diff --git a/src/workflow.py b/src/workflow.py
index 41444ec7c537d6d0a498617872cda59147b065e2..7e0243eba7cfc3da9a45717834b5286cda80171f 100644
--- a/src/workflow.py
+++ b/src/workflow.py
@@ -1,9 +1,12 @@
-
+#Import dependencies
+#Local
from .nextflow_file import Nextflow_File
from .ro_crate import RO_Crate
from . import constant
from .outils_graph import flatten_dico, initia_link_dico_rec, get_number_cycles
+from .bioflowinsighterror import BioFlowInsightError
+#Outside packages
import os
import re
import json
@@ -11,11 +14,32 @@ from pathlib import Path
import glob
import ctypes
-from .bioflowinsighterror import BioFlowInsightError
-
class Workflow:
+ """
+ This is the main workflow class, from this class, workflow analysis can be done.
+ After analysis, workflow structure reconstruction can be done.
+
+ Attributes:
+ file: A string indicating the address to the workflow main or the directory containing the workflow
+ duplicate: A boolean indicating if processes are to be duplicated in the structure
+ display_info: A boolean indicating if the analysis information should be printed
+ output_dir: A string indicating where the results will be saved
+ name: A string indicating the name of the workflow
+ datePublished: A string indicating the date of publication of the workflow
+ description: A string indicating the description of the workflow
+ license: A string indicating the license of the workflow
+ creativeWorkStatus: A string indicating the creative work statuts of the workflow
+ authors: A string inidcating the authors of the workflow
+ version: A string indicating the version of the workflow
+ keywords: A string indicating the keywords of the workflow
+ producer: A string indicating the producer of the workflow
+ publisher: A string indicating the publisher of the workflow
+ processes_2_remove: A string indicating the processes to remove from the workflow
+ processes_annotation: A dictionnary containing processes 2 annotations
+ """
+
def __init__(self, file, duplicate=False, display_info=True, output_dir = './results',
name = None, datePublished=None, description=None,
license = None, creativeWorkStatus = None, authors = None,
@@ -66,6 +90,11 @@ class Workflow:
self.get_dico()
def get_repo_adress(self):
+ """Function that returns the adress of the workflow repository
+
+ Keyword arguments:
+
+ """
current_directory = os.getcwd()
repo = "/".join(self.nextflow_file.get_file_address().split("/")[:-1])
if(repo==''):
@@ -73,9 +102,19 @@ class Workflow:
return repo
def get_processes_annotation(self):
+ """Function the dictionnary of the process annotations
+
+ Keyword arguments:
+
+ """
return self.processes_annotation
def fill_log(self):
+ """Function that reads the git log and saves it
+
+ Keyword arguments:
+
+ """
current_directory = os.getcwd()
os.chdir(self.get_repo_adress())
try:
@@ -88,9 +127,19 @@ class Workflow:
os.chdir(current_directory)
def get_address(self):
+ """Function that returns the adress of the workflow main
+
+ Keyword arguments:
+
+ """
return self.address
def set_address(self):
+ """Function that sets the adress of the workflow main
+
+ Keyword arguments:
+
+ """
current_directory = os.getcwd()
os.chdir(self.get_repo_adress())
try:
@@ -105,6 +154,11 @@ class Workflow:
self.address = match.group(1)
def get_dico(self):
+ """Function that returns a dictionnary containg information regarding the github repository
+
+ Keyword arguments:
+
+ """
current_directory = os.getcwd()
os.chdir(self.get_repo_adress())
try:
@@ -120,6 +174,11 @@ class Workflow:
def get_name(self):
+ """Function that returns the name of the workflow
+
+ Keyword arguments:
+
+ """
if(self.name==None):
return self.nextflow_file.get_file_address().split("/")[-2]
else:
@@ -128,6 +187,11 @@ class Workflow:
#Format yyyy-mm-dd
#Here i return the first commit date
def get_datePublished(self):
+ """Function that returns the date of publication
+
+ Keyword arguments:
+
+ """
if(self.datePublished==None):
for match in re.finditer(r"Date: +\w+ +(\w+) +(\d+) +\d+:\d+:\d+ +(\d+)",self.log):
month = constant.month_mapping[match.group(1)]
@@ -139,6 +203,11 @@ class Workflow:
def get_description(self):
+ """Function that returns the description
+
+ Keyword arguments:
+
+ """
if(self.description==None):
try:
res = self.dico["description"]
@@ -151,10 +220,20 @@ class Workflow:
def get_main_file(self):
+ """Function that returns the name of the main file
+
+ Keyword arguments:
+
+ """
return self.nextflow_file.get_file_address().split("/")[-1]
def get_license(self):
+ """Function that returns the license
+
+ Keyword arguments:
+
+ """
if(self.license==None):
try:
res = self.dico["license"]["key"]
@@ -175,6 +254,11 @@ class Workflow:
def get_authors(self):
+ """Function that returns a list of the authors
+
+ Keyword arguments:
+
+ """
if(self.authors==None):
authors = {}
for match in re.finditer(r"Author: ([^>]+)<([^>]+)>",self.log):
@@ -194,6 +278,11 @@ class Workflow:
#Need to follow this format : "rna-seq, nextflow, bioinformatics, reproducibility, workflow, reproducible-research, bioinformatics-pipeline"
def get_keywords(self):
+ """Function that returns the keywords
+
+ Keyword arguments:
+
+ """
if(self.keywords==None):
try:
res = ", ".join(self.dico["topics"])
@@ -206,6 +295,11 @@ class Workflow:
def get_producer(self):
+ """Function that returns the producer
+
+ Keyword arguments:
+
+ """
if(self.producer==None):
try:
res = {"@id": self.dico["owner"]["login"]}
@@ -217,28 +311,60 @@ class Workflow:
def get_publisher(self):
+ """Function that returns the publisher
+
+ Keyword arguments:
+
+ """
if(self.dico!={}):
return "https://github.com/"
else:
return None
def get_output_dir(self):
+ """Function that returns the output directory
+
+ Keyword arguments:
+
+ """
return self.nextflow_file.get_output_dir()
def get_file_address(self):
+ """Function that returns the adress of the workflow main
+
+ Keyword arguments:
+
+ """
return self.nextflow_file.get_file_address()
def add_2_rocrate(self, dico):
+ """TODO
+ """
self.nextflow_file.add_2_rocrate(dico)
def get_processes_defined(self):
+ """Function that returns a list of the processes defined
+
+ Keyword arguments:
+
+ """
processes = self.nextflow_file.get_processes_defined(dict={}).keys()
return list(processes)
def get_processes_called(self):
+ """Function that returns a list of the processes called/used during the workflow execution
+
+ Keyword arguments:
+
+ """
return self.nextflow_file.get_processes_called()
def get_tools(self):
+ """Function that returns a list of the tools used by the workflow
+
+ Keyword arguments:
+
+ """
processes = self.get_processes_called()
tab = []
for p in processes:
@@ -246,6 +372,11 @@ class Workflow:
return list(set(tab))
def get_commands(self):
+ """Function that returns a list of the commands used by the workflow
+
+ Keyword arguments:
+
+ """
processes = self.get_processes_called()
tab = []
for p in processes:
@@ -253,6 +384,11 @@ class Workflow:
return list(set(tab))
def get_modules(self):
+ """Function that returns a list of the modules used by the workflow
+
+ Keyword arguments:
+
+ """
processes = self.get_processes_called()
tab = []
for p in processes:
@@ -260,10 +396,17 @@ class Workflow:
return list(set(tab))
def initialise_rocrate(self):
+ """Function that initialises the RO-Crate file
+
+ Keyword arguments:
+
+ """
self.rocrate = RO_Crate(self)
self.rocrate.initialise()
def get_layers(self):
+ """TODO
+ """
graph = self.nextflow_file.get_graph()
if(not graph.is_initialised()):
graph.initialise()
@@ -338,11 +481,21 @@ class Workflow:
def initialise(self, create_rocrate = True):
+ """Function that initialises the analysis of the worflow
+
+ Keyword arguments:
+
+ """
self.nextflow_file.initialise()
if(create_rocrate):
self.initialise_rocrate()
def generate_all_graphs(self, render_graphs = True):
+ """Function that generates all graphs representing the workflow
+
+ Keyword arguments:
+
+ """
tab_processes_2_remove = []
if(self.processes_2_remove!=None):
temp = self.processes_2_remove.split(",")