From 62ba268ffee303dac629bed2414c50f6f8f09c0c Mon Sep 17 00:00:00 2001 From: Evan Pratten Date: Thu, 14 Nov 2024 12:45:29 -0500 Subject: [PATCH] Revert "clean up existing unused files" This reverts commit ee4b001300e24509dc6978771002a49225fd76ef. --- .../{ewpratten-com-deploy.yml => deploy.yml} | 4 +- .vscode/tasks.json | 2 +- _headers | 1 + _redirects | 1 + functions | 1 + requirements.txt | 1 + scripts/find_external_assets.py | 37 +++++++++++ scripts/fix_md_file_aliases.py | 66 +++++++++++++++++++ 8 files changed, 109 insertions(+), 4 deletions(-) rename .github/workflows/{ewpratten-com-deploy.yml => deploy.yml} (91%) create mode 120000 _headers create mode 120000 _redirects create mode 120000 functions create mode 100644 requirements.txt create mode 100644 scripts/find_external_assets.py create mode 100644 scripts/fix_md_file_aliases.py diff --git a/.github/workflows/ewpratten-com-deploy.yml b/.github/workflows/deploy.yml similarity index 91% rename from .github/workflows/ewpratten-com-deploy.yml rename to .github/workflows/deploy.yml index 0f5e335..4f40f4f 100644 --- a/.github/workflows/ewpratten-com-deploy.yml +++ b/.github/workflows/deploy.yml @@ -24,7 +24,6 @@ jobs: - name: Build only uses: shalzz/zola-deploy-action@v0.19.1 env: - BUILD_DIR: sites/ewpratten.com BUILD_ONLY: true BUILD_FLAGS: --drafts @@ -47,7 +46,6 @@ jobs: - name: Build only uses: shalzz/zola-deploy-action@v0.19.1 env: - BUILD_DIR: sites/ewpratten.com BUILD_ONLY: true - name: Publish to Cloudflare Pages @@ -56,6 +54,6 @@ jobs: apiToken: ${{ secrets.CLOUDFLARE_API_TOKEN }} accountId: ${{ secrets.CLOUDFLARE_ACCOUNT_ID }} projectName: ewpratten - directory: sites/ewpratten.com/public + directory: public gitHubToken: ${{ secrets.GITHUB_TOKEN }} wranglerVersion: '2' diff --git a/.vscode/tasks.json b/.vscode/tasks.json index ebb7bc4..412fc1f 100644 --- a/.vscode/tasks.json +++ b/.vscode/tasks.json @@ -8,7 +8,7 @@ "type": "shell", "command": "zola", "options": { - "cwd": "${workspaceFolder}/sites/ewpratten.com" + "cwd": "${workspaceFolder}" }, "args": [ "serve", diff --git a/_headers b/_headers new file mode 120000 index 0000000..c73f6b0 --- /dev/null +++ b/_headers @@ -0,0 +1 @@ +./static/_headers \ No newline at end of file diff --git a/_redirects b/_redirects new file mode 120000 index 0000000..12b15c0 --- /dev/null +++ b/_redirects @@ -0,0 +1 @@ +./static/_redirects \ No newline at end of file diff --git a/functions b/functions new file mode 120000 index 0000000..910093e --- /dev/null +++ b/functions @@ -0,0 +1 @@ +./static/functions \ No newline at end of file diff --git a/requirements.txt b/requirements.txt new file mode 100644 index 0000000..c04e3b4 --- /dev/null +++ b/requirements.txt @@ -0,0 +1 @@ +python-frontmatter \ No newline at end of file diff --git a/scripts/find_external_assets.py b/scripts/find_external_assets.py new file mode 100644 index 0000000..84401b2 --- /dev/null +++ b/scripts/find_external_assets.py @@ -0,0 +1,37 @@ +import re +from pathlib import Path + +REPO_ROOT = Path(__file__).parent.parent + +# Find all MD and HTML files +md_files = list(REPO_ROOT.rglob("*.md")) +html_files = list(REPO_ROOT.rglob("*.html")) + +# Ignore any files in the `public` directory +md_files = [f for f in md_files if "public" not in f.parts] +html_files = [f for f in html_files if "public" not in f.parts] + +# Result storage +external_assets = set() + +# Find Markdown images +for file in md_files: + body = file.read_text() + for match in re.finditer(r"!\[.*?\]\((.*?)\)", body): + link = match.group(1) + if link.startswith("http"): + external_assets.add((file, link)) + +# Search HTML +for file in html_files: + body = file.read_text() + for match in re.finditer(r'src="(.*?)"', body): + link = match.group(1) + if link.startswith("http"): + external_assets.add((file, link)) + +# Print all external assets +for file_path, link in external_assets: + # Strip the prefix off the file path + file_path = file_path.relative_to(REPO_ROOT) + print(f"{file_path}:\t{link}") \ No newline at end of file diff --git a/scripts/fix_md_file_aliases.py b/scripts/fix_md_file_aliases.py new file mode 100644 index 0000000..b08eea1 --- /dev/null +++ b/scripts/fix_md_file_aliases.py @@ -0,0 +1,66 @@ +import argparse +import sys +import re +import frontmatter +import yaml +from pathlib import Path + +BLOG_POST_RE = re.compile(r"^\d{4}-\d+-\d+-(.*)\.md$") + + +def main() -> int: + # Handle program arguments + ap = argparse.ArgumentParser( + description="Fixes the `aliases` field in the front matter of markdown files" + ) + ap.add_argument( + "--root", + type=Path, + default=Path(__file__).parent.parent / "content" / "blog", + help="The root directory to search for markdown files", + ) + args = ap.parse_args() + + # Find all markdown files + md_files = list(args.root.glob("**/*.md")) + print(f"Found {len(md_files)} markdown files") + + # Handle each file + for file in md_files: + print(f"Processing: {file}") + + # Determine what the alias path should be + title_matches = BLOG_POST_RE.match(file.name) + if not title_matches: + print("Skipping file, not a blog post") + continue + + title = title_matches.group(1) + correct_alias = f"/blog/{title.lower()}" + print("Correct alias:", correct_alias) + + # Load and parse the frontmatter + post = frontmatter.load(file) + + # Get the list of aliases + aliases = post.metadata.get("aliases", []) + + # If the alias is already correct, skip it + if correct_alias in aliases: + print("Found correct alias") + continue + + # Otherwise, add the correct alias + aliases.append(correct_alias) + + # Write out the new frontmatter + post.metadata["aliases"] = aliases + file_contents = frontmatter.dumps(post, sort_keys=False) + file_contents += "\n" + file.write_text(file_contents) + + return 0 + + +if __name__ == "__main__": + sys.exit(main())