Files
secondo/Tools/pd/PDLex.l
2026-01-23 17:03:45 +08:00

148 lines
5.2 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

/*
----
This file is part of the PD system
Copyright (C) 1998 Ralf Hartmut Gueting, Fachbereich Informatik, FernUniversitaet Hagen
This program is free software; you can redistribute it and/or
modify it under the terms of the GNU General Public License
as published by the Free Software Foundation; either version 2
of the License, or (at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
----
*/
%option yylineno
%option debug
%{
#include "PDNestedText.h"
extern int yylex();
%}
/* regular definitions */
lbracket ("(*"|"/*")
rbracket ("*)"|"*/")
star [*]
other [-;,?!`´'()/@#$%_\^{}+=|<>\n&üÜäÄöÖßµ¤]
open {lbracket}{star}*(" "*[\n])+
open2 ([\n]" "*)*[\n]{lbracket}{star}*(" "*[\n])+
close {star}*{rbracket}(" "*[\n])+
epar [\n]" "*[\n](" "*[\n])*
defline1 [\n]" "*"//"
defline2 " "*"//"
digit [0-9]
num ({digit}{digit}|{digit})
ref "["{num}"]"
verbatim "----"
tt "__"
head1 {num}" "
head2 {num}"."{head1}
head3 {num}"."{head2}
head4 {num}"."{head3}
head5 {num}"."{head4}
enum1 " "{digit}" "|" "{digit}{digit}" "
enum2 " "{enum1}
bullet1 " * "
bullet2 " "{bullet1}
follow1 " "
follow2 " "{follow1}
display " "
figure " "
%x VERB
%%
<INITIAL>^{open} {return(OPEN);}
<INITIAL>{open2} {return(OPEN);}
<INITIAL>^{close} {return(CLOSE);}
<INITIAL>^{close}{open} { }
<INITIAL>^{verbatim} {
BEGIN(VERB);
return(VERBATIM);
}
<VERB>.|\n {
const char* v1="\\verb!{!";
const char* v2="\\verb!}!";
const char* v3="\\verb!\\!";
switch (yytext[0]) {
case '{' : { yylval = atom(v1,8); break; }
case '}' : { yylval = atom(v2,8); break; }
case '\\' : { yylval = atom(v3,8); break; }
default : { yylval = atom(yytext, yyleng); }
}
return(VCHAR);
}
<VERB>^{verbatim} {
BEGIN(INITIAL);
return(ENDVERBATIM);
}
<INITIAL>{epar} {yylval = atom(yytext, yyleng); return(EPAR);}
<INITIAL>{defline1} {yylval = atom(yytext, yyleng); return(DEFLINE);}
<INITIAL>^{defline2} {yylval = atom(yytext, yyleng); return(DEFLINE);}
<INITIAL>[A-Za-z] {yylval = atom(yytext, yyleng); return(LETTER);}
<INITIAL>^{head1} {yylval = atom(yytext, yyleng); return(HEAD1);}
<INITIAL>^{head2} {yylval = atom(yytext, yyleng); return(HEAD2);}
<INITIAL>^{head3} {yylval = atom(yytext, yyleng); return(HEAD3);}
<INITIAL>^{head4} {yylval = atom(yytext, yyleng); return(HEAD4);}
<INITIAL>^{head5} {yylval = atom(yytext, yyleng); return(HEAD5);}
<INITIAL>^{enum1} {yylval = atom(yytext, yyleng); return(ENUM1);}
<INITIAL>^{enum2} {yylval = atom(yytext, yyleng); return(ENUM2);}
<INITIAL>^{bullet1} {yylval = atom(yytext, yyleng); return(BULLET1);}
<INITIAL>^{bullet2} {yylval = atom(yytext, yyleng); return(BULLET2);}
<INITIAL>^{follow1} {yylval = atom(yytext, yyleng); return(FOLLOW1);}
<INITIAL>^{follow2} {yylval = atom(yytext, yyleng); return(FOLLOW2);}
<INITIAL>^{display} {yylval = atom(yytext, yyleng); return(DISPLAY);}
<INITIAL>^{figure} {yylval = atom(yytext, yyleng); return(FIGURE);}
<INITIAL>^({ref}" "|"[] ") {yylval = atom(yytext, yyleng); return(STARTREF);}
<INITIAL>{ref} {yylval = atom(yytext, yyleng); return(REF);}
<INITIAL>[0-9] {yylval = atom(yytext, yyleng); return(DIGIT);}
<INITIAL>"[~]" {yylval = atom(yytext, yyleng); return(TILDE);}
<INITIAL>"[*]" {yylval = atom(yytext, yyleng); return(STAR);}
<INITIAL>"[__]" {yylval = atom(yytext, yyleng); return(DUS);}
<INITIAL>"[\"]" {yylval = atom(yytext, yyleng); return(QUOTE);}
<INITIAL>" ~ " {yylval = atom(yytext, yyleng); return(BLANKTILDE);}
<INITIAL>" * " {yylval = atom(yytext, yyleng); return(BLANKSTAR);}
<INITIAL>" __ " {yylval = atom(yytext, yyleng); return(BLANKDUS);}
<INITIAL>" \" " {yylval = atom(yytext, yyleng); return(BLANKQUOTE);}
<INITIAL>{other} {yylval = atom(yytext, yyleng); return(OTHER);}
<INITIAL>. {yylval = atom(yytext, yyleng); return(yytext[0]);}
<INITIAL>"paragraph" {yylval = atom(yytext, yyleng); return(PARFORMAT);}
<INITIAL>"characters" {yylval = atom(yytext, yyleng); return(CHARFORMAT);}
<INITIAL>{tt} {yylval = atom(yytext, yyleng); return(TTFORMAT);}
%%
/*
<INITIAL>"'" { yylval = atom(yytext, yyleng); return(OTHER);}
3.3 Testing the Lexical Analyser
One can test lexical analysis separately from the rest of the system. The files ~PDTokens.h~ and ~PDLexTest.c~ are needed. The file ~PDTokens.h~ needs to be included in the ~declarations~ section of ~Lex.l~:
---- %{
#include "PDTokens.h"
}%
----
This file just defines each token as an integer constant:
*/