From 4f9a2a5816134f417f15a6bde01c32a432e978d1 Mon Sep 17 00:00:00 2001
From: George Marchment <georgemarchment@yahoo.fr>
Date: Wed, 18 Jun 2025 15:28:14 +0200
Subject: [PATCH] Added Ro-crate generation
---
src/code_.py | 3 +
src/include.py | 3 +
src/main.py | 55 +++++-
src/nextflow_building_blocks.py | 14 +-
src/nextflow_file.py | 19 ++
src/process.py | 56 ++++++
src/ro_crate.py | 297 +++++++++++++++++++++++++++-----
src/subworkflow.py | 62 ++++++-
src/workflow.py | 15 ++
9 files changed, 475 insertions(+), 49 deletions(-)
diff --git a/src/code_.py b/src/code_.py
index 3b2ead5..5a9ee7e 100644
--- a/src/code_.py
+++ b/src/code_.py
@@ -476,4 +476,7 @@ class Code:
def get_file_address(self):
return self.origin.get_file_address()
+
+ def get_nextflow_file(self):
+ return self.origin.get_nextflow_file()
\ No newline at end of file
diff --git a/src/include.py b/src/include.py
index a86fdd9..ce217e8 100644
--- a/src/include.py
+++ b/src/include.py
@@ -38,6 +38,9 @@ class Include(Nextflow_Building_Blocks):
def get_duplicate_status(self):
return self.nextflow_file_origin.get_duplicate_status()
+ def get_nextflow_file(self):
+ return self.nextflow_file
+
#def get_list_name_includes(self):
# if(self.get_duplicate_status()):
diff --git a/src/main.py b/src/main.py
index b6514af..e12a175 100644
--- a/src/main.py
+++ b/src/main.py
@@ -98,6 +98,9 @@ class Main(Nextflow_Building_Blocks):
def get_file_address(self):
return self.nextflow_file.get_file_address()
+
+ def get_nextflow_file(self):
+ return self.nextflow_file
def get_output_dir(self):
@@ -254,4 +257,54 @@ class Main(Nextflow_Building_Blocks):
def check_that_a_channel_is_not_defined_used_and_redefined_used_in_another_block(self):
- return self.root.check_that_a_channel_is_not_defined_used_and_redefined_used_in_another_block()
\ No newline at end of file
+ return self.root.check_that_a_channel_is_not_defined_used_and_redefined_used_in_another_block()
+
+
+
+ #=========================================================
+ #-----------------------RO-CRATE--------------------------
+ #=========================================================
+
+
+ def add_2_rocrate(self, dico):
+ #By definition we add this info
+ dico["@graph"].append({ "@id": "#nextflow", "@type": "ComputerLanguage", "name": "Nextflow", "identifier": { "@id": "https://www.nextflow.io/" }, "url": { "@id": "https://www.nextflow.io/" }})
+ parent_key = self.nextflow_file.get_file_rocrate_key(dico)
+ self.nextflow_file.add_computational_workflow_to_types(dico)
+ main_key = f"{parent_key}#MAIN"
+ dico_main = get_dico_from_tab_from_id(dico, main_key)
+ if(dico_main==None):
+ dico_main = {}
+ dico_main["@id"] = main_key
+ dico_main["name"] = "Main Workflow"
+ dico_main["@type"] = ["SoftwareSourceCode", "ComputationalWorkflow"]
+ #TODO -> check if this remains true
+ #dico_main["conformsTo"] = {"@id": "https://bioschemas.org/profiles/ComputationalWorkflow/0.5-DRAFT-2020_07_21"}
+ #dico_main["dct:conformsTo"]= "https://bioschemas.org/profiles/ComputationalWorkflow/1.0-RELEASE/"
+ dico_main["input"] = []
+ dico_main["output"] = []
+ dico_main["isPartOf"] = [{"@id": parent_key}]
+ dico_main["hasPart"] = []
+ called = []
+ for call in self.root.get_all_calls_from_root():
+ called.append(call.get_first_element_called())
+ for c in called:
+ c.add_2_rocrate(dico, main_key)
+ dico_main["hasPart"].append({"@id":c.get_rocrate_key(dico)})
+
+ dico["@graph"].append(dico_main)
+ self.nextflow_file.add_to_has_part(dico, main_key)
+
+ #Remove duplicates from dico["@graph"]
+ duplicates = []
+ seen = []
+ for ele in dico["@graph"]:
+ if(ele in seen):
+ duplicates.append(ele)
+ else:
+ seen.append(ele)
+ for ele in duplicates:
+ dico["@graph"].remove(ele)
+
+
+
\ No newline at end of file
diff --git a/src/nextflow_building_blocks.py b/src/nextflow_building_blocks.py
index aba604f..c27c2d0 100644
--- a/src/nextflow_building_blocks.py
+++ b/src/nextflow_building_blocks.py
@@ -51,6 +51,13 @@ class Nextflow_Building_Blocks:
def get_file_address(self):
return self.origin.get_file_address()
+ def get_nextflow_file(self):
+ try:
+ return self.origin.get_file_address()
+ except:
+ return self.nextflow_file
+
+
def get_display_info(self):
return self.origin.get_display_info()
@@ -91,10 +98,13 @@ class Nextflow_Building_Blocks:
def get_rocrate_key(self, dico):
- return f"{self.get_file_address()[len(dico['temp_directory'])+1:]}#{self.get_name()}"
+ return f"{str(self.get_file_address())[len(dico['temp_directory']):]}#{self.get_name()}"
def get_file_address(self):
- return self.origin.get_file_address()
+ try:
+ return self.origin.get_file_address()
+ except:
+ return self.nextflow_file.get_file_address()
def get_workflow_address(self):
return self.origin.get_workflow_address()
diff --git a/src/nextflow_file.py b/src/nextflow_file.py
index 14c6fa2..f4aef0e 100644
--- a/src/nextflow_file.py
+++ b/src/nextflow_file.py
@@ -29,6 +29,7 @@ class Nextflow_File(Nextflow_Building_Blocks):
self.subworkflows = []
self.functions = []
self.initialised = False
+ self.added_2_rocrate = False
contents = check_file_exists(self.get_file_address(), self)
Nextflow_Building_Blocks.__init__(self, contents, initialise_code=True)
self.check_file_correctness()
@@ -59,6 +60,9 @@ class Nextflow_File(Nextflow_Building_Blocks):
def get_file_address(self):
return Path(os.path.normpath(self.address))
+ def get_nextflow_file(self):
+ return self
+
def get_DSL(self):
return self.workflow.get_DSL()
@@ -395,3 +399,18 @@ class Nextflow_File(Nextflow_Building_Blocks):
else:
raise Exception("This shouldn't happen")
+
+ def add_to_has_part(self, dico, to_add_key):
+ file_name = str(self.get_file_address())[len(dico["temp_directory"]):]
+ file_dico = get_dico_from_tab_from_id(dico, file_name)
+ file_dico["hasPart"].append({"@id":to_add_key})
+
+
+ def add_computational_workflow_to_types(self, dico):
+ file_name = str(self.get_file_address())[len(dico["temp_directory"]):]
+ file_dico = get_dico_from_tab_from_id(dico, file_name)
+ file_dico["@type"].append("ComputationalWorkflow")
+
+ def get_file_rocrate_key(self, dico):
+ file_name = str(self.get_file_address())[len(dico["temp_directory"]):]
+ return file_name
diff --git a/src/process.py b/src/process.py
index e887430..3ffb410 100644
--- a/src/process.py
+++ b/src/process.py
@@ -593,5 +593,61 @@ class Process(Nextflow_Building_Blocks):
return self.origin.get_all_conditions(conditions)
+ def add_2_rocrate(self, dico, parent_key):
+ process_key = self.get_rocrate_key(dico)
+ dico_process = get_dico_from_tab_from_id(dico, process_key)
+ if(dico_process==None):
+ dico_process = {}
+ dico_process["@id"] = process_key
+ dico_process["name"] = f"Process#{self.get_alias()}"
+ dico_process["@type"] = ["SoftwareSourceCode"]
