Use dedicated libs to parse TOML, YAML

Fixes #15, parsing YAML and TOML using dedicated libraries that support multiline strings correctly.

Also adds tests that were run before and after changes. Multiline string tests expectedly failed before.

bun.lock

···
         "@clack/prompts": "^1.0.0",
         "cmd-ts": "^0.14.3",
         "glob": "^13.0.0",
+        "js-yaml": "^4.1.1",
         "mime-types": "^2.1.35",
         "minimatch": "^10.1.1",
         "open": "^11.0.0",
+        "smol-toml": "^1.6.0",
       },
       "devDependencies": {
         "@biomejs/biome": "^2.3.13",
+        "@types/js-yaml": "^4.0.9",
         "@types/mime-types": "^3.0.1",
         "@types/node": "^20",
       },
···
 
     "@types/hast": ["@types/hast@3.0.4", "", { "dependencies": { "@types/unist": "*" } }, "sha512-WPs+bbQw5aCj+x6laNGWLH3wviHtoCv/P3+otBhbOhJgG8qtpdAMlTCxLtsTWA7LH1Oh/bFCHsBn0TPS5m30EQ=="],
 
+    "@types/js-yaml": ["@types/js-yaml@4.0.9", "", {}, "sha512-k4MGaQl5TGo/iipqb2UDG2UwjXziSWkh0uysQelTlJpX1qGlpUZYm8PnO4DxG1qBomtJUdYJ6qR6xdIah10JLg=="],
+
     "@types/mdast": ["@types/mdast@4.0.4", "", { "dependencies": { "@types/unist": "*" } }, "sha512-kGaNbPh1k7AFzgpud/gMdvIm5xuECykRR+JnWKQno9TAXVa6WIVCGTPvYGekIDL4uwCZQSYbUxNBSb1aUo79oA=="],
 
     "@types/mdx": ["@types/mdx@2.0.13", "", {}, "sha512-+OWZQfAYyio6YkJb3HLxDrvnx6SWWDbC0zVPfBRzUk0/nqoDyf6dNxQi3eArPe8rJ473nobTMQ/8Zk+LxJ+Yuw=="],
···
 
     "ansi-regex": ["ansi-regex@6.2.2", "", {}, "sha512-Bq3SmSpyFHaWjPk8If9yc6svM8c56dB5BAtW4Qbw5jHTwwXXcTLoRMkpDJp6VL0XzlWaCHTXrkFURMYmD0sLqg=="],
 
+    "argparse": ["argparse@2.0.1", "", {}, "sha512-8+9WqebbFzpX9OR+Wa6O29asIogeRMzcGtAINdpMHHyAg10f05aSFVBbcEqGf/PXw1EjAZ+q2/bEBg3DvurK3Q=="],
+
     "aria-hidden": ["aria-hidden@1.2.6", "", { "dependencies": { "tslib": "^2.0.0" } }, "sha512-ik3ZgC9dY/lYVVM++OISsaYDeg1tb0VtP5uL3ouh1koGOaUMDPpbFIei4JkFimWUFPn90sbMNMXQAIVOlnYKJA=="],
 
     "astring": ["astring@1.9.0", "", { "bin": { "astring": "bin/astring" } }, "sha512-LElXdjswlqjWrPpJFg1Fx4wpkOCxj1TDHlSV4PlaRxHGWko024xICaa97ZkMfs6DRKlCguiAI+rbXv5GWwXIkg=="],
···
 
     "js-tokens": ["js-tokens@4.0.0", "", {}, "sha512-RdJUflcE3cUzKiMqQgsCu06FPu9UdIJO0beYbPhHN4k6apgJtifcoCtT9bcxOpYBtpD2kCM6Sbzg4CausW/PKQ=="],
 
+    "js-yaml": ["js-yaml@4.1.1", "", { "dependencies": { "argparse": "^2.0.1" }, "bin": { "js-yaml": "bin/js-yaml.js" } }, "sha512-qQKT4zQxXl8lLwBtHMWwaTcGfFOZviOJet3Oy/xmGk2gZH677CJM9EvtfdSkgWcATZhj/55JZ0rmy3myCT5lsA=="],
+
     "jsesc": ["jsesc@3.1.0", "", { "bin": { "jsesc": "bin/jsesc" } }, "sha512-/sM3dO2FOzXjKQhJuo0Q173wf2KOo8t4I8vHy6lF9poUp7bKT0/NHE8fPX23PwfhnykfqnC2xRxOnVw5XuGIaA=="],
 
