From 819ab10281c9bd6c000364c3a243959edd18abf7 Mon Sep 17 00:00:00 2001
From: Timotej Lazar <timotej.lazar@araneo.org>
Date: Thu, 15 Jan 2015 12:10:22 +0100
Subject: Move pymonkey stuff to monkey/

Importing pymonkey into webmonkey, let's see how this works.
---
 monkey/prolog/lexer.py | 90 ++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 90 insertions(+)
 create mode 100644 monkey/prolog/lexer.py

(limited to 'monkey/prolog/lexer.py')

diff --git a/monkey/prolog/lexer.py b/monkey/prolog/lexer.py
new file mode 100644
index 0000000..971e8a6
--- /dev/null
+++ b/monkey/prolog/lexer.py
@@ -0,0 +1,90 @@
+#!/usr/bin/python3
+
+import ply.lex as lex
+
+# LEXER
+
+#states = (
+#    ('comment', 'exclusive'),
+#)
+
+# tokens; treat operators as names if followed by (
+operators = {
+    r':-':  'FROM',
+    r'->':  'IMPLIES',
+    r'\+':  'NOT',
+    r'not': 'NOT',
+    r'=':   'EQU',
+    r'\=':  'NEQU',
+    r'==':  'EQ',
+    r'\==': 'NEQ',
+    r'=..': 'UNIV',
+    r'is':  'IS',
+    r'=:=': 'EQA',
+    r'=\=': 'NEQA',
+    r'<':   'LT',
+    r'=<':  'LE',
+    r'>':   'GT',
+    r'>=':  'GE',
+    r'@<':  'LTL',
+    r'@=<': 'LEL',
+    r'@>':  'GTL',
+    r'@>=': 'GEL',
+    r'+':   'PLUS',
+    r'-':   'MINUS',
+    r'*':   'STAR',
+    r'/':   'DIV',
+    r'//':  'IDIV',
+    r'mod': 'MOD',
+    r'**':  'POW',
+    r'.':   'PERIOD',
+    r',':   'COMMA',
+    r';':   'SEMI'
+}
+tokens = list(operators.values()) + [
+    'UINTEGER', 'UREAL',
+    'NAME', 'VARIABLE', 'STRING',
+    'LBRACKET', 'RBRACKET', 'LPAREN', 'RPAREN', 'PIPE', 'LBRACE', 'RBRACE',
+    'INVALID'
+]
+
+# punctuation
+t_LBRACKET = r'\['
+t_RBRACKET = r'\]'
+t_LPAREN = r'\('
+t_RPAREN = r'\)'
+t_PIPE = r'\|'
+t_LBRACE = r'{'
+t_RBRACE = r'}'
+
+t_UINTEGER = r'[0-9]+'
+t_UREAL    = r'[0-9]+\.[0-9]+([eE][-+]?[0-9]+)?|inf|nan'
+t_VARIABLE = r'(_|[A-Z])[a-zA-Z0-9_]*'
+t_STRING   = r'"(""|\\.|[^\"])*"'
+
+# no support for nested comments yet
+def t_comment(t):
+    r'(/\*(.|\n)*?\*/)|(%.*)'
+    pass
+
+def t_NAME(t):
+    r"'(''|\\.|[^\\'])*'|[a-z][a-zA-Z0-9_]*|[-+*/\\^<>=~:.?@#$&]+|!|;|,"
+    if t.lexer.lexpos >= len(t.lexer.lexdata) or t.lexer.lexdata[t.lexer.lexpos] != '(':
+        t.type = operators.get(t.value, 'NAME')
+    return t
+
+t_ignore  = ' \t'
+
+def t_newline(t):
+    r'\n+'
+    t.lexer.lineno += len(t.value)
+
+def t_error(t):
+    # TODO send this to stderr
+    #print("Illegal character '" + t.value[0] + "'")
+    t.type = 'INVALID'
+    t.value = t.value[0]
+    t.lexer.skip(1)
+    return t
+
+lexer = lex.lex()
-- 
cgit v1.2.1