apunkt/trustgraph
1
0
Fork 0
mirror of https://github.com/trustgraph-ai/trustgraph.git synced 2026-06-09 23:05:12 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

fix: reject invalid PDF decoder input (#977)

Browse source
This commit is contained in:
Jacob Molz 2026-06-09 11:37:10 -04:00 • committed by GitHub
parent fa5ebe2393
commit 28a51c244f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 79 additions and 29 deletions
Download patch file Download diff file Expand all files Collapse all files

48
tests/unit/test_decoding/test_pdf_decoder.py
View file

@ -49,7 +49,7 @@ class TestPdfDecoderProcessor(IsolatedAsyncioTestCase):
async def test_on_message_success(self, mock_pdf_loader_class, mock_producer, mock_consumer):
"""Test successful PDF processing"""
# Mock PDF content
pdf_content = b"fake pdf content"
pdf_content = b"%PDF-1.7\nfake pdf content"
pdf_base64 = base64.b64encode(pdf_content).decode('utf-8')
# Mock PyPDFLoader
@ -88,13 +88,55 @@ class TestPdfDecoderProcessor(IsolatedAsyncioTestCase):
# Verify triples were sent for each page (provenance)
assert mock_triples_flow.send.call_count == 2
@patch('trustgraph.base.librarian_client.Consumer')
@patch('trustgraph.base.librarian_client.Producer')
@patch('trustgraph.decoding.pdf.pdf_decoder.PyPDFLoader')
@patch('trustgraph.base.async_processor.AsyncProcessor', MockAsyncProcessor)
async def test_on_message_rejects_librarian_content_that_is_not_pdf(self, mock_pdf_loader_class, mock_producer, mock_consumer):
"""Test rejecting non-PDF content before invoking the PDF loader"""
html_content = b"<html><body>Not found</body></html>"
html_base64 = base64.b64encode(html_content)
mock_metadata = Metadata(id="test-doc")
mock_document = Document(metadata=mock_metadata, document_id="doc-123")
mock_msg = MagicMock()
mock_msg.value.return_value = mock_document
mock_output_flow = AsyncMock()
mock_triples_flow = AsyncMock()
mock_flow = MagicMock(side_effect=lambda name: {
"output": mock_output_flow,
"triples": mock_triples_flow,
}.get(name))
mock_flow.librarian.fetch_document_metadata = AsyncMock(
return_value=MagicMock(kind="application/pdf")
)
mock_flow.librarian.fetch_document_content = AsyncMock(
return_value=html_base64
)
mock_flow.librarian.save_child_document = AsyncMock()
config = {
'id': 'test-pdf-decoder',
'taskgroup': AsyncMock()
}
processor = Processor(**config)
await processor.on_message(mock_msg, None, mock_flow)
mock_pdf_loader_class.assert_not_called()
mock_output_flow.send.assert_not_called()
mock_triples_flow.send.assert_not_called()
mock_flow.librarian.save_child_document.assert_not_called()
@patch('trustgraph.base.librarian_client.Consumer')
@patch('trustgraph.base.librarian_client.Producer')
@patch('trustgraph.decoding.pdf.pdf_decoder.PyPDFLoader')
@patch('trustgraph.base.async_processor.AsyncProcessor', MockAsyncProcessor)
async def test_on_message_empty_pdf(self, mock_pdf_loader_class, mock_producer, mock_consumer):
"""Test handling of empty PDF"""
pdf_content = b"fake pdf content"
pdf_content = b"%PDF-1.7\nfake pdf content"
pdf_base64 = base64.b64encode(pdf_content).decode('utf-8')
mock_loader = MagicMock()
@ -126,7 +168,7 @@ class TestPdfDecoderProcessor(IsolatedAsyncioTestCase):
@patch('trustgraph.base.async_processor.AsyncProcessor', MockAsyncProcessor)
async def test_on_message_unicode_content(self, mock_pdf_loader_class, mock_producer, mock_consumer):
"""Test handling of unicode content in PDF"""
pdf_content = b"fake pdf content"
pdf_content = b"%PDF-1.7\nfake pdf content"
pdf_base64 = base64.b64encode(pdf_content).decode('utf-8')
mock_loader = MagicMock()

60
trustgraph-flow/trustgraph/decoding/pdf/pdf_decoder.py
View file

@ -32,6 +32,10 @@ logger = logging.getLogger(__name__)
default_ident = "document-decoder"
def _looks_like_pdf(content):
return content.lstrip().startswith(b"%PDF-")
class Processor(FlowProcessor):
def __init__(self, **params):
@ -94,33 +98,37 @@ class Processor(FlowProcessor):
)
return
with tempfile.NamedTemporaryFile(delete_on_close=False, suffix='.pdf') as fp:
# Check if we should fetch from librarian or use inline data
if v.document_id:
# Fetch from librarian via Pulsar
logger.info(f"Fetching document {v.document_id} from librarian...")
content = await flow.librarian.fetch_document_content(
document_id=v.document_id,
)
# Content is base64 encoded
if isinstance(content, str):
content = content.encode('utf-8')
decoded_content = base64.b64decode(content)
logger.info(f"Fetched {len(decoded_content)} bytes from librarian")
else:
# Use inline data (backward compatibility)
decoded_content = base64.b64decode(v.data)
if not _looks_like_pdf(decoded_content):
logger.error(
f"Document {v.metadata.id} is not valid PDF content. "
f"Ignoring document."
)
return
with tempfile.NamedTemporaryFile(delete=False, suffix='.pdf') as fp:
temp_path = fp.name
# Check if we should fetch from librarian or use inline data
if v.document_id:
# Fetch from librarian via Pulsar
logger.info(f"Fetching document {v.document_id} from librarian...")
fp.close()
content = await flow.librarian.fetch_document_content(
document_id=v.document_id,
)
# Content is base64 encoded
if isinstance(content, str):
content = content.encode('utf-8')
decoded_content = base64.b64decode(content)
with open(temp_path, 'wb') as f:
f.write(decoded_content)
logger.info(f"Fetched {len(decoded_content)} bytes from librarian")
else:
# Use inline data (backward compatibility)
fp.write(base64.b64decode(v.data))
fp.close()
fp.write(decoded_content)
fp.close()
global PyPDFLoader
if PyPDFLoader is None: