ynab-amazon-categorizer 2.2.0__tar.gz → 2.2.2__tar.gz

{ynab_amazon_categorizer-2.2.0 → ynab_amazon_categorizer-2.2.2}/CHANGELOG.md

@@ -7,6 +7,20 @@ and this project adheres to [Semantic Versioning](https://semver.org/).
 
 ## [Unreleased]
 
+## [2.2.2] - 2026-04-23
+
+### Fixed
+
+- Pin `ty==0.0.14` in dev dependencies so CI uses the same type-checker version as the lock file
+
+## [2.2.1] - 2026-04-23
+
+### Fixed
+
+- Cancelled orders no longer cause their items to bleed into the preceding valid order
+- Quantity badge numbers (e.g. trailing ` 2`, ` 4`) are stripped from item names when the bare form also appears, without corrupting size numbers like `Size 10`
+- `"Now arriving today X:XX p.m."` delivery status lines are no longer extracted as item names
+
 ## [2.2.0] - 2026-02-23
 
 ### Fixed

{ynab_amazon_categorizer-2.2.0 → ynab_amazon_categorizer-2.2.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ynab-amazon-categorizer
-Version: 2.2.0
+Version: 2.2.2
 Summary: Automatically categorize Amazon transactions in YNAB with rich item information
 Author: dizzlkheinz
 License: GPL-3.0
@@ -28,7 +28,7 @@ Provides-Extra: dev
 Requires-Dist: pytest>=9.0.2; extra == "dev"
 Requires-Dist: pytest-cov>=7.0.0; extra == "dev"
 Requires-Dist: ruff>=0.15.0; extra == "dev"
-Requires-Dist: ty>=0.0.14; extra == "dev"
+Requires-Dist: ty==0.0.14; extra == "dev"
 Requires-Dist: pre-commit>=4.5.1; extra == "dev"
 Dynamic: license-file
 

{ynab_amazon_categorizer-2.2.0 → ynab_amazon_categorizer-2.2.2}/pyproject.toml

@@ -36,7 +36,7 @@ dev = [
     "pytest>=9.0.2",
     "pytest-cov>=7.0.0",
     "ruff>=0.15.0",
-    "ty>=0.0.14",
+    "ty==0.0.14",
     "pre-commit>=4.5.1",
 ]
 

ynab_amazon_categorizer-2.2.2/src/ynab_amazon_categorizer/_version.py

@@ -0,0 +1,24 @@
+# file generated by vcs-versioning
+# don't change, don't track in version control
+from __future__ import annotations
+
+__all__ = [
+    "__version__",
+    "__version_tuple__",
+    "version",
+    "version_tuple",
+    "__commit_id__",
+    "commit_id",
+]
+
+version: str
+__version__: str
+__version_tuple__: tuple[int | str, ...]
+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)
+
+__commit_id__ = commit_id = 'g993627dd7'

{ynab_amazon_categorizer-2.2.0 → ynab_amazon_categorizer-2.2.2}/src/ynab_amazon_categorizer/amazon_parser.py

@@ -22,6 +22,19 @@ class Order:
 class AmazonParser:
     """Parses Amazon order data from order history pages."""
 
+    def _remove_cancelled_orders(self, text: str) -> str:
+        """Remove cancelled order blocks so their items don't bleed into adjacent orders."""
+        parts = re.split(r"(?=Order placed)", text)
+        kept = []
+        for part in parts:
+            if (
+                re.match(r"\s*Order placed", part)
+                and "Your order was cancelled" in part
+            ):
+                continue
+            kept.append(part)
+        return "".join(kept)
+
     def parse_orders_page(self, orders_text: str) -> list[Order]:
         """Parse Amazon orders page text to extract order information.
 
@@ -31,6 +44,8 @@ class AmazonParser:
         if not orders_text.strip():
             return []
 
+        orders_text = self._remove_cancelled_orders(orders_text)
+
         orders = []
 
         # Find all order blocks using regex
@@ -76,7 +91,7 @@ class AmazonParser:
 
     def extract_items_from_content(self, order_content: str) -> list[str]:
         """Extract item names from order content."""
-        items = []
+        candidates: list[str] = []
         lines = order_content.split("\n")
 
         for line in lines:
@@ -84,10 +99,10 @@ class AmazonParser:
             if not line or len(line) < 15:
                 continue
 
-            # Skip common UI elements
+            # Skip common UI elements and delivery status lines
             skip_patterns = [
                 r"^(Buy it again|Track package|View|Return|Write|Get|Share|Leave|Ask)",
-                r"^(Delivered|Arriving|Auto-delivered|Package was)",
+                r"^(Delivered|Arriving|Now arriving|Auto-delivered|Package was)",
                 r"^(Return items:|Return or replace)",
                 r"^\d+\.?\d* out of \d+ stars",
                 r"^FREE|^Today by|^Get it|^List:|^Was:|^Limited-time deal",
@@ -139,15 +154,23 @@ class AmazonParser:
                     "shipping",
                 ]
                 if not any(word in cleaned_line.lower() for word in skip_words):
-                    items.append(cleaned_line)
+                    candidates.append(cleaned_line)
+
+        # Build lookup set to detect quantity-badge duplicates.
+        # Amazon shows "Product Name <qty>" and "Product Name" on adjacent lines when
+        # qty > 1. We want to strip the badge only when the bare form also appears.
+        candidate_set = set(candidates)
 
-        # Remove duplicates, keep up to MAX_ITEMS_PER_ORDER
         seen: set[str] = set()
         unique_items: list[str] = []
-        for item in items:
-            if item not in seen and len(item) > 15:  # Only keep substantial items
-                seen.add(item)
-                unique_items.append(item)
+        for item in candidates:
+            stripped = re.sub(r"\s+\d+$", "", item)
+            normalized = (
+                stripped if (stripped != item and stripped in candidate_set) else item
+            )
+            if normalized not in seen and len(normalized) > 15:
+                seen.add(normalized)
+                unique_items.append(normalized)
                 if len(unique_items) >= MAX_ITEMS_PER_ORDER:
                     break
 

{ynab_amazon_categorizer-2.2.0 → ynab_amazon_categorizer-2.2.2}/src/ynab_amazon_categorizer.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ynab-amazon-categorizer
-Version: 2.2.0
+Version: 2.2.2
 Summary: Automatically categorize Amazon transactions in YNAB with rich item information
 Author: dizzlkheinz
 License: GPL-3.0
@@ -28,7 +28,7 @@ Provides-Extra: dev
 Requires-Dist: pytest>=9.0.2; extra == "dev"
 Requires-Dist: pytest-cov>=7.0.0; extra == "dev"
 Requires-Dist: ruff>=0.15.0; extra == "dev"
-Requires-Dist: ty>=0.0.14; extra == "dev"
+Requires-Dist: ty==0.0.14; extra == "dev"
 Requires-Dist: pre-commit>=4.5.1; extra == "dev"
 Dynamic: license-file
 

{ynab_amazon_categorizer-2.2.0 → ynab_amazon_categorizer-2.2.2}/src/ynab_amazon_categorizer.egg-info/requires.txt

@@ -6,5 +6,5 @@ python-dotenv>=1.2.1
 pytest>=9.0.2
 pytest-cov>=7.0.0
 ruff>=0.15.0
-ty>=0.0.14
+ty==0.0.14
 pre-commit>=4.5.1

