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
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, \
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
54
55
56
    
    @ testing    = True
    @ whitespace = /[ \t]*(?:\n(?![ \t]*\n)[ \t]*)?/    # optional whitespace, including at most one linefeed
    @ comment    = /%.*(?:\n|$)/
    
    
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
123
    tabular_row         = (multicolumn | tabular_cell) { "&" (multicolumn | tabular_cell) }
                          "\\" ( hline | { cline } )
    tabular_cell        = { text_element //~ }
Eckhart Arnold's avatar
Eckhart Arnold committed
124
    tabular_config      = "{" /[lcr|]+/~ §"}"
125
    
126
127
    #### paragraphs and sequences of paragraphs ####
    
128
    block_of_paragraphs = "{" [sequence] §"}"
129
    sequence            = { (paragraph | block_environment ) [PARSEP] }+
130
    paragraph           = { !blockcmd (text_element | LINEFEED) //~ }+
Eckhart Arnold's avatar
Eckhart Arnold committed
131
    text_element        = text | block | inline_environment | command
132
133
134
    
    #### inline enivronments ####
    
135
    inline_environment  = known_inline_env | generic_inline_env
136
    known_inline_env    = inline_math
Eckhart Arnold's avatar
Eckhart Arnold committed
137
138
    generic_inline_env  = begin_inline_env //~ paragraph §end_inline_env
    begin_inline_env    = (-!LB begin_environment) | (begin_environment !LFF)
139
    end_inline_env      = end_environment
Eckhart Arnold's avatar
Eckhart Arnold committed
140
141
142
                          ## (-!LB end_environment)   | (end_environment !LFF)  # ambiguity with genric_block when EOF
    begin_environment   = /\\begin{/ §NAME §/}/
    end_environment     = /\\end{/ §::NAME §/}/
143
    
Eckhart Arnold's avatar
Eckhart Arnold committed
144
    inline_math         = /\$/ /[^$]*/ §/\$/
145
146
147
    
    #### commands ####
    
Eckhart Arnold's avatar
Eckhart Arnold committed
148
    command             = known_command | text_command | generic_command
Eckhart Arnold's avatar
Eckhart Arnold committed
149
    known_command       = footnote | includegraphics | caption | multicolumn | hline | cline
150
    text_command        = TXTCOMMAND | ESCAPED | BRACKETS
Eckhart Arnold's avatar
Eckhart Arnold committed
151
    generic_command     = !no_command CMDNAME [[ //~ config ] //~ block ]
152
153
    
    footnote            = "\footnote" block_of_paragraphs
Eckhart Arnold's avatar
Eckhart Arnold committed
154
    includegraphics     = "\includegraphics" [ config ] block
Eckhart Arnold's avatar
Eckhart Arnold committed
155
    caption             = "\caption" block
Eckhart Arnold's avatar
Eckhart Arnold committed
156
157
158
159
    multicolumn         = "\multicolumn" "{" INTEGER "}" tabular_config block_of_paragraphs
    hline               = "\hline"
    cline               = "\cline{" INTEGER "-" INTEGER "}"
    
160
    
161
162
163
164
165
166
    #######################################################################
    #
    # low-level text and character sequences
    #
    #######################################################################
    
167
    
168
    config     = "[" cfg_text §"]"
Eckhart Arnold's avatar
Eckhart Arnold committed
169
    cfg_text   = { ([//~] text) | CMDNAME | SPECIAL }
Eckhart Arnold's avatar
Eckhart Arnold committed
170
171
    block      = /{/ //~ { !blockcmd text_element //~ } §/}/
    text       = TEXTCHUNK { //~ TEXTCHUNK }
172
    
Eckhart Arnold's avatar
Eckhart Arnold committed
173
174
175
176
177
    no_command = "\begin{" | "\end" | BACKSLASH structural
    blockcmd   = BACKSLASH ( ( "begin{" | "end{" )
                             ( "enumerate" | "itemize" | "figure" | "quote"
                             | "quotation" | "tabular") "}"
                           | structural | begin_generic_block | end_generic_block )
178
179
180
    
    structural = "subsection" | "section" | "chapter" | "subsubsection"
               | "paragraph" | "subparagraph" | "item"
181
182
183
184
185
186
187
    
