admin/cjk-autospace
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: 字符分類規則集抽象（charClass，可配置；向下兼容）

Browse Source 
把散落於各 pass 之硬編碼字符分類（中文 CJK／西文 ANS／全寬標點 BD_* 子類）統一抽象為
規則集 Ruleset：內置默認即現狀值，消費端經 options.charClass 擴充，以覆寫 spacing／
jiya／jinze 對特定字符之分類判定。

動機：英文全角句號 ．（U+FF0E，異於中文句號 。U+3002）實證為**完全未分類**——不被
charify、不挤壓、與 CJK 間不補隙。與其每次硬編碼補字符（如先前 € 之西文集），不如給
消費端可配置之分類鉤子。

API（追加語義）：
  charClass?: {
    cjk?: string;        // 追加為中文
    western?: string;    // 追加為西文（半寬標點亦歸此）
    biaodian?: { stop?, pause?, open?, close?, middle?, liga? };  // 追加為全寬標點，按子類
  }

實作：
- core/unicode.ts：新增 Ruleset／CharClassOverride／BdSubclass 型別、DEFAULT_RULESET、
  resolveRuleset（追加合併）；classifyBiaodian(ch, biaodian) 改吃規則集（預設參數向下兼容）。
- types.ts：JuzhenOptions.charClass；ResolvedOptions.ruleset；index 再匯出公開型別。
- index.ts：resolveRuleset(opts.charClass) → ResolvedOptions.ruleset。
- typeset/spacing.ts：所有 CJK／ANS 依賴正則移入 makeRules(ruleset)，per-instance 編譯
  （非每 block）；ALNUM／ALPHA／運算符等結構性 ASCII 仍為固定常數。
- typeset/jiya.ts：classifyBiaodian(ch, ruleset.biaodian)。
- typeset/jinze.ts：詞元邊界之 anyCjk 由 ruleset.cjk 建。

向下兼容：不傳 charClass 則 ruleset === DEFAULT_RULESET、行為與重構前完全一致。
v1 為追加語義，不支援重分類／移除內置字符（範圍式集合難挖洞、需求罕見，列後續）。

驗證：實 Chromium end-to-end——charClass.biaodian.stop="．" → ． charify 為 bd-stop
（开明式句末維持全角，比照 。）；western="★"／cjk="〇" → 與對側正確補／不補中西間隙。
測試 66 通過（含 9 條 charClass 新測——默認未分類／各子類 charify／實例隔離不可變
（resolveRuleset 不污染 DEFAULT）／追加不破壞內置／多子類組合；57 既有不變）。

- README「自定義字符分類」節＋ARCHITECTURE §4.2 規則集抽象。dist 重建。
This commit is contained in:
Commilitia
2026-06-04 16:22:14 +08:00
parent 5b9c6b5fa1
commit b821cd1134
14 changed files with 701 additions and 326 deletions
Download Patch File Download Diff File Expand all files Collapse all files
dist/core/unicode.d.ts
Vendored
+37 -3
View File
@@ -25,11 +25,45 @@ export declare const BD_MIDDLE = "\u00B7\u30FB\u2027";
export declare const BD_LIGA = "\u2026\u2014";
/** 全體標點字元（供 charify 走訪偵測）。 */
export declare const BD_ALL: string;
/** 全寬標點之六子類鍵。 */
export type BdSubclass = "stop" | "pause" | "open" | "close" | "middle" | "liga";
/**
* 將單一標點字元歸入其 bd-* 子類；非標點回傳 null。
* 供 jiya 之 charify 為 jz-char 標記 class。
* 字符分類規則集（§4.2）：把「中文／西文／全寬標點各子類」各表為 regex 字元類片段。
* 各 pass（spacing 之 CJK／ANS 正則、jiya 之 classifyBiaodian、jinze 之 anyCjk）皆由此
* 取分類，不再各自硬編碼。內置默認見 DEFAULT_RULESET；消費端經 options.charClass 擴充
* （resolveRuleset）。
*/
export declare function classifyBiaodian(ch: string): string | null;
export interface Ruleset {
/** 中文（CJK 表意／假名／注音等）——中西間隙之「中」側、禁則／justify 原子。 */
cjk: string;
/** 西文，CJK 之後可接隙者（含 @）。 */
ansAfter: string;
/** 西文，CJK 之前可接隙者（去 @）。 */
ansBefore: string;
/** 全寬標點，按子類——jiya charify／擠壓、禁則避頭尾、行端。 */
biaodian: Record<BdSubclass, string>;
}
/** 消費端字符分類覆寫（追加語義；見 README「自定義字符分類」）。 */
export interface CharClassOverride {
/** 追加為中文（CJK）。 */
cjk?: string;
/** 追加為西文（半寬標點亦歸此，按西文處理間隙）；併入 ansAfter／ansBefore。 */
western?: string;
/** 追加為全寬標點，按子類。 */
biaodian?: Partial<Record<BdSubclass, string>>;
}
/** 內置默認規則集（即現狀硬編碼值）。 */
export declare const DEFAULT_RULESET: Ruleset;
/**
* 合併消費端覆寫，回傳最終規則集。v1 為**追加**語義：把 override 字元併入內置對應類
* （未分類字符→歸類、新符號→納入）。不傳則回傳 DEFAULT_RULESET（零行為變更）。
*/
export declare function resolveRuleset(override?: CharClassOverride): Ruleset;
/**
* 將單一標點字元歸入其 bd-* 子類；非標點回傳 null。供 jiya charify 標記 class。
* biaodian 取自規則集（預設 DEFAULT_RULESET.biaodian，向下兼容無參數呼叫）。
*/
export declare function classifyBiaodian(ch: string, biaodian?: Record<BdSubclass, string>): string | null;
/** 全體 bd-* 子類名（DOM 端讀取 jz-char 之 bd class 用）。 */
export declare const BD_CLASS_NAMES: readonly ["bd-stop", "bd-pause", "bd-open", "bd-close", "bd-middle", "bd-liga"];
/**
dist/index.d.ts
Vendored
+1
View File
@@ -1,5 +1,6 @@
import type { JuzhenOptions, Pass, ResolvedOptions } from "./types.js";
export type { JuzhenOptions, ResolvedOptions, Pass };
export type { CharClassOverride, BdSubclass, Ruleset, Bias, BiasTable } from "./types.js";
export { createCjkAutospace } from "./compat/v1.js";
/** 正規化公開選項為內部 ResolvedOptions。 */
export declare function normalizeOptions(opts?: JuzhenOptions): ResolvedOptions;
dist/juzhen.iife.js
Vendored
+147 -101
View File
@@ -522,18 +522,52 @@ var Juzhen = (() => {
var BD_MIDDLE = "\xB7\u30FB\u2027";
var BD_LIGA = "\u2026\u2014";
var BD_ALL = BD_STOP + BD_PAUSE + BD_OPEN + BD_CLOSE + BD_MIDDLE + BD_LIGA;
var BD_SETS = [
["bd-stop", BD_STOP],
["bd-pause", BD_PAUSE],
["bd-open", BD_OPEN],
["bd-close", BD_CLOSE],
["bd-middle", BD_MIDDLE],
["bd-liga", BD_LIGA]
var BD_ORDER = [
"stop",
"pause",
"open",
"close",
"middle",
"liga"
];
function classifyBiaodian(ch) {
for (const [name, set] of BD_SETS) {
if (set.indexOf(ch) >= 0) {
return name;
var DEFAULT_RULESET = {
cjk: CJK,
ansAfter: ANS_AFTER_CJK,
ansBefore: ANS_BEFORE_CJK,
biaodian: {
stop: BD_STOP,
pause: BD_PAUSE,
open: BD_OPEN,
close: BD_CLOSE,
middle: BD_MIDDLE,
liga: BD_LIGA
}
};
function resolveRuleset(override) {
if (!override) {
return DEFAULT_RULESET;
}
const west = override.western || "";
const bd = { ...DEFAULT_RULESET.biaodian };
if (override.biaodian) {
for (const sub of BD_ORDER) {
const extra = override.biaodian[sub];
if (extra) {
bd[sub] = bd[sub] + extra;
}
}
}
return {
cjk: CJK + (override.cjk || ""),
ansAfter: ANS_AFTER_CJK + west,
ansBefore: ANS_BEFORE_CJK + west,
biaodian: bd
};
}
function classifyBiaodian(ch, biaodian = DEFAULT_RULESET.biaodian) {
for (const sub of BD_ORDER) {
if (biaodian[sub].indexOf(ch) >= 0) {
return "bd-" + sub;
}
}
return null;
@@ -642,9 +676,10 @@ var Juzhen = (() => {
let style = null;
let langClass = null;
const biasOverrides = ctx.options.jiyaConfig.bias;
const biaodian = ctx.options.ruleset.biaodian;
for (let i = 0; i < data.length; i += 1) {
const ch = data.charAt(i);
const bdClass = classifyBiaodian(ch);
const bdClass = classifyBiaodian(ch, biaodian);
if (!bdClass) {
continue;
}
@@ -737,46 +772,46 @@ var Juzhen = (() => {
}
return false;
}
function isTokenChar(ch) {
return !ANY_CJK.test(ch) && !/\s/.test(ch);
function isTokenChar(ch, anyCjk) {
return !anyCjk.test(ch) && !/\s/.test(ch);
}
function leadingTokenEnd(d) {
if (ANY_CJK.test(d.charAt(0))) {
function leadingTokenEnd(d, anyCjk) {
if (anyCjk.test(d.charAt(0))) {
return 1;
}
let e = 1;
while (e < d.length && isTokenChar(d.charAt(e))) {
while (e < d.length && isTokenChar(d.charAt(e), anyCjk)) {
e += 1;
}
return e;
}
function trailingTokenStart(d) {
function trailingTokenStart(d, anyCjk) {
const last = d.length - 1;
if (ANY_CJK.test(d.charAt(last))) {
if (anyCjk.test(d.charAt(last))) {
return last;
}
let s = last;
while (s > 0 && isTokenChar(d.charAt(s - 1))) {
while (s > 0 && isTokenChar(d.charAt(s - 1), anyCjk)) {
s -= 1;
}
return s;
}
function splitBoundaries(t, needFirst, needLast) {
function splitBoundaries(t, needFirst, needLast, anyCjk) {
let node = t;
if (needFirst) {
const e = leadingTokenEnd(node.data);
const e = leadingTokenEnd(node.data, anyCjk);
if (e < node.data.length) {
node = node.splitText(e);
}
}
if (needLast) {
const s = trailingTokenStart(node.data);
const s = trailingTokenStart(node.data, anyCjk);
if (s > 0) {
node.splitText(s);
}
}
}
function processParent(parent, finder) {
function processParent(parent, finder, anyCjk) {
for (let c = parent.firstChild; c; c = c.nextSibling) {
if (c.nodeType === 1 && c.nodeName === "JZ-JINZE") {
return;
@@ -806,7 +841,7 @@ var Juzhen = (() => {
const needFirst = i2 > 0 && forbidden[i2 - 1];
const needLast = i2 < n - 1 && forbidden[i2];
if (needFirst || needLast) {
splitBoundaries(u, needFirst, needLast);
splitBoundaries(u, needFirst, needLast, anyCjk);
}
}
const kids = [];
@@ -836,6 +871,7 @@ var Juzhen = (() => {
order: 40,
enabled: (o) => o.features.jinze,
render(ctx) {
const anyCjk = new RegExp("[" + ctx.options.ruleset.cjk + "]");
const parents = /* @__PURE__ */ new Set();
ctx.root.querySelectorAll("jz-char").forEach((c) => {
if (c.parentNode) {
@@ -843,7 +879,7 @@ var Juzhen = (() => {
}
});
for (const parent of parents) {
processParent(parent, ctx.finder);
processParent(parent, ctx.finder, anyCjk);
}
},
revert(ctx) {
@@ -1089,79 +1125,88 @@ var Juzhen = (() => {
var LBR_EXT = "\\(\\[\\{<>";
var RBR_EXT = "\\)\\]\\}<>";
var DEL = String.fromCharCode(57347);
var STRIP_CJK_SPACE_ANS = new RegExp("([" + CJK + "]) ([" + ANS_AFTER_CJK + "])", "g");
var STRIP_ANS_SPACE_CJK = new RegExp("([" + ANS_BEFORE_CJK + "]) ([" + CJK + "])", "g");
var STRIP_CJK_SPACE_CJK = new RegExp("([" + CJK + "]) (?=[" + CJK + "])", "g");
var DOTS_CJK = new RegExp("([\\.]{2,})([" + CJK + "])", "g");
var CJK_PUNCTUATION = new RegExp("([" + CJK + "])([!;,\\?:]+)(?=[" + CJK + ALNUM + "])", "g");
var AN_PUNCTUATION_CJK = new RegExp("([" + ALNUM + "])([!;,\\?]+)([" + CJK + "])", "g");
var CJK_TILDE = new RegExp("([" + CJK + "])(~+)(?!=)(?=[" + CJK + ALNUM + "])", "g");
var CJK_TILDE_EQUALS = new RegExp("([" + CJK + "])(~=)", "g");
var CJK_PERIOD = new RegExp("([" + CJK + "])(\\.)(?![" + ALNUM + "\\./])(?=[" + CJK + ALNUM + "])", "g");
var AN_PERIOD_CJK = new RegExp("([" + ALNUM + "])(\\.)([" + CJK + "])", "g");
var AN_COLON_CJK = new RegExp("([" + ALNUM + "])(:)([" + CJK + "])", "g");
var CJK_QUOTE = new RegExp("([" + CJK + "])([" + QUOTES_CLS + "])", "g");
var QUOTE_CJK = new RegExp("([" + QUOTES_CLS + "])([" + CJK + "])", "g");
var CJK_QUOTE_AN = new RegExp("([" + CJK + '])(")([' + ALNUM + "])", "g");
var CJK_HASH = new RegExp("([" + CJK + "])(#([^ ]))", "g");
var HASH_CJK = new RegExp("(([^ ])#)([" + CJK + "])", "g");
var SINGLE_LETTER_GRADE = new RegExp("\\b([" + ALPHA + "])([" + OPS_GRADE + "])([" + CJK + "])", "g");
var CJK_OPERATOR_ANS = new RegExp("([" + CJK + "])([" + OPS_HYPHEN + "])([" + ALNUM + "])", "g");
var ANS_OPERATOR_CJK = new RegExp("([" + ALNUM + "])([" + OPS_HYPHEN + "])([" + CJK + "])", "g");
var CJK_LESS_THAN = new RegExp("([" + CJK + "])(<)([" + ALNUM + "])", "g");
var LESS_THAN_CJK = new RegExp("([" + ALNUM + "])(<)([" + CJK + "])", "g");
var CJK_GREATER_THAN = new RegExp("([" + CJK + "])(>)([" + ALNUM + "])", "g");
var GREATER_THAN_CJK = new RegExp("([" + ALNUM + "])(>)([" + CJK + "])", "g");
var CJK_LEFT_BRACKET = new RegExp("([" + CJK + "])([" + LBR_EXT + "])", "g");
var RIGHT_BRACKET_CJK = new RegExp("([" + RBR_EXT + "])([" + CJK + "])", "g");
var AN_LEFT_BRACKET = new RegExp("([" + ALNUM + "])(?<!\\.[" + ALNUM + "]*)([" + LBR_BASIC + "])", "g");
var RIGHT_BRACKET_AN = new RegExp("([" + RBR_BASIC + "])([" + ALNUM + "])", "g");
var CJK_ANS = new RegExp("([" + CJK + "])([" + ANS_AFTER_CJK + "])", "g");
var ANS_CJK = new RegExp("([" + ANS_BEFORE_CJK + "])([" + CJK + "])", "g");
var S_A = new RegExp("(%)([" + ALPHA + "])", "g");
function makeRules(rs) {
const CJK2 = rs.cjk;
const ANS_AFTER = rs.ansAfter;
const ANS_BEFORE = rs.ansBefore;
return {
anyCjk: new RegExp("[" + CJK2 + "]"),
pillNeighbor: new RegExp("[" + ALNUM + CJK2 + "]"),
STRIP_CJK_SPACE_ANS: new RegExp("([" + CJK2 + "]) ([" + ANS_AFTER + "])", "g"),
STRIP_ANS_SPACE_CJK: new RegExp("([" + ANS_BEFORE + "]) ([" + CJK2 + "])", "g"),
STRIP_CJK_SPACE_CJK: new RegExp("([" + CJK2 + "]) (?=[" + CJK2 + "])", "g"),
DOTS_CJK: new RegExp("([\\.]{2,})([" + CJK2 + "])", "g"),
CJK_PUNCTUATION: new RegExp("([" + CJK2 + "])([!;,\\?:]+)(?=[" + CJK2 + ALNUM + "])", "g"),
AN_PUNCTUATION_CJK: new RegExp("([" + ALNUM + "])([!;,\\?]+)([" + CJK2 + "])", "g"),
CJK_TILDE: new RegExp("([" + CJK2 + "])(~+)(?!=)(?=[" + CJK2 + ALNUM + "])", "g"),
CJK_TILDE_EQUALS: new RegExp("([" + CJK2 + "])(~=)", "g"),
CJK_PERIOD: new RegExp("([" + CJK2 + "])(\\.)(?![" + ALNUM + "\\./])(?=[" + CJK2 + ALNUM + "])", "g"),
AN_PERIOD_CJK: new RegExp("([" + ALNUM + "])(\\.)([" + CJK2 + "])", "g"),
AN_COLON_CJK: new RegExp("([" + ALNUM + "])(:)([" + CJK2 + "])", "g"),
CJK_QUOTE: new RegExp("([" + CJK2 + "])([" + QUOTES_CLS + "])", "g"),
QUOTE_CJK: new RegExp("([" + QUOTES_CLS + "])([" + CJK2 + "])", "g"),
CJK_QUOTE_AN: new RegExp("([" + CJK2 + '])(")([' + ALNUM + "])", "g"),
CJK_HASH: new RegExp("([" + CJK2 + "])(#([^ ]))", "g"),
HASH_CJK: new RegExp("(([^ ])#)([" + CJK2 + "])", "g"),
SINGLE_LETTER_GRADE: new RegExp("\\b([" + ALPHA + "])([" + OPS_GRADE + "])([" + CJK2 + "])", "g"),
CJK_OPERATOR_ANS: new RegExp("([" + CJK2 + "])([" + OPS_HYPHEN + "])([" + ALNUM + "])", "g"),
ANS_OPERATOR_CJK: new RegExp("([" + ALNUM + "])([" + OPS_HYPHEN + "])([" + CJK2 + "])", "g"),
CJK_LESS_THAN: new RegExp("([" + CJK2 + "])(<)([" + ALNUM + "])", "g"),
LESS_THAN_CJK: new RegExp("([" + ALNUM + "])(<)([" + CJK2 + "])", "g"),
CJK_GREATER_THAN: new RegExp("([" + CJK2 + "])(>)([" + ALNUM + "])", "g"),
GREATER_THAN_CJK: new RegExp("([" + ALNUM + "])(>)([" + CJK2 + "])", "g"),
CJK_LEFT_BRACKET: new RegExp("([" + CJK2 + "])([" + LBR_EXT + "])", "g"),
RIGHT_BRACKET_CJK: new RegExp("([" + RBR_EXT + "])([" + CJK2 + "])", "g"),
AN_LEFT_BRACKET: new RegExp("([" + ALNUM + "])(?<!\\.[" + ALNUM + "]*)([" + LBR_BASIC + "])", "g"),
RIGHT_BRACKET_AN: new RegExp("([" + RBR_BASIC + "])([" + ALNUM + "])", "g"),
CJK_ANS: new RegExp("([" + CJK2 + "])([" + ANS_AFTER + "])", "g"),
ANS_CJK: new RegExp("([" + ANS_BEFORE + "])([" + CJK2 + "])", "g"),
S_A: new RegExp("(%)([" + ALPHA + "])", "g")
};
}
var COMPOUND_WORD = /\b(?:[A-Za-z0-9]*[a-z][A-Za-z0-9]*-[A-Za-z0-9]+|[A-Za-z0-9]+-[A-Za-z0-9]*[a-z][A-Za-z0-9]*|[A-Za-z]+-[0-9]+|[A-Za-z]+[0-9]+-[A-Za-z0-9]+)(?:-[A-Za-z0-9]+)*\b/g;
var PH_PATTERN = new RegExp(PH_OPEN + "(\\d+)" + PH_CLOSE, "g");
function panguSpace(text) {
if (text.length <= 1 || !ANY_CJK.test(text)) {
function panguSpace(text, R) {
if (text.length <= 1 || !R.anyCjk.test(text)) {
return text;
}
let s = text;
s = s.replace(STRIP_CJK_SPACE_ANS, "$1$2");
s = s.replace(STRIP_ANS_SPACE_CJK, "$1$2");
s = s.replace(STRIP_CJK_SPACE_CJK, "$1" + DEL);
s = s.replace(DOTS_CJK, "$1" + MARK + "$2");
s = s.replace(CJK_PUNCTUATION, "$1$2" + MARK);
s = s.replace(AN_PUNCTUATION_CJK, "$1$2" + MARK + "$3");