+ #ADD INPUTS
+ dico_process["input"] = []
+ for input in self.get_inputs():
+ if(type(input)==str):
+ name_input = input
+ else:
+ name_input = input.get_code()
+ dico_input = get_dico_from_tab_from_id(dico, name_input)
+ if(dico_input==None):
+ dico_input = {"@id":f"#{name_input}", "name": name_input, "@type": "FormalParameter"}
+ dico["@graph"].append(dico_input)
+ dico_process["input"].append({"@id":dico_input["@id"]})
+ #ADD OUTPUTS
+ dico_process["output"] = []
+ for output in self.get_outputs():
+ if(type(output)==str):
+ name_output = output
+ else:
+ name_output = output.get_code()
+ dico_output = get_dico_from_tab_from_id(dico, name_output)
+ if(dico_output==None):
+ dico_output = {"@id":f"#{name_output}", "name": name_output, "@type": "FormalParameter"}
+ dico["@graph"].append(dico_output)
+ dico_process["output"].append({"@id":dico_output["@id"]})
+ #ADD isPartOf
+ dico_process["isPartOf"] = []
+ dico_process["isPartOf"].append({"@id":parent_key})
+ #ADD hasPart
+ dico_process["hasPart"] = []
+ for tool in self.get_tools():
+ dico_tool = get_dico_from_tab_from_id(dico, tool)
+ if(dico_tool==None):
+ dico_tool = {"@id":tool,
+ "name": tool,
+ "@type": "Tool"
+ #TODO in later versions
+ , "url": f"https://bio.tools/t?page=1&q={tool}&sort=score"
+ #, "identifier": "tool_identifier"
+ }
+ dico["@graph"].append(dico_tool)
+ dico_process["hasPart"].append({"@id":dico_tool["@id"]})
+
+ dico["@graph"].append(dico_process)
+ else:
+ if(not check_if_element_in_tab_rocrate(dico_process["isPartOf"], parent_key)):
+ dico_process["isPartOf"].append({"@id":parent_key})
+ self.get_nextflow_file().add_to_has_part(dico, process_key)
+
diff --git a/src/ro_crate.py b/src/ro_crate.py
index 186c53f..935f541 100644
--- a/src/ro_crate.py
+++ b/src/ro_crate.py
@@ -19,19 +19,228 @@ from . import constant
class RO_Crate:
- def __init__(self, workflow):
+ def __init__(self, workflow, personnal_acces_token = None,
+ display_info=False,
+ datePublished=None, description=None,
+ license=None, authors = None,
+ publisher = None, keywords = None,
+ producer = None):
self.workflow = workflow
- self.directory = '/'.join(workflow.get_file_address().split('/')[:-1])
+ self.directory = workflow.get_root_directory()
+ self.personnal_acces_token = personnal_acces_token
+ self.display_info = display_info
self.files = []
self.dico = {}
+ self.info_dico_workflow = {}
+ self.log = ""
self.dico["temp_directory"] = self.directory
+ self.datePublished = datePublished
+ self.description = description
+ self.license = license
+ self.authors = authors
+ self.publisher = publisher
+ self.keywords = keywords
+ self.producer = producer
+
+ self.fill_log()
+ self.workflow_git_name = self.set_address()
+ self.fill_info_dico_workflow()
+
+ def set_address(self):
+ address = ""
+ current_directory = os.getcwd()
+ os.chdir(self.directory)
+ try:
+ os.system(f"git ls-remote --get-url origin > temp_address_{id(self)}.txt")
+ with open(f'temp_address_{id(self)}.txt') as f:
+ address = f.read()
+ os.system(f"rm temp_address_{id(self)}.txt")
+ except:
+ None
+ os.chdir(current_directory)
+ for match in re.finditer(r"https:\/\/github\.com\/([^\.]+)\.git", address):
+ address = match.group(1)
+ return address
+ return ""
+
+ def fill_info_dico_workflow(self):
+ current_directory = os.getcwd()
+ os.chdir(self.directory)
+ try:
+ if(self.personnal_acces_token!=None):
+ command = f'curl --silent --request GET --url "https://api.github.com/repos/{self.workflow_git_name}" --header "Authorization: Bearer {self.personnal_acces_token}" --header "X-GitHub-Api-Version: 2022-11-28" > temp_dico_{id(self)}.json'
+ else:
+ command = f'curl --silent --request GET --url "https://api.github.com/repos/{self.workflow_git_name}" > temp_dico_{id(self)}.json'
+ _ = os.system(command)
+ with open(f'temp_dico_{id(self)}.json') as json_file:
+ self.info_dico_workflow = json.load(json_file)
+ os.system(f"rm temp_dico_{id(self)}.json")
+
+ except:
+ _ = os.system(f"rm temp_dico_{id(self)}.json")
+ if(self.display_info):
+ if(self.info_dico_workflow=={}):
+ print("Unable to retrieve information regarding the commits")
+ else:
+ print("Successfully retrieved information regarding the commits")
+ os.chdir(current_directory)
+
+
+ def fill_log(self):
+ """Method that reads the git log and saves it
+
+ Keyword arguments:
+
+ """
+ current_directory = os.getcwd()
+ os.chdir(self.directory)
+ try:
+
+ os.system(f"git log --reverse > temp_{id(self)}.txt")
+ with open(f'temp_{id(self)}.txt') as f:
+ self.log = f.read()
+ os.system(f"rm temp_{id(self)}.txt")
+ except:
+ None
+ if(self.display_info):
+ if(self.log==""):
+ print("Unable to retrieve the git log")
+ else:
+ print("Successfully retrieved the git log")
+ os.chdir(current_directory)
def get_files(self):
self.files = glob.glob(f'{self.directory}/**/*.*', recursive=True)
tab_files = []
for file in self.files:
- tab_files.append({"@id":file[len(self.directory)+1:]})
+ tab_files.append({"@id":file[len(self.directory):]})
return tab_files
+
+ #Format yyyy-mm-dd
+ #Here i return the first commit date
+ def get_datePublished(self):
+ """Method 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)]
+ day = match.group(2)
+ year = match.group(3)
+ if(int(month)<10 and len(month)==1):
+ month = f"0{month}"
+ if(int(day)<10):
+ day = f"0{day}"
+ return f"{year}-{month}-{day}"
+ else:
+ return self.datePublished
+
+ def get_description(self):
+ """Method that returns the description
+
+ Keyword arguments:
+
+ """
+ if(self.description==None):
+ try:
+ res = self.info_dico_workflow["description"]
+ except:
+ res = None
+ return res
+ else:
+ return self.description
+
+ def get_license(self):
+ """Method that returns the license
+
+ Keyword arguments:
+
+ """
+ if(self.license==None):
+ try:
+ res = self.info_dico_workflow["license"]["key"]
+ except:
+ res = None
+ return res
+ else:
+ return self.license
+
+ def get_authors(self):
+ """Method that returns a list of the authors
+
+ Keyword arguments:
+
+ """
+ if(self.authors==None):
+ authors = {}
+ for match in re.finditer(r"Author: ([^>]+)<([^>]+)>",self.log):
+ authors[match.group(2)] = match.group(1).strip()
+ tab = []
+ for author in authors:
+ #tab.append({"@id":author, "name":authors[author]})
+ tab.append({"@id":authors[author], "email":author})
+ return tab
+ else:
+ authors = self.authors.split(',')
+ tab = []
+ for a in authors:
+ tab.append({"@id":a.strip()})
+ return tab
+
+ def get_publisher(self):
+ """Method that returns the publisher
+
+ Keyword arguments:
+
+ """
+ if(self.publisher==None):
+ if(self.info_dico_workflow!={}):
+ return "https://github.com/"
+ else:
+ return None
+ else:
+ self.publisher
+
+ #TODO
+ def get_creativeWorkStatus(self):
+ return "TODO"
+
+ #TODO
+ def get_version(self):
+ return "TODO"
+
+ #Need to follow this format : "rna-seq, nextflow, bioinformatics, reproducibility, workflow, reproducible-research, bioinformatics-pipeline"
+ def get_keywords(self):
+ """Method that returns the keywords
+
+ Keyword arguments:
+
+ """
+ if(self.keywords==None):
+ try:
+ res = ", ".join(self.info_dico_workflow["topics"])
+ except:
+ res = None
+ return res
+ else:
+ return self.keywords
+
+ def get_producer(self):
+ """Method that returns the producer
+
+ Keyword arguments:
+
+ """
+ if(self.producer==None):
+ try:
+ res = {"@id": str(self.dico["owner"]["login"])}
+ except:
+ res = None
+ return res
+ else:
+ return self.producer
def initialise_dico(self):
self.dico["@context"] = "https://w3id.org/ro/crate/1.1/context"
@@ -51,88 +260,89 @@ class RO_Crate:
root["@id"] = "./"
root["@type"] = "Dataset"
root["name"] = self.workflow.get_name()
- root["datePublished"] = self.workflow.get_datePublished()
- root["description"] = self.workflow.get_description()
- root["mainEntity"] = {"@id": self.workflow.get_main_file()}
+ root["datePublished"] = self.get_datePublished()
+ root["description"] = str(self.get_description())
+ root["mainEntity"] = {"@id": str(self.workflow.get_first_file().get_file_address()).split("/")[-1]}
#, "@type":["File", "SoftwareSourceCode"]} #We do not consider a File as a "ComputationalWorkflow" since multiple (sub)workflows can be defined in a same file
- root["license"] = {"@id":self.workflow.get_license()}
- authors = self.workflow.get_authors()
- tab_authors = []
+ root["license"] = {"@id":str(self.get_license())}
+ authors = self.get_authors()
+ tab_authors, tab_authors_ids= [], []
for author in authors:
+ id_author = f'#{"_".join(author["@id"].split())}'
+ tab_authors_ids.append({"@id":id_author})
try:
#tab_authors.append({"@id":author["@id"], "email":author["email"]})
- tab_authors.append({"@id":f'#{"_".join(author["@id"].split())}', "@name":author["@id"],"email":author["email"]})
+ tab_authors.append({"@id":id_author, "@type": ["Person"], "name":author["@id"],"email":author["email"]})
except:
#tab_authors.append({"@id":author["@id"]})
- tab_authors.append({"@id":f'#{"_".join(author["@id"].split())}', "@name":author["@id"]})
- root["author"] = tab_authors
- root["maintainer"] = tab_authors #Right now i'm assuming that all the authors are maintainers
+ tab_authors.append({"@id":id_author, "@type": ["Person"], "name":author["@id"]})
+ self.dico["@graph"]+=tab_authors
+ root["author"] = tab_authors_ids
+ root["maintainer"] = tab_authors_ids #Right now i'm assuming that all the authors are maintainers
files = self.get_files()
tab_files = []
for file in files:
tab_files.append({"@id":file["@id"]})
root["hasPart"] = tab_files
- root["publisher"] = {"@id":self.workflow.get_publisher()}
+ publisher = str(self.get_publisher())
+ root["publisher"] = {"@id":publisher}
+ self.dico["@graph"].append({"@id":publisher, "@type":["Organization"]})
#subjectOf TODO
root["subjectOf"] = None
- root["creativeWorkStatus"] = self.workflow.get_creativeWorkStatus()
- root["@version"] = self.workflow.get_version()
- root["keywords"] = self.workflow.get_keywords()
- root["producer"] = self.workflow.get_producer()
+ root["creativeWorkStatus"] = self.get_creativeWorkStatus()
+ root["version"] = self.get_version()
+ root["keywords"] = self.get_keywords()