    
    #######################################################################
    #
    # Primitives
    #
    #######################################################################
188
    
189
    
190
    CMDNAME    = /\\(?:(?!_)\w)+/~
Eckhart Arnold's avatar
Eckhart Arnold committed
191
192
    TXTCOMMAND = /\\text\w+/
    ESCAPED    = /\\[%$&_\/{}]/
Eckhart Arnold's avatar
Eckhart Arnold committed
193
    SPECIAL    = /[$&_\\\\\/]/
Eckhart Arnold's avatar
Eckhart Arnold committed
194
    BRACKETS   = /[\[\]]/                       # left or right square bracket: [ ]
195
    LINEFEED   = /[\\][\\]/
Eckhart Arnold's avatar
Eckhart Arnold committed
196
    
197
    NAME       = /\w+/~
198
    INTEGER    = /\d+/~
199
200
201
    
    TEXTCHUNK  = /[^\\%$&\{\}\[\]\s\n]+/        # some piece of text excluding whitespace,
                                                # linefeed and special characters
Eckhart Arnold's avatar
Eckhart Arnold committed
202
    LF         = !GAP /[ \t]*\n[ \t]*/          # linefeed but not an empty line
203
204
    LFF        = ~/\n?/ -&LB [ WSPC ]              # at least one linefeed
    WSPC       = { COMMENT__ | /\s+/ }+         # arbitrary horizontal or vertical whitespace
Eckhart Arnold's avatar
Eckhart Arnold committed
205
    # WSPC       = { /\s+/~ | ~/\s+/ }+           # arbitrary horizontal or vertical whitespace
Eckhart Arnold's avatar
Eckhart Arnold committed
206
207
    PARSEP     = { GAP }+                       # paragraph separator
    GAP        = /[ \t]*(?:\n[ \t]*)+\n/~       # at least one empty line, i.e.
208
                                                # [whitespace] linefeed [whitespace] linefeed
209
210
    LB         = /\s*?\n|$/                     # backwards line break for Lookbehind-Operator
                                                # beginning of text marker '$' added for test code
Eckhart Arnold's avatar
Eckhart Arnold committed
211
212
213
    BACKSLASH  = /[\\]/
    
