diff --git a/src/constant.py b/src/constant.py
index ba73cea71e1ff1280046cb4d8bc33b330c84b4ad..76ee6a62047ed825fa3618ff8728fd4a8ed29ef3 100644
--- a/src/constant.py
+++ b/src/constant.py
@@ -49,7 +49,7 @@ TOOLS = [
# CALLS
#--------------------------
-BEGINNING_CALL = r"(\w+)\s*\("
+BEGINNING_CALL = r"\s(\w+)\s*\("
CALL_ID = r"Call_\d+"
END_CALL = r'\s*\('
diff --git a/src/nextflow_file.py b/src/nextflow_file.py
index 0be98fa758bf66190ce5297d26ce52bd056f55d7..b78af3bb02c4bfb4ed7c3bc72855c4ad188bef7d 100644
--- a/src/nextflow_file.py
+++ b/src/nextflow_file.py
@@ -34,7 +34,7 @@ class Nextflow_File(Nextflow_Building_Blocks):
self.initialised = False
contents = check_file_exists(self.get_file_address(), self)
Nextflow_Building_Blocks.__init__(self, contents)
-
+ self.check_file_correctness()
#----------------------
#GENERAL
@@ -56,6 +56,21 @@ class Nextflow_File(Nextflow_Building_Blocks):
def get_DSL(self):
return self.workflow.get_DSL()
+ def check_file_correctness(self):
+ code = self.get_code()
+ if(code.count("{")!=code.count("}")):
+ curly_count = get_curly_count(code)
+ if(curly_count!=0):
+ raise BioFlowInsightError(f"Not the same number of opening and closing curlies '{'{}'}' in the file.", num = 16,origin=self)
+ if(code.count("(")!=code.count(")")):
+ parenthese_count = get_parenthese_count(code)
+ if(parenthese_count!=0):
+ raise BioFlowInsightError(f"Not the same number of opening and closing parentheses '()' in the file.", num = 16, origin=self)
+
+ if(code.count('"""')%2!=0):
+ raise BioFlowInsightError(f"An odd number of '\"\"\"' was found in the code.", num = 16, origin=self)
+
+
#Method which returns the DSL of the workflow -> by default it's DSL2
#I use the presence of include, subworkflows and into/from in processes as a proxy
diff --git a/src/operation.py b/src/operation.py
index 77356940cf8dd9cc96de1c19a9d05b1c654ef989..3b2254a06072eb1e234c46106a309a5b0acec430 100644
--- a/src/operation.py
+++ b/src/operation.py
@@ -706,14 +706,16 @@ class Operation(Executor):
searching = True
while(searching):
searching= False
- text = self.get_code(clean_pipe = clean_pipe)
+ text = " "+self.get_code(clean_pipe = clean_pipe)
for c in self.calls:
text = text.replace(self.calls[c].get_code(), "")
for match in re.finditer(pattern_call, text):
if(match.group(1) in to_call):
- searching=True
start, end = match.span(0)
+ #We do this cause the first caracter is a " "
+ start+=1
+ searching=True
call = Call(code =get_end_call(text, start, end), origin =self)
call.initialise()
self.calls[str(call)] = call
diff --git a/src/root.py b/src/root.py
index fd4c755b27103cdef355d4d5164b09ff0513c7ad..23edb5198a24679cb572da4f4dfea5d295f953c1 100644
--- a/src/root.py
+++ b/src/root.py
@@ -227,7 +227,7 @@ class Root(Nextflow_Building_Blocks):
code = self.get_code()
#For each block -> remove its code
for b in self.blocks:
- code = code.replace(b.get_code(), "")
+ code = code.replace(b.get_code(), "", 1)
for match in re.finditer(r"\<src\.process\.Process object at \w+\>", code):
for process in self.modules_defined:
@@ -240,13 +240,14 @@ class Root(Nextflow_Building_Blocks):
#Define the blocks
code = self.get_code()
conditions = extract_conditions(code)
+
#TODO -> normally it is not a problem -> cause i've removed the recursive option
#But just check that the bodies don't appear twice in the dico
#For each condition -> create a block
for c in conditions:
from .block import Block
- body = code[conditions[c][0]:conditions[c][1]]
+ body = code[conditions[c][0]:conditions[c][1]].strip()
c = c.split("$$__$$")[0]
import copy
block = Block(code=body, origin=self, condition=c, modules_defined=self.modules_defined, existing_channels = copy.copy(self.channels))
@@ -258,22 +259,26 @@ class Root(Nextflow_Building_Blocks):
#Case DSL1 -> need to extract the processes which have been defined but rplaced in the code
