Currently job artifacts in CI/CD pipelines on LRZ GitLab never expire. Starting from Wed 26.1.2022 the default expiration time will be 30 days (GitLab default). Currently existing artifacts in already completed jobs will not be affected by the change. The latest artifacts for all jobs in the latest successful pipelines will be kept. More information: https://gitlab.lrz.de/help/user/admin_area/settings/continuous_integration.html#default-artifacts-expiration

LaTeXCompiler.py 24.4 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
from DHParser import logging, is_filename, Grammar, Compiler, Lookbehind, Alternative, Pop, \
    Required, Token, Synonym, \
20
    Option, NegativeLookbehind, OneOrMore, RegExp, Series, RE, Capture, \
21
    ZeroOrMore, Forward, NegativeLookahead, mixin_comment, compile_source, \
22
    PreprocessorFunc, TransformationDict, \
Eckhart Arnold's avatar
Eckhart Arnold committed
23
    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
    
    @ testing    = True
    @ whitespace = /[ \t]*(?:\n(?![ \t]*\n)[ \t]*)?/    # optional whitespace, including at most one linefeed
Eckhart Arnold's avatar
Eckhart Arnold committed
54
    @ comment    = /%.*/
55
56
    
    
57
    latexdoc       = preamble document
58
    preamble       = { [WSPC] command }+
59
    
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
    Chapters       = { Chapter [WSPC] }+
Eckhart Arnold's avatar
Eckhart Arnold committed
75
    Chapter        = "\chapter" block [WSPC] { sequence | Sections }
76
    
Eckhart Arnold's avatar
Eckhart Arnold committed
77
    Sections       = { Section [WSPC] }+
Eckhart Arnold's avatar
Eckhart Arnold committed
78
    Section        = "\section" block [WSPC] { sequence | SubSections }
79
    
Eckhart Arnold's avatar
Eckhart Arnold committed
80
    SubSections    = { SubSection [WSPC] }+
Eckhart Arnold's avatar
Eckhart Arnold committed
81
    SubSection     = "\subsection" block [WSPC] { sequence | SubSubSections }
82
    
Eckhart Arnold's avatar
Eckhart Arnold committed
83
    SubSubSections = { SubSubSection [WSPC] }+
Eckhart Arnold's avatar
Eckhart Arnold committed
84
    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
    figure              = "\begin{figure}" sequence §"\end{figure}"
    quotation           = ("\begin{quotation}" sequence §"\end{quotation}")
                        | ("\begin{quote}" sequence §"\end{quote}")
    verbatim            = "\begin{verbatim}" sequence §"\end{verbatim}"
Eckhart Arnold's avatar
Eckhart Arnold committed
120
    tabular             = "\begin{tabular}" tabular_config { tabular_row } §"\end{tabular}"
121
122
    tabular_row         = (multicolumn | tabular_cell) { "&" (multicolumn | tabular_cell) }
                          "\\" ( hline | { cline } )
123
    tabular_cell        = { line_element //~ }
Eckhart Arnold's avatar
Eckhart Arnold committed
124
    tabular_config      = "{" /[lcr|]+/~ §"}"
125
    
Eckhart Arnold's avatar
Eckhart Arnold committed
126
    
127
128
    #### paragraphs and sequences of paragraphs ####
    
129
    block_of_paragraphs = "{" [sequence] §"}"
130
    sequence            = { (paragraph | block_environment ) [PARSEP] }+
131
132
133
    paragraph           = { !blockcmd text_element //~ }+
    text_element        = line_element | LINEFEED
    line_element        = text | block | inline_environment | command
134
    
Eckhart Arnold's avatar
Eckhart Arnold committed
135
    
136
137
    #### inline enivronments ####
    
138
    inline_environment  = known_inline_env | generic_inline_env
139
    known_inline_env    = inline_math
Eckhart Arnold's avatar
Eckhart Arnold committed
140
141
    generic_inline_env  = begin_inline_env //~ paragraph §end_inline_env
    begin_inline_env    = (-!LB begin_environment) | (begin_environment !LFF)
142
    end_inline_env      = end_environment
Eckhart Arnold's avatar
Eckhart Arnold committed
143
144
145
                          ## (-!LB end_environment)   | (end_environment !LFF)  # ambiguity with genric_block when EOF
    begin_environment   = /\\begin{/ §NAME §/}/
    end_environment     = /\\end{/ §::NAME §/}/
146
    