    EOF        = /(?!.)/                        # End-Of-File
214
    """
Eckhart Arnold's avatar
Eckhart Arnold committed
215
    begin_generic_block = Forward()
216
    block_environment = Forward()
217
    block_of_paragraphs = Forward()
Eckhart Arnold's avatar
Eckhart Arnold committed
218
    end_generic_block = Forward()
Eckhart Arnold's avatar
Eckhart Arnold committed
219
    paragraph = Forward()
220
    tabular_config = Forward()
221
    text_element = Forward()
222
    source_hash__ = "e493869bdc02eb835ec3ce1ebfb0a4ea"
223
224
225
226
227
    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
228
    EOF = RegExp('(?!.)')
Eckhart Arnold's avatar
Eckhart Arnold committed
229
230
    BACKSLASH = RegExp('[\\\\]')
    LB = RegExp('\\s*?\\n|$')
Eckhart Arnold's avatar
Eckhart Arnold committed
231
232
    GAP = RE('[ \\t]*(?:\\n[ \\t]*)+\\n')
    PARSEP = OneOrMore(GAP)
Eckhart Arnold's avatar
Eckhart Arnold committed
233
    WSPC = OneOrMore(Alternative(RegExp(COMMENT__), RegExp('\\s+')))
234
    LFF = Series(RE('\\n?', wR='', wL=WSP__), Lookbehind(LB), Optional(WSPC))
Eckhart Arnold's avatar
Eckhart Arnold committed
235
    LF = Series(NegativeLookahead(GAP), RegExp('[ \\t]*\\n[ \\t]*'))
Eckhart Arnold's avatar
Eckhart Arnold committed
236
    TEXTCHUNK = RegExp('[^\\\\%$&\\{\\}\\[\\]\\s\\n]+')
237
    INTEGER = RE('\\d+')
238
    NAME = Capture(RE('\\w+'))
239
    LINEFEED = RegExp('[\\\\][\\\\]')
Eckhart Arnold's avatar
Eckhart Arnold committed
240
    BRACKETS = RegExp('[\\[\\]]')
Eckhart Arnold's avatar
Eckhart Arnold committed
241
    SPECIAL = RegExp('[$&_\\\\\\\\/]')
Eckhart Arnold's avatar
Eckhart Arnold committed
242
243
    ESCAPED = RegExp('\\\\[%$&_/{}]')
    TXTCOMMAND = RegExp('\\\\text\\w+')
244
    CMDNAME = RE('\\\\(?:(?!_)\\w)+')
Eckhart Arnold's avatar
Eckhart Arnold committed
245
    structural = Alternative(Token("subsection"), Token("section"), Token("chapter"), Token("subsubsection"), Token("paragraph"), Token("subparagraph"), Token("item"))
Eckhart Arnold's avatar
Eckhart Arnold committed
246
247
    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
248
249
    text = Series(TEXTCHUNK, ZeroOrMore(Series(RE(''), TEXTCHUNK)))
    block = Series(RegExp('{'), RE(''), ZeroOrMore(Series(NegativeLookahead(blockcmd), text_element, RE(''))), Required(RegExp('}')))
Eckhart Arnold's avatar
Eckhart Arnold committed
250
    cfg_text = ZeroOrMore(Alternative(Series(Optional(RE('')), text), CMDNAME, SPECIAL))
251
    config = Series(Token("["), cfg_text, Required(Token("]")))
Eckhart Arnold's avatar
Eckhart Arnold committed
252
253
    cline = Series(Token("\\cline{"), INTEGER, Token("-"), INTEGER, Token("}"))
    hline = Token("\\hline")
254
    multicolumn = Series(Token("\\multicolumn"), Token("{"), INTEGER, Token("}"), tabular_config, block_of_paragraphs)
Eckhart Arnold's avatar
Eckhart Arnold committed
255
    caption = Series(Token("\\caption"), block)
Eckhart Arnold's avatar
Eckhart Arnold committed
256
    includegraphics = Series(Token("\\includegraphics"), Optional(config), block)
257
    footnote = Series(Token("\\footnote"), block_of_paragraphs)
Eckhart Arnold's avatar
Eckhart Arnold committed
258
    generic_command = Series(NegativeLookahead(no_command), CMDNAME, Optional(Series(Optional(Series(RE(''), config)), RE(''), block)))
259
    text_command = Alternative(TXTCOMMAND, ESCAPED, BRACKETS)
Eckhart Arnold's avatar
Eckhart Arnold committed
260
    known_command = Alternative(footnote, includegraphics, caption, multicolumn, hline, cline)
Eckhart Arnold's avatar
