diff --git a/Makefile b/Makefile index bb58a95..108b6c5 100644 --- a/Makefile +++ b/Makefile @@ -318,14 +318,15 @@ endif KMAPS=Arabic.kmap ArmenianEast.kmap ArmenianWest.kmap Chinese-CJ.kmap \ Cyrillic.kmap Czech.kmap DE-RU.kmap Danish.kmap Dutch.kmap \ Esperanto.kmap Ethiopic.kmap French.kmap Georgian.kmap German.kmap \ - Greek.kmap GreekMono.kmap Guarani.kmap Hebrew.kmap \ + Greek.kmap GreekMono.kmap Guarani.kmap HebrewP.kmap \ Hungarian.kmap \ KOI8_R.kmap Lithuanian.kmap Mnemonic.kmap Polish.kmap \ Russian.kmap SGML.kmap TeX.kmap Troff.kmap VNtelex.kmap \ Vietnamese.kmap XKB_iso8859-4.kmap \ DanishAlternate.kmap GreekBible.kmap Polytonic.kmap Spanish.kmap \ - Thai.kmap VietnameseTelex.kmap Welsh.kmap -# HebrewIsraeli.kmap Kana.kmap + Thai.kmap VietnameseTelex.kmap Welsh.kmap \ + Hebrew.kmap HebrewIsraeli.kmap HebrewP.kmap Israeli.kmap Yiddish.kmap \ + Kana.kmap # Hangul.kmap Hangul2.kmap Hangul3.kmap Unicode2.kmap #KMAPS_DIR=$(prefix)/share/yudit/data KMAPS_DIR=kmap diff --git a/charsetmore.c b/charsetmore.c index 6ab1d7e..18393c3 100644 --- a/charsetmore.c +++ b/charsetmore.c @@ -475,7 +475,7 @@ static QECharset charset_8859_15 = { /*---------------------------------------------------------------- * filename: cp/8859-16.TXT - * iso_name: ISO 8859-16 (Romainian) + * iso_name: ISO 8859-16 (Romanian) * name: 8859-16 * id: 8859_16 */ diff --git a/clang.c b/clang.c index a963f37..0237e66 100644 --- a/clang.c +++ b/clang.c @@ -178,6 +178,11 @@ void c_colorize_line(unsigned int *buf, int len, type_decl = 1; } set_color(p_start, p1 - p_start, QE_STYLE_TYPE); + } else + if (*p == '(') { + /* function call */ + /* XXX: different styles for call and definition */ + set_color(p_start, p1 - p_start, QE_STYLE_FUNCTION); } else { /* assume typedef if starting at first column */ if (p_start == buf) @@ -209,7 +214,7 @@ void c_colorize_line(unsigned int *buf, int len, #define MAX_BUF_SIZE 512 #define MAX_STACK_SIZE 64 -/* gives the position of the first non while space character in +/* gives the position of the first non white space character in buf. TABs are counted correctly */ static int find_indent1(EditState *s, unsigned int *buf) { diff --git a/cp/cpdata.txt b/cp/cpdata.txt index 08bb91c..becaf4b 100644 --- a/cp/cpdata.txt +++ b/cp/cpdata.txt @@ -74,7 +74,7 @@ ISO 8859-15 (Western European) include 8859-15.TXT [8859-16] -ISO 8859-16 (Romainian) +ISO 8859-16 (Romanian) "ISO-8859-16", "8859-16", "latin10", "l10" include 8859-16.TXT diff --git a/input.c b/input.c index ff3711f..109da03 100644 --- a/input.c +++ b/input.c @@ -25,7 +25,9 @@ InputMethod *input_methods; -static int default_input(__unused__ int *match_len_ptr, +static int default_input(__unused__ int *match_buf, + __unused__ int match_buf_size, + __unused__ int *match_len_ptr, __unused__ const u8 *data, __unused__ const unsigned int *buf, __unused__ int len) @@ -33,7 +35,9 @@ static int default_input(__unused__ int *match_len_ptr, return INPUTMETHOD_NOMATCH; } -static int unicode_input(int *match_len_ptr, +static int unicode_input(int *match_buf, + int match_buf_size, + int *match_len_ptr, __unused__ const u8 *data, const unsigned int *buf, int len) { @@ -52,7 +56,8 @@ static int unicode_input(int *match_len_ptr, } if (len == 5) { *match_len_ptr = len; - return c; + match_buf[0] = c; + return 1; } else { return INPUTMETHOD_MORECHARS; } @@ -83,12 +88,14 @@ static void register_input_method(InputMethod *m) /* XXX: use an edit buffer to access the kmap !!!! */ /* parse the internal compressed input method format */ -static int kmap_input(int *match_len_ptr, - const u8 *data, const unsigned int *buf, int len) +static int kmap_input(int *match_buf, int match_buf_size, + int *match_len_ptr, const u8 *data, + const unsigned int *buf, int len) { - const u8 *p, *p1; - int c, d, i, l, l1, match_len, match_char, match_count, match_real_len; - int nb_prefixes, last_outputc, match, prefix_len, trailing_space; + const u8 *p, *p1, *match_extra; + int c, flag, i, l, l1, match_len, match_char, match_count, match_real_len; + int match_olen; + int nb_prefixes, last_outputc, match, prefix_len, trailing_space, olen; p = data; nb_prefixes = p[0] & 0x7f; @@ -113,27 +120,50 @@ static int kmap_input(int *match_len_ptr, match_char = 0; match_count = 0; last_outputc = 0; + match_olen = 0; + match_extra = NULL; for (;;) { match = 1; + olen = 1; l1 = prefix_len; /* length of input pattern */ for (;;) { + /* c = 0x00 end of table + * c = 0x01..0x1d delta unicode + * c = 0x1e unicode output mapping follows + * c = 0x1f unicode input char follows. + * c = 0x20..0x7f input character + * c = 0x80 unused + * c = 0x81 unused + * c = 0x82..0x9d extra unicode outputs follow + * c = 0x9e first unicode output mapping follows + * c = 0x9f last unicode input char follows and delta==1. + * c = 0xa0..0xff last input character and delta==1 + */ c = *p++; - d = c & 0x80; - c = c & 0x7f; + flag = c & 0x80; + c &= 0x7f; if (c == 0) { - /* end of table */ + /* end of table / unused */ goto the_end; } else - if (c <= 0x1d) { - /* delta */ - last_outputc += c; + if (c < 0x1e) { + if (flag) { + /* extra output glyphs */ + olen = c; + } else { + /* delta */ + last_outputc += c; + } break; } else if (c == 0x1e) { /* explicit output */ last_outputc = (p[0] << 8) | p[1]; p += 2; - break; + if (flag) + continue; + else + break; } else if (c == 0x1f) { /* unicode value */ @@ -143,7 +173,7 @@ static int kmap_input(int *match_len_ptr, if (l1 < len && c != (int)buf[l1]) match = 0; l1++; - if (d) { + if (flag) { /* delta = 1 */ last_outputc++; break; @@ -161,22 +191,34 @@ static int kmap_input(int *match_len_ptr, l = len; if (l == match_len) { match_count++; - } else if (l > match_len) { + } else + if (l > match_len) { match_len = l; match_real_len = l1; match_char = last_outputc; match_count = 1; + match_olen = olen; + match_extra = p; } } + p += (olen - 1) << 1; } -the_end: + the_end: if (match_len == 0) { return INPUTMETHOD_NOMATCH; - } else if (match_count > 1 || match_real_len > len) { + } else + if (match_count > 1 || match_real_len > len) { return INPUTMETHOD_MORECHARS; } else { *match_len_ptr = match_len; - return match_char; + if (match_buf_size > 0) { + match_buf[0] = match_char; + p = match_extra; + for (i = 1; i < match_olen && i < match_buf_size; i++, p += 2) { + match_buf[i] = (p[0] << 8) + p[1]; + } + } + return match_olen; } } diff --git a/kmap/Arabic.kmap b/kmap/Arabic.kmap index e5c44d6..e15bb0e 100644 --- a/kmap/Arabic.kmap +++ b/kmap/Arabic.kmap @@ -1,6 +1,8 @@ -// Experimental Arabic.kmap for Yudit +// This kmap file was generated from +// The Experimental Arabic.kmap // 1998-06-18 Roman Czyborra@cs.tu-berlin.de - +// By Gaspar Sinai's perl script ./arabickmap.pl at 2001-12-05. +// "$=0x064C", // ٌ = ARABIC DAMMATAN "%=0x064F", // ُ = ARABIC DAMMA "&=0x0651", // ّ = ARABIC SHADDA @@ -66,3 +68,13 @@ "z=0x0632", // ز = ARABIC LETTER ZAIN "zH=0x0638", // ظ = ARABIC LETTER ZAH "zJ=0x0698", // ژ = ARABIC LETTER JEH +// +// Shaping part using shape.mys. Autogenerated. +// +"l aM=0x0644 0x0622", // لآ LAM ALEF WITH MADDA ABOVE +"l aH=0x0644 0x0623", // لأ LAM ALEF WITH HAMZA ABOVE +"l aB=0x0644 0x0625", // لإ LAM ALEF WITH HAMZA BELOW +"l a=0x0644 0x0627", // لا LAM ALEF +// +// End of shaping part. Autogenerated. +// diff --git a/kmap/Czech.kmap b/kmap/Czech.kmap index 032a720..4b99487 100644 --- a/kmap/Czech.kmap +++ b/kmap/Czech.kmap @@ -1,36 +1,55 @@ // Czech kmap v1.1 1999/11/30 11:36:00 // send your criticism to roman@czyborra.com +// +// modified by Radovan Garabík +// to include ä, ĺ, ľ, ó, ô, ö, ŕ, ú, ü and capital variants +// (Slovak letters and letters commonly occuring in Czech and Slovak texts) + ",,=0x201E", // „ = DOUBLE LOW-9 QUOTATION MARK = "``=0x201C", // “ = LEFT DOUBLE QUOTATION MARK = "A'=0x00C1", // Á = LATIN CAPITAL LETTER A WITH ACUTE +"A:=0x00C4", // Ä = LATIN CAPITAL LETTER A WITH DIARESIS "C$=0x00A4", // ¤ = CURRENCY SIGN "C<=0x010C", // Č = LATIN CAPITAL LETTER C WITH CARON "D<=0x010E", // Ď = LATIN CAPITAL LETTER D WITH CARON "E'=0x00C9", // É = LATIN CAPITAL LETTER E WITH ACUTE "E<=0x011A", // Ě = LATIN CAPITAL LETTER E WITH CARON "I'=0x00CD", // Í = LATIN CAPITAL LETTER I WITH ACUTE +"L'=0x0139", // Ĺ = LATIN CAPITAL LETTER L WITH ACUTE +"L<=0x013D", // Ľ = LATIN CAPITAL LETTER L WITH CARON "N<=0x0147", // Ň = LATIN CAPITAL LETTER N WITH CARON "O'=0x00D3", // Ó = LATIN CAPITAL LETTER O WITH ACUTE +"O^=0x00D4", // Ô = LATIN CAPITAL LETTER O WITH CIRCUMFLEX +"O:=0x00D6", // Ö = LATIN CAPITAL LETTER O WITH DIARESIS +"R'=0x0154", // Ŕ = LATIN CAPITAL LETTER R WITH ACUTE "R<=0x0158", // Ř = LATIN CAPITAL LETTER R WITH CARON "S<=0x0160", // Š = LATIN CAPITAL LETTER S WITH CARON "T<=0x0164", // Ť = LATIN CAPITAL LETTER T WITH CARON "U'=0x00DA", // Ú = LATIN CAPITAL LETTER U WITH ACUTE "U0=0x016E", // Ů = LATIN CAPITAL LETTER U WITH RING ABOVE +"U:=0x00DC", // Ü = LATIN CAPITAL LETTER U WITH DIARESIS "Y'=0x00DD", // Ý = LATIN CAPITAL LETTER Y WITH ACUTE "Z<=0x017D", // Ž = LATIN CAPITAL LETTER Z WITH CARON "a'=0x00E1", // á = LATIN SMALL LETTER A WITH ACUTE +"a:=0x00E4", // ä = LATIN SMALL LETTER A WITH DIARESIS "c<=0x010D", // č = LATIN SMALL LETTER C WITH CARON "d<=0x010F", // ď = LATIN SMALL LETTER D WITH CARON "e'=0x00E9", // é = LATIN SMALL LETTER E WITH ACUTE "e<=0x011B", // ě = LATIN SMALL LETTER E WITH CARON "i'=0x00ED", // í = LATIN SMALL LETTER I WITH ACUTE +"l'=0x013A", // ĺ = LATIN SMALL LETTER L WITH ACUTE +"l<=0x013E", // ľ = LATIN SMALL LETTER L WITH CARON "n<=0x0148", // ň = LATIN SMALL LETTER N WITH CARON "o'=0x00F3", // ó = LATIN SMALL LETTER O WITH ACUTE +"o^=0x00F4", // ô = LATIN SMALL LETTER O WITH CIRCUMFLEX +"o:=0x00F6", // ö = LATIN SMALL LETTER O WITH DIARESIS +"r'=0x0155", // ŕ = LATIN SMALL LETTER R WITH ACUTE "r<=0x0159", // ř = LATIN SMALL LETTER R WITH CARON "s<=0x0161", // š = LATIN SMALL LETTER S WITH CARON "t<=0x0165", // ť = LATIN SMALL LETTER T WITH CARON "u'=0x00FA", // ú = LATIN SMALL LETTER U WITH ACUTE "u0=0x016F", // ů = LATIN SMALL LETTER U WITH RING ABOVE +"u:=0x00FC", // ü = LATIN SMALL LETTER U WITH