mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-08-02 07:22:14 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix test data paths in examples

Browse Source 
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Christoph Auer 2025-02-06 19:17:29 +01:00
parent 8979abd865
commit d7df1eae0c
3 changed files with 10 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
docs/examples/batch_convert.py
View File

@ -103,10 +103,10 @@ def main():
logging.basicConfig(level=logging.INFO)
input_doc_paths = [
Path("./tests/data/2206.01062.pdf"),
Path("./tests/data/2203.01017v2.pdf"),
Path("./tests/data/2305.03393v1.pdf"),
Path("./tests/data/redp5110_sampled.pdf"),
Path("./tests/data/pdf/2206.01062.pdf"),
Path("./tests/data/pdf/2203.01017v2.pdf"),
Path("./tests/data/pdf/2305.03393v1.pdf"),
Path("./tests/data/pdf/redp5110_sampled.pdf"),
]
# buf = BytesIO(Path("./test/data/2206.01062.pdf").open("rb").read())

2
docs/examples/translate.py
View File

@ -32,7 +32,7 @@ def translate(text: str, src: str = "en", dest: str = "de"):
def main():
logging.basicConfig(level=logging.INFO)
input_doc_path = Path("./tests/data/2206.01062.pdf")
input_doc_path = Path("./tests/data/pdf/2206.01062.pdf")
output_dir = Path("scratch")
# Important: For operating with page images, we must keep them, otherwise the DocumentConverter

10
docs/v2.md
View File

@ -117,12 +117,12 @@ conv_result: ConversionResult = doc_converter.convert("https://arxiv.org/pdf/240
## Convert several files at once:
input_files = [
"tests/data/wiki_duck.html",
"tests/data/word_sample.docx",
"tests/data/lorem_ipsum.docx",
"tests/data/powerpoint_sample.pptx",
"tests/data/html/wiki_duck.html",
"tests/data/docx/word_sample.docx",
"tests/data/docx/lorem_ipsum.docx",
"tests/data/pptx/powerpoint_sample.pptx",
"tests/data/2305.03393v1-pg9-img.png",
"tests/data/2206.01062.pdf",
"tests/data/pdf/2206.01062.pdf",
]
# Directly pass list of files or streams to `convert_all`