OBFI

Add lexer

Diffstat

2 files changed, 80 insertions, 0 deletions

diff --git a/src/lex.c b/src/lex.c
new file mode 100644
index 0000000..18a2fbc
--- /dev/null
+++ b/src/lex.c
@@ -0,0 +1,49 @@
+// lex.c
+// Lexer source file for OBFI
+// Copyright (C) 2020, Jakob Wakeling
+// All rights reserved.
+
+#include "lex.h"
+
+#include <stddef.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#define TOKSET(type) tok.typ = type; tok.ln = line; tok.cl = col
+
+tok_t lex(char *str) {
+	static char *p; static size_t line, col; tok_t tok;
+	if (str) { p = str; line = 0; col = 0; } tok.num = 1;
+	
+	for (; *p; ++p) {
+		switch (*p) {
+		case '>': { TOKSET(RGT); goto count; }
+		case '<': { TOKSET(LFT); goto count; }
+		case '+': { TOKSET(ADD); goto count; }
+		case '-': { TOKSET(SUB); goto count; }
+		case '.': { TOKSET(PUT); ++p; ++col; return tok; }
+		case ',': { TOKSET(GET); ++p; ++col; return tok; }
+		case '[': { TOKSET(OPN); ++p; ++col; return tok; }
+		case ']': { TOKSET(CLS); ++p; ++col; return tok; }
+		case '\n': { ++line; col = 0; continue; }
+		count: {
+			for (register char c = *p++; *p == c; ++p) { ++tok.num; }
+			col += tok.num; return tok;
+		}
+		}
+	}
+	
+	tok.typ = END; return tok;
+}
+
+tok_t *parse(char *str, size_t len) {
+	tok_t *toks = malloc(sizeof (*toks) * len);
+	register tok_t *p = toks;
+	
+	tok_t tok = lex(str); if (tok.typ == EOF) { goto end; }
+	do { *p++ = tok; } while ((tok = lex(NULL)).typ != EOF);
+	
+end:
+	*p = tok; return toks;
+}
diff --git a/src/lex.h b/src/lex.h
new file mode 100644
index 0000000..178abd7
--- /dev/null
+++ b/src/lex.h
@@ -0,0 +1,31 @@
+// lex.h
+// Lexer header file for OBFI
+// Copyright (C) 2020, Jakob Wakeling
+// All rights reserved.
+
+#ifndef OMKOV_OBFI_LEX_H_AD07BU3C
+#define OMKOV_OBFI_LEX_H_AD07BU3C
+
+#include <stddef.h>
+#include <stdio.h>
+
+enum {
+	END = EOF, // EOF
+	ERR = 0,   // ERROR
+	RGT = 1,   // '>'
+	LFT = 2,   // '<'
+	ADD = 3,   // '+'
+	SUB = 4,   // '-'
+	PUT = 5,   // '.'
+	GET = 6,   // ','
+	OPN = 7,   // '['
+	CLS = 8,   // ']'
+	SET = 9,   // '[-]', '[+]'
+};
+
+typedef struct { int typ; size_t num, ln, cl; } tok_t;
+
+tok_t  lex(char *str);
+tok_t *parse(char *str, size_t len);
+
+#endif // OMKOV_OBFI_LEX_H_AD07BU3C