Rc/2.2.0 bak

.github/workflows/unit-test-cpp.yml

@@ -104,12 +104,15 @@ jobs:
               core.setOutput('platform_suffix', ``)
             }
 
-      - name: Install clang-format
+      # Install dependencies
+      - name: Install dependencies
         shell: bash
         run: |
           if [[ "$RUNNER_OS" == "Linux" ]]; then
             sudo update-alternatives --install /usr/bin/clang-format clang-format /usr/bin/clang-format-17 100
             sudo update-alternatives --set clang-format /usr/bin/clang-format-17
+            sudo apt-get update
+            sudo apt-get install -y uuid-dev
           elif [[ "$RUNNER_OS" == "Windows" ]]; then
             choco install llvm --version 17.0.6 --force
           else

.github/workflows/unit-test-python.yml

@@ -75,6 +75,23 @@ jobs:
               core.setOutput('platform_suffix', ``)
             }
 
+      # Install dependencies
+      - name: Install dependencies
+        shell: bash
+        run: |
+          if [[ "$RUNNER_OS" == "Linux" ]]; then
+            sudo update-alternatives --install /usr/bin/clang-format clang-format /usr/bin/clang-format-17 100
+            sudo update-alternatives --set clang-format /usr/bin/clang-format-17
+            sudo apt-get update
+            sudo apt-get install -y uuid-dev
+          elif [[ "$RUNNER_OS" == "Windows" ]]; then
+            choco install llvm --version 17.0.6 --force
+          else
+            brew install llvm@17
+            ln -sf $(brew --prefix llvm@17)/bin/clang-format /opt/homebrew/bin/clang-format
+          fi
+
+
       # Run the actual maven build including all tests.
       - name: Build and test with Maven
         shell: bash

cpp/.clang-format

@@ -65,7 +65,6 @@ ConstructorInitializerIndentWidth: 4
 ContinuationIndentWidth: 4
 Cpp11BracedListStyle: true
 DeriveLineEnding: true
-DerivePointerAlignment: true
 DisableFormat:   false
 EmptyLineAfterAccessModifier: Never
 EmptyLineBeforeAccessModifier: LogicalBlock
@@ -207,7 +206,7 @@ SpacesInParentheses: false
 SpacesInSquareBrackets: false
 SpaceBeforeSquareBrackets: false
 BitFieldColonSpacing: Both
-Standard:        Auto
+Standard:        Cpp11
 StatementAttributeLikeMacros:
   - Q_EMIT
 StatementMacros:

cpp/CMakeLists.txt

@@ -19,9 +19,17 @@ under the License.
 cmake_minimum_required(VERSION 3.11)
 project(TsFile_CPP)
 
+if (DEFINED ToolChain)
+    include(${CMAKE_SOURCE_DIR}/cmake/ToolChain.cmake)
+    message(STATUS "Using ToolChain: ${CMAKE_TOOLCHAIN_FILE}")
+else()
+    message(STATUS "Not using ToolChain")
+endif ()
+
 cmake_policy(SET CMP0079 NEW)
 set(TsFile_CPP_VERSION 2.2.0.dev)
 set(CMAKE_CXX_FLAGS "$ENV{CXXFLAGS} -Wall")
+
 if (CMAKE_CXX_COMPILER_ID MATCHES "GNU")
     set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wunused -Wuninitialized -D__STDC_FORMAT_MACROS")
 endif ()
@@ -55,6 +63,18 @@ if (NOT CMAKE_BUILD_TYPE)
     set(CMAKE_BUILD_TYPE "Release" CACHE STRING "Choose the type of build." FORCE)
 endif ()
 
+if (NOT DEFINED CMAKE_BUILD_PARALLEL_LEVEL)
+    include(ProcessorCount)
+    ProcessorCount(N)
+    if (N EQUAL 0)
+        set(N 1)
+    endif ()
+    set(CMAKE_BUILD_PARALLEL_LEVEL ${N} CACHE STRING "Number of parallel build jobs")
+    message("CMAKE BUILD PARALLEL LEVEL: ${CMAKE_BUILD_PARALLEL_LEVEL} (auto-detected)")
+else ()
+    message("CMAKE BUILD PARALLEL LEVEL: ${CMAKE_BUILD_PARALLEL_LEVEL} (from environment)")
+endif ()
+
 message("CMAKE BUILD TYPE " ${CMAKE_BUILD_TYPE})
 if (CMAKE_BUILD_TYPE STREQUAL "Debug")
     set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -O0 -g")
@@ -88,6 +108,40 @@ if (NOT WIN32)
     endif ()
 endif ()
 
+option(BUILD_TEST "Build tests" ON)
+message("cmake using: BUILD_TEST=${BUILD_TEST}")
+
+option(ENABLE_ANTLR4 "Enable ANTLR4 runtime" ON)
+message("cmake using: ENABLE_ANTLR4=${ENABLE_ANTLR4}")
+
+option(ENABLE_SNAPPY "Enable Google Snappy compression" ON)
+message("cmake using: ENABLE_SNAPPY=${ENABLE_SNAPPY}")
+
+if (ENABLE_SNAPPY)
+    add_definitions(-DENABLE_SNAPPY)
+endif()
+
+option(ENABLE_LZ4 "Enable LZ4 compression" ON)
+message("cmake using: ENABLE_LZ4=${ENABLE_LZ4}")
+
+if (ENABLE_LZ4)
+    add_definitions(-DENABLE_LZ4)
+endif()
+
+option(ENABLE_LZOKAY "Enable LZOKAY compression" ON)
+message("cmake using: ENABLE_LZOKAY=${ENABLE_LZOKAY}")
+
+if (ENABLE_LZOKAY)
+    add_definitions(-DENABLE_LZOKAY)
+endif()
+
+option(ENABLE_ZLIB "Enable Zlib compression" ON)
+message("cmake using: ENABLE_ZLIB=${ENABLE_ZLIB}")
+
+if (ENABLE_ZLIB)
+    add_definitions(-DENABLE_ZLIB)
+    add_definitions(-DENABLE_GZIP)
+endif()
 
 # All libs will be stored here, including libtsfile, compress-encoding lib.
 set(LIBRARY_OUTPUT_PATH ${PROJECT_BINARY_DIR}/lib)
@@ -106,9 +160,14 @@ add_subdirectory(third_party)
 set(CMAKE_CXX_FLAGS "${SAVED_CXX_FLAGS}")
 
 add_subdirectory(src)
-add_subdirectory(test)
-add_subdirectory(examples)
-if (TESTS_ENABLED)
-    add_dependencies(TsFile_Test tsfile)
+if (BUILD_TEST)
+    add_subdirectory(test)
+    if (TESTS_ENABLED)
+        add_dependencies(TsFile_Test tsfile)
+    endif ()
+else()
+    message("BUILD_TEST is OFF, skipping test directory")
 endif ()
 
+add_subdirectory(examples)
+

cpp/README.md

@@ -42,23 +42,6 @@ The source code can be found in the `./src` directory. C/C++ examples are locate
 
 We use `clang-format` to ensure that our C++ code adheres to a consistent set of rules defined in `./clang-format`. This is similar to the Google style.
 
-**Feature List**:
-
-- [ ] Add unit tests for the reader, writer, compression, etc.
-- [ ] Add unit tests for the C wrapper.
-- [ ] Support multiple data flushes.
-- [ ] Support aligned timeseries.
-- [ ] Support table description in tsfile.
-- [ ] Retrieve all table schemas/names.
-- [ ] Implement automatic flush.
-- [ ] Support out-of-order data writing.
-- [ ] Support TsFile V4. Note: TsFile CPP does not implement support for the table model, therefore there are differences in file output compared to the Java version.
-
-**Bug List**:
-
-- [ ] Flushing without writing after registering a timeseries will cause a core dump.
-- [ ] Misalignment in memory may lead to a bus error.
-
 We welcome any bug reports. You can open an issue with a title starting with [CPP] to describe the bug, like: https://github.com/apache/tsfile/issues/94
 
 ## Build
@@ -67,7 +50,7 @@ We welcome any bug reports. You can open an issue with a title starting with [CP
 
 ```bash
 sudo apt-get update
-sudo apt-get install -y cmake make g++ clang-format
+sudo apt-get install -y cmake make g++ clang-format libuuid-dev
 ```
 
