dmitriikuzinepam commented on a change in pull request #15775:
URL: https://github.com/apache/beam/pull/15775#discussion_r735329837
##########
File path: sdks/python/apache_beam/io/textio.py
##########
@@ -257,17 +259,37 @@ def _find_separator_bounds(self, file_to_read,
read_buffer):
# Using find() here is more efficient than a linear scan
# of the byte array.
- next_lf = read_buffer.data.find(self._delimiter, current_pos)
+ next_lf = read_buffer.data.find(delimiter, current_pos)
if next_lf >= 0:
- if self._delimiter == b'\n' and read_buffer.data[next_lf -
- 1:next_lf] == b'\r':
+ if self._delimiter is None and delimiter == b'\n' \
+ and read_buffer.data[next_lf - 1:next_lf] == b'\r':
+ # Default delimiter
# Found a '\r\n'. Accepting that as the next separator.
return (next_lf - 1, next_lf + 1)
else:
+ # User defined delimiter
# Found a delimiter. Accepting that as the next separator.
return (next_lf, next_lf + delimiter_len)
+ elif read_buffer.data.find(delimiter[0], current_pos) >= 0:
Review comment:
Thanks too much!
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
