BibTeXCompiler.py 8.63 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
#!/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

sys.path.extend(['../../', '../', './'])

from DHParser import logging, is_filename, load_if_file, \
    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, \
28
    content_from_sinlge_child, replace_by_single_child, replace_or_reduce, remove_whitespace, \
29
    remove_expendables, remove_empty, remove_tokens, flatten, is_whitespace, \
eckhart's avatar
eckhart committed
30
    is_empty, is_expendable, collapse, replace_content, remove_nodes, remove_content, remove_brackets, replace_parser, \
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
62
63
64
65
66
67
68
69
70
71
72
73
74
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
    keep_children, is_one_of, has_content, apply_if, remove_first, remove_last, \
    WHITESPACE_PTYPE, TOKEN_PTYPE


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

def BibTeXPreprocessor(text):
    return text

def get_preprocessor() -> PreprocessorFunc:
    return BibTeXPreprocessor


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

class BibTeXGrammar(Grammar):
    r"""Parser for a BibTeX source file, with this grammar:
    
    # BibTeX-Grammar
    
    
    #######################################################################
    #
    #  EBNF-Directives
    #
    ######################################################################
    
    @ whitespace  = /\s*/
    @ ignorecase  = True
    @ comment     = /%.*(?:\n|$)/
    
    
    #######################################################################
    #
    #  Bib-file Structure and Components
    #
    #######################################################################
    
    bibliography = { preamble | comment | entry }
    
    preamble      = "@Preamble{" /"/ pre_code /"/~ §"}"
    pre_code      = { /[^"%]+/ | /%.*\n/ }
    
    comment       = "@Comment{" text §"}"
    
    entry         = /@/ type "{" key { "," field §"=" content } §"}"
    type          = WORD
    key           = NO_BLANK_STRING
    field         = WORD_
    content       = "{" text "}" | plain_content
    
    plain_content = COMMA_TERMINATED_STRING
    text          = { CONTENT_STRING | "{" text "}" }
    
    
    #######################################################################
    #
    #  Regular Expressions
    #
    #######################################################################
    
    WORD          = /\w+/
    WORD_         = /\w+/~
    NO_BLANK_STRING         = /[^ \t\n,%]+/~
    COMMA_TERMINATED_STRING = { /[^,%]+/ | /(?=%)/~ }
    CONTENT_STRING = { /[^{}%]+/ | /(?=%)/~ }+
    """
    text = Forward()
    source_hash__ = "9c5e3c56e3d420e2ea5885612c07de46"
    parser_initialization__ = "upon instantiation"
    COMMENT__ = r'(?i)%.*(?:\n|$)'
    WHITESPACE__ = r'\s*'
    WSP__ = mixin_comment(whitespace=WHITESPACE__, comment=COMMENT__)
    wspL__ = ''
    wspR__ = WSP__
    CONTENT_STRING = OneOrMore(Alternative(RegExp('(?i)[^{}%]+'), RE('(?i)(?=%)')))
    COMMA_TERMINATED_STRING = ZeroOrMore(Alternative(RegExp('(?i)[^,%]+'), RE('(?i)(?=%)')))
    NO_BLANK_STRING = RE('(?i)[^ \\t\\n,%]+')
    WORD_ = RE('(?i)\\w+')
    WORD = RegExp('(?i)\\w+')
    text.set(ZeroOrMore(Alternative(CONTENT_STRING, Series(Token("{"), text, Token("}")))))
    plain_content = Synonym(COMMA_TERMINATED_STRING)
    content = Alternative(Series(Token("{"), text, Token("}")), plain_content)
    field = Synonym(WORD_)
    key = Synonym(NO_BLANK_STRING)
    type = Synonym(WORD)
    entry = Series(RegExp('(?i)@'), type, Token("{"), key, ZeroOrMore(Series(Token(","), field, Token("="), content, mandatory=2)), Token("}"), mandatory=5)
    comment = Series(Token("@Comment{"), text, Token("}"), mandatory=2)
    pre_code = ZeroOrMore(Alternative(RegExp('(?i)[^"%]+'), RegExp('(?i)%.*\\n')))
    preamble = Series(Token("@Preamble{"), RegExp('(?i)"'), pre_code, RE('(?i)"'), Token("}"), mandatory=4)
    bibliography = ZeroOrMore(Alternative(preamble, comment, entry))
    root__ = bibliography
    
def get_grammar() -> BibTeXGrammar:
    global thread_local_BibTeX_grammar_singleton
    try:
        grammar = thread_local_BibTeX_grammar_singleton
    except NameError:
        thread_local_BibTeX_grammar_singleton = BibTeXGrammar()
        grammar = thread_local_BibTeX_grammar_singleton
    return grammar


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

BibTeX_AST_transformation_table = {
    # AST Transformations for the BibTeX-grammar
    "+": remove_empty,
    "bibliography": [],
    "preamble": [],
    "pre_code": [],
    "comment": [],
    "entry": [],
    "type": [],
    "key": [],
    "field": [],
    "content": [replace_or_reduce],
    "plain_content": [],
    "text": [],
162
163
    ":Token, :RE": content_from_sinlge_child,
    "*": replace_by_single_child
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
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
}


def BibTeXTransform() -> TransformationDict:
    return partial(traverse, processing_table=BibTeX_AST_transformation_table.copy())

def get_transformer() -> TransformationFunc:
    global thread_local_BibTeX_transformer_singleton
    try:
        transformer = thread_local_BibTeX_transformer_singleton
    except NameError:
        thread_local_BibTeX_transformer_singleton = BibTeXTransform()
        transformer = thread_local_BibTeX_transformer_singleton
    return transformer


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

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

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

    def on_bibliography(self, node):
        return node

    def on_preamble(self, node):
        pass

    def on_pre_code(self, node):
        pass

    def on_comment(self, node):
        pass

    def on_entry(self, node):
        pass

    def on_type(self, node):
        pass

    def on_key(self, node):
        pass

    def on_field(self, node):
        pass

    def on_content(self, node):
        pass

    def on_plain_content(self, node):
        pass

    def on_text(self, node):
        pass


def get_compiler(grammar_name="BibTeX", grammar_source="") -> BibTeXCompiler:
    global thread_local_BibTeX_compiler_singleton
    try:
        compiler = thread_local_BibTeX_compiler_singleton
        compiler.set_grammar_name(grammar_name, grammar_source)
    except NameError:
        thread_local_BibTeX_compiler_singleton = \
            BibTeXCompiler(grammar_name, grammar_source)
        compiler = thread_local_BibTeX_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: BibTeXCompiler.py [FILENAME]")