File: formatters.py

package info (click to toggle)
python-pweave 0.25-3
  • links: PTS, VCS
  • area: main
  • in suites: bullseye
  • size: 908 kB
  • sloc: python: 30,007; makefile: 3
file content (829 lines) | stat: -rw-r--r-- 31,130 bytes parent folder | download
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
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
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
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
678
679
680
681
682
683
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
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
import sys, os
from subprocess import Popen, PIPE
import base64
import textwrap
import io
from .config import *
from distutils.version import LooseVersion


# Pweave output formatters

class PwebFormatter(object):

    def __init__(self, source=None):
        self.initformat()
        self._fillformatdict()
        self.header = None
        self.footer = None
        self.executed = None
        self.source = source
        self.wrapper = textwrap.TextWrapper(subsequent_indent="", break_long_words=False)

    def setexecuted(self, executed):
        self.executed = executed

    def format(self):
        self.formatted = []
        for chunk in self.executed:
            # Fill in options for code chunks
            if chunk['type'] == "code":
                for key in self.formatdict.keys():
                    if not key in chunk:
                        chunk[key] = self.formatdict[key]

            # Wrap text if option is set
            if chunk['type'] == "code":
                if chunk['wrap']:
                    chunk['content'] = self._wrap(chunk['content'])
                    chunk['result'] = self._wrap(chunk['result'])
                if chunk['wrap'] == 'code':
                    chunk['content'] = self._wrap(chunk['content'])
                if chunk['wrap'] == 'results':
                    chunk['result'] = self._wrap(chunk['result'])
                if not chunk['wrap']:
                    chunk['content'] = chunk['content'] + "\n"

            # Preformat chunk content before default formatters
            chunk = self.preformat_chunk(chunk)

            if chunk['type'] == "doc":
                self.formatted.append(self.format_docchunk(chunk))
            elif chunk['type'] == "code":
                self.formatted.append(self.format_codechunks(chunk))
            else:
                self.formatted.append(chunk["content"])

        self.formatted = "\n".join(self.formatted)
        self.convert()  # Convert to e.g. markdown
        self.add_header()
        self.add_footer()

    def convert(self):
        pass

    def preformat_chunk(self, chunk):
        """You can use this method in subclasses to preformat chunk content"""
        return chunk

    def format_termchunk(self, chunk):
        if chunk['echo'] and chunk['results'] != 'hidden':
            chunk['result'] = self._termindent(chunk['result'])
            result = '%(termstart)s%(result)s%(termend)s' % chunk
        else:
            result = ""
        return result

    def format_codeblock(self, chunk):
        pass

    def format_results(self, chunk):
        pass

    def format_codechunks(self, chunk):
        chunk['content'] = self._indent(chunk['content'])

        # Code is not executed
        if not chunk['evaluate']:
            if "%s" in chunk["codestart"]:
                chunk["codestart"] = chunk["codestart"] % chunk["engine"]
            if chunk['echo']:
                result = '%(codestart)s%(content)s%(codeend)s' % chunk
                return result
            else:
                return ''

        #Set lexers for code and output
        if "%s" in chunk["codestart"]:
            chunk["codestart"] = chunk["codestart"] % chunk["engine"]
        if "%s" in chunk["outputstart"]:
            chunk["outputstart"] = chunk["outputstart"] % chunk["engine"]
        if "%s" in chunk["termstart"]:
            chunk["termstart"] = chunk["termstart"] % chunk["engine"]

        #Code is executed
        #-------------------
        result = ""

        #Hidden results
        if chunk['results'] == 'hidden':
            chunk['result'] = ''

