ps2ascii.ps

GhostScript的源代码

       { (F ) //print
	 3 -1 roll dup //.font.height exch .iput .show==only ( ) //print
         exch dup //.font.width exch .iput .show==only ( ) //print
	 dup length //.font.name.length exch .iput
         //.font.name cvs .show==only (\n) //print
       }
      ifelse
    }
   ifelse
 } odef

% Define the letters -- characters which, if they occur followed by a hyphen
% at the end of a line, cause the hyphen and line break to be ignored.
/.letter.chars 100 dict def
mark
  65 1 90 { dup 32 add } for
    counttomark
        { StandardEncoding exch get .letter.chars exch dup put }
    repeat
pop

%%* Add the rest of the letters from the [O]T1Encoding and
%%* ISOLatin1Encoding vectors

mark
    /AE
    /Aacute
    /Abreve
    /Acircumflex
    /Adieresis
    /Agrave
    /Aogonek
    /Aring
    /Atilde
    /Cacute
    /Ccaron
    /Ccedilla
    /Dcaron
    /Eacute
    /Ecaron
    /Ecircumflex
    /Edieresis
    /Egrave
    /Eng
    /Eogonek
    /Eth
    /Gbreve
    /Germandbls 
    /IJ
    /Iacute
    /Icircumflex
    /Idieresis
    /Idot
    /Igrave
    /Lacute
    /Lcaron
    /Lslash
    /Nacute
    /Ncaron
    /Ntilde
    /OE
    /Oacute
    /Ocircumflex
    /Odieresis
    /Ograve
    /Ohungarumlaut
    /Oslash
    /Otilde
    /Racute
    /Rcaron
    /Sacute
    /Scaron
    /Scedilla
    /Tcaron
    /Tcedilla
    /Thorn
    /Uacute
    /Ucircumflex
    /Udieresis
    /Ugrave
    /Uhungarumlaut
    /Uring
    /Yacute
    /Ydieresis
    /Zacute
    /Zcaron
    /Zdot
    /aacute
    /abreve
    /acircumflex
    /adieresis
    /ae
    /agrave
    /aogonek
    /aring
    /atilde
    /cacute
    /ccaron
    /ccedilla
    /dbar
    /dcaron
    /dotlessi
    /dotlessj
    /eacute
    /ecaron
    /ecircumflex
    /edieresis
    /egrave
    /eng
    /eogonek
    /eth
    /exclamdown
    /ff
    /ffi
    /ffl
    /fi
    /fl
    /gbreve
    /germandbls
    /iacute
    /icircumflex
    /idieresis
    /igrave
    /ij
    /lacute
    /lcaron
    /lslash
    /nacute
    /ncaron
    /ntilde
    /oacute
    /ocircumflex
    /odieresis
    /oe
    /ograve
    /ohungarumlaut
    /oslash
    /otilde
    /questiondown
    /racute
    /rcaron
    /sacute
    /scaron
    /scedilla
    /section
    /sterling
    /tcaron
    /tcedilla
    /thorn
    /uacute
    /ucircumflex
    /udieresis
    /ugrave
    /uhungarumlaut
    /uring
    /yacute
    /ydieresis
    /zacute
    /zcaron
    /zdot
counttomark
    { .letter.chars exch dup put }
repeat
pop

% Define a set of characters which, if they occur at the start of a line,
% are taken as indicating a paragraph break.
/.break.chars 50 dict def
mark
    /bullet /dagger /daggerdbl /periodcentered /section
    counttomark
        { .break.chars exch dup put }
    repeat
pop

% Define character translation to ASCII.
% We have to do this for the entire character set.

/.char.map 500 dict def

/.chars.def { counttomark 2 idiv { .char.map 3 1 roll put } repeat pop } def

% Encode the printable ASCII characters.

mark 32 1 126
 { 1 string dup 0 4 -1 roll put
   dup 0 get StandardEncoding exch get exch
 }
for .chars.def

        % Encode accents.
mark
    /acute      (')
    /caron      (^)
    /cedilla    (,)
    /circumflex (^)
    /dieresis   (")
    /grave      (`)
    /ring       (*)
    /tilde      (~)
.chars.def

        % Encode the ISO accented characters.
mark 192 1 255
 { ISOLatin1Encoding exch get =string cvs
   dup 0 1 getinterval 1 index dup length 1 sub 1 exch getinterval
   .char.map 2 index known .char.map 2 index known and
    { .char.map 3 -1 roll get .char.map 3 -1 roll get concatstrings
      .char.map 3 1 roll put
    }
    { pop pop pop
    }
   ifelse
 }
for .chars.def

