LaTeXCompiler.py 30.4 KB
Newer Older
1
2
3
4
5
6
7
8
9
#!/usr/bin/python

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


10
from collections import defaultdict
11
12
import os
import sys
Eckhart Arnold's avatar
Eckhart Arnold committed
13
14
from functools import partial

15
16
17
18
try:
    import regex as re
except ImportError:
    import re
19
from DHParser import is_filename, Grammar, Compiler, Lookbehind, Alternative, Pop, \
di68kap's avatar
di68kap committed
20
21
    Synonym, Whitespace, Token, \
    Option, NegativeLookbehind, OneOrMore, RegExp, Series, Capture, \
22
    ZeroOrMore, Forward, NegativeLookahead, mixin_comment, compile_source, \
23
    PreprocessorFunc, TransformationDict, \
Eckhart Arnold's avatar
Eckhart Arnold committed
24
    Node, TransformationFunc, traverse, remove_children_if, is_anonymous, \
Eckhart Arnold's avatar
Eckhart Arnold committed
25
    reduce_single_child, replace_by_single_child, remove_whitespace, \
26
    flatten, is_empty, collapse, replace_content, replace_content_by, remove_brackets, \
eckhart's avatar
eckhart committed
27
    is_one_of, traverse_locally, remove_tokens, remove_nodes, TOKEN_PTYPE, Error, GLOBALS
28
from DHParser.log import logging
29
30
31
32


#######################################################################
#
Eckhart Arnold's avatar
Eckhart Arnold committed
33
# PREPROCESSOR SECTION - Can be edited. Changes will be preserved.
34
35
36
#
#######################################################################

Eckhart Arnold's avatar
Eckhart Arnold committed
37
def LaTeXPreprocessor(text):
38
39
    return text

Eckhart Arnold's avatar
Eckhart Arnold committed
40
41
def get_preprocessor() -> PreprocessorFunc:
    return LaTeXPreprocessor
42
43
44
45
46
47
48
49
50
51
52


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

class LaTeXGrammar(Grammar):
    r"""Parser for a LaTeX source file, with this grammar:
    
53
    # LaTeX-Grammar for DHParser
54
    
55
    # preamble
56
    @ whitespace = /[ \t]*(?:\n(?![ \t]*\n)[ \t]*)?/    # optional whitespace, including at most one linefeed
Eckhart Arnold's avatar
Eckhart Arnold committed
57
    @ comment    = /%.*/
58
    
Eckhart Arnold's avatar
Eckhart Arnold committed
59
60
61
62
63
64
    ########################################################################
    #
    # outer document structure
    #
    ########################################################################
    
65
    latexdoc       = preamble document
66
    preamble       = { [WSPC] command }+
67
    
eckhart's avatar
eckhart committed
68
69
70
    document       = [WSPC] "\begin{document}"
                     frontpages
                     (Chapters | Sections)
Eckhart Arnold's avatar
Eckhart Arnold committed
71
72
                     [Bibliography] [Index] [WSPC]
                     "\end{document}" [WSPC] §EOF
73
74
75
76
77
78
79
80
81
    frontpages     = sequence
    
    
    #######################################################################
    #
    # document structure
    #
    #######################################################################
    
eckhart's avatar
eckhart committed
82
83
    Chapters       = { [WSPC] Chapter }+
    Chapter        = "\chapter" heading { sequence | Sections }
84
    
eckhart's avatar
eckhart committed
85
86
    Sections       = { [WSPC] Section }+
    Section        = "\section" heading { sequence | SubSections }
87
    
eckhart's avatar
eckhart committed
88
89
    SubSections    = { [WSPC] SubSection }+
    SubSection     = "\subsection" heading { sequence | SubSubSections }
90
    
eckhart's avatar
eckhart committed
91
92
    SubSubSections = { [WSPC] SubSubSection }+
    SubSubSection  = "\subsubsection" heading { sequence | Paragraphs }
93
    
eckhart's avatar
eckhart committed
94
95
    Paragraphs     = { [WSPC] Paragraph  }+
    Paragraph      = "\paragraph" heading { sequence | SubParagraphs }
96
    
eckhart's avatar
eckhart committed
97
98
    SubParagraphs  = { [WSPC] SubParagraph }+
    SubParagraph   = "\subparagraph" heading [ sequence ]
99
    
eckhart's avatar
eckhart committed
100
101
    Bibliography   = [WSPC] "\bibliography" heading
    Index          = [WSPC] "\printindex"
102
    
103
    heading        = block
104
105
106
107
108
109
110
111
112
    
    #######################################################################
    #
    # document content
    #
    #######################################################################
    
    
    #### block environments ####
113
    
Eckhart Arnold's avatar
Eckhart Arnold committed
114
    block_environment   = known_environment | generic_block
Eckhart Arnold's avatar
Eckhart Arnold committed
115
    known_environment   = itemize | enumerate | figure | tabular | quotation
116
                        | verbatim
Eckhart Arnold's avatar
Eckhart Arnold committed
117
    generic_block       = begin_generic_block sequence §end_generic_block
Eckhart Arnold's avatar
Eckhart Arnold committed
118
119
    begin_generic_block = -&LB begin_environment LFF
    end_generic_block   = -&LB  end_environment LFF
120
    
