[CI] Refactor compute_projects to Introduce Meta Projects

This patch introduces the concept of meta projects into the
compute_projects script. Meta projects are projects like CIR and
GoogleTest where they do not have their own top level project. This
patch adds a little bit of extra code in exchange for making meta
projects a first level concept that can be configured almost entirely by
changing around the mappings at the top of the file. This patch also
refactors the project skipping functionality to use meta projects.

This (arguably) makes the CIR support a little bit cleaner and is
necessary for some future improvements like running all the tests on
Github workflow changes and running tests when third-party changes.

Reviewers: Endilll, andykaylor, lnihlen, gburgessiv, dschuff, Keenuts, cmtice

Reviewed By: andykaylor

Pull Request: #150249

Author: boomanaiden154

.ci/compute_projects.py

@@ -144,6 +144,21 @@
 
 RUNTIMES = {"libcxx", "libcxxabi", "libunwind", "compiler-rt", "libc"}
 
+# Meta projects are projects that need explicit handling but do not reside
+# in their own top level folder. To add a meta project, the start of the path
+# for the metaproject should be mapped to the name of the project below.
+# Multiple paths can map to the same metaproject.
+META_PROJECTS = {
+    ("clang", "lib", "CIR"): "CIR",
+    ("clang", "test", "CIR"): "CIR",
+    ("clang", "include", "clang", "CIR"): "CIR",
+    ("*", "docs"): "docs",
+    ("llvm", "utils", "gn"): "gn",
+}
+
+# Projects that should not run any tests. These need to be metaprojects.
+SKIP_PROJECTS = ["docs", "gn"]
+
 
 def _add_dependencies(projects: Set[str], runtimes: Set[str]) -> Set[str]:
     projects_with_dependents = set(projects)
@@ -236,29 +251,34 @@ def _compute_runtimes_to_build(
     return _exclude_projects(runtimes_to_build, platform)
 
 
+def _path_matches(matcher: tuple[str], file_path: tuple[str]) -> bool:
+    if len(file_path) < len(matcher):
+        return False
+    for match_part, file_part in zip(matcher, file_path):
+        if match_part == "*" or file_part == "*":
+            continue
+        if match_part != file_part:
+            return False
+    return True
+
+
+def _get_modified_projects_for_file(modified_file: str) -> Set[str]:
+    modified_projects = set()
+    path_parts = pathlib.Path(modified_file).parts
+    for meta_project_files in META_PROJECTS.keys():
+        if _path_matches(meta_project_files, path_parts):
+            meta_project = META_PROJECTS[meta_project_files]
+            if meta_project in SKIP_PROJECTS:
+                return set()
+            modified_projects.add(meta_project)
+    modified_projects.add(pathlib.Path(modified_file).parts[0])
+    return modified_projects
+
+
 def _get_modified_projects(modified_files: list[str]) -> Set[str]:
     modified_projects = set()
     for modified_file in modified_files:
-        path_parts = pathlib.Path(modified_file).parts
-        # Exclude files in the docs directory. They do not impact an test
-        # targets and there is a separate workflow used for ensuring the
-        # documentation builds.
-        if len(path_parts) > 2 and path_parts[1] == "docs":
-            continue
-        # Exclude files for the gn build. We do not test it within premerge
-        # and changes occur often enough that they otherwise take up
-        # capacity.
-        if len(path_parts) > 3 and path_parts[:3] == ("llvm", "utils", "gn"):
-            continue
-        # If the file is in the clang/lib/CIR directory, add the CIR project.
-        if len(path_parts) > 3 and (
-            path_parts[:3] == ("clang", "lib", "CIR")
-            or path_parts[:3] == ("clang", "test", "CIR")
-            or path_parts[:4] == ("clang", "include", "clang", "CIR")
-        ):
-            modified_projects.add("CIR")
-            # Fall through to add clang.
-        modified_projects.add(pathlib.Path(modified_file).parts[0])
+        modified_projects.update(_get_modified_projects_for_file(modified_file))
     return modified_projects