def appendtextindex(table,
index_or_dirname,
indexname=None,
merge=True,
optimize=False):
"""
Load all rows from `table` into a Whoosh index, adding them to any existing
data in the index.
Keyword arguments:
table
A table container with the data to be loaded.
index_or_dirname
Either an instance of `whoosh.index.Index` or a string containing the
directory path where the index is to be stored.
indexname
String containing the name of the index, if multiple indexes are stored
in the same directory.
merge
Merge small segments during commit?
optimize
Merge all segments together?
"""
import whoosh.index
# deal with polymorphic argument
if isinstance(index_or_dirname, string_types):
dirname = index_or_dirname
index = whoosh.index.open_dir(dirname,
indexname=indexname,
readonly=False)
needs_closing = True
elif isinstance(index_or_dirname, whoosh.index.Index):
index = index_or_dirname
needs_closing = False
else:
raise ArgumentError('expected string or index, found %r' %
index_or_dirname)
writer = index.writer()
try:
for d in dicts(table):
writer.add_document(**d)
writer.commit(merge=merge, optimize=optimize)
except Exception:
writer.cancel()
raise
finally:
if needs_closing:
index.close()
def appendtextindex(table, index_or_dirname, indexname=None, merge=True,
optimize=False):
"""
Load all rows from `table` into a Whoosh index, adding them to any existing
data in the index.
Keyword arguments:
table
A table container with the data to be loaded.
index_or_dirname
Either an instance of `whoosh.index.Index` or a string containing the
directory path where the index is to be stored.
indexname
String containing the name of the index, if multiple indexes are stored
in the same directory.
merge
Merge small segments during commit?
optimize
Merge all segments together?
"""
import whoosh.index
# deal with polymorphic argument
if isinstance(index_or_dirname, string_types):
dirname = index_or_dirname
index = whoosh.index.open_dir(dirname, indexname=indexname,
readonly=False)
needs_closing = True
elif isinstance(index_or_dirname, whoosh.index.Index):
index = index_or_dirname
needs_closing = False
else:
raise ArgumentError('expected string or index, found %r'
% index_or_dirname)
writer = index.writer()
try:
for d in dicts(table):
writer.add_document(**d)
writer.commit(merge=merge, optimize=optimize)
except Exception:
writer.cancel()
raise
finally:
if needs_closing:
index.close()
def itertextindex(index_or_dirname, indexname, docnum_field):
import whoosh.index
if isinstance(index_or_dirname, string_types):
dirname = index_or_dirname
index = whoosh.index.open_dir(dirname,
indexname=indexname,
readonly=True)
needs_closing = True
elif isinstance(index_or_dirname, whoosh.index.Index):
index = index_or_dirname
needs_closing = False
else:
raise ArgumentError('expected string or index, found %r' %
index_or_dirname)
try:
if docnum_field is None:
# figure out the field names
hdr = tuple(index.schema.stored_names())
yield hdr
# yield all documents
astuple = operator.itemgetter(*index.schema.stored_names())
for _, stored_fields_dict in index.reader().iter_docs():
yield astuple(stored_fields_dict)
else:
# figure out the field names
hdr = (docnum_field, ) + tuple(index.schema.stored_names())
yield hdr
# yield all documents
astuple = operator.itemgetter(*index.schema.stored_names())
for docnum, stored_fields_dict in index.reader().iter_docs():
yield (docnum, ) + astuple(stored_fields_dict)
except:
raise
finally:
if needs_closing:
# close the index if we're the ones who opened it
index.close()
def itertextindex(index_or_dirname, indexname, docnum_field):
import whoosh.index
if isinstance(index_or_dirname, string_types):
dirname = index_or_dirname
index = whoosh.index.open_dir(dirname, indexname=indexname,
readonly=True)
needs_closing = True
elif isinstance(index_or_dirname, whoosh.index.Index):
index = index_or_dirname
needs_closing = False
else:
raise ArgumentError('expected string or index, found %r'
% index_or_dirname)
try:
if docnum_field is None:
# figure out the field names
hdr = tuple(index.schema.stored_names())
yield hdr
# yield all documents
astuple = operator.itemgetter(*index.schema.stored_names())
for _, stored_fields_dict in index.reader().iter_docs():
yield astuple(stored_fields_dict)
else:
# figure out the field names
hdr = (docnum_field,) + tuple(index.schema.stored_names())
yield hdr
# yield all documents
astuple = operator.itemgetter(*index.schema.stored_names())
for docnum, stored_fields_dict in index.reader().iter_docs():
yield (docnum,) + astuple(stored_fields_dict)
except:
raise
finally:
if needs_closing:
# close the index if we're the ones who opened it
index.close()
def itersearchindex(index_or_dirname, query, limit, pagenum, pagelen, indexname,
docnum_field, score_field, fieldboosts, search_kwargs):
import whoosh.index
import whoosh.query
import whoosh.qparser
if not search_kwargs:
search_kwargs = dict()
if isinstance(index_or_dirname, string_types):
dirname = index_or_dirname
index = whoosh.index.open_dir(dirname,
indexname=indexname,
readonly=True)
needs_closing = True
elif isinstance(index_or_dirname, whoosh.index.Index):
index = index_or_dirname
needs_closing = False
else:
raise ArgumentError('expected string or index, found %r'
% index_or_dirname)
try:
# figure out header
hdr = tuple()
if docnum_field is not None:
hdr += (docnum_field,)
if score_field is not None:
hdr += (score_field,)
stored_names = tuple(index.schema.stored_names())
hdr += stored_names
yield hdr
# parse the query
if isinstance(query, string_types):
# search all fields by default
parser = whoosh.qparser.MultifieldParser(
index.schema.names(),
index.schema,
fieldboosts=fieldboosts
)
query = parser.parse(query)
elif isinstance(query, whoosh.query.Query):
pass
else:
raise ArgumentError(
'expected string or whoosh.query.Query, found %r' % query
)
# make a function to turn docs into tuples
astuple = operator.itemgetter(*index.schema.stored_names())
with index.searcher() as searcher:
if limit is not None:
results = searcher.search(query, limit=limit,
**search_kwargs)
else:
results = searcher.search_page(query, pagenum,
pagelen=pagelen,
**search_kwargs)
if docnum_field is None and score_field is None:
for doc in results:
yield astuple(doc)
else:
for (docnum, score), doc in izip(results.items(), results):
row = tuple()
if docnum_field is not None:
row += (docnum,)
if score_field is not None:
row += (score,)
row += astuple(doc)
yield row
except:
raise
finally:
if needs_closing:
# close the index if we're the ones who opened it
index.close()
# TODO guess schema
def totextindex(table, index_or_dirname, schema=None, indexname=None,
merge=False, optimize=False):
"""
Load all rows from `table` into a Whoosh index. N.B., this will clear any
existing data in the index before loading. E.g.::
>>> import petl as etl
>>> import datetime
>>> import os
>>> # here is the table we want to load into an index
... table = (('f0', 'f1', 'f2', 'f3', 'f4'),
... ('AAA', 12, 4.3, True, datetime.datetime.now()),
... ('BBB', 6, 3.4, False, datetime.datetime(1900, 1, 31)),
... ('CCC', 42, 7.8, True, datetime.datetime(2100, 12, 25)))
>>> # define a schema for the index
... from whoosh.fields import *
>>> schema = Schema(f0=TEXT(stored=True),
... f1=NUMERIC(int, stored=True),
... f2=NUMERIC(float, stored=True),
... f3=BOOLEAN(stored=True),
... f4=DATETIME(stored=True))
>>> # load index
... dirname = 'example.whoosh'
>>> if not os.path.exists(dirname):
... os.mkdir(dirname)
...
>>> etl.totextindex(table, dirname, schema=schema)
Keyword arguments:
table
A table container with the data to be loaded.
index_or_dirname
Either an instance of `whoosh.index.Index` or a string containing the
directory path where the index is to be stored.
schema
Index schema to use if creating the index.
indexname
String containing the name of the index, if multiple indexes are stored
in the same directory.
merge
Merge small segments during commit?
optimize
Merge all segments together?
"""
import whoosh.index
import whoosh.writing
# deal with polymorphic argument
if isinstance(index_or_dirname, string_types):
dirname = index_or_dirname
index = whoosh.index.create_in(dirname, schema,
indexname=indexname)
needs_closing = True
elif isinstance(index_or_dirname, whoosh.index.Index):
index = index_or_dirname
needs_closing = False
else:
raise ArgumentError('expected string or index, found %r'
% index_or_dirname)
writer = index.writer()
try:
for d in dicts(table):
writer.add_document(**d)
writer.commit(merge=merge, optimize=optimize,
mergetype=whoosh.writing.CLEAR)
except:
writer.cancel()
raise
finally:
if needs_closing:
index.close()
def itersearchindex(index_or_dirname, query, limit, pagenum, pagelen,
indexname, docnum_field, score_field, fieldboosts,
search_kwargs):
import whoosh.index
import whoosh.query
import whoosh.qparser
if not search_kwargs:
search_kwargs = dict()
if isinstance(index_or_dirname, string_types):
dirname = index_or_dirname
index = whoosh.index.open_dir(dirname,
indexname=indexname,
readonly=True)
needs_closing = True
elif isinstance(index_or_dirname, whoosh.index.Index):
index = index_or_dirname
needs_closing = False
else:
raise ArgumentError('expected string or index, found %r' %
index_or_dirname)
try:
# figure out header
hdr = tuple()
if docnum_field is not None:
hdr += (docnum_field, )
if score_field is not None:
hdr += (score_field, )
stored_names = tuple(index.schema.stored_names())
hdr += stored_names
yield hdr
# parse the query
if isinstance(query, string_types):
# search all fields by default
parser = whoosh.qparser.MultifieldParser(index.schema.names(),
index.schema,
fieldboosts=fieldboosts)
query = parser.parse(query)
elif isinstance(query, whoosh.query.Query):
pass
else:
raise ArgumentError(
'expected string or whoosh.query.Query, found %r' % query)
# make a function to turn docs into tuples
astuple = operator.itemgetter(*index.schema.stored_names())
with index.searcher() as searcher:
if limit is not None:
results = searcher.search(query, limit=limit, **search_kwargs)
else:
results = searcher.search_page(query,
pagenum,
pagelen=pagelen,
**search_kwargs)
if docnum_field is None and score_field is None:
for doc in results:
yield astuple(doc)
else:
for (docnum, score), doc in izip(results.items(), results):
row = tuple()
if docnum_field is not None:
row += (docnum, )
if score_field is not None:
row += (score, )
row += astuple(doc)
yield row
except:
raise
finally:
if needs_closing:
# close the index if we're the ones who opened it
index.close()
# TODO guess schema
def totextindex(table,
index_or_dirname,
schema=None,
indexname=None,
merge=False,
optimize=False):
"""
Load all rows from `table` into a Whoosh index. N.B., this will clear any
existing data in the index before loading. E.g.::
>>> import petl as etl
>>> import datetime
>>> import os
>>> # here is the table we want to load into an index
... table = (('f0', 'f1', 'f2', 'f3', 'f4'),
... ('AAA', 12, 4.3, True, datetime.datetime.now()),
... ('BBB', 6, 3.4, False, datetime.datetime(1900, 1, 31)),
... ('CCC', 42, 7.8, True, datetime.datetime(2100, 12, 25)))
>>> # define a schema for the index
... from whoosh.fields import *
>>> schema = Schema(f0=TEXT(stored=True),
... f1=NUMERIC(int, stored=True),
... f2=NUMERIC(float, stored=True),
... f3=BOOLEAN(stored=True),
... f4=DATETIME(stored=True))
>>> # load index
... dirname = 'example.whoosh'
>>> if not os.path.exists(dirname):
... os.mkdir(dirname)
...
>>> etl.totextindex(table, dirname, schema=schema)
Keyword arguments:
table
A table container with the data to be loaded.
index_or_dirname
Either an instance of `whoosh.index.Index` or a string containing the
directory path where the index is to be stored.
schema
Index schema to use if creating the index.
indexname
String containing the name of the index, if multiple indexes are stored
in the same directory.
merge
Merge small segments during commit?
optimize
Merge all segments together?
"""
import whoosh.index
import whoosh.writing
# deal with polymorphic argument
if isinstance(index_or_dirname, string_types):
dirname = index_or_dirname
index = whoosh.index.create_in(dirname, schema, indexname=indexname)
needs_closing = True
elif isinstance(index_or_dirname, whoosh.index.Index):
index = index_or_dirname
needs_closing = False
else:
raise ArgumentError('expected string or index, found %r' %
index_or_dirname)
writer = index.writer()
try:
for d in dicts(table):
writer.add_document(**d)
writer.commit(merge=merge,
optimize=optimize,
mergetype=whoosh.writing.CLEAR)
except:
writer.cancel()
raise
finally:
if needs_closing:
index.close()
def closeIndex(searcher, index):
try:
searcher.close()
index.close()
except Exception as ex:
print ex
