Update models to pydantic v2

.github/workflows/python_package.yml

@@ -0,0 +1,37 @@
+# This workflow will install Python dependencies, run tests and lint with a variety of Python versions
+# For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
+
+name: Python package
+
+on:
+  push:
+    branches: [master]
+  pull_request:
+    branches: [master]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.9", "3.10", "3.11", "3.12"]
+
+    steps:
+      - uses: actions/checkout@v2
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v2
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install -r requirements.txt
+          pip install pytest coveralls==2.1.2 pytest-cov
+      - name: Test with pytest
+        run: |
+          pytest tests/ --cov=anchorpoint --cov-report=term-missing
+      - name: Upload coverage data to coveralls.io
+        if: matrix.python-version == 3.12
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: coveralls

README.rst

@@ -11,9 +11,9 @@ A Python library for anchoring annotations with text substring selectors.
     :target: https://coveralls.io/github/mscarey/anchorpoint?branch=master
     :alt: Test Coverage Percentage
 
-.. image:: https://circleci.com/gh/mscarey/anchorpoint.svg?style=svg
-    :target: https://circleci.com/gh/mscarey/anchorpoint
-    :alt: CircleCI Status
+.. image:: https://github.com/mscarey/anchorpoint/actions/workflows/python-package.yml/badge.svg
+    :target: https://github.com/mscarey/anchorpoint/actions
+    :alt: GitHub Actions Workflow
 
 .. image:: https://readthedocs.org/projects/anchorpoint/badge/?version=latest
     :target: https://anchorpoint.readthedocs.io/en/latest/?badge=latest

anchorpoint/textselectors.py

@@ -10,11 +10,10 @@
 import re
 
 from typing import List, Optional, Sequence, Tuple, Union
-
 from anchorpoint.textsequences import TextPassage, TextSequence
 from ranges import Range, RangeSet, Inf
 from ranges._helper import _InfiniteValue
-from pydantic import BaseModel, validator
+from pydantic import BaseModel, field_validator, model_validator
 
 
 class TextSelectionError(Exception):
@@ -69,8 +68,9 @@ def split_anchor_text(text: str) -> Tuple[str, ...]:
             "two, separating the string into 'prefix', 'exact', and 'suffix'."
         )
 
-    @validator("prefix", "exact", "suffix", pre=True)
-    def no_none_for_prefix(cls, value):
+    @field_validator("prefix", "exact", "suffix", mode="before")
+    @classmethod
+    def no_none_for_prefix(cls, value: str | None) -> str:
         """Ensure that 'prefix', 'exact', and 'suffix' are not None."""
         if value is None:
             return ""
@@ -282,8 +282,9 @@ def from_range(
             end = range.end
         return TextPositionSelector(start=range.start, end=end)
 
-    @validator("start")
-    def start_not_negative(cls, v) -> bool:
+    @field_validator("start", mode="after")
+    @classmethod
+    def start_not_negative(cls, v: int) -> int:
         """
         Verify start position is not negative.
 
@@ -294,18 +295,17 @@ def start_not_negative(cls, v) -> bool:
             raise IndexError("Start position for text range cannot be negative.")
         return v
 
-    @validator("end")
-    def start_less_than_end(cls, v, values):
+    @model_validator(mode="after")
+    def start_less_than_end(self) -> "TextPositionSelector":
         """
         Verify start position is before the end position.
 
         :returns:
             the end position, which after the start position
         """
-        start, end = values.get("start"), v
-        if end is not None and end <= start:
+        if self.end is not None and self.end <= self.start:
             raise IndexError("End position must be greater than start position.")
-        return v
+        return self
 
     def range(self) -> Range:
         """Get the range of the text."""
@@ -399,7 +399,7 @@ def __and__(
         if isinstance(other, (TextPositionSelector, TextPositionSet)):
             other = other.rangeset()
 
-        new_rangeset = self.rangeset() & other
+        new_rangeset: RangeSet = self.rangeset() & other
 
         if not new_rangeset:
             return None
@@ -552,7 +552,7 @@ class TextPositionSet(BaseModel):
 
