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
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
|
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"id": "07ebb5d3",
"metadata": {},
"outputs": [],
"source": [
"%%capture\n",
"%load_ext autoreload\n",
"%autoreload 2"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b92ad576",
"metadata": {},
"outputs": [],
"source": [
"#| default_exp: export"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "96525ac4",
"metadata": {},
"outputs": [],
"source": [
"#| export\n",
"import enum,pathlib,re\n",
"from pathlib import Path\n",
"from typing import IO\n",
"\n",
"import nbformat\n",
"from nbformat import NotebookNode"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "eb27bbd6",
"metadata": {},
"outputs": [],
"source": [
"import os,json,tempfile\n",
"from io import StringIO"
]
},
{
"cell_type": "markdown",
"id": "a682b39f",
"metadata": {},
"source": [
"# Exporting Notebooks to Python Files"
]
},
{
"cell_type": "markdown",
"id": "a21a7e2c",
"metadata": {},
"source": [
"To get our notebook-driven source code bootstrapped, we'll first need to be able to convert `ipynb` files to `py` files. Without that, we'd be unable to later import code we want to use in one notebook from another notebook because it's not in a plain importable Python file yet.\n",
"\n",
"To accomplish that, for any given code well, we'll need to know:\n",
"- What Python file are we exporting our notebook to?\n",
"- Which cells are we exporting to our Python file?\n",
"\n",
"The approach tools like [nbdev](https://nbdev.fast.ai/) or [nbexport](https://github.com/danhorner/nbexport) take is to have certain directives that determine the code export behavior:\n",
"- `#|default_exp: mymodule`: Set the output module for this notebook\n",
"- `#|export`: Export this cell to the corresponding Python file"
]
},
{
"cell_type": "markdown",
"id": "3b670537",
"metadata": {},
"source": [
"To export a notebook, we'll need to:\n",
"1. Read in a ipynb notebook\n",
"2. Retrieve all code cells from the notebook\n",
"3. Find all cells that should be exported:\n",
" - Each notebook must have 1 (and only 1) `#| default_exp`. When a `#| default_exp` is found, it must be a single word e.g. `mymodule` or a dotted path e.g. `mymodules.other_module`. If it is a dotted path, the submodules created should have `__init__.py` files also created alongside them.\n",
" - Any cells with an `#| export` explicit directive should be marked for export.\n",
"4. Write out each cell sequentially into the Python file, stripping out any directives. When each cell is written out, it should have a comment above it describing the cell ID it came from."
]
},
{
"cell_type": "markdown",
"id": "f1c95690",
"metadata": {},
"source": [
"## Reading Notebooks"
]
},
{
"cell_type": "markdown",
"id": "037fb28c",
"metadata": {},
"source": [
"To read in `ipynb` files, we can use a library provided Jupyter called `nbformat`. And simply because we'll be reading in this notebook as our working copy while developing this export behavior, let's add a raw cell just so we have an example of all 3 cell types."
]
},
{
"cell_type": "raw",
"id": "d9f3cb10",
"metadata": {},
"source": [
"This is a raw cell just to have an example."
