github-actions[bot] commented on code in PR #43115: URL: https://github.com/apache/doris/pull/43115#discussion_r1827278101
########## be/test/olap/rowset/segment_v2/inverted_index/index_compaction_with_deleted_term.cpp: ########## @@ -0,0 +1,689 @@ +// Licensed to the Apache Software Foundation (ASF) under one +// or more contributor license agreements. See the NOTICE file +// distributed with this work for additional information +// regarding copyright ownership. The ASF licenses this file +// to you 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 <iostream> +#include <memory> + +#include "CLucene/StdHeader.h" +#include "CLucene/config/repl_wchar.h" +#include "common/status.h" +#include "json2pb/json_to_pb.h" +#include "json2pb/pb_to_json.h" +#include "olap/base_compaction.h" +#include "olap/rowset/beta_rowset.h" +#include "olap/rowset/beta_rowset_writer.h" +#include "olap/rowset/rowset_factory.h" +#include "olap/rowset/segment_v2/inverted_index/query/phrase_query.h" +#include "olap/rowset/segment_v2/inverted_index/query/query_factory.h" +#include "olap/rowset/segment_v2/inverted_index_compaction.h" +#include "olap/rowset/segment_v2/inverted_index_file_reader.h" +#include "olap/rowset/segment_v2/inverted_index_fs_directory.h" +#include "olap/storage_engine.h" + +namespace doris { + +using namespace doris::vectorized; + +constexpr static uint32_t MAX_PATH_LEN = 1024; +constexpr static std::string_view dest_dir = "/ut_dir/inverted_index_test"; +constexpr static std::string_view tmp_dir = "./ut_dir/tmp"; +static int64_t inc_id = 1000; + +struct DataRow { + int key; + std::string word; + std::string url; + int num; +}; + +static std::vector<DataRow> read_data(const std::string file_name) { + std::ifstream file(file_name); + EXPECT_TRUE(file.is_open()); + + std::string line; + std::vector<DataRow> data; + + while (std::getline(file, line)) { + std::stringstream ss(line); + std::string item; + DataRow row; + EXPECT_TRUE(std::getline(ss, item, ',')); + row.key = std::stoi(item); + EXPECT_TRUE(std::getline(ss, item, ',')); + row.word = item; + EXPECT_TRUE(std::getline(ss, item, ',')); + row.url = item; + EXPECT_TRUE(std::getline(ss, item, ',')); + row.num = std::stoi(item); + data.emplace_back(std::move(row)); + } + + file.close(); + return data; +} + +static void check_terms_stats(lucene::store::Directory* dir) { + IndexReader* r = IndexReader::open(dir); + + printf("Max Docs: %d\n", r->maxDoc()); + printf("Num Docs: %d\n", r->numDocs()); + + int64_t ver = r->getCurrentVersion(dir); + printf("Current Version: %f\n", (float_t)ver); + + TermEnum* te = r->terms(); + int32_t nterms; + for (nterms = 0; te->next(); nterms++) { + /* empty */ + std::string token = + lucene_wcstoutf8string(te->term(false)->text(), te->term(false)->textLength()); + std::string field = lucene_wcstoutf8string(te->term(false)->field(), + lenOfString(te->term(false)->field())); + + printf("Field: %s ", field.c_str()); + printf("Term: %s ", token.c_str()); + printf("Freq: %d\n", te->docFreq()); + if (false) { + TermDocs* td = r->termDocs(te->term()); + while (td->next()) { + printf("DocID: %d ", td->doc()); + printf("TermFreq: %d\n", td->freq()); + } + _CLLDELETE(td); + } + } + printf("Term count: %d\n\n", nterms); + te->close(); + _CLLDELETE(te); + + r->close(); + _CLLDELETE(r); +} +static Status check_idx_file_correctness(lucene::store::Directory* index_reader, Review Comment: warning: function 'check_idx_file_correctness' exceeds recommended size/complexity thresholds [readability-function-size] ```cpp static Status check_idx_file_correctness(lucene::store::Directory* index_reader, ^ ``` <details> <summary>Additional context</summary> **be/test/olap/rowset/segment_v2/inverted_index/index_compaction_with_deleted_term.cpp:117:** 97 lines including whitespace and comments (threshold 80) ```cpp static Status check_idx_file_correctness(lucene::store::Directory* index_reader, ^ ``` </details> ########## be/test/olap/rowset/segment_v2/inverted_index/index_compaction_with_deleted_term.cpp: ########## @@ -0,0 +1,689 @@ +// Licensed to the Apache Software Foundation (ASF) under one +// or more contributor license agreements. See the NOTICE file +// distributed with this work for additional information +// regarding copyright ownership. The ASF licenses this file +// to you 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 <iostream> +#include <memory> + +#include "CLucene/StdHeader.h" +#include "CLucene/config/repl_wchar.h" +#include "common/status.h" +#include "json2pb/json_to_pb.h" +#include "json2pb/pb_to_json.h" +#include "olap/base_compaction.h" +#include "olap/rowset/beta_rowset.h" +#include "olap/rowset/beta_rowset_writer.h" +#include "olap/rowset/rowset_factory.h" +#include "olap/rowset/segment_v2/inverted_index/query/phrase_query.h" +#include "olap/rowset/segment_v2/inverted_index/query/query_factory.h" +#include "olap/rowset/segment_v2/inverted_index_compaction.h" +#include "olap/rowset/segment_v2/inverted_index_file_reader.h" +#include "olap/rowset/segment_v2/inverted_index_fs_directory.h" +#include "olap/storage_engine.h" + +namespace doris { + +using namespace doris::vectorized; + +constexpr static uint32_t MAX_PATH_LEN = 1024; +constexpr static std::string_view dest_dir = "/ut_dir/inverted_index_test"; +constexpr static std::string_view tmp_dir = "./ut_dir/tmp"; +static int64_t inc_id = 1000; + +struct DataRow { + int key; + std::string word; + std::string url; + int num; +}; + +static std::vector<DataRow> read_data(const std::string file_name) { + std::ifstream file(file_name); + EXPECT_TRUE(file.is_open()); + + std::string line; + std::vector<DataRow> data; + + while (std::getline(file, line)) { + std::stringstream ss(line); + std::string item; + DataRow row; + EXPECT_TRUE(std::getline(ss, item, ',')); + row.key = std::stoi(item); + EXPECT_TRUE(std::getline(ss, item, ',')); + row.word = item; + EXPECT_TRUE(std::getline(ss, item, ',')); + row.url = item; + EXPECT_TRUE(std::getline(ss, item, ',')); + row.num = std::stoi(item); + data.emplace_back(std::move(row)); + } + + file.close(); + return data; +} + +static void check_terms_stats(lucene::store::Directory* dir) { + IndexReader* r = IndexReader::open(dir); + + printf("Max Docs: %d\n", r->maxDoc()); + printf("Num Docs: %d\n", r->numDocs()); + + int64_t ver = r->getCurrentVersion(dir); + printf("Current Version: %f\n", (float_t)ver); + + TermEnum* te = r->terms(); + int32_t nterms; + for (nterms = 0; te->next(); nterms++) { + /* empty */ + std::string token = + lucene_wcstoutf8string(te->term(false)->text(), te->term(false)->textLength()); + std::string field = lucene_wcstoutf8string(te->term(false)->field(), + lenOfString(te->term(false)->field())); + + printf("Field: %s ", field.c_str()); + printf("Term: %s ", token.c_str()); + printf("Freq: %d\n", te->docFreq()); + if (false) { + TermDocs* td = r->termDocs(te->term()); + while (td->next()) { + printf("DocID: %d ", td->doc()); + printf("TermFreq: %d\n", td->freq()); + } + _CLLDELETE(td); + } Review Comment: warning: redundant boolean literal in if statement condition [readability-simplify-boolean-expr] ```suggestion ``` ########## be/test/olap/rowset/segment_v2/inverted_index/index_compaction_with_deleted_term.cpp: ########## @@ -0,0 +1,689 @@ +// Licensed to the Apache Software Foundation (ASF) under one +// or more contributor license agreements. See the NOTICE file +// distributed with this work for additional information +// regarding copyright ownership. The ASF licenses this file +// to you 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 <iostream> +#include <memory> + +#include "CLucene/StdHeader.h" +#include "CLucene/config/repl_wchar.h" +#include "common/status.h" +#include "json2pb/json_to_pb.h" +#include "json2pb/pb_to_json.h" +#include "olap/base_compaction.h" +#include "olap/rowset/beta_rowset.h" +#include "olap/rowset/beta_rowset_writer.h" +#include "olap/rowset/rowset_factory.h" +#include "olap/rowset/segment_v2/inverted_index/query/phrase_query.h" +#include "olap/rowset/segment_v2/inverted_index/query/query_factory.h" +#include "olap/rowset/segment_v2/inverted_index_compaction.h" +#include "olap/rowset/segment_v2/inverted_index_file_reader.h" +#include "olap/rowset/segment_v2/inverted_index_fs_directory.h" +#include "olap/storage_engine.h" + +namespace doris { + +using namespace doris::vectorized; + +constexpr static uint32_t MAX_PATH_LEN = 1024; +constexpr static std::string_view dest_dir = "/ut_dir/inverted_index_test"; +constexpr static std::string_view tmp_dir = "./ut_dir/tmp"; +static int64_t inc_id = 1000; + +struct DataRow { + int key; + std::string word; + std::string url; + int num; +}; + +static std::vector<DataRow> read_data(const std::string file_name) { + std::ifstream file(file_name); + EXPECT_TRUE(file.is_open()); + + std::string line; + std::vector<DataRow> data; + + while (std::getline(file, line)) { + std::stringstream ss(line); + std::string item; + DataRow row; + EXPECT_TRUE(std::getline(ss, item, ',')); + row.key = std::stoi(item); + EXPECT_TRUE(std::getline(ss, item, ',')); + row.word = item; + EXPECT_TRUE(std::getline(ss, item, ',')); + row.url = item; + EXPECT_TRUE(std::getline(ss, item, ',')); + row.num = std::stoi(item); + data.emplace_back(std::move(row)); + } + + file.close(); + return data; +} + +static void check_terms_stats(lucene::store::Directory* dir) { + IndexReader* r = IndexReader::open(dir); + + printf("Max Docs: %d\n", r->maxDoc()); + printf("Num Docs: %d\n", r->numDocs()); + + int64_t ver = r->getCurrentVersion(dir); + printf("Current Version: %f\n", (float_t)ver); + + TermEnum* te = r->terms(); + int32_t nterms; + for (nterms = 0; te->next(); nterms++) { + /* empty */ + std::string token = + lucene_wcstoutf8string(te->term(false)->text(), te->term(false)->textLength()); + std::string field = lucene_wcstoutf8string(te->term(false)->field(), + lenOfString(te->term(false)->field())); + + printf("Field: %s ", field.c_str()); + printf("Term: %s ", token.c_str()); + printf("Freq: %d\n", te->docFreq()); + if (false) { + TermDocs* td = r->termDocs(te->term()); + while (td->next()) { + printf("DocID: %d ", td->doc()); + printf("TermFreq: %d\n", td->freq()); + } + _CLLDELETE(td); + } + } + printf("Term count: %d\n\n", nterms); + te->close(); + _CLLDELETE(te); + + r->close(); + _CLLDELETE(r); +} +static Status check_idx_file_correctness(lucene::store::Directory* index_reader, + lucene::store::Directory* tmp_index_reader) { + lucene::index::IndexReader* idx_reader = lucene::index::IndexReader::open(index_reader); + lucene::index::IndexReader* tmp_idx_reader = lucene::index::IndexReader::open(tmp_index_reader); + + // compare numDocs + if (idx_reader->numDocs() != tmp_idx_reader->numDocs()) { + return Status::InternalError( + "index compaction correctness check failed, numDocs not