[fda8168] | 1 | /* -*- Mode: C -*- |
---|
| 2 | * |
---|
| 3 | * Pretty Printer Lexer, Copyright (C) Rodolfo Gabriel Esteves and Peter A. Buhr 2001 |
---|
| 4 | * Permission is granted to copy this grammar and to use it within software systems. |
---|
| 5 | * THIS GRAMMAR IS PROVIDED "AS IS" AND WITHOUT ANY EXPRESS OR IMPLIED WARRANTIES. |
---|
| 6 | * |
---|
| 7 | * lex.l -- |
---|
| 8 | * |
---|
| 9 | * Author : Rodolfo Gabriel Esteves |
---|
| 10 | * Created On : Sat Dec 15 11:45:59 2001 |
---|
| 11 | * Last Modified By : Peter A. Buhr |
---|
| 12 | * Last Modified On : Mon Apr 8 15:48:24 2002 |
---|
| 13 | * Update Count : 245 |
---|
| 14 | */ |
---|
| 15 | |
---|
| 16 | %option stack |
---|
| 17 | %option yylineno |
---|
| 18 | |
---|
| 19 | %{ |
---|
| 20 | #include <list> |
---|
| 21 | #include <string> |
---|
| 22 | #include <iostream> |
---|
| 23 | |
---|
| 24 | #include "parse.h" |
---|
| 25 | #include "yacc.tab.h" |
---|
| 26 | |
---|
| 27 | #define RETURN_TOKEN( kind ) yylval.tokenp = new Token( yytext, ws_list, kind ); return kind; |
---|
| 28 | |
---|
| 29 | list<string> ws_list; |
---|
| 30 | string comment_str; |
---|
| 31 | string code_str; |
---|
| 32 | %} |
---|
| 33 | |
---|
| 34 | integer [0-9]+ |
---|
| 35 | identifier [a-zA-Z_$][0-9a-zA-Z_$]* |
---|
| 36 | |
---|
| 37 | simple_escape ['"?\\] |
---|
| 38 | escape_sequence [\\]{simple_escape} |
---|
| 39 | c_char [^'\\\n]|{escape_sequence} |
---|
| 40 | s_char [^"\\\n]|{escape_sequence} |
---|
| 41 | |
---|
| 42 | %x C_COMMENT STR C_CODE |
---|
| 43 | |
---|
| 44 | /* ---------------------------- Token Section ---------------------------- */ |
---|
| 45 | %% |
---|
| 46 | <INITIAL,C_CODE>"/*" { /* C style comments */ |
---|
| 47 | #if defined(DEBUG_ALL) | defined(DEBUG_COMMENT) |
---|
| 48 | cerr << "\"/*\" : " << yytext << endl; |
---|
| 49 | #endif |
---|
| 50 | if ( YYSTATE == C_CODE ) code_str += yytext; |
---|
| 51 | else comment_str += yytext; |
---|
| 52 | yy_push_state(C_COMMENT); |
---|
| 53 | } |
---|
| 54 | <C_COMMENT>(.|"\n") { /* C style comments */ |
---|
| 55 | #if defined(DEBUG_ALL) | defined(DEBUG_COMMENT) |
---|
| 56 | cerr << "<C_COMMENT>(.|\\n) : " << yytext << endl; |
---|
| 57 | #endif |
---|
| 58 | if ( yy_top_state() == C_CODE ) code_str += yytext; |
---|
| 59 | else comment_str += yytext; |
---|
| 60 | } |
---|
| 61 | <C_COMMENT>"*/" { /* C style comments */ |
---|
| 62 | #if defined(DEBUG_ALL) | defined(DEBUG_COMMENT) |
---|
| 63 | cerr << "<C_COMMENT>\"*/\" : " << yytext << endl; |
---|
| 64 | #endif |
---|
| 65 | if ( yy_top_state() == C_CODE ) code_str += yytext; |
---|
| 66 | else { |
---|
| 67 | comment_str += yytext; |
---|
| 68 | //cerr << "C COMMENT : " << endl << comment_str << endl; |
---|
| 69 | ws_list.push_back( comment_str ); |
---|
| 70 | comment_str = ""; |
---|
| 71 | } |
---|
| 72 | yy_pop_state(); |
---|
| 73 | } |
---|
| 74 | <INITIAL,C_CODE>"//"[^\n]*"\n" { /* C++ style comments */ |
---|
| 75 | #if defined(DEBUG_ALL) | defined(DEBUG_COMMENT) |
---|
| 76 | cerr << "\"//\"[^\\n]*\"\n\" : " << yytext << endl; |
---|
| 77 | #endif |
---|
| 78 | if ( YYSTATE == C_CODE ) code_str += yytext; |
---|
| 79 | else { |
---|
| 80 | comment_str += yytext; |
---|
| 81 | //cerr << "C++ COMMENT : " << endl << comment_str << endl; |
---|
| 82 | ws_list.push_back( comment_str ); |