Eckhart Arnold's avatar
Eckhart Arnold committed
121
122
    itemize             = "\begin{itemize}" [WSPC] { item } §"\end{itemize}"
    enumerate           = "\begin{enumerate}" [WSPC] {item } §"\end{enumerate}"
eckhart's avatar
eckhart committed
123
    item                = "\item" sequence
124
    
Eckhart Arnold's avatar
Eckhart Arnold committed
125
126
127
128
    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
129
    tabular             = "\begin{tabular}" tabular_config { tabular_row } §"\end{tabular}"
130
131
    tabular_row         = (multicolumn | tabular_cell) { "&" (multicolumn | tabular_cell) }
                          "\\" ( hline | { cline } )
132
    tabular_cell        = { line_element //~ }
Eckhart Arnold's avatar
Eckhart Arnold committed
133
    tabular_config      = "{" /[lcr|]+/~ §"}"
134
    
Eckhart Arnold's avatar
Eckhart Arnold committed
135
    
136
137
    #### paragraphs and sequences of paragraphs ####
    
138
    block_of_paragraphs = "{" [sequence] §"}"
eckhart's avatar
eckhart committed
139
    sequence            = [WSPC] { (paragraph | block_environment ) [PARSEP] }+
140
141
142
    paragraph           = { !blockcmd text_element //~ }+
    text_element        = line_element | LINEFEED
    line_element        = text | block | inline_environment | command
143
    
Eckhart Arnold's avatar
Eckhart Arnold committed
144
    
145
146
    #### inline enivronments ####
    
147
    inline_environment  = known_inline_env | generic_inline_env
148
    known_inline_env    = inline_math
Eckhart Arnold's avatar
Eckhart Arnold committed
149
150
    generic_inline_env  = begin_inline_env //~ paragraph §end_inline_env
    begin_inline_env    = (-!LB begin_environment) | (begin_environment !LFF)
151
    end_inline_env      = end_environment
eckhart's avatar
eckhart committed
152
                          ## (-!LB end_environment)   | (end_environment !LFF)  # ambiguity with generic_block when EOF
153
154
    begin_environment   = /\\begin{/ §NAME /}/
    end_environment     = /\\end{/ §::NAME /}/
155
    
Eckhart Arnold's avatar
Eckhart Arnold committed
156
    inline_math         = /\$/ /[^$]*/ §/\$/
157
    
Eckhart Arnold's avatar
Eckhart Arnold committed
158
    
159
160
    #### commands ####
    
Eckhart Arnold's avatar
Eckhart Arnold committed
161
    command             = known_command | text_command | generic_command
162
163
    known_command       = citet | citep | footnote | includegraphics | caption
                        | multicolumn | hline | cline | documentclass | pdfinfo
164
    text_command        = TXTCOMMAND | ESCAPED | BRACKETS
Eckhart Arnold's avatar
Eckhart Arnold committed
165
    generic_command     = !no_command CMDNAME [[ //~ config ] //~ block ]
166
    
167
168
    citet               = "\citet" [config] block
    citep               = ("\citep" | "\cite") [config] block
169
    footnote            = "\footnote" block_of_paragraphs
Eckhart Arnold's avatar
Eckhart Arnold committed
170
    includegraphics     = "\includegraphics" [ config ] block
Eckhart Arnold's avatar
Eckhart Arnold committed
171
    caption             = "\caption" block
Eckhart Arnold's avatar
Eckhart Arnold committed
172
173
174
    multicolumn         = "\multicolumn" "{" INTEGER "}" tabular_config block_of_paragraphs
    hline               = "\hline"
    cline               = "\cline{" INTEGER "-" INTEGER "}"
175
176
    documentclass       = "\documentclass" [ config ] block
    pdfinfo             = "\pdfinfo" block
Eckhart Arnold's avatar
Eckhart Arnold committed
177
    
178
    
179
180
181
182
183
184
    #######################################################################
    #
    # low-level text and character sequences
    #
    #######################################################################
    
185
    
186
    config     = "[" cfg_text §"]"
Eckhart Arnold's avatar
Eckhart Arnold committed
187
    cfg_text   = { ([//~] text) | CMDNAME | SPECIAL }
Eckhart Arnold's avatar
Eckhart Arnold committed
188
189
    block      = /{/ //~ { !blockcmd text_element //~ } §/}/
    text       = TEXTCHUNK { //~ TEXTCHUNK }
190
    
Eckhart Arnold's avatar
Eckhart Arnold committed
191
192
193
194
195
    no_command = "\begin{" | "\end" | BACKSLASH structural
    blockcmd   = BACKSLASH ( ( "begin{" | "end{" )
                             ( "enumerate" | "itemize" | "figure" | "quote"
                             | "quotation" | "tabular") "}"
                           | structural | begin_generic_block | end_generic_block )
196
197
198
    
    structural = "subsection" | "section" | "chapter" | "subsubsection"
               | "paragraph" | "subparagraph" | "item"
199
200
201
202
    
    
    #######################################################################
    #
203
    # primitives
204
205
    #
    #######################################################################
206
    
207
    
208
    CMDNAME    = /\\(?:(?!_)\w)+/~
Eckhart Arnold's avatar
Eckhart Arnold committed
209
210
    TXTCOMMAND = /\\text\w+/
    ESCAPED    = /\\[%$&_\/{}]/
Eckhart Arnold's avatar
Eckhart Arnold committed
211
    SPECIAL    = /[$&_\\\\\/]/
Eckhart Arnold's avatar
Eckhart Arnold committed
212
    BRACKETS   = /[\[\]]/                       # left or right square bracket: [ ]
213
    LINEFEED   = /[\\][\\]/
Eckhart Arnold's avatar
Eckhart Arnold committed
214
    
215
    NAME       = /\w+/~
216
    INTEGER    = /\d+/~
217
218
219
    
    TEXTCHUNK  = /[^\\%$&\{\}\[\]\s\n]+/        # some piece of text excluding whitespace,
                                                # linefeed and special characters
Eckhart Arnold's avatar
Eckhart Arnold committed
220
221
222
    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
223
    WSPC       = { COMMENT__ | /\s+/ }+         # arbitrary horizontal or vertical whitespace
Eckhart Arnold's avatar
Eckhart Arnold committed
224
    GAP        = /[ \t]*(?:\n[ \t]*)+\n/~       # at least one empty line, i.e.
225
                                                # [whitespace] linefeed [whitespace] linefeed
Eckhart Arnold's avatar
Eckhart Arnold committed
226
    NEW_LINE   = /[ \t]*/ [COMMENT__] /\n/
227
228
    LB         = /\s*?\n|$/                     # backwards line break for Lookbehind-Operator
                                                # beginning of text marker '$' added for test code
Eckhart Arnold's avatar
Eckhart Arnold committed
229
230
231
    BACKSLASH  = /[\\]/
    
