[Python-checkins] python/nondist/sandbox/mailbox libmailbox.tex, 1.14, 1.15 mailbox.py, 1.15, 1.16 test_mailbox.py, 1.10, 1.11
gregorykjohnson@users.sourceforge.net
gregorykjohnson at users.sourceforge.net
Tue Aug 23 05:43:21 CEST 2005
Update of /cvsroot/python/python/nondist/sandbox/mailbox
In directory sc8-pr-cvs1.sourceforge.net:/tmp/cvs-serv9944
Modified Files:
libmailbox.tex mailbox.py test_mailbox.py
Log Message:
* Overhaul handling of line endings to play more nicely with the email
and smtplib modules and to be less surprising:
* Message instances and strings use C-style '\n' line endings, and
files passed to add() or __setitem__() should be text-mode.
* When written to disk, messages use native line endings.
* As in the older module, file-like objects supplied to a message
factory (or returned by get_file()) are still binary-mode-like.
Index: libmailbox.tex
===================================================================
RCS file: /cvsroot/python/python/nondist/sandbox/mailbox/libmailbox.tex,v
retrieving revision 1.14
retrieving revision 1.15
diff -u -d -r1.14 -r1.15
--- libmailbox.tex 22 Aug 2005 20:19:27 -0000 1.14
+++ libmailbox.tex 23 Aug 2005 03:43:11 -0000 1.15
@@ -62,11 +62,12 @@
it.
Parameter \var{message} may be a \class{Message} instance, an
-\class{email.Message.Message} instance, a string, or a file-like object. If
-\var{message} is an instance of the appropriate format-specific
-\class{Message} subclass (e.g., if it's an \class{mboxMessage} instance and
-this is an \class{mbox} instance), its format-specific information is used.
-Otherwise, reasonable defaults for format-specific information are used.
+\class{email.Message.Message} instance, a string, or a file-like object (which
+should be open in text mode). If \var{message} is an instance of the
+appropriate format-specific \class{Message} subclass (e.g., if it's an
+\class{mboxMessage} instance and this is an \class{mbox} instance), its
+format-specific information is used. Otherwise, reasonable defaults for
+format-specific information are used.
\end{methoddesc}
\begin{methoddesc}{remove}{key}
@@ -87,11 +88,11 @@
As with \method{add()}, parameter \var{message} may be a \class{Message}
instance, an \class{email.Message.Message} instance, a string, or a file-like
-object. If \var{message} is an instance of the appropriate format-specific
-\class{Message} subclass (e.g., if it's an \class{mboxMessage} instance and
-this is an \class{mbox} instance), its format-specific information is used.
-Otherwise, the format-specific information of the message that currently
-corresponds to \var{key} is left unchanged.
+object (which should be open in text mode). If \var{message} is an instance of
+the appropriate format-specific \class{Message} subclass (e.g., if it's an
+\class{mboxMessage} instance and this is an \class{mbox} instance), its
+format-specific information is used. Otherwise, the format-specific information
+of the message that currently corresponds to \var{key} is left unchanged.
\end{methoddesc}
\begin{methoddesc}{iterkeys}{}
@@ -146,8 +147,9 @@
\begin{methoddesc}{get_file}{key}
Return a file-like representation of the message corresponding to \var{key},
-or raise a \exception{KeyError} exception if no such message exists. This file
-should be closed once it is no longer needed.
+or raise a \exception{KeyError} exception if no such message exists. The
+file-like object behaves as if open in binary mode. This file should be closed
+once it is no longer needed.
\note{Unlike other representations of messages, file-like representations are
not necessarily independent of the \class{Mailbox} instance that created them
@@ -228,10 +230,10 @@
create=True}}}
A subclass of \class{Mailbox} for mailboxes in Maildir format. Parameter
\var{factory} is a callable object that accepts a file-like message
-representation and returns a custom representation. If \var{factory} is
-\code{None}, \class{MaildirMessage} is used as the default message
-representation. If \var{create} is \code{True}, the mailbox is created if it
-does not exist.
+representation (which behaves as if open in binary mode) and returns a custom
+representation. If \var{factory} is \code{None}, \class{MaildirMessage} is used
+as the default message representation. If \var{create} is \code{True}, the
+mailbox is created if it does not exist.
It is for historical reasons that \var{factory} defaults to
\class{rfc822.Message} and that \var{dirname} is named as such rather than
@@ -353,9 +355,10 @@
\begin{classdesc}{mbox}{path\optional{, factory=None\optional{, create=True}}}
A subclass of \class{Mailbox} for mailboxes in mbox format. Parameter
\var{factory} is a callable object that accepts a file-like message
-representation and returns a custom representation. If \var{factory} is
-\code{None}, \class{mboxMessage} is used as the default message representation.
-If \var{create} is \code{True}, the mailbox is created if it does not exist.
+representation (which behaves as if open in binary mode) and returns a custom
+representation. If \var{factory} is \code{None}, \class{mboxMessage} is used as
+the default message representation. If \var{create} is \code{True}, the mailbox
+is created if it does not exist.
\end{classdesc}
The mbox format is the classic format for storing mail on \UNIX{} systems. All
@@ -405,9 +408,10 @@
\begin{classdesc}{MH}{path\optional{, factory=None\optional{, create=True}}}
A subclass of \class{Mailbox} for mailboxes in MH format. Parameter
\var{factory} is a callable object that accepts a file-like message
-representation and returns a custom representation. If \var{factory} is
-\code{None}, \class{MHMessage} is used as the default message representation.
-If \var{create} is \code{True}, the mailbox is created if it does not exist.
+representation (which behaves as if open in binary mode) and returns a custom
+representation. If \var{factory} is \code{None}, \class{MHMessage} is used as
+the default message representation. If \var{create} is \code{True}, the mailbox
+is created if it does not exist.
\end{classdesc}
MH is a directory-based mailbox format invented for the MH Message Handling
@@ -511,10 +515,10 @@
\begin{classdesc}{Babyl}{path\optional{, factory=None\optional{, create=True}}}
A subclass of \class{Mailbox} for mailboxes in Babyl format. Parameter
\var{factory} is a callable object that accepts a file-like message
-representation and returns a custom representation. If \var{factory} is
-\code{None}, \class{BabylMessage} is used as the default message
-representation. If \var{create} is \code{True}, the mailbox is created if it
-does not exist.
+representation (which behaves as if open in binary mode) and returns a custom
+representation. If \var{factory} is \code{None}, \class{BabylMessage} is used
+as the default message representation. If \var{create} is \code{True}, the
+mailbox is created if it does not exist.
\end{classdesc}
Babyl is a single-file mailbox format invented for the Rmail mail user agent
@@ -574,9 +578,10 @@
\begin{classdesc}{MMDF}{path\optional{, factory=None\optional{, create=True}}}
A subclass of \class{Mailbox} for mailboxes in MMDF format. Parameter
\var{factory} is a callable object that accepts a file-like message
-representation and returns a custom representation. If \var{factory} is
-\code{None}, \class{MMDFMessage} is used as the default message representation.
-If \var{create} is \code{True}, the mailbox is created if it does not exist.
+representation (which behaves as if open in binary mode) and returns a custom
+representation. If \var{factory} is \code{None}, \class{MMDFