aboutsummaryrefslogtreecommitdiffstats
path: root/vanilla/node_modules/bidi-js/src
diff options
context:
space:
mode:
Diffstat (limited to 'vanilla/node_modules/bidi-js/src')
-rw-r--r--vanilla/node_modules/bidi-js/src/brackets.js30
-rw-r--r--vanilla/node_modules/bidi-js/src/charTypes.js66
-rw-r--r--vanilla/node_modules/bidi-js/src/data/bidiBrackets.data.js5
-rw-r--r--vanilla/node_modules/bidi-js/src/data/bidiCharTypes.data.js25
-rw-r--r--vanilla/node_modules/bidi-js/src/data/bidiMirroring.data.js2
-rw-r--r--vanilla/node_modules/bidi-js/src/embeddingLevels.js690
-rw-r--r--vanilla/node_modules/bidi-js/src/index.js5
-rw-r--r--vanilla/node_modules/bidi-js/src/mirroring.js48
-rw-r--r--vanilla/node_modules/bidi-js/src/reordering.js99
-rw-r--r--vanilla/node_modules/bidi-js/src/util/parseCharacterMap.js30
10 files changed, 1000 insertions, 0 deletions
diff --git a/vanilla/node_modules/bidi-js/src/brackets.js b/vanilla/node_modules/bidi-js/src/brackets.js
new file mode 100644
index 0000000..c598bc1
--- /dev/null
+++ b/vanilla/node_modules/bidi-js/src/brackets.js
@@ -0,0 +1,30 @@
+import data from './data/bidiBrackets.data.js'
+import { parseCharacterMap } from './util/parseCharacterMap.js'
+
+let openToClose, closeToOpen, canonical
+
+function parse () {
+ if (!openToClose) {
+ //const start = performance.now()
+ let { map, reverseMap } = parseCharacterMap(data.pairs, true)
+ openToClose = map
+ closeToOpen = reverseMap
+ canonical = parseCharacterMap(data.canonical, false).map
+ //console.log(`brackets parsed in ${performance.now() - start}ms`)
+ }
+}
+
+export function openingToClosingBracket (char) {
+ parse()
+ return openToClose.get(char) || null
+}
+
+export function closingToOpeningBracket (char) {
+ parse()
+ return closeToOpen.get(char) || null
+}
+
+export function getCanonicalBracket (char) {
+ parse()
+ return canonical.get(char) || null
+}
diff --git a/vanilla/node_modules/bidi-js/src/charTypes.js b/vanilla/node_modules/bidi-js/src/charTypes.js
new file mode 100644
index 0000000..057e871
--- /dev/null
+++ b/vanilla/node_modules/bidi-js/src/charTypes.js
@@ -0,0 +1,66 @@
+import DATA from './data/bidiCharTypes.data.js'
+
+const TYPES = {}
+const TYPES_TO_NAMES = {}
+TYPES.L = 1 //L is the default
+TYPES_TO_NAMES[1] = 'L'
+Object.keys(DATA).forEach((type, i) => {
+ TYPES[type] = 1 << (i + 1)
+ TYPES_TO_NAMES[TYPES[type]] = type
+})
+Object.freeze(TYPES)
+
+const ISOLATE_INIT_TYPES = TYPES.LRI | TYPES.RLI | TYPES.FSI
+const STRONG_TYPES = TYPES.L | TYPES.R | TYPES.AL
+const NEUTRAL_ISOLATE_TYPES = TYPES.B | TYPES.S | TYPES.WS | TYPES.ON | TYPES.FSI | TYPES.LRI | TYPES.RLI | TYPES.PDI
+const BN_LIKE_TYPES = TYPES.BN | TYPES.RLE | TYPES.LRE | TYPES.RLO | TYPES.LRO | TYPES.PDF
+const TRAILING_TYPES = TYPES.S | TYPES.WS | TYPES.B | ISOLATE_INIT_TYPES | TYPES.PDI | BN_LIKE_TYPES
+
+let map = null
+
+function parseData () {
+ if (!map) {
+ //const start = performance.now()
+ map = new Map()
+ for (let type in DATA) {
+ if (DATA.hasOwnProperty(type)) {
+ let lastCode = 0
+ DATA[type].split(',').forEach(range => {
+ let [skip, step] = range.split('+')
+ skip = parseInt(skip, 36)
+ step = step ? parseInt(step, 36) : 0
+ map.set(lastCode += skip, TYPES[type])
+ for (let i = 0; i < step; i++) {
+ map.set(++lastCode, TYPES[type])
+ }
+ })
+ }
+ }
+ //console.log(`char types parsed in ${performance.now() - start}ms`)
+ }
+}
+
+/**
+ * @param {string} char
+ * @return {number}
+ */
+function getBidiCharType (char) {
+ parseData()
+ return map.get(char.codePointAt(0)) || TYPES.L
+}
+
+function getBidiCharTypeName(char) {
+ return TYPES_TO_NAMES[getBidiCharType(char)]
+}
+
+export {
+ getBidiCharType,
+ getBidiCharTypeName,
+ TYPES,
+ TYPES_TO_NAMES,
+ ISOLATE_INIT_TYPES,
+ STRONG_TYPES,
+ NEUTRAL_ISOLATE_TYPES,
+ BN_LIKE_TYPES,
+ TRAILING_TYPES
+}
diff --git a/vanilla/node_modules/bidi-js/src/data/bidiBrackets.data.js b/vanilla/node_modules/bidi-js/src/data/bidiBrackets.data.js
new file mode 100644
index 0000000..885ae97
--- /dev/null
+++ b/vanilla/node_modules/bidi-js/src/data/bidiBrackets.data.js
@@ -0,0 +1,5 @@
+// Bidi bracket pairs data, auto generated
+export default {
+ "pairs": "14>1,1e>2,u>2,2wt>1,1>1,1ge>1,1wp>1,1j>1,f>1,hm>1,1>1,u>1,u6>1,1>1,+5,28>1,w>1,1>1,+3,b8>1,1>1,+3,1>3,-1>-1,3>1,1>1,+2,1s>1,1>1,x>1,th>1,1>1,+2,db>1,1>1,+3,3>1,1>1,+2,14qm>1,1>1,+1,4q>1,1e>2,u>2,2>1,+1",
+ "canonical": "6f1>-6dx,6dy>-6dx,6ec>-6ed,6ee>-6ed,6ww>2jj,-2ji>2jj,14r4>-1e7l,1e7m>-1e7l,1e7m>-1e5c,1e5d>-1e5b,1e5c>-14qx,14qy>-14qx,14vn>-1ecg,1ech>-1ecg,1edu>-1ecg,1eci>-1ecg,1eda>-1ecg,1eci>-1ecg,1eci>-168q,168r>-168q,168s>-14ye,14yf>-14ye"
+}
diff --git a/vanilla/node_modules/bidi-js/src/data/bidiCharTypes.data.js b/vanilla/node_modules/bidi-js/src/data/bidiCharTypes.data.js
new file mode 100644
index 0000000..b263c80
--- /dev/null
+++ b/vanilla/node_modules/bidi-js/src/data/bidiCharTypes.data.js
@@ -0,0 +1,25 @@
+// Bidi character types data, auto generated
+export default {
+ "R": "13k,1a,2,3,3,2+1j,ch+16,a+1,5+2,2+n,5,a,4,6+16,4+3,h+1b,4mo,179q,2+9,2+11,2i9+7y,2+68,4,3+4,5+13,4+3,2+4k,3+29,8+cf,1t+7z,w+17,3+3m,1t+3z,16o1+5r,8+30,8+mc,29+1r,29+4v,75+73",
+ "EN": "1c+9,3d+1,6,187+9,513,4+5,7+9,sf+j,175h+9,qw+q,161f+1d,4xt+a,25i+9",
+ "ES": "17,2,6dp+1,f+1,av,16vr,mx+1,4o,2",
+ "ET": "z+2,3h+3,b+1,ym,3e+1,2o,p4+1,8,6u,7c,g6,1wc,1n9+4,30+1b,2n,6d,qhx+1,h0m,a+1,49+2,63+1,4+1,6bb+3,12jj",
+ "AN": "16o+5,2j+9,2+1,35,ed,1ff2+9,87+u",
+ "CS": "18,2+1,b,2u,12k,55v,l,17v0,2,3,53,2+1,b",
+ "B": "a,3,f+2,2v,690",
+ "S": "9,2,k",
+ "WS": "c,k,4f4,1vk+a,u,1j,335",
+ "ON": "x+1,4+4,h+5,r+5,r+3,z,5+3,2+1,2+1,5,2+2,3+4,o,w,ci+1,8+d,3+d,6+8,2+g,39+1,9,6+1,2,33,b8,3+1,3c+1,7+1,5r,b,7h+3,sa+5,2,3i+6,jg+3,ur+9,2v,ij+1,9g+9,7+a,8m,4+1,49+x,14u,2+2,c+2,e+2,e+2,e+1,i+n,e+e,2+p,u+2,e+2,36+1,2+3,2+1,b,2+2,6+5,2,2,2,h+1,5+4,6+3,3+f,16+2,5+3l,3+81,1y+p,2+40,q+a,m+13,2r+ch,2+9e,75+hf,3+v,2+2w,6e+5,f+6,75+2a,1a+p,2+2g,d+5x,r+b,6+3,4+o,g,6+1,6+2,2k+1,4,2j,5h+z,1m+1,1e+f,t+2,1f+e,d+3,4o+3,2s+1,w,535+1r,h3l+1i,93+2,2s,b+1,3l+x,2v,4g+3,21+3,kz+1,g5v+1,5a,j+9,n+v,2,3,2+8,2+1,3+2,2,3,46+1,4+4,h+5,r+5,r+a,3h+2,4+6,b+4,78,1r+24,4+c,4,1hb,ey+6,103+j,16j+c,1ux+7,5+g,fsh,jdq+1t,4,57+2e,p1,1m,1m,1m,1m,4kt+1,7j+17,5+2r,d+e,3+e,2+e,2+10,m+4,w,1n+5,1q,4z+5,4b+rb,9+c,4+c,4+37,d+2g,8+b,l+b,5+1j,9+9,7+13,9+t,3+1,27+3c,2+29,2+3q,d+d,3+4,4+2,6+6,a+o,8+6,a+2,e+6,16+42,2+1i",
+ "BN": "0+8,6+d,2s+5,2+p,e,4m9,1kt+2,2b+5,5+5,17q9+v,7k,6p+8,6+1,119d+3,440+7,96s+1,1ekf+1,1ekf+1,1ekf+1,1ekf+1,1ekf+1,1ekf+1,1ekf+1,1ekf+1,1ekf+1,1ekf+1,1ekf+1,1ekf+75,6p+2rz,1ben+1,1ekf+1,1ekf+1",
+ "NSM": "lc+33,7o+6,7c+18,2,2+1,2+1,2,21+a,1d+k,h,2u+6,3+5,3+1,2+3,10,v+q,2k+a,1n+8,a,p+3,2+8,2+2,2+4,18+2,3c+e,2+v,1k,2,5+7,5,4+6,b+1,u,1n,5+3,9,l+1,r,3+1,1m,5+1,5+1,3+2,4,v+1,4,c+1,1m,5+4,2+1,5,l+1,n+5,2,1n,3,2+3,9,8+1,c+1,v,1q,d,1f,4,1m+2,6+2,2+3,8+1,c+1,u,1n,g+1,l+1,t+1,1m+1,5+3,9,l+1,u,21,8+2,2,2j,3+6,d+7,2r,3+8,c+5,23+1,s,2,2,1k+d,2+4,2+1,6+a,2+z,a,2v+3,2+5,2+1,3+1,q+1,5+2,h+3,e,3+1,7,g,jk+2,qb+2,u+2,u+1,v+1,1t+1,2+6,9,3+a,a,1a+2,3c+1,z,3b+2,5+1,a,7+2,64+1,3,1n,2+6,2,2,3+7,7+9,3,1d+g,1s+3,1d,2+4,2,6,15+8,d+1,x+3,3+1,2+2,1l,2+1,4,2+2,1n+7,3+1,49+2,2+c,2+6,5,7,4+1,5j+1l,2+4,k1+w,2db+2,3y,2p+v,ff+3,30+1,n9x+3,2+9,x+1,29+1,7l,4,5,q+1,6,48+1,r+h,e,13+7,q+a,1b+2,1d,3+3,3+1,14,1w+5,3+1,3+1,d,9,1c,1g,2+2,3+1,6+1,2,17+1,9,6n,3,5,fn5,ki+f,h+f,r2,6b,46+4,1af+2,2+1,6+3,15+2,5,4m+1,fy+3,as+1,4a+a,4x,1j+e,1l+2,1e+3,3+1,1y+2,11+4,2+7,1r,d+1,1h+8,b+3,3,2o+2,3,2+1,7,4h,4+7,m+1,1m+1,4,12+6,4+4,5g+7,3+2,2,o,2d+5,2,5+1,2+1,6n+3,7+1,2+1,s+1,2e+7,3,2+1,2z,2,3+5,2,2u+2,3+3,2+4,78+8,2+1,75+1,2,5,41+3,3+1,5,x+5,3+1,15+5,3+3,9,a+5,3+2,1b+c,2+1,bb+6,2+5,2d+l,3+6,2+1,2+1,3f+5,4,2+1,2+6,2,21+1,4,2,9o+1,f0c+4,1o+6,t5,1s+3,2a,f5l+1,43t+2,i+7,3+6,v+3,45+2,1j0+1i,5+1d,9,f,n+4,2+e,11t+6,2+g,3+6,2+1,2+4,7a+6,c6+3,15t+6,32+6,gzhy+6n",
+ "AL": "16w,3,2,e+1b,z+2,2+2s,g+1,8+1,b+m,2+t,s+2i,c+e,4h+f,1d+1e,1bwe+dp,3+3z,x+c,2+1,35+3y,2rm+z,5+7,b+5,dt+l,c+u,17nl+27,1t+27,4x+6n,3+d",
+ "LRO": "6ct",
+ "RLO": "6cu",
+ "LRE": "6cq",
+ "RLE": "6cr",
+ "PDF": "6cs",
+ "LRI": "6ee",
+ "RLI": "6ef",
+ "FSI": "6eg",
+ "PDI": "6eh"
+}
diff --git a/vanilla/node_modules/bidi-js/src/data/bidiMirroring.data.js b/vanilla/node_modules/bidi-js/src/data/bidiMirroring.data.js
new file mode 100644
index 0000000..b9cf987
--- /dev/null
+++ b/vanilla/node_modules/bidi-js/src/data/bidiMirroring.data.js
@@ -0,0 +1,2 @@
+// Bidi mirrored chars data, auto generated
+export default "14>1,j>2,t>2,u>2,1a>g,2v3>1,1>1,1ge>1,1wd>1,b>1,1j>1,f>1,ai>3,-2>3,+1,8>1k0,-1jq>1y7,-1y6>1hf,-1he>1h6,-1h5>1ha,-1h8>1qi,-1pu>1,6>3u,-3s>7,6>1,1>1,f>1,1>1,+2,3>1,1>1,+13,4>1,1>1,6>1eo,-1ee>1,3>1mg,-1me>1mk,-1mj>1mi,-1mg>1mi,-1md>1,1>1,+2,1>10k,-103>1,1>1,4>1,5>1,1>1,+10,3>1,1>8,-7>8,+1,-6>7,+1,a>1,1>1,u>1,u6>1,1>1,+5,26>1,1>1,2>1,2>2,8>1,7>1,4>1,1>1,+5,b8>1,1>1,+3,1>3,-2>1,2>1,1>1,+2,c>1,3>1,1>1,+2,h>1,3>1,a>1,1>1,2>1,3>1,1>1,d>1,f>1,3>1,1a>1,1>1,6>1,7>1,13>1,k>1,1>1,+19,4>1,1>1,+2,2>1,1>1,+18,m>1,a>1,1>1,lk>1,1>1,4>1,2>1,f>1,3>1,1>1,+3,db>1,1>1,+3,3>1,1>1,+2,14qm>1,1>1,+1,6>1,4j>1,j>2,t>2,u>2,2>1,+1"
diff --git a/vanilla/node_modules/bidi-js/src/embeddingLevels.js b/vanilla/node_modules/bidi-js/src/embeddingLevels.js
new file mode 100644
index 0000000..3815393
--- /dev/null
+++ b/vanilla/node_modules/bidi-js/src/embeddingLevels.js
@@ -0,0 +1,690 @@
+import {
+ BN_LIKE_TYPES,
+ getBidiCharType,
+ ISOLATE_INIT_TYPES,
+ NEUTRAL_ISOLATE_TYPES,
+ STRONG_TYPES,
+ TRAILING_TYPES,
+ TYPES
+} from './charTypes.js'
+import { closingToOpeningBracket, getCanonicalBracket, openingToClosingBracket } from './brackets.js'
+
+// Local type aliases
+const {
+ L: TYPE_L,
+ R: TYPE_R,
+ EN: TYPE_EN,
+ ES: TYPE_ES,
+ ET: TYPE_ET,
+ AN: TYPE_AN,
+ CS: TYPE_CS,
+ B: TYPE_B,
+ S: TYPE_S,
+ ON: TYPE_ON,
+ BN: TYPE_BN,
+ NSM: TYPE_NSM,
+ AL: TYPE_AL,
+ LRO: TYPE_LRO,
+ RLO: TYPE_RLO,
+ LRE: TYPE_LRE,
+ RLE: TYPE_RLE,
+ PDF: TYPE_PDF,
+ LRI: TYPE_LRI,
+ RLI: TYPE_RLI,
+ FSI: TYPE_FSI,
+ PDI: TYPE_PDI
+} = TYPES
+
+/**
+ * @typedef {object} GetEmbeddingLevelsResult
+ * @property {{start, end, level}[]} paragraphs
+ * @property {Uint8Array} levels
+ */
+
+/**
+ * This function applies the Bidirectional Algorithm to a string, returning the resolved embedding levels
+ * in a single Uint8Array plus a list of objects holding each paragraph's start and end indices and resolved
+ * base embedding level.
+ *
+ * @param {string} string - The input string
+ * @param {"ltr"|"rtl"|"auto"} [baseDirection] - Use "ltr" or "rtl" to force a base paragraph direction,
+ * otherwise a direction will be chosen automatically from each paragraph's contents.
+ * @return {GetEmbeddingLevelsResult}
+ */
+export function getEmbeddingLevels (string, baseDirection) {
+ const MAX_DEPTH = 125
+
+ // Start by mapping all characters to their unicode type, as a bitmask integer
+ const charTypes = new Uint32Array(string.length)
+ for (let i = 0; i < string.length; i++) {
+ charTypes[i] = getBidiCharType(string[i])
+ }
+
+ const charTypeCounts = new Map() //will be cleared at start of each paragraph
+ function changeCharType(i, type) {
+ const oldType = charTypes[i]
+ charTypes[i] = type
+ charTypeCounts.set(oldType, charTypeCounts.get(oldType) - 1)
+ if (oldType & NEUTRAL_ISOLATE_TYPES) {
+ charTypeCounts.set(NEUTRAL_ISOLATE_TYPES, charTypeCounts.get(NEUTRAL_ISOLATE_TYPES) - 1)
+ }
+ charTypeCounts.set(type, (charTypeCounts.get(type) || 0) + 1)
+ if (type & NEUTRAL_ISOLATE_TYPES) {
+ charTypeCounts.set(NEUTRAL_ISOLATE_TYPES, (charTypeCounts.get(NEUTRAL_ISOLATE_TYPES) || 0) + 1)
+ }
+ }
+
+ const embedLevels = new Uint8Array(string.length)
+ const isolationPairs = new Map() //init->pdi and pdi->init
+
+ // === 3.3.1 The Paragraph Level ===
+ // 3.3.1 P1: Split the text into paragraphs
+ const paragraphs = [] // [{start, end, level}, ...]
+ let paragraph = null
+ for (let i = 0; i < string.length; i++) {
+ if (!paragraph) {
+ paragraphs.push(paragraph = {
+ start: i,
+ end: string.length - 1,
+ // 3.3.1 P2-P3: Determine the paragraph level
+ level: baseDirection === 'rtl' ? 1 : baseDirection === 'ltr' ? 0 : determineAutoEmbedLevel(i, false)
+ })
+ }
+ if (charTypes[i] & TYPE_B) {
+ paragraph.end = i
+ paragraph = null
+ }
+ }
+
+ const FORMATTING_TYPES = TYPE_RLE | TYPE_LRE | TYPE_RLO | TYPE_LRO | ISOLATE_INIT_TYPES | TYPE_PDI | TYPE_PDF | TYPE_B
+ const nextEven = n => n + ((n & 1) ? 1 : 2)
+ const nextOdd = n => n + ((n & 1) ? 2 : 1)
+
+ // Everything from here on will operate per paragraph.
+ for (let paraIdx = 0; paraIdx < paragraphs.length; paraIdx++) {
+ paragraph = paragraphs[paraIdx]
+ const statusStack = [{
+ _level: paragraph.level,
+ _override: 0, //0=neutral, 1=L, 2=R
+ _isolate: 0 //bool
+ }]
+ let stackTop
+ let overflowIsolateCount = 0
+ let overflowEmbeddingCount = 0
+ let validIsolateCount = 0
+ charTypeCounts.clear()
+
+ // === 3.3.2 Explicit Levels and Directions ===
+ for (let i = paragraph.start; i <= paragraph.end; i++) {
+ let charType = charTypes[i]
+ stackTop = statusStack[statusStack.length - 1]
+
+ // Set initial counts
+ charTypeCounts.set(charType, (charTypeCounts.get(charType) || 0) + 1)
+ if (charType & NEUTRAL_ISOLATE_TYPES) {
+ charTypeCounts.set(NEUTRAL_ISOLATE_TYPES, (charTypeCounts.get(NEUTRAL_ISOLATE_TYPES) || 0) + 1)
+ }
+
+ // Explicit Embeddings: 3.3.2 X2 - X3
+ if (charType & FORMATTING_TYPES) { //prefilter all formatters
+ if (charType & (TYPE_RLE | TYPE_LRE)) {
+ embedLevels[i] = stackTop._level // 5.2
+ const level = (charType === TYPE_RLE ? nextOdd : nextEven)(stackTop._level)
+ if (level <= MAX_DEPTH && !overflowIsolateCount && !overflowEmbeddingCount) {
+ statusStack.push({
+ _level: level,
+ _override: 0,
+ _isolate: 0
+ })
+ } else if (!overflowIsolateCount) {
+ overflowEmbeddingCount++
+ }
+ }
+
+ // Explicit Overrides: 3.3.2 X4 - X5
+ else if (charType & (TYPE_RLO | TYPE_LRO)) {
+ embedLevels[i] = stackTop._level // 5.2
+ const level = (charType === TYPE_RLO ? nextOdd : nextEven)(stackTop._level)
+ if (level <= MAX_DEPTH && !overflowIsolateCount && !overflowEmbeddingCount) {
+ statusStack.push({
+ _level: level,
+ _override: (charType & TYPE_RLO) ? TYPE_R : TYPE_L,
+ _isolate: 0
+ })
+ } else if (!overflowIsolateCount) {
+ overflowEmbeddingCount++
+ }
+ }
+
+ // Isolates: 3.3.2 X5a - X5c
+ else if (charType & ISOLATE_INIT_TYPES) {
+ // X5c - FSI becomes either RLI or LRI
+ if (charType & TYPE_FSI) {
+ charType = determineAutoEmbedLevel(i + 1, true) === 1 ? TYPE_RLI : TYPE_LRI
+ }
+
+ embedLevels[i] = stackTop._level
+ if (stackTop._override) {
+ changeCharType(i, stackTop._override)
+ }
+ const level = (charType === TYPE_RLI ? nextOdd : nextEven)(stackTop._level)
+ if (level <= MAX_DEPTH && overflowIsolateCount === 0 && overflowEmbeddingCount === 0) {
+ validIsolateCount++
+ statusStack.push({
+ _level: level,
+ _override: 0,
+ _isolate: 1,
+ _isolInitIndex: i
+ })
+ } else {
+ overflowIsolateCount++
+ }
+ }
+
+ // Terminating Isolates: 3.3.2 X6a
+ else if (charType & TYPE_PDI) {
+ if (overflowIsolateCount > 0) {
+ overflowIsolateCount--
+ } else if (validIsolateCount > 0) {
+ overflowEmbeddingCount = 0
+ while (!statusStack[statusStack.length - 1]._isolate) {
+ statusStack.pop()
+ }
+ // Add to isolation pairs bidirectional mapping:
+ const isolInitIndex = statusStack[statusStack.length - 1]._isolInitIndex
+ if (isolInitIndex != null) {
+ isolationPairs.set(isolInitIndex, i)
+ isolationPairs.set(i, isolInitIndex)
+ }
+ statusStack.pop()
+ validIsolateCount--
+ }
+ stackTop = statusStack[statusStack.length - 1]
+ embedLevels[i] = stackTop._level
+ if (stackTop._override) {
+ changeCharType(i, stackTop._override)
+ }
+ }
+
+
+ // Terminating Embeddings and Overrides: 3.3.2 X7
+ else if (charType & TYPE_PDF) {
+ if (overflowIsolateCount === 0) {
+ if (overflowEmbeddingCount > 0) {
+ overflowEmbeddingCount--
+ } else if (!stackTop._isolate && statusStack.length > 1) {
+ statusStack.pop()
+ stackTop = statusStack[statusStack.length - 1]
+ }
+ }
+ embedLevels[i] = stackTop._level // 5.2
+ }
+
+ // End of Paragraph: 3.3.2 X8
+ else if (charType & TYPE_B) {
+ embedLevels[i] = paragraph.level
+ }
+ }
+
+ // Non-formatting characters: 3.3.2 X6
+ else {
+ embedLevels[i] = stackTop._level
+ // NOTE: This exclusion of BN seems to go against what section 5.2 says, but is required for test passage
+ if (stackTop._override && charType !== TYPE_BN) {
+ changeCharType(i, stackTop._override)
+ }
+ }
+ }
+
+ // === 3.3.3 Preparations for Implicit Processing ===
+
+ // Remove all RLE, LRE, RLO, LRO, PDF, and BN characters: 3.3.3 X9
+ // Note: Due to section 5.2, we won't remove them, but we'll use the BN_LIKE_TYPES bitset to
+ // easily ignore them all from here on out.
+
+ // 3.3.3 X10
+ // Compute the set of isolating run sequences as specified by BD13
+ const levelRuns = []
+ let currentRun = null
+ let isolationLevel = 0
+ for (let i = paragraph.start; i <= paragraph.end; i++) {
+ const charType = charTypes[i]
+ if (!(charType & BN_LIKE_TYPES)) {
+ const lvl = embedLevels[i]
+ const isIsolInit = charType & ISOLATE_INIT_TYPES
+ const isPDI = charType === TYPE_PDI
+ if (isIsolInit) {
+ isolationLevel++
+ }
+ if (currentRun && lvl === currentRun._level) {
+ currentRun._end = i
+ currentRun._endsWithIsolInit = isIsolInit
+ } else {
+ levelRuns.push(currentRun = {
+ _start: i,
+ _end: i,
+ _level: lvl,
+ _startsWithPDI: isPDI,
+ _endsWithIsolInit: isIsolInit
+ })
+ }
+ if (isPDI) {
+ isolationLevel--
+ }
+ }
+ }
+ const isolatingRunSeqs = [] // [{seqIndices: [], sosType: L|R, eosType: L|R}]
+ for (let runIdx = 0; runIdx < levelRuns.length; runIdx++) {
+ const run = levelRuns[runIdx]
+ if (!run._startsWithPDI || (run._startsWithPDI && !isolationPairs.has(run._start))) {
+ const seqRuns = [currentRun = run]
+ for (let pdiIndex; currentRun && currentRun._endsWithIsolInit && (pdiIndex = isolationPairs.get(currentRun._end)) != null;) {
+ for (let i = runIdx + 1; i < levelRuns.length; i++) {
+ if (levelRuns[i]._start === pdiIndex) {
+ seqRuns.push(currentRun = levelRuns[i])
+ break
+ }
+ }
+ }
+ // build flat list of indices across all runs:
+ const seqIndices = []
+ for (let i = 0; i < seqRuns.length; i++) {
+ const run = seqRuns[i]
+ for (let j = run._start; j <= run._end; j++) {
+ seqIndices.push(j)
+ }
+ }
+ // determine the sos/eos types:
+ let firstLevel = embedLevels[seqIndices[0]]
+ let prevLevel = paragraph.level
+ for (let i = seqIndices[0] - 1; i >= 0; i--) {
+ if (!(charTypes[i] & BN_LIKE_TYPES)) { //5.2
+ prevLevel = embedLevels[i]
+ break
+ }
+ }
+ const lastIndex = seqIndices[seqIndices.length - 1]
+ let lastLevel = embedLevels[lastIndex]
+ let nextLevel = paragraph.level
+ if (!(charTypes[lastIndex] & ISOLATE_INIT_TYPES)) {
+ for (let i = lastIndex + 1; i <= paragraph.end; i++) {
+ if (!(charTypes[i] & BN_LIKE_TYPES)) { //5.2
+ nextLevel = embedLevels[i]
+ break
+ }
+ }
+ }
+ isolatingRunSeqs.push({
+ _seqIndices: seqIndices,
+ _sosType: Math.max(prevLevel, firstLevel) % 2 ? TYPE_R : TYPE_L,
+ _eosType: Math.max(nextLevel, lastLevel) % 2 ? TYPE_R : TYPE_L
+ })
+ }
+ }
+
+ // The next steps are done per isolating run sequence
+ for (let seqIdx = 0; seqIdx < isolatingRunSeqs.length; seqIdx++) {
+ const { _seqIndices: seqIndices, _sosType: sosType, _eosType: eosType } = isolatingRunSeqs[seqIdx]
+ /**
+ * All the level runs in an isolating run sequence have the same embedding level.
+ *
+ * DO NOT change any `embedLevels[i]` within the current scope.
+ */
+ const embedDirection = ((embedLevels[seqIndices[0]]) & 1) ? TYPE_R : TYPE_L;
+
+ // === 3.3.4 Resolving Weak Types ===
+
+ // W1 + 5.2. Search backward from each NSM to the first character in the isolating run sequence whose
+ // bidirectional type is not BN, and set the NSM to ON if it is an isolate initiator or PDI, and to its
+ // type otherwise. If the NSM is the first non-BN character, change the NSM to the type of sos.
+ if (charTypeCounts.get(TYPE_NSM)) {
+ for (let si = 0; si < seqIndices.length; si++) {
+ const i = seqIndices[si]
+ if (charTypes[i] & TYPE_NSM) {
+ let prevType = sosType
+ for (let sj = si - 1; sj >= 0; sj--) {
+ if (!(charTypes[seqIndices[sj]] & BN_LIKE_TYPES)) { //5.2 scan back to first non-BN
+ prevType = charTypes[seqIndices[sj]]
+ break
+ }
+ }
+ changeCharType(i, (prevType & (ISOLATE_INIT_TYPES | TYPE_PDI)) ? TYPE_ON : prevType)
+ }
+ }
+ }
+
+ // W2. Search backward from each instance of a European number until the first strong type (R, L, AL, or sos)
+ // is found. If an AL is found, change the type of the European number to Arabic number.
+ if (charTypeCounts.get(TYPE_EN)) {
+ for (let si = 0; si < seqIndices.length; si++) {
+ const i = seqIndices[si]
+ if (charTypes[i] & TYPE_EN) {
+ for (let sj = si - 1; sj >= -1; sj--) {
+ const prevCharType = sj === -1 ? sosType : charTypes[seqIndices[sj]]
+ if (prevCharType & STRONG_TYPES) {
+ if (prevCharType === TYPE_AL) {
+ changeCharType(i, TYPE_AN)
+ }
+ break
+ }
+ }
+ }
+ }
+ }
+
+ // W3. Change all ALs to R
+ if (charTypeCounts.get(TYPE_AL)) {
+ for (let si = 0; si < seqIndices.length; si++) {
+ const i = seqIndices[si]
+ if (charTypes[i] & TYPE_AL) {
+ changeCharType(i, TYPE_R)
+ }
+ }
+ }
+
+ // W4. A single European separator between two European numbers changes to a European number. A single common
+ // separator between two numbers of the same type changes to that type.
+ if (charTypeCounts.get(TYPE_ES) || charTypeCounts.get(TYPE_CS)) {
+ for (let si = 1; si < seqIndices.length - 1; si++) {
+ const i = seqIndices[si]
+ if (charTypes[i] & (TYPE_ES | TYPE_CS)) {
+ let prevType = 0, nextType = 0
+ for (let sj = si - 1; sj >= 0; sj--) {
+ prevType = charTypes[seqIndices[sj]]
+ if (!(prevType & BN_LIKE_TYPES)) { //5.2
+ break
+ }
+ }
+ for (let sj = si + 1; sj < seqIndices.length; sj++) {
+ nextType = charTypes[seqIndices[sj]]
+ if (!(nextType & BN_LIKE_TYPES)) { //5.2
+ break
+ }
+ }
+ if (prevType === nextType && (charTypes[i] === TYPE_ES ? prevType === TYPE_EN : (prevType & (TYPE_EN | TYPE_AN)))) {
+ changeCharType(i, prevType)
+ }
+ }
+ }
+ }
+
+ // W5. A sequence of European terminators adjacent to European numbers changes to all European numbers.
+ if (charTypeCounts.get(TYPE_EN)) {
+ for (let si = 0; si < seqIndices.length; si++) {
+ const i = seqIndices[si]
+ if (charTypes[i] & TYPE_EN) {
+ for (let sj = si - 1; sj >= 0 && (charTypes[seqIndices[sj]] & (TYPE_ET | BN_LIKE_TYPES)); sj--) {
+ changeCharType(seqIndices[sj], TYPE_EN)
+ }
+ for (si++; si < seqIndices.length && (charTypes[seqIndices[si]] & (TYPE_ET | BN_LIKE_TYPES | TYPE_EN)); si++) {
+ if (charTypes[seqIndices[si]] !== TYPE_EN) {
+ changeCharType(seqIndices[si], TYPE_EN)
+ }
+ }
+ }
+ }
+ }
+
+ // W6. Otherwise, separators and terminators change to Other Neutral.
+ if (charTypeCounts.get(TYPE_ET) || charTypeCounts.get(TYPE_ES) || charTypeCounts.get(TYPE_CS)) {
+ for (let si = 0; si < seqIndices.length; si++) {
+ const i = seqIndices[si]
+ if (charTypes[i] & (TYPE_ET | TYPE_ES | TYPE_CS)) {
+ changeCharType(i, TYPE_ON)
+ // 5.2 transform adjacent BNs too:
+ for (let sj = si - 1; sj >= 0 && (charTypes[seqIndices[sj]] & BN_LIKE_TYPES); sj--) {
+ changeCharType(seqIndices[sj], TYPE_ON)
+ }
+ for (let sj = si + 1; sj < seqIndices.length && (charTypes[seqIndices[sj]] & BN_LIKE_TYPES); sj++) {
+ changeCharType(seqIndices[sj], TYPE_ON)
+ }
+ }
+ }
+ }
+
+ // W7. Search backward from each instance of a European number until the first strong type (R, L, or sos)
+ // is found. If an L is found, then change the type of the European number to L.
+ // NOTE: implemented in single forward pass for efficiency
+ if (charTypeCounts.get(TYPE_EN)) {
+ for (let si = 0, prevStrongType = sosType; si < seqIndices.length; si++) {
+ const i = seqIndices[si]
+ const type = charTypes[i]
+ if (type & TYPE_EN) {
+ if (prevStrongType === TYPE_L) {
+ changeCharType(i, TYPE_L)
+ }
+ } else if (type & STRONG_TYPES) {
+ prevStrongType = type
+ }
+ }
+ }
+
+ // === 3.3.5 Resolving Neutral and Isolate Formatting Types ===
+
+ if (charTypeCounts.get(NEUTRAL_ISOLATE_TYPES)) {
+ // N0. Process bracket pairs in an isolating run sequence sequentially in the logical order of the text
+ // positions of the opening paired brackets using the logic given below. Within this scope, bidirectional
+ // types EN and AN are treated as R.
+ const R_TYPES_FOR_N_STEPS = (TYPE_R | TYPE_EN | TYPE_AN)
+ const STRONG_TYPES_FOR_N_STEPS = R_TYPES_FOR_N_STEPS | TYPE_L
+
+ // * Identify the bracket pairs in the current isolating run sequence according to BD16.
+ const bracketPairs = []
+ {
+ const openerStack = []
+ for (let si = 0; si < seqIndices.length; si++) {
+ // NOTE: for any potential bracket character we also test that it still carries a NI
+ // type, as that may have been changed earlier. This doesn't seem to be explicitly
+ // called out in the spec, but is required for passage of certain tests.
+ if (charTypes[seqIndices[si]] & NEUTRAL_ISOLATE_TYPES) {
+ const char = string[seqIndices[si]]
+ let oppositeBracket
+ // Opening bracket
+ if (openingToClosingBracket(char) !== null) {
+ if (openerStack.length < 63) {
+ openerStack.push({ char, seqIndex: si })
+ } else {
+ break
+ }
+ }
+ // Closing bracket
+ else if ((oppositeBracket = closingToOpeningBracket(char)) !== null) {
+ for (let stackIdx = openerStack.length - 1; stackIdx >= 0; stackIdx--) {
+ const stackChar = openerStack[stackIdx].char
+ if (stackChar === oppositeBracket ||
+ stackChar === closingToOpeningBracket(getCanonicalBracket(char)) ||
+ openingToClosingBracket(getCanonicalBracket(stackChar)) === char
+ ) {
+ bracketPairs.push([openerStack[stackIdx].seqIndex, si])
+ openerStack.length = stackIdx //pop the matching bracket and all following
+ break
+ }
+ }
+ }
+ }
+ }
+ bracketPairs.sort((a, b) => a[0] - b[0])
+ }
+ // * For each bracket-pair element in the list of pairs of text positions
+ for (let pairIdx = 0; pairIdx < bracketPairs.length; pairIdx++) {
+ const [openSeqIdx, closeSeqIdx] = bracketPairs[pairIdx]
+ // a. Inspect the bidirectional types of the characters enclosed within the bracket pair.
+ // b. If any strong type (either L or R) matching the embedding direction is found, set the type for both
+ // brackets in the pair to match the embedding direction.
+ let foundStrongType = false
+ let useStrongType = 0
+ for (let si = openSeqIdx + 1; si < closeSeqIdx; si++) {
+ const i = seqIndices[si]
+ if (charTypes[i] & STRONG_TYPES_FOR_N_STEPS) {
+ foundStrongType = true
+ const lr = (charTypes[i] & R_TYPES_FOR_N_STEPS) ? TYPE_R : TYPE_L
+ if (lr === embedDirection) {
+ useStrongType = lr
+ break
+ }
+ }
+ }
+ // c. Otherwise, if there is a strong type it must be opposite the embedding direction. Therefore, test
+ // for an established context with a preceding strong type by checking backwards before the opening paired
+ // bracket until the first strong type (L, R, or sos) is found.
+ // 1. If the preceding strong type is also opposite the embedding direction, context is established, so
+ // set the type for both brackets in the pair to that direction.
+ // 2. Otherwise set the type for both brackets in the pair to the embedding direction.
+ if (foundStrongType && !useStrongType) {
+ useStrongType = sosType
+ for (let si = openSeqIdx - 1; si >= 0; si--) {
+ const i = seqIndices[si]
+ if (charTypes[i] & STRONG_TYPES_FOR_N_STEPS) {
+ const lr = (charTypes[i] & R_TYPES_FOR_N_STEPS) ? TYPE_R : TYPE_L
+ if (lr !== embedDirection) {
+ useStrongType = lr
+ } else {
+ useStrongType = embedDirection
+ }
+ break
+ }
+ }
+ }
+ if (useStrongType) {
+ charTypes[seqIndices[openSeqIdx]] = charTypes[seqIndices[closeSeqIdx]] = useStrongType
+ // * Any number of characters that had original bidirectional character type NSM prior to the application
+ // of W1 that immediately follow a paired bracket which changed to L or R under N0 should change to match
+ // the type of their preceding bracket.
+ if (useStrongType !== embedDirection) {
+ for (let si = openSeqIdx + 1; si < seqIndices.length; si++) {
+ if (!(charTypes[seqIndices[si]] & BN_LIKE_TYPES)) {
+ if (getBidiCharType(string[seqIndices[si]]) & TYPE_NSM) {
+ charTypes[seqIndices[si]] = useStrongType
+ }
+ break
+ }
+ }
+ }
+ if (useStrongType !== embedDirection) {
+ for (let si = closeSeqIdx + 1; si < seqIndices.length; si++) {
+ if (!(charTypes[seqIndices[si]] & BN_LIKE_TYPES)) {
+ if (getBidiCharType(string[seqIndices[si]]) & TYPE_NSM) {
+ charTypes[seqIndices[si]] = useStrongType
+ }
+ break
+ }
+ }
+ }
+ }
+ }
+
+ // N1. A sequence of NIs takes the direction of the surrounding strong text if the text on both sides has the
+ // same direction.
+ // N2. Any remaining NIs take the embedding direction.
+ for (let si = 0; si < seqIndices.length; si++) {
+ if (charTypes[seqIndices[si]] & NEUTRAL_ISOLATE_TYPES) {
+ let niRunStart = si, niRunEnd = si
+ let prevType = sosType //si === 0 ? sosType : (charTypes[seqIndices[si - 1]] & R_TYPES_FOR_N_STEPS) ? TYPE_R : TYPE_L
+ for (let si2 = si - 1; si2 >= 0; si2--) {
+ if (charTypes[seqIndices[si2]] & BN_LIKE_TYPES) {
+ niRunStart = si2 //5.2 treat BNs adjacent to NIs as NIs
+ } else {
+ prevType = (charTypes[seqIndices[si2]] & R_TYPES_FOR_N_STEPS) ? TYPE_R : TYPE_L
+ break
+ }
+ }
+ let nextType = eosType
+ for (let si2 = si + 1; si2 < seqIndices.length; si2++) {
+ if (charTypes[seqIndices[si2]] & (NEUTRAL_ISOLATE_TYPES | BN_LIKE_TYPES)) {
+ niRunEnd = si2
+ } else {
+ nextType = (charTypes[seqIndices[si2]] & R_TYPES_FOR_N_STEPS) ? TYPE_R : TYPE_L
+ break
+ }
+ }
+ for (let sj = niRunStart; sj <= niRunEnd; sj++) {
+ charTypes[seqIndices[sj]] = prevType === nextType ? prevType : embedDirection
+ }
+ si = niRunEnd
+ }
+ }
+ }
+ }
+
+ // === 3.3.6 Resolving Implicit Levels ===
+
+ for (let i = paragraph.start; i <= paragraph.end; i++) {
+ const level = embedLevels[i]
+ const type = charTypes[i]
+ // I2. For all characters with an odd (right-to-left) embedding level, those of type L, EN or AN go up one level.
+ if (level & 1) {
+ if (type & (TYPE_L | TYPE_EN | TYPE_AN)) {
+ embedLevels[i]++
+ }
+ }
+ // I1. For all characters with an even (left-to-right) embedding level, those of type R go up one level
+ // and those of type AN or EN go up two levels.
+ else {
+ if (type & TYPE_R) {
+ embedLevels[i]++
+ } else if (type & (TYPE_AN | TYPE_EN)) {
+ embedLevels[i] += 2
+ }
+ }
+
+ // 5.2: Resolve any LRE, RLE, LRO, RLO, PDF, or BN to the level of the preceding character if there is one,
+ // and otherwise to the base level.
+ if (type & BN_LIKE_TYPES) {
+ embedLevels[i] = i === 0 ? paragraph.level : embedLevels[i - 1]
+ }
+
+ // 3.4 L1.1-4: Reset the embedding level of segment/paragraph separators, and any sequence of whitespace or
+ // isolate formatting characters preceding them or the end of the paragraph, to the paragraph level.
+ // NOTE: this will also need to be applied to each individual line ending after line wrapping occurs.
+ if (i === paragraph.end || getBidiCharType(string[i]) & (TYPE_S | TYPE_B)) {
+ for (let j = i; j >= 0 && (getBidiCharType(string[j]) & TRAILING_TYPES); j--) {
+ embedLevels[j] = paragraph.level
+ }
+ }
+ }
+ }
+
+ // DONE! The resolved levels can then be used, after line wrapping, to flip runs of characters
+ // according to section 3.4 Reordering Resolved Levels
+ return {
+ levels: embedLevels,
+ paragraphs
+ }
+
+ function determineAutoEmbedLevel (start, isFSI) {
+ // 3.3.1 P2 - P3
+ for (let i = start; i < string.length; i++) {
+ const charType = charTypes[i]
+ if (charType & (TYPE_R | TYPE_AL)) {
+ return 1
+ }
+ if ((charType & (TYPE_B | TYPE_L)) || (isFSI && charType === TYPE_PDI)) {
+ return 0
+ }
+ if (charType & ISOLATE_INIT_TYPES) {
+ const pdi = indexOfMatchingPDI(i)
+ i = pdi === -1 ? string.length : pdi
+ }
+ }
+ return 0
+ }
+
+ function indexOfMatchingPDI (isolateStart) {
+ // 3.1.2 BD9
+ let isolationLevel = 1
+ for (let i = isolateStart + 1; i < string.length; i++) {
+ const charType = charTypes[i]
+ if (charType & TYPE_B) {
+ break
+ }
+ if (charType & TYPE_PDI) {
+ if (--isolationLevel === 0) {
+ return i
+ }
+ } else if (charType & ISOLATE_INIT_TYPES) {
+ isolationLevel++
+ }
+ }
+ return -1
+ }
+}
diff --git a/vanilla/node_modules/bidi-js/src/index.js b/vanilla/node_modules/bidi-js/src/index.js
new file mode 100644
index 0000000..d146bb0
--- /dev/null
+++ b/vanilla/node_modules/bidi-js/src/index.js
@@ -0,0 +1,5 @@
+export { getEmbeddingLevels } from './embeddingLevels.js'
+export { getReorderSegments, getReorderedIndices, getReorderedString } from './reordering.js'
+export { getBidiCharType, getBidiCharTypeName } from './charTypes.js'
+export { getMirroredCharacter, getMirroredCharactersMap } from './mirroring.js'
+export { closingToOpeningBracket, openingToClosingBracket, getCanonicalBracket } from './brackets.js'
diff --git a/vanilla/node_modules/bidi-js/src/mirroring.js b/vanilla/node_modules/bidi-js/src/mirroring.js
new file mode 100644
index 0000000..c214b04
--- /dev/null
+++ b/vanilla/node_modules/bidi-js/src/mirroring.js
@@ -0,0 +1,48 @@
+import data from './data/bidiMirroring.data.js'
+import { parseCharacterMap } from './util/parseCharacterMap.js'
+
+let mirrorMap
+
+function parse () {
+ if (!mirrorMap) {
+ //const start = performance.now()
+ const { map, reverseMap } = parseCharacterMap(data, true)
+ // Combine both maps into one
+ reverseMap.forEach((value, key) => {
+ map.set(key, value)
+ })
+ mirrorMap = map
+ //console.log(`mirrored chars parsed in ${performance.now() - start}ms`)
+ }
+}
+
+export function getMirroredCharacter (char) {
+ parse()
+ return mirrorMap.get(char) || null
+}
+
+/**
+ * Given a string and its resolved embedding levels, build a map of indices to replacement chars
+ * for any characters in right-to-left segments that have defined mirrored characters.
+ * @param string
+ * @param embeddingLevels
+ * @param [start]
+ * @param [end]
+ * @return {Map<number, string>}
+ */
+export function getMirroredCharactersMap(string, embeddingLevels, start, end) {
+ let strLen = string.length
+ start = Math.max(0, start == null ? 0 : +start)
+ end = Math.min(strLen - 1, end == null ? strLen - 1 : +end)
+
+ const map = new Map()
+ for (let i = start; i <= end; i++) {
+ if (embeddingLevels[i] & 1) { //only odd (rtl) levels
+ const mirror = getMirroredCharacter(string[i])
+ if (mirror !== null) {
+ map.set(i, mirror)
+ }
+ }
+ }
+ return map
+}
diff --git a/vanilla/node_modules/bidi-js/src/reordering.js b/vanilla/node_modules/bidi-js/src/reordering.js
new file mode 100644
index 0000000..94a42ed
--- /dev/null
+++ b/vanilla/node_modules/bidi-js/src/reordering.js
@@ -0,0 +1,99 @@
+import { getBidiCharType, TRAILING_TYPES } from './charTypes.js'
+import { getMirroredCharacter } from './mirroring.js'
+
+/**
+ * Given a start and end denoting a single line within a string, and a set of precalculated
+ * bidi embedding levels, produce a list of segments whose ordering should be flipped, in sequence.
+ * @param {string} string - the full input string
+ * @param {GetEmbeddingLevelsResult} embeddingLevelsResult - the result object from getEmbeddingLevels
+ * @param {number} [start] - first character in a subset of the full string
+ * @param {number} [end] - last character in a subset of the full string
+ * @return {number[][]} - the list of start/end segments that should be flipped, in order.
+ */
+export function getReorderSegments(string, embeddingLevelsResult, start, end) {
+ let strLen = string.length
+ start = Math.max(0, start == null ? 0 : +start)
+ end = Math.min(strLen - 1, end == null ? strLen - 1 : +end)
+
+ const segments = []
+ embeddingLevelsResult.paragraphs.forEach(paragraph => {
+ const lineStart = Math.max(start, paragraph.start)
+ const lineEnd = Math.min(end, paragraph.end)
+ if (lineStart < lineEnd) {
+ // Local slice for mutation
+ const lineLevels = embeddingLevelsResult.levels.slice(lineStart, lineEnd + 1)
+
+ // 3.4 L1.4: Reset any sequence of whitespace characters and/or isolate formatting characters at the
+ // end of the line to the paragraph level.
+ for (let i = lineEnd; i >= lineStart && (getBidiCharType(string[i]) & TRAILING_TYPES); i--) {
+ lineLevels[i] = paragraph.level
+ }
+
+ // L2. From the highest level found in the text to the lowest odd level on each line, including intermediate levels
+ // not actually present in the text, reverse any contiguous sequence of characters that are at that level or higher.
+ let maxLevel = paragraph.level
+ let minOddLevel = Infinity
+ for (let i = 0; i < lineLevels.length; i++) {
+ const level = lineLevels[i]
+ if (level > maxLevel) maxLevel = level
+ if (level < minOddLevel) minOddLevel = level | 1
+ }
+ for (let lvl = maxLevel; lvl >= minOddLevel; lvl--) {
+ for (let i = 0; i < lineLevels.length; i++) {
+ if (lineLevels[i] >= lvl) {
+ const segStart = i
+ while (i + 1 < lineLevels.length && lineLevels[i + 1] >= lvl) {
+ i++
+ }
+ if (i > segStart) {
+ segments.push([segStart + lineStart, i + lineStart])
+ }
+ }
+ }
+ }
+ }
+ })
+ return segments
+}
+
+/**
+ * @param {string} string
+ * @param {GetEmbeddingLevelsResult} embedLevelsResult
+ * @param {number} [start]
+ * @param {number} [end]
+ * @return {string} the new string with bidi segments reordered
+ */
+export function getReorderedString(string, embedLevelsResult, start, end) {
+ const indices = getReorderedIndices(string, embedLevelsResult, start, end)
+ const chars = [...string]
+ indices.forEach((charIndex, i) => {
+ chars[i] = (
+ (embedLevelsResult.levels[charIndex] & 1) ? getMirroredCharacter(string[charIndex]) : null
+ ) || string[charIndex]
+ })
+ return chars.join('')
+}
+
+/**
+ * @param {string} string
+ * @param {GetEmbeddingLevelsResult} embedLevelsResult
+ * @param {number} [start]
+ * @param {number} [end]
+ * @return {number[]} an array with character indices in their new bidi order
+ */
+export function getReorderedIndices(string, embedLevelsResult, start, end) {
+ const segments = getReorderSegments(string, embedLevelsResult, start, end)
+ // Fill an array with indices
+ const indices = []
+ for (let i = 0; i < string.length; i++) {
+ indices[i] = i
+ }
+ // Reverse each segment in order
+ segments.forEach(([start, end]) => {
+ const slice = indices.slice(start, end + 1)
+ for (let i = slice.length; i--;) {
+ indices[end - i] = slice[i]
+ }
+ })
+ return indices
+}
diff --git a/vanilla/node_modules/bidi-js/src/util/parseCharacterMap.js b/vanilla/node_modules/bidi-js/src/util/parseCharacterMap.js
new file mode 100644
index 0000000..86a96b8
--- /dev/null
+++ b/vanilla/node_modules/bidi-js/src/util/parseCharacterMap.js
@@ -0,0 +1,30 @@
+/**
+ * Parses an string that holds encoded codepoint mappings, e.g. for bracket pairs or
+ * mirroring characters, as encoded by scripts/generateBidiData.js. Returns an object
+ * holding the `map`, and optionally a `reverseMap` if `includeReverse:true`.
+ * @param {string} encodedString
+ * @param {boolean} includeReverse - true if you want reverseMap in the output
+ * @return {{map: Map<number, number>, reverseMap?: Map<number, number>}}
+ */
+export function parseCharacterMap (encodedString, includeReverse) {
+ const radix = 36
+ let lastCode = 0
+ const map = new Map()
+ const reverseMap = includeReverse && new Map()
+ let prevPair
+ encodedString.split(',').forEach(function visit(entry) {
+ if (entry.indexOf('+') !== -1) {
+ for (let i = +entry; i--;) {
+ visit(prevPair)
+ }
+ } else {
+ prevPair = entry
+ let [a, b] = entry.split('>')
+ a = String.fromCodePoint(lastCode += parseInt(a, radix))
+ b = String.fromCodePoint(lastCode += parseInt(b, radix))
+ map.set(a, b)
+ includeReverse && reverseMap.set(b, a)
+ }
+ })
+ return { map, reverseMap }
+}
generated by cgit v1.2.3 (git 2.25.1) at 2026-02-25 20:02:38 +0000