2 files changed, 112 insertions, 1 deletions

diff --git a/include/lexer.h b/include/lexer.h
index 4b5f180..c8cd1a3 100644
--- a/include/lexer.h
+++ b/include/lexer.h
@@ -10,6 +10,20 @@ private:
   char *m_script;
   List *m_tokens;
 
+private:
+  size_t m_start;
+  size_t m_current;
+  size_t m_end;
+  size_t m_line;
+
+private:
+  bool at_end(void);
+  char advance(void);
+  char peek(void);
+  bool match(char c);
+  void add_token(token_type_e type);
+  void scan_token(void);
+
 public:
   void init(char *script);
   List *scan(void);
diff --git a/src/lexer.cc b/src/lexer.cc
index 5a6f7b9..2ccc349 100644
--- a/src/lexer.cc
+++ b/src/lexer.cc
@@ -13,16 +13,25 @@ Lexer::init(char *script)
 
   m_tokens = (List *) calloc(1, sizeof(List));
   m_tokens->init(sizeof(Token));
+
+  m_start = 0;
+  m_current = 0;
+  m_end = strlen(m_script);
+  m_line = 1;
 }
 
 List *
 Lexer::scan(void)
 {
-  printf("%s\n", m_script);
+  while (!at_end()) {
+    m_start = m_current;
+    scan_token();
+  }
 
   Token token_eof;
   token_eof.init(EOFF, "EOF", 2);
   m_tokens->add(&token_eof);
+  token_eof.clean();
 
   return m_tokens;
 }
@@ -38,3 +47,91 @@ Lexer::clean(void)
   m_tokens->clean();
   free(m_script);
 }
+
+bool
+Lexer::at_end(void)
+{
+  return m_current > m_end;
+}
+
+char
+Lexer::advance(void)
+{
+  return m_script[m_current++];
+}
+
+char
+Lexer::peek(void)
+{
+  return m_script[m_current];
+}
+
+bool
+Lexer::match(char c)
+{
+  if (at_end())
+    return false;
+  if (m_script[m_current] != c)
+    return false;
+
+  m_current++;
+  return true;
+}
+
+void
+Lexer::add_token(token_type_e type)
+{
+  size_t token_size = m_current - m_start;
+  if (token_size == 0)
+    token_size++;
+
+  char *text = (char *) malloc(sizeof(char) * token_size);
+  strncpy(text, m_script + m_start, token_size);
+
+  Token token;
+  token.init(type, text, m_line);
+  m_tokens->add(&token);
+  token.clean();
+}
+
+void
+Lexer::scan_token(void)
+{
+  char c = advance();
+  switch (c) {
+  case '(':
+    add_token(LEFT_PAREN);
+    break;
+  case ')':
+    add_token(RIGHT_PAREN);
+    break;
+  case '{':
+    add_token(LEFT_BRACE);
+    break;
+  case '}':
+    add_token(RIGHT_BRACE);
+    break;
+  case ',':
+    add_token(COMMA);
+    break;
+  case '.':
+    add_token(DOT);
+    break;
+  case '-':
+    add_token(MINUS);
+    break;
+  case '+':
+    add_token(PLUS);
+    break;
+  case ';':
+    add_token(SEMICOLON);
+    break;
+  case '*':
+    add_token(STAR);
+    break;
+
+  case '\n':
+    m_line++;
+    break;
+  }
+}