File size: 6,688 Bytes
bc20498 |
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 |
"use strict";
Object.defineProperty(exports, "__esModule", { value: true });
const boundaries_1 = require("./boundaries");
// BreakTypes
// @type {BreakType}
const NotBreak = 0;
const BreakStart = 1;
const Break = 2;
const BreakLastRegional = 3;
const BreakPenultimateRegional = 4;
class GraphemerHelper {
/**
* Check if the the character at the position {pos} of the string is surrogate
* @param str {string}
* @param pos {number}
* @returns {boolean}
*/
static isSurrogate(str, pos) {
return (0xd800 <= str.charCodeAt(pos) &&
str.charCodeAt(pos) <= 0xdbff &&
0xdc00 <= str.charCodeAt(pos + 1) &&
str.charCodeAt(pos + 1) <= 0xdfff);
}
/**
* The String.prototype.codePointAt polyfill
* Private function, gets a Unicode code point from a JavaScript UTF-16 string
* handling surrogate pairs appropriately
* @param str {string}
* @param idx {number}
* @returns {number}
*/
static codePointAt(str, idx) {
if (idx === undefined) {
idx = 0;
}
const code = str.charCodeAt(idx);
// if a high surrogate
if (0xd800 <= code && code <= 0xdbff && idx < str.length - 1) {
const hi = code;
const low = str.charCodeAt(idx + 1);
if (0xdc00 <= low && low <= 0xdfff) {
return (hi - 0xd800) * 0x400 + (low - 0xdc00) + 0x10000;
}
return hi;
}
// if a low surrogate
if (0xdc00 <= code && code <= 0xdfff && idx >= 1) {
const hi = str.charCodeAt(idx - 1);
const low = code;
if (0xd800 <= hi && hi <= 0xdbff) {
return (hi - 0xd800) * 0x400 + (low - 0xdc00) + 0x10000;
}
return low;
}
// just return the char if an unmatched surrogate half or a
// single-char codepoint
return code;
}
//
/**
* Private function, returns whether a break is allowed between the two given grapheme breaking classes
* Implemented the UAX #29 3.1.1 Grapheme Cluster Boundary Rules on extended grapheme clusters
* @param start {number}
* @param mid {Array<number>}
* @param end {number}
* @param startEmoji {number}
* @param midEmoji {Array<number>}
* @param endEmoji {number}
* @returns {number}
*/
static shouldBreak(start, mid, end, startEmoji, midEmoji, endEmoji) {
const all = [start].concat(mid).concat([end]);
const allEmoji = [startEmoji].concat(midEmoji).concat([endEmoji]);
const previous = all[all.length - 2];
const next = end;
const nextEmoji = endEmoji;
// Lookahead terminator for:
// GB12. ^ (RI RI)* RI ? RI
// GB13. [^RI] (RI RI)* RI ? RI
const rIIndex = all.lastIndexOf(boundaries_1.CLUSTER_BREAK.REGIONAL_INDICATOR);
if (rIIndex > 0 &&
all.slice(1, rIIndex).every(function (c) {
return c === boundaries_1.CLUSTER_BREAK.REGIONAL_INDICATOR;
}) &&
[boundaries_1.CLUSTER_BREAK.PREPEND, boundaries_1.CLUSTER_BREAK.REGIONAL_INDICATOR].indexOf(previous) === -1) {
if (all.filter(function (c) {
return c === boundaries_1.CLUSTER_BREAK.REGIONAL_INDICATOR;
}).length %
2 ===
1) {
return BreakLastRegional;
}
else {
return BreakPenultimateRegional;
}
}
// GB3. CR × LF
if (previous === boundaries_1.CLUSTER_BREAK.CR && next === boundaries_1.CLUSTER_BREAK.LF) {
return NotBreak;
}
// GB4. (Control|CR|LF) ÷
else if (previous === boundaries_1.CLUSTER_BREAK.CONTROL ||
previous === boundaries_1.CLUSTER_BREAK.CR ||
previous === boundaries_1.CLUSTER_BREAK.LF) {
return BreakStart;
}
// GB5. ÷ (Control|CR|LF)
else if (next === boundaries_1.CLUSTER_BREAK.CONTROL ||
next === boundaries_1.CLUSTER_BREAK.CR ||
next === boundaries_1.CLUSTER_BREAK.LF) {
return BreakStart;
}
// GB6. L × (L|V|LV|LVT)
else if (previous === boundaries_1.CLUSTER_BREAK.L &&
(next === boundaries_1.CLUSTER_BREAK.L ||
next === boundaries_1.CLUSTER_BREAK.V ||
next === boundaries_1.CLUSTER_BREAK.LV ||
next === boundaries_1.CLUSTER_BREAK.LVT)) {
return NotBreak;
}
// GB7. (LV|V) × (V|T)
else if ((previous === boundaries_1.CLUSTER_BREAK.LV || previous === boundaries_1.CLUSTER_BREAK.V) &&
(next === boundaries_1.CLUSTER_BREAK.V || next === boundaries_1.CLUSTER_BREAK.T)) {
return NotBreak;
}
// GB8. (LVT|T) × (T)
else if ((previous === boundaries_1.CLUSTER_BREAK.LVT || previous === boundaries_1.CLUSTER_BREAK.T) &&
next === boundaries_1.CLUSTER_BREAK.T) {
return NotBreak;
}
// GB9. × (Extend|ZWJ)
else if (next === boundaries_1.CLUSTER_BREAK.EXTEND || next === boundaries_1.CLUSTER_BREAK.ZWJ) {
return NotBreak;
}
// GB9a. × SpacingMark
else if (next === boundaries_1.CLUSTER_BREAK.SPACINGMARK) {
return NotBreak;
}
// GB9b. Prepend ×
else if (previous === boundaries_1.CLUSTER_BREAK.PREPEND) {
return NotBreak;
}
// GB11. \p{Extended_Pictographic} Extend* ZWJ × \p{Extended_Pictographic}
const previousNonExtendIndex = allEmoji
.slice(0, -1)
.lastIndexOf(boundaries_1.EXTENDED_PICTOGRAPHIC);
if (previousNonExtendIndex !== -1 &&
allEmoji[previousNonExtendIndex] === boundaries_1.EXTENDED_PICTOGRAPHIC &&
all.slice(previousNonExtendIndex + 1, -2).every(function (c) {
return c === boundaries_1.CLUSTER_BREAK.EXTEND;
}) &&
previous === boundaries_1.CLUSTER_BREAK.ZWJ &&
nextEmoji === boundaries_1.EXTENDED_PICTOGRAPHIC) {
return NotBreak;
}
// GB12. ^ (RI RI)* RI × RI
// GB13. [^RI] (RI RI)* RI × RI
if (mid.indexOf(boundaries_1.CLUSTER_BREAK.REGIONAL_INDICATOR) !== -1) {
return Break;
}
if (previous === boundaries_1.CLUSTER_BREAK.REGIONAL_INDICATOR &&
next === boundaries_1.CLUSTER_BREAK.REGIONAL_INDICATOR) {
return NotBreak;
}
// GB999. Any ? Any
return BreakStart;
}
}
exports.default = GraphemerHelper;
|