        #Term sets echo to true
        if chunk['term']:
            result = self.format_termchunk(chunk)
        #Other things than term
        elif chunk['evaluate'] and chunk['echo'] and chunk['results'] == 'verbatim':
            result = '%(codestart)s%(content)s%(codeend)s' % chunk
            if len(chunk['result'].strip()) > 1:
                chunk['result'] = self._indent(chunk['result'])
                result += '%(outputstart)s%(result)s%(outputend)s' % chunk

        elif chunk['evaluate'] and chunk['echo'] and chunk['results'] != 'verbatim':
            chunk['result'] = chunk['result'].replace('\n', '', 1)
            result = '%(codestart)s%(content)s%(codeend)s%(result)s' % chunk

        elif chunk['evaluate'] and not chunk['echo'] and chunk['results'] == 'verbatim':
            if len(chunk['result'].strip()) > 1:
                chunk['result'] = self._indent(chunk['result'])
                result += '%(outputstart)s%(result)s%(outputend)s' % chunk

        elif chunk['evaluate'] and not chunk['echo']:
            #Remove extra line added when results are captured in run phase
            result = chunk['result'].replace('\n', '', 1)

        #Handle figures
        if chunk['fig'] and 'figure' in chunk:
            if chunk['include']:
                result += self.formatfigure(chunk)
        return result

    def format_docchunk(self, chunk):
        return chunk['content']

    def add_header(self):
        """Can be used to add header to self.formatted list"""
        if self.header is not None:
            self.formatted = self.header + self.formatted

    def add_footer(self):
        """Can be used to add footer to self.formatted list"""
        if self.footer is not None:
            self.formatted += self.footer

    def getformatdict(self):
        return self.formatdict

    def getformatted(self):
        return self.formatted

    def updateformatdict(self, format_dict):
        self.formatdict.update(format_dict)

    def _wrapper(self, string, width=80):
        """Wrap a string to specified width like Python terminal"""
        if len(string) < width:
            return string
        # Wrap also comment lines
        if string.lstrip()[0] == "#":
            return string[0:width] + '\n' + self._wrapper("#" + string[width:len(string)], width)
        else:
            return string[0:width] + '\n' + self._wrapper(string[width:len(string)], width)

    def _wrap(self, content):
        splitted = content.split("\n")
        result = ""
        for line in splitted:
            result += self.wrapper.fill(line) + '\n'
        return result

    def _fillformatdict(self):
        """Fill in the blank options that are now only used for rst
            but also allow e.g. special latex style for terminal blocks etc."""
        self._fillkey('termstart', self.formatdict['codestart'])
        self._fillkey('termend', self.formatdict['codeend'])
        self._fillkey('savedformats', list([self.formatdict['figfmt']]))

    def _fillkey(self, key, value):
        if key not in self.formatdict:
            self.formatdict[key] = value

    def _indent(self, text):
        """Indent blocks for formats where indent is significant"""
        return text
        # return(text.replace('\n', '\n' + self.formatdict['indent']))

    def _termindent(self, text):
        """Indent blocks for formats where indent is significant"""
        return text
        # return(text.replace('\n', '\n' + self.formatdict['termindent']))


class PwebTexFormatter(PwebFormatter):
    def initformat(self):
        self.formatdict = dict(codestart='\\begin{verbatim}',
                               codeend='\end{verbatim}\n',
                               outputstart='\\begin{verbatim}',
                               outputend='\end{verbatim}\n',
                               figfmt='.pdf',
                               extension='tex',
                               width='\\linewidth',
                               doctype='tex')

    def formatfigure(self, chunk):

        fignames = chunk['figure']
        caption = chunk['caption']
        width = chunk['width']
        result = ""
        figstring = ""

        if chunk["f_env"] is not None:
            result += "\\begin{%s}\n" % chunk["f_env"]

        for fig in fignames:
            figstring += ("\\includegraphics[width= %s]{%s}\n" % (width, fig))