Eckhart Arnold committed
261
262
263
264
    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('}')))
265
    end_inline_env = Synonym(end_environment)
Eckhart Arnold's avatar
Eckhart Arnold committed
266
267
    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))
268
    known_inline_env = Synonym(inline_math)
269
    inline_environment = Alternative(known_inline_env, generic_inline_env)
Eckhart Arnold's avatar
Eckhart Arnold committed
270
    text_element.set(Alternative(text, block, inline_environment, command))
Eckhart Arnold's avatar
Eckhart Arnold committed
271
    paragraph.set(OneOrMore(Series(NegativeLookahead(blockcmd), Alternative(text_element, LINEFEED), RE(''))))
272
    sequence = OneOrMore(Series(Alternative(paragraph, block_environment), Optional(PARSEP)))
273
    block_of_paragraphs.set(Series(Token("{"), Optional(sequence), Required(Token("}"))))
274
    tabular_config.set(Series(Token("{"), RE('[lcr|]+'), Required(Token("}"))))
275
276
277
278
    tabular_cell = ZeroOrMore(Series(text_element, RE('')))
    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
279
    tabular = Series(Token("\\begin{tabular}"), tabular_config, ZeroOrMore(tabular_row), Required(Token("\\end{tabular}")))
Eckhart Arnold's avatar
Eckhart Arnold committed
280
281
282
    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
283
284
285
    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
286
287
    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
288
    generic_block = Series(begin_generic_block, sequence, Required(end_generic_block))
Eckhart Arnold's avatar
Eckhart Arnold committed
289
    known_environment = Alternative(itemize, enumerate, figure, tabular, quotation, verbatim)
Eckhart Arnold's avatar
Eckhart Arnold committed
290
    block_environment.set(Alternative(known_environment, generic_block))
Eckhart Arnold's avatar
Eckhart Arnold committed
291
292
293
294
295
296
    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)))
Eckhart Arnold's avatar
Eckhart Arnold committed
297
    SubSubSection = Series(Token("\\subsubsection"), block, Optional(WSPC), ZeroOrMore(Alternative(sequence, Paragraphs)))
Eckhart Arnold's avatar
Eckhart Arnold committed
298
    SubSubSections = OneOrMore(Series(SubSubSection, Optional(WSPC)))
Eckhart Arnold's avatar
Eckhart Arnold committed
299
    SubSection = Series(Token("\\subsection"), block, Optional(WSPC), ZeroOrMore(Alternative(sequence, SubSubSections)))
Eckhart Arnold's avatar
Eckhart Arnold committed
300
    SubSections = OneOrMore(Series(SubSection, Optional(WSPC)))
Eckhart Arnold's avatar
Eckhart Arnold committed
301
    Section = Series(Token("\\section"), block, Optional(WSPC), ZeroOrMore(Alternative(sequence, SubSections)))
Eckhart Arnold's avatar
Eckhart Arnold committed
302
    Sections = OneOrMore(Series(Section, Optional(WSPC)))
Eckhart Arnold's avatar
Eckhart Arnold committed
303
    Chapter = Series(Token("\\chapter"), block, Optional(WSPC), ZeroOrMore(Alternative(sequence, Sections)))
Eckhart Arnold's avatar
Eckhart Arnold committed
304
    Chapters = OneOrMore(Series(Chapter, Optional(WSPC)))
305
    frontpages = Synonym(sequence)
Eckhart Arnold's avatar
Eckhart Arnold committed
306
    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))
307
    preamble = OneOrMore(Series(Optional(WSPC), command))
308
309
310
311
312
313
314
315
316
    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
317
318
        grammar = thread_local_LaTeX_grammar_singleton
    return grammar
319
320
321
322
323
324
325
326
327