     @classmethod
     def from_quotes(
-        self,
+        cls,
         selection: Union[str, TextQuoteSelector, List[Union[TextQuoteSelector, str]]],
     ) -> TextPositionSet:
         """
@@ -562,11 +562,11 @@ def from_quotes(
         """
         if isinstance(selection, (str, TextQuoteSelector)):
             selection = [selection]
-        selection = [
+        selection_as_selectors: list[TextQuoteSelector] = [
             TextQuoteSelector.from_text(s) if isinstance(s, str) else s
             for s in selection
         ]
-        return TextPositionSet(quotes=selection)
+        return TextPositionSet(quotes=selection_as_selectors)
 
     @classmethod
     def from_ranges(
@@ -650,7 +650,7 @@ def __and__(
     ) -> TextPositionSet:
         if isinstance(other, TextPositionSelector):
             other = TextPositionSet(positions=[other])
-        new_rangeset = self.rangeset() & other.rangeset()
+        new_rangeset: RangeSet = self.rangeset() & other.rangeset()
         return TextPositionSet.from_ranges(new_rangeset)
 
     def __sub__(
@@ -659,24 +659,16 @@ def __sub__(
         """Decrease all startpoints and endpoints by the given amount."""
         if not isinstance(value, int):
             new_rangeset = self.rangeset() - value.rangeset()
+            new = TextPositionSet.from_ranges(new_rangeset)
         else:
-            new_rangeset = [
+            new_selectors = [
                 selector.subtract_integer(value) for selector in self.positions
             ]
-        new = TextPositionSet.from_ranges(new_rangeset)
+            new = TextPositionSet.from_ranges(new_selectors)
         new.quotes = self.quotes
         return new
 
-    @validator("positions", pre=True)
-    def selectors_are_in_list(
-        cls, selectors: Union[TextPositionSelector, List[TextPositionSelector]]
-    ):
-        """Put single selector in list."""
-        if not isinstance(selectors, Sequence):
-            selectors = [selectors]
-        return selectors
-
-    @validator("quotes", pre=True)
+    @field_validator("quotes", mode="before")
     def quote_selectors_are_in_list(
         cls,
         selectors: Union[str, TextQuoteSelector, List[Union[str, TextQuoteSelector]]],
@@ -693,9 +685,12 @@ def quote_selectors_are_in_list(
         ]
         return selectors
 
-    @validator("positions")
-    def order_of_selectors(cls, v):
+    @field_validator("positions", mode="before")
+    @classmethod
+    def order_of_selectors(cls, v: list[TextPositionSelector]):
         """Ensure that selectors are in order."""
+        if not isinstance(v, Sequence):
+            v = [v]
         return sorted(v, key=lambda x: x.start)
 
     def positions_as_quotes(self, text: str) -> List[TextQuoteSelector]:
@@ -741,7 +736,11 @@ def as_text_sequence(self, text: str, include_nones: bool = True) -> TextSequenc
             if include_nones and 0 < selection_ranges[0].start < len(text):
                 selected.append(None)
             for passage in selection_ranges:
-                if passage.start < passage.end and passage.start < len(text):
+                if (
+                    passage.start is not None
+                    and passage.start < passage.end
+                    and passage.start < len(text)
+                ):
                     string_end = (
                         passage.end
                         if not isinstance(passage.end, _InfiniteValue)
@@ -834,7 +833,10 @@ def add_margin(
         margin_selectors = TextPositionSet()
         for left in new_rangeset.ranges():
             for right in new_rangeset.ranges():
-                if left.end < right.start <= left.end + margin_width:
+                if (
+                    left.end is not None
+                    and left.end < right.start <= left.end + margin_width
+                ):
                     if all(
                         letter in margin_characters
                         for letter in text[left.end : right.start]

anchorpoint/textsequences.py

@@ -74,7 +74,7 @@ class TextSequence(Sequence[Union[None, TextPassage]]):
     def __init__(self, passages: List[Optional[TextPassage]] = None):
         """
         Make new TextSequence from :class:`.TextPassage` list.
-        
+
         :param passages:
             the text passages included in the TextSequence, which should be chosen
             to express a coherent idea. "None"s in the sequence represent spans of

docs/guides/selecting.rst

@@ -152,9 +152,9 @@ Anchorpoint uses `Pydantic <https://pydantic-docs.helpmanual.io/>`__ to
 serialize selectors either to Python dictionaries
 or to JSON strings suitable for sending over the internet with APIs.
 
