def test_get_form(src, expected, expected_get_fields):
"""Check if we can read out form data."""
src = os.path.join(RESOURCE_ROOT, src)
reader = PdfReader(src)
fields = reader.get_form_text_fields()
assert fields == expected
with open("tmp-fields-report.txt", "w") as f:
fields = reader.get_fields(fileobj=f)
assert fields == expected_get_fields
if fields:
for field in fields.values():
# Just access the attributes
[
field.field_type,
field.parent,
field.kids,
field.name,
field.alternate_name,
field.mapping_name,
field.flags,
field.value,
field.default_value,
field.additional_actions,
]
# cleanup
os.remove("tmp-fields-report.txt")
def test_get_fields():
url = "https://corpora.tika.apache.org/base/docs/govdocs1/972/972486.pdf"
name = "tika-972486.pdf"
reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name)))
fields = reader.get_fields()
assert fields is not None
assert "c1-1" in fields
assert dict(fields["c1-1"]) == ({"/FT": "/Btn", "/T": "c1-1"})
def test_get_fields_read_write_report():
url = "https://corpora.tika.apache.org/base/docs/govdocs1/909/909655.pdf"
name = "tika-909655.pdf"
reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name)))
with open("tmp-fields-report.txt", "w") as fp:
fields = reader.get_fields(fileobj=fp)
assert fields
# cleanup
os.remove("tmp-fields-report.txt")
def test_get_fields():
url = "https://corpora.tika.apache.org/base/docs/govdocs1/961/961883.pdf"
name = "tika-961883.pdf"
data = BytesIO(get_pdf_from_url(url, name=name))
reader = PdfReader(data)
with open("tmp.txt", "w") as fp:
with pytest.warns(PdfReadWarning, match="Object 2 0 not defined."):
retrieved_fields = reader.get_fields(fileobj=fp)
assert retrieved_fields == {}
# Cleanup
os.remove("tmp.txt")
def test_get_fields_read_else_block2():
url = "https://corpora.tika.apache.org/base/docs/govdocs1/914/914902.pdf"
name = "tika-914902.pdf"
reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name)))
fields = reader.get_fields()
assert fields is None
