Merge pull request '2.4.0' (#251) from develop into master

Author: strangetom

.github/workflows/tests.yml

@@ -13,7 +13,7 @@ jobs:
     strategy:
       max-parallel: 4
       matrix:
-        python-version: ['3.10', '3.11', '3.12', '3.13']
+        python-version: ['3.11', '3.12', '3.13', "3.14"]
 
     steps:
     - uses: actions/checkout@v4

.pre-commit-config.yaml

@@ -2,7 +2,7 @@
 # See https://pre-commit.com/hooks.html for info on hooks
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v5.0.0
+    rev: v6.0.0
     hooks:
       - id: check-added-large-files
         name: (base:repo) debug-statements
@@ -21,7 +21,7 @@ repos:
         name: (base:repo) debug-statements
         stages: [pre-commit]
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.11.6
+    rev: v0.14.0
     hooks:
       - id: ruff
         name: (base:repo) ruff

.readthedocs.yaml

@@ -7,9 +7,9 @@ version: 2
 
 # Set the version of Python and other tools you might need
 build:
-  os: ubuntu-22.04
+  os: ubuntu-24.04
   tools:
-    python: "3.11"
+    python: "3.13"
     # You can also specify other tool versions:
     # nodejs: "16"
     # rust: "1.55"

CHANGELOG.md

@@ -1,5 +1,25 @@
 # Changelog
 
+## 2.4.0
+
+### General
+
+> [!WARNING]
+>
+> This release drops support for Python 3.10.
+
+* Drop support for Python 3.10.
+* Add support for Python 3.14.
+* Require pint >= 0.25.0
+
+### Processing
+
+* Improve the part of speech tagging accuracy by extending the built-in `tagdict` in NLTK's part of speech tagger with ingredient specific entries.
+* Add `name_index` field to `FoundationFood` objects. This field refers to the index of the matching name in the `ParsedIngredient.name` list.
+  * The list of names and foundation foods are also guaranteed to be in the same order (although be aware that a name may not have a matching foundation food).
+* Improve processing of names, particularly related to handling of punctuation at the beginning or end of the name.
+
+
 ## 2.3.0
 
 > [!NOTE]

MANIFEST.in

@@ -3,5 +3,6 @@ include ingredient_parser/en/data/model.en.crfsuite
 include ingredient_parser/en/data/ModelCard.en.md
 include ingredient_parser/en/data/ingredient_embeddings.25d.glove.txt.gz
 include ingredient_parser/en/data/fdc_ingredients.csv.gz
+include ingredient_parser/en/data/ingredient_tagdict.json.gz
 global-exclude test*
 prune */__pycache__

README.md

@@ -47,14 +47,14 @@ The core of the library is a sequence labelling model that is used to label each
 The model has the following accuracy on a test data set of 20% of the total data used:
 
 ```
-Sentence-level results:
-	Accuracy: 94.94%
-
-Word-level results:
-	Accuracy 97.90%
-	Precision (micro) 97.88%
-	Recall (micro) 97.90%
-	F1 score (micro) 97.88%
+╒══════════════════════════╤══════════════════════════╕
+│ Sentence-level results   │ Word-level results       │
+╞══════════════════════════╪══════════════════════════╡
+│ Accuracy: 95.27%         │ Accuracy: 98.10%         │
+│                          │ Precision (micro) 98.08% │
+│                          │ Recall (micro) 98.10%    │
+│                          │ F1 score (micro) 98.09%  │
+╘══════════════════════════╧══════════════════════════╛
 ```
 
 ## Development