LaTeXCompiler.py 22.5 KB
Newer Older
1
2
3
4
5
6
7
8
9
#!/usr/bin/python

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


10
from functools import partial
11
12
13
14
15
16
import os
import sys
try:
    import regex as re
except ImportError:
    import re
17
18
19
20
from DHParser import logging, is_filename, load_if_file, \
    Grammar, Compiler, nil_preprocessor, \
    Lookbehind, Lookahead, Alternative, Pop, Required, Token, Synonym, \
    Optional, NegativeLookbehind, OneOrMore, RegExp, Retrieve, Series, RE, Capture, \
21
    ZeroOrMore, Forward, NegativeLookahead, mixin_comment, compile_source, \
22
23
24
25
26
27
28
29
    last_value, counterpart, accumulate, PreprocessorFunc, \
    Node, TransformationFunc, MockParser, \
    traverse, remove_children_if, merge_children, TRUE_CONDITION, is_anonymous, \
    reduce_single_child, replace_by_single_child, remove_whitespace, \
    remove_expendables, remove_empty, remove_tokens, flatten, is_whitespace, \
    is_empty, is_expendable, collapse, replace_content, WHITESPACE_PTYPE, TOKEN_PTYPE, \
    remove_parser, remove_content, remove_brackets, replace_parser, \
    keep_children, is_one_of, has_content, apply_if, remove_first, remove_last
30
31
32
33


#######################################################################
#
Eckhart Arnold's avatar
Eckhart Arnold committed
34
# PREPROCESSOR SECTION - Can be edited. Changes will be preserved.
35
36
37
#
#######################################################################

Eckhart Arnold's avatar
Eckhart Arnold committed
38
def LaTeXPreprocessor(text):
39
40
    return text

Eckhart Arnold's avatar
Eckhart Arnold committed
41
42
def get_preprocessor() -> PreprocessorFunc:
    return LaTeXPreprocessor
43
44
45
46
47
48
49
50
51
52
53


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

class LaTeXGrammar(Grammar):
    r"""Parser for a LaTeX source file, with this grammar:
    
54
    # LaTeX-Grammar for DHParser
55
56
57
58
59
60
    
    @ testing    = True
    @ whitespace = /[ \t]*(?:\n(?![ \t]*\n)[ \t]*)?/    # optional whitespace, including at most one linefeed
    @ comment    = /%.*(?:\n|$)/
    
    
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
    latexdoc       = preamble document
    preamble       = { command }+
    
    document       = [PARSEP] "\begin{document}" [PARSEP]
                     frontpages [PARSEP]
                     (Chapters | Sections) [PARSEP]
                     [Bibliography] [Index] [PARSEP]
                     "\end{document}" [PARSEP] §EOF
    frontpages     = sequence
    
    
    #######################################################################
    #
    # document structure
    #
    #######################################################################
    
    Chapters       = { Chapter [PARSEP] }+
    Chapter        = "\Chapter" block [PARSEP] { sequence | Sections }
    
    Sections       = { Section [PARSEP] }+
    Section        = "\Section" block [PARSEP] { sequence | SubSections }
    
    SubSections    = { SubSection [PARSEP] }+
    SubSection     = "\SubSection" block [PARSEP] { sequence | SubSubSections }
    
    SubSubSections = { SubSubSection [PARSEP] }+
    SubSubSection  = "\SubSubSection" block [PARSEP] { sequence | Paragraphs }
    
    Paragraphs     = { Paragraph [PARSEP] }+
    Paragraph      = "\paragraph" block [PARSEP] { sequence | SubParagraphs }
    
    SubParagraphs  = { SubParagraph [PARSEP] }+
    SubParagraph   = "\subparagpaph" block [PARSEP] { sequence }
    
    Bibliography   = "\bibliography" block [PARSEP]
    Index          = "\printindex" [PARSEP]
    
    
    #######################################################################
    #
    # document content
    #
    #######################################################################
    
