mirror of
https://github.com/Smaug123/KaTeX
synced 2025-10-06 19:58:40 +00:00
484d44ee70
* Unicode accents * Lexer now looks for combining dicritical marks and adds them to the same character * Parser's `parseSymbol` now recognizes both combined and uncombined forms of Unicode accents, and builds accent objects just like the accent functions * Added CJK support to math mode (not just text mode) * Add invalid combining character test * Add MathML test * Add weak support for other Latin-1 characters This maintains backwards compatibility, but it uses the wrong font. There's a TODO to fix this later. Also refactor symbol code to use for..of * Update Unicode screenshot * Remove dot from accented i and j (in math mode) Also add dotless Unicode characters to support some accented i's and j's * Fix \imath, \jmath, \pounds, and more tests * Switch from for..of to .split().forEach() Save around 800 bytes in minified code * Fix split * normalize() detection * Convert back to vanilla for loops * Fix merge * Move normalize dependency to unicodeMake.js * Make unicodeSymbols into a lookup table instead of macros This is important for multi-accented characters. * Add comments about when to run * Move symbols definition into unicodeMake/Symbols.js * Remove CJK support in text mode * Add missing semicolon * Refactor unicodeAccents to its own file * Dotless i/j support in text mode * Remove excess character mappings * Fix Åå in math mode (still via Times) * Update to support #1030 * Add accented Greek letter support (for supported Greek symbols) * Update screenshot * remove Æ, æ, Ø, ø, and ß from math mode test
404 lines
15 KiB
JavaScript
404 lines
15 KiB
JavaScript
// @flow
|
|
/**
|
|
* Predefined macros for KaTeX.
|
|
* This can be used to define some commands in terms of others.
|
|
*/
|
|
|
|
import fontMetricsData from "./fontMetricsData";
|
|
import symbols from "./symbols";
|
|
import utils from "./utils";
|
|
import {Token} from "./Token";
|
|
|
|
/**
|
|
* Provides context to macros defined by functions. Implemented by
|
|
* MacroExpander.
|
|
*/
|
|
export interface MacroContextInterface {
|
|
/**
|
|
* Returns the topmost token on the stack, without expanding it.
|
|
* Similar in behavior to TeX's `\futurelet`.
|
|
*/
|
|
future(): Token;
|
|
|
|
/**
|
|
* Expand the next token only once (if possible), and return the resulting
|
|
* top token on the stack (without removing anything from the stack).
|
|
* Similar in behavior to TeX's `\expandafter\futurelet`.
|
|
*/
|
|
expandAfterFuture(): Token;
|
|
|
|
/**
|
|
* Consume the specified number of arguments from the token stream,
|
|
* and return the resulting array of arguments.
|
|
*/
|
|
consumeArgs(numArgs: number): Token[][];
|
|
}
|
|
|
|
/** Macro tokens (in reverse order). */
|
|
export type MacroExpansion = {tokens: Token[], numArgs: number};
|
|
|
|
type MacroDefinition = string | MacroExpansion |
|
|
(MacroContextInterface => (string | MacroExpansion));
|
|
export type MacroMap = {[string]: MacroDefinition};
|
|
|
|
const builtinMacros: MacroMap = {};
|
|
export default builtinMacros;
|
|
|
|
// This function might one day accept an additional argument and do more things.
|
|
export function defineMacro(name: string, body: MacroDefinition) {
|
|
builtinMacros[name] = body;
|
|
}
|
|
|
|
//////////////////////////////////////////////////////////////////////
|
|
// macro tools
|
|
|
|
// LaTeX's \@firstoftwo{#1}{#2} expands to #1, skipping #2
|
|
// TeX source: \long\def\@firstoftwo#1#2{#1}
|
|
defineMacro("\\@firstoftwo", function(context) {
|
|
const args = context.consumeArgs(2);
|
|
return {tokens: args[0], numArgs: 0};
|
|
});
|
|
|
|
// LaTeX's \@secondoftwo{#1}{#2} expands to #2, skipping #1
|
|
// TeX source: \long\def\@secondoftwo#1#2{#2}
|
|
defineMacro("\\@secondoftwo", function(context) {
|
|
const args = context.consumeArgs(2);
|
|
return {tokens: args[1], numArgs: 0};
|
|
});
|
|
|
|
// LaTeX's \@ifnextchar{#1}{#2}{#3} looks ahead to the next (unexpanded)
|
|
// symbol. If it matches #1, then the macro expands to #2; otherwise, #3.
