def reset():
"""
Reset the index.
"""
Document_Index.es_reset()
def delete():
"""
Delete the index.
"""
Document_Index.es_delete()
def create():
"""
Create the index.
"""
Document_Index.es_create()
def test_matches(add_doc, add_text):
"""
When documents match the query, write doc -> text rows.
"""
wp1 = add_doc(content='War and Peace, Leo Tolstoy 1')
wp2 = add_doc(content='War and Peace, Leo Tolstoy 2')
wp3 = add_doc(content='War and Peace, Leo Tolstoy 3')
ak1 = add_doc(content='Anna Karenina, Leo Tolstoy 1')
ak2 = add_doc(content='Anna Karenina, Leo Tolstoy 2')
Document_Index.es_insert()
text = add_text(title='War and Peace', surname='Tolstoy')
text_to_docs(text.id)
# Should write 3 citation links.
assert Citation.select().count() == 3
# Should match "War and Peace," ignore "Anna Karenina".
for doc in [wp1, wp2, wp3]:
assert Citation.select().where(
Citation.text==text,
Citation.document==doc,
Citation.tokens.contains(text.hash_tokens),
)
def insert():
"""
Index documents.
"""
Document_Index.es_insert()
def test_matches(add_doc, add_text):
"""
When documents match the query, write doc -> text rows.
"""
wp1 = add_doc(content='War and Peace, Leo Tolstoy 1')
wp2 = add_doc(content='War and Peace, Leo Tolstoy 2')
wp3 = add_doc(content='War and Peace, Leo Tolstoy 3')
ak1 = add_doc(content='Anna Karenina, Leo Tolstoy 1')
ak2 = add_doc(content='Anna Karenina, Leo Tolstoy 2')
Document_Index.es_insert()
text = add_text(title='War and Peace', surname='Tolstoy')
text_to_docs(text.id)
# Should write 3 citation links.
assert Citation.select().count() == 3
# Should match "War and Peace," ignore "Anna Karenina".
for doc in [wp1, wp2, wp3]:
assert Citation.select().where(
Citation.text==text,
Citation.document==doc,
Citation.tokens.contains(text.hash_tokens),
)
def test_no_matches(add_doc, add_text):
"""
When no documents match, don't write any rows.
"""
add_doc(content='War and Peace, Leo Tolstoy')
Document_Index.es_insert()
text = add_text(title='Master and Man', surname='Tolstoy')
text_to_docs(text.id)
# Shouldn't write any rows.
assert Citation.select().count() == 0
def test_no_matches(add_doc, add_text):
"""
When no documents match, don't write any rows.
"""
add_doc(content='War and Peace, Leo Tolstoy')
Document_Index.es_insert()
text = add_text(title='Master and Man', surname='Tolstoy')
text_to_docs(text.id)
# Shouldn't write any rows.
assert Citation.select().count() == 0
def test_es_insert(add_doc):
"""
Document_Index.es_insert() should index the document body and id.
"""
doc = add_doc(content='text')
Document_Index.es_insert()
es_doc = config.es.get(
index='document',
id=doc.id,
)
assert es_doc['_source']['body'] == 'text'
def test_es_insert(add_doc):
"""
Document_Index.es_insert() should index the document body and id.
"""
doc = add_doc(content='text')
Document_Index.es_insert()
es_doc = config.es.get(
index='document',
id=doc.id,
)
assert es_doc['_source']['body'] == 'text'
def count():
"""
Count documents.
"""
click.echo(Document_Index.es_count())
def test_citation_formats(title, surname, content, add_doc, add_text):
"""
Test title/author -> citation formats.
"""
# Pad tokens around the match.
padded = ('XXX '*1000) + content + (' XXX'*1000)
doc = add_doc(content=padded)
Document_Index.es_insert()
text = add_text(title=title, surname=surname)
text_to_docs(text.id)
assert Citation.select().where(
Citation.text==text,
Citation.document==doc,
Citation.tokens.contains(text.hash_tokens),
)
def insert():
"""
Index documents.
"""
Document_Index.es_insert()
def count():
"""
Count documents.
"""
click.echo(Document_Index.es_count())
def reset():
"""
Reset the index.
"""
Document_Index.es_reset()
def delete():
"""
Delete the index.
"""
Document_Index.es_delete()
def create():
"""
Create the index.
"""
Document_Index.es_create()