temml 0.10.8 → 0.10.10

package/dist/temml.mjs

@@ -11233,109 +11233,6 @@ class MacroExpander {
   }
 }
 
-/*
- * 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]]
-  }
-];
-
-/**
- * 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.
- */
-function supportedCodepoint(codepoint) {
-  for (let i = 0; i < allBlocks.length; i += 2) {
-    if (codepoint >= allBlocks[i] && codepoint <= allBlocks[i + 1]) {
-      return true;
-    }
-  }
-  return false;
-}
-
 // Helpers for Parser.js handling of Unicode (sub|super)script characters.
 
 const unicodeSubRegEx = /^[₊₋₌₍₎₀₁₂₃₄₅₆₇₈₉ₐₑₕᵢⱼₖₗₘₙₒₚᵣₛₜᵤᵥₓᵦᵧᵨᵩᵪ]/;
@@ -11459,7 +11356,7 @@ const asciiFromScript = Object.freeze({
   "\ud835\udca5": "J",
   "\ud835\udca6": "K",
   "\u2112": "L",
-  "\u2113": "M",
+  "\u2133": "M",
   "\ud835\udca9": "N",
   "\ud835\udcaa": "O",
   "\ud835\udcab": "P",
@@ -12738,13 +12635,8 @@ class Parser {
       symbol = s;
     } else if (text.charCodeAt(0) >= 0x80) {
       // no symbol for e.g. ^
-      if (this.settings.strict) {
-        if (!supportedCodepoint(text.charCodeAt(0))) {
-          throw new ParseError(`Unrecognized Unicode character "${text[0]}"` +
-          ` (${text.charCodeAt(0)})`, nucleus);
-        } else if (this.mode === "math") {
-          throw new ParseError(`Unicode text character "${text[0]}" used in math mode`, nucleus)
-        }
+      if (this.settings.strict && this.mode === "math") {
+        throw new ParseError(`Unicode text character "${text[0]}" used in math mode`, nucleus)
       }
       // All nonmathematical Unicode characters are rendered as if they
       // are in text mode (wrapped in \text) because that's what it
@@ -12975,7 +12867,7 @@ class Style {
  * https://mit-license.org/
  */
 
-const version = "0.10.8";
+const version = "0.10.10";
 
 function postProcess(block) {
   const labelMap = {};

package/dist/temmlPostProcess.js

@@ -14,7 +14,7 @@
    * https://mit-license.org/
    */
 
-  const version = "0.10.8";
+  const version = "0.10.10";
 
   function postProcess(block) {
     const labelMap = {};

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "temml",
-  "version": "0.10.8",
+  "version": "0.10.10",
   "description": "TeX to MathML conversion in JavaScript.",
   "main": "dist/temml.js",
   "exports": {

package/src/Parser.js

@@ -3,7 +3,6 @@ import functions from "./functions";
 import MacroExpander, { implicitCommands } from "./MacroExpander";
 import symbols, { ATOMS } from "./symbols";
 import { validUnit } from "./units";
-import { supportedCodepoint } from "./unicodeScripts";
 import ParseError from "./ParseError";
 import { combiningDiacriticalMarksEndRegex } from "./Lexer";
 import { uSubsAndSups, unicodeSubRegEx } from "./unicodeSupOrSub"
@@ -939,13 +938,8 @@ export default class Parser {
       symbol = s;
     } else if (text.charCodeAt(0) >= 0x80) {
       // no symbol for e.g. ^
-      if (this.settings.strict) {
-        if (!supportedCodepoint(text.charCodeAt(0))) {
-          throw new ParseError(`Unrecognized Unicode character "${text[0]}"` +
-          ` (${text.charCodeAt(0)})`, nucleus);
-        } else if (this.mode === "math") {
-          throw new ParseError(`Unicode text character "${text[0]}" used in math mode`, nucleus)
-        }
+      if (this.settings.strict && this.mode === "math") {
+        throw new ParseError(`Unicode text character "${text[0]}" used in math mode`, nucleus)
       }
       // All nonmathematical Unicode characters are rendered as if they
       // are in text mode (wrapped in \text) because that's what it

package/src/asciiFromScript.js

@@ -12,7 +12,7 @@ export const asciiFromScript = Object.freeze({
   "\ud835\udca5": "J",
   "\ud835\udca6": "K",
   "\u2112": "L",
-  "\u2113": "M",
+  "\u2133": "M",
   "\ud835\udca9": "N",
   "\ud835\udcaa": "O",
   "\ud835\udcab": "P",

package/src/postProcess.js

@@ -8,7 +8,7 @@
  * https://mit-license.org/
  */
 
-export const version = "0.10.8";
+export const version = "0.10.10";
 
 export function postProcess(block) {
   const labelMap = {}

package/src/unicodeScripts.js

@@ -1,119 +0,0 @@
-/*
- * 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;
-}