diff options
Diffstat (limited to 'src/PositionCache.cxx')
| -rw-r--r-- | src/PositionCache.cxx | 69 |
1 files changed, 69 insertions, 0 deletions
diff --git a/src/PositionCache.cxx b/src/PositionCache.cxx index a0b7f3129..ae8dd1e66 100644 --- a/src/PositionCache.cxx +++ b/src/PositionCache.cxx @@ -51,6 +51,7 @@ #include "CaseFolder.h" #include "Document.h" #include "UniConversion.h" +#include "DBCS.h" #include "Selection.h" #include "PositionCache.h" @@ -638,6 +639,40 @@ constexpr unsigned int KeyFromString(std::string_view charBytes) noexcept { constexpr unsigned int representationKeyCrLf = KeyFromString("\r\n"); +const char *const repsC0[] = { + "NUL", "SOH", "STX", "ETX", "EOT", "ENQ", "ACK", "BEL", + "BS", "HT", "LF", "VT", "FF", "CR", "SO", "SI", + "DLE", "DC1", "DC2", "DC3", "DC4", "NAK", "SYN", "ETB", + "CAN", "EM", "SUB", "ESC", "FS", "GS", "RS", "US" +}; + +const char *const repsC1[] = { + "PAD", "HOP", "BPH", "NBH", "IND", "NEL", "SSA", "ESA", + "HTS", "HTJ", "VTS", "PLD", "PLU", "RI", "SS2", "SS3", + "DCS", "PU1", "PU2", "STS", "CCH", "MW", "SPA", "EPA", + "SOS", "SGCI", "SCI", "CSI", "ST", "OSC", "PM", "APC" +}; + +} + +namespace Scintilla::Internal { + +const char *ControlCharacterString(unsigned char ch) noexcept { + if (ch < std::size(repsC0)) { + return repsC0[ch]; + } else { + return "BAD"; + } +} + + +void Hexits(char *hexits, int ch) noexcept { + hexits[0] = 'x'; + hexits[1] = "0123456789ABCDEF"[ch / 0x10]; + hexits[2] = "0123456789ABCDEF"[ch % 0x10]; + hexits[3] = 0; +} + } void SpecialRepresentations::SetRepresentation(std::string_view charBytes, std::string_view value) { @@ -731,6 +766,40 @@ void SpecialRepresentations::Clear() { crlf = false; } +void SpecialRepresentations::SetDefaultRepresentations(int dbcsCodePage) { + Clear(); + + // C0 control set + for (size_t j = 0; j < std::size(repsC0); j++) { + const char c[2] = { static_cast<char>(j), 0 }; + SetRepresentation(std::string_view(c, 1), repsC0[j]); + } + SetRepresentation("\x7f", "DEL"); + + // C1 control set + // As well as Unicode mode, ISO-8859-1 should use these + if (CpUtf8 == dbcsCodePage) { + for (size_t j = 0; j < std::size(repsC1); j++) { + const char c1[3] = { '\xc2', static_cast<char>(0x80 + j), 0 }; + SetRepresentation(c1, repsC1[j]); + } + SetRepresentation("\xe2\x80\xa8", "LS"); + SetRepresentation("\xe2\x80\xa9", "PS"); + } + + // Invalid as single bytes in multi-byte encodings + if (dbcsCodePage) { + for (int k = 0x80; k < 0x100; k++) { + if ((CpUtf8 == dbcsCodePage) || !IsDBCSValidSingleByte(dbcsCodePage, k)) { + const char hiByte[2] = { static_cast<char>(k), 0 }; + char hexits[4]; + Hexits(hexits, k); + SetRepresentation(hiByte, hexits); + } + } + } +} + void BreakFinder::Insert(Sci::Position val) { const int posInLine = static_cast<int>(val); if (posInLine > nextBreak) { |