From: Xiang Zhang <angwerzx@126.com>
Date: Mon, 6 Feb 2017 02:50:09 +0000 (+0800)
Subject: Issue #29405: Make total calculation in _guess_delimiter more accurate.
X-Git-Tag: v3.7.0a1~1406
X-Git-Url: http://git.ipfire.org/gitweb.cgi?a=commitdiff_plain;h=6aee6fbce8f3d7b8c8eae5d8f88fc2282698a6dc;p=thirdparty%2FPython%2Fcpython.git

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

diff --git a/Lib/csv.py b/Lib/csv.py
index 0349e0bd1162..6a8587674fe0 100644
--- a/Lib/csv.py
+++ b/Lib/csv.py
@@ -307,7 +307,7 @@ class Sniffer:
         charFrequency = {}
         modes = {}
         delims = {}
-        start, end = 0, min(chunkLength, len(data))
+        start, end = 0, chunkLength
         while start < len(data):
             iteration += 1
             for line in data[start:end]:
@@ -336,7 +336,7 @@ class Sniffer:
 
             # build a list of possible delimiters
             modeList = modes.items()
-            total = float(chunkLength * iteration)
+            total = float(min(chunkLength * iteration, len(data)))
             # (rows of consistent data) / (number of rows) = 100%
             consistency = 1.0
             # minimum consistency threshold