pantsdown 1.0.1

package/.eslintrc.json

@@ -0,0 +1,26 @@
+{
+  "root": true,
+  "parser": "@typescript-eslint/parser",
+  "parserOptions": {
+    "ecmaVersion": "latest",
+    "sourceType": "module",
+    "project": ["tsconfig.json"]
+  },
+  "extends": [
+    "eslint:recommended",
+    "plugin:@typescript-eslint/strict-type-checked",
+    "plugin:@typescript-eslint/stylistic-type-checked"
+  ],
+  "rules": {
+    "@typescript-eslint/no-non-null-assertion": "off",
+    "@typescript-eslint/consistent-type-definitions": ["error", "type"],
+    "@typescript-eslint/no-unused-vars": ["error", { "argsIgnorePattern": "^_" }],
+    "@typescript-eslint/consistent-type-imports": [
+      "warn",
+      { "prefer": "type-imports", "fixStyle": "inline-type-imports" }
+    ],
+    "no-useless-escape": "off",
+    "no-control-regex": "off",
+    "no-cond-assign": "off"
+  }
+}

package/.github/workflows/release.yaml

@@ -0,0 +1,44 @@
+name: Release
+on:
+    push:
+        branches:
+            - main
+
+permissions:
+    contents: read
+
+jobs:
+    Test:
+        runs-on: ubuntu-latest
+        steps:
+            - name: Checkout repo
+              uses: actions/checkout@v4
+            - name: Install bun
+              uses: oven-sh/setup-bun@v1
+            - name: Install dependencies
+              run: bun install
+            - name: Lint
+              run: bun run lint
+            - name: Test
+              run: bun test
+
+    Release:
+        permissions:
+            contents: write
+        needs: [Test]
+        if: |
+            github.ref == 'refs/heads/main' &&
+            github.event.repository.fork == false
+        runs-on: ubuntu-latest
+        steps:
+            - name: Checkout Code
+              uses: actions/checkout@v4
+            - name: Install bun
+              uses: oven-sh/setup-bun@v1
+            - name: Install dependencies
+              run: bun install
+            - name: Release
+              env:
+                  GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+                  NPM_TOKEN: ${{ secrets.NPM_TOKEN }}
+              run: bun run semantic-release

package/.prettierrc.json

@@ -0,0 +1,11 @@
+{
+  "tabWidth": 4,
+  "printWidth": 100,
+  "plugins": ["prettier-plugin-organize-imports"],
+  "overrides": [
+    {
+      "files": ["*.json"],
+      "options": { "tabWidth": 2 }
+    }
+  ]
+}

package/LICENSE.md

@@ -0,0 +1,67 @@
+# License information
+
+## Contribution License Agreement
+
+If you contribute code to this project, you are implicitly allowing your code
+to be distributed under the MIT license. You are also implicitly verifying that
+all code is your original work.
+
+## Pantsdown
+
+Copyright (c) 2023+, Wallpants (https://github.com/wallpants/)
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+## Marked
+
+Copyright (c) 2018+, MarkedJS (https://github.com/markedjs/)
+
+Copyright (c) 2011-2018, Christopher Jeffrey (https://github.com/chjj/)
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+## Markdown
+
+Copyright © 2004, John Gruber
+http://daringfireball.net/
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without modification, are permitted provided that the following conditions are met:
+
+-   Redistributions of source code must retain the above copyright notice, this list of conditions and the following disclaimer.
+-   Redistributions in binary form must reproduce the above copyright notice, this list of conditions and the following disclaimer in the documentation and/or other materials provided with the distribution.
+-   Neither the name “Markdown” nor the names of its contributors may be used to endorse or promote products derived from this software without specific prior written permission.
+
+This software is provided by the copyright holders and contributors “as is” and any express or implied warranties, including, but not limited to, the implied warranties of merchantability and fitness for a particular purpose are disclaimed. In no event shall the copyright owner or contributors be liable for any direct, indirect, incidental, special, exemplary, or consequential damages (including, but not limited to, procurement of substitute goods or services; loss of use, data, or profits; or business interruption) however caused and on any theory of liability, whether in contract, strict liability, or tort (including negligence or otherwise) arising in any way out of the use of this software, even if advised of the possibility of such damage.

package/README.md

@@ -0,0 +1,5 @@
+# Pantsdown
+
+<!-- Up to https://github.com/markedjs/marked/commit/f90ae0692c772fee55182216b7158f4df5b37bb9 -->
+
+The Markdown parser.

package/package.json

@@ -0,0 +1,46 @@
+{
+  "name": "pantsdown",
+  "version": "1.0.1",
+  "description": "The markdown parser",
+  "repository": {
+    "type": "git",
+    "url": "git://github.com/wallpants/pantsdown.git"
+  },
+  "license": "MIT",
+  "type": "module",
+  "exports": {
+    "types": "./src/index.ts",
+    "bun": "./src/index.ts",
+    "import": "./src/index.ts"
+  },
+  "config": {
+    "commitizen": {
+      "path": "cz-conventional-changelog"
+    }
+  },
+  "scripts": {
+    "format": "prettier **/*{ts,js} --write",
+    "lint": "tsc && eslint . --ext ts --report-unused-disable-directives --max-warnings 0",
+    "commit": "cz"
+  },
+  "release": {
+    "branches": [
+      "main"
+    ]
+  },
+  "devDependencies": {
+    "@typescript-eslint/eslint-plugin": "^6.7.3",
+    "@typescript-eslint/parser": "^6.7.3",
+    "bun-types": "latest",
+    "commitizen": "^4.3.0",
+    "cz-conventional-changelog": "^3.3.0",
+    "eslint": "^8.50.0",
+    "prettier": "^3.0.2",
+    "prettier-plugin-organize-imports": "^3.2.3",
+    "semantic-release": "^22.0.5",
+    "typescript": "5.2.2"
+  },
+  "dependencies": {
+    "highlight.js": "^11.9.0"
+  }
+}

package/src/index.ts

@@ -0,0 +1,2 @@
+export { Pantsdown } from "./pantsdown.ts";
+export * from "./types.ts";

