QUnicodeTools: Adjust properties of WSegSpace word break class
Disable break between sequences of WSegSpace characters (rule WB3d, introduced in UAX #29, version 33, Unicode 11.0.0). Also disable breaks between WSegSpace and (Extend | Format | ZWJ) due to rule WB4. Adjust "words4" test to take the above changes into account (space character belongs to WSegSpace). Mention the full class name in a comment inside the word break table. This fixes 34 word break tests. Task-number: QTBUG-97537 Pick-to: 6.2 6.3 Change-Id: I7dfe8367e45c86913bb7d7fe2adb053711978487 Reviewed-by: Edward Welbourne <edward.welbourne@qt.io>
This commit is contained in:
parent
9a831bdf54
commit
79d26ef3ae
@ -209,29 +209,29 @@ enum Action {
|
||||
|
||||
static const uchar breakTable[QUnicodeTables::NumWordBreakClasses][QUnicodeTables::NumWordBreakClasses] = {
|
||||
// Any CR LF Newline Extend ZWJ Format RI Katakana HLetter ALetter SQuote DQuote MidNumLet MidLetter MidNum Numeric ExtNumLet E_Base E_Mod GAZ EBG WSeg
|
||||
{ Break , Break , Break , Break , NoBreak, NoBreak, NoBreak, Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break }, // Any
|
||||
{ Break , Break , NoBreak, Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break }, // CR
|
||||
{ Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break }, // LF
|
||||
{ Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break }, // Newline
|
||||
{ Break , Break , Break , Break , NoBreak, NoBreak, NoBreak, Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break }, // Extend
|
||||
{ Break , Break , Break , Break , NoBreak, NoBreak, NoBreak, Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , NoBreak, NoBreak, Break }, // ZWJ
|
||||
{ Break , Break , Break , Break , NoBreak, NoBreak, NoBreak, Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break }, // Format
|
||||
{ Break , Break , Break , Break , NoBreak, NoBreak, NoBreak, NoBreak, Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break }, // RegionalIndicator
|
||||
{ Break , Break , Break , Break , NoBreak, NoBreak, NoBreak, Break , NoBreak, Break , Break , Break , Break , Break , Break , Break , Break , NoBreak, Break , Break , Break , Break , Break }, // Katakana
|
||||
{ Break , Break , Break , Break , NoBreak, NoBreak, NoBreak, Break , Break , NoBreak, NoBreak, LookupW, Lookup , LookupW, LookupW, Break , NoBreak, NoBreak, Break , Break , Break , Break , Break }, // HebrewLetter
|
||||
{ Break , Break , Break , Break , NoBreak, NoBreak, NoBreak, Break , Break , NoBreak, NoBreak, LookupW, Break , LookupW, LookupW, Break , NoBreak, NoBreak, Break , Break , Break , Break , Break }, // ALetter
|
||||
{ Break , Break , Break , Break , NoBreak, NoBreak, NoBreak, Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break }, // SingleQuote
|
||||
{ Break , Break , Break , Break , NoBreak, NoBreak, NoBreak, Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break }, // DoubleQuote
|
||||
{ Break , Break , Break , Break , NoBreak, NoBreak, NoBreak, Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break }, // MidNumLet
|
||||
{ Break , Break , Break , Break , NoBreak, NoBreak, NoBreak, Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break }, // MidLetter
|
||||
{ Break , Break , Break , Break , NoBreak, NoBreak, NoBreak, Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break }, // MidNum
|
||||
{ Break , Break , Break , Break , NoBreak, NoBreak, NoBreak, Break , Break , NoBreak, NoBreak, Lookup , Break , Lookup , Break , Lookup , NoBreak, NoBreak, Break , Break , Break , Break , Break }, // Numeric
|
||||
{ Break , Break , Break , Break , NoBreak, NoBreak, NoBreak, Break , NoBreak, NoBreak, NoBreak, Break , Break , Break , Break , Break , NoBreak, NoBreak, Break , Break , Break , Break , Break }, // ExtendNumLet
|
||||
{ Break , Break , Break , Break , NoBreak, NoBreak, NoBreak, Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , NoBreak, Break , Break , Break }, // E_Base
|
||||
{ Break , Break , Break , Break , NoBreak, NoBreak, NoBreak, Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break }, // E_Mod
|
||||
{ Break , Break , Break , Break , NoBreak, NoBreak, NoBreak, Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break }, // GAZ
|
||||
{ Break , Break , Break , Break , NoBreak, NoBreak, NoBreak, Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , NoBreak, Break , Break , Break }, // EBG
|
||||
{ Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break }, // WSeg
|
||||
{ Break , Break , Break , Break , NoBreak, NoBreak, NoBreak, Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break }, // Any
|
||||
{ Break , Break , NoBreak, Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break }, // CR
|
||||
{ Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break }, // LF
|
||||
{ Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break }, // Newline
|
||||
{ Break , Break , Break , Break , NoBreak, NoBreak, NoBreak, Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break }, // Extend
|
||||
{ Break , Break , Break , Break , NoBreak, NoBreak, NoBreak, Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , NoBreak, NoBreak, Break }, // ZWJ
|
||||
{ Break , Break , Break , Break , NoBreak, NoBreak, NoBreak, Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break }, // Format
|
||||
{ Break , Break , Break , Break , NoBreak, NoBreak, NoBreak, NoBreak, Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break }, // RegionalIndicator
|
||||
{ Break , Break , Break , Break , NoBreak, NoBreak, NoBreak, Break , NoBreak, Break , Break , Break , Break , Break , Break , Break , Break , NoBreak, Break , Break , Break , Break , Break }, // Katakana
|
||||
{ Break , Break , Break , Break , NoBreak, NoBreak, NoBreak, Break , Break , NoBreak, NoBreak, LookupW, Lookup , LookupW, LookupW, Break , NoBreak, NoBreak, Break , Break , Break , Break , Break }, // HebrewLetter
|
||||
{ Break , Break , Break , Break , NoBreak, NoBreak, NoBreak, Break , Break , NoBreak, NoBreak, LookupW, Break , LookupW, LookupW, Break , NoBreak, NoBreak, Break , Break , Break , Break , Break }, // ALetter
|
||||
{ Break , Break , Break , Break , NoBreak, NoBreak, NoBreak, Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break }, // SingleQuote
|
||||
{ Break , Break , Break , Break , NoBreak, NoBreak, NoBreak, Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break }, // DoubleQuote
|
||||
{ Break , Break , Break , Break , NoBreak, NoBreak, NoBreak, Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break }, // MidNumLet
|
||||
{ Break , Break , Break , Break , NoBreak, NoBreak, NoBreak, Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break }, // MidLetter
|
||||
{ Break , Break , Break , Break , NoBreak, NoBreak, NoBreak, Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break }, // MidNum
|
||||
{ Break , Break , Break , Break , NoBreak, NoBreak, NoBreak, Break , Break , NoBreak, NoBreak, Lookup , Break , Lookup , Break , Lookup , NoBreak, NoBreak, Break , Break , Break , Break , Break }, // Numeric
|
||||
{ Break , Break , Break , Break , NoBreak, NoBreak, NoBreak, Break , NoBreak, NoBreak, NoBreak, Break , Break , Break , Break , Break , NoBreak, NoBreak, Break , Break , Break , Break , Break }, // ExtendNumLet
|
||||
{ Break , Break , Break , Break , NoBreak, NoBreak, NoBreak, Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , NoBreak, Break , Break , Break }, // E_Base
|
||||
{ Break , Break , Break , Break , NoBreak, NoBreak, NoBreak, Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break }, // E_Mod
|
||||
{ Break , Break , Break , Break , NoBreak, NoBreak, NoBreak, Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break }, // GAZ
|
||||
{ Break , Break , Break , Break , NoBreak, NoBreak, NoBreak, Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , NoBreak, Break , Break , Break }, // EBG
|
||||
{ Break , Break , Break , Break , NoBreak, NoBreak, NoBreak, Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , Break , NoBreak }, // WSegSpace
|
||||
};
|
||||
|
||||
} // namespace WB
|
||||
|
@ -951,63 +951,63 @@
|
||||
÷ 231A ÷ 0031 ÷ 002E × 2060 ÷ # ÷ [0.2] WATCH (ExtPict) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) ÷ [0.3]
|
||||
÷ 231A × 0308 ÷ 0031 ÷ 002E × 2060 ÷ # ÷ [0.2] WATCH (ExtPict) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) ÷ [0.3]
|
||||
÷ 0020 ÷ 0001 ÷ # ÷ [0.2] SPACE (WSegSpace) ÷ [999.0] <START OF HEADING> (Other) ÷ [0.3]
|
||||
# ÷ 0020 × 0308 ÷ 0001 ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] <START OF HEADING> (Other) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 0001 ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] <START OF HEADING> (Other) ÷ [0.3]
|
||||
÷ 0020 ÷ 000D ÷ # ÷ [0.2] SPACE (WSegSpace) ÷ [3.2] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
# ÷ 0020 × 0308 ÷ 000D ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [3.2] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 000D ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [3.2] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
÷ 0020 ÷ 000A ÷ # ÷ [0.2] SPACE (WSegSpace) ÷ [3.2] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
# ÷ 0020 × 0308 ÷ 000A ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [3.2] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 000A ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [3.2] <LINE FEED (LF)> (LF) ÷ [0.3]
|
||||
÷ 0020 ÷ 000B ÷ # ÷ [0.2] SPACE (WSegSpace) ÷ [3.2] <LINE TABULATION> (Newline) ÷ [0.3]
|
||||
# ÷ 0020 × 0308 ÷ 000B ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [3.2] <LINE TABULATION> (Newline) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 000B ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [3.2] <LINE TABULATION> (Newline) ÷ [0.3]
|
||||
÷ 0020 ÷ 3031 ÷ # ÷ [0.2] SPACE (WSegSpace) ÷ [999.0] VERTICAL KANA REPEAT MARK (Katakana) ÷ [0.3]
|
||||
# ÷ 0020 × 0308 ÷ 3031 ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] VERTICAL KANA REPEAT MARK (Katakana) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 3031 ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] VERTICAL KANA REPEAT MARK (Katakana) ÷ [0.3]
|
||||
÷ 0020 ÷ 0041 ÷ # ÷ [0.2] SPACE (WSegSpace) ÷ [999.0] LATIN CAPITAL LETTER A (ALetter) ÷ [0.3]
|
||||
# ÷ 0020 × 0308 ÷ 0041 ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LATIN CAPITAL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 0041 ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LATIN CAPITAL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0020 ÷ 003A ÷ # ÷ [0.2] SPACE (WSegSpace) ÷ [999.0] COLON (MidLetter) ÷ [0.3]
|
||||
# ÷ 0020 × 0308 ÷ 003A ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] COLON (MidLetter) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 003A ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] COLON (MidLetter) ÷ [0.3]
|
||||
÷ 0020 ÷ 002C ÷ # ÷ [0.2] SPACE (WSegSpace) ÷ [999.0] COMMA (MidNum) ÷ [0.3]
|
||||
# ÷ 0020 × 0308 ÷ 002C ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] COMMA (MidNum) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 002C ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] COMMA (MidNum) ÷ [0.3]
|
||||
÷ 0020 ÷ 002E ÷ # ÷ [0.2] SPACE (WSegSpace) ÷ [999.0] FULL STOP (MidNumLet) ÷ [0.3]
|
||||
# ÷ 0020 × 0308 ÷ 002E ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] FULL STOP (MidNumLet) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 002E ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] FULL STOP (MidNumLet) ÷ [0.3]
|
||||
÷ 0020 ÷ 0030 ÷ # ÷ [0.2] SPACE (WSegSpace) ÷ [999.0] DIGIT ZERO (Numeric) ÷ [0.3]
|
||||
# ÷ 0020 × 0308 ÷ 0030 ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ZERO (Numeric) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 0030 ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ZERO (Numeric) ÷ [0.3]
|
||||
÷ 0020 ÷ 005F ÷ # ÷ [0.2] SPACE (WSegSpace) ÷ [999.0] LOW LINE (ExtendNumLet) ÷ [0.3]
|
||||
# ÷ 0020 × 0308 ÷ 005F ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LOW LINE (ExtendNumLet) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 005F ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LOW LINE (ExtendNumLet) ÷ [0.3]
|
||||
÷ 0020 ÷ 1F1E6 ÷ # ÷ [0.2] SPACE (WSegSpace) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
|
||||
# ÷ 0020 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
|
||||
÷ 0020 ÷ 05D0 ÷ # ÷ [0.2] SPACE (WSegSpace) ÷ [999.0] HEBREW LETTER ALEF (Hebrew_Letter) ÷ [0.3]
|
||||
# ÷ 0020 × 0308 ÷ 05D0 ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] HEBREW LETTER ALEF (Hebrew_Letter) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 05D0 ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] HEBREW LETTER ALEF (Hebrew_Letter) ÷ [0.3]
|
||||
÷ 0020 ÷ 0022 ÷ # ÷ [0.2] SPACE (WSegSpace) ÷ [999.0] QUOTATION MARK (Double_Quote) ÷ [0.3]
|
||||
# ÷ 0020 × 0308 ÷ 0022 ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] QUOTATION MARK (Double_Quote) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 0022 ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] QUOTATION MARK (Double_Quote) ÷ [0.3]
|
||||
÷ 0020 ÷ 0027 ÷ # ÷ [0.2] SPACE (WSegSpace) ÷ [999.0] APOSTROPHE (Single_Quote) ÷ [0.3]
|
||||
# ÷ 0020 × 0308 ÷ 0027 ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] APOSTROPHE (Single_Quote) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 0027 ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] APOSTROPHE (Single_Quote) ÷ [0.3]
|
||||
÷ 0020 ÷ 231A ÷ # ÷ [0.2] SPACE (WSegSpace) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
|
||||
# ÷ 0020 × 0308 ÷ 231A ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
|
||||
# ÷ 0020 × 0020 ÷ # ÷ [0.2] SPACE (WSegSpace) × [3.4] SPACE (WSegSpace) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 231A ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
|
||||
÷ 0020 × 0020 ÷ # ÷ [0.2] SPACE (WSegSpace) × [3.4] SPACE (WSegSpace) ÷ [0.3]
|
||||
# ÷ 0020 × 0308 ÷ 0020 ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] SPACE (WSegSpace) ÷ [0.3]
|
||||
# ÷ 0020 × 00AD ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
|
||||
# ÷ 0020 × 0308 × 00AD ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
|
||||
# ÷ 0020 × 0300 ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
|
||||
# ÷ 0020 × 0308 × 0300 ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) × [4.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
|
||||
# ÷ 0020 × 200D ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] ZERO WIDTH JOINER (ZWJ_FE) ÷ [0.3]
|
||||
# ÷ 0020 × 0308 × 200D ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) × [4.0] ZERO WIDTH JOINER (ZWJ_FE) ÷ [0.3]
|
||||
÷ 0020 × 00AD ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
|
||||
÷ 0020 × 0308 × 00AD ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) × [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
|
||||
÷ 0020 × 0300 ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
|
||||
÷ 0020 × 0308 × 0300 ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) × [4.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
|
||||
÷ 0020 × 200D ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] ZERO WIDTH JOINER (ZWJ_FE) ÷ [0.3]
|
||||
÷ 0020 × 0308 × 200D ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) × [4.0] ZERO WIDTH JOINER (ZWJ_FE) ÷ [0.3]
|
||||
÷ 0020 ÷ 0061 × 2060 ÷ # ÷ [0.2] SPACE (WSegSpace) ÷ [999.0] LATIN SMALL LETTER A (ALetter) × [4.0] WORD JOINER (Format_FE) ÷ [0.3]
|
||||
# ÷ 0020 × 0308 ÷ 0061 × 2060 ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LATIN SMALL LETTER A (ALetter) × [4.0] WORD JOINER (Format_FE) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 0061 × 2060 ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LATIN SMALL LETTER A (ALetter) × [4.0] WORD JOINER (Format_FE) ÷ [0.3]
|
||||
÷ 0020 ÷ 0061 ÷ 003A ÷ # ÷ [0.2] SPACE (WSegSpace) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) ÷ [0.3]
|
||||
# ÷ 0020 × 0308 ÷ 0061 ÷ 003A ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 0061 ÷ 003A ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) ÷ [0.3]
|
||||
÷ 0020 ÷ 0061 ÷ 0027 ÷ # ÷ [0.2] SPACE (WSegSpace) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (Single_Quote) ÷ [0.3]
|
||||
# ÷ 0020 × 0308 ÷ 0061 ÷ 0027 ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (Single_Quote) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 0061 ÷ 0027 ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (Single_Quote) ÷ [0.3]
|
||||
÷ 0020 ÷ 0061 ÷ 0027 × 2060 ÷ # ÷ [0.2] SPACE (WSegSpace) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (Single_Quote) × [4.0] WORD JOINER (Format_FE) ÷ [0.3]
|
||||
# ÷ 0020 × 0308 ÷ 0061 ÷ 0027 × 2060 ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (Single_Quote) × [4.0] WORD JOINER (Format_FE) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 0061 ÷ 0027 × 2060 ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (Single_Quote) × [4.0] WORD JOINER (Format_FE) ÷ [0.3]
|
||||
÷ 0020 ÷ 0061 ÷ 002C ÷ # ÷ [0.2] SPACE (WSegSpace) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) ÷ [0.3]
|
||||
# ÷ 0020 × 0308 ÷ 0061 ÷ 002C ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 0061 ÷ 002C ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COMMA (MidNum) ÷ [0.3]
|
||||
÷ 0020 ÷ 0031 ÷ 003A ÷ # ÷ [0.2] SPACE (WSegSpace) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) ÷ [0.3]
|
||||
# ÷ 0020 × 0308 ÷ 0031 ÷ 003A ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 0031 ÷ 003A ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) ÷ [0.3]
|
||||
÷ 0020 ÷ 0031 ÷ 0027 ÷ # ÷ [0.2] SPACE (WSegSpace) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] APOSTROPHE (Single_Quote) ÷ [0.3]
|
||||
# ÷ 0020 × 0308 ÷ 0031 ÷ 0027 ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] APOSTROPHE (Single_Quote) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 0031 ÷ 0027 ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] APOSTROPHE (Single_Quote) ÷ [0.3]
|
||||
÷ 0020 ÷ 0031 ÷ 002C ÷ # ÷ [0.2] SPACE (WSegSpace) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) ÷ [0.3]
|
||||
# ÷ 0020 × 0308 ÷ 0031 ÷ 002C ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 0031 ÷ 002C ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] COMMA (MidNum) ÷ [0.3]
|
||||
÷ 0020 ÷ 0031 ÷ 002E × 2060 ÷ # ÷ [0.2] SPACE (WSegSpace) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) ÷ [0.3]
|
||||
# ÷ 0020 × 0308 ÷ 0031 ÷ 002E × 2060 ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) ÷ [0.3]
|
||||
÷ 0020 × 0308 ÷ 0031 ÷ 002E × 2060 ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) ÷ [0.3]
|
||||
÷ 00AD ÷ 0001 ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) ÷ [999.0] <START OF HEADING> (Other) ÷ [0.3]
|
||||
÷ 00AD × 0308 ÷ 0001 ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] <START OF HEADING> (Other) ÷ [0.3]
|
||||
÷ 00AD ÷ 000D ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) ÷ [3.2] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
|
||||
@ -1706,7 +1706,7 @@
|
||||