    
    #### block environments ####
108
    
Eckhart Arnold's avatar
Eckhart Arnold committed
109
    block_environment   = known_environment | generic_block
110
    known_environment   = itemize | enumerate | figure | table | quotation
111
                        | verbatim
Eckhart Arnold's avatar
Eckhart Arnold committed
112
    generic_block       = begin_generic_block sequence §end_generic_block
113
114
    begin_generic_block = -&LB begin_environment -&LB
    end_generic_block   = -&LB  end_environment  -&LB
115
    
116
    itemize             = "\begin{itemize}" [PARSEP] { item } §"\end{itemize}"
117
    enumerate           = "\begin{enumerate}" [PARSEP] {item } §"\end{enumerate}"
118
    item                = "\item" [PARSEP] sequence
119
    
120
121
122
123
124
125
    figure              = "\begin{figure}" sequence "\end{figure}"
    quotation           = ("\begin{quotation}" sequence "\end{quotation}")
                        | ("\begin{quote}" sequence "\end{quote}")
    verbatim            = "\begin{verbatim}" sequence "\end{verbatim}"
    table               = "\begin{tabular}" table_config sequence "\end{tabular}"
    table_config        = "{" /[lcr|]+/~ "}"
126
127
    
    
128
129
130
    #### paragraphs and sequences of paragraphs ####
    
    block_of_paragraphs = /{/ sequence §/}/
131
    sequence            = { (paragraph | block_environment ) [PARSEP] }+
132
    
133
134
    paragraph           = { !blockcmd text_element //~ }+
    text_element       = command | text | block | inline_environment
135
136
137
138
    
    
    #### inline enivronments ####
    
139
    inline_environment  = known_inline_env | generic_inline_env
140
    known_inline_env    = inline_math
141
    generic_inline_env  = (begin_inline_env { text_element }+ §end_inline_env)
Eckhart Arnold's avatar
Eckhart Arnold committed
142
    begin_inline_env    = (-!LB begin_environment) | (begin_environment -!LB)
143
144
    end_inline_env      = end_environment
                          # (-!LB end_environment)   | (end_environment   -!LB)  # ambiguity with genric_block when EOF
145
146
    begin_environment   = "\begin{" §NAME §"}"
    end_environment     = "\end{" §::NAME §"}"
147
    
Eckhart Arnold's avatar
Eckhart Arnold committed
148
    inline_math         = "$" /[^$]*/ "$"
149
150
151
152
153
    
    
    #### commands ####
    
    command             = known_command | generic_command
Eckhart Arnold's avatar
Eckhart Arnold committed
154
    known_command       = footnote | includegraphics | caption
Eckhart Arnold's avatar
Eckhart Arnold committed
155
    generic_command     = !no_command CMDNAME [[ //~ config ] //~ block ]
156
157
    
    footnote            = "\footnote" block_of_paragraphs
Eckhart Arnold's avatar
Eckhart Arnold committed
158
159
    includegraphics     = "\includegraphics" config block
    caption             = "\caption" block
160
    
161
    
162
163
164
165
166
167
    #######################################################################
    #
    # low-level text and character sequences
    #
    #######################################################################
    
168
    
169
    config     = "[" cfgtext §"]"
170
    block      = /{/ { text_element } §/}/
171
172
173
174
175
    
    text       = { cfgtext | (BRACKETS //~) }+
    cfgtext    = { word_sequence | (ESCAPED //~) }+
    word_sequence = { TEXTCHUNK //~ }+
    
Eckhart Arnold's avatar
Eckhart Arnold committed
176
177
178
179
180
    no_command = "\begin{" | "\end" | BACKSLASH structural
    blockcmd   = BACKSLASH ( ( "begin{" | "end{" )
                             ( "enumerate" | "itemize" | "figure" | "quote"
                             | "quotation" | "tabular") "}"
                           | structural | begin_generic_block | end_generic_block )
181
182
183
    
    structural = "subsection" | "section" | "chapter" | "subsubsection"
               | "paragraph" | "subparagraph" | "item"
184
185
186
187
188
189
190
    
