Mercurial > repos > shellac > guppy_basecaller
comparison env/lib/python3.7/site-packages/planemo/training/tutorial.py @ 5:9b1c78e6ba9c draft default tip
"planemo upload commit 6c0a8142489327ece472c84e558c47da711a9142"
author | shellac |
---|---|
date | Mon, 01 Jun 2020 08:59:25 -0400 |
parents | 79f47841a781 |
children |
comparison
equal
deleted
inserted
replaced
4:79f47841a781 | 5:9b1c78e6ba9c |
---|---|
1 """Module contains code for the Tutorial class, dealing with the creation of a training tutorial.""" | |
2 | |
3 import collections | |
4 import json | |
5 import os | |
6 import re | |
7 import shutil | |
8 | |
9 import oyaml as yaml | |
10 import requests | |
11 import six | |
12 | |
13 from planemo import templates | |
14 from planemo.bioblend import galaxy | |
15 from planemo.engine import ( | |
16 engine_context, | |
17 is_galaxy_engine, | |
18 ) | |
19 from planemo.io import info | |
20 from planemo.runnable import for_path | |
21 from .tool_input import ( | |
22 get_empty_input, | |
23 get_empty_param, | |
24 ToolInput | |
25 ) | |
26 from .utils import ( | |
27 load_yaml, | |
28 save_to_yaml | |
29 ) | |
30 | |
31 TUTO_HAND_ON_TEMPLATE = """--- | |
32 layout: tutorial_hands_on | |
33 | |
34 {{ metadata }} | |
35 --- | |
36 | |
37 {{ body }} | |
38 """ | |
39 | |
40 TUTO_SLIDES_TEMPLATE = """--- | |
41 layout: tutorial_slides | |
42 logo: "GTN" | |
43 | |
44 {{ metadata }} | |
45 --- | |
46 | |
47 ### How to fill the slide decks? | |
48 | |
49 Please follow our | |
50 [tutorial to learn how to fill the slides]({{ '{{' }} site.baseurl {{ '}}' }}/topics/contributing/tutorials/create-new-tutorial-slides/slides.html) | |
51 """ | |
52 | |
53 | |
54 HANDS_ON_TOOL_BOX_TEMPLATE = """ | |
55 ## Sub-step with **{{tool_name}}** | |
56 | |
57 > ### {{ '{%' }} icon hands_on {{ '%}' }} Hands-on: Task description | |
58 > | |
59 > 1. **{{tool_name}}** {{ '{%' }} icon tool {{ '%}' }} with the following parameters:{{inputlist}}{{paramlist}} | |
60 > | |
61 > ***TODO***: *Check parameter descriptions* | |
62 > | |
63 > ***TODO***: *Consider adding a comment or tip box* | |
64 > | |
65 > > ### {{ '{%' }} icon comment {{ '%}' }} Comment | |
66 > > | |
67 > > A comment about the tool or something else. This box can also be in the main text | |
68 > {: .comment} | |
69 > | |
70 {: .hands_on} | |
71 | |
72 ***TODO***: *Consider adding a question to test the learners understanding of the previous exercise* | |
73 | |
74 > ### {{ '{%' }} icon question {{ '%}' }} Questions | |
75 > | |
76 > 1. Question1? | |
77 > 2. Question2? | |
78 > | |
79 > > ### {{ '{%' }} icon solution {{ '%}' }} Solution | |
80 > > | |
81 > > 1. Answer for question1 | |
82 > > 2. Answer for question2 | |
83 > > | |
84 > {: .solution} | |
85 > | |
86 {: .question} | |
87 | |
88 """ | |
89 | |
90 TUTO_BIBLIOGRAPHY_TEMPLATE = """ | |
91 # This is the bibliography file for your tutorial. | |
92 # | |
93 # To add bibliography (bibtex) entries here, follow these steps: | |
94 # 1) Find the DOI for the article you want to cite | |
95 # 2) Go to https://doi2bib.org and fill in the DOI | |
96 # 3) Copy the resulting bibtex entry into this file | |
97 # | |
98 # To cite the example below, in your tutorial.md file | |
99 # use {{ '{%' }} Batut2018 {{ '%}' }} | |
100 | |
101 @article{Batut2018, | |
102 doi = {10.1016/j.cels.2018.05.012}, | |
103 url = {https://doi.org/10.1016/j.cels.2018.05.012}, | |
104 year = {2018}, | |
105 month = jun, | |
106 publisher = {Elsevier {BV}}, | |