]
},
{
"cell_type": "markdown",
"id": "4c0671ed",
"metadata": {},
"source": [
"Now, we can read in our current notebook:"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "29a65b22",
"metadata": {},
"outputs": [],
"source": [
"#| export\n",
"type PathOrFileLike = str|Path|IO[str]"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "27202360",
"metadata": {},
"outputs": [],
"source": [
"#| export\n",
"def read_nb(\n",
" fp:PathOrFileLike, # Where to read the notebook from.\n",
" v:int=4, # The notebook format major version to read the notebook as.\n",
")->NotebookNode:\n",
" \"Read in a notebook as a dictionary-like NotebookNode.\"\n",
" return nbformat.read(fp, as_version=v)\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a689a07b",
"metadata": {},
"outputs": [],
"source": [
"for fp in ['export.ipynb', Path('export.ipynb')]:\n",
" nb = read_nb(fp)\n",
" assert list(nb.keys()) == ['cells', 'metadata', 'nbformat', 'nbformat_minor']\n",
" assert type(nb) == NotebookNode"
]
},
{
"cell_type": "markdown",
"id": "7d133fff",
"metadata": {},
"source": [
"We can see that the top-level format of a notebook is:\n",
"- `cells`: A list of objects for each cell in the notebook.\n",
"- `metadata`: Free-form notebook level metadata used by tools and editors.\n",
"- `nbformat`: Notebook format major version\n",
"- `nbformat_minor`: Notebook format minor version"
]
},
{
"cell_type": "markdown",
"id": "10a6afcb",
"metadata": {},
"source": [
"Within cells, there are generally 3 types of cells:\n",
"- `code`\n",
"- `markdown`\n",
"- `raw`"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "1ee0d459",
"metadata": {},
"outputs": [],
"source": [
"#| export\n",
"class CellType(enum.StrEnum):\n",
" \"Possible Jupyter notebook cell types.\"\n",
" CODE = 'code'\n",
" MD = 'markdown'\n",
" RAW = 'raw'"
]
},
{
"cell_type": "markdown",
"id": "46ed0445",
"metadata": {},
"source": [
"## Retrieving All Code Cells"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "133ebd88",
"metadata": {},
"outputs": [],
"source": [
"#| export\n",
"def filter_cells(\n",
" nb:NotebookNode, # A notebook that has been read in via `read_nb`.\n",
" ct:CellType, # The cells to filter down to.\n",
")->list[NotebookNode]:\n",
" \"Retrieve specific cell types from a notebook.\"\n",
" return list(filter(lambda c: c['cell_type'] == ct, nb['cells']))"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "76917bc5",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'cell_type': 'code',\n",
" 'execution_count': None,\n",
" 'id': '07ebb5d3',\n",
" 'metadata': {},\n",
" 'outputs': [],\n",
" 'source': '%%capture\\n%load_ext autoreload\\n%autoreload 2'}"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"code_cell = filter_cells(nb, CellType.CODE)[0]\n",
"assert list(code_cell.keys()) == ['cell_type', 'execution_count', 'id', 'metadata', 'outputs', 'source']\n",
"assert code_cell['cell_type'] == CellType.CODE\n",
"code_cell"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4186fffe",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'cell_type': 'markdown',\n",
" 'id': 'a682b39f',\n",
" 'metadata': {},\n",
" 'source': '# Exporting Notebooks to Python Files'}"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"md_cell = filter_cells(nb, CellType.MD)[0]\n",
"assert list(md_cell.keys()) == ['cell_type', 'id', 'metadata', 'source']\n",
"assert md_cell['cell_type'] == CellType.MD\n",
"md_cell"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "46e56abf",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'cell_type': 'raw',\n",
" 'id': 'd9f3cb10',\n",
" 'metadata': {},\n",
" 'source': 'This is a raw cell just to have an example.'}"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"raw_cell = filter_cells(nb, CellType.RAW)[0]\n",
"assert list(raw_cell.keys()) == ['cell_type', 'id', 'metadata', 'source']\n",
"assert raw_cell['cell_type'] == CellType.RAW\n",
"raw_cell"
]
},
{
"cell_type": "markdown",
"id": "4852b261",
"metadata": {},
"source": [
"Within each cell object, they will all have:\n",
"- `id`: A unique identifier for that cell.\n",
"- `cell_type`: One of the 3 cell type names.\n",
"- `metadata`: Free-form metadata for that cell used by various tools/editors.\n",
"- `source`: The content of the cell, whether it is prose or code.\n",
"\n",
"Additionally, `code` cell types will have:\n",
"- `outputs`: The stdout/stderr of the cell after the code is executed.\n",
"- `execution_count`: The number of times the cell was run."
