Filter out files to feed into several regular expressions to remove "Contributed by", "Written by", etc. notices.

glibc_contrib_filter.py

from glibc_shared_code import get_glibc_shared_code                          
import os                                                                    
import stat                                                                  
import re                                                                    
                                                                             
shared_code = ['./' + f for f in                                             
        sum(get_glibc_shared_code('SHARED-FILES').values(), [])]             
                                                                             
exclude_patterns = [                                                         
        r'.*ChangeLog.*',                                                    
        r'.*/tst-regex.input',                                               
        r'.*\.git/.*',                                                       
        r'.*/NEWS',                                                          
        r'.*\.data',                                                         
        r'.*configure.ac',                                                   
        r'.*benchtests.*',                                                   
        r'.*CONTRIBUTED-BY',                                                 
        r'.*po\/.*\.po',                                                     
        r'.*build/.*']                                                       
                                                                             
exclude_re = [re.compile(r) for r in exclude_patterns]                       
                                                                             
def doesnt_match(f):                                                         
    global exclude_re                                                        
                                                                             
    for r in exclude_re:                                                     
        if r.match(f):                                                       
            return False                                                     
                                                                             
    return True                                                              
                                                                             
PATH='.'                                                                     
result = [os.path.join(dp, f) for dp, dn, filenames in os.walk(PATH) for f in
        filenames if stat.S_ISREG(os.stat(os.path.join(dp, f)).st_mode) and  
        not stat.S_ISLNK(os.stat(os.path.join(dp, f)).st_mode) and           
        doesnt_match(os.path.join(dp, f)) and os.path.join(dp, f) not in     
        shared_code]                                                         
                                                                             
for r in result:                                                             
    print(r)