From 3152bdb38eca129e73665e6e065082a26d37dc95 Mon Sep 17 00:00:00 2001
From: George Marchment <georgemarchment@yahoo.fr>
Date: Wed, 12 Feb 2025 14:09:46 +0100
Subject: [PATCH] Good version which works on DSL1
---
src/bioflowinsighterror.py | 8 ++--
src/include.py | 10 ++--
src/main.py | 84 +++++++++++++++++++--------------
src/nextflow_building_blocks.py | 2 -
src/nextflow_file.py | 3 ++
src/workflow.py | 6 ++-
6 files changed, 65 insertions(+), 48 deletions(-)
diff --git a/src/bioflowinsighterror.py b/src/bioflowinsighterror.py
index d10e765..3166381 100644
--- a/src/bioflowinsighterror.py
+++ b/src/bioflowinsighterror.py
@@ -12,10 +12,10 @@ class BioFlowInsightError(Exception):
def __init__(self, error, num=None, origin = None):
self.origin = origin
if(num!=None):
- if(origin!=None):
- super().__init__(f"[{num}] Error in the file '{self.origin.get_file_address()}': "+error)
- else:
- super().__init__(f"[{num}] {error}")
+ #if(origin!=None):
+ # super().__init__(f"[{num}] Error in the file '{self.origin.get_file_address()}': "+error)
+ #else:
+ super().__init__(f"[{num}] {error}")
else:
super().__init__(f"{error}")
diff --git a/src/include.py b/src/include.py
index fa11136..e2ee93f 100644
--- a/src/include.py
+++ b/src/include.py
@@ -38,9 +38,6 @@ class Include(Nextflow_Building_Blocks):
def get_duplicate_status(self):
return self.nextflow_file_origin.get_duplicate_status()
- def get_root_directory(self):
- return self.origin.get_root_directory()
-
#def get_list_name_includes(self):
# if(self.get_duplicate_status()):
@@ -67,7 +64,8 @@ class Include(Nextflow_Building_Blocks):
if(address.split('/')[0] in ["$projectDir", "${projectDir}", "${baseDir}", "$baseDir"]):
address = '/'.join(address.split('/')[1:])
- root = self.get_root_directory()
+ #root = self.get_root_directory()
+ root = self.nextflow_file_origin.get_root_directory()
address = root+'/'+address
if(os.path.isfile(address)):
found_file = True
@@ -79,14 +77,14 @@ class Include(Nextflow_Building_Blocks):
found_file = True
if(not found_file and os.path.isfile(address[:-3]+"/main.nf")):
- self.nextflow_file = Nextflow_File(address[:-3]+"/main.nf", workflow = self.nextflow_file_origin.get_workflow())
+ self.nextflow_file = Nextflow_File(address[:-3]+"/main.nf", workflow = self.nextflow_file_origin.get_workflow(), first_file=False)
#TODO -> check if the nextflow_file is defined somewhere else?
#In the cas the nextflow file is imported multiple times
else:
if(os.path.isfile(address)):
- self.nextflow_file = Nextflow_File(address, workflow = self.nextflow_file_origin.get_workflow())
+ self.nextflow_file = Nextflow_File(address, workflow = self.nextflow_file_origin.get_workflow(), first_file=False)
else:
address = os.path.normpath(address)
raise BioFlowInsightError(f"Something went wrong in an include{self.get_string_line(self.get_code())}. No such file: '{address}'.", num = 10,origin=self)
diff --git a/src/main.py b/src/main.py
index 9167875..1fe16cd 100644
--- a/src/main.py
+++ b/src/main.py
@@ -85,38 +85,52 @@ class Main(Nextflow_Building_Blocks):
def get_most_influential_conditions(self):
most_influential_conditions = {}
- all_calls = self.get_all_calls_in_subworkflow()
- for c in all_calls:
- if(c.get_first_element_called().get_type()=="Process"):
- for condition in c.get_block().get_all_conditions(conditions = {}):
- try:
- temp = most_influential_conditions[condition]
- except:
- most_influential_conditions[condition] = 0
- most_influential_conditions[condition]+=1
- if(c.get_first_element_called().get_type()=="Subworkflow"):
- #Adding the number of calls from a process at the root of the subworkflow
- num = 0
- calls_at_root = c.get_first_element_called().root.get_calls_same_level()
- for call_at_root in calls_at_root:
- for c_at_root in call_at_root.get_all_calls():
- if(c_at_root.get_first_element_called().get_type()=="Process"):
- num +=1
-
- most_influential_conditions_in_sub = c.get_first_element_called().get_most_influential_conditions()
- #Adding the conditions from inside the subworkflow
- for condition in most_influential_conditions_in_sub:
- try:
- temp = most_influential_conditions[condition]
- except:
- most_influential_conditions[condition] = 0