self.extract_defined_processes()
+
#This is to get the order of execution
code = self.get_code()
position_2_thing_2_analyse = {}
for block in self.blocks:
- block_code = block.get_code()
- found = False
- while(not found or len(block_code)==0):
- pos = code.find(block_code)
- if(pos!=-1):
- position_2_thing_2_analyse[pos] = block
- code = code.replace(block_code, "a"*len(block_code), 1)
- found = True
- else:
- block_code = block_code[:-1]
- if(not found):
- raise Exception("This shouldn't happen")
+ block_code = block.get_code().strip()
+ if(block_code!=""):
+ found = False
+ while(not found):
+ if(len(block_code)<=0):
+ break
+ pos = code.find(block_code)
+ if(pos!=-1):
+ position_2_thing_2_analyse[pos] = block
+ code = code.replace(block_code, "a"*len(block_code), 1)
+ found = True
+ else:
+ block_code = block_code[:-1]
+ if(not found):
+ raise Exception("This shouldn't happen")
for process in self.defined_processes:
found = False
@@ -284,11 +289,12 @@ class Root(Nextflow_Building_Blocks):
if(not found):
raise Exception("This shouldn't happen")
-
for e in self.executors:
e_code = e.get_code()
found = False
- while(not found or len(e_code)==0):
+ while(not found):
+ if(len(e_code)<=0):
+ break
pos = code.find(e_code)
if(pos!=-1):
position_2_thing_2_analyse[pos] = e
@@ -306,19 +312,6 @@ class Root(Nextflow_Building_Blocks):
element.initialise()
- #for block in self.blocks:
- # #TODO -> this would be the place you put the verification of the conditions
- # block.initialise()
- #
- ##Analyse Executors
- #for e in self.executors:
- # e.initialise()
-
- #Initialise each subworkflow being called
- #for sub in self.elements_being_called:
- # if(sub.get_type()=="Subworkflow"):
- # sub.initialise()
-
def get_process_from_name(self, name):
for m in self.modules_defined:
if(m.get_type()=="Process" and m.get_alias()==name):
@@ -345,7 +338,7 @@ class Root(Nextflow_Building_Blocks):
#For each block -> remove its code
for b in self.blocks:
- code = code.replace(b.get_code(), "")
+ code = code.replace(b.get_code(), "", 1)
things_to_remove = []
#things_to_remove+= self.processes+self.includes+self.subworkflows+self.functions
@@ -414,7 +407,7 @@ class Root(Nextflow_Building_Blocks):
searching = True
while(searching):
searching= False
- text = code
+ text = " "+code
for e in self.executors:
text = text.replace(e.get_code(), "", 1)
@@ -422,6 +415,8 @@ class Root(Nextflow_Building_Blocks):
if(match.group(1) in to_call):
start, end = match.span(0)
+ #We do this cause the first caracter is a " "
+ start+=1
txt_call = get_end_call(text, start, end)
txt_call = expand_to_pipe_operators(text, txt_call)
#If the thing which is extracted is not in the conditon of an if
diff --git a/tests/ressources/workflows/wf18/specification_graph.json b/tests/ressources/workflows/wf18/specification_graph.json
new file mode 100644
index 0000000000000000000000000000000000000000..7fe9450dccde6c46ff2699a4da0f3c5323eb4a9c
--- /dev/null
+++ b/tests/ressources/workflows/wf18/specification_graph.json
@@ -0,0 +1,139 @@
+{
+ "nodes": [
+ {
+ "id": "<src.operation.Operation object at 0x79717dcc3a00>",
+ "name": "",
+ "shape": "point",
+ "xlabel": "a = sub1.out",
+ "fillcolor": "white"
+ },
+ {
+ "id": "<src.operation.Operation object at 0x79717db0d3c0>",
+ "name": "",
+ "shape": "point",
+ "xlabel": "b = sub2.out",
+ "fillcolor": "white"
+ },
+ {
+ "id": "<src.operation.Operation object at 0x79717db0e2f0>",
+ "name": "",
+ "shape": "point",
+ "xlabel": "b = Channel.empty()",
+ "fillcolor": ""
+ }
+ ],
+ "edges": [
+ {
+ "A": "<src.operation.Operation object at 0x79717db0d900>",
+ "B": "<src.operation.Operation object at 0x79717dcc3a00>",
+ "label": "sub1.out"
+ },
+ {
+ "A": "<src.operation.Operation object at 0x79717db0dc30>",
+ "B": "<src.operation.Operation object at 0x79717db0d3c0>",
+ "label": "sub2.out"
+ }
+ ],
+ "subworkflows": {
+ "sub1_0": {