Eckhart Arnold's avatar
Eckhart Arnold committed
147
    inline_math         = /\$/ /[^$]*/ §/\$/
148
    
Eckhart Arnold's avatar
Eckhart Arnold committed
149
    
150
151
    #### commands ####
    
Eckhart Arnold's avatar
Eckhart Arnold committed
152
    command             = known_command | text_command | generic_command
Eckhart Arnold's avatar
Eckhart Arnold committed
153
    known_command       = footnote | includegraphics | caption | multicolumn | hline | cline
154
    text_command        = TXTCOMMAND | ESCAPED | BRACKETS
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
    includegraphics     = "\includegraphics" [ config ] block
Eckhart Arnold's avatar
Eckhart Arnold committed
159
    caption             = "\caption" block
Eckhart Arnold's avatar
Eckhart Arnold committed
160
161
162
163
    multicolumn         = "\multicolumn" "{" INTEGER "}" tabular_config block_of_paragraphs
    hline               = "\hline"
    cline               = "\cline{" INTEGER "-" INTEGER "}"
    
164
    
165
166
167
168
169
170
    #######################################################################
    #
    # low-level text and character sequences
    #
    #######################################################################
    
171
    
172
    config     = "[" cfg_text §"]"
Eckhart Arnold's avatar
Eckhart Arnold committed
173
    cfg_text   = { ([//~] text) | CMDNAME | SPECIAL }
Eckhart Arnold's avatar
Eckhart Arnold committed
174
175
    block      = /{/ //~ { !blockcmd text_element //~ } §/}/
    text       = TEXTCHUNK { //~ TEXTCHUNK }
176
    
Eckhart Arnold's avatar
Eckhart Arnold committed
177
178
179
180
181
    no_command = "\begin{" | "\end" | BACKSLASH structural
    blockcmd   = BACKSLASH ( ( "begin{" | "end{" )
                             ( "enumerate" | "itemize" | "figure" | "quote"
                             | "quotation" | "tabular") "}"
                           | structural | begin_generic_block | end_generic_block )
182
183
184
    
    structural = "subsection" | "section" | "chapter" | "subsubsection"
               | "paragraph" | "subparagraph" | "item"
185
186
187
188
189
190
191
    
    
    #######################################################################
    #
    # Primitives
    #
    #######################################################################
192
    
193
    
194
    CMDNAME    = /\\(?:(?!_)\w)+/~
Eckhart Arnold's avatar
Eckhart Arnold committed
195
196
    TXTCOMMAND = /\\text\w+/
    ESCAPED    = /\\[%$&_\/{}]/
Eckhart Arnold's avatar
Eckhart Arnold committed
197
    SPECIAL    = /[$&_\\\\\/]/
Eckhart Arnold's avatar
Eckhart Arnold committed
198
    BRACKETS   = /[\[\]]/                       # left or right square bracket: [ ]
199
    LINEFEED   = /[\\][\\]/
Eckhart Arnold's avatar
Eckhart Arnold committed
200
    
