LaTeXCompiler.py 22.5 KB
Newer Older
1
2
3
4
5
6
7
8
9
10
11
#!/usr/bin/python

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


import os
import sys
Eckhart Arnold's avatar
Eckhart Arnold committed
12
13
from functools import partial

14
15
16
17
try:
    import regex as re
except ImportError:
    import re
Eckhart Arnold's avatar
Eckhart Arnold committed
18
19
20
from DHParser import logging, is_filename, Grammar, Compiler, Lookbehind, Alternative, Pop, \
    Required, Token, Synonym, \
    Optional, NegativeLookbehind, OneOrMore, RegExp, Series, RE, Capture, \
21
    ZeroOrMore, Forward, NegativeLookahead, mixin_comment, compile_source, \
Eckhart Arnold's avatar
Eckhart Arnold committed
22
23
    PreprocessorFunc, \
    Node, TransformationFunc, traverse, remove_children_if, is_anonymous, \
24
    reduce_single_child, replace_by_single_child, remove_whitespace, \
Eckhart Arnold's avatar
Eckhart Arnold committed
25
    flatten, is_empty, collapse, replace_content, remove_brackets, is_one_of, remove_first
26
27
28
29


#######################################################################
#
Eckhart Arnold's avatar
Eckhart Arnold committed
30
# PREPROCESSOR SECTION - Can be edited. Changes will be preserved.
31
32
33
#
#######################################################################

Eckhart Arnold's avatar
Eckhart Arnold committed
34
def LaTeXPreprocessor(text):
35
36
    return text

Eckhart Arnold's avatar
Eckhart Arnold committed
37
38
def get_preprocessor() -> PreprocessorFunc:
    return LaTeXPreprocessor
39
40
41
42
43
44
45
46
47
48
49


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

class LaTeXGrammar(Grammar):
    r"""Parser for a LaTeX source file, with this grammar:
    
50
    # LaTeX-Grammar for DHParser
51
52
53
54
55
56
    
    @ testing    = True
    @ whitespace = /[ \t]*(?:\n(?![ \t]*\n)[ \t]*)?/    # optional whitespace, including at most one linefeed
    @ comment    = /%.*(?:\n|$)/
    
    
57
58
59
    latexdoc       = preamble document
    preamble       = { command }+
    
Eckhart Arnold's avatar
Eckhart Arnold committed
60
61
62
63
64
    document       = [WSPC] "\begin{document}" [WSPC]
                     frontpages [WSPC]
                     (Chapters | Sections) [WSPC]
                     [Bibliography] [Index] [WSPC]
                     "\end{document}" [WSPC] §EOF
65
66
67
68
69
70
71
72
73
    frontpages     = sequence
    
    
    #######################################################################
    #
    # document structure
    #
    #######################################################################
    
Eckhart Arnold's avatar
Eckhart Arnold committed
74
75
    Chapters       = { Chapter [WSPC] }+
    Chapter        = "\Chapter" block [WSPC] { sequence | Sections }
76
    
Eckhart Arnold's avatar
Eckhart Arnold committed
77
78
    Sections       = { Section [WSPC] }+
    Section        = "\Section" block [WSPC] { sequence | SubSections }
79
    
Eckhart Arnold's avatar
Eckhart Arnold committed
80
81
    SubSections    = { SubSection [WSPC] }+
    SubSection     = "\SubSection" block [WSPC] { sequence | SubSubSections }
82
    
Eckhart Arnold's avatar
Eckhart Arnold committed
83
84
    SubSubSections = { SubSubSection [WSPC] }+
    SubSubSection  = "\SubSubSection" block [WSPC] { sequence | Paragraphs }
85
    
Eckhart Arnold's avatar
Eckhart Arnold committed
86
87
    Paragraphs     = { Paragraph [WSPC] }+
    Paragraph      = "\paragraph" block [WSPC] { sequence | SubParagraphs }
88
    
Eckhart Arnold's avatar
Eckhart Arnold committed
89
90
    SubParagraphs  = { SubParagraph [WSPC] }+
    SubParagraph   = "\subparagraph" block [WSPC] [ sequence ]
91
    
Eckhart Arnold's avatar
Eckhart Arnold committed
92
93
    Bibliography   = "\bibliography" block [WSPC]
    Index          = "\printindex" [WSPC]
94
95
96
97
98
99
100
101
102
103
    
    
    #######################################################################
    #
    # document content
    #
    #######################################################################
    
    
    #### block environments ####
104
    
Eckhart Arnold's avatar
Eckhart Arnold committed
105
    block_environment   = known_environment | generic_block
Eckhart Arnold's avatar
Eckhart Arnold committed
106
    known_environment   = itemize | enumerate | figure | tabular | quotation
107
                        | verbatim
Eckhart Arnold's avatar
Eckhart Arnold committed
108
    generic_block       = begin_generic_block sequence §end_generic_block
Eckhart Arnold's avatar
Eckhart Arnold committed
109
110
    begin_generic_block = -&LB begin_environment LFF
    end_generic_block   = -&LB  end_environment LFF
111
    
Eckhart Arnold's avatar
Eckhart Arnold committed
112
113
114
    itemize             = "\begin{itemize}" [WSPC] { item } §"\end{itemize}"
    enumerate           = "\begin{enumerate}" [WSPC] {item } §"\end{enumerate}"
    item                = "\item" [WSPC] sequence
115
    
Eckhart Arnold's avatar
Eckhart Arnold committed
116
117
118
119
120
121
    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|]+/~ §"}"
122
123
    
    
124
125
    #### paragraphs and sequences of paragraphs ####
    
Eckhart Arnold's avatar
Eckhart Arnold committed
126
    block_of_paragraphs = /{/~ sequence §/}/
127
    sequence            = { (paragraph | block_environment ) [PARSEP] }+
128
    paragraph           = { !blockcmd text_element //~ }+
Eckhart Arnold's avatar
Eckhart Arnold committed
129
    text_element        = text | block | inline_environment | command
130
131
132
    
    #### inline enivronments ####
    
133
    inline_environment  = known_inline_env | generic_inline_env
134
    known_inline_env    = inline_math
Eckhart Arnold's avatar
Eckhart Arnold committed
135
136
    generic_inline_env  = begin_inline_env //~ paragraph §end_inline_env
    begin_inline_env    = (-!LB begin_environment) | (begin_environment !LFF)
137
    end_inline_env      = end_environment
Eckhart Arnold's avatar
Eckhart Arnold committed
138
139
140
                          ## (-!LB end_environment)   | (end_environment !LFF)  # ambiguity with genric_block when EOF
    begin_environment   = /\\begin{/ §NAME §/}/
    end_environment     = /\\end{/ §::NAME §/}/
141
    
Eckhart Arnold's avatar
Eckhart Arnold committed
142
    inline_math         = /\$/ /[^$]*/ §/\$/
143
144
145
146
    
    
    #### commands ####
    
Eckhart Arnold's avatar
Eckhart Arnold committed
147
    command             = known_command | text_command | generic_command
Eckhart Arnold's avatar
Eckhart Arnold committed
148
    known_command       = footnote | includegraphics | caption
Eckhart Arnold's avatar
Eckhart Arnold committed
149
    text_command        = TXTCOMMAND | ESCAPED | BRACKETS
Eckhart Arnold's avatar
Eckhart Arnold committed
150
    generic_command     = !no_command CMDNAME [[ //~ config ] //~ block ]
151
152
    
    footnote            = "\footnote" block_of_paragraphs
Eckhart Arnold's avatar
Eckhart Arnold committed
153
    includegraphics     = "\includegraphics" [ config ] block
Eckhart Arnold's avatar
Eckhart Arnold committed
154
    caption             = "\caption" block
155
    
156
    
157
158
159
160
161
162
    #######################################################################
    #
    # low-level text and character sequences
    #
    #######################################################################
    
163
    
Eckhart Arnold's avatar
Eckhart Arnold committed
164
165
166
    config     = "[" text §"]"
    block      = /{/ //~ { !blockcmd text_element //~ } §/}/
    text       = TEXTCHUNK { //~ TEXTCHUNK }
167
    
Eckhart Arnold's avatar
Eckhart Arnold committed
168
169
170
171
172
    no_command = "\begin{" | "\end" | BACKSLASH structural
    blockcmd   = BACKSLASH ( ( "begin{" | "end{" )
                             ( "enumerate" | "itemize" | "figure" | "quote"
                             | "quotation" | "tabular") "}"
                           | structural | begin_generic_block | end_generic_block )
173
174
175
    
    structural = "subsection" | "section" | "chapter" | "subsubsection"
               | "paragraph" | "subparagraph" | "item"
176
177
178
179
180
181
182
    
    
    #######################################################################
    #
    # Primitives
    #
    #######################################################################
183
    
184
    
185
    CMDNAME    = /\\(?:(?!_)\w)+/~
Eckhart Arnold's avatar
Eckhart Arnold committed
186
187
188
189
    TXTCOMMAND = /\\text\w+/
    ESCAPED    = /\\[%$&_\/{}]/
    BRACKETS   = /[\[\]]/                       # left or right square bracket: [ ]
    
190
191
192
193
    NAME       = /\w+/~
    
    TEXTCHUNK  = /[^\\%$&\{\}\[\]\s\n]+/        # some piece of text excluding whitespace,
                                                # linefeed and special characters
Eckhart Arnold's avatar
Eckhart Arnold committed
194
    LF         = !GAP /[ \t]*\n[ \t]*/          # linefeed but not an empty line
Eckhart Arnold's avatar
Eckhart Arnold committed
195
    LFF        = //~ -&LB [ WSPC ]              # at least one linefeed
Eckhart Arnold's avatar
Eckhart Arnold committed
196
197
    WSPC       = { COMMENT__ | /\s+/ }+
    # WSPC       = { /\s+/~ | ~/\s+/ }+           # arbitrary horizontal or vertical whitespace
Eckhart Arnold's avatar
Eckhart Arnold committed
198
199
    PARSEP     = { GAP }+                       # paragraph separator
    GAP        = /[ \t]*(?:\n[ \t]*)+\n/~       # at least one empty line, i.e.
200
                                                # [whitespace] linefeed [whitespace] linefeed
201
202
    LB         = /\s*?\n|$/                     # backwards line break for Lookbehind-Operator
                                                # beginning of text marker '$' added for test code
Eckhart Arnold's avatar
Eckhart Arnold committed
203
204
205
    BACKSLASH  = /[\\]/
    
