X-Git-Url: https://git.lyx.org/gitweb/?a=blobdiff_plain;f=src%2FAspellChecker.cpp;h=c4b24199940fa2146418638e50024b11abf0694e;hb=28be7d552f62cc02fa86d7f79201d089bfb2d7b5;hp=06cc6bf49a123c40a0ea7d8c5904d9536f711ead;hpb=e4f2484cb5899da6d98e0be6db465ca011989e04;p=lyx.git

diff --git a/src/AspellChecker.cpp b/src/AspellChecker.cpp
index 06cc6bf49a..c4b2419994 100644
--- a/src/AspellChecker.cpp
+++ b/src/AspellChecker.cpp
@@ -12,17 +12,20 @@
 #include <config.h>
 
 #include "AspellChecker.h"
+#include "PersonalWordList.h"
+
 #include "LyXRC.h"
 #include "WordLangTuple.h"
 
 #include "support/lassert.h"
 #include "support/debug.h"
+#include "support/lstrings.h"
 #include "support/docstring_list.h"
 
 #include "support/filetools.h"
 #include "support/Package.h"
 #include "support/FileName.h"
-#include "support/Path.h"
+#include "support/PathChanger.h"
 
 #include <aspell.h>
 
@@ -39,63 +42,88 @@ namespace {
 struct Speller {
 	AspellConfig * config;
 	AspellCanHaveError * e_speller;
+	bool accept_compound;
+	docstring_list ignored_words_;
 };
 
 typedef std::map<std::string, Speller> Spellers;
+typedef map<std::string, PersonalWordList *> LangPersonalWordList;
 
 } // anon namespace
 
 struct AspellChecker::Private
 {
-	Private() {}
+	Private()
+	{}
 
 	~Private();
 
 	/// add a speller of the given language and variety
-	AspellSpeller * addSpeller(string const & lang,
-				   string const & variety = string());
+	AspellSpeller * addSpeller(Language const * lang);
 
 	///
-	AspellSpeller * speller(string const & lang,
-				string const & variety);
-
-	/// create a unique ID from lang code and variety
-	string const spellerID(string const & lang,
-			       string const & variety);
+	AspellSpeller * speller(Language const * lang);
 
 	bool isValidDictionary(AspellConfig * config,
 			string const & lang, string const & variety);
+	int numDictionaries() const;
 	bool checkAspellData(AspellConfig * config,
 		string const & basepath, string const & datapath, string const & dictpath,
 		string const & lang, string const & variety);
 	AspellConfig * getConfig(string const & lang, string const & variety);
 
+	string toAspellWord(docstring const & word) const;
+
+	SpellChecker::Result check(AspellSpeller * m,
+		WordLangTuple const & word) const;
+
+	void initSessionDictionary(Speller const & speller, PersonalWordList * pd);
+	void addToSession(AspellCanHaveError * speller, docstring const & word);
+	void insert(WordLangTuple const & word);
+	void remove(WordLangTuple const & word);
+	bool learned(WordLangTuple const & word);
+
+	void accept(Speller & speller, WordLangTuple const & word);
+
 	/// the spellers
 	Spellers spellers_;
 
+	LangPersonalWordList personal_;
+
 	/// the location below system/user directory
 	/// there the rws files lookup will happen
-	const string dictDirectory(void) { return "dict"; }
+	const string dictDirectory(void)
+	{
+		return "dicts";
+	}
 	/// there the dat+cmap files lookup will happen
-	const string dataDirectory(void) { return "data"; }
+	const string dataDirectory(void)
+	{
+		return "data";
+	}
 	/// os package directory constants
 	/// macports on Mac OS X or
 	/// aspell rpms on Linux
-	const string osPackageBase(void) {
+	const string osPackageBase(void)
+	{
 #ifdef USE_MACOSX_PACKAGING
 		return "/opt/local";
 #else
 		return "/usr";
 #endif
 	}
-	const string osPackageDictDirectory(void) {
+	const string osPackageDictDirectory(void)
+	{
 #ifdef USE_MACOSX_PACKAGING
 		return "/share/aspell";
 #else
 		return "/lib/aspell-0.60";
 #endif
 	}
-	const string osPackageDataDirectory(void) { return "/lib/aspell-0.60"; }
+	const string osPackageDataDirectory(void)
+	{
+		return "/lib/aspell-0.60";
+	}
 
