add more tokens and fix identifier regex

lab-3/main.c

@@ -8,7 +8,7 @@ extern char *yytext;
 
 int main(int argc, char *argv[]) {
   FILE *file;
-  const char *filename = "samples/sorting-snippet.cbl"; // Default filename
+  const char *filename = "samples/quadratic-snippet.cbl"; // Default filename
 
   // Check if a filename is provided as a command-line argument
   if (argc > 1) {

lab-3/main_test.c

@@ -48,6 +48,16 @@ UTEST(scanner, assignment) {
   yy_delete_buffer(buffer);
 }
 
+UTEST(scanner, hello) {
+  struct token_st tokens[] = {
+    {TOKEN_IDENTIFICATION, "IDENTIFICATION"},
+    {TOKEN_PROGRAM_ID, "PROGRAM-ID. HELLO-WORLD."}
+    {TOKEN_PROCEDURE_DIVISION, "PROCEDURE DIVISION."},
+    {TOKEN_STRING, "Hello World!"},
+    {TOKEN_KEYWORD_PRINT, "DISPLAY"},
+    {TOKEN_EOF, "STOP RUN."},
+  };
+
 UTEST(scanner, sample) {
   struct token_st tokens[] = {
     {TOKEN_IDENT, "answer"},

lab-3/scanner.flex

@@ -1,11 +1,11 @@
 %{
 #include "token.h"
 %}
-DIGIT [0-9]
+NAME [a-zA-Z]([a-zA-Z0-9_-]*[a-zA-Z0-9])?
-LETTER [a-zA-Z]
+DIGIT [0-9]+
-NAME [a-zA-Z0-9][a-zA-Z0-9_-]*[a-zA-Z0-9]
 
 %%
+
 (" "|\t|\n) /* skip whitespace */
 \*>\ ?.* { return TOKEN_COMMENT; }
 IDENTIFICATION { return TOKEN_IDENTIFICATION; }
@@ -32,23 +32,34 @@ SPACE { return TOKEN_SPACE; }
 PIC { return TOKEN_PICTURE; }
 OCCURS { return TOKEN_KEYWORD_OCCURS; }
 VALUE { return TOKEN_KEYWORD_VALUE; }
+COMPUTE { return TOKEN_KEYWORD_COMPUTE; }
+FUNCTION { return TOKEN_KEYWORD_FUNCTION; }
 X { return TOKEN_ALPHANUMERIC; }
 S9 { return TOKEN_SIGNED_NUMERIC; }
 9 { return TOKEN_NUMERIC; }
+V9 { return TOKEN_IMPLIED_DECIMAL; }
+COMP { return TOKEN_COMPUTATION_LEVEL_0; }
+COMP-1 { return TOKEN_COMPUTATION_LEVEL_1; }
+COMP-2 { return TOKEN_COMPUTATION_LEVEL_2; }
+COMP-3 { return TOKEN_COMPUTATION_LEVEL_3; }
 
+{DIGIT} { return TOKEN_INTEGER; }
+{NAME} { return TOKEN_IDENT; }
 \+ { return TOKEN_ADD; }
 \- { return TOKEN_SUB; }
+\*\* { return TOKEN_EXPONENTIAL; }
+\* { return TOKEN_MULTIPLY; }
+\/ { return TOKEN_DIVIDE; }
 \> { return TOKEN_GREATER_THAN; }
 \< { return TOKEN_LESS_THAN; }
+\= { return TOKEN_EQUAL;}
 
 "\""[^"]*"\""   { return TOKEN_STRING; }
 "\'"[^']*"\'"   { return TOKEN_STRING; }
 "("             { return TOKEN_LEFT_PARENTHESIS; }
 ")"             { return TOKEN_RIGHT_PARENTHESIS; }
 
-
 \. { return TOKEN_DOT; }
-{NAME} { return TOKEN_IDENT; }
+
-{DIGIT} { return TOKEN_INTEGER; }
 %%
 int yywrap() { return 1; }

lab-3/token.h

@@ -26,6 +26,8 @@ typedef enum {
   TOKEN_SPACE,
   TOKEN_KEYWORD_OCCURS,
   TOKEN_KEYWORD_VALUE,
+  TOKEN_KEYWORD_COMPUTE,
+  TOKEN_KEYWORD_FUNCTION,
 
   // Identifiers
   TOKEN_IDENT,
@@ -36,6 +38,13 @@ typedef enum {
   TOKEN_ALPHANUMERIC,
   TOKEN_NUMERIC,
   TOKEN_SIGNED_NUMERIC,
+  TOKEN_IMPLIED_DECIMAL,
+  // https://ibmmainframes.com/about393.html
+  TOKEN_COMPUTATION_LEVEL_0,
+  TOKEN_COMPUTATION_LEVEL_1,
+  TOKEN_COMPUTATION_LEVEL_2,
+  TOKEN_COMPUTATION_LEVEL_3,
+
   // Grammar
   TOKEN_LEFT_PARENTHESIS,
   TOKEN_RIGHT_PARENTHESIS,
@@ -45,6 +54,10 @@ typedef enum {
   // Operators
   TOKEN_ADD,
   TOKEN_SUB,
+  TOKEN_MULTIPLY,
+  TOKEN_DIVIDE,
+  TOKEN_EQUAL,
   TOKEN_GREATER_THAN,
   TOKEN_LESS_THAN,
+  TOKEN_EXPONENTIAL,
 } token_t;