s = s.replace(CJK_TILDE, "$1$2" + MARK);
s = s.replace(CJK_TILDE_EQUALS, "$1" + MARK + "$2" + MARK);
s = s.replace(CJK_PERIOD, "$1$2" + MARK);
s = s.replace(AN_PERIOD_CJK, "$1$2" + MARK + "$3");
s = s.replace(AN_COLON_CJK, "$1$2" + MARK + "$3");
s = s.replace(CJK_QUOTE, "$1" + MARK + "$2");
s = s.replace(QUOTE_CJK, "$1" + MARK + "$2");
s = s.replace(CJK_QUOTE_AN, "$1$2" + MARK + "$3");
s = s.replace(CJK_HASH, "$1" + MARK + "$2");
s = s.replace(HASH_CJK, "$1" + MARK + "$3");
s = s.replace(R.STRIP_CJK_SPACE_ANS, "$1$2");
s = s.replace(R.STRIP_ANS_SPACE_CJK, "$1$2");
s = s.replace(R.STRIP_CJK_SPACE_CJK, "$1" + DEL);
s = s.replace(R.DOTS_CJK, "$1" + MARK + "$2");
s = s.replace(R.CJK_PUNCTUATION, "$1$2" + MARK);
s = s.replace(R.AN_PUNCTUATION_CJK, "$1$2" + MARK + "$3");
s = s.replace(R.CJK_TILDE, "$1$2" + MARK);
s = s.replace(R.CJK_TILDE_EQUALS, "$1" + MARK + "$2" + MARK);
s = s.replace(R.CJK_PERIOD, "$1$2" + MARK);
s = s.replace(R.AN_PERIOD_CJK, "$1$2" + MARK + "$3");
s = s.replace(R.AN_COLON_CJK, "$1$2" + MARK + "$3");
s = s.replace(R.CJK_QUOTE, "$1" + MARK + "$2");
s = s.replace(R.QUOTE_CJK, "$1" + MARK + "$2");
s = s.replace(R.CJK_QUOTE_AN, "$1$2" + MARK + "$3");
s = s.replace(R.CJK_HASH, "$1" + MARK + "$2");
s = s.replace(R.HASH_CJK, "$1" + MARK + "$3");
const compounds = [];
s = s.replace(COMPOUND_WORD, (m) => {
compounds.push(m);
return PH_OPEN + (compounds.length - 1) + PH_CLOSE;
});
s = s.replace(SINGLE_LETTER_GRADE, "$1$2" + MARK + "$3");
s = s.replace(CJK_OPERATOR_ANS, "$1" + MARK + "$2" + MARK + "$3");
s = s.replace(ANS_OPERATOR_CJK, "$1" + MARK + "$2" + MARK + "$3");
s = s.replace(CJK_LESS_THAN, "$1" + MARK + "$2" + MARK + "$3");
s = s.replace(LESS_THAN_CJK, "$1" + MARK + "$2" + MARK + "$3");
s = s.replace(CJK_GREATER_THAN, "$1" + MARK + "$2" + MARK + "$3");
s = s.replace(GREATER_THAN_CJK, "$1" + MARK + "$2" + MARK + "$3");
s = s.replace(R.SINGLE_LETTER_GRADE, "$1$2" + MARK + "$3");
s = s.replace(R.CJK_OPERATOR_ANS, "$1" + MARK + "$2" + MARK + "$3");
s = s.replace(R.ANS_OPERATOR_CJK, "$1" + MARK + "$2" + MARK + "$3");
s = s.replace(R.CJK_LESS_THAN, "$1" + MARK + "$2" + MARK + "$3");
s = s.replace(R.LESS_THAN_CJK, "$1" + MARK + "$2" + MARK + "$3");
s = s.replace(R.CJK_GREATER_THAN, "$1" + MARK + "$2" + MARK + "$3");
s = s.replace(R.GREATER_THAN_CJK, "$1" + MARK + "$2" + MARK + "$3");
s = s.replace(PH_PATTERN, (_m, idx) => compounds[Number(idx)] || "");
s = s.replace(CJK_LEFT_BRACKET, "$1" + MARK + "$2");
s = s.replace(RIGHT_BRACKET_CJK, "$1" + MARK + "$2");
s = s.replace(AN_LEFT_BRACKET, "$1" + MARK + "$2");
s = s.replace(RIGHT_BRACKET_AN, "$1" + MARK + "$2");
s = s.replace(CJK_ANS, "$1" + MARK + "$2");
s = s.replace(ANS_CJK, "$1" + MARK + "$2");
s = s.replace(S_A, "$1" + MARK + "$2");
s = s.replace(R.CJK_LEFT_BRACKET, "$1" + MARK + "$2");
s = s.replace(R.RIGHT_BRACKET_CJK, "$1" + MARK + "$2");
s = s.replace(R.AN_LEFT_BRACKET, "$1" + MARK + "$2");
s = s.replace(R.RIGHT_BRACKET_AN, "$1" + MARK + "$2");
s = s.replace(R.CJK_ANS, "$1" + MARK + "$2");
s = s.replace(R.ANS_CJK, "$1" + MARK + "$2");
s = s.replace(R.S_A, "$1" + MARK + "$2");
return s;
}
function wrapNodeInGap(node) {
@@ -1186,11 +1231,11 @@ var Juzhen = (() => {
}
wrapNodeInGap(tn);
}
function processBlock(block, finder) {
function processBlock(block, finder, R) {
const runs = finder.collectRuns(block);
for (const run of runs) {
const { text, map } = run;
const spaced = panguSpace(text);
const spaced = panguSpace(text, R);
if (spaced === text) {
continue;
}
@@ -1231,8 +1276,7 @@ var Juzhen = (() => {
}
}
}
var PILL_NEIGHBOR = new RegExp("[A-Za-z0-9" + CJK + "]");
function processPills(root, finder, pillSelector) {
function processPills(root, finder, pillSelector, pillNeighbor) {
root.querySelectorAll(pillSelector).forEach((pill) => {
if (finder.isAvoided(pill) || !finder.inScope(pill)) {
return;
@@ -1242,36 +1286,36 @@ var Juzhen = (() => {
}
const prev = finder.adjacentLogicalChar(pill, -1);
if (prev) {
handlePillSide(prev, pill, -1);
handlePillSide(prev, pill, -1, pillNeighbor);
}
const next = finder.adjacentLogicalChar(pill, 1);
if (next) {
handlePillSide(next, pill, 1);
handlePillSide(next, pill, 1, pillNeighbor);
}
});
}
function handlePillSide(adj, pill, dir) {
function handlePillSide(adj, pill, dir, pillNeighbor) {
if (dir === -1) {
if (PILL_NEIGHBOR.test(adj.ch)) {
if (pillNeighbor.test(adj.ch)) {
wrapGapLeft({ textNode: adj.textNode, offset: adj.offset });
return;
}
if (adj.ch === " " && adj.offset >= 1) {
const tn = adj.textNode;
const bc = tn.data.charAt(adj.offset - 1);
if (bc !== " " && PILL_NEIGHBOR.test(bc)) {
if (bc !== " " && pillNeighbor.test(bc)) {
tn.data = tn.data.slice(0, adj.offset) + tn.data.slice(adj.offset + 1);
wrapGapLeft({ textNode: tn, offset: adj.offset - 1 });
}
}
} else {
if (PILL_NEIGHBOR.test(adj.ch)) {
if (pillNeighbor.test(adj.ch)) {
wrapNodeInGap(pill);
return;
}
if (adj.ch === " " && adj.textNode.data.length >= 2) {
const ac = adj.textNode.data.charAt(1);
if (ac !== " " && PILL_NEIGHBOR.test(ac)) {
if (ac !== " " && pillNeighbor.test(ac)) {
adj.textNode.data = adj.textNode.data.slice(1);
wrapNodeInGap(pill);
}
@@ -1285,13 +1329,14 @@ var Juzhen = (() => {
enabled: (o) => o.features.spacing,
render(ctx) {
const { finder, options } = ctx;
const R = makeRules(options.ruleset);
ctx.finder.eachBlock(ctx.root, (block) => {
if (!finder.featureEnabledFor(block, PASS4)) {
return;
}
processBlock(block, finder);
processBlock(block, finder, R);
});
processPills(ctx.root, finder, options.finder.pillSelector);
processPills(ctx.root, finder, options.finder.pillSelector, R.pillNeighbor);
},
revert(ctx) {
revertPass(PASS4, ctx.root);
@@ -1482,6 +1527,7 @@ var Juzhen = (() => {
...langOpt.style ? { style: langOpt.style } : {},
policy: langOpt.policy || {}
},
ruleset: resolveRuleset(opts.charClass),
autospaceClass: opts.autospaceClass || "",
justifyAtoms: opts.justifyAtoms === false ? false : true,
scope: {
dist/juzhen.mjs
Vendored
+147 -101
View File
@@ -494,18 +494,52 @@ var BD_CLOSE = "\u300D\u300F\uFF09\u300B\u3009\u3011\u3017\u3015\uFF3D\uFF5D\u20
var BD_MIDDLE = "\xB7\u30FB\u2027";
var BD_LIGA = "\u2026\u2014";
var BD_ALL = BD_STOP + BD_PAUSE + BD_OPEN + BD_CLOSE + BD_MIDDLE + BD_LIGA;
var BD_SETS = [
["bd-stop", BD_STOP],
["bd-pause", BD_PAUSE],
["bd-open", BD_OPEN],
["bd-close", BD_CLOSE],
["bd-middle", BD_MIDDLE],
["bd-liga", BD_LIGA]
var BD_ORDER = [
"stop",
"pause",
"open",
"close",
"middle",
"liga"
];
function classifyBiaodian(ch) {
for (const [name, set] of BD_SETS) {
if (set.indexOf(ch) >= 0) {
return name;
var DEFAULT_RULESET = {
cjk: CJK,
ansAfter: ANS_AFTER_CJK,
ansBefore: ANS_BEFORE_CJK,
biaodian: {
stop: BD_STOP,
pause: BD_PAUSE,
open: BD_OPEN,
close: BD_CLOSE,
middle: BD_MIDDLE,
liga: BD_LIGA
}
};
function resolveRuleset(override) {
if (!override) {
return DEFAULT_RULESET;
}
const west = override.western || "";
const bd = { ...DEFAULT_RULESET.biaodian };
if (override.biaodian) {
for (const sub of BD_ORDER) {
const extra = override.biaodian[sub];
if (extra) {
bd[sub] = bd[sub] + extra;
}
}
}
return {
cjk: CJK + (override.cjk || ""),
ansAfter: ANS_AFTER_CJK + west,
ansBefore: ANS_BEFORE_CJK + west,
biaodian: bd
};
}
function classifyBiaodian(ch, biaodian = DEFAULT_RULESET.biaodian) {
for (const sub of BD_ORDER) {
if (biaodian[sub].indexOf(ch) >= 0) {
return "bd-" + sub;
}
}
return null;
@@ -614,9 +648,10 @@ var jiyaPass = {
let style = null;
let langClass = null;
const biasOverrides = ctx.options.jiyaConfig.bias;
const biaodian = ctx.options.ruleset.biaodian;
for (let i = 0; i < data.length; i += 1) {
const ch = data.charAt(i);
const bdClass = classifyBiaodian(ch);
const bdClass = classifyBiaodian(ch, biaodian);
if (!bdClass) {
continue;
}
@@ -709,46 +744,46 @@ function forbiddenBreak(a, b, finder) {
}
return false;
}
function isTokenChar(ch) {
return !ANY_CJK.test(ch) && !/\s/.test(ch);
function isTokenChar(ch, anyCjk) {
return !anyCjk.test(ch) && !/\s/.test(ch);
}
function leadingTokenEnd(d) {
if (ANY_CJK.test(d.charAt(0))) {
function leadingTokenEnd(d, anyCjk) {
if (anyCjk.test(d.charAt(0))) {
return 1;
}
let e = 1;
while (e < d.length && isTokenChar(d.charAt(e))) {
while (e < d.length && isTokenChar(d.charAt(e), anyCjk)) {
e += 1;
}
return e;
}
function trailingTokenStart(d) {
function trailingTokenStart(d, anyCjk) {
const last = d.length - 1;
if (ANY_CJK.test(d.charAt(last))) {
if (anyCjk.test(d.charAt(last))) {
return last;
}
let s = last;
while (s > 0 && isTokenChar(d.charAt(s - 1))) {
while (s > 0 && isTokenChar(d.charAt(s - 1), anyCjk)) {
s -= 1;
}
return s;
}
function splitBoundaries(t, needFirst, needLast) {
function splitBoundaries(t, needFirst, needLast, anyCjk) {
let node = t;
if (needFirst) {
const e = leadingTokenEnd(node.data);
const e = leadingTokenEnd(node.data, anyCjk);
if (e < node.data.length) {
node = node.splitText(e);
}
}
if (needLast) {
const s = trailingTokenStart(node.data);
const s = trailingTokenStart(node.data, anyCjk);
if (s > 0) {
node.splitText(s);
}
}
}
function processParent(parent, finder) {
function processParent(parent, finder, anyCjk) {
for (let c = parent.firstChild; c; c = c.nextSibling) {