 };
 
@@ -113,6 +141,17 @@ AspellChecker::Private::~Private()
 		}
 		delete_aspell_config(it->second.config);
 	}
+
+	LangPersonalWordList::const_iterator pdit = personal_.begin();
+	LangPersonalWordList::const_iterator pdet = personal_.end();
+	
+	for (; pdit != pdet; ++pdit) {
+		if ( 0 == pdit->second)
+			continue;
+		PersonalWordList * pd = pdit->second;
+		pd->save();
+		delete pd;
+	}
 }
 
 
@@ -180,22 +219,49 @@ AspellConfig * AspellChecker::Private::getConfig(string const & lang, string con
 	}
 	if (!have_dict) {
 		// check for package data of OS installation
-		have_dict = checkAspellData(config, osPackageBase(), osPackageDataDirectory(), osPackageDictDirectory(), lang, variety);
+		checkAspellData(config, osPackageBase(), osPackageDataDirectory(), osPackageDictDirectory(), lang, variety);
 	}
 	return config ;
 }
 
 
-AspellSpeller * AspellChecker::Private::addSpeller(string const & lang,
-						   string const & variety)
+void AspellChecker::Private::addToSession(AspellCanHaveError * speller, docstring const & word)
 {
-	Speller m;
+	string const word_to_add = toAspellWord(word);
+	if(1 != aspell_speller_add_to_session(to_aspell_speller(speller), word_to_add.c_str(), -1))
+		LYXERR(Debug::GUI, "aspell add to session: " << aspell_error_message(speller));
+}
+
+
+void AspellChecker::Private::initSessionDictionary(
+	Speller const & speller,
+	PersonalWordList * pd)
+{
+	AspellSpeller * aspell = to_aspell_speller(speller.e_speller);
+	aspell_speller_clear_session(aspell);
+	docstring_list::const_iterator it = pd->begin();
+	docstring_list::const_iterator et = pd->end();
+	for (; it != et; ++it) {
+		addToSession(speller.e_speller, *it);
+	}
+	it = speller.ignored_words_.begin();
+	et = speller.ignored_words_.end();
+	for (; it != et; ++it) {
+		addToSession(speller.e_speller, *it);
+	}
+}
 
-	m.config = getConfig(lang, variety);
+
+AspellSpeller * AspellChecker::Private::addSpeller(Language const * lang)
+{
+	Speller m;
+	string const code = lang->code();
+	string const variety = lang->variety();
+	m.config = getConfig(code, variety);
 	// Aspell supports both languages and varieties (such as German
 	// old vs. new spelling). The respective naming convention is
 	// lang_REGION-variety (e.g. de_DE-alt).
-	aspell_config_replace(m.config, "lang", lang.c_str());
+	aspell_config_replace(m.config, "lang", code.c_str());
 	if (!variety.empty())
 		aspell_config_replace(m.config, "variety", variety.c_str());
 	// Set the encoding to utf-8.
@@ -213,6 +279,7 @@ AspellSpeller * AspellChecker::Private::addSpeller(string const & lang,
 		// Report run-together words as errors
 		aspell_config_replace(m.config, "run-together", "false");
 
+	m.accept_compound = lyxrc.spellchecker_accept_compound;
 	m.e_speller = new_aspell_speller(m.config);
 	if (aspell_error_number(m.e_speller) != 0) {
 		// FIXME: We should indicate somehow that this language is not supported.
@@ -221,38 +288,141 @@ AspellSpeller * AspellChecker::Private::addSpeller(string const & lang,
 		delete_aspell_config(m.config);
 		m.config = 0;
 		m.e_speller = 0;
+	} else {
+		PersonalWordList * pd = new PersonalWordList(lang->lang());
+		pd->load();
+		personal_[lang->lang()] = pd;
+		initSessionDictionary(m, pd);
 	}
-
-	spellers_[spellerID(lang, variety)] = m;
+	
+	spellers_[lang->lang()] = m;
 	return m.e_speller ? to_aspell_speller(m.e_speller) : 0;
 }
 
 
-AspellSpeller * AspellChecker::Private::speller(string const & lang,
-						string const & variety)
+AspellSpeller * AspellChecker::Private::speller(Language const * lang)
 {
-	Spellers::iterator it = spellers_.find(spellerID(lang, variety));
-	if (it != spellers_.end())
-		return to_aspell_speller(it->second.e_speller);
-	
-	return addSpeller(lang, variety);
+	Spellers::iterator it = spellers_.find(lang->lang());
+	if (it != spellers_.end()) {
+		Speller aspell = it->second;
+		if (lyxrc.spellchecker_accept_compound != aspell.accept_compound) {
+			// spell checker setting changed... adjust run-together
+			aspell.accept_compound = lyxrc.spellchecker_accept_compound;
+			if (aspell.accept_compound)
+				// Consider run-together words as legal compounds
+				aspell_config_replace(aspell.config, "run-together", "true");
+			else
+				// Report run-together words as errors
+				aspell_config_replace(aspell.config, "run-together", "false");
+			AspellCanHaveError * e_speller = aspell.e_speller;
+			aspell.e_speller = new_aspell_speller(aspell.config);
+			delete_aspell_speller(to_aspell_speller(e_speller));
+			spellers_[lang->lang()] = aspell;
+		}
+		return to_aspell_speller(aspell.e_speller);
+	}
+
+	return addSpeller(lang);
+}
+
+
+int AspellChecker::Private::numDictionaries() const
+{
+	int result = 0;
+	Spellers::const_iterator it = spellers_.begin();
+	Spellers::const_iterator et = spellers_.end();
+
+	for (; it != et; ++it) {
+		Speller aspell = it->second;
+		result += aspell.e_speller != 0;
+	}
+	return result;
+}
+
+
+string AspellChecker::Private::toAspellWord(docstring const & word) const
+{
+	size_t mpos;
+	string word_str = to_utf8(word);
+	while ((mpos = word_str.find('-')) != word_str.npos) {
+		word_str.erase(mpos, 1);
+	}
+	return word_str;
 }
 
 
-string const AspellChecker::Private::spellerID(string const & lang,
-					string const & variety)
+SpellChecker::Result AspellChecker::Private::check(
+	AspellSpeller * m, WordLangTuple const & word) 
+	const
 {
-	if (variety.empty())
-		return lang;
-	return lang + "-" + variety;
+	SpellChecker::Result result = WORD_OK;
+	docstring w1;
+	LYXERR(Debug::GUI, "spellCheck: \"" <<
+		   word.word() << "\", lang = " << word.lang()->lang()) ;
+	docstring rest = split(word.word(), w1, '-');
+	for (; result == WORD_OK;) {
+		string const word_str = toAspellWord(w1);
+		int const word_ok = aspell_speller_check(m, word_str.c_str(), -1);
+		LASSERT(word_ok != -1, return UNKNOWN_WORD);
+		result = (word_ok) ? WORD_OK : UNKNOWN_WORD;
+		if (rest.empty())
+			break;
+		rest = split(rest,w1,'-');
+	}
+	if (result == WORD_OK)
+		return result;
+	string const word_str = toAspellWord(word.word());
+	int const word_ok = aspell_speller_check(m, word_str.c_str(), -1);
+	LASSERT(word_ok != -1, return UNKNOWN_WORD);
+	return (word_ok) ? WORD_OK : UNKNOWN_WORD;
 }
 
+void AspellChecker::Private::accept(Speller & speller, WordLangTuple const & word)
+{
+	speller.ignored_words_.push_back(word.word());
+}
+
+
+/// personal word list interface
+void AspellChecker::Private::remove(WordLangTuple const & word)
+{
+	PersonalWordList * pd = personal_[word.lang()->lang()];
+	if (!pd)
+		return;
+	pd->remove(word.word());
+	Spellers::iterator it = spellers_.find(word.lang()->lang());
+	if (it != spellers_.end()) {
+		initSessionDictionary(it->second, pd);
+	}
+}
+
+		
+void AspellChecker::Private::insert(WordLangTuple const & word)
+{
+	Spellers::iterator it = spellers_.find(word.lang()->lang());
+	if (it != spellers_.end()) {
+		addToSession(it->second.e_speller, word.word());
+		PersonalWordList * pd = personal_[word.lang()->lang()];
+		if (!pd)
+			return;
+		pd->insert(word.word());
+	}
+}
 
