apunkt/PageIndex
1
0
Fork 0
mirror of https://github.com/VectifyAI/PageIndex.git synced 2026-06-12 19:55:17 +02:00
Code Issues Projects Releases Packages Wiki Activity

feat(filesystem): support space-separated cat node ids

Browse source
This commit is contained in:
BukeLy 2026-05-26 20:49:28 +08:00
parent 4a158f9e5f
commit 2b69719f60
2 changed files with 17 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

11
tests/test_pageindex_structural_read.py
View file

@ -481,11 +481,18 @@ def test_cat_structure_page_node_and_text_outputs_are_hard_limited():
executor.execute("cat dsid_limited_pdf --page 1-4")
nodes = json.loads(
executor.execute("cat dsid_limited_pdf --node 0001,0002,0003,0004,0005")
executor.execute("cat dsid_limited_pdf --node 0001 0002 0003 0004 0005")
)
assert nodes["data"]["node_ids"] == ["0001", "0002", "0003", "0004", "0005"]
comma_nodes = json.loads(
executor.execute("cat dsid_limited_pdf --node 0001,0002")
)
assert comma_nodes["data"]["node_ids"] == ["0001", "0002"]
with pytest.raises(PIFSCommandError, match="at most 5"):
executor.execute("cat dsid_limited_pdf --node 0001,0002,0003,0004,0005,0006")
executor.execute("cat dsid_limited_pdf --node 0001 0002 0003 0004 0005 0006")
with pytest.raises(PIFSCommandError, match="cat accepts one file target"):
executor.execute("cat dsid_limited_pdf 0001")
text = json.loads(executor.execute("cat dsid_long_text --all"))
assert "line 100" in text["data"]["text"]