Scribd
Upload
2 views

Lexical Analyzer

The document contains a C++ implementation of a lexical analyzer for arithmetic expressions. It defines various token codes, functions to read characters, and parse identifiers and literals. The main function processes an input file, extracting tokens until the end of the file is reached.

Uploaded by

mustuni2004
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
2 views

Lexical Analyzer

The document contains a C++ implementation of a lexical analyzer for arithmetic expressions. It defines various token codes, functions to read characters, and parse identifiers and literals. The main function processes an input file, extracting tokens until the end of the file is reached.

Uploaded by

mustuni2004
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

...g\LexicalAnalyzer\LexicalAnalyzer\LexicalAnalyzer.

cpp 1
1 #include <stdio.h>
2 #include <ctype.h>
3
4 #define LETTER 0
5 #define DIGIT 1
6 #define UNKNOWN 99
7
8 // Token codes
9 #define INT_LIT 10
10 #define IDENT 11
11 #define ASSIGN_OP 20
12 #define ADD_OP 21
13 #define SUB_OP 22
14 #define MULT_OP 23
15 #define DIV_OP 24
16 #define LEFT_PAREN 25
17 #define RIGHT_PAREN 26
18
19 // Global variables
20 int charClass;
21 char lexeme[100];
22 char nextChar;
23 int lexLen;
24 int token;
25 int nextToken;
26 FILE* in_fp, * fopen();
27
28 // Function declarations
29 void addChar();
30 void getChar();
31 void getNonBlank();
32 int lex();
33 int lookup(char ch);
34
35 // Main driver
36 int main() {
37 // Open the input data file and process its contents
38 if (fopen_s(&in_fp, "front.in", "r") != 0) {
39 printf("ERROR - cannot open front.in \n");
40 }
41 else {
42 getChar();
43 do
44 lex();
45 while (nextToken != EOF);
46 }
47 return 0;
48 }
49
...g\LexicalAnalyzer\LexicalAnalyzer\LexicalAnalyzer.cpp 2
50 // lookup - a function to lookup operators and parentheses and return the
token
51 int lookup(char ch) {
52 switch (ch) {
53 case '(':
54 addChar();
55 nextToken = LEFT_PAREN;
56 break;
57 case ')':
58 addChar();
59 nextToken = RIGHT_PAREN;
60 break;
61 case '+':
62 addChar();
63 nextToken = ADD_OP;
64 break;
65 case '-':
66 addChar();
67 nextToken = SUB_OP;
68 break;
69 case '*':
70 addChar();
71 nextToken = MULT_OP;
72 break;
73 case '/':
74 addChar();
75 nextToken = DIV_OP;
76 break;
77 default:
78 addChar();
79 nextToken = EOF;
80 break;
81 }
82 return nextToken;
83 }
84
85 // addChar - a function to add nextChar to lexeme
86 void addChar() {
87 if (lexLen <= 98) {
88 lexeme[lexLen++] = nextChar;
89 lexeme[lexLen] = 0;
90 }
91 else {
92 printf("Error - lexeme is too long \n");
93 }
94 }
95
96 // getChar - a function to get the next character of input and determine
its character class
...g\LexicalAnalyzer\LexicalAnalyzer\LexicalAnalyzer.cpp 3
97 void getChar() {
98 if ((nextChar = getc(in_fp)) != EOF) {
99 if (isalpha(nextChar))
100 charClass = LETTER;
101 else if (isdigit(nextChar))
102 charClass = DIGIT;
103 else
104 charClass = UNKNOWN;
105 }
106 else {
107 charClass = EOF;
108 }
109 }
110
111 // getNonBlank - a function to call getChar until it returns a non-
whitespace character
112 void getNonBlank() {
113 while (isspace(nextChar))
114 getChar();
115 }
116
117 // lex - a simple lexical analyzer for arithmetic expressions
118 int lex() {
119 lexLen = 0;
120 getNonBlank();
121 switch (charClass) {
122 // Parse identifiers
123 case LETTER:
124 addChar();
125 getChar();
126 while (charClass == LETTER || charClass == DIGIT) {
127 addChar();
128 getChar();
129 }
130 nextToken = IDENT;
131 break;
132 // Parse integer literals
133 case DIGIT:
134 addChar();
135 getChar();
136 while (charClass == DIGIT) {
137 addChar();
138 getChar();
139 }
140 nextToken = INT_LIT;
141 break;
142 // Parentheses and operators
143 case UNKNOWN:
144 lookup(nextChar);
...g\LexicalAnalyzer\LexicalAnalyzer\LexicalAnalyzer.cpp 4
145 getChar();
146 break;
147 // EOF
148 case EOF:
149 nextToken = EOF;
150 lexeme[0] = 'E';
151 lexeme[1] = '0';
152 lexeme[2] = 'F';
153 lexeme[3] = 0;
154 break;
155 } // End of switch
156 printf("Next token is: %d, Next lexeme is %s\n", nextToken, lexeme);
157 return nextToken;
158 }
159

You might also like