    
    #######################################################################
    #
    # Primitives
    #
    #######################################################################
191
    
192
    
193
194
195
196
197
198
199
    CMDNAME    = /\\(?:(?!_)\w)+/~
    NAME       = /\w+/~
    
    ESCAPED    = /\\[%$&_\/]/
    BRACKETS   = /[\[\]]/                       # left or right square bracket: [ ]
    TEXTCHUNK  = /[^\\%$&\{\}\[\]\s\n]+/        # some piece of text excluding whitespace,
                                                # linefeed and special characters
Eckhart Arnold's avatar
Eckhart Arnold committed
200
    LF         = !PARSEP /[ \t]*\n[ \t]*/       # linefeed but not an empty line
201
202
    PARSEP     = /[ \t]*(?:\n[ \t]*)+\n[ \t]*/  # at least one empty line, i.e.
                                                # [whitespace] linefeed [whitespace] linefeed
203
204
    LB         = /\s*?\n|$/                     # backwards line break for Lookbehind-Operator
                                                # beginning of text marker '$' added for test code
Eckhart Arnold's avatar
Eckhart Arnold committed
205
206
207
    BACKSLASH  = /[\\]/
    
    EOF        = /(?!.)/                        # End-Of-File
208
    """
Eckhart Arnold's avatar
Eckhart Arnold committed
209
    begin_generic_block = Forward()
210
    block_environment = Forward()
211
    block_of_paragraphs = Forward()
Eckhart Arnold's avatar
Eckhart Arnold committed
212
    end_generic_block = Forward()
213
214
    text_element = Forward()
    source_hash__ = "4e001b31490278efccfe43953bfdcf58"
215
216
217
218
219
    parser_initialization__ = "upon instantiation"
    COMMENT__ = r'%.*(?:\n|$)'
    WSP__ = mixin_comment(whitespace=r'[ \t]*(?:\n(?![ \t]*\n)[ \t]*)?', comment=r'%.*(?:\n|$)')
    wspL__ = ''
    wspR__ = WSP__
Eckhart Arnold's avatar
Eckhart Arnold committed
220
    EOF = RegExp('(?!.)')
Eckhart Arnold's avatar
Eckhart Arnold committed
221
222
    BACKSLASH = RegExp('[\\\\]')
    LB = RegExp('\\s*?\\n|$')
Eckhart Arnold's avatar
Eckhart Arnold committed
223
224
225
226
227
    PARSEP = RegExp('[ \\t]*(?:\\n[ \\t]*)+\\n[ \\t]*')
    LF = Series(NegativeLookahead(PARSEP), RegExp('[ \\t]*\\n[ \\t]*'))
    TEXTCHUNK = RegExp('[^\\\\%$&\\{\\}\\[\\]\\s\\n]+')
    BRACKETS = RegExp('[\\[\\]]')
    ESCAPED = RegExp('\\\\[%$&_/]')
228
229
    NAME = Capture(RE('\\w+'))
    CMDNAME = RE('\\\\(?:(?!_)\\w)+')
Eckhart Arnold's avatar
Eckhart Arnold committed
230
    structural = Alternative(Token("subsection"), Token("section"), Token("chapter"), Token("subsubsection"), Token("paragraph"), Token("subparagraph"), Token("item"))
Eckhart Arnold's avatar
Eckhart Arnold committed
231
232
    blockcmd = Series(BACKSLASH, Alternative(Series(Alternative(Token("begin{"), Token("end{")), Alternative(Token("enumerate"), Token("itemize"), Token("figure"), Token("quote"), Token("quotation"), Token("tabular")), Token("}")), structural, begin_generic_block, end_generic_block))
    no_command = Alternative(Token("\\begin{"), Token("\\end"), Series(BACKSLASH, structural))
233
234
235
    word_sequence = OneOrMore(Series(TEXTCHUNK, RE('')))
    cfgtext = OneOrMore(Alternative(word_sequence, Series(ESCAPED, RE(''))))
    text = OneOrMore(Alternative(cfgtext, Series(BRACKETS, RE(''))))
236
    block = Series(RegExp('{'), ZeroOrMore(text_element), Required(RegExp('}')))
237
    config = Series(Token("["), cfgtext, Required(Token("]")))
Eckhart Arnold's avatar
Eckhart Arnold committed
238
239
    caption = Series(Token("\\caption"), block)
    includegraphics = Series(Token("\\includegraphics"), config, block)
240
    footnote = Series(Token("\\footnote"), block_of_paragraphs)
Eckhart Arnold's avatar
Eckhart Arnold committed
241
    generic_command = Series(NegativeLookahead(no_command), CMDNAME, Optional(Series(Optional(Series(RE(''), config)), RE(''), block)))
Eckhart Arnold's avatar
Eckhart Arnold committed
242
    known_command = Alternative(footnote, includegraphics, caption)
243
    command = Alternative(known_command, generic_command)
Eckhart Arnold's avatar
Eckhart Arnold committed
244
    inline_math = Series(Token("$"), RegExp('[^$]*'), Token("$"))
245
246
    end_environment = Series(Token("\\end{"), Required(Pop(NAME)), Required(Token("}")))
    begin_environment = Series(Token("\\begin{"), Required(NAME), Required(Token("}")))
247
    end_inline_env = Synonym(end_environment)
Eckhart Arnold's avatar
Eckhart Arnold committed
248
    begin_inline_env = Alternative(Series(NegativeLookbehind(LB), begin_environment), Series(begin_environment, NegativeLookbehind(LB)))
249
    generic_inline_env = Series(begin_inline_env, OneOrMore(text_element), Required(end_inline_env))
250
    known_inline_env = Synonym(inline_math)
251
    inline_environment = Alternative(known_inline_env, generic_inline_env)
252
253
    text_element.set(Alternative(command, text, block, inline_environment))
    paragraph = OneOrMore(Series(NegativeLookahead(blockcmd), text_element, RE('')))
254
    sequence = OneOrMore(Series(Alternative(paragraph, block_environment), Optional(PARSEP)))
Eckhart Arnold's avatar
Eckhart Arnold committed
255
    block_of_paragraphs.set(Series(RegExp('{'), sequence, Required(RegExp('}'))))
256
257
258
    table_config = Series(Token("{"), RE('[lcr|]+'), Token("}"))
    table = Series(Token("\\begin{tabular}"), table_config, sequence, Token("\\end{tabular}"))
    verbatim = Series(Token("\\begin{verbatim}"), sequence, Token("\\end{verbatim}"))
Eckhart Arnold's avatar
Eckhart Arnold committed
259
    quotation = Alternative(Series(Token("\\begin{quotation}"), sequence, Token("\\end{quotation}")), Series(Token("\\begin{quote}"), sequence, Token("\\end{quote}")))
260
261
    figure = Series(Token("\\begin{figure}"), sequence, Token("\\end{figure}"))
    item = Series(Token("\\item"), Optional(PARSEP), sequence)
Eckhart Arnold's avatar
Eckhart Arnold committed
262
    enumerate = Series(Token("\\begin{enumerate}"), Optional(PARSEP), ZeroOrMore(item), Required(Token("\\end{enumerate}")))
263
    itemize = Series(Token("\\begin{itemize}"), Optional(PARSEP), ZeroOrMore(item), Required(Token("\\end{itemize}")))
264
265
    end_generic_block.set(Series(Lookbehind(LB), end_environment, Lookbehind(LB)))
    begin_generic_block.set(Series(Lookbehind(LB), begin_environment, Lookbehind(LB)))
Eckhart Arnold's avatar
Eckhart Arnold committed
266
    generic_block = Series(begin_generic_block, sequence, Required(end_generic_block))
267
    known_environment = Alternative(itemize, enumerate, figure, table, quotation, verbatim)
Eckhart Arnold's avatar
Eckhart Arnold committed
268
    block_environment.set(Alternative(known_environment, generic_block))
269
270
271
272
273
274
    Index = Series(Token("\\printindex"), Optional(PARSEP))
    Bibliography = Series(Token("\\bibliography"), block, Optional(PARSEP))
    SubParagraph = Series(Token("\\subparagpaph"), block, Optional(PARSEP), ZeroOrMore(sequence))
    SubParagraphs = OneOrMore(Series(SubParagraph, Optional(PARSEP)))
    Paragraph = Series(Token("\\paragraph"), block, Optional(PARSEP), ZeroOrMore(Alternative(sequence, SubParagraphs)))
    Paragraphs = OneOrMore(Series(Paragraph, Optional(PARSEP)))
Eckhart Arnold's avatar
Eckhart Arnold committed
275
    SubSubSection = Series(Token("\\SubSubSection"), block, Optional(PARSEP), ZeroOrMore(Alternative(sequence, Paragraphs)))
276
    SubSubSections = OneOrMore(Series(SubSubSection, Optional(PARSEP)))
Eckhart Arnold's avatar
Eckhart Arnold committed
277
    SubSection = Series(Token("\\SubSection"), block, Optional(PARSEP), ZeroOrMore(Alternative(sequence, SubSubSections)))
278
279
280
281
282
283
    SubSections = OneOrMore(Series(SubSection, Optional(PARSEP)))
    Section = Series(Token("\\Section"), block, Optional(PARSEP), ZeroOrMore(Alternative(sequence, SubSections)))
    Sections = OneOrMore(Series(Section, Optional(PARSEP)))
    Chapter = Series(Token("\\Chapter"), block, Optional(PARSEP), ZeroOrMore(Alternative(sequence, Sections)))
    Chapters = OneOrMore(Series(Chapter, Optional(PARSEP)))
    frontpages = Synonym(sequence)
Eckhart Arnold's avatar
Eckhart Arnold committed
284
    document = Series(Optional(PARSEP), Token("\\begin{document}"), Optional(PARSEP), frontpages, Optional(PARSEP), Alternative(Chapters, Sections), Optional(PARSEP), Optional(Bibliography), Optional(Index), Optional(PARSEP), Token("\\end{document}"), Optional(PARSEP), Required(EOF))
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
    preamble = OneOrMore(command)
    latexdoc = Series(preamble, document)
    root__ = latexdoc
    