|
|
// Note, however, that it does not consume the next symbol in either case.
|
|
defineMacro("\\@ifnextchar", function(context) {
|
|
const args = context.consumeArgs(3); // symbol, if, else
|
|
const nextToken = context.future();
|
|
if (args[0].length === 1 && args[0][0].text === nextToken.text) {
|
|
return {tokens: args[1], numArgs: 0};
|
|
} else {
|
|
return {tokens: args[2], numArgs: 0};
|
|
}
|
|
});
|
|
|
|
// LaTeX's \@ifstar{#1}{#2} looks ahead to the next (unexpanded) symbol.
|
|
// If it is `*`, then it consumes the symbol, and the macro expands to #1;
|
|
// otherwise, the macro expands to #2 (without consuming the symbol).
|
|
// TeX source: \def\@ifstar#1{\@ifnextchar *{\@firstoftwo{#1}}}
|
|
defineMacro("\\@ifstar", "\\@ifnextchar *{\\@firstoftwo{#1}}");
|
|
|
|
// LaTeX's \TextOrMath{#1}{#2} expands to #1 in text mode, #2 in math mode
|
|
defineMacro("\\TextOrMath", function(context) {
|
|
const args = context.consumeArgs(2);
|
|
if (context.mode === 'text') {
|
|
return {tokens: args[0], numArgs: 0};
|
|
} else {
|
|
return {tokens: args[1], numArgs: 0};
|
|
}
|
|
});
|
|
|
|
//////////////////////////////////////////////////////////////////////
|
|
// basics
|
|
defineMacro("\\bgroup", "{");
|
|
defineMacro("\\egroup", "}");
|
|
defineMacro("\\begingroup", "{");
|
|
defineMacro("\\endgroup", "}");
|
|
|
|
// Unicode double-struck letters
|
|
defineMacro("\u2102", "\\mathbb{C}");
|
|
defineMacro("\u210D", "\\mathbb{H}");
|
|
defineMacro("\u2115", "\\mathbb{N}");
|
|
defineMacro("\u2119", "\\mathbb{P}");
|
|
defineMacro("\u211A", "\\mathbb{Q}");
|
|
defineMacro("\u211D", "\\mathbb{R}");
|
|
defineMacro("\u2124", "\\mathbb{Z}");
|
|
|
|
// Unicode middle dot
|
|
// The KaTeX fonts do not contain U+00B7. Instead, \cdotp displays
|
|
// the dot at U+22C5 and gives it punct spacing.
|
|
defineMacro("\u00b7", "\\cdotp");
|
|
|
|
// \llap and \rlap render their contents in text mode
|
|
defineMacro("\\llap", "\\mathllap{\\textrm{#1}}");
|
|
defineMacro("\\rlap", "\\mathrlap{\\textrm{#1}}");
|
|
defineMacro("\\clap", "\\mathclap{\\textrm{#1}}");
|
|
|
|
//////////////////////////////////////////////////////////////////////
|
|
// amsmath.sty
|
|
// http://mirrors.concertpass.com/tex-archive/macros/latex/required/amsmath/amsmath.pdf
|
|
|
|
// \def\overset#1#2{\binrel@{#2}\binrel@@{\mathop{\kern\z@#2}\limits^{#1}}}
|
|
defineMacro("\\overset", "\\mathop{#2}\\limits^{#1}");
|
|
defineMacro("\\underset", "\\mathop{#2}\\limits_{#1}");
|
|
|
|
// \newcommand{\boxed}[1]{\fbox{\m@th$\displaystyle#1$}}
|
|
defineMacro("\\boxed", "\\fbox{\\displaystyle{#1}}");
|
|
|
|
// \def\iff{\DOTSB\;\Longleftrightarrow\;}
|
|
// \def\implies{\DOTSB\;\Longrightarrow\;}
|
|
// \def\impliedby{\DOTSB\;\Longleftarrow\;}
|
|
defineMacro("\\iff", "\\DOTSB\\;\\Longleftrightarrow\\;");
|
|
defineMacro("\\implies", "\\DOTSB\\;\\Longrightarrow\\;");
|
|
defineMacro("\\impliedby", "\\DOTSB\\;\\Longleftarrow\\;");
|
|
|
|
// AMSMath's automatic \dots, based on \mdots@@ macro.
