Created
April 15, 2016 15:52
-
-
Save mp4096/c905e85bddb57e95c5d62bc9b058fe97 to your computer and use it in GitHub Desktop.
Strip trailing whitespaces and replace hard tabs
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import codecs | |
import os | |
import fnmatch | |
def delete_if_exists(filename): | |
if os.path.exists(filename): | |
os.remove(filename) | |
def find_files(root_folder, filter_pattern): | |
for root, dirs, files in os.walk(root_folder): | |
for basename in files: | |
if fnmatch.fnmatch(basename, filter_pattern): | |
filename = os.path.join(root, basename) | |
yield filename | |
def normalize_line(line): | |
soft_tab_length = 2 | |
return line.rstrip().replace("\t", " "*soft_tab_length) | |
def normalize_single_file(filename): | |
preferred_linesep = "\n" | |
filename_bak = os.path.splitext(filename)[0] + ".bak" | |
delete_if_exists(filename_bak) | |
os.rename(filename, filename_bak) | |
with codecs.open(filename_bak, "r", encoding="utf-8") as f_in, \ | |
codecs.open(filename, "w", encoding="utf-8") as f_out: | |
for line in f_in: | |
normalized_line = normalize_line(line) | |
f_out.write(normalized_line) | |
f_out.write(preferred_linesep) | |
def normalize_in_all_subfolders(root_folder, filter_pattern): | |
for filename in find_files(root_folder, filter_pattern): | |
print("Processing '{:s}'...".format(filename)) | |
normalize_single_file(filename) | |
normalize_in_all_subfolders(".", "*.tex") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment