indexing_example.py

from whoosh import index, fields
from whoosh import qparser


# Fake data from external files
files = [
    (u"t1.txt", u"Earth is a beautiful planet.Earth is the third planet from the Sun. It is the densest and fifth-largest of the eight planets in the Solar System. It is also the largest of the Solar System's four terrestrial planets. It is sometimes referred to as the world or the Blue Planet."),
    (u"t2.txt", u"jupiter is the biggest planet."),
    (u"t3.txt", u"earth is known as blue planet."),
    (u"t4.txt", u"earth is the 3rd most planet in the universe."),
    (u"t5.txt", u"Distance between earth and sun is some light years."),
]

schema = fields.Schema(content=fields.TEXT, name=fields.ID(stored=True))
ix = index.create_in("index", schema)

with ix.writer() as w:
    for filename, content in files:
        w.add_document(content=content, name=filename)

ix = index.open_dir("index")
qp = qparser.QueryParser("content", ix.schema)
with ix.searcher() as s:
    q = qp.parse(u"earth")
    results = s.search(q)
    for hit in results:
        print(hit["name"])