|
|
const dotsByToken = {
|
|
',': '\\dotsc',
|
|
'\\not': '\\dotsb',
|
|
// \keybin@ checks for the following:
|
|
'+': '\\dotsb',
|
|
'=': '\\dotsb',
|
|
'<': '\\dotsb',
|
|
'>': '\\dotsb',
|
|
'-': '\\dotsb',
|
|
'*': '\\dotsb',
|
|
':': '\\dotsb',
|
|
// Symbols whose definition starts with \DOTSB:
|
|
'\\DOTSB': '\\dotsb',
|
|
'\\coprod': '\\dotsb',
|
|
'\\bigvee': '\\dotsb',
|
|
'\\bigwedge': '\\dotsb',
|
|
'\\biguplus': '\\dotsb',
|
|
'\\bigcap': '\\dotsb',
|
|
'\\bigcup': '\\dotsb',
|
|
'\\prod': '\\dotsb',
|
|
'\\sum': '\\dotsb',
|
|
'\\bigotimes': '\\dotsb',
|
|
'\\bigoplus': '\\dotsb',
|
|
'\\bigodot': '\\dotsb',
|
|
'\\bigsqcup': '\\dotsb',
|
|
'\\implies': '\\dotsb',
|
|
'\\impliedby': '\\dotsb',
|
|
'\\And': '\\dotsb',
|
|
'\\longrightarrow': '\\dotsb',
|
|
'\\Longrightarrow': '\\dotsb',
|
|
'\\longleftarrow': '\\dotsb',
|
|
'\\Longleftarrow': '\\dotsb',
|
|
'\\longleftrightarrow': '\\dotsb',
|
|
'\\Longleftrightarrow': '\\dotsb',
|
|
'\\mapsto': '\\dotsb',
|
|
'\\longmapsto': '\\dotsb',
|
|
'\\hookrightarrow': '\\dotsb',
|
|
'\\iff': '\\dotsb',
|
|
'\\doteq': '\\dotsb',
|
|
// Symbols whose definition starts with \mathbin:
|
|
'\\mathbin': '\\dotsb',
|
|
'\\bmod': '\\dotsb',
|
|
// Symbols whose definition starts with \mathrel:
|
|
'\\mathrel': '\\dotsb',
|
|
'\\relbar': '\\dotsb',
|
|
'\\Relbar': '\\dotsb',
|
|
'\\xrightarrow': '\\dotsb',
|
|
'\\xleftarrow': '\\dotsb',
|
|
// Symbols whose definition starts with \DOTSI:
|
|
'\\DOTSI': '\\dotsi',
|
|
'\\int': '\\dotsi',
|
|
'\\oint': '\\dotsi',
|
|
'\\iint': '\\dotsi',
|
|
'\\iiint': '\\dotsi',
|
|
'\\iiiint': '\\dotsi',
|
|
'\\idotsint': '\\dotsi',
|
|
// Symbols whose definition starts with \DOTSX:
|
|
'\\DOTSX': '\\dotsx',
|
|
};
|
|
|
|
defineMacro("\\dots", function(context) {
|
|
// TODO: If used in text mode, should expand to \textellipsis.
|
|
// However, in KaTeX, \textellipsis and \ldots behave the same
|
|
// (in text mode), and it's unlikely we'd see any of the math commands
|
|
// that affect the behavior of \dots when in text mode. So fine for now
|
|
// (until we support \ifmmode ... \else ... \fi).
