def test_es_insert(models, config, corpus_index):
"""
CorpusIndex.index() should index all rows in Elasticsearch.
"""
# Index 100 documents.
for i in range(10):
doc = Document.create(path=str(i))
Document_Text.create(document=doc, text=str(i))
Document_Text.es_insert()
# Should insert 10 docs.
assert Document_Text.es_count() == 10
# For each text row:
for t in Document_Text.select():
# A document should exist.
doc = config.es.get('osp', t.document.path)
# Should index text / doc ID.
assert doc['_source']['doc_id'] == t.document.id
assert doc['_source']['body'] == t.document.path
def test_es_doc(models):
"""
Document_Text#es_doc() should return an Elasticsearch document.
"""
doc = Document.create(path='000/abc')
text = Document_Text.create(document=doc, text='text')
assert text.es_doc['_id'] == '000/abc'
assert text.es_doc['doc_id'] == doc.id
assert text.es_doc['body'] == 'text'
def ext_text(doc_id):
"""
Write the document as plain text.
Args:
doc_id (int): The document id.
"""
doc = Document.get(Document.id==doc_id)
if doc.syllabus.text:
return Document_Text.create(
text=doc.syllabus.text,
document=doc
)
def test_link_with_document(models, mock_osp):
"""
When a semester marker is found, the metadata row should be associated
with the document that was passed to the job.
"""
# 2 document rows.
doc1 = Document.create(path='path1')
doc2 = Document.create(path='path2')
# Just 1 text row.
doc_text = Document_Text.create(document=doc2, text='Fall 2012')
assert doc_text.id != doc_text.document.id
row = ext_semester(doc2.id)
assert row.document == doc2
