LaTeXCompiler.py 25.9 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
from DHParser import logging, is_filename, Grammar, Compiler, Lookbehind, Alternative, Pop, \
19
    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, \
Eckhart Arnold's avatar
Eckhart Arnold committed
24
    reduce_single_child, replace_by_single_child, remove_whitespace, \
25
    flatten, is_empty, collapse, replace_content, remove_brackets, is_one_of, remove_first, \
eckhart's avatar
eckhart committed
26
    remove_tokens, remove_nodes, TOKEN_PTYPE
27
28
29
30


#######################################################################
#
Eckhart Arnold's avatar
Eckhart Arnold committed
31
# PREPROCESSOR SECTION - Can be edited. Changes will be preserved.
32
33
34
#
#######################################################################

Eckhart Arnold's avatar
Eckhart Arnold committed
35
def LaTeXPreprocessor(text):
36
37
    return text

Eckhart Arnold's avatar
Eckhart Arnold committed
38
39
def get_preprocessor() -> PreprocessorFunc:
    return LaTeXPreprocessor
40
41
42
43
44
45
46
47
48
49
50


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

class LaTeXGrammar(Grammar):
    r"""Parser for a LaTeX source file, with this grammar:
    
51
    # LaTeX-Grammar for DHParser
52
    
53
    # preamble
54
    @ whitespace = /[ \t]*(?:\n(?![ \t]*\n)[ \t]*)?/    # optional whitespace, including at most one linefeed
Eckhart Arnold's avatar
Eckhart Arnold committed
55
    @ comment    = /%.*/
56
    
Eckhart Arnold's avatar
Eckhart Arnold committed
57
58
59
60
61
62
    ########################################################################
    #
    # outer document structure
    #
    ########################################################################
    
63
    latexdoc       = preamble document
64
    preamble       = { [WSPC] command }+
65
    
eckhart's avatar
eckhart committed
66
67
68
    document       = [WSPC] "\begin{document}"
                     frontpages
                     (Chapters | Sections)
Eckhart Arnold's avatar
Eckhart Arnold committed
69
70
                     [Bibliography] [Index] [WSPC]
                     "\end{document}" [WSPC] §EOF
71
72
73
74
75
76
77
78
79
    frontpages     = sequence
    
    
    #######################################################################
    #
    # document structure
    #
    #######################################################################
    
eckhart's avatar
eckhart committed
80
81
    Chapters       = { [WSPC] Chapter }+
    Chapter        = "\chapter" heading { sequence | Sections }
82
    
eckhart's avatar
eckhart committed
83
84
    Sections       = { [WSPC] Section }+
    Section        = "\section" heading { sequence | SubSections }
85
    
eckhart's avatar
eckhart committed
86
87
    SubSections    = { [WSPC] SubSection }+
    SubSection     = "\subsection" heading { sequence | SubSubSections }
88
    
eckhart's avatar
eckhart committed
89
90
    SubSubSections = { [WSPC] SubSubSection }+
    SubSubSection  = "\subsubsection" heading { sequence | Paragraphs }
91
    
eckhart's avatar
eckhart committed
92
93
    Paragraphs     = { [WSPC] Paragraph  }+
    Paragraph      = "\paragraph" heading { sequence | SubParagraphs }
94
    
eckhart's avatar
eckhart committed
95
96
    SubParagraphs  = { [WSPC] SubParagraph }+
    SubParagraph   = "\subparagraph" heading [ sequence ]
97
    
eckhart's avatar
eckhart committed
98
99
    Bibliography   = [WSPC] "\bibliography" heading
    Index          = [WSPC] "\printindex"
100
    
101
    heading        = block
102
103
104
105
106
107
108
109
110
    
    #######################################################################
    #
    # document content
    #
    #######################################################################
    
    
    #### block environments ####
111
    
Eckhart Arnold's avatar
Eckhart Arnold committed
112
    block_environment   = known_environment | generic_block
Eckhart Arnold's avatar
Eckhart Arnold committed
113
    known_environment   = itemize | enumerate | figure | tabular | quotation
114
                        | verbatim
Eckhart Arnold's avatar
Eckhart Arnold committed
115
    generic_block       = begin_generic_block sequence §end_generic_block
Eckhart Arnold's avatar
Eckhart Arnold committed
116
117
    begin_generic_block = -&LB begin_environment LFF
    end_generic_block   = -&LB  end_environment LFF
118
    
Eckhart Arnold's avatar
Eckhart Arnold committed
119
120
    itemize             = "\begin{itemize}" [WSPC] { item } §"\end{itemize}"
    enumerate           = "\begin{enumerate}" [WSPC] {item } §"\end{enumerate}"
eckhart's avatar
eckhart committed
121
    item                = "\item" sequence
122
    
Eckhart Arnold's avatar
Eckhart Arnold committed
123
124
125
126
    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
127
    tabular             = "\begin{tabular}" tabular_config { tabular_row } §"\end{tabular}"
128
129
    tabular_row         = (multicolumn | tabular_cell) { "&" (multicolumn | tabular_cell) }
                          "\\" ( hline | { cline } )
130
    tabular_cell        = { line_element //~ }
Eckhart Arnold's avatar
Eckhart Arnold committed
131
    tabular_config      = "{" /[lcr|]+/~ §"}"
132
    
Eckhart Arnold's avatar
Eckhart Arnold committed
133
    
134
135
    #### paragraphs and sequences of paragraphs ####
    
136
    block_of_paragraphs = "{" [sequence] §"}"
eckhart's avatar
eckhart committed
137
    sequence            = [WSPC] { (paragraph | block_environment ) [PARSEP] }+
138
139
140
    paragraph           = { !blockcmd text_element //~ }+
    text_element        = line_element | LINEFEED
    line_element        = text | block | inline_environment | command
141
    
Eckhart Arnold's avatar
Eckhart Arnold committed
142
    
143
144
    #### inline enivronments ####
    
145
    inline_environment  = known_inline_env | generic_inline_env
146
    known_inline_env    = inline_math
Eckhart Arnold's avatar
Eckhart Arnold committed
147
148
    generic_inline_env  = begin_inline_env //~ paragraph §end_inline_env
    begin_inline_env    = (-!LB begin_environment) | (begin_environment !LFF)
149
    end_inline_env      = end_environment
Eckhart Arnold's avatar
Eckhart Arnold committed
150
                          ## (-!LB end_environment)   | (end_environment !LFF)  # ambiguity with genric_block when EOF
151
152
    begin_environment   = /\\begin{/ §NAME /}/
    end_environment     = /\\end{/ §::NAME /}/
153
    
Eckhart Arnold's avatar
Eckhart Arnold committed
154
    inline_math         = /\$/ /[^$]*/ §/\$/
155
    
Eckhart Arnold's avatar
Eckhart Arnold committed
156
    
157
158
    #### commands ####
    
Eckhart Arnold's avatar
Eckhart Arnold committed
159
    command             = known_command | text_command | generic_command
Eckhart Arnold's avatar
Eckhart Arnold committed
160
    known_command       = footnote | includegraphics | caption | multicolumn | hline | cline
161
    text_command        = TXTCOMMAND | ESCAPED | BRACKETS
Eckhart Arnold's avatar
Eckhart Arnold committed
162
    generic_command     = !no_command CMDNAME [[ //~ config ] //~ block ]
163
164
    
    footnote            = "\footnote" block_of_paragraphs
Eckhart Arnold's avatar
Eckhart Arnold committed
165
    includegraphics     = "\includegraphics" [ config ] block
Eckhart Arnold's avatar
Eckhart Arnold committed
166
    caption             = "\caption" block
Eckhart Arnold's avatar
Eckhart Arnold committed
167
168
169
170
    multicolumn         = "\multicolumn" "{" INTEGER "}" tabular_config block_of_paragraphs
    hline               = "\hline"
    cline               = "\cline{" INTEGER "-" INTEGER "}"
    
171
    
172
173
174
175
176
177
    #######################################################################
    #
    # low-level text and character sequences
    #
    #######################################################################
    
178
    
179
    config     = "[" cfg_text §"]"
Eckhart Arnold's avatar
Eckhart Arnold committed
180
    cfg_text   = { ([//~] text) | CMDNAME | SPECIAL }
Eckhart Arnold's avatar
Eckhart Arnold committed
181
182
    block      = /{/ //~ { !blockcmd text_element //~ } §/}/
    text       = TEXTCHUNK { //~ TEXTCHUNK }
183
    
Eckhart Arnold's avatar
Eckhart Arnold committed
184
185
186
187
188
    no_command = "\begin{" | "\end" | BACKSLASH structural
    blockcmd   = BACKSLASH ( ( "begin{" | "end{" )
                             ( "enumerate" | "itemize" | "figure" | "quote"
                             | "quotation" | "tabular") "}"
                           | structural | begin_generic_block | end_generic_block )
189
190
191
    
    structural = "subsection" | "section" | "chapter" | "subsubsection"
               | "paragraph" | "subparagraph" | "item"
192
193
194
195
    
    
    #######################################################################
    #
196
    # primitives
197
198
    #
    #######################################################################
199
    
200
    
201
    CMDNAME    = /\\(?:(?!_)\w)+/~
Eckhart Arnold's avatar
Eckhart Arnold committed
202
203
    TXTCOMMAND = /\\text\w+/
    ESCAPED    = /\\[%$&_\/{}]/
Eckhart Arnold's avatar
Eckhart Arnold committed
204
    SPECIAL    = /[$&_\\\\\/]/
Eckhart Arnold's avatar
Eckhart Arnold committed
205
    BRACKETS   = /[\[\]]/                       # left or right square bracket: [ ]
206
    LINEFEED   = /[\\][\\]/
Eckhart Arnold's avatar
Eckhart Arnold committed
207
    
208
    NAME       = /\w+/~
209
    INTEGER    = /\d+/~
210
211
212
    
    TEXTCHUNK  = /[^\\%$&\{\}\[\]\s\n]+/        # some piece of text excluding whitespace,
                                                # linefeed and special characters
Eckhart Arnold's avatar
Eckhart Arnold committed
213
214
215
    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
216
    WSPC       = { COMMENT__ | /\s+/ }+         # arbitrary horizontal or vertical whitespace
Eckhart Arnold's avatar
Eckhart Arnold committed
217
    GAP        = /[ \t]*(?:\n[ \t]*)+\n/~       # at least one empty line, i.e.
218
                                                # [whitespace] linefeed [whitespace] linefeed
Eckhart Arnold's avatar
Eckhart Arnold committed
219
    NEW_LINE   = /[ \t]*/ [COMMENT__] /\n/
220
221
    LB         = /\s*?\n|$/                     # backwards line break for Lookbehind-Operator
                                                # beginning of text marker '$' added for test code
Eckhart Arnold's avatar
Eckhart Arnold committed
222
223
224
    BACKSLASH  = /[\\]/
    
    EOF        = /(?!.)/                        # End-Of-File
225
    """
Eckhart Arnold's avatar
Eckhart Arnold committed
226
    begin_generic_block = Forward()
227
    block_environment = Forward()
228
    block_of_paragraphs = Forward()
Eckhart Arnold's avatar
Eckhart Arnold committed
229
    end_generic_block = Forward()
Eckhart Arnold's avatar
Eckhart Arnold committed
230
    paragraph = Forward()
231
    tabular_config = Forward()
232
    text_element = Forward()
eckhart's avatar
eckhart committed
233
    source_hash__ = "a078d3d46ee55a7543f37c62b3fb24a7"
234
    parser_initialization__ = "upon instantiation"
Eckhart Arnold's avatar
Eckhart Arnold committed
235
236
237
    COMMENT__ = r'%.*'
    WHITESPACE__ = r'[ \t]*(?:\n(?![ \t]*\n)[ \t]*)?'
    WSP__ = mixin_comment(whitespace=WHITESPACE__, comment=COMMENT__)
238
239
    wspL__ = ''
    wspR__ = WSP__
Eckhart Arnold's avatar
Eckhart Arnold committed
240
    EOF = RegExp('(?!.)')
Eckhart Arnold's avatar
Eckhart Arnold committed
241
242
    BACKSLASH = RegExp('[\\\\]')
    LB = RegExp('\\s*?\\n|$')
di68kap's avatar
di68kap committed
243
    NEW_LINE = Series(RegExp('[ \\t]*'), Option(RegExp(COMMENT__)), RegExp('\\n'))
Eckhart Arnold's avatar
Eckhart Arnold committed
244
    GAP = RE('[ \\t]*(?:\\n[ \\t]*)+\\n')
Eckhart Arnold's avatar
Eckhart Arnold committed
245
    WSPC = OneOrMore(Alternative(RegExp(COMMENT__), RegExp('\\s+')))
di68kap's avatar
di68kap committed
246
247
248
    PARSEP = Series(ZeroOrMore(Series(RegExp(WHITESPACE__), RegExp(COMMENT__))), GAP, Option(WSPC))
    LFF = Series(NEW_LINE, Option(WSPC))
    LF = Series(NEW_LINE, ZeroOrMore(Series(RegExp(COMMENT__), RegExp(WHITESPACE__))))
Eckhart Arnold's avatar
Eckhart Arnold committed
249
    TEXTCHUNK = RegExp('[^\\\\%$&\\{\\}\\[\\]\\s\\n]+')
250
    INTEGER = RE('\\d+')
251
    NAME = Capture(RE('\\w+'))
252
    LINEFEED = RegExp('[\\\\][\\\\]')
Eckhart Arnold's avatar
Eckhart Arnold committed
253
    BRACKETS = RegExp('[\\[\\]]')
Eckhart Arnold's avatar
Eckhart Arnold committed
254
    SPECIAL = RegExp('[$&_\\\\\\\\/]')
Eckhart Arnold's avatar
Eckhart Arnold committed
255
256
    ESCAPED = RegExp('\\\\[%$&_/{}]')
    TXTCOMMAND = RegExp('\\\\text\\w+')
257
    CMDNAME = RE('\\\\(?:(?!_)\\w)+')
Eckhart Arnold's avatar
Eckhart Arnold committed
258
    structural = Alternative(Token("subsection"), Token("section"), Token("chapter"), Token("subsubsection"), Token("paragraph"), Token("subparagraph"), Token("item"))
di68kap's avatar
di68kap committed
259
260
261
262
263
    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))
    text = Series(TEXTCHUNK, ZeroOrMore(Series(RE(''), TEXTCHUNK)))
    block = Series(RegExp('{'), RE(''), ZeroOrMore(Series(NegativeLookahead(blockcmd), text_element, RE(''))), RegExp('}'), mandatory=3)
    cfg_text = ZeroOrMore(Alternative(Series(Option(RE('')), text), CMDNAME, SPECIAL))
264
    config = Series(Token("["), cfg_text, Token("]"), mandatory=2)
di68kap's avatar
di68kap committed
265
    cline = Series(Token("\\cline{"), INTEGER, Token("-"), INTEGER, Token("}"))
Eckhart Arnold's avatar
Eckhart Arnold committed
266
    hline = Token("\\hline")
di68kap's avatar
di68kap committed
267
268
269
270
271
    multicolumn = Series(Token("\\multicolumn"), Token("{"), INTEGER, Token("}"), tabular_config, block_of_paragraphs)
    caption = Series(Token("\\caption"), block)
    includegraphics = Series(Token("\\includegraphics"), Option(config), block)
    footnote = Series(Token("\\footnote"), block_of_paragraphs)
    generic_command = Series(NegativeLookahead(no_command), CMDNAME, Option(Series(Option(Series(RE(''), config)), RE(''), block)))
272
    text_command = Alternative(TXTCOMMAND, ESCAPED, BRACKETS)
Eckhart Arnold's avatar
Eckhart Arnold committed
273
    known_command = Alternative(footnote, includegraphics, caption, multicolumn, hline, cline)
Eckhart Arnold's avatar
Eckhart Arnold committed
274
    command = Alternative(known_command, text_command, generic_command)
275
276
277
    inline_math = Series(RegExp('\\$'), RegExp('[^$]*'), RegExp('\\$'), mandatory=2)
    end_environment = Series(RegExp('\\\\end{'), Pop(NAME), RegExp('}'), mandatory=1)
    begin_environment = Series(RegExp('\\\\begin{'), NAME, RegExp('}'), mandatory=1)
278
    end_inline_env = Synonym(end_environment)
di68kap's avatar
di68kap committed
279
    begin_inline_env = Alternative(Series(NegativeLookbehind(LB), begin_environment), Series(begin_environment, NegativeLookahead(LFF)))
280
    generic_inline_env = Series(begin_inline_env, RE(''), paragraph, end_inline_env, mandatory=3)
281
    known_inline_env = Synonym(inline_math)
282
    inline_environment = Alternative(known_inline_env, generic_inline_env)
283
284
    line_element = Alternative(text, block, inline_environment, command)
    text_element.set(Alternative(line_element, LINEFEED))
di68kap's avatar
di68kap committed
285
    paragraph.set(OneOrMore(Series(NegativeLookahead(blockcmd), text_element, RE(''))))
eckhart's avatar
eckhart committed
286
    sequence = Series(Option(WSPC), OneOrMore(Series(Alternative(paragraph, block_environment), Option(PARSEP))))
287
288
    block_of_paragraphs.set(Series(Token("{"), Option(sequence), Token("}"), mandatory=2))
    tabular_config.set(Series(Token("{"), RE('[lcr|]+'), Token("}"), mandatory=2))
di68kap's avatar
di68kap committed
289
290
291
    tabular_cell = ZeroOrMore(Series(line_element, RE('')))
    tabular_row = Series(Alternative(multicolumn, tabular_cell), ZeroOrMore(Series(Token("&"), Alternative(multicolumn, tabular_cell))), Token("\\\\"), Alternative(hline, ZeroOrMore(cline)))
    tabular = Series(Token("\\begin{tabular}"), tabular_config, ZeroOrMore(tabular_row), Token("\\end{tabular}"), mandatory=3)
292
    verbatim = Series(Token("\\begin{verbatim}"), sequence, Token("\\end{verbatim}"), mandatory=2)
di68kap's avatar
di68kap committed
293
    quotation = Alternative(Series(Token("\\begin{quotation}"), sequence, Token("\\end{quotation}"), mandatory=2), Series(Token("\\begin{quote}"), sequence, Token("\\end{quote}"), mandatory=2))
294
    figure = Series(Token("\\begin{figure}"), sequence, Token("\\end{figure}"), mandatory=2)
eckhart's avatar
eckhart committed
295
    item = Series(Token("\\item"), sequence)
di68kap's avatar
di68kap committed
296
297
298
299
    enumerate = Series(Token("\\begin{enumerate}"), Option(WSPC), ZeroOrMore(item), Token("\\end{enumerate}"), mandatory=3)
    itemize = Series(Token("\\begin{itemize}"), Option(WSPC), ZeroOrMore(item), Token("\\end{itemize}"), mandatory=3)
    end_generic_block.set(Series(Lookbehind(LB), end_environment, LFF))
    begin_generic_block.set(Series(Lookbehind(LB), begin_environment, LFF))
300
    generic_block = Series(begin_generic_block, sequence, end_generic_block, mandatory=2)
Eckhart Arnold's avatar
Eckhart Arnold committed
301
    known_environment = Alternative(itemize, enumerate, figure, tabular, quotation, verbatim)
Eckhart Arnold's avatar
Eckhart Arnold committed
302
    block_environment.set(Alternative(known_environment, generic_block))
303
    heading = Synonym(block)
eckhart's avatar
eckhart committed
304
305
306
307
308
309
310
311
312
313
314
315
316
317
    Index = Series(Option(WSPC), Token("\\printindex"))
    Bibliography = Series(Option(WSPC), Token("\\bibliography"), heading)
    SubParagraph = Series(Token("\\subparagraph"), heading, Option(sequence))
    SubParagraphs = OneOrMore(Series(Option(WSPC), SubParagraph))
    Paragraph = Series(Token("\\paragraph"), heading, ZeroOrMore(Alternative(sequence, SubParagraphs)))
    Paragraphs = OneOrMore(Series(Option(WSPC), Paragraph))
    SubSubSection = Series(Token("\\subsubsection"), heading, ZeroOrMore(Alternative(sequence, Paragraphs)))
    SubSubSections = OneOrMore(Series(Option(WSPC), SubSubSection))
    SubSection = Series(Token("\\subsection"), heading, ZeroOrMore(Alternative(sequence, SubSubSections)))
    SubSections = OneOrMore(Series(Option(WSPC), SubSection))
    Section = Series(Token("\\section"), heading, ZeroOrMore(Alternative(sequence, SubSections)))
    Sections = OneOrMore(Series(Option(WSPC), Section))
    Chapter = Series(Token("\\chapter"), heading, ZeroOrMore(Alternative(sequence, Sections)))
    Chapters = OneOrMore(Series(Option(WSPC), Chapter))
318
    frontpages = Synonym(sequence)
eckhart's avatar
eckhart committed
319
    document = Series(Option(WSPC), Token("\\begin{document}"), frontpages, Alternative(Chapters, Sections), Option(Bibliography), Option(Index), Option(WSPC), Token("\\end{document}"), Option(WSPC), EOF, mandatory=9)
di68kap's avatar
di68kap committed
320
321
    preamble = OneOrMore(Series(Option(WSPC), command))
    latexdoc = Series(preamble, document)
322
323
324
325
326
327
328
329
    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
330
331
        grammar = thread_local_LaTeX_grammar_singleton
    return grammar
332
333
334
335
336
337
338
339
340


