feat: create an exportable version of plan loading

CMakeLists.txt

@@ -10,6 +10,7 @@ message(STATUS "Build type: ${CMAKE_BUILD_TYPE}")
 set(CMAKE_CXX_STANDARD 17)
 set(CMAKE_CXX_STANDARD_REQUIRED True)
 set(CMAKE_EXPORT_COMPILE_COMMANDS ON)
+set(CMAKE_POSITION_INDEPENDENT_CODE TRUE)
 
 option(SUBSTRAIT_CPP_SANITIZE_DEBUG_BUILD
        "Turns on address and undefined memory sanitization runtime checking."
@@ -55,3 +56,4 @@ if(${SUBSTRAIT_CPP_BUILD_TESTING})
 endif()
 
 add_subdirectory(src/substrait)
+add_subdirectory(export)

export/CMakeLists.txt

@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: Apache-2.0
+
+add_subdirectory(planloader)

export/planloader/CMakeLists.txt

@@ -0,0 +1,25 @@
+# SPDX-License-Identifier: Apache-2.0
+
+set(CMAKE_POSITION_INDEPENDENT_CODE TRUE)
+
+if(NOT BUILD_SUBDIR_NAME EQUAL "release")
+  message(
+    SEND_ERROR,
+    "The planloader library does not work in Debug mode due to its dependencies."
+  )
+endif()
+
+add_library(planloader SHARED planloader.cpp)
+set_target_properties(planloader PROPERTIES SUBVERSION 1)
+
+add_dependencies(planloader substrait_io)
+target_link_libraries(planloader substrait_io)
+
+install(
+  TARGETS planloader
+  LIBRARY DESTINATION ${CMAKE_INSTALL_LIBDIR}
+  PRIVATE_HEADER DESTINATION ${CMAKE_INSTALL_INCDIR})
+
+if(${SUBSTRAIT_CPP_BUILD_TESTING})
+  add_subdirectory(tests)
+endif()

export/planloader/planloader.cpp

@@ -0,0 +1,61 @@
+/* SPDX-License-Identifier: Apache-2.0 */
+
+#include "planloader.h"
+
+#include <limits>
+#include <substrait/common/Io.h>
+
+extern "C" {
+
+// Load a Substrait plan (in any format) from disk.
+// Stores the Substrait plan in planBuffer in serialized form.
+// Returns a SerializedPlan structure containing either the serialized plan or
+// an error message.  errorMessage is nullptr upon success.
+SerializedPlan* load_substrait_plan(const char* filename) {
+  auto newPlan = new SerializedPlan();
+  newPlan->buffer = nullptr;
+  newPlan->size = 0;
+  newPlan->errorMessage = nullptr;
+
+  auto planOrError = io::substrait::loadPlan(filename);
+  if (!planOrError.ok()) {
+    auto errMsg = planOrError.status().message();
+    newPlan->errorMessage = new char[errMsg.length()+1];
+    strncpy(newPlan->errorMessage, errMsg.data(), errMsg.length()+1);
+    return newPlan;
+  }
+  ::substrait::proto::Plan plan = *planOrError;
+  std::string text = plan.SerializeAsString();
+  newPlan->buffer = new char[text.length()+1];
+  memcpy(newPlan->buffer, text.data(), text.length()+1);
+  newPlan->size = static_cast<int32_t>(
+            text.length() &
+            std::numeric_limits<int32_t>::max());
+  return newPlan;
+}
+
+void free_substrait_plan(SerializedPlan* plan) {
+  delete[] plan->buffer;
+  delete[] plan->errorMessage;
+  delete plan;
+}
+
+// Write a serialized Substrait plan to disk in the specified format.
+// On error returns a non-empty error message.
+// On success a nullptr is returned.
+const char* save_substrait_plan(
+    const char* planData,
+    uint32_t planDataLength,
+    const char* filename,
+    io::substrait::PlanFileFormat format) {
+  ::substrait::proto::Plan plan;
+  std::string data(planData, planDataLength);
+  plan.ParseFromString(data);
+  auto result = io::substrait::savePlan(plan, filename, format);
+  if (!result.ok()) {
+    return result.message().data();
+  }
+  return nullptr;
+}
+
+}  // extern "C"

export/planloader/planloader.h

@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: Apache-2.0 */
+
+#include <substrait/common/Io.h>
+
+extern "C" {
+
+using SerializedPlan = struct {
+  // If set, contains a serialized ::substrait::proto::Plan object.
+  char *buffer;
+  // If buffer is set, this is the size of the buffer.
+  int32_t size;
+  // If null the buffer is valid, otherwise this points to an error message.
+  char *errorMessage;
+};
+
+// Since this is actually C code, stick to C style names for exporting.
+// NOLINTBEGIN(readability-identifier-naming)
+
+// Load a Substrait plan (in any format) from disk.
+// Stores the Substrait plan in planBuffer in serialized form.
+// Returns a SerializedPlan structure containing either the serialized plan or
+// an error message.
+SerializedPlan* load_substrait_plan(const char* filename);
+
+void free_substrait_plan(SerializedPlan* plan);
+
+// Write a serialized Substrait plan to disk in the specified format.
+// On error returns a non-empty error message.
+// On success an empty string is returned.
+const char* save_substrait_plan(
+    const char* planData,
+    uint32_t planDataLength,
+    const char* filename,
+    io::substrait::PlanFileFormat format);
+
+// NOLINTEND(readability-identifier-naming)
+
+}  // extern "C"