DIARESIS "y'=0x00FD", // ý = LATIN SMALL LETTER Y WITH ACUTE "z<=0x017E", // ž = LATIN SMALL LETTER Z WITH CARON diff --git a/kmap/Esperanto.kmap b/kmap/Esperanto.kmap index 023374d..e5aa154 100644 --- a/kmap/Esperanto.kmap +++ b/kmap/Esperanto.kmap @@ -5,12 +5,21 @@ // 1998-04-20 Roman Czyborra +// 2001-11-13: Modified by Bertil Wennergren +// to work with all-caps typing + "Cx=0x0108", // Ĉ = latin capital letter c with circumflex +"CX=0x0108", // Ĉ = latin capital letter c with circumflex "Gx=0x011C", // Ĝ = latin capital letter g with circumflex +"GX=0x011C", // Ĝ = latin capital letter g with circumflex "Hx=0x0124", // Ĥ = latin capital letter h with circumflex +"HX=0x0124", // Ĥ = latin capital letter h with circumflex "Jx=0x0134", // Ĵ = latin capital letter j with circumflex +"JX=0x0134", // Ĵ = latin capital letter j with circumflex "Sx=0x015C", // Ŝ = latin capital letter s with circumflex +"SX=0x015C", // Ŝ = latin capital letter s with circumflex "Ux=0x016C", // Ŭ = latin capital letter u with breve +"UX=0x016C", // Ŭ = latin capital letter u with breve "cx=0x0109", // ĉ = latin small letter c with circumflex "gx=0x011D", // ĝ = latin small letter g with circumflex "hx=0x0125", // ĥ = latin small letter h with circumflex diff --git a/kmap/French.kmap b/kmap/French.kmap index 3af9ea6..4164948 100644 --- a/kmap/French.kmap +++ b/kmap/French.kmap @@ -1,6 +1,9 @@ // French.kmap for the Unicode text editor Yudit // 1998-06-10 roman@czyborra.com - improvements welcome +// 2004-07-05 Modified by Yves Codet +"~=0x00A0", //   = NO-BREAK SPACE +"'=0x2019", // ’ = RIGHT SINGLE QUOTATION MARK (APOSTROPHE) "<<=0x00AB", // « = LEFT-POINTING DOUBLE ANGLE QUOTATION MARK ">>=0x00BB", // » = RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK "e'=0x00E9", // é = LATIN SMALL LETTER E WITH ACUTE diff --git a/kmap/German.kmap b/kmap/German.kmap index 5b19d42..8024fe9 100644 --- a/kmap/German.kmap +++ b/kmap/German.kmap @@ -1,5 +1,13 @@ // German.kmap for the Unicode editor Yudit // 1998-04-17 Roman Czyborra@cs.tu-berlin.de +// Changes: +// 202-04-02 Gaspar Sinai : +// o added die Auslassungspunkte ellipsis dots omission marks … +// o added der Gedankenstrich long dash – + +"...=0x2026", // … die Auslassungspunkte +"--=0x2013", // – der Gedankenstrich +"'' = 0x201D", // “ RIGHT DOUBLE QUOTATION MARK // „German“ quotation marks: diff --git a/kmap/Hangul2.kmap b/kmap/Hangul2.kmap index c368868..c436513 100644 --- a/kmap/Hangul2.kmap +++ b/kmap/Hangul2.kmap @@ -50,7 +50,7 @@ "end vowel", "begin consonant3", - "=0x0000", +// "=0x0000", "r=0x0001", "R=0x0002", "rt=0x0003", diff --git a/kmap/Hangul3.kmap b/kmap/Hangul3.kmap index d83fe85..1cd4378 100644 --- a/kmap/Hangul3.kmap +++ b/kmap/Hangul3.kmap @@ -32,7 +32,7 @@ "t=0x0070", "c=0x008C", "e=0x00A8", - "0x37e=0x00C4", + "0x37=0x00C4", "/=0x00E0", "v=0x00E0", "/f=0x00FC", @@ -58,7 +58,7 @@ "begin e", // this should be made legal, sweat here - "=0x0000", +// "=0x0000", "x=0x0001", "!=0x0002", "V=0x0003", diff --git a/kmap/Hebrew.kmap b/kmap/Hebrew.kmap index 89dc57e..ef271d3 100644 --- a/kmap/Hebrew.kmap +++ b/kmap/Hebrew.kmap @@ -1,33 +1,50 @@ // Hebrew.kmap for Yudit -// 1998-06-17 Roman Czyborra@cs.tu-berlin.de +// 2001-01-30 Raphael Finkel raphael@cs.uky.edu -// These are the Hebrew letters from ISO-8859-6 -// at hopefully not too surprising ASCII keys: +// These are the Yiddish letters, according to the UYIP mapping convention -"a=0x05D0", // א = HEBREW LETTER ALEF -"b=0x05D1", // ב = HEBREW LETTER BET -"g=0x05D2", // ג = HEBREW LETTER GIMEL -"d=0x05D3", // ד = HEBREW LETTER DALET -"h=0x05D4", // ה = HEBREW LETTER HE -"v=0x05D5", // ו = HEBREW LETTER VAV -"z=0x05D6", // ז = HEBREW LETTER ZAYIN -"x=0x05D7", // ח = HEBREW LETTER HET -"y=0x05D8", // ט = HEBREW LETTER TET -"j=0x05D9", // י = HEBREW LETTER YOD -"k;=0x05DA", // ך = HEBREW LETTER FINAL KAF -"k=0x05DB", // כ = HEBREW LETTER KAF -"l=0x05DC", // ל = HEBREW LETTER LAMED -"m;=0x05DD", // ם = HEBREW LETTER FINAL MEM -"m=0x05DE", // מ = HEBREW LETTER MEM -"n;=0x05DF", // ן = HEBREW LETTER FINAL NUN -"n=0x05E0", // נ = HEBREW LETTER NUN -"s=0x05E1", // ס = HEBREW LETTER SAMEKH -"e=0x05E2", // ע = HEBREW LETTER AYIN -"p;=0x05E3", // ף = HEBREW LETTER FINAL PE -"p=0x05E4", // פ = HEBREW LETTER PE -"c;=0x05E5", // ץ = HEBREW LETTER FINAL TSADI -"c=0x05E6", // צ = HEBREW LETTER TSADI -"q=0x05E7", // ק = HEBREW LETTER QOF -"r=0x05E8", // ר = HEBREW LETTER RESH -"w=0x05E9", // ש = HEBREW LETTER SHIN -"t=0x05EA", // ת = HEBREW LETTER TAV +"a=0x05D0 0x05b7", // HEBREW LETTER ALEF, HEBREW POINT PATAH +"A=0x05D0", // HEBREW LETTER ALEF +"B=0x05D1 0x05BF", // HEBREW LETTER BET, HEBREW POINT RAFE +"b=0x05D1", // HEBREW LETTER BET +"c=0x05E6", // HEBREW LETTER TSADI +"C=0x05E5", // HEBREW LETTER FINAL TSADI +"d=0x05D3", // HEBREW LETTER DALET +"e=0x05E2", // HEBREW LETTER AYIN +"E=0x05F2", // HEBREW LIGATURE YIDDISH DOUBLE YOD +"f=0x05E4 0x05BF", // HEBREW LETTER PE, HEBREW POINT RAFE +"F=0x05E3", // HEBREW LETTER FINAL PE +"g=0x05D2", // HEBREW LETTER