How to quickly batch remove roman numerals from csv file-CodePudding

Currently, I'm removing the Roman numerals in some csv files with the following Python code:

def inplace_change(filename, old_string, new_string):
    # Safely read the input filename using 'with'
    with open(filename) as f:
        s = f.read()
        if old_string not in s:
            print('"{old_string}" not found in {filename}.'.format(**locals()))
            return

    # Safely write the changed content, if found in the file
    with open(filename, 'w') as f:
        print('Changing "{old_string}" to "{new_string}" in {filename}'.format(**locals()))
        s = s.replace(old_string, new_string)
        f.write(s)

d_list = ['1. ', '2. ', '3. ', '4. ','XVIII. ','XVII. ','XVI. ','XV. ','XIV. ', 'XIII. ', 
          'XII. ','XI. ', 'IX. ','VIII. ', 'VII. ', 'VI. ','IV. ', 'IV. ', 'XVIII.','XVII.','XVI.','XV.','XIV.', 'XIII.', 
          'XII.','XI.', 'IX.','VIII.', 'VII.', 'VI.','IV.', 'IV.', 'Ⅰ.', 'Ⅱ.','Ⅲ.','Ⅳ.','Ⅴ.','Ⅵ.','Ⅶ-1.','Ⅶ-2.','Ⅶ.','Ⅱ.'
           'Ⅷ.','Ⅸ.','Ⅹ.','1.','2.','3.','4.','5.','6.','7.',
         'I. ','II. ','III. ','Ⅷ.',
         'ⅥI. ',  'VIIII. ',  '- ',  'I',  'II',
          'V.',  'Ⅵ',  'VIII',  'I.',  'II.',
          'V.',  'X.',  'Ⅹ',  'V',  'Ⅷ.',
         ]
for file in os.listdir(output_path   '/CIS'): 
    for dlist in d_list:    
        inplace_change(output_path  '/CIS/'  file,  old_string= dlist, new_string= '')  
        continue

However, the processing speed is too slow, which is a concern. Is there a faster and more convenient way?

CodePudding user response：

From what I understood from your code, in each iteration over d_list, you have to then open the file. So the process is not efficient because each read/write on files will cost some time.

How about opening a file, then iterate over d_list? For example:

new_string= ''
d_list = ['1. ', '2. ', '3. ', '4. ','XVIII. ','XVII. ','XVI. ','XV. ','XIV. ', 'XIII. ', 
          'XII. ','XI. ', 'IX. ','VIII. ', 'VII. ', 'VI. ','IV. ', 'IV. ', 'XVIII.','XVII.','XVI.','XV.','XIV.', 'XIII.', 
          'XII.','XI.', 'IX.','VIII.', 'VII.', 'VI.','IV.', 'IV.', 'Ⅰ.', 'Ⅱ.','Ⅲ.','Ⅳ.','Ⅴ.','Ⅵ.','Ⅶ-1.','Ⅶ-2.','Ⅶ.','Ⅱ.'
           'Ⅷ.','Ⅸ.','Ⅹ.','1.','2.','3.','4.','5.','6.','7.',
         'I. ','II. ','III. ','Ⅷ.',
         'ⅥI. ',  'VIIII. ',  '- ',  'I',  'II',
          'V.',  'Ⅵ',  'VIII',  'I.',  'II.',
          'V.',  'X.',  'Ⅹ',  'V',  'Ⅷ.',
         ]

def inplace_change(filename):
    # Safely read the input filename using 'with'
    with open(filename, 'r ') as f:    #'r ' is for read and write
        s = f.read()
        for old_string in d_list: 
            if old_string not in s:
                print(f'"{old_string}" not found in {filename}.')
            else:
                # Safely write the changed content, if found in the file
                f.seek(0)    #IMPORTANT, to bring the cursor to the beginning of the file
                print(f'Changing "{old_string}" to "{new_string}" in {filename}')
                s = s.replace(old_string, new_string)
                f.write(s)

for file in os.listdir(output_path   '/CIS'): 
    inplace_change(output_path  '/CIS/'  file)