EBNFCompiler.py 10.7 KB
Newer Older
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
#!/usr/bin/python

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


from functools import partial
import os
import sys
try:
    import regex as re
except ImportError:
    import re
17
from DHParser import is_filename, load_if_file, \
18
19
20
21
22
23
24
    Grammar, Compiler, nil_preprocessor, \
    Lookbehind, Lookahead, Alternative, Pop, Required, Token, Synonym, \
    Option, NegativeLookbehind, OneOrMore, RegExp, Retrieve, Series, RE, Capture, \
    ZeroOrMore, Forward, NegativeLookahead, mixin_comment, compile_source, \
    last_value, counterpart, accumulate, PreprocessorFunc, \
    Node, TransformationFunc, TransformationDict, TRUE_CONDITION, \
    traverse, remove_children_if, merge_children, is_anonymous, \
Eckhart Arnold's avatar
Eckhart Arnold committed
25
    reduce_single_child, replace_by_single_child, replace_or_reduce, remove_whitespace, \
26
27
    remove_expendables, remove_empty, remove_tokens, flatten, is_whitespace, \
    is_empty, is_expendable, collapse, replace_content, WHITESPACE_PTYPE, TOKEN_PTYPE, \
eckhart's avatar
eckhart committed
28
    remove_nodes, remove_content, remove_brackets, replace_parser, \
29
    keep_children, is_one_of, has_content, apply_if, remove_first, remove_last
30
from DHParser.log import logging
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


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

def EBNFPreprocessor(text):
    return text

def get_preprocessor() -> PreprocessorFunc:
    return EBNFPreprocessor


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

class EBNFGrammar(Grammar):
    r"""Parser for an EBNF source file, with this grammar:
    
    # EBNF-Grammar in EBNF
    
57
58
59
    @ comment    = /#.*(?:\n|$)/                    # comments start with '#' and eat all chars up to and including '\n'
    @ whitespace = /\s*/                            # whitespace includes linefeed
    @ literalws  = right                            # trailing whitespace of literals will be ignored tacitly
60
    
61
62
63
    syntax     = [~//] { definition | directive } §EOF
    definition = symbol §"=" expression
    directive  = "@" §symbol "=" ( regexp | literal | list_ )
64
    
65
66
67
68
69
70
71
72
73
74
75
76
    expression = term { "|" term }
    term       = { ["§"] factor }+                       # "§" means all following factors mandatory
    factor     = [flowmarker] [retrieveop] symbol !"="   # negative lookahead to be sure it's not a definition
               | [flowmarker] literal
               | [flowmarker] plaintext
               | [flowmarker] regexp
               | [flowmarker] whitespace
               | [flowmarker] oneormore
               | [flowmarker] group
               | [flowmarker] unordered
               | repetition
               | option
77
    
78
79
80
    flowmarker = "!"  | "&"                         # '!' negative lookahead, '&' positive lookahead
               | "-!" | "-&"                        # '-' negative lookbehind, '-&' positive lookbehind
    retrieveop = "::" | ":"                         # '::' pop, ':' retrieve
81
    
82
83
84
85
86
    group      = "(" §expression ")"
    unordered  = "<" §expression ">"                # elements of expression in arbitrary order
    oneormore  = "{" expression "}+"
    repetition = "{" §expression "}"
    option     = "[" §expression "]"
87
    
88
89
90
91
92
93
94
95
96
97
98
    symbol     = /(?!\d)\w+/~                       # e.g. expression, factor, parameter_list
    literal    = /"(?:[^"]|\\")*?"/~                # e.g. "(", '+', 'while'
               | /'(?:[^']|\\')*?'/~                # whitespace following literals will be ignored tacitly.
    plaintext  = /`(?:[^"]|\\")*?`/~                # like literal but does not eat whitespace
    regexp     = /~?\/(?:\\\/|[^\/])*?\/~?/~        # e.g. /\w+/, ~/#.*(?:\n|$)/~
                                                    # '~' is a whitespace-marker, if present leading or trailing
                                                    # whitespace of a regular expression will be ignored tacitly.
    whitespace = /~/~                               # implicit or default whitespace
    list_      = /\w+/~ { "," /\w+/~ }              # comma separated list of symbols, e.g. BEGIN_LIST, END_LIST,
                                                    # BEGIN_QUOTE, END_QUOTE ; see CommonMark/markdown.py for an exmaple
    EOF = !/./
99
100
    """
    expression = Forward()
101
    source_hash__ = "d807c57c29ef6c674abe1addfce146c4"
102
103
104
105
106
107
108
109
    parser_initialization__ = "upon instantiation"
    COMMENT__ = r'#.*(?:\n|$)'
    WHITESPACE__ = r'\s*'
    WSP__ = mixin_comment(whitespace=WHITESPACE__, comment=COMMENT__)
    wspL__ = ''
    wspR__ = WSP__
    EOF = NegativeLookahead(RegExp('.'))
    list_ = Series(RE('\\w+'), ZeroOrMore(Series(Token(","), RE('\\w+'))))
110
    whitespace = RE('~')
111
    regexp = RE('~?/(?:\\\\/|[^/])*?/~?')
112
    plaintext = RE('`(?:[^"]|\\\\")*?`')
113
114
115
116
117
    literal = Alternative(RE('"(?:[^"]|\\\\")*?"'), RE("'(?:[^']|\\\\')*?'"))
    symbol = RE('(?!\\d)\\w+')
    option = Series(Token("["), expression, Token("]"), mandatory=1)
    repetition = Series(Token("{"), expression, Token("}"), mandatory=1)
    oneormore = Series(Token("{"), expression, Token("}+"))
118
    unordered = Series(Token("<"), expression, Token(">"), mandatory=1)
119
120
121
    group = Series(Token("("), expression, Token(")"), mandatory=1)
    retrieveop = Alternative(Token("::"), Token(":"))
    flowmarker = Alternative(Token("!"), Token("&"), Token("-!"), Token("-&"))
122
    factor = Alternative(Series(Option(flowmarker), Option(retrieveop), symbol, NegativeLookahead(Token("="))), Series(Option(flowmarker), literal), Series(Option(flowmarker), plaintext), Series(Option(flowmarker), regexp), Series(Option(flowmarker), whitespace), Series(Option(flowmarker), oneormore), Series(Option(flowmarker), group), Series(Option(flowmarker), unordered), repetition, option)
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
    term = OneOrMore(Series(Option(Token("§")), factor))
    expression.set(Series(term, ZeroOrMore(Series(Token("|"), term))))
    directive = Series(Token("@"), symbol, Token("="), Alternative(regexp, literal, list_), mandatory=1)
    definition = Series(symbol, Token("="), expression, mandatory=1)
    syntax = Series(Option(RE('', wR='', wL=WSP__)), ZeroOrMore(Alternative(definition, directive)), EOF, mandatory=2)
    root__ = syntax
    
def get_grammar() -> EBNFGrammar:
    global thread_local_EBNF_grammar_singleton
    try:
        grammar = thread_local_EBNF_grammar_singleton
    except NameError:
        thread_local_EBNF_grammar_singleton = EBNFGrammar()
        grammar = thread_local_EBNF_grammar_singleton
    return grammar


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

EBNF_AST_transformation_table = {
    # AST Transformations for the EBNF-grammar
    "+": remove_empty,
    "syntax": [],
    "definition": [],
    "directive": [],
    "expression": [],
    "term": [],
    "factor": [replace_or_reduce],
    "flowmarker": [replace_or_reduce],
    "retrieveop": [replace_or_reduce],
    "group": [],
    "oneormore": [],
    "repetition": [],
    "option": [],
    "symbol": [],
    "literal": [replace_or_reduce],
    "regexp": [],
    "list_": [],
    "EOF": [],
Eckhart Arnold's avatar
Eckhart Arnold committed
166
    ":Token, :RE": reduce_single_child,
167
    "*": replace_by_single_child
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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
}


def EBNFTransform() -> TransformationDict:
    return partial(traverse, processing_table=EBNF_AST_transformation_table.copy())

def get_transformer() -> TransformationFunc:
    global thread_local_EBNF_transformer_singleton
    try:
        transformer = thread_local_EBNF_transformer_singleton
    except NameError:
        thread_local_EBNF_transformer_singleton = EBNFTransform()
        transformer = thread_local_EBNF_transformer_singleton
    return transformer


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

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

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

    def on_syntax(self, node):
        return node

    def on_definition(self, node):
        pass

    def on_directive(self, node):
        pass

    def on_expression(self, node):
        pass

    def on_term(self, node):
        pass

    def on_factor(self, node):
        pass

    def on_flowmarker(self, node):
        pass

    def on_retrieveop(self, node):
        pass

    def on_group(self, node):
        pass

    def on_oneormore(self, node):
        pass

    def on_repetition(self, node):
        pass

    def on_option(self, node):
        pass

    def on_symbol(self, node):
        pass

    def on_literal(self, node):
        pass

    def on_regexp(self, node):
        pass

    def on_list_(self, node):
        pass

    def on_EOF(self, node):
        pass


def get_compiler(grammar_name="EBNF", grammar_source="") -> EBNFCompiler:
    global thread_local_EBNF_compiler_singleton
    try:
        compiler = thread_local_EBNF_compiler_singleton
        compiler.set_grammar_name(grammar_name, grammar_source)
    except NameError:
        thread_local_EBNF_compiler_singleton = \
            EBNFCompiler(grammar_name, grammar_source)
        compiler = thread_local_EBNF_compiler_singleton
    return compiler


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


def compile_src(source):
    """Compiles ``source`` and returns (result, errors, ast).
    """
    with logging("LOGS"):
        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:
        result, errors, ast = compile_src(sys.argv[1])
        if errors:
            for error in errors:
                print(error)
            sys.exit(1)
        else:
            print(result.as_xml() if isinstance(result, Node) else result)
    else:
        print("Usage: EBNFCompiler.py [FILENAME]")