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
|
"use strict";
const cmn = require("../$common.js");
const fs = require("fs");
const path = require("path");
const https = require("https");
const fCODE = 0;
const fNAME = 1;
const fCATEGORY = 2;
// combining class, bidirectional category, decomposition mapping
const fDECDIGIT = 6;
const fDIGIT = 7;
const fNUMERIC = 8;
const fMIRRORED = 9;
const fOLDNAME = 10;
const fCOMMENT = 11;
const fUPPERCASE = 12;
const fLOWERCASE = 13;
const fTITLECASE = 14;
// db: Map(int => [Field]) (NAME is in uppercase)
let db = new Map();
// ranges: [{name: String, first: int, last: int}]
let ranges = [];
function importDatabase(csv) {
// clear the database if necessary
db = new Map();
ranges = [];
let currentRange = null;
let cursor = 0, endidx;
while ((endidx = csv.indexOf("\n", cursor)) != -1) {
const row = csv.slice(cursor, endidx).split(";");
cursor = endidx + 1;
const code = parseInt(row[fCODE], 16);
const m = row[fNAME].match(/^<(.*), (First|Last)>$/)
if (m != null) {
if (m[2] == "First") {
row[fNAME] = "<" + m[1] + ">";
currentRange = {name: m[1], first: code, last: null, row: row};
} else if (currentRange != null && m[1] == currentRange.name) {
currentRange.last = code;
ranges.push(currentRange);
currentRange = null;
}
} else {
row[fNAME] = row[fNAME].toUpperCase();
db.set(code, row);
}
}
}
function lookupCode(codepoint) {
for (const range of ranges) {
if (range.first <= codepoint && codepoint <= range.last) {
const row = range.row.slice();
row[fCODE] = codepoint.toString(16).toUpperCase();
return row;
}
}
return db.get(codepoint);
}
function searchDescription(text) {
text = text.toUpperCase();
const result = [];
for (const row of db.values()) {
if (row[fNAME].includes(text)) {
result.push(row);
if (result.length >= 200) break;
}
}
return result;
}
function recogniseIndex(text) {
let m;
m = text.match(/^([0-9]+)$/); // 1234
if (m) return lookupCode(parseInt(m[1], 10));
m = text.match(/^(?:0[Xx]|[Uu]\+)([0-9a-fA-F]+)$/); // 0x34ab / U+34ab
if (m) return lookupCode(parseInt(m[1], 16));
m = text.match(/^&#([0-9]+);$/); // Ӓ
if (m) return lookupCode(parseInt(m[1], 10));
m = text.match(/^&#[Xx]([0-9a-fA-F]+);$/); // 㒫
if (m) return lookupCode(parseInt(m[1], 16));
return null;
}
module.exports = function (app, io, moddir) {
const dataFilePath = path.join(moddir, "UnicodeData.txt");
if (fs.existsSync(dataFilePath)) {
importDatabase(fs.readFileSync(dataFilePath).toString());
} else {
console.log("Downloading UnicodeData.txt...");
https.get("https://www.unicode.org/Public/13.0.0/ucd/UnicodeData.txt", res => {
if (res.statusCode != 200) {
console.log(`Could not download UnicodeData.txt: status code ${res.statusCode}`);
return;
}
res.setEncoding("utf8");
let buffer = "";
res.on("data", data => buffer += data);
res.on("end", () => {
fs.writeFileSync(dataFilePath, buffer);
console.log("Downloaded UnicodeData.txt");
importDatabase(buffer);
});
}).on("error", err => {
console.log("Error downloading UnicodeData.txt:", err);
});
}
app.get("/unicode", (req, res) => {
res.sendFile(path.join(moddir, "index.html"));
});
app.get("/unicode/lookup/:query", (req, res) => {
const chars = [];
for (let codepoint of req.params.query) {
codepoint = codepoint.codePointAt(0);
chars.push(lookupCode(codepoint));
}
res.json({
index: recogniseIndex(req.params.query) || undefined,
chars: chars,
search: searchDescription(req.params.query),
});
});
};
|