        # Figure environment
        if chunk['caption']:
            result += ("\\begin{figure}[%s]\n"
                       "\\center\n"
                       "%s"
                       "\\caption{%s}\n" % (chunk['f_pos'], figstring, caption))
            if 'name' in chunk:
                result += "\label{fig:%s}\n" % chunk['name']
            result += "\\end{figure}\n"

        else:
            result += figstring

        if chunk["f_env"] is not None:
            result += "\\end{%s}\n" % chunk["f_env"]

        return result


class PwebMintedFormatter(PwebTexFormatter):
    def initformat(self):
        self.formatdict = dict(
            codestart=r'\begin{minted}[mathescape, fontsize=\small, xleftmargin=0.5em]{%s}',
            codeend='\end{minted}\n',
            outputstart=r'\begin{minted}[fontsize=\small, xleftmargin=0.5em, mathescape, frame = leftline]{text}',
            outputend='\end{minted}\n',
            termstart=r'\begin{minted}[fontsize=\footnotesize, xleftmargin=0.5em, mathescape]{%s}',
            termend='\end{minted}\n',
            figfmt='.pdf',
            extension='tex',
            width='\\linewidth',
            doctype='tex')


class PwebTexPygmentsFormatter(PwebTexFormatter):
    def initformat(self):

        self.formatdict = dict(
            codestart="",
            codeend="",
            outputstart="",
            outputend="",
            termstart="",
            termend="",
            figfmt='.pdf',
            extension='tex',
            width='\\linewidth',
            doctype='tex')

    def format_codechunks(self, chunk):
        from pygments import highlight
        from pygments.lexers import PythonLexer, TextLexer, PythonConsoleLexer
        from pygments.formatters import LatexFormatter

        chunk['content'] = highlight(chunk['content'], PythonLexer(),
                                     LatexFormatter(verboptions="frame=single,fontsize=\small, xleftmargin=0.5em"))
        if len(chunk['result'].strip()) > 0 and chunk['results'] == 'verbatim':
            if chunk['term']:
                chunk['result'] = highlight(chunk['result'], PythonLexer(), LatexFormatter(
                    verboptions="frame=single,fontsize=\small, xleftmargin=0.5em"))
            else:
                chunk['result'] = highlight(chunk['result'], TextLexer(), LatexFormatter(
                    verboptions="frame=leftline,fontsize=\small, xleftmargin=0.5em"))
        return PwebFormatter.format_codechunks(self, chunk)


class PwebTexPweaveFormatter(PwebTexFormatter):
    """User defined formatting for chunks in header using pweavecode, pweaveoutput and pweaveterm environments"""

    def initformat(self):
        self.formatdict = dict(
            codestart=r'\begin{pweavecode}',
            codeend='\end{pweavecode}\n',
            outputstart=r'\begin{pweaveout}',
            outputend='\end{pweaveout}\n',
            termstart=r'\begin{pweaveterm}',
            termend='\end{pweaveterm}\n',
            figfmt='.pdf',
            extension='tex',
            width='\\linewidth',
            doctype='tex')


class PwebRstFormatter(PwebFormatter):
    def initformat(self):
        self.formatdict = dict(codestart='.. code:: %s\n',
                               codeend='\n\n',
                               outputstart='.. code::\n',
                               outputend='\n\n',
                               # rst has specific format (doctest) for term blocks
                               termstart='.. code:: %s\n',
                               termend='\n\n',
                               termindent='    ',
                               indent='    ',
                               figfmt='.png',
                               extension='rst',
                               width='15 cm',
                               doctype='rst')

    def formatfigure(self, chunk):
        fignames = chunk['figure']
        caption = chunk['caption']
        width = chunk['width']
        result = ""
        figstring = ""

        for fig in fignames:
            figstring += ('.. image:: %s\n   :width: %s\n\n' % (fig, width))

        if chunk['caption']:
            result += (".. figure:: %s\n"
                       "   :width: %s\n\n"
                       "   %s\n\n" % (fignames[0], width, caption))
        else:
            result += figstring
        return result

    def _indent(self, text):
        """Indent blocks for formats where indent is significant"""
        return text.replace('\n', '\n' + self.formatdict['indent'])

    def _termindent(self, text):
        return text.replace('\n', '\n' + self.formatdict['termindent'])


class PwebPandocFormatter(PwebFormatter):

    def __init__(self, source=None):
        PwebFormatter.__init__(self, source)
        pandoc_ver = False

        try:
            pandoc = Popen(["pandoc", "--version"], stdin=PIPE, stdout=PIPE)
            pandoc_ver = pandoc.communicate()[0].decode('utf-8').split("\n")[0]
            pandoc_ver = LooseVersion(pandoc_ver.split(" ")[1])
        except:
            pandoc_ver = LooseVersion("0.0.1")
            print("Error in trying to detect pandoc version")

        if pandoc_ver < LooseVersion("1.16.0"):
            self.new_pandoc = False
            print("Your pandoc version is below 1.16, not setting figure size and id")
        else:
            self.new_pandoc = True

    def initformat(self):
        self.formatdict = dict(codestart='~~~~{.%s}',
                               codeend='~~~~~~~~~~~~~\n\n',
                               outputstart='~~~~{.%s}',
                               outputend='~~~~~~~~~~~~~\n\n',
                               indent='',
                               termindent='',
                               figfmt='.png',
                               extension='md',
                               width = None,
                               doctype='pandoc')

    def make_figure_string(self, figname, width, label, caption = ""):
        figstring = "![%s](%s)" % (caption, figname)

        #Pandoc >= 1.16 supports figure width and id
        if (self.new_pandoc):
            attributes = ""
            if label is not None:
                attributes += "#%s " % label
            if width is not None:
                attributes += "width=%s" % width
            if attributes != "":
                figstring += "{%s}" % attributes

        if caption == "":
            figstring += "\\"

        figstring += "\n"

        return figstring

    def formatfigure(self, chunk):

        fignames = chunk['figure']

        if chunk["caption"]:
            caption = chunk["caption"]
        else:
            caption = ""

        figstring = ""

        if chunk['caption'] and len(fignames) > 0:
            if len(fignames) > 1:
                print("INFO: Only including the first plot in a chunk when the caption is set")
            figstring = self.make_figure_string(fignames[0], chunk["width"], chunk["name"], caption)
            return figstring

        for fig in fignames:
            figstring += self.make_figure_string(fignames[0], chunk["width"], chunk["name"])

        return figstring


class PwebLeanpubFormatter(PwebFormatter):
    def initformat(self):
        self.formatdict = dict(codestart='{line-numbers=off}\n~~~~~~~~',
                               codeend='~~~~~~~~\n\n',
                               outputstart='{line-numbers=off}\n~~~~~~~~',
                               outputend='~~~~~~~~\n\n',
                               indent='',
                               termindent='',
                               figfmt='.png',
                               extension='txt',
                               width='15 cm',
                               doctype='leanpub')

    def formatfigure(self, chunk):
        fignames = chunk['figure']
        caption = chunk['caption']
        width = chunk['width']
        result = ""
        figstring = ""

        # print chunk["name"]

        if chunk['caption']:
            if fignames:
                result += '![%s](%s)\n' % (caption, fignames[0])
                if len(fignames) > 1:
                    for fig in fignames[1:]:
                        figstring += '![](%s)\n' % fig
                        sys.stderr.write("Warning, only the first figure gets a caption\n")
        else:
            for fig in fignames:
                figstring += '![](%s)\n' % fig
            result += figstring
        return result


class PwebSoftCoverFormatter(PwebLeanpubFormatter):
    def initformat(self):
        self.formatdict = dict(codestart='\n```python',
                               codeend='```\n\n',
                               outputstart='```\n',
                               outputend='```\n\n',
                               indent='',
                               termindent='',
                               figfmt='.png',
                               extension='md',
                               width='15cm',
                               doctype='softcover')

    def formatfigure(self, chunk):
        fignames = chunk['figure']
        caption = chunk['caption']
        width = chunk['width']
        label = chunk['name']
        result = ""
        figstring = ""

        if chunk['caption']:
            if fignames:
                result += '![%s \\label{fig:%s}](%s)\n' % (caption, label, fignames[0])
                if len(fignames) > 1:
                    for fig in fignames[1:]:
                        figstring += '![](%s)\n' % fig
                        sys.stderr.write("Warning, only the first figure gets a caption\n")
        else:
            for fig in fignames:
                figstring += '![](%s)\n' % fig
            result += figstring
        return result


class PwebSphinxFormatter(PwebRstFormatter):
    def initformat(self):
        self.formatdict = dict(codestart='.. code-block:: %s\n',
                               codeend='\n\n',
                               outputstart='::\n',
                               outputend='\n\n',
                               # rst has specific format (doctest) for term blocks
                               termstart='.. code-block:: %s\n',
                               termend='\n\n',
                               termindent='    ',
                               indent='    ',
                               # Sphinx determines the figure format automatically
                               # for different output formats
                               figfmt='.*',
                               savedformats=['.png', '.pdf'],
                               extension='rst',
                               width='15 cm',
                               doctype='rst')

    def formatfigure(self, chunk):
        fignames = chunk['figure']
        caption = chunk['caption']
        width = chunk['width']
        result = ""
        figstring = ""

        for fig in fignames:
            figstring += ('.. image:: %s\n   :width: %s\n\n' % (fig, width))

        if chunk['caption']:
            result += (".. figure:: %s\n" \
                       "   :width: %s\n\n" \
                       "   %s\n\n" % (fignames[0], width, caption))
        else:
            result += figstring
        return result


class PwebHTMLFormatter(PwebFormatter):
    def format_codechunks(self, chunk):
        from pygments import highlight
        from pygments.lexers import PythonLexer, PythonConsoleLexer, TextLexer
        from pygments.formatters import HtmlFormatter

        chunk['content'] = highlight(chunk['content'], PythonLexer(), HtmlFormatter())
        if len(chunk['result'].strip()) > 0 and chunk['results'] == 'verbatim':
            if chunk['term']:
                chunk['result'] = highlight(chunk['result'], PythonLexer(), HtmlFormatter())
            else:
                chunk['result'] = highlight(chunk['result'], TextLexer(), HtmlFormatter())

        return PwebFormatter.format_codechunks(self, chunk)

    def initformat(self):
        self.formatdict = dict(codestart='',
                               codeend='',
                               outputstart='',
                               outputend='',
                               figfmt='.png',
                               extension='html',
                               width='600',
                               doctype='html')

    def formatfigure(self, chunk):
        result = ""
        figstring = ""
        for fig in chunk['figure']:
            figstring += ('<img src="%s" width="%s"/>\n' % (fig, chunk['width']))

        # Figure environment
        if chunk['caption']:
            # Write labels as data-attribute for javascript etc.
            if chunk['name']:
                labelstring = 'data-label = "fig:%s"' % chunk["name"]
            else:
                labelstring = ""

            result += ("<figure>\n" \
                       "%s"
                       "<figcaption %s>%s</figcaption>\n</figure>" % (figstring, labelstring, chunk['caption']))

        else:
            result += figstring
        return result


class PwebMDtoHTMLFormatter(PwebHTMLFormatter):

    def __init__(self, source = None, theme = "skeleton"):
        from .templates import htmltemplate
        from . import themes
        from pygments.formatters import HtmlFormatter
        from . import __version__
        import time
        PwebHTMLFormatter.__init__(self, source)

        if self.source is not None:
            self.path = os.path.dirname(os.path.abspath(self.source))
        else:
             self.path = "."

        theme_css = ""
        try:
            theme_css += getattr(themes, theme)
        except:
            print("Can't find requested theme. Using Skeleton")
            theme_css += getattr(themes, "skeleton")

        self.header = (htmltemplate["header"] %
                {"pygments_css"  : HtmlFormatter().get_style_defs(),
                "theme_css" : theme_css})


        self.footer = (htmltemplate["footer"] %
                       {"source": self.source, "version": __version__,
                        "time": time.strftime("%d-%m-%Y", time.localtime())})

    def parsetitle(self, chunk):
        """Parse titleblock from first doc chunk, like Pandoc"""
        lines = chunk['content'].splitlines()
        if len(lines) > 3:
            if lines[0].startswith("%"):
                lines[0] = '<H1 class = "title">%s</H1>' % (lines[0].replace("%", "", ))
                if lines[1].startswith("%"):
                    lines[1] = '<strong>Author:</strong> %s <BR/>' % (lines[1].replace("%", "", ))
                if lines[2].startswith("%"):
                    lines[2] = '<strong>Date:</strong> %s <BR/>' % (lines[2].replace("%", "", ))
        chunk['content'] = "\n".join(lines)
        return chunk

    def format_docchunk(self, chunk):
        if 'number' in chunk and chunk['number'] == 1:
            chunk = self.parsetitle(chunk)

        try:
            import markdown
        except ImportError:
            message = "You'll need to install python markdown in order to use markdown to html formatter\nrun 'pip install markdown' to install"
            print(message)
            return message # was returning None, which was passed to join method
        from .markdownmath import MathExtension

        chunk["content"] = markdown.markdown(chunk["content"], extensions=[MathExtension()])
        return chunk['content']

    def formatfigure(self, chunk):
        result = ""
        figstring = ""

        for fig in chunk['figure']:
            #print(self.path + "/" + fig)
            fig_base64 = base64.b64encode(io.open(self.path + "/" + fig, "rb").read()).decode("utf-8")
            figstring += ('<img src="data:image/png;base64,%s" width="%s"/>\n' % (fig_base64, chunk['width']))

        # Figure environment
        if chunk['caption']:
            # Write labels as data-attribute for javascript etc.
            if chunk['name']:
                labelstring = 'data-label = "fig:%s"' % chunk["name"]
            else:
                labelstring = ""

            result += ("<figure>\n" \
                       "%s"
                       "<figcaption %s>%s</figcaption>\n</figure>" % (figstring, labelstring, chunk['caption']))

        else:
            result += figstring
        return result


class PwebPandocMDtoHTMLFormatter(PwebMDtoHTMLFormatter):

    def format_docchunk(self, chunk):
        if 'number' in chunk and chunk['number'] == 1:
            chunk = self.parsetitle(chunk)
        try:
            pandoc = Popen(["pandoc", "--mathjax", "-t", "html", "-f", "markdown"], stdin=PIPE, stdout=PIPE)
        except:
            sys.stderr.write("ERROR: Can't find pandoc")
            raise
        pandoc.stdin.write(chunk['content'].encode('utf-8'))
        chunk['content'] = pandoc.communicate()[0].decode('utf-8')
        return chunk['content']


class PwebPandoctoTexFormatter(PwebTexPygmentsFormatter):
    def __init__(self, source=None):
        PwebTexPygmentsFormatter.__init__(self, source)
        from pygments.formatters import LatexFormatter

        x = LatexFormatter()
        self.header = ("""\\documentclass[a4paper,11pt,final]{article}
        \\usepackage{fancyvrb, color, graphicx, hyperref, amsmath, url, textcomp}
        \\usepackage{palatino}
        \\usepackage[a4paper,text={16.5cm,25.2cm},centering]{geometry}

        %%Set different options for xetex and luatex
        \\usepackage{iftex}
        \\ifxetex\\usepackage{fontspec}\\fi

        \\ifluatex\\usepackage{fontspec}\\fi

        \\hypersetup
        {   pdfauthor = {Pweave},
            pdftitle={Published from %s},
            colorlinks=TRUE,
            linkcolor=black,
            citecolor=blue,
            urlcolor=blue
        }
        \\setlength{\parindent}{0pt}
        \\setlength{\parskip}{1.2ex}
        %% fix for pandoc 1.14
        \\providecommand{\\tightlist}{%%
            \\setlength{\\itemsep}{0pt}\\setlength{\\parskip}{0pt}}
        %s
        """) % (self.source, x.get_style_defs())
        self.footer = r"\end{document}"
        self.subheader = "\n\\begin{document}\n"

    def add_header(self):
        """Can be used to add header to self.formatted list"""
        self.formatted = self.header + self.subheader + self.formatted

    def parsetitle(self, chunk):
        """Parse titleblock from first doc chunk, like Pandoc"""
        lines = chunk['content'].splitlines()
        if len(lines) > 3:
            if lines[0].startswith("%"):
                self.header += '\n\\title{%s}\n' % (lines[0].replace("%", "", ))
                lines[0] = ""
                if lines[1].startswith("%"):
                    self.header += '\\author{%s}\n' % (lines[1].replace("%", "", ))
                    lines[1] = ""
                if lines[2].startswith("%"):
                    self.header += '\\date{%s}\n' % (lines[2].replace("%", "", ))
                    lines[2] = ""
                self.subheader += "\maketitle\n"

