Unverified Commit 3b9b95c3 authored by Xiaomeng Zhao's avatar Xiaomeng Zhao Committed by GitHub
Browse files

Merge pull request #1036 from icecraft/fix/remove_test_code

parents 6c8f5638 22008b82
...@@ -35,7 +35,7 @@ def read_jsonl( ...@@ -35,7 +35,7 @@ def read_jsonl(
jsonl_d = [ jsonl_d = [
json.loads(line) for line in jsonl_bits.decode().split('\n') if line.strip() json.loads(line) for line in jsonl_bits.decode().split('\n') if line.strip()
] ]
for d in jsonl_d[:5]: for d in jsonl_d:
pdf_path = d.get('file_location', '') or d.get('path', '') pdf_path = d.get('file_location', '') or d.get('path', '')
if len(pdf_path) == 0: if len(pdf_path) == 0:
raise EmptyData('pdf file location is empty') raise EmptyData('pdf file location is empty')
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment