temml 0.9.1

package/src/tree.js

@@ -0,0 +1,50 @@
+/**
+ * This node represents a document fragment, which contains elements, but when
+ * placed into the DOM doesn't have any representation itself. It only contains
+ * children and doesn't have any DOM node properties.
+ */
+export class DocumentFragment {
+  constructor(children) {
+    this.children = children;
+    this.classes = [];
+    this.style = {};
+  }
+
+  hasClass(className) {
+    return this.classes.includes(className);
+  }
+
+  /** Convert the fragment into a node. */
+  toNode() {
+    const frag = document.createDocumentFragment();
+
+    for (let i = 0; i < this.children.length; i++) {
+      frag.appendChild(this.children[i].toNode());
+    }
+
+    return frag;
+  }
+
+  /** Convert the fragment into HTML markup. */
+  toMarkup() {
+    let markup = "";
+
+    // Simply concatenate the markup for the children together.
+    for (let i = 0; i < this.children.length; i++) {
+      markup += this.children[i].toMarkup();
+    }
+
+    return markup;
+  }
+
+  /**
+   * Converts the math node into a string, similar to innerText. Applies to
+   * MathDomNode's only.
+   */
+  toText() {
+    // To avoid this, we would subclass documentFragment separately for
+    // MathML, but polyfills for subclassing is expensive per PR 1469.
+    const toText = (child) => child.toText();
+    return this.children.map(toText).join("");
+  }
+}

package/src/unicodeAccents.js

@@ -0,0 +1,16 @@
+// Mapping of Unicode accent characters to their LaTeX equivalent in text and
+// math mode (when they exist).
+export default {
+  "\u0301": { text: "\\'", math: "\\acute" },
+  "\u0300": { text: "\\`", math: "\\grave" },
+  "\u0308": { text: '\\"', math: "\\ddot" },
+  "\u0303": { text: "\\~", math: "\\tilde" },
+  "\u0304": { text: "\\=", math: "\\bar" },
+  "\u0306": { text: "\\u", math: "\\breve" },
+  "\u030c": { text: "\\v", math: "\\check" },
+  "\u0302": { text: "\\^", math: "\\hat" },
+  "\u0307": { text: "\\.", math: "\\dot" },
+  "\u030a": { text: "\\r", math: "\\mathring" },
+  "\u030b": { text: "\\H" },
+  '\u0327': { text: '\\c' }
+};

package/src/unicodeScripts.js

@@ -0,0 +1,119 @@
+/*
+ * This file defines the Unicode scripts and script families that we
+ * support. To add new scripts or families, just add a new entry to the
+ * scriptData array below. Adding scripts to the scriptData array allows
+ * characters from that script to appear in \text{} environments.
+ */
+
+/**
+ * Each script or script family has a name and an array of blocks.
+ * Each block is an array of two numbers which specify the start and
+ * end points (inclusive) of a block of Unicode codepoints.
+
+/**
+ * Unicode block data for the families of scripts we support in \text{}.
+ * Scripts only need to appear here if they do not have font metrics.
+ */
+const scriptData = [
+  {
+    // Latin characters beyond the Latin-1 characters we have metrics for.
+    // Needed for Czech, Hungarian and Turkish text, for example.
+    name: "latin",
+    blocks: [
+      [0x0100, 0x024f], // Latin Extended-A and Latin Extended-B
+      [0x0300, 0x036f] // Combining Diacritical marks
+    ]
+  },
+  {
+    // The Cyrillic script used by Russian and related languages.
+    // A Cyrillic subset used to be supported as explicitly defined
+    // symbols in symbols.js
+    name: "cyrillic",
+    blocks: [[0x0400, 0x04ff]]
+  },
+  {
+    // Armenian
+    name: "armenian",
+    blocks: [[0x0530, 0x058f]]
+  },
+  {
+    // The Brahmic scripts of South and Southeast Asia
+    // Devanagari (0900–097F)
+    // Bengali (0980–09FF)
+    // Gurmukhi (0A00–0A7F)
+    // Gujarati (0A80–0AFF)
+    // Oriya (0B00–0B7F)
+    // Tamil (0B80–0BFF)
+    // Telugu (0C00–0C7F)
+    // Kannada (0C80–0CFF)
+    // Malayalam (0D00–0D7F)
+    // Sinhala (0D80–0DFF)
+    // Thai (0E00–0E7F)
+    // Lao (0E80–0EFF)
+    // Tibetan (0F00–0FFF)
+    // Myanmar (1000–109F)
+    name: "brahmic",
+    blocks: [[0x0900, 0x109f]]
+  },
+  {
+    name: "georgian",
+    blocks: [[0x10a0, 0x10ff]]
+  },
+  {
+    // Chinese and Japanese.
+    // The "k" in cjk is for Korean, but we've separated Korean out
+    name: "cjk",
+    blocks: [
+      [0x3000, 0x30ff], // CJK symbols and punctuation, Hiragana, Katakana
+      [0x4e00, 0x9faf], // CJK ideograms
+      [0xff00, 0xff60] // Fullwidth punctuation
+      // TODO: add halfwidth Katakana and Romanji glyphs
+    ]
+  },
+  {
+    // Korean
+    name: "hangul",
+    blocks: [[0xac00, 0xd7af]]
+  }
+];
+
+/**
+ * Given a codepoint, return the name of the script or script family
+ * it is from, or null if it is not part of a known block
+ */
+export function scriptFromCodepoint(codepoint) {
+  for (let i = 0; i < scriptData.length; i++) {
+    const script = scriptData[i];
+    for (let i = 0; i < script.blocks.length; i++) {
+      const block = script.blocks[i];
+      if (codepoint >= block[0] && codepoint <= block[1]) {
+        return script.name;
+      }
+    }
+  }
+  return null;
+}
+
+/**
+ * A flattened version of all the supported blocks in a single array.
+ * This is an optimization to make supportedCodepoint() fast.
+ */
+const allBlocks = [];
+scriptData.forEach((s) => s.blocks.forEach((b) => allBlocks.push(...b)));
+
+/**
+ * Given a codepoint, return true if it falls within one of the
+ * scripts or script families defined above and false otherwise.
+ *
+ * Micro benchmarks shows that this is faster than
+ * /[\u3000-\u30FF\u4E00-\u9FAF\uFF00-\uFF60\uAC00-\uD7AF\u0900-\u109F]/.test()
+ * in Firefox, Chrome and Node.
+ */
+export function supportedCodepoint(codepoint) {
+  for (let i = 0; i < allBlocks.length; i += 2) {
+    if (codepoint >= allBlocks[i] && codepoint <= allBlocks[i + 1]) {
+      return true;
+    }
+  }
+  return false;
+}

package/src/unicodeSupOrSub.js

@@ -0,0 +1,108 @@
+// Helpers for Parser.js handling of Unicode (sub|super)script characters.
+
+export const unicodeSubRegEx = /^[₊₋₌₍₎₀₁₂₃₄₅₆₇₈₉ₐₑₕᵢⱼₖₗₘₙₒₚᵣₛₜᵤᵥₓᵦᵧᵨᵩᵪ]/
+
+export const uSubsAndSups = Object.freeze({
+  '₊': '+',
+  '₋': '-',
+  '₌': '=',
+  '₍': '(',
+  '₎': ')',
+  '₀': '0',
+  '₁': '1',
+  '₂': '2',
+  '₃': '3',
+  '₄': '4',
+  '₅': '5',
+  '₆': '6',
+  '₇': '7',
+  '₈': '8',
+  '₉': '9',
+  '\u2090': 'a',
+  '\u2091': 'e',
+  '\u2095': 'h',
+  '\u1D62': 'i',
+  '\u2C7C': 'j',
+  '\u2096': 'k',
+  '\u2097': 'l',
+  '\u2098': 'm',
+  '\u2099': 'n',
+  '\u2092': 'o',
+  '\u209A': 'p',
+  '\u1D63': 'r',
+  '\u209B': 's',
+  '\u209C': 't',
+  '\u1D64': 'u',
+  '\u1D65': 'v',
+  '\u2093': 'x',
+  '\u1D66': 'β',
+  '\u1D67': 'γ',
+  '\u1D68': 'ρ',
+  '\u1D69': '\u03d5',
+  '\u1D6A': 'χ',
+  '⁺': '+',
+  '⁻': '-',
+  '⁼': '=',
+  '⁽': '(',
+  '⁾': ')',
+  '⁰': '0',
+  '¹': '1',
+  '²': '2',
+  '³': '3',
+  '⁴': '4',
+  '⁵': '5',
+  '⁶': '6',
+  '⁷': '7',
+  '⁸': '8',
+  '⁹': '9',
+  '\u1D2C': 'A',
+  '\u1D2E': 'B',
+  '\u1D30': 'D',
+  '\u1D31': 'E',
+  '\u1D33': 'G',
+  '\u1D34': 'H',
+  '\u1D35': 'I',
+  '\u1D36': 'J',
+  '\u1D37': 'K',
+  '\u1D38': 'L',
+  '\u1D39': 'M',
+  '\u1D3A': 'N',
+  '\u1D3C': 'O',
+  '\u1D3E': 'P',
+  '\u1D3F': 'R',
+  '\u1D40': 'T',
+  '\u1D41': 'U',
+  '\u2C7D': 'V',
+  '\u1D42': 'W',
+  '\u1D43': 'a',
+  '\u1D47': 'b',
+  '\u1D9C': 'c',
+  '\u1D48': 'd',
+  '\u1D49': 'e',
+  '\u1DA0': 'f',
+  '\u1D4D': 'g',
+  '\u02B0': 'h',
+  '\u2071': 'i',
+  '\u02B2': 'j',
+  '\u1D4F': 'k',
+  '\u02E1': 'l',
+  '\u1D50': 'm',
+  '\u207F': 'n',
+  '\u1D52': 'o',
+  '\u1D56': 'p',
+  '\u02B3': 'r',
+  '\u02E2': 's',
+  '\u1D57': 't',
+  '\u1D58': 'u',
+  '\u1D5B': 'v',
+  '\u02B7': 'w',
+  '\u02E3': 'x',
+  '\u02B8': 'y',
+  '\u1DBB': 'z',
+  '\u1D5D': 'β',
+  '\u1D5E': 'γ',
+  '\u1D5F': 'δ',
+  '\u1D60': '\u03d5',
+  '\u1D61': 'χ',
+  '\u1DBF': 'θ'
+})

package/src/unicodeSymbolBuilder.js

@@ -0,0 +1,31 @@
+// This is an internal module, not part of the Temml distribution,
+// whose purpose is to generate `unicodeSymbols` for Parser.js
+// In this way, only this module, and not the distribution/browser,
+// needs String's normalize function.
+import * as accents from "./unicodeAccents";
+
+const result = {};
+const letters =
+  "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ" +
+  "αβγδεϵζηθϑικλμνξοπϖρϱςστυφϕχψωΓΔΘΛΞΠΣΥΦΨΩ";
+for (const letter of letters) {
+  for (const accent of Object.getOwnPropertyNames(accents)) {
+    const combined = letter + accent;
+    const normalized = combined.normalize("NFC");
+    if (normalized.length === 1) {
+      result[normalized] = combined;
+    }
+    for (const accent2 of Object.getOwnPropertyNames(accents)) {
+      if (accent === accent2) {
+        continue;
+      }
+      const combined2 = combined + accent2;
+      const normalized2 = combined2.normalize("NFC");
+      if (normalized2.length === 1) {
+        result[normalized2] = combined2;
+      }
+    }
+  }
+}
+
+export default result;

package/src/unicodeSymbols.js

@@ -0,0 +1,320 @@
+export default {
+  "á": "á",
+  "à": "à",
+  "ä": "ä",
+  "ǟ": "ǟ",
+  "ã": "ã",
+  "ā": "ā",
+  "ă": "ă",
+  "ắ": "ắ",
+  "ằ": "ằ",
+  "ẵ": "ẵ",
+  "ǎ": "ǎ",
+  "â": "â",
+  "ấ": "ấ",
+  "ầ": "ầ",
+  "ẫ": "ẫ",
+  "ȧ": "ȧ",
+  "ǡ": "ǡ",
+  "å": "å",
+  "ǻ": "ǻ",
+  "ḃ": "ḃ",
+  "ć": "ć",
+  "č": "č",
+  "ĉ": "ĉ",
+  "ċ": "ċ",
+  "ď": "ď",
+  "ḋ": "ḋ",
+  "é": "é",
+  "è": "è",
+  "ë": "ë",
+  "ẽ": "ẽ",
+  "ē": "ē",
+  "ḗ": "ḗ",
+  "ḕ": "ḕ",
+  "ĕ": "ĕ",
+  "ě": "ě",
+  "ê": "ê",
+  "ế": "ế",
+  "ề": "ề",
+  "ễ": "ễ",
+  "ė": "ė",
+  "ḟ": "ḟ",
+  "ǵ": "ǵ",
+  "ḡ": "ḡ",
+  "ğ": "ğ",
+  "ǧ": "ǧ",
+  "ĝ": "ĝ",
+  "ġ": "ġ",
+  "ḧ": "ḧ",
+  "ȟ": "ȟ",
+  "ĥ": "ĥ",
+  "ḣ": "ḣ",
+  "í": "í",
+  "ì": "ì",
+  "ï": "ï",
+  "ḯ": "ḯ",
+  "ĩ": "ĩ",
+  "ī": "ī",
+  "ĭ": "ĭ",
+  "ǐ": "ǐ",
+  "î": "î",
+  "ǰ": "ǰ",
+  "ĵ": "ĵ",
+  "ḱ": "ḱ",
+  "ǩ": "ǩ",
+  "ĺ": "ĺ",
+  "ľ": "ľ",
+  "ḿ": "ḿ",
+  "ṁ": "ṁ",
+  "ń": "ń",
+  "ǹ": "ǹ",
+  "ñ": "ñ",
+  "ň": "ň",
+  "ṅ": "ṅ",
+  "ó": "ó",
+  "ò": "ò",
+  "ö": "ö",
+  "ȫ": "ȫ",
+  "õ": "õ",
+  "ṍ": "ṍ",
+  "ṏ": "ṏ",
+  "ȭ": "ȭ",
+  "ō": "ō",
+  "ṓ": "ṓ",
+  "ṑ": "ṑ",
+  "ŏ": "ŏ",
+  "ǒ": "ǒ",
+  "ô": "ô",
+  "ố": "ố",
+  "ồ": "ồ",
+  "ỗ": "ỗ",
+  "ȯ": "ȯ",
+  "ȱ": "ȱ",
+  "ő": "ő",
+  "ṕ": "ṕ",
+  "ṗ": "ṗ",
+  "ŕ": "ŕ",
+  "ř": "ř",
+  "ṙ": "ṙ",
+  "ś": "ś",
+  "ṥ": "ṥ",
+  "š": "š",
+  "ṧ": "ṧ",
+  "ŝ": "ŝ",
+  "ṡ": "ṡ",
+  "ẗ": "ẗ",
+  "ť": "ť",
+  "ṫ": "ṫ",
+  "ú": "ú",
+  "ù": "ù",
+  "ü": "ü",
+  "ǘ": "ǘ",
+  "ǜ": "ǜ",
+  "ǖ": "ǖ",
+  "ǚ": "ǚ",
+  "ũ": "ũ",
+  "ṹ": "ṹ",
+  "ū": "ū",
+  "ṻ": "ṻ",
+  "ŭ": "ŭ",
+  "ǔ": "ǔ",
+  "û": "û",
+  "ů": "ů",
+  "ű": "ű",
+  "ṽ": "ṽ",
+  "ẃ": "ẃ",
+  "ẁ": "ẁ",
+  "ẅ": "ẅ",
+  "ŵ": "ŵ",
+  "ẇ": "ẇ",
+  "ẘ": "ẘ",
+  "ẍ": "ẍ",
+  "ẋ": "ẋ",
+  "ý": "ý",
+  "ỳ": "ỳ",
+  "ÿ": "ÿ",
+  "ỹ": "ỹ",
+  "ȳ": "ȳ",
+  "ŷ": "ŷ",
+  "ẏ": "ẏ",
+  "ẙ": "ẙ",
+  "ź": "ź",
+  "ž": "ž",
+  "ẑ": "ẑ",
+  "ż": "ż",
+  "Á": "Á",
+  "À": "À",
+  "Ä": "Ä",
+  "Ǟ": "Ǟ",
+  "Ã": "Ã",
+  "Ā": "Ā",
+  "Ă": "Ă",
+  "Ắ": "Ắ",
+  "Ằ": "Ằ",
+  "Ẵ": "Ẵ",
+  "Ǎ": "Ǎ",
+  "Â": "Â",
+  "Ấ": "Ấ",
+  "Ầ": "Ầ",
+  "Ẫ": "Ẫ",
+  "Ȧ": "Ȧ",
+  "Ǡ": "Ǡ",
+  "Å": "Å",
+  "Ǻ": "Ǻ",
+  "Ḃ": "Ḃ",
+  "Ć": "Ć",
+  "Č": "Č",
+  "Ĉ": "Ĉ",
+  "Ċ": "Ċ",
+  "Ď": "Ď",
+  "Ḋ": "Ḋ",
+  "É": "É",
+  "È": "È",
+  "Ë": "Ë",
+  "Ẽ": "Ẽ",
+  "Ē": "Ē",
+  "Ḗ": "Ḗ",
+  "Ḕ": "Ḕ",
+  "Ĕ": "Ĕ",
+  "Ě": "Ě",
+  "Ê": "Ê",
+  "Ế": "Ế",
+  "Ề": "Ề",
+  "Ễ": "Ễ",
+  "Ė": "Ė",
+  "Ḟ": "Ḟ",
+  "Ǵ": "Ǵ",
+  "Ḡ": "Ḡ",
+  "Ğ": "Ğ",
+  "Ǧ": "Ǧ",
+  "Ĝ": "Ĝ",
+  "Ġ": "Ġ",
+  "Ḧ": "Ḧ",
+  "Ȟ": "Ȟ",
+  "Ĥ": "Ĥ",
+  "Ḣ": "Ḣ",
+  "Í": "Í",
+  "Ì": "Ì",
+  "Ï": "Ï",
+  "Ḯ": "Ḯ",
+  "Ĩ": "Ĩ",
+  "Ī": "Ī",
+  "Ĭ": "Ĭ",
+  "Ǐ": "Ǐ",
+  "Î": "Î",
+  "İ": "İ",
+  "Ĵ": "Ĵ",
+  "Ḱ": "Ḱ",
+  "Ǩ": "Ǩ",
+  "Ĺ": "Ĺ",
+  "Ľ": "Ľ",
+  "Ḿ": "Ḿ",
+  "Ṁ": "Ṁ",
+  "Ń": "Ń",
+  "Ǹ": "Ǹ",
+  "Ñ": "Ñ",
+  "Ň": "Ň",
+  "Ṅ": "Ṅ",
+  "Ó": "Ó",
+  "Ò": "Ò",
+  "Ö": "Ö",
+  "Ȫ": "Ȫ",
+  "Õ": "Õ",
+  "Ṍ": "Ṍ",
+  "Ṏ": "Ṏ",
+  "Ȭ": "Ȭ",
+  "Ō": "Ō",
+  "Ṓ": "Ṓ",
+  "Ṑ": "Ṑ",
+  "Ŏ": "Ŏ",
+  "Ǒ": "Ǒ",
+  "Ô": "Ô",
+  "Ố": "Ố",
+  "Ồ": "Ồ",
+  "Ỗ": "Ỗ",
+  "Ȯ": "Ȯ",
+  "Ȱ": "Ȱ",
+  "Ő": "Ő",
+  "Ṕ": "Ṕ",
+  "Ṗ": "Ṗ",
+  "Ŕ": "Ŕ",
+  "Ř": "Ř",
+  "Ṙ": "Ṙ",
+  "Ś": "Ś",
+  "Ṥ": "Ṥ",
+  "Š": "Š",
+  "Ṧ": "Ṧ",
+  "Ŝ": "Ŝ",
+  "Ṡ": "Ṡ",
+  "Ť": "Ť",
+  "Ṫ": "Ṫ",
+  "Ú": "Ú",
+  "Ù": "Ù",
+  "Ü": "Ü",
+  "Ǘ": "Ǘ",
+  "Ǜ": "Ǜ",
+  "Ǖ": "Ǖ",
+  "Ǚ": "Ǚ",
+  "Ũ": "Ũ",
+  "Ṹ": "Ṹ",
+  "Ū": "Ū",
+  "Ṻ": "Ṻ",
+  "Ŭ": "Ŭ",
+  "Ǔ": "Ǔ",
+  "Û": "Û",
+  "Ů": "Ů",
+  "Ű": "Ű",
+  "Ṽ": "Ṽ",
+  "Ẃ": "Ẃ",
+  "Ẁ": "Ẁ",
+  "Ẅ": "Ẅ",
+  "Ŵ": "Ŵ",
+  "Ẇ": "Ẇ",
+  "Ẍ": "Ẍ",
+  "Ẋ": "Ẋ",
+  "Ý": "Ý",
+  "Ỳ": "Ỳ",
+  "Ÿ": "Ÿ",
+  "Ỹ": "Ỹ",
+  "Ȳ": "Ȳ",
+  "Ŷ": "Ŷ",
+  "Ẏ": "Ẏ",
+  "Ź": "Ź",
+  "Ž": "Ž",
+  "Ẑ": "Ẑ",
+  "Ż": "Ż",
+  "ά": "ά",
+  "ὰ": "ὰ",
+  "ᾱ": "ᾱ",
+  "ᾰ": "ᾰ",
+  "έ": "έ",
+  "ὲ": "ὲ",
+  "ή": "ή",
+  "ὴ": "ὴ",
+  "ί": "ί",
+  "ὶ": "ὶ",
+  "ϊ": "ϊ",
+  "ΐ": "ΐ",
+  "ῒ": "ῒ",
+  "ῑ": "ῑ",
+  "ῐ": "ῐ",
+  "ό": "ό",
+  "ὸ": "ὸ",
+  "ύ": "ύ",
+  "ὺ": "ὺ",
+  "ϋ": "ϋ",
+  "ΰ": "ΰ",
+  "ῢ": "ῢ",
+  "ῡ": "ῡ",
+  "ῠ": "ῠ",
+  "ώ": "ώ",
+  "ὼ": "ὼ",
+  "Ύ": "Ύ",
+  "Ὺ": "Ὺ",
+  "Ϋ": "Ϋ",
+  "Ῡ": "Ῡ",
+  "Ῠ": "Ῠ",
+  "Ώ": "Ώ",
+  "Ὼ": "Ὼ"
+};