def index_document(self, data):
"""Add the given data to the database.
:param data: the data to be indexed.
A dictionary will be treated as ``fieldname:value``
combinations.
If the fieldname is None then the value will be
interpreted as a plain term or as a list of plain terms.
Lists of terms are indexed separately.
Lists of strings are treated as plain terms.
:type data: dict | list of str
"""
doc = self._create_empty_document()
if isinstance(data, dict):
data = data.items()
# add all data
for dataset in data:
if isinstance(dataset, tuple):
# the dataset tuple consists of '(key, value)'
key, value = dataset
if key is None:
if isinstance(value, list):
terms = value[:]
elif isinstance(value, basestring):
terms = [value]
else:
raise ValueError(
"Invalid data type to be indexed: %s" %
str(type(data)))
for one_term in terms:
self._add_plain_term(doc, self._decode(one_term),
(self.ANALYZER_DEFAULT
& self.ANALYZER_TOKENIZE > 0))
else:
analyze_settings = self.get_field_analyzers(key)
# handle multiple terms
if not isinstance(value, list):
value = [value]
for one_term in value:
self._add_field_term(
doc, key, self._decode(one_term),
(analyze_settings & self.ANALYZER_TOKENIZE > 0))
elif isinstance(dataset, basestring):
self._add_plain_term(
doc, self._decode(dataset),
(self.ANALYZER_DEFAULT & self.ANALYZER_TOKENIZE > 0))
else:
raise ValueError("Invalid data type to be indexed: %s" %
str(type(data)))
self._add_document_to_index(doc)
def index_document(self, data):
"""Add the given data to the database.
:param data: the data to be indexed.
A dictionary will be treated as ``fieldname:value``
combinations.
If the fieldname is None then the value will be
interpreted as a plain term or as a list of plain terms.
Lists of terms are indexed separately.
Lists of strings are treated as plain terms.
:type data: dict | list of str
"""
doc = self._create_empty_document()
if isinstance(data, dict):
data = data.items()
# add all data
for dataset in data:
if isinstance(dataset, tuple):
# the dataset tuple consists of '(key, value)'
key, value = dataset
if key is None:
if isinstance(value, list):
terms = value[:]
elif isinstance(value, six.string_types):
terms = [value]
else:
raise ValueError("Invalid data type to be indexed: %s" %
str(type(data)))
for one_term in terms:
self._add_plain_term(
doc, self._decode(one_term),
(self.ANALYZER_DEFAULT & self.ANALYZER_TOKENIZE > 0))
else:
analyze_settings = self.get_field_analyzers(key)
# handle multiple terms
if not isinstance(value, list):
value = [value]
for one_term in value:
self._add_field_term(
doc, key, self._decode(one_term),
(analyze_settings & self.ANALYZER_TOKENIZE > 0))
elif isinstance(dataset, six.string_types):
self._add_plain_term(
doc, self._decode(dataset),
(self.ANALYZER_DEFAULT & self.ANALYZER_TOKENIZE > 0))
else:
raise ValueError("Invalid data type to be indexed: %s" %
str(type(data)))
self._add_document_to_index(doc)