     "json5": ["json5@2.2.3", "", { "bin": { "json5": "lib/cli.js" } }, "sha512-XmOWe7eyHYH14cLdVPoyg+GOH3rYX++KpzrylJwSW98t3Nk+U8XOl8FWKOgwtzdb8lXGf6zYwDUzeHMWfxasyg=="],
···
     "signal-exit": ["signal-exit@3.0.7", "", {}, "sha512-wnD2ZE+l+SPC/uoS0vXeE9L1+0wuaMqKlfz9AMUo38JsyLSBWSFcHR1Rri62LZc12vLr1gb3jl7iwQhgwpAbGQ=="],
 
     "sisteransi": ["sisteransi@1.0.5", "", {}, "sha512-bLGGlR1QxBcynn2d5YmDX4MGjlZvy2MRBDRNHLJ8VI6l6+9FUiyTFNJ0IveOSP0bcXgVDPRcfGqA0pjaqUpfVg=="],
+
+    "smol-toml": ["smol-toml@1.6.0", "", {}, "sha512-4zemZi0HvTnYwLfrpk/CF9LOd9Lt87kAt50GnqhMpyF9U3poDAP2+iukq2bZsO/ufegbYehBkqINbsWxj4l4cw=="],
 
     "source-map": ["source-map@0.7.6", "", {}, "sha512-i5uvt8C3ikiWeNZSVZNWcfZPItFQOsYTUAOkcUPGd8DqDy1uOUikjt5dG+uRlwyvR108Fb9DOd4GvXfT0N2/uQ=="],
 

packages/cli/package.json

···
 		"lint": "biome lint --write",
 		"format": "biome format --write",
 		"build": "bun build src/index.ts --target node --outdir dist && mkdir -p dist/components && cp src/components/*.js dist/components/",
+		"test": "bun test",
 		"dev": "bun run build && bun link",
 		"deploy": "bun run build && bun publish"
 	},
 	"devDependencies": {
 		"@biomejs/biome": "^2.3.13",
+		"@types/js-yaml": "^4.0.9",
 		"@types/mime-types": "^3.0.1",
 		"@types/node": "^20"
 	},
···
 		"@clack/prompts": "^1.0.0",
 		"cmd-ts": "^0.14.3",
 		"glob": "^13.0.0",
+		"js-yaml": "^4.1.1",
 		"mime-types": "^2.1.35",
 		"minimatch": "^10.1.1",
-		"open": "^11.0.0"
+		"open": "^11.0.0",
+		"smol-toml": "^1.6.0"
 	}
 }

packages/cli/src/lib/markdown.ts

···
 import * as fs from "node:fs/promises";
 import * as path from "node:path";
 import { glob } from "glob";
+import yaml from "js-yaml";
 import { minimatch } from "minimatch";
+import * as toml from "smol-toml";
 import type { BlogPost, FrontmatterMapping, PostFrontmatter } from "./types";
 
 export function parseFrontmatter(
···
 	// +++ uses TOML (key = value)
 	// --- and *** use YAML (key: value)
 	const isToml = delimiter === "+++";
-	const separator = isToml ? "=" : ":";
-
-	// Parse frontmatter manually
-	const raw: Record<string, unknown> = {};
-	const lines = frontmatterStr.split("\n");
-
-	let i = 0;
-	while (i < lines.length) {
-		const line = lines[i];
-		if (line === undefined) {
-			i++;
-			continue;
-		}
-		const sepIndex = line.indexOf(separator);
-		if (sepIndex === -1) {
-			i++;
-			continue;
-		}
-
-		const key = line.slice(0, sepIndex).trim();
-		let value = line.slice(sepIndex + 1).trim();
 
