added comment functionality for lexer, expanded tests, and updated to identify empty strings

This commit is contained in:
Partho Bhattacharya
2025-02-10 23:41:37 -05:00
parent f4a86f0de7
commit 3757434417
2 changed files with 19 additions and 5 deletions

View File

@ -7,8 +7,13 @@
DIGIT [0-9]
CHAR \\n|\\t|\\'|[^'\n\t\\]
SCHAR \\n|\\t|\\\"|[^\"\n\\]
/* char can be a newline, tab, an escaped quote, or anything but a single quote, an actual line break, an actual tab, or a backslash by itself (to prevent confusion from escaped quote */
SCHAR \\n|\\t|\\\"|[^\"\n\\]
/*similar to above, a string Char (SCHAR) is the same as a CHAR except we cannot have double quotes instead of single quotes. Double quotes need to be escaped in Flex unlike single quotes based on documentation */
STARTCOM \(\*
ENDCOM \*\)
COMMENTCHAR [^\*]|\*[^\)]
/*Making the contents of a comment anything that is either not a * or not a * followed by ) to terminate comments at the first ENDCOM */
%%
/* rules */
{DIGIT}+ {printf( "C_INTEGER: %s (%d)\n", yytext, atoi( yytext ) );}
@ -21,7 +26,9 @@ SCHAR \\n|\\t|\\\"|[^\"\n\\]
"false" {printf( "C_FALSE: %s (%d)\n", yytext, atoi( yytext ) );}
\"{SCHAR}+\" {printf( "C_STRING: %s (%d)\n", yytext, atoi( yytext ) );}
\"{SCHAR}*\" {printf( "C_STRING: %s (%d)\n", yytext, atoi( yytext ) );}
{STARTCOM}{COMMENTCHAR}*{ENDCOM} {printf( "COMMENT: %s (%d)\n", yytext, atoi( yytext ) );}
.|\n

View File

@ -1,9 +1,15 @@
"this is a string" 721398 'g' '/n'
12893 "this is not a string
"this is a string" 721398 'g' '/n' (* should print 3 tokens before this *)
'
'
12893 "this is not a string (*one valid token before this*)
(* spacey comment here
over multiple lines
will it work? *)
"
'''
'\'
false
(**)
'''
nullfalse
"nulltrue
@ -21,6 +27,7 @@ true
'n'
'\'
'fdsf'
(*/jnewjno2893u86^ Lots of random characters /n /t '") *)
'
'
' '