lyx_mirror/src/Thesaurus.cpp

304 lines
7.5 KiB
C++
Raw Normal View History

/**
* \file Thesaurus.cpp
* This file is part of LyX, the document processor.
* Licence details can be found in the file COPYING.
*
* \author John Levon
* \author Jürgen Spitzmüller
*
* Full author contact details are available in file CREDITS.
*/
#include <config.h>
#include "Thesaurus.h"
#include "LyXRC.h"
#include "SpellChecker.h"
#include "WordLangTuple.h"
#include "support/FileNameList.h"
#include "support/Package.h"
#include "support/debug.h"
#include "support/docstring_list.h"
#include "support/filetools.h"
#include "support/gettext.h"
#include "support/lstrings.h"
#include "support/os.h"
#include <cstdio>
#include MYTHES_H_LOCATION
#include "frontends/alert.h"
#include <algorithm>
#include <cstring>
#include <fstream>
using namespace std;
using namespace lyx::support;
using namespace lyx::support::os;
namespace lyx {
namespace {
typedef std::map<docstring, MyThes *> Thesauri;
Bulk cleanup/fix incorrect annotation at the end of namespaces. This commit does a bulk fix of incorrect annotations (comments) at the end of namespaces. The commit was generated by initially running clang-format, and then from the diff of the result extracting the hunks corresponding to fixes of namespace comments. The changes being applied and all the results have been manually reviewed. The source code successfully builds on macOS. Further details on the steps below, in case they're of interest to someone else in the future. 1. Checkout a fresh and up to date version of src/ git pull && git checkout -- src && git status src 2. Ensure there's a suitable .clang-format in place, i.e. with options to fix the comment at the end of namespaces, including: FixNamespaceComments: true SpacesBeforeTrailingComments: 1 and that clang-format is >= 5.0.0, by doing e.g.: clang-format -dump-config | grep Comments: clang-format --version 3. Apply clang-format to the source: clang-format -i $(find src -name "*.cpp" -or -name "*.h") 4. Create and filter out hunks related to fixing the namespace git diff -U0 src > tmp.patch grepdiff '^} // namespace' --output-matching=hunk tmp.patch > fix_namespace.patch 5. Filter out hunks corresponding to simple fixes into to a separate patch: pcregrep -M -e '^diff[^\n]+\nindex[^\n]+\n--- [^\n]+\n\+\+\+ [^\n]+\n' \ -e '^@@ -[0-9]+ \+[0-9]+ @@[^\n]*\n-\}[^\n]*\n\+\}[^\n]*\n' \ fix_namespace.patch > fix_namespace_simple.patch 6. Manually review the simple patch and then apply it, after first restoring the source. git checkout -- src patch -p1 < fix_namespace_simple.path 7. Manually review the (simple) changes and then stage the changes git diff src git add src 8. Again apply clang-format and filter out hunks related to any remaining fixes to the namespace, this time filter with more context. There will be fewer hunks as all the simple cases have already been handled: clang-format -i $(find src -name "*.cpp" -or -name "*.h") git diff src > tmp.patch grepdiff '^} // namespace' --output-matching=hunk tmp.patch > fix_namespace2.patch 9. Manually review/edit the resulting patch file to remove hunks for files which need to be dealt with manually, noting the file names and line numbers. Then restore files to as before applying clang-format and apply the patch: git checkout src patch -p1 < fix_namespace2.patch 10. Manually fix the files noted in the previous step. Stage files, review changes and commit.
2017-07-23 11:11:54 +00:00
} // namespace
struct Thesaurus::Private
{
~Private()
{
for (Thesauri::iterator it = thes_.begin();
it != thes_.end(); ++it) {
delete it->second;
}
}
///
bool thesaurusAvailable(docstring const & lang) const
{
for (Thesauri::const_iterator it = thes_.begin();
it != thes_.end(); ++it) {
if (it->first == lang)
if (it->second)
return true;
}
return false;
}
///
typedef std::pair<std::string, std::string> ThesFiles;
///
ThesFiles getThesaurus(string const & path, docstring const & lang);
ThesFiles getThesaurus(docstring const & lang);
/// add a thesaurus to the list
bool addThesaurus(docstring const & lang);
/// the thesauri
Thesauri thes_;
/// the location below system/user directory
/// there the data+idx files lookup will happen
const string dataDirectory(void) { return "thes"; }
};
pair<string,string> Thesaurus::Private::getThesaurus(string const & path, docstring const & lang)
{
FileName base(path);
if (!base.isDirectory()) {
return make_pair(string(), string());
}
FileNameList const idx_files = base.dirList("idx");
FileNameList const data_files = base.dirList("dat");
string idx;
string data;
string basename;
LYXERR(Debug::FILES, "thesaurus path: " << path);
for (FileNameList::const_iterator it = idx_files.begin(); it != idx_files.end(); ++it) {
basename = it->onlyFileNameWithoutExt();
if (contains(basename, to_ascii(lang))) {
// do not use more specific dicts.
