summaryrefslogtreecommitdiffstats
path: root/Lib/csv.py
diff options
context:
space:
mode:
authorBenjamin Peterson <benjamin@python.org>2009-10-04 14:49:41 (GMT)
committerBenjamin Peterson <benjamin@python.org>2009-10-04 14:49:41 (GMT)
commit4ac9ce4f9a33a330a555ae8015e2f2ae2780fafb (patch)
treeb9bbcfd8f4aae362d8335d13e592f605b674ea19 /Lib/csv.py
parentbd27aef8a0f776cc72387be31e1e74ecbcbbdf54 (diff)
downloadcpython-4ac9ce4f9a33a330a555ae8015e2f2ae2780fafb.zip
cpython-4ac9ce4f9a33a330a555ae8015e2f2ae2780fafb.tar.gz
cpython-4ac9ce4f9a33a330a555ae8015e2f2ae2780fafb.tar.bz2
Merged revisions 74779-74786,74793,74795,74811,74860-74861,74863,74876,74886,74896,74901,74903,74908,74912,74930,74933,74943,74946,74952-74955,75015,75019,75032,75068,75076,75095,75098,75102,75129,75139,75230 via svnmerge from
svn+ssh://pythondev@svn.python.org/python/trunk ........ r74779 | michael.foord | 2009-09-13 11:13:36 -0500 (Sun, 13 Sep 2009) | 1 line Change to tutorial wording for reading text / binary files on Windows. Issue #6301. ........ r74780 | michael.foord | 2009-09-13 11:40:02 -0500 (Sun, 13 Sep 2009) | 1 line Objects that compare equal automatically pass or fail assertAlmostEqual and assertNotAlmostEqual tests on unittest.TestCase. Issue 6567. ........ r74781 | michael.foord | 2009-09-13 11:46:19 -0500 (Sun, 13 Sep 2009) | 1 line Note that sys._getframe is not guaranteed to exist in all implementations of Python, and a corresponding note in inspect.currentframe. Issue 6712. ........ r74782 | michael.foord | 2009-09-13 12:07:46 -0500 (Sun, 13 Sep 2009) | 1 line Tutorial tweaks. Issue 6849. ........ r74783 | michael.foord | 2009-09-13 12:28:35 -0500 (Sun, 13 Sep 2009) | 1 line unittest.TestLoader.loadTestsFromName honors the loader suiteClass attribute. Issue 6866. ........ r74784 | georg.brandl | 2009-09-13 13:15:07 -0500 (Sun, 13 Sep 2009) | 1 line Typo fix. ........ r74785 | michael.foord | 2009-09-13 14:07:03 -0500 (Sun, 13 Sep 2009) | 1 line Test discovery in unittest will only attempt to import modules that are importable; i.e. their names are valid Python identifiers. If an import fails during discovery this will be recorded as an error and test discovery will continue. Issue 6568. ........ r74786 | michael.foord | 2009-09-13 14:08:18 -0500 (Sun, 13 Sep 2009) | 1 line Remove an extraneous space in unittest documentation. ........ r74793 | georg.brandl | 2009-09-14 09:50:47 -0500 (Mon, 14 Sep 2009) | 1 line #6908: fix association of hashlib hash attributes. ........ r74795 | benjamin.peterson | 2009-09-14 22:36:26 -0500 (Mon, 14 Sep 2009) | 1 line Py_SetPythonHome uses static storage #6913 ........ r74811 | georg.brandl | 2009-09-15 15:26:59 -0500 (Tue, 15 Sep 2009) | 1 line Add Armin Ronacher. ........ r74860 | benjamin.peterson | 2009-09-16 21:46:54 -0500 (Wed, 16 Sep 2009) | 1 line kill bare except ........ r74861 | benjamin.peterson | 2009-09-16 22:18:28 -0500 (Wed, 16 Sep 2009) | 1 line pep 8 defaults ........ r74863 | benjamin.peterson | 2009-09-16 22:27:33 -0500 (Wed, 16 Sep 2009) | 1 line rationalize a bit ........ r74876 | georg.brandl | 2009-09-17 11:15:53 -0500 (Thu, 17 Sep 2009) | 1 line #6932: remove paragraph that advises relying on __del__ being called. ........ r74886 | benjamin.peterson | 2009-09-17 16:33:46 -0500 (Thu, 17 Sep 2009) | 1 line use macros ........ r74896 | georg.brandl | 2009-09-18 02:22:41 -0500 (Fri, 18 Sep 2009) | 1 line #6936: for interactive use, quit() is just fine. ........ r74901 | georg.brandl | 2009-09-18 04:14:52 -0500 (Fri, 18 Sep 2009) | 1 line #6905: use better exception messages in inspect when the argument is of the wrong type. ........ r74903 | georg.brandl | 2009-09-18 04:18:27 -0500 (Fri, 18 Sep 2009) | 1 line #6938: "ident" is always a string, so use a format code which works. ........ r74908 | georg.brandl | 2009-09-18 08:57:11 -0500 (Fri, 18 Sep 2009) | 1 line Use str.format() to fix beginner's mistake with %-style string formatting. ........ r74912 | georg.brandl | 2009-09-18 11:19:56 -0500 (Fri, 18 Sep 2009) | 1 line Optimize optimization and fix method name in docstring. ........ r74930 | georg.brandl | 2009-09-18 16:21:41 -0500 (Fri, 18 Sep 2009) | 1 line #6925: rewrite docs for locals() and vars() a bit. ........ r74933 | georg.brandl | 2009-09-18 16:35:59 -0500 (Fri, 18 Sep 2009) | 1 line #6930: clarify description about byteorder handling in UTF decoder routines. ........ r74943 | georg.brandl | 2009-09-19 02:35:07 -0500 (Sat, 19 Sep 2009) | 1 line #6944: the argument to PyArg_ParseTuple should be a tuple, otherwise a SystemError is set. Also clean up another usage of PyArg_ParseTuple. ........ r74946 | georg.brandl | 2009-09-19 03:43:16 -0500 (Sat, 19 Sep 2009) | 1 line Update bug tracker reference. ........ r74952 | georg.brandl | 2009-09-19 05:42:34 -0500 (Sat, 19 Sep 2009) | 1 line #6946: fix duplicate index entries for datetime classes. ........ r74953 | georg.brandl | 2009-09-19 07:04:16 -0500 (Sat, 19 Sep 2009) | 1 line Fix references to threading.enumerate(). ........ r74954 | georg.brandl | 2009-09-19 08:13:56 -0500 (Sat, 19 Sep 2009) | 1 line Add Doug. ........ r74955 | georg.brandl | 2009-09-19 08:20:49 -0500 (Sat, 19 Sep 2009) | 1 line Add Mark Summerfield. ........ r75015 | georg.brandl | 2009-09-22 05:55:08 -0500 (Tue, 22 Sep 2009) | 1 line Fix encoding name. ........ r75019 | vinay.sajip | 2009-09-22 12:23:41 -0500 (Tue, 22 Sep 2009) | 1 line Fixed a typo, and added sections on optimization and using arbitrary objects as messages. ........ r75032 | benjamin.peterson | 2009-09-22 17:15:28 -0500 (Tue, 22 Sep 2009) | 1 line fix typos/rephrase ........ r75068 | benjamin.peterson | 2009-09-25 21:57:59 -0500 (Fri, 25 Sep 2009) | 1 line comment out ugly xxx ........ r75076 | vinay.sajip | 2009-09-26 09:53:32 -0500 (Sat, 26 Sep 2009) | 1 line Tidied up name of parameter in StreamHandler ........ r75095 | michael.foord | 2009-09-27 14:15:41 -0500 (Sun, 27 Sep 2009) | 1 line Test creation moved from TestProgram.parseArgs to TestProgram.createTests exclusively. Issue 6956. ........ r75098 | michael.foord | 2009-09-27 15:08:23 -0500 (Sun, 27 Sep 2009) | 1 line Documentation improvement for load_tests protocol in unittest. Issue 6515. ........ r75102 | skip.montanaro | 2009-09-27 21:12:27 -0500 (Sun, 27 Sep 2009) | 3 lines Patch from Thomas Barr so that csv.Sniffer will set doublequote property. Closes issue 6606. ........ r75129 | vinay.sajip | 2009-09-29 02:08:54 -0500 (Tue, 29 Sep 2009) | 1 line Issue #7014: logging: Improved IronPython 2.6 compatibility. ........ r75139 | raymond.hettinger | 2009-09-29 13:53:24 -0500 (Tue, 29 Sep 2009) | 3 lines Issue 7008: Better document str.title and show how to work around the apostrophe problem. ........ r75230 | benjamin.peterson | 2009-10-04 08:38:38 -0500 (Sun, 04 Oct 2009) | 1 line test logging ........
Diffstat (limited to 'Lib/csv.py')
-rw-r--r--Lib/csv.py22
1 files changed, 17 insertions, 5 deletions
diff --git a/Lib/csv.py b/Lib/csv.py
index ee62abe..59ec372 100644
--- a/Lib/csv.py
+++ b/Lib/csv.py
@@ -165,7 +165,7 @@ class Sniffer:
Returns a dialect (or None) corresponding to the sample
"""
- quotechar, delimiter, skipinitialspace = \
+ quotechar, doublequote, delimiter, skipinitialspace = \
self._guess_quote_and_delimiter(sample, delimiters)
if not delimiter:
delimiter, skipinitialspace = self._guess_delimiter(sample,
@@ -179,8 +179,8 @@ class Sniffer:
lineterminator = '\r\n'
quoting = QUOTE_MINIMAL
# escapechar = ''
- doublequote = False
+ dialect.doublequote = doublequote
dialect.delimiter = delimiter
# _csv.reader won't accept a quotechar of ''
dialect.quotechar = quotechar or '"'
@@ -212,8 +212,8 @@ class Sniffer:
break
if not matches:
- return ('', None, 0) # (quotechar, delimiter, skipinitialspace)
-
+ # (quotechar, doublequote, delimiter, skipinitialspace)
+ return ('', False, None, 0)
quotes = {}
delims = {}
spaces = 0
@@ -248,7 +248,19 @@ class Sniffer:
delim = ''
skipinitialspace = 0
- return (quotechar, delim, skipinitialspace)
+ # if we see an extra quote between delimiters, we've got a
+ # double quoted format
+ dq_regexp = re.compile(r"((%(delim)s)|^)\W*%(quote)s[^%(delim)s\n]*%(quote)s[^%(delim)s\n]*%(quote)s\W*((%(delim)s)|$)" % \
+ {'delim':delim, 'quote':quotechar}, re.MULTILINE)
+
+
+
+ if dq_regexp.search(data):
+ doublequote = True
+ else:
+ doublequote = False
+
+ return (quotechar, doublequote, delim, skipinitialspace)
def _guess_delimiter(self, data, delimiters):