]
},
{
"cell_type": "markdown",
"id": "6b7469e3",
"metadata": {},
"source": [
"## Find Code Cells to Export"
]
},
{
"cell_type": "markdown",
"id": "798249d5",
"metadata": {},
"source": [
"### Matching Directives"
]
},
{
"cell_type": "markdown",
"id": "f671cafa",
"metadata": {},
"source": [
"A regular expression ran against each line in a cell should allow us to find each directive we support. Since we'll need to re-create this regression expression for a few directives, we'll create a small helper."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "83a898c2",
"metadata": {},
"outputs": [],
"source": [
"#| export\n",
"def _mk_directive_re(\n",
" name:str, # The name of the directive\n",
" arg_re:str|None=None, # A regex pattern to match an argument for the directive\n",
")->re.Pattern:\n",
" \"Compile a regex to match a directive, optionally supporting an argument.\"\n",
" arg = rf':\\s*{arg_re}' if arg_re else ''\n",
" return re.compile(rf'^\\s*#\\|\\s*{name}{arg}\\s*$')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "698d769b",
"metadata": {},
"outputs": [],
"source": [
"_TEST_DIRECTIVE_RE = _mk_directive_re('test')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f6d654fd",
"metadata": {},
"outputs": [],
"source": [
"test_dir_match = [\n",
" ' #| test \\t \\n', # Lots of whitespace around each token\n",
" '#|test', # No whitespace around each token\n",
"]\n",
"for line in test_dir_match:\n",
" assert _TEST_DIRECTIVE_RE.match(line), f\"No match: {line!r}\""
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "02f06ee6",
"metadata": {},
"outputs": [],
"source": [
"test_dir_no_match = [\n",
" '| test', # Missing #\n",
" '# test', # Missing |\n",
" '#| testt', # Misspelled directive\n",
" '#| test test', # Extra word after directive\n",
"]\n",
"for line in test_dir_no_match:\n",
" assert not _TEST_DIRECTIVE_RE.match(line), f\"Unexpected match: {line!r}\""
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "285e2320",
"metadata": {},
"outputs": [],
"source": [
"_TEST_ARG_DIRECTIVE_RE = _mk_directive_re('test', arg_re=r'\\w')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "83fd068c",
"metadata": {},
"outputs": [],
"source": [
"test_dir_arg_match = [\n",
" ' #| test: \\t a \\n', # Lots of whitespace around each token\n",
" '#|test:b', # No whitespace around each token\n",
"]\n",
"for line in test_dir_arg_match:\n",
" assert _TEST_ARG_DIRECTIVE_RE.match(line), f\"No match: {line!r}\""
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "dd9945ab",
"metadata": {},
"outputs": [],
"source": [
"test_arg_dir_no_match = [\n",
" '#| test a', # Missing :\n",
" '#| test: ', # Missing arg\n",
" '#| test: aa', # Invalid arg (should be only 1 letter)\n",
"]\n",
"for line in test_dir_no_match + test_arg_dir_no_match:\n",
" assert not _TEST_ARG_DIRECTIVE_RE.match(line), f\"Unexpected match: {line!r}\""
]
},
{
"cell_type": "markdown",
"id": "dfd6ac40",
"metadata": {},
"source": [
"#### Supporting the default_exp directive"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ac846aaa",
"metadata": {},
"outputs": [],
"source": [
"#| export\n",
"DIRECTIVE_DEFAULT_EXP_RE = _mk_directive_re('default_exp', arg_re=r'(?P<module>\\w+(\\.\\w+)*)')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "5f890ed5",
"metadata": {},
"outputs": [],
"source": [
"matching_cells = [\n",
" ('#| default_exp: bootstrap', 'bootstrap'), # Module name\n",
" ('#| default_exp: bootstrap.another_module', 'bootstrap.another_module'), # Dotted module path\n",
"]\n",
"for line, module in matching_cells:\n",
" match = DIRECTIVE_DEFAULT_EXP_RE.match(line)\n",
" assert match, f\"No match: {line!r}\"\n",
" assert match.group('module') == module"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d1f22bb8",
"metadata": {},
"outputs": [],
"source": [
"not_matching_cells = [\n",
" '#| default_exp: ', # Missing module name\n",
" '#| default_exp: !$', # Invalid module name\n",
" '#| default_export: bootstrap', # Misspelled directive\n",
" '#| default_exp: bootstrap.', # Dot without a following word\n",
" '#| default_exp: bootstrap..', # Too many dots without a word in between\n",
"]\n",
"for line in not_matching_cells:\n",
" assert not DIRECTIVE_DEFAULT_EXP_RE.match(line), f\"Unexpected match: {line!r}\""
]
},
{
"cell_type": "markdown",
"id": "50495b37",
"metadata": {},
"source": [
"#### Supporting the export directive"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "5b4e8fe6",
"metadata": {},
"outputs": [],
"source": [
"#| export\n",
"DIRECTIVE_EXPORT_RE = _mk_directive_re('export')"
]
},
{
"cell_type": "markdown",
"id": "a7a778d2",
"metadata": {},
"source": [
"#### All Directives"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "828159b2",
"metadata": {},
"outputs": [],
"source": [
"#| export\n",
"DIRECTIVES = [DIRECTIVE_DEFAULT_EXP_RE, DIRECTIVE_EXPORT_RE]"
]
},
{
"cell_type": "markdown",
"id": "21e3d799",
"metadata": {},
"source": [
"### Identifying Cells to Export"
]
},
{
"cell_type": "markdown",
"id": "295b4a99",
"metadata": {},
"source": [
"So, we should now have all the pieces to determine find all cells we should be exporting and the module we should be exporting to.\n",
"\n",
"**Algorithm:**\n",
"1. Always check if there is a `default_exp` directive. There must be one (and only one) `default_exp` directive.\n",
"3. Check for an explicit export directive."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d327883e",
"metadata": {},
"outputs": [],
"source": [
"#| export\n",
"def has_directive(src:str)->bool:\n",
" \"Check whether a line or block of source code has a nb directive.\"\n",
" return any(any(r.match(l) for r in DIRECTIVES) for l in src.splitlines())"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "6ea5e776",
"metadata": {},
"outputs": [],
"source": [
"assert has_directive('#| default_exp: bootstrap')\n",
"assert has_directive('#| export')\n",
"assert has_directive('max(1,20)\\n#| export')\n",
"assert not has_directive('# comment\\nmax(1, 20)\\n')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b6f47497",
"metadata": {},
"outputs": [],
"source": [
"#| export\n",
"def strip_directives(src:str|list[str])->str:\n",
" \"Remove all nb directives from the source code.\"\n",
" src = src if isinstance(src, list) else src.splitlines()\n",
" return \"\\n\".join(filter(lambda l: not has_directive(l), src))"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7acbb8ff",
"metadata": {},
"outputs": [],
"source": [
"assert strip_directives('#| export\\na=5') == 'a=5'\n",
"assert strip_directives('#| default_exp: bootstrap\\na=5') == 'a=5'\n",
"assert strip_directives(['a=10', 'a+=10', '#|export']) == 'a=10\\na+=10'"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d1f32654",
"metadata": {},
"outputs": [],
"source": [
"#| export\n",
"def is_cell_exported(cell:NotebookNode)->bool:\n",
" \"Check whether the code cell should be exported.\"\n",
" return any(DIRECTIVE_EXPORT_RE.match(l) for l in cell['source'].splitlines())"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "64175ad3",
"metadata": {},
"outputs": [],
"source": [
"mk_cell = lambda s,id=1: dict(id=id,source=s,cell_type=CellType.CODE)\n",
"assert is_cell_exported(mk_cell('#| export'))\n",
"assert is_cell_exported(mk_cell('import re\\n#| export'))\n",
"assert not is_cell_exported(mk_cell('import re'))\n",
"assert not is_cell_exported(mk_cell('1+1\\nfrom re import Pattern'))"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ddc5c9e6",
"metadata": {},
"outputs": [],
"source": [
"#| export\n",
"def get_default_export(cells:list[NotebookNode])->str:\n",
