Merge pull request #326 from HLasse/pydantic-2

feat: bump pydantic version to 2.0 and spacy version to >=3.6

.github/workflows/release.yml

@@ -34,7 +34,7 @@ jobs:
 
       - name: Python Semantic Release
         id: release
-        uses: python-semantic-release/python-semantic-release@v8.0.4
+        uses: python-semantic-release/python-semantic-release@v9.4.1
         with:
           github_token: ${{ secrets.RELEASE }}
           root_options: "-vv"

docs/tutorials/requirements.txt

@@ -2,4 +2,4 @@
 # e.g. links to wheels which is not allowed in pyproject.toml on pypi
 
 # spacy pipeline
-https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.4.0/en_core_web_sm-3.4.0.tar.gz
+https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.6.0/en_core_web_sm-3.6.0.tar.gz

pyproject.toml

@@ -34,12 +34,12 @@ keywords = [
 ]
 
 dependencies = [
-    "spacy[lookups]>=3.1.0",
+    "spacy[lookups]>=3.6.0",
     "numpy>=1.20.0",
     "pandas>=1.0.0",
     "pyphen>=0.11.0,<0.15.0",
     "ftfy>=6.0.3,<6.1.0",
-    "pydantic<2.0.0",
+    "pydantic>=2.0",
 ]
 
 requires-python = ">=3.8"
@@ -53,13 +53,14 @@ documentation = "https://hlasse.github.io/TextDescriptives/"
 style = ["black==24.1.1", "pre-commit==3.6.0", "ruff==0.1.15", "mypy==1.8.0"]
 tests = ["pytest>=7.1.3", "pytest-cov>=3.0.0"]
 docs = [
+    "pydantic==2.1",
     "sphinx>=5.3.0",
     "furo==2022.12.7",
     "sphinx-copybutton>=0.5.1",
     "sphinxext-opengraph>=0.7.3",
     "myst-nb>=0.6.0",
     "sphinx_design>=0.3.0",
-    "autodoc_pydantic==1.9.0",
+    "autodoc_pydantic==2.1.0",
 ]
 tutorials = [
     "jupyter",

src/textdescriptives/components/quality.py

@@ -514,7 +514,7 @@ def set_quality(self, doc: Doc) -> None:
         # to allow the variable to json serializable we convert it to json
         # it is then converted back into a quality output object in the getter
 
-        doc._._quality = self.quality_setter(doc).dict()
+        doc._._quality = self.quality_setter(doc).model_dump()
         doc._.passed_quality_check = self.passed_quality_thresholds(doc)
 
     def passed_quality_thresholds(self, span: Union[Span, Doc]) -> bool:

src/textdescriptives/components/quality_data_classes.py

@@ -2,7 +2,7 @@
 
 from typing import Any, Dict, Optional, Tuple, Union
 
-from pydantic import BaseModel, Extra, Field
+from pydantic import ConfigDict, BaseModel, Field
 
 Interval = Tuple[Optional[float], Optional[float]]
 
@@ -21,8 +21,7 @@ class ThresholdsOutput(BaseModel):
         True
     """
 
-    class Config:
-        extra = Extra.forbid
+    model_config = ConfigDict(extra="forbid")
 
     threshold: Union[Interval, bool, None]
     value: Union[float, None]
@@ -61,8 +60,7 @@ def __eq__(self, other: Any) -> bool:
 class QualityThresholds(BaseModel):
     """Thresholds for quality metrics."""
 
-    class Config:
-        extra = Extra.forbid
+    model_config = ConfigDict(extra="forbid")
 
     n_stop_words: Interval = Field(
         (2, None),
@@ -164,8 +162,7 @@ class Config:
 class QualityOutput(BaseModel):
     """The output of the quality function."""
 
-    class Config:
-        extra = Extra.forbid
+    model_config = ConfigDict(extra="forbid")
 
     n_stop_words: ThresholdsOutput = Field(
         ...,

tests/requirements.txt

@@ -2,5 +2,5 @@
 # e.g. links to wheels which is not allowed in pyproject.toml on pypi
 
 # spacy pipelines
-https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.5.0/en_core_web_sm-3.5.0.tar.gz
-https://github.com/explosion/spacy-models/releases/download/en_core_web_md-3.5.0/en_core_web_md-3.5.0.tar.gz
+https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.6.0/en_core_web_sm-3.6.0.tar.gz
+https://github.com/explosion/spacy-models/releases/download/en_core_web_md-3.6.0/en_core_web_md-3.6.0.tar.gz

tests/test_quality.py

@@ -4,7 +4,6 @@
 
 import pytest
 import spacy
-
 import textdescriptives as td
 from textdescriptives.components.quality import (
     alpha_ratio,
@@ -208,7 +207,7 @@ def test_quality_component_with_config(nlp: spacy.Language):
         proportion_bullet_points=(None, 0.8),
         duplicate_line_chr_fraction=(None, 0.2),
         duplicate_paragraph_chr_fraction=(None, 0.2),
-        top_ngram_chr_fraction={2: (None, 0.6), 3: (None, 0.6)},
+        top_ngram_chr_fraction={"2": (None, 0.6), "3": (None, 0.6)},
         duplicate_ngram_chr_fraction={},
         contains={"lorem ipsum": False},
         oov_ratio=(None, 0.3),