Force "unicodesymbols" conversions for Hebrew and Arabic encodings.

Fixes wrong output with these encodings for Latin Unicode blocks.
Other Unicode blocks still need verification for correct output.

diff --git a/lib/unicodesymbols b/lib/unicodesymbols
index 32e6ba285d35137fd93e02e6b25859d75a4f054d..0a5096ab85ecf4720b6ed2f17288660b5e5e0f97 100644 (file)
--- a/lib/unicodesymbols
+++ b/lib/unicodesymbols
@@ -58,38 +58,38 @@
 #
 # 2 Latin-1 Supplement
 #
-0x00a0 "~"                        "" "force=koi8-u;iso8859-7,notermination=both" "~" "" # NO-BREAK SPACE
-0x00a1 "\\textexclamdown"         "" "force=euc-jp;euc-kr" # INVERTED EXCLAMATION MARK
-0x00a2 "\\textcent"               "textcomp" "force=euc-jp;jis" #"\\mathcent" "txfonts|pxfonts" # CENT SIGN
-0x00a3 "\\pounds"                 "" "force=iso8859-7;euc-jp;jis" "\\pounds" "" # £ POUND SIGN
-0x00a4 "\\textcurrency"           "textcomp" "force=euc-cn;euc-jp;euc-kr;gbk" # CURRENCY SYMBOL
-0x00a5 "\\textyen"                "textcomp" "force=euc-jp;jis" "\\yen" "amssymb" # YEN SIGN
-0x00a6 "\\textbrokenbar"          "textcomp" "force=iso8859-7;euc-jp" # BROKEN BAR
-0x00a7 "\\textsection"            "textcomp" "force=iso8859-7;euc-cn;euc-jp;euc-kr;euc-tw;gbk;jis" "\\mathsection" "" # SECTION SIGN
-0x00a8 "\\textasciidieresis"      "textcomp" "force=iso8859-7;euc-cn;euc-jp;euc-kr;gbk;jis" # DIAERESIS
-0x00a9 "\\textcopyright"          "textcomp" "force=koi8-u;iso8859-7;euc-jp" # COPYRIGHT SIGN
-0x00aa "\\textordfeminine"        "textcomp" "force=euc-jp;euc-kr" # FEMININE ORDINAL INDICATOR
-0x00ab "\\guillemotleft"          "" "force=armscii8;iso8859-7" # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+0x00a0 "~"                        "" "force=cp862;cp1255;cp1256;koi8-u;iso8859-6;iso8859-7,notermination=both" "~" "" # NO-BREAK SPACE
+0x00a1 "\\textexclamdown"         "" "force=cp862;cp1255;euc-jp;euc-kr" # INVERTED EXCLAMATION MARK
+0x00a2 "\\textcent"               "textcomp" "force=cp862;cp1255;cp1256;euc-jp;jis" #"\\mathcent" "txfonts|pxfonts" # CENT SIGN
+0x00a3 "\\pounds"                 "" "force=cp862;cp1255;cp1256;iso8859-7;euc-jp;jis" "\\pounds" "" # £ POUND SIGN
+0x00a4 "\\textcurrency"           "textcomp" "force=cp1256;euc-cn;euc-jp;euc-kr;gbk;iso8859-6" # CURRENCY SYMBOL
+0x00a5 "\\textyen"                "textcomp" "force=cp862;cp1255;cp1256;euc-jp;jis" "\\yen" "amssymb" # YEN SIGN
+0x00a6 "\\textbrokenbar"          "textcomp" "force=cp1255;cp1256;iso8859-7;euc-jp" # BROKEN BAR
+0x00a7 "\\textsection"            "textcomp" "force=cp1255;cp1256;iso8859-7;euc-cn;euc-jp;euc-kr;euc-tw;gbk;jis" "\\mathsection" "" # SECTION SIGN
+0x00a8 "\\textasciidieresis"      "textcomp" "force=cp1255;cp1256;iso8859-7;euc-cn;euc-jp;euc-kr;gbk;jis" # DIAERESIS
+0x00a9 "\\textcopyright"          "textcomp" "force=cp1255;cp1256;koi8-u;iso8859-7;euc-jp" # COPYRIGHT SIGN
+0x00aa "\\textordfeminine"        "textcomp" "force=cp862;euc-jp;euc-kr" # FEMININE ORDINAL INDICATOR
+0x00ab "\\guillemotleft"          "" "force=armscii8;cp862;cp1255;cp1256;iso8859-7" # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
 0x00ac "\\textlnot"               "textcomp" "force" "\\neg" "" # ¬ NOT SIGN
-0x00ad "\\-"                      "" "force=iso8859-13;euc-jp;euc-kr,notermination=text" "" "" # SOFT HYPHEN
-0x00ae "\\textregistered"         "textcomp" "force=euc-jp;euc-kr" "\\circledR" "amssymb" # REGISTERED SIGN
-0x00af "\\textasciimacron"        "textcomp" "force=euc-jp" # MACRON
-0x00b0 "\\textdegree"             "textcomp" "force=koi8-u;iso8859-7;euc-cn;euc-jp;euc-kr;euc-tw;gbk;jis" "{^\\circ}" "" # DEGREE SIGN
+0x00ad "\\-"                      "" "force=cp1255;cp1256;iso8859-13;euc-jp;euc-kr;iso8859-6,notermination=text" "" "" # SOFT HYPHEN
+0x00ae "\\textregistered"         "textcomp" "force=cp1255;cp1256;euc-jp;euc-kr" "\\circledR" "amssymb" # REGISTERED SIGN
+0x00af "\\textasciimacron"        "textcomp" "force=cp1255;cp1256;euc-jp" # MACRON
+0x00b0 "\\textdegree"             "textcomp" "force=cp862;cp1255;cp1256;koi8-u;iso8859-7;euc-cn;euc-jp;euc-kr;euc-tw;gbk;jis" "{^\\circ}" "" # DEGREE SIGN
 0x00b1 "\\textpm"                 "textcomp" "force" "\\pm" "" # ± PLUS-MINUS SIGN
 0x00b2 "\\texttwosuperior"        "textcomp" "force" "{{}^2}" "" # ² SUPERSCRIPT TWO
 0x00b3 "\\textthreesuperior"      "textcomp" "force" "{{}^3}" "" # ³ SUPERSCRIPT THREE
-0x00b4 "\\textasciiacute"         "textcomp" "force=euc-jp;euc-kr;jis" # ACUTE ACCENT
+0x00b4 "\\textasciiacute"         "textcomp" "force=cp1255;cp1256;euc-jp;euc-kr;jis" # ACUTE ACCENT
 0x00b5 "\\textmu"                 "textcomp" "force!=utf8;jis" "" "" # µ MICRO SIGN (upright, not $\mu$)
-0x00b6 "\\textparagraph"          "textcomp" "force=euc-jp;euc-kr;jis" "\\mathparagraph" "" # PILCROW SIGN # not equal to \textpilcrow
-0x00b7 "\\textperiodcentered"     "" "force=koi8-u;iso8859-7;euc-kr;euc-tw;gbk" "\\cdot" "" # MIDDLE DOT
-0x00b8 "\\c{ }"                   "" "force=euc-jp;euc-kr" "" "" # CEDILLA
+0x00b6 "\\textparagraph"          "textcomp" "force=cp1255;cp1256;euc-jp;euc-kr;jis" "\\mathparagraph" "" # PILCROW SIGN # not equal to \textpilcrow
+0x00b7 "\\textperiodcentered"     "" "force=cp862;cp1255;cp1256;koi8-u;iso8859-7;euc-kr;euc-tw;gbk" "\\cdot" "" # MIDDLE DOT
+0x00b8 "\\c{ }"                   "" "force=cp1255;cp1256;euc-jp;euc-kr" "" "" # CEDILLA
 0x00b9 "\\textonesuperior"        "textcomp" "force" "{{}^1}" "" # ¹ SUPERSCRIPT ONE
-0x00ba "\\textordmasculine"       "textcomp" "force=euc-jp;euc-kr" # MASCULINE ORDINAL INDICATOR
-0x00bb "\\guillemotright"         "" "force=armscii8;iso8859-7" # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
