quartz-research-note/quartz/plugins/transformers/oxhugofm.ts
Hrishikesh Barman 2f99339dcf
feat: add transformations for latex in oxhugofm (#510)
ox-hugo currently supports the following syntax for latex equations:
- https://orgmode.org/manual/LaTeX-fragments.html
- https://ox-hugo.scripter.co/doc/equations

This syntax is supported by mathjax as is mentioned in the ox-hugo documentation.

But quartz uses remark-math which has some issues with the \( \) syntax.
See https://github.com/remarkjs/remark-math/issues/39

This change adds few more transformations to the OxHugoFlavouredMarkdown
plugin, which makes a best effort conversion of this syntax into what
the Quartz Latex transformer plugin supports.

With these changes, the generated files show latex formatting with
default quartz configuration.

Sidenote on `\_` escape by ox-hugo:

ox-hugo escapes, _ using \_, we match against it after we transform
equations into what quartz supports($$ and $).

This could be achieved using lookaround like regex as follows
```js
(?<=(\$|\$\$)[\s\S]*) -> Positive lookbehind for $ or $$
\\_ -> Matches \_
(?=[\s\S]*(?:\1)) Positive lookahead for $ or $$ if matched
const escapedUnderscoreRegex = new RegExp(/(?<=(\$|\$\$)[\s\S]*)\\_(?=[\s\S]*(?:\1))/, "g")
````

But since lookahead/behind can slow things down on large files, we just
look up all equations with $ and $$ delimiters and then try replacing \_
2023-09-29 11:35:26 -07:00

109 lines
3.4 KiB
TypeScript

import { QuartzTransformerPlugin } from "../types"
export interface Options {
/** Replace {{ relref }} with quartz wikilinks []() */
wikilinks: boolean
/** Remove pre-defined anchor (see https://ox-hugo.scripter.co/doc/anchors/) */
removePredefinedAnchor: boolean
/** Remove hugo shortcode syntax */
removeHugoShortcode: boolean
/** Replace <figure/> with ![]() */
replaceFigureWithMdImg: boolean
/** Replace org latex fragments with $ and $$ */
replaceOrgLatex: boolean
}
const defaultOptions: Options = {
wikilinks: true,
removePredefinedAnchor: true,
removeHugoShortcode: true,
replaceFigureWithMdImg: true,
replaceOrgLatex: true,
}
const relrefRegex = new RegExp(/\[([^\]]+)\]\(\{\{< relref "([^"]+)" >\}\}\)/, "g")
const predefinedHeadingIdRegex = new RegExp(/(.*) {#(?:.*)}/, "g")
const hugoShortcodeRegex = new RegExp(/{{(.*)}}/, "g")
const figureTagRegex = new RegExp(/< ?figure src="(.*)" ?>/, "g")
// \\\\\( -> matches \\(
// (.+?) -> Lazy match for capturing the equation
// \\\\\) -> matches \\)
const inlineLatexRegex = new RegExp(/\\\\\((.+?)\\\\\)/, "g")
// (?:\\begin{equation}|\\\\\(|\\\\\[) -> start of equation
// ([\s\S]*?) -> Matches the block equation
// (?:\\\\\]|\\\\\)|\\end{equation}) -> end of equation
const blockLatexRegex = new RegExp(
/(?:\\begin{equation}|\\\\\(|\\\\\[)([\s\S]*?)(?:\\\\\]|\\\\\)|\\end{equation})/,
"g",
)
// \$\$[\s\S]*?\$\$ -> Matches block equations
// \$.*?\$ -> Matches inline equations
const quartzLatexRegex = new RegExp(/\$\$[\s\S]*?\$\$|\$.*?\$/, "g")
/**
* ox-hugo is an org exporter backend that exports org files to hugo-compatible
* markdown in an opinionated way. This plugin adds some tweaks to the generated
* markdown to make it compatible with quartz but the list of changes applied it
* is not exhaustive.
* */
export const OxHugoFlavouredMarkdown: QuartzTransformerPlugin<Partial<Options> | undefined> = (
userOpts,
) => {
const opts = { ...defaultOptions, ...userOpts }
return {
name: "OxHugoFlavouredMarkdown",
textTransform(_ctx, src) {
if (opts.wikilinks) {
src = src.toString()
src = src.replaceAll(relrefRegex, (value, ...capture) => {
const [text, link] = capture
return `[${text}](${link})`
})
}
if (opts.removePredefinedAnchor) {
src = src.toString()
src = src.replaceAll(predefinedHeadingIdRegex, (value, ...capture) => {
const [headingText] = capture
return headingText
})
}
if (opts.removeHugoShortcode) {
src = src.toString()
src = src.replaceAll(hugoShortcodeRegex, (value, ...capture) => {
const [scContent] = capture
return scContent
})
}
if (opts.replaceFigureWithMdImg) {
src = src.toString()
src = src.replaceAll(figureTagRegex, (value, ...capture) => {
const [src] = capture
return `![](${src})`
})
}
if (opts.replaceOrgLatex) {
src = src.toString()
src = src.replaceAll(inlineLatexRegex, (value, ...capture) => {
const [eqn] = capture
return `$${eqn}$`
})
src = src.replaceAll(blockLatexRegex, (value, ...capture) => {
const [eqn] = capture
return `$$${eqn}$$`
})
// ox-hugo escapes _ as \_
src = src.replaceAll(quartzLatexRegex, (value) => {
return value.replaceAll("\\_", "_")
})
}
return src
},
}
}