[GitHub] [arrow] lidavidm commented on a change in pull request #10369: ARROW-12835: [C++][Python][R] Implement case-insensitive match using RE2

[GitBox <gi...@apache.org>]

lidavidm commented on a change in pull request #10369:
URL: https://github.com/apache/arrow/pull/10369#discussion_r639947037



##########
File path: cpp/src/arrow/compute/kernels/scalar_string.cc
##########
@@ -509,38 +484,109 @@ struct PlainSubstringMatcher {
   bool Match(util::string_view current) const { return Find(current) >= 0; }
 };
 
-const FunctionDoc match_substring_doc(
-    "Match strings against literal pattern",
-    ("For each string in `strings`, emit true iff it contains a given pattern.\n"
-     "Null inputs emit null.  The pattern must be given in MatchSubstringOptions."),
-    {"strings"}, "MatchSubstringOptions");
-
 #ifdef ARROW_WITH_RE2
 struct RegexSubstringMatcher {
   const MatchSubstringOptions& options_;
   const RE2 regex_match_;
 
   static Result<std::unique_ptr<RegexSubstringMatcher>> Make(
-      const MatchSubstringOptions& options) {
-    auto matcher = ::arrow::internal::make_unique<RegexSubstringMatcher>(options);
+      const MatchSubstringOptions& options, bool literal = false) {
+    auto matcher =
+        ::arrow::internal::make_unique<RegexSubstringMatcher>(options, literal);
     RETURN_NOT_OK(RegexStatus(matcher->regex_match_));
     return std::move(matcher);
   }
 
-  explicit RegexSubstringMatcher(const MatchSubstringOptions& options)
-      : options_(options), regex_match_(options_.pattern, RE2::Quiet) {}
+  explicit RegexSubstringMatcher(const MatchSubstringOptions& options,
+                                 bool literal = false)
+      : options_(options),
+        regex_match_(options_.pattern, MakeRE2Options(options, literal)) {}
 
   bool Match(util::string_view current) const {
     auto piece = re2::StringPiece(current.data(), current.length());
     return re2::RE2::PartialMatch(piece, regex_match_);
   }
+
+  static RE2::RE2::Options MakeRE2Options(const MatchSubstringOptions& options,
+                                          bool literal) {
+    RE2::RE2::Options re2_options(RE2::Quiet);
+    re2_options.set_case_sensitive(!options.ignore_case);
+    re2_options.set_literal(literal);
+    return re2_options;
+  }
+};
+#endif
+
+template <typename Type, typename Matcher>
+struct MatchSubstringImpl {
+  using offset_type = typename Type::offset_type;
+
+  static Status Exec(KernelContext* ctx, const ExecBatch& batch, Datum* out,
+                     const Matcher* matcher) {
+    StringBoolTransform<Type>(
+        ctx, batch,
+        [&matcher](const void* raw_offsets, const uint8_t* data, int64_t length,
+                   int64_t output_offset, uint8_t* output) {
+          const offset_type* offsets = reinterpret_cast<const offset_type*>(raw_offsets);
+          FirstTimeBitmapWriter bitmap_writer(output, output_offset, length);
+          for (int64_t i = 0; i < length; ++i) {
+            const char* current_data = reinterpret_cast<const char*>(data + offsets[i]);
+            int64_t current_length = offsets[i + 1] - offsets[i];
+            if (matcher->Match(util::string_view(current_data, current_length))) {
+              bitmap_writer.Set();
+            }
+            bitmap_writer.Next();
+          }
+          bitmap_writer.Finish();
+        },
+        out);
+    return Status::OK();
+  }
 };
 
+template <typename Type, typename Matcher>
+struct MatchSubstring {

Review comment:
       There's only one of each. I moved them around in this PR, but it's the same as before.




-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org