107 volume = {6}, | |
108 number = {6}, | |
109 pages = {752--758.e1}, | |
110 author = {B{\\'{e}}r{\\'{e}}nice Batut and Saskia Hiltemann and Andrea Bagnacani and Dannon Baker and Vivek Bhardwaj and | |
111 Clemens Blank and Anthony Bretaudeau and Loraine Brillet-Gu{\\'{e}}guen and Martin {\\v{C}}ech and John Chilton | |
112 and Dave Clements and Olivia Doppelt-Azeroual and Anika Erxleben and Mallory Ann Freeberg and Simon Gladman and | |
113 Youri Hoogstrate and Hans-Rudolf Hotz and Torsten Houwaart and Pratik Jagtap and Delphine Larivi{\\`{e}}re and | |
114 Gildas Le Corguill{\\'{e}} and Thomas Manke and Fabien Mareuil and Fidel Ram{\\'{i}}rez and Devon Ryan and | |
115 Florian Christoph Sigloch and Nicola Soranzo and Joachim Wolff and Pavankumar Videm and Markus Wolfien and | |
116 Aisanjiang Wubuli and Dilmurat Yusuf and James Taylor and Rolf Backofen and Anton Nekrutenko and Bj\\"{o}rn Gr\\"{u}ning}, | |
117 title = {Community-Driven Data Analysis Training for Biology}, | |
118 journal = {Cell Systems} | |
119 } | |
120 """ | |
121 | |
122 TUTO_HAND_ON_BODY_TEMPLATE = """ | |
123 # Introduction | |
124 {:.no_toc} | |
125 | |
126 <!-- This is a comment. --> | |
127 | |
128 General introduction about the topic and then an introduction of the | |
129 tutorial (the questions and the objectives). It is nice also to have a | |
130 scheme to sum up the pipeline used during the tutorial. The idea is to | |
131 give to trainees insight into the content of the tutorial and the (theoretical | |
132 and technical) key concepts they will learn. | |
133 | |
134 You may want to cite some publications; this can be done by adding citations to the | |
135 bibliography file (`tutorial.bib` file next to your `tutorial.md` file). These citations | |
136 must be in bibtex format. If you have the DOI for the paper you wish to cite, you can | |
137 get the corresponding bibtex entry using [doi2bib.org](https://doi2bib.org). | |
138 | |
139 With the example you will find in the `tutorial.bib` file, you can add a citation to | |
140 this article here in your tutorial like this: | |
141 {{ '{%' }} raw {{ '%}' }} `{{ '{%' }} cite Batut2018 {{ '%}' }}`{{ '{%' }} endraw {{ '%}' }}. | |
142 This will be rendered like this: {{ '{%' }} cite Batut2018 {{ '%}' }}, and links to a | |
143 [bibliography section](#bibliography) which will automatically be created at the end of the | |
144 tutorial. | |
145 | |
146 | |
147 **Please follow our | |
148 [tutorial to learn how to fill the Markdown]({{ '{{' }} site.baseurl {{ '}}' }}/topics/contributing/tutorials/\ | |
149 create-new-tutorial-content/tutorial.html)** | |
150 | |
151 > ### Agenda | |
152 > | |
153 > In this tutorial, we will cover: | |
154 > | |
155 > 1. TOC | |
156 > {:toc} | |
157 > | |
158 {: .agenda} | |
159 | |
160 # Title for your first section | |
161 | |
162 Give some background about what the trainees will be doing in the section. | |
163 Remember that many people reading your materials will likely be novices, | |
164 so make sure to explain all the relevant concepts. | |
165 | |
166 ## Title for a subsection | |
167 Section and subsection titles will be displayed in the tutorial index on the left side of | |
168 the page, so try to make them informative and concise! | |
169 | |
170 # Hands-on Sections | |
171 Below are a series of hand-on boxes, one for each tool in your workflow file. | |
172 Often you may wish to combine several boxes into one or make other adjustments such | |