|
|
let thedots = '\\dotso';
|
|
const next = context.expandAfterFuture().text;
|
|
if (next in dotsByToken) {
|
|
thedots = dotsByToken[next];
|
|
} else if (next.substr(0, 4) === '\\not') {
|
|
thedots = '\\dotsb';
|
|
} else if (next in symbols.math) {
|
|
if (utils.contains(['bin', 'rel'], symbols.math[next].group)) {
|
|
thedots = '\\dotsb';
|
|
}
|
|
}
|
|
return thedots;
|
|
});
|
|
|
|
const spaceAfterDots = {
|
|
// \rightdelim@ checks for the following:
|
|
')': true,
|
|
']': true,
|
|
'\\rbrack': true,
|
|
'\\}': true,
|
|
'\\rbrace': true,
|
|
'\\rangle': true,
|
|
'\\rceil': true,
|
|
'\\rfloor': true,
|
|
'\\rgroup': true,
|
|
'\\rmoustache': true,
|
|
'\\right': true,
|
|
'\\bigr': true,
|
|
'\\biggr': true,
|
|
'\\Bigr': true,
|
|
'\\Biggr': true,
|
|
// \extra@ also tests for the following:
|
|
'$': true,
|
|
// \extrap@ checks for the following:
|
|
';': true,
|
|
'.': true,
|
|
',': true,
|
|
};
|
|
|
|
defineMacro("\\dotso", function(context) {
|
|
const next = context.future().text;
|
|
if (next in spaceAfterDots) {
|
|
return "\\ldots\\,";
|
|
} else {
|
|
return "\\ldots";
|
|
}
|
|
});
|
|
|
|
defineMacro("\\dotsc", function(context) {
|
|
const next = context.future().text;
|
|
// \dotsc uses \extra@ but not \extrap@, instead specially checking for
|
|
// ';' and '.', but doesn't check for ','.
|
|
if (next in spaceAfterDots && next !== ',') {
|
|
return "\\ldots\\,";
|
|
} else {
|
|
return "\\ldots";
|
|
}
|
|
});
|
|
|
|
defineMacro("\\cdots", function(context) {
|
|
const next = context.future().text;
|
|
if (next in spaceAfterDots) {
|
|
return "\\@cdots\\,";
|
|
} else {
|
|
return "\\@cdots";
|
|
}
|
|
});
|
|
|
|
defineMacro("\\dotsb", "\\cdots");
|
|
defineMacro("\\dotsm", "\\cdots");
|
|
defineMacro("\\dotsi", "\\!\\cdots");
|
|
// amsmath doesn't actually define \dotsx, but \dots followed by a macro
|
|
// starting with \DOTSX implies \dotso, and then \extra@ detects this case
|
|
// and forces the added `\,`.
|
|
defineMacro("\\dotsx", "\\ldots\\,");
|
|
|
|
// \let\DOTSI\relax
|
|
// \let\DOTSB\relax
|
|
// \let\DOTSX\relax
|
|
defineMacro("\\DOTSI", "\\relax");
|
|
defineMacro("\\DOTSB", "\\relax");
|
|
defineMacro("\\DOTSX", "\\relax");
|
|
|
|
// http://texdoc.net/texmf-dist/doc/latex/amsmath/amsmath.pdf
|
|
defineMacro("\\thinspace", "\\,"); // \let\thinspace\,
|
|
defineMacro("\\medspace", "\\:"); // \let\medspace\:
|
|
defineMacro("\\thickspace", "\\;"); // \let\thickspace\;
|
|
|
|
//////////////////////////////////////////////////////////////////////
|
|
// LaTeX source2e
|
|
|
|
// \def\TeX{T\kern-.1667em\lower.5ex\hbox{E}\kern-.125emX\@}
|
|
// TODO: Doesn't normally work in math mode because \@ fails. KaTeX doesn't
|
|
// support \@ yet, so that's omitted, and we add \text so that the result
|
|
// doesn't look funny in math mode.
