1berry/qtbase
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Clean-up the Unicode tables generator code and the generated header

Browse Source 
This fixes the blocks and memory consumption reports, the whitespace issues
and makes the code a bit cleaner.

Since I'm the only one who does change this code, such a no-op commit
could not hurt anyone or even git blame ;)

Change-Id: Ib069f925a3791c82e16c368c8392bcffbfd68c53
Reviewed-by: Lars Knoll <lars.knoll@nokia.com>
Reviewed-by: Konstantin Ritt <ritt.ks@gmail.com>
This commit is contained in:
Konstantin Ritt 2012-06-17 04:20:59 +03:00 committed by Qt by Nokia
parent 57ca02b1d2
commit c1329fba13
2 changed files with 637 additions and 638 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

404
src/corelib/tools/qunicodetables_p.h
View File

@ -63,221 +63,217 @@ QT_BEGIN_NAMESPACE
namespace QUnicodeTables { namespace QUnicodeTables {
struct Properties { struct Properties {
ushort category : 8; /* 5 used */ ushort category : 8; /* 5 used */
ushort direction : 8; /* 5 used */ ushort direction : 8; /* 5 used */
ushort combiningClass : 8; ushort combiningClass : 8;
ushort joining : 2; ushort joining : 2;
signed short digitValue : 6; /* 5 used */ signed short digitValue : 6; /* 5 used */
signed short mirrorDiff : 16; signed short mirrorDiff : 16;
signed short lowerCaseDiff : 16; signed short lowerCaseDiff : 16;
signed short upperCaseDiff : 16; signed short upperCaseDiff : 16;
signed short titleCaseDiff : 16; signed short titleCaseDiff : 16;
signed short caseFoldDiff : 16; signed short caseFoldDiff : 16;
ushort lowerCaseSpecial : 1; ushort lowerCaseSpecial : 1;
ushort upperCaseSpecial : 1; ushort upperCaseSpecial : 1;
ushort titleCaseSpecial : 1; ushort titleCaseSpecial : 1;
ushort caseFoldSpecial : 1; ushort caseFoldSpecial : 1;
ushort unicodeVersion : 4; ushort unicodeVersion : 4;
ushort graphemeBreak : 8; /* 4 used */ ushort graphemeBreak : 8; /* 4 used */
ushort wordBreak : 8; /* 4 used */ ushort wordBreak : 8; /* 4 used */
ushort sentenceBreak : 8; /* 4 used */ ushort sentenceBreak : 8; /* 4 used */
ushort line_break_class : 8; /* 6 used */ ushort line_break_class : 8; /* 6 used */
ushort script : 8; /* 5 used */ ushort script : 8; /* 5 used */
}; };
Q_CORE_EXPORT const Properties * QT_FASTCALL properties(uint ucs4);
Q_CORE_EXPORT const Properties * QT_FASTCALL properties(ushort ucs2);
// See http://www.unicode.org/reports/tr24/tr24-5.html Q_CORE_EXPORT const Properties * QT_FASTCALL properties(uint ucs4);
enum Script { Q_CORE_EXPORT const Properties * QT_FASTCALL properties(ushort ucs2);
Common,
Greek,
Cyrillic,
Armenian,
Hebrew,
Arabic,
Syriac,
Thaana,
Devanagari,
Bengali,
Gurmukhi,
Gujarati,
Oriya,
Tamil,
Telugu,
Kannada,
Malayalam,
Sinhala,
Thai,
Lao,
Tibetan,
Myanmar,
Georgian,
Hangul,
Ogham,
Runic,
Khmer,
Nko,
Inherited,
ScriptCount = Inherited,
Latin = Common,
Ethiopic = Common,
Cherokee = Common,
CanadianAboriginal = Common,
Mongolian = Common,
Hiragana = Common,
Katakana = Common,
Bopomofo = Common,
Han = Common,
Yi = Common,
OldItalic = Common,
Gothic = Common,
Deseret = Common,
Tagalog = Common,
Hanunoo = Common,
Buhid = Common,
Tagbanwa = Common,
Limbu = Common,
TaiLe = Common,
LinearB = Common,
Ugaritic = Common,
Shavian = Common,
Osmanya = Common,
Cypriot = Common,
Braille = Common,
Buginese = Common,
Coptic = Common,
NewTaiLue = Common,
Glagolitic = Common,
Tifinagh = Common,
SylotiNagri = Common,
OldPersian = Common,
Kharoshthi = Common,
Balinese = Common,
Cuneiform = Common,
Phoenician = Common,
PhagsPa = Common,
Sundanese = Common,
Lepcha = Common,
OlChiki = Common,
Vai = Common,
Saurashtra = Common,
KayahLi = Common,
Rejang = Common,
Lycian = Common,
Carian = Common,
Lydian = Common,
Cham = Common,
TaiTham = Common,
TaiViet = Common,
Avestan = Common,
EgyptianHieroglyphs = Common,
Samaritan = Common,
Lisu = Common,
Bamum = Common,
Javanese = Common,
MeeteiMayek = Common,
ImperialAramaic = Common,
OldSouthArabian = Common,
InscriptionalParthian = Common,
InscriptionalPahlavi = Common,
OldTurkic = Common,
Kaithi = Common,
Batak = Common,
Brahmi = Common,
Mandaic = Common,
Chakma = Common,
MeroiticCursive = Common,
MeroiticHieroglyphs = Common,
Miao = Common,
Sharada = Common,
SoraSompeng = Common,
Takri = Common
};
// See http://www.unicode.org/reports/tr24/tr24-5.html
enum Script {
Common,
Greek,
Cyrillic,
Armenian,
Hebrew,
Arabic,
Syriac,
Thaana,
Devanagari,
Bengali,
Gurmukhi,
Gujarati,
Oriya,
Tamil,
Telugu,
Kannada,
Malayalam,
Sinhala,
Thai,
Lao,
Tibetan,
Myanmar,
Georgian,
Hangul,
Ogham,
Runic,
Khmer,
Nko,
Inherited,
ScriptCount = Inherited,
Latin = Common,
Ethiopic = Common,
Cherokee = Common,
CanadianAboriginal = Common,
Mongolian = Common,
Hiragana = Common,
Katakana = Common,
Bopomofo = Common,
Han = Common,
Yi = Common,
OldItalic = Common,
Gothic = Common,
Deseret = Common,
Tagalog = Common,
Hanunoo = Common,
Buhid = Common,
Tagbanwa = Common,
Limbu = Common,
TaiLe = Common,
LinearB = Common,
Ugaritic = Common,
Shavian = Common,
Osmanya = Common,
Cypriot = Common,
Braille = Common,
Buginese = Common,
Coptic = Common,
NewTaiLue = Common,
Glagolitic = Common,
Tifinagh = Common,
SylotiNagri = Common,
OldPersian = Common,
Kharoshthi = Common,
Balinese = Common,
Cuneiform = Common,
Phoenician = Common,
PhagsPa = Common,
Sundanese = Common,
Lepcha = Common,
OlChiki = Common,
Vai = Common,
Saurashtra = Common,
KayahLi = Common,
Rejang = Common,
Lycian = Common,
Carian = Common,
Lydian = Common,
Cham = Common,
TaiTham = Common,
TaiViet = Common,
Avestan = Common,
EgyptianHieroglyphs = Common,
Samaritan = Common,
Lisu = Common,
Bamum = Common,
Javanese = Common,
MeeteiMayek = Common,
ImperialAramaic = Common,
OldSouthArabian = Common,
InscriptionalParthian = Common,
InscriptionalPahlavi = Common,
OldTurkic = Common,
Kaithi = Common,
Batak = Common,
Brahmi = Common,
Mandaic = Common,
Chakma = Common,
MeroiticCursive = Common,
MeroiticHieroglyphs = Common,
Miao = Common,
Sharada = Common,
SoraSompeng = Common,
Takri = Common
};
enum GraphemeBreak { enum GraphemeBreak {
GraphemeBreakOther, GraphemeBreakOther,
GraphemeBreakCR, GraphemeBreakCR,
GraphemeBreakLF, GraphemeBreakLF,
GraphemeBreakControl, GraphemeBreakControl,
GraphemeBreakExtend, GraphemeBreakExtend,
GraphemeBreakPrepend, GraphemeBreakPrepend,
GraphemeBreakSpacingMark, GraphemeBreakSpacingMark,
GraphemeBreakL, GraphemeBreakL,
GraphemeBreakV, GraphemeBreakV,
GraphemeBreakT, GraphemeBreakT,
GraphemeBreakLV, GraphemeBreakLV,
GraphemeBreakLVT GraphemeBreakLVT
}; };
enum WordBreak {
WordBreakOther,
WordBreakCR,
WordBreakLF,
WordBreakNewline,
WordBreakFormat,
WordBreakKatakana,
WordBreakALetter,
WordBreakMidNumLet,
WordBreakMidLetter,
WordBreakMidNum,
WordBreakNumeric,
WordBreakExtendNumLet
};
enum WordBreak { enum SentenceBreak {
WordBreakOther, SentenceBreakOther,
WordBreakCR, SentenceBreakCR,
WordBreakLF, SentenceBreakLF,
WordBreakNewline, SentenceBreakSep,
WordBreakFormat, SentenceBreakFormat,
WordBreakKatakana, SentenceBreakSp,
WordBreakALetter, SentenceBreakLower,
WordBreakMidNumLet, SentenceBreakUpper,
WordBreakMidLetter, SentenceBreakOLetter,
WordBreakMidNum, SentenceBreakNumeric,
WordBreakNumeric, SentenceBreakATerm,
WordBreakExtendNumLet SentenceBreakSContinue,
}; SentenceBreakSTerm,
SentenceBreakClose
};
// see http://www.unicode.org/reports/tr14/tr14-28.html
// we don't use the XX and AI classes and map them to AL instead.
enum LineBreakClass {
LineBreak_OP, LineBreak_CL, LineBreak_CP, LineBreak_QU, LineBreak_GL,
LineBreak_NS, LineBreak_EX, LineBreak_SY, LineBreak_IS, LineBreak_PR,
LineBreak_PO, LineBreak_NU, LineBreak_AL, LineBreak_HL, LineBreak_ID,
LineBreak_IN, LineBreak_HY, LineBreak_BA, LineBreak_BB, LineBreak_B2,
LineBreak_ZW, LineBreak_CM, LineBreak_WJ, LineBreak_H2, LineBreak_H3,
LineBreak_JL, LineBreak_JV, LineBreak_JT, LineBreak_CB, LineBreak_SA,
LineBreak_SG, LineBreak_SP, LineBreak_CR, LineBreak_LF, LineBreak_BK
};
enum SentenceBreak { Q_CORE_EXPORT GraphemeBreak QT_FASTCALL graphemeBreakClass(uint ucs4);
SentenceBreakOther, inline GraphemeBreak graphemeBreakClass(QChar ch)
SentenceBreakCR, { return graphemeBreakClass(ch.unicode()); }
SentenceBreakLF,
SentenceBreakSep,
SentenceBreakFormat,
SentenceBreakSp,
SentenceBreakLower,
SentenceBreakUpper,
SentenceBreakOLetter,
SentenceBreakNumeric,
SentenceBreakATerm,
SentenceBreakSContinue,
SentenceBreakSTerm,
SentenceBreakClose
};
Q_CORE_EXPORT WordBreak QT_FASTCALL wordBreakClass(uint ucs4);
inline WordBreak wordBreakClass(QChar ch)
{ return wordBreakClass(ch.unicode()); }
// see http://www.unicode.org/reports/tr14/tr14-28.html Q_CORE_EXPORT SentenceBreak QT_FASTCALL sentenceBreakClass(uint ucs4);
// we don't use the XX and AI classes and map them to AL instead. inline SentenceBreak sentenceBreakClass(QChar ch)
enum LineBreakClass { { return sentenceBreakClass(ch.unicode()); }
LineBreak_OP, LineBreak_CL, LineBreak_CP, LineBreak_QU, LineBreak_GL,
LineBreak_NS, LineBreak_EX, LineBreak_SY, LineBreak_IS, LineBreak_PR,
LineBreak_PO, LineBreak_NU, LineBreak_AL, LineBreak_HL, LineBreak_ID,
LineBreak_IN, LineBreak_HY, LineBreak_BA, LineBreak_BB, LineBreak_B2,
LineBreak_ZW, LineBreak_CM, LineBreak_WJ, LineBreak_H2, LineBreak_H3,
LineBreak_JL, LineBreak_JV, LineBreak_JT, LineBreak_CB, LineBreak_SA,
LineBreak_SG, LineBreak_SP, LineBreak_CR, LineBreak_LF, LineBreak_BK
};
Q_CORE_EXPORT LineBreakClass QT_FASTCALL lineBreakClass(uint ucs4);
inline LineBreakClass lineBreakClass(QChar ch)
{ return lineBreakClass(ch.unicode()); }
Q_CORE_EXPORT GraphemeBreak QT_FASTCALL graphemeBreakClass(uint ucs4); Q_CORE_EXPORT Script QT_FASTCALL script(uint ucs4);
inline GraphemeBreak graphemeBreakClass(QChar ch) inline Script script(QChar ch)
{ return graphemeBreakClass(ch.unicode()); } { return script(ch.unicode()); }
Q_CORE_EXPORT WordBreak QT_FASTCALL wordBreakClass(uint ucs4);
inline WordBreak wordBreakClass(QChar ch)
{ return wordBreakClass(ch.unicode()); }
Q_CORE_EXPORT SentenceBreak QT_FASTCALL sentenceBreakClass(uint ucs4);
inline SentenceBreak sentenceBreakClass(QChar ch)
{ return sentenceBreakClass(ch.unicode()); }
Q_CORE_EXPORT LineBreakClass QT_FASTCALL lineBreakClass(uint ucs4);
inline LineBreakClass lineBreakClass(QChar ch)
{ return lineBreakClass(ch.unicode()); }
Q_CORE_EXPORT Script QT_FASTCALL script(uint ucs4);
inline Script script(QChar ch)
{ return script(ch.unicode()); }
} // namespace QUnicodeTables } // namespace QUnicodeTables

871
util/unicode/main.cpp
View File

File diff suppressed because it is too large Load Diff