-0x00bc "\\textonequarter"         "textcomp" "force=euc-kr" "\\sfrac{1}{4}" "xfrac" # 1/4 FRACTION
-0x00bd "\\textonehalf"            "textcomp" "force=iso8859-7;euc-kr" "\\sfrac{1}{2}" "xfrac" # 1/2 FRACTION
-0x00be "\\textthreequarters"      "textcomp" "force=euc-kr" "\\sfrac{3}{4}" "xfrac" # 3/4 FRACTION
-0x00bf "\\textquestiondown"       "" "force=euc-jp;euc-kr" # INVERTED QUESTION MARK
+0x00ba "\\textordmasculine"       "textcomp" "force=cp862;euc-jp;euc-kr" # MASCULINE ORDINAL INDICATOR
+0x00bb "\\guillemotright"         "" "force=armscii8;cp862;cp1255;cp1256;iso8859-7" # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+0x00bc "\\textonequarter"         "textcomp" "force=cp862;cp1255;cp1256;euc-kr" "\\sfrac{1}{4}" "xfrac" # 1/4 FRACTION
+0x00bd "\\textonehalf"            "textcomp" "force=cp862;cp1255;cp1256;iso8859-7;euc-kr" "\\sfrac{1}{2}" "xfrac" # 1/2 FRACTION
+0x00be "\\textthreequarters"      "textcomp" "force=cp1255;cp1256;euc-kr" "\\sfrac{3}{4}" "xfrac" # 3/4 FRACTION
+0x00bf "\\textquestiondown"       "" "force=cp862;cp1255;euc-jp;euc-kr" # INVERTED QUESTION MARK
 0x00c0 "\\`{A}"                   "" "mathalpha,force=euc-jp" "\\grave{A}" # LATIN CAPITAL LETTER A WITH GRAVE
 0x00c1 "\\'{A}"                   "" "mathalpha,force=euc-jp" "\\acute{A}" # LATIN CAPITAL LETTER A WITH ACUTE
 0x00c2 "\\^{A}"                   "" "mathalpha,force=euc-jp" "\\hat{A}" # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
@@ -107,7 +107,7 @@
 0x00ce "\\^{I}"                   "" "mathalpha,force=euc-jp" "\\hat{I}" # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
 0x00cf "\\\"{I}"                  "" "mathalpha,force=euc-jp" "\\ddot{I}" # LATIN CAPITAL LETTER I WITH DIAERESIS
 0x00d0 "\\DH"                     "" "mathalpha,force=euc-kr,notermination=math" "\\mkern2mu\\rule[0.75ex]{0.75ex}{0.06ex}\\mkern-8mu D" # LATIN CAPITAL LETTER ETH
-0x00d1 "\\~{N}"                   "" "mathalpha,force=euc-jp" "\\tilde{N}" # LATIN CAPITAL LETTER N WITH TILDE
+0x00d1 "\\~{N}"                   "" "mathalpha,force=cp862;euc-jp" "\\tilde{N}" # LATIN CAPITAL LETTER N WITH TILDE
 0x00d2 "\\`{O}"                   "" "mathalpha,force=euc-jp" "\\grave{O}" # LATIN CAPITAL LETTER O WITH GRAVE
 0x00d3 "\\'{O}"                   "" "mathalpha,force=euc-jp" "\\acute{O}" # LATIN CAPITAL LETTER O WITH ACUTE
 0x00d4 "\\^{O}"                   "" "mathalpha,force=euc-jp" "\\hat{O}" # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
@@ -121,9 +121,9 @@
 0x00dc "\\\"{U}"                  "" "mathalpha,force=euc-jp" "\\ddot{U}" # LATIN CAPITAL LETTER U WITH DIAERESIS
 0x00dd "\\'{Y}"                   "" "mathalpha,force=euc-jp" "\\acute{Y}" # LATIN CAPITAL LETTER Y WITH ACUTE
 0x00de "\\TH"                     "" "force=euc-jp;euc-kr" # LATIN CAPITAL LETTER THORN