" \"Retrieve the `default_exp` directive argument from a list of cells.\"\n",
" matches = [\n",
" m.group('module')\n",
" for c in cells\n",
" for l in c['source'].splitlines()\n",
" if c['cell_type'] == CellType.CODE and (m:=DIRECTIVE_DEFAULT_EXP_RE.match(l))\n",
" ]\n",
" if len(matches) > 1: raise ValueError('More than one default_exp directive')\n",
" if len(matches) == 0: raise ValueError('Missing default_exp directive')\n",
" return matches[0]"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7310f069",
"metadata": {},
"outputs": [],
"source": [
"assert get_default_export(read_nb('export.ipynb')['cells']) == 'export'\n",
"\n",
"try: get_default_export([mk_cell('a=5')]); assert False, \"Expected ValueError\"\n",
"except ValueError: pass\n",
"\n",
"try:\n",
" get_default_export([mk_cell('#| default_exp: hello'), mk_cell('#| default_exp: test')])\n",
" assert False, \"Expected ValueError\"\n",
"except ValueError: pass"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9ce855f0",
"metadata": {},
"outputs": [],
"source": [
"#| export\n",
"def find_cells_to_export(\n",
" fp:PathOrFileLike|NotebookNode, # Where to read the notebook from.\n",
")->tuple[str,list[NotebookNode]]: # Returns the module name and list of cells to export.\n",
" \"Find the code cells in an ipynb file to export out.\"\n",
" if not isinstance(fp, NotebookNode): fp = read_nb(fp)\n",
" code_cells = filter_cells(fp, CellType.CODE)\n",
" module = get_default_export(code_cells)\n",
" cells = [\n",
" {**c, 'source': strip_directives(c['source'])}\n",
" for c in code_cells\n",
" if is_cell_exported(c)\n",
" ]\n",
" return module, cells"
]
},
{
"cell_type": "markdown",
"id": "aa285ef2",
"metadata": {},
"source": [
"If a notebook has a `default_exp` directive and exported cells, we should see those extracted out and the directive comments stripped out."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ffaa9942",
"metadata": {},
"outputs": [],
"source": [
"nb = nbformat.v4.new_notebook()\n",
"nb.cells = [\n",
" nbformat.v4.new_code_cell('#| default_exp: mymodule'),\n",
" nbformat.v4.new_code_cell('#| export\\ndef hello(): return \"hi\"'),\n",
"]\n",
"assert find_cells_to_export(nb) == ('mymodule', [{**nb.cells[1], 'source': 'def hello(): return \"hi\"'}])"
]
},
{
"cell_type": "markdown",
"id": "85a57955",
"metadata": {},
"source": [
"Additionally, we can pass in a path to a notebook rather than an in-memory notebook. If no cell is exported, the cells to export will be empty."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "329abbe7",
"metadata": {},
"outputs": [],
"source": [
"nb = nbformat.v4.new_notebook(cells=[nbformat.v4.new_code_cell('#| default_exp: mymodule')])\n",
"with tempfile.TemporaryDirectory() as tmp:\n",
" p = tmp/Path('test.ipynb')\n",
" p.write_text(json.dumps(nb))\n",
" assert find_cells_to_export(p) == ('mymodule', [])"
]
},
{
"cell_type": "markdown",
"id": "9e1d96de",
"metadata": {},
"source": [
"An empty notebook should raise a `ValueError` because it doesn't have a `default_exp` directive."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "2c349b45",
"metadata": {},
"outputs": [],
"source": [
"nb = nbformat.v4.new_notebook()\n",
"try: find_cells_to_export(nb); assert False\n",
"except ValueError: pass"
]
},
{
"cell_type": "markdown",
"id": "66574d29",
"metadata": {},
"source": [
"## Exporting a Notebook"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "3070f710",
"metadata": {},
"outputs": [],
"source": [
"#| export\n",
"def fmt_export_cell(cell:dict)->dict:\n",
" \"Format a code cell's source with metadata to prepare for export.\"\n",
" cell['source'] = f'# cell: {cell[\"id\"]}\\n' + cell['source'] + '\\n'\n",
" return cell"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e24f633f",
"metadata": {},
"outputs": [],
"source": [
