From d7f97ada22e1296d879e1de49b97ec9e50d32490 Mon Sep 17 00:00:00 2001
From: David Wendt <dwendt@nvidia.com>
Date: Fri, 7 Jan 2022 09:29:45 -0500
Subject: [PATCH 1/2] Fix octal pattern matching in regex string

---
 cpp/src/strings/regex/regcomp.cpp    |  8 ++++----
 cpp/tests/strings/contains_tests.cpp | 15 ++++++++++++++-
 2 files changed, 18 insertions(+), 5 deletions(-)

diff --git a/cpp/src/strings/regex/regcomp.cpp b/cpp/src/strings/regex/regcomp.cpp
index 7da4915d668..9471380fe0b 100644
--- a/cpp/src/strings/regex/regcomp.cpp
+++ b/cpp/src/strings/regex/regcomp.cpp
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2019-2021, NVIDIA CORPORATION.  All rights reserved.
+ * Copyright (c) 2019-2022, NVIDIA CORPORATION.  All rights reserved.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -258,10 +258,10 @@ class regex_parser {
       // treating all quoted numbers as Octal, since we are not supporting backreferences
       if (yy >= '0' && yy <= '7') {
         yy         = yy - '0';
-        char32_t c = *exprp++;
+        char32_t c = *exprp;
         while (c >= '0' && c <= '7') {
           yy = (yy << 3) | (c - '0');
-          c  = *exprp++;
+          c  = *++exprp;
         }
         return CHAR;
       } else {
@@ -926,7 +926,7 @@ void reprog::optimize2()
   _startinst_ids.push_back(-1);  // terminator mark
 }
 
-#ifndef NDBUG
+#ifndef NDEBUG
 void reprog::print(regex_flags const flags)
 {
   printf("Flags = 0x%08x\n", static_cast<uint32_t>(flags));
diff --git a/cpp/tests/strings/contains_tests.cpp b/cpp/tests/strings/contains_tests.cpp
index f95b282171f..48c4aac9e8a 100644
--- a/cpp/tests/strings/contains_tests.cpp
+++ b/cpp/tests/strings/contains_tests.cpp
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2019, NVIDIA CORPORATION.
+ * Copyright (c) 2019-2022, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -237,6 +237,19 @@ TEST_F(StringsContainsTests, MatchesIPV4Test)
   }
 }
 
+TEST_F(StringsContainsTests, OctalTest)
+{
+  cudf::test::strings_column_wrapper strings({"AZ", "B", "CDAZEY", ""});
+  auto strings_view = cudf::strings_column_view(strings);
+  cudf::test::fixed_width_column_wrapper<bool> expected({1, 0, 1, 0});
+  auto results = cudf::strings::contains_re(strings_view, "\\101");
+  CUDF_TEST_EXPECT_COLUMNS_EQUAL(*results, expected);
+  results = cudf::strings::contains_re(strings_view, "\\101Z");
+  CUDF_TEST_EXPECT_COLUMNS_EQUAL(*results, expected);
+  results = cudf::strings::contains_re(strings_view, "D*\\101\\132");
+  CUDF_TEST_EXPECT_COLUMNS_EQUAL(*results, expected);
+}
+
 TEST_F(StringsContainsTests, EmbeddedNullCharacter)
 {
   std::vector<std::string> data(10);

From 377ab9da64bace39545281711a8d5a7451bdf141 Mon Sep 17 00:00:00 2001
From: David Wendt <dwendt@nvidia.com>
Date: Wed, 12 Jan 2022 09:26:54 -0500
Subject: [PATCH 2/2] change *++exprp to *(++exprp)

---
 cpp/src/strings/regex/regcomp.cpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/cpp/src/strings/regex/regcomp.cpp b/cpp/src/strings/regex/regcomp.cpp
index 9471380fe0b..8fbd82b8dc7 100644
--- a/cpp/src/strings/regex/regcomp.cpp
+++ b/cpp/src/strings/regex/regcomp.cpp
@@ -261,7 +261,7 @@ class regex_parser {
         char32_t c = *exprp;
         while (c >= '0' && c <= '7') {
           yy = (yy << 3) | (c - '0');
-          c  = *++exprp;
+          c  = *(++exprp);
         }
         return CHAR;
       } else {