updated tests (desc. in uchar.tex)

source/texk/web2c/eptexdir/pdfutils.ch

@@ -843,7 +843,9 @@ function str_toks_cat(@!b:pool_pointer;@!cat:small_number):pointer;
   else t:=other_token+t;
 @y
   else if (t=" ")and(cat=0) then t:=space_token
-  else if cat=0 then t:=other_token+t else t:=left_brace_token*cat+t;
+  else if (cat=0)or(cat>=kanji) then t:=other_token+t 
+  else if cat=active_char then t:= cs_token_flag + active_base + t
+  else t:=left_brace_token*cat+t;
 @z
 
 @x \Ucharcat: str_toks_cat
@@ -1128,9 +1130,10 @@ eTeX_revision_code: print(eTeX_revision);
 pdf_strcmp_code: print_int(cur_val);
 uniform_deviate_code:     print_int(unif_rand(cur_val));
 normal_deviate_code:      print_int(norm_rand);
-Uchar_convert_code,
-Ucharcat_convert_code:
+Uchar_convert_code:
 if is_char_ascii(cur_val) then print_char(cur_val) else print_kanji(cur_val);
+Ucharcat_convert_code:
+if cat<kanji then print_char(cur_val) else print_kanji(cur_val);
 @z
 
 @x e-pTeX: if primitives - leave room for \ifincsname

source/texk/web2c/eptexdir/tests/uchar.tex

@@ -1,41 +1,124 @@
-% euptex
-
-\kcatcode`α=15
-\def\KCAT{%
-  \message{\expandafter\ifcat\x 空 [kanji]\fi}%
-  \message{\expandafter\ifcat\x ア [kana]\fi}%
-  \message{\expandafter\ifcat\x ｛ [other\string_kchar]\fi}%
-  \message{\expandafter\ifcat\x 한 [hangul]\fi}%
-}
+% eptex
+
+% \Uchar <chr_code>
+%  0--255：常に欧文文字トークン
+%  256以上の，内部コードで許される値：常に和文文字トークン
+% \Ucharcat <chr_code> <catcode>
+% <chr_code> in [0,128): 欧文文字トークンを生成．<catcode> in {1..4, 6..8, 10..13}
+% <chr_code> in [128,256)
+%    e-pTeX の場合：欧文文字トークンを生成．<catcode> in {1..4, 6..8, 10..13}
+%    e-upTeX の場合：欧文/和文文字トークンを生成．<catcode> in {1..4, 6..8, 10..13, 16..19}
+% <chr_code> >=256: 和文文字トークンを生成．
+%    e-pTeX の場合： <catcode> in {16..18}
+%    e-upTeX の場合：<catcode> in {16..19}
+
+
+% e-upTeX:
+
+
+\let\bg={ \let\eg=}
+{\catcode`\ =9\relax
+\gdef\KCAT{%
+  \immediate\write17{%
+    [\expandafter\string\x\space
+    \expandafter\ifcat\x$   math\space shift\fi
+    \expandafter\ifcat\x&   alignment\fi
+    \expandafter\ifcat\x^   superscript\fi
+    \expandafter\ifcat\x_   subscript\fi
+    \expandafter\ifcat\x\space space\fi
+    \expandafter\ifcat\x a  letter\fi
+    \expandafter\ifcat\x 1  other\space char\fi
+    \expandafter\ifcat\x ~  active\fi
+    \expandafter\ifcat\x 空 kanji\fi
+    \expandafter\ifcat\x ア kana\fi
+    \expandafter\ifcat\x ｛ other\space kchar\fi
+    \ifdefined\ucs
+      \expandafter\ifcat\x 한 hangul\fi
+    \fi]}%
+}}
+\let\sharp=#
 \font\x=ec-lmtt10 \x
 \scrollmode
 
-\edef\x{\Uchar`\$}
-\expandafter\show\x
-
+\edef\x{\Uchar`\{}\KCAT
+\edef\x{\Uchar`\}}\KCAT
+\edef\x{\Uchar`\$}\KCAT
+\edef\x{\Uchar`\&}\KCAT
+\edef\x{\Uchar`\#}\KCAT
+\edef\x{\Uchar`\^}\KCAT
+\edef\x{\Uchar`\_}\KCAT
+\edef\x{\Uchar`\ }\KCAT
+\edef\x{\Uchar`\a}\KCAT
+\edef\x{\Uchar`\1}\KCAT
+\edef\x{\Uchar`~}\KCAT
 \edef\x{\Uchar`漢}\KCAT
-
 \edef\x{\Uchar`あ}\KCAT
-
 \edef\x{\Uchar`）}\KCAT
 
-\edef\x{\Uchar"03B1}\KCAT
+\ifdefined\ucs %======
+\immediate\write0{■\string\Uchar\space and \string\kcatcode}
+{\kcatcode"03B1=15 \kcatcode"FF=15
+\edef\x{\Uchar"FF}\KCAT%"}
+\edef\x{\Uchar"03B1}\KCAT%"}
 
