def test_missing_term_docfreq():
schema = fields.Schema(id=fields.ID)
ix = RamIndex(schema)
ix.add_document(id=u("alfa bravo charlie"))
ix.add_document(id=u("charlie delta echo"))
ix.add_document(id=u("sierra tango xray"))
assert_raises(TermNotFound, ix.doc_frequency, "content", "foo")
assert_equal(ix.doc_frequency("id", "foo"), 0)
def test_missing_term_docfreq():
schema = fields.Schema(id=fields.ID)
ix = RamIndex(schema)
ix.add_document(id=u("alfa bravo charlie"))
ix.add_document(id=u("charlie delta echo"))
ix.add_document(id=u("sierra tango xray"))
assert_raises(TermNotFound, ix.doc_frequency, "content", "foo")
assert_equal(ix.doc_frequency("id", "foo"), 0)
def test_block_info():
schema = fields.Schema(key=fields.KEYWORD)
ix = RamIndex(schema)
ix.add_document(key=u("alfa bravo charlie"))
ix.add_document(key=u("bravo delta"))
ix.add_document(key=u("charlie delta echo foxtrot"))
ix.add_document(key=u("delta echo foxtrot golf hotel india"))
ix.add_document(key=u("echo foxtrot golf hotel india juliet alfa bravo"))
s = ix.searcher()
p = s.postings("key", "bravo")
assert p.supports_block_quality()
assert_equal(p.block_min_length(), 2)
assert_equal(p.block_max_length(), 8)
def test_block_info():
schema = fields.Schema(key=fields.KEYWORD)
ix = RamIndex(schema)
ix.add_document(key=u("alfa bravo charlie"))
ix.add_document(key=u("bravo delta"))
ix.add_document(key=u("charlie delta echo foxtrot"))
ix.add_document(key=u("delta echo foxtrot golf hotel india"))
ix.add_document(key=u("echo foxtrot golf hotel india juliet alfa bravo"))
s = ix.searcher()
p = s.postings("key", "bravo")
assert p.supports_block_quality()
assert_equal(p.block_min_length(), 2)
assert_equal(p.block_max_length(), 8)
assert_equal(p.block_max_wol(), 0.5)
def test_missing_postings():
schema = fields.Schema(id=fields.ID)
ix = RamIndex(schema)
ix.add_document(id=u("one"))
assert_raises(TermNotFound, ix.postings, "content", "foo")
assert_raises(TermNotFound, ix.postings, "id", "foo")
def test_empty_field():
schema = fields.Schema(id=fields.ID(stored=True), text=fields.TEXT)
ix = RamIndex(schema)
ix.add_document(id=u("alfa"), text=u("bravo"))
ix.add_document(id=u("charlie"))
ix.add_document(text=u("delta"))
ix.add_document(id=u("echo"), text=None)
ix.add_document(id=None, text=u("foxtrot"))
ix.add_document(id=u("golf"), text=u(""))
ix.add_document(id=u(""), text=u("hotel"))
ix.add_document(id=u(""), text=u(""))
def make_index():
ana = analysis.StandardAnalyzer(stoplist=None)
sc = fields.Schema(id=fields.ID(stored=True),
text=fields.TEXT(analyzer=ana, vector=formats.Frequency()),
subs=fields.NUMERIC(int, stored=True))
ix = RamIndex(sc)
ix.add_document(id=u("fieldtype"),
text=u("The FieldType object supports the following attributes"),
subs=56)
ix.add_document(id=u("format"),
text=u("the storage format for the field contents"),
subs=100)
ix.add_document(id=u("vector"),
text=u("the storage format for the field vectors (forward index)"),
subs=23)
ix.add_document(id=u("scorable"),
text=u("whether searches against this field may be scored."),
subs=34)
ix.add_document(id=u("stored"),
text=u("whether the content of this field is stored for each document."),
subs=575)
ix.add_document(id=u("unique"),
text=u("whether this field value is unique to each document."),
subs=2)
ix.add_document(id=u("const"),
text=u("The constructor for the base field type simply"),
subs=58204)
return ix
def test_missing_postings():
schema = fields.Schema(id=fields.ID)
ix = RamIndex(schema)
ix.add_document(id=u("one"))
assert_raises(TermNotFound, ix.postings, "content", "foo")
assert_raises(TermNotFound, ix.postings, "id", "foo")
def test_empty_field():
schema = fields.Schema(id=fields.ID(stored=True), text=fields.TEXT)
ix = RamIndex(schema)
ix.add_document(id=u("alfa"), text=u("bravo"))
ix.add_document(id=u("charlie"))
ix.add_document(text=u("delta"))
ix.add_document(id=u("echo"), text=None)
ix.add_document(id=None, text=u("foxtrot"))
ix.add_document(id=u("golf"), text=u(""))
ix.add_document(id=u(""), text=u("hotel"))
ix.add_document(id=u(""), text=u(""))
def make_index():
ana = analysis.StandardAnalyzer(stoplist=None)
sc = fields.Schema(id=fields.ID(stored=True),
text=fields.TEXT(analyzer=ana,
vector=formats.Frequency()),
subs=fields.NUMERIC(int, stored=True))
ix = RamIndex(sc)
ix.add_document(
id=u("fieldtype"),
text=u("The FieldType object supports the following attributes"),
subs=56)
ix.add_document(id=u("format"),
text=u("the storage format for the field contents"),
subs=100)
ix.add_document(
id=u("vector"),
text=u("the storage format for the field vectors (forward index)"),
subs=23)
ix.add_document(
id=u("scorable"),
text=u("whether searches against this field may be scored."),
subs=34)
ix.add_document(
id=u("stored"),
text=u(
"whether the content of this field is stored for each document."),
subs=575)
ix.add_document(
id=u("unique"),
text=u("whether this field value is unique to each document."),
subs=2)
ix.add_document(id=u("const"),
text=u("The constructor for the base field type simply"),
subs=58204)
return ix