mirror of
https://github.com/DS4SD/docling.git
synced 2025-07-27 04:24:45 +00:00
raise a failure if examples fail
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
This commit is contained in:
parent
2ad85fdf97
commit
9b6b8c4ca0
@ -49,6 +49,7 @@ def export_documents(
|
|||||||
f"of which {failure_count} failed "
|
f"of which {failure_count} failed "
|
||||||
f"and {partial_success_count} were partially converted."
|
f"and {partial_success_count} were partially converted."
|
||||||
)
|
)
|
||||||
|
return success_count, partial_success_count, failure_count
|
||||||
|
|
||||||
|
|
||||||
def main():
|
def main():
|
||||||
@ -73,12 +74,19 @@ def main():
|
|||||||
start_time = time.time()
|
start_time = time.time()
|
||||||
|
|
||||||
conv_results = doc_converter.convert(input)
|
conv_results = doc_converter.convert(input)
|
||||||
export_documents(conv_results, output_dir=Path("./scratch"))
|
success_count, partial_success_count, failure_count = export_documents(
|
||||||
|
conv_results, output_dir=Path("./scratch")
|
||||||
|
)
|
||||||
|
|
||||||
end_time = time.time() - start_time
|
end_time = time.time() - start_time
|
||||||
|
|
||||||
_log.info(f"All documents were converted in {end_time:.2f} seconds.")
|
_log.info(f"All documents were converted in {end_time:.2f} seconds.")
|
||||||
|
|
||||||
|
if failure_count > 0:
|
||||||
|
raise RuntimeError(
|
||||||
|
f"The example failed converting {failure_count} on {len(input_doc_paths)}."
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
if __name__ == "__main__":
|
if __name__ == "__main__":
|
||||||
main()
|
main()
|
||||||
|
@ -42,6 +42,8 @@ def export_documents(
|
|||||||
f"Processed {success_count + failure_count} docs, of which {failure_count} failed"
|
f"Processed {success_count + failure_count} docs, of which {failure_count} failed"
|
||||||
)
|
)
|
||||||
|
|
||||||
|
return success_count, failure_count
|
||||||
|
|
||||||
|
|
||||||
def main():
|
def main():
|
||||||
logging.basicConfig(level=logging.INFO)
|
logging.basicConfig(level=logging.INFO)
|
||||||
@ -114,12 +116,19 @@ def main():
|
|||||||
start_time = time.time()
|
start_time = time.time()
|
||||||
|
|
||||||
conv_results = doc_converter.convert(input)
|
conv_results = doc_converter.convert(input)
|
||||||
export_documents(conv_results, output_dir=Path("./scratch"))
|
success_count, failure_count = export_documents(
|
||||||
|
conv_results, output_dir=Path("./scratch")
|
||||||
|
)
|
||||||
|
|
||||||
end_time = time.time() - start_time
|
end_time = time.time() - start_time
|
||||||
|
|
||||||
_log.info(f"All documents were converted in {end_time:.2f} seconds.")
|
_log.info(f"All documents were converted in {end_time:.2f} seconds.")
|
||||||
|
|
||||||
|
if failure_count > 0:
|
||||||
|
raise RuntimeError(
|
||||||
|
f"The example failed converting {failure_count} on {len(input_doc_paths)}."
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
if __name__ == "__main__":
|
if __name__ == "__main__":
|
||||||
main()
|
main()
|
||||||
|
@ -41,10 +41,13 @@ def main():
|
|||||||
|
|
||||||
conv_results = doc_converter.convert(input_files)
|
conv_results = doc_converter.convert(input_files)
|
||||||
|
|
||||||
|
success_count = 0
|
||||||
|
failure_count = 0
|
||||||
output_dir.mkdir(parents=True, exist_ok=True)
|
output_dir.mkdir(parents=True, exist_ok=True)
|
||||||
for conv_res in conv_results:
|
for conv_res in conv_results:
|
||||||
if conv_res.status != ConversionStatus.SUCCESS:
|
if conv_res.status != ConversionStatus.SUCCESS:
|
||||||
_log.info(f"Document {conv_res.input.file} failed to convert.")
|
_log.info(f"Document {conv_res.input.file} failed to convert.")
|
||||||
|
failure_count += 1
|
||||||
continue
|
continue
|
||||||
|
|
||||||
doc_filename = conv_res.input.file.stem
|
doc_filename = conv_res.input.file.stem
|
||||||
@ -66,10 +69,17 @@ def main():
|
|||||||
with element_image_filename.open("wb") as fp:
|
with element_image_filename.open("wb") as fp:
|
||||||
image.save(fp, "PNG")
|
image.save(fp, "PNG")
|
||||||
|
|
||||||
|
success_count += 1
|
||||||
|
|
||||||
end_time = time.time() - start_time
|
end_time = time.time() - start_time
|
||||||
|
|
||||||
_log.info(f"All documents were converted in {end_time:.2f} seconds.")
|
_log.info(f"All documents were converted in {end_time:.2f} seconds.")
|
||||||
|
|
||||||
|
if failure_count > 0:
|
||||||
|
raise RuntimeError(
|
||||||
|
f"The example failed converting {failure_count} on {len(input_doc_paths)}."
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
if __name__ == "__main__":
|
if __name__ == "__main__":
|
||||||
main()
|
main()
|
||||||
|
Loading…
Reference in New Issue
Block a user