#!/usr/bin/env python
# coding: utf-8

# ### based on https://www.biostars.org/p/9513063/#9513063

# In[1]:


s='''1.83155e-63 8 25

7.37596e-64 10 20

9.14344e-65 7 24

6.86568e-72 30 50

6.45089e-69 24679455 24680333

4.49086e-56 24679455 24680312

1.78896e-52 35167152 35167547

2.57611e-51 35167209 35167547'''
get_ipython().run_line_magic('store', 's >data.txt')


# In[2]:


import pandas as pd
df = pd.read_csv("data.txt",sep=" ",names=["e-value","start","end"])


# In[3]:


df.head()


# In[4]:


def range_extract(lst):
    'Yield 2-tuple ranges or 1-tuple single elements from list of increasing'
    'ints; interval making code modified from'  
    'https://www.rosettacode.org/wiki/Range_extraction#Python'
    lenlst = len(lst)
    i = 0
    while i< lenlst:
        low = lst[i]
        while i <lenlst-1 and lst[i]+1 == lst[i+1]: i +=1
        hi = lst[i]
        if hi - low >= 1:    #<---MAIN DIFFERENCE
            yield (low, hi)
        else:
            yield (low,)
        i += 1
 
def printr(ranges):
    print( '\n'.join( (('%i:%i' % r) if len(r) == 2 else '%i' % r)
                     for r in ranges ) )
def expand_all_ranges_to_each_position(the_min,the_max):
    '''
    Takes the minimum and the max position and returns a list of all the positions
    in between as well as both the boundaries.
    '''
    return list(range(the_min,the_max+1))
all_positions = []
for row in df.itertuples():
    all_positions.extend(expand_all_ranges_to_each_position(min(row.start,row.end),max(row.start,row.end)))
all_positions = sorted(set(all_positions)) #get unique individual positions sorted; `set()` insures unique positions
for lst in [all_positions]:
    #print(list(range_extract(lst)))
    printr(range_extract(sorted(lst)))


# In[ ]: