Last active
November 2, 2017 01:07
-
-
Save mrvaldes/8130f23da938cf596e7cda10fdabaeb5 to your computer and use it in GitHub Desktop.
Example of inplace line editing (update line by line) on a big file
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
def iterate_rainbow(file): | |
import mmap | |
import contextlib | |
import csv | |
from io import StringIO | |
encoding = 'utf-8' | |
csv_opts = {'delimiter': ';', 'quoting': csv.QUOTE_MINIMAL, 'quotechar': '"'} | |
with open(file, 'r+b') as fd: | |
with contextlib.closing(mmap.mmap(fd.fileno(), 0, access=mmap.ACCESS_WRITE)) as mm: | |
start = 0 | |
n_line = 0 | |
for line in iter(mm.readline, b''): | |
n_line += 1 | |
print("n_line {0}".format(n_line)) | |
end = mm.tell() | |
line = line.decode(encoding).rstrip() | |
# print("{0}-{1}: {2}".format(start, end, line)) | |
row = next(csv.reader([line], **csv_opts)) | |
encrypt_row(row, encoding) | |
new_line_buff = StringIO() | |
csv.writer(new_line_buff, **csv_opts).writerow(row) | |
new_line = new_line_buff.getvalue().encode(encoding) | |
new_end = start + len(new_line) | |
# mm.seek(start) | |
fd.seek(0) | |
size_before = mm.size() | |
fd.write(mm[0:start] + new_line + mm[end:]) | |
fd.flush() | |
size_after = mm.size() | |
if size_after > size_before: | |
mm.resize(size_after) | |
mm.seek(new_end) | |
start = new_end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment