X-Git-Url: https://git.lyx.org/gitweb/?a=blobdiff_plain;f=src%2FParagraph.cpp;h=67965ef4c5950da18f47d9143db248161b87d68b;hb=68fe13dfa1ed24891d930b0d9b8b79e217c7f1e4;hp=971501f4aee034fca8247615abe2497cd2c86d71;hpb=504b893ec8ab0b0ebd45a6915ed5f1c823c418a5;p=lyx.git diff --git a/src/Paragraph.cpp b/src/Paragraph.cpp index 971501f4ae..67965ef4c5 100644 --- a/src/Paragraph.cpp +++ b/src/Paragraph.cpp @@ -51,6 +51,7 @@ #include "insets/InsetBibitem.h" #include "insets/InsetLabel.h" +#include "insets/InsetSpecialChar.h" #include "support/debug.h" #include "support/docstring_list.h" @@ -71,6 +72,53 @@ namespace lyx { namespace { /// Inset identifier (above 0x10ffff, for ucs-4) char_type const META_INSET = 0x200001; +} + + +///////////////////////////////////////////////////////////////////// +// +// SpellResultRange +// +///////////////////////////////////////////////////////////////////// + +class SpellResultRange { +public: + SpellResultRange(FontSpan range, SpellChecker::Result result) + : range_(range), result_(result) + {} + /// + FontSpan const & range() const { return range_; } + /// + void range(FontSpan const & r) { range_ = r; } + /// + SpellChecker::Result result() const { return result_; } + /// + void result(SpellChecker::Result r) { result_ = r; } + /// + bool inside(pos_type pos) const { return range_.inside(pos); } + /// + bool covered(FontSpan const & r) const + { + // 1. first of new range inside current range or + // 2. last of new range inside current range or + // 3. first of current range inside new range or + // 4. last of current range inside new range + return range_.inside(r.first) || range_.inside(r.last) || + r.inside(range_.first) || r.inside(range_.last); + } + /// + void shift(pos_type pos, int offset) + { + if (range_.first > pos) { + range_.first += offset; + range_.last += offset; + } else if (range_.last > pos) { + range_.last += offset; + } + } +private: + FontSpan range_ ; + SpellChecker::Result result_ ; }; @@ -91,7 +139,7 @@ public: { eraseCoveredRanges(fp); if (state != SpellChecker::WORD_OK) - ranges_[fp] = state; + ranges_.push_back(SpellResultRange(fp, state)); } void increasePosAfterPos(pos_type pos) @@ -106,21 +154,39 @@ public: needsRefresh(pos); } + void refreshLast(pos_type pos) + { + if (pos < refresh_.last) + refresh_.last = pos; + } + SpellChecker::Result getState(pos_type pos) const { SpellChecker::Result result = SpellChecker::WORD_OK; RangesIterator et = ranges_.end(); RangesIterator it = ranges_.begin(); for (; it != et; ++it) { - FontSpan fc = it->first; - if(fc.first <= pos && pos <= fc.last) { - result = it->second; - break; + if(it->inside(pos)) { + return it->result(); } } return result; } + FontSpan const & getRange(pos_type pos) const + { + /// empty span to indicate mismatch + static FontSpan empty_; + RangesIterator et = ranges_.end(); + RangesIterator it = ranges_.begin(); + for (; it != et; ++it) { + if(it->inside(pos)) { + return it->range(); + } + } + return empty_; + } + bool needsRefresh() const { return needs_refresh_; } @@ -155,52 +221,35 @@ public: } private: - /// store the ranges as map of FontSpan and spell result pairs - typedef map Ranges; + typedef vector Ranges; typedef Ranges::const_iterator RangesIterator; Ranges ranges_; - /// + /// the area of the paragraph with pending spell check FontSpan refresh_; bool needs_refresh_; + /// spell state cache version number SpellChecker::ChangeNumber current_change_number_; + void eraseCoveredRanges(FontSpan const fp) { Ranges result; RangesIterator et = ranges_.end(); RangesIterator it = ranges_.begin(); for (; it != et; ++it) { - FontSpan fc = it->first; - // 1. first of new range inside current range or - // 2. last of new range inside current range or - // 3. first of current range inside new range or - // 4. last of current range inside new range - if (fc.inside(fp.first) || fc.inside(fp.last) || - fp.inside(fc.first) || fp.inside(fc.last)) - { - continue; - } - result[fc] = it->second; + if (!it->covered(fp)) + result.push_back(SpellResultRange(it->range(), it->result())); } ranges_ = result; } void correctRangesAfterPos(pos_type pos, int offset) { - Ranges result; RangesIterator et = ranges_.end(); - RangesIterator it = ranges_.begin(); + Ranges::iterator it = ranges_.begin(); for (; it != et; ++it) { - FontSpan m = it->first; - if (m.first > pos) { - m.first += offset; - m.last += offset; - } else if (m.last > pos) { - m.last += offset; - } - result[m] = it->second; + it->shift(pos, offset); } - ranges_ = result; } }; @@ -305,14 +354,16 @@ public: /// match a string against a particular point in the paragraph bool isTextAt(string const & str, pos_type pos) const; - /// a vector of inset positions - typedef vector Positions; - typedef Positions::const_iterator PositionsIterator; + /// a vector of speller skip positions + typedef vector SkipPositions; + typedef SkipPositions::const_iterator SkipPositionsIterator; + void appendSkipPosition(SkipPositions & skips, pos_type const pos) const; + Language * getSpellLanguage(pos_type const from) const; Language * locateSpellRange(pos_type & from, pos_type & to, - Positions & softbreaks) const; + SkipPositions & skips) const; bool hasSpellerChange() const { SpellChecker::ChangeNumber speller_change_number = 0; @@ -321,6 +372,8 @@ public: return speller_change_number > speller_state_.currentChangeNumber(); } + bool ignoreWord(docstring const & word) const ; + void setMisspelled(pos_type from, pos_type to, SpellChecker::Result state) { pos_type textsize = owner_->size(); @@ -363,22 +416,23 @@ public: last = endpos; } - int countSoftbreaks(PositionsIterator & it, PositionsIterator const et, - pos_type & start) const + int countSkips(SkipPositionsIterator & it, SkipPositionsIterator const et, + int & start) const { - int numbreaks = 0; - while (it != et && *it < start) { - ++start; - ++numbreaks; + int numskips = 0; + while (it != et && it->first < start) { + int skip = it->last - it->first + 1; + start += skip; + numskips += skip; ++it; } - return numbreaks; + return numskips; } void markMisspelledWords(pos_type const & first, pos_type const & last, SpellChecker::Result result, docstring const & word, - Positions const & softbreaks); + SkipPositions const & skips); InsetCode ownerCode() const { @@ -462,7 +516,7 @@ Paragraph::Private::Private(Private const & p, Paragraph * owner) : owner_(owner), inset_owner_(p.inset_owner_), fontlist_(p.fontlist_), params_(p.params_), changes_(p.changes_), insetlist_(p.insetlist_), begin_of_body_(p.begin_of_body_), text_(p.text_), words_(p.words_), - layout_(p.layout_), speller_state_(p.speller_state_) + layout_(p.layout_) { id_ = ++paragraph_id; requestSpellCheck(p.text_.size()); @@ -475,7 +529,7 @@ Paragraph::Private::Private(Private const & p, Paragraph * owner, params_(p.params_), changes_(p.changes_), insetlist_(p.insetlist_, beg, end), begin_of_body_(p.begin_of_body_), words_(p.words_), - layout_(p.layout_), speller_state_(p.speller_state_) + layout_(p.layout_) { id_ = ++paragraph_id; if (beg >= pos_type(p.text_.size())) @@ -720,6 +774,8 @@ bool Paragraph::eraseChar(pos_type pos, bool trackChanges) if (!change.changed() || (change.inserted() && !change.currentAuthor())) { setChange(pos, Change(Change::DELETED)); + // request run of spell checker + requestSpellCheck(pos); return false; } @@ -751,6 +807,7 @@ bool Paragraph::eraseChar(pos_type pos, bool trackChanges) // Update list of misspelled positions d->speller_state_.decreasePosAfterPos(pos); + d->speller_state_.refreshLast(size()); return true; } @@ -1071,7 +1128,7 @@ void Paragraph::Private::latexInset(BufferParams const & bparams, texrow.start(owner_->id(), i + 1); column = 0; } else { - column += os.tellp() - len; + column += (unsigned int)(os.tellp() - len); } if (owner_->isDeleted(i)) @@ -1287,20 +1344,35 @@ bool Paragraph::Private::latexSpecialPhrase(odocstream & os, pos_type & i, void Paragraph::Private::validate(LaTeXFeatures & features) const { if (layout_->inpreamble && inset_owner_) { + bool const is_command = layout_->latextype == LATEX_COMMAND; Buffer const & buf = inset_owner_->buffer(); BufferParams const & bp = buf.params(); Font f; TexRow tr; + // Using a string stream here circumvents the encoding + // switching machinery of odocstream. Therefore the + // output is wrong if this paragraph contains content + // that needs to switch encoding. odocstringstream ods; - // we have to provide all the optional arguments here, even though - // the last one is the only one we care about. + if (is_command) { + ods << '\\' << from_ascii(layout_->latexname()); + // we have to provide all the optional arguments here, even though + // the last one is the only one we care about. + // Separate handling of optional argument inset. + if (layout_->optargs != 0 || layout_->reqargs != 0) + latexArgInsets(*owner_, ods, features.runparams(), + layout_->reqargs, layout_->optargs); + else + ods << from_ascii(layout_->latexparam()); + } + docstring::size_type const length = ods.str().length(); + // this will output "{" at the beginning, but not at the end owner_->latex(bp, f, ods, tr, features.runparams(), 0, -1, true); - docstring const d = ods.str(); - if (!d.empty()) { - // this will have "{" at the beginning, but not at the end - string const content = to_utf8(d); - string const cmd = layout_->latexname(); - features.addPreambleSnippet("\\" + cmd + content + "}"); + if (ods.str().length() > length) { + if (is_command) + ods << '}'; + string const snippet = to_utf8(ods.str()); + features.addPreambleSnippet(snippet); } } @@ -2328,12 +2400,16 @@ void Paragraph::latex(BufferParams const & bparams, open_font = false; } + string const running_lang = runparams.use_polyglossia ? + running_font.language()->polyglossia() : running_font.language()->babel(); // close babel's font environment before opening CJK. - if (!running_font.language()->babel().empty() && + string const lang_end_command = runparams.use_polyglossia ? + "\\end{$$lang}" : lyxrc.language_command_end; + if (!running_lang.empty() && font.language()->encoding()->package() == Encoding::CJK) { - string end_tag = subst(lyxrc.language_command_end, + string end_tag = subst(lang_end_command, "$$lang", - running_font.language()->babel()); + running_lang); os << from_ascii(end_tag); column += end_tag.length(); } @@ -2471,7 +2547,7 @@ void Paragraph::latex(BufferParams const & bparams, if (allowcust && d->endTeXParParams(bparams, os, texrow, runparams) && runparams.encoding != prev_encoding) { runparams.encoding = prev_encoding; - if (!bparams.useXetex) + if (!runparams.isFullUnicode()) os << setEncoding(prev_encoding->iconvName()); } @@ -2685,13 +2761,9 @@ docstring Paragraph::simpleLyXHTMLOnePar(Buffer const & buf, Inset const * inset = getInset(i); if (inset) { - InsetCommand const * ic = inset->asInsetCommand(); - InsetLayout const & il = inset->getLayout(); - InsetMath const * im = inset->asInsetMath(); - if (!runparams.for_toc - || im || il.isInToc() || (ic && ic->isInToc())) { + if (!runparams.for_toc || inset->isInToc()) { OutputParams np = runparams; - if (!il.htmlisblock()) + if (!inset->getLayout().htmlisblock()) np.html_in_par = true; retval += inset->xhtml(xs, np); } @@ -2718,7 +2790,7 @@ docstring Paragraph::simpleLyXHTMLOnePar(Buffer const & buf, // We don't want to escape the entities. Note that // it is safe to do this, since str can otherwise // only be "-". E.g., it can't be "<". - xs << XHTMLStream::NextRaw() << str; + xs << XHTMLStream::ESCAPE_NONE << str; } else xs << c; } @@ -2762,17 +2834,24 @@ bool Paragraph::isWordSeparator(pos_type pos) const char_type const c = d->text_[pos]; // We want to pass the ' and escape chars to the spellchecker static docstring const quote = from_utf8(lyxrc.spellchecker_esc_chars + '\''); - return (!isLetterChar(c) && !isDigit(c) && !contains(quote, c)) + return (!isLetterChar(c) && !isDigitASCII(c) && !contains(quote, c)) || pos == size(); } +bool Paragraph::isSameSpellRange(pos_type pos1, pos_type pos2) const +{ + return pos1 == pos2 + || d->speller_state_.getRange(pos1) == d->speller_state_.getRange(pos2); +} + + bool Paragraph::isChar(pos_type pos) const { if (Inset const * inset = getInset(pos)) return inset->isChar(); char_type const c = d->text_[pos]; - return !isLetterChar(c) && !isDigit(c) && !lyx::isSpace(c); + return !isLetterChar(c) && !isDigitASCII(c) && !lyx::isSpace(c); } @@ -2863,12 +2942,14 @@ docstring Paragraph::asString(pos_type beg, pos_type end, int options) const os << d->params_.labelString() << ' '; for (pos_type i = beg; i < end; ++i) { + if ((options & AS_STR_SKIPDELETE) && isDeleted(i)) + continue; char_type const c = d->text_[i]; if (isPrintable(c) || c == '\t' || (c == '\n' && (options & AS_STR_NEWLINES))) os.put(c); else if (c == META_INSET && (options & AS_STR_INSETS)) { - getInset(i)->tocString(os); + getInset(i)->toString(os); if (getInset(i)->asInsetMath()) os << " "; } @@ -2878,6 +2959,24 @@ docstring Paragraph::asString(pos_type beg, pos_type end, int options) const } +void Paragraph::forToc(docstring & os, size_t maxlen) const +{ + if (!d->params_.labelString().empty()) + os += d->params_.labelString() + ' '; + for (pos_type i = 0; i < size() && os.length() < maxlen; ++i) { + if (isDeleted(i)) + continue; + char_type const c = d->text_[i]; + if (isPrintable(c)) + os += c; + else if (c == '\t' || c == '\n') + os += ' '; + else if (c == META_INSET) + getInset(i)->forToc(os, maxlen); + } +} + + docstring Paragraph::stringify(pos_type beg, pos_type end, int options, OutputParams & runparams) const { odocstringstream os; @@ -3032,7 +3131,7 @@ int Paragraph::checkBiblio(Buffer const & buffer) { // FIXME From JS: // This is getting more and more a mess. ...We really should clean - // up this bibitem issue for 1.6. See also bug 2743. + // up this bibitem issue for 1.6. // Add bibitem insets if necessary if (d->layout_->labeltype != LABEL_BIBLIO) @@ -3058,8 +3157,8 @@ int Paragraph::checkBiblio(Buffer const & buffer) InsetList::iterator end = d->insetlist_.end(); for (; it != end; ++it) if (it->inset->lyxCode() == BIBITEM_CODE - && it->pos > 0) { - InsetBibitem * olditem = static_cast(it->inset); + && it->pos > 0) { + InsetCommand * olditem = it->inset->asInsetCommand(); oldkey = olditem->getParam("key"); oldlabel = olditem->getParam("label"); erasedInsetPosition = it->pos; @@ -3075,8 +3174,7 @@ int Paragraph::checkBiblio(Buffer const & buffer) // There was an InsetBibitem at the beginning and we did have to // erase one. So we give its properties to the beginning inset. if (hasbibitem) { - InsetBibitem * inset = - static_cast(d->insetlist_.begin()->inset); + InsetCommand * inset = d->insetlist_.begin()->inset->asInsetCommand(); if (!oldkey.empty()) inset->setParam("key", oldkey); inset->setParam("label", oldlabel); @@ -3091,7 +3189,7 @@ int Paragraph::checkBiblio(Buffer const & buffer) if (!oldkey.empty()) inset->setParam("key", oldkey); inset->setParam("label", oldlabel); - insertInset(0, static_cast(inset), + insertInset(0, inset, Change(track_changes ? Change::INSERTED : Change::UNCHANGED)); return 1; @@ -3221,36 +3319,44 @@ void Paragraph::changeCase(BufferParams const & bparams, pos_type pos, } -bool Paragraph::find(docstring const & str, bool cs, bool mw, - pos_type pos, bool del) const +int Paragraph::find(docstring const & str, bool cs, bool mw, + pos_type start_pos, bool del) const { + pos_type pos = start_pos; int const strsize = str.length(); int i = 0; pos_type const parsize = d->text_.size(); - for (i = 0; pos + i < parsize; ++i) { - if (i >= strsize) - break; - if (cs && str[i] != d->text_[pos + i]) + for (i = 0; i < strsize && pos < parsize; ++i, ++pos) { + // Ignore ligature break and hyphenation chars while searching + while (pos < parsize - 1 && isInset(pos)) { + const InsetSpecialChar *isc = dynamic_cast(getInset(pos)); + if (isc == 0 + || (isc->kind() != InsetSpecialChar::HYPHENATION + && isc->kind() != InsetSpecialChar::LIGATURE_BREAK)) + break; + pos++; + } + if (cs && str[i] != d->text_[pos]) break; - if (!cs && uppercase(str[i]) != uppercase(d->text_[pos + i])) + if (!cs && uppercase(str[i]) != uppercase(d->text_[pos])) break; - if (!del && isDeleted(pos + i)) + if (!del && isDeleted(pos)) break; } if (i != strsize) - return false; + return 0; // if necessary, check whether string matches word if (mw) { - if (pos > 0 && !isWordSeparator(pos - 1)) - return false; - if (pos + strsize < parsize - && !isWordSeparator(pos + strsize)) - return false; + if (start_pos > 0 && !isWordSeparator(start_pos - 1)) + return 0; + if (pos < parsize + && !isWordSeparator(pos)) + return 0; } - return true; + return pos - start_pos; } @@ -3382,9 +3488,24 @@ void Paragraph::updateWords() } +void Paragraph::Private::appendSkipPosition(SkipPositions & skips, pos_type const pos) const +{ + SkipPositionsIterator begin = skips.begin(); + SkipPositions::iterator end = skips.end(); + if (pos > 0 && begin < end) { + --end; + if (end->last == pos - 1) { + end->last = pos; + return; + } + } + skips.insert(end, FontSpan(pos, pos)); +} + + Language * Paragraph::Private::locateSpellRange( pos_type & from, pos_type & to, - Positions & softbreaks) const + SkipPositions & skips) const { // skip leading white space while (from < to && owner_->isWordSeparator(from)) @@ -3401,7 +3522,9 @@ Language * Paragraph::Private::locateSpellRange( // hop to end of word while (last < to && !owner_->isWordSeparator(last)) { if (owner_->getInset(last)) { - softbreaks.insert(softbreaks.end(), last); + appendSkipPosition(skips, last); + } else if (owner_->isDeleted(last)) { + appendSkipPosition(skips, last); } ++last; } @@ -3409,6 +3532,9 @@ Language * Paragraph::Private::locateSpellRange( while (sameinset && last < to && owner_->isWordSeparator(last)) { if (Inset const * inset = owner_->getInset(last)) sameinset = inset->isChar() && inset->isLetter(); + if (sameinset && owner_->isDeleted(last)) { + appendSkipPosition(skips, last); + } if (sameinset) last++; } @@ -3460,6 +3586,21 @@ bool Paragraph::needsSpellCheck() const } +bool Paragraph::Private::ignoreWord(docstring const & word) const +{ + // Ignore words with digits + // FIXME: make this customizable + // (note that some checkers ignore words with digits by default) + docstring::const_iterator cit = word.begin(); + docstring::const_iterator const end = word.end(); + for (; cit != end; ++cit) { + if (isNumber((*cit))) + return true; + } + return false; +} + + SpellChecker::Result Paragraph::spellCheck(pos_type & from, pos_type & to, WordLangTuple & wl, docstring_list & suggestions, bool do_suggestion, bool check_learned) const @@ -3473,10 +3614,10 @@ SpellChecker::Result Paragraph::spellCheck(pos_type & from, pos_type & to, return