diff options
-rw-r--r-- | src/CellBuffer.cxx | 26 | ||||
-rw-r--r-- | src/CellBuffer.h | 14 | ||||
-rw-r--r-- | src/DBCS.cxx | 2 | ||||
-rw-r--r-- | src/DBCS.h | 2 | ||||
-rw-r--r-- | src/Document.cxx | 165 | ||||
-rw-r--r-- | src/Document.h | 19 | ||||
-rw-r--r-- | src/Partitioning.h | 6 | ||||
-rw-r--r-- | src/PositionCache.cxx | 2 | ||||
-rw-r--r-- | src/SplitVector.h | 8 | ||||
-rw-r--r-- | src/UniConversion.cxx | 6 | ||||
-rw-r--r-- | src/UniConversion.h | 20 |
11 files changed, 150 insertions, 120 deletions
diff --git a/src/CellBuffer.cxx b/src/CellBuffer.cxx index 177aa60e8..58ab3b3f4 100644 --- a/src/CellBuffer.cxx +++ b/src/CellBuffer.cxx @@ -35,9 +35,9 @@ public: virtual void InsertLine(Sci::Line line, Sci::Position position, bool lineStart) = 0; virtual void SetLineStart(Sci::Line line, Sci::Position position) = 0; virtual void RemoveLine(Sci::Line line) = 0; - virtual Sci::Line Lines() const = 0; - virtual Sci::Line LineFromPosition(Sci::Position pos) const = 0; - virtual Sci::Position LineStart(Sci::Line line) const = 0; + virtual Sci::Line Lines() const noexcept = 0; + virtual Sci::Line LineFromPosition(Sci::Position pos) const noexcept = 0; + virtual Sci::Position LineStart(Sci::Line line) const noexcept = 0; virtual ~ILineVector() {} }; @@ -84,13 +84,13 @@ public: perLine->RemoveLine(line); } } - Sci::Line Lines() const override { + Sci::Line Lines() const noexcept override { return static_cast<Sci::Line>(starts.Partitions()); } - Sci::Line LineFromPosition(Sci::Position pos) const override { + Sci::Line LineFromPosition(Sci::Position pos) const noexcept override { return static_cast<Sci::Line>(starts.PartitionFromPosition(static_cast<POS>(pos))); } - Sci::Position LineStart(Sci::Line line) const override { + Sci::Position LineStart(Sci::Line line) const noexcept override { return starts.PositionFromPartition(static_cast<POS>(line)); } }; @@ -377,11 +377,11 @@ CellBuffer::CellBuffer(bool hasStyles_, bool largeDocument_) : CellBuffer::~CellBuffer() { } -char CellBuffer::CharAt(Sci::Position position) const { +char CellBuffer::CharAt(Sci::Position position) const noexcept { return substance.ValueAt(position); } -unsigned char CellBuffer::UCharAt(Sci::Position position) const { +unsigned char CellBuffer::UCharAt(Sci::Position position) const noexcept { return static_cast<unsigned char>(substance.ValueAt(position)); } @@ -398,7 +398,7 @@ void CellBuffer::GetCharRange(char *buffer, Sci::Position position, Sci::Positio substance.GetRange(buffer, position, lengthRetrieve); } -char CellBuffer::StyleAt(Sci::Position position) const { +char CellBuffer::StyleAt(Sci::Position position) const noexcept { return hasStyles ? style.ValueAt(position) : 0; } @@ -496,7 +496,7 @@ const char *CellBuffer::DeleteChars(Sci::Position position, Sci::Position delete return data; } -Sci::Position CellBuffer::Length() const { +Sci::Position CellBuffer::Length() const noexcept { return substance.Length(); } @@ -537,11 +537,11 @@ void CellBuffer::SetPerLine(PerLine *pl) { plv->SetPerLine(pl); } -Sci::Line CellBuffer::Lines() const { +Sci::Line CellBuffer::Lines() const noexcept { return plv->Lines(); } -Sci::Position CellBuffer::LineStart(Sci::Line line) const { +Sci::Position CellBuffer::LineStart(Sci::Line line) const noexcept { if (line < 0) return 0; else if (line >= Lines()) @@ -550,7 +550,7 @@ Sci::Position CellBuffer::LineStart(Sci::Line line) const { return plv->LineStart(line); } -Sci::Line CellBuffer::LineFromPosition(Sci::Position pos) const { +Sci::Line CellBuffer::LineFromPosition(Sci::Position pos) const noexcept { return plv->LineFromPosition(pos); } diff --git a/src/CellBuffer.h b/src/CellBuffer.h index 065c73795..20e81def6 100644 --- a/src/CellBuffer.h +++ b/src/CellBuffer.h @@ -134,24 +134,24 @@ public: ~CellBuffer(); /// Retrieving positions outside the range of the buffer works and returns 0 - char CharAt(Sci::Position position) const; - unsigned char UCharAt(Sci::Position position) const; + char CharAt(Sci::Position position) const noexcept; + unsigned char UCharAt(Sci::Position position) const noexcept; void GetCharRange(char *buffer, Sci::Position position, Sci::Position lengthRetrieve) const; - char StyleAt(Sci::Position position) const; + char StyleAt(Sci::Position position) const noexcept; void GetStyleRange(unsigned char *buffer, Sci::Position position, Sci::Position lengthRetrieve) const; const char *BufferPointer(); const char *RangePointer(Sci::Position position, Sci::Position rangeLength); Sci::Position GapPosition() const; - Sci::Position Length() const; + Sci::Position Length() const noexcept; void Allocate(Sci::Position newSize); int GetLineEndTypes() const { return utf8LineEnds; } void SetLineEndTypes(int utf8LineEnds_); bool ContainsLineEnd(const char *s, Sci::Position length) const; void SetPerLine(PerLine *pl); - Sci::Line Lines() const; - Sci::Position LineStart(Sci::Line line) const; - Sci::Line LineFromPosition(Sci::Position pos) const; + Sci::Line Lines() const noexcept; + Sci::Position LineStart(Sci::Line line) const noexcept; + Sci::Line LineFromPosition(Sci::Position pos) const noexcept; void InsertLine(Sci::Line line, Sci::Position position, bool lineStart); void RemoveLine(Sci::Line line); const char *InsertString(Sci::Position position, const char *s, Sci::Position insertLength, bool &startSequence); diff --git a/src/DBCS.cxx b/src/DBCS.cxx index 0fb7ef0af..644cad04d 100644 --- a/src/DBCS.cxx +++ b/src/DBCS.cxx @@ -11,7 +11,7 @@ using namespace Scintilla; namespace Scintilla { -bool DBCSIsLeadByte(int codePage, char ch) { +bool DBCSIsLeadByte(int codePage, char ch) noexcept { // Byte ranges found in Wikipedia articles with relevant search strings in each case const unsigned char uch = static_cast<unsigned char>(ch); switch (codePage) { diff --git a/src/DBCS.h b/src/DBCS.h index 531437f45..ff3f9f22f 100644 --- a/src/DBCS.h +++ b/src/DBCS.h @@ -10,7 +10,7 @@ namespace Scintilla { -bool DBCSIsLeadByte(int codePage, char ch); +bool DBCSIsLeadByte(int codePage, char ch) noexcept; } diff --git a/src/Document.cxx b/src/Document.cxx index b0efee5e7..127b6872a 100644 --- a/src/Document.cxx +++ b/src/Document.cxx @@ -387,7 +387,7 @@ Sci_Position SCI_METHOD Document::LineFromPosition(Sci_Position pos) const { return cb.LineFromPosition(pos); } -Sci::Line Document::SciLineFromPosition(Sci::Position pos) const { +Sci::Line Document::SciLineFromPosition(Sci::Position pos) const noexcept { // Avoids casting in callers for this very common function return cb.LineFromPosition(pos); } @@ -582,13 +582,13 @@ int Document::LenChar(Sci::Position pos) { else return widthCharBytes; } else if (dbcsCodePage) { - return IsDBCSLeadByte(cb.CharAt(pos)) ? 2 : 1; + return IsDBCSLeadByteNoExcept(cb.CharAt(pos)) ? 2 : 1; } else { return 1; } } -bool Document::InGoodUTF8(Sci::Position pos, Sci::Position &start, Sci::Position &end) const { +bool Document::InGoodUTF8(Sci::Position pos, Sci::Position &start, Sci::Position &end) const noexcept { Sci::Position trail = pos; while ((trail>0) && (pos-trail < UTF8MaxBytes) && UTF8IsTrailByte(cb.UCharAt(trail-1))) trail--; @@ -661,12 +661,12 @@ Sci::Position Document::MovePositionOutsideChar(Sci::Position pos, Sci::Position // Step back until a non-lead-byte is found. Sci::Position posCheck = pos; - while ((posCheck > posStartLine) && IsDBCSLeadByte(cb.CharAt(posCheck-1))) + while ((posCheck > posStartLine) && IsDBCSLeadByteNoExcept(cb.CharAt(posCheck-1))) posCheck--; // Check from known start of character. while (posCheck < pos) { - const int mbsize = IsDBCSLeadByte(cb.CharAt(posCheck)) ? 2 : 1; + const int mbsize = IsDBCSLeadByteNoExcept(cb.CharAt(posCheck)) ? 2 : 1; if (posCheck + mbsize == pos) { return pos; } else if (posCheck + mbsize > pos) { @@ -687,13 +687,13 @@ Sci::Position Document::MovePositionOutsideChar(Sci::Position pos, Sci::Position // NextPosition moves between valid positions - it can not handle a position in the middle of a // multi-byte character. It is used to iterate through text more efficiently than MovePositionOutsideChar. // A \r\n pair is treated as two characters. -Sci::Position Document::NextPosition(Sci::Position pos, int moveDir) const { +Sci::Position Document::NextPosition(Sci::Position pos, int moveDir) const noexcept { // If out of range, just return minimum/maximum value. const int increment = (moveDir > 0) ? 1 : -1; if (pos + increment <= 0) return 0; - if (pos + increment >= Length()) - return Length(); + if (pos + increment >= cb.Length()) + return cb.Length(); if (dbcsCodePage) { if (SC_CP_UTF8 == dbcsCodePage) { @@ -731,25 +731,25 @@ Sci::Position Document::NextPosition(Sci::Position pos, int moveDir) const { } } else { if (moveDir > 0) { - const int mbsize = IsDBCSLeadByte(cb.CharAt(pos)) ? 2 : 1; + const int mbsize = IsDBCSLeadByteNoExcept(cb.CharAt(pos)) ? 2 : 1; pos += mbsize; - if (pos > Length()) - pos = Length(); + if (pos > cb.Length()) + pos = cb.Length(); } else { // Anchor DBCS calculations at start of line because start of line can // not be a DBCS trail byte. - const Sci::Position posStartLine = LineStart(LineFromPosition(pos)); + const Sci::Position posStartLine = cb.LineStart(cb.LineFromPosition(pos)); // See http://msdn.microsoft.com/en-us/library/cc194792%28v=MSDN.10%29.aspx // http://msdn.microsoft.com/en-us/library/cc194790.aspx if ((pos - 1) <= posStartLine) { return pos - 1; - } else if (IsDBCSLeadByte(cb.CharAt(pos - 1))) { + } else if (IsDBCSLeadByteNoExcept(cb.CharAt(pos - 1))) { // Must actually be trail byte return pos - 2; } else { // Otherwise, step back until a non-lead-byte is found. Sci::Position posTemp = pos - 1; - while (posStartLine <= --posTemp && IsDBCSLeadByte(cb.CharAt(posTemp))) + while (posStartLine <= --posTemp && IsDBCSLeadByteNoExcept(cb.CharAt(posTemp))) ; // Now posTemp+1 must point to the beginning of a character, // so figure out whether we went back an even or an odd @@ -765,7 +765,7 @@ Sci::Position Document::NextPosition(Sci::Position pos, int moveDir) const { return pos; } -bool Document::NextCharacter(Sci::Position &pos, int moveDir) const { +bool Document::NextCharacter(Sci::Position &pos, int moveDir) const noexcept { // Returns true if pos changed Sci::Position posNext = NextPosition(pos, moveDir); if (posNext == pos) { @@ -798,7 +798,7 @@ Document::CharacterExtracted Document::CharacterAfter(Sci::Position position) co return CharacterExtracted(UnicodeFromUTF8(charBytes), utf8status & UTF8MaskWidth); } } else { - if (IsDBCSLeadByte(leadByte) && ((position + 1) < Length())) { + if (IsDBCSLeadByteNoExcept(leadByte) && ((position + 1) < Length())) { return CharacterExtracted::DBCS(leadByte, cb.UCharAt(position + 1)); } else { return CharacterExtracted(leadByte, 1); @@ -912,7 +912,7 @@ int SCI_METHOD Document::GetCharacterAndWidth(Sci_Position position, Sci_Positio } } } else { - if (IsDBCSLeadByte(leadByte)) { + if (IsDBCSLeadByteNoExcept(leadByte)) { bytesInCharacter = 2; character = (leadByte << 8) | cb.UCharAt(position+1); } else { @@ -933,6 +933,12 @@ int SCI_METHOD Document::CodePage() const { } bool SCI_METHOD Document::IsDBCSLeadByte(char ch) const { + // Used by lexers so must match IDocument method exactly + return IsDBCSLeadByteNoExcept(ch); +} + +bool Document::IsDBCSLeadByteNoExcept(char ch) const noexcept { + // Used inside core Scintilla // Byte ranges found in Wikipedia articles with relevant search strings in each case const unsigned char uch = static_cast<unsigned char>(ch); switch (dbcsCodePage) { @@ -960,7 +966,7 @@ bool SCI_METHOD Document::IsDBCSLeadByte(char ch) const { return false; } -static inline bool IsSpaceOrTab(int ch) { +static inline bool IsSpaceOrTab(int ch) noexcept { return ch == ' ' || ch == '\t'; } @@ -996,7 +1002,7 @@ int Document::SafeSegment(const char *text, int length, int lengthSegment) const if (dbcsCodePage == SC_CP_UTF8) { j += UTF8BytesOfLead[ch]; } else if (dbcsCodePage) { - j += IsDBCSLeadByte(ch) ? 2 : 1; + j += IsDBCSLeadByteNoExcept(ch) ? 2 : 1; } else { j++; } @@ -1306,7 +1312,7 @@ void Document::DelCharBack(Sci::Position pos) { } } -static Sci::Position NextTab(Sci::Position pos, Sci::Position tabSize) { +static Sci::Position NextTab(Sci::Position pos, Sci::Position tabSize) noexcept { return ((pos / tabSize) + 1) * tabSize; } @@ -1818,7 +1824,7 @@ void Document::SetCaseFolder(CaseFolder *pcf_) { pcf.reset(pcf_); } -Document::CharacterExtracted Document::ExtractCharacter(Sci::Position position) const { +Document::CharacterExtracted Document::ExtractCharacter(Sci::Position position) const noexcept { const unsigned char leadByte = cb.UCharAt(position); if (UTF8IsAscii(leadByte)) { // Common case: ASCII character @@ -1894,8 +1900,8 @@ Sci::Position Document::FindText(Sci::Position minPos, Sci::Position maxPos, con std::vector<char> searchThing((lengthFind+1) * UTF8MaxBytes * maxFoldingExpansion + 1); const size_t lenSearch = pcf->Fold(&searchThing[0], searchThing.size(), search, lengthFind); - char bytes[UTF8MaxBytes + 1]; - char folded[UTF8MaxBytes * maxFoldingExpansion + 1]; + char bytes[UTF8MaxBytes + 1] = ""; + char folded[UTF8MaxBytes * maxFoldingExpansion + 1] = ""; while (forward ? (pos < endPos) : (pos >= endPos)) { int widthFirstCharacter = 0; Sci::Position posIndexDocument = pos; @@ -1955,7 +1961,7 @@ Sci::Position Document::FindText(Sci::Position minPos, Sci::Position maxPos, con (indexSearch < lenSearch)) { char bytes[maxBytesCharacter + 1]; bytes[0] = cb.CharAt(pos + indexDocument); - const Sci::Position widthChar = IsDBCSLeadByte(bytes[0]) ? 2 : 1; + const Sci::Position widthChar = IsDBCSLeadByteNoExcept(bytes[0]) ? 2 : 1; if (widthChar == 2) bytes[1] = cb.CharAt(pos + indexDocument + 1); if ((pos + indexDocument + widthChar) > limitPos) @@ -2295,7 +2301,7 @@ void Document::NotifyModified(DocModification mh) { } // Used for word part navigation. -static bool IsASCIIPunctuationCharacter(unsigned int ch) { +static bool IsASCIIPunctuationCharacter(unsigned int ch) noexcept { switch (ch) { case '!': case '"': @@ -2429,7 +2435,7 @@ Sci::Position Document::WordPartRight(Sci::Position pos) const { return pos; } -static bool IsLineEndChar(char c) { +static bool IsLineEndChar(char c) noexcept { return (c == '\n' || c == '\r'); } @@ -2446,7 +2452,7 @@ Sci::Position Document::ExtendStyleRange(Sci::Position pos, int delta, bool sing return pos; } -static char BraceOpposite(char ch) { +static char BraceOpposite(char ch) noexcept { switch (ch) { case '(': return ')'; @@ -2506,9 +2512,11 @@ Sci::Position Document::BraceMatch(Sci::Position position, Sci::Position /*maxRe class BuiltinRegex : public RegexSearchBase { public: explicit BuiltinRegex(CharClassify *charClassTable) : search(charClassTable) {} - - ~BuiltinRegex() override { - } + BuiltinRegex(const BuiltinRegex &) = delete; + BuiltinRegex(BuiltinRegex &&) = delete; + BuiltinRegex &operator=(const BuiltinRegex &) = delete; + BuiltinRegex &operator=(BuiltinRegex &&) = delete; + ~BuiltinRegex() override = default; Sci::Position FindText(Document *doc, Sci::Position minPos, Sci::Position maxPos, const char *s, bool caseSensitive, bool word, bool wordStart, int flags, @@ -2569,14 +2577,18 @@ class DocumentIndexer : public CharacterIndexer { Document *pdoc; Sci::Position end; public: - DocumentIndexer(Document *pdoc_, Sci::Position end_) : + DocumentIndexer(Document *pdoc_, Sci::Position end_) noexcept : pdoc(pdoc_), end(end_) { } - ~DocumentIndexer() override { - } + DocumentIndexer(const DocumentIndexer &) = delete; + DocumentIndexer(DocumentIndexer &&) = delete; + DocumentIndexer &operator=(const DocumentIndexer &) = delete; + DocumentIndexer &operator=(DocumentIndexer &&) = delete; - char CharAt(Sci::Position index) const override { + ~DocumentIndexer() override = default; + + char CharAt(Sci::Position index) const noexcept override { if (index < 0 || index >= end) return 0; else @@ -2596,45 +2608,53 @@ public: const Document *doc; Sci::Position position; - ByteIterator(const Document *doc_ = 0, Sci::Position position_ = 0) : doc(doc_), position(position_) { + + ByteIterator(const Document *doc_=nullptr, Sci::Position position_=0) noexcept : + doc(doc_), position(position_) { } ByteIterator(const ByteIterator &other) noexcept { doc = other.doc; position = other.position; } - ByteIterator &operator=(const ByteIterator &other) { + ByteIterator(ByteIterator &&other) noexcept { + doc = other.doc; + position = other.position; + } + ByteIterator &operator=(const ByteIterator &other) noexcept { if (this != &other) { doc = other.doc; position = other.position; } return *this; } - char operator*() const { + ByteIterator &operator=(ByteIterator &&) noexcept = default; + ~ByteIterator() = default; + char operator*() const noexcept { return doc->CharAt(position); } - ByteIterator &operator++() { + ByteIterator &operator++() noexcept { position++; return *this; } - ByteIterator operator++(int) { + ByteIterator operator++(int) noexcept { ByteIterator retVal(*this); position++; return retVal; } - ByteIterator &operator--() { + ByteIterator &operator--() noexcept { position--; return *this; } - bool operator==(const ByteIterator &other) const { + bool operator==(const ByteIterator &other) const noexcept { return doc == other.doc && position == other.position; } - bool operator!