traverseda
/
cpython
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Issue #29405: Make total calculation in _guess_delimiter more accurate.

This commit is contained in:
Xiang Zhang 2017-02-06 10:50:09 +08:00
parent 97353845f8
commit 6aee6fbce8
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
Lib/csv.py
View File

@ -307,7 +307,7 @@ class Sniffer:
charFrequency = {} charFrequency = {}
modes = {} modes = {}
delims = {} delims = {}
start, end = 0, min(chunkLength, len(data)) start, end = 0, chunkLength
while start < len(data): while start < len(data):
iteration += 1 iteration += 1
for line in data[start:end]: for line in data[start:end]:
@ -336,7 +336,7 @@ class Sniffer:
# build a list of possible delimiters # build a list of possible delimiters
modeList = modes.items() modeList = modes.items()
total = float(chunkLength * iteration) total = float(min(chunkLength * iteration, len(data)))
# (rows of consistent data) / (number of rows) = 100% # (rows of consistent data) / (number of rows) = 100%
consistency = 1.0 consistency = 1.0
# minimum consistency threshold # minimum consistency threshold