File: ipython_directive.py

package info (click to toggle)
pykml 0.2.0%2Bdfsg-3
  • links: PTS, VCS
  • area: main
  • in suites: bookworm
  • size: 920 kB
  • sloc: python: 3,919; makefile: 108; sh: 8
file content (567 lines) | stat: -rw-r--r-- 15,656 bytes parent folder | download | duplicates (2)
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
import sys, os, shutil, imp, warnings, cStringIO, re

import IPython
from IPython.Shell import MatplotlibShell

try:
    from hashlib import md5
except ImportError:
    from md5 import md5

from docutils.parsers.rst import directives
import sphinx


sphinx_version = sphinx.__version__.split(".")
# The split is necessary for sphinx beta versions where the string is
# '6b1'
sphinx_version = tuple([int(re.split('[a-z]', x)[0])
                        for x in sphinx_version[:2]])



COMMENT, INPUT, OUTPUT =  range(3)
rgxin = re.compile('In \[(\d+)\]:\s?(.*)\s*')
rgxout = re.compile('Out\[(\d+)\]:\s?(.*)\s*')
fmtin = 'In [%d]:'
fmtout = 'Out[%d]:'

def block_parser(part):
    """
    part is a string of ipython text, comprised of at most one
    input, one ouput, comments, and blank lines.  The block parser
    parses the text into a list of::

      blocks = [ (TOKEN0, data0), (TOKEN1, data1), ...]
    where TOKEN is one of [COMMENT | INPUT | OUTPUT ] and
    data is, depending on the type of token::

      COMMENT : the comment string

      INPUT: the (DECORATOR, INPUT_LINE, REST) where
         DECORATOR: the input decorator (or None)
         INPUT_LINE: the input as string (possibly multi-line)
         REST : any stdout generated by the input line (not OUTPUT)


      OUTPUT: the output string, possibly multi-line

    """

    block = []
    lines = part.split('\n')
    #print 'PARSE', lines
    N = len(lines)
    i = 0
    decorator = None
    while 1:

        if i==N:
            # nothing left to parse -- the last line
            break

        line = lines[i]
        i += 1
        line_stripped = line.strip()
        if line_stripped.startswith('#'):
            block.append((COMMENT, line))
            continue


        if line_stripped.startswith('@'):
            # we're assuming at most one decorator -- may need to
            # rethink
            decorator = line_stripped
            continue

        # does this look like an input line?
        matchin = rgxin.match(line)
        if matchin:
            lineno, inputline = int(matchin.group(1)), matchin.group(2)

            # the ....: continuation string
            continuation = '   %s:'%''.join(['.']*(len(str(lineno))+2))
            Nc = len(continuation)
            # input lines can continue on for more than one line, if
            # we have a '\' line continuation char or a function call
            # echo line 'print'.  The input line can only be
            # terminated by the end of the block or an output line, so
            # we parse out the rest of the input line if it is
            # multiline as well as any echo text

            rest = []
            while i<N:

                # look ahead; if the next line is blank, or a comment, or
                # an output line, we're done

                nextline = lines[i]
                matchout = rgxout.match(nextline)
                #print "nextline=%s, continuation=%s, starts=%s"%(nextline, continuation, nextline.startswith(continuation))
                if matchout or nextline.startswith('#'):
                    break
                elif nextline.startswith(continuation):
                    inputline += '\n' + nextline[Nc:]
                else:
                    rest.append(nextline)
                i+= 1

            block.append((INPUT, (decorator, inputline, '\n'.join(rest))))
            continue

        # if it looks like an output line grab all the text to the end
        # of the block
        matchout = rgxout.match(line)
        if matchout:
            lineno, output = int(matchout.group(1)), matchout.group(2)
            if i<N-1:
                output = '\n'.join([output] + lines[i:])

            #print 'OUTPUT', output
            block.append((OUTPUT, output))
            break

    #print 'returning block', block
    return block



import matplotlib
matplotlib.use('Agg')


class EmbeddedSphinxShell:

    def __init__(self):

        self.cout = cStringIO.StringIO()

        IPython.Shell.Term.cout = self.cout
        IPython.Shell.Term.cerr = self.cout
        argv = ['-autocall', '0']
        self.user_ns = {}
        self.user_glocal_ns = {}

        self.IP = IPython.ipmaker.make_IPython(
            argv, self.user_ns, self.user_glocal_ns, embedded=True,
            #shell_class=IPython.Shell.InteractiveShell,
            shell_class=MatplotlibShell,
            rc_override=dict(colors = 'NoColor'))

        self.input = ''
        self.output = ''

        self.is_verbatim = False
        self.is_doctest = False
        self.is_suppress = False

        # on the first call to the savefig decorator, we'll import
        # pyplot as plt so we can make a call to the plt.gcf().savefig
        self._pyplot_imported = False