def get_grammar() -> LaTeXGrammar:
    global thread_local_LaTeX_grammar_singleton
    try:
        grammar = thread_local_LaTeX_grammar_singleton
        return grammar
    except NameError:
        thread_local_LaTeX_grammar_singleton = LaTeXGrammar()
        return thread_local_LaTeX_grammar_singleton


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


def streamline_whitespace(node):
    assert node.tag_name in ['WSPC', ':Whitespace']
    s = str(node)
    c = s.find('%')
    n = s.find('\n')
    if c >= 0:
312
313
314
        node.result = '\n'
        # node.result = ('  ' if (n >= c) or (n < 0) else '\n')+ s[c:].rstrip(' \t')
        # node.parser = MockParser('COMMENT', '')
315
316
317
318
319
320
    elif s.find('\n') >= 0:
        node.result = '\n'
    else:
        node.result = ' '


321
322
323
324
def watch(node):
    print(node.as_sxpr())


325
326
LaTeX_AST_transformation_table = {
    # AST Transformations for the LaTeX-grammar
327
    "+": remove_empty,
328
329
330
    "latexdoc": [],
    "preamble": [],
    "document": [],
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
    "frontpages": [],
    "Chapters": [],
    "Chapter": [],
    "Sections": [],
    "Section": [],
    "SubSections": [],
    "SubSection": [],
    "SubSubSections": [],
    "SubSubSection": [],
    "Paragraphs": [],
    "Paragraph": [],
    "SubParagraphs": [],
    "SubParagraph": [],
    "Bibliography": [],
    "Index": [],
    "block_environment": replace_by_single_child,
    "known_environment": replace_by_single_child,
    "generic_block": [],
    "begin_generic_block, end_generic_block": reduce_single_child,
    "itemize, enumerate": [remove_brackets, flatten],
    "item": [remove_first],
    "figure": [],
    "quotation": [reduce_single_child, remove_brackets],
    "verbatim": [],
    "table": [],
    "table_config": [],
    "block_of_paragraphs": [],
    "sequence": [flatten],
    "paragraph": [flatten],
    "text_element": [],
    "inline_environment": replace_by_single_child,
    "known_inline_env": replace_by_single_child,
    "generic_inline_env": [],
    "begin_inline_env, end_inline_env": [reduce_single_child],
    "begin_environment, end_environment": [remove_brackets, reduce_single_child],
    "inline_math": [remove_brackets, reduce_single_child],
    "command": [],
    "known_command": [],
    "generic_command": [flatten],
    "footnote": [],
    "includegraphics": [],
    "caption": [],
    "config": [remove_brackets],
    "block": [remove_brackets, reduce_single_child(is_anonymous)],
    "text": [reduce_single_child, merge_children('word_sequence', ':Whitespace', 'TEXTCHUNK')],
    "cfgtext": [flatten, reduce_single_child, replace_parser('text')],
    "word_sequence": collapse,  # [flatten, merge_children('TEXTCHUNK', ':Whitespace'), reduce_single_child],
    "no_command": [],
379
    "blockcmd": [],
380
381
382
383
    "structural": [],
    "CMDNAME": [remove_whitespace, reduce_single_child(is_anonymous)],
    "NAME": [reduce_single_child, remove_whitespace, reduce_single_child],
    "ESCAPED": [replace_content(lambda node: str(node)[1:])],
384
385
    "BRACKETS": [],
    "TEXTCHUNK": [],
386
387
388
389
    "LF": [],
    "PARSEP": replace_content(lambda node: '\n\n'),
    "LB": [],
    "BACKSLASH": [],
390
    "EOF": [],
391
392
393
394
    ":Token": [],
    ":RE": replace_by_single_child,
    ":Whitespace": streamline_whitespace,
    "*": replace_by_single_child
395
396
397
}

LaTeXTransform = partial(traverse, processing_table=LaTeX_AST_transformation_table)
398

399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418

def get_transformer() -> TransformationFunc:
    return LaTeXTransform


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

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

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

    def on_latexdoc(self, node):
Eckhart Arnold's avatar
Eckhart Arnold committed
419
        return node
420
421
422
423
424
425
426

    def on_preamble(self, node):
        pass

    def on_document(self, node):
        pass

Eckhart Arnold's avatar
Eckhart Arnold committed
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
    def on_frontpages(self, node):
        pass

    def on_Chapters(self, node):
        pass

    def on_Chapter(self, node):
        pass

    def on_Sections(self, node):
        pass

    def on_Section(self, node):
        pass

    def on_SubSections(self, node):
        pass

    def on_SubSection(self, node):
        pass

    def on_SubSubSections(self, node):
        pass

    def on_SubSubSection(self, node):
        pass

    def on_Paragraphs(self, node):
        pass

    def on_Paragraph(self, node):
        pass

    def on_SubParagraphs(self, node):
        pass

    def on_SubParagraph(self, node):
        pass

    def on_Bibliography(self, node):
        pass

    def on_Index(self, node):
        pass

    def on_block_environment(self, node):
        pass

    def on_known_environment(self, node):
        pass

    def on_generic_block(self, node):
        pass

    def on_begin_generic_block(self, node):
        pass

    def on_end_generic_block(self, node):
        pass

    def on_itemize(self, node):
        pass

    def on_enumerate(self, node):
        pass

    def on_item(self, node):
        pass

    def on_figure(self, node):
        pass

    def on_quotation(self, node):
        pass

    def on_verbatim(self, node):
        pass

    def on_table(self, node):
506
507
        pass

Eckhart Arnold's avatar
Eckhart Arnold committed
508
509
510
511
    def on_table_config(self, node):
        pass

