diff --git a/src/operation.py b/src/operation.py
index ff93b0d83cd3a2612a136c63f67d0d0ca06cd4c5..11a5503a48cf093f44b1de65f705e87c7d49bcfc 100644
--- a/src/operation.py
+++ b/src/operation.py
@@ -84,35 +84,42 @@ class Operation(Executor):
#I don't need to define the equivalent gives -> cause it's not possible:)
def add_origin_emits(self, full_code, name_called, name_emitted):
from .emitted import Emitted
- #full_code, name_called, name_emitted = match.group(1), match.group(2), match.group(3)
- IGNORE_NAMES = ['params']
- #In the cas an operator is extracted at the end of the emit
- if(full_code.count('.')>=2):
- splited = full_code.split('.')
- if( splited[-1] in constant.LIST_OPERATORS):
- full_code = '.'.join(splited[:-1])
- if(name_called not in IGNORE_NAMES):
- process = self.origin.get_process_from_name(name_called)
- subworkflow = self.origin.get_subworkflow_from_name(name_called)
-
- if(process!=None and subworkflow!=None):
- raise Exception(f"Problem in get_element -> {name_called} exists as process and subworkflow")
- #Case subworkflow
- if(process==None and subworkflow!=None):
- emitted = Emitted(name=full_code, origin=self.origin, emitted_by=subworkflow)
- emitted.set_emits(name_emitted)
- #Case Process
- if(process!=None and subworkflow==None):
- emitted = Emitted(name=full_code, origin=self.origin, emitted_by=process)
- #TODO -> analyse the outputs of the process
-
- if(process==None and subworkflow==None):
- if(name_called[:5]=="Call_"):
- name_called = self.calls[name_called].get_code()
- raise BioFlowInsightError(f"The call for '{name_called}' coudn't be found, before its use in the operation '{self.get_code(get_OG=True)}'{self.get_string_line(self.get_code(get_OG=True))}. Either because the call wasn't made before the operation or that the element it is calling doesn't exist.", num =8, origin=self)
-
- emitted.add_sink(self)
- self.origins.append(emitted)
+ #Check that it not already been added
+ added = False
+ for o in self.origins:
+ if(full_code==o.get_code()):
+ added = True
+
+ if(not added):
+ #full_code, name_called, name_emitted = match.group(1), match.group(2), match.group(3)
+ IGNORE_NAMES = ['params']
+ #In the cas an operator is extracted at the end of the emit
+ if(full_code.count('.')>=2):
+ splited = full_code.split('.')
+ if( splited[-1] in constant.LIST_OPERATORS):
+ full_code = '.'.join(splited[:-1])
+ if(name_called not in IGNORE_NAMES):
+ process = self.origin.get_process_from_name(name_called)
+ subworkflow = self.origin.get_subworkflow_from_name(name_called)
+
+ if(process!=None and subworkflow!=None):
+ raise Exception(f"Problem in get_element -> {name_called} exists as process and subworkflow")
+ #Case subworkflow
+ if(process==None and subworkflow!=None):
+ emitted = Emitted(name=full_code, origin=self.origin, emitted_by=subworkflow)
+ emitted.set_emits(name_emitted)
+ #Case Process
+ if(process!=None and subworkflow==None):
+ emitted = Emitted(name=full_code, origin=self.origin, emitted_by=process)
+ #TODO -> analyse the outputs of the process
+
+ if(process==None and subworkflow==None):
+ if(name_called[:5]=="Call_"):
+ name_called = self.calls[name_called].get_code()
+ raise BioFlowInsightError(f"The call for '{name_called}' coudn't be found, before its use in the operation '{self.get_code(get_OG=True)}'{self.get_string_line(self.get_code(get_OG=True))}. Either because the call wasn't made before the operation or that the element it is calling doesn't exist.", num =8, origin=self)