GIMEL +"h=0x05D4", // HEBREW LETTER HE +"H=0x05D7", // HEBREW LETTER HET +"i=0x05D9", // HEBREW LETTER YOD +"I=0x05D9 0x05B4", // HEBREW LETTER YOD, HEBREW POINT HIRIQ +"j=0x05F2", // HEBREW LIGATURE YIDDISH DOUBLE YOD +"J=0x05F2 0x05B7", // HEBREW LIGATURE YIDDISH DOUBLE YOD, HEBREW POINT PATAH +"k=0x05E7", // HEBREW LETTER QOF +"K=0x05DB 0x05BC", // HEBREW LETTER KAF, HEBREW POINT DAGESH OR MAPIQ +"l=0x05DC", // HEBREW LETTER LAMED +"m=0x05DE", // HEBREW LETTER MEM +"M=0x05DD", // HEBREW LETTER FINAL MEM +"n=0x05E0", // HEBREW LETTER NUN +"N=0x05DF", // HEBREW LETTER FINAL NUN +"o=0x05D0 0x05B8", // HEBREW LETTER ALEF, HEBREW POINT QAMATS +"O=0x05F1", // HEBREW LIGATURE YIDDISH VAV YOD +"p=0x05E4 0x05BC", // HEBREW LETTER PE, HEBREW POINT DAGESH OR MAPIQ +"q=0x05F2 0x05B7", // HEBREW LIGATURE YIDDISH DOUBLE YOD, HEBREW POINT PATAH +"r=0x05E8", // HEBREW LETTER RESH +"s=0x05E1", // HEBREW LETTER SAMEKH +"S=0x05EA", // HEBREW LETTER TAV +"t=0x05D8", // HEBREW LETTER TET +"T=0x05EA 0x05BC", // HEBREW LETTER TAV, HEBREW POINT DAGESH OR MAPIQ +"u=0x05D5", // HEBREW LETTER VAV +"U=0x05D5 0x05BC", // HEBREW LETTER VAV, HEBREW POINT DAGESH OR MAPIQ +"v=0x05F0", // HEBREW LIGATURE YIDDISH DOUBLE VAV +"V=0x05D1 0x05BF", // HEBREW LETTER BET, HEBREW POINT RAFE +"w=0x05E9", // HEBREW LETTER SHIN +"W=0x05E9 0x05C2", // HEBREW LETTER SHIN, HEBREW POINT SIN DOT +"x=0x05DB", // HEBREW LETTER KAF +"X=0x05DA", // HEBREW LETTER FINAL KAF +"y=0x05D9", // HEBREW LETTER YOD +"Y=0x05F2 0x05B7", // HEBREW LIGATURE YIDDISH DOUBLE YOD, HEBREW POINT PATAH +"z=0x05D6", // HEBREW LETTER ZAYIN diff --git a/kmap/HebrewP.kmap b/kmap/HebrewP.kmap new file mode 100644 index 0000000..89dc57e --- /dev/null +++ b/kmap/HebrewP.kmap @@ -0,0 +1,33 @@ +// Hebrew.kmap for Yudit +// 1998-06-17 Roman Czyborra@cs.tu-berlin.de + +// These are the Hebrew letters from ISO-8859-6 +// at hopefully not too surprising ASCII keys: + +"a=0x05D0", // א = HEBREW LETTER ALEF +"b=0x05D1", // ב = HEBREW LETTER BET +"g=0x05D2", // ג = HEBREW LETTER GIMEL +"d=0x05D3", // ד = HEBREW LETTER DALET +"h=0x05D4", // ה = HEBREW LETTER HE +"v=0x05D5", // ו = HEBREW LETTER VAV +"z=0x05D6", // ז = HEBREW LETTER ZAYIN +"x=0x05D7", // ח = HEBREW LETTER HET +"y=0x05D8", // ט = HEBREW LETTER TET +"j=0x05D9", // י = HEBREW LETTER YOD +"k;=0x05DA", // ך = HEBREW LETTER FINAL KAF +"k=0x05DB", // כ = HEBREW LETTER KAF +"l=0x05DC", // ל = HEBREW LETTER LAMED +"m;=0x05DD", // ם = HEBREW LETTER FINAL MEM +"m=0x05DE", // מ = HEBREW LETTER MEM +"n;=0x05DF", // ן = HEBREW LETTER FINAL NUN +"n=0x05E0", // נ = HEBREW LETTER NUN +"s=0x05E1", // ס = HEBREW LETTER SAMEKH +"e=0x05E2", // ע = HEBREW LETTER AYIN +"p;=0x05E3", // ף = HEBREW LETTER FINAL PE +"p=0x05E4", // פ = HEBREW LETTER PE +"c;=0x05E5", // ץ = HEBREW LETTER FINAL TSADI +"c=0x05E6", // צ = HEBREW LETTER TSADI +"q=0x05E7", // ק = HEBREW LETTER QOF +"r=0x05E8", // ר = HEBREW LETTER RESH +"w=0x05E9", // ש = HEBREW LETTER SHIN +"t=0x05EA", // ת = HEBREW LETTER TAV diff --git a/kmap/HebrewR.kmap b/kmap/HebrewR.kmap new file mode 100644 index 0000000..ef271d3 --- /dev/null +++ b/kmap/HebrewR.kmap @@ -0,0 +1,50 @@ +// Hebrew.kmap for Yudit +// 2001-01-30 Raphael Finkel raphael@cs.uky.edu + +// These are the Yiddish letters, according to the UYIP mapping convention + +"a=0x05D0 0x05b7", // HEBREW LETTER ALEF, HEBREW POINT PATAH +"A=0x05D0", // HEBREW LETTER ALEF +"B=0x05D1 0x05BF", // HEBREW LETTER BET, HEBREW POINT RAFE +"b=0x05D1", // HEBREW LETTER BET +"c=0x05E6", // HEBREW LETTER TSADI +"C=0x05E5", // HEBREW LETTER FINAL TSADI +"d=0x05D3", // HEBREW LETTER DALET +"e=0x05E2", // HEBREW LETTER AYIN +"E=0x05F2", // HEBREW LIGATURE YIDDISH DOUBLE YOD +"f=0x05E4 0x05BF", // HEBREW LETTER PE, HEBREW POINT RAFE +"F=0x05E3", // HEBREW LETTER FINAL PE +"g=0x05D2", // HEBREW LETTER GIMEL +"h=0x05D4", // HEBREW LETTER HE +"H=0x05D7", // HEBREW LETTER HET +"i=0x05D9", // HEBREW LETTER YOD +"I=0x05D9 0x05B4", // HEBREW LETTER YOD, HEBREW POINT HIRIQ +"j=0x05F2", // HEBREW LIGATURE YIDDISH DOUBLE YOD +"J=0x05F2 0x05B7", // HEBREW LIGATURE YIDDISH DOUBLE YOD, HEBREW POINT PATAH +"k=0x05E7", // HEBREW LETTER QOF +"K=0x05DB 0x05BC", // HEBREW LETTER KAF, HEBREW POINT DAGESH OR MAPIQ +"l=0x05DC", // HEBREW LETTER LAMED +"m=0x05DE", // HEBREW LETTER MEM +"M=0x05DD", // HEBREW LETTER FINAL MEM +"n=0x05E0", // HEBREW LETTER NUN +"N=0x05DF", // HEBREW LETTER FINAL NUN +"o=0x05D0 0x05B8", // HEBREW LETTER ALEF, HEBREW POINT QAMATS +"O=0x05F1", // HEBREW LIGATURE YIDDISH VAV YOD +"p=0x05E4 0x05BC", // HEBREW LETTER PE, HEBREW POINT DAGESH OR MAPIQ +"q=0x05F2 0x05B7", // HEBREW LIGATURE YIDDISH DOUBLE YOD, HEBREW POINT PATAH +"r=0x05E8", // HEBREW LETTER RESH +"s=0x05E1", // HEBREW LETTER SAMEKH +"S=0x05EA", // HEBREW LETTER TAV +"t=0x05D8", // HEBREW LETTER TET +"T=0x05EA 0x05BC", // HEBREW LETTER TAV, HEBREW POINT DAGESH OR MAPIQ +"u=0x05D5", // HEBREW LETTER VAV +"U=0x05D5 0x05BC", // HEBREW LETTER VAV, HEBREW POINT DAGESH OR MAPIQ +"v=0x05F0", // HEBREW LIGATURE YIDDISH DOUBLE VAV +"V=0x05D1 0x05BF", // HEBREW LETTER BET, HEBREW POINT RAFE +"w=0x05E9", // HEBREW LETTER SHIN +"W=0x05E9 0x05C2", // HEBREW LETTER SHIN, HEBREW POINT SIN DOT +"x=0x05DB", // HEBREW LETTER KAF +"X=0x05DA", // HEBREW LETTER FINAL KAF +"y=0x05D9", // HEBREW LETTER YOD +"Y=0x05F2 0x05B7", // HEBREW LIGATURE YIDDISH DOUBLE YOD, HEBREW POINT PATAH +"z=0x05D6", // HEBREW LETTER ZAYIN diff --git a/kmap/Hungarian.kmap b/kmap/Hungarian.kmap index 692a8ae..8969195 100644 --- a/kmap/Hungarian.kmap +++ b/kmap/Hungarian.kmap @@ -4,6 +4,10 @@ "A' = 0xc1", "A: = 0xc4", "E' = 0xc9", +"E$ = 0x20AC", +"e$ = 0x20AC", +"Y$ =0xFFE5", +"y$ =0x00A5", "I' = 0xcd", "O' = 0xd3", "O\" = 0x0150", @@ -23,4 +27,9 @@ "u' = 0xfa", "u\" = 0x0171", "u: = 0xfc", - +":) = 0x263A", +"'' = 0x201D", // ” RIGHT DOUBLE QUOTATION MARK +",,=0x201E", // „ DOUBLE LOW-9 QUOTATION MARK +"``=0x201C", // “ LEFT DOUBLE QUOTATION MARK +"...=0x2026", // … +"--=0x2013", // – diff --git a/kmap/Israeli.kmap b/kmap/Israeli.kmap new file mode 100644 index 0000000..cc33e7f --- /dev/null +++ b/kmap/Israeli.kmap @@ -0,0 +1,52 @@ +// Hebrew.kmap for Yudit +// 1998-06-17 Roman Czyborra@cs.tu-berlin.de + +// Changed from the il_phonetic map to the standard israeli map by +// Tzafrir Cohen + +"t=0x05D0", // א = HEBREW LETTER ALEF +"c=0x05D1", // ב = HEBREW LETTER BET +"d=0x05D2", // ג = HEBREW LETTER GIMEL +"s=0x05D3", // ד = HEBREW LETTER DALET +"v=0x05D4", // ה = HEBREW LETTER HE +"u=0x05D5", // ו = HEBREW LETTER VAV +"z=0x05D6", // ז = HEBREW LETTER ZAYIN +"j=0x05D7", // ח = HEBREW LETTER HET +"y=0x05D8", // ט = HEBREW LETTER TET +"h=0x05D9", // י = HEBREW LETTER YOD +"l=0x05DA", // ך = HEBREW LETTER FINAL KAF +"f=0x05DB", // כ = HEBREW LETTER KAF +"k=0x05DC", // ל = HEBREW LETTER LAMED +"o=0x05DD", // ם = HEBREW LETTER FINAL MEM +"n=0x05DE", // מ = HEBREW LETTER MEM +"i=0x05DF", // ן = HEBREW LETTER FINAL NUN +"b=0x05E0", // נ = HEBREW LETTER NUN +"x=0x05E1", // ס = HEBREW LETTER SAMEKH +"g=0x05E2", // ע = HEBREW LETTER AYIN +";=0x05E3", // ף = HEBREW LETTER FINAL PE +"p=0x05E4", // פ = HEBREW LETTER PE +".=0x05E5", // ץ = HEBREW LETTER FINAL TSADI +"m=0x05E6", // צ = HEBREW LETTER TSADI +"e=0x05E7", // ק = HEBREW LETTER QOF +"r=0x05E8", // ר = HEBREW LETTER RESH +"a=0x05E9", // ש = HEBREW LETTER SHIN +",=0x05EA", // ת = HEBREW LETTER TAV + +// Some other mappings that change, besides the letters themselves: +"q=0x002F", // slash (/) +"w=0x0027", // apostrophy (') +"`=0x003B", // smicolon (;) +"'=0x002C", // comma (,) +"/=0x002E", // dot (.) + +// There is said to be support for bidirectionality. If so: swapping +// between left and right parathensis might prove useful. Just in case +// Those should not mean "left-{brace|bracket|etc.}" and "right-" +// but "open-" and "close-" +// it does, I add the mapping remmed-out: +//"[=0x005D", // "]" +//"]=0x005B", // "[" +//"{=0x007D", // "}" +//"}=0x007B", // "{" +//"(=0x0029", // ")" +//")=0x0028", // "(" diff --git a/kmap/README b/kmap/README index c943122..3967572 100644 --- a/kmap/README +++ b/kmap/README @@ -58,3 +58,5 @@ imported: version 2.8.1 of yudit uses a compiled format. kmap files have moved to yudit-2.8.1/mytool/kmap + +imported fixes and more keymaps diff --git a/kmap/SGML.kmap b/kmap/SGML.kmap index 1342dd5..58ce160 100644 --- a/kmap/SGML.kmap +++ b/kmap/SGML.kmap @@ -4,6 +4,11 @@ // Gaspar Sinai's Unicode text editor Yudit // 1998-04-18 Roman Czyborra@cs.tu-berlin.de +// 2001-10-Jernej Kovacic +// The SGML keymap contains only small southern Slavic characters. I have added +// their capital "counterparts" which cover Slovene, Croatian and Serbian (in +// Latin transcription) languages. The 5 new characters are added at the end of +// the original file. "!=0x0021", "#=0x0023", @@ -693,5 +698,18 @@ "⧫=0x2726", "◊=0x2727", "&sextile;=0x2736", +// some southern Slavic (for Slovene, Croatian and Serbian in Latin transliteration) capital letters +"Č=0x010C", // LATIN CAPITAL LETTER C WITH CARON +"Š=0x0160", // LATIN CAPITAL LETTER S WITH CARON +"Ž=0x017D", // LATIN CAPITAL LETTER Z WITH CARON +"Ć=0x0106", // LATIN CAPITAL LETTER C WITH ACUTE +"Đ=0x0110", // LATIN CAPITAL LETTER D WITH STROKE +// Capital letters with diaeresis (umlaut), Euro +"Ä=0x00C4", // LATIN CAPITAL LETTER A WITH DIAERESIS +"Ë=0x00CB", // LATIN CAPITAL LETTER E WITH DIAERESIS +"Ï=0x00CF", // LATIN CAPITAL LETTER I WITH DIAERESIS +"Ö=0x00D6", // LATIN CAPITAL LETTER O WITH DIAERESIS +"Ü=0x00DC", // LATIN CAPITAL LETTER U WITH DIAERESIS - +"€=0x20AC", // EURO SIGN +"€=0x20AC", // EURO SIGN diff --git a/kmap/TeX.kmap b/kmap/TeX.kmap index 68a090a..a1fe578 100644 --- a/kmap/TeX.kmap +++ b/kmap/TeX.kmap @@ -1,4 +1,11 @@ // http://czyborra.com/yudit/TeX.kmap 1998-09-24 czyborra@dds.nl +// 12 June 2001 +// Jernej Kovacic added ex-Yugoslav characters +// "\\'{c}=0x0107", +// "\\'{C}=0x0106", +// "\\dj=0x0111", +// "\\DJ=0x0110", +// "\\Dj=0x0110", "!`=0x00a1", "?