From 007c81acad5fed97bca673bcd2a351e44bbf97e5 Mon Sep 17 00:00:00 2001
From: Chris Pressey <cpressey@catseye.tc>
Date: Thu, 16 Jun 2016 11:04:03 -0500
Subject: [PATCH] Split scanner off from parser module, into own module.

---
 src/sixtypical/parser.py  | 74 +--------------------------------------
 src/sixtypical/scanner.py | 74 +++++++++++++++++++++++++++++++++++++++
 2 files changed, 75 insertions(+), 73 deletions(-)
 create mode 100644 src/sixtypical/scanner.py

diff --git a/src/sixtypical/parser.py b/src/sixtypical/parser.py
index 403f9aa..b2e775a 100644
--- a/src/sixtypical/parser.py
+++ b/src/sixtypical/parser.py
@@ -1,84 +1,12 @@
 # encoding: UTF-8
 
-import re
-
 from sixtypical.ast import Program, Defn, Routine, Block, Instr
 from sixtypical.model import (
     TYPE_BIT, TYPE_BYTE, TYPE_BYTE_TABLE,
     RoutineType, VectorType, ExecutableType,
     LocationRef, ConstantRef
 )
-
-
-class Scanner(object):
-    def __init__(self, text):
-        self.text = text
-        self.token = None
-        self.type = None
-        self.scan()
-
-    def scan_pattern(self, pattern, type, token_group=1, rest_group=2):
-        pattern = r'^(' + pattern + r')(.*?)$'
-        match = re.match(pattern, self.text, re.DOTALL)
-        if not match:
-            return False
-        else:
-            self.type = type
-            self.token = match.group(token_group)
-            self.text = match.group(rest_group)
-            return True
-
-    def scan(self):
-        self.scan_pattern(r'[ \t\n\r]*', 'whitespace')
-        while self.scan_pattern(r'\/\/.*?[\n\r]', 'comment'):
-            self.scan_pattern(r'[ \t\n\r]*', 'whitespace')
-        if not self.text:
-            self.token = None
-            self.type = 'EOF'
-            return
-        if self.scan_pattern(r'\,|\@|\+|\:|\{|\}', 'operator'):
-            return
-        if self.scan_pattern(r'\d+', 'integer literal'):
-            return
-        if self.scan_pattern(r'\$([0-9a-fA-F]+)', 'integer literal',
-                             token_group=2, rest_group=3):
-            # ecch
-            self.token = str(eval('0x' + self.token))
-            return
-        if self.scan_pattern(r'\"(.*?)\"', 'string literal',
-                             token_group=2, rest_group=3):
-            return
-        if self.scan_pattern(r'\w+', 'identifier'):
-            return
-        if self.scan_pattern(r'.', 'unknown character'):
-            return
-        else:
-            raise AssertionError("this should never happen, self.text=(%s)" % self.text)
-
-    def expect(self, token):
-        if self.token == token:
-            self.scan()
-        else:
-            raise SyntaxError("Expected '%s', but found '%s'" %
-                              (token, self.token))
-
-    def on(self, token):
-        return self.token == token
-
-    def on_type(self, type):
-        return self.type == type
-
-    def check_type(self, type):
-        if not self.type == type:
-            raise SyntaxError("Expected %s, but found %s ('%s')" %
-                              (type, self.type, self.token))
-
-    def consume(self, token):
-        if self.token == token:
-            self.scan()
-            return True
-        else:
-            return False
+from sixtypical.scanner import Scanner
 
 
 class SymEntry(object):
diff --git a/src/sixtypical/scanner.py b/src/sixtypical/scanner.py
new file mode 100644
index 0000000..bd189c8
--- /dev/null
+++ b/src/sixtypical/scanner.py
@@ -0,0 +1,74 @@
+# encoding: UTF-8
+
+import re
+
+
+class Scanner(object):
+    def __init__(self, text):
+        self.text = text
+        self.token = None
+        self.type = None
+        self.scan()
+
+    def scan_pattern(self, pattern, type, token_group=1, rest_group=2):
+        pattern = r'^(' + pattern + r')(.*?)$'
+        match = re.match(pattern, self.text, re.DOTALL)
+        if not match:
+            return False
+        else:
+            self.type = type
+            self.token = match.group(token_group)
+            self.text = match.group(rest_group)
+            return True
+
+    def scan(self):
+        self.scan_pattern(r'[ \t\n\r]*', 'whitespace')
+        while self.scan_pattern(r'\/\/.*?[\n\r]', 'comment'):
+            self.scan_pattern(r'[ \t\n\r]*', 'whitespace')
+        if not self.text:
+            self.token = None
+            self.type = 'EOF'
+            return
+        if self.scan_pattern(r'\,|\@|\+|\:|\{|\}', 'operator'):
+            return
+        if self.scan_pattern(r'\d+', 'integer literal'):
+            return
+        if self.scan_pattern(r'\$([0-9a-fA-F]+)', 'integer literal',
+                             token_group=2, rest_group=3):
+            # ecch
+            self.token = str(eval('0x' + self.token))
+            return
+        if self.scan_pattern(r'\"(.*?)\"', 'string literal',
+                             token_group=2, rest_group=3):
+            return
+        if self.scan_pattern(r'\w+', 'identifier'):
+            return
+        if self.scan_pattern(r'.', 'unknown character'):
+            return
+        else:
+            raise AssertionError("this should never happen, self.text=(%s)" % self.text)
+
+    def expect(self, token):
+        if self.token == token:
+            self.scan()
+        else:
+            raise SyntaxError("Expected '%s', but found '%s'" %
+                              (token, self.token))
+
+    def on(self, token):
+        return self.token == token
+
+    def on_type(self, type):
+        return self.type == type
+
+    def check_type(self, type):
+        if not self.type == type:
+            raise SyntaxError("Expected %s, but found %s ('%s')" %
+                              (type, self.type, self.token))
+
+    def consume(self, token):
+        if self.token == token:
+            self.scan()
+            return True
+        else:
+            return False