new2Compiler.py 6.88 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61
#!/usr/bin/python

#######################################################################
#
# SYMBOLS SECTION - Can be edited. Changes will be preserved.
#
#######################################################################


from functools import partial
import os
import sys

sys.path.append(r'/home/eckhart/Entwicklung/DHParser')

try:
    import regex as re
except ImportError:
    import re
from DHParser import logging, is_filename, load_if_file, \
    Grammar, Compiler, nil_preprocessor, PreprocessorToken, Whitespace, \
    Lookbehind, Lookahead, Alternative, Pop, Token, Synonym, AllOf, SomeOf, Unordered, \
    Option, NegativeLookbehind, OneOrMore, RegExp, Retrieve, Series, RE, Capture, \
    ZeroOrMore, Forward, NegativeLookahead, mixin_comment, compile_source, \
    last_value, counterpart, accumulate, PreprocessorFunc, \
    Node, TransformationFunc, TransformationDict, \
    traverse, remove_children_if, merge_children, is_anonymous, \
    reduce_single_child, replace_by_single_child, replace_or_reduce, remove_whitespace, \
    remove_expendables, remove_empty, remove_tokens, flatten, is_whitespace, \
    is_empty, is_expendable, collapse, replace_content, WHITESPACE_PTYPE, TOKEN_PTYPE, \
    remove_nodes, remove_content, remove_brackets, replace_parser, \
    keep_children, is_one_of, has_content, apply_if, remove_first, remove_last, \
    remove_anonymous_empty, keep_nodes, traverse_locally, strip, lstrip, rstrip, \
    grammar_changed


#######################################################################
#
# PREPROCESSOR SECTION - Can be edited. Changes will be preserved.
#
#######################################################################

def new2Preprocessor(text):
    return text, lambda i: i

def get_preprocessor() -> PreprocessorFunc:
    return new2Preprocessor


#######################################################################
#
# PARSER SECTION - Don't edit! CHANGES WILL BE OVERWRITTEN!
#
#######################################################################

class new2Grammar(Grammar):
    r"""Parser for a new2 source file, with this grammar:
    
    document = ~ { sentence } §EOF
    sentence = part {"," part } "."
    part     = { WORD }+
62
    WORD     =  /[\w’]+/~
63 64
    EOF      =  !/./
    """
65
    source_hash__ = "7a9984368b1c959222099d389d18c54f"
66 67 68 69 70 71 72 73
    parser_initialization__ = "upon instantiation"
    COMMENT__ = r''
    WHITESPACE__ = r'\s*'
    WSP__ = mixin_comment(whitespace=WHITESPACE__, comment=COMMENT__)
    wspL__ = ''
    wspR__ = WSP__
    whitespace__ = Whitespace(WSP__)
    EOF = NegativeLookahead(RegExp('.'))
74
    WORD = RE('[\\w’]+')
75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200
    part = OneOrMore(WORD)
    sentence = Series(part, ZeroOrMore(Series(Token(","), part)), Token("."))
    document = Series(whitespace__, ZeroOrMore(sentence), EOF, mandatory=2)
    root__ = document
    
def get_grammar() -> new2Grammar:
    global thread_local_new2_grammar_singleton
    try:
        grammar = thread_local_new2_grammar_singleton
    except NameError:
        thread_local_new2_grammar_singleton = new2Grammar()
        grammar = thread_local_new2_grammar_singleton
    return grammar


#######################################################################
#
# AST SECTION - Can be edited. Changes will be preserved.
#
#######################################################################

new2_AST_transformation_table = {
    # AST Transformations for the new2-grammar
    "+": remove_empty,
    "document": [],
    "WORD": [],
    "EOF": [],
    ":Token, :RE": reduce_single_child,
    "*": replace_by_single_child
}


def new2Transform() -> TransformationDict:
    return partial(traverse, processing_table=new2_AST_transformation_table.copy())

def get_transformer() -> TransformationFunc:
    global thread_local_new2_transformer_singleton
    try:
        transformer = thread_local_new2_transformer_singleton
    except NameError:
        thread_local_new2_transformer_singleton = new2Transform()
        transformer = thread_local_new2_transformer_singleton
    return transformer


#######################################################################
#
# COMPILER SECTION - Can be edited. Changes will be preserved.
#
#######################################################################

class new2Compiler(Compiler):
    """Compiler for the abstract-syntax-tree of a new2 source file.
    """

    def __init__(self, grammar_name="new2", grammar_source=""):
        super(new2Compiler, self).__init__(grammar_name, grammar_source)
        assert re.match('\w+\Z', grammar_name)

    def on_document(self, node):
        return self.fallback_compiler(node)

    # def on_WORD(self, node):
    #     return node

    # def on_EOF(self, node):
    #     return node


def get_compiler(grammar_name="new2", grammar_source="") -> new2Compiler:
    global thread_local_new2_compiler_singleton
    try:
        compiler = thread_local_new2_compiler_singleton
        compiler.set_grammar_name(grammar_name, grammar_source)
    except NameError:
        thread_local_new2_compiler_singleton = \
            new2Compiler(grammar_name, grammar_source)
        compiler = thread_local_new2_compiler_singleton
    return compiler


#######################################################################
#
# END OF DHPARSER-SECTIONS
#
#######################################################################


def compile_src(source, log_dir=''):
    """Compiles ``source`` and returns (result, errors, ast).
    """
    with logging(log_dir):
        compiler = get_compiler()
        cname = compiler.__class__.__name__
        log_file_name = os.path.basename(os.path.splitext(source)[0]) \
            if is_filename(source) < 0 else cname[:cname.find('.')] + '_out'
        result = compile_source(source, get_preprocessor(),
                                get_grammar(),
                                get_transformer(), compiler)
    return result


if __name__ == "__main__":
    if len(sys.argv) > 1:
        try:
            grammar_file_name = os.path.basename(__file__).replace('Compiler.py', '.ebnf')
            if grammar_changed(new2Grammar, grammar_file_name):
                print("Grammar has changed. Please recompile Grammar first.")
                sys.exit(1)
        except FileNotFoundError:
            print('Could not check for changed grammar, because grammar file "%s" was not found!'
                  % grammar_file_name)
        file_name, log_dir = sys.argv[1], ''
        if file_name in ['-d', '--debug'] and len(sys.argv) > 2:
            file_name, log_dir = sys.argv[2], 'LOGS'
        result, errors, ast = compile_src(file_name, log_dir)
        if errors:
            cwd = os.getcwd()
            rel_path = file_name[len(cwd):] if file_name.startswith(cwd) else file_name
            for error in errors:
                print(rel_path + ':' + str(error))
            sys.exit(1)
        else:
            print(result.as_xml() if isinstance(result, Node) else result)
    else:
        print("Usage: new2Compiler.py [FILENAME]")