From ac906c6dc7e6edc6513dee7bf492005e6ef8d022 Mon Sep 17 00:00:00 2001
From: Zanie <contact@zanie.dev>
Date: Wed, 1 Nov 2023 11:38:22 -0500
Subject: [PATCH] Add `PackageName::validate`

---
 crates/puffin-package/src/package_name.rs | 50 ++++++++++++++++++++---
 1 file changed, 45 insertions(+), 5 deletions(-)

diff --git a/crates/puffin-package/src/package_name.rs b/crates/puffin-package/src/package_name.rs
index f13c8e92a..2231f5ea8 100644
--- a/crates/puffin-package/src/package_name.rs
+++ b/crates/puffin-package/src/package_name.rs
@@ -1,11 +1,11 @@
 use std::fmt;
 use std::fmt::{Display, Formatter};
 
+use crate::dist_info_name::DistInfoName;
+use anyhow::{anyhow, Result};
 use once_cell::sync::Lazy;
 use regex::Regex;
 
-use crate::dist_info_name::DistInfoName;
-
 #[derive(Debug, Clone, PartialEq, Eq, Hash, PartialOrd, Ord)]
 pub struct PackageName(String);
 
@@ -23,20 +23,37 @@ impl Display for PackageName {
 }
 
 static NAME_NORMALIZE: Lazy<Regex> = Lazy::new(|| Regex::new(r"[-_.]+").unwrap());
+static NAME_VALIDATE: Lazy<Regex> =
+    Lazy::new(|| Regex::new(r"(?i)^([A-Z0-9]|[A-Z0-9][A-Z0-9._-]*[A-Z0-9])$").unwrap());
 
+/// A package name.
+///
+/// See:
+/// - <https://packaging.python.org/en/latest/specifications/name-normalization/>
+/// - <https://peps.python.org/pep-0508/#names>
+/// - <https://peps.python.org/pep-0503/#normalized-names>
 impl PackageName {
-    /// Create a normalized representation of a package name.
+    /// Create a normalized package name without validation.
     ///
     /// Converts the name to lowercase and collapses any run of the characters `-`, `_` and `.`
     /// down to a single `-`, e.g., `---`, `.`, and `__` all get converted to just `-`.
-    ///
-    /// See: <https://packaging.python.org/en/latest/specifications/name-normalization/>
     pub fn normalize(name: impl AsRef<str>) -> Self {
         // TODO(charlie): Avoid allocating in the common case (when no normalization is required).
         let mut normalized = NAME_NORMALIZE.replace_all(name.as_ref(), "-").to_string();
         normalized.make_ascii_lowercase();
         Self(normalized)
     }
+
+    /// Create a validated, normalized extra name.
+    pub fn validate(name: impl AsRef<str>) -> Result<Self> {
+        if NAME_VALIDATE.is_match(name.as_ref()) {
+            Ok(Self::normalize(name))
+        } else {
+            Err(anyhow!(
+                "Package names must start and end with a letter or digit and may only contain -, _, ., and alphanumeric characters"
+            ))
+        }
+    }
 }
 
 impl AsRef<str> for PackageName {
@@ -86,4 +103,27 @@ mod tests {
             "friendly-bard"
         );
     }
+
+    #[test]
+    fn validate() {
+        // Unchanged
+        assert_eq!(
+            PackageName::validate("friendly-bard").unwrap().as_ref(),
+            "friendly-bard"
+        );
+        assert_eq!(PackageName::validate("1okay").unwrap().as_ref(), "1okay");
+        assert_eq!(PackageName::validate("okay2").unwrap().as_ref(), "okay2");
+        // Normalizes
+        assert_eq!(
+            PackageName::validate("Friendly-Bard").unwrap().as_ref(),
+            "friendly-bard"
+        );
+        // Failures...
+        assert!(PackageName::validate(" starts-with-space").is_err());
+        assert!(PackageName::validate("-starts-with-dash").is_err());
+        assert!(PackageName::validate("ends-with-dash-").is_err());
+        assert!(PackageName::validate("ends-with-space ").is_err());
+        assert!(PackageName::validate("includes!invalid-char").is_err());
+        assert!(PackageName::validate("space in middle").is_err());
+    }
 }