    EOF        = /(?!.)/                        # End-Of-File
232
    """
Eckhart Arnold's avatar
Eckhart Arnold committed
233
    begin_generic_block = Forward()
234
    block_environment = Forward()
235
    block_of_paragraphs = Forward()
Eckhart Arnold's avatar
Eckhart Arnold committed
236
    end_generic_block = Forward()
Eckhart Arnold's avatar
Eckhart Arnold committed
237
    paragraph = Forward()
238
    tabular_config = Forward()
239
    text_element = Forward()
240
    source_hash__ = "79e85f223d89452f2ba796f9c40daac9"
241
    parser_initialization__ = "upon instantiation"
Eckhart Arnold's avatar
Eckhart Arnold committed
242
243
    COMMENT__ = r'%.*'
    WHITESPACE__ = r'[ \t]*(?:\n(?![ \t]*\n)[ \t]*)?'
244
    WSP_RE__ = mixin_comment(whitespace=WHITESPACE__, comment=COMMENT__)
di68kap's avatar
di68kap committed
245
    wsp__ = Whitespace(WSP_RE__)
Eckhart Arnold's avatar
Eckhart Arnold committed
246
    EOF = RegExp('(?!.)')
Eckhart Arnold's avatar
Eckhart Arnold committed
247
248
    BACKSLASH = RegExp('[\\\\]')
    LB = RegExp('\\s*?\\n|$')
di68kap's avatar
di68kap committed
249
    NEW_LINE = Series(RegExp('[ \\t]*'), Option(RegExp(COMMENT__)), RegExp('\\n'))
di68kap's avatar
di68kap committed
250
    GAP = Series(RegExp('[ \\t]*(?:\\n[ \\t]*)+\\n'), wsp__)
Eckhart Arnold's avatar
Eckhart Arnold committed
251
    WSPC = OneOrMore(Alternative(RegExp(COMMENT__), RegExp('\\s+')))
di68kap's avatar
di68kap committed
252
253
254
    PARSEP = Series(ZeroOrMore(Series(RegExp(WHITESPACE__), RegExp(COMMENT__))), GAP, Option(WSPC))
    LFF = Series(NEW_LINE, Option(WSPC))
    LF = Series(NEW_LINE, ZeroOrMore(Series(RegExp(COMMENT__), RegExp(WHITESPACE__))))
Eckhart Arnold's avatar
Eckhart Arnold committed
255
    TEXTCHUNK = RegExp('[^\\\\%$&\\{\\}\\[\\]\\s\\n]+')
di68kap's avatar
di68kap committed
256
257
    INTEGER = Series(RegExp('\\d+'), wsp__)
    NAME = Capture(Series(RegExp('\\w+'), wsp__))
258
    LINEFEED = RegExp('[\\\\][\\\\]')
Eckhart Arnold's avatar
Eckhart Arnold committed
259
    BRACKETS = RegExp('[\\[\\]]')
Eckhart Arnold's avatar
Eckhart Arnold committed
260
    SPECIAL = RegExp('[$&_\\\\\\\\/]')
Eckhart Arnold's avatar
Eckhart Arnold committed
261
262
    ESCAPED = RegExp('\\\\[%$&_/{}]')
    TXTCOMMAND = RegExp('\\\\text\\w+')
di68kap's avatar
di68kap committed
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
    CMDNAME = Series(RegExp('\\\\(?:(?!_)\\w)+'), wsp__)
    structural = Alternative(Series(Token("subsection"), wsp__), Series(Token("section"), wsp__), Series(Token("chapter"), wsp__), Series(Token("subsubsection"), wsp__), Series(Token("paragraph"), wsp__), Series(Token("subparagraph"), wsp__), Series(Token("item"), wsp__))
    blockcmd = Series(BACKSLASH, Alternative(Series(Alternative(Series(Token("begin{"), wsp__), Series(Token("end{"), wsp__)), Alternative(Series(Token("enumerate"), wsp__), Series(Token("itemize"), wsp__), Series(Token("figure"), wsp__), Series(Token("quote"), wsp__), Series(Token("quotation"), wsp__), Series(Token("tabular"), wsp__)), Series(Token("}"), wsp__)), structural, begin_generic_block, end_generic_block))
    no_command = Alternative(Series(Token("\\begin{"), wsp__), Series(Token("\\end"), wsp__), Series(BACKSLASH, structural))
    text = Series(TEXTCHUNK, ZeroOrMore(Series(RegExp(''), wsp__, TEXTCHUNK)))
    block = Series(RegExp('{'), RegExp(''), wsp__, ZeroOrMore(Series(NegativeLookahead(blockcmd), text_element, RegExp(''), wsp__)), RegExp('}'), mandatory=4)
    cfg_text = ZeroOrMore(Alternative(Series(Option(Series(RegExp(''), wsp__)), text), CMDNAME, SPECIAL))
    config = Series(Series(Token("["), wsp__), cfg_text, Series(Token("]"), wsp__), mandatory=2)
    pdfinfo = Series(Series(Token("\\pdfinfo"), wsp__), block)
    documentclass = Series(Series(Token("\\documentclass"), wsp__), Option(config), block)
    cline = Series(Series(Token("\\cline{"), wsp__), INTEGER, Series(Token("-"), wsp__), INTEGER, Series(Token("}"), wsp__))
    hline = Series(Token("\\hline"), wsp__)
    multicolumn = Series(Series(Token("\\multicolumn"), wsp__), Series(Token("{"), wsp__), INTEGER, Series(Token("}"), wsp__), tabular_config, block_of_paragraphs)
    caption = Series(Series(Token("\\caption"), wsp__), block)
    includegraphics = Series(Series(Token("\\includegraphics"), wsp__), Option(config), block)
    footnote = Series(Series(Token("\\footnote"), wsp__), block_of_paragraphs)
    citep = Series(Alternative(Series(Token("\\citep"), wsp__), Series(Token("\\cite"), wsp__)), Option(config), block)
    citet = Series(Series(Token("\\citet"), wsp__), Option(config), block)
    generic_command = Series(NegativeLookahead(no_command), CMDNAME, Option(Series(Option(Series(RegExp(''), wsp__, config)), RegExp(''), wsp__, block)))
282
    text_command = Alternative(TXTCOMMAND, ESCAPED, BRACKETS)
283
    known_command = Alternative(citet, citep, footnote, includegraphics, caption, multicolumn, hline, cline, documentclass, pdfinfo)
Eckhart Arnold's avatar
Eckhart Arnold committed
284
    command = Alternative(known_command, text_command, generic_command)
285
286
287
    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)
288
    end_inline_env = Synonym(end_environment)
di68kap's avatar
di68kap committed
289
    begin_inline_env = Alternative(Series(NegativeLookbehind(LB), begin_environment), Series(begin_environment, NegativeLookahead(LFF)))
di68kap's avatar
di68kap committed
290
    generic_inline_env = Series(begin_inline_env, RegExp(''), wsp__, paragraph, end_inline_env, mandatory=4)
291
    known_inline_env = Synonym(inline_math)
292
    inline_environment = Alternative(known_inline_env, generic_inline_env)
293
294
    line_element = Alternative(text, block, inline_environment, command)
    text_element.set(Alternative(line_element, LINEFEED))
di68kap's avatar
di68kap committed
295
    paragraph.set(OneOrMore(Series(NegativeLookahead(blockcmd), text_element, RegExp(''), wsp__)))
eckhart's avatar
eckhart committed
296
    sequence = Series(Option(WSPC), OneOrMore(Series(Alternative(paragraph, block_environment), Option(PARSEP))))
di68kap's avatar
di68kap committed
297
298
299
300
301
302
303
304
305
306
307
    block_of_paragraphs.set(Series(Series(Token("{"), wsp__), Option(sequence), Series(Token("}"), wsp__), mandatory=2))
    tabular_config.set(Series(Series(Token("{"), wsp__), RegExp('[lcr|]+'), wsp__, Series(Token("}"), wsp__), mandatory=3))
    tabular_cell = ZeroOrMore(Series(line_element, RegExp(''), wsp__))
    tabular_row = Series(Alternative(multicolumn, tabular_cell), ZeroOrMore(Series(Series(Token("&"), wsp__), Alternative(multicolumn, tabular_cell))), Series(Token("\\\\"), wsp__), Alternative(hline, ZeroOrMore(cline)))
    tabular = Series(Series(Token("\\begin{tabular}"), wsp__), tabular_config, ZeroOrMore(tabular_row), Series(Token("\\end{tabular}"), wsp__), mandatory=3)
    verbatim = Series(Series(Token("\\begin{verbatim}"), wsp__), sequence, Series(Token("\\end{verbatim}"), wsp__), mandatory=2)
    quotation = Alternative(Series(Series(Token("\\begin{quotation}"), wsp__), sequence, Series(Token("\\end{quotation}"), wsp__), mandatory=2), Series(Series(Token("\\begin{quote}"), wsp__), sequence, Series(Token("\\end{quote}"), wsp__), mandatory=2))
    figure = Series(Series(Token("\\begin{figure}"), wsp__), sequence, Series(Token("\\end{figure}"), wsp__), mandatory=2)
    item = Series(Series(Token("\\item"), wsp__), sequence)
    enumerate = Series(Series(Token("\\begin{enumerate}"), wsp__), Option(WSPC), ZeroOrMore(item), Series(Token("\\end{enumerate}"), wsp__), mandatory=3)
    itemize = Series(Series(Token("\\begin{itemize}"), wsp__), Option(WSPC), ZeroOrMore(item), Series(Token("\\end{itemize}"), wsp__), mandatory=3)
di68kap's avatar
di68kap committed
308
309
    end_generic_block.set(Series(Lookbehind(LB), end_environment, LFF))
    begin_generic_block.set(Series(Lookbehind(LB), begin_environment, LFF))
310
    generic_block = Series(begin_generic_block, sequence, end_generic_block, mandatory=2)
Eckhart Arnold's avatar
Eckhart Arnold committed
311
    known_environment = Alternative(itemize, enumerate, figure, tabular, quotation, verbatim)
Eckhart Arnold's avatar
Eckhart Arnold committed
312
    block_environment.set(Alternative(known_environment, generic_block))
313
    heading = Synonym(block)
di68kap's avatar
di68kap committed
314
315
316
    Index = Series(Option(WSPC), Series(Token("\\printindex"), wsp__))
    Bibliography = Series(Option(WSPC), Series(Token("\\bibliography"), wsp__), heading)
    SubParagraph = Series(Series(Token("\\subparagraph"), wsp__), heading, Option(sequence))
eckhart's avatar
eckhart committed
317
    SubParagraphs = OneOrMore(Series(Option(WSPC), SubParagraph))
di68kap's avatar
di68kap committed
318
    Paragraph = Series(Series(Token("\\paragraph"), wsp__), heading, ZeroOrMore(Alternative(sequence, SubParagraphs)))
eckhart's avatar
eckhart committed
319
    Paragraphs = OneOrMore(Series(Option(WSPC), Paragraph))
di68kap's avatar
di68kap committed
320
    SubSubSection = Series(Series(Token("\\subsubsection"), wsp__), heading, ZeroOrMore(Alternative(sequence, Paragraphs)))
eckhart's avatar
eckhart committed
321
    SubSubSections = OneOrMore(Series(Option(WSPC), SubSubSection))
di68kap's avatar
di68kap committed
322
    SubSection = Series(Series(Token("\\subsection"), wsp__), heading, ZeroOrMore(Alternative(sequence, SubSubSections)))
eckhart's avatar
eckhart committed
323
    SubSections = OneOrMore(Series(Option(WSPC), SubSection))
di68kap's avatar
di68kap committed
324
    Section = Series(Series(Token("\\section"), wsp__), heading, ZeroOrMore(Alternative(sequence, SubSections)))
eckhart's avatar
eckhart committed
325
    Sections = OneOrMore(Series(Option(WSPC), Section))
di68kap's avatar
di68kap committed
326
    Chapter = Series(Series(Token("\\chapter"), wsp__), heading, ZeroOrMore(Alternative(sequence, Sections)))
eckhart's avatar
eckhart committed
327
    Chapters = OneOrMore(Series(Option(WSPC), Chapter))
328
    frontpages = Synonym(sequence)
di68kap's avatar
di68kap committed
329
    document = Series(Option(WSPC), Series(Token("\\begin{document}"), wsp__), frontpages, Alternative(Chapters, Sections), Option(Bibliography), Option(Index), Option(WSPC), Series(Token("\\end{document}"), wsp__), Option(WSPC), EOF, mandatory=9)
di68kap's avatar
di68kap committed
330
331
    preamble = OneOrMore(Series(Option(WSPC), command))
    latexdoc = Series(preamble, document)
332
333
334
335
    root__ = latexdoc
    
def get_grammar() -> LaTeXGrammar:
    try:
eckhart's avatar
eckhart committed
336
337
338
339
        grammar = GLOBALS.LaTeX_1_grammar_singleton
    except AttributeError:
        GLOBALS.LaTeX_1_grammar_singleton = LaTeXGrammar()
        grammar = GLOBALS.LaTeX_1_grammar_singleton
Eckhart Arnold's avatar
Eckhart Arnold committed
340
    return grammar
341
342
343
344
345
346
347
348
349


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


350
def streamline_whitespace(context):
351
    if context[-2].parser.ptype == ":_Token":
eckhart's avatar
eckhart committed
352
        return
353
    node = context[-1]
354
    assert node.tag_name in ['WSPC', ':Whitespace']
355
356
    s = node.content
    if s.find('%') >= 0:
357
        node.result = '\n'
358
        # c = s.find('%')
359
360
        # node.result = ('  ' if (n >= c) or (n < 0) else '\n')+ s[c:].rstrip(' \t')
        # node.parser = MockParser('COMMENT', '')
361
362
363
    elif s.find('\n') >= 0:
        node.result = '\n'
    else:
364
        node.result = ' ' if s else ''
365
366


367
368
369
def watch(node):
    print(node.as_sxpr())

eckhart's avatar
eckhart committed
370
371
flatten_structure = flatten(lambda context: is_anonymous(context) or is_one_of(
    context, {"Chapters", "Sections", "SubSections", "SubSubSections", "Paragraphs",
372
              "SubParagraphs", "sequence"}), recursive=True)
eckhart's avatar
eckhart committed
373
374
375


def is_commandname(context):
eckhart's avatar
eckhart committed
376
377
    """Returns True, if last node in the content represents a (potentially
    unknown) LaTeX-command."""
eckhart's avatar
eckhart committed
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
    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))

395

396
397
LaTeX_AST_transformation_table = {
    # AST Transformations for the LaTeX-grammar
398
    "<": [drop_expendables, flatten_structure],
399
    "latexdoc": [],
400
    "preamble": [traverse_locally({'<': remove_whitespace, 'block': replace_by_single_child})],
eckhart's avatar
eckhart committed
401
    "document": [flatten_structure],
eckhart's avatar
eckhart committed
402
    "pdfinfo": [],
Eckhart Arnold's avatar
Eckhart Arnold committed
403
    "frontpages": reduce_single_child,
404
    "Chapters, Sections, SubSections, SubSubSections, Paragraphs, SubParagraphs": [],
eckhart's avatar
eckhart committed
405
    "Chapter, Section, SubSection, SubSubSection, Paragraph, SubParagraph": [],
Eckhart Arnold's avatar
Eckhart Arnold committed
406
    "heading": reduce_single_child,
407
408
    "Bibliography": [],
    "Index": [],
409
410
    "block_environment": replace_by_single_child,
    "known_environment": replace_by_single_child,
411
    "generic_block": [],
412
    "begin_generic_block, end_generic_block": [remove_nodes('NEW_LINE'), replace_by_single_child],
413
    "itemize, enumerate": [remove_brackets, flatten],
eckhart's avatar
eckhart committed
414
    "item": [],
415
    "figure": [],
Eckhart Arnold's avatar
Eckhart Arnold committed
416
    "quotation": [reduce_single_child, remove_brackets],
417
    "verbatim": [],
eckhart's avatar
eckhart committed
418
    "tabular": [],
Eckhart Arnold's avatar
Eckhart Arnold committed
419
    "tabular_config, block_of_paragraphs": [remove_brackets, reduce_single_child],
eckhart's avatar
eckhart committed
420
421
422
    "tabular_row": [flatten, remove_tokens('&', '\\')],
    "tabular_cell": [flatten, remove_whitespace],
    "multicolumn": [remove_tokens('{', '}')],
Eckhart Arnold's avatar
Eckhart Arnold committed
423
    "hline": [remove_whitespace, reduce_single_child],
424
425
    "sequence": [flatten],
    "paragraph": [flatten],
426
427
428
429
    "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,
430
    "generic_inline_env": [],
431
    "begin_inline_env, end_inline_env": [replace_by_single_child],
Eckhart Arnold's avatar
Eckhart Arnold committed
432
433
    "begin_environment, end_environment": [remove_brackets, reduce_single_child],
    "inline_math": [remove_brackets, reduce_single_child],
434
435
    "command": replace_by_single_child,
    "known_command": replace_by_single_child,
Eckhart Arnold's avatar
Eckhart Arnold committed
436
    "text_command": [],
437
438
439
440
    "generic_command": [flatten],
    "footnote": [],
    "includegraphics": [],
    "caption": [],
Eckhart Arnold's avatar
Eckhart Arnold committed
441
    "config": [remove_brackets, reduce_single_child],
442
    "block": [remove_brackets, flatten, replace_by_single_child],
443
444
    "text": collapse,
    "no_command, blockcmd": [],
445
    "structural": [],
Eckhart Arnold's avatar
Eckhart Arnold committed
446
447
448
    "CMDNAME": [remove_whitespace, reduce_single_child],
    "TXTCOMMAND": [remove_whitespace, reduce_single_child],
    "NAME": [reduce_single_child, remove_whitespace, reduce_single_child],
449
    "ESCAPED": [replace_content(lambda node: str(node)[1:])],
450
451
    "BRACKETS": [],
    "TEXTCHUNK": [],
452
453
    "LF": [],
    "PARSEP": replace_content(lambda node: '\n\n'),
Eckhart Arnold's avatar
Eckhart Arnold committed
454
    "GAP": [],
455
456
    "LB": [],
    "BACKSLASH": [],
457
    "EOF": [],
458
459
    # "PARSEP": [replace_content_by('\n\n')],
    # "WSPC": [replace_content_by(' ')],
460
    ":Whitespace": streamline_whitespace,
461
    "*": replace_by_single_child
462
463
}

464

465
466
def LaTeXTransform() -> TransformationDict:
    return partial(traverse, processing_table=LaTeX_AST_transformation_table.copy())
467

468

469
def get_transformer() -> TransformationFunc:
470
471
472
473
474
475
476
477
    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