173 as breaking the tutorial into sections, we encourage you to make such changes as you | |
174 see fit, this is just a starting point :) | |
175 | |
176 Anywhere you find the word "***TODO***", there is something that needs to be changed | |
177 depending on the specifics of your tutorial. | |
178 | |
179 have fun! | |
180 | |
181 ## Get data | |
182 | |
183 > ### {{ '{%' }} icon hands_on {{ '%}' }} Hands-on: Data upload | |
184 > | |
185 > 1. Create a new history for this tutorial | |
186 > 2. Import the files from [Zenodo]({{ zenodo_link }}) or from the shared data library | |
187 > | |
188 > ``` | |
189 > {{ z_file_links }} | |
190 > ``` | |
191 > ***TODO***: *Add the files by the ones on Zenodo here (if not added)* | |
192 > | |
193 > ***TODO***: *Remove the useless files (if added)* | |
194 > | |
195 > {{ '{%' }} include snippets/import_via_link.md {{ '%}' }} | |
196 > {{ '{%' }} include snippets/import_from_data_library.md {{ '%}' }} | |
197 > | |
198 > 3. Rename the datasets | |
199 > 4. Check that the datatype | |
200 > | |
201 > {{ '{%' }} include snippets/change_datatype.md datatype="datatypes" {{ '%}' }} | |
202 > | |
203 > 5. Add to each database a tag corresponding to ... | |
204 > | |
205 > {{ '{%' }} include snippets/add_tag.md {{ '%}' }} | |
206 > | |
207 {: .hands_on} | |
208 | |
209 # Title of the section usually corresponding to a big step in the analysis | |
210 | |
211 It comes first a description of the step: some background and some theory. | |
212 Some image can be added there to support the theory explanation: | |
213 | |
214 ![Alternative text](../../images/image_name "Legend of the image") | |
215 | |
216 The idea is to keep the theory description before quite simple to focus more on the practical part. | |
217 | |
218 ***TODO***: *Consider adding a detail box to expand the theory* | |
219 | |
220 > ### {{ '{%' }} icon details {{ '%}' }} More details about the theory | |
221 > | |
222 > But to describe more details, it is possible to use the detail boxes which are expandable | |
223 > | |
224 {: .details} | |
225 | |
226 A big step can have several subsections or sub steps: | |
227 | |
228 {{ body }} | |
229 | |
230 ## Re-arrange | |
231 | |
232 To create the template, each step of the workflow had its own subsection. | |
233 | |
234 ***TODO***: *Re-arrange the generated subsections into sections or other subsections. | |
235 Consider merging some hands-on boxes to have a meaningful flow of the analyses* | |
236 | |
237 # Conclusion | |
238 {:.no_toc} | |
239 | |
240 Sum up the tutorial and the key takeaways here. We encourage adding an overview image of the | |
241 pipeline used. | |
242 """ | |
243 | |
244 | |
245 class Tutorial(object): | |
246 """Class to describe a training tutorial.""" | |
247 | |
248 def __init__(self, training, topic, name="new_tuto", title="The new tutorial", zenodo_link=""): | |
249 """Init a tutorial instance.""" | |
250 self.training = training | |
251 self.topic = topic | |
252 self.name = name | |
253 self.title = title | |
254 self.zenodo_link = zenodo_link | |
255 self.zenodo_file_links = [] | |
256 self.questions = [] | |
257 self.objectives = [] | |
258 self.time = "" | |
259 self.key_points = [] | |
260 self.contributors = [] | |
261 self.body = "" | |
262 self.init_wf_fp = None | |
263 self.init_wf_id = None | |
264 self.hands_on = True | |
265 self.slides = False | |
266 self.datatype_fp = "" | |
267 self.set_dir_name() | |
268 self.init_data_lib() | |
269 self.body = templates.render(HANDS_ON_TOOL_BOX_TEMPLATE, **{ | |
270 'tool_name': "My Tool", | |
271 'inputlist': get_empty_input(), | |
272 'paramlist': get_empty_param() | |
273 }) | |
274 | |
275 def init_from_kwds(self, kwds): | |
276 """Init a tutorial instance from a kwds dictionary.""" | |
277 self.name = kwds["tutorial_name"] | |
278 self.title = kwds["tutorial_title"] | |
279 self.zenodo_link = kwds["zenodo_link"] if kwds["zenodo_link"] else '' | |
280 self.questions = [ | |
281 "Which biological questions are addressed by the tutorial?", | |
282 "Which bioinformatics techniques are important to know for this type of data?"] | |
283 self.objectives = [ | |
284 "The learning objectives are the goals of the tutorial", | |
285 "They will be informed by your audience and will communicate to them and to yourself what you should focus on during the course", | |
286 "They are single sentences describing what a learner should be able to do once they have completed the tutorial", | |
287 "You can use Bloom's Taxonomy to write effective learning objectives"] | |
288 self.time = "3H" | |
289 self.key_points = [ | |
290 "The take-home messages", | |
291 "They will appear at the end of the tutorial"] | |
292 self.contributors = ["contributor1", "contributor2"] | |
293 self.init_wf_fp = kwds['workflow'] | |
294 self.init_wf_id = kwds['workflow_id'] | |
295 self.hands_on = kwds['hands_on'] | |
296 self.slides = kwds['slides'] | |
297 self.datatype_fp = kwds['datatypes'] | |
298 self.set_dir_name() | |
299 self.init_data_lib() | |
300 | |
301 def init_from_existing_tutorial(self, tuto_name): | |
302 """Init a tutorial instance from an existing tutorial (data library and tutorial.md).""" | |
303 self.name = tuto_name | |
304 self.set_dir_name() | |
305 | |
306 if not self.exists(): | |
307 raise Exception("The tutorial %s does not exists. It should be created" % self.name) | |
308 | |
309 # get the metadata information of the tutorial (from the top of the tutorial.md) | |
310 with open(self.tuto_fp, "r") as tuto_f: | |
311 tuto_content = tuto_f.read() | |
312 regex = r'^---\n(?P<metadata>[\s\S]*)\n---(?P<body>[\s\S]*)' | |
313 tuto_split_regex = re.search(regex, tuto_content) | |
314 if not tuto_split_regex: | |
315 raise Exception("No metadata found at the top of the tutorial") | |
316 metadata = yaml.safe_load(tuto_split_regex.group("metadata")) | |
317 self.title = metadata["title"] | |
318 self.zenodo_link = metadata["zenodo_link"] | |
319 self.questions = metadata["questions"] | |
320 self.objectives = metadata["objectives"] | |
321 self.time_estimation = metadata["time_estimation"] | |
322 self.key_points = metadata["key_points"] | |
323 self.contributors = metadata["contributors"] | |
324 | |
325 # the tutorial content | |
326 self.body = tuto_split_regex.group("body") | |
327 | |
328 # get the data library | |
329 self.init_data_lib() | |
330 | |
331 def init_data_lib(self): | |
332 """Init the data library dictionary.""" | |
333 if os.path.exists(self.data_lib_fp): | |
334 self.data_lib = load_yaml(self.data_lib_fp) | |
335 else: | |
336 self.data_lib = collections.OrderedDict() | |
337 # set default information | |
338 self.data_lib.setdefault('destination', collections.OrderedDict()) | |
339 self.data_lib['destination']['type'] = 'library' | |
340 self.data_lib['destination']['name'] = 'GTN - Material' | |
341 self.data_lib['destination']['description'] = 'Galaxy Training Network Material' | |
342 self.data_lib['destination']['synopsis'] = 'Galaxy Training Network Material. See https://training.galaxyproject.org' | |
343 self.data_lib.setdefault('items', []) | |
344 self.data_lib.pop('libraries', None) | |
345 # get topic or create new one | |
346 topic = collections.OrderedDict() | |
347 for item in self.data_lib['items']: | |
348 if item['name'] == self.topic.title: | |
349 topic = item | |
350 if not topic: | |
351 self.data_lib['items'].append(topic) | |
352 topic['name'] = self.topic.title | |
353 topic['description'] = self.topic.summary | |
354 topic['items'] = [] | |
355 # get tutorial or create new one | |
356 self.tuto_data_lib = collections.OrderedDict() | |
357 for item in topic['items']: | |
358 if item['name'] == self.title: | |
359 self.tuto_data_lib = item | |
360 if not self.tuto_data_lib: | |
361 topic['items'].append(self.tuto_data_lib) | |
362 self.tuto_data_lib['name'] = self.title | |
363 self.tuto_data_lib['items'] = [] | |
364 | |
365 # GETTERS | |
366 def get_tuto_metata(self): | |
367 """Return the string corresponding to the tutorial metadata.""" | |
368 metadata = collections.OrderedDict() | |
369 metadata['title'] = self.title | |
370 metadata['zenodo_link'] = self.zenodo_link | |
371 metadata['questions'] = self.questions | |
372 metadata['objectives'] = self.objectives | |
373 metadata['time_estimation'] = self.time | |
374 metadata['key_points'] = self.key_points | |
375 metadata['contributors'] = self.contributors | |
376 return yaml.safe_dump( | |
377 metadata, | |
378 indent=2, | |
379 default_flow_style=False, | |
380 default_style='', | |
381 explicit_start=False) | |
382 | |
383 # SETTERS | |
384 def set_dir_name(self): | |
385 """Set the path to dir and files of a tutorial.""" | |
386 self.dir = os.path.join(self.topic.dir, "tutorials", self.name) | |
387 self.tuto_fp = os.path.join(self.dir, "tutorial.md") | |
388 self.bib_fp = os.path.join(self.dir, "tutorial.bib") | |
389 self.slide_fp = os.path.join(self.dir, 'slides.html') | |
390 self.data_lib_fp = os.path.join(self.dir, "data-library.yaml") | |
391 self.wf_dir = os.path.join(self.dir, "workflows") | |
392 self.wf_fp = os.path.join(self.wf_dir, "main_workflow.ga") | |
393 self.tour_dir = os.path.join(self.dir, "tours") | |
394 # remove empty workflow file if there | |
395 empty_wf_filepath = os.path.join(self.wf_dir, "empty_workflow.ga") | |
396 if os.path.exists(empty_wf_filepath): | |
397 os.remove(empty_wf_filepath) | |
398 | |
399 # TEST METHODS | |
400 def exists(self): | |
401 """Test if the tutorial exists.""" | |
402 return os.path.isdir(self.dir) | |
403 | |
404 def has_workflow(self): | |
405 """Test if a workflow is provided for the tutorial.""" | |
406 return self.init_wf_fp or self.init_wf_id | |
407 | |
408 # EXPORT METHODS | |
409 def export_workflow_file(self): | |
410 """Copy or extract workflow file and add it to the tutorial directory.""" | |
411 if not os.path.exists(self.wf_dir): | |
412 os.makedirs(self.wf_dir) | |
413 if not os.path.exists(os.path.join(self.wf_dir, 'index.md')): | |
414 with open(os.path.join(self.wf_dir, 'index.md'), 'w') as handle: | |
415 handle.write('---\nlayout: workflow-list\n---\n') | |
416 if self.init_wf_fp: | |
417 shutil.copy(self.init_wf_fp, self.wf_fp) | |
418 elif self.init_wf_id: | |
419 gi = galaxy.GalaxyInstance(self.training.galaxy_url, key=self.training.galaxy_api_key) | |
420 gi.workflows.export_workflow_to_local_path( | |
421 self.init_wf_id, | |
422 self.wf_fp, | |
423 use_default_filename=False) | |
424 | |
