Refactor VT control sequence identification

.github/actions/spell-check/expect/expect.txt

@@ -542,6 +542,7 @@ DECSCUSR
 DECSED
 DECSEL
 DECSET
+DECSLPP
 DECSLRM
 DECSMBV
 DECSMKR
@@ -2546,6 +2547,7 @@ vstudio
 vswhere
 vtapp
 VTE
+VTID
 vtio
 vtmode
 vtpipeterm

src/terminal/adapter/DispatchTypes.hpp

@@ -3,6 +3,94 @@
 
 #pragma once
 
+namespace Microsoft::Console::VirtualTerminal
+{
+    class VTID
+    {
+    public:
+        template<size_t Length>
+        constexpr VTID(const char (&s)[Length]) :
+            _value{ _FromString(s) }
+        {
+        }
+
+        constexpr VTID(const uint64_t value) :
+            _value{ value }
+        {
+        }
+
+        constexpr operator uint64_t() const
+        {
+            return _value;
+        }
+
+        constexpr char operator[](const size_t offset) const
+        {
+            return SubSequence(offset)._value & 0xFF;
+        }
+
+        constexpr VTID SubSequence(const size_t offset) const
+        {
+            return _value >> (CHAR_BIT * offset);
+        }
+
+    private:
+        template<size_t Length>
+        static constexpr uint64_t _FromString(const char (&s)[Length])
+        {
+            static_assert(Length - 1 <= sizeof(_value));
+            uint64_t value = 0;
+            for (auto i = Length - 1; i-- > 0;)
+            {
+                value = (value << CHAR_BIT) + gsl::at(s, i);
+            }
+            return value;
+        }
+
+        uint64_t _value;
+    };
+
+    class VTIDBuilder
+    {
+    public:
+        void Clear() noexcept
+        {
+            _idAccumulator = 0;
+            _idShift = 0;
+        }
+
+        void AddIntermediate(const wchar_t intermediateChar) noexcept
+        {
+            if (_idShift + CHAR_BIT >= sizeof(_idAccumulator) * CHAR_BIT)
+            {
+                // If there is not enough space in the accumulator to add
+                // the intermediate and still have room left for the final,
+                // then we reset the accumulator to zero. This will result
+                // in an id with all zero intermediates, which shouldn't
+                // match anything.
+                _idAccumulator = 0;
+            }
+            else
+            {
+                // Otherwise we shift the intermediate so as to add it to the
+                // accumulator in the next available space, and then increment
+                // the shift by 8 bits in preparation for the next character.
+                _idAccumulator += (static_cast<uint64_t>(intermediateChar) << _idShift);
+                _idShift += CHAR_BIT;
+            }
+        }
+
+        VTID Finalize(const wchar_t finalChar) noexcept
+        {
+            return _idAccumulator + (static_cast<uint64_t>(finalChar) << _idShift);
+        }
+
+    private:
+        uint64_t _idAccumulator = 0;
+        size_t _idShift = 0;
+    };
+}
+
 namespace Microsoft::Console::VirtualTerminal::DispatchTypes
 {
     enum class EraseType : unsigned int
@@ -101,16 +189,16 @@ namespace Microsoft::Console::VirtualTerminal::DispatchTypes
         W32IM_Win32InputMode = 9001
     };
 
-    namespace CharacterSets
+    enum CharacterSets : uint64_t
     {
-        constexpr auto DecSpecialGraphics = std::make_pair(L'0', L'\0');
-        constexpr auto ASCII = std::make_pair(L'B', L'\0');
-    }
+        DecSpecialGraphics = VTID("0"),
+        ASCII = VTID("B")
+    };
 
-    enum CodingSystem : wchar_t
+    enum CodingSystem : uint64_t
     {
-        ISO2022 = L'@',
-        UTF8 = L'G'
+        ISO2022 = VTID("@"),
+        UTF8 = VTID("G")
     };
 
     enum TabClearType : unsigned short

src/terminal/adapter/ITermDispatch.hpp

@@ -98,9 +98,9 @@ class Microsoft::Console::VirtualTerminal::ITermDispatch
     virtual bool TertiaryDeviceAttributes() = 0; // DA3
     virtual bool Vt52DeviceAttributes() = 0; // VT52 Identify
 
-    virtual bool DesignateCodingSystem(const wchar_t codingSystem) = 0; // DOCS
-    virtual bool Designate94Charset(const size_t gsetNumber, const std::pair<wchar_t, wchar_t> charset) = 0; // SCS
-    virtual bool Designate96Charset(const size_t gsetNumber, const std::pair<wchar_t, wchar_t> charset) = 0; // SCS
+    virtual bool DesignateCodingSystem(const VTID codingSystem) = 0; // DOCS
+    virtual bool Designate94Charset(const size_t gsetNumber, const VTID charset) = 0; // SCS
+    virtual bool Designate96Charset(const size_t gsetNumber, const VTID charset) = 0; // SCS
     virtual bool LockingShift(const size_t gsetNumber) = 0; // LS0, LS1, LS2, LS3
     virtual bool LockingShiftRight(const size_t gsetNumber) = 0; // LS1R, LS2R, LS3R
     virtual bool SingleShift(const size_t gsetNumber) = 0; // SS2, SS3

src/terminal/adapter/adaptDispatch.cpp

@@ -1670,7 +1670,7 @@ void AdaptDispatch::_InitTabStopsForWidth(const size_t width)
 // - codingSystem - The coding system that will be selected.
 // Return value:
 // True if handled successfully. False otherwise.
-bool AdaptDispatch::DesignateCodingSystem(const wchar_t codingSystem)
+bool AdaptDispatch::DesignateCodingSystem(const VTID codingSystem)
 {
     // If we haven't previously saved the initial code page, do so now.
     // This will be used to restore the code page in response to a reset.
@@ -1712,10 +1712,10 @@ bool AdaptDispatch::DesignateCodingSystem(const wchar_t codingSystem)
 //     If the specified charset is unsupported, we do nothing (remain on the current one)
 //Arguments:
 // - gsetNumber - The G-set into which the charset will be selected.
-// - charset - The characters indicating the charset that will be used.
+// - charset - The identifier indicating the charset that will be used.
 // Return value:
 // True if handled successfully. False otherwise.
-bool AdaptDispatch::Designate94Charset(const size_t gsetNumber, const std::pair<wchar_t, wchar_t> charset)
+bool AdaptDispatch::Designate94Charset(const size_t gsetNumber, const VTID charset)
 {
     return _termOutput.Designate94Charset(gsetNumber, charset);
 }
@@ -1727,10 +1727,10 @@ bool AdaptDispatch::Designate94Charset(const size_t gsetNumber, const std::pair<
 //     If the specified charset is unsupported, we do nothing (remain on the current one)
 //Arguments:
 // - gsetNumber - The G-set into which the charset will be selected.
-// - charset - The characters indicating the charset that will be used.
+// - charset - The identifier indicating the charset that will be used.
 // Return value:
 // True if handled successfully. False otherwise.
-bool AdaptDispatch::Designate96Charset(const size_t gsetNumber, const std::pair<wchar_t, wchar_t> charset)
+bool AdaptDispatch::Designate96Charset(const size_t gsetNumber, const VTID charset)
 {
     return _termOutput.Designate96Charset(gsetNumber, charset);
 }

src/terminal/adapter/adaptDispatch.hpp

@@ -89,9 +89,9 @@ namespace Microsoft::Console::VirtualTerminal
         bool ForwardTab(const size_t numTabs) override; // CHT, HT
         bool BackwardsTab(const size_t numTabs) override; // CBT
         bool TabClear(const size_t clearType) override; // TBC
-        bool DesignateCodingSystem(const wchar_t codingSystem) override; // DOCS
-        bool Designate94Charset(const size_t gsetNumber, const std::pair<wchar_t, wchar_t> charset) override; // SCS
-        bool Designate96Charset(const size_t gsetNumber, const std::pair<wchar_t, wchar_t> charset) override; // SCS
+        bool DesignateCodingSystem(const VTID codingSystem) override; // DOCS
+        bool Designate94Charset(const size_t gsetNumber, const VTID charset) override; // SCS
+        bool Designate96Charset(const size_t gsetNumber, const VTID charset) override; // SCS
         bool LockingShift(const size_t gsetNumber) override; // LS0, LS1, LS2, LS3
         bool LockingShiftRight(const size_t gsetNumber) override; // LS1R, LS2R, LS3R
         bool SingleShift(const size_t gsetNumber) override; // SS2, SS3

src/terminal/adapter/termDispatch.hpp

@@ -92,9 +92,9 @@ class Microsoft::Console::VirtualTerminal::TermDispatch : public Microsoft::Cons
     bool TertiaryDeviceAttributes() noexcept override { return false; } // DA3
     bool Vt52DeviceAttributes() noexcept override { return false; } // VT52 Identify
 
-    bool DesignateCodingSystem(const wchar_t /*codingSystem*/) noexcept override { return false; } // DOCS
-    bool Designate94Charset(const size_t /*gsetNumber*/, const std::pair<wchar_t, wchar_t> /*charset*/) noexcept override { return false; } // SCS
-    bool Designate96Charset(const size_t /*gsetNumber*/, const std::pair<wchar_t, wchar_t> /*charset*/) noexcept override { return false; } // SCS
+    bool DesignateCodingSystem(const VTID /*codingSystem*/) noexcept override { return false; } // DOCS
+    bool Designate94Charset(const size_t /*gsetNumber*/, const VTID /*charset*/) noexcept override { return false; } // SCS
+    bool Designate96Charset(const size_t /*gsetNumber*/, const VTID /*charset*/) noexcept override { return false; } // SCS
     bool LockingShift(const size_t /*gsetNumber*/) noexcept override { return false; } // LS0, LS1, LS2, LS3
     bool LockingShiftRight(const size_t /*gsetNumber*/) noexcept override { return false; } // LS1R, LS2R, LS3R
     bool SingleShift(const size_t /*gsetNumber*/) noexcept override { return false; } // SS2, SS3

src/terminal/adapter/terminalOutput.cpp

@@ -17,107 +17,89 @@ TerminalOutput::TerminalOutput() noexcept
     _gsetTranslationTables.at(3) = Latin1;
 }
 
-bool TerminalOutput::Designate94Charset(size_t gsetNumber, const std::pair<wchar_t, wchar_t> charset)
+bool TerminalOutput::Designate94Charset(size_t gsetNumber, const VTID charset)
 {
-    switch (charset.first)
+    switch (charset)
     {
-    case L'B': // US ASCII
-    case L'1': // Alternate Character ROM
+    case VTID("B"): // US ASCII
+    case VTID("1"): // Alternate Character ROM
         return _SetTranslationTable(gsetNumber, Ascii);
-    case L'0': // DEC Special Graphics
-    case L'2': // Alternate Character ROM Special Graphics
+    case VTID("0"): // DEC Special Graphics
+    case VTID("2"): // Alternate Character ROM Special Graphics
         return _SetTranslationTable(gsetNumber, DecSpecialGraphics);
-    case L'<': // DEC Supplemental
+    case VTID("<"): // DEC Supplemental
         return _SetTranslationTable(gsetNumber, DecSupplemental);
-    case L'A': // British NRCS
+    case VTID("A"): // British NRCS
         return _SetTranslationTable(gsetNumber, BritishNrcs);
-    case L'4': // Dutch NRCS
+    case VTID("4"): // Dutch NRCS
         return _SetTranslationTable(gsetNumber, DutchNrcs);
-    case L'5': // Finnish NRCS
-    case L'C': // (fallback)
+    case VTID("5"): // Finnish NRCS
+    case VTID("C"): // (fallback)
         return _SetTranslationTable(gsetNumber, FinnishNrcs);
-    case L'R': // French NRCS
+    case VTID("R"): // French NRCS
         return _SetTranslationTable(gsetNumber, FrenchNrcs);
-    case L'f': // French NRCS (ISO update)
+    case VTID("f"): // French NRCS (ISO update)
         return _SetTranslationTable(gsetNumber, FrenchNrcsIso);
-    case L'9': // French Canadian NRCS
-    case L'Q': // (fallback)
+    case VTID("9"): // French Canadian NRCS
+    case VTID("Q"): // (fallback)
         return _SetTranslationTable(gsetNumber, FrenchCanadianNrcs);
-    case L'K': // German NRCS
+    case VTID("K"): // German NRCS
         return _SetTranslationTable(gsetNumber, GermanNrcs);
-    case L'Y': // Italian NRCS
+    case VTID("Y"): // Italian NRCS
         return _SetTranslationTable(gsetNumber, ItalianNrcs);
-    case L'6': // Norwegian/Danish NRCS
-    case L'E': // (fallback)
+    case VTID("6"): // Norwegian/Danish NRCS
+    case VTID("E"): // (fallback)
         return _SetTranslationTable(gsetNumber, NorwegianDanishNrcs);
-    case L'`': // Norwegian/Danish NRCS (ISO standard)
+    case VTID("`"): // Norwegian/Danish NRCS (ISO standard)
         return _SetTranslationTable(gsetNumber, NorwegianDanishNrcsIso);
-    case L'Z': // Spanish NRCS
+    case VTID("Z"): // Spanish NRCS
         return _SetTranslationTable(gsetNumber, SpanishNrcs);
-    case L'7': // Swedish NRCS
-    case L'H': // (fallback)
+    case VTID("7"): // Swedish NRCS
+    case VTID("H"): // (fallback)
         return _SetTranslationTable(gsetNumber, SwedishNrcs);
-    case L'=': // Swiss NRCS
+    case VTID("="): // Swiss NRCS
         return _SetTranslationTable(gsetNumber, SwissNrcs);
-    case L'&':
-        switch (charset.second)
-        {
-        case L'4': // DEC Cyrillic
-            return _SetTranslationTable(gsetNumber, DecCyrillic);
-        case L'5': // Russian NRCS
-            return _SetTranslationTable(gsetNumber, RussianNrcs);
-        default:
-            return false;
-        }
-    case L'"':
-        switch (charset.second)
-        {
-        case L'?': // DEC Greek
-            return _SetTranslationTable(gsetNumber, DecGreek);
-        case L'>': // Greek NRCS
-            return _SetTranslationTable(gsetNumber, GreekNrcs);
-        case L'4': // DEC Hebrew
-            return _SetTranslationTable(gsetNumber, DecHebrew);
-        default:
-            return false;
-        }
-    case L'%':
-        switch (charset.second)
-        {
-        case L'=': // Hebrew NRCS
-            return _SetTranslationTable(gsetNumber, HebrewNrcs);
-        case L'0': // DEC Turkish
-            return _SetTranslationTable(gsetNumber, DecTurkish);
-        case L'2': // Turkish NRCS
-            return _SetTranslationTable(gsetNumber, TurkishNrcs);
-        case L'5': // DEC Supplemental
-            return _SetTranslationTable(gsetNumber, DecSupplemental);
-        case L'6': // Portuguese NRCS
-            return _SetTranslationTable(gsetNumber, PortugueseNrcs);
-        default:
-            return false;
-        }
+    case VTID("&4"): // DEC Cyrillic
+        return _SetTranslationTable(gsetNumber, DecCyrillic);
+    case VTID("&5"): // Russian NRCS
+        return _SetTranslationTable(gsetNumber, RussianNrcs);
+    case VTID("\"?"): // DEC Greek
+        return _SetTranslationTable(gsetNumber, DecGreek);
+    case VTID("\">"): // Greek NRCS
+        return _SetTranslationTable(gsetNumber, GreekNrcs);
+    case VTID("\"4"): // DEC Hebrew
+        return _SetTranslationTable(gsetNumber, DecHebrew);
+    case VTID("%="): // Hebrew NRCS
+        return _SetTranslationTable(gsetNumber, HebrewNrcs);
+    case VTID("%0"): // DEC Turkish
+        return _SetTranslationTable(gsetNumber, DecTurkish);
+    case VTID("%2"): // Turkish NRCS
+        return _SetTranslationTable(gsetNumber, TurkishNrcs);
+    case VTID("%5"): // DEC Supplemental
+        return _SetTranslationTable(gsetNumber, DecSupplemental);
+    case VTID("%6"): // Portuguese NRCS
+        return _SetTranslationTable(gsetNumber, PortugueseNrcs);
     default:
         return false;
     }
 }
 