-AspellChecker::AspellChecker(): d(new Private)
+bool AspellChecker::Private::learned(WordLangTuple const & word)
 {
+	PersonalWordList * pd = personal_[word.lang()->lang()];
+	if (!pd)
+		return false;
+	return pd->exists(word.word());
 }
 
 
+AspellChecker::AspellChecker()
+	: d(new Private)
+{}
+
+
 AspellChecker::~AspellChecker()
 {
 	delete d;
@@ -262,42 +432,40 @@ AspellChecker::~AspellChecker()
 SpellChecker::Result AspellChecker::check(WordLangTuple const & word)
 {
   
-	AspellSpeller * m =
-		d->speller(word.lang()->code(), word.lang()->variety());
+	AspellSpeller * m = d->speller(word.lang());
 
 	if (!m)
-		return WORD_OK;
+		return NO_DICTIONARY;
 
 	if (word.word().empty())
 		// MSVC compiled Aspell doesn't like it.
 		return WORD_OK;
 
-	string const word_str = to_utf8(word.word());
-	int const word_ok = aspell_speller_check(m, word_str.c_str(), -1);
-	LASSERT(word_ok != -1, /**/);
+	SpellChecker::Result rc = d->check(m, word);
+	return (rc == WORD_OK && d->learned(word)) ? LEARNED_WORD : rc;
+}
 
-	return (word_ok) ? WORD_OK : UNKNOWN_WORD;
+
+void AspellChecker::advanceChangeNumber()
+{
+	nextChangeNumber();
 }
 
 
 void AspellChecker::insert(WordLangTuple const & word)
 {
-	Spellers::iterator it = d->spellers_.find(
-		d->spellerID(word.lang()->code(), word.lang()->variety()));
-	if (it != d->spellers_.end()) {
-		AspellSpeller * speller = to_aspell_speller(it->second.e_speller);
-		aspell_speller_add_to_personal(speller, to_utf8(word.word()).c_str(), -1);
-	}
+	d->insert(word);
+	advanceChangeNumber();
 }
 
 
 void AspellChecker::accept(WordLangTuple const & word)
 {
-	Spellers::iterator it = d->spellers_.find(
-		d->spellerID(word.lang()->code(), word.lang()->variety()));
+	Spellers::iterator it = d->spellers_.find(word.lang()->lang());
 	if (it != d->spellers_.end()) {
-		AspellSpeller * speller = to_aspell_speller(it->second.e_speller);
-		aspell_speller_add_to_session(speller, to_utf8(word.word()).c_str(), -1);
+		d->addToSession(it->second.e_speller, word.word());
+		d->accept(it->second, word);
+		advanceChangeNumber();
 	}
 }
 
@@ -306,15 +474,15 @@ void AspellChecker::suggest(WordLangTuple const & wl,
 	docstring_list & suggestions)
 {
 	suggestions.clear();
-	AspellSpeller * m =
-		d->speller(wl.lang()->code(), wl.lang()->variety());
+	AspellSpeller * m = d->speller(wl.lang());
 
 	if (!m)
 		return;
 
+	string const word = d->toAspellWord(wl.word());
 	AspellWordList const * sugs =
-		aspell_speller_suggest(m, to_utf8(wl.word()).c_str(), -1);
-	LASSERT(sugs != 0, /**/);
+		aspell_speller_suggest(m, word.c_str(), -1);
+	LASSERT(sugs != 0, return);
 	AspellStringEnumeration * els = aspell_word_list_elements(sugs);
 	if (!els || aspell_word_list_empty(sugs))
 		return;
@@ -330,6 +498,13 @@ void AspellChecker::suggest(WordLangTuple const & wl,
 }
 
 
+void AspellChecker::remove(WordLangTuple const & word)
+{
+	d->remove(word);
+	advanceChangeNumber();
+}
+
+
 bool AspellChecker::hasDictionary(Language const * lang) const
 {
 	bool have = false;
@@ -350,6 +525,12 @@ bool AspellChecker::hasDictionary(Language const * lang) const
 }
 
 
+int AspellChecker::numDictionaries() const
+{
+	return d->numDictionaries();
+}
+	
+	
 docstring const AspellChecker::error()
 {
 	Spellers::iterator it = d->spellers_.begin();