Files
game-library/app/models/activity.py
Claude Agent 66ae831c36 Rebuild extraction pipeline infrastructure (Faza 0 prep)
Implements the approved plan to replace the broken regex/index-master
extraction with an LLM-subagent pipeline. Four parallel lanes:

Lane A — scripts/extract_common.py (PDF/docx/doc/pptx/html/zip, no
  max_pages truncation), normalize_sources.py, chunk_sources.py
  (~20pg chunks + overlap, manifest registry), activity_schema.json.
Lane B — app/config_taxonomy.py (16 fixed category slugs), schema
  rebuilt from scratch in app/models/ with content_type, language,
  source_files, source_excerpt, normalized_name, extraction_confidence,
  needs_review; FTS5 + 3 triggers extended with materials_list and
  skills_developed.
Lane C — build_database.py (--rebuild, atomic swap, schema + fuzzy
  source_excerpt validation, dedup with needs_review band),
  validate_extractions.py, review_queue.py, new run_extraction.py
  orchestrator, SUBAGENT_PROMPT.md.
Lane D — search.py content_type/language filters (default search
  excludes non-game content), E7 schema-compat audit; fixed a NULL
  keywords AttributeError in _boost_search_relevance.

Removes 8 orphaned/dead scripts and app/services/parser.py +
indexer.py. Adds tests/ (70 passing, 1 skipped — libreoffice absent).

Note: Lane D made one additive edit to app/models/database.py
(_update_category_counts) to surface content_type/language in
get_filter_options, outside its nominal lane boundary but after
Lane B completed.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-19 17:43:38 +00:00