package/src/lexer.ts

@@ -0,0 +1,369 @@
+import { inline } from "./rules/inline.ts";
+import { Tokenizer } from "./tokenizer.ts";
+import { type Links, type Token } from "./types.ts";
+
+export class Lexer {
+    private tokenizer: Tokenizer;
+    private inlineQueue: { src: string; tokens: Token[] }[];
+    private tokens: Token[] = [];
+    private links: Links = {};
+
+    state = {
+        inLink: false,
+        inRawBlock: false,
+        top: true,
+    };
+
+    constructor() {
+        this.tokenizer = new Tokenizer(this);
+        this.inlineQueue = [];
+    }
+
+    /**
+     * Preprocessing
+     */
+    lex(src: string) {
+        // reset values from previous parse
+        this.tokens = [];
+        this.links = {};
+
+        src = src.replace(/\r\n|\r/g, "\n");
+
+        this.blockTokens(src, this.tokens);
+
+        let next;
+        while ((next = this.inlineQueue.shift())) {
+            this.inlineTokens(next.src, next.tokens);
+        }
+
+        return this.tokens;
+    }
+
+    /**
+     * Lexing
+     */
+    blockTokens(src: string, tokens: Token[]): Token[] {
+        src = src.replace(/^( *)(\t+)/gm, (_, leading, tabs: string) => {
+            return leading + "    ".repeat(tabs.length);
+        });
+
+        let token: Token | undefined;
+        let lastToken: Token | undefined;
+        let cutSrc;
+        let lastParagraphClipped;
+
+        while (src) {
+            // newline
+            if ((token = this.tokenizer.space(src))) {
+                src = src.substring(token.raw.length);
+                if (token.raw.length === 1 && tokens.length > 0) {
+                    // if there's a single \n as a spacer, it's terminating the last line,
+                    // so move it there so that we don't get unecessary paragraph tags
+                    const last = tokens[tokens.length - 1];
+                    if (last) last.raw += "\n";
+                } else {
+                    tokens.push(token);
+                }
+                continue;
+            }
+
+            // code
+            if ((token = this.tokenizer.code(src))) {
+                src = src.substring(token.raw.length);
+                lastToken = tokens[tokens.length - 1];
+                // An indented code block cannot interrupt a paragraph.
+                if (lastToken && (lastToken.type === "paragraph" || lastToken.type === "text")) {
+                    lastToken.raw += "\n" + token.raw;
+                    lastToken.text += "\n" + token.text;
+                    const lastInline = this.inlineQueue[this.inlineQueue.length - 1];
+                    if (lastInline) lastInline.src = lastToken.text;
+                } else {
+                    tokens.push(token);
+                }
+                continue;
+            }
+
+            // fences
+            if ((token = this.tokenizer.fences(src))) {
+                src = src.substring(token.raw.length);
+                tokens.push(token);
+                continue;
+            }
+
+            // heading
+            if ((token = this.tokenizer.heading(src))) {
+                src = src.substring(token.raw.length);
+                tokens.push(token);
+                continue;
+            }
+
+            // hr
+            if ((token = this.tokenizer.hr(src))) {
+                src = src.substring(token.raw.length);
+                tokens.push(token);
+                continue;
+            }
+
+            // blockquote
+            if ((token = this.tokenizer.blockquote(src))) {
+                src = src.substring(token.raw.length);
+                tokens.push(token);
+                continue;
+            }
+
+            // list
+            if ((token = this.tokenizer.list(src))) {
+                src = src.substring(token.raw.length);
+                tokens.push(token);
+                continue;
+            }
+
+            // html
+            if ((token = this.tokenizer.html(src))) {
+                src = src.substring(token.raw.length);
+                tokens.push(token);
+                continue;
+            }
+
+            // def
+            if ((token = this.tokenizer.def(src))) {
+                src = src.substring(token.raw.length);
+                lastToken = tokens[tokens.length - 1];
+                if (lastToken && (lastToken.type === "paragraph" || lastToken.type === "text")) {
+                    lastToken.raw += "\n" + token.raw;
+                    lastToken.text += "\n" + token.raw;
+                    const lastInline = this.inlineQueue[this.inlineQueue.length - 1];
+                    if (lastInline) lastInline.src = lastToken.text;
+                } else if (!this.links[token.tag]) {
+                    this.links[token.tag] = {
+                        href: token.href,
+                        title: token.title,
+                    };
+                }
+                continue;
+            }
+
+            // table (gfm)
+            if ((token = this.tokenizer.table(src))) {
+                src = src.substring(token.raw.length);
+                tokens.push(token);
+                continue;
+            }
+
+            // lheading
+            if ((token = this.tokenizer.lheading(src))) {
+                src = src.substring(token.raw.length);
+                tokens.push(token);
+                continue;
+            }
+
+            // top-level paragraph
+            // prevent paragraph consuming extensions by clipping 'src' to extension start
+            cutSrc = src;
+            if (this.state.top && (token = this.tokenizer.paragraph(cutSrc))) {
+                lastToken = tokens[tokens.length - 1];
+                if (lastParagraphClipped && lastToken?.type === "paragraph") {
+                    lastToken.raw += "\n" + token.raw;
+                    lastToken.text += "\n" + token.text;
+                    this.inlineQueue.pop();
+                    const lastInline = this.inlineQueue[this.inlineQueue.length - 1];
+                    if (lastInline) lastInline.src = lastToken.text;
+                } else {
+                    tokens.push(token);
+                }
+                lastParagraphClipped = cutSrc.length !== src.length;
+                src = src.substring(token.raw.length);
+                continue;
+            }
+
+            // text
+            if ((token = this.tokenizer.text(src))) {
+                src = src.substring(token.raw.length);
+                lastToken = tokens[tokens.length - 1];
+                if (lastToken && lastToken.type === "text") {
+                    lastToken.raw += "\n" + token.raw;
+                    lastToken.text += "\n" + token.text;
+                    this.inlineQueue.pop();
