LaTeXCompiler.py 22.9 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
Eckhart Arnold's avatar
Eckhart Arnold committed
110
    known_environment   = itemize | enumerate | figure | tabular | quotation
111
                        | verbatim
Eckhart Arnold's avatar
Eckhart Arnold committed
112
    generic_block       = begin_generic_block sequence §end_generic_block
Eckhart Arnold's avatar
Eckhart Arnold committed
113
114
    begin_generic_block = -&LB begin_environment LFF
    end_generic_block   = -&LB  end_environment LFF
115
    
116
    itemize             = "\begin{itemize}" [PARSEP] { item } §"\end{itemize}"
117
    enumerate           = "\begin{enumerate}" [PARSEP] {item } §"\end{enumerate}"
118
    item                = "\item" [PARSEP] sequence
119
    
Eckhart Arnold's avatar
Eckhart Arnold committed
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}"
    tabular             = "\begin{tabular}" tabular_config sequence §"\end{tabular}"
    tabular_config      = "{" /[lcr|]+/~ §"}"
126
127
    
    
128
129
    #### paragraphs and sequences of paragraphs ####
    
Eckhart Arnold's avatar
Eckhart Arnold committed
130
    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
Eckhart Arnold's avatar
Eckhart Arnold committed
141
142
    generic_inline_env  = begin_inline_env //~ paragraph §end_inline_env
    begin_inline_env    = (-!LB begin_environment) | (begin_environment !LFF)
143
    end_inline_env      = end_environment
Eckhart Arnold's avatar
Eckhart Arnold committed
144
145
146
                          ## (-!LB end_environment)   | (end_environment !LFF)  # ambiguity with genric_block when EOF
    begin_environment   = /\\begin{/ §NAME §/}/
    end_environment     = /\\end{/ §::NAME §/}/
147
    
Eckhart Arnold's avatar
Eckhart Arnold committed
148
    inline_math         = /\$/ /[^$]*/ §/\$/
149
150
151
152
    
    
    #### commands ####
    
Eckhart Arnold's avatar
Eckhart Arnold committed
153
    command             = known_command | text_command | generic_command
Eckhart Arnold's avatar
Eckhart Arnold committed
154
    known_command       = footnote | includegraphics | caption
Eckhart Arnold's avatar
Eckhart Arnold committed
155
    text_command        = TXTCOMMAND | ESCAPED | BRACKETS
Eckhart Arnold's avatar
Eckhart Arnold committed
156
    generic_command     = !no_command CMDNAME [[ //~ config ] //~ block ]
157
158
    
    footnote            = "\footnote" block_of_paragraphs
Eckhart Arnold's avatar
Eckhart Arnold committed
159
    includegraphics     = "\includegraphics" [ config ] block
Eckhart Arnold's avatar
Eckhart Arnold committed
160
    caption             = "\caption" block
161
    
162
    
163
164
165
166
167
168
    #######################################################################
    #
    # low-level text and character sequences
    #
    #######################################################################
    
169
    
Eckhart Arnold's avatar
Eckhart Arnold committed
170
171
172
    config     = "[" text §"]"
    block      = /{/ //~ { !blockcmd text_element //~ } §/}/
    text       = TEXTCHUNK { //~ TEXTCHUNK }
173
    
Eckhart Arnold's avatar
Eckhart Arnold committed
174
175
176
177
178
    no_command = "\begin{" | "\end" | BACKSLASH structural
    blockcmd   = BACKSLASH ( ( "begin{" | "end{" )
                             ( "enumerate" | "itemize" | "figure" | "quote"
                             | "quotation" | "tabular") "}"
                           | structural | begin_generic_block | end_generic_block )
179
180
181
    
    structural = "subsection" | "section" | "chapter" | "subsubsection"
               | "paragraph" | "subparagraph" | "item"
182
183
184
185
186
187
188
    
    
    #######################################################################
    #
    # Primitives
    #
    #######################################################################
189
    
190
    
191
    CMDNAME    = /\\(?:(?!_)\w)+/~
Eckhart Arnold's avatar
Eckhart Arnold committed
192
193
194
195
    TXTCOMMAND = /\\text\w+/
    ESCAPED    = /\\[%$&_\/{}]/
    BRACKETS   = /[\[\]]/                       # left or right square bracket: [ ]
    