|
|
defineMacro("\\TeX", "\\textrm{T\\kern-.1667em\\raisebox{-.5ex}{E}\\kern-.125emX}");
|
|
|
|
// \DeclareRobustCommand{\LaTeX}{L\kern-.36em%
|
|
// {\sbox\z@ T%
|
|
// \vbox to\ht\z@{\hbox{\check@mathfonts
|
|
// \fontsize\sf@size\z@
|
|
// \math@fontsfalse\selectfont
|
|
// A}%
|
|
// \vss}%
|
|
// }%
|
|
// \kern-.15em%
|
|
// \TeX}
|
|
// This code aligns the top of the A with the T (from the perspective of TeX's
|
|
// boxes, though visually the A appears to extend above slightly).
|
|
// We compute the corresponding \raisebox when A is rendered at \scriptsize,
|
|
// which is size3, which has a scale factor of 0.7 (see Options.js).
|
|
const latexRaiseA = fontMetricsData['Main-Regular']["T".charCodeAt(0)][1] -
|
|
0.7 * fontMetricsData['Main-Regular']["A".charCodeAt(0)][1] + "em";
|
|
defineMacro("\\LaTeX",
|
|
`\\textrm{L\\kern-.36em\\raisebox{${latexRaiseA}}{\\scriptsize A}` +
|
|
"\\kern-.15em\\TeX}");
|
|
|
|
// New KaTeX logo based on tweaking LaTeX logo
|
|
defineMacro("\\KaTeX",
|
|
`\\textrm{K\\kern-.17em\\raisebox{${latexRaiseA}}{\\scriptsize A}` +
|
|
"\\kern-.15em\\TeX}");
|
|
|
|
// \DeclareRobustCommand\hspace{\@ifstar\@hspacer\@hspace}
|
|
// \def\@hspace#1{\hskip #1\relax}
|
|
// KaTeX doesn't do line breaks, so \hspace and \hspace* are the same as \kern
|
|
defineMacro("\\hspace", "\\@ifstar\\kern\\kern");
|
|
|
|
//////////////////////////////////////////////////////////////////////
|
|
// mathtools.sty
|
|
|
|
//\providecommand\ordinarycolon{:}
|
|
defineMacro("\\ordinarycolon", ":");
|
|
//\def\vcentcolon{\mathrel{\mathop\ordinarycolon}}
|
|
//TODO(edemaine): Not yet centered. Fix via \raisebox or #726
|
|
defineMacro("\\vcentcolon", "\\mathrel{\\mathop\\ordinarycolon}");
|
|
// \providecommand*\dblcolon{\vcentcolon\mathrel{\mkern-.9mu}\vcentcolon}
|
|
defineMacro("\\dblcolon", "\\vcentcolon\\mathrel{\\mkern-.9mu}\\vcentcolon");
|
|
// \providecommand*\coloneqq{\vcentcolon\mathrel{\mkern-1.2mu}=}
|
|
defineMacro("\\coloneqq", "\\vcentcolon\\mathrel{\\mkern-1.2mu}=");
|
|
// \providecommand*\Coloneqq{\dblcolon\mathrel{\mkern-1.2mu}=}
|
|
defineMacro("\\Coloneqq", "\\dblcolon\\mathrel{\\mkern-1.2mu}=");
|
|
// \providecommand*\coloneq{\vcentcolon\mathrel{\mkern-1.2mu}\mathrel{-}}
|
|
defineMacro("\\coloneq", "\\vcentcolon\\mathrel{\\mkern-1.2mu}\\mathrel{-}");
|
|
// \providecommand*\Coloneq{\dblcolon\mathrel{\mkern-1.2mu}\mathrel{-}}
|
|
defineMacro("\\Coloneq", "\\dblcolon\\mathrel{\\mkern-1.2mu}\\mathrel{-}");
|
|
// \providecommand*\eqqcolon{=\mathrel{\mkern-1.2mu}\vcentcolon}
|
|
defineMacro("\\eqqcolon", "=\\mathrel{\\mkern-1.2mu}\\vcentcolon");
|
|
// \providecommand*\Eqqcolon{=\mathrel{\mkern-1.2mu}\dblcolon}
|
|
