Merge branch 'Dev' into Sprint1-TokenizeID_MainFunction-FE-t#04
This commit is contained in:
21
Makefile
21
Makefile
@ -7,25 +7,10 @@ lexicalStructure:
|
||||
$(FLEX) $(LEX)
|
||||
$(CC) lex.yy.c -o $(EXE)
|
||||
|
||||
test1:
|
||||
./$(EXE) ./tests/test_constants_literals.alpha
|
||||
|
||||
test2:
|
||||
./$(EXE) ./tests/test_keywards.alpha
|
||||
|
||||
test3:
|
||||
./$(EXE) ./tests/test_types.alpha
|
||||
|
||||
test4:
|
||||
./$(EXE) ./tests/test_variables.alpha
|
||||
|
||||
test5:
|
||||
./$(EXE) ./tests/test_otherpunc.alpha
|
||||
|
||||
test6:
|
||||
./$(EXE) ./tests/test_comments.alpha
|
||||
test_operators:
|
||||
./$(EXE) ./tests/test_operators.alpha
|
||||
|
||||
clean:
|
||||
rm -f *.o
|
||||
rm -f lex.yy.c
|
||||
rm -f $(EXE)
|
||||
rm -f $(EXE)
|
||||
|
@ -1,32 +1,72 @@
|
||||
/* Lexical Analysis with Flex (2.6.0) We used some of the code from this manual */
|
||||
/* Lexical Analysis with Flex (1.6.0) We used some of the code from this manual */
|
||||
/* so we placed the citation here. */
|
||||
/* definitions */
|
||||
|
||||
%option noyywrap
|
||||
%{
|
||||
#include "typedefs.h"
|
||||
int line_number = 1, column_number = 1;
|
||||
%}
|
||||
|
||||
COM ([^*]|\*+[^)*])*
|
||||
ID [A-Za-z_][0-9A-Za-z_]*
|
||||
DIGIT [0-9]
|
||||
CHAR \\n|\\t|\\'|[^'\n\t\\]
|
||||
/* 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 */
|
||||
|
||||
%%
|
||||
|
||||
"(*"{COM}"*)" {return COMMENT;}
|
||||
"integer" {return T_INTEGER;}
|
||||
"address" {return T_ADDRESS;}
|
||||
"Boolean" {return T_BOOLEAN;}
|
||||
"character" {return T_CHARACTER;}
|
||||
|
||||
{DIGIT}+ {return C_INTEGER;}
|
||||
"null" {return C_NULL;}
|
||||
|
||||
"while" {return WHILE;}
|
||||
"if" {return IF;}
|
||||
"then" {return THEN;}
|
||||
"else" {return ELSE;}
|
||||
"type" {return TYPE;}
|
||||
"function" {return FUNCTION;}
|
||||
"return" {return RETURN;}
|
||||
"external" {return EXTERNAL;}
|
||||
"as" {return AS;}
|
||||
|
||||
'{CHAR}' {return C_CHARACTER;}
|
||||
"true" {return C_TRUE;}
|
||||
"false" {return C_FALSE;}
|
||||
|
||||
"+" {return ADD;}
|
||||
"-" {return SUB_OR_NEG;}
|
||||
"*" {return MUL;}
|
||||
"/" {return DIV;}
|
||||
"%" {return REM;}
|
||||
"<" {return LESS_THAN;}
|
||||
"=" {return EQUAL_TO;}
|
||||
":=" {return ASSIGN;}
|
||||
"!" {return NOT;}
|
||||
"&" {return AND;}
|
||||
"|" {return OR;}
|
||||
"." {return DOT;}
|
||||
|
||||
";" {return SEMI_COLON;}
|
||||
":" {return COLON;}
|
||||
"," {return COMMA;}
|
||||
"->" {return ARROW;}
|
||||
|
||||
"reserve" {return RESERVE;}
|
||||
"release" {return RELEASE;}
|
||||
|
||||
\"{SCHAR}*\" {return C_STRING;}
|
||||
"(*"{COM}"*)" {return COMMENT;}
|
||||
|
||||
{ID} {return ID;}
|
||||
|
||||
%%
|
||||
\n {line_number++; column_number = 1;}
|
||||
. {column_number++;}
|
||||
|
||||
int main(int argc, char *argv[]){
|
||||
argc--, argv++;
|
||||
if ( argc > 0 )
|
||||
yyin = fopen( argv[0], "r" );
|
||||
else
|
||||
yyin = stdin;
|
||||
yylex();
|
||||
}
|
||||
%%
|
38
runner.c
38
runner.c
@ -0,0 +1,38 @@
|
||||
#include "runner.h"
|
||||
|
||||
|
||||
int main(int argc, char *argv[]) {
|
||||
char *check_input;
|
||||
int token;
|
||||
//check_input can be compared to INVALID_ARG and DIFF_ARG to determine if -tok and holds the generated file name if it is
|
||||
check_input = is_tok(argc, argv);
|
||||
FILE * output = fopen(check_input, "w");
|
||||
|
||||
if (check_input == INVALID_ARG) {
|
||||
return -1;
|
||||
}
|
||||
|
||||
while (0 != (token = yylex())) {
|
||||
if (check_input != DIFF_ARG) {
|
||||
fprintf(output, "%d %d %3d \"%s\"\n", line_number, column_number, token, yytext);
|
||||
}
|
