EBNFCompiler.py 11.2 KB
Newer Older
1
2
3
4
5
6
7
8
9
10
11
12
#!/usr/bin/python

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


from functools import partial
import os
import sys
13

eckhart's avatar
eckhart committed
14
sys.path.extend(['../', '../../', './'])
15

16
17
18
19
try:
    import regex as re
except ImportError:
    import re
20
from DHParser import is_filename, load_if_file, \
21
    Grammar, Compiler, nil_preprocessor, \
di68kap's avatar
di68kap committed
22
23
    Lookbehind, Lookahead, Alternative, Pop, Required, Token, Synonym, \
    Option, NegativeLookbehind, OneOrMore, RegExp, Retrieve, Series, Capture, \
24
25
    ZeroOrMore, Forward, NegativeLookahead, mixin_comment, compile_source, \
    last_value, counterpart, accumulate, PreprocessorFunc, \
26
    Node, TransformationFunc, TransformationDict, Whitespace, \
eckhart's avatar
eckhart committed
27
    traverse, remove_children_if, is_anonymous, \
Eckhart Arnold's avatar
Eckhart Arnold committed
28
    reduce_single_child, replace_by_single_child, replace_or_reduce, remove_whitespace, \
29
30
    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
31
    remove_nodes, remove_content, remove_brackets, replace_parser, \
di68kap's avatar
di68kap committed
32
    keep_children, is_one_of, has_content, apply_if, remove_first, remove_last, \
eckhart's avatar
eckhart committed
33
    forbid, assert_content, remove_infix_operator, GLOBALS
34
from DHParser.log import logging
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


#######################################################################
#
# 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
    
61
62
63
    @ 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
64
    
65
66
67
    syntax     = [~//] { definition | directive } §EOF
    definition = symbol §"=" expression
    directive  = "@" §symbol "=" ( regexp | literal | list_ )
68
    
69
70
71
72
73
74
75
76
77
78
79
80
    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
81
    
82
83
84
    flowmarker = "!"  | "&"                         # '!' negative lookahead, '&' positive lookahead
               | "-!" | "-&"                        # '-' negative lookbehind, '-&' positive lookbehind
    retrieveop = "::" | ":"                         # '::' pop, ':' retrieve
85
    
86
87
88
89
90
    group      = "(" §expression ")"
    unordered  = "<" §expression ">"                # elements of expression in arbitrary order
    oneormore  = "{" expression "}+"
    repetition = "{" §expression "}"
    option     = "[" §expression "]"
91
    