-0x00df "\\ss"                     "" "force=cp437;cp865;euc-jp;euc-kr" # LATIN SMALL LETTER SHARP S
+0x00df "\\ss"                     "" "force=cp437;cp862;cp865;euc-jp;euc-kr" # LATIN SMALL LETTER SHARP S
 0x00e0 "\\`{a}"                   "" "mathalpha,force=euc-cn;euc-jp;gbk" "\\grave{a}" # LATIN SMALL LETTER A WITH GRAVE
-0x00e1 "\\'{a}"                   "" "mathalpha,force=euc-cn;euc-jp;gbk" "\\acute{a}" # LATIN SMALL LETTER A WITH ACUTE
+0x00e1 "\\'{a}"                   "" "mathalpha,force=cp862;euc-cn;euc-jp;gbk" "\\acute{a}" # LATIN SMALL LETTER A WITH ACUTE
 0x00e2 "\\^{a}"                   "" "mathalpha,force=euc-jp" "\\hat{a}" # LATIN SMALL LETTER A WITH CIRCUMFLEX
 0x00e3 "\\~{a}"                   "" "mathalpha,force=euc-jp" "\\tilde{a}" # LATIN SMALL LETTER A WITH TILDE
 0x00e4 "\\\"{a}"                  "" "mathalpha,force=euc-jp" "\\ddot{a}" # LATIN SMALL LETTER A WITH DIAERESIS
@@ -135,11 +135,11 @@
 0x00ea "\\^{e}"                   "" "mathalpha,force=euc-cn;euc-jp;gbk" "\\hat{e}" # LATIN SMALL LETTER E WITH CIRCUMFLEX
 0x00eb "\\\"{e}"                  "" "mathalpha,force=euc-jp" "\\ddot{e}" # LATIN SMALL LETTER E WITH DIAERESIS
 0x00ec "\\`{\\i}"                 "" "mathalpha,force=euc-cn;euc-jp;gbk" "\\grave{\\imath}" # LATIN SMALL LETTER I WITH GRAVE
-0x00ed "\\'{\\i}"                 "" "mathalpha,force=euc-cn;euc-jp;gbk" "\\acute{\\imath}" # LATIN SMALL LETTER I WITH ACUTE
+0x00ed "\\'{\\i}"                 "" "mathalpha,force=cp862;euc-cn;euc-jp;gbk" "\\acute{\\imath}" # LATIN SMALL LETTER I WITH ACUTE
 0x00ee "\\^{\\i}"                 "" "mathalpha,force=euc-jp" "\\hat{\\imath}" # LATIN SMALL LETTER I WITH CIRCUMFLEX
 0x00ef "\\\"{\\i}"                "" "mathalpha,force=euc-jp" "\\ddot{\\imath}" # LATIN SMALL LETTER I WITH DIAERESIS
 0x00f0 "\\dh"                     "" "force=euc-jp;euc-kr,tipashortcut=D" "\\eth" "amssymb" # LATIN SMALL LETTER ETH
-0x00f1 "\\~{n}"                   "" "mathalpha,force=euc-jp" "\\tilde{n}" # LATIN SMALL LETTER N WITH TILDE
+0x00f1 "\\~{n}"                   "" "mathalpha,force=cp862;euc-jp" "\\tilde{n}" # LATIN SMALL LETTER N WITH TILDE
 0x00f2 "\\`{o}"                   "" "mathalpha,force=euc-cn;euc-jp;gbk" "\\grave{o}" # LATIN SMALL LETTER O WITH GRAVE
 0x00f3 "\\'{o}"                   "" "mathalpha,force=euc-cn;euc-jp;gbk" "\\acute{o}" # LATIN SMALL LETTER O WITH ACUTE
 0x00f4 "\\^{o}"                   "" "mathalpha,force=euc-jp" "\\hat{o}" # LATIN SMALL LETTER O WITH CIRCUMFLEX
@@ -207,8 +207,8 @@
 0x012f "\\k{i}"                   "" "mathalpha,force=euc-jp" "\\ogonek{i}" "accents,tipasymb,ogonek" # LATIN SMALL LETTER I WITH OGONEK
 0x0130 "\\.{I}"                   "" "mathalpha,force=euc-jp" "\\dot{I}" # LATIN CAPITAL LETTER I WITH DOT ABOVE
 0x0131 "\\i"                      "" "mathalpha,force=euc-jp;euc-kr" "\\imath" # LATIN SMALL LETTER DOTLESS I