478
479
480
481
482
483
484
485


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

486
487
488
489
490
491

def empty_defaultdict():
    """Returns a defaultdict with an empty defaultdict as default value."""
    return defaultdict(empty_defaultdict)


492
493
494
class LaTeXCompiler(Compiler):
    """Compiler for the abstract-syntax-tree of a LaTeX source file.
    """
495
496
    KNOWN_DOCUMENT_CLASSES = {'book', 'article'}
    KNOWN_LANGUAGES = {'english', 'german'}
497

eckhart's avatar
eckhart committed
498
499
    def __init__(self):
        super(LaTeXCompiler, self).__init__()
500
        self.metadata = defaultdict(empty_defaultdict)
501

502
503
504
505
    # def on_latexdoc(self, node):
    #     self.compile(node['preamble'])
    #     self.compile(node['document'])
    #     return node
506

507
508
    # def on_preamble(self, node):
    #     return node
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532

    # def on_document(self, node):
    #     return node

    # def on_frontpages(self, node):
    #     return node

    # def on_Chapters(self, node):
    #     return node

    # def on_Chapter(self, node):
    #     return node

    # def on_Sections(self, node):
    #     return node

    # def on_Section(self, node):
    #     return node

    # def on_SubSections(self, node):
    #     return node

    # def on_SubSection(self, node):
    #     return node
533

534
535
    # def on_SubSubSections(self, node):
    #     return node
536

537
538
    # def on_SubSubSection(self, node):
    #     return node
Eckhart Arnold's avatar
Eckhart Arnold committed
539

540
541
    # def on_Paragraphs(self, node):
    #     return node
Eckhart Arnold's avatar
Eckhart Arnold committed
542

543
544
    # def on_Paragraph(self, node):
    #     return node
Eckhart Arnold's avatar
Eckhart Arnold committed
545

546
547
    # def on_SubParagraphs(self, node):
    #     return node
Eckhart Arnold's avatar
Eckhart Arnold committed
548

549
550
    # def on_SubParagraph(self, node):
    #     return node
Eckhart Arnold's avatar
Eckhart Arnold committed
551

552
553
    # def on_Bibliography(self, node):
    #     return node
Eckhart Arnold's avatar
Eckhart Arnold committed
554

555
556
    # def on_Index(self, node):
    #     return node
Eckhart Arnold's avatar
Eckhart Arnold committed
557

558
559
    # def on_heading(self, node):
    #     return node
Eckhart Arnold's avatar
Eckhart Arnold committed
560

561
562
    # def on_block_environment(self, node):
    #     return node
Eckhart Arnold's avatar
Eckhart Arnold committed
563

564
565
    # def on_known_environment(self, node):
    #     return node
Eckhart Arnold's avatar
Eckhart Arnold committed
566

567
568
    # def on_generic_block(self, node):
    #     return node
Eckhart Arnold's avatar
Eckhart Arnold committed
569

570
571
    # def on_begin_generic_block(self, node):
    #     return node
Eckhart Arnold's avatar
Eckhart Arnold committed
572

573
574
    # def on_end_generic_block(self, node):
    #     return node
Eckhart Arnold's avatar
Eckhart Arnold committed
575

576
577
    # def on_itemize(self, node):
    #     return node
Eckhart Arnold's avatar
Eckhart Arnold committed
578

579
580
    # def on_enumerate(self, node):
    #     return node
Eckhart Arnold's avatar
Eckhart Arnold committed
581

582
583
    # def on_item(self, node):
    #     return node
Eckhart Arnold's avatar
Eckhart Arnold committed
584

585
586
    # def on_figure(self, node):
    #     return node
Eckhart Arnold's avatar
Eckhart Arnold committed
587

588
589
    # def on_quotation(self, node):
    #     return node
Eckhart Arnold's avatar
Eckhart Arnold committed
590

591
592
    # def on_verbatim(self, node):
    #     return node
Eckhart Arnold's avatar
Eckhart Arnold committed
593

594
595
    # def on_tabular(self, node):
    #     return node
Eckhart Arnold's avatar
Eckhart Arnold committed
596

597
598
    # def on_tabular_row(self, node):
    #     return node
Eckhart Arnold's avatar
Eckhart Arnold committed
599

600
601
    # def on_tabular_cell(self, node):
    #     return node
Eckhart Arnold's avatar
Eckhart Arnold committed
602

603
604
    # def on_tabular_config(self, node):
    #     return node
Eckhart Arnold's avatar
Eckhart Arnold committed
605

606
607
    # def on_block_of_paragraphs(self, node):
    #     return node
Eckhart Arnold's avatar
Eckhart Arnold committed
608

609
610
    # def on_sequence(self, node):
    #     return node
Eckhart Arnold's avatar
Eckhart Arnold committed
611

612
613
    # def on_paragraph(self, node):
    #     return node
Eckhart Arnold's avatar
Eckhart Arnold committed
614

615
616
    # def on_text_element(self, node):
    #     return node
617

618
619
    # def on_line_element(self, node):
    #     return node
Eckhart Arnold's avatar
Eckhart Arnold committed
620