||||
}
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
char *is_tok(int argc, char *argv[]) {
|
||||
if (argc == 3 && strcmp("-tok", argv[1])) {
|
||||
char *input_prog = argv[2];
|
||||
int file_len = strlen(input);
|
||||
//check that input program is a .alpha file
|
||||
if (strcmp(".alpha", input_prog[file_len - ALPHA_OFFSET]) != 0) {
|
||||
return INVALID_ARG;
|
||||
}
|
||||
char *FILE_tok[file_len - ALPHA_OFFSET + TOK_LEN];
|
||||
strncpy(input, FILE_tok, file_len - ALPHA_OFFSET); //copy name of prog before .alpha
|
||||
strcpy(".tok", FILE_tok[file_len - ALPHA_OFFSET]); //add .tok to end of file name
|
||||
return FILE_tok;
|
||||
}
|
||||
return DIFF_ARG;
|
||||
}
|
||||
|
13
runner.h
Normal file
13
runner.h
Normal file
@ -0,0 +1,13 @@
|
||||
#define ALPHA_OFFSET 5
|
||||
#define TOK_LEN 3
|
||||
#define INVALID_ARG "invalid"
|
||||
#define DIFF_ARG "diff"
|
||||
#include <string.h>
|
||||
#include <std.io>
|
||||
#include "lex.yy.c"
|
||||
|
||||
extern int line_number, column_number;
|
||||
extern char *yytext;
|
||||
|
||||
int main(int argc, char* argv);
|
||||
char *is_tok(int argc, char* argv);#define ALPHA_OFFSET 5
|
24
tests/generalTokenTest.alpha
Normal file
24
tests/generalTokenTest.alpha
Normal file
@ -0,0 +1,24 @@
|
||||
This is a test
|
||||
9combined 7okens
|
||||
12345
|
||||
893247892
|
||||
combined'DueToUnknownChar _validtoken __validtoken1 _valid_token2 validToken3_
|
||||
true false
|
||||
null while !wrong if when
|
||||
else type function
|
||||
return external as
|
||||
string _NOte_that_was_not_reserved
|
||||
([)]{}:;,->"\
|
||||
+-*/%
|
||||
<=
|
||||
:=
|
||||
"This is not a valid
|
||||
String"
|
||||
"This is a valid String"
|
||||
!|
|
||||
..
|
||||
(* this is a comment *)
|
||||
(*Not a comment
|
||||
$^&
|
||||
>
|
||||
|
4
tests/simpleIntTest.alpha
Normal file
4
tests/simpleIntTest.alpha
Normal file
@ -0,0 +1,4 @@
|
||||
45
|
||||
123
|
||||
8392
|
||||
|
47
tests/simpleLiteralAndCommentsTest.alpha
Normal file
47
tests/simpleLiteralAndCommentsTest.alpha
Normal file
@ -0,0 +1,47 @@
|
||||
"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
|
||||
null
|
||||
'7'
|
||||
true
|
||||
'189
|
||||
'\t'
|
||||
'"'
|
||||
'/'
|
||||
'\n'
|
||||
'\''
|
||||
'\t'
|
||||
'\\'
|
||||
'n'
|
||||
'\'
|
||||
'fdsf'
|
||||
(*/jnewjno2893u86^ Lots of random characters /n /t '") *)
|
||||
'
|
||||
'
|
||||
' '
|
||||
'''
|
||||
"STRINGwithnotSPaces"
|
||||
' '
|
||||
'\ '
|
||||
"J"
|
||||
""
|
||||
" "
|
||||
\"\"
|
||||
"{SCHAR}"
|
||||
"SCHAR"
|
||||
"[SCHAR]"
|
||||
"FINAL: I'd think this is a legal \"string\" that contains \n \t several escaped characters, isn't it?"
|
||||
"I'd think this is a legal \"string\" that contains several \\n \t escaped characters, isn't it?"
|
||||
nullLike
|
29
tests/test_keywords.alpha
Normal file
29
tests/test_keywords.alpha
Normal file
@ -0,0 +1,29 @@
|
||||
while
|
||||
While
|
||||
whiLe
|
||||
if
|
||||
IF
|
||||
If
|
||||
iF
|
||||
then
|
||||
Then
|
||||
theN
|
||||
else
|
||||
eLse
|
||||
elSe
|
||||
Else
|
||||
type
|
||||
Type
|
||||
tyPe
|
||||
function
|
||||
Function
|
||||
functioN
|
||||
return
|
||||
Return
|
||||
returN
|
||||
external
|
||||
External
|
||||
exteRnal
|
||||
as
|
||||
As
|
||||
aS
|
23
tests/test_operators.alpha
Normal file
23
tests/test_operators.alpha
Normal file
@ -0,0 +1,23 @@
|
||||
+
|
||||
-
|
||||
*
|
||||
/
|
||||
\
|
||||
%
|
||||
<
|
||||
>
|
||||
=
|
||||
:=
|
||||
=:
|
||||
:
|
||||
=
|
||||
!
|
||||
&
|
||||
|
|
||||
.
|
||||
relEASE
|
||||
release
|
||||
RELEASE
|
||||
reserve
|
||||
RESERVE
|
||||
reSERVe
|
Reference in New Issue
Block a user