From 67e4ecd451fb7d675603b93e035883b4a2bdf277 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Walter=20D=C3=B6rwald?= Date: Mon, 4 Apr 2005 21:56:28 +0000 Subject: Backport checkin: Fix for SF bug #1175396: readline() will now read one more character, if the last character read is "\r" (and size is None, i.e. we're allowed to call read() multiple times), so that we can return the correct line ending (this additional character might be a "\n"). If the stream is temporarily exhausted, we might return the wrong line ending (if the last character read is "\r" and the next one (after the byte stream provides more data) is "\n", but at least the atcr member ensures that we get the correct number of lines (i.e. this "\n" will not be treated as another line ending). --- Lib/codecs.py | 9 +++++ Lib/test/test_codecs.py | 91 ++++++++++++++++++++++++++++++++++++++++++++----- 2 files changed, 91 insertions(+), 9 deletions(-) diff --git a/Lib/codecs.py b/Lib/codecs.py index 022b51b..3db9248 100644 --- a/Lib/codecs.py +++ b/Lib/codecs.py @@ -310,6 +310,15 @@ class StreamReader(Codec): data = data[1:] if data: self.atcr = data.endswith(u"\r") + # If we're at a "\r" (and are allowed to read more), read one + # extra character (which might be a "\n") to get a proper + # line ending. (If the stream is temporarily exhausted we return + # the wrong line ending, but at least we won't generate a bogus + # second line.) + if self.atcr and size is None: + data += self.read(size=1, chars=1) + self.atcr = data.endswith(u"\r") + line += data lines = line.splitlines(True) if lines: diff --git a/Lib/test/test_codecs.py b/Lib/test/test_codecs.py index c8d99fe..7a19b32 100644 --- a/Lib/test/test_codecs.py +++ b/Lib/test/test_codecs.py @@ -84,15 +84,88 @@ class ReadTest(unittest.TestCase): # reader has to look ahead whether this is a lone \r or a \r\n for size in xrange(80): for lineend in u"\n \r\n \r \u2028".split(): - s = size*u"a" + lineend + u"xxx\n" - self.assertEqual( - getreader(s).readline(keepends=True), - size*u"a" + lineend, - ) - self.assertEqual( - getreader(s).readline(keepends=False), - size*u"a", - ) + s = 10*(size*u"a" + lineend + u"xxx\n") + reader = getreader(s) + for i in xrange(10): + self.assertEqual( + reader.readline(keepends=True), + size*u"a" + lineend, + ) + reader = getreader(s) + for i in xrange(10): + self.assertEqual( + reader.readline(keepends=False), + size*u"a", + ) + + def test_bug1175396(self): + s = [ + '<%!--===================================================\r\n', + ' BLOG index page: show recent articles,\r\n', + ' today\'s articles, or articles of a specific date.\r\n', + '========================================================--%>\r\n', + '<%@inputencoding="ISO-8859-1"%>\r\n', + '<%@pagetemplate=TEMPLATE.y%>\r\n', + '<%@import=import frog.util, frog%>\r\n', + '<%@import=import frog.objects%>\r\n', + '<%@import=from frog.storageerrors import StorageError%>\r\n', + '<%\r\n', + '\r\n', + 'import logging\r\n', + 'log=logging.getLogger("Snakelets.logger")\r\n', + '\r\n', + '\r\n', + 'user=self.SessionCtx.user\r\n', + 'storageEngine=self.SessionCtx.storageEngine\r\n', + '\r\n', + '\r\n', + 'def readArticlesFromDate(date, count=None):\r\n', + ' entryids=storageEngine.listBlogEntries(date)\r\n', + ' entryids.reverse() # descending\r\n', + ' if count:\r\n', + ' entryids=entryids[:count]\r\n', + ' try:\r\n', + ' return [ frog.objects.BlogEntry.load(storageEngine, date, Id) for Id in entryids ]\r\n', + ' except StorageError,x:\r\n', + ' log.error("Error loading articles: "+str(x))\r\n', + ' self.abort("cannot load articles")\r\n', + '\r\n', + 'showdate=None\r\n', + '\r\n', + 'arg=self.Request.getArg()\r\n', + 'if arg=="today":\r\n', + ' #-------------------- TODAY\'S ARTICLES\r\n', + ' self.write("

Today\'s articles

")\r\n', + ' showdate = frog.util.isodatestr() \r\n', + ' entries = readArticlesFromDate(showdate)\r\n', + 'elif arg=="active":\r\n', + ' #-------------------- ACTIVE ARTICLES redirect\r\n', + ' self.Yredirect("active.y")\r\n', + 'elif arg=="login":\r\n', + ' #-------------------- LOGIN PAGE redirect\r\n', + ' self.Yredirect("login.y")\r\n', + 'elif arg=="date":\r\n', + ' #-------------------- ARTICLES OF A SPECIFIC DATE\r\n', + ' showdate = self.Request.getParameter("date")\r\n', + ' self.write("

Articles written on %s

"% frog.util.mediumdatestr(showdate))\r\n', + ' entries = readArticlesFromDate(showdate)\r\n', + 'else:\r\n', + ' #-------------------- RECENT ARTICLES\r\n', + ' self.write("

Recent articles

")\r\n', + ' dates=storageEngine.listBlogEntryDates()\r\n', + ' if dates:\r\n', + ' entries=[]\r\n', + ' SHOWAMOUNT=10\r\n', + ' for showdate in dates:\r\n', + ' entries.extend( readArticlesFromDate(showdate, SHOWAMOUNT-len(entries)) )\r\n', + ' if len(entries)>=SHOWAMOUNT:\r\n', + ' break\r\n', + ' \r\n', + ] + stream = StringIO.StringIO("".join(s).encode(self.encoding)) + reader = codecs.getreader(self.encoding)(stream) + for (i, line) in enumerate(reader): + self.assertEqual(line, s[i]) def test_readlinequeue(self): q = Queue() -- cgit v0.12