Last active
December 26, 2015 18:29
-
-
Save bjorndown/7195299 to your computer and use it in GitHub Desktop.
Tries to transform a bunch of INSERT statements into a CSV 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
import re | |
import sys | |
PATTERN = re.compile("INSERT INTO ([\w_\.]+) \(([\w,\"]+)\) VALUES \(([\w ,:'\.\(\)]+)\);$", flags=re.IGNORECASE) | |
TO_DATE_PATTERN = "to_date\(('[0-9 :\.]+'),'DD.MM.RR HH24:MI:SS'\)" | |
def convert(filename): | |
with open(filename) as source_file: | |
output = None | |
current_table_name = None | |
for line in source_file: | |
match = PATTERN.search(line) | |
if match: | |
table = match.group(1) | |
header = match.group(2) | |
row = match.group(3) | |
if output is None: | |
output = create_new_csv(table, header, filename) | |
if not current_table_name == table: | |
output.close() | |
output = create_new_csv(table, header, filename) | |
current_table_name = table | |
processed_row = process_row(row) | |
print(processed_row, file=output) | |
output.close() | |
def create_new_csv(table, header, filename): | |
output = open('{}-{}.csv'.format(filename, table), 'w') | |
print(header, file=output) | |
return output | |
def process_row(row): | |
return re.sub(TO_DATE_PATTERN, '\g<1>', row) | |
if __name__ == '__main__': | |
convert(sys.argv[1]) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment