Exemplo n.º 1
0
def add_spelling(ix, fieldnames, commit=True):
    """Adds spelling files to an existing index that was created without
    them, and modifies the schema so the given fields have the ``spelling``
    attribute. Only works on filedb indexes.

    >>> ix = index.open_dir("testindex")
    >>> add_spelling(ix, ["content", "tags"])

    :param ix: a :class:`whoosh.filedb.fileindex.FileIndex` object.
    :param fieldnames: a list of field names to create word graphs for.
    :param force: if True, overwrites existing word graph files. This is only
        useful for debugging.
    """

    from whoosh.automata import fst
    from whoosh.reading import SegmentReader

    writer = ix.writer()
    storage = writer.storage
    schema = writer.schema
    segments = writer.segments

    for segment in segments:
        ext = segment.codec().FST_EXT

        r = SegmentReader(storage, schema, segment)
        f = segment.create_file(storage, ext)
        gw = fst.GraphWriter(f)
        for fieldname in fieldnames:
            gw.start_field(fieldname)
            for word in r.lexicon(fieldname):
                gw.insert(word)
            gw.finish_field()
        gw.close()

    for fieldname in fieldnames:
        schema[fieldname].spelling = True

    if commit:
        writer.commit(merge=False)
Exemplo n.º 2
0
def add_spelling(ix, fieldnames, commit=True):
    """Adds spelling files to an existing index that was created without
    them, and modifies the schema so the given fields have the ``spelling``
    attribute. Only works on filedb indexes.

    >>> ix = index.open_dir("testindex")
    >>> add_spelling(ix, ["content", "tags"])

    :param ix: a :class:`whoosh.filedb.fileindex.FileIndex` object.
    :param fieldnames: a list of field names to create word graphs for.
    :param force: if True, overwrites existing word graph files. This is only
        useful for debugging.
    """

    from whoosh.automata import fst
    from whoosh.reading import SegmentReader

    writer = ix.writer()
    storage = writer.storage
    schema = writer.schema
    segments = writer.segments

    for segment in segments:
        ext = segment.codec().FST_EXT

        r = SegmentReader(storage, schema, segment)
        f = segment.create_file(storage, ext)
        gw = fst.GraphWriter(f)
        for fieldname in fieldnames:
            gw.start_field(fieldname)
            for word in r.lexicon(fieldname):
                gw.insert(word)
            gw.finish_field()
        gw.close()

    for fieldname in fieldnames:
        schema[fieldname].spelling = True

    if commit:
        writer.commit(merge=False)