diff options
author | Timothy Pearson <kb9vqf@pearsoncomputing.net> | 2011-11-08 12:31:36 -0600 |
---|---|---|
committer | Timothy Pearson <kb9vqf@pearsoncomputing.net> | 2011-11-08 12:31:36 -0600 |
commit | d796c9dd933ab96ec83b9a634feedd5d32e1ba3f (patch) | |
tree | 6e3dcca4f77e20ec8966c666aac7c35bd4704053 /src/codecs/qisciicodec.cpp | |
download | tqt3-d796c9dd933ab96ec83b9a634feedd5d32e1ba3f.tar.gz tqt3-d796c9dd933ab96ec83b9a634feedd5d32e1ba3f.zip |
Test conversion to TQt3 from Qt3 8c6fc1f8e35fd264dd01c582ca5e7549b32ab731
Diffstat (limited to 'src/codecs/qisciicodec.cpp')
-rw-r--r-- | src/codecs/qisciicodec.cpp | 240 |
1 files changed, 240 insertions, 0 deletions
diff --git a/src/codecs/qisciicodec.cpp b/src/codecs/qisciicodec.cpp new file mode 100644 index 000000000..fa181ca80 --- /dev/null +++ b/src/codecs/qisciicodec.cpp @@ -0,0 +1,240 @@ +#include "qisciicodec_p.h" +#ifndef QT_NO_CODECS + +#define TQValidChar(u) ((u) ? TQChar((u)) : TQChar::replacement) + +/*! + \class TQIsciiCodec + \brief The TQIsciiCodec class provides conversion to and from the ISCII encoding. + + \ingroup i18n + \internal +*/ + +TQIsciiCodec::TQIsciiCodec(int i) +: idx(i) +{ +} + +int TQIsciiCodec::mibEnum() const +{ + /* There is no MIBEnum for Iscii */ + return -3000-idx; +} + + +struct Codecs { + const char *name; + ushort base; +}; + +static const Codecs codecs [] = { + { "Iscii-Dev", 0x900 }, + { "Iscii-Bng", 0x980 }, + { "Iscii-Pnj", 0xa00 }, + { "Iscii-Gjr", 0xa80 }, + { "Iscii-Ori", 0xb00 }, + { "Iscii-Tml", 0xb80 }, + { "Iscii-Tlg", 0xc00 }, + { "Iscii-Knd", 0xc80 }, + { "Iscii-Mlm", 0xd00 } +}; + +const char* TQIsciiCodec::name() const +{ + return codecs[idx].name; +} + +const char* TQIsciiCodec::mimeName() const +{ + return codecs[idx].name; +} + + +int TQIsciiCodec::heuristicNameMatch(const char* hint) const +{ + const char *p = strchr(hint, '.'); + if (p) + p++; + else + p = hint; + + if (TQString::fromLatin1(p).lower() == TQString::fromLatin1(codecs[idx].name).lower()) + return 4; + else + return TQTextCodec::heuristicNameMatch(hint); +} + +int TQIsciiCodec::heuristicContentMatch(const char*, int) const +{ + return 0; +} + +#define INV 0xff + +/* iscii range from 0xa0 - 0xff */ +static const uchar iscii_to_uni_table[0x60] = { + 0x00, 0x01, 0x02, 0x03, + 0x05, 0x06, 0x07, 0x08, + 0x09, 0x0a, 0x0b, 0x0e, + 0x0f, 0x20, 0x0d, 0x12, + + 0x13, 0x14, 0x11, 0x15, + 0x16, 0x17, 0x18, 0x19, + 0x1a, 0x1b, 0x1c, 0x1d, + 0x1e, 0x1f, 0x20, 0x21, + + 0x22, 0x23, 0x24, 0x25, + 0x26, 0x27, 0x28, 0x29, + 0x2a, 0x2b, 0x2c, 0x2d, + 0x2e, 0x2f, 0x5f, 0x30, + + 0x31, 0x32, 0x33, 0x34, + 0x35, 0x36, 0x37, 0x38, + 0x39, INV, 0x3e, 0x3f, + 0x40, 0x41, 0x42, 0x43, + + 0x46, 0x47, 0x48, 0x45, + 0x4a, 0x4b, 0x4c, 0x49, + 0x4d, 0x3c, 0x64, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x66, 0x67, 0x68, + 0x69, 0x6a, 0x6b, 0x6c, + 0x6d, 0x6e, 0x6f, 0x00, + 0x00, 0x00, 0x00, 0x00 +}; + +static const uchar uni_to_iscii_table[0x80] = { + 0x00, 0xa1, 0xa2, 0xa3, + 0x00, 0xa4, 0xa5, 0xa6, + 0xa7, 0xa8, 0xa9, 0xaa, + 0x00, 0xae, 0xab, 0xac, + + 0xad, 0xb2, 0xaf, 0xb0, + 0xb1, 0xb3, 0xb4, 0xb5, + 0xb6, 0xb7, 0xb8, 0xb9, + 0xba, 0xbb, 0xbc, 0xbd, + + 0xbe, 0xbf, 0xc0, 0xc1, + 0xc2, 0xc3, 0xc4, 0xc5, + 0xc6, 0xc7, 0xc8, 0xc9, + 0xca, 0xcb, 0xcc, 0xcd, + + 0xcf, 0xd0, 0xd1, 0xd2, + 0xd3, 0xd4, 0xd5, 0xd6, + 0xd7, 0xd8, 0x00, 0x00, + 0xe9, 0x00, 0xda, 0xdb, + + 0xdc, 0xdd, 0xde, 0xdf, + 0x00, 0xe3, 0xe0, 0xe1, + 0xe2, 0xe7, 0xe4, 0xe5, + 0xe6, 0xe8, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x01, 0x02, 0x03, 0x04, // decomposable into the uc codes listed here + nukta + 0x05, 0x06, 0x07, 0xce, + + 0x00, 0x00, 0x00, 0x00, + 0xea, 0x08, 0xf1, 0xf2, + 0xf3, 0xf4, 0xf5, 0xf6, + 0xf7, 0xf8, 0xf9, 0xfa, + + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00 +}; + +static const uchar uni_to_iscii_pairs[] = { + 0x00, 0x00, + 0x15, 0x3c, // 0x958 + 0x16, 0x3c, // 0x959 + 0x17, 0x3c, // 0x95a + 0x1c, 0x3c, // 0x95b + 0x21, 0x3c, // 0x95c + 0x22, 0x3c, // 0x95d + 0x2b, 0x3c, // 0x95e + 0x64, 0x64 // 0x965 +}; + + +TQCString TQIsciiCodec::fromUnicode(const TQString& uc, int& len_in_out) const +{ + int l = uc.length(); + if (len_in_out > 0) + l = TQMIN(l, len_in_out); + TQCString result(2*l); //worst case + + const TQChar *data = uc.unicode(); + uchar *ch = (uchar *)result.data(); + + int base = codecs[idx].base; + + bool halant = FALSE; + for (int i =0; i < l; ++i) { + int pos = data[i].unicode() - base; + if (pos > 0 && pos < 0x80) { + uchar iscii = uni_to_iscii_table[pos]; + if (iscii > 0x80) { + *ch++ = iscii; + } else if (iscii) { + const uchar *pair = uni_to_iscii_pairs + 2*iscii; + *ch++ = *pair++; + *ch++ = *pair++; + } else { + *ch++ = '?'; + } + } else { + if (data[i].unicode() == 0x200c) { // ZWNJ + if (halant) + // Consonant Halant ZWNJ -> Consonant Halant Halant + *ch++ = 0xe8; + } else if (data[i].unicode() == 0x200d) { // ZWJ + if (halant) + // Consonant Halant ZWJ -> Consonant Halant Nukta + *ch++ = 0xe9; + } else { + *ch++ = '?'; + } + } + halant = (pos == 0x4d); + } + len_in_out = ch - (uchar *)result.data(); + result.truncate(len_in_out); + return result; +} + +TQString TQIsciiCodec::toUnicode( const char* chars, int len_in ) const +{ + TQString result; + result.setLength(len_in); + + TQChar *uc = (TQChar *)result.unicode(); + + int base = codecs[idx].base; + + bool halant = FALSE; + for (int i = 0; i < len_in; ++i) { + ushort ch = (uchar) chars[i]; + if (ch < 0xa0) + *uc++ = TQValidChar(ch); + else { + ushort c = iscii_to_uni_table[ch - 0xa0]; + if (halant && (c == INV || c == 0xe9)) { + // Consonant Halant INV -> Consonant Halant ZWJ + // Consonant Halant Nukta -> Consonant Halant ZWJ + *uc++ = TQChar(0x200d); + } else if (halant && c == 0xe8) { + // Consonant Halant Halant -> Consonant Halant ZWNJ + *uc++ = TQChar(0x200c); + } else { + *uc++ = TQChar(c+base); + } + } + halant = ((uchar)chars[i] == 0xe8); + } + return result; +} +#endif // QT_NO_CODECS |