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
solution:
#include <stdio.h> #include <the iostream> #include <string.h> the using namespace STD; char * Reserved [. 6] = { "the begin", "IF", "the then", "the while", "do" , "End"}; char INPUT [80], Output [. 8]; char CH; int SYN, p, I; // SYN code is a species other, p is the scanning adding int m = 0, n, row , sum 0 =, COUNT = 0; int flag = 0; // flag void parseS (); // parse the statement void ParseS1 (); void ParseS2 (); void ParseS3 (); void ParseS4 (); void PARSEC (); analysis conditions // void ParseE (); // analytic expression void ParseE1 (); void PARSET (); // resolvables void ParseT1 (); void ParseF (); // parse factor void Scanner () { for (I = 0; i <8;i++ ){ output[i] = NULL;++ I) { } // initialize output ch = input[p++]; while( ch == ' ' ){ ch = input[p] ; p ++ ; } //持续读入 if( ( ch >= 'a' && ch <= 'z' ) || ( ch >= 'A' && ch <= 'Z' ) ){ m = 0 ; while( ( ch >= 'a' && ch <= 'z' ) || ( ch >= 'A' && ch <= 'Z' ) || ( ch >= '0' && ch <= '9' ) ){ output[m++] = ch ; ch = input[p++]; } output[m++] = '\0'; p -- ; syn = 10 ; for( n = 0 ; n < 6 ; n ++ ){ if( strcmp(output,reserved[n]) == 0 ){ syn = n + 1; break; } } }else if( ( ch >= '0' && ch <= '9' ) ){ sum = 0 ; while( ch >= '0' && ch <= '9' ){ sum=sum*10+ch-'0' ; ch = input[p++] ; } p -- ; syn = 11; } else if(ch == '/'){ ch = input[p++] ; if(ch == '/'){ while(ch != '\n'){ ch = input[p++] ; } scanner(); } else if(ch == '*'){ ch = input[p++]; int flag=0; // printf("%c %c",ch,input[p]); while((ch == '*' && input[p] != '/')||(ch != '*' && input[p] == '/') || (ch != '*' && input[p] != '/')){ ch = input[p++] ; if(p==count-2 && (ch != '*' && input[p] != '/')){ flag =1; syn = 100; break; } } p++; if(flag==0){ scanner(); } }else{ p = p - 2 ; ch = input[p++] ; output[0] = ch ; syn = 16 ; } }else switch(ch){ case '+': output[0] = ch ; syn = 13; break; case '-': output[0] = ch ; syn = 14; break; case '*': output[0] = ch ; syn = 15 ; break; case '/': output[0] = ch ; syn = 16 ; break; case ':': i = 0; output[i++] = ch ; ch = input[p++]; if( ch == '=' ){ output[i++] = ch; syn = 18 ; }else{ syn = 17; p-- ; } break; case '<': i = 0 ; output[i++] = ch ; ch = input[p++] ; if( ch == '=' ){ output[i++] = ch ; syn = 21 ; }else if( ch == '>' ){ output[i++] = ch ; syn = 22 ; }else{ syn = 20 ; p-- ; } break; case '>': i = 0; output[i++] = ch ; ch = input[p++] ; if( ch == '=' ){ output[i++] = ch; syn=24; }else{ syn=23; p--; } break; case '=': output[0] = ch ; syn = 25 ; break; case ';': output[0] = ch ; syn = 26 ; break; case '(': output[0] = ch ; syn = 27 ; break; case ')': output[0] = ch ; syn = 28 ; break; case '#': output[0] = ch ; syn = 0; break; case '\n': syn = 99 ; break; default: syn = -1 ; break; } } void ParseS(){ if(flag != 0){ if(syn == 10){ //<id>:=<表达式> scanner(); ParseS1(); } else if(syn == 2){ //if scanner(); ParseS2(); } else if(syn == 4){//while scanner(); ParseS3(); } else if(syn == 0){ } else{ printf("statement syntx error S\n"); exit(0); } } else{ if(syn == 1){//begin scanner(); flag = 1; ParseS4(); }else{ printf("error,缺少begin!\n"); exit(0); } } } void ParseS1(){ if(syn==18){ scanner(); ParseE(); } else{ printf("statement syntx error S1\n"); exit(0); } } void ParseS2(){//if ParseC(); if(syn== 3 ){ scanner(); ParseS(); } else{ printf("statement syntx error S2\n"); exit(0); } } void ParseS3(){//while ParseC(); if(syn== 5 ){ scanner(); ParseS(); } else{ printf("statement syntx error S3 \n"); exit(0); } } void ParseS4(){//begin ParseS(); while(syn == 26){ scanner(); ParseS(); } if(syn == 6){ scanner(); if(syn == 0){ printf("success!"); } else{ printf("statement syntx error S4\n"); } } else{ printf("error,缺少end\n"); exit(0); } } void ParseC(){ ParseE(); if(syn==25||syn==0||syn==20||syn==21||syn==23||syn==24){ scanner(); scanner(); } else{ printf("condition syntx error C\n"); exit(0); } ParseE(); } void ParseE(){ ParseT(); ParseE1(); } void ParseE1(){ if(syn == 13 || syn == 14){ scanner(); ParseT(); ParseE1(); } else if(syn == 28 || syn == 0){ } } void ParseT(){ ParseF(); ParseT1(); } void ParseT1(){ if(syn == 15 || syn == 16){ scanner(); ParseF(); ParseT1(); } else if(syn == 13 ||syn == 14 || syn == 28 || syn == 0){ } } void ParseF(){ if(syn == 27){ scanner(); ParseE(); if(syn == 28){ scanner(); } else{ printf("factor syntx error F\n"); exit(0); } } else if(syn == 10 || syn == 11){ scanner(); } else{ printf("factor syntx error F\n"); exit(0); } } int main() { p = 0; printf("请输入源程序:"); do{ ch = getchar(); input[p++] = ch; }while(ch != '#'); count = p; p = 0; scanner(); ParseS(); return 0; }