=(const ByteIterator &other) const { + bool operator!=(const ByteIterator &other) const noexcept { return doc != other.doc || position != other.position; } - Sci::Position Pos() const { + Sci::Position Pos() const noexcept { return position; } - Sci::Position PosRoundUp() const { + Sci::Position PosRoundUp() const noexcept { return position; } }; @@ -2671,15 +2691,15 @@ public: typedef wchar_t* pointer; typedef wchar_t& reference; - UTF8Iterator(const Document *doc_ = 0, Sci::Position position_ = 0) : - doc(doc_), position(position_), characterIndex(0), lenBytes(0), lenCharacters(0) { + UTF8Iterator(const Document *doc_=nullptr, Sci::Position position_=0) noexcept : + doc(doc_), position(position_), characterIndex(0), lenBytes(0), lenCharacters(0), buffered{} { buffered[0] = 0; buffered[1] = 0; if (doc) { ReadCharacter(); } } - UTF8Iterator(const UTF8Iterator &other) { + UTF8Iterator(const UTF8Iterator &other) noexcept : buffered{} { doc = other.doc; position = other.position; characterIndex = other.characterIndex; @@ -2688,7 +2708,8 @@ public: buffered[0] = other.buffered[0]; buffered[1] = other.buffered[1]; } - UTF8Iterator &operator=(const UTF8Iterator &other) { + UTF8Iterator(UTF8Iterator &&other) noexcept = default; + UTF8Iterator &operator=(const UTF8Iterator &other) noexcept { if (this != &other) { doc = other.doc; position = other.position; @@ -2700,11 +2721,13 @@ public: } return *this; } - wchar_t operator*() const { + UTF8Iterator &operator=(UTF8Iterator &&) noexcept = default; + ~UTF8Iterator() = default; + wchar_t operator*() const noexcept { assert(lenCharacters != 0); return buffered[characterIndex]; } - UTF8Iterator &operator++() { + UTF8Iterator &operator++() noexcept { if ((characterIndex + 1) < (lenCharacters)) { characterIndex++; } else { @@ -2714,7 +2737,7 @@ public: } return *this; } - UTF8Iterator operator++(int) { + UTF8Iterator operator++(int) noexcept { UTF8Iterator retVal(*this); if ((characterIndex + 1) < (lenCharacters)) { characterIndex++; @@ -2725,7 +2748,7 @@ public: } return retVal; } - UTF8Iterator &operator--() { + UTF8Iterator &operator--() noexcept { if (characterIndex) { characterIndex--; } else { @@ -2735,29 +2758,29 @@ public: } return *this; } - bool operator==(const UTF8Iterator &other) const { + bool operator==(const UTF8Iterator &other) const noexcept { // Only test the determining fields, not the character widths and values derived from this return doc == other.doc && position == other.position && characterIndex == other.characterIndex; } - bool operator!=(const UTF8Iterator &other) const { + bool operator!=(const UTF8Iterator &other) const noexcept { // Only test the determining fields, not the character widths and values derived from this return doc != other.doc || position != other.position || characterIndex != other.characterIndex; } - Sci::Position Pos() const { + Sci::Position Pos() const noexcept { return position; } - Sci::Position PosRoundUp() const { + Sci::Position PosRoundUp() const noexcept { if (characterIndex) return position + lenBytes; // Force to end of character else return position; } private: - void ReadCharacter() { + void ReadCharacter() noexcept { const Document::CharacterExtracted charExtracted = doc->ExtractCharacter(position); lenBytes = charExtracted.widthBytes; if (charExtracted.character == unicodeReplacementChar) { @@ -2783,46 +2806,50 @@ public: typedef wchar_t* pointer; typedef wchar_t& reference; - UTF8Iterator(const Document *doc_=0, Sci::Position position_=0) : doc(doc_), position(position_) { + UTF8Iterator(const Document *doc_=nullptr, Sci::Position position_=0) noexcept : + doc(doc_), position(position_) { } UTF8Iterator(const UTF8Iterator &other) noexcept { doc = other.doc; position = other.position; } - UTF8Iterator &operator=(const UTF8Iterator &other) { + UTF8Iterator(UTF8Iterator &&other) noexcept = default; + UTF8Iterator &operator=(const UTF8Iterator &other) noexcept { if (this != &other) { doc = other.doc; position = other.position; } return *this; } - wchar_t operator*() const { - Document::CharacterExtracted charExtracted = doc->ExtractCharacter(position); + UTF8Iterator &operator=(UTF8Iterator &&) noexcept = default; + ~UTF8Iterator() = default; + wchar_t operator*() const noexcept { + const Document::CharacterExtracted charExtracted = doc->ExtractCharacter(position); return charExtracted.character; } - UTF8Iterator &operator++() { + UTF8Iterator &operator++() noexcept { position = doc->NextPosition(position, 1); return *this; } - UTF8Iterator operator++(int) { + UTF8Iterator operator++(int) noexcept { UTF8Iterator retVal(*this); position = doc->NextPosition(position, 1); return retVal; } - UTF8Iterator &operator--() { + UTF8Iterator &operator--() noexcept { position = doc->NextPosition(position, -1); return *this; } - bool operator==(const UTF8Iterator &other) const { + bool operator==(const UTF8Iterator &other) const noexcept { return doc == other.doc && position == other.position; } - bool operator!=(const UTF8Iterator &other) const { + bool operator!=(const UTF8Iterator &other) const noexcept { return doc != other.doc || position != other.position; } - Sci::Position Pos() const { + Sci::Position Pos() const noexcept { return position; } - Sci::Position PosRoundUp() const { + Sci::Position PosRoundUp() const noexcept { return position; } }; @@ -2893,7 +2920,7 @@ bool MatchOnLines(const Document *doc, const Regex ®exp, const RESearchRange return matched; } -Sci::Position Cxx11RegexFindText(Document *doc, Sci::Position minPos, Sci::Position maxPos, const char *s, +Sci::Position Cxx11RegexFindText(const Document *doc, Sci::Position minPos, Sci::Position maxPos, const char *s, bool caseSensitive, Sci::Position *length, RESearch &search) { const RESearchRange resr(doc, minPos, maxPos); try { diff --git a/src/Document.h b/src/Document.h index 387af74f0..48363d92e 100644 --- a/src/Document.h +++ b/src/Document.h @@ -240,11 +240,11 @@ public: struct CharacterExtracted { unsigned int character; unsigned int widthBytes; - CharacterExtracted(unsigned int character_, unsigned int widthBytes_) : + CharacterExtracted(unsigned int character_, unsigned int widthBytes_) noexcept : character(character_), widthBytes(widthBytes_) { } // For DBCS characters turn 2 bytes into an int - static CharacterExtracted DBCS(unsigned char lead, unsigned char trail) { + static CharacterExtracted DBCS(unsigned char lead, unsigned char trail) noexcept { return CharacterExtracted((lead << 8) | trail, 2); } }; @@ -266,7 +266,9 @@ public: Document(int options); // Deleted so Document objects can not be copied. Document(const Document &) = delete; + Document(Document &&) = delete; void operator=(const Document &) = delete; + Document &operator=(Document &&) = delete; ~Document() override; int AddRef(); @@ -290,15 +292,15 @@ public: void SCI_METHOD SetErrorStatus(int status) override; Sci_Position SCI_METHOD LineFromPosition(Sci_Position pos) const override; - Sci::Line SciLineFromPosition(Sci::Position pos) const; // Avoids casting LineFromPosition + Sci::Line SciLineFromPosition(Sci::Position pos) const noexcept; // Avoids casting LineFromPosition Sci::Position ClampPositionIntoDocument(Sci::Position pos) const; bool ContainsLineEnd(const char *s, Sci::Position length) const { return cb.ContainsLineEnd(s, length); } bool IsCrLf(Sci::Position pos) const; int LenChar(Sci::Position pos); - bool InGoodUTF8(Sci::Position pos, Sci::Position &start, Sci::Position &end) const; + bool InGoodUTF8(Sci::Position pos, Sci::Position &start, Sci::Position &end) const noexcept; Sci::Position MovePositionOutsideChar(Sci::Position pos, Sci::Position moveDir, bool checkLineEnd=true) const; - Sci::Position NextPosition(Sci::Position pos, int moveDir) const; - bool NextCharacter(Sci::Position &pos, int moveDir) const; // Returns true if pos changed + Sci::Position NextPosition(Sci::Position pos, int moveDir) const noexcept; + bool NextCharacter(Sci::Position &pos, int moveDir) const noexcept; // Returns true if pos