Reranko05 commented on code in PR #51038:
URL: https://github.com/apache/arrow/pull/51038#discussion_r4072096192


##########
cpp/src/arrow/json/parser.cc:
##########
@@ -762,150 +743,276 @@ class HandlerBase : public BlockParser,
   }
 
  protected:
-  template <typename Handler, typename Stream>
-  Status DoParse(Handler& handler, Stream&& json, size_t json_size) {
-    constexpr auto parse_flags = rj::kParseIterativeFlag | 
rj::kParseNanAndInfFlag |
-                                 rj::kParseStopWhenDoneFlag |
-                                 rj::kParseNumbersAsStringsFlag;
-
-    rj::Reader reader;
-    // ensure that the loop can exit when the block too large.
-    for (; num_rows_ < std::numeric_limits<int32_t>::max(); ++num_rows_) {
-      auto ok = reader.Parse<parse_flags>(json, handler);
-      switch (ok.Code()) {
-        case rj::kParseErrorNone:
-          // parse the next object
-          continue;
-        case rj::kParseErrorDocumentEmpty:
-          if (json.Tell() < json_size) {
-            return ParseError(rj::GetParseError_En(ok.Code()));
-          }
-          // parsed all objects, finish
-          return Status::OK();
-        case rj::kParseErrorTermination:
-          // handler emitted an error
-          return handler.Error();
-        default:
-          // rj emitted an error
-          return ParseError(rj::GetParseError_En(ok.Code()), " in row ", 
num_rows_);
+  Status DoParse(const std::shared_ptr<Buffer>& json) {
+    RETURN_NOT_OK(ReserveScalarStorage(json->size()));
+
+    const std::string_view input(reinterpret_cast<const char*>(json->data()),
+                                 json->size());
+
+    const int64_t input_size = input.size();
+    if (internal::ConsumeJsonWhitespace(input, /*trailing=*/false) == 
input_size) {
+      return Status::OK();
+    }
+
+    auto parse = [&](const auto& input) -> Status {
+      ARROW_ASSIGN_OR_RAISE(auto stream, 
arrow::internal::ResolveSimdjsonResult(
+                                             parser_.iterate_many(input),
+                                             "Failed to create JSON document 
stream"));
+
+      for (auto document_result : stream) {
+        ARROW_ASSIGN_OR_RAISE(
+            auto document,
+            arrow::internal::ResolveSimdjsonResult(
+                document_result, "Failed to iterate JSON document stream"));
+
+        if (num_rows_ == std::numeric_limits<int32_t>::max()) {
+          return Status::Invalid("Row count overflowed int32_t");
+        }
+
+        ARROW_ASSIGN_OR_RAISE(
+            auto value,
+            arrow::internal::ResolveSimdjsonResult(
+                document.get_value(), "JSON parse error: Failed to get JSON 
value"));
+
+        RETURN_NOT_OK(ParseValue(value));
+
+        ++num_rows_;
+      }
+
+      if (stream.truncated_bytes() != 0) {
+        return ParseError("The document is empty");
       }
+
+      return Status::OK();
+    };
+
+    if (json->capacity() - json->size() >=
+        static_cast<int64_t>(simdjson::SIMDJSON_PADDING)) {
+      const auto padded_json = simdjson::padded_string_view(
+          reinterpret_cast<const char*>(json->data()), json->size(), 
json->capacity());
+      return parse(padded_json);
     }
-    return Status::Invalid("Row count overflowed int32_t");
-  }
 
-  template <typename Handler>
-  Status DoParse(Handler& handler, const std::shared_ptr<Buffer>& json) {
-    RETURN_NOT_OK(ReserveScalarStorage(json->size()));
-    rj::MemoryStream ms(reinterpret_cast<const char*>(json->data()), 
json->size());
-    using InputStream = rj::EncodedInputStream<rj::UTF8<>, rj::MemoryStream>;
-    return DoParse(handler, InputStream(ms), 
static_cast<size_t>(json->size()));
+    simdjson::padded_string padded_json(reinterpret_cast<const 
char*>(json->data()),
+                                        json->size());
+    return parse(padded_json);
   }
 
