From de6ef0ac023f4dcdbc4cc0d17f1fa3b9c755653d Mon Sep 17 00:00:00 2001
From: Riley Smith <riley@rileysmith.me>
Date: Tue, 22 Oct 2024 16:22:26 -0700
Subject: [PATCH] first pass at flex lexer

Co-authored-by: Jenessyl <Jenessyl@users.noreply.github.com>
---
 lab-3/main.c                      |  2 +-
 lab-3/samples/hello-world.cbl     |  3 +--
 lab-3/samples/sorting-snippet.cbl |  2 +-
 lab-3/scanner.flex                | 44 ++++++++++++++++++++++++++++---
 lab-3/token.h                     | 32 +++++++++++++++++++++-
 5 files changed, 74 insertions(+), 9 deletions(-)

diff --git a/lab-3/main.c b/lab-3/main.c
index 4a96a9e..66a6605 100644
--- a/lab-3/main.c
+++ b/lab-3/main.c
@@ -8,7 +8,7 @@ extern char *yytext;
 
 int main(int argc, char *argv[]) {
   FILE *file;
-  const char *filename = "samples/hello.py"; // Default filename
+  const char *filename = "samples/sorting-snippet.cbl"; // Default filename
 
   // Check if a filename is provided as a command-line argument
   if (argc > 1) {
diff --git a/lab-3/samples/hello-world.cbl b/lab-3/samples/hello-world.cbl
index 3c78e9b..737f19e 100644
--- a/lab-3/samples/hello-world.cbl
+++ b/lab-3/samples/hello-world.cbl
@@ -1,6 +1,5 @@
 IDENTIFICATION DIVISION.
 PROGRAM-ID. HELLO-WORLD.
 PROCEDURE DIVISION.
-    DISPLAY "Hello World!"
+    DISPLAY 'Hello World!'
 STOP RUN.
-if
\ No newline at end of file
diff --git a/lab-3/samples/sorting-snippet.cbl b/lab-3/samples/sorting-snippet.cbl
index a0eae92..8324e47 100644
--- a/lab-3/samples/sorting-snippet.cbl
+++ b/lab-3/samples/sorting-snippet.cbl
@@ -13,7 +13,7 @@ WORKING-STORAGE SECTION.
     05  WS-INDEX        PIC S9(4) COMP.
 
 PROCEDURE DIVISION.
-*> * Initialize test data
+*> Initialize test data
     MOVE "30" TO WS-SORT-ROW(1)
     MOVE "10" TO WS-SORT-ROW(2)
     MOVE "50" TO WS-SORT-ROW(3)
diff --git a/lab-3/scanner.flex b/lab-3/scanner.flex
index 021db23..0838033 100644
--- a/lab-3/scanner.flex
+++ b/lab-3/scanner.flex
@@ -3,10 +3,46 @@
 %}
 DIGIT [0-9]
 LETTER [a-zA-Z]
-%%
-(" "|\t|\n) /* skip whitespace */
-IDENTIFICATION { return TOKEN_IDENTIFICATION; }
-DIVISION { return TOKEN_KEYWORD_DIVISION; }
+NAME [a-zA-Z0-9][a-zA-Z0-9_-]*[a-zA-Z0-9]
 
+%%
+(" "|\t|\n) /* skip whitespace */
+\*>\ ?.* { return TOKEN_COMMENT; }
+IDENTIFICATION { return TOKEN_IDENTIFICATION; }
+DIVISION { return TOKEN_KEYWORD_DIVISION; }
+PROGRAM-ID { return TOKEN_PROGRAM_ID; }
+PROCEDURE { return TOKEN_PROCEDURE; }
+DATA { return TOKEN_KEYWORD_DATA; }
+SECTION { return TOKEN_KEYWORD_SECTION; }
+WORKING-STORAGE { return TOKEN_WORKING_STORAGE; }
+DISPLAY { return TOKEN_DISPLAY; }
+STOP { return TOKEN_STOP; }
+RUN { return TOKEN_RUN; }
+MOVE { return TOKEN_MOVE; }
+TO { return TOKEN_KEYWORD_TO; }
+VARYING { return TOKEN_VARYING; }
+FROM { return TOKEN_KEYWORD_FROM; }
+BY { return TOKEN_KEYWORD_BY; }
+UNTIL { return TOKEN_UNTIL; }
+PERFORM { return TOKEN_PERFORM; }
+END-PERFORM { return TOKEN_END_PERFORM; }
+IF { return TOKEN_IF; }
+END-IF { return TOKEN_END_IF; }
+SPACE { return TOKEN_SPACE; }
+
+\+ { return TOKEN_ADD; }
+\- { return TOKEN_SUB; }
+\> { return TOKEN_GREATER_THAN; }
+\< { return TOKEN_LESS_THAN; }
+
+"\""[^"]*"\""   { 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; }
diff --git a/lab-3/token.h b/lab-3/token.h
index 993c7a1..7ffcc96 100644
--- a/lab-3/token.h
+++ b/lab-3/token.h
@@ -1,12 +1,42 @@
 typedef enum {
   TOKEN_EOF = 0,
+  // Identification Keywords
   TOKEN_IDENTIFICATION,
   TOKEN_KEYWORD_DIVISION,
+  TOKEN_KEYWORD_DATA,
+  TOKEN_KEYWORD_SECTION,
   TOKEN_PROGRAM_ID,
+  TOKEN_WORKING_STORAGE,
   TOKEN_PROCEDURE,
+
+  // Program Keywords
   TOKEN_DISPLAY,
   TOKEN_STOP,
   TOKEN_RUN,
+  TOKEN_MOVE,
+  TOKEN_KEYWORD_TO,
+  TOKEN_PERFORM,
+  TOKEN_VARYING,
+  TOKEN_KEYWORD_FROM,
+  TOKEN_KEYWORD_BY,
+  TOKEN_UNTIL,
+  TOKEN_END_PERFORM,
+  TOKEN_IF,
+  TOKEN_END_IF,
+  TOKEN_SPACE,
+
+  // Identifiers
+  TOKEN_IDENT,
   TOKEN_STRING,
-  TOKEN_DOT
+  TOKEN_INTEGER,
+  TOKEN_LEFT_PARENTHESIS,
+  TOKEN_RIGHT_PARENTHESIS,
+  TOKEN_DOT,
+  TOKEN_COMMENT,
+
+  // Operators
+  TOKEN_ADD,
+  TOKEN_SUB,
+  TOKEN_GREATER_THAN,
+  TOKEN_LESS_THAN,
 } token_t;
\ No newline at end of file