Create separate function for duplicate check

[Johannes Wiesner]

Code would be more readable if the duplicate checks would get their own function with their own doc-strings:

demetrius/demetrius.py

Lines 166 to 178 in 1d4c6d3

 # find literal duplicates and modify the respective destination directories 
 for _,dir_name in dst_dirs_df.groupby('src_dir_name'): 
     if not dir_name['src_dir_path'].nunique() == 1: 
         for idx,(_,src_dir_path) in enumerate(dir_name.groupby('src_dir_path'),start=1): 
             dst_dirs_df.loc[src_dir_path.index,'dst_dir_path'] =  dst_dirs_df.loc[src_dir_path.index,'dst_dir_path'] + '_' + str(idx) 
  
 # find pseudo duplicates and modify the respective destination directories 
 dst_dirs_df['dst_dir_path_lower_case'] = dst_dirs_df['dst_dir_path'].map(str.lower) 
      
 for _,dst_dir_path in dst_dirs_df.groupby('dst_dir_path_lower_case'): 
     if dst_dir_path['src_dir_path'].nunique() != 1: 
         for idx,(_,dir_name) in enumerate(dst_dir_path.groupby('src_dir_name'),start=1): 
             dst_dirs_df.loc[dir_name.index,'dst_dir_path'] = dst_dirs_df.loc[dir_name.index,'dst_dir_path'] + ' (' + str(idx) + ')' 

[Johannes Wiesner]

Then it would be also more easy + readable to define how the index should look like (e.g. _idx or (idx))