                if price_text:
-                    self.microdata['price'] = float(price_text)
+                price = Restock().parse_currency(data.strip())
+                if price is not None:
+                    self.microdata['price'] = price
             except ValueError:
                 pass
         elif self.current_itemprop == 'priceCurrency':
@@ -241,7 +242,7 @@ def query_price_availability(extracted_data):
                 elif isinstance(price_val, str):
                     # Extract numeric value from string
                     try:
-                        result['price'] = float(re.sub(r'[^\d.]', '', price_val))
+                        result['price'] = Restock().parse_currency(price_val)
                     except ValueError:
                         pass
 

changedetectionio/tests/unit/test_restock_logic.py

@@ -44,5 +44,25 @@ class TestDiffBuilder(unittest.TestCase):
         assert any(s in value.get('availability') for s in ['instock', 'instoreonly']), \
             "a product advertised as available must read as in stock, not out of stock"
 
+    def test_price_decimal_comma(self):
+        """A decimal comma ("39,99", common for EUR) must not be stripped into 3999"""
+        from changedetectionio.processors.restock_diff import Restock
+        from changedetectionio.processors.restock_diff.pure_python_extractor import extract_metadata_pure_python, query_price_availability
+
+        for raw, expected in [("39,99", 39.99), ("12.56", 12.56), ("1.299,00", 1299.0), ("1,299.00", 1299.0),
+                              ("1,299", 1299.0), ("€ 39,99", 39.99), ("$159", 159.0), ("159", 159.0)]:
+            assert Restock().parse_currency(raw) == expected, f"parse_currency({raw!r})"
+
+            microdata = f"""<div itemscope itemtype="http://schema.org/Product"><div itemprop="offers" itemscope itemtype="http://schema.org/Offer">
+            <meta itemprop="priceCurrency" content="EUR"><meta itemprop="price" content="{raw}"></div></div>"""
+            ld_json = f"""<script type="application/ld+json">{{"@context": "https://schema.org", "@type": "Product", "name": "Some Product",
+             "offers": {{"@type": "Offer", "price": "{raw}", "priceCurrency": "EUR"}}}}</script>"""
+            microdata_text = f"""<div itemscope itemtype="http://schema.org/Product"><span itemprop="price">{raw}</span></div>"""
+
+            assert restock_diff.get_itemprop_availability(microdata).get('price') == expected, f"microdata {raw!r}"
+            assert restock_diff.get_itemprop_availability(ld_json).get('price') == expected, f"JSON-LD {raw!r}"
+            assert query_price_availability(extract_metadata_pure_python(ld_json)).get('price') == expected, f"pure python JSON-LD {raw!r}"
+            assert query_price_availability(extract_metadata_pure_python(microdata_text)).get('price') == expected, f"pure python microdata text {raw!r}"
+
 if __name__ == '__main__':
     unittest.main()