export/planloader/tests/CMakeLists.txt

@@ -0,0 +1,35 @@
+# SPDX-License-Identifier: Apache-2.0
+
+cmake_path(GET CMAKE_CURRENT_BINARY_DIR PARENT_PATH
+           CMAKE_CURRENT_BINARY_PARENT_DIR)
+cmake_path(GET CMAKE_CURRENT_BINARY_PARENT_DIR PARENT_PATH
+           CMAKE_CURRENT_BINARY_TOPLEVEL_DIR)
+
+set(CMAKE_RUNTIME_OUTPUT_DIRECTORY
+    "${CMAKE_CURRENT_BINARY_TOPLEVEL_DIR}/${BUILD_SUBDIR_NAME}")
+
+add_test_case(
+  planloader_test
+  SOURCES
+  PlanLoaderTest.cpp
+  EXTRA_LINK_LIBS
+  planloader
+  gtest
+  gtest_main)
+
+set(TEXTPLAN_SOURCE_DIR "${CMAKE_SOURCE_DIR}/src/substrait/textplan")
+
+add_custom_command(
+  TARGET planloader_test
+  POST_BUILD
+  COMMAND ${CMAKE_COMMAND} -E echo "Copying unit test data.."
+  COMMAND ${CMAKE_COMMAND} -E make_directory
+          "${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/tests/data"
+  COMMAND
+    ${CMAKE_COMMAND} -E copy
+    "${TEXTPLAN_SOURCE_DIR}/converter/data/q6_first_stage.json"
+    "${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/tests/data/q6_first_stage.json")
+
+message(
+  STATUS "test data will be here:  ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/tests/data"
+)

export/planloader/tests/PlanLoaderTest.cpp

@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: Apache-2.0 */
+
+#include <gtest/gtest.h>
+#include <functional>
+
+#include "../planloader.h"
+#include "substrait/proto/plan.pb.h"
+
+namespace io::substrait::textplan {
+namespace {
+
+TEST(PlanLoaderTest, LoadAndSave) {
+  auto serializedPlan = load_substrait_plan("data/q6_first_stage.json");
+  ASSERT_EQ(serializedPlan->errorMessage, nullptr);
+
+  ::substrait::proto::Plan plan;
+  bool parseStatus =
+      plan.ParseFromArray(serializedPlan->buffer, serializedPlan->size);
+  ASSERT_TRUE(parseStatus) << "Failed to parse the plan.";
+
+  const char* saveStatus = save_substrait_plan(
+      serializedPlan->buffer,
+      serializedPlan->size,
+      "outfile.splan",
+      PlanFileFormat::kText);
+  ASSERT_EQ(saveStatus, nullptr);
+
+  free_substrait_plan(serializedPlan);
+}
+
+} // namespace
+} // namespace io::substrait::textplan

src/substrait/common/Io.cpp

@@ -55,6 +55,8 @@ absl::StatusOr<::substrait::proto::Plan> loadPlan(
     case PlanFileFormat::kText:
       return textplan::loadFromText(*contentOrError);
   }
+  // There are no other possibilities so this can't happen.
+  return absl::UnimplementedError("Unexpected format encountered.");
 }
 
 absl::Status savePlan(

third_party/antlr4/cmake/ExternalAntlr4Cpp.cmake

@@ -97,6 +97,7 @@ if(ANTLR4_ZIP_REPOSITORY)
           -DCMAKE_BUILD_TYPE:STRING=${CMAKE_BUILD_TYPE}
           -DWITH_STATIC_CRT:BOOL=${ANTLR4_WITH_STATIC_CRT}
           -DDISABLE_WARNINGS:BOOL=ON
+	  -DCMAKE_POSITION_INDEPENDENT_CODE:BOOL=ON
           # -DCMAKE_CXX_STANDARD:STRING=17 # if desired, compile the runtime with a different C++ standard
           # -DCMAKE_CXX_STANDARD:STRING=${CMAKE_CXX_STANDARD} # alternatively, compile the runtime with the same C++ standard as the outer project
       INSTALL_COMMAND ""
@@ -116,6 +117,7 @@ else()
           -DCMAKE_BUILD_TYPE:STRING=${CMAKE_BUILD_TYPE}
           -DWITH_STATIC_CRT:BOOL=${ANTLR4_WITH_STATIC_CRT}
           -DDISABLE_WARNINGS:BOOL=ON
+	  -DCMAKE_POSITION_INDEPENDENT_CODE:BOOL=ON
           # -DCMAKE_CXX_STANDARD:STRING=17 # if desired, compile the runtime with a different C++ standard
           # -DCMAKE_CXX_STANDARD:STRING=${CMAKE_CXX_STANDARD} # alternatively, compile the runtime with the same C++ standard as the outer project
       INSTALL_COMMAND ""