Merge pull request #879 from BYVoid/bazel

Merge Bazel build.

.github/workflows/bazel.yml

@@ -2,9 +2,9 @@ name: C++ CI with Bazel
 
 on:
  push:
- branches: [ master ]
+ branches: [master, bazel]
  pull_request:
- branches: [ master ]
+ branches: [master]
 
 jobs:
  build:
@@ -13,4 +13,4 @@ jobs:
  - uses: actions/checkout@v4
  - uses: bazelbuild/setup-bazelisk@v3
  - run: bazel build //:opencc
- - run: bazel test //src/...
+ - run: bazel test --test_output=all //src/... //data/... //test/...

BUILD.bazel

@@ -1,5 +1,18 @@
+package(default_visibility = ["//visibility:public"])
+
 cc_library(
  name = "opencc",
+ hdrs = [
+ "//src:Export.hpp",
+ "//src:SimpleConverter.hpp",
+ "//src:opencc.h",
+ ],
+ data = [
+ "//data/config",
+ "//data/dictionary:binary_dictionaries",
+ "//data/dictionary:text_dictionaries",
+ ],
+ strip_include_prefix = "src",
  deps = [
  "//src:opencc",
  ],

MODULE.bazel

@@ -9,3 +9,7 @@ module(
 bazel_dep(name = "darts-clone", version = "0.32")
 bazel_dep(name = "googletest", version = "1.14.0.bcr.1")
 bazel_dep(name = "marisa-trie", version = "0.2.6")
+bazel_dep(name = "rapidjson", version = "1.1.0")
+bazel_dep(name = "rules_cc", version = "0.0.9")
+bazel_dep(name = "rules_python", version = "0.34.0")
+bazel_dep(name = "tclap", version = "1.2.5")

data/config/BUILD.bazel

@@ -0,0 +1,6 @@
+package(default_visibility = ["//visibility:public"])
+
+filegroup(
+ name = "config",
+ srcs = glob(["*.json"]),
+)

data/dictionary/BUILD.bazel

@@ -0,0 +1,79 @@
+package(default_visibility = ["//visibility:public"])
+
+genrule(
+ name = "merge_TWPhrases",
+ srcs = [
+ "TWPhrasesIT.txt",
+ "TWPhrasesName.txt",
+ "TWPhrasesOther.txt",
+ ],
+ outs = ["TWPhrases.txt"],
+ cmd = "$(location //data/scripts:merge) " +
+ "$(SRCS) $(OUTS)",
+ tools = ["//data/scripts:merge"],
+)
+
+[
+ genrule(
+ name = "reverse_" + txt,
+ srcs = [txt + ".txt"],
+ outs = [txt + "Rev.txt"],
+ cmd = "$(location //data/scripts:reverse) " +
+ "$(SRCS) $(OUTS)",
+ tools = ["//data/scripts:reverse"],
+ )
+ for txt in [
+ "TWVariants",
+ "TWPhrases",
+ "HKVariants",
+ "JPVariants",
+ ]
+]
+
+TEXT_DICTS = glob(["*.txt"]) + [
+ "TWPhrases.txt",
+ "TWVariantsRev.txt",
+ "TWPhrasesRev.txt",
+ "HKVariantsRev.txt",
+ "JPVariantsRev.txt",
+]
+
+[
+ genrule(
+ name = "generate_bin_" + txt[:-4],
+ srcs = [txt],
+ outs = [txt.replace(".txt", ".ocd2")],
+ cmd = "$(location //src/tools:dict_converter) " +
+ "--input $(location " + txt + ") " +
+ "--output $(OUTS) " +
+ "--from text " +
+ "--to ocd2",
+ tools = ["//src/tools:dict_converter"],
+ )
+ for txt in TEXT_DICTS
+]
+
+filegroup(
+ name = "text_dictionaries",
+ srcs = TEXT_DICTS,
+)
+
+filegroup(
+ name = "binary_dictionaries",
+ srcs = [txt.replace(".txt", ".ocd2") for txt in TEXT_DICTS],
+)
+
+cc_test(
+ name = "dictionary_test",
+ srcs = ["DictionaryTest.cpp"],
+ data = [
+ ":binary_dictionaries",
+ ":text_dictionaries",
+ ],
+ deps = [
+ "//src:lexicon",
+ "//src:marisa_dict",
+ "//src:utf8_util",
+ "@googletest//:gtest_main",
+ ],
+)

