Question

Imagine we have a piece of code which cuts the large data into smaller data and do some process on it.

def node_cut(input_file):
    NODE_LENGTH = 500
    count_output = 0
    node_list=[]

    for line in input_file.readlines():
        if len(node_list) >= NODE_LENGTH :
            count_output += 1   
            return( node_list,count_output )
            node_list=[]  

        node,t=line.split(',')
        node_list.append(node) 

if __name__ =='__main__':

    input_data = open('all_nodes.txt','r')
    node_list, count_output = node_cut(input_data)
    some_process(node_list)

while node_cut return the first data list, the for loop stop going on for the rest of the large data. How I can make sure that it returns but still the loop continues?

Answer 1

Use yield:

def node_cut(input_file):
    NODE_LENGTH = 500
    count_output = 0
    node_list=[]

    for line in input_file.readlines():
        if len(node_list) >= NODE_LENGTH :
            count_output += 1   
            yield( node_list,count_output )
            node_list=[]  

        node,t=line.split(',')
        node_list.append(node) 

if __name__ =='__main__':
    with open('all_nodes.txt','r') as input_data:
      for node_list, count_output in node_cut(input_data):
        some_process(node_list)