425 # OTHER METHODS | |
426 def get_files_from_zenodo(self): | |
427 """Extract a list of URLs and dictionary describing the files from the JSON output of the Zenodo API.""" | |
428 z_record, req_res = get_zenodo_record(self.zenodo_link) | |
429 | |
430 self.zenodo_file_links = [] | |
431 if 'files' not in req_res: | |
432 raise ValueError("No files in the Zenodo record") | |
433 | |
434 files = [] | |
435 for f in req_res['files']: | |
436 file_dict = {'url': '', 'src': 'url', 'ext': '', 'info': self.zenodo_link} | |
437 if 'type' in f: | |
438 file_dict['ext'] = get_galaxy_datatype(f['type'], self.datatype_fp) | |
439 if 'links' not in f and 'self' not in f['links']: | |
440 raise ValueError("No link for file %s" % f) | |
441 file_dict['url'] = f['links']['self'] | |
442 self.zenodo_file_links.append(f['links']['self']) | |
443 files.append(file_dict) | |
444 | |
445 return (files, z_record) | |
446 | |
447 def prepare_data_library_from_zenodo(self): | |
448 """Get the list of URLs of the files on Zenodo, fill the data library, save it into the file.""" | |
449 self.zenodo_file_links = [] | |
450 if self.zenodo_link != '': | |
451 files, z_record = self.get_files_from_zenodo() | |
452 if z_record: | |
453 # get current data library and/or previous data library for the tutorial | |
454 # remove the latest tag of any existing library | |
455 # remove the any other existing library | |
456 current_data_lib = collections.OrderedDict() | |
457 previous_data_lib = collections.OrderedDict() | |
458 for item in self.tuto_data_lib['items']: | |
459 if item['name'] == "DOI: 10.5281/zenodo.%s" % z_record: | |
460 current_data_lib = item | |
461 elif item['description'] == 'latest': | |
462 previous_data_lib = item | |
463 previous_data_lib['description'] = '' | |
464 if not current_data_lib: | |
465 current_data_lib['name'] = "DOI: 10.5281/zenodo.%s" % z_record | |
466 current_data_lib['description'] = 'latest' | |
467 current_data_lib['items'] = [] | |
468 current_data_lib['items'] = files | |
469 | |
470 self.tuto_data_lib['items'] = [current_data_lib] | |
471 if previous_data_lib: | |
472 self.tuto_data_lib['items'].append(previous_data_lib) | |
473 save_to_yaml(self.data_lib, self.data_lib_fp) | |
474 | |
475 def write_hands_on_tutorial(self, add_z_file_links=True): | |
476 """Write the content of the hands-on tutorial in the corresponding file.""" | |
477 if add_z_file_links: | |
478 self.body = templates.render(TUTO_HAND_ON_BODY_TEMPLATE, **{ | |
479 "z_file_links": "\n> ".join(self.zenodo_file_links), | |
480 "body": self.body | |
481 }) | |
482 # write in the tutorial file with the metadata on the top | |
483 metadata = self.get_tuto_metata() | |
484 with open(self.tuto_fp, 'w') as md: | |
485 md.write(templates.render(TUTO_HAND_ON_TEMPLATE, **{ | |
486 "metadata": metadata, | |
487 "body": self.body | |
488 })) | |
489 | |
490 # create the bibliography file | |
491 self.write_bibliography() | |
492 | |
493 def write_bibliography(self): | |
494 """Write the content of the bibliography file for the tutorial.""" | |
495 with open(self.bib_fp, 'w') as bib: | |
496 bib.write(templates.render(TUTO_BIBLIOGRAPHY_TEMPLATE, **{ | |
497 "body": self.body | |
498 })) | |
499 | |
500 def create_hands_on_tutorial(self, ctx): | |
501 """Create tutorial structure from the workflow file (if it is provided).""" | |
502 # load workflow and get hands-on body from the workflow | |
503 if self.init_wf_id: | |
504 if not self.training.galaxy_url: | |
