ynab-amazon-categorizer 2.2.2__tar.gz → 2.2.3__tar.gz

{ynab_amazon_categorizer-2.2.2 → ynab_amazon_categorizer-2.2.3}/CHANGELOG.md

@@ -7,6 +7,12 @@ and this project adheres to [Semantic Versioning](https://semver.org/).
 
 ## [Unreleased]
 
+## [2.2.3] - 2026-05-05
+
+### Fixed
+
+- Footer and nav boilerplate from the Amazon orders page (copyright lines, address blocks, credit card promos, accessibility hints) is no longer extracted as order items
+
 ## [2.2.2] - 2026-04-23
 
 ### Fixed

{ynab_amazon_categorizer-2.2.2 → ynab_amazon_categorizer-2.2.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ynab-amazon-categorizer
-Version: 2.2.2
+Version: 2.2.3
 Summary: Automatically categorize Amazon transactions in YNAB with rich item information
 Author: dizzlkheinz
 License: GPL-3.0

{ynab_amazon_categorizer-2.2.2 → ynab_amazon_categorizer-2.2.3}/src/ynab_amazon_categorizer/_version.py

@@ -18,7 +18,7 @@ version_tuple: tuple[int | str, ...]
 commit_id: str | None
 __commit_id__: str | None
 
-__version__ = version = '2.2.2'
-__version_tuple__ = version_tuple = (2, 2, 2)
+__version__ = version = '2.2.3'
+__version_tuple__ = version_tuple = (2, 2, 3)
 
-__commit_id__ = commit_id = 'g993627dd7'
+__commit_id__ = commit_id = 'gb865ea2d2'

{ynab_amazon_categorizer-2.2.2 → ynab_amazon_categorizer-2.2.3}/src/ynab_amazon_categorizer/amazon_parser.py

@@ -91,6 +91,15 @@ class AmazonParser:
 
     def extract_items_from_content(self, order_content: str) -> list[str]:
         """Extract item names from order content."""
+        # Trim at page footer sentinels to avoid extracting navigation/legal boilerplate
+        footer_sentinel = re.search(
+            r"©\s*\d{4}|To move between items",
+            order_content,
+            re.IGNORECASE,
+        )
+        if footer_sentinel:
+            order_content = order_content[: footer_sentinel.start()]
+
         candidates: list[str] = []
         lines = order_content.split("\n")
 
@@ -152,6 +161,11 @@ class AmazonParser:
                     "browse",
                     "prime",
                     "shipping",
+                    "mastercard",
+                    "your brand",
+                    "registry & gift",
+                    "attract and engage",
+                    "interest-based",
                 ]
                 if not any(word in cleaned_line.lower() for word in skip_words):
                     candidates.append(cleaned_line)

{ynab_amazon_categorizer-2.2.2 → ynab_amazon_categorizer-2.2.3}/src/ynab_amazon_categorizer.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ynab-amazon-categorizer
-Version: 2.2.2
+Version: 2.2.3
 Summary: Automatically categorize Amazon transactions in YNAB with rich item information
 Author: dizzlkheinz
 License: GPL-3.0

{ynab_amazon_categorizer-2.2.2 → ynab_amazon_categorizer-2.2.3}/tests/test_amazon_parser.py

@@ -222,3 +222,40 @@ Now arriving today 5:15 p.m. - 8:15 p.m.
     items = parser.extract_items_from_content(order_content)
     assert all("arriving" not in i.lower() for i in items)
     assert any("Psyllium" in i for i in items)
+
+
+def test_footer_boilerplate_not_extracted() -> None:
+    """Page footer and Amazon nav boilerplate must not appear as items."""
+    parser = AmazonParser()
+
+    order_content = """
+    Tampax Pearl Tampons, Plastic Applicator, Light Absorbency, 50 Count
+    Buy it again
+    Protect & Build Your Brand
+    Amazon.ca Rewards Mastercard
+    Registry & Gift List
+    Find, attract and engage customers
+    Interest-Based Ads
+    © 1996-2026, Amazon.com, Inc. or its affiliates
+    Amazon.com.ca ULC | 40 King Street W 47th Floor, Toronto, Ontario, Canada, M5H 3Y2
+    Influencers & Associates
+    To move between items, use your keyboard's up or down arrows.
+    """
+
+    items = parser.extract_items_from_content(order_content)
+
+    assert len(items) == 1
+    assert "Tampax" in items[0]
+    for word in [
+        "Mastercard",
+        "Registry",
+        "attract",
+        "Interest-Based",
+        "affiliates",
+        "ULC",
+        "Influencers",
+        "keyboard",
+    ]:
+        assert not any(word.lower() in item.lower() for item in items), (
+            f"Boilerplate '{word}' leaked into items"
+        )

{ynab_amazon_categorizer-2.2.2 → ynab_amazon_categorizer-2.2.3}/uv.lock

@@ -486,6 +486,6 @@ requires-dist = [
     { name = "python-dotenv", specifier = ">=1.2.1" },
     { name = "requests", specifier = ">=2.32.5" },
     { name = "ruff", marker = "extra == 'dev'", specifier = ">=0.15.0" },
-    { name = "ty", marker = "extra == 'dev'", specifier = ">=0.0.14" },
+    { name = "ty", marker = "extra == 'dev'", specifier = "==0.0.14" },
 ]
 provides-extras = ["dev"]