From 4fe9e76cadd24ce20588623fc1fc3993df468564 Mon Sep 17 00:00:00 2001 From: Aman Date: Sun, 19 Jul 2026 08:46:53 +0000 Subject: [PATCH] add ImagePreprocessor, compute_image_hash, and OutputMetadata --- src/ocr_pipeline/output/markdown.py | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/src/ocr_pipeline/output/markdown.py b/src/ocr_pipeline/output/markdown.py index 1d56c6f..7997a60 100644 --- a/src/ocr_pipeline/output/markdown.py +++ b/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()