505 raise ValueError("No Galaxy URL given") | |
506 if not self.training.galaxy_api_key: | |
507 raise ValueError("No API key to access the given Galaxy instance") | |
508 self.body = get_hands_on_boxes_from_running_galaxy(self.init_wf_id, self.training.galaxy_url, self.training.galaxy_api_key) | |
509 elif self.init_wf_fp: | |
510 self.body = get_hands_on_boxes_from_local_galaxy(self.training.kwds, self.init_wf_fp, ctx) | |
511 # write tutorial body | |
512 self.write_hands_on_tutorial() | |
513 | |
514 def create_tutorial(self, ctx): | |
515 """Create the skeleton of a new tutorial.""" | |
516 # create tuto folder and empty files | |
517 os.makedirs(self.dir) | |
518 os.makedirs(self.tour_dir) | |
519 os.makedirs(self.wf_dir) | |
520 | |
521 # extract the data library from Zenodo and the links for the tutorial | |
522 if self.zenodo_link != '': | |
523 info("Create the data library from Zenodo") | |
524 self.prepare_data_library_from_zenodo() | |
525 | |
526 # create tutorial skeleton from workflow and copy workflow file | |
527 if self.hands_on: | |
528 info("Create tutorial skeleton from workflow (if it is provided)") | |
529 self.create_hands_on_tutorial(ctx) | |
530 self.export_workflow_file() | |
531 | |
532 # create slide skeleton | |
533 if self.slides: | |
534 with open(self.slide_fp, 'w') as slide_f: | |
535 slide_f.write( | |
536 templates.render(TUTO_SLIDES_TEMPLATE, **{"metadata": self.get_tuto_metata()})) | |
537 | |
538 | |
539 def get_galaxy_datatype(z_ext, datatype_fp): | |
540 """Get the Galaxy datatype corresponding to a Zenodo file type.""" | |
541 g_datatype = '' | |
542 datatypes = load_yaml(datatype_fp) | |
543 if z_ext in datatypes: | |
544 g_datatype = datatypes[z_ext] | |
545 if g_datatype == '': | |
546 g_datatype = '# Please add a Galaxy datatype or update the shared/datatypes.yaml file' | |
547 info("Get Galaxy datatypes: %s --> %s" % (z_ext, g_datatype)) | |
548 return g_datatype | |
549 | |
550 | |
551 def get_zenodo_record(zenodo_link): | |
552 """Get the content of a Zenodo record.""" | |
553 # get the record in the Zenodo link | |
554 if 'doi' in zenodo_link: | |
555 z_record = zenodo_link.split('.')[-1] | |
556 else: | |
557 z_record = zenodo_link.split('/')[-1] | |
558 # get JSON corresponding to the record from Zenodo API | |
559 req = "https://zenodo.org/api/records/%s" % (z_record) | |
560 r = requests.get(req) | |
561 if r: | |
562 req_res = r.json() | |
563 else: | |
564 info("The Zenodo link (%s) seems invalid" % (zenodo_link)) | |
565 req_res = {'files': []} | |
566 z_record = None | |
567 return(z_record, req_res) | |
568 | |
569 | |
570 def get_wf_inputs(step_inp): | |
571 """Get the inputs from a workflow step and format them into a hierarchical dictionary.""" | |
572 inputs = {} | |
573 for inp_n, inp in step_inp.items(): | |
574 if '|' in inp_n: | |
575 repeat_regex = r'(?P<prefix>[^\|]*)_(?P<nb>\d+)\|(?P<suffix>.+).+' | |
576 repeat_search = re.search(repeat_regex, inp_n) | |
577 hier_regex = r'(?P<prefix>[^\|]*)\|(?P<suffix>.+)' | |
578 hier_regex = re.search(hier_regex, inp_n) | |
579 if repeat_search and repeat_search.start(0) <= hier_regex.start(0): | |
580 inputs.setdefault(repeat_search.group('prefix'), {}) | |
581 inputs[repeat_search.group('prefix')].setdefault( | |
582 repeat_search.group('nb'), | |
583 get_wf_inputs({hier_regex.group('suffix'): inp})) | |
584 else: | |
585 inputs.setdefault(hier_regex.group('prefix'), {}) | |
586 inputs[hier_regex.group('prefix')].update( | |