"assert fmt_export_cell(mk_cell('a=5', id=1))['source'] == '# cell: 1\\na=5\\n'"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "633e256b",
"metadata": {},
"outputs": [],
"source": [
"#| export\n",
"def mk_py_mod_scaffold(\n",
" mod:str, # The Python module name or dotted path e.g. mod.mymod.file\n",
" src_dir:str|Path, # The Python package source code directory scaffold\n",
"):\n",
" \"Create all intermediary __init__.py files and directories, if any, and the final .py file.\"\n",
" if not mod: raise ValueError('The module path cannot be empty')\n",
" src_dir = Path(src_dir)\n",
" mod_file = (src_dir/Path(*mod.split('.'))).with_suffix('.py')\n",
" mod_file.parent.mkdir(parents=True, exist_ok=True)\n",
" mod_file.touch()\n",
" pkg_dirs = list(mod_file.parents)\n",
" for p in pkg_dirs[:pkg_dirs.index(src_dir) + 1]:\n",
" (p / '__init__.py').touch()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e19b3289",
"metadata": {},
"outputs": [],
"source": [
"with tempfile.TemporaryDirectory() as tmp:\n",
" try: mk_py_mod_scaffold('', src_dir=tmp); assert False, \"Should raise ValueError\"\n",
" except ValueError: pass\n",
" assert os.listdir(tmp) == []"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c3a33968",
"metadata": {},
"outputs": [],
"source": [
"with tempfile.TemporaryDirectory() as tmp:\n",
" mk_py_mod_scaffold('file', src_dir=tmp)\n",
" assert os.listdir(tmp) == ['__init__.py', 'file.py']"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f2e3fcb4",
"metadata": {},
"outputs": [],
"source": [
"with tempfile.TemporaryDirectory() as tmp:\n",
" mk_py_mod_scaffold('mod.file', src_dir=tmp)\n",
" assert os.listdir(tmp) == ['__init__.py', 'mod']\n",
" assert os.listdir(Path(tmp)/'mod') == ['__init__.py', 'file.py']"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f3ab7819",
"metadata": {},
"outputs": [],
"source": [
"#| export\n",
"def export_nb(\n",
" fp:PathOrFileLike|NotebookNode, # The notebook to export.\n",
" src_dir:str|Path='.', # The source directory to export the Python module to.\n",
"):\n",
" \"Export the exportable code cells to a Python file.\"\n",
" module, cells = find_cells_to_export(fp)\n",
" mk_py_mod_scaffold(module, src_dir)\n",
" exp_path = (Path(src_dir)/module).with_suffix('.py')\n",
" src = '\\n'.join(\n",
" ['# AUTOGENERATED! DO NOT EDIT!\\n'] +\n",
" list(map(lambda c: fmt_export_cell(c)['source'], cells))\n",
" )\n",
" Path(exp_path).write_text(src)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "55f57bee",
"metadata": {},
"outputs": [],
"source": [
"def mk_nb(cells)->StringIO:\n",
" nb = nbformat.v4.new_notebook(cells=cells)\n",
" buf = StringIO()\n",
" nbformat.write(nb, buf)\n",
" buf.seek(0)\n",
" return buf"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "31bb0f0b",
"metadata": {},
"outputs": [],
"source": [
"cells = [\n",
" nbformat.v4.new_code_cell('#| default_exp: testmod'),\n",
" nbformat.v4.new_code_cell('#| export \\nimport os'),\n",
" nbformat.v4.new_code_cell('#| export\\ndef foo(): pass'),\n",
" nbformat.v4.new_code_cell('import pathlib'),\n",
"]\n",
"nb = mk_nb(cells)\n",
"src = f\"\"\"# AUTOGENERATED! DO NOT EDIT!\n",
"\n",
"# cell: {cells[1]['id']}\n",
"import os\n",
"\n",
"# cell: {cells[2]['id']}\n",
"def foo(): pass\n",
"\"\"\"\n",
"with tempfile.TemporaryDirectory() as tmp:\n",
" export_nb(nb, src_dir=tmp)\n",
" result = Path(tmp, 'testmod.py').read_text()\n",
" assert result == src, result"
]
},
{
"cell_type": "markdown",
"id": "e7c49602",
"metadata": {},
"source": [
"And...we've successfully bootstrapped our notebook! Let's export it out."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "8e1d4096",
"metadata": {},
"outputs": [],
"source": [
"export_nb('export.ipynb', src_dir='../nb/')"
]
}
],
"metadata": {},
"nbformat": 4,
"nbformat_minor": 5
}
|