Evergreen Synonym Dictionary Setup

readme oclc synonyms.txt

Please files in the tsearch data directory, which differs based on postgres version.
Postgres 9.4 = /usr/share/postgresql/9.4/tsearch_data

Limitations - only single words can be mapped.  So numbers over 20 cannot be mapped to their spelled out formats.  To be clear, they can be mapped "21" -> "twenty-one" but the Evergreen search subsystem splits "twenty-one" into "Twenty" and "One" which won't ever match "Twenty-one" so it is pointless.

eg search synonym setup.sql

-- Create dictionaries

CREATE TEXT SEARCH DICTIONARY public.synonym_larl (template=pg_catalog.synonym, synonyms='synonym_larl');

CREATE TEXT SEARCH DICTIONARY public.synonym_larl_int (template=pg_catalog.synonym, synonyms='synonym_larl_int');

CREATE TEXT SEARCH DICTIONARY public.synonym_larl_int_roman (template=pg_catalog.synonym, synonyms='synonym_larl_int_roman');

CREATE TEXT SEARCH DICTIONARY public.synonym_larl_txt_roman (template=pg_catalog.synonym, synonyms='synonym_larl_txt_roman');

-- Create Tsearch configs - Need two, one for words, one for extra roman numeral mapping

CREATE TEXT SEARCH CONFIGURATION public.synonym_larl (copy=DEFAULT);

CREATE TEXT SEARCH CONFIGURATION public.synonym_larl_roman (copy=DEFAULT);

-- Map dictionaries to search config data types

ALTER TEXT SEARCH CONFIGURATION public.synonym_larl 
  ALTER MAPPING FOR asciiword, asciihword, hword_asciipart
  WITH synonym_larl;

ALTER TEXT SEARCH CONFIGURATION public.synonym_larl 
  ALTER MAPPING FOR uint
  WITH synonym_larl_int;

ALTER TEXT SEARCH CONFIGURATION public.synonym_larl_roman 
  ALTER MAPPING FOR uint
  WITH synonym_larl_int_roman;
  
ALTER TEXT SEARCH CONFIGURATION public.synonym_larl_roman 
  ALTER MAPPING FOR asciiword, asciihword, hword_asciipart
  WITH synonym_larl_txt_roman;

-- Insert search configs into Evergreen config list
    
INSERT INTO config.ts_config_list VALUES ('synonym_larl', 'LARL Synonym List');

INSERT INTO config.ts_config_list VALUES ('synonym_larl_roman', 'LARL Roman Numeral Synonym List');

-- Map evergreen search configs to indexes

INSERT INTO config.metabib_class_ts_map (field_class, ts_config, index_weight) VALUES 
('keyword', 'synonym_larl', 'C'),
('title', 'synonym_larl', 'C'),
('subject', 'synonym_larl', 'C');

INSERT INTO config.metabib_class_ts_map (field_class, ts_config, index_weight) VALUES 
('keyword', 'synonym_larl_roman', 'C'),
('title', 'synonym_larl_roman', 'C'),
('subject', 'synonym_larl_roman', 'C');

synonym_larl.syn

one          1
two          2
three        3
four         4
five         5
six          6
seven        7
eight        8
nine         9
ten          10
eleven       11
twelve       12
thirteen     13
fourteen     14
fifteen      15
sixteen      16
seventeen    17
eighteen     18
nineteen     19
twenty       20
thirty       30
forty        40
fifty        50
sixty        60
seventy      70
eighty       80
ninety       90
1st          first
first        1st
2nd          second
second       2nd
3rd          third
third        3rd
4th          fourth
fourth       4th
5th          fifth
fifth        5th
6th          sixth
sixth        6th
7th          seventh
seventh      7th
8th          eighth
eighth       8th
9th          ninth
ninth        9th
10th         tenth
tenth        10th
11th         eleventh
eleventh     11th
12th         twelfth
twelfth      12th
13th         thirteenth
thirteenth   13th
14th         fourteenth
fourteenth   14th
15th         fifteenth
fifteenth    15th
16th         sixteenth
sixteenth    16th
17th         seventeenth
seventeenth  17th
18th         eighteenth
eighteenth   18th
19th         nineteenth
nineteenth   19th
20th         twentieth
twentieth    20th
30th         thirtieth
thirtieth    30th
40th         fortieth
fortieth     40th
50th         fiftieth
fiftieth     50th
60th         sixtieth
sixtieth     60th
70th         seventieth
seventieth   70th
80th         eightieth
eightieth    80th
90th         ninetieth
ninetieth    90th
colour       color
color        colour
favour       favor
favor        favour
favourite    favorite
favorite     favourite
encyclopaedia   encyclopedia
encyclopedia    encyclopaedia
medieval        mediaeval
mediaeval       medieval
amongst      among
among        amongst
dreamt       dreamed
dreamed      dreamt
ameba        amoeba
amoeba       ameba
foetus       fetus
fetus        foetus
whisky       whiskey
whiskey      whisky
judgement    judgment
judgment     judgement
theatre      theater
theater      theatre
chanukah     hanukkah
hanukkah     chanukah
child        children
children     child
cat          cats
cats         cat
dog          dogs
dogs         dog
mouse        mice
mice         mouse
horse        horses
horses       horse
cow          cows
cows         cow
duck         ducks
ducks        duck
chicken      chickens
chickens     chicken
puffin       puffins
puffins      puffin
penguin      penguins
penguins     penguin
&            and
and          &
mr           mister
mister       mr
mrs          misses
missus       mrs
mlle         mademoiselle
madomoiselle mlle
doctor       dr
dr           doctor
sir          sr
sr           sir
professor    prof
prof         professor
i            one
ii           two
iii          three
iv           four
v            five
vi           six
vii          seven
viii         eight
ix           nine
x            ten
xi           eleven
xii          twelve
xiii         thirteen
xiv          fourteen
xv           fifteen
xvi          sixteen
xvii         seventeen
xviii        eighteen
xix          nineteen
xx           twenty
xxx          thirty
xl           forty
l            fifty
lx           sixty
lxx          seventy
lxxx         eighty
xc           ninety

synonym_larl_int.syn

0            zero
1            one
2            two
3            three
4            four
5            five
6            six
7            seven
8            eight
9            nine
10           ten
11           eleven
12           twelve
13           thirteen
14           fourteen
15           fifteen
16           sixteen
17           seventeen
18           eighteen
19           nineteen
20           twenty
30           thirty
40           forty
50           fifty
60           sixty
70           seventy
80           eighty
90           ninety

synonym_larl_int_roman.syn

1            i
2            ii
3            iii
4            iv
5            v
6            vi
7            vii
8            viii
9            iv
10           x
11           xi
12           xii
13           xiii
14           xiv
15           xv
16           xvi
17           xvii
18           xviii
19           xix
20           xx
21           xxi
22           xxii
23           xxiii
24           xxiv
25           xxv
26           xxvi
27           xxvii
28           xxviii
29           xxix
30           xxx
31           xxxi
32           xxxii
33           xxxiv
34           xxxiv
35           xxxv
36           xxxvi
37           xxxvii
38           xxxviii
39           xxxix
40           xl
41           xli
42           xlii
43           xliii
44           xliv
45           xlv
46           xlvi
47           xlvii
48           xlviii
49           xlix
50           l
51           li
52           lii
53           liii
54           liv
60           lx
66           lxvi
70           lxx
71           lxxi
72           lxxii
73           lxxiii
74           lxxiv
80           lxxx
90           xc

synonym_larl_txt_roman.syn

i           1
ii          2
iii         3
iv          4
v           5
vi          6
vii         7
viii        8
ix          9
x           10
xi          11
xii         12
xiii        13
xiv         14
xv          15
xvi         16
xvii        17
xviii       18
xix         19
xx          20
xxi         21
xxii        22
xxiii       23
xxiv        24
xxv         25
xxvi        26
xxvii       27
xxviii      28
xxix        29
xxx         30
xxxi        31
xxxii       32
xxxiv       33
xxxiv       34
xxxv        35
xxxvi       36
xxxvii      37
xxxviii     38
xxxix       39
xl          40
xli         41
xlii        42
xliii       43
xliv        44
xlv         45
xlvi        46
xlvii       47
xlviii      48
xlix        49
l           50
li          51
lii         52
liii        53
liv         54
lx          60
lxvi        66
lxx         70
lxxi        71
lxxii       72
lxxiii      73
lxxiv       74
lxxx        80
xc          90