Return to Revisions

There were so many changes I would have to make to my first answer I start this one !!!

USE test
DROP TABLE IF EXISTS ngram_key;
DROP TABLE IF EXISTS ngram_rec;
DROP TABLE IF EXISTS ngram_blk;
CREATE TABLE ngram_key
(
    NGRAM_ID BIGINT NOT NULL AUTO_INCREMENT,
    NGRAM VARCHAR(64) NOT NULL,
    PRIMARY KEY (NGRAM),
    KEY (NGRAM_ID)
) ENGINE=MyISAM ROW_FORMAT=FIXED PARTITION BY KEY(NGRAM) PARTITIONS 256;
CREATE TABLE ngram_rec
(
    NGRAM_ID BIGINT NOT NULL,
    YR SMALLINT NOT NULL,
    MC SMALLINT NOT NULL,
    PC SMALLINT NOT NULL,
    VC SMALLINT NOT NULL,
    PRIMARY KEY (NGRAM_ID,YR)
) ENGINE=MyISAM ROW_FORMAT=FIXED;
CREATE TABLE ngram_blk
(
    NGRAM VARCHAR(64) NOT NULL,
    YR SMALLINT NOT NULL,
    MC SMALLINT NOT NULL,
    PC SMALLINT NOT NULL,
    VC SMALLINT NOT NULL
) ENGINE=BLACKHOLE;
DELIMITER $$
CREATE TRIGGER populate_ngram AFTER INSERT ON ngram_blk FOR EACH ROW
BEGIN
    DECLARE NEW_ID BIGINT;

    INSERT IGNORE INTO ngram_key (NGRAM) VALUES (NEW.NGRAM);
    SELECT NGRAM_ID INTO NEW_ID FROM ngram_key WHERE NGRAM=NEW.NGRAM;
    INSERT IGNORE INTO ngram_rec VALUES (NEW_ID,NEW.YR,NEW.MC,NEW.PC,NEW.VC);
END; $$
DELIMITER ;
INSERT INTO ngram_blk VALUES
('rolando',1965,31,29,85),
('pamela',1971,33,21,86),
('dominique',1996,30,18,87),
('diamond',1998,13,28,88),
('rolando edwards',1965,31,29,85),
('pamela edwards',1971,33,21,86),
('dominique edwards',1996,30,18,87),
('diamond edwards',1998,13,28,88),
('rolando angel edwards',1965,31,29,85),
('pamela claricia edwards',1971,33,21,86),
('dominique sharlisee edwards',1996,30,18,87),
('diamond ashley edwards',1998,13,28,88);
UPDATE ngram_rec SET yr=yr+1,mc=mc+30,pc=pc+30,vc=vc+30;
INSERT INTO ngram_blk VALUES
('rolando',1965,31,29,85),
('pamela',1971,33,21,86),
('dominique',1996,30,18,87),
('diamond',1998,13,28,88),
('rolando edwards',1965,31,29,85),
('pamela edwards',1971,33,21,86),
('dominique edwards',1996,30,18,87),
('diamond edwards',1998,13,28,88),
('rolando angel edwards',1965,31,29,85),
('pamela claricia edwards',1971,33,21,86),
('dominique sharlisee edwards',1996,30,18,87),
('diamond ashley edwards',1998,13,28,88);
UPDATE ngram_rec SET yr=yr+1,mc=mc+30,pc=pc+30;
INSERT INTO ngram_blk VALUES
('rolando',1965,31,29,85),
('pamela',1971,33,21,86),
('dominique',1996,30,18,87),
('diamond',1998,13,28,88),
('rolando edwards',1965,31,29,85),
('pamela edwards',1971,33,21,86),
('dominique edwards',1996,30,18,87),
('diamond edwards',1998,13,28,88),
('rolando angel edwards',1965,31,29,85),
('pamela claricia edwards',1971,33,21,86),
('dominique sharlisee edwards',1996,30,18,87),
('diamond ashley edwards',1998,13,28,88);
UPDATE ngram_rec SET yr=yr+1,mc=mc+30;
SELECT * FROM ngram_key;
SELECT * FROM ngram_rec;
SELECT A.ngram NGram,B.yr Year,B.mc Matches,B.pc Pages,B.vc Volumes FROM 
ngram_key A,ngram_rec B
WHERE A.ngram='rolando angel edwards'
AND A.ngram_id=B.ngram_id;

Much smaller tables and keys. I also increased the amount of test data. I'll explain the data size metrics later. For now, you can cut and paste this directly into MySQL. Stay tuned...