        chunk['content'] = "\n".join(lines)
        return chunk

    def format_docchunk(self, chunk):
        if 'number' in chunk and chunk['number'] == 1:
            chunk = self.parsetitle(chunk)
        try:
            pandoc = Popen(["pandoc", "-t", "latex+raw_tex", "-f", "markdown"], stdin=PIPE, stdout=PIPE)
        except:
            sys.stderr.write("ERROR: Can't find pandoc")
            raise
        pandoc.stdin.write(chunk['content'].encode('utf-8'))
        chunk['content'] = pandoc.communicate()[0].decode('utf-8')
        return chunk['content']


class PwebFormats(object):
    """Contains a dictionary of available output formats"""
    formats = {'tex': {'class': PwebTexFormatter,
                       'description': 'Latex with verbatim for code and results'},
               'texminted': {'class': PwebMintedFormatter,
                             'description': 'Latex with predefined minted environment for codeblocks'},
               'texpweave': {'class': PwebTexPweaveFormatter,
                             'description': 'Latex output with user defined formatting using named environments (in latex header)'},
               'texpygments': {'class': PwebTexPygmentsFormatter,
                               'description': 'Latex output with pygments highlighted output'},
               'rst': {'class': PwebRstFormatter,
                       'description': 'reStructuredText'},
               'pandoc': {'class': PwebPandocFormatter,
                          'description': 'Pandoc markdown'},
               'markdown': {'class': PwebPandocFormatter, 'description':
                   'Pandoc markdown, same as format pandoc'},
               'leanpub': {'class': PwebLeanpubFormatter,
                           'description': 'Leanpub markdown'},
               'sphinx': {'class': PwebSphinxFormatter,
                          'description': 'reStructuredText for Sphinx'},
               'html': {'class': PwebHTMLFormatter,
                        'description': 'HTML with pygments highlighting'},
               'md2html': {'class': PwebMDtoHTMLFormatter,
                           'description': 'Markdown to HTML using Python-Markdown'},
               'softcover': {'class': PwebSoftCoverFormatter,
                            'description': 'SoftCover markdown'},
               'pandoc2latex': {'class': PwebPandoctoTexFormatter,
                                'description': 'Markdown to Latex using Pandoc, requires Pandoc in path'},
               'pandoc2html': {'class': PwebPandocMDtoHTMLFormatter,
                               'description': 'Markdown to HTML using Pandoc, requires Pandoc in path'}
                }

    @classmethod
    def getFormatter(cls, doctype):
        return cls.formats[doctype]['class']

    @classmethod
    def guessFromFilename(cls, filename):
        _, ext = os.path.splitext(filename)
        return cls.guessFromExtension(ext.lower())

    @staticmethod
    def guessFromExtension(ext):
        if ext in ('.pmd', ',py'): return 'markdown'
        if 'md' in ext: return 'markdown'
        if 'tex' in ext: return 'texpygments'
        if 'rst' in ext: return 'rst'
        if 'htm' in ext: return 'html'

        print("Can't autodetect output format, defaulting to reStructured text")
        return 'rst'

    @classmethod
    def shortformats(cls):
        fmtstring = ""
        names = list(cls.formats.keys())
        n = len(names)
        for i in range(n):
            fmtstring += " %s" % (names[i])
            if i < (n - 1):
                fmtstring += ","

        return fmtstring

    @classmethod
    def getformats(cls):
        fmtstring = ""
        for format in sorted(cls.formats):
            fmtstring += "* %s:\n   %s\n" % (format, cls.formats[format]['description'])
        return fmtstring

    @classmethod
    def listformats(cls):
        print("\nPweave supported output formats:\n")
        print(cls.getformats())
        print("More info: http://mpastell.com/pweave/formats.html \n")