-		// Handle quoted strings
-		if (
-			(value.startsWith('"') && value.endsWith('"')) ||
-			(value.startsWith("'") && value.endsWith("'"))
-		) {
-			value = value.slice(1, -1);
-		}
-
-		// Handle inline arrays (simple case for tags)
-		if (value.startsWith("[") && value.endsWith("]")) {
-			const arrayContent = value.slice(1, -1);
-			raw[key] = arrayContent
-				.split(",")
-				.map((item) => item.trim().replace(/^["']|["']$/g, ""));
-		} else if (value === "" && !isToml) {
-			// Check for YAML-style multiline array (key with no value followed by - items)
-			const arrayItems: string[] = [];
-			let j = i + 1;
-			while (j < lines.length) {
-				const nextLine = lines[j];
-				if (nextLine === undefined) {
-					j++;
-					continue;
-				}
-				// Check if line is a list item (starts with whitespace and -)
-				const listMatch = nextLine.match(/^\s+-\s*(.*)$/);
-				if (listMatch && listMatch[1] !== undefined) {
-					let itemValue = listMatch[1].trim();
-					// Remove quotes if present
-					if (
-						(itemValue.startsWith('"') && itemValue.endsWith('"')) ||
-						(itemValue.startsWith("'") && itemValue.endsWith("'"))
-					) {
-						itemValue = itemValue.slice(1, -1);
-					}
-					arrayItems.push(itemValue);
-					j++;
-				} else if (nextLine.trim() === "") {
-					// Skip empty lines within the array
-					j++;
-				} else {
-					// Hit a new key or non-list content
-					break;
-				}
-			}
-			if (arrayItems.length > 0) {
-				raw[key] = arrayItems;
-				i = j;
-				continue;
-			} else {
-				raw[key] = value;
-			}
-		} else if (value === "true") {
-			raw[key] = true;
-		} else if (value === "false") {
-			raw[key] = false;
-		} else {
-			raw[key] = value;
-		}
-		i++;
+	// Parse frontmatter using the appropriate library
+	let raw: Record<string, unknown>;
+	if (isToml) {
+		raw = toml.parse(frontmatterStr) as Record<string, unknown>;
+	} else {
+		// Use CORE_SCHEMA to keep dates as strings rather than Date objects
+		raw = (yaml.load(frontmatterStr, { schema: yaml.CORE_SCHEMA }) as Record<string, unknown>) ?? {};
 	}
 
 	// Apply field mappings to normalize to standard PostFrontmatter fields

packages/cli/test/markdown.test.ts

···
+import { describe, expect, it } from "bun:test";
+import { parseFrontmatter } from "../src/lib/markdown";
+
+describe("parseFrontmatter", () => {
+	describe("delimiters", () => {
+		it("parses YAML frontmatter (--- delimiter)", () => {
+			const content = `---
+title: Hello World
+---
+Body content here.`;
+			const { frontmatter, body } = parseFrontmatter(content);
+			expect(frontmatter.title).toBe("Hello World");
+			expect(body).toBe("Body content here.");
+		});
+
+		it("parses TOML frontmatter (+++ delimiter)", () => {
+			const content = `+++
+title = "Hugo Post"
++++
+Body content here.`;
+			const { frontmatter, body } = parseFrontmatter(content);
+			expect(frontmatter.title).toBe("Hugo Post");
+			expect(body).toBe("Body content here.");
+		});
+
+		it("parses alternative frontmatter (*** delimiter)", () => {
+			const content = `***
+title: Alt Post
+***
+Body content here.`;
+			const { frontmatter, body } = parseFrontmatter(content);
+			expect(frontmatter.title).toBe("Alt Post");
+			expect(body).toBe("Body content here.");
+		});
+
+		it("throws when no frontmatter is present", () => {
+			const content = "Just plain content with no frontmatter.";
+			expect(() => parseFrontmatter(content)).toThrow(
+				"Could not parse frontmatter",
+			);
+		});
+	});
+
+	describe("scalar values", () => {
+		it("parses a string value", () => {
+			const content = `---
+title: My Post
+description: A short description
+---
+`;
+			const { frontmatter } = parseFrontmatter(content);
+			expect(frontmatter.title).toBe("My Post");
+			expect(frontmatter.description).toBe("A short description");
+		});
+
+		it("strips double quotes from values", () => {
+			const content = `---
+title: "Quoted Title"
+---
+`;
+			const { frontmatter } = parseFrontmatter(content);
+			expect(frontmatter.title).toBe("Quoted Title");
+		});
+
+		it("strips single quotes from values", () => {
+			const content = `---
+title: 'Single Quoted'
+---
+`;
+			const { frontmatter } = parseFrontmatter(content);
+			expect(frontmatter.title).toBe("Single Quoted");
+		});
+
+		it("parses YAML folded multiline string", () => {
+			const content = `---
+excerpt: >
+  This is a folded
+  multiline string
+---
+`;
+			const { rawFrontmatter } = parseFrontmatter(content);
+			expect(rawFrontmatter.excerpt).toBe("This is a folded multiline string\n");
+		});
+
+		it("parses YAML stripped folded multiline string", () => {
+			const content = `---
+excerpt: >-
+  This is a stripped folded
+  multiline string
+---
+`;
+			const { rawFrontmatter } = parseFrontmatter(content);
+			expect(rawFrontmatter.excerpt).toBe("This is a stripped folded multiline string");
+		});
+
+		it("parses YAML literal multiline string", () => {
+			const content = `---
+excerpt: |
+  This is a literal
+  multiline string
+---
+`;
+			const { rawFrontmatter } = parseFrontmatter(content);
+			expect(rawFrontmatter.excerpt).toBe("This is a literal\nmultiline string\n");
+		});
+
+		it("parses YAML kept literal multiline string", () => {
+			const content = `---
+excerpt: |+
+  This is a kept literal
+  multiline string
+
+end: true
+---
+`;
+			const { rawFrontmatter } = parseFrontmatter(content);
+			expect(rawFrontmatter.excerpt).toBe("This is a kept literal\nmultiline string\n\n");
+		});
+
+		it("parses boolean true", () => {
+			const content = `---
+draft: true
+---
+`;
+			const { frontmatter } = parseFrontmatter(content);
+			expect(frontmatter.draft).toBe(true);
+		});
+
+		it("parses boolean false", () => {
+			const content = `---
+draft: false
+---
+`;
+			const { frontmatter } = parseFrontmatter(content);
+			expect(frontmatter.draft).toBe(false);
+		});
+
+		it('parses string "true" in draft field as boolean true', () => {
+			const content = `---
+draft: true
+---
+`;
+			const { rawFrontmatter } = parseFrontmatter(content);
+			expect(rawFrontmatter.draft).toBe(true);
+		});
+	});
+
+	describe("arrays", () => {
+		it("parses inline YAML arrays", () => {
+			const content = `---
+tags: [typescript, bun, testing]
+---
+`;
+			const { frontmatter } = parseFrontmatter(content);
+			expect(frontmatter.tags).toEqual(["typescript", "bun", "testing"]);
+		});
+
+		it("parses inline YAML arrays with quoted items", () => {
+			const content = `---
+tags: ["typescript", "bun", "testing"]
+---
+`;
+			const { frontmatter } = parseFrontmatter(content);
+			expect(frontmatter.tags).toEqual(["typescript", "bun", "testing"]);
+		});
+
+		it("parses YAML block arrays", () => {
+			const content = `---
+tags:
+  - typescript
+  - bun
+  - testing
+---
+`;
+			const { frontmatter } = parseFrontmatter(content);
+			expect(frontmatter.tags).toEqual(["typescript", "bun", "testing"]);
+		});
+
+		it("parses YAML block arrays with quoted items", () => {
+			const content = `---
+tags:
