process_MDA_strings_github_migration

process_MDA_strings_github_migration.py

'''Module to assess and adjust URLs / links in MDA project documentation after recent move to github.'''
import os
import subprocess

for dirname, dirnames, filenames in os.walk('/Users/treddy/python_modules/MDAnalysis/MDA_dev/mdanalysis/'):
    # print path to all filenames.
    #for filename in filenames:
        #print os.path.join(dirname, filename)

    #print all lines from .py files with OLD HOMEPAGE URLs in them:
    #for filename in filenames:
        #if filename[-2:] == 'py':
            #with open(os.path.join(dirname,filename),'r') as python_module:
                #for line in python_module.readlines():
                    #if 'http://mdanalysis.googlecode.com' in line:
                        #print filename,':', line

    
    #replace old homepage URL with new homepage URL in all .py files in MDA dir structure
#    for filename in filenames:
#        if filename[-2:] == 'py':
#            filepath = os.path.join(dirname,filename)
#            with open(filepath,'r') as current_file:
#                list_lines_current_file = current_file.readlines()
#                list_new_lines = []
#                for line in list_lines_current_file:
#                    if 'http://mdanalysis.googlecode.com' in line:
#                        new_line = line.replace('mdanalysis.googlecode.com','www.MDAnalysis.org') 
#                        list_new_lines.append(new_line)
#                    else:
#                        list_new_lines.append(line)
#            with open(filepath,'w') as replacement_file:
#                replacement_file.writelines(list_new_lines)

    #print all lines from .py files with ANY URLs in them:
    #for filename in filenames:
        #if filename[-2:] == 'py':
            #with open(os.path.join(dirname,filename),'r') as python_module:
                #for line in python_module.readlines():
                    #if 'http' in line:
                        #print filename,':', line

    #print all lines from .py files with OLD issue URLs in them:
    #for filename in filenames:
        #if filename[-2:] == 'py':
            #path = os.path.join(dirname,filename)
            #with open(path,'r') as python_module:
                #for line in python_module.readlines():
                    #if 'http' in line and 'issue' in line and 'google' in line:
                        #print path,':', line

    #replace all SIMPLE issue lines with github equivalents:
    #for filename in filenames:
        #if filename[-2:] == 'py':
            #filepath = os.path.join(dirname,filename)
            #with open(filepath,'r') as current_file:
                #list_lines_current_file = current_file.readlines()
                #list_new_lines = []
                #for line in list_lines_current_file:
                    #if 'http' in line and 'issue' in line and 'google' in line and 'detail' in line and not '#' in line:
                        #print 'old line:', line
                        #issue_number = line.split('=')[-1]
                        #print 'issue_number:', issue_number
                        #new_line = line.replace('http://code.google.com/p/mdanalysis/issues/detail?id=','https://github.com/MDAnalysis/mdanalysis/issues/') 
                        #new_line = new_line.replace('https://code.google.com/p/mdanalysis/issues/detail?id=','https://github.com/MDAnalysis/mdanalysis/issues/') 
                        #list_new_lines.append(new_line)
                        #print 'new line:', new_line
                    #else:
                        #list_new_lines.append(line)
            #with open(filepath,'w') as replacement_file:
                #replacement_file.writelines(list_new_lines)

    #print all lines from .py files containing pertinent (OLD) 'wiki' string:
    #for filename in filenames:
        #if filename[-2:] == 'py':
            #path = os.path.join(dirname,filename)
            #with open(path,'r') as python_module:
                #for line in python_module.readlines():
                    #if 'wiki' in line and 'google' in line:
                        #print path,':', line

    #print all lines from .py files containing ANY URLs (for quick visual check):
    for filename in filenames:
        if filename[-2:] == 'py':
            path = os.path.join(dirname,filename)
            with open(path,'r') as python_module:
                for line in python_module.readlines():
                    if 'http' in line:
                        print filename,':', line