data/dictionary/DictionaryTest.cpp

@@ -0,0 +1,90 @@
+/*
+ * Open Chinese Convert
+ *
+ * Copyright 2024-2024 Carbo Kuo <byvoid@byvoid.com>
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+#include "gtest/gtest.h"
+
+#include "src/Lexicon.hpp"
+#include "src/MarisaDict.hpp"
+#include "src/UTF8Util.hpp"
+
+namespace opencc {
+
+const char* RUNFILE_SUFFIX = ".runfiles/_main";
+
+class DictionaryTest : public ::testing::Test,
+ public ::testing::WithParamInterface<std::string> {
+protected:
+ static void SetUpTestSuite() {
+
+ std::string program_filename = ::testing::internal::GetArgvs().front();
+ size_t suffix_pos = program_filename.find(RUNFILE_SUFFIX);
+ ASSERT_NE(suffix_pos, std::string::npos);
+
+ runfile_dir_ =
+ program_filename.substr(0, suffix_pos + strlen(RUNFILE_SUFFIX));
+ }
+
+ static std::string runfile_dir_;
+};
+
+std::string DictionaryTest::runfile_dir_;
+
+INSTANTIATE_TEST_SUITE_P(
+ , DictionaryTest,
+ ::testing::Values("HKVariants", "HKVariantsRevPhrases",
+ "JPShinjitaiCharacters", "JPShinjitaiPhrases",
+ "JPVariants", "STCharacters", "STPhrases", "TSCharacters",
+ "TSPhrases", "TWPhrasesIT", "TWPhrasesName",
+ "TWPhrasesOther", "TWVariants", "TWVariantsRevPhrases",
+ "TWPhrases", "TWVariantsRev", "TWPhrasesRev",
+ "HKVariantsRev", "JPVariantsRev"),
+ [](const testing::TestParamInfo<DictionaryTest::ParamType>& info) {
+ return info.param;
+ });
+
+TEST_P(DictionaryTest, UniqueSortedTest) {
+ const std::string dictionaryFileName =
+ runfile_dir_ + "/data/dictionary/" + GetParam() + ".txt";
+ FILE* fp =
+ fopen(UTF8Util::GetPlatformString(dictionaryFileName).c_str(), "rb");
+ ASSERT_NE(fp, nullptr);
+ LexiconPtr lexicon = Lexicon::ParseLexiconFromFile(fp);
+ EXPECT_TRUE(lexicon->IsUnique()) << GetParam() << " has duplicated keys.";
+ EXPECT_TRUE(lexicon->IsSorted()) << GetParam() << " is not sorted.";
+}
+
+TEST_P(DictionaryTest, BinaryTest) {
+ const std::string binaryDictionaryFileName =
+ runfile_dir_ + "/data/dictionary/" + GetParam() + ".ocd2";
+ FILE* fp_bin = fopen(
+ UTF8Util::GetPlatformString(binaryDictionaryFileName).c_str(), "rb");
+ ASSERT_NE(fp_bin, nullptr);
+ MarisaDictPtr dict = MarisaDict::NewFromFile(fp_bin);
+ ASSERT_NE(dict, nullptr);
+
+ const std::string textDictionaryFileName =
+ runfile_dir_ + "/data/dictionary/" + GetParam() + ".txt";
+ FILE* fp_txt =
+ fopen(UTF8Util::GetPlatformString(textDictionaryFileName).c_str(), "rb");
+ ASSERT_NE(fp_txt, nullptr);
+ LexiconPtr txt_lexicon = Lexicon::ParseLexiconFromFile(fp_txt);
+
+ EXPECT_EQ(dict->GetLexicon()->Length(), txt_lexicon->Length());
+}
+
+} // namespace opencc