if (contains(basename, '_') && !contains(lang, '_'))
continue;
if (contains(basename, '-') && !contains(lang, '-'))
continue;
ifstream ifs(it->absFileName().c_str());
if (ifs) {
// check for appropriate version of index file
string encoding; // first line is encoding
int items = 0; // second line is no. of items
getline(ifs,encoding);
ifs >> items;
if (ifs.fail()) {
LYXERR(Debug::FILES, "ignore irregular thesaurus idx file: " << it->absFileName());
continue;
}
if (encoding.length() == 0 || encoding.find_first_of(',') != string::npos) {
LYXERR(Debug::FILES, "ignore version1 thesaurus idx file: " << it->absFileName());
continue;
}
}
idx = it->absFileName();
LYXERR(Debug::FILES, "selected thesaurus idx file: " << idx);
break;
}
}
if (idx.empty()) {
// try with a more general dictionary
docstring shortcode;
if (contains(lang, '_')) {
split(lang, shortcode, '_');
LYXERR(Debug::FILES, "Did not find thesaurus for LANG code "
<< lang << ". Trying with " << shortcode);
return getThesaurus(path, shortcode);
}
else if (contains(lang, '-')) {
split(lang, shortcode, '-');
LYXERR(Debug::FILES, "Did not find thesaurus for LANG code "
<< lang << ". Trying with " << shortcode);
return getThesaurus(path, shortcode);
}
return make_pair(string(), string());
}
for (support::FileNameList::const_iterator it = data_files.begin(); it != data_files.end(); ++it) {
if (contains(it->onlyFileName(), basename)) {
data = it->absFileName();
LYXERR(Debug::FILES, "selected thesaurus data file: " << data);
break;
}
}
return make_pair(idx, data);
}
pair<string,string> Thesaurus::Private::getThesaurus(docstring const & lang)
{
string const thes_path = external_path(lyxrc.thesaurusdir_path);
pair<string,string> result ;
if (thesaurusAvailable(lang))
return make_pair(string(), string());
if (!thes_path.empty())
result = getThesaurus(thes_path, lang);
if (result.first.empty() || result.second.empty()) {
string const sys_path = external_path(addName(lyx::support::package().system_support().absFileName(),dataDirectory())) ;
result = getThesaurus(sys_path, lang);
}
if (result.first.empty() || result.second.empty()) {
string const user_path = external_path(addName(lyx::support::package().user_support().absFileName(),dataDirectory())) ;
result = getThesaurus(user_path, lang);
}
return result;
}
bool Thesaurus::Private::addThesaurus(docstring const & lang)
{
if (thesaurusAvailable(lang))
return true;
ThesFiles files = getThesaurus(lang);
string const idx = files.first;
string const data = files.second;
if (idx.empty() || data.empty())
return false;
char const * af = idx.c_str();
char const * df = data.c_str();
thes_[lang] = new MyThes(af, df);
return true;
}
bool Thesaurus::thesaurusAvailable(docstring const & lang) const
{
return d->thesaurusAvailable(lang);
}
bool Thesaurus::thesaurusInstalled(docstring const & lang) const
{
if (thesaurusAvailable(lang))
return true;
pair<string, string> files = d->getThesaurus(lang);
return (!files.first.empty() && !files.second.empty());
}
Thesaurus::Meanings Thesaurus::lookup(WordLangTuple const & wl)
{
Meanings meanings;
2020-05-03 06:32:39 +00:00
MyThes * mythes = nullptr;
docstring const lang_code = from_ascii(wl.lang()->code());
docstring const t = wl.word();
if (!d->addThesaurus(lang_code))
return meanings;
for (Thesauri::const_iterator it = d->thes_.begin();
it != d->thes_.end(); ++it) {
if (it->first == lang_code) {
mythes = it->second;
break;
}
}
if (!mythes)
return meanings;
string const encoding = mythes->get_th_encoding();
2017-07-03 17:53:14 +00:00
mentry * pmean;
string const text = to_iconv_encoding(support::lowercase(t), encoding);
int len = strlen(text.c_str());
int count = mythes->Lookup(text.c_str(), len, &pmean);
if (!count) {
SpellChecker * speller = theSpellChecker();
if (!speller)
return meanings;
docstring_list suggestions;
speller->stem(wl, suggestions);
for (size_t i = 0; i != suggestions.size(); ++i) {
string const wordform = to_iconv_encoding(support::lowercase(suggestions[i]), encoding);
len = strlen(wordform.c_str());
count = mythes->Lookup(wordform.c_str(), len, &pmean);
if (count)
break;
}
if (!count)
return meanings;
}
// don't change value of pmean or count
// they are needed for the CleanUpAfterLookup routine
mentry * pm = pmean;
docstring meaning;
for (int i = 0; i < count; i++) {
vector<docstring> ret;
meaning = from_iconv_encoding(string(pm->defn), encoding);
// remove silly item
if (support::prefixIs(meaning, '-'))
meaning = support::ltrim(meaning, "- ");
for (int j = 0; j < pm->count; j++) {
ret.push_back(from_iconv_encoding(string(pm->psyns[j]), encoding));
}
meanings[meaning] = ret;
++pm;
}
// now clean up all allocated memory
mythes->CleanUpAfterLookup(&pmean, count);
for (Meanings::iterator it = meanings.begin();
it != meanings.end(); ++it)
sort(it->second.begin(), it->second.end());
return meanings;
}
Thesaurus::Thesaurus()
: d(new Thesaurus::Private)
{
}
Thesaurus::~Thesaurus()
{
delete d;
}
// Global instance
Thesaurus thesaurus;
} // namespace lyx