apunkt/PageIndex
1
0
Fork 0
mirror of https://github.com/VectifyAI/PageIndex.git synced 2026-06-24 20:28:12 +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
pageindex/filesystem/commands.py
View file

@ -517,7 +517,10 @@ class PIFSCommandExecutor:
if i >= len(args): if i >= len(args):
raise PIFSCommandError("cat --node requires a node id") raise PIFSCommandError("cat --node requires a node id")
structural_mode = "node" structural_mode = "node"
node_ids.extend(self._parse_node_ids(args[i])) while i < len(args) and not args[i].startswith("-"):
node_ids.extend(self._parse_node_ids(args[i]))
i += 1
i -= 1
elif arg == "--page": elif arg == "--page":
i += 1 i += 1
if i >= len(args): if i >= len(args):
@ -528,8 +531,10 @@ class PIFSCommandExecutor:
raise PIFSCommandError(f"Unsupported cat option: {arg}") raise PIFSCommandError(f"Unsupported cat option: {arg}")
else: else:
raise PIFSCommandError( raise PIFSCommandError(
"cat accepts one file target. Use: cat <path|file_ref|document_id> --page <page-or-range>, " "cat accepts one file target. Use target-first syntax: "
"for example: cat /documents/report.pdf --page 31-59" "cat <path|file_ref|document_id> --structure, "
"cat <path|file_ref|document_id> --node 0002 0004, or "
"cat <path|file_ref|document_id> --page 31-33"
) )
i += 1 i += 1
if structural_mode == "structure": if structural_mode == "structure":

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") executor.execute("cat dsid_limited_pdf --page 1-4")
nodes = json.loads( 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"] 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"): 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")) text = json.loads(executor.execute("cat dsid_long_text --all"))
assert "line 100" in text["data"]["text"] assert "line 100" in text["data"]["text"]