- num+=most_influential_conditions_in_sub[condition]
- most_influential_conditions[condition]+=most_influential_conditions_in_sub[condition]
- #Adding calls from the subworkflow to the conditions
- for condition in c.get_block().get_all_conditions(conditions = {}):
- try:
- temp = most_influential_conditions[condition]
- except:
- most_influential_conditions[condition] = 0
- most_influential_conditions[condition]+=num
- return most_influential_conditions
\ No newline at end of file
+ if(self.nextflow_file.get_DSL()=="DSL2"):
+ all_calls = self.get_all_calls_in_subworkflow()
+ for c in all_calls:
+ if(c.get_first_element_called().get_type()=="Process"):
+ for condition in c.get_block().get_all_conditions(conditions = {}):
+ try:
+ temp = most_influential_conditions[condition]
+ except:
+ most_influential_conditions[condition] = 0
+ most_influential_conditions[condition]+=1
+ if(c.get_first_element_called().get_type()=="Subworkflow"):
+ #Adding the number of calls from a process at the root of the subworkflow
+ num = 0
+ calls_at_root = c.get_first_element_called().root.get_calls_same_level()
+ for call_at_root in calls_at_root:
+ for c_at_root in call_at_root.get_all_calls():
+ if(c_at_root.get_first_element_called().get_type()=="Process"):
+ num +=1
+
+ most_influential_conditions_in_sub = c.get_first_element_called().get_most_influential_conditions()
+ #Adding the conditions from inside the subworkflow
+ for condition in most_influential_conditions_in_sub:
+ try:
+ temp = most_influential_conditions[condition]
+ except:
+ most_influential_conditions[condition] = 0
+ num+=most_influential_conditions_in_sub[condition]
+ most_influential_conditions[condition]+=most_influential_conditions_in_sub[condition]
+ #Adding calls from the subworkflow to the conditions
+ for condition in c.get_block().get_all_conditions(conditions = {}):
+ try:
+ temp = most_influential_conditions[condition]
+ except:
+ most_influential_conditions[condition] = 0
+ most_influential_conditions[condition]+=num
+ return most_influential_conditions
+ elif(self.nextflow_file.get_DSL()=="DSL1"):
+ processes = self.get_modules_defined()
+ for p in processes:
+ if(p.is_initialised()):
+ for condition in p.origin.get_all_conditions(conditions = {}):
+ try:
+ temp = most_influential_conditions[condition]
+ except:
+ most_influential_conditions[condition] = 0
+ most_influential_conditions[condition]+=1
+ return most_influential_conditions
+ else:
+ raise Exception("This shouldn't happen")
\ No newline at end of file
diff --git a/src/nextflow_building_blocks.py b/src/nextflow_building_blocks.py
index 78954c0..4f554df 100644
--- a/src/nextflow_building_blocks.py
+++ b/src/nextflow_building_blocks.py
@@ -83,8 +83,6 @@ class Nextflow_Building_Blocks:
def get_name_file(self):
return self.origin.get_name_file()
- def get_root_directory(self):
- return self.origin.get_root_directory()
def get_rocrate_key(self, dico):
return f"{self.get_file_address()[len(dico['temp_directory'])+1:]}#{self.get_name()}"
diff --git a/src/nextflow_file.py b/src/nextflow_file.py
index ba05366..0be98fa 100644
--- a/src/nextflow_file.py
+++ b/src/nextflow_file.py
@@ -40,6 +40,9 @@ class Nextflow_File(Nextflow_Building_Blocks):
#GENERAL
#----------------------
+ def get_root_directory(self):
+ return self.workflow.get_root_directory()
+
def get_string_line(self, bit_of_code):
return self.code.get_string_line(bit_of_code)
diff --git a/src/workflow.py b/src/workflow.py
index 21ddda5..35f48c9 100644
--- a/src/workflow.py
+++ b/src/workflow.py
@@ -56,7 +56,7 @@ class Workflow:
with open(file, 'r') as f:
txt= f.read()
else:
- raise BioFlowInsightError("Multiple Nextflow files found at the root with no 'main.nf' file: I don't know which want to select")
+ raise BioFlowInsightError("Multiple Nextflow files found at the root with no 'main.nf' file: I don't know which one to select")
@@ -90,6 +90,10 @@ class Workflow:
with open(self.output_dir / "debug" / "operations_in_call.nf",'w') as file:
pass
+ def get_root_directory(self):
+ first_file = self.get_first_file()
+ return '/'.join(str(first_file.get_file_address()).split('/')[:-1])+"/"
+
def get_conditions_2_ignore(self):
return self.conditions_2_ignore
--
GitLab