From a0c19d3b358dc5c681af73115b37eb371a9a1463 Mon Sep 17 00:00:00 2001
From: Luthaf <luthaf@luthaf.fr>
Date: Mon, 6 Oct 2014 22:30:46 +0200
Subject: [PATCH] First minimalist chordpro lexer

---
 patacrep/chordpro/__init__.py |  0
 patacrep/chordpro/lexer.py    | 59 +++++++++++++++++++++++++++++++++++
 2 files changed, 59 insertions(+)
 create mode 100644 patacrep/chordpro/__init__.py
 create mode 100644 patacrep/chordpro/lexer.py

diff --git a/patacrep/chordpro/__init__.py b/patacrep/chordpro/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/patacrep/chordpro/lexer.py b/patacrep/chordpro/lexer.py
new file mode 100644
index 00000000..860e16d5
--- /dev/null
+++ b/patacrep/chordpro/lexer.py
@@ -0,0 +1,59 @@
+"""ChordPro lexer"""
+
+import logging
+import ply.lex as lex
+
+LOGGER = logging.getLogger()
+
+#pylint: disable=invalid-name
+tokens = (
+   'LBRACKET',
+   'RBRACKET',
+   'LBRACE',
+   'RBRACE',
+   'NEWLINE',
+   'COLON',
+   'WORD',
+   'SPACE',
+   'NUMBER'
+)
+
+class ChordProLexer:
+    """ChordPro Lexer class"""
+
+    tokens = tokens
+
+    t_LBRACKET = r'\['
+    t_RBRACKET = r'\]'
+    t_LBRACE = r'{'
+    t_RBRACE = r'}'
+    t_SPACE = r'[ \t]+'
+    t_COLON = r':'
+    t_WORD = r'[a-zA-Z_]+'  #TODO: handle unicode
+
+    def __init__(self):
+        self.__class__.lexer = lex.lex(module=self)
+
+    # Define a rule so we can track line numbers
+    @staticmethod
+    def t_NEWLINE(token):
+        r'[\n\r]'
+        token.lexer.lineno += 1
+        return token
+
+    @staticmethod
+    def t_comment(token):
+        r'\#.*'
+        pass
+    
+    @staticmethod
+    def t_NUMBER(token):
+        r'[0-9]+'
+        token.value = int(token.value)
+        return token
+
+    @staticmethod
+    def t_error(token):
+        """Manage errors"""
+        LOGGER.error("Illegal character '{}'".format(token.value[0]))
+        token.lexer.skip(1)
\ No newline at end of file