 To build tsfile, you can run: `bash build.sh`. If you have Maven tools, you can run: `mvn package -P with-cpp clean verify`. Then, you can find the shared object at `./build`.
@@ -81,6 +64,21 @@ If you compile using MinGW on windows and encounter an error, you can try replac
 * GCC 12.2.0 + LLVM/Clang/LLD/LLDB 16.0.0 + MinGW-w64 10.0.0 (MSVCRT) - release 5
 * GCC 11.2.0 + MinGW-w64 10.0.0 (MSVCRT) - release 1
 
+### configure the cross-compilation toolchain
+
+Modify the Toolchain File `cmake/ToolChain.cmake`, define the following variables:
+
+- `CMAKE_C_COMPILER`: Specify the path to the C compiler.
+- `CMAKE_CXX_COMPILER`: Specify the path to the C++ compiler.
+- `CMAKE_FIND_ROOT_PATH`: Set the root path for the cross-compilation environment (e.g., the directory of the cross-compilation toolchain).
+
+In the `cpp/` directory, run the following commands to create the build directory and start the compilation:
+```
+mkdir build && cd build
+cmake .. -DToolChian=ON
+make
+```
+
 ## Use TsFile
 
 You can find examples on how to read and write data in `demo_read.cpp` and `demo_write.cpp` located under `./examples/cpp_examples`. There are also examples under `./examples/c_examples`on how to use a C-style API to read and write data in a C environment. You can run `bash build.sh` under `./examples` to generate an executable output under `./examples/build`.

cpp/build.sh

@@ -25,22 +25,38 @@ use_cpp11=1
 enable_cov=0
 debug_se=0
 run_cov_only=0
+enable_antlr4=ON
+
+enable_snappy=ON
+enable_lz4=ON
+enable_lzokay=ON
+enable_zlib=ON
 
 shell_dir=$(cd "$(dirname "$0")";pwd)
 
+# 添加get_key_value函数
+get_key_value() {
+    echo "${1#*=}"
+}
+
 function print_config()
 {
   echo "build_type=$build_type"
   echo "build_test=$build_test"
   echo "use_cpp11=$use_cpp11"
   echo "enable_cov=$enable_cov"
   echo "enable_asan=$enable_asan"
+  echo "enable_antlr4=$enable_antlr4"
+  echo "enable_snappy=$enable_snappy"
+  echo "enable_lz4=$enable_lz4"
+  echo "enable_lzokay=$enable_lzokay"
+  echo "enable_zlib=$enable_zlib"
 }
 
 function run_test_for_cov()
 {
   # sh ${shell_dir}/scripts/regression_unittest.sh
-  sh ${shell_dir}/test/libtsfile_test/run_sdk_tests.sh 
+  sh ${shell_dir}/test/libtsfile_test/run_sdk_tests.sh
 }
 
 parse_options()
@@ -53,20 +69,40 @@ parse_options()
     run_cov)
       run_cov_only=1;;
     -t=*)
-      build_type=`get_key_value "$1"`;;
+      build_type=$(get_key_value "$1");;
     -t)
       shift
-      build_type=`get_key_value "$1"`;;
+      build_type=$(get_key_value "$1");;
     -a=*)
-      enable_asan=`get_key_value "$1"`;;
+      enable_asan=$(get_key_value "$1");;
     -a)
       shift
-      enable_asan=`get_key_value "$1"`;;
+      enable_asan=$(get_key_value "$1");;
     -c=*)
-      enable_cov=`get_key_value "$1"`;;
+      enable_cov=$(get_key_value "$1");;
     -c)
       shift
-      enable_cov=`get_key_value "$1"`;;
+      enable_cov=$(get_key_value "$1");;
+    --enable-antlr4=*)
+      enable_antlr4=$(get_key_value "$1");;
+    --enable-snappy=*)
+      enable_snappy=$(get_key_value "$1");;
+    --enable-lz4=*)
+      enable_lz4=$(get_key_value "$1");;
+    --enable-lzokay=*)
+      enable_lzokay=$(get_key_value "$1");;
+    --enable-zlib=*)
+      enable_zlib=$(get_key_value "$1");;
+    --disable-antlr4)
+      enable_antlr4=OFF;;
+    --disable-snappy)
+      enable_snappy=OFF;;
+    --disable-lz4)
+      enable_lz4=OFF;;
+    --disable-lzokay)
+      enable_lzokay=OFF;;
+    --disable-zlib)
+      enable_zlib=OFF;;
     #-h | --help)
     #  usage
     #  exit 0;;
@@ -127,14 +163,12 @@ cmake ../../                           \
   -DUSE_CPP11=$use_cpp11               \
   -DENABLE_COV=$enable_cov             \
   -DDEBUG_SE=$debug_se                 \
-  -DBUILD_TSFILE_ONLY=$build_tsfile_only
+  -DENABLE_ANTLR4=$enable_antlr4       \
+  -DBUILD_TSFILE_ONLY=$build_tsfile_only \
+  -DENABLE_SNAPPY=$enable_snappy       \
+  -DENABLE_LZ4=$enable_lz4             \
+  -DENABLE_LZOKAY=$enable_lzokay       \
+  -DENABLE_ZLIB=$enable_zlib
 