196
197
198
199
    NAME       = /\w+/~
    
    TEXTCHUNK  = /[^\\%$&\{\}\[\]\s\n]+/        # some piece of text excluding whitespace,
                                                # linefeed and special characters
Eckhart Arnold's avatar
Eckhart Arnold committed
200
    LF         = !GAP /[ \t]*\n[ \t]*/          # linefeed but not an empty line
Eckhart Arnold's avatar
Eckhart Arnold committed
201
202
    LFF        = //~ -&LB WSPC                  # at least one linefeed
    WSPC       = { ~/\s+/~ }                    # arbitrary horizontal or vertical whitespace
Eckhart Arnold's avatar
Eckhart Arnold committed
203
204
    PARSEP     = { GAP }+                       # paragraph separator
    GAP        = /[ \t]*(?:\n[ \t]*)+\n/~       # at least one empty line, i.e.
205
                                                # [whitespace] linefeed [whitespace] linefeed
206
207
    LB         = /\s*?\n|$/                     # backwards line break for Lookbehind-Operator
                                                # beginning of text marker '$' added for test code
Eckhart Arnold's avatar
Eckhart Arnold committed
208
209
210
    BACKSLASH  = /[\\]/
    
    EOF        = /(?!.)/                        # End-Of-File
211
    """
Eckhart Arnold's avatar
Eckhart Arnold committed
212
    begin_generic_block = Forward()
213
    block_environment = Forward()
214
    block_of_paragraphs = Forward()
Eckhart Arnold's avatar
Eckhart Arnold committed
215
    end_generic_block = Forward()
Eckhart Arnold's avatar
Eckhart Arnold committed
216
    paragraph = Forward()
217
    text_element = Forward()
Eckhart Arnold's avatar
Eckhart Arnold committed
218
    source_hash__ = "b06aca9481c1e5bd756caadb8b707dff"
219
220
221
222
223
    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
224
    EOF = RegExp('(?!.)')
Eckhart Arnold's avatar
Eckhart Arnold committed
225
226
    BACKSLASH = RegExp('[\\\\]')
    LB = RegExp('\\s*?\\n|$')
Eckhart Arnold's avatar
Eckhart Arnold committed
227
228
    GAP = RE('[ \\t]*(?:\\n[ \\t]*)+\\n')
    PARSEP = OneOrMore(GAP)
Eckhart Arnold's avatar
Eckhart Arnold committed
229
230
    WSPC = ZeroOrMore(RE('\\s+', wL=WSP__))
    LFF = Series(RE(''), Lookbehind(LB), WSPC)
Eckhart Arnold's avatar
Eckhart Arnold committed
231
    LF = Series(NegativeLookahead(GAP), RegExp('[ \\t]*\\n[ \\t]*'))
Eckhart Arnold's avatar
Eckhart Arnold committed
232
    TEXTCHUNK = RegExp('[^\\\\%$&\\{\\}\\[\\]\\s\\n]+')
233
    NAME = Capture(RE('\\w+'))
Eckhart Arnold's avatar
Eckhart Arnold committed
234
235
236
    BRACKETS = RegExp('[\\[\\]]')
    ESCAPED = RegExp('\\\\[%$&_/{}]')
    TXTCOMMAND = RegExp('\\\\text\\w+')
237
    CMDNAME = RE('\\\\(?:(?!_)\\w)+')
Eckhart Arnold's avatar
Eckhart Arnold committed
238
    structural = Alternative(Token("subsection"), Token("section"), Token("chapter"), Token("subsubsection"), Token("paragraph"), Token("subparagraph"), Token("item"))
Eckhart Arnold's avatar
Eckhart Arnold committed
239
240
    blockcmd = Series(BACKSLASH, Alternative(Series(Alternative(Token("begin{"), Token("end{")), Alternative(Token("enumerate"), Token("itemize"), Token("figure"), Token("quote"), Token("quotation"), Token("tabular")), Token("}")), structural, begin_generic_block, end_generic_block))
    no_command = Alternative(Token("\\begin{"), Token("\\end"), Series(BACKSLASH, structural))
Eckhart Arnold's avatar
Eckhart Arnold committed
241
242
243
    text = Series(TEXTCHUNK, ZeroOrMore(Series(RE(''), TEXTCHUNK)))
    block = Series(RegExp('{'), RE(''), ZeroOrMore(Series(NegativeLookahead(blockcmd), text_element, RE(''))), Required(RegExp('}')))
    config = Series(Token("["), text, Required(Token("]")))
Eckhart Arnold's avatar
Eckhart Arnold committed
244
    caption = Series(Token("\\caption"), block)
Eckhart Arnold's avatar
Eckhart Arnold committed
245
    includegraphics = Series(Token("\\includegraphics"), Optional(config), block)
246
    footnote = Series(Token("\\footnote"), block_of_paragraphs)
Eckhart Arnold's avatar
Eckhart Arnold committed
247
    generic_command = Series(NegativeLookahead(no_command), CMDNAME, Optional(Series(Optional(Series(RE(''), config)), RE(''), block)))
Eckhart Arnold's avatar
Eckhart Arnold committed
248
    text_command = Alternative(TXTCOMMAND, ESCAPED, BRACKETS)
Eckhart Arnold's avatar
Eckhart Arnold committed
249
    known_command = Alternative(footnote, includegraphics, caption)
Eckhart Arnold's avatar
Eckhart Arnold committed
250
251
252
253
    command = Alternative(known_command, text_command, generic_command)
    inline_math = Series(RegExp('\\$'), RegExp('[^$]*'), Required(RegExp('\\$')))
    end_environment = Series(RegExp('\\\\end{'), Required(Pop(NAME)), Required(RegExp('}')))
    begin_environment = Series(RegExp('\\\\begin{'), Required(NAME), Required(RegExp('}')))
254
    end_inline_env = Synonym(end_environment)
Eckhart Arnold's avatar
Eckhart Arnold committed
255
256
    begin_inline_env = Alternative(Series(NegativeLookbehind(LB), begin_environment), Series(begin_environment, NegativeLookahead(LFF)))
    generic_inline_env = Series(begin_inline_env, RE(''), paragraph, Required(end_inline_env))
257
    known_inline_env = Synonym(inline_math)
258
    inline_environment = Alternative(known_inline_env, generic_inline_env)
259
    text_element.set(Alternative(command, text, block, inline_environment))
Eckhart Arnold's avatar
Eckhart Arnold committed
260
    paragraph.set(OneOrMore(Series(NegativeLookahead(blockcmd), text_element, RE(''))))
261
    sequence = OneOrMore(Series(Alternative(paragraph, block_environment), Optional(PARSEP)))
Eckhart Arnold's avatar
Eckhart Arnold committed
262
263
264
265
266
267
    block_of_paragraphs.set(Series(RE('{'), sequence, Required(RegExp('}'))))
    tabular_config = Series(Token("{"), RE('[lcr|]+'), Required(Token("}")))
    tabular = Series(Token("\\begin{tabular}"), tabular_config, sequence, Required(Token("\\end{tabular}")))
    verbatim = Series(Token("\\begin{verbatim}"), sequence, Required(Token("\\end{verbatim}")))
    quotation = Alternative(Series(Token("\\begin{quotation}"), sequence, Required(Token("\\end{quotation}"))), Series(Token("\\begin{quote}"), sequence, Required(Token("\\end{quote}"))))
    figure = Series(Token("\\begin{figure}"), sequence, Required(Token("\\end{figure}")))
268
    item = Series(Token("\\item"), Optional(PARSEP), sequence)
Eckhart Arnold's avatar
Eckhart Arnold committed
269
    enumerate = Series(Token("\\begin{enumerate}"), Optional(PARSEP), ZeroOrMore(item), Required(Token("\\end{enumerate}")))
270
    itemize = Series(Token("\\begin{itemize}"), Optional(PARSEP), ZeroOrMore(item), Required(Token("\\end{itemize}")))
Eckhart Arnold's avatar
Eckhart Arnold committed
271
272
    end_generic_block.set(Series(Lookbehind(LB), end_environment, LFF))
    begin_generic_block.set(Series(Lookbehind(LB), begin_environment, LFF))
Eckhart Arnold's avatar
Eckhart Arnold committed
273
    generic_block = Series(begin_generic_block, sequence, Required(end_generic_block))
Eckhart Arnold's avatar
Eckhart Arnold committed
274
    known_environment = Alternative(itemize, enumerate, figure, tabular, quotation, verbatim)
Eckhart Arnold's avatar
Eckhart Arnold committed
275
    block_environment.set(Alternative(known_environment, generic_block))
276
277
278
279
280
281
    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
282
    SubSubSection = Series(Token("\\SubSubSection"), block, Optional(PARSEP), ZeroOrMore(Alternative(sequence, Paragraphs)))
283
    SubSubSections = OneOrMore(Series(SubSubSection, Optional(PARSEP)))
Eckhart Arnold's avatar
Eckhart Arnold committed
284
    SubSection = Series(Token("\\SubSection"), block, Optional(PARSEP), ZeroOrMore(Alternative(sequence, SubSubSections)))
285
286
287
288
289
290
    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
291
    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))
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
    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:
319
320
321
        node.result = '\n'
        # node.result = ('  ' if (n >= c) or (n < 0) else '\n')+ s[c:].rstrip(' \t')
        # node.parser = MockParser('COMMENT', '')
322
323
324
325
326
327
    elif s.find('\n') >= 0:
        node.result = '\n'
    else:
        node.result = ' '


328
329
330
331
def watch(node):
    print(node.as_sxpr())