if (c.nodeType === 1 && c.nodeName === "JZ-JINZE") {
return;
@@ -778,7 +813,7 @@ function processParent(parent, finder) {
const needFirst = i2 > 0 && forbidden[i2 - 1];
const needLast = i2 < n - 1 && forbidden[i2];
if (needFirst || needLast) {
splitBoundaries(u, needFirst, needLast);
splitBoundaries(u, needFirst, needLast, anyCjk);
}
}
const kids = [];
@@ -808,6 +843,7 @@ var jinzePass = {
order: 40,
enabled: (o) => o.features.jinze,
render(ctx) {
const anyCjk = new RegExp("[" + ctx.options.ruleset.cjk + "]");
const parents = /* @__PURE__ */ new Set();
ctx.root.querySelectorAll("jz-char").forEach((c) => {
if (c.parentNode) {
@@ -815,7 +851,7 @@ var jinzePass = {
}
});
for (const parent of parents) {
processParent(parent, ctx.finder);
processParent(parent, ctx.finder, anyCjk);
}
},
revert(ctx) {
@@ -1061,79 +1097,88 @@ var RBR_BASIC = "\\)\\]\\}";
var LBR_EXT = "\\(\\[\\{<>";
var RBR_EXT = "\\)\\]\\}<>";
var DEL = String.fromCharCode(57347);
var STRIP_CJK_SPACE_ANS = new RegExp("([" + CJK + "]) ([" + ANS_AFTER_CJK + "])", "g");
var STRIP_ANS_SPACE_CJK = new RegExp("([" + ANS_BEFORE_CJK + "]) ([" + CJK + "])", "g");
var STRIP_CJK_SPACE_CJK = new RegExp("([" + CJK + "]) (?=[" + CJK + "])", "g");
var DOTS_CJK = new RegExp("([\\.]{2,})([" + CJK + "])", "g");
var CJK_PUNCTUATION = new RegExp("([" + CJK + "])([!;,\\?:]+)(?=[" + CJK + ALNUM + "])", "g");
var AN_PUNCTUATION_CJK = new RegExp("([" + ALNUM + "])([!;,\\?]+)([" + CJK + "])", "g");
var CJK_TILDE = new RegExp("([" + CJK + "])(~+)(?!=)(?=[" + CJK + ALNUM + "])", "g");
var CJK_TILDE_EQUALS = new RegExp("([" + CJK + "])(~=)", "g");
var CJK_PERIOD = new RegExp("([" + CJK + "])(\\.)(?![" + ALNUM + "\\./])(?=[" + CJK + ALNUM + "])", "g");
var AN_PERIOD_CJK = new RegExp("([" + ALNUM + "])(\\.)([" + CJK + "])", "g");
var AN_COLON_CJK = new RegExp("([" + ALNUM + "])(:)([" + CJK + "])", "g");
var CJK_QUOTE = new RegExp("([" + CJK + "])([" + QUOTES_CLS + "])", "g");
var QUOTE_CJK = new RegExp("([" + QUOTES_CLS + "])([" + CJK + "])", "g");
var CJK_QUOTE_AN = new RegExp("([" + CJK + '])(")([' + ALNUM + "])", "g");
var CJK_HASH = new RegExp("([" + CJK + "])(#([^ ]))", "g");
var HASH_CJK = new RegExp("(([^ ])#)([" + CJK + "])", "g");
var SINGLE_LETTER_GRADE = new RegExp("\\b([" + ALPHA + "])([" + OPS_GRADE + "])([" + CJK + "])", "g");
var CJK_OPERATOR_ANS = new RegExp("([" + CJK + "])([" + OPS_HYPHEN + "])([" + ALNUM + "])", "g");
var ANS_OPERATOR_CJK = new RegExp("([" + ALNUM + "])([" + OPS_HYPHEN + "])([" + CJK + "])", "g");
var CJK_LESS_THAN = new RegExp("([" + CJK + "])(<)([" + ALNUM + "])", "g");
var LESS_THAN_CJK = new RegExp("([" + ALNUM + "])(<)([" + CJK + "])", "g");
var CJK_GREATER_THAN = new RegExp("([" + CJK + "])(>)([" + ALNUM + "])", "g");
var GREATER_THAN_CJK = new RegExp("([" + ALNUM + "])(>)([" + CJK + "])", "g");
var CJK_LEFT_BRACKET = new RegExp("([" + CJK + "])([" + LBR_EXT + "])", "g");
var RIGHT_BRACKET_CJK = new RegExp("([" + RBR_EXT + "])([" + CJK + "])", "g");
var AN_LEFT_BRACKET = new RegExp("([" + ALNUM + "])(?<!\\.[" + ALNUM + "]*)([" + LBR_BASIC + "])", "g");
var RIGHT_BRACKET_AN = new RegExp("([" + RBR_BASIC + "])([" + ALNUM + "])", "g");
var CJK_ANS = new RegExp("([" + CJK + "])([" + ANS_AFTER_CJK + "])", "g");
var ANS_CJK = new RegExp("([" + ANS_BEFORE_CJK + "])([" + CJK + "])", "g");
var S_A = new RegExp("(%)([" + ALPHA + "])", "g");
function makeRules(rs) {
const CJK2 = rs.cjk;
const ANS_AFTER = rs.ansAfter;
const ANS_BEFORE = rs.ansBefore;
return {
anyCjk: new RegExp("[" + CJK2 + "]"),
pillNeighbor: new RegExp("[" + ALNUM + CJK2 + "]"),
STRIP_CJK_SPACE_ANS: new RegExp("([" + CJK2 + "]) ([" + ANS_AFTER + "])", "g"),
STRIP_ANS_SPACE_CJK: new RegExp("([" + ANS_BEFORE + "]) ([" + CJK2 + "])", "g"),
STRIP_CJK_SPACE_CJK: new RegExp("([" + CJK2 + "]) (?=[" + CJK2 + "])", "g"),
DOTS_CJK: new RegExp("([\\.]{2,})([" + CJK2 + "])", "g"),
CJK_PUNCTUATION: new RegExp("([" + CJK2 + "])([!;,\\?:]+)(?=[" + CJK2 + ALNUM + "])", "g"),
AN_PUNCTUATION_CJK: new RegExp("([" + ALNUM + "])([!;,\\?]+)([" + CJK2 + "])", "g"),
CJK_TILDE: new RegExp("([" + CJK2 + "])(~+)(?!=)(?=[" + CJK2 + ALNUM + "])", "g"),
CJK_TILDE_EQUALS: new RegExp("([" + CJK2 + "])(~=)", "g"),
CJK_PERIOD: new RegExp("([" + CJK2 + "])(\\.)(?![" + ALNUM + "\\./])(?=[" + CJK2 + ALNUM + "])", "g"),
AN_PERIOD_CJK: new RegExp("([" + ALNUM + "])(\\.)([" + CJK2 + "])", "g"),
AN_COLON_CJK: new RegExp("([" + ALNUM + "])(:)([" + CJK2 + "])", "g"),
CJK_QUOTE: new RegExp("([" + CJK2 + "])([" + QUOTES_CLS + "])", "g"),
QUOTE_CJK: new RegExp("([" + QUOTES_CLS + "])([" + CJK2 + "])", "g"),