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


341
def streamline_whitespace(context):
eckhart's avatar
eckhart committed
342
343
    if context[-2].parser.ptype == ":Token":
        return
344
    node = context[-1]
345
346
347
348
349
    assert node.tag_name in ['WSPC', ':Whitespace']
    s = str(node)
    c = s.find('%')
    n = s.find('\n')
    if c >= 0:
350
351
352
        node.result = '\n'
        # node.result = ('  ' if (n >= c) or (n < 0) else '\n')+ s[c:].rstrip(' \t')
        # node.parser = MockParser('COMMENT', '')
353
354
355
356
357
358
    elif s.find('\n') >= 0:
        node.result = '\n'
    else:
        node.result = ' '


359
360
361
def watch(node):
    print(node.as_sxpr())

eckhart's avatar
eckhart committed
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
flatten_structure = flatten(lambda context: is_anonymous(context) or is_one_of(
    context, {"Chapters", "Sections", "SubSections", "SubSubSections", "Paragraphs",
              "SubParagraphs", "sequence"}), True)


def is_commandname(context):
    node = context[-1]
    if node.parser.ptype == TOKEN_PTYPE:
        parent = context[-2]
        if len(parent.children) > 1:
            parent_name = parent.tag_name.lower()
            content = str(node)
            if (content == '\\' + parent_name
                or content == '\\begin{' + parent_name + '}'
                or content == '\\end{' + parent_name + '}'):
                return True
    return False


drop_expendables = remove_children_if(lambda context: is_empty(context) or
                                                      is_one_of(context, {'PARSEP', 'WSPC'}) or
                                                      is_commandname(context))

385

386
387
LaTeX_AST_transformation_table = {
    # AST Transformations for the LaTeX-grammar
eckhart's avatar
eckhart committed
388
    "+": [drop_expendables, flatten_structure],
389
390
    "latexdoc": [],
    "preamble": [],
eckhart's avatar
eckhart committed
391
    "document": [flatten_structure],
Eckhart Arnold's avatar
Eckhart Arnold committed
392
    "frontpages": reduce_single_child,
393
    "Chapters, Sections, SubSections, SubSubSections, Paragraphs, SubParagraphs": [],
eckhart's avatar
eckhart committed
394
    "Chapter, Section, SubSection, SubSubSection, Paragraph, SubParagraph": [],
Eckhart Arnold's avatar
Eckhart Arnold committed
395
    "heading": reduce_single_child,
396
397
    "Bibliography": [],
    "Index": [],
398
399
    "block_environment": replace_by_single_child,
    "known_environment": replace_by_single_child,
400
    "generic_block": [],
401
    "begin_generic_block, end_generic_block": [remove_nodes('NEW_LINE'), replace_by_single_child],
402
    "itemize, enumerate": [remove_brackets, flatten],
eckhart's avatar
eckhart committed
403
    "item": [],
404
    "figure": [],
Eckhart Arnold's avatar
Eckhart Arnold committed
405
    "quotation": [reduce_single_child, remove_brackets],
406
    "verbatim": [],
eckhart's avatar
eckhart committed
407
    "tabular": [],
Eckhart Arnold's avatar
Eckhart Arnold committed
408
    "tabular_config, block_of_paragraphs": [remove_brackets, reduce_single_child],
eckhart's avatar
eckhart committed
409
410
411
    "tabular_row": [flatten, remove_tokens('&', '\\')],
    "tabular_cell": [flatten, remove_whitespace],
    "multicolumn": [remove_tokens('{', '}')],
Eckhart Arnold's avatar
Eckhart Arnold committed
412
    "hline": [remove_whitespace, reduce_single_child],
413
414
    "sequence": [flatten],
    "paragraph": [flatten],
415
416
417
418
    "text_element": replace_by_single_child,
    "line_element": replace_by_single_child,
    "inline_environment": replace_by_single_child,
    "known_inline_env": replace_by_single_child,
419
    "generic_inline_env": [],
420
    "begin_inline_env, end_inline_env": [replace_by_single_child],
Eckhart Arnold's avatar
Eckhart Arnold committed
421
422
    "begin_environment, end_environment": [remove_brackets, reduce_single_child],
    "inline_math": [remove_brackets, reduce_single_child],
423
424
    "command": replace_by_single_child,
    "known_command": replace_by_single_child,
Eckhart Arnold's avatar
Eckhart Arnold committed
425
    "text_command": [],
426
427
428
429
    "generic_command": [flatten],
    "footnote": [],
    "includegraphics": [],
    "caption": [],
Eckhart Arnold's avatar
Eckhart Arnold committed
430
    "config": [remove_brackets, reduce_single_child],
431
    "block": [remove_brackets, flatten, replace_by_single_child],
432
433
    "text": collapse,
    "no_command, blockcmd": [],
434
    "structural": [],
Eckhart Arnold's avatar
Eckhart Arnold committed
435
436
437
    "CMDNAME": [remove_whitespace, reduce_single_child],
    "TXTCOMMAND": [remove_whitespace, reduce_single_child],
    "NAME": [reduce_single_child, remove_whitespace, reduce_single_child],
438
    "ESCAPED": [replace_content(lambda node: str(node)[1:])],
439
440
    "BRACKETS": [],
    "TEXTCHUNK": [],
441
442
    "LF": [],
    "PARSEP": replace_content(lambda node: '\n\n'),
Eckhart Arnold's avatar
Eckhart Arnold committed
443
    "GAP": [],
444
445
    "LB": [],
    "BACKSLASH": [],
446
    "EOF": [],
eckhart's avatar
eckhart committed
447
    ":Token":
Eckhart Arnold's avatar
Eckhart Arnold committed
448
        [remove_whitespace, reduce_single_child],
449
    ":RE": replace_by_single_child,
450
    ":Whitespace": streamline_whitespace,
451
    "*": replace_by_single_child
452
453
}