+  - "typescript"
+  - 'bun'
+---
+`;
+			const { frontmatter } = parseFrontmatter(content);
+			expect(frontmatter.tags).toEqual(["typescript", "bun"]);
+		});
+
+		it("parses inline TOML arrays", () => {
+			const content = `+++
+tags = ["typescript", "bun"]
++++
+`;
+			const { frontmatter } = parseFrontmatter(content);
+			expect(frontmatter.tags).toEqual(["typescript", "bun"]);
+		});
+	});
+
+	describe("publish date fallbacks", () => {
+		it("uses publishDate field directly", () => {
+			const content = `---
+publishDate: 2024-01-15
+---
+`;
+			const { frontmatter } = parseFrontmatter(content);
+			expect(frontmatter.publishDate).toBe("2024-01-15");
+		});
+
+		it("falls back to pubDate", () => {
+			const content = `---
+pubDate: 2024-02-01
+---
+`;
+			const { frontmatter } = parseFrontmatter(content);
+			expect(frontmatter.publishDate).toBe("2024-02-01");
+		});
+
+		it("falls back to date", () => {
+			const content = `---
+date: 2024-03-10
+---
+`;
+			const { frontmatter } = parseFrontmatter(content);
+			expect(frontmatter.publishDate).toBe("2024-03-10");
+		});
+
+		it("falls back to createdAt", () => {
+			const content = `---
+createdAt: 2024-04-20
+---
+`;
+			const { frontmatter } = parseFrontmatter(content);
+			expect(frontmatter.publishDate).toBe("2024-04-20");
+		});
+
+		it("falls back to created_at", () => {
+			const content = `---
+created_at: 2024-05-30
+---
+`;
+			const { frontmatter } = parseFrontmatter(content);
+			expect(frontmatter.publishDate).toBe("2024-05-30");
+		});
+
+		it("prefers publishDate over other fallbacks", () => {
+			const content = `---
+publishDate: 2024-01-01
+date: 2023-01-01
+---
+`;
+			const { frontmatter } = parseFrontmatter(content);
+			expect(frontmatter.publishDate).toBe("2024-01-01");
+		});
+	});
+
+	describe("rawFrontmatter", () => {
+		it("returns all raw fields", () => {
+			const content = `---
+title: Raw Test
+custom: value
+---
+`;
+			const { rawFrontmatter } = parseFrontmatter(content);
+			expect(rawFrontmatter.title).toBe("Raw Test");
+			expect(rawFrontmatter.custom).toBe("value");
+		});
+
+		it("preserves atUri in both frontmatter and rawFrontmatter", () => {
+			const content = `---
+title: Post
+atUri: at://did:plc:abc123/app.bsky.feed.post/xyz
+---
+`;
+			const { frontmatter, rawFrontmatter } = parseFrontmatter(content);
+			expect(frontmatter.atUri).toBe(
+				"at://did:plc:abc123/app.bsky.feed.post/xyz",
+			);
+			expect(rawFrontmatter.atUri).toBe(
+				"at://did:plc:abc123/app.bsky.feed.post/xyz",
+			);
+		});
+	});
+
+	describe("FrontmatterMapping", () => {
+		it("maps a custom title field", () => {
+			const content = `---
+name: My Mapped Title
+---
+`;
+			const { frontmatter } = parseFrontmatter(content, { title: "name" });
+			expect(frontmatter.title).toBe("My Mapped Title");
+		});
+
+		it("maps a custom description field", () => {
+			const content = `---
+summary: Custom description
+---
+`;
+			const { frontmatter } = parseFrontmatter(content, {
+				description: "summary",
+			});
+			expect(frontmatter.description).toBe("Custom description");
+		});
+
+		it("maps a custom publishDate field", () => {
+			const content = `---
+publishedOn: 2024-06-15
+---
+`;
+			const { frontmatter } = parseFrontmatter(content, {
+				publishDate: "publishedOn",
+			});
+			expect(frontmatter.publishDate).toBe("2024-06-15");
+		});
+
+		it("maps a custom coverImage field", () => {
+			const content = `---
+heroImage: /images/cover.jpg
+---
+`;
+			const { frontmatter } = parseFrontmatter(content, {
+				coverImage: "heroImage",
+			});
+			expect(frontmatter.ogImage).toBe("/images/cover.jpg");
+		});
+
+		it("maps a custom tags field", () => {
+			const content = `---
+categories: [news, updates]
+---
+`;
+			const { frontmatter } = parseFrontmatter(content, { tags: "categories" });
+			expect(frontmatter.tags).toEqual(["news", "updates"]);
+		});
+
+		it("maps a custom draft field", () => {
+			const content = `---
+unpublished: true
+---
+`;
+			const { frontmatter } = parseFrontmatter(content, { draft: "unpublished" });
+			expect(frontmatter.draft).toBe(true);
+		});
+
+		it("falls back to standard field name when mapped field is absent", () => {
+			const content = `---
+title: Standard Title
+---
+`;
+			const { frontmatter } = parseFrontmatter(content, { title: "heading" });
+			expect(frontmatter.title).toBe("Standard Title");
+		});
+	});
+
+	describe("body", () => {
+		it("returns the body content after the closing delimiter", () => {
+			const content = `---
+title: Post
+---
+# Heading
+
+Some paragraph text.`;
+			const { body } = parseFrontmatter(content);
+			expect(body).toBe("# Heading\n\nSome paragraph text.");
+		});
+
+		it("returns an empty body when there is no content after frontmatter", () => {
+			const content = `---
+title: Post
+---
+`;
+			const { body } = parseFrontmatter(content);
+			expect(body).toBe("");
+		});
+	});
+});