defineMacro("\\Eqqcolon", "=\\mathrel{\\mkern-1.2mu}\\dblcolon");
|
|
// \providecommand*\eqcolon{\mathrel{-}\mathrel{\mkern-1.2mu}\vcentcolon}
|
|
defineMacro("\\eqcolon", "\\mathrel{-}\\mathrel{\\mkern-1.2mu}\\vcentcolon");
|
|
// \providecommand*\Eqcolon{\mathrel{-}\mathrel{\mkern-1.2mu}\dblcolon}
|
|
defineMacro("\\Eqcolon", "\\mathrel{-}\\mathrel{\\mkern-1.2mu}\\dblcolon");
|
|
// \providecommand*\colonapprox{\vcentcolon\mathrel{\mkern-1.2mu}\approx}
|
|
defineMacro("\\colonapprox", "\\vcentcolon\\mathrel{\\mkern-1.2mu}\\approx");
|
|
// \providecommand*\Colonapprox{\dblcolon\mathrel{\mkern-1.2mu}\approx}
|
|
defineMacro("\\Colonapprox", "\\dblcolon\\mathrel{\\mkern-1.2mu}\\approx");
|
|
// \providecommand*\colonsim{\vcentcolon\mathrel{\mkern-1.2mu}\sim}
|
|
defineMacro("\\colonsim", "\\vcentcolon\\mathrel{\\mkern-1.2mu}\\sim");
|
|
// \providecommand*\Colonsim{\dblcolon\mathrel{\mkern-1.2mu}\sim}
|
|
defineMacro("\\Colonsim", "\\dblcolon\\mathrel{\\mkern-1.2mu}\\sim");
|
|
|
|
//////////////////////////////////////////////////////////////////////
|
|
// colonequals.sty
|
|
|
|
// Alternate names for mathtools's macros:
|
|
defineMacro("\\ratio", "\\vcentcolon");
|
|
defineMacro("\\coloncolon", "\\dblcolon");
|
|
defineMacro("\\colonequals", "\\coloneqq");
|
|
defineMacro("\\coloncolonequals", "\\Coloneqq");
|
|
defineMacro("\\equalscolon", "\\eqqcolon");
|
|
defineMacro("\\equalscoloncolon", "\\Eqqcolon");
|
|
defineMacro("\\colonminus", "\\coloneq");
|
|
defineMacro("\\coloncolonminus", "\\Coloneq");
|
|
defineMacro("\\minuscolon", "\\eqcolon");
|
|
defineMacro("\\minuscoloncolon", "\\Eqcolon");
|
|
// \colonapprox name is same in mathtools and colonequals.
|
|
defineMacro("\\coloncolonapprox", "\\Colonapprox");
|
|
// \colonsim name is same in mathtools and colonequals.
|
|
defineMacro("\\coloncolonsim", "\\Colonsim");
|
|
|
|
// Additional macros, implemented by analogy with mathtools definitions:
|
|
defineMacro("\\simcolon", "\\sim\\mathrel{\\mkern-1.2mu}\\vcentcolon");
|
|
defineMacro("\\simcoloncolon", "\\sim\\mathrel{\\mkern-1.2mu}\\dblcolon");
|
|
defineMacro("\\approxcolon", "\\approx\\mathrel{\\mkern-1.2mu}\\vcentcolon");
|
|
defineMacro("\\approxcoloncolon",
|
|
"\\approx\\mathrel{\\mkern-1.2mu}\\dblcolon");
|
|
|
|
// Present in newtxmath, pxfonts and txfonts
|
|
// TODO: The unicode character U+220C ∌ should be added to the font, and this
|
|
// macro turned into a propper defineSymbol in symbols.js. That way, the
|
|
// MathML result will be much cleaner.
|
|
defineMacro("\\notni", "\\not\\ni");
|
|
defineMacro("\\limsup", "\\DOTSB\\mathop{\\operatorname{lim\\,sup}}\\limits");
|
|
defineMacro("\\liminf", "\\DOTSB\\mathop{\\operatorname{lim\\,inf}}\\limits");
|