src/ports/postgres/modules/utilities/test/text_utilities.ic.sql_in

/* ----------------------------------------------------------------------- *//**
 *
 * Licensed to the Apache Software Foundation (ASF) under one
 * or more contributor license agreements.  See the NOTICE file
 * distributed with this work for additional information
 * regarding copyright ownership.  The ASF licenses this file
 * to you under the Apache License, Version 2.0 (the
 * "License"); you may not use this file except in compliance
 * with the License.  You may obtain a copy of the License at
 *
 *   http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing,
 * software distributed under the License is distributed on an
 * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
 * KIND, either express or implied.  See the License for the
 * specific language governing permissions and limitations
 * under the License.
 *
 *//* ----------------------------------------------------------------------- */

---------------------------------------------------------------------------
-- Build training dataset:
---------------------------------------------------------------------------
DROP TABLE IF EXISTS training;
CREATE TABLE training
(
    docid INT4,
    wordid INT4,
    count INT4
);

INSERT INTO training VALUES
(0, 0, 2),(0, 3, 2),(0, 5, 1),(9, 18, 1),(9, 19, 1);


DROP TABLE IF EXISTS documents;
CREATE TABLE documents AS
SELECT docid, array_agg(wordid) as words
FROM (
      SELECT docid, wordid, generate_series(1, count)
      FROM training
) q
GROUP BY docid;

DROP TABLE IF EXISTS output_terms;
DROP TABLE IF EXISTS output_terms_vocabulary;
SELECT term_frequency('documents', 'docid', 'words', 'output_terms', FALSE);