-bool TerminalOutput::Designate96Charset(size_t gsetNumber, const std::pair<wchar_t, wchar_t> charset)
+bool TerminalOutput::Designate96Charset(size_t gsetNumber, const VTID charset)
 {
-    switch (charset.first)
+    switch (charset)
     {
-    case L'A': // ISO Latin-1 Supplemental
-    case L'<': // (UPSS when assigned to Latin-1)
+    case VTID("A"): // ISO Latin-1 Supplemental
+    case VTID("<"): // (UPSS when assigned to Latin-1)
         return _SetTranslationTable(gsetNumber, Latin1);
-    case L'B': // ISO Latin-2 Supplemental
+    case VTID("B"): // ISO Latin-2 Supplemental
         return _SetTranslationTable(gsetNumber, Latin2);
-    case L'L': // ISO Latin-Cyrillic Supplemental
+    case VTID("L"): // ISO Latin-Cyrillic Supplemental
         return _SetTranslationTable(gsetNumber, LatinCyrillic);
-    case L'F': // ISO Latin-Greek Supplemental
+    case VTID("F"): // ISO Latin-Greek Supplemental
         return _SetTranslationTable(gsetNumber, LatinGreek);
-    case L'H': // ISO Latin-Hebrew Supplemental
+    case VTID("H"): // ISO Latin-Hebrew Supplemental
         return _SetTranslationTable(gsetNumber, LatinHebrew);
-    case L'M': // ISO Latin-5 Supplemental
+    case VTID("M"): // ISO Latin-5 Supplemental
         return _SetTranslationTable(gsetNumber, Latin5);
     default:
         return false;

src/terminal/adapter/terminalOutput.hpp

@@ -26,8 +26,8 @@ namespace Microsoft::Console::VirtualTerminal
         TerminalOutput() noexcept;
 
         wchar_t TranslateKey(const wchar_t wch) const noexcept;
-        bool Designate94Charset(const size_t gsetNumber, const std::pair<wchar_t, wchar_t> charset);
-        bool Designate96Charset(const size_t gsetNumber, const std::pair<wchar_t, wchar_t> charset);
+        bool Designate94Charset(const size_t gsetNumber, const VTID charset);
+        bool Designate96Charset(const size_t gsetNumber, const VTID charset);
         bool LockingShift(const size_t gsetNumber);
         bool LockingShiftRight(const size_t gsetNumber);
         bool SingleShift(const size_t gsetNumber);