    EOF        = /(?!.)/                        # End-Of-File
206
    """
Eckhart Arnold's avatar
Eckhart Arnold committed
207
    begin_generic_block = Forward()
208
    block_environment = Forward()
209
    block_of_paragraphs = Forward()
Eckhart Arnold's avatar
Eckhart Arnold committed
210
    end_generic_block = Forward()
Eckhart Arnold's avatar
Eckhart Arnold committed
211
    paragraph = Forward()
212
    text_element = Forward()
Eckhart Arnold's avatar
Eckhart Arnold committed
213
    source_hash__ = "529c853d5829c3016605e4ee7ed69ddb"
214
215
216
217
218
    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
219
    EOF = RegExp('(?!.)')
Eckhart Arnold's avatar
Eckhart Arnold committed
220
221
    BACKSLASH = RegExp('[\\\\]')
    LB = RegExp('\\s*?\\n|$')
Eckhart Arnold's avatar
Eckhart Arnold committed
222
223
    GAP = RE('[ \\t]*(?:\\n[ \\t]*)+\\n')
    PARSEP = OneOrMore(GAP)
Eckhart Arnold's avatar
Eckhart Arnold committed
224
    WSPC = OneOrMore(Alternative(RegExp(COMMENT__), RegExp('\\s+')))
Eckhart Arnold's avatar
Eckhart Arnold committed
225
    LFF = Series(RE(''), Lookbehind(LB), Optional(WSPC))
Eckhart Arnold's avatar
Eckhart Arnold committed
226
    LF = Series(NegativeLookahead(GAP), RegExp('[ \\t]*\\n[ \\t]*'))
Eckhart Arnold's avatar
Eckhart Arnold committed
227
    TEXTCHUNK = RegExp('[^\\\\%$&\\{\\}\\[\\]\\s\\n]+')
228
    NAME = Capture(RE('\\w+'))
Eckhart Arnold's avatar
Eckhart Arnold committed
229
230
231
    BRACKETS = RegExp('[\\[\\]]')
    ESCAPED = RegExp('\\\\[%$&_/{}]')
    TXTCOMMAND = RegExp('\\\\text\\w+')
232
    CMDNAME = RE('\\\\(?:(?!_)\\w)+')
Eckhart Arnold's avatar
Eckhart Arnold committed
233
    structural = Alternative(Token("subsection"), Token("section"), Token("chapter"), Token("subsubsection"), Token("paragraph"), Token("subparagraph"), Token("item"))
Eckhart Arnold's avatar
Eckhart Arnold committed
234
235
    blockcmd = Series(BACKSLASH, Alternative(Series(Alternative(Token("begin{"), Token("end{")), Alternative(Token("enumerate"), Token("itemize"), Token("figure"), Token("quote"), Token("quotation"), Token("tabular")), Token("}")), structural, begin_generic_block, end_generic_block))
    no_command = Alternative(Token("\\begin{"), Token("\\end"), Series(BACKSLASH, structural))
Eckhart Arnold's avatar
Eckhart Arnold committed
236
237
238
    text = Series(TEXTCHUNK, ZeroOrMore(Series(RE(''), TEXTCHUNK)))
    block = Series(RegExp('{'), RE(''), ZeroOrMore(Series(NegativeLookahead(blockcmd), text_element, RE(''))), Required(RegExp('}')))
    config = Series(Token("["), text, Required(Token("]")))
Eckhart Arnold's avatar
Eckhart Arnold committed
239
    caption = Series(Token("\\caption"), block)
Eckhart Arnold's avatar
Eckhart Arnold committed
240
    includegraphics = Series(Token("\\includegraphics"), Optional(config), block)
241
    footnote = Series(Token("\\footnote"), block_of_paragraphs)
Eckhart Arnold's avatar
Eckhart Arnold committed
242
    generic_command = Series(NegativeLookahead(no_command), CMDNAME, Optional(Series(Optional(Series(RE(''), config)), RE(''), block)))
Eckhart Arnold's avatar
Eckhart Arnold committed
243
    text_command = Alternative(TXTCOMMAND, ESCAPED, BRACKETS)
Eckhart Arnold's avatar
Eckhart Arnold committed
244
    known_command = Alternative(footnote, includegraphics, caption)
Eckhart Arnold's avatar
Eckhart Arnold committed
245
246
247
248
    command = Alternative(known_command, text_command, generic_command)
    inline_math = Series(RegExp('\\$'), RegExp('[^$]*'), Required(RegExp('\\$')))
    end_environment = Series(RegExp('\\\\end{'), Required(Pop(NAME)), Required(RegExp('}')))
    begin_environment = Series(RegExp('\\\\begin{'), Required(NAME), Required(RegExp('}')))
249
    end_inline_env = Synonym(end_environment)
Eckhart Arnold's avatar
Eckhart Arnold committed
250
251
    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))
252
    known_inline_env = Synonym(inline_math)
253
    inline_environment = Alternative(known_inline_env, generic_inline_env)
Eckhart Arnold's avatar
Eckhart Arnold committed
254
    text_element.set(Alternative(text, block, inline_environment, command))
Eckhart Arnold's avatar
Eckhart Arnold committed
255
    paragraph.set(OneOrMore(Series(NegativeLookahead(blockcmd), text_element, RE(''))))
256
    sequence = OneOrMore(Series(Alternative(paragraph, block_environment), Optional(PARSEP)))
Eckhart Arnold's avatar
Eckhart Arnold committed
257
258
259
260
261
262
    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}")))
Eckhart Arnold's avatar
Eckhart Arnold committed
263
264
265
    item = Series(Token("\\item"), Optional(WSPC), sequence)
    enumerate = Series(Token("\\begin{enumerate}"), Optional(WSPC), ZeroOrMore(item), Required(Token("\\end{enumerate}")))
    itemize = Series(Token("\\begin{itemize}"), Optional(WSPC), ZeroOrMore(item), Required(Token("\\end{itemize}")))
Eckhart Arnold's avatar
Eckhart Arnold committed
266
267
    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
268
    generic_block = Series(begin_generic_block, sequence, Required(end_generic_block))
Eckhart Arnold's avatar
Eckhart Arnold committed
269
    known_environment = Alternative(itemize, enumerate, figure, tabular, quotation, verbatim)
Eckhart Arnold's avatar
Eckhart Arnold committed
270
    block_environment.set(Alternative(known_environment, generic_block))
Eckhart Arnold's avatar
Eckhart Arnold committed
271
272
273
274
275
276
277
278
279
280
281
282
283
284
    Index = Series(Token("\\printindex"), Optional(WSPC))
    Bibliography = Series(Token("\\bibliography"), block, Optional(WSPC))
    SubParagraph = Series(Token("\\subparagraph"), block, Optional(WSPC), Optional(sequence))
    SubParagraphs = OneOrMore(Series(SubParagraph, Optional(WSPC)))
    Paragraph = Series(Token("\\paragraph"), block, Optional(WSPC), ZeroOrMore(Alternative(sequence, SubParagraphs)))
    Paragraphs = OneOrMore(Series(Paragraph, Optional(WSPC)))
    SubSubSection = Series(Token("\\SubSubSection"), block, Optional(WSPC), ZeroOrMore(Alternative(sequence, Paragraphs)))
    SubSubSections = OneOrMore(Series(SubSubSection, Optional(WSPC)))
    SubSection = Series(Token("\\SubSection"), block, Optional(WSPC), ZeroOrMore(Alternative(sequence, SubSubSections)))
    SubSections = OneOrMore(Series(SubSection, Optional(WSPC)))
    Section = Series(Token("\\Section"), block, Optional(WSPC), ZeroOrMore(Alternative(sequence, SubSections)))
    Sections = OneOrMore(Series(Section, Optional(WSPC)))
    Chapter = Series(Token("\\Chapter"), block, Optional(WSPC), ZeroOrMore(Alternative(sequence, Sections)))
    Chapters = OneOrMore(Series(Chapter, Optional(WSPC)))
285
    frontpages = Synonym(sequence)
Eckhart Arnold's avatar
Eckhart Arnold committed
286
    document = Series(Optional(WSPC), Token("\\begin{document}"), Optional(WSPC), frontpages, Optional(WSPC), Alternative(Chapters, Sections), Optional(WSPC), Optional(Bibliography), Optional(Index), Optional(WSPC), Token("\\end{document}"), Optional(WSPC), Required(EOF))
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
312
313
    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:
314
315
316
        node.result = '\n'
        # node.result = ('  ' if (n >= c) or (n < 0) else '\n')+ s[c:].rstrip(' \t')
        # node.parser = MockParser('COMMENT', '')
317
318
319
320
321
322
    elif s.find('\n') >= 0:
        node.result = '\n'
    else:
        node.result = ' '


323
324
325
326
def watch(node):
    print(node.as_sxpr())


327
328
LaTeX_AST_transformation_table = {
    # AST Transformations for the LaTeX-grammar
Eckhart Arnold's avatar
Eckhart Arnold committed
329
330
    "+": remove_children_if(lambda node: is_empty(node) or is_one_of(node, {'PARSEP'})),
    # remove_empty,
331
332
333
    "latexdoc": [],
    "preamble": [],
    "document": [],
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
    "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": [],
352
    "begin_generic_block, end_generic_block": replace_by_single_child,
353
354
355
356
357
358
359
360
361
362
363
364
365
366
    "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": [],
367
    "begin_inline_env, end_inline_env": [replace_by_single_child],
368
369
370
371
    "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
372
    "text_command": [],
373
374
375
376
377
    "generic_command": [flatten],
    "footnote": [],
    "includegraphics": [],
    "caption": [],
    "config": [remove_brackets],
Eckhart Arnold's avatar
Eckhart Arnold committed
378
    "block": [remove_brackets, flatten],
379
380
    "text": collapse,
    "no_command, blockcmd": [],
381
382
    "structural": [],
    "CMDNAME": [remove_whitespace, reduce_single_child(is_anonymous)],
Eckhart Arnold's avatar
Eckhart Arnold committed
383
    "TXTCOMMAND": [remove_whitespace, reduce_single_child(is_anonymous)],
384
385
    "NAME": [reduce_single_child, remove_whitespace, reduce_single_child],
    "ESCAPED": [replace_content(lambda node: str(node)[1:])],
386
387
    "BRACKETS": [],
    "TEXTCHUNK": [],
388
389
    "LF": [],
    "PARSEP": replace_content(lambda node: '\n\n'),
Eckhart Arnold's avatar
Eckhart Arnold committed
390
    "GAP": [],
391
392
    "LB": [],
    "BACKSLASH": [],
393
    "EOF": [],
394
395
396
397
    ":Token": [],
    ":RE": replace_by_single_child,
    ":Whitespace": streamline_whitespace,
    "*": replace_by_single_child
398
399
400
}

LaTeXTransform = partial(traverse, processing_table=LaTeX_AST_transformation_table)
401

402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421

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
422
        return node
423
424
425
426
427
428
429

    def on_preamble(self, node):
        pass

    def on_document(self, node):
        pass

Eckhart Arnold's avatar
Eckhart Arnold committed
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
506
507
508
    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):
509
510
        pass

Eckhart Arnold's avatar
Eckhart Arnold committed
511
512
513
514
    def on_table_config(self, node):
        pass

    def on_block_of_paragraphs(self, node):
515
516
517
518
519
520
521
522
        pass

    def on_sequence(self, node):
        pass

    def on_paragraph(self, node):
        pass

523
    def on_text_element(self, node):
Eckhart Arnold's avatar
Eckhart Arnold committed
524
525
526
527
528
529
        pass

    def on_inline_environment(self, node):
        pass

    def on_known_inline_env(self, node):
530
531
        pass

Eckhart Arnold's avatar
Eckhart Arnold committed
532
    def on_generic_inline_env(self, node):
533
534
        pass

Eckhart Arnold's avatar
Eckhart Arnold committed
535
536
537
538
539
540
541
542
543
544
    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):
545
546
547
548
549
        pass

    def on_command(self, node):
        pass

Eckhart Arnold's avatar
Eckhart Arnold committed
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
    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

565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
    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

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

583
584
585
    def on_blockcmd(self, node):
        pass

Eckhart Arnold's avatar
Eckhart Arnold committed
586
587
588
    def on_structural(self, node):
        pass

589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
    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

613
    def on_LB(self, node):
614
615
        pass

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

619
    def on_EOF(self, node):
Eckhart Arnold's avatar
Eckhart Arnold committed
620
621
        pass

622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648

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]) \
649
650
            if is_filename(source) < 0 else cname[:cname.find('.')] + '_out'    
        result = compile_source(source, get_preprocessor(), 
651
652
653
654
655
656
657
658
659
660
661
662
663
                                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
664
            print(result.as_xml() if isinstance(result, Node) else result)
665
666
    else:
        print("Usage: LaTeXCompiler.py [FILENAME]")