ynab_amazon_categorizer-2.2.2/tests/test_amazon_parser.py

@@ -0,0 +1,224 @@
+"""Tests for Amazon order parsing functionality."""
+
+from ynab_amazon_categorizer.amazon_parser import AmazonParser
+
+
+def test_parse_simple_order() -> None:
+    """Test parsing a simple Amazon order."""
+    order_text = """
+    Order placed July 31, 2024
+    Total $57.57
+    Order # 702-8237239-1234567
+    Fancy Feast Grilled Wet Cat Food, Tuna Feast - 85 g Can (24 Pack)
+    """
+
+    parser = AmazonParser()
+    orders = parser.parse_orders_page(order_text)
+
+    assert len(orders) == 1
+    order = orders[0]
+    assert order.order_id == "702-8237239-1234567"
+    assert order.total == 57.57
+    assert order.date_str == "July 31, 2024"
+    assert len(order.items) == 1
+    assert "Fancy Feast" in order.items[0]
+
+
+def test_parse_empty_order_text() -> None:
+    """Test parsing empty order text returns empty list."""
+    parser = AmazonParser()
+    orders = parser.parse_orders_page("")
+    assert len(orders) == 0
+
+
+def test_extract_items_from_order_content() -> None:
+    """Test extracting items from Amazon order content."""
+    parser = AmazonParser()
+
+    order_content = """
+    Fancy Feast Grilled Wet Cat Food, Tuna Feast - 85 g Can (24 Pack)
+    ACME Brand Premium Dog Treats - Large Size 2 lb bag
+    Skip this line
+    Buy it again - should be skipped
+    Another product: Organic Cat Litter - 20 lbs Natural Clay
+    Track package - should be skipped
+    """
+
+    items = parser.extract_items_from_content(order_content)
+
+    assert len(items) >= 1
+    assert "Fancy Feast Grilled Wet Cat Food, Tuna Feast - 85 g Can (24 Pack)" in items
+
+
+def test_parse_order_without_items_kept() -> None:
+    """Orders without parseable items are still kept (partial orders)."""
+    order_text = """
+    Order placed January 5, 2025
+    Total $15.00
+    Order # 702-1111111-2222222
+    short
+    """
+    parser = AmazonParser()
+    orders = parser.parse_orders_page(order_text)
+
+    # Order is kept even without items
+    assert len(orders) == 1
+    assert orders[0].order_id == "702-1111111-2222222"
+    assert orders[0].total == 15.00
+    assert orders[0].items == []
+
+
+def test_parse_multiple_orders() -> None:
+    """Multiple orders in same text are parsed correctly."""
+    order_text = """
+    Order placed July 31, 2024
+    Total $57.57
+    Order # 702-1111111-1111111
+    Fancy Feast Grilled Wet Cat Food, Tuna Feast - 85 g Can (24 Pack)
+
+    Order placed August 15, 2024
+    Total $89.99
+    Order # 702-2222222-2222222
+    Wireless Bluetooth Headphones - Over-Ear Noise Cancelling
+    """
+
+    parser = AmazonParser()
+    orders = parser.parse_orders_page(order_text)
+
+    assert len(orders) == 2
+    assert orders[0].order_id == "702-1111111-1111111"
+    assert orders[0].total == 57.57
+    assert orders[1].order_id == "702-2222222-2222222"
+    assert orders[1].total == 89.99
+
+
+def test_extract_more_than_three_items() -> None:
+    """More than 3 items can be extracted (old 3-item limit removed)."""
+    parser = AmazonParser()
+
+    order_content = """
+    Fancy Feast Grilled Wet Cat Food, Tuna Feast - 85 g Can (24 Pack)
+    ACME Brand Premium Dog Treats - Large Size 2 lb bag
+    Another product: Organic Cat Litter - 20 lbs Natural Clay
+    Super Premium Fancy Dog Collar with LED - Size Medium
+    Deluxe Pet Bed Extra Large Orthopedic Memory Foam 36 inch
+    """
+
+    items = parser.extract_items_from_content(order_content)
+    assert len(items) >= 4  # Should extract more than 3 now
+
+
+def test_cancelled_order_items_do_not_bleed() -> None:
+    """Items from a cancelled order must not appear under the preceding valid order."""
+    # Order 701-9742314-2110603 ($29.58 capsules) is followed by a cancelled order
+    # whose item (Altra sneaker) must not be attributed to the capsules order.
+    order_text = """Order placed
+April 22, 2026
+Total
+$29.58
+Ship to
+Shelby and Kalman Sutker
+Order # 701-9742314-2110603
+View order details Invoice
+
+Now arriving today 5:15 p.m. - 8:15 p.m.
+
+    Yogti Psyllium Husk Capsules, 300 Count 2
+    Yogti Psyllium Husk Capsules, 300 Count
+    Buy it again
+
+    Track package
+    Return or replace items
+    Write a product review
+
+Order placed
+April 22, 2026
+Order # 701-0552104-1147435
+
+Cancelled
+Your order was cancelled. You have not been charged for this order.
+
+    Altra Men's Lone Peak 9 Trail Running Shoe, Tan, 13 Wide
+    Altra Men's Lone Peak 9 Trail Running Shoe, Tan, 13 Wide
+
+Order placed
+April 22, 2026
+Total
+$29.73
+Ship to
+Shelby and Kalman Sutker
+Order # 701-5052171-6951446
+View order details Invoice
+
+    TEMPTATIONS Cat Treats, Seafood Medley Flavour, 454g Tub 4
+    TEMPTATIONS Cat Treats, Seafood Medley Flavour, 454g Tub
+    Buy it again
+    View your item
+"""
+
+    parser = AmazonParser()
+    orders = parser.parse_orders_page(order_text)
+
+    # Cancelled order must be omitted entirely
+    assert len(orders) == 2
+    order_ids = [o.order_id for o in orders]
+    assert "701-0552104-1147435" not in order_ids
+
+    capsules_order = next(o for o in orders if o.order_id == "701-9742314-2110603")
+    item_text = " ".join(capsules_order.items)
+    assert "Altra" not in item_text, "Cancelled-order item bled into adjacent order"
+    assert "Psyllium" in item_text
+
+
+def test_quantity_badge_stripped_from_item_name() -> None:
+    """Trailing quantity badge numbers are removed when the bare name also appears."""
+    parser = AmazonParser()
+
+    # Amazon shows "Product Name <qty>" then "Product Name" on successive lines.
+    order_content = """
+    TEMPTATIONS Cat Treats, Seafood Medley Flavour, 454g Tub 4
+    TEMPTATIONS Cat Treats, Seafood Medley Flavour, 454g Tub
+    Buy it again
+    View your item
+    Nizoral Anti-Dandruff Shampoo with 2% Ketoconazole, Fresh Scent, 325 ml
+    Nizoral Anti-Dandruff Shampoo with 2% Ketoconazole, Fresh Scent, 325 ml
+    """
+
+    items = parser.extract_items_from_content(order_content)
+    assert len(items) == 2
+    assert all("454g Tub" in i or "Ketoconazole" in i for i in items)
+    # Bare form preserved, badge number gone
+    assert not any(i.endswith(" 4") for i in items)
+
+
+def test_size_number_not_stripped() -> None:
+    """Trailing size numbers (2+ digits) are NOT stripped — they are part of the name."""
+    parser = AmazonParser()
+
+    order_content = """
+    Corset Femme Tops Floral Renaissance Pirate Overbust Boned Bustier Tops Green Size 10
+    Corset Femme Tops Floral Renaissance Pirate Overbust Boned Bustier Tops Green Size 10
+    Return items: Eligible through May 17, 2026
+    Buy it again
+    """
+
+    items = parser.extract_items_from_content(order_content)
+    assert len(items) == 1
+    assert items[0].endswith("Size 10")
+
+
+def test_now_arriving_status_line_skipped() -> None:
+    """'Now arriving today X:XX p.m.' delivery status must not be extracted as an item."""
+    parser = AmazonParser()
+
+    order_content = """
+Now arriving today 5:15 p.m. - 8:15 p.m.
+
+    Yogti Psyllium Husk Capsules, 300 Count
+    Yogti Psyllium Husk Capsules, 300 Count
+    Buy it again
+    """
+
+    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)