        # we need bookmark the current dir first so we can save
        # relative to it
        self.process_input('bookmark ipy_basedir')
        self.cout.seek(0)
        self.cout.truncate(0)

    def process_input(self, line):
        'process the input, capturing stdout'
        #print "input='%s'"%self.input
        stdout = sys.stdout
        sys.stdout = self.cout
        #self.IP.resetbuffer()
        self.IP.push(self.IP.prefilter(line, 0))
        #self.IP.runlines(line)
        sys.stdout = stdout


    def process_block(self, block):
        """
        process block from the block_parser and return a list of processed lines
        """

        #print 'BLOCK', block
        ret = []

        output = None
        input_lines = None

        m = rgxin.match(str(self.IP.outputcache.prompt1).strip())
        lineno = int(m.group(1))

        input_prompt = fmtin%lineno
        output_prompt = fmtout%lineno
        image_file = None
        image_directive = None
        for token, data in block:

            if token==COMMENT:
                if not self.is_suppress:
                    ret.append(data)

            elif token==INPUT:

                decorator, input, rest = data
                #print 'INPUT:', data
                is_verbatim = decorator=='@verbatim' or self.is_verbatim
                is_doctest = decorator=='@doctest' or self.is_doctest
                is_suppress = decorator=='@suppress' or self.is_suppress
                is_savefig = decorator is not None and decorator.startswith('@savefig')
                #print 'is_verbatim=%s, is_doctest=%s, is_suppress=%s, is_savefig=%s'%(is_verbatim, is_doctest, is_suppress, is_savefig)
                input_lines = input.split('\n')


                continuation = '   %s:'%''.join(['.']*(len(str(lineno))+2))
                Nc = len(continuation)

                if is_savefig:
                    saveargs = decorator.split(' ')
                    filename = saveargs[1]
                    outfile = os.path.join('_static/%s'%filename)
                    # build out an image directive like
                    # .. image:: somefile.png
                    #    :width 4in
                    #
                    # from an input like
                    # savefig somefile.png width=4in
                    imagerows = ['.. image:: %s'%outfile]

                    for kwarg in saveargs[2:]:
                        arg, val = kwarg.split('=')
                        arg = arg.strip()
                        val = val.strip()
                        imagerows.append('   :%s: %s'%(arg, val))


                    image_file = outfile
                    image_directive = '\n'.join(imagerows)



                # TODO: can we get "rest" from ipython
                #self.process_input('\n'.join(input_lines))


                is_semicolon = False
                for i, line in enumerate(input_lines):
                    if line.endswith(';'):
                        is_semicolon = True

                    if i==0:
                        # process the first input line
                        if is_verbatim:
                            self.process_input('')
                        else:
                            # only submit the line in non-verbatim mode
                            self.process_input(line)
                        formatted_line = '%s %s'%(input_prompt, line)
                    else:
                        # process a continuation line
                        if not is_verbatim:
                            self.process_input(line)

                        formatted_line = '%s %s'%(continuation, line)


                    if not is_suppress:
                        ret.append(formatted_line)

                if not is_suppress:
                    if len(rest.strip()):
                        if is_verbatim:
                            # the "rest" is the standard output of the
                            # input, which needs to be added in
                            # verbatim mode
                            ret.append("%s"%rest)
                            ret.append('')

                self.cout.seek(0)
                output = self.cout.read()
                if not is_suppress and not is_semicolon and not is_verbatim:
                    ret.append(output)

                self.cout.truncate(0)




            elif token==OUTPUT:
                #print 'token==OUTPUT is_verbatim=%s'%is_verbatim
                if is_verbatim:
                    # construct a mock output prompt
                    output = '%s %s\n'%(fmtout%lineno, data)
                    ret.append(output)

                #print 'token==OUTPUT', output
                if is_doctest:
                    submitted = data.strip()
                    found = output
                    if found is not None:
                        ind = found.find(output_prompt)
                        if ind<0:
                            raise RuntimeError('output prompt="%s" does not match out line=%s'%(output_prompt, found))
                        found = found[len(output_prompt):].strip()

                        if found!=submitted:
                            raise RuntimeError('doctest failure for input_lines="%s" with found_output="%s" and submitted output="%s"'%(input_lines, found, submitted))
                        #print 'doctest PASSED for input_lines="%s" with found_output="%s" and submitted output="%s"'%(input_lines, found, submitted)


        if image_file is not None:
            self.insure_pyplot()
            command = 'plt.gcf().savefig("%s")'%image_file
            #print 'SAVEFIG', command
            self.process_input('bookmark ipy_thisdir')
            self.process_input('cd -b ipy_basedir')
            self.process_input(command)
            self.process_input('cd -b ipy_thisdir')
            self.cout.seek(0)
            self.cout.truncate(0)

        #print 'returning', ret, figure
        return ret, image_directive


    def insure_pyplot(self):
        if self._pyplot_imported:
            return
        self.process_input('import matplotlib.pyplot as plt')



shell = EmbeddedSphinxShell()


def ipython_directive(name, arguments, options, content, lineno,
                      content_offset, block_text, state, state_machine,
                      ):

    debug = ipython_directive.DEBUG
    shell.is_suppress = options.has_key('suppress')
    shell.is_doctest = options.has_key('doctest')
    shell.is_verbatim = options.has_key('verbatim')

    #print 'ipy', shell.is_suppress, options
    parts = '\n'.join(content).split('\n\n')
    lines = ['.. sourcecode:: ipython', '']

    figures = []
    for part in parts:
        block = block_parser(part)

        if len(block):
            rows, figure = shell.process_block(block)
            for row in rows:
                lines.extend(['    %s'%line for line in row.split('\n')])

            if figure is not None:
                figures.append(figure)

    for figure in figures:
        lines.append('')
        lines.extend(figure.split('\n'))
        lines.append('')

    #print lines
    if len(lines)>2:
        if debug:
            print '\n'.join(lines)
        else:
            #print 'INSERTING %d lines'%len(lines)
            state_machine.insert_input(
                lines, state_machine.input_lines.source(0))

    return []

ipython_directive.DEBUG = False

def setup(app):
    setup.app = app
    options = {
        'suppress': directives.flag,
        'doctest': directives.flag,
        'verbatim': directives.flag,
        }


    app.add_directive('ipython', ipython_directive, True, (0, 2, 0), **options)


def test():

    examples = [
        r"""
In [9]: pwd
Out[9]: '/home/jdhunter/py4science/book'

In [10]: cd bookdata/
/home/jdhunter/py4science/book/bookdata

In [2]: from pylab import *

In [2]: ion()

In [3]: im = imread('stinkbug.png')

@savefig mystinkbug.png width=4in
In [4]: imshow(im)
Out[4]: <matplotlib.image.AxesImage object at 0x39ea850>

""",
        r"""

In [1]: x = 'hello world'

# string methods can be
# used to alter the string
@doctest
In [2]: x.upper()
Out[2]: 'HELLO WORLD'

@verbatim
In [3]: x.st<TAB>
x.startswith  x.strip
""",
    r"""

In [130]: url = 'http://ichart.finance.yahoo.com/table.csv?s=CROX\
   .....: &d=9&e=22&f=2009&g=d&a=1&br=8&c=2006&ignore=.csv'

In [131]: print url.split('&')
--------> print(url.split('&'))
['http://ichart.finance.yahoo.com/table.csv?s=CROX', 'd=9', 'e=22', 'f=2009', 'g=d', 'a=1', 'b=8', 'c=2006', 'ignore=.csv']

In [60]: import urllib

""",
    r"""\

In [133]: import numpy.random

@suppress
In [134]: numpy.random.seed(2358)

@doctest
In [135]: np.random.rand(10,2)
Out[135]:
array([[ 0.64524308,  0.59943846],
       [ 0.47102322,  0.8715456 ],
       [ 0.29370834,  0.74776844],
       [ 0.99539577,  0.1313423 ],
       [ 0.16250302,  0.21103583],
       [ 0.81626524,  0.1312433 ],
       [ 0.67338089,  0.72302393],
       [ 0.7566368 ,  0.07033696],
       [ 0.22591016,  0.77731835],
       [ 0.0072729 ,  0.34273127]])

""",

    r"""
In [106]: print x
--------> print(x)
jdh

In [109]: for i in range(10):
   .....:     print i
   .....:
   .....:
0
1
2
3
4
5
6
7
8
9


""",

        r"""

In [144]: from pylab import *

In [145]: ion()

# use a semicolon to suppress the output
@savefig test_hist.png width=4in
In [151]: hist(np.random.randn(10000), 100);


@savefig test_plot.png width=4in
In [151]: plot(np.random.randn(10000), 'o');
   """,

        r"""
# use a semicolon to suppress the output
In [151]: plt.clf()

@savefig plot_simple.png width=4in
In [151]: plot([1,2,3])

@savefig hist_simple.png width=4in
In [151]: hist(np.random.randn(10000), 100);

""",
     r"""
# update the current fig
In [151]: ylabel('number')

In [152]: title('normal distribution')


@savefig hist_with_text.png
In [153]: grid(True)

        """,


        r"""

In [239]: 1/2
@verbatim
Out[239]: 0

In [240]: 1.0/2.0
Out[240]: 0.5
""",

        r"""
@verbatim
In [6]: pwd
Out[6]: '/home/jdhunter/mypy'
""",

        r"""
@verbatim
In [151]: myfile.upper?
Type:           builtin_function_or_method
Base Class:     <type 'builtin_function_or_method'>
String Form:    <built-in method upper of str object at 0x980e2f0>
Namespace:      Interactive
Docstring:
    S.upper() -> string
    Return a copy of the string S converted to uppercase.
 """
    ]



    ipython_directive.DEBUG = True
    #options = dict(suppress=True)
    options = dict()
    for example in examples:
        content = example.split('\n')
        ipython_directive('debug', arguments=None, options=options,
                          content=content, lineno=0,
                          content_offset=None, block_text=None,
                          state=None, state_machine=None,
                          )


if __name__=='__main__':
    test()