First, the purpose of the experiment:
The use of C language compiled recursive descent parsing procedures, and simple language parsing.
The preparation of a recursive descent parser, syntax checking and realize the structure of the word lexical analysis program provided by sequence analysis.
Second, the experimental principle
Each nonterminal symbol corresponds to a subroutine.
This subroutine is determined according to a next input symbol (SELECT sets) which are processed in a production, then the right end of the production according to:
- Each encounter a terminator, it is determined whether the current read word matches the terminator, if matched, then the next word is read to continue the analysis; do not match, an error process is performed
- Each encounter a nonterminal, the appropriate subroutine is called
Third, the experiment asked for clarification
Enter the word string to "#" end if the grammar is correct sentences, the output success information, print "success", otherwise output "error", and pointed out grammatical errors of the type and location.
E.g:
Input begin a: = 9; x: = 2 * 3; b: = a + x end #
Output success
Input x: = a + b * c end #
Output 'end' error
Fourth, the experimental procedures
1. Grammar of the language to be analyzed (refer to P90)
2. Grammar to be expressed, at least comprising
- Statement
-condition
-expression
3. eliminate left recursion
4. Extract the left common factor
5. SELECT set computing
6. LL (1) grammar is determined
7. recursive descent parser
1 #include "string.h" 2 #include <stdio.h> 3 #include<conio.h> 4 5 void lrparser(); 6 void yucu(); 7 void statement(); 8 void expression(); 9 void term(); 10 void factor(); 11 int kk=0; 12 char prog[80],token[8]; 13 int syn,p,m,n,sum=0; 14 char ch; 15 char *rwtab[6]= {"begin","if","then","while","do","end"}; 16 17 void scaner() { 18 m=0; 19 for(n=0; n<8; n++) token[n]=NULL; 20 ch=prog[p++]; 21 while(ch==' ') ch=prog[p++]; 22 if((ch>='a' && ch<='z') ||(ch>='A' && ch<='Z')) { 23 while((ch>='a' && ch<='z') ||(ch>='A' && ch<='Z')||(ch>='0' && ch<='9')) { 24 token [m ++] = CH; 25 CH = PROG [P ++ ]; 26 is } 27 token [m ++] = ' \ 0 ' ; 28 SYN = 10 ; 29 P = p- . 1 ; // back one character 30 for (n- = 0 ; n-< . 6 ; n-++ ) { 31 is IF (strcmp (token, rwtab [n-]) == 0 ) { 32 SYN = n-+ . 1 ; 33 is BREAK ; 34 is } 35 } 36 } else if(ch>='0' && ch<='9') { 37 sum=0; 38 while(ch>='0' && ch<='9') { 39 sum=sum*10+ch-'0'; 40 ch=prog[p++]; 41 } 42 p=p-1; syn =4311; 44 } else { 45 switch(ch) { 46 case '<': 47 m=0; 48 token[m++]=ch; 49 ch=prog[p]; 50 if(ch=='>') { 51 syn=21; 52 token[m++]=ch; 53 } else if(ch=='=') { 54 syn=22; 55 token[m++]=ch; 56 } else { 57 syn=20; 58 p=p-1; 59 } 60 p=p+1; 61 token[m]='\0'; 62 break; 63 case '>': 64 m=0; 65 token[m++]=ch; 66 ch=prog[p++]; 67 if(ch=='=') { 68 syn=24; 69 token[m++]=ch; 70 } else { 71 syn=23; 72 p=p-1; 73 } 74 break; 75 case ':': 76 m=0; 77 token[m++]=ch; 78 ch=prog[p++]; 79 if(ch=='=') { 80 syn=18; 81 token[m++]=ch; 82 } else { 83 syn=17; 84 p=p-1; 85 } 86 break; 87 case '+': 88 syn=13; 89 token[0]=ch; 90 break; 91 case '-': 92 syn=14; 93 token[0]=ch; 94 break; 95 case '*': 96 syn=15; 97 token[0]=ch; 98 break; 99 case '/': 100 syn=16; 101 token[0]=ch; 102 break; 103 case ';': 104 syn=26; 105 token[0]=ch; 106 break; 107 case '(': 108 syn=27; 109 token[0]=ch; 110 break; 111 case ')': 112 syn=28; 113 token[0]=ch; 114 break; 115 case '=': 116 syn=25; 117 token[0]=ch; 118 break; 119 case '#': 120 syn=0; 121 token[0]=ch; 122 break; 123 default: 124 syn=-1; 125 } 126 } 127 } 128 129 void lrparser() { 130 if (syn==1) { //begin 131 scaner(); 132 yucu(); 133 if (syn==6) { //end 134 scaner(); 135 if (syn==0 && kk==0) printf("success \n"); 136 } else { 137 if(kk!=1) printf("error,lose 'end' ! \n"); 138 kk=1; 139 } 140 } else { 141 printf("error,lose 'begin' ! \n"); 142 kk=1; 143 } 144 return; 145 } 146 147 void yucu() { 148 statement(); 149 while(syn==26) { 150 scaner(); 151 statement(); 152 } 153 return; 154 } 155 156 void statement() { 157 if (syn==10) { //An identifier 158 Scaner (); 159 IF (SYN == 18 is ) { // is: = 160. Scaner (); 161 expression The (); 162 } the else { 163 the printf ( " ! Error " ); 164 is KK = . 1 ; 165 } 166 } the else { 167 is the printf ( " error! " ); 168 KK = . 1 ; 169 } 170 return; 171 } 172 173 174 void expression() { 175 term(); 176 while(syn==13 || syn==14) { 177 scaner(); 178 term(); 179 } 180 return; 181 } 182 183 184 void term() { 185 factor(); 186 while(syn==15 || syn==16) { 187 Scaner (); 188 factor (); 189 } 190 return ; 191 } 192 193 194 void factor () { 195 IF (SYN == 10 || == SYN . 11 ) Scaner (); // an identifier or an integer constant when the next read word symbol 196 the else IF (SYN == 27 ) { 197 Scaner (); 198 expression the (); 199 IF (SYN == 28 ) Scaner (); 200 is the else { 201 the printf ( "')' Error \ n- " ); 202 KK = . 1 ; 203 } 204 } the else { 205 the printf ( " Expression Error \ n- " ); 206 KK = . 1 ; 207 } 208 return ; 209 } 210 211 212 int main ( ) { 213 P = 0 ; int I; 214 the printf ( " ************************************************************ parser ************* ** \ the n- " ); 215 the printf ( " Please enter the source: \ n- " ); 216 do { 217 Scanf ( " % C " , & CH); 218 PROG [P ++] = CH; 219 } the while (! CH = ' # ' ); 220 = P 0 ; 221 Scaner (); 222 lrparser (); 223 the printf ( " parsing end \ n-! " ); 224 getch (); 225 }
Test Results: