feat: resolve request paths within contained site roots

core/src/mime.rs

@@ -0,0 +1,78 @@
+//! Media types for files served byte for byte.
+//!
+//! A fixed table rather than a system lookup: Python's `mimetypes` consults
+//! `/etc/mime.types` where it exists, so smolweb's `Content-Type` for the same
+//! file differs between hosts. Determinism is worth more here than coverage of
+//! the long tail, and an unknown extension has a correct answer anyway.
+
+use std::path::Path;
+
+/// Returned when the extension is absent or unrecognised.
+pub const DEFAULT: &str = "application/octet-stream";
+
+/// The media type to serve `path` as, by extension, compared case-insensitively.
+pub fn media_type(path: &Path) -> &'static str {
+    let Some(extension) = path.extension().and_then(|e| e.to_str()) else { return DEFAULT };
+    let extension = extension.to_ascii_lowercase();
+    TABLE
+        .iter()
+        .find(|(known, _)| *known == extension)
+        .map(|(_, media_type)| *media_type)
+        .unwrap_or(DEFAULT)
+}
+
+/// Extensions a folder of Markdown actually carries. Text types name their
+/// charset, since a client has no other way to know it.
+const TABLE: &[(&str, &str)] = &[
+    // Images
+    ("png", "image/png"),
+    ("jpg", "image/jpeg"),
+    ("jpeg", "image/jpeg"),
+    ("gif", "image/gif"),
+    ("webp", "image/webp"),
+    ("svg", "image/svg+xml"),
+    ("ico", "image/vnd.microsoft.icon"),
+    ("avif", "image/avif"),
+    // Documents and data
+    ("txt", "text/plain; charset=utf-8"),
+    ("gmi", "text/gemini; charset=utf-8"),
+    ("css", "text/css; charset=utf-8"),
+    ("html", "text/html; charset=utf-8"),
+    ("xml", "application/xml"),
+    ("json", "application/json"),
+    ("toml", "application/toml"),
+    ("pdf", "application/pdf"),
+    ("asc", "text/plain; charset=utf-8"),
+    // Audio and video
+    ("mp3", "audio/mpeg"),
+    ("ogg", "audio/ogg"),
+    ("opus", "audio/ogg"),
+    ("flac", "audio/flac"),
+    ("wav", "audio/wav"),
+    ("mp4", "video/mp4"),
+    ("webm", "video/webm"),
+    // Archives and fonts
+    ("gz", "application/gzip"),
+    ("zip", "application/zip"),
+    ("tar", "application/x-tar"),
+    ("woff2", "font/woff2"),
+];
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn recognises_common_extensions() {
+        assert_eq!(media_type(Path::new("img.png")), "image/png");
+        assert_eq!(media_type(Path::new("a/b/photo.JPEG")), "image/jpeg");
+        assert_eq!(media_type(Path::new("notes.txt")), "text/plain; charset=utf-8");
+    }
+
+    #[test]
+    fn falls_back_for_the_unknown_and_the_extensionless() {
+        assert_eq!(media_type(Path::new("mystery.xyz")), DEFAULT);
+        assert_eq!(media_type(Path::new("LICENSE")), DEFAULT);
+        assert_eq!(media_type(Path::new("archive.tar.zst")), DEFAULT);
+    }
+}