+ root["producer"] = self.get_producer()
self.dico["@graph"].append(root)
#TODO
def get_programming_language(self, file):
if(file[-3:]==".nf"):
- return "https://w3id.org/workflowhub/workflow-ro-crate#nextflow"
+ #return "https://w3id.org/workflowhub/workflow-ro-crate#nextflow"
+ return "#nextflow"
return None
def get_contentSize(self, file):
file_stats = os.stat(file)
return file_stats.st_size/1e3
- def fill_log_file(self, file, reverse = True):
- info = ""
- current_directory = os.getcwd()
- os.chdir("/".join(self.workflow.nextflow_file.get_file_address().split("/")[:-1]))
- try:
- os.system(f"git log {'--reverse'*reverse} \"{file}\" > temp_{id(self)}.txt")
- with open(f'temp_{id(self)}.txt') as f:
- info = f.read()
- os.system(f"rm temp_{id(self)}.txt")
- except:
- None
- os.chdir(current_directory)
- return info
+
def get_dateCreated(self, file):
- info = self.fill_log_file(file, reverse = True)
+ info = self.log
for match in re.finditer(r"Date: +\w+ +(\w+) +(\d+) +\d+:\d+:\d+ +(\d+)", info):
month = constant.month_mapping[match.group(1)]
day = match.group(2)
year = match.group(3)
+ if(int(month)<10 and len(month)==1):
+ month = f"0{month}"
+ if(int(day)<10):
+ day = f"0{day}"
return f"{year}-{month}-{day}"
return None
def get_dateModified(self, file):
- info = self.fill_log_file(file, reverse = False)
+ info = self.log
for match in re.finditer(r"Date: +\w+ +(\w+) +(\d+) +\d+:\d+:\d+ +(\d+)", info):
month = constant.month_mapping[match.group(1)]
day = match.group(2)
year = match.group(3)
- return f"{year}-{month}-{day}"
- return None
+ if(int(month)<10 and len(month)==1):
+ month = f"0{month}"
+ if(int(day)<10):
+ day = f"0{day}"
+ return f"{year}-{month}-{day}"
+
- #TODO -> update this -> it's incomplet
def get_url(self, file):
- if(self.workflow.dico!={}):
- return f"https://github.com/{self.workflow.get_file_address()}/blob/main/{file}"
+ if(self.workflow_git_name!=""):
+ return f"https://github.com/{self.workflow_git_name}/blob/main/{file}"
return None
def get_creators(self, file):
- info = self.fill_log_file(file, reverse = True)
+ info = self.log
for match in re.finditer(r"Author: ([^>]+)<([^>]+)>",info):
return [{"@id": match.group(1).strip()}]
return []
@@ -146,12 +356,12 @@ class RO_Crate:
def initialise_file(self, file):
- key = file[len(self.directory)+1:]
+ key = file[len(self.directory):]
dico = {}
dico["@id"] = key
dico["name"] = key
dico["@type"] = self.get_types(file)
- dico["programmingLanguage"] = {"@id":self.get_programming_language(file)}
+ dico["programmingLanguage"] = {"@id":str(self.get_programming_language(file))}
dico["contentSize"] = self.get_contentSize(file)
dico["dateCreated"] = self.get_dateCreated(key)
dico["dateModified"] = self.get_dateModified(key)
@@ -174,9 +384,6 @@ class RO_Crate:
self.fill_from_workflow()
self.dico.pop("temp_directory")
- name = self.workflow.get_name()
- name = name.replace('github.com/', '')
- name = re.sub(r"^[ .]|[/<>:\"\\|?*]+|[ .]$", "-", name)
#with open(f"{self.workflow.get_output_dir()}/ro-crate-metadata-{name}.json", 'w') as output_file :
with open(f"{self.workflow.get_output_dir()}/ro-crate-metadata.json", 'w') as output_file :
diff --git a/src/subworkflow.py b/src/subworkflow.py
index 4749628..fc16dd2 100644
--- a/src/subworkflow.py
+++ b/src/subworkflow.py
@@ -464,4 +464,64 @@ class Subworkflow(Main):
