Experimental parser: simplified rule lexer and parser

tools/lexer_generator/generator.py

 # Copyright 2013 the V8 project authors. All rights reserved.
 # Redistribution and use in source and binary forms, with or without
 # modification, are permitted provided that the following conditions are
 # met:
 #
 #     * Redistributions of source code must retain the above copyright
 #       notice, this list of conditions and the following disclaimer.
 #     * Redistributions in binary form must reproduce the above
 #       copyright notice, this list of conditions and the following
 #       disclaimer in the documentation and/or other materials provided
 #       with the distribution.
 #     * Neither the name of Google Inc. nor the names of its
 #       contributors may be used to endorse or promote products derived
 #       from this software without specific prior written permission.
 #
 # THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 # "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
 # LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
 # A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
 # OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 # SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 # LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
 # DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
 # THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 # (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
 # OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 
+from nfa import Nfa
+from dfa import Dfa
+from rule_lexer import RuleLexer
+from rule_parser import RuleParser
+from regex_parser import RegexParser
 
-import xml.etree.ElementTree as xml
+def lex_file(file_name):
+  lexer = RuleLexer()
+  lexer.build()
+  with open(file_name, 'r') as f:
+    lexer.lexer.input(f.read())
+    while True:
+        tok = lexer.lexer.token()
+        if not tok: break      # No more input
+        print tok
 
+def parse_file(file_name):
+  rule_parser = RuleParser()
+  rule_parser.build()
+  with open(file_name, 'r') as f:
+    rule_parser.parse(f.read())
+  print "aliases"
+  for k, v in rule_parser.aliases.items():
+    print "\t%s : %s" % (k, v)
+  print "rules"
+  for k, v in rule_parser.rules.items():
+    print "\t%s" % k
+    for t in v:
+      print "\t\t%s" % str(t)
 
-class JUnitTestOutput:
-  def __init__(self, test_suite_name):
-    self.root = xml.Element("testsuite")
-    self.root.attrib["name"] = test_suite_name
-
-  def HasRunTest(self, test_name, test_duration, test_failure):
-    testCaseElement = xml.Element("testcase")
-    testCaseElement.attrib["name"] = " ".join(test_name)
-    testCaseElement.attrib["time"] = str(round(test_duration, 3))
-    if len(test_failure):
-      failureElement = xml.Element("failure")
-      failureElement.text = test_failure
-      testCaseElement.append(failureElement)
-    self.root.append(testCaseElement)
-
-  def FinishAndWrite(self, file):
-    xml.ElementTree(self.root).write(file, "UTF-8")
-
+if __name__ == '__main__':
+  # lex_file('src/lexer/lexer_py.re')
+  parse_file('src/lexer/lexer_py.re')