From 713b5078cddd0b7605b478931fe24ae984326592 Mon Sep 17 00:00:00 2001
From: Markus Hauschild <hauschildm@gmx.net>
Date: Fri, 31 May 2013 22:20:31 +0200
Subject: [PATCH] ZOMFG IT TOKENIZES!!11eleven

---
 CMakeLists.txt    | 13 +++++----
 grammar/grammar.y |  3 ++
 src/test.cpp      | 72 +++++++++++++++++++++++++++++++++++++++++++++--
 3 files changed, 80 insertions(+), 8 deletions(-)

diff --git a/CMakeLists.txt b/CMakeLists.txt
index b9ddf96..7f6e77e 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -15,8 +15,10 @@ INCLUDE_DIRECTORIES (${CMAKE_CURRENT_BINARY_DIR})
 
 INCLUDE_DIRECTORIES (${CMAKE_SOURCE_DIR}/inc)
 
+ADD_DEFINITIONS("-std=c++0x")
+
 ADD_EXECUTABLE (lemon grammar/lemon.c)
-ADD_EXECUTABLE (makeheaders grammar/makeheaders.c)
+#ADD_EXECUTABLE (makeheaders grammar/makeheaders.c)
 
 ADD_CUSTOM_COMMAND(
     COMMAND cp
@@ -24,17 +26,18 @@ ADD_CUSTOM_COMMAND(
     COMMAND cp
     ARGS ${CMAKE_CURRENT_SOURCE_DIR}/grammar/lempar.c ${CMAKE_CURRENT_BINARY_DIR}
     COMMAND ${CMAKE_CURRENT_BINARY_DIR}/lemon
-    ARGS -q -m ${CMAKE_CURRENT_BINARY_DIR}/grammar.y
+#    ARGS -q -m ${CMAKE_CURRENT_BINARY_DIR}/grammar.y
+    ARGS -q ${CMAKE_CURRENT_BINARY_DIR}/grammar.y
     COMMAND rm
     ARGS ${CMAKE_CURRENT_BINARY_DIR}/lempar.c
     COMMAND rm
     ARGS ${CMAKE_CURRENT_BINARY_DIR}/grammar.y
-    COMMAND ${CMAKE_CURRENT_BINARY_DIR}/makeheaders
-    ARGS ${CMAKE_CURRENT_BINARY_DIR}/grammar.c
+#    COMMAND ${CMAKE_CURRENT_BINARY_DIR}/makeheaders
+#    ARGS ${CMAKE_CURRENT_BINARY_DIR}/grammar.c
     COMMAND mv
     ARGS ${CMAKE_CURRENT_BINARY_DIR}/grammar.c ${CMAKE_CURRENT_BINARY_DIR}/grammar.cpp
     DEPENDS lemon
-    DEPENDS makeheaders
+#    DEPENDS makeheaders
     DEPENDS ${CMAKE_CURRENT_SOURCE_DIR}/grammar/grammar.y
     OUTPUT ${CMAKE_CURRENT_BINARY_DIR}/grammar.cpp
     OUTPUT ${CMAKE_CURRENT_BINARY_DIR}/grammar.h
diff --git a/grammar/grammar.y b/grammar/grammar.y
index 6264236..2453f46 100644
--- a/grammar/grammar.y
+++ b/grammar/grammar.y
@@ -9,6 +9,9 @@
 
 %token_type {int}
 
+// whitespace and comments
+%type T_WHITESPACE {int}
+
 %right T_ASSIGN.
 %left T_EQUALS.
 %left T_LESS.
diff --git a/src/test.cpp b/src/test.cpp
index c4c52f7..0dac0d0 100644
--- a/src/test.cpp
+++ b/src/test.cpp
@@ -5,8 +5,7 @@
  */
 
 // this file is auto generated from grammar/grammar.y
-// but it does not work yet
-// #include "grammar.h"
+#include "grammar.h"
 
 #include "lexertl/generator.hpp"
 #include "lexertl/lookup.hpp"
@@ -14,5 +13,72 @@
 #include "lexertl/state_machine.hpp"
 
 int main() {
-    return 0;
+	lexertl::rules rules;
+	lexertl::state_machine state_machine;
+
+	//keywords
+	rules.add("bool", T_BOOL);
+	rules.add("for", T_FOR);
+	rules.add("if", T_IF);
+	rules.add("int", T_INT);
+	rules.add("return", T_RETURN);
+	rules.add("void", T_VOID);
+	rules.add("rfor", T_RFOR);
+	rules.add("rif", T_RIF);
+
+	// special characters
+	rules.add("\"(\"", T_LPAREN);
+	rules.add("\")\"", T_RPAREN);
+	rules.add("mulder", T_BEGIN);
+	rules.add("scully", T_END);
+	rules.add(",", T_COMMA);
+	rules.add(";", T_SEMICOLON);
+
+	// operators
+	rules.add("=", T_ASSIGN);
+	rules.add("==", T_EQUALS);
+	rules.add("<", T_LESS);
+	rules.add("\"+\"", T_PLUS);
+	rules.add("\"-\"", T_MINUS);
+	rules.add("\"*\"", T_TIMES);
+	rules.add("\"/\"", T_DIV);
+
+	// constants
+	rules.add("true", T_TRUE);
+	rules.add("false", T_FALSE);
+	rules.add("\\d+", T_CINT);
+
+	// identifier
+	rules.add("[a-zA-Z_][a-zA-Z_0-9]*", T_IDENTIFIER);
+
+	// whitespace
+	rules.add("\\s+", T_WHITESPACE);
+
+	lexertl::generator::build(rules, state_machine);
+	state_machine.minimise();
+
+	std::cout << "The scully programming languae v0.1" << std::endl;
+
+	while (true) {
+		std::cout << "> ";
+		std::string input;
+		std::getline(std::cin, input);
+		if (std::cin.eof()) {
+			std::cout << std::endl << "Bye." << std::endl;
+			return 0;
+		}
+
+		auto iter = input.begin();
+		auto end = input.end();
+		lexertl::smatch results(iter, end);
+
+		do {
+			lexertl::lookup (state_machine, results);
+			std::string s(results.start, results.end);
+			if (results.id != T_WHITESPACE) {
+				std::cout << "Id: " << results.id << ", Token: " << s << std::endl;
+			}
+		} while (results.id != 0);
+	}
+	return 0;
 }