201
    NAME       = /\w+/~
202
    INTEGER    = /\d+/~
203
204
205
    
    TEXTCHUNK  = /[^\\%$&\{\}\[\]\s\n]+/        # some piece of text excluding whitespace,
                                                # linefeed and special characters
Eckhart Arnold's avatar
Eckhart Arnold committed
206
207
208
    LF         = NEW_LINE { COMMENT__ WHITESPACE__ }   # linefeed but not an empty line
    LFF        = NEW_LINE [ WSPC ]              # at least one linefeed
    PARSEP     = { WHITESPACE__ COMMENT__ } GAP [WSPC] # paragraph separator
209
    WSPC       = { COMMENT__ | /\s+/ }+         # arbitrary horizontal or vertical whitespace
Eckhart Arnold's avatar
Eckhart Arnold committed
210
    GAP        = /[ \t]*(?:\n[ \t]*)+\n/~       # at least one empty line, i.e.
211
                                                # [whitespace] linefeed [whitespace] linefeed
Eckhart Arnold's avatar
Eckhart Arnold committed
212
    NEW_LINE   = /[ \t]*/ [COMMENT__] /\n/
213
214
    LB         = /\s*?\n|$/                     # backwards line break for Lookbehind-Operator
                                                # beginning of text marker '$' added for test code
Eckhart Arnold's avatar
Eckhart Arnold committed
215
216
217
    BACKSLASH  = /[\\]/
    
    EOF        = /(?!.)/                        # End-Of-File
218
    """
Eckhart Arnold's avatar
Eckhart Arnold committed
219
    begin_generic_block = Forward()
220
    block_environment = Forward()
221
    block_of_paragraphs = Forward()
Eckhart Arnold's avatar
Eckhart Arnold committed
222
    end_generic_block = Forward()
Eckhart Arnold's avatar
Eckhart Arnold committed
223
    paragraph = Forward()
224
    tabular_config = Forward()
225
    text_element = Forward()
Eckhart Arnold's avatar
Eckhart Arnold committed
226
    source_hash__ = "57dd004091e87ff603b51f0a47857cf4"
227
    parser_initialization__ = "upon instantiation"
Eckhart Arnold's avatar
Eckhart Arnold committed
228
229
230
    COMMENT__ = r'%.*'
    WHITESPACE__ = r'[ \t]*(?:\n(?![ \t]*\n)[ \t]*)?'
    WSP__ = mixin_comment(whitespace=WHITESPACE__, comment=COMMENT__)
231
232
    wspL__ = ''
    wspR__ = WSP__
Eckhart Arnold's avatar
Eckhart Arnold committed
233
    EOF = RegExp('(?!.)')
Eckhart Arnold's avatar
Eckhart Arnold committed
234
235
    BACKSLASH = RegExp('[\\\\]')
    LB = RegExp('\\s*?\\n|$')
236
    NEW_LINE = Series(RegExp('[ \\t]*'), Option(RegExp(COMMENT__)), RegExp('\\n'))
Eckhart Arnold's avatar
Eckhart Arnold committed
237
    GAP = RE('[ \\t]*(?:\\n[ \\t]*)+\\n')
Eckhart Arnold's avatar
Eckhart Arnold committed
238
    WSPC = OneOrMore(Alternative(RegExp(COMMENT__), RegExp('\\s+')))
239
240
    PARSEP = Series(ZeroOrMore(Series(RegExp(WHITESPACE__), RegExp(COMMENT__))), GAP, Option(WSPC))
    LFF = Series(NEW_LINE, Option(WSPC))
Eckhart Arnold's avatar
Eckhart Arnold committed
241
    LF = Series(NEW_LINE, ZeroOrMore(Series(RegExp(COMMENT__), RegExp(WHITESPACE__))))
Eckhart Arnold's avatar
Eckhart Arnold committed
242
    TEXTCHUNK = RegExp('[^\\\\%$&\\{\\}\\[\\]\\s\\n]+')
243
    INTEGER = RE('\\d+')
244
    NAME = Capture(RE('\\w+'))
245
    LINEFEED = RegExp('[\\\\][\\\\]')
Eckhart Arnold's avatar
Eckhart Arnold committed
246
    BRACKETS = RegExp('[\\[\\]]')
Eckhart Arnold's avatar
Eckhart Arnold committed
247
    SPECIAL = RegExp('[$&_\\\\\\\\/]')
Eckhart Arnold's avatar
Eckhart Arnold committed
248
249
    ESCAPED = RegExp('\\\\[%$&_/{}]')
    TXTCOMMAND = RegExp('\\\\text\\w+')
250
    CMDNAME = RE('\\\\(?:(?!_)\\w)+')
Eckhart Arnold's avatar
Eckhart Arnold committed
251
    structural = Alternative(Token("subsection"), Token("section"), Token("chapter"), Token("subsubsection"), Token("paragraph"), Token("subparagraph"), Token("item"))
Eckhart Arnold's avatar
Eckhart Arnold committed
252
253
    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
254
255
    text = Series(TEXTCHUNK, ZeroOrMore(Series(RE(''), TEXTCHUNK)))
    block = Series(RegExp('{'), RE(''), ZeroOrMore(Series(NegativeLookahead(blockcmd), text_element, RE(''))), Required(RegExp('}')))
256
    cfg_text = ZeroOrMore(Alternative(Series(Option(RE('')), text), CMDNAME, SPECIAL))
257
    config = Series(Token("["), cfg_text, Required(Token("]")))
Eckhart Arnold's avatar
Eckhart Arnold committed
258
259
    cline = Series(Token("\\cline{"), INTEGER, Token("-"), INTEGER, Token("}"))
    hline = Token("\\hline")
260
    multicolumn = Series(Token("\\multicolumn"), Token("{"), INTEGER, Token("}"), tabular_config, block_of_paragraphs)
Eckhart Arnold's avatar
Eckhart Arnold committed
261
    caption = Series(Token("\\caption"), block)
262
    includegraphics = Series(Token("\\includegraphics"), Option(config), block)
263
    footnote = Series(Token("\\footnote"), block_of_paragraphs)
264
    generic_command = Series(NegativeLookahead(no_command), CMDNAME, Option(Series(Option(Series(RE(''), config)), RE(''), block)))
265
    text_command = Alternative(TXTCOMMAND, ESCAPED, BRACKETS)
Eckhart Arnold's avatar
Eckhart Arnold committed
266
    known_command = Alternative(footnote, includegraphics, caption, multicolumn, hline, cline)
Eckhart Arnold's avatar
Eckhart Arnold committed
267
268
269
270
    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('}')))
271
    end_inline_env = Synonym(end_environment)
Eckhart Arnold's avatar
Eckhart Arnold committed
272
273
    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))
274
    known_inline_env = Synonym(inline_math)
275
    inline_environment = Alternative(known_inline_env, generic_inline_env)
276
277
278
    line_element = Alternative(text, block, inline_environment, command)
    text_element.set(Alternative(line_element, LINEFEED))
    paragraph.set(OneOrMore(Series(NegativeLookahead(blockcmd), text_element, RE(''))))
279
280
    sequence = OneOrMore(Series(Alternative(paragraph, block_environment), Option(PARSEP)))
    block_of_paragraphs.set(Series(Token("{"), Option(sequence), Required(Token("}"))))
281
    tabular_config.set(Series(Token("{"), RE('[lcr|]+'), Required(Token("}"))))
282
    tabular_cell = ZeroOrMore(Series(line_element, RE('')))
di68kap's avatar
di68kap committed
283
    tabular_row = Series(Alternative(multicolumn, tabular_cell), ZeroOrMore(Series(Token("&"), Alternative(multicolumn, tabular_cell))), Token("\\\\"), Alternative(hline, ZeroOrMore(cline)))
Eckhart Arnold's avatar
Eckhart Arnold committed
284
    tabular = Series(Token("\\begin{tabular}"), tabular_config, ZeroOrMore(tabular_row), Required(Token("\\end{tabular}")))
Eckhart Arnold's avatar
Eckhart Arnold committed
285
286
287
    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}")))
288
289
290
    item = Series(Token("\\item"), Option(WSPC), sequence)
    enumerate = Series(Token("\\begin{enumerate}"), Option(WSPC), ZeroOrMore(item), Required(Token("\\end{enumerate}")))
    itemize = Series(Token("\\begin{itemize}"), Option(WSPC), ZeroOrMore(item), Required(Token("\\end{itemize}")))
Eckhart Arnold's avatar
Eckhart Arnold committed
291
292
    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
293
    generic_block = Series(begin_generic_block, sequence, Required(end_generic_block))
Eckhart Arnold's avatar
Eckhart Arnold committed
294
    known_environment = Alternative(itemize, enumerate, figure, tabular, quotation, verbatim)
Eckhart Arnold's avatar
Eckhart Arnold committed
295
    block_environment.set(Alternative(known_environment, generic_block))
296
297
298
299
300
301
302
303
304
305
306
307
308
309
    Index = Series(Token("\\printindex"), Option(WSPC))
    Bibliography = Series(Token("\\bibliography"), block, Option(WSPC))
    SubParagraph = Series(Token("\\subparagraph"), block, Option(WSPC), Option(sequence))
    SubParagraphs = OneOrMore(Series(SubParagraph, Option(WSPC)))
    Paragraph = Series(Token("\\paragraph"), block, Option(WSPC), ZeroOrMore(Alternative(sequence, SubParagraphs)))
    Paragraphs = OneOrMore(Series(Paragraph, Option(WSPC)))
    SubSubSection = Series(Token("\\subsubsection"), block, Option(WSPC), ZeroOrMore(Alternative(sequence, Paragraphs)))
    SubSubSections = OneOrMore(Series(SubSubSection, Option(WSPC)))
    SubSection = Series(Token("\\subsection"), block, Option(WSPC), ZeroOrMore(Alternative(sequence, SubSubSections)))
    SubSections = OneOrMore(Series(SubSection, Option(WSPC)))
    Section = Series(Token("\\section"), block, Option(WSPC), ZeroOrMore(Alternative(sequence, SubSections)))
    Sections = OneOrMore(Series(Section, Option(WSPC)))
    Chapter = Series(Token("\\chapter"), block, Option(WSPC), ZeroOrMore(Alternative(sequence, Sections)))
    Chapters = OneOrMore(Series(Chapter, Option(WSPC)))
310
    frontpages = Synonym(sequence)
311
312
    document = Series(Option(WSPC), Token("\\begin{document}"), Option(WSPC), frontpages, Option(WSPC), Alternative(Chapters, Sections), Option(WSPC), Option(Bibliography), Option(Index), Option(WSPC), Token("\\end{document}"), Option(WSPC), Required(EOF))
    preamble = OneOrMore(Series(Option(WSPC), command))
313
314
315
316
317
318
319
320
321
    latexdoc = Series(preamble, document)
    root__ = latexdoc
    
