def test_documents_by_text_should(self):
"""
https://stackoverflow.com/questions/28768277/elasticsearch-difference-between-must-and-should-bool-query
Must: The clause (query) must appear in matching documents.
Should: The clause (query) should appear in the matching document. In a boolean query with no must clauses,
one or more should clauses must match a document. The minimum number of should clauses to match can be set
using the minimum_should_match parameter.
Here, we assume the soeur document *will* match because there is no must clause.
"""
global envIdReadOnly
global authorizationReadOnly
grouped_targets = {CORPUS_ID: []}
documents_by_text = DocumentsByText(envIdReadOnly,
authorizationReadOnly)
should = {
'operator': 'should',
'search_mode': 'language',
'language': 'fr-xx',
'text': 'sœur'
}
count, documents = documents_by_text.documents_by_text(
grouped_targets, [should], 0, 10)
self.assertEqual(1, count)
document_ids = [document["id"] for document in documents]
self.assertIn(ALICE_FR_DOC_ID, document_ids)
def test_documents_by_text_should_sister_french(self):
global envIdReadOnly
global authorizationReadOnly
documents_by_text = DocumentsByText(envIdReadOnly,
authorizationReadOnly)
grouped_targets = {CORPUS_ID: []}
queries = [{
'operator': 'should',
'search_mode': 'language',
'language': 'fr-xx',
'text': 'sœur'
}]
count, documents = documents_by_text.documents_by_text(
grouped_targets, queries, 0, 10)
self.assertEqual(1, count)
document_ids = [document["id"] for document in documents]
self.assertIn(ALICE_FR_DOC_ID, document_ids)
def test_documents_by_text_english_books(self):
global envIdReadOnly
global authorizationReadOnly
grouped_targets = {CORPUS_ID: []}
documents_by_text = DocumentsByText(envIdReadOnly,
authorizationReadOnly)
queries = [{
'operator': 'must',
'search_mode': 'language',
'language': 'en-xx',
'text': 'books'
}]
count, documents = documents_by_text.documents_by_text(
grouped_targets, queries, 0, 10)
self.assertEqual(1, count)
document_ids = [document["id"] for document in documents]
self.assertIn(ALICE_EN_DOC_ID, document_ids)
def test_documents_by_text_basic(self):
global envIdReadOnly
global authorizationReadOnly
documents_by_text = DocumentsByText(envIdReadOnly,
authorizationReadOnly)
grouped_targets = {CORPUS_ID: []}
queries = [{
'operator': 'must',
'search_mode': 'basic',
'language': '',
'text': 'alice'
}]
count, documents = documents_by_text.documents_by_text(
grouped_targets, queries, 0, 10)
self.assertEqual(2, count)
document_ids = [document["id"] for document in documents]
self.assertIn(ALICE_EN_DOC_ID, document_ids)
self.assertIn(ALICE_FR_DOC_ID, document_ids)
def test_documents_by_text_must_and_must_not(self):
global envIdReadOnly
global authorizationReadOnly
grouped_targets = {CORPUS_ID: []}
documents_by_text = DocumentsByText(envIdReadOnly,
authorizationReadOnly)
must = {
'operator': 'must',
'search_mode': 'basic',
'language': '',
'text': 'alice'
}
must_not = {
'operator': 'must_not',
'search_mode': 'language',
'language': 'fr-xx',
'text': 'sœur'
}
count, documents = documents_by_text.documents_by_text(
grouped_targets, [must, must_not], 0, 10)
self.assertEqual(1, count)
document_ids = [document["id"] for document in documents]
self.assertIn(ALICE_EN_DOC_ID, document_ids)