tests: Add regex-based ignore rules for ref files

There are cases where we need to ignore files with specific extensions
(e.g., when Mercurial litters the file system with patch
rejects). Implement this functionality using a helper class
(FileIgnoreList) that supports both regular expressions and basic
string comparisons.

Change-Id: I34549754bd2e10ed230ffb2dc057403349f8fa78
Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com>

tests/testing/helpers.py

@@ -40,6 +40,7 @@
 import subprocess
 from threading import Timer
 import time
+import re
 
 class CallTimeoutException(Exception):
     """Exception that indicates that a process call timed out"""
@@ -105,6 +106,47 @@ class ProcessHelper(subprocess.Popen):
         else:
             return status, stdout, stderr
 
+class FileIgnoreList(object):
+    """Helper class to implement file ignore lists.
+
+    This class implements ignore lists using plain string matching and
+    regular expressions. In the simplest use case, rules are created
+    statically upon initialization:
+
+        ignore_list = FileIgnoreList(name=("ignore_me.txt", ), rex=(r".*~", )
+
+    Ignores can be queried using in the same ways as normal Python
+    containers:
+
+        if file_name in ignore_list:
+            print "Ignoring %s" % file_name
+
+
+    New rules can be added at runtime by extending the list in the
+    rules attribute:
+
+        ignore_list.rules.append(FileIgnoreList.simple("bar.txt"))
+    """
+
+    @staticmethod
+    def simple(r):
+        return lambda f: f == r
+
+    @staticmethod
+    def rex(r):
+        re_obj = r if hasattr(r, "search") else re.compile(r)
+        return lambda name: re_obj.search(name)
+
+    def __init__(self, names=(), rex=()):
+        self.rules = [ FileIgnoreList.simple(n) for n in names ] + \
+                     [ FileIgnoreList.rex(r) for r in rex ]
+
+    def __contains__(self, name):
+        for rule in self.rules:
+            if rule(name):
+                return True
+        return False
+
 if __name__ == "__main__":
     # Run internal self tests to ensure that the helpers are working
     # properly. The expected output when running this script is
@@ -129,4 +171,20 @@ if __name__ == "__main__":
     except CallTimeoutException:
         pass
 
+    ignore_list = FileIgnoreList(
+        names=("ignore.txt", "foo/test.txt"),
+        rex=(r"~$", re.compile("^#")))
+
+    assert "ignore.txt" in ignore_list
+    assert "bar.txt" not in ignore_list
+    assert "foo/test.txt" in ignore_list
+    assert "test.txt" not in ignore_list
+    assert "file1.c~" in ignore_list
+    assert "file1.c" not in ignore_list
+    assert "#foo" in ignore_list
+    assert "foo#" not in ignore_list
+
+    ignore_list.rules.append(FileIgnoreList.simple("bar.txt"))
+    assert "bar.txt" in ignore_list
+
     print "SUCCESS!"

tests/testing/tests.py

@@ -224,16 +224,23 @@ class ClassicTest(Test):
     # The diff ignore list contains all files that shouldn't be diffed
     # using DiffOutFile. These files typically use special-purpose
     # diff tools (e.g., DiffStatFile).
-    diff_ignore_files = (
+    diff_ignore_files = FileIgnoreList(
-        # Stat files use a special stat differ
+        names=(
-        "stats.txt",
+            # Stat files use a special stat differ
-    )
+            "stats.txt",
+        ), rex=(
+        ))
 
     # These files should never be included in the list of
     # reference files. This list should include temporary files
     # and other files that we don't care about.
-    ref_ignore_files = (
+    ref_ignore_files = FileIgnoreList(
-    )
+        names=(
+        ), rex=(
+            # Mercurial sometimes leaves backups when applying MQ patches
+            r"\.orig$",
+            r"\.rej$",
+        ))
 
     def __init__(self, gem5, output_dir, config_tuple,
                  timeout=None,