def get_grammar() -> LaTeXGrammar:
    global thread_local_LaTeX_grammar_singleton
    try:
        grammar = thread_local_LaTeX_grammar_singleton
    except NameError:
        thread_local_LaTeX_grammar_singleton = LaTeXGrammar()
Eckhart Arnold's avatar
Eckhart Arnold committed
322
323
        grammar = thread_local_LaTeX_grammar_singleton
    return grammar
324
325
326
327
328
329
330
331
332


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


333
334
def streamline_whitespace(context):
    node = context[-1]
335
336
337
338
339
    assert node.tag_name in ['WSPC', ':Whitespace']
    s = str(node)
    c = s.find('%')
    n = s.find('\n')
    if c >= 0:
340
341
342
        node.result = '\n'
        # node.result = ('  ' if (n >= c) or (n < 0) else '\n')+ s[c:].rstrip(' \t')
        # node.parser = MockParser('COMMENT', '')
343
344
345
346
347
348
    elif s.find('\n') >= 0:
        node.result = '\n'
    else:
        node.result = ' '


349
350
351
352
def watch(node):
    print(node.as_sxpr())


353
354
LaTeX_AST_transformation_table = {
    # AST Transformations for the LaTeX-grammar
Eckhart Arnold's avatar
Eckhart Arnold committed
355
356
    "+": remove_children_if(lambda node: is_empty(node) or is_one_of(node, {'PARSEP'})),
    # remove_empty,
357
358
359
    "latexdoc": [],
    "preamble": [],
    "document": [],
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
    "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": [],
378
    "begin_generic_block, end_generic_block": replace_by_single_child,
379
380
381
382
383
384
385
386
387
388
389
390
391
392
    "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": [],
393
    "begin_inline_env, end_inline_env": [replace_by_single_child],
394
395
396
397
    "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
398
    "text_command": [],
399
400
401
402
403
    "generic_command": [flatten],
    "footnote": [],
    "includegraphics": [],
    "caption": [],
    "config": [remove_brackets],
Eckhart Arnold's avatar
Eckhart Arnold committed
404
    "block": [remove_brackets, flatten],
405
406
    "text": collapse,
    "no_command, blockcmd": [],
407
408
    "structural": [],
    "CMDNAME": [remove_whitespace, reduce_single_child(is_anonymous)],
Eckhart Arnold's avatar
Eckhart Arnold committed
409
    "TXTCOMMAND": [remove_whitespace, reduce_single_child(is_anonymous)],
410
411
    "NAME": [reduce_single_child, remove_whitespace, reduce_single_child],
    "ESCAPED": [replace_content(lambda node: str(node)[1:])],
412
413
    "BRACKETS": [],
    "TEXTCHUNK": [],
414
415
    "LF": [],
    "PARSEP": replace_content(lambda node: '\n\n'),
Eckhart Arnold's avatar
Eckhart Arnold committed
416
    "GAP": [],
417
418
    "LB": [],
    "BACKSLASH": [],
419
    "EOF": [],
420
421
422
423
    ":Token": [],
    ":RE": replace_by_single_child,
    ":Whitespace": streamline_whitespace,
    "*": replace_by_single_child
424
425
}

426

427
428
def LaTeXTransform() -> TransformationDict:
    return partial(traverse, processing_table=LaTeX_AST_transformation_table.copy())
429
430

def get_transformer() -> TransformationFunc:
431
432
433
434
435
436
437
438
    global thread_local_LaTeX_transformer_singleton
    try:
        transformer = thread_local_LaTeX_transformer_singleton
    except NameError:
        thread_local_LaTeX_transformer_singleton = LaTeXTransform()
        transformer = thread_local_LaTeX_transformer_singleton
    return transformer

439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455


#######################################################################
#
# 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
456
        return node
457
458
459
460
461
462
463

    def on_preamble(self, node):
        pass

    def on_document(self, node):
        pass

Eckhart Arnold's avatar
Eckhart Arnold committed
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
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
    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):
543
544
        pass

Eckhart Arnold's avatar
Eckhart Arnold committed
545
546
547
548
    def on_table_config(self, node):
        pass

    def on_block_of_paragraphs(self, node):
549
550
551
552
553
554
555
556
        pass

    def on_sequence(self, node):
        pass

    def on_paragraph(self, node):
        pass

557
    def on_text_element(self, node):
Eckhart Arnold's avatar
Eckhart Arnold committed
558
559
560
561
562
563
        pass

    def on_inline_environment(self, node):
        pass

    def on_known_inline_env(self, node):
564
565
        pass

Eckhart Arnold's avatar
Eckhart Arnold committed
566
    def on_generic_inline_env(self, node):
567
568
        pass

Eckhart Arnold's avatar
Eckhart Arnold committed
569
570
571
572
573
574
575
576
577
578
    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):
579
580
581
582
583
        pass

    def on_command(self, node):
        pass

Eckhart Arnold's avatar
Eckhart Arnold committed
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
    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

599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
    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

614
615
616
    def on_no_command(self, node):
        pass

617
618
619
    def on_blockcmd(self, node):
        pass

Eckhart Arnold's avatar
Eckhart Arnold committed
620
621
622
    def on_structural(self, node):
        pass

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

647
    def on_LB(self, node):
648
649
        pass

650
    def on_BACKSLASH(self, node):
Eckhart Arnold's avatar
Eckhart Arnold committed
651
652
        pass

653
    def on_EOF(self, node):
Eckhart Arnold's avatar
Eckhart Arnold committed
654
655
        pass

656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682

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]) \
683
684
            if is_filename(source) < 0 else cname[:cname.find('.')] + '_out'    
        result = compile_source(source, get_preprocessor(), 
685
686
687
688
689
690
691
692
693
694
695
696
697
                                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
698
            print(result.as_xml() if isinstance(result, Node) else result)
699
700
    else:
        print("Usage: LaTeXCompiler.py [FILENAME]")