syz-ci: improve commit matching

1. Fetch last 200K commits instead of commits for past year.
For merged commits both author date and commit date can be
arbitrary long in past (e.g. we got a commit dated by 2014).

2. Strip some commit prefixes from commits.
We have some trees where backports are prefixed with "BACKPORT:".
Previously we could no match such commits.

1 files changed, 23 insertions, 0 deletions

diff --git a/pkg/git/git_test.go b/pkg/git/git_test.go
new file mode 100644
index 000000000..42d2d3a07
--- /dev/null
+++ b/pkg/git/git_test.go
@@ -0,0 +1,23 @@
+// Copyright 2017 syzkaller project authors. All rights reserved.
+// Use of this source code is governed by Apache 2 LICENSE that can be found in the LICENSE file.
+
+package git
+
+import (
+	"testing"
+)
+
+func TestCanonicalizeCommit(t *testing.T) {
+	tests := map[string]string{
+		"foo bar":                     "foo bar",
+		" foo ":                       "foo",
+		"UPSTREAM: foo bar":           "foo bar",
+		"BACKPORT: UPSTREAM: foo bar": "UPSTREAM: foo bar",
+	}
+	for in, want := range tests {
+		got := CanonicalizeCommit(in)
+		if got != want {
+			t.Errorf("input %q: got %q, want %q", in, got, want)
+		}
+	}
+}