-    >>> authorship_selector.json()
+    >>> authorship_selector.model_dump_json()
     '{"exact": "authorship", "prefix": "", "suffix": "include"}'
-    >>> selector_set.dict()
+    >>> selector_set.model_dump()
     {'positions': [{'start': 65, 'end': 79}, {'start': 100, 'end': 136}], 'quotes': []}
 
 Pydantic's data loading methods mean that you can also create the data for an

requirements-dev.txt

@@ -2,11 +2,11 @@ black
 build
 coverage
 coveralls
-flake8
 mypy
 pydocstyle
 pytest
 pytest-cov
+ruff
 rstcheck
 setuptools
 Sphinx

requirements.txt

@@ -1,2 +1,2 @@
-pydantic>=1.8.2
-python-ranges>=0.2.1
+pydantic>=2.4.2
+python-ranges>=1.2.2

setup.py

@@ -19,11 +19,15 @@
     classifiers=[
         "Development Status :: 4 - Beta",
         "License :: Free To Use But Restricted",
+        "Programming Language :: Python :: 3.8",
         "Programming Language :: Python :: 3.9",
+        "Programming Language :: Python :: 3.10",
+        "Programming Language :: Python :: 3.11",
+        "Programming Language :: Python :: 3.12",
         "Operating System :: OS Independent",
         "Natural Language :: English",
     ],
     packages=setuptools.find_packages(exclude=["tests"]),
-    install_requires=["pydantic>=1.8.2"],
+    install_requires=["pydantic>2.4.2", "python-ranges>=1.2.2"],
     python_requires=">=3.8",
 )

tests/test_schema.py

@@ -40,7 +40,7 @@ def test_ordered_position_selector_fields(self):
         """Test that "start" is before "end"."""
         data = {"start": 0, "end": 12}
         loaded = TextPositionSelector(**data)
-        dumped = loaded.dict()
+        dumped = loaded.model_dump()
         assert list(dumped.keys())[0] == "start"
 
 
@@ -69,14 +69,14 @@ class TestDumpSelector:
     def test_dump_quote_selector(self):
         data = "eats,|shoots,|and leaves"
         loaded = TextQuoteSelector.from_text(data)
-        dumped = loaded.dict()
+        dumped = loaded.model_dump()
         assert dumped["prefix"] == "eats,"
         assert dumped["suffix"] == "and leaves"
 
     def test_ordered_position_selector_fields(self):
         """Test that "start" is before "end"."""
         data = {"start": 0, "end": 12}
         loaded = TextPositionSelector(**data)
-        dumped = loaded.dict()
+        dumped = loaded.model_dump()
         assert dumped == {"start": 0, "end": 12}
         assert list(dumped.keys())[0] == "start"

tests/test_selectors.py

@@ -32,8 +32,8 @@ class TestTextQuoteSelectors:
     )
 
     def test_convert_selector_to_json(self):
-        copyright_json = self.preexisting_material.json()
-        assert '"exact": "protection for a work' in copyright_json
+        copyright_json = self.preexisting_material.model_dump_json()
+        assert '"exact":"protection for a work' in copyright_json
 
     def test_create_from_text(self):
         method = TextQuoteSelector.from_text(

tests/test_set.py

@@ -400,12 +400,12 @@ def test_serialize_set_with_pydantic(self):
                 TextPositionSelector(start=5, end=10),
             ]
         )
-        assert selector_set.dict()["positions"][0]["end"] == 4
+        assert selector_set.model_dump()["positions"][0]["end"] == 4
 
     def test_get_schema_with_pydantic(self):
         assert (
-            TextPositionSet.schema()["properties"]["positions"]["items"]["$ref"]
-            == "#/definitions/TextPositionSelector"
+            TextPositionSet.model_json_schema()["properties"]["positions"]["items"]["$ref"]
+            == "#/$defs/TextPositionSelector"
         )
 
     def test_set_as_text_sequence_with_no_endpoint(self):

tox.ini

@@ -1,6 +1,6 @@
 # content of: tox.ini , put in same dir as setup.py
 [tox]
-envlist = py310, py39, py38
+envlist = py312, py311, py310, py39, py38
 [testenv]
 # install testing framework
 # ... or install anything else you might need here