[7.2.1] Enforce and await cleanup in StarlarkBaseExternalContext (b…

…azelbuild#22814)

`StarlarkBaseExternalContext` now implements `AutoCloseable` and, in
`close()`:
1. Cancels all pending async tasks.
2. Awaits their termination.
3. Cleans up the working directory (always for module extensions, on
failure for repo rules).
4. Fails if there were pending async tasks in an otherwise successful
evaluation.

Previously, module extensions didn't do any of those. Repo rules did 1
and 4 and sometimes 3, but not in all cases.

This change required replacing the fixed-size thread pool in
`DownloadManager` with virtual threads, thereby resolving a TODO about
not using a fixed-size thread pool for the `GrpcRemoteDownloader`.

Work towards bazelbuild#22680
Work towards bazelbuild#22748

Closes bazelbuild#22772

PiperOrigin-RevId: 644669599
Change-Id: Ib71e5bf346830b92277ac2bd473e11c834cb2624

Closes bazelbuild#22775

src/main/java/com/google/devtools/build/lib/bazel/repository/starlark/StarlarkRepositoryContext.java

@@ -448,6 +448,118 @@ public void patch(Object patchFile, StarlarkInt stripI, String watchPatch, Starl
     }
   }
 
+  @StarlarkMethod(
+      name = "extract",
+      doc = "Extract an archive to the repository directory.",
+      useStarlarkThread = true,
+      parameters = {
+        @Param(
+            name = "archive",
+            allowedTypes = {
+              @ParamType(type = String.class),
+              @ParamType(type = Label.class),
+              @ParamType(type = StarlarkPath.class)
+            },
+            named = true,
+            doc =
+                "path to the archive that will be unpacked,"
+                    + " relative to the repository directory."),
+        @Param(
+            name = "output",
+            allowedTypes = {
+              @ParamType(type = String.class),
+              @ParamType(type = Label.class),
+              @ParamType(type = StarlarkPath.class)
+            },
+            defaultValue = "''",
+            named = true,
+            doc =
+                "path to the directory where the archive will be unpacked,"
+                    + " relative to the repository directory."),
+        @Param(
+            name = "stripPrefix",
+            defaultValue = "''",
+            named = true,
+            doc =
+                "a directory prefix to strip from the extracted files."
+                    + "\nMany archives contain a top-level directory that contains all files in the"
+                    + " archive. Instead of needing to specify this prefix over and over in the"
+                    + " <code>build_file</code>, this field can be used to strip it from extracted"
+                    + " files."),
+        @Param(
+            name = "rename_files",
+            defaultValue = "{}",
+            named = true,
+            positional = false,
+            doc =
+                "An optional dict specifying files to rename during the extraction. Archive entries"
+                    + " with names exactly matching a key will be renamed to the value, prior to"
+                    + " any directory prefix adjustment. This can be used to extract archives that"
+                    + " contain non-Unicode filenames, or which have files that would extract to"
+                    + " the same path on case-insensitive filesystems."),
+        @Param(
+            name = "watch_archive",
+            defaultValue = "'auto'",
+            positional = false,
+            named = true,
+            doc =
+                "whether to <a href=\"#watch\">watch</a> the archive file. Can be the string "
+                    + "'yes', 'no', or 'auto'. Passing 'yes' is equivalent to immediately invoking "
+                    + "the <a href=\"#watch\"><code>watch()</code></a> method; passing 'no' does "
+                    + "not attempt to watch the file; passing 'auto' will only attempt to watch "
+                    + "the file when it is legal to do so (see <code>watch()</code> docs for more "
+                    + "information."),
+      })
+  public void extract(
+      Object archive,
+      Object output,
+      String stripPrefix,
+      Dict<?, ?> renameFiles, // <String, String> expected
+      String watchArchive,
+      StarlarkThread thread)
+      throws RepositoryFunctionException, InterruptedException, EvalException {
+    StarlarkPath archivePath = getPath("extract()", archive);
+
+    if (!archivePath.exists()) {
+      throw new RepositoryFunctionException(
+          Starlark.errorf("Archive path '%s' does not exist.", archivePath), Transience.TRANSIENT);
+    }
+    if (archivePath.isDir()) {
+      throw Starlark.errorf("attempting to extract a directory: %s", archivePath);
+    }
+    maybeWatch(archivePath, ShouldWatch.fromString(watchArchive));
+
+    StarlarkPath outputPath = getPath("extract()", output);
+    checkInOutputDirectory("write", outputPath);
+
+    Map<String, String> renameFilesMap =
+        Dict.cast(renameFiles, String.class, String.class, "rename_files");
+
+    WorkspaceRuleEvent w =
+        WorkspaceRuleEvent.newExtractEvent(
+            archive.toString(),
+            output.toString(),
+            stripPrefix,
+            renameFilesMap,
+            identifyingStringForLogging,
+            thread.getCallerLocation());
+    env.getListener().post(w);
+
+    env.getListener()
+        .post(
+            new ExtractProgress(
+                outputPath.getPath().toString(), "Extracting " + archivePath.getBasename()));
+    DecompressorValue.decompress(
+        DecompressorDescriptor.builder()
+            .setContext(identifyingStringForLogging)
+            .setArchivePath(archivePath.getPath())
+            .setDestinationPath(outputPath.getPath())
+            .setPrefix(stripPrefix)
+            .setRenameFiles(renameFilesMap)
+            .build());
+    env.getListener().post(new ExtractProgress(outputPath.getPath().toString()));
+  }
+
   @StarlarkMethod(
       name = "watch_tree",
       doc =

src/test/py/bazel/bzlmod/bazel_module_test.py

@@ -1069,6 +1069,5 @@ def testRegression22754(self):
     self.ScratchFile('testdata/WORKSPACE')
     self.RunBazel(['build', ':all'])
 
-
 if __name__ == '__main__':
   absltest.main()