Interface improvements for the Lark instance

examples/python_parser.py

@@ -10,7 +10,7 @@ import glob, time
 from lark import Lark
 from lark.indenter import Indenter
 
-__path__ = os.path.dirname(__file__)
+# __path__ = os.path.dirname(__file__)
 
 class PythonIndenter(Indenter):
     NL_type = '_NEWLINE'
@@ -20,18 +20,14 @@ class PythonIndenter(Indenter):
     DEDENT_type = '_DEDENT'
     tab_len = 8
 
+kwargs = dict(rel_to=__file__, postlex=PythonIndenter(), start='file_input')
 
-grammar2_filename = os.path.join(__path__, 'python2.g')
-grammar3_filename = os.path.join(__path__, 'python3.g')
-with open(grammar2_filename) as f:
-    python_parser2 = Lark(f, parser='lalr', postlex=PythonIndenter(), start='file_input')
-with open(grammar3_filename) as f:
-    python_parser3 = Lark(f, parser='lalr', postlex=PythonIndenter(), start='file_input')
+python_parser2 = Lark.open('python2.g', parser='lalr', **kwargs)
+python_parser3 = Lark.open('python3.g',parser='lalr', **kwargs)
+python_parser2_earley = Lark.open('python2.g', parser='earley', lexer='standard', **kwargs)
+print(python_parser3)
 
 
-with open(grammar2_filename) as f:
-    python_parser2_earley = Lark(f, parser='lalr', lexer='standard', postlex=PythonIndenter(), start='file_input')
-
 def _read(fn, *args):
     kwargs = {'encoding': 'iso-8859-1'}
     with open(fn, *args, **kwargs) as f:
@@ -82,6 +78,6 @@ def test_earley_equals_lalr():
 
 if __name__ == '__main__':
     test_python_lib()
-    # test_earley_equals_lalr()
+    test_earley_equals_lalr()
     # python_parser3.parse(_read(sys.argv[1]) + '\n')
 

lark/lark.py

@@ -3,6 +3,7 @@ from __future__ import absolute_import
 import os
 import time
 from collections import defaultdict
+from io import open
 
 from .utils import STRING_TYPE
 from .load_grammar import load_grammar
@@ -105,12 +106,12 @@ class Lark:
 
         # Some, but not all file-like objects have a 'name' attribute
         try:
-            source = grammar.name
+            self.source = grammar.name
         except AttributeError:
-            source = '<string>'
+            self.source = '<string>'
             cache_file = "larkcache_%s" % str(hash(grammar)%(2**32))
         else:
-            cache_file = "larkcache_%s" % os.path.basename(source)
+            cache_file = "larkcache_%s" % os.path.basename(self.source)
 
         # Drain file-like objects to get their contents
         try:
@@ -150,7 +151,7 @@ class Lark:
         assert self.options.ambiguity in ('resolve', 'explicit', 'auto', 'resolve__antiscore_sum')
 
         # Parse the grammar file and compose the grammars (TODO)
-        self.grammar = load_grammar(grammar, source)
+        self.grammar = load_grammar(grammar, self.source)
 
         # Compile the EBNF grammar into BNF
         tokens, self.rules, self.ignore_tokens = self.grammar.compile(lexer=bool(lexer), start=self.options.start)
@@ -183,6 +184,27 @@ class Lark:
 
         return self.parser_class(self.lexer_conf, parser_conf, options=self.options)
 
+    @classmethod
+    def open(cls, grammar_filename, rel_to=None, **options):
+        """Create an instance of Lark with the grammar given by its filename
+
+        If rel_to is provided, the function will find the grammar filename in relation to it.
+
+        Example:
+
+            >>> Lark.open("grammar_file.g", rel_to=__file__, parser="lalr")
+            Lark(...)
+
+        """
+        if rel_to:
+            basepath = os.path.dirname(rel_to)
+            grammar_filename = os.path.join(basepath, grammar_filename)
+        with open(grammar_filename) as f:
+            return cls(f, **options)
+
+    def __repr__(self):
+        return 'Lark(open(%r), parser=%r, lexer=%r, ...)' % (self.source, self.options.parser, self.options.lexer)
+
 
     def lex(self, text):
         if not hasattr(self, 'lexer'):