+ "nodes": [
+ {
+ "id": "<src.process.Process object at 0x79717db0d0c0>",
+ "name": "M1",
+ "shape": "ellipse",
+ "xlabel": "",
+ "fillcolor": ""
+ },
+ {
+ "id": "<src.process.Process object at 0x79717db0d180>",
+ "name": "M2",
+ "shape": "ellipse",
+ "xlabel": "",
+ "fillcolor": ""
+ },
+ {
+ "id": "<src.operation.Operation object at 0x79717db0cdc0>",
+ "name": "",
+ "shape": "point",
+ "xlabel": "M1.out",
+ "fillcolor": "white"
+ },
+ {
+ "id": "<src.operation.Operation object at 0x79717db0d900>",
+ "name": "",
+ "shape": "point",
+ "xlabel": "emit: M2.out",
+ "fillcolor": ""
+ }
+ ],
+ "edges": [
+ {
+ "A": "<src.process.Process object at 0x79717db0d0c0>",
+ "B": "<src.operation.Operation object at 0x79717db0cdc0>",
+ "label": "M1.out"
+ },
+ {
+ "A": "<src.operation.Operation object at 0x79717db0cdc0>",
+ "B": "<src.process.Process object at 0x79717db0d180>",
+ "label": ""
+ },
+ {
+ "A": "<src.process.Process object at 0x79717db0d180>",
+ "B": "<src.operation.Operation object at 0x79717db0d900>",
+ "label": "M2.out"
+ }
+ ],
+ "subworkflows": {}
+ },
+ "sub2_0": {
+ "nodes": [
+ {
+ "id": "<src.process.Process object at 0x79717db0dfc0>",
+ "name": "M1",
+ "shape": "ellipse",
+ "xlabel": "",
+ "fillcolor": ""
+ },
+ {
+ "id": "<src.process.Process object at 0x79717db0e110>",
+ "name": "M2",
+ "shape": "ellipse",
+ "xlabel": "",
+ "fillcolor": ""
+ },
+ {
+ "id": "<src.operation.Operation object at 0x79717db0e200>",
+ "name": "",
+ "shape": "point",
+ "xlabel": "M1.out",
+ "fillcolor": "white"
+ },
+ {
+ "id": "<src.operation.Operation object at 0x79717db0dc30>",
+ "name": "",
+ "shape": "point",
+ "xlabel": "emit: M2.out",
+ "fillcolor": ""
+ }
+ ],
+ "edges": [
+ {
+ "A": "<src.process.Process object at 0x79717db0dfc0>",
+ "B": "<src.operation.Operation object at 0x79717db0e200>",
+ "label": "M1.out"
+ },
+ {
+ "A": "<src.operation.Operation object at 0x79717db0e200>",
+ "B": "<src.process.Process object at 0x79717db0e110>",
+ "label": ""
+ },
+ {
+ "A": "<src.process.Process object at 0x79717db0e110>",
+ "B": "<src.operation.Operation object at 0x79717db0dc30>",
+ "label": "M2.out"
+ }
+ ],
+ "subworkflows": {}
+ }
+ }
+}
\ No newline at end of file
diff --git a/tests/ressources/workflows/wf18/test.nf b/tests/ressources/workflows/wf18/test.nf
new file mode 100644
index 0000000000000000000000000000000000000000..c142ffbefd02f11ac5bfd8f756278096bb079509
--- /dev/null
+++ b/tests/ressources/workflows/wf18/test.nf
@@ -0,0 +1,53 @@
+
+#!/usr/bin/env nextflow
+
+process M1 {
+ output:
+ path 'chunk_*'
+
+ """
+ SOMETHING
+ """
+}
+
+process M2 {
+ input:
+ path a
+
+ """
+ SOMETHING
+ """
+}
+
+workflow sub1 {
+ main:
+ M1()
+ M2(M1.out)
+
+ emit:
+ M2.out
+}
+
+workflow sub2 {
+ main:
+ M1()
+ M2(M1.out)
+
+ emit:
+ M2.out
+
+}
+
+
+workflow {
+
+ if (!params.cloudProcess) { sub1(); a = sub1.out }
+ if (params.cloudProcess) {
+ sub2()
+ if (1==1) { b = sub2.out }
+ else { b = Channel.empty() }
+ }
+
+}
+
+
diff --git a/tests/test_workflows_simple_duplicate.py b/tests/test_workflows_simple_duplicate.py
index 30c2ed5a9a8ad920ddd76637435d1c55f9bb164d..9f2685ea23108a13343178ac1e1828460c4fbb3a 100644
--- a/tests/test_workflows_simple_duplicate.py
+++ b/tests/test_workflows_simple_duplicate.py
@@ -16,6 +16,12 @@ class TestWorkflows(unittest.TestCase):
json_files = glob.glob(f'tests/ressources/workflows/wf1/*.json', recursive=False)
self.assertTrue(w.check_if_equal(json_files[0]))
+ def test_wfwf18_simple_duplicate(self):
+ w = Workflow(f"tests/ressources/workflows/wf18", display_info=False, duplicate=True)
+ w.initialise()
+ json_files = glob.glob(f'tests/ressources/workflows/wf18/*.json', recursive=False)
+ self.assertTrue(w.check_if_equal(json_files[0]))
+
def test_wfwf13_simple_duplicate(self):
w = Workflow(f"tests/ressources/workflows/wf13", display_info=False, duplicate=True)
w.initialise()