ynab_amazon_categorizer-2.2.0/src/ynab_amazon_categorizer/_version.py

@@ -1,34 +0,0 @@
-# file generated by setuptools-scm
-# don't change, don't track in version control
-
-__all__ = [
-    "__version__",
-    "__version_tuple__",
-    "version",
-    "version_tuple",
-    "__commit_id__",
-    "commit_id",
-]
-
-TYPE_CHECKING = False
-if TYPE_CHECKING:
-    from typing import Tuple
-    from typing import Union
-
-    VERSION_TUPLE = Tuple[Union[int, str], ...]
-    COMMIT_ID = Union[str, None]
-else:
-    VERSION_TUPLE = object
-    COMMIT_ID = object
-
-version: str
-__version__: str
-__version_tuple__: VERSION_TUPLE
-version_tuple: VERSION_TUPLE
-commit_id: COMMIT_ID
-__commit_id__: COMMIT_ID
-
-__version__ = version = '2.2.0'
-__version_tuple__ = version_tuple = (2, 2, 0)
-
-__commit_id__ = commit_id = 'g431256193'

ynab_amazon_categorizer-2.2.0/tests/test_amazon_parser.py

@@ -1,108 +0,0 @@
-"""Tests for Amazon order parsing functionality."""
-
-from ynab_amazon_categorizer.amazon_parser import AmazonParser
-
-
-def test_parse_simple_order() -> None:
-    """Test parsing a simple Amazon order."""
-    order_text = """
-    Order placed July 31, 2024
-    Total $57.57
-    Order # 702-8237239-1234567
-    Fancy Feast Grilled Wet Cat Food, Tuna Feast - 85 g Can (24 Pack)
-    """
-
-    parser = AmazonParser()
-    orders = parser.parse_orders_page(order_text)
-
-    assert len(orders) == 1
-    order = orders[0]
-    assert order.order_id == "702-8237239-1234567"
-    assert order.total == 57.57
-    assert order.date_str == "July 31, 2024"
-    assert len(order.items) == 1
-    assert "Fancy Feast" in order.items[0]
-
-
-def test_parse_empty_order_text() -> None:
-    """Test parsing empty order text returns empty list."""
-    parser = AmazonParser()
-    orders = parser.parse_orders_page("")
-    assert len(orders) == 0
-
-
-def test_extract_items_from_order_content() -> None:
-    """Test extracting items from Amazon order content."""
-    parser = AmazonParser()
-
-    order_content = """
-    Fancy Feast Grilled Wet Cat Food, Tuna Feast - 85 g Can (24 Pack)
-    ACME Brand Premium Dog Treats - Large Size 2 lb bag
-    Skip this line
-    Buy it again - should be skipped
-    Another product: Organic Cat Litter - 20 lbs Natural Clay
-    Track package - should be skipped
-    """
-
-    items = parser.extract_items_from_content(order_content)
-
-    assert len(items) >= 1
-    assert "Fancy Feast Grilled Wet Cat Food, Tuna Feast - 85 g Can (24 Pack)" in items
-
-
-def test_parse_order_without_items_kept() -> None:
-    """Orders without parseable items are still kept (partial orders)."""
-    order_text = """
-    Order placed January 5, 2025
-    Total $15.00
-    Order # 702-1111111-2222222
-    short
-    """
-    parser = AmazonParser()
-    orders = parser.parse_orders_page(order_text)
-
-    # Order is kept even without items
-    assert len(orders) == 1
-    assert orders[0].order_id == "702-1111111-2222222"
-    assert orders[0].total == 15.00
-    assert orders[0].items == []
-
-
-def test_parse_multiple_orders() -> None:
-    """Multiple orders in same text are parsed correctly."""
-    order_text = """
-    Order placed July 31, 2024
-    Total $57.57
-    Order # 702-1111111-1111111
-    Fancy Feast Grilled Wet Cat Food, Tuna Feast - 85 g Can (24 Pack)
-
-    Order placed August 15, 2024
-    Total $89.99
-    Order # 702-2222222-2222222
-    Wireless Bluetooth Headphones - Over-Ear Noise Cancelling
-    """
-
-    parser = AmazonParser()
-    orders = parser.parse_orders_page(order_text)
-
-    assert len(orders) == 2
-    assert orders[0].order_id == "702-1111111-1111111"
-    assert orders[0].total == 57.57
-    assert orders[1].order_id == "702-2222222-2222222"
-    assert orders[1].total == 89.99
-
-
-def test_extract_more_than_three_items() -> None:
-    """More than 3 items can be extracted (old 3-item limit removed)."""
-    parser = AmazonParser()
-
-    order_content = """
-    Fancy Feast Grilled Wet Cat Food, Tuna Feast - 85 g Can (24 Pack)
-    ACME Brand Premium Dog Treats - Large Size 2 lb bag
-    Another product: Organic Cat Litter - 20 lbs Natural Clay
-    Super Premium Fancy Dog Collar with LED - Size Medium
-    Deluxe Pet Bed Extra Large Orthopedic Memory Foam 36 inch
-    """
-
-    items = parser.extract_items_from_content(order_content)
-    assert len(items) >= 4  # Should extract more than 3 now