encode percent signs

phylum-dev · Nov 20, 2023 · 46a7904 · 46a7904
1 parent c71730c
commit 46a7904
Show file tree

Hide file tree

Showing 3 changed files with 55 additions and 4 deletions.
diff --git a/purl/src/format.rs b/purl/src/format.rs
@@ -17,13 +17,14 @@ const PATH: &AsciiSet = &QUERY.add(b'?').add(b'`').add(b'{').add(b'}');
 
 // https://github.com/package-url/purl-spec/blob/master/PURL-SPECIFICATION.rst#how-to-build-purl-string-from-its-components
 // We mostly use the standard URL rules, but the PURL spec says '@' '?' '#' must
-// be escaped except when used as a separator.
-const PURL_PATH: &AsciiSet = &PATH.add(b'@').add(b'?').add(b'#');
+// be escaped except when used as a separator, and we do all the encoding in one
+// pass so we need to include '%'.
+const PURL_PATH: &AsciiSet = &PATH.add(b'@').add(b'?').add(b'#').add(b'%');
 const PURL_PATH_SEGMENT: &AsciiSet = &PURL_PATH.add(b'/');
 // For compatibility with PURL implementations that treat qualifiers as
 // form-urlencoded, escape '+' as well.
-const PURL_QUERY: &AsciiSet = &QUERY.add(b'@').add(b'?').add(b'#').add(b'+');
-const PURL_FRAGMENT: &AsciiSet = &FRAGMENT.add(b'@').add(b'?').add(b'#');
+const PURL_QUERY: &AsciiSet = &QUERY.add(b'@').add(b'?').add(b'#').add(b'+').add(b'%');
+const PURL_FRAGMENT: &AsciiSet = &FRAGMENT.add(b'@').add(b'?').add(b'#').add(b'%');
 
 impl<T> fmt::Display for GenericPurl<T>
 where

diff --git a/purl_test/src/lib.rs b/purl_test/src/lib.rs
@@ -1260,3 +1260,39 @@ fn plus_signs_and_spaces() {
         "Incorrect string representation"
     );
 }
+#[test]
+/// unsupported: percent signs
+fn unsupported_percent_signs() {
+    assert!(
+        matches!(Purl::from_str("pkg:generic/%40100%25/100%25@100%25?repository_url=https://example.com/100%2525/#100%25"),
+        Err(PackageError::UnsupportedType)), "Type {} is not supported", "generic"
+    );
+    let parsed = match GenericPurl::<String>::from_str(
+        "pkg:generic/%40100%25/100%25@100%25?repository_url=https://example.com/100%2525/#100%25",
+    ) {
+        Ok(purl) => purl,
+        Err(error) => {
+            panic!(
+                "Failed to parse valid purl {:?}: {}",
+                "pkg:generic/%40100%25/100%25@100%25?repository_url=https://example.com/100%2525/#100%25",
+                error
+            )
+        },
+    };
+    assert_eq!("generic", parsed.package_type(), "Incorrect package type");
+    assert_eq!(Some("@100%"), parsed.namespace(), "Incorrect namespace");
+    assert_eq!("100%", parsed.name(), "Incorrect name");
+    assert_eq!(Some("100%"), parsed.version(), "Incorrect version");
+    assert_eq!(Some("100%"), parsed.subpath(), "Incorrect subpath");
+    let expected_qualifiers: HashMap<&str, &str> =
+        [("repository_url", "https://example.com/100%25/")].into_iter().collect();
+    assert_eq!(
+        expected_qualifiers,
+        parsed.qualifiers().iter().map(|(k, v)| (k.as_str(), v)).collect::<HashMap<&str, &str>>()
+    );
+    assert_eq!(
+        "pkg:generic/%40100%25/100%25@100%25?repository_url=https://example.com/100%2525/#100%25",
+        &parsed.to_string(),
+        "Incorrect string representation"
+    );
+}
diff --git a/xtask/src/generate_tests/phylum-test-suite-data.json b/xtask/src/generate_tests/phylum-test-suite-data.json
@@ -120,5 +120,19 @@
     },
     "subpath": null,
     "is_invalid": false
+  },
+  {
+    "description": "percent signs",
+    "purl": "pkg:generic/%40100%25/100%25@100%25?repository_url=https://example.com/100%2525/#100%25",
+    "canonical_purl": "pkg:generic/%40100%25/100%25@100%25?repository_url=https://example.com/100%2525/#100%25",
+    "type": "generic",
+    "namespace": "@100%",
+    "name": "100%",
+    "version": "100%",
+    "qualifiers": {
+      "repository_url": "https://example.com/100%25/"
+    },
+    "subpath": "100%",
+    "is_invalid": false
   }
 ]