From 9f7d9da449cab4119d07da3ecd2e3b868e092afd Mon Sep 17 00:00:00 2001
From: Charlie Marsh <charlie.r.marsh@gmail.com>
Date: Mon, 16 Sep 2024 19:18:20 -0400
Subject: [PATCH] Prune unzipped source distributions in `uv cache prune --ci`
 (#7446)

## Summary

It's very unlikely that retaining these is beneficial, since you tend to
partition the cache by platform anyway.

Closes https://github.com/astral-sh/uv/issues/7394.
---
 crates/uv-cache/src/lib.rs     | 27 +++++++++++++++++++++++----
 crates/uv/tests/cache_prune.rs |  2 +-
 docs/concepts/cache.md         |  6 +++---
 3 files changed, 27 insertions(+), 8 deletions(-)

diff --git a/crates/uv-cache/src/lib.rs b/crates/uv-cache/src/lib.rs
index 0ecf2f39e018..e97db0897c2a 100644
--- a/crates/uv-cache/src/lib.rs
+++ b/crates/uv-cache/src/lib.rs
@@ -447,12 +447,31 @@ impl Cache {
                 Err(err) => return Err(err),
             }
 
-            // Remove any unzipped wheels (i.e., symlinks) from the built wheels cache.
             for entry in walkdir::WalkDir::new(self.bucket(CacheBucket::SourceDistributions)) {
                 let entry = entry?;
-                if entry.file_type().is_symlink() {
-                    debug!("Removing unzipped wheel entry: {}", entry.path().display());
-                    summary += rm_rf(entry.path())?;
+
+                // If the directory contains a `metadata.msgpack`, then it's a built wheel revision.
+                if !entry.file_type().is_dir() {
+                    continue;
+                }
+
+                if !entry.path().join("metadata.msgpack").exists() {
+                    continue;
+                }
+
+                // Remove any symlinks and directories in the revision. The symlinks represent
+                // unzipped wheels, and the directories represent the source distribution archives.
+                for entry in fs_err::read_dir(entry.path())? {
+                    let entry = entry?;
+                    let path = entry.path();
+
+                    if path.is_dir() {
+                        debug!("Removing unzipped built wheel entry: {}", path.display());
+                        summary += rm_rf(path)?;
+                    } else if path.is_symlink() {
+                        debug!("Removing unzipped built wheel entry: {}", path.display());
+                        summary += rm_rf(path)?;
+                    }
                 }
             }
         }
diff --git a/crates/uv/tests/cache_prune.rs b/crates/uv/tests/cache_prune.rs
index 2c3c436a7a0e..227150c49265 100644
--- a/crates/uv/tests/cache_prune.rs
+++ b/crates/uv/tests/cache_prune.rs
@@ -204,7 +204,7 @@ fn prune_unzipped() -> Result<()> {
 
     ----- stderr -----
     Pruning cache at: [CACHE_DIR]/
-    Removed 162 files ([SIZE])
+    Removed 170 files ([SIZE])
     "###);
 
     // Reinstalling the source distribution should not require re-downloading the source
diff --git a/docs/concepts/cache.md b/docs/concepts/cache.md
index 04caf9889d35..7f5c9441b00f 100644
--- a/docs/concepts/cache.md
+++ b/docs/concepts/cache.md
@@ -115,9 +115,9 @@ from source tends to be worthwhile, since the wheel building process can be expe
 for extension modules.
 
 To support this caching strategy, uv provides a `uv cache prune --ci` command, which removes all
-pre-built wheels from the cache but retains any wheels that were built from source. We recommend
-running `uv cache prune --ci` at the end of your continuous integration job to ensure maximum cache
-efficiency. For an example, see the
+pre-built wheels and unzipped source distributions from the cache, but retains any wheels that were
+built from source. We recommend running `uv cache prune --ci` at the end of your continuous
+integration job to ensure maximum cache efficiency. For an example, see the
 [GitHub integration guide](../guides/integration/github.md#caching).
 
 ## Cache directory