 VERBOSE=1 make
-VERBOSE=1 make install
-
-
-
-
-
-
-
+VERBOSE=1 make install

cpp/examples/c_examples/demo_write.c

@@ -27,6 +27,14 @@
 // This example shows you how to write tsfile.
 ERRNO write_tsfile() {
     ERRNO code = 0;
+    code = set_global_compression(TS_COMPRESSION_LZ4);
+    if (code != RET_OK) {
+        return code;
+    }
+    code = set_datatype_encoding(TS_DATATYPE_INT32, TS_ENCODING_TS_2DIFF);
+    if (code != RET_OK) {
+        return code;
+    }
     char* table_name = "table1";
 
     // Create table schema to describe a table in a tsfile.
@@ -67,8 +75,10 @@ ERRNO write_tsfile() {
     for (int row = 0; row < 5; row++) {
         Timestamp timestamp = row;
         tablet_add_timestamp(tablet, row, timestamp);
-        tablet_add_value_by_name_string(tablet, row, "id1", "id_field_1");
-        tablet_add_value_by_name_string(tablet, row, "id2", "id_field_2");
+        tablet_add_value_by_name_string_with_len(
+            tablet, row, "id1", "id_field_1", strlen("id_field_1"));
+        tablet_add_value_by_name_string_with_len(
+            tablet, row, "id2", "id_field_2", strlen("id_field_2"));
         tablet_add_value_by_name_int32_t(tablet, row, "s1", row);
     }
 

cpp/examples/cpp_examples/cpp_examples.h

@@ -26,6 +26,7 @@
 #include "file/write_file.h"
 #include "reader/expression.h"
 #include "reader/filter/filter.h"
+#include "reader/filter/tag_filter.h"
 #include "reader/qds_with_timegenerator.h"
 #include "reader/qds_without_timegenerator.h"
 #include "reader/tsfile_reader.h"

cpp/examples/cpp_examples/demo_read.cpp

@@ -40,8 +40,16 @@ int demo_read() {
     columns.emplace_back("id2");
     columns.emplace_back("s1");
 
+    auto table_schema = reader.get_table_schema(table_name);
+    storage::Filter* tag_filter1 =
+        storage::TagFilterBuilder(table_schema.get()).eq("id1", "id1_filed_1");
+    storage::Filter* tag_filter2 =
+        storage::TagFilterBuilder(table_schema.get()).eq("id2", "id1_filed_2");
+    storage::Filter* tag_filter = storage::TagFilterBuilder(table_schema.get())
+                                      .and_filter(tag_filter1, tag_filter2);
     // Column vector contains the columns you want to select.
-    HANDLE_ERROR(reader.query(table_name, columns, 0, 100, temp_ret));
+    HANDLE_ERROR(
+        reader.query(table_name, columns, 0, 100, temp_ret, tag_filter));
 
     // Get query handler.
     auto ret = dynamic_cast<storage::TableResultSet*>(temp_ret);
@@ -61,6 +69,7 @@ int demo_read() {
     while ((code = ret->next(has_next)) == common::E_OK && has_next) {
         // Timestamp at column 1 and column index begin from 1.
         Timestamp timestamp = ret->get_value<Timestamp>(1);
+        std::cout << timestamp << std::endl;
         for (int i = 1; i <= column_num; i++) {
             if (ret->is_null(i)) {
                 std::cout << "null" << std::endl;
@@ -97,5 +106,6 @@ int demo_read() {
 
     // Close reader.
     reader.close();
+    delete tag_filter;
     return 0;
 }