Make hashes optional (#910)

There is no guarantee that indexes provide hashes at all or the sha256
we support specifically. [PEP
503](https://peps.python.org/pep-0503/#specification):

> The URL SHOULD include a hash in the form of a URL fragment with the
following syntax: #<hashname>=<hashvalue>, where <hashname> is the
lowercase name of the hash function (such as sha256) and <hashvalue> is
the hex encoded digest.

We instead use the url as input to generate a hash when caching.

crates/distribution-types/Cargo.toml

@@ -24,10 +24,12 @@ requirements-txt = { path = "../requirements-txt" }
 
 anyhow = { workspace = true }
 chrono = { workspace = true, features = ["serde"] }
+data-encoding = { workspace = true }
 fs-err = { workspace = true }
 once_cell = { workspace = true }
 rustc-hash = { workspace = true }
 serde = { workspace = true, features = ["derive"] }
 serde_json = { workspace = true }
+sha2 = { workspace = true }
 thiserror = { workspace = true }
 url = { workspace = true }

crates/distribution-types/src/id.rs

@@ -18,6 +18,12 @@ impl DistributionId {
     }
 }
 
+impl DistributionId {
+    pub fn as_str(&self) -> &str {
+        &self.0
+    }
+}
+
 /// A unique identifier for a resource, like a URL or a Git repository.
 #[derive(Debug, Clone, PartialEq, Eq, Hash, PartialOrd, Ord)]
 pub struct ResourceId(String);

crates/distribution-types/src/lib.rs

@@ -652,11 +652,19 @@ impl Identifier for Url {
 
 impl Identifier for File {
     fn distribution_id(&self) -> DistributionId {
-        DistributionId::new(self.hashes.sha256.clone())
+        if let Some(hash) = &self.hashes.sha256 {
+            DistributionId::new(hash)
+        } else {
+            self.url.distribution_id()
+        }
     }
 
     fn resource_id(&self) -> ResourceId {
-        ResourceId::new(self.hashes.sha256.clone())
+        if let Some(hash) = &self.hashes.sha256 {
+            ResourceId::new(hash)
+        } else {
+            self.url.resource_id()
+        }
     }
 }