automated: kselftest: Rewrite parser to support nesting

automated/linux/kselftest/kselftest.sh

@@ -135,7 +135,7 @@ install() {
     dist_name
     # shellcheck disable=SC2154
     case "${dist}" in
-        debian|ubuntu) install_deps "sed perl wget xz-utils iproute2" "${SKIP_INSTALL}" ;;
+        debian|ubuntu) install_deps "sed perl wget xz-utils iproute2 python3-tap" "${SKIP_INSTALL}" ;;
         centos|fedora) install_deps "sed perl wget xz iproute" "${SKIP_INSTALL}" ;;
         unknown) warn_msg "Unsupported distro: package install skipped" ;;
     esac

automated/linux/kselftest/parse-output.py

@@ -1,6 +1,7 @@
 #!/usr/bin/env python3
 import sys
 import re
+from tap import parser
 
 
 def slugify(line):
@@ -11,25 +12,71 @@ def slugify(line):
     )
 
 
-tests = ""
-for line in sys.stdin:
-    if "# selftests: " in line:
-        tests = slugify(line.replace("\n", "").split("selftests:")[1])
-    elif re.search(r"^.*?not ok \d{1,5} ", line):
-        match = re.match(r"^.*?not ok [0-9]+ (.*?)$", line)
-        ascii_test_line = slugify(re.sub("# .*$", "", match.group(1)))
-        output = f"{tests}_{ascii_test_line} fail"
-        if f"selftests_{tests}" in output:
-            output = re.sub(r"^.*_selftests_", "", output)
-        print(f"{output}")
-    elif re.search(r"^.*?ok \d{1,5} ", line):
-        match = re.match(r"^.*?ok [0-9]+ (.*?)$", line)
-        if "# skip" in match.group(1).lower():
-            ascii_test_line = slugify(re.sub("# skip", "", match.group(1).lower()))
-            output = f"{tests}_{ascii_test_line} skip"
+def parse_nested_tap(string):
+    results = []
+
+    def uncomment(line):
+        # All of the input lines should be comments and begin with #, but let's
+        # be cautious; don't do anything if the line doesn't begin with #.
+        if len(line) > 0 and line[0] == "#":
+            return line[1:].strip()
+        return line
+
+    def make_name(name, directive, ok, skip):
+        # Some of this is to maintain compatibility with the old parser.
+        if name.startswith("selftests:"):
+            name = name[10:]
+        if ok and skip and directive.lower().startswith("skip"):
+            directive = directive[4:]
         else:
-            ascii_test_line = slugify(match.group(1))
-            output = f"{tests}_{ascii_test_line} pass"
-        if f"selftests_{tests}" in output:
-            output = re.sub(r"^.*_selftests_", "", output)
-        print(f"{output}")
+            directive = ""
+        name = f"{name} {directive}".strip()
+        if name == "":
+            name = "<unknown>"
+        return slugify(name)
+
+    def make_result(ok, skip):
+        return ("skip" if skip else "pass") if ok else "fail"
+
+    output = ""
+    ps = parser.Parser()
+    for l in ps.parse_text(string):
+        if l.category == "test":
+            results.append(
+                {
+                    "name": make_name(l.description, l.directive.text, l.ok, l.skip),
+                    "result": make_result(l.ok, l.skip),
+                    "children": parse_nested_tap(output),
+                }
+            )
+            output = ""
+        elif l.category == "diagnostic":
+            output += f"{uncomment(l.text)}\n"
+
+    return results
+
+
+def flatten_results(prefix, results):
+    ret = []
+    for r in results:
+        test = f"{prefix}{r['name']}"
+        children = flatten_results(f"{test}_", r["children"])
+        ret += children + [{"name": test, "result": r["result"]}]
+    return ret
+
+
+def make_names_unique(results):
+    namecounts = {}
+    for r in results:
+        name = r["name"]
+        namecounts[name] = namecounts.get(name, 0) + 1
+        if namecounts[name] > 1:
+            r["name"] += f"_dup{namecounts[name]}"
+
+
+if __name__ == "__main__":
+    results = parse_nested_tap(sys.stdin.read())
+    results = flatten_results("", results)
+    make_names_unique(results)
+    for r in results:
+        print(f"{r['name']} {r['result']}")