CJK_QUOTE_AN: new RegExp("([" + CJK2 + '])(")([' + ALNUM + "])", "g"),
CJK_HASH: new RegExp("([" + CJK2 + "])(#([^ ]))", "g"),
HASH_CJK: new RegExp("(([^ ])#)([" + CJK2 + "])", "g"),
SINGLE_LETTER_GRADE: new RegExp("\\b([" + ALPHA + "])([" + OPS_GRADE + "])([" + CJK2 + "])", "g"),
CJK_OPERATOR_ANS: new RegExp("([" + CJK2 + "])([" + OPS_HYPHEN + "])([" + ALNUM + "])", "g"),
ANS_OPERATOR_CJK: new RegExp("([" + ALNUM + "])([" + OPS_HYPHEN + "])([" + CJK2 + "])", "g"),
CJK_LESS_THAN: new RegExp("([" + CJK2 + "])(<)([" + ALNUM + "])", "g"),
LESS_THAN_CJK: new RegExp("([" + ALNUM + "])(<)([" + CJK2 + "])", "g"),
CJK_GREATER_THAN: new RegExp("([" + CJK2 + "])(>)([" + ALNUM + "])", "g"),
GREATER_THAN_CJK: new RegExp("([" + ALNUM + "])(>)([" + CJK2 + "])", "g"),
CJK_LEFT_BRACKET: new RegExp("([" + CJK2 + "])([" + LBR_EXT + "])", "g"),
RIGHT_BRACKET_CJK: new RegExp("([" + RBR_EXT + "])([" + CJK2 + "])", "g"),
AN_LEFT_BRACKET: new RegExp("([" + ALNUM + "])(?<!\\.[" + ALNUM + "]*)([" + LBR_BASIC + "])", "g"),
RIGHT_BRACKET_AN: new RegExp("([" + RBR_BASIC + "])([" + ALNUM + "])", "g"),
CJK_ANS: new RegExp("([" + CJK2 + "])([" + ANS_AFTER + "])", "g"),
ANS_CJK: new RegExp("([" + ANS_BEFORE + "])([" + CJK2 + "])", "g"),
S_A: new RegExp("(%)([" + ALPHA + "])", "g")
};
}
var COMPOUND_WORD = /\b(?:[A-Za-z0-9]*[a-z][A-Za-z0-9]*-[A-Za-z0-9]+|[A-Za-z0-9]+-[A-Za-z0-9]*[a-z][A-Za-z0-9]*|[A-Za-z]+-[0-9]+|[A-Za-z]+[0-9]+-[A-Za-z0-9]+)(?:-[A-Za-z0-9]+)*\b/g;
var PH_PATTERN = new RegExp(PH_OPEN + "(\\d+)" + PH_CLOSE, "g");
function panguSpace(text) {
if (text.length <= 1 || !ANY_CJK.test(text)) {
function panguSpace(text, R) {
if (text.length <= 1 || !R.anyCjk.test(text)) {
return text;
}
let s = text;
s = s.replace(STRIP_CJK_SPACE_ANS, "$1$2");
s = s.replace(STRIP_ANS_SPACE_CJK, "$1$2");
s = s.replace(STRIP_CJK_SPACE_CJK, "$1" + DEL);
s = s.replace(DOTS_CJK, "$1" + MARK + "$2");
s = s.replace(CJK_PUNCTUATION, "$1$2" + MARK);
s = s.replace(AN_PUNCTUATION_CJK, "$1$2" + MARK + "$3");
s = s.replace(CJK_TILDE, "$1$2" + MARK);
s = s.replace(CJK_TILDE_EQUALS, "$1" + MARK + "$2" + MARK);
s = s.replace(CJK_PERIOD, "$1$2" + MARK);
s = s.replace(AN_PERIOD_CJK, "$1$2" + MARK + "$3");
s = s.replace(AN_COLON_CJK, "$1$2" + MARK + "$3");
s = s.replace(CJK_QUOTE, "$1" + MARK + "$2");
s = s.replace(QUOTE_CJK, "$1" + MARK + "$2");
s = s.replace(CJK_QUOTE_AN, "$1$2" + MARK + "$3");
s = s.replace(CJK_HASH, "$1" + MARK + "$2");
s = s.replace(HASH_CJK, "$1" + MARK + "$3");
s = s.replace(R.STRIP_CJK_SPACE_ANS, "$1$2");
s = s.replace(R.STRIP_ANS_SPACE_CJK, "$1$2");
s = s.replace(R.STRIP_CJK_SPACE_CJK, "$1" + DEL);
s = s.replace(R.DOTS_CJK, "$1" + MARK + "$2");
s = s.replace(R.CJK_PUNCTUATION, "$1$2" + MARK);
s = s.replace(R.AN_PUNCTUATION_CJK, "$1$2" + MARK + "$3");
s = s.replace(R.CJK_TILDE, "$1$2" + MARK);
s = s.replace(R.CJK_TILDE_EQUALS, "$1" + MARK + "$2" + MARK);
s = s.replace(R.CJK_PERIOD, "$1$2" + MARK);
s = s.replace(R.AN_PERIOD_CJK, "$1$2" + MARK + "$3");
s = s.replace(R.AN_COLON_CJK, "$1$2" + MARK + "$3");
s = s.replace(R.CJK_QUOTE, "$1" + MARK + "$2");
s = s.replace(R.QUOTE_CJK, "$1" + MARK + "$2");
s = s.replace(R.CJK_QUOTE_AN, "$1$2" + MARK + "$3");
s = s.replace(R.CJK_HASH, "$1" + MARK + "$2");
s = s.replace(R.HASH_CJK, "$1" + MARK + "$3");
const compounds = [];
s = s.replace(COMPOUND_WORD, (m) => {
compounds.push(m);
return PH_OPEN + (compounds.length - 1) + PH_CLOSE;
});
s = s.replace(SINGLE_LETTER_GRADE, "$1$2" + MARK + "$3");
s = s.replace(CJK_OPERATOR_ANS, "$1" + MARK + "$2" + MARK + "$3");
s = s.replace(ANS_OPERATOR_CJK, "$1" + MARK + "$2" + MARK + "$3");
s = s.replace(CJK_LESS_THAN, "$1" + MARK + "$2" + MARK + "$3");
s = s.replace(LESS_THAN_CJK, "$1" + MARK + "$2" + MARK + "$3");
s = s.replace(CJK_GREATER_THAN, "$1" + MARK + "$2" + MARK + "$3");
s = s.replace(GREATER_THAN_CJK, "$1" + MARK + "$2" + MARK + "$3");
s = s.replace(R.SINGLE_LETTER_GRADE, "$1$2" + MARK + "$3");
s = s.replace(R.CJK_OPERATOR_ANS, "$1" + MARK + "$2" + MARK + "$3");
s = s.replace(R.ANS_OPERATOR_CJK, "$1" + MARK + "$2" + MARK + "$3");
s = s.replace(R.CJK_LESS_THAN, "$1" + MARK + "$2" + MARK + "$3");
s = s.replace(R.LESS_THAN_CJK, "$1" + MARK + "$2" + MARK + "$3");
s = s.replace(R.CJK_GREATER_THAN, "$1" + MARK + "$2" + MARK + "$3");
s = s.replace(R.GREATER_THAN_CJK, "$1" + MARK + "$2" + MARK + "$3");
s = s.replace(PH_PATTERN, (_m, idx) => compounds[Number(idx)] || "");
s = s.replace(CJK_LEFT_BRACKET, "$1" + MARK + "$2");
s = s.replace(RIGHT_BRACKET_CJK, "$1" + MARK + "$2");
s = s.replace(AN_LEFT_BRACKET, "$1" + MARK + "$2");