332
333
LaTeX_AST_transformation_table = {
    # AST Transformations for the LaTeX-grammar
Eckhart Arnold's avatar
Eckhart Arnold committed
334
335
    "+": remove_children_if(lambda node: is_empty(node) or is_one_of(node, {'PARSEP'})),
    # remove_empty,
336
337
338
    "latexdoc": [],
    "preamble": [],
    "document": [],
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
    "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": [],
357
    "begin_generic_block, end_generic_block": replace_by_single_child,
358
359
360
361
362
363
364
365
366
367
368
369
370
371
    "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": [],
372
    "begin_inline_env, end_inline_env": [replace_by_single_child],
373
374
375
376
    "begin_environment, end_environment": [remove_brackets, reduce_single_child],
    "inline_math": [remove_brackets, reduce_single_child],
    "command": [],
    "known_command": [],
Eckhart Arnold's avatar
Eckhart Arnold committed
377
    "text_command": [],
378
379
380
381
382
    "generic_command": [flatten],
    "footnote": [],
    "includegraphics": [],
    "caption": [],
    "config": [remove_brackets],
Eckhart Arnold's avatar
Eckhart Arnold committed
383
    "block": [remove_brackets, flatten],
384
385
    "text": collapse,
    "no_command, blockcmd": [],
386
387
    "structural": [],
    "CMDNAME": [remove_whitespace, reduce_single_child(is_anonymous)],
Eckhart Arnold's avatar
Eckhart Arnold committed
388
    "TXTCOMMAND": [remove_whitespace, reduce_single_child(is_anonymous)],
389
390
    "NAME": [reduce_single_child, remove_whitespace, reduce_single_child],
    "ESCAPED": [replace_content(lambda node: str(node)[1:])],
391
392
    "BRACKETS": [],
    "TEXTCHUNK": [],
393
394
    "LF": [],
    "PARSEP": replace_content(lambda node: '\n\n'),
Eckhart Arnold's avatar
Eckhart Arnold committed
395
    "GAP": [],
396
397
    "LB": [],
    "BACKSLASH": [],
398
    "EOF": [],
399
400
401
402
    ":Token": [],
    ":RE": replace_by_single_child,
    ":Whitespace": streamline_whitespace,
    "*": replace_by_single_child
403
404
405
}

LaTeXTransform = partial(traverse, processing_table=LaTeX_AST_transformation_table)
406

407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426

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
427
        return node
428
429
430
431
432
433
434

    def on_preamble(self, node):
        pass

    def on_document(self, node):
        pass

Eckhart Arnold's avatar
Eckhart Arnold committed
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
506
507
508
509
510
511
512
513
    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):
514
515
        pass

Eckhart Arnold's avatar
Eckhart Arnold committed
516
517
518
519
    def on_table_config(self, node):
        pass

    def on_block_of_paragraphs(self, node):
520
521
522
523
524
525
526
527
        pass

    def on_sequence(self, node):
        pass

    def on_paragraph(self, node):
        pass

528
    def on_text_element(self, node):
Eckhart Arnold's avatar
Eckhart Arnold committed
529
530
531
532
533
534
        pass

    def on_inline_environment(self, node):
        pass

    def on_known_inline_env(self, node):
535
536
        pass

Eckhart Arnold's avatar
Eckhart Arnold committed
537
    def on_generic_inline_env(self, node):
538
539
        pass

Eckhart Arnold's avatar
Eckhart Arnold committed
540
541
542
543
544
545
546
547
548
549
    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):
550
551
552
553
554
        pass

    def on_command(self, node):
        pass

Eckhart Arnold's avatar
Eckhart Arnold committed
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
    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

570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
    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

585
586
587
    def on_no_command(self, node):
        pass

588
589
590
    def on_blockcmd(self, node):
        pass

Eckhart Arnold's avatar
Eckhart Arnold committed
591
592
593
    def on_structural(self, node):
        pass

594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
    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

618
    def on_LB(self, node):
619
620
        pass

621
    def on_BACKSLASH(self, node):
Eckhart Arnold's avatar
Eckhart Arnold committed
622
623
        pass

624
    def on_EOF(self, node):
Eckhart Arnold's avatar
Eckhart Arnold committed
625
626
        pass

627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653

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]) \
654
655
            if is_filename(source) < 0 else cname[:cname.find('.')] + '_out'    
        result = compile_source(source, get_preprocessor(), 
656
657
658
659
660
661
662
663
664
665
666
667
668
                                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
669
            print(result.as_xml() if isinstance(result, Node) else result)
670
671
    else:
        print("Usage: LaTeXCompiler.py [FILENAME]")