From 02cc0cef84e3f36e8313750d0c214c45dca80fca Mon Sep 17 00:00:00 2001
From: suke <32221726+wangsrGit119@users.noreply.github.com>
Date: Sun, 15 Dec 2024 11:52:58 +0800
Subject: [PATCH] feat: Add OCR fallback when MLM is unavailable for image
 processing

feat: Add OCR fallback when MLM is unavailable for image processing

- Add OCR text extraction using easyocr when MLM client/model is not configured
- Support both Chinese and English text recognition
- Add OCR results under "OCR Text" section in markdown output
- Only execute OCR as fallback when MLM description is not available
---
 src/markitdown/_markitdown.py | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/src/markitdown/_markitdown.py b/src/markitdown/_markitdown.py
index 96997cf..332b2d1 100644
--- a/src/markitdown/_markitdown.py
+++ b/src/markitdown/_markitdown.py
@@ -798,6 +798,20 @@ def convert(self, local_path, **kwargs) -> Union[None, DocumentConverterResult]:
                 ).strip()
                 + "\n"
             )
+        # add ocr only when MLM is not available
+        if mlm_client is None or mlm_model is None:
+            try:
+                import easyocr
+                reader = easyocr.Reader(['ch_sim','en']) # support chinese and english 
+                ocr_result = reader.readtext(local_path)
+                if ocr_result:
+                    md_content += "\n"
+                    for detection in ocr_result:
+                        text = detection[1]  # extract text
+                        md_content += f"- {text}\n"
+            except ImportError:
+                # easyocr not installed
+                pass
 
         return DocumentConverterResult(
             title=None,