diff options
author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-07 09:06:44 +0000 |
---|---|---|
committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-07 09:06:44 +0000 |
commit | ed5640d8b587fbcfed7dd7967f3de04b37a76f26 (patch) | |
tree | 7a5f7c6c9d02226d7471cb3cc8fbbf631b415303 /l10ntools/source/idxdict | |
parent | Initial commit. (diff) | |
download | libreoffice-upstream/4%7.4.7.tar.xz libreoffice-upstream/4%7.4.7.zip |
Adding upstream version 4:7.4.7.upstream/4%7.4.7upstream
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'l10ntools/source/idxdict')
-rw-r--r-- | l10ntools/source/idxdict/idxdict.cxx | 89 |
1 files changed, 89 insertions, 0 deletions
diff --git a/l10ntools/source/idxdict/idxdict.cxx b/l10ntools/source/idxdict/idxdict.cxx new file mode 100644 index 000000000..6d2a22b3d --- /dev/null +++ b/l10ntools/source/idxdict/idxdict.cxx @@ -0,0 +1,89 @@ +/* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */ +/* + * This file is part of the LibreOffice project. + * + * This Source Code Form is subject to the terms of the Mozilla Public + * License, v. 2.0. If a copy of the MPL was not distributed with this + * file, You can obtain one at http://mozilla.org/MPL/2.0/. + */ + +#include <cerrno> +#include <iostream> +#include <fstream> +#include <string> +#include <map> +#include <stdlib.h> +#include <string.h> + +const int MAXLINE = 1024*64; + +int main(int argc, char *argv[]) +{ + if (argc != 3 || strcmp(argv[1],"-o")) + { + std::cout << "Usage: idxdict -o outputfile < input\n"; + ::exit(99); + } + // This call improves performance by approx 5x + std::ios_base::sync_with_stdio(false); + + const char * outputFile(argv[2]); + char inputBuffer[MAXLINE]; + std::multimap<std::string, size_t> entries; + std::multimap<std::string,size_t>::iterator ret(entries.begin()); + + std::cin.getline(inputBuffer, MAXLINE); + const std::string encoding(inputBuffer); + size_t currentOffset(encoding.size()+1); + while (true) + { + // Extract the next word, but not the entry count + std::cin.getline(inputBuffer, MAXLINE, '|'); + + if (std::cin.eof()) break; + + std::string word(inputBuffer); + ret = entries.insert(ret, std::pair<std::string, size_t>(word, currentOffset)); + currentOffset += word.size() + 1; + // Next is the entry count + std::cin.getline(inputBuffer, MAXLINE); + if (!std::cin.good()) + { + std::cerr << "Unable to read entry - insufficient buffer?.\n"; + exit(99); + } + currentOffset += strlen(inputBuffer)+1; + char * endptr; + errno = 0; + int entryCount(strtol(inputBuffer, &endptr, 10)); + if (errno != 0 || endptr == inputBuffer || *endptr != '\0') + { + std::cerr + << "Unable to read count from \"" << inputBuffer + << "\" input.\n"; + exit(99); + } + for (int i(0); i < entryCount; ++i) + { + std::cin.getline(inputBuffer, MAXLINE); + currentOffset += strlen(inputBuffer)+1; + } + } + + // Use binary mode to prevent any translation of LF to CRLF on Windows + std::ofstream outputStream(outputFile, std::ios_base::binary| std::ios_base::trunc|std::ios_base::out); + if (!outputStream.is_open()) + { + std::cerr << "Unable to open output file " << outputFile << std::endl; + ::exit(99); + } + + outputStream << encoding << '\n' << entries.size() << '\n'; + + for (auto const& entry : entries) + { + outputStream << entry.first << '|' << entry.second << '\n'; + } +} + +/* vim:set shiftwidth=4 softtabstop=4 expandtab: */ |