def doc_to_fields(doc_id, radius=100):
"""
Search for field / department codes in a document.
Args:
doc_id (int)
radius (int)
"""
doc_text = Document_Text.get(Document_Text.document==doc_id)
# Search for each field.
for subfield in Subfield.select():
match = subfield.search(doc_text.text)
# If found, link field -> doc.
if match:
# Slice out the snippet.
i1 = max(match.start() - radius, 0)
i2 = min(match.end() + radius, len(doc_text.text))
snippet = doc_text.text[i1:i2]
Subfield_Document.create(
subfield=subfield,
document=doc_text.document,
offset=match.start(),
snippet=crunch(snippet),
)
def doc_to_fields(doc_id, radius=100):
"""
Search for field / department codes in a document.
Args:
doc_id (int)
radius (int)
"""
doc_text = Document_Text.get(Document_Text.document == doc_id)
# Search for each field.
for subfield in Subfield.select():
match = subfield.search(doc_text.text)
# If found, link field -> doc.
if match:
# Slice out the snippet.
i1 = max(match.start() - radius, 0)
i2 = min(match.end() + radius, len(doc_text.text))
snippet = doc_text.text[i1:i2]
Subfield_Document.create(
subfield=subfield,
document=doc_text.document,
offset=match.start(),
snippet=crunch(snippet),
)
def test_text_extraction_succeeds(mock_osp):
"""
read_text() should extract text for a document and write the result into
the `document_text` table.
"""
# Add a file, create a document row.
path = mock_osp.add_file(content='text')
document = Document.create(path=path)
ext_text(document.id)
# Pop out the new row.
row = Document_Text.get(Document_Text.document == document)
assert row.text == 'text'
def test_text_extraction_succeeds(mock_osp):
"""
read_text() should extract text for a document and write the result into
the `document_text` table.
"""
# Add a file, create a document row.
path = mock_osp.add_file(content='text')
document = Document.create(path=path)
ext_text(document.id)
# Pop out the new row.
row = Document_Text.get(Document_Text.document==document)
assert row.text == 'text'