    def on_block_of_paragraphs(self, node):
512
513
514
515
516
517
518
519
        pass

    def on_sequence(self, node):
        pass

    def on_paragraph(self, node):
        pass

520
    def on_text_element(self, node):
Eckhart Arnold's avatar
Eckhart Arnold committed
521
522
523
524
525
526
        pass

    def on_inline_environment(self, node):
        pass

    def on_known_inline_env(self, node):
527
528
        pass

Eckhart Arnold's avatar
Eckhart Arnold committed
529
    def on_generic_inline_env(self, node):
530
531
        pass

Eckhart Arnold's avatar
Eckhart Arnold committed
532
533
534
535
536
537
538
539
540
541
    def on_begin_inline_env(self, node):
        pass

    def on_begin_environment(self, node):
        pass

    def on_end_environment(self, node):
        pass

    def on_inline_math(self, node):
542
543
544
545
546
        pass

    def on_command(self, node):
        pass

Eckhart Arnold's avatar
Eckhart Arnold committed
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
    def on_known_command(self, node):
        pass

    def on_generic_command(self, node):
        pass

    def on_footnote(self, node):
        pass

    def on_includegraphics(self, node):
        pass

    def on_caption(self, node):
        pass

562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
    def on_config(self, node):
        pass

    def on_block(self, node):
        pass

    def on_text(self, node):
        pass

    def on_cfgtext(self, node):
        pass

    def on_word_sequence(self, node):
        pass

577
578
579
    def on_no_command(self, node):
        pass

580
581
582
    def on_blockcmd(self, node):
        pass

Eckhart Arnold's avatar
Eckhart Arnold committed
583
584
585
    def on_structural(self, node):
        pass

586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
    def on_CMDNAME(self, node):
        pass

    def on_NAME(self, node):
        pass

    def on_ESCAPED(self, node):
        pass

    def on_BRACKETS(self, node):
        pass

    def on_TEXTCHUNK(self, node):
        pass

    def on_WSPC(self, node):
        pass

    def on_LF(self, node):
        pass

    def on_PARSEP(self, node):
        pass

610
    def on_LB(self, node):
611
612
        pass

613
    def on_BACKSLASH(self, node):
Eckhart Arnold's avatar
Eckhart Arnold committed
614
615
        pass

616
    def on_EOF(self, node):
Eckhart Arnold's avatar
Eckhart Arnold committed
617
618
        pass

619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645

def get_compiler(grammar_name="LaTeX", grammar_source="") -> LaTeXCompiler:
    global thread_local_LaTeX_compiler_singleton
    try:
        compiler = thread_local_LaTeX_compiler_singleton
        compiler.set_grammar_name(grammar_name, grammar_source)
        return compiler
    except NameError:
        thread_local_LaTeX_compiler_singleton = \
            LaTeXCompiler(grammar_name, grammar_source)
        return thread_local_LaTeX_compiler_singleton 


#######################################################################
#
# 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]) \
646
647
            if is_filename(source) < 0 else cname[:cname.find('.')] + '_out'    
        result = compile_source(source, get_preprocessor(), 
648
649
650
651
652
653
654
655
656
657
658
659
660
                                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:
Eckhart Arnold's avatar
Eckhart Arnold committed
661
            print(result.as_xml() if isinstance(result, Node) else result)
662
663
    else:
        print("Usage: LaTeXCompiler.py [FILENAME]")