aboutsummaryrefslogtreecommitdiff
path: root/src/lutf8lib.js
blob: 6ebbec8100e358c4511f710c4394ae88e550aff1 (plain)
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
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
"use strict";

const assert  = require('assert');

const lua     = require('./lua.js');
const lapi    = require('./lapi.js');
const lauxlib = require('./lauxlib.js');

const MAXUNICODE = 0x10FFFF;

const iscont = function(p) {
    let c = p & 0xC0;
    return c === 0x80;
};

/* translate a relative string position: negative means back from end */
const u_posrelat = function(pos, len) {
    if (pos >= 0) return pos;
    else if (0 - pos > len) return 0;
    else return len + pos + 1;
};

/*
** Decode one UTF-8 sequence, returning NULL if byte sequence is invalid.
*/
const utf8_decode = function(s, val) {
    let limits = [0xFF, 0x7F, 0x7FF, 0xFFFF];
    let c = s[0];
    let res = 0;  /* final result */
    if (c < 0x80)  /* ascii? */
        res = c;
    else {
        let count = 0;  /* to count number of continuation bytes */
        while (c & 0x40) {  /* still have continuation bytes? */
            let cc = s[++count];  /* read next byte */
            if ((cc & 0xC0) != 0x80)  /* not a continuation byte? */
                return null;  /* invalid byte sequence */
            res = (res << 6) | (cc & 0x3F);  /* add lower 6 bits from cont. byte */
            c <<= 1;  /* to test next bit */
        }
        res |= ((c & 0x7F) << (count * 5));  /* add first byte */
        if (count > 3 || res > MAXUNICODE || res <= limits[count])
            return null;  /* invalid byte sequence */
        s = s.slice(count);  /* skip continuation bytes read */
    }

    return {
        string: s.slice(1),  /* +1 to include first byte */
        code: res
    };
};

const pushutfchar = function(L, arg) {
    let code = lauxlib.luaL_checkinteger(L, arg);
    lauxlib.luaL_argcheck(L, 0 <= code && code <= MAXUNICODE, arg, "value out of range");
    lapi.lua_pushstring(L, `${String.fromCharCode(code)}`);
};

/*
** utfchar(n1, n2, ...)  -> char(n1)..char(n2)...
*/
const utfchar = function(L) {
    let n = lapi.lua_gettop(L);  /* number of arguments */
    if (n === 1)  /* optimize common case of single char */
        pushutfchar(L, 1);
    else {
        let b = new lauxlib.luaL_Buffer();
        lauxlib.luaL_buffinit(L, b);
        for (let i = 1; i <= n; i++) {
            pushutfchar(L, i);
            lauxlib.luaL_addvalue(b);
        }
        lauxlib.luaL_pushresult(b);
    }
    return 1;
};

/*
** offset(s, n, [i])  -> index where n-th character counting from
**   position 'i' starts; 0 means character at 'i'.
*/
const byteoffset = function(L) {
    let s = lauxlib.luaL_checkstring(L, 1);
    s = L.stack[lapi.index2addr_(L, 1)].value;
    let n = lauxlib.luaL_checkinteger(L, 2);
    let posi = n >= 0 ? 1 : s.length + 1;
    posi = u_posrelat(lauxlib.luaL_optinteger(L, 3, posi), s.length);

    lauxlib.luaL_argcheck(L, 1 <= posi && --posi <= s.length, 3, "position ot ouf range");

    if (n === 0) {
        /* find beginning of current byte sequence */
        while (posi > 0 && iscont(s[posi])) posi--;
    } else {
        if (iscont(s[posi]))
            lauxlib.luaL_error(L, "initial position is a continuation byte");

        if (n < 0) {
            while (n < 0 && posi > 0) {  /* move back */
                do {  /* find beginning of previous character */
                    posi--;
                } while (posi > 0 && iscont(s[posi]));
                n++;
            }
        } else {
            n--;  /* do not move for 1st character */
            while (n > 0 && posi < s.length) {
                do {  /* find beginning of next character */
                    posi++;
                } while (iscont(s[posi]));  /* (cannot pass final '\0') */
                n--;
            }
        }
    }

    if (n === 0)  /* did it find given character? */
        lapi.lua_pushinteger(L, posi + 1);
    else  /* no such character */
        lapi.lua_pushnil(L);

    return 1;
};

/*
** codepoint(s, [i, [j]])  -> returns codepoints for all characters
** that start in the range [i,j]
*/
const codepoint = function(L) {
    let s = lauxlib.luaL_checkstring(L, 1);
    s = L.stack[lapi.index2addr_(L, 1)].value;
    let posi = u_posrelat(lauxlib.luaL_optinteger(L, 2, 1), s.length);
    let pose = u_posrelat(lauxlib.luaL_optinteger(L, 3, posi), s.length);

    lauxlib.luaL_argcheck(L, posi >= 1, 2, "out of range");
    lauxlib.luaL_argcheck(L, pose <= s.length, 3, "out of range");

    if (posi > pose) return 0;  /* empty interval; return no values */
    if (pose - posi >= Number.MAX_SAFE_INTEGER)
        return lauxlib.luaL_error(L, "string slice too long");
    let n = (pose - posi) + 1;
    lauxlib.luaL_checkstack(L, n, "string slice too long");
    n = 0;
    for (s = s.slice(posi - 1); n < pose - posi;) {
        let dec = utf8_decode(s);
        if (dec === null)
            return lauxlib.luaL_error(L, "invalid UTF-8 code");
        s = dec.string;
        let code = dec.code;
        lapi.lua_pushinteger(L, code);
        n++;
    }
    return n;
};

const funcs = {
    "char":      utfchar,
    "codepoint": codepoint,
    "offset":    byteoffset,
};

/* pattern to match a single UTF-8 character */
const UTF8PATT = "[\0-\x7F\xC2-\xF4][\x80-\xBF]*";

const luaopen_utf8 = function(L) {
    lauxlib.luaL_newlib(L, funcs);
    lapi.lua_pushstring(L, UTF8PATT);
    lapi.lua_setfield(L, -2, "charpattern");
    return 1;
};

module.exports.luaopen_utf8 = luaopen_utf8;