213 lines
8.3 KiB
Python

"""
Activity data model for INDEX-SISTEM-JOCURI v2.0
"""
from dataclasses import dataclass, field
from typing import List, Optional, Dict, Any
import json
import re
import unicodedata
def normalize_name(name: str) -> str:
"""Diacritic-free, lowercased, whitespace-collapsed form of a name.
Used as the exact-match key for dedup grouping (see plan §4).
"""
if not name:
return ""
decomposed = unicodedata.normalize("NFKD", name)
ascii_str = "".join(c for c in decomposed if not unicodedata.combining(c))
ascii_str = ascii_str.lower().strip()
ascii_str = re.sub(r"\s+", " ", ascii_str)
return ascii_str
@dataclass
class Activity:
"""Activity data model with comprehensive fields"""
# Basic information
name: str
description: str
rules: Optional[str] = None
variations: Optional[str] = None
# Categories
category: str = ""
subcategory: Optional[str] = None
# content_type is an axis INDEPENDENT of category:
# one of joc/activitate/reteta/cantec/ceremonie (see config_taxonomy).
content_type: Optional[str] = None
# Source information
source_file: str = ""
page_reference: Optional[str] = None
# source_files: JSON-encoded list of every source the activity was seen in.
# `source_file` (singular) stays as the primary/original source; build_database
# (Lane C) accumulates the full list here on dedup-merge.
source_files: List[str] = field(default_factory=list)
# Short verbatim quote from the source — anti-hallucination anchor.
source_excerpt: Optional[str] = None
# Age and participants
age_group_min: Optional[int] = None
age_group_max: Optional[int] = None
participants_min: Optional[int] = None
participants_max: Optional[int] = None
# Duration
duration_min: Optional[int] = None # minutes
duration_max: Optional[int] = None # minutes
# Materials and setup
materials_category: Optional[str] = None
materials_list: Optional[str] = None
skills_developed: Optional[str] = None
difficulty_level: Optional[str] = None
# Search and metadata
keywords: Optional[str] = None
tags: List[str] = field(default_factory=list)
popularity_score: int = 0
# Extraction / language metadata
language: Optional[str] = None # 'ro' / 'en'
normalized_name: Optional[str] = None # dedup key; auto-derived from name
extraction_confidence: Optional[str] = None # 'high' / 'med' / 'low'
needs_review: int = 0
# Database fields
id: Optional[int] = None
created_at: Optional[str] = None
updated_at: Optional[str] = None
def __post_init__(self):
"""Derive normalized_name from name when not explicitly provided."""
if not self.normalized_name:
self.normalized_name = normalize_name(self.name)
def to_dict(self) -> Dict[str, Any]:
"""Convert activity to dictionary for database storage"""
return {
'name': self.name,
'description': self.description,
'rules': self.rules,
'variations': self.variations,
'category': self.category,
'subcategory': self.subcategory,
'content_type': self.content_type,
'source_file': self.source_file,
'source_files': json.dumps(self.source_files) if self.source_files else None,
'page_reference': self.page_reference,
'source_excerpt': self.source_excerpt,
'age_group_min': self.age_group_min,
'age_group_max': self.age_group_max,
'participants_min': self.participants_min,
'participants_max': self.participants_max,
'duration_min': self.duration_min,
'duration_max': self.duration_max,
'materials_category': self.materials_category,
'materials_list': self.materials_list,
'skills_developed': self.skills_developed,
'difficulty_level': self.difficulty_level,
'keywords': self.keywords,
'tags': json.dumps(self.tags) if self.tags else None,
'popularity_score': self.popularity_score,
'language': self.language,
'normalized_name': self.normalized_name or normalize_name(self.name),
'extraction_confidence': self.extraction_confidence,
'needs_review': self.needs_review,
}
@classmethod
def from_dict(cls, data: Dict[str, Any]) -> 'Activity':
"""Create activity from dictionary"""
# Parse tags from JSON if present
tags = []
if data.get('tags'):
try:
tags = json.loads(data['tags'])
except (json.JSONDecodeError, TypeError):
tags = []
# source_files may arrive as a JSON string (DB) or a list (extraction)
source_files = data.get('source_files')
if isinstance(source_files, str):
try:
source_files = json.loads(source_files)
except (json.JSONDecodeError, TypeError):
source_files = []
elif source_files is None:
source_files = []
return cls(
id=data.get('id'),
name=data.get('name', ''),
description=data.get('description', ''),
rules=data.get('rules'),
variations=data.get('variations'),
category=data.get('category', ''),
subcategory=data.get('subcategory'),
content_type=data.get('content_type'),
source_file=data.get('source_file', ''),
source_files=source_files,
page_reference=data.get('page_reference'),
source_excerpt=data.get('source_excerpt'),
age_group_min=data.get('age_group_min'),
age_group_max=data.get('age_group_max'),
participants_min=data.get('participants_min'),
participants_max=data.get('participants_max'),
duration_min=data.get('duration_min'),
duration_max=data.get('duration_max'),
materials_category=data.get('materials_category'),
materials_list=data.get('materials_list'),
skills_developed=data.get('skills_developed'),
difficulty_level=data.get('difficulty_level'),
keywords=data.get('keywords'),
tags=tags,
popularity_score=data.get('popularity_score', 0),
language=data.get('language'),
normalized_name=data.get('normalized_name'),
extraction_confidence=data.get('extraction_confidence'),
needs_review=data.get('needs_review', 0) or 0,
created_at=data.get('created_at'),
updated_at=data.get('updated_at')
)
def get_age_range_display(self) -> str:
"""Get formatted age range for display"""
if self.age_group_min and self.age_group_max:
return f"{self.age_group_min}-{self.age_group_max} ani"
elif self.age_group_min:
return f"{self.age_group_min}+ ani"
elif self.age_group_max:
return f"până la {self.age_group_max} ani"
return "toate vârstele"
def get_participants_display(self) -> str:
"""Get formatted participants range for display"""
if self.participants_min and self.participants_max:
return f"{self.participants_min}-{self.participants_max} persoane"
elif self.participants_min:
return f"{self.participants_min}+ persoane"
elif self.participants_max:
return f"până la {self.participants_max} persoane"
return "orice număr"
def get_duration_display(self) -> str:
"""Get formatted duration for display"""
if self.duration_min and self.duration_max:
return f"{self.duration_min}-{self.duration_max} minute"
elif self.duration_min:
return f"{self.duration_min}+ minute"
elif self.duration_max:
return f"până la {self.duration_max} minute"
return "durată variabilă"
def get_materials_display(self) -> str:
"""Get formatted materials for display"""
if self.materials_category:
return self.materials_category
elif self.materials_list:
return self.materials_list[:100] + "..." if len(self.materials_list) > 100 else self.materials_list
return "nu specificate"