equal, idx_numDocs={}, " + "tmp_idx_numDocs={}", + idx_reader->numDocs(), tmp_idx_reader->numDocs()); + } + + lucene::index::TermEnum* term_enum = idx_reader->terms(); + lucene::index::TermEnum* tmp_term_enum = tmp_idx_reader->terms(); + lucene::index::TermDocs* term_docs = nullptr; + lucene::index::TermDocs* tmp_term_docs = nullptr; + + // iterate TermEnum + while (term_enum->next() && tmp_term_enum->next()) { + std::string token = lucene_wcstoutf8string(term_enum->term(false)->text(), + term_enum->term(false)->textLength()); + std::string field = lucene_wcstoutf8string(term_enum->term(false)->field(), + lenOfString(term_enum->term(false)->field())); + std::string tmp_token = lucene_wcstoutf8string(tmp_term_enum->term(false)->text(), + tmp_term_enum->term(false)->textLength()); + std::string tmp_field = + lucene_wcstoutf8string(tmp_term_enum->term(false)->field(), + lenOfString(tmp_term_enum->term(false)->field())); + // compare token and field + if (field != tmp_field) { + return Status::InternalError( + "index compaction correctness check failed, fields not equal, field={}, " + "tmp_field={}", + field, field); + } + if (token != tmp_token) { + return Status::InternalError( + "index compaction correctness check failed, tokens not equal, token={}, " + "tmp_token={}", + token, tmp_token); + } + + // get term's docId and freq + term_docs = idx_reader->termDocs(term_enum->term(false)); + tmp_term_docs = tmp_idx_reader->termDocs(tmp_term_enum->term(false)); + + // compare term's docId and freq + while (term_docs->next() && tmp_term_docs->next()) { + if (term_docs->doc() != tmp_term_docs->doc() || + term_docs->freq() != tmp_term_docs->freq()) { + return Status::InternalError( + "index compaction correctness check failed, docId or freq not equal, " + "docId={}, tmp_docId={}, freq={}, tmp_freq={}", + term_docs->doc(), tmp_term_docs->doc(), term_docs->freq(), + tmp_term_docs->freq()); + } + } + + // check if there are remaining docs + if (term_docs->next() || tmp_term_docs->next()) { + return Status::InternalError( + "index compaction correctness check failed, number of docs not equal for " + "term={}, tmp_term={}", + token, tmp_token); + } + if (term_docs) { + term_docs->close(); + _CLLDELETE(term_docs); + } + if (tmp_term_docs) { + tmp_term_docs->close(); + _CLLDELETE(tmp_term_docs); + } + } + + // check if there are remaining terms + if (term_enum->next() || tmp_term_enum->next()) { + return Status::InternalError( + "index compaction correctness check failed, number of terms not equal"); + } + if (term_enum) { + term_enum->close(); + _CLLDELETE(term_enum); + } + if (tmp_term_enum) { + tmp_term_enum->close(); + _CLLDELETE(tmp_term_enum); + } + if (idx_reader) { + idx_reader->close(); + _CLLDELETE(idx_reader); + } + if (tmp_idx_reader) { + tmp_idx_reader->close(); + _CLLDELETE(tmp_idx_reader); + } + return Status::OK(); +} + +static RowsetSharedPtr do_compaction(std::vector<RowsetSharedPtr> rowsets, Review Comment: warning: function 'do_compaction' exceeds recommended size/complexity thresholds [readability-function-size] ```cpp static RowsetSharedPtr do_compaction(std::vector<RowsetSharedPtr> rowsets, ^ ``` <details> <summary>Additional context</summary> **be/test/olap/rowset/segment_v2/inverted_index/index_compaction_with_deleted_term.cpp:217:** 245 lines including whitespace and comments (threshold 80) ```cpp static RowsetSharedPtr do_compaction(std::vector<RowsetSharedPtr> rowsets, ^ ``` </details> -- 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: commits-unsubscr...@doris.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@doris.apache.org For additional commands, e-mail: commits-h...@doris.apache.org