changed Document::CharacterExtracted CharacterAfter(Sci::Position position) const; Document::CharacterExtracted CharacterBefore(Sci::Position position) const; Sci_Position SCI_METHOD GetRelativePosition(Sci_Position positionStart, Sci_Position characterOffset) const override; @@ -306,6 +308,7 @@ public: int SCI_METHOD GetCharacterAndWidth(Sci_Position position, Sci_Position *pWidth) const override; int SCI_METHOD CodePage() const override; bool SCI_METHOD IsDBCSLeadByte(char ch) const override; + bool IsDBCSLeadByteNoExcept(char ch) const noexcept; int SafeSegment(const char *text, int length, int lengthSegment) const; EncodingFamily CodePageFamily() const; @@ -359,7 +362,7 @@ public: void DelChar(Sci::Position pos); void DelCharBack(Sci::Position pos); - char CharAt(Sci::Position position) const { return cb.CharAt(position); } + char CharAt(Sci::Position position) const noexcept { return cb.CharAt(position); } void SCI_METHOD GetCharRange(char *buffer, Sci_Position position, Sci_Position lengthRetrieve) const override { cb.GetCharRange(buffer, position, lengthRetrieve); } @@ -397,7 +400,7 @@ public: Sci_Position SCI_METHOD Length() const override { return cb.Length(); } void Allocate(Sci::Position newSize) { cb.Allocate(newSize); } - CharacterExtracted ExtractCharacter(Sci::Position position) const; + CharacterExtracted ExtractCharacter(Sci::Position position) const noexcept; bool IsWordStartAt(Sci::Position pos) const; bool IsWordEndAt(Sci::Position pos) const; diff --git a/src/Partitioning.h b/src/Partitioning.h index d1887e325..9237df0fa 100644 --- a/src/Partitioning.h +++ b/src/Partitioning.h @@ -102,7 +102,7 @@ public: ~Partitioning() { } - T Partitions() const { + T Partitions() const noexcept { return static_cast<T>(body->Length())-1; } @@ -154,7 +154,7 @@ public: body->Delete(partition); } - T PositionFromPartition(T partition) const { + T PositionFromPartition(T partition) const noexcept { PLATFORM_ASSERT(partition >= 0); PLATFORM_ASSERT(partition < body->Length()); const ptrdiff_t lengthBody = body->Length(); @@ -168,7 +168,7 @@ public: } /// Return value in range [0 .. Partitions() - 1] even for arguments outside interval - T PartitionFromPosition(T pos) const { + T PartitionFromPosition(T pos) const noexcept { if (body->Length() <= 1) return 0; if (pos >= (PositionFromPartition(Partitions()))) diff --git a/src/PositionCache.cxx b/src/PositionCache.cxx index 20a2ddda3..0af487a1d 100644 --- a/src/PositionCache.cxx +++ b/src/PositionCache.cxx @@ -497,7 +497,7 @@ TextSegment BreakFinder::Next() { charWidth = UTF8DrawBytes(reinterpret_cast<unsigned char *>(&ll->chars[nextBreak]), static_cast<int>(lineRange.end - nextBreak)); else if (encodingFamily == efDBCS) - charWidth = pdoc->IsDBCSLeadByte(ll->chars[nextBreak]) ? 2 : 1; + charWidth = pdoc->IsDBCSLeadByteNoExcept(ll->chars[nextBreak]) ? 2 : 1; const Representation *repr = preprs->RepresentationFromCharacter(&ll->chars[nextBreak], charWidth); if (((nextBreak > 0) && (ll->styles[nextBreak] != ll->styles[nextBreak - 1])) || repr || diff --git a/src/SplitVector.h b/src/SplitVector.h index 3fb595eef..40061c955 100644 --- a/src/SplitVector.h +++ b/src/SplitVector.h @@ -104,7 +104,7 @@ public: /// Retrieve the element at a particular position. /// Retrieving positions outside the range of the buffer returns empty or 0. - const T& ValueAt(ptrdiff_t position) const { + const T& ValueAt(ptrdiff_t position) const noexcept { if (position < part1Length) { if (position < 0) { return empty; @@ -144,7 +144,7 @@ public: /// Retrieve the element at a particular position. /// The position must be within bounds or an assertion is triggered. - const T &operator[](ptrdiff_t position) const { + const T &operator[](ptrdiff_t position) const noexcept { PLATFORM_ASSERT(position >= 0 && position < lengthBody); if (position < part1Length) { return body[position]; @@ -156,7 +156,7 @@ public: /// Retrieve reference to the element at a particular position. /// This, instead of the const variant, can be used to mutate in-place. /// The position must be within bounds or an assertion is triggered. - T &operator[](ptrdiff_t position) { + T &operator[](ptrdiff_t position) noexcept { PLATFORM_ASSERT(position >= 0 && position < lengthBody); if (position < part1Length) { return body[position]; @@ -166,7 +166,7 @@ public: } /// Retrieve the length of the buffer. - ptrdiff_t Length() const { + ptrdiff_t Length() const noexcept { return lengthBody; } diff --git a/src/UniConversion.cxx b/src/UniConversion.cxx index 18c1cd521..fb50b9277 100644 --- a/src/UniConversion.cxx +++ b/src/UniConversion.cxx @@ -218,7 +218,7 @@ size_t UTF32FromUTF8(const char *s, size_t len, unsigned int *tbuf, size_t tlen) return ui; } -unsigned int UTF16FromUTF32Character(unsigned int val, wchar_t *tbuf) { +unsigned int UTF16FromUTF32Character(unsigned int val, wchar_t *tbuf) noexcept { if (val < SUPPLEMENTAL_PLANE_FIRST) { tbuf[0] = static_cast<wchar_t>(val); return 1; @@ -254,7 +254,7 @@ const unsigned char UTF8BytesOfLead[256] = { // the non-characters *FFFE, *FFFF and FDD0 .. FDEF return 3 or 4 as they can be // reasonably treated as code points in some circumstances. They will, however, // not have associated glyphs. -int UTF8Classify(const unsigned char *us, int len) { +int UTF8Classify(const unsigned char *us, int len) noexcept { // For the rules: http://www.cl.cam.ac.uk/~mgk25/unicode.html#utf-8 if (us[0] < 0x80) { // ASCII @@ -325,7 +325,7 @@ int UTF8Classify(const unsigned char *us, int len) { return UTF8MaskInvalid | 1; } -int UTF8DrawBytes(const unsigned char *us, int len) { +int UTF8DrawBytes(const unsigned char *us, int len) noexcept { const int utf8StatusNext = UTF8Classify(us, len); return (utf8StatusNext & UTF8MaskInvalid) ? 1 : (utf8StatusNext & UTF8MaskWidth); } diff --git a/src/UniConversion.h b/src/UniConversion.h index 98bcd0329..bece53f4d 100644 --- a/src/UniConversion.h +++ b/src/UniConversion.h @@ -20,12 +20,12 @@ void UTF8FromUTF32Character(int uch, char *putf); size_t UTF16Length(const char *s, size_t len); size_t UTF16FromUTF8(const char *s, size_t len, wchar_t *tbuf, size_t tlen); size_t UTF32FromUTF8(const char *s, size_t len, unsigned int *tbuf, size_t tlen); -unsigned int UTF16FromUTF32Character(unsigned int val, wchar_t *tbuf); +unsigned int UTF16FromUTF32Character(unsigned int val, wchar_t *tbuf) noexcept; std::string FixInvalidUTF8(const std::string &text); extern const unsigned char UTF8BytesOfLead[256]; -inline int UnicodeFromUTF8(const unsigned char *us) { +inline int UnicodeFromUTF8(const unsigned char *us) noexcept { switch (UTF8BytesOfLead[us[0]]) { case 1: return us[0]; @@ -38,31 +38,31 @@ inline int UnicodeFromUTF8(const unsigned char *us) { } } -inline bool UTF8IsTrailByte(unsigned char ch) { +inline bool UTF8IsTrailByte(unsigned char ch) noexcept { return (ch >= 0x80) && (ch < 0xc0); } -inline bool UTF8IsAscii(int ch) { +inline bool UTF8IsAscii(int ch) noexcept { return ch < 0x80; } enum { UTF8MaskWidth=0x7, UTF8MaskInvalid=0x8 }; -int UTF8Classify(const unsigned char *us, int len); +int UTF8Classify(const unsigned char *us, int len) noexcept; // Similar to UTF8Classify but returns a length of 1 for invalid bytes // instead of setting the invalid flag -int UTF8DrawBytes(const unsigned char *us, int len); +int UTF8DrawBytes(const unsigned char *us, int len) noexcept; // Line separator is U+2028 \xe2\x80\xa8 // Paragraph separator is U+2029 \xe2\x80\xa9 const int UTF8SeparatorLength = 3; -inline bool UTF8IsSeparator(const unsigned char *us) { +inline bool UTF8IsSeparator(const unsigned char *us) noexcept { return (us[0] == 0xe2) && (us[1] == 0x80) && ((us[2] == 0xa8) || (us[2] == 0xa9)); } // NEL is U+0085 \xc2\x85 const int UTF8NELLength = 2; -inline bool UTF8IsNEL(const unsigned char *us) { +inline bool UTF8IsNEL(const unsigned char *us) noexcept { return (us[0] == 0xc2) && (us[1] == 0x85); } @@ -72,11 +72,11 @@ enum { SURROGATE_TRAIL_FIRST = 0xDC00 }; enum { SURROGATE_TRAIL_LAST = 0xDFFF }; enum { SUPPLEMENTAL_PLANE_FIRST = 0x10000 }; -inline unsigned int UTF16CharLength(wchar_t uch) { +inline unsigned int UTF16CharLength(wchar_t uch) noexcept { return ((uch >= SURROGATE_LEAD_FIRST) && (uch <= SURROGATE_LEAD_LAST)) ? 2 : 1; } -inline unsigned int UTF16LengthFromUTF8ByteCount(unsigned int byteCount) { +inline unsigned int UTF16LengthFromUTF8ByteCount(unsigned int byteCount) noexcept { return (byteCount < 4) ? 1 : 2; } |