add ImagePreprocessor, compute_image_hash, and OutputMetadata

src/ocr_pipeline/output/markdown.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import datetime
+from dataclasses import dataclass
 from pathlib import Path
 from typing import Any
 
@@ -12,6 +13,22 @@ from ocr_pipeline.utils.logging import get_logger
 logger = get_logger(__name__)
 
 
+@dataclass
+class OutputMetadata:
+    source_path: str
+    source_hash: str
+    timestamp: str
+    ocr_engine: str
+    ocr_confidence_mean: float
+    language: str
+    detected_entities: list[str]
+    has_figures: bool
+    has_tables: bool
+    citations_found: list[str]
+    chunk_index: int
+    total_chunks: int
+
+
 class MarkdownWriter:
     def __init__(self):
         self.base_dir = Path(settings.output.base_directory).expanduser().resolve()