454

455
456
def LaTeXTransform() -> TransformationDict:
    return partial(traverse, processing_table=LaTeX_AST_transformation_table.copy())
457
458

def get_transformer() -> TransformationFunc:
459
460
461
462
463
464
465
466
    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

467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483


#######################################################################
#
# 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
484
        return node
485
486
487
488
489
490
491

    def on_preamble(self, node):
        pass

    def on_document(self, node):
        pass

Eckhart Arnold's avatar
Eckhart Arnold committed
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
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
    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):
571
572
        pass

Eckhart Arnold's avatar
Eckhart Arnold committed
573
574
575
576
    def on_table_config(self, node):
        pass

    def on_block_of_paragraphs(self, node):
577
578
579
580
581
582
583
584
        pass

    def on_sequence(self, node):
        pass

    def on_paragraph(self, node):
        pass

585
    def on_text_element(self, node):
Eckhart Arnold's avatar
Eckhart Arnold committed
586
587
588
589
590
591
        pass

    def on_inline_environment(self, node):
        pass

    def on_known_inline_env(self, node):
592
593
        pass

Eckhart Arnold's avatar
Eckhart Arnold committed
594
    def on_generic_inline_env(self, node):
595
596
        pass

Eckhart Arnold's avatar
Eckhart Arnold committed
597
598
599
600
601
602
603
604
605
606
    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):
607
608
609
610
611
        pass

    def on_command(self, node):
        pass

Eckhart Arnold's avatar
Eckhart Arnold committed
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
    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

627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
    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

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

645
646
647
    def on_blockcmd(self, node):
        pass

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

675
    def on_LB(self, node):
676
677
        pass

678
    def on_BACKSLASH(self, node):
Eckhart Arnold's avatar
Eckhart Arnold committed
679
680
        pass

681
    def on_EOF(self, node):
Eckhart Arnold's avatar
Eckhart Arnold committed
682
683
        pass

684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710

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]) \
711
712
            if is_filename(source) < 0 else cname[:cname.find('.')] + '_out'    
        result = compile_source(source, get_preprocessor(), 
713
714
715
716
717
718
719
720
721
722
723
724
725
                                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
726
            print(result.as_xml() if isinstance(result, Node) else result)
727
728
    else:
        print("Usage: LaTeXCompiler.py [FILENAME]")