% Encode the remaining standard and ISO alphabetic characters.

mark
  /AE (AE) /Eth (DH) /OE (OE) /Thorn (Th)
  /ae (ae) /eth (dh)
  /ffi (ffi) /ffl (ffl) /fi (fi) /fl (fl)
  /germandbls (ss) /oe (oe) /thorn (th)
.chars.def

% Encode the other standard and ISO characters.

mark
  /brokenbar (|) /bullet (*) /copyright ((C)) /currency (#)
  /dagger (#) /daggerdbl (##) /degree (o) /divide (/) /dotaccent (.)
  /dotlessi (i)
  /ellipsis (...) /emdash (--) /endash (-) /exclamdown (!)
  /florin (f) /fraction (/)
  /guillemotleft (<<) /guillemotright (>>)
  /guilsingleft (<) /guilsingright (>) /hungarumlaut ("") /logicalnot (~)
  /macron (_) /minus (-) /mu (u) /multiply (*)
  /ogonek (,) /onehalf (1/2) /onequarter (1/4) /onesuperior (1)
  /ordfeminine (-a) /ordmasculine (-o)
  /paragraph (||) /periodcentered (*) /perthousand (o/oo) /plusminus (+-)
  /questiondown (?) /quotedblbase (") /quotedblleft (") /quotedblright (")
  /quotesinglbase (,) /quotesingle (') /registered ((R))
  /section ($) /sterling (#)
  /threequarters (3/4) /threesuperior (3) /trademark ((TM)) /twosuperior (2)
  /yen (Y)
.chars.def

% Encode a few common Symbol characters.

mark
  /asteriskmath (*) /copyrightsans ((C)) /copyrightserif ((C))
  /greaterequal (>=) /lessequal (<=) /registersans ((R)) /registerserif ((R))
  /trademarksans ((TM)) /trademarkserif ((TM))
.chars.def

%%* Add a few characters from StandardEncoding and ISOLatin1Encoding
%%* that were missing.

mark
    /cent           (c)
    /guilsinglleft  (<)
    /guilsinglright (>)
    /breve          (*)
    /Lslash         (L/)
    /lslash         (l/)
.chars.def

%%* Define the OT1Encoding and T1Encoding vectors for use with dvips
%%* files.  Unfortunately, there's no way of telling what font is
%%* really being used within a dvips document, so we can't provide an
%%* appropriate encoding for each individual font.  Instead, we'll
%%* just provide support for the two most popular text encodings, the
%%* OT1 and T1 encodings, and just accept the fact that any font not
%%* using one of those encodings will be rendered as gibberish.
%%* 
%%* OT1 is Knuth's 7-bit encoding for the CMR text fonts, while T1
%%* (aka the Cork encoding) is the 8-bit encoding used by the DC
%%* fonts, a preliminary version of the proposed Extended Computer
%%* Modern fonts.  Unfortunately, T1 is not a strict extension of OT1;
%%* they differ in positions 8#000 through 8#040, 8#074, 8#076, 8#134,
%%* 8#137, 8#173, 8#174, 8#175 and 8#177, so we can't use the same
%%* vector for both.
%%* 
%%* Of course, we also can't reliably tell the difference between an
%%* OT1-encoded font and a T1-encoded font based on the information in
%%* a dvips-created PostScript file.  As a best-guess solution, we'll
%%* use the T1 encoding if the font contains any characters in
%%* positions above 8#177 and the OT1 encoding if it doesn't.

/T1Encoding  256 array def

/OT1Encoding 256 array def

%%* T1Encoding shares a lot with StandardEncoding, so let's start
%%* there.

StandardEncoding T1Encoding copy pop

/OT1.encode {
    counttomark
    2 idiv
      { OT1Encoding 3 1 roll put }
    repeat
    cleartomark
} def

/T1.encode {
    counttomark
    2 idiv
      { T1Encoding 3 1 roll put }
    repeat
    cleartomark
} def

mark
    8#000 /grave
    8#001 /acute
    8#002 /circumflex
    8#003 /tilde
    8#004 /dieresis
    8#005 /hungarumlaut
    8#006 /ring
    8#007 /caron

    8#010 /breve
    8#011 /macron
    8#012 /dotaccent
    8#013 /cedilla
    8#014 /ogonek
    8#015 /quotesinglbase
    8#016 /guilsinglleft
    8#017 /guilsinglright

    8#020 /quotedblleft
    8#021 /quotedblright
    8#022 /quotedblbase
    8#023 /guillemotleft
    8#024 /guillemotright
    8#025 /endash
    8#026 /emdash
    8#027 /cwm

    8#030 /perthousandzero
    8#031 /dotlessi
    8#032 /dotlessj
    8#033 /ff
    8#034 /fi
    8#035 /fl
    8#036 /ffi
    8#037 /ffl

%%  8#040 through 8#176 follow StandardEncoding

    8#177 /hyphen
T1.encode

mark
    8#200 /Abreve
    8#201 /Aogonek
    8#202 /Cacute
    8#203 /Ccaron
    8#204 /Dcaron
    8#205 /Ecaron
    8#206 /Eogonek
    8#207 /Gbreve
    8#210 /Lacute
    8#211 /Lcaron
    8#212 /Lslash
    8#213 /Nacute
    8#214 /Ncaron
    8#215 /Eng
    8#216 /Ohungarumlaut
    8#217 /Racute
    8#220 /Rcaron
    8#221 /Sacute
    8#222 /Scaron
    8#223 /Scedilla
    8#224 /Tcaron
    8#225 /Tcedilla
    8#226 /Uhungarumlaut
    8#227 /Uring
    8#230 /Ydieresis
    8#231 /Zacute
    8#232 /Zcaron
    8#233 /Zdot
    8#234 /IJ
    8#235 /Idot
    8#236 /dbar
    8#237 /section
    8#240 /abreve
    8#241 /aogonek
    8#242 /cacute
    8#243 /ccaron
    8#244 /dcaron
    8#245 /ecaron
    8#246 /eogonek
    8#247 /gbreve
    8#250 /lacute
    8#251 /lcaron
    8#252 /lslash
    8#253 /nacute
    8#254 /ncaron
    8#255 /eng
    8#256 /ohungarumlaut
    8#257 /racute
    8#260 /rcaron
    8#261 /sacute
    8#262 /scaron
    8#263 /scedilla
    8#264 /tcaron
    8#265 /tcedilla
    8#266 /uhungarumlaut
    8#267 /uring
    8#270 /ydieresis
    8#271 /zacute
    8#272 /zcaron
    8#273 /zdot
    8#274 /ij
    8#275 /exclamdown
    8#276 /questiondown
    8#277 /sterling

    8#300 /Agrave
    8#301 /Aacute
    8#302 /Acircumflex
    8#303 /Atilde
    8#304 /Adieresis
    8#305 /Aring
    8#306 /AE
    8#307 /Ccedilla
    8#310 /Egrave
    8#311 /Eacute
    8#312 /Ecircumflex
    8#313 /Edieresis
    8#314 /Igrave
    8#315 /Iacute
    8#316 /Icircumflex
    8#317 /Idieresis
    8#320 /Eth
    8#321 /Ntilde
    8#322 /Ograve
    8#323 /Oacute
    8#324 /Ocircumflex
    8#325 /Otilde
    8#326 /Odieresis
    8#327 /OE
    8#330 /Oslash
    8#331 /Ugrave
    8#332 /Uacute
    8#333 /Ucircumflex
    8#334 /Udieresis
    8#335 /Yacute
    8#336 /Thorn
    8#337 /Germandbls 

    8#340 /agrave
    8#341 /aacute
    8#342 /acircumflex
    8#343 /atilde
    8#344 /adieresis
    8#345 /aring
    8#346 /ae
    8#347 /ccedilla
    8#350 /egrave
    8#351 /eacute
    8#352 /ecircumflex
    8#353 /edieresis
    8#354 /igrave
    8#355 /iacute
    8#356 /icircumflex
    8#357 /idieresis
    8#360 /eth
    8#361 /ntilde
    8#362 /ograve
    8#363 /oacute
    8#364 /ocircumflex
    8#365 /otilde
    8#366 /odieresis
    8#367 /oe
    8#370 /oslash
    8#371 /ugrave
    8#372 /uacute
    8#373 /ucircumflex
    8#374 /udieresis
    8#375 /yacute
    8#376 /thorn
    8#377 /germandbls

T1.encode

%%* Now copy OT1Encoding into T1Encoding and make a few changes.

T1Encoding OT1Encoding copy pop

mark
    8#000 /Gamma
    8#001 /Delta
    8#002 /Theta
    8#003 /Lambda
    8#004 /Xi
    8#005 /Pi
    8#006 /Sigma
    8#007 /Upsilon