92
93
94
95
    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
di68kap's avatar
di68kap committed
96
97
    regexp     = /\/(?:\\\/|[^\/])*?\//~            # e.g. /\w+/, ~/#.*(?:\n|$)/~
    whitespace = /~/~                               # insignificant whitespace
98
99
100
    list_      = /\w+/~ { "," /\w+/~ }              # comma separated list of symbols, e.g. BEGIN_LIST, END_LIST,
                                                    # BEGIN_QUOTE, END_QUOTE ; see CommonMark/markdown.py for an exmaple
    EOF = !/./
101
102
    """
    expression = Forward()
eckhart's avatar
eckhart committed
103
    source_hash__ = "6099690fa36228d49e6c35ec60750c59"
104
105
106
    parser_initialization__ = "upon instantiation"
    COMMENT__ = r'#.*(?:\n|$)'
    WHITESPACE__ = r'\s*'
107
    WSP_RE__ = mixin_comment(whitespace=WHITESPACE__, comment=COMMENT__)
di68kap's avatar
di68kap committed
108
    wsp__ = Whitespace(WSP_RE__)
109
    EOF = NegativeLookahead(RegExp('.'))
di68kap's avatar
di68kap committed
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
    list_ = Series(RegExp('\\w+'), wsp__, ZeroOrMore(Series(Series(Token(","), wsp__), RegExp('\\w+'), wsp__)))
    whitespace = Series(RegExp('~'), wsp__)
    regexp = Series(RegExp('/(?:\\\\/|[^/])*?/'), wsp__)
    plaintext = Series(RegExp('`(?:[^"]|\\\\")*?`'), wsp__)
    literal = Alternative(Series(RegExp('"(?:[^"]|\\\\")*?"'), wsp__), Series(RegExp("'(?:[^']|\\\\')*?'"), wsp__))
    symbol = Series(RegExp('(?!\\d)\\w+'), wsp__)
    option = Series(Series(Token("["), wsp__), expression, Series(Token("]"), wsp__), mandatory=1)
    repetition = Series(Series(Token("{"), wsp__), expression, Series(Token("}"), wsp__), mandatory=1)
    oneormore = Series(Series(Token("{"), wsp__), expression, Series(Token("}+"), wsp__))
    unordered = Series(Series(Token("<"), wsp__), expression, Series(Token(">"), wsp__), mandatory=1)
    group = Series(Series(Token("("), wsp__), expression, Series(Token(")"), wsp__), mandatory=1)
    retrieveop = Alternative(Series(Token("::"), wsp__), Series(Token(":"), wsp__))
    flowmarker = Alternative(Series(Token("!"), wsp__), Series(Token("&"), wsp__), Series(Token("-!"), wsp__), Series(Token("-&"), wsp__))
    factor = Alternative(Series(Option(flowmarker), Option(retrieveop), symbol, NegativeLookahead(Series(Token("="), wsp__))), 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)
    term = OneOrMore(Series(Option(Series(Token("§"), wsp__)), factor))
    expression.set(Series(term, ZeroOrMore(Series(Series(Token("|"), wsp__), term))))
    directive = Series(Series(Token("@"), wsp__), symbol, Series(Token("="), wsp__), Alternative(regexp, literal, list_), mandatory=1)
    definition = Series(symbol, Series(Token("="), wsp__), expression, mandatory=1)
    syntax = Series(Option(Series(wsp__, RegExp(''))), ZeroOrMore(Alternative(definition, directive)), EOF, mandatory=2)
129
130
131
132
    root__ = syntax
    
def get_grammar() -> EBNFGrammar:
    try:
eckhart's avatar
eckhart committed
133
134
135
136
        grammar = GLOBALS.EBNF_2_grammar_singleton
    except AttributeError:
        GLOBALS.EBNF_2_grammar_singleton = EBNFGrammar()
        grammar = GLOBALS.EBNF_2_grammar_singleton
137
138
139
140
141
142
143
144
145
146
    return grammar


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

EBNF_AST_transformation_table = {
di68kap's avatar
di68kap committed
147
    # AST Transformations for EBNF-grammar
148
    "<":
di68kap's avatar
di68kap committed
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
        remove_expendables,
    "syntax":
        [],  # otherwise '"*": replace_by_single_child' would be applied
    "directive, definition":
        remove_tokens('@', '='),
    "expression":
        [replace_by_single_child, flatten, remove_tokens('|')],  # remove_infix_operator],
    "term":
        [replace_by_single_child, flatten],  # supports both idioms:
                                             # "{ factor }+" and "factor { factor }"
    "factor, flowmarker, retrieveop":
        replace_by_single_child,
    "group":
        [remove_brackets, replace_by_single_child],
    "unordered":
        remove_brackets,
    "oneormore, repetition, option":
        [reduce_single_child, remove_brackets,
         forbid('repetition', 'option', 'oneormore'), assert_content(r'(?!§)(?:.|\n)*')],
    "symbol, literal, regexp":
        reduce_single_child,
    (TOKEN_PTYPE, WHITESPACE_PTYPE):
        reduce_single_child,
    "list_":
        [flatten, remove_infix_operator],
    "*":
        replace_by_single_child
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
}


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 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


eckhart's avatar
eckhart committed
253
def get_compiler() -> EBNFCompiler:
254
255
256
257
    global thread_local_EBNF_compiler_singleton
    try:
        compiler = thread_local_EBNF_compiler_singleton
    except NameError:
eckhart's avatar
eckhart committed
258
        thread_local_EBNF_compiler_singleton = EBNFCompiler()
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
        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:
292
            print(result.as_sxpr() if isinstance(result, Node) else result)
293
294
    else:
        print("Usage: EBNFCompiler.py [FILENAME]")