-\edef\x{\Ucharcat`\# 3}
-\expandafter\show\x
+{\kcatcode"03B1=17 \kcatcode"FF=17
+\edef\x{\Uchar"FF}\KCAT%"}
+\edef\x{\Uchar"03B1}\KCAT%"}
+\fi %======
+
+\immediate\write0{■\string\Ucharcat.}
+
+\edef\x{\Ucharcat`\# 0}\KCAT % error "! Invalid code"
+\edef\x{\Ucharcat`\# 3}\KCAT
+\edef\x{\Ucharcat`\# 4}\KCAT
+\edef\x{\Ucharcat`\# 5}\KCAT % error "! Invalid code"
+\edef\x{\Ucharcat`\# 7}\KCAT
+\edef\x{\Ucharcat`\# 8}\KCAT
+\edef\x{\Ucharcat`\# 9}\KCAT % error "! Invalid code"
+\edef\x{\Ucharcat`\# 10}\KCAT
+\edef\x{\Ucharcat`\# 11}\KCAT
+\edef\x{\Ucharcat`\# 12}\KCAT
+\edef\x{\unexpanded\expandafter{\Ucharcat`\# 13}}
+\message{\expandafter\meaning\unexpanded\expandafter{\x}} % undefined
+\edef\x{\Ucharcat`\# 14}\KCAT % error "! Invalid code"
+\edef\x{\Ucharcat`\# 15}\KCAT % error "! Invalid code"
 
 \edef\x{\Ucharcat`\# 16} % error "! Invalid code (16)"
-\expandafter\show\x
+\KCAT
 
-\edef\x{\Ucharcat`漢 3} % error "! Bad character code" in eptex
+\ifdefined\ucs %======
+\edef\x{\Ucharcat`漢 3} % error "! Invalid code (3)"
 \KCAT
 
 \edef\x{\Ucharcat`＄ 16}\KCAT
 \edef\x{\Ucharcat`： 17}\KCAT
 \edef\x{\Ucharcat`あ 18}\KCAT
 \edef\x{\Ucharcat`漢 19}\KCAT
 
-\edef\x{\Ucharcat"03B1 17}\KCAT
+{\kcatcode"03B1=15 %"
+\edef\x{\Ucharcat"03B1 12}\KCAT%" error "! Invalid code (12)"
+\edef\x{\Ucharcat"03B1 17}\KCAT%"
+}
+
+{\kcatcode"03B1=16 %"
+\edef\x{\Ucharcat"03B1 12}\KCAT%" error "! Invalid code (12)"
+\edef\x{\Ucharcat"03B1 17}\KCAT%"
+}
+
+{\kcatcode"FF=15 %"
+\edef\x{\Ucharcat"FF 12}\KCAT%"
+\edef\x{\Ucharcat"FF 17}\KCAT%"
+}
+
+{\kcatcode"FF=16 %"
+\edef\x{\Ucharcat"FF 12}\KCAT%"
+\edef\x{\Ucharcat"FF 17}\KCAT%"
+}
+\else
+
+\edef\x{\Ucharcat`漢 3} % error "! Bad character code" in eptex
+
+\fi % ======
 
 
 \end

source/texk/web2c/euptexdir/pdfstrcmp-eup-post.ch

@@ -26,10 +26,14 @@
 
 @x
   else if (t=" ")and(cat=0) then t:=space_token
-  else if cat=0 then t:=other_token+t else t:=left_brace_token*cat+t;
+  else if (cat=0)or(cat>=kanji) then t:=other_token+t
+  else if cat=active_char then t:= cs_token_flag + active_base + t
+  else t:=left_brace_token*cat+t;
 @y
     if (t=" ")and(cat=0) then t:=space_token
-    else if cat=0 then t:=other_token+t else t:=left_brace_token*cat+t;
+    else if (cat=0)or(cat>=kanji) then t:=other_token+t
+    else if cat=active_char then t:= cs_token_flag + active_base + t
+    else t:=left_brace_token*cat+t;
 @z
 
 @x
@@ -61,20 +65,29 @@ Ucharcat_convert_code:
       error; cat:=12;
     end else cat:=cur_val;
 @y
-    if is_char_ascii(i) then
+    if i<=@"7F then { no |wchar_token| }
       begin if illegal_Ucharcat_ascii_catcode(cur_val) then
         begin print_err("Invalid code ("); print_int(cur_val);
 @.Invalid code@>
         print("), should be in the ranges 1..4, 6..8, 10..13");
         help1("I'm going to use 12 instead of that illegal code value.");@/
         error; cat:=12;
       end else cat:=cur_val;
-	end else
+    end else if i<=@"FF then
+      begin if (illegal_Ucharcat_ascii_catcode(cur_val))
+        and (illegal_Ucharcat_wchar_catcode(cur_val)) then
+        begin print_err("Invalid code ("); print_int(cur_val);
+@.Invalid code@>
+        print("), should be in the ranges 1..4, 6..8, 10..13, 16..19");
+        help1("I'm going to use 12 instead of that illegal code value.");@/
+        error; cat:=12;
+      end else cat:=cur_val;
+    end else { |wchar_token| only }
       begin if illegal_Ucharcat_wchar_catcode(cur_val) then
         begin print_err("Invalid code ("); print_int(cur_val);
 @.Invalid code@>
         print("), should be in the ranges 16..19");
-        help1("I'm going to use 12 instead of that illegal code value.");@/
+        help1("I'm going to use 18 instead of that illegal code value.");@/
         error; cat:=other_kchar;
       end else cat:=cur_val;
 	end;