s = s.replace(RIGHT_BRACKET_AN, "$1" + MARK + "$2");
s = s.replace(CJK_ANS, "$1" + MARK + "$2");
s = s.replace(ANS_CJK, "$1" + MARK + "$2");
s = s.replace(S_A, "$1" + MARK + "$2");
s = s.replace(R.CJK_LEFT_BRACKET, "$1" + MARK + "$2");
s = s.replace(R.RIGHT_BRACKET_CJK, "$1" + MARK + "$2");
s = s.replace(R.AN_LEFT_BRACKET, "$1" + MARK + "$2");
s = s.replace(R.RIGHT_BRACKET_AN, "$1" + MARK + "$2");
s = s.replace(R.CJK_ANS, "$1" + MARK + "$2");
s = s.replace(R.ANS_CJK, "$1" + MARK + "$2");
s = s.replace(R.S_A, "$1" + MARK + "$2");
return s;
}
function wrapNodeInGap(node) {
@@ -1158,11 +1203,11 @@ function wrapGapLeft(pos) {
}
wrapNodeInGap(tn);
}
function processBlock(block, finder) {
function processBlock(block, finder, R) {
const runs = finder.collectRuns(block);
for (const run of runs) {
const { text, map } = run;
const spaced = panguSpace(text);
const spaced = panguSpace(text, R);
if (spaced === text) {
continue;
}
@@ -1203,8 +1248,7 @@ function processBlock(block, finder) {
}
}
}
var PILL_NEIGHBOR = new RegExp("[A-Za-z0-9" + CJK + "]");
function processPills(root, finder, pillSelector) {
function processPills(root, finder, pillSelector, pillNeighbor) {
root.querySelectorAll(pillSelector).forEach((pill) => {
if (finder.isAvoided(pill) || !finder.inScope(pill)) {
return;
@@ -1214,36 +1258,36 @@ function processPills(root, finder, pillSelector) {
}
const prev = finder.adjacentLogicalChar(pill, -1);
if (prev) {
handlePillSide(prev, pill, -1);
handlePillSide(prev, pill, -1, pillNeighbor);
}
const next = finder.adjacentLogicalChar(pill, 1);
if (next) {
handlePillSide(next, pill, 1);
handlePillSide(next, pill, 1, pillNeighbor);
}
});
}
function handlePillSide(adj, pill, dir) {
function handlePillSide(adj, pill, dir, pillNeighbor) {
if (dir === -1) {
if (PILL_NEIGHBOR.test(adj.ch)) {
if (pillNeighbor.test(adj.ch)) {
wrapGapLeft({ textNode: adj.textNode, offset: adj.offset });
return;
}
if (adj.ch === " " && adj.offset >= 1) {
const tn = adj.textNode;
const bc = tn.data.charAt(adj.offset - 1);
if (bc !== " " && PILL_NEIGHBOR.test(bc)) {
if (bc !== " " && pillNeighbor.test(bc)) {
tn.data = tn.data.slice(0, adj.offset) + tn.data.slice(adj.offset + 1);
wrapGapLeft({ textNode: tn, offset: adj.offset - 1 });
}
}
} else {
if (PILL_NEIGHBOR.test(adj.ch)) {
if (pillNeighbor.test(adj.ch)) {
wrapNodeInGap(pill);
return;
}
if (adj.ch === " " && adj.textNode.data.length >= 2) {
const ac = adj.textNode.data.charAt(1);
if (ac !== " " && PILL_NEIGHBOR.test(ac)) {
if (ac !== " " && pillNeighbor.test(ac)) {
adj.textNode.data = adj.textNode.data.slice(1);
wrapNodeInGap(pill);
}
@@ -1257,13 +1301,14 @@ var spacingPass = {
enabled: (o) => o.features.spacing,
render(ctx) {
const { finder, options } = ctx;
const R = makeRules(options.ruleset);
ctx.finder.eachBlock(ctx.root, (block) => {
if (!finder.featureEnabledFor(block, PASS4)) {
return;
}
processBlock(block, finder);
processBlock(block, finder, R);
});
processPills(ctx.root, finder, options.finder.pillSelector);
processPills(ctx.root, finder, options.finder.pillSelector, R.pillNeighbor);
},
revert(ctx) {
revertPass(PASS4, ctx.root);
@@ -1454,6 +1499,7 @@ function normalizeOptions(opts = {}) {
...langOpt.style ? { style: langOpt.style } : {},
policy: langOpt.policy || {}
},
ruleset: resolveRuleset(opts.charClass),
autospaceClass: opts.autospaceClass || "",
justifyAtoms: opts.justifyAtoms === false ? false : true,
scope: {
dist/types.d.ts
Vendored
+7 -2
View File
@@ -1,7 +1,7 @@
import type { Finder } from "./core/finder.js";
import type { LangClass, LocaleConfig, PunctStyle } from "./core/locale.js";
import type { Bias, BiasTable } from "./core/unicode.js";
export type { LangClass, PunctStyle, Bias, BiasTable };
import type { Bias, BiasTable, BdSubclass, CharClassOverride, Ruleset } from "./core/unicode.js";
export type { LangClass, PunctStyle, Bias, BiasTable, BdSubclass, CharClassOverride, Ruleset };
/** 長英文詞包裝設定。 */
export interface LongWordOptions {
minLength?: number;
@@ -34,6 +34,9 @@ export interface JuzhenOptions {
/** 逐 lang 覆寫（最高優先）。 */
policy?: Partial<Record<LangClass, PunctStyle>>;
};
/** 自定義字符分類（擴充內置規則集）。把未分類字符或新符號歸入中文／西文／
* 全寬標點各子類，以覆寫 spacing／jiya 等規則之分類判定（追加語義）。 */
charClass?: CharClassOverride;
/** 間隙標記沿用之 class（v1 相容；預設無額外 class）。 */
autospaceClass?: string;
/** justify 原子化：jz-char／jz-jinze 是否以 inline-block 作對齊單一原子
@@ -67,6 +70,8 @@ export interface JuzhenOptions {
/** 正規化後之內部選項。 */
export interface ResolvedOptions {
locale: LocaleConfig;
/** 最終字符分類規則集（內置默認 ＋ charClass 覆寫）。 */
ruleset: Ruleset;
autospaceClass: string;
justifyAtoms: boolean;
scope: {