tegwick
9031e1162c
Deterministic validation of EntityMeta against declarative schemas: section presence/word counts, heading format, domain enum values. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
145 lines
3.9 KiB
Python
145 lines
3.9 KiB
Python
"""
|
|
Declarative schema definitions for entity compliance validation.
|
|
|
|
A schema describes the expected structure of an entity: which sections
|
|
are required, word count bounds, heading format, and valid enum values.
|
|
Schemas are frozen (immutable once created).
|
|
"""
|
|
|
|
from dataclasses import dataclass
|
|
from enum import Enum
|
|
from typing import Optional, Tuple
|
|
|
|
|
|
class SectionRequirement(Enum):
|
|
"""How strictly a section must be present."""
|
|
|
|
REQUIRED = "required"
|
|
RECOMMENDED = "recommended"
|
|
OPTIONAL = "optional"
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class SectionRule:
|
|
"""Validation rule for a single H2 section.
|
|
|
|
Parameters
|
|
----------
|
|
slug:
|
|
Section slug as it appears in entity metadata (e.g. ``definition``).
|
|
label:
|
|
Human-readable section name for diagnostics.
|
|
requirement:
|
|
Whether the section is required, recommended, or optional.
|
|
min_words:
|
|
Minimum word count (inclusive). ``None`` means no lower bound.
|
|
max_words:
|
|
Maximum word count (inclusive). ``None`` means no upper bound.
|
|
"""
|
|
|
|
slug: str
|
|
label: str
|
|
requirement: SectionRequirement
|
|
min_words: Optional[int] = None
|
|
max_words: Optional[int] = None
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class EnumConstraint:
|
|
"""Constraint limiting a field to a set of allowed values.
|
|
|
|
Parameters
|
|
----------
|
|
field_name:
|
|
The ``EntityMeta`` field to check (e.g. ``domain``).
|
|
allowed_values:
|
|
Tuple of acceptable string values.
|
|
severity:
|
|
``"error"`` or ``"warning"`` when the value is not in the set.
|
|
"""
|
|
|
|
field_name: str
|
|
allowed_values: Tuple[str, ...]
|
|
severity: str = "warning"
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class EntitySchema:
|
|
"""Complete validation schema for an entity type.
|
|
|
|
Parameters
|
|
----------
|
|
name:
|
|
Human-readable schema name (e.g. ``"Economic Entity"``).
|
|
section_rules:
|
|
Tuple of :class:`SectionRule` objects.
|
|
enum_constraints:
|
|
Tuple of :class:`EnumConstraint` objects.
|
|
h1_title_case_severity:
|
|
Severity for non-title-case H1 headings (``"error"`` or ``"warning"``).
|
|
require_h1:
|
|
Whether a non-empty slug (H1) is required.
|
|
"""
|
|
|
|
name: str
|
|
section_rules: Tuple[SectionRule, ...]
|
|
enum_constraints: Tuple[EnumConstraint, ...] = ()
|
|
h1_title_case_severity: str = "warning"
|
|
require_h1: bool = True
|
|
|
|
|
|
# ── Default schema for the economic-entity infospace ──────────────
|
|
|
|
ECONOMIC_ENTITY_SCHEMA = EntitySchema(
|
|
name="Economic Entity",
|
|
section_rules=(
|
|
SectionRule(
|
|
slug="definition",
|
|
label="Definition",
|
|
requirement=SectionRequirement.REQUIRED,
|
|
min_words=20,
|
|
max_words=150,
|
|
),
|
|
SectionRule(
|
|
slug="source_chapter",
|
|
label="Source Chapter",
|
|
requirement=SectionRequirement.REQUIRED,
|
|
),
|
|
SectionRule(
|
|
slug="context",
|
|
label="Context",
|
|
requirement=SectionRequirement.REQUIRED,
|
|
),
|
|
SectionRule(
|
|
slug="economic_domain",
|
|
label="Economic Domain",
|
|
requirement=SectionRequirement.REQUIRED,
|
|
),
|
|
SectionRule(
|
|
slug="smith_s_original_wording",
|
|
label="Smith's Original Wording",
|
|
requirement=SectionRequirement.OPTIONAL,
|
|
),
|
|
SectionRule(
|
|
slug="modern_interpretation",
|
|
label="Modern Interpretation",
|
|
requirement=SectionRequirement.OPTIONAL,
|
|
),
|
|
),
|
|
enum_constraints=(
|
|
EnumConstraint(
|
|
field_name="domain",
|
|
allowed_values=(
|
|
"Production",
|
|
"Exchange",
|
|
"Distribution",
|
|
"Regulation",
|
|
"General Theory",
|
|
),
|
|
severity="warning",
|
|
),
|
|
),
|
|
h1_title_case_severity="warning",
|
|
require_h1=True,
|
|
)
|