`=0x00bf", @@ -785,3 +792,8 @@ "_8=0x2088", "_9=0x2089", "_ 0x3D =0x208c", +"\\'{c}=0x0107", +"\\'{C}=0x0106", +"\\dj=0x0111", +"\\DJ=0x0110", +"\\Dj=0x0110", diff --git a/kmap/Yiddish.kmap b/kmap/Yiddish.kmap new file mode 100644 index 0000000..b99b831 --- /dev/null +++ b/kmap/Yiddish.kmap @@ -0,0 +1,147 @@ +// Yiddish.kmap for Yudit +// 2001-01-30 Raphael Finkel raphael@cs.uky.edu + +// These are the Yiddish letters, according to the UYIP mapping convention +// I have excluded the keystrokes using the key. +// I have added a few ligatures for YIVO input. + +"a=0x05D0 0x05b7", // HEBREW LETTER ALEF, HEBREW POINT PATAH +"ay=0x05F2 0x05B7", // HEBREW LIGATURE YIDDISH DOUBLE YOD, HEBREW POINT PATAH +"A=0x05D0", // HEBREW LETTER ALEF +"#=0x05D0" , // HEBREW LETTER ALEF +"B=0x05D1 0x05BF", // HEBREW LETTER BET, HEBREW POINT RAFE +"b=0x05D1", // HEBREW LETTER BET +"c=0x05E6", // HEBREW LETTER TSADI +"ts=0x05E6", // HEBREW LETTER TSADI +"tsh=0x05D8 0x05E9", // HEBREW LETTER TET, SHIN + +"ts,=0x05E5 ," , // final form +"ts.=0x05E5 ." , // final form +"ts?=0x05E5 ?" , // final form +"ts:=0x05E5 :" , // final form +"ts!=0x05E5 !" , // final form +"ts;=0x05E5 ;" , // final form +"ts-=0x05E5 -" , // final form +"ts)=0x05E5 )" , // final form +"ts 0x0020= 0x05E5 0x0020" , // final form + +"C=0x05E5", // HEBREW LETTER FINAL TSADI + +"c,=0x05E5 ," , // final form +"c.=0x05E5 ." , // final form +"c?=0x05E5 ?" , // final form +"c:=0x05E5 :" , // final form +"c!=0x05E5 !" , // final form +"c;=0x05E5 ;" , // final form +"c-=0x05E5 -" , // final form +"c)=0x05E5 )" , // final form +"c 0x0020= 0x05E5 0x0020" , // final form + +"d=0x05D3", // HEBREW LETTER DALET +"dj=0x05D3 0x05D6 0x05E9", // DALET, ZAYIN, SHIN +"e=0x05E2", // HEBREW LETTER AYIN +"E=0x05F2", // HEBREW LIGATURE YIDDISH DOUBLE YOD +"ey=0x05F2", // HEBREW LIGATURE YIDDISH DOUBLE YOD +"eyi=0x05F2 0x05D9 0x05B4", // DOUBLE YOD, YOD, HIRIQ +"f=0x05E4 0x05BF", // HEBREW LETTER PE, HEBREW POINT RAFE +"F=0x05E3", // HEBREW LETTER FINAL PE + +"f,=0x05E3 ," , // final form +"f.=0x05E3 ." , // final form +"f?=0x05E3 ?" , // final form +"f:=0x05E3 :" , // final form +"f!=0x05E3 !" , // final form +"f;=0x05E3 ;" , // final form +"f-=0x05E3 -" , // final form +"f)=0x05E3 )" , // final form +"f 0x0020= 0x05E3 0x0020" , // final form + +"g=0x05D2", // HEBREW LETTER GIMEL +"h=0x05D4", // HEBREW LETTER HE +"H=0x05D7", // HEBREW LETTER HET +"i=0x05D9", // HEBREW LETTER YOD +"ii=0x05D9 0x05D9 0x05B4", // YOD, YOD, HIRIQ +"iy=0x05D9 0x05B4 0x05D9", // YOD, HIRIQ, YOD +"I=0x05D9 0x05B4", // HEBREW LETTER YOD, HEBREW POINT HIRIQ +"j=0x05F2", // HEBREW LIGATURE YIDDISH DOUBLE YOD +"J=0x05F2 0x05B7", // HEBREW LIGATURE YIDDISH DOUBLE YOD, HEBREW POINT PATAH +"k=0x05E7", // HEBREW LETTER QOF +"kh=0x05DB" , // HEBREW LETTER KAF + +"kh,=0x05DA ," , // final form +"kh.=0x05DA ." , // final form +"kh?=0x05DA ?" , // final form +"kh:=0x05DA :" , // final form +"kh!=0x05DA !" , // final form +"kh;=0x05DA ;" , // final form +"kh-=0x05DA -" , // final form +"kh)=0x05DA )" , // final form +"kh 0x0020= 0x05DA 0x0020" , // final form + +"K=0x05DB 0x05BC", // HEBREW LETTER KAF, HEBREW POINT DAGESH OR MAPIQ +"l=0x05DC", // HEBREW LETTER LAMED +"m=0x05DE", // HEBREW LETTER MEM +"M=0x05DD", // HEBREW LETTER FINAL MEM + +"m,=0x05DD ," , // final form +"m.=0x05DD ." , // final form +"m?=0x05DD ?" , // final form +"m:=0x05DD :" , // final form +"m!=0x05DD !" , // final form +"m;=0x05DD ;" , // final form +"m-=0x05DD -" , // final form +"m)=0x05DD )" , // final form +"m 0x0020= 0x05DD 0x0020" , // final form + +"n=0x05E0", // HEBREW LETTER NUN +"N=0x05DF", // HEBREW LETTER FINAL NUN + +"n,=0x05DF ," , // final form +"n.=0x05DF ." , // final form +"n?=0x05DF ?" , // final form +"n:=0x05DF :" , // final form +"n!=0x05DF !" , // final form +"n;=0x05DF ;" , // final form +"n-=0x05DF -" , // final form +"n)=0x05DF )" , // final form +"n 0x0020= 0x05DF 0x0020" , // final form + +"o=0x05D0 0x05B8", // HEBREW LETTER ALEF, HEBREW POINT QAMATS +"oy=0x05F1", // HEBREW LIGATURE YIDDISH VAV YOD +"O=0x05F1", // HEBREW LIGATURE YIDDISH VAV YOD +"p=0x05E4 0x05BC", // HEBREW LETTER PE, HEBREW POINT DAGESH OR MAPIQ +"q=0x05F2 0x05B7", // HEBREW LIGATURE YIDDISH DOUBLE YOD, HEBREW POINT PATAH +"r=0x05E8", // HEBREW LETTER RESH +"s=0x05E1", // HEBREW LETTER SAMEKH +"S=0x05EA", // HEBREW LETTER TAV +"t=0x05D8", // HEBREW LETTER TET +"T=0x05EA 0x05BC", // HEBREW LETTER TAV, HEBREW POINT DAGESH OR MAPIQ +"u=0x05D5", // HEBREW LETTER VAV +"ui=0x05D5 0x05D9 0x05B4", // HEBREW LETTER VAV, YOD, POINT HIRIQ +"uv=0x05D5 0x05BC 0x05F0", // VAV, DAGESH, DOUBLE VAV +"uu=0x05D5 0x05BC 0x05D5", // VAV, DAGESH, VAV +"U=0x05D5 0x05BC", // HEBREW LETTER VAV, HEBREW POINT DAGESH OR MAPIQ +"v=0x05F0", // HEBREW LIGATURE YIDDISH DOUBLE VAV +"vu=0x05F0 0x05D5 0x05BC", // DOUBLE VAV, VAV, DAGESH +"V=0x05D1 0x05BF", // HEBREW LETTER BET, HEBREW POINT RAFE +"w=0x05E9", // HEBREW LETTER SHIN +"sh=0x05E9", // HEBREW LETTER SHIN +"W=0x05E9 0x05C2", // HEBREW LETTER SHIN, HEBREW POINT SIN DOT +"x=0x05DB", // HEBREW LETTER KAF +"X=0x05DA", // HEBREW LETTER FINAL KAF + +"x,=0x05DA ," , // final form +"x.