621
622
    # def on_inline_environment(self, node):
    #     return node
623

624
625
    # def on_known_inline_env(self, node):
    #     return node
626

627
628
    # def on_generic_inline_env(self, node):
    #     return node
629

630
631
    # def on_begin_inline_env(self, node):
    #     return node
Eckhart Arnold's avatar
Eckhart Arnold committed
632

633
634
    # def on_end_inline_env(self, node):
    #     return node
Eckhart Arnold's avatar
Eckhart Arnold committed
635

636
637
    # def on_begin_environment(self, node):
    #     return node
638

639
640
    # def on_end_environment(self, node):
    #     return node
641

642
643
    # def on_inline_math(self, node):
    #     return node
Eckhart Arnold's avatar
Eckhart Arnold committed
644

645
646
    # def on_command(self, node):
    #     return node
Eckhart Arnold's avatar
Eckhart Arnold committed
647

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

651
652
    # def on_text_command(self, node):
    #     return node
653

654
655
    # def on_generic_command(self, node):
    #     return node
656

657
658
    # def on_footnote(self, node):
    #     return node
Eckhart Arnold's avatar
Eckhart Arnold committed
659

660
661
    # def on_includegraphics(self, node):
    #     return node
Eckhart Arnold's avatar
Eckhart Arnold committed
662

663
664
    # def on_caption(self, node):
    #     return node
Eckhart Arnold's avatar
Eckhart Arnold committed
665

666
667
    # def on_multicolumn(self, node):
    #     return node
Eckhart Arnold's avatar
Eckhart Arnold committed
668

669
670
    # def on_hline(self, node):
    #     return node
Eckhart Arnold's avatar
Eckhart Arnold committed
671

672
673
    # def on_cline(self, node):
    #     return node
674

675
    def on_documentclass(self, node):
eckhart's avatar
eckhart committed
676
677
678
679
        """
        Saves the documentclass (if known) and the language (if given)
        in the metadata dictionary.
        """
680
681
682
        if 'config' in node:
            for it in {part.strip() for part in node['config'].content.split(',')}:
                if it in self.KNOWN_LANGUAGES:
683
                    if 'language' in node.attr:
684
685
                        self.metadata['language'] = it
                    else:
eckhart's avatar
eckhart committed
686
                        self.tree.new_error(node, 'Only one document language supported. '
687
688
                                            'Using %s, ignoring %s.'
                                            % (self.metadata['language'], it), Error.WARNING)
689
690
691
692
693
694
695
        if node['text'] in self.KNOWN_DOCUMENT_CLASSES:
            self.metadata['documentclass'] = node['text']
        return node

    def on_pdfinfo(self, node):
        return node

696
697
    # def on_config(self, node):
    #     return node
698

699
700
    # def on_cfg_text(self, node):
    #     return node
701

702
703
    # def on_block(self, node):
    #     return node
704

705
706
    # def on_text(self, node):
    #     return node
707

708
709
    # def on_no_command(self, node):
    #     return node
710

711
712
    # def on_blockcmd(self, node):
    #     return node
713

714
715
    # def on_structural(self, node):
    #     return node
Eckhart Arnold's avatar
Eckhart Arnold committed
716

717
718
    # def on_CMDNAME(self, node):
    #     return node
719

720
721
    # def on_TXTCOMMAND(self, node):
    #     return node
722

723
724
    # def on_ESCAPED(self, node):
    #     return node
725

726
727
    # def on_SPECIAL(self, node):
    #     return node
728

729
730
    # def on_BRACKETS(self, node):
    #     return node
731

732
733
    # def on_LINEFEED(self, node):
    #     return node
734

735
736
    # def on_NAME(self, node):
    #     return node
737

738
739
    # def on_INTEGER(self, node):
    #     return node
740

741
742
    # def on_TEXTCHUNK(self, node):
    #     return node
743

744
745
    # def on_LF(self, node):
    #     return node
Eckhart Arnold's avatar
Eckhart Arnold committed
746

747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
    # def on_LFF(self, node):
    #     return node

    # def on_PARSEP(self, node):
    #     return node

    # def on_WSPC(self, node):
    #     return node

    # def on_GAP(self, node):
    #     return node

    # def on_NEW_LINE(self, node):
    #     return node

    # def on_LB(self, node):
    #     return node

    # def on_BACKSLASH(self, node):
    #     return node

    # def on_EOF(self, node):
    #     return node
Eckhart Arnold's avatar
Eckhart Arnold committed
770

771

eckhart's avatar
eckhart committed
772
def get_compiler() -> LaTeXCompiler:
773
774
775
776
    global thread_local_LaTeX_compiler_singleton
    try:
        compiler = thread_local_LaTeX_compiler_singleton
    except NameError:
eckhart's avatar
eckhart committed
777
        thread_local_LaTeX_compiler_singleton = LaTeXCompiler()
778
779
        compiler = thread_local_LaTeX_compiler_singleton
    return compiler
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795


#######################################################################
#
# 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]) \
796
797
            if is_filename(source) < 0 else cname[:cname.find('.')] + '_out'    
        result = compile_source(source, get_preprocessor(), 
798
799
800
801
802
803
804
805
806
807
808
809
810
                                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
811
            print(result.as_xml() if isinstance(result, Node) else result)
812
813
    else:
        print("Usage: LaTeXCompiler.py [FILENAME]")