Fix octal pattern matching in regex string (#9993)

Closes #9946 

Fixes decoding logic in regex pattern compile step to consume only up to the last octal character. The original logic was incorrectly discarding the next pattern character. And if the octal characters were specified at the end of the pattern invalid bytes were read passed the end of the pattern. This is what caused the intermittent failure since sometimes the invalid bytes were 0 which masked the issue.

This PR also includes tests for octal patterns in various positions in the regex pattern.

Authors:
  - David Wendt (https://github.com/davidwendt)

Approvers:
  - Conor Hoekstra (https://github.com/codereport)
  - Mike Wilson (https://github.com/hyperbolic2346)
  - Nghia Truong (https://github.com/ttnghia)

URL: #9993

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));

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);