result; locateWord(from, to, WHOLE_WORD); - if (from == to || from >= pos_type(d->text_.size())) + if (from == to || from >= size()) return result; - docstring word = asString(from, to, AS_STR_INSETS); + docstring word = asString(from, to, AS_STR_INSETS | AS_STR_SKIPDELETE); Language * lang = d->getSpellLanguage(from); wl = WordLangTuple(word, lang); @@ -3485,11 +3626,24 @@ SpellChecker::Result Paragraph::spellCheck(pos_type & from, pos_type & to, return result; if (needsSpellCheck() || check_learned) { - // Ignore words with digits - // FIXME: make this customizable - // (note that some checkers ignore words with digits by default) - if (!hasDigit(word)) + if (!d->ignoreWord(word)) { + bool const trailing_dot = to < size() && d->text_[to] == '.'; result = speller->check(wl); + if (SpellChecker::misspelled(result) && trailing_dot) { + wl = WordLangTuple(word.append(from_ascii(".")), lang); + result = speller->check(wl); + if (!SpellChecker::misspelled(result)) { + LYXERR(Debug::GUI, "misspelled word is correct with dot: \"" << + word << "\" [" << + from << ".." << to << "]"); + } else { + // spell check with dot appended failed + // restore original word/lang value + word = asString(from, to, AS_STR_INSETS | AS_STR_SKIPDELETE); + wl = WordLangTuple(word, lang); + } + } + } d->setMisspelled(from, to, result); } else { result = d->speller_state_.getState(from); @@ -3513,19 +3667,19 @@ void Paragraph::Private::markMisspelledWords( pos_type const & first, pos_type const & last, SpellChecker::Result result, docstring const & word, - Positions const & softbreaks) + SkipPositions const & skips) { if (!SpellChecker::misspelled(result)) { setMisspelled(first, last, SpellChecker::WORD_OK); return; } - pos_type snext = first; + int snext = first; SpellChecker * speller = theSpellChecker(); // locate and enumerate the error positions int nerrors = speller->numMisspelledWords(); - int numbreaks = 0; - PositionsIterator it = softbreaks.begin(); - PositionsIterator et = softbreaks.end(); + int numskipped = 0; + SkipPositionsIterator it = skips.begin(); + SkipPositionsIterator et = skips.end(); for (int index = 0; index < nerrors; ++index) { int wstart; int wlen = 0; @@ -3533,15 +3687,15 @@ void Paragraph::Private::markMisspelledWords( /// should not happen if speller supports range checks if (!wlen) continue; docstring const misspelled = word.substr(wstart, wlen); - wstart += first + numbreaks; + wstart += first + numskipped; if (snext < wstart) { /// mark the range of correct spelling - numbreaks += countSoftbreaks(it, et, wstart); + numskipped += countSkips(it, et, wstart); setMisspelled(snext, wstart - 1, SpellChecker::WORD_OK); } snext = wstart + wlen; - numbreaks += countSoftbreaks(it, et, snext); + numskipped += countSkips(it, et, snext); /// mark the range of misspelling setMisspelled(wstart, snext, result); LYXERR(Debug::GUI, "misspelled word: \"" << @@ -3568,16 +3722,16 @@ void Paragraph::spellCheck() const // loop until we leave the range for (pos_type first = start; first < endpos; ) { pos_type last = endpos; - Private::Positions softbreaks; - Language * lang = d->locateSpellRange(first, last, softbreaks); + Private::SkipPositions skips; + Language * lang = d->locateSpellRange(first, last, skips); if (first >= endpos) break; // start the spell checker on the unit of meaning - docstring word = asString(first, last, AS_STR_INSETS); + docstring word = asString(first, last, AS_STR_INSETS + AS_STR_SKIPDELETE); WordLangTuple wl = WordLangTuple(word, lang); SpellChecker::Result result = word.size() ? speller->check(wl) : SpellChecker::WORD_OK; - d->markMisspelledWords(first, last, result, word, softbreaks); + d->markMisspelledWords(first, last, result, word, skips); first = ++last; } } else {