Mirrors/dots.ocr
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #34 from openmartin/master

Browse Source 
Update parser.py open file with encoding to support windows
This commit is contained in:
Qing Yan
2025-08-05 21:19:26 +08:00
committed by GitHub
parent ae0ca3a8be 37b62d9b7c
commit dbbe9d78ba
1 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
dots_ocr/parser.py
+3 -3
View File
@@ -116,7 +116,7 @@ class DotsOCRParser:
)
if filtered and prompt_mode != 'prompt_layout_only_en': # model output json failed, use filtered process
json_file_path = os.path.join(save_dir, f"{save_name}.json")
with open(json_file_path, 'w') as w:
with open(json_file_path, 'w', encoding="utf-8") as w:
json.dump(response, w, ensure_ascii=False)
image_layout_path = os.path.join(save_dir, f"{save_name}.jpg")
@@ -143,7 +143,7 @@ class DotsOCRParser:
image_with_layout = origin_image
json_file_path = os.path.join(save_dir, f"{save_name}.json")
with open(json_file_path, 'w') as w:
with open(json_file_path, 'w', encoding="utf-8") as w:
json.dump(cells, w, ensure_ascii=False)
image_layout_path = os.path.join(save_dir, f"{save_name}.jpg")
@@ -242,7 +242,7 @@ class DotsOCRParser:
raise ValueError(f"file extension {file_ext} not supported, supported extensions are {image_extensions} and pdf")
print(f"Parsing finished, results saving to {save_dir}")
with open(os.path.join(output_dir, os.path.basename(filename)+'.jsonl'), 'w') as w:
with open(os.path.join(output_dir, os.path.basename(filename)+'.jsonl'), 'w', encoding="utf-8") as w:
for result in results:
w.write(json.dumps(result, ensure_ascii=False) + '\n')