summaryrefslogtreecommitdiff
path: root/Lib/email/feedparser.py
diff options
context:
space:
mode:
authorR David Murray <rdmurray@bitdance.com>2011-04-18 13:59:37 -0400
committerR David Murray <rdmurray@bitdance.com>2011-04-18 13:59:37 -0400
commit3edd22ac950d3a2bcc1ad2e5a83554970aef3369 (patch)
treeb4661afc1be45e0d072c1c83ab354b2362f05afb /Lib/email/feedparser.py
parentce16be91dc68597b0c5bfc7b4b1c5136fe5697a6 (diff)
downloadcpython-git-3edd22ac950d3a2bcc1ad2e5a83554970aef3369.tar.gz
#11731: simplify/enhance parser/generator API by introducing policy objects.
This new interface will also allow for future planned enhancements in control over the parser/generator without requiring any additional complexity in the parser/generator API. Patch reviewed by Éric Araujo and Barry Warsaw.
Diffstat (limited to 'Lib/email/feedparser.py')
-rw-r--r--Lib/email/feedparser.py23
1 files changed, 17 insertions, 6 deletions
diff --git a/Lib/email/feedparser.py b/Lib/email/feedparser.py
index 1b752d0193..60de49e97f 100644
--- a/Lib/email/feedparser.py
+++ b/Lib/email/feedparser.py
@@ -25,6 +25,7 @@ import re
from email import errors
from email import message
+from email import policy
NLCRE = re.compile('\r\n|\r|\n')
NLCRE_bol = re.compile('(\r\n|\r|\n)')
@@ -134,9 +135,16 @@ class BufferedSubFile(object):
class FeedParser:
"""A feed-style parser of email."""
- def __init__(self, _factory=message.Message):
- """_factory is called with no arguments to create a new message obj"""
+ def __init__(self, _factory=message.Message, *, policy=policy.default):
+ """_factory is called with no arguments to create a new message obj
+
+ The policy keyword specifies a policy object that controls a number of
+ aspects of the parser's operation. The default policy maintains
+ backward compatibility.
+
+ """
self._factory = _factory
+ self.policy = policy
self._input = BufferedSubFile()
self._msgstack = []
self._parse = self._parsegen().__next__
@@ -168,7 +176,8 @@ class FeedParser:
# Look for final set of defects
if root.get_content_maintype() == 'multipart' \
and not root.is_multipart():
- root.defects.append(errors.MultipartInvariantViolationDefect())
+ defect = errors.MultipartInvariantViolationDefect()
+ self.policy.handle_defect(root, defect)
return root
def _new_message(self):
@@ -281,7 +290,8 @@ class FeedParser:
# defined a boundary. That's a problem which we'll handle by
# reading everything until the EOF and marking the message as
# defective.
- self._cur.defects.append(errors.NoBoundaryInMultipartDefect())
+ defect = errors.NoBoundaryInMultipartDefect()
+ self.policy.handle_defect(self._cur, defect)
lines = []
for line in self._input:
if line is NeedMoreData:
@@ -385,7 +395,8 @@ class FeedParser:
# that as a defect and store the captured text as the payload.
# Everything from here to the EOF is epilogue.
if capturing_preamble:
- self._cur.defects.append(errors.StartBoundaryNotFoundDefect())
+ defect = errors.StartBoundaryNotFoundDefect()
+ self.policy.handle_defect(self._cur, defect)
self._cur.set_payload(EMPTYSTRING.join(preamble))
epilogue = []
for line in self._input:
@@ -437,7 +448,7 @@ class FeedParser:
# is illegal, so let's note the defect, store the illegal
# line, and ignore it for purposes of headers.
defect = errors.FirstHeaderLineIsContinuationDefect(line)
- self._cur.defects.append(defect)
+ self.policy.handle_defect(self._cur, defect)
continue
lastvalue.append(line)
continue