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


328
329
def streamline_whitespace(context):
    node = context[-1]
330
331
332
333
334
    assert node.tag_name in ['WSPC', ':Whitespace']
    s = str(node)
    c = s.find('%')
    n = s.find('\n')
    if c >= 0:
335
336
337
        node.result = '\n'
        # node.result = ('  ' if (n >= c) or (n < 0) else '\n')+ s[c:].rstrip(' \t')
        # node.parser = MockParser('COMMENT', '')
338
339
340
341
342
343
    elif s.find('\n') >= 0:
        node.result = '\n'
    else:
        node.result = ' '


344
345
346
347
def watch(node):
    print(node.as_sxpr())


348
349
LaTeX_AST_transformation_table = {
    # AST Transformations for the LaTeX-grammar
Eckhart Arnold's avatar
Eckhart Arnold committed
350
351
    "+": remove_children_if(lambda node: is_empty(node) or is_one_of(node, {'PARSEP'})),
    # remove_empty,
352
353
354
    "latexdoc": [],
    "preamble": [],
    "document": [],
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
    "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": [],
373
    "begin_generic_block, end_generic_block": replace_by_single_child,
374
375
376
377
378
379
380
381
382
383
384
385
386
387
    "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": [],
388
    "begin_inline_env, end_inline_env": [replace_by_single_child],
389
390
391
392
    "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
393
    "text_command": [],
394
395
396
397
398
    "generic_command": [flatten],
    "footnote": [],
    "includegraphics": [],
    "caption": [],
    "config": [remove_brackets],
Eckhart Arnold's avatar
Eckhart Arnold committed
399
    "block": [remove_brackets, flatten],
400
401
    "text": collapse,
    "no_command, blockcmd": [],
402
403
    "structural": [],
    "CMDNAME": [remove_whitespace, reduce_single_child(is_anonymous)],
Eckhart Arnold's avatar
Eckhart Arnold committed
404
    "TXTCOMMAND": [remove_whitespace, reduce_single_child(is_anonymous)],
405
406
    "NAME": [reduce_single_child, remove_whitespace, reduce_single_child],
    "ESCAPED": [replace_content(lambda node: str(node)[1:])],
407
408
    "BRACKETS": [],
    "TEXTCHUNK": [],
409
410
    "LF": [],
    "PARSEP": replace_content(lambda node: '\n\n'),
Eckhart Arnold's avatar
Eckhart Arnold committed
411
    "GAP": [],
412
413
    "LB": [],
    "BACKSLASH": [],
414
    "EOF": [],
415
416
417
418
    ":Token": [],
    ":RE": replace_by_single_child,
    ":Whitespace": streamline_whitespace,
    "*": replace_by_single_child
419
420
}

421

422
423
def LaTeXTransform() -> TransformationDict:
    return partial(traverse, processing_table=LaTeX_AST_transformation_table.copy())
424
425

def get_transformer() -> TransformationFunc:
426
427
428
429
430
431
432
433
    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

434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450


#######################################################################
#
# 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
451
        return node
452
453
454
455
456
457
458

    def on_preamble(self, node):
        pass

    def on_document(self, node):
        pass

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

Eckhart Arnold's avatar
Eckhart Arnold committed
540
541
542
543
    def on_table_config(self, node):
        pass

    def on_block_of_paragraphs(self, node):
544
545
546
547
548
549
550
551
        pass

    def on_sequence(self, node):
        pass

    def on_paragraph(self, node):
        pass

552
    def on_text_element(self, node):
Eckhart Arnold's avatar
Eckhart Arnold committed
553
554
555
556
557
558
        pass

    def on_inline_environment(self, node):
        pass

    def on_known_inline_env(self, node):
559
560
        pass

Eckhart Arnold's avatar
Eckhart Arnold committed
561
    def on_generic_inline_env(self, node):
562
563
        pass

Eckhart Arnold's avatar
Eckhart Arnold committed
564
565
566
567
568
569
570
571
572
573
    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):
574
575
576
577
578
        pass

    def on_command(self, node):
        pass

Eckhart Arnold's avatar
Eckhart Arnold committed
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
    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

594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
    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

609
610
611
    def on_no_command(self, node):
        pass

612
613
614
    def on_blockcmd(self, node):
        pass

Eckhart Arnold's avatar
Eckhart Arnold committed
615
616
617
    def on_structural(self, node):
        pass

618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
    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

642
    def on_LB(self, node):
643
644
        pass

645
    def on_BACKSLASH(self, node):
Eckhart Arnold's avatar
Eckhart Arnold committed
646
647
        pass

648
    def on_EOF(self, node):
Eckhart Arnold's avatar
Eckhart Arnold committed
649
650
        pass

651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677

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]) \
678
679
            if is_filename(source) < 0 else cname[:cname.find('.')] + '_out'    
        result = compile_source(source, get_preprocessor(), 
680
681
682
683
684
685
686
687
688
689
690
691
692
                                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
693
            print(result.as_xml() if isinstance(result, Node) else result)
694
695
    else:
        print("Usage: LaTeXCompiler.py [FILENAME]")