+
+ emitted.add_sink(self)
+ self.origins.append(emitted)
#This methods checks if the input is an emit and adds it if it's the case, it also returns T/F if it's an emit
def check_is_emit(self, name):
@@ -171,28 +178,35 @@ class Operation(Executor):
channel.add_source(self)
def add_origin(self, name):
- if(self.origin.get_DSL()=="DSL2"):
- #Case it's a call and it's been replaced
- if(re.fullmatch(constant.CALL_ID, name)):
- self.origins.append(self.calls[name])
+ #Check that it's not already been added
+ added = False
+ for o in self.origins:
+ if(name==o.get_code()):
+ added = True
+
+ if(not added):
+ if(self.origin.get_DSL()=="DSL2"):
+ #Case it's a call and it's been replaced
+ if(re.fullmatch(constant.CALL_ID, name)):
+ self.origins.append(self.calls[name])
+ else:
+ ##Case it's a subworkflow
+ #subworkflow = self.origin.get_subworkflow_from_name(name)
+ #process = self.origin.get_process_from_name(name)
+ #if(subworkflow!=None):
+ # print("George it's a subworkflow")
+ # #Case suborkflow
+ # self.origins.append(subworkflow)
+ ##Case process
+ #elif(process!=None):
+ # print("George it's a process")
+ # #Case process
+ # self.origins.append(process)
+ ##In this case it's a channel
+ #else:
+ self.add_origin_channel(name)
else:
- ##Case it's a subworkflow
- #subworkflow = self.origin.get_subworkflow_from_name(name)
- #process = self.origin.get_process_from_name(name)
- #if(subworkflow!=None):
- # print("George it's a subworkflow")
- # #Case suborkflow
- # self.origins.append(subworkflow)
- ##Case process
- #elif(process!=None):
- # print("George it's a process")
- # #Case process
- # self.origins.append(process)
- ##In this case it's a channel
- #else:
self.add_origin_channel(name)
- else:
- self.add_origin_channel(name)
#Function that from an operation gives the origin ('input') channels
diff --git a/src/process.py b/src/process.py
index dc1f16820173fdf92206154027b552c409e630d6..ca7d81b8fce88c188218cab584cbfe2bf9638cd2 100644
--- a/src/process.py
+++ b/src/process.py
@@ -75,6 +75,7 @@ class Process(Nextflow_Building_Blocks):
def get_nb_outputs(self):
return len(self.outputs)
+ #TODO -> Have a much better way of doing this
def extract_tools(self):
script = self.script_code.lower()
for tool in constant.TOOLS:
diff --git a/src/ro_crate.py b/src/ro_crate.py
index 073e9b183f2d07109f09b8ca8b7db698f5db0f40..0e4b85ab2e0f2f4979e8baff2bbe18072f2bfbde 100644
--- a/src/ro_crate.py
+++ b/src/ro_crate.py
@@ -105,7 +105,7 @@ class RO_Crate:
return f"{year}-{month}-{day}"
return None
-
+ #TODO -> update this -> it's incomplet
def get_url(self, file):
if(self.workflow.dico!={}):
return f"https://github.com/{self.workflow.get_address()}/blob/main/{file}"
@@ -114,8 +114,8 @@ class RO_Crate:
def get_creators(self, file):
info = self.fill_log_file(file, reverse = True)
- for match in re.finditer(r"Author: ([ \w-]+) <([^>]+)>", info):
- return [{"@id": match.group(1)}]
+ for match in re.finditer(r"Author: ([^>]+)<([^>]+)>",info):
+ return [{"@id": match.group(1).strip()}]
return None
diff --git a/src/workflow.py b/src/workflow.py
index e69d9691ae030a5e0a747085eb9d2e7fe493a20f..b29ea75bb39edab8f5cd7c0265fc5a97df092b6e 100644
--- a/src/workflow.py
+++ b/src/workflow.py
@@ -134,8 +134,8 @@ class Workflow:
def get_authors(self):
if(self.authors==None):
authors = {}
- for match in re.finditer(r"Author: ([ \w-]+) <([^>]+)>",self.log):
- authors[match.group(2)] = match.group(1)
+ 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]})