From e48b1c0dae438bf4a0f138d1817290b8974abede Mon Sep 17 00:00:00 2001
From: Philip Okugbe <16838612+Philipinho@users.noreply.github.com>
Date: Mon, 9 Dec 2024 15:08:25 +0000
Subject: [PATCH] fix: markdown math import (#529)

* fix: markdown math block import

* fix: block and inline math import

* cleanup
---
 .../src/integrations/export/turndown-utils.ts |  2 +-
 .../integrations/import/utils/marked.utils.ts |  4 +-
 .../import/utils/math-block.marked.ts         | 37 +++++++++++++
 .../import/utils/math-inline.marked.ts        | 55 +++++++++++++++++++
 4 files changed, 96 insertions(+), 2 deletions(-)
 create mode 100644 apps/server/src/integrations/import/utils/math-block.marked.ts
 create mode 100644 apps/server/src/integrations/import/utils/math-inline.marked.ts

diff --git a/apps/server/src/integrations/export/turndown-utils.ts b/apps/server/src/integrations/export/turndown-utils.ts
index 8d46e661..c48ba364 100644
--- a/apps/server/src/integrations/export/turndown-utils.ts
+++ b/apps/server/src/integrations/export/turndown-utils.ts
@@ -117,7 +117,7 @@ function mathBlock(turndownService: TurndownService) {
       );
     },
     replacement: function (content: any, node: HTMLInputElement) {
-      return `\n$$${content}$$\n`;
+      return `\n$$\n${content}\n$$\n`;
     },
   });
 }
diff --git a/apps/server/src/integrations/import/utils/marked.utils.ts b/apps/server/src/integrations/import/utils/marked.utils.ts
index a34cb465..cfc7e6a9 100644
--- a/apps/server/src/integrations/import/utils/marked.utils.ts
+++ b/apps/server/src/integrations/import/utils/marked.utils.ts
@@ -1,5 +1,7 @@
 import { marked } from 'marked';
 import { calloutExtension } from './callout.marked';
+import { mathBlockExtension } from './math-block.marked';
+import { mathInlineExtension } from "./math-inline.marked";
 
 marked.use({
   renderer: {
@@ -26,7 +28,7 @@ marked.use({
   },
 });
 
-marked.use({ extensions: [calloutExtension] });
+marked.use({ extensions: [calloutExtension, mathBlockExtension, mathInlineExtension] });
 
 export async function markdownToHtml(markdownInput: string): Promise<string> {
   const YAML_FONT_MATTER_REGEX = /^\s*---[\s\S]*?---\s*/;
diff --git a/apps/server/src/integrations/import/utils/math-block.marked.ts b/apps/server/src/integrations/import/utils/math-block.marked.ts
new file mode 100644
index 00000000..b2165a3b
--- /dev/null
+++ b/apps/server/src/integrations/import/utils/math-block.marked.ts
@@ -0,0 +1,37 @@
+import { Token, marked } from 'marked';
+
+interface MathBlockToken {
+  type: 'mathBlock';
+  text: string;
+  raw: string;
+}
+
+export const mathBlockExtension = {
+  name: 'mathBlock',
+  level: 'block',
+  start(src: string) {
+    return src.match(/\$\$/)?.index ?? -1;
+  },
+  tokenizer(src: string): MathBlockToken | undefined {
+    const rule = /^\$\$(?!(\$))([\s\S]+?)\$\$/;
+    const match = rule.exec(src);
+
+    if (match) {
+      return {
+        type: 'mathBlock',
+        raw: match[0],
+        text: match[2]?.trim(),
+      };
+    }
+  },
+  renderer(token: Token) {
+    const mathBlockToken = token as MathBlockToken;
+    // parse to prevent escaping slashes
+    const latex = marked
+      .parse(mathBlockToken.text)
+      .toString()
+      .replace(/<(\/)?p>/g, '');
+
+    return `<div data-type="${mathBlockToken.type}" data-katex="true">${latex}</div>`;
+  },
+};
diff --git a/apps/server/src/integrations/import/utils/math-inline.marked.ts b/apps/server/src/integrations/import/utils/math-inline.marked.ts
new file mode 100644
index 00000000..e6eb978d
--- /dev/null
+++ b/apps/server/src/integrations/import/utils/math-inline.marked.ts
@@ -0,0 +1,55 @@
+import { Token, marked } from 'marked';
+
+interface MathInlineToken {
+  type: 'mathInline';
+  text: string;
+  raw: string;
+}
+
+const inlineMathRegex = /^\$(?!\s)(.+?)(?<!\s)\$(?!\d)/;
+
+export const mathInlineExtension = {
+  name: 'mathInline',
+  level: 'inline',
+  start(src: string) {
+    let index: number;
+    let indexSrc = src;
+
+    while (indexSrc) {
+      index = indexSrc.indexOf('$');
+      if (index === -1) {
+        return;
+      }
+      const f = index === 0 || indexSrc.charAt(index - 1) === ' ';
+      if (f) {
+        const possibleKatex = indexSrc.substring(index);
+        if (possibleKatex.match(inlineMathRegex)) {
+          return index;
+        }
+      }
+
+      indexSrc = indexSrc.substring(index + 1).replace(/^\$+/, '');
+    }
+  },
+  tokenizer(src: string): MathInlineToken | undefined {
+    const match = inlineMathRegex.exec(src);
+
+    if (match) {
+      return {
+        type: 'mathInline',
+        raw: match[0],
+        text: match[1]?.trim(),
+      };
+    }
+  },
+  renderer(token: Token) {
+    const mathInlineToken = token as MathInlineToken;
+    // parse to prevent escaping slashes
+    const latex = marked
+      .parse(mathInlineToken.text)
+      .toString()
+      .replace(/<(\/)?p>/g, '');
+
+    return `<span data-type="${mathInlineToken.type}" data-katex="true">${latex}</span>`;
+  },
+};