-0x0132 "IJ"                       "" "mathalpha,force=utf8x;euc-jp;euc-kr,notermination=both" "IJ" "" # LATIN CAPITAL LIGATURE IJ
-0x0133 "ij"                       "" "mathalpha,force=utf8x;euc-jp;euc-kr,notermination=both" "ij" "" # LATIN SMALL LIGATURE IJ
+0x0132 "\IJ"                      "" "mathalpha,force=utf8x;euc-jp;euc-kr,notermination=math" "IJ" "" # LATIN CAPITAL LIGATURE IJ
+0x0133 "\ij"                      "" "mathalpha,force=utf8x;euc-jp;euc-kr,notermination=math" "ij" "" # LATIN SMALL LIGATURE IJ
 0x0134 "\\^{J}"                   "" "mathalpha,force=euc-jp" "\\hat{J}" # LATIN CAPITAL LETTER J WITH CIRCUMFLEX
 0x0135 "\\^{\\j}"                 "" "mathalpha,force=utf8;euc-jp" "\\hat{\\jmath}" "" # LATIN SMALL LETTER J WITH CIRCUMFLEX
 0x0136 "\\c{K}"                   "textbaltic!=L7x" "mathalpha,force=utf8;euc-jp" "\\cedilla{K}" "accents,cedilla" # LATIN CAPITAL LETTER K WITH CEDILLA  (actually a comma accent, Latvian)
@@ -239,8 +239,8 @@
 0x014f "\\u{o}"                   "" "mathalpha,force=euc-jp" "\\breve{o}" # LATIN SMALL LETTER O WITH BREVE
 0x0150 "\\H{O}"                   "" "mathalpha,force=euc-jp" "\\dacute{O}" "dacute" # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
 0x0151 "\\H{o}"                   "" "mathalpha,force=euc-jp" "\\dacute{o}" "dacute" # LATIN SMALL LETTER O WITH DOUBLE ACUTE
-0x0152 "\\OE"                     "" "force=euc-jp;euc-kr" "" "" # LATIN CAPITAL LIGATURE OE
-0x0153 "\\oe"                     "" "force=euc-jp;euc-kr" "" "" # LATIN SMALL LIGATURE OE
+0x0152 "\\OE"                     "" "force=cp1256;euc-jp;euc-kr" "" "" # LATIN CAPITAL LIGATURE OE
+0x0153 "\\oe"                     "" "force=cp1256;euc-jp;euc-kr" "" "" # LATIN SMALL LIGATURE OE
 0x0154 "\\'{R}"                   "" "mathalpha,force=euc-jp" "\\acute{R}" # LATIN CAPITAL LETTER R WITH ACUTE
 0x0155 "\\'{r}"                   "" "mathalpha,force=euc-jp" "\\acute{r}" # LATIN SMALL LETTER R WITH ACUTE
 0x0156 "\\c{R}"                   "textbaltic!=L7x" "mathalpha,force=utf8;euc-jp" "\\cedilla{R}" "accents,cedilla" # LATIN CAPITAL LETTER R WITH CEDILLA (actually a comma accent, Latvian)
@@ -306,7 +306,7 @@
 #0x018f ""                         "" "" # LATIN CAPITAL LETTER SCHWA
 #0x0190 ""                         "" "" # LATIN CAPITAL LETTER OPEN E
 #0x0191 ""                         "" "" # LATIN CAPITAL LETTER F WITH HOOK
-0x0192 "\\textflorin"             "textcomp" "" # LATIN SMALL LETTER F WITH HOOK
+0x0192 "\\textflorin"             "textcomp" "force=cp862;cp1255;cp1256" # LATIN SMALL LETTER F WITH HOOK
 #0x0193 ""                         "" "" # LATIN CAPITAL LETTER G WITH HOOK
 #0x0194 ""                         "" "" # LATIN CAPITAL LETTER GAMMA
 #0x0195 ""                         "" "" # LATIN SMALL LETTER HV