Skip existing, second iteration: Check the index before uploading (#8531)

Co-authored-by: Zanie Blue <contact@zanie.dev>

Author: konstin

Cargo.lock

@@ -4819,6 +4819,22 @@ pub struct PublishArgs {
         value_parser = parse_insecure_host,
     )]
     pub allow_insecure_host: Option<Vec<Maybe<TrustedHost>>>,
+
+    /// Check an index URL for existing files to skip duplicate uploads.
+    ///
+    /// This option allows retrying publishing that failed after only some, but not all files have
+    /// been uploaded, and handles error due to parallel uploads of the same file.
+    ///
+    /// Before uploading, the index is checked. If the exact same file already exists in the index,
+    /// the file will not be uploaded. If an error occurred during the upload, the index is checked
+    /// again, to handle cases where the identical file was uploaded twice in parallel.
+    ///
+    /// The exact behavior will vary based on the index. When uploading to PyPI, uploading the same
+    /// file succeeds even without `--check-url`, while most other indexes error.
+    ///
+    /// The index must provide one of the supported hashes (SHA-256, SHA-384, or SHA-512).
+    #[arg(long,env = EnvVars::UV_PUBLISH_CHECK_URL)]
+    pub check_url: Option<IndexUrl>,
 }
 
 /// See [PEP 517](https://peps.python.org/pep-0517/) and

crates/uv-cli/src/lib.rs

@@ -31,7 +31,7 @@ use crate::cached_client::CacheControl;
 use crate::html::SimpleHtml;
 use crate::remote_metadata::wheel_metadata_from_remote_zip;
 use crate::rkyvutil::OwnedArchive;
-use crate::{CachedClient, CachedClientError, Error, ErrorKind};
+use crate::{BaseClient, CachedClient, CachedClientError, Error, ErrorKind};
 
 /// A builder for an [`RegistryClient`].
 #[derive(Debug, Clone)]
@@ -143,6 +143,27 @@ impl<'a> RegistryClientBuilder<'a> {
             timeout,
         }
     }
+
+    /// Share the underlying client between two different middleware configurations.
+    pub fn wrap_existing(self, existing: &BaseClient) -> RegistryClient {
+        // Wrap in any relevant middleware and handle connectivity.
+        let client = self.base_client_builder.wrap_existing(existing);
+
+        let timeout = client.timeout();
+        let connectivity = client.connectivity();
+
+        // Wrap in the cache middleware.
+        let client = CachedClient::new(client);
+
+        RegistryClient {
+            index_urls: self.index_urls,
+            index_strategy: self.index_strategy,
+            cache: self.cache,
+            connectivity,
+            client,
+            timeout,
+        }
+    }
 }
 
 impl<'a> TryFrom<BaseClientBuilder<'a>> for RegistryClientBuilder<'a> {

crates/uv-client/src/registry_client.rs

@@ -23,15 +23,6 @@ impl Hasher {
             Hasher::Sha512(hasher) => hasher.update(data),
         }
     }
-
-    pub fn finalize(self) -> Vec<u8> {
-        match self {
-            Hasher::Md5(hasher) => hasher.finalize().to_vec(),
-            Hasher::Sha256(hasher) => hasher.finalize().to_vec(),
-            Hasher::Sha384(hasher) => hasher.finalize().to_vec(),
-            Hasher::Sha512(hasher) => hasher.finalize().to_vec(),
-        }
-    }
 }
 
 impl From<HashAlgorithm> for Hasher {

crates/uv-extract/src/hash.rs

@@ -13,9 +13,12 @@ license.workspace = true
 doctest = false
 
 [dependencies]
+uv-cache = { workspace = true }
 uv-client = { workspace = true }
 uv-configuration = { workspace = true }
 uv-distribution-filename = { workspace = true }
+uv-distribution-types = { workspace = true }
+uv-extract = { workspace = true }
 uv-fs = { workspace = true }
 uv-metadata = { workspace = true }
 uv-pypi-types = { workspace = true }
@@ -35,7 +38,6 @@ reqwest-retry = { workspace = true }
 rustc-hash = { workspace = true }
 serde = { workspace = true, features = ["derive"] }
 serde_json = { workspace = true }
-sha2 = { workspace = true }
 thiserror = { workspace = true }
 tokio = { workspace = true }
 tokio-util = { workspace = true , features = ["io"] }