add copy of lark

Author: jsiek

lark/__init__.py

@@ -0,0 +1,10 @@
+from .utils import logger
+from .tree import Tree
+from .visitors import Transformer, Visitor, v_args, Discard, Transformer_NonRecursive
+from .visitors import InlineTransformer, inline_args   # XXX Deprecated
+from .exceptions import (ParseError, LexError, GrammarError, UnexpectedToken,
+                         UnexpectedInput, UnexpectedCharacters, UnexpectedEOF, LarkError)
+from .lexer import Token
+from .lark import Lark
+
+__version__ = "0.11.4"

lark/__pyinstaller/__init__.py

@@ -0,0 +1,6 @@
+# For usage of lark with PyInstaller. See https://pyinstaller-sample-hook.readthedocs.io/en/latest/index.html
+
+import os
+
+def get_hook_dirs():
+    return [os.path.dirname(__file__)]

lark/__pyinstaller/hook-lark.py

@@ -0,0 +1,14 @@
+#-----------------------------------------------------------------------------
+# Copyright (c) 2017-2020, PyInstaller Development Team.
+#
+# Distributed under the terms of the GNU General Public License (version 2
+# or later) with exception for distributing the bootloader.
+#
+# The full license is in the file COPYING.txt, distributed with this software.
+#
+# SPDX-License-Identifier: (GPL-2.0-or-later WITH Bootloader-exception)
+#-----------------------------------------------------------------------------
+
+from PyInstaller.utils.hooks import collect_data_files
+
+datas = collect_data_files('lark')

lark/ast_utils.py

@@ -0,0 +1,52 @@
+"""
+    Module of utilities for transforming a lark.Tree into a custom Abstract Syntax Tree
+"""
+
+import inspect, re
+
+from lark import Transformer, v_args
+
+class Ast(object):
+    """Abstract class
+
+    Subclasses will be collected by `create_transformer()`
+    """
+    pass
+
+class AsList(object):
+    """Abstract class
+
+    Subclasses will be instanciated with the parse results as a single list, instead of as arguments.
+    """
+
+def camel_to_snake(name):
+    return re.sub(r'(?<!^)(?=[A-Z])', '_', name).lower()
+
+def _call(func, _data, children, _meta):
+    return func(*children)
+
+inline = v_args(wrapper=_call)
+
+def create_transformer(ast_module, transformer=None):
+    """Collects `Ast` subclasses from the given module, and creates a Lark transformer that builds the AST.
+
+    For each class, we create a corresponding rule in the transformer, with a matching name.
+    CamelCase names will be converted into snake_case. Example: "CodeBlock" -> "code_block".
+
+    Classes starting with an underscore (`_`) will be skipped.
+
+    Parameters:
+        ast_module: A Python module containing all the subclasses of ``ast_utils.Ast``
+        transformer (Optional[Transformer]): An initial transformer. Its attributes may be overwritten.
+    """
+    t = transformer or Transformer()
+
+    for name, obj in inspect.getmembers(ast_module):
+        if not name.startswith('_') and inspect.isclass(obj):
+            if issubclass(obj, Ast):
+                if not issubclass(obj, AsList):
+                    obj = inline(obj).__get__(t)
+
+                setattr(t, camel_to_snake(name), obj)
+
+    return t

lark/common.py

@@ -0,0 +1,59 @@
+from warnings import warn
+from copy import deepcopy
+
+from .utils import Serialize
+from .lexer import TerminalDef
+
+###{standalone
+
+
+class LexerConf(Serialize):
+    __serialize_fields__ = 'terminals', 'ignore', 'g_regex_flags', 'use_bytes', 'lexer_type'
+    __serialize_namespace__ = TerminalDef,
+
+    def __init__(self, terminals, re_module, ignore=(), postlex=None, callbacks=None, g_regex_flags=0, skip_validation=False, use_bytes=False):
+        self.terminals = terminals
+        self.terminals_by_name = {t.name: t for t in self.terminals}
+        assert len(self.terminals) == len(self.terminals_by_name)
+        self.ignore = ignore
+        self.postlex = postlex
+        self.callbacks = callbacks or {}
+        self.g_regex_flags = g_regex_flags
+        self.re_module = re_module
+        self.skip_validation = skip_validation
+        self.use_bytes = use_bytes
+        self.lexer_type = None
+
+    @property
+    def tokens(self):
+        warn("LexerConf.tokens is deprecated. Use LexerConf.terminals instead", DeprecationWarning)
+        return self.terminals
+
+    def _deserialize(self):
+        self.terminals_by_name = {t.name: t for t in self.terminals}
+
+    def __deepcopy__(self, memo=None):
+        return type(self)(
+            deepcopy(self.terminals, memo),
+            self.re_module,
+            deepcopy(self.ignore, memo),
+            deepcopy(self.postlex, memo),
+            deepcopy(self.callbacks, memo),
+            deepcopy(self.g_regex_flags, memo),
+            deepcopy(self.skip_validation, memo),
+            deepcopy(self.use_bytes, memo),
+        )
+
+
+class ParserConf(Serialize):
+    __serialize_fields__ = 'rules', 'start', 'parser_type'
+
+    def __init__(self, rules, callbacks, start):
+        assert isinstance(start, list)
+        self.rules = rules
+        self.callbacks = callbacks
+        self.start = start
+
+        self.parser_type = None
+
+###}