-  /// \defgroup handlerbase-append-methods append non-nested values
-  ///
-  /// @{
-
   template <Kind::type kind>
-  Status AppendScalar(BuilderPtr builder, std::string_view scalar) {
-    if (ARROW_PREDICT_FALSE(builder.kind != kind)) {
-      return IllegallyChangedTo(kind);
+  Status MaybePromoteFromNull() {
+    if (builder_.kind != Kind::kNull) {
+      return Status::OK();
     }
-    auto index = static_cast<int32_t>(scalar_values_builder_.length());
-    auto value_length = static_cast<int32_t>(scalar.size());
-    RETURN_NOT_OK(Cast<kind>(builder)->Append(index, value_length));
-    RETURN_NOT_OK(scalar_values_builder_.Reserve(1));
-    scalar_values_builder_.UnsafeAppend(scalar);
+
+    auto parent = builder_stack_.back();
+
+    if (parent.kind == Kind::kArray) {
+      auto list_builder = Cast<Kind::kArray>(parent);
+      DCHECK_EQ(list_builder->value_builder(), builder_);
+
+      RETURN_NOT_OK(builder_set_.MakeBuilder<kind>(builder_.index, &builder_));
+
+      list_builder = Cast<Kind::kArray>(parent);
+      list_builder->value_builder(builder_);
+    } else {
+      auto struct_builder = Cast<Kind::kObject>(parent);
+      DCHECK_EQ(struct_builder->field_builder(field_index_), builder_);
+
+      RETURN_NOT_OK(builder_set_.MakeBuilder<kind>(builder_.index, &builder_));
+
+      struct_builder = Cast<Kind::kObject>(parent);
+      struct_builder->field_builder(field_index_, builder_);
+    }
+
     return Status::OK();
   }
 
-  /// @}
+  Status ParseValue(sj::value value) {
+    ARROW_ASSIGN_OR_RAISE(auto type, arrow::internal::ResolveSimdjsonResult(
+                                         value.type(), "Failed to determine 
JSON type"));
 
-  Status StartObjectImpl() {
+    switch (type) {
+      case sj::json_type::null: {
+        ARROW_ASSIGN_OR_RAISE([[maybe_unused]] auto is_null,
+                              arrow::internal::ResolveSimdjsonResult(
+                                  value.is_null(), "Failed to validate JSON 
null"));
+        return Null();
+      }
+
+      case sj::json_type::boolean: {
+        RETURN_NOT_OK(MaybePromoteFromNull<Kind::kBoolean>());
+
+        ARROW_ASSIGN_OR_RAISE(auto boolean,
+                              arrow::internal::ResolveSimdjsonResult(
+                                  value.get_bool(), "Failed to get JSON 
boolean"));
+        return Bool(boolean);
+      }
+
+      case sj::json_type::string: {
+        RETURN_NOT_OK(MaybePromoteFromNull<Kind::kString>());
+
+        ARROW_ASSIGN_OR_RAISE(auto string,
+                              arrow::internal::ResolveSimdjsonResult(
+                                  value.get_string(), "Failed to get JSON 
string"));
+        return String(string);
+      }
+
+      case sj::json_type::number: {
+        RETURN_NOT_OK(MaybePromoteFromNull<Kind::kNumber>());
+        auto raw_number = value.raw_json_token();
+        RETURN_NOT_OK(arrow::internal::ResolveSimdjsonResult(
+            value.get_number(), "Failed to parse JSON number"));

Review Comment:
   `raw_json_token()` gives us the raw token text, but doesn't validate the 
number. `get_number()` is intentionally called here to validate the numeric 
syntax before passing the raw token to `RawNumber()`



-- 
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.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]

Reply via email to