Add comprehensive test suite for image processing and related services

- Implement tests for database generator to ensure proper session handling.
- Create tests for EXIF extraction and conversion functions.
- Add tests for image-related endpoints, ensuring proper data retrieval and isolation between clients.
- Develop tests for OCR functionality, including language detection and text extraction.
- Introduce tests for the image processing pipeline, covering success and failure scenarios.
- Validate rate limiting functionality and ensure independent counters for different clients.
- Implement scraper tests to verify HTML content fetching and error handling.
- Add unit tests for various services, including storage and filename generation.
- Establish worker entry point for ARQ to handle background image processing tasks.

app/models/image.py

@@ -0,0 +1,97 @@
+"""
+Modèle SQLAlchemy — Image et métadonnées associées
+"""
+import enum
+from datetime import datetime, timezone
+from sqlalchemy import (
+    Column, Integer, String, Text, DateTime,
+    JSON, Float, Enum as SAEnum, BigInteger, Boolean, ForeignKey
+)
+from sqlalchemy.orm import relationship
+from app.database import Base
+
+
+class ProcessingStatus(str, enum.Enum):
+    PENDING    = "pending"
+    PROCESSING = "processing"
+    DONE       = "done"
+    ERROR      = "error"
+
+
+class Image(Base):
+    __tablename__ = "images"
+
+    # ── Identité ──────────────────────────────────────────────
+    id              = Column(Integer, primary_key=True, index=True)
+    uuid            = Column(String(36), unique=True, index=True, nullable=False)
+
+    # ── Client (multi-tenant) ─────────────────────────────────
+    client_id       = Column(String(36), ForeignKey("api_clients.id"), nullable=False, index=True)
+    client          = relationship("APIClient", back_populates="images")
+
+    # ── Fichier ───────────────────────────────────────────────
+    original_name   = Column(String(512), nullable=False)
+    filename        = Column(String(512), nullable=False)       # nom sur disque (uuid-based)
+    file_path       = Column(String(1024), nullable=False)
+    thumbnail_path  = Column(String(1024))
+    mime_type       = Column(String(128))
+    file_size       = Column(BigInteger)                        # bytes
+    width           = Column(Integer)
+    height          = Column(Integer)
+    uploaded_at     = Column(DateTime, default=lambda: datetime.now(timezone.utc))
+
+    # ── Statut du pipeline AI ─────────────────────────────────
+    processing_status = Column(
+        SAEnum(ProcessingStatus),
+        default=ProcessingStatus.PENDING,
+        nullable=False,
+        index=True
+    )
+    processing_error  = Column(Text)
+    processing_started_at = Column(DateTime)
+    processing_done_at    = Column(DateTime)
+
+    # ── Métadonnées EXIF ──────────────────────────────────────
+    exif_raw        = Column(JSON)          # dict complet brut
+    exif_make       = Column(String(256))   # Appareil — fabricant
+    exif_model      = Column(String(256))   # Appareil — modèle
+    exif_lens       = Column(String(256))
+    exif_taken_at   = Column(DateTime)      # DateTimeOriginal EXIF
+    exif_gps_lat    = Column(Float)
+    exif_gps_lon    = Column(Float)
+    exif_altitude   = Column(Float)
+    exif_iso        = Column(Integer)
+    exif_aperture   = Column(String(32))    # ex: "f/2.8"
+    exif_shutter    = Column(String(32))    # ex: "1/250"
+    exif_focal      = Column(String(32))    # ex: "50mm"
+    exif_flash      = Column(Boolean)
+    exif_orientation = Column(Integer)
+    exif_software   = Column(String(256))
+
+    # ── OCR ───────────────────────────────────────────────────
+    ocr_text        = Column(Text)
+    ocr_language    = Column(String(64))
+    ocr_confidence  = Column(Float)         # 0.0 – 1.0
+    ocr_has_text    = Column(Boolean, default=False)
+
+    # ── AI Vision ─────────────────────────────────────────────
+    ai_description  = Column(Text)
+    ai_tags         = Column(JSON)          # ["nature", "paysage", ...]
+    ai_confidence   = Column(Float)         # score de confiance global
+    ai_model_used   = Column(String(128))
+    ai_processed_at = Column(DateTime)
+    ai_prompt_tokens  = Column(Integer)
+    ai_output_tokens  = Column(Integer)
+
+    def __repr__(self):
+        return f"<Image id={self.id} name={self.original_name} status={self.processing_status}>"
+
+    @property
+    def has_gps(self) -> bool:
+        return self.exif_gps_lat is not None and self.exif_gps_lon is not None
+
+    @property
+    def dimensions(self) -> str | None:
+        if self.width and self.height:
+            return f"{self.width}x{self.height}"
+        return None