1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
|
import ndb from ".";
import toneDb from "@/lib/db/prosodydb";
// function test() {
// const tones = ["low", "mid"];
// const ndb = new BigQueries();
// const nq = ndb.fetchWordsByToneAndSyls(tones);
// const oq = toneDb.fetchWordsByToneAndSyls(tones);
// // const senses = JSON.parse(res[0].senses_array);
// console.log({ nq });
// console.log(nq.length, oq.length);
// }
function test() {
const tones = ["low", "mid"];
console.log("wtf");
// const qq = ndb.fetchWordsByToneAndSyls1(tones);
// const oq = ndb.fetchWordsByToneAndSylsO(tones);
const nq = ndb.fetchWordsByToneAndSyls(tones);
// const roq = toneDb.fetchWordsByToneAndSyls(tones);
// const senses = JSON.parse(res[0].senses_array);
// console.log({ nq });
// console.log("old", oq.length);
// console.log("old db", roq.length);
console.log("new", nq);
// console.log("test", qq.length);
}
test();
// `
// `
// WITH word_tone_sequences AS (
// SELECT
// w.id as word_id,
// w.spelling,
// wp.ipa,
// w.frequency,
// GROUP_CONCAT(sy.text ORDER BY sw.idx) as syl_seq,
// GROUP_CONCAT(t.name ORDER BY sw.idx) as tone_sequence,
// COUNT(sw.syl_id) as syllable_count,
// (SELECT
// json_group_array(json_object(
// 'id', s.id,
// 'pos', s.pos,
// 'etymology', s.etymology,
// 'confidence', s.confidence,
// 'subsenses', (
// SELECT json_group_array(json_object(
// 'id', ss.id,
// 'gloss', ss.gloss
// ))
// FROM subsenses ss
// WHERE ss.sid = s.id
// ),
// 'examples', (
// SELECT json_group_array(json_object(
// 'id', ex.id,
// 'example', ex.example,
// 'ref', ex.ref
// ))
// FROM examples ex
// WHERE ex.sid = s.id
// ),
// 'derivation', (
// SELECT json_group_array(json_object(
// 'id', d.id,
// 'type', d.type,
// 'text', d.text,
// 'tags', d.tags
// ))
// FROM derivation d
// WHERE d.sid = s.id
// ),
// 'categories', (
// SELECT json_group_array(wc.category)
// FROM word_categories wc
// WHERE wc.word_id = s.id
// )
// ))
// FROM senses s
// WHERE s.parent_id = w.id
// ) as senses_array
// FROM expressions w
// JOIN word_phonetics wp ON w.id = wp.word_id
// JOIN syllables_words sw ON wp.id = sw.word_id
// JOIN syllables sy ON sw.syl_id = sy.id
// JOIN tones t ON sy.tone = t.id
// GROUP BY w.id, w.spelling, w.lang, w.frequency
// )
// SELECT *
// FROM word_tone_sequences
// WHERE tone_sequence LIKE ?
// AND syllable_count = ?
// ORDER BY frequency ASC NULLS LAST;
// `
//
//
//
// `
// WITH word_tone_sequences AS (
// SELECT
// w.id as word_id,
// w.spelling,
// wp.ipa,
// w.frequency,
// GROUP_CONCAT(sy.text ORDER BY sw.idx) as syl_seq,
// GROUP_CONCAT(t.name ORDER BY sw.idx) as tone_sequence,
// COUNT(sw.syl_id) as syllable_count
// FROM expressions w
// JOIN word_phonetics wp ON w.id = wp.word_id
// JOIN syllables_words sw ON wp.id = sw.word_id
// JOIN syllables sy ON sw.syl_id = sy.id
// JOIN tones t ON sy.tone = t.id
// GROUP BY w.id, w.spelling, w.lang, w.frequency, wp.ipa
// ),
// sense_data AS (
// SELECT
// s.*,
// GROUP_CONCAT(DISTINCT ss.id || ':' || ss.gloss, '|') as subsenses_data,
// GROUP_CONCAT(DISTINCT ex.id || ':' || ex.example || ':' || COALESCE(ex.ref, ''), '|') as examples_data,
// GROUP_CONCAT(DISTINCT d.id || ':' || d.type || ':' || d.text, '|') as derivation_data,
// GROUP_CONCAT(DISTINCT wc.category, '|') as categories_data
// FROM senses s
// LEFT JOIN subsenses ss ON ss.sid = s.id
// LEFT JOIN examples ex ON ex.sid = s.id
// LEFT JOIN derivation d ON d.sid = s.id
// LEFT JOIN word_categories wc ON wc.word_id = s.id
// GROUP BY s.id
// )
// SELECT
// wts.*,
// (SELECT
// json_group_array(json_object(
// 'id', sd.id,
// 'pos', sd.pos,
// 'etymology', sd.etymology,
// 'confidence', sd.confidence,
// 'subsenses_data', sd.subsenses_data,
// 'examples_data', sd.examples_data,
// 'derivation_data', sd.derivation_data,
// 'categories_data', sd.categories_data
// ))
// FROM sense_data sd
// WHERE sd.parent_id = wts.word_id
// ) as senses_array
// FROM word_tone_sequences wts
// WHERE wts.tone_sequence LIKE ?
// AND wts.syllable_count = ?
// ORDER BY wts.frequency ASC NULLS LAST;
// `
|