=0x05DA ." , // final form +"x?=0x05DA ?" , // final form +"x:=0x05DA :" , // final form +"x!=0x05DA !" , // final form +"x;=0x05DA ;" , // final form +"x-=0x05DA -" , // final form +"x)=0x05DA )" , // final form +"x 0x0020= 0x05DA 0x0020" , // final form + +"y=0x05D9", // HEBREW LETTER YOD +"yi=0x05D9 0x05D9 0x05B4", // YOD, YOD, HIRIQ +"Y=0x05F2 0x05B7", // HEBREW LIGATURE YIDDISH DOUBLE YOD, HEBREW POINT PATAH +"z=0x05D6", // HEBREW LETTER ZAYIN +"zh=0x05D5 0x05E9", // ZAYIN, SHIN diff --git a/kmaps b/kmaps index 0f9b5b8..8d02784 100644 Binary files a/kmaps and b/kmaps differ diff --git a/kmaptoqe.c b/kmaptoqe.c index 62e50d1..b7e66f3 100644 --- a/kmaptoqe.c +++ b/kmaptoqe.c @@ -36,7 +36,8 @@ typedef struct InputEntry { unsigned char input[20]; int len; - int output; + unsigned short output[20]; + int olen; } InputEntry; static InputEntry inputs[NB_MAX]; @@ -63,7 +64,7 @@ static int sort_func(const void *a1, const void *b1) if (val != 0) return val; } - return a->output - b->output; + return a->output[0] - b->output[0]; } @@ -78,30 +79,31 @@ static void put_byte(int b) static void gen_map(void) { - int len, c, d, last, delta, k, j; + int len, c, d, last, delta, i, k, j; int last_input0; + InputEntry *ip; last = 0; nb_starts = 0; last_input0 = 0; offset = 0; - for (k = 0; k < nb_inputs; k++) { - unsigned char *input = inputs[k].input; + for (k = 0, ip = inputs; k < nb_inputs; k++, ip++) { + unsigned char *input = ip->input; int first, output; if (gen_table) { - if (last_input0 != inputs[k].input[0]) { + if (last_input0 != ip->input[0]) { if (last_input0 != 0) put_byte(0); - last_input0 = inputs[k].input[0]; + last_input0 = ip->input[0]; table_val[nb_starts] = last_input0; table_start[nb_starts++] = offset; last = 0; } } - len = inputs[k].len; - output = inputs[k].output; + len = ip->len; + output = ip->output[0]; delta = output - last; last = output; @@ -123,16 +125,22 @@ static void gen_map(void) if (gen_table) first = 1; - /* c = 0 : end of table - c = 1..0x1d : delta unicode - c = 0x1e : unicode char follows. - c = 0x1f : unicode mapping follows - bit 7 : eof and delta == 1 - */ + /* c = 0x00 end of table + * c = 0x01..0x1d delta unicode + * c = 0x1e unicode output mapping follows + * c = 0x1f unicode input char follows. + * c = 0x20..0x7f input character + * c = 0x80 unused + * c = 0x81 unused + * c = 0x82..0x9d extra unicode outputs follow + * c = 0x9e first unicode output mapping follows + * c = 0x9f last unicode input char follows and delta==1. + * c = 0xa0..0xff last input character and delta==1 + */ for (j = first; j < len; j++) { c = input[j]; d = 0; - if ((j == (len - 1) && delta == 1)) + if (j == (len - 1) && delta == 1 && ip->olen == 1) d = 0x80; if (c >= 0x20 && c <= 0x7f) { put_byte(c | d); @@ -142,18 +150,31 @@ static void gen_map(void) put_byte(c & 0xff); } } - /* XXX: potential problem if first == len. We avoid it - by forcing an emission of a unicode char */ - if (first == len) - delta = 0; - if (delta != 1) { - if (delta >= 1 && delta <= 0x1d) { - put_byte(delta); - } else { - put_byte(0x1e); + if (ip->olen > 1) { + if (delta != 0) { + put_byte(0x80 | 0x1e); put_byte((output >> 8) & 0xff); put_byte(output & 0xff); } + put_byte(0x80 | ip->olen); + for (i = 1; i < ip->olen; i++) { + put_byte((ip->output[i] >> 8) & 0xff); + put_byte(ip->output[i] & 0xff); + } + } else { + /* XXX: potential problem if first == len. We avoid it + by forcing an emission of a unicode char */ + if (first == len) + delta = 0; + if (delta != 1) { + if (delta >= 1 && delta <= 0x1d) { + put_byte(delta); + } else { + put_byte(0x1e); + put_byte((output >> 8) & 0xff); + put_byte(output & 0xff); + } + } } } put_byte(0); @@ -290,13 +311,14 @@ static int dump_kmap(const char *filename) x = 0; if (1) { - int len, flag, k, s, last = 0, sp; + int len, olen, flag, k, s, last = 0, sp; s = 0; for (k = 0;; k++) { unsigned char *input; input = inputs[k].input; + olen = 1; len = 0; sp = 1; @@ -306,11 +328,17 @@ static int dump_kmap(const char *filename) if (c == EOF) break; - /* c = 0 : end of table - * c = 1..0x1d : delta unicode - * c = 0x1e : unicode char follows. - * c = 0x1f : unicode mapping follows - * bit 7 : eof and delta == 1 + /* c = 0x00 end of table + * c = 0x01..0x1d delta unicode + * c = 0x1e unicode output mapping follows + * c = 0x1f unicode input char follows. + * c = 0x20..0x7f input character + * c = 0x80 unused + * c = 0x81 unused + * c = 0x82..0x9d extra unicode outputs follow + * c = 0x9e first unicode output mapping follows + * c = 0x9f last unicode input char follows and delta==1. + * c = 0xa0..0xff last input character and delta==1 */ if (c == 0) { if (!gen_table || ++s >= nb_starts) @@ -329,6 +357,23 @@ static int dump_kmap(const char *filename) flag = c >> 7; c &= 0x7f; + if (c < 0x1e) { + if (flag) { + olen = c; + } else { + last += c; + } + goto nextk; + } + if (c == 0x1e) { + last = getc(f) << 8; + last |= getc(f) << 0; + pos += 2; + if (flag) + goto nextc; + else + goto nextk; + } if (c == 0x1f) { c = getc(f) << 8; c |= getc(f) << 0; @@ -341,16 +386,6 @@ static int dump_kmap(const char *filename) } goto nextc; } - if (c == 0x1e) { - last = getc(f) << 8; - last |= getc(f) << 0; - pos += 2; - goto nextk; - } - if (c < 0x1e) { - last += c; - goto nextk; - } if (c >= 0x20) { input[len++] = c; putcp(c, &sp); @@ -366,7 +401,15 @@ static int dump_kmap(const char *filename) } if (!sp) printf(" "); - printf("= 0x%04X\",\n", last); + printf("= 0x%04X", last); + /* multiple unicode chars */ + for (i = 1; i < olen; i++) { + c = getc(f) << 8; + c |= getc(f) << 0; + pos += 2; + printf(" 0x%04X", c); + } + printf("\",\n"); } } if (pos == kmap_offsets[n]) @@ -448,6 +491,7 @@ int main(int argc, char **argv) char line[1024], *p; unsigned char *q; int c, size; + InputEntry *ip; if (argc < 3) { printf("usage: kmaptoqe outfile kmaps...\n" @@ -499,6 +543,7 @@ int main(int argc, char **argv) col = 0; nb_inputs = 0; + ip = inputs; line_num = 0; for (;;) { if (fgets(line, sizeof(line), f) == NULL) @@ -511,7 +556,7 @@ int main(int argc, char **argv) goto invalid; p++; len = 0; - q = inputs[nb_inputs].input; + q = ip->input; for (;;) { p = skipspaces(p); if (*p == '=' && p[1] != '=') @@ -524,17 +569,24 @@ int main(int argc, char **argv) filename, line_num, c); goto skip; } - if (len >= countof(inputs[nb_inputs].input)) + if (len >= countof(ip->input)) goto invalid; q[len++] = c; } - inputs[nb_inputs].len = len; + ip->len = len; p = skipspaces(p + 1); - c = getcp(p, &p); - p = skipspaces(p); - if (c < 0 || *p != '"') - goto invalid; - inputs[nb_inputs].output = c; + for (ip->olen = 0;;) { + c = getcp(p, &p); + if (c < 0) + goto invalid; + if (ip->olen >= countof(ip->output)) + goto invalid; + ip->output[ip->olen++] = c; + p = skipspaces(p); + if (*p == '"') + break; + } + ip++; nb_inputs++; continue; invalid: diff --git a/qe.c b/qe.c index ffd84ad..d98642d 100644 --- a/qe.c +++ b/qe.c @@ -1237,7 +1237,7 @@ void text_write_char(EditState *s, int key) if (insert) { const InputMethod *m; - int match_len, offset, i; + int match_buf[20], match_len, offset, i; /* use compose system only if insert mode */ if (s->compose_len == 0) @@ -1254,12 +1254,11 @@ void text_write_char(EditState *s, int key) s->compose_len = 0; break; } - // XXX: handle multiple translation - ret = m->input_match(&match_len, m->data, s->compose_buf, + ret = m->input_match(match_buf, countof(match_buf), + &match_len, m->data, s->compose_buf, s->compose_len); if (ret == INPUTMETHOD_NOMATCH) { /* no match : reset compose state */ - s->compose_len = 0; break; } else @@ -1268,7 +1267,6 @@ void text_write_char(EditState *s, int key) break; } else { /* match : delete matched chars */ - key = ret; offset = s->compose_start_offset; offset1 = s->offset; /* save offset so that we are not disturb when it moves in eb_delete() */ @@ -1276,14 +1274,18 @@ void text_write_char(EditState *s, int key) eb_nextc(s->b, offset, &offset); eb_delete(s->b, s->compose_start_offset, offset - s->compose_start_offset); + s->offset = offset1 - (offset - s->compose_start_offset); s->compose_len -= match_len; umemmove(s->compose_buf, s->compose_buf + match_len, s->compose_len); /* then insert match */ - len = unicode_to_charset(buf, key, s->b->charset); - eb_insert(s->b, s->compose_start_offset, buf, len); - s->offset = offset1 + len - (offset - s->compose_start_offset); - s->compose_start_offset += len; + for (i = 0; i < ret; i++) { + key = match_buf[i]; + len = unicode_to_charset(buf, key, s->b->charset); + eb_insert(s->b, s->compose_start_offset, buf, len); + s->offset += len; + s->compose_start_offset += len; + } /* if some compose chars are left, we iterate */ if (s->compose_len == 0) break; @@ -6926,7 +6928,7 @@ void set_user_option(const char *user) /* put source directory first if qe invoked as ./qe */ // should use actual directory - if (!strcmp(qs->argv[0], "./qe")) { + if (stristart(qs->argv[0], "./qe", NULL)) { pstrcat(qs->res_path, sizeof(qs->res_path), ".:"); } diff --git a/qe.h b/qe.h index 61d94e8..cc18f90 100644 --- a/qe.h +++ b/qe.h @@ -64,6 +64,10 @@ #define force_cast(type, expr) ((type)(expr)) #endif +#ifndef countof +#define countof(a) ((int)(sizeof(a) / sizeof((a)[0]))) +#endif + /************************/ #include "cutils.h" @@ -1134,13 +1138,16 @@ static inline int display_char(DisplayState *s, int offset1, int offset2, typedef struct InputMethod { const char *name; /* input match returns: - ch >= 0 if a character ch of len '*match_len_ptr' in buf was found, INPUTMETHOD_NOMATCH if no match was found INPUTMETHOD_MORECHARS if more chars need to be typed to find - a suitable completion + a suitable completion + n > 0: number of code points in replacement found for a sequence + of keystrokes in buf. number of keystrokes in match was stored + in '*match_len_ptr'. */ - int (*input_match)(int *match_len_ptr, - const u8 *data, const unsigned int *buf, int len); + int (*input_match)(int *match_buf, int match_buf_size, + int *match_len_ptr, const u8 *data, + const unsigned int *buf, int len); const u8 *data; struct InputMethod *next; } InputMethod;