587 get_wf_inputs({hier_regex.group('suffix'): inp})) | |
588 else: | |
589 inputs.setdefault(inp_n, inp) | |
590 return inputs | |
591 | |
592 | |
593 def get_wf_param_values(init_params, inp_connections): | |
594 """Get the param values from a workflow step and format them into a hierarchical dictionary.""" | |
595 if not isinstance(init_params, six.string_types) or '": ' not in init_params: | |
596 form_params = init_params | |
597 else: | |
598 form_params = json.loads(init_params) | |
599 if isinstance(form_params, dict): | |
600 if '__class__' in form_params and (form_params['__class__'] == 'RuntimeValue' or form_params['__class__'] == 'ConnectedValue'): | |
601 form_params = inp_connections | |
602 else: | |
603 for p in form_params: | |
604 inp = inp_connections[p] if p in inp_connections else {} | |
605 form_params[p] = get_wf_param_values(form_params[p], inp) | |
606 elif isinstance(form_params, list): | |
607 json_params = form_params | |
608 form_params = [] | |
609 for i, p in enumerate(json_params): | |
610 inp = inp_connections[str(i)] if str(i) in inp_connections else {} | |
611 form_params.append(get_wf_param_values(p, inp)) | |
612 elif isinstance(form_params, six.string_types) and '"' in form_params: | |
613 form_params = form_params.replace('"', '') | |
614 return form_params | |
615 | |
616 | |
617 def format_wf_steps(wf, gi): | |
618 """Get a string with the hands-on boxes describing the different steps of the worklow.""" | |
619 body = '' | |
620 steps = wf['steps'] | |
621 | |
622 for s in range(len(steps)): | |
623 wf_step = steps[str(s)] | |
624 # get params in workflow | |
625 wf_param_values = {} | |
626 if wf_step['tool_state'] and wf_step['input_connections']: | |
627 wf_param_values = get_wf_param_values(wf_step['tool_state'], get_wf_inputs(wf_step['input_connections'])) | |
628 if not wf_param_values: | |
629 continue | |
630 # get tool description | |
631 try: | |
632 tool_desc = gi.tools.show_tool(wf_step['tool_id'], io_details=True) | |
633 except Exception: | |
634 tool_desc = {'inputs': []} | |
635 # get formatted param description | |
636 paramlist = '' | |
637 for inp in tool_desc["inputs"]: | |
638 tool_inp = ToolInput(inp, wf_param_values, steps, 1, should_be_there=True) | |
639 paramlist += tool_inp.get_formatted_desc() | |
640 # format the hands-on box | |
641 body += templates.render(HANDS_ON_TOOL_BOX_TEMPLATE, **{ | |
642 "tool_name": wf_step['name'], | |
643 "paramlist": paramlist}) | |
644 return body | |
645 | |
646 | |
647 def get_hands_on_boxes_from_local_galaxy(kwds, wf_filepath, ctx): | |
648 """Server local Galaxy and get the workflow dictionary.""" | |
649 assert is_galaxy_engine(**kwds) | |
650 runnable = for_path(wf_filepath) | |
651 tuto_body = '' | |
652 with engine_context(ctx, **kwds) as galaxy_engine: | |
653 with galaxy_engine.ensure_runnables_served([runnable]) as config: | |
654 workflow_id = config.workflow_id(wf_filepath) | |
655 wf = config.gi.workflows.export_workflow_dict(workflow_id) | |
656 tuto_body = format_wf_steps(wf, config.gi) | |
657 return tuto_body | |
658 | |
659 | |
660 def get_hands_on_boxes_from_running_galaxy(wf_id, galaxy_url, galaxy_api_key): | |
661 """Get the workflow dictionary from a running Galaxy instance with the workflow installed on it.""" | |
662 gi = galaxy.GalaxyInstance(galaxy_url, key=galaxy_api_key) | |
663 wf = gi.workflows.export_workflow_dict(wf_id) | |
664 tuto_body = format_wf_steps(wf, gi) | |
665 return tuto_body |