÷ 0031 × 002E × 2060 × 0308 × 0031 ÷ 002E × 2060 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [12.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) × [11.0] DIGIT ONE (Numeric) ÷ [999.0] FULL STOP (MidNumLet) × [4.0] WORD JOINER (Format_FE) ÷ [0.3]
|
||||
÷ 000D × 000A ÷ 0061 ÷ 000A ÷ 0308 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) × [3.0] <LINE FEED (LF)> (LF) ÷ [3.1] LATIN SMALL LETTER A (ALetter) ÷ [3.2] <LINE FEED (LF)> (LF) ÷ [3.1] COMBINING DIAERESIS (Extend_FE) ÷ [0.3]
|
||||
÷ 0061 × 0308 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [0.3]
|
||||
# ÷ 0020 × 200D ÷ 0646 ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] ZERO WIDTH JOINER (ZWJ_FE) ÷ [999.0] ARABIC LETTER NOON (ALetter) ÷ [0.3]
|
||||
÷ 0020 × 200D ÷ 0646 ÷ # ÷ [0.2] SPACE (WSegSpace) × [4.0] ZERO WIDTH JOINER (ZWJ_FE) ÷ [999.0] ARABIC LETTER NOON (ALetter) ÷ [0.3]
|
||||
÷ 0646 × 200D ÷ 0020 ÷ # ÷ [0.2] ARABIC LETTER NOON (ALetter) × [4.0] ZERO WIDTH JOINER (ZWJ_FE) ÷ [999.0] SPACE (WSegSpace) ÷ [0.3]
|
||||
÷ 0041 × 0041 × 0041 ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (ALetter) × [5.0] LATIN CAPITAL LETTER A (ALetter) × [5.0] LATIN CAPITAL LETTER A (ALetter) ÷ [0.3]
|
||||
÷ 0041 × 003A × 0041 ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (ALetter) × [6.0] COLON (MidLetter) × [7.0] LATIN CAPITAL LETTER A (ALetter) ÷ [0.3]
|
||||
@ -1736,7 +1736,7 @@
|
||||
# ÷ 200D × 1F6D1 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ_FE) × [3.3] OCTAGONAL SIGN (ExtPict) ÷ [0.3]
|
||||
÷ 1F6D1 ÷ 1F6D1 ÷ # ÷ [0.2] OCTAGONAL SIGN (ExtPict) ÷ [999.0] OCTAGONAL SIGN (ExtPict) ÷ [0.3]
|
||||
÷ 0061 × 0308 × 200D × 0308 × 0062 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) × [4.0] COMBINING DIAERESIS (Extend_FE) × [4.0] ZERO WIDTH JOINER (ZWJ_FE) × [4.0] COMBINING DIAERESIS (Extend_FE) × [5.0] LATIN SMALL LETTER B (ALetter) ÷ [0.3]
|
||||
# ÷ 0061 ÷ 0020 × 0020 ÷ 0062 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] SPACE (WSegSpace) × [3.4] SPACE (WSegSpace) ÷ [999.0] LATIN SMALL LETTER B (ALetter) ÷ [0.3]
|
||||
÷ 0061 ÷ 0020 × 0020 ÷ 0062 ÷ # ÷ [0.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] SPACE (WSegSpace) × [3.4] SPACE (WSegSpace) ÷ [999.0] LATIN SMALL LETTER B (ALetter) ÷ [0.3]
|
||||
÷ 0031 ÷ 003A ÷ 003A ÷ 0031 ÷ # ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0031 × 005F × 0031 ÷ 003A ÷ 003A ÷ 0031 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [13.1] LOW LINE (ExtendNumLet) × [13.2] DIGIT ONE (Numeric) ÷ [999.0] COLON (MidLetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
÷ 0031 × 005F × 0061 ÷ 003A ÷ 003A ÷ 0031 ÷ # ÷ [0.2] DIGIT ONE (Numeric) × [13.1] LOW LINE (ExtendNumLet) × [13.2] LATIN SMALL LETTER A (ALetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] COLON (MidLetter) ÷ [999.0] DIGIT ONE (Numeric) ÷ [0.3]
|
||||
|
@ -420,9 +420,9 @@ void tst_QTextBoundaryFinder::wordBoundaries_manual_data()
|
||||
{
|
||||
QString testString(QString::fromUtf8("This is a sample buffer.Please test me . He's don't Le'Clerk."));
|
||||
QList<int> expectedBreakPositions, expectedStartPositions, expectedEndPositions;
|
||||
expectedBreakPositions << 0 << 4 << 5 << 7 << 8 << 9 << 10 << 11 << 12 << 13 << 14 << 20 << 21 << 27
|
||||
<< 28 << 34 << 35 << 39 << 40 << 42 << 43 << 44 << 45 << 46 << 47 << 48
|
||||
<< 49 << 53 << 54 << 59 << 60 << 68 << 69;
|
||||
expectedBreakPositions << 0 << 4 << 5 << 7 << 12 << 13 << 14 << 20 << 21 << 27 << 28 << 34
|
||||
<< 35 << 39 << 40 << 42 << 43 << 44 << 49 << 53 << 54 << 59 << 60
|
||||
<< 68 << 69;
|
||||
expectedStartPositions << 0 << 5 << 12 << 14 << 21 << 28 << 35 << 40 << 49 << 54 << 60;
|
||||
expectedEndPositions << 4 << 7 << 13 << 20 << 27 << 34 << 39 << 42 << 53 << 59 << 68;
|
||||
|
||||
|
Loading…
x
Reference in New Issue
Block a user