#ope.set_operation_type("Branch")
ope.get_structure(dico)
-
\ No newline at end of file
+
+ def add_2_rocrate(self, dico, parent_key):
+ sub_key = self.get_rocrate_key(dico)
+ dico_sub = get_dico_from_tab_from_id(dico, sub_key)
+ if(dico_sub==None):
+ dico_sub = {}
+ dico_sub["@id"] = sub_key
+ dico_sub["name"] = f"Subworkflow#{self.get_alias()}"
+ dico_sub["@type"] = ["SoftwareSourceCode", "ComputationalWorkflow"]
+ #TODO -> check if this remains true
+ #dico_main["conformsTo"] = {"@id": "https://bioschemas.org/profiles/ComputationalWorkflow/0.5-DRAFT-2020_07_21"}
+ #dico_main["dct:conformsTo"]= "https://bioschemas.org/profiles/ComputationalWorkflow/1.0-RELEASE/"
+
+
+ #ADD INPUTS
+ dico_sub["input"] = []
+ for input in self.get_takes():
+ if(type(input)==str):
+ name_input = input
+ else:
+ name_input = input.get_code(get_OG = True)
+ dico_input = get_dico_from_tab_from_id(dico, name_input)
+ if(dico_input==None):
+ dico_input = {"@id":f"#{name_input}", "name": name_input, "@type": "FormalParameter"}
+ dico["@graph"].append(dico_input)
+ dico_sub["input"].append({"@id":dico_input["@id"]})
+ #ADD OUTPUTS
+ dico_sub["output"] = []
+ for output in self.get_emit():
+ if(type(output)==str):
+ name_output = output
+ else:
+ name_output = output.get_code(get_OG = True)
+ dico_output = get_dico_from_tab_from_id(dico, name_output)
+ if(dico_output==None):
+ dico_output = {"@id":f"#{name_output}", "name": name_output, "@type": "FormalParameter"}
+ dico["@graph"].append(dico_output)
+ dico_sub["output"].append({"@id":dico_output["@id"]})
+
+
+ dico_sub["isPartOf"] = [{"@id": parent_key}]
+ dico_sub["hasPart"] = []
+
+
+ called = []
+ for call in self.root.get_all_calls_from_root():
+ called.append(call.get_first_element_called())
+
+ for c in called:
+ if(c==self):
+ raise Exception("This shoudn't happen!")
+ c.add_2_rocrate(dico, sub_key)
+ dico_sub["hasPart"].append({"@id":c.get_rocrate_key(dico)})
+
+ dico["@graph"].append(dico_sub)
+ else:
+ if(not check_if_element_in_tab_rocrate(dico_sub["isPartOf"], parent_key)):
+ dico_sub["isPartOf"].append({"@id":parent_key})
+
+ self.get_nextflow_file().add_to_has_part(dico, sub_key)
+
\ No newline at end of file
diff --git a/src/workflow.py b/src/workflow.py
index e21542b..7f66578 100644
--- a/src/workflow.py
+++ b/src/workflow.py
@@ -91,6 +91,12 @@ class Workflow:
self.alias_2_tools = {}
self.scripts_2_tools = {}
+ def get_name(self):
+ if(self.name!=None):
+ return self.name
+ else:
+ return self.get_root_directory().split('/')[-2]
+
def create_empty_results(self):
os.makedirs(self.output_dir, exist_ok=True)
@@ -129,6 +135,9 @@ class Workflow:
def set_DSL(self, DSL):
self.DSL = DSL
+ def add_2_rocrate(self, dico):
+ self.get_workflow_main().add_2_rocrate(dico)
+
def get_first_file(self):
for file in self.nextflow_files:
if(file.first_file):
@@ -291,6 +300,12 @@ George Marchment, Bryan Brancotte, Marie Schmit, Frédéric Lemoine, Sarah Cohen
self.generate_executors_per_subworkflows()
+ #The generation of the Ro-Crate has been valid from
+ # - https://ro-crate.ldaca.edu.au/explorer, and
+ # - https://github.com/crs4/rocrate-validator (with the workflow-ro-crate-1.0 profile)
+ def get_rocrate(self, display_info=False):
+ self.rocrate = RO_Crate(self, display_info=display_info)
+ self.rocrate.initialise()
#Returns a dico of number of processes called per each condition
--
GitLab