+                    const lastInline = this.inlineQueue[this.inlineQueue.length - 1];
+                    if (lastInline) lastInline.src = lastToken.text;
+                } else {
+                    tokens.push(token);
+                }
+                continue;
+            }
+
+            if (src) {
+                const errMsg = "Infinite loop on byte: " + src.charCodeAt(0);
+                throw new Error(errMsg);
+            }
+        }
+
+        this.state.top = true;
+        return tokens;
+    }
+
+    inline(src: string, tokens: Token[] = []) {
+        this.inlineQueue.push({ src, tokens });
+        return tokens;
+    }
+
+    /**
+     * Lexing/Compiling
+     */
+    inlineTokens(src: string, tokens: Token[] = []): Token[] {
+        let token, lastToken, cutSrc;
+
+        // String with links masked to avoid interference with em and strong
+        let maskedSrc = src;
+        let match;
+        let keepPrevChar, prevChar;
+
+        // Mask out reflinks
+        const links = Object.keys(this.links);
+        if (links.length > 0) {
+            while ((match = inline.reflinkSearch.exec(maskedSrc)) != null) {
+                if (links.includes(match[0].slice(match[0].lastIndexOf("[") + 1, -1))) {
+                    maskedSrc =
+                        maskedSrc.slice(0, match.index) +
+                        "[" +
+                        "a".repeat(match[0].length - 2) +
+                        "]" +
+                        maskedSrc.slice(inline.reflinkSearch.lastIndex);
+                }
+            }
+        }
+        // Mask out other blocks
+        while ((match = inline.blockSkip.exec(maskedSrc)) != null) {
+            maskedSrc =
+                maskedSrc.slice(0, match.index) +
+                "[" +
+                "a".repeat(match[0].length - 2) +
+                "]" +
+                maskedSrc.slice(inline.blockSkip.lastIndex);
+        }
+
+        // Mask out escaped characters
+        while ((match = inline.anyPunctuation.exec(maskedSrc)) != null) {
+            maskedSrc =
+                maskedSrc.slice(0, match.index) +
+                "++" +
+                maskedSrc.slice(inline.anyPunctuation.lastIndex);
+        }
+
+        while (src) {
+            if (!keepPrevChar) {
+                prevChar = "";
+            }
+            keepPrevChar = false;
+
+            // escape
+            if ((token = this.tokenizer.escape(src))) {
+                src = src.substring(token.raw.length);
+                tokens.push(token);
+                continue;
+            }
+
+            // tag
+            if ((token = this.tokenizer.tag(src))) {
+                src = src.substring(token.raw.length);
+                lastToken = tokens[tokens.length - 1];
+                if (lastToken && token.type === "text" && lastToken.type === "text") {
+                    lastToken.raw += token.raw;
+                    lastToken.text += token.text;
+                } else {
+                    tokens.push(token);
+                }
+                continue;
+            }
+
+            // link
+            if ((token = this.tokenizer.link(src))) {
+                src = src.substring(token.raw.length);
+                tokens.push(token);
+                continue;
+            }
+
+            // reflink, nolink
+            if ((token = this.tokenizer.reflink(src, this.links))) {
+                src = src.substring(token.raw.length);
+                lastToken = tokens[tokens.length - 1];
+                if (lastToken && token.type === "text" && lastToken.type === "text") {
+                    lastToken.raw += token.raw;
+                    lastToken.text += token.text;
+                } else {
+                    tokens.push(token);
+                }
+                continue;
+            }
+
+            // em & strong
+            if ((token = this.tokenizer.emStrong(src, maskedSrc, prevChar))) {
+                src = src.substring(token.raw.length);
+                tokens.push(token);
+                continue;
+            }
+
+            // code
+            if ((token = this.tokenizer.codespan(src))) {
+                src = src.substring(token.raw.length);
+                tokens.push(token);
+                continue;
+            }
+
+            // br
+            if ((token = this.tokenizer.br(src))) {
+                src = src.substring(token.raw.length);
+                tokens.push(token);
+                continue;
+            }
+
+            // del (gfm)
+            if ((token = this.tokenizer.del(src))) {
+                src = src.substring(token.raw.length);
+                tokens.push(token);
+                continue;
+            }
+
+            // autolink
+            if ((token = this.tokenizer.autolink(src))) {
+                src = src.substring(token.raw.length);
+                tokens.push(token);
+                continue;
+            }
+
+            // url (gfm)
+            if (!this.state.inLink && (token = this.tokenizer.url(src))) {
+                src = src.substring(token.raw.length);
+                tokens.push(token);
+                continue;
+            }
+
+            // text
+            // prevent inlineText consuming extensions by clipping 'src' to extension start
+            cutSrc = src;
+            if ((token = this.tokenizer.inlineText(cutSrc))) {
+                src = src.substring(token.raw.length);
+                if (!token.raw.endsWith("_")) {
+                    // Track prevChar before string of ____ started
+                    prevChar = token.raw.slice(-1);
+                }
+                keepPrevChar = true;
+                lastToken = tokens[tokens.length - 1];
+                if (lastToken && lastToken.type === "text") {
+                    lastToken.raw += token.raw;
+                    lastToken.text += token.text;
+                } else {
+                    tokens.push(token);
+                }
+                continue;
+            }
+
+            if (src) {
+                const errMsg = "Infinite loop on byte: " + src.charCodeAt(0);
+                throw new Error(errMsg);
+            }
+        }
+
+        return tokens;
+    }
+}

package/src/pantsdown.ts

@@ -0,0 +1,19 @@
+import { Lexer } from "./lexer.ts";
+import { Parser } from "./parser.ts";
+import { type RendererProps } from "./types.ts";
+
+export class Pantsdown {
+    private lexer: Lexer;
+    private parser: Parser;
+
+    constructor({ renderer }: { renderer: RendererProps }) {
+        this.lexer = new Lexer();
+        this.parser = new Parser({ renderer });
+    }
+
+    parse(src: string): string {
+        const tokens = this.lexer.lex(src);
+        const html = this.parser.parse(tokens);
+        return html;
+    }
+}