summaryrefslogtreecommitdiffstats
path: root/l10ntools/source/idxdict/idxdict.cxx
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-27 16:51:28 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-27 16:51:28 +0000
commit940b4d1848e8c70ab7642901a68594e8016caffc (patch)
treeeb72f344ee6c3d9b80a7ecc079ea79e9fba8676d /l10ntools/source/idxdict/idxdict.cxx
parentInitial commit. (diff)
downloadlibreoffice-1ad18e38974bb28c3d98d0be8f7d8c18fc56de29.tar.xz
libreoffice-1ad18e38974bb28c3d98d0be8f7d8c18fc56de29.zip
Adding upstream version 1:7.0.4.upstream/1%7.0.4upstream
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'l10ntools/source/idxdict/idxdict.cxx')
-rw-r--r--l10ntools/source/idxdict/idxdict.cxx91
1 files changed, 91 insertions, 0 deletions
diff --git a/l10ntools/source/idxdict/idxdict.cxx b/l10ntools/source/idxdict/idxdict.cxx
new file mode 100644
index 000000000..0a4a6ddb0
--- /dev/null
+++ b/l10ntools/source/idxdict/idxdict.cxx
@@ -0,0 +1,91 @@
+/* -*- 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>
+
+static const int MAXLINE = 1024*64;
+
+using namespace std;
+
+int main(int argc, char *argv[])
+{
+ if (argc != 3 || strcmp(argv[1],"-o"))
+ {
+ 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];
+ multimap<string, size_t> entries;
+ multimap<string,size_t>::iterator ret(entries.begin());
+
+ cin.getline(inputBuffer, MAXLINE);
+ const string encoding(inputBuffer);
+ size_t currentOffset(encoding.size()+1);
+ while (true)
+ {
+ // Extract the next word, but not the entry count
+ cin.getline(inputBuffer, MAXLINE, '|');
+
+ if (cin.eof()) break;
+
+ string word(inputBuffer);
+ ret = entries.insert(ret, pair<string, size_t>(word, currentOffset));
+ currentOffset += word.size() + 1;
+ // Next is the entry count
+ cin.getline(inputBuffer, MAXLINE);
+ if (!cin.good())
+ {
+ 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')
+ {
+ cerr
+ << "Unable to read count from \"" << inputBuffer
+ << "\" input.\n";
+ exit(99);
+ }
+ for (int i(0); i < entryCount; ++i)
+ {
+ cin.getline(inputBuffer, MAXLINE);
+ currentOffset += strlen(inputBuffer)+1;
+ }
+ }
+
+ // Use binary mode to prevent any translation of LF to CRLF on Windows
+ ofstream outputStream(outputFile, ios_base::binary| ios_base::trunc|ios_base::out);
+ if (!outputStream.is_open())
+ {
+ cerr << "Unable to open output file " << outputFile << 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: */