chore: switch from attrs to pydantic (#388)

* chore: switch from attrs to pydantic

* Update src/ebdamame/__init__.py

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* rm keyword only

---------

Co-authored-by: Konstantin <konstantin.klein+github@hochfrequenz.de>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

Author: 3 people

pyproject.toml

@@ -22,7 +22,7 @@ dependencies = [
     "rebdhuhn>=0.16.0",
     "python-docx>=1.1.2",
     "more_itertools>=10.5.0",
-    "attrs>=24.3.0",
+    "pydantic>=2.0",
     "click>=8.1.8"
     # add all the dependencies from requirements.in here, too
 ]

requirements.in

@@ -4,9 +4,10 @@
 #
 #    pip-compile pyproject.toml
 #
+annotated-types==0.7.0
+    # via pydantic
 attrs==25.4.0
     # via
-    #   -r requirements.in
     #   cattrs
     #   rebdhuhn
 cattrs==25.3.0
@@ -16,7 +17,9 @@ certifi==2025.10.5
 charset-normalizer==3.4.3
     # via requests
 click==8.3.1
-    # via -r requirements.in
+    # via ebdamame (pyproject.toml)
+colorama==0.4.6
+    # via click
 idna==3.10
     # via requests
 lxml==6.0.2
@@ -25,20 +28,29 @@ lxml==6.0.2
     #   rebdhuhn
     #   svgutils
 more-itertools==10.8.0
-    # via -r requirements.in
+    # via ebdamame (pyproject.toml)
 networkx==3.5
     # via rebdhuhn
+pydantic==2.12.5
+    # via ebdamame (pyproject.toml)
+pydantic-core==2.41.5
+    # via pydantic
 python-docx==1.2.0
-    # via -r requirements.in
+    # via ebdamame (pyproject.toml)
 rebdhuhn==0.17.5
-    # via -r requirements.in
+    # via ebdamame (pyproject.toml)
 requests==2.32.5
     # via rebdhuhn
 svgutils==0.3.4
     # via rebdhuhn
 typing-extensions==4.15.0
     # via
     #   cattrs
+    #   pydantic
+    #   pydantic-core
     #   python-docx
+    #   typing-inspection
+typing-inspection==0.4.2
+    # via pydantic
 urllib3==2.6.0
     # via requests

requirements.txt

@@ -11,13 +11,13 @@
 from pathlib import Path
 from typing import Generator, Iterable, Optional, Union
 
-import attrs
 import docx
 from docx.document import Document as DocumentType
 from docx.oxml.table import CT_Tbl
 from docx.oxml.text.paragraph import CT_P
 from docx.table import Table, _Cell
 from docx.text.paragraph import Paragraph
+from pydantic import BaseModel, ConfigDict, Field
 
 _logger = logging.getLogger(__name__)
 
@@ -149,14 +149,15 @@ def _table_is_first_ebd_table(table: Table) -> bool:
     return "prüfende rolle" in table.rows[0].cells[0].text.lower()
 
 
-@attrs.define(kw_only=True, frozen=True)
-class EbdNoTableSection:
+class EbdNoTableSection(BaseModel):
     """
     Represents an empty section in the document
     """
 
-    ebd_key: str = attrs.field(validator=attrs.validators.instance_of(str))
-    remark: str = attrs.field(validator=attrs.validators.instance_of(str))
+    model_config = ConfigDict(frozen=True, extra="forbid")
+
+    ebd_key: str
+    remark: str
 
 
 # pylint:disable=too-many-branches
@@ -272,8 +273,7 @@ def get_ebd_docx_tables(docx_file_path: Path, ebd_key: str) -> list[Table] | Ebd
 
 
 # pylint:disable=too-few-public-methods
-@attrs.define(kw_only=True, frozen=True)
-class EbdChapterInformation:
+class EbdChapterInformation(BaseModel):
     """
     Contains information about where an EBD is located within the document.
     If the heading is e.g. "5.2.1" we denote this as:
@@ -282,22 +282,14 @@ class EbdChapterInformation:
     * subsection 1
     """
 
-    chapter: int = attrs.field(
-        validator=attrs.validators.and_(attrs.validators.instance_of(int), attrs.validators.ge(1))
-    )
-    chapter_title: Optional[str] = attrs.field(validator=attrs.validators.optional(attrs.validators.instance_of(str)))
-    section: int = attrs.field(
-        validator=attrs.validators.and_(attrs.validators.instance_of(int), attrs.validators.ge(1))
-    )
-
-    section_title: Optional[str] = attrs.field(validator=attrs.validators.optional(attrs.validators.instance_of(str)))
-    subsection: int = attrs.field(
-        validator=attrs.validators.and_(attrs.validators.instance_of(int), attrs.validators.ge(1))
-    )
-
-    subsection_title: Optional[str] = attrs.field(
-        validator=attrs.validators.optional(attrs.validators.instance_of(str))
-    )
+    model_config = ConfigDict(frozen=True)
+
+    chapter: int = Field(ge=1)
+    chapter_title: Optional[str] = None
+    section: int = Field(ge=1)
+    section_title: Optional[str] = None
+    subsection: int = Field(ge=1)
+    subsection_title: Optional[str] = None
 
 
 def _enrich_paragraphs_with_sections(

src/ebdamame/__init__.py

@@ -8,9 +8,9 @@
 from itertools import cycle, groupby
 from typing import Generator, Literal, Optional
 
-import attrs
 from docx.table import Table, _Cell, _Row
 from more_itertools import first, first_true, last
+from pydantic import BaseModel, ConfigDict
 from rebdhuhn.models.ebd_table import (
     _STEP_NUMBER_REGEX,
     EbdCheckResult,
@@ -120,33 +120,28 @@ class _EbdSubRowPosition(Enum):
 
 
 # pylint:disable=too-few-public-methods
-@attrs.define
-class _EnhancedDocxTableLine:
+class _EnhancedDocxTableLine(BaseModel):
     """
     A structure that primarily contains a single row from a DOCX table but also meta information about previous and
     following elements in the table. It gathers information that are not directly accessible when only looking at one
     single row.
     """
 
-    row: _Row = attrs.field(validator=attrs.validators.instance_of(_Row))
+    model_config = ConfigDict(frozen=True, arbitrary_types_allowed=True)
+
+    row: _Row
     """
     The row that is currently being processed
     """
-    sub_row_position: _EbdSubRowPosition = attrs.field(validator=attrs.validators.instance_of(_EbdSubRowPosition))
+    sub_row_position: _EbdSubRowPosition
     """
     denotes if row is an upper/lower sub row
     """
-    cells: list[_Cell] = attrs.field(
-        validator=attrs.validators.deep_iterable(
-            member_validator=attrs.validators.instance_of(_Cell), iterable_validator=attrs.validators.instance_of(list)
-        )
-    )
+    cells: list[_Cell]
     """
     the (sanitized) cells of the row
     """
-    multi_step_instruction_text: Optional[str] = attrs.field(
-        validator=attrs.validators.optional(attrs.validators.instance_of(str))
-    )
+    multi_step_instruction_text: Optional[str] = None
     """
     a multistep instruction text that may be applicable to this row (if not None)
     """

src/ebdamame/docxtableconverter.py

@@ -99,6 +99,5 @@ deps =
     pre-commit
 commands =
     python -m pip install --upgrade pip
-    pip-compile requirements.in
     pip install -r requirements.txt
     pre-commit install