---|
| 83 | comment_str = ""; |
---|
| 84 | } |
---|
| 85 | } |
---|
| 86 | |
---|
| 87 | ";" { RETURN_TOKEN( ';' ) } |
---|
| 88 | ":" { RETURN_TOKEN( ':' ) } |
---|
| 89 | "|" { RETURN_TOKEN( '|' ) } |
---|
| 90 | "," { RETURN_TOKEN( ',' ) } |
---|
| 91 | "<" { RETURN_TOKEN( '<' ) } |
---|
| 92 | ">" { RETURN_TOKEN( '>' ) } |
---|
| 93 | |
---|
| 94 | [[:space:]]+ { /* [ \t\n]+ */ |
---|
| 95 | ws_list.push_back( yytext ); |
---|
| 96 | //cerr << "WS : " << "\"" << yytext << "\"" << endl; |
---|
| 97 | } |
---|
| 98 | |
---|
| 99 | <INITIAL>"{" { RETURN_TOKEN( '{' ) } |
---|
| 100 | <INITIAL>"}" { RETURN_TOKEN( '}' ) } |
---|
| 101 | <C_CODE>"{" { |
---|
| 102 | #if defined(DEBUG_ALL) | defined(DEBUG_C) |
---|
| 103 | cerr << "<C_CODE>. : " << yytext << endl; |
---|
| 104 | #endif |
---|
| 105 | code_str += yytext; |
---|
| 106 | RETURN_TOKEN( '{' ) |
---|
| 107 | } |
---|
| 108 | <C_CODE>"}" { |
---|
| 109 | #if defined(DEBUG_ALL) | defined(DEBUG_C) |
---|
| 110 | cerr << "<C_CODE>. : " << yytext << endl; |
---|
| 111 | #endif |
---|
| 112 | code_str += yytext; |
---|
| 113 | RETURN_TOKEN( '}' ) |
---|
| 114 | } |
---|
| 115 | |
---|
| 116 | "%%" { RETURN_TOKEN( MARK ) } |
---|
| 117 | "%{" { RETURN_TOKEN( LCURL ) } |
---|
| 118 | <C_CODE>"%}" { RETURN_TOKEN( RCURL ) } |
---|
| 119 | |
---|
| 120 | ^"%union" { RETURN_TOKEN( UNION ) } |
---|
| 121 | ^"%start" { RETURN_TOKEN( START ) } |
---|
| 122 | ^"%token" { RETURN_TOKEN( TOKEN ) } |
---|
| 123 | ^"%type" { RETURN_TOKEN( TYPE ) } |
---|
| 124 | ^"%left" { RETURN_TOKEN( LEFT ) } |
---|
| 125 | ^"%right" { RETURN_TOKEN( RIGHT ) } |
---|
| 126 | ^"%nonassoc" { RETURN_TOKEN( NONASSOC ) } |
---|
| 127 | ^"%pure_parser" { RETURN_TOKEN( PURE_PARSER ) } |
---|
| 128 | ^"%semantic_parser" { RETURN_TOKEN( SEMANTIC_PARSER ) } |
---|
| 129 | ^"%expect" { RETURN_TOKEN( EXPECT ) } |
---|
| 130 | ^"%thong" { RETURN_TOKEN( THONG ) } |
---|
| 131 | |
---|
| 132 | "%prec" { RETURN_TOKEN( PREC ) } |
---|
| 133 | |
---|
| 134 | {integer} { RETURN_TOKEN( INTEGER ); } |
---|
| 135 | [']{c_char}['] { RETURN_TOKEN( CHARACTER ); } |
---|
| 136 | {identifier} { RETURN_TOKEN( IDENTIFIER ); } |
---|
| 137 | |
---|
| 138 | <C_CODE>["]{s_char}*["] { /* hide braces "{}" in strings */ |
---|
| 139 | #if defined(DEBUG_ALL) | defined(DEBUG_C) |
---|
| 140 | cerr << "<C_CODE>. : " << yytext << endl; |
---|
| 141 | #endif |
---|
| 142 | code_str += yytext; |
---|
| 143 | } |
---|
| 144 | |
---|
| 145 | <C_CODE>(.|\n) { /* must be last rule of C_CODE */ |
---|
| 146 | #if defined(DEBUG_ALL) | defined(DEBUG_C) |
---|
| 147 | cerr << "<C_CODE>. : " << yytext << endl; |
---|
| 148 | #endif |
---|
| 149 | code_str += yytext; |
---|
| 150 | } |
---|
| 151 | |
---|
| 152 | . { printf("UNKNOWN CHARACTER:%s\n", yytext); } /* unknown characters */ |
---|
| 153 | %% |
---|
| 154 | void lexC(void) { |
---|
| 155 | BEGIN(C_CODE); |
---|
| 156 | } |
---|
| 157 | |
---|
| 158 | string lexYacc(void) { |
---|
| 159 | BEGIN(INITIAL); |
---|
| 160 | //cerr << "CODE: " << endl << code_str << endl; |
---|
| 161 | string temp( code_str ); |
---|
| 162 | code_str = ""; |
---|
| 163 | return temp; |
---|
| 164 | } |
---|
| 165 | |
---|
| 166 | /* Local Variables: */ |
---|
| 167 | /* fill-column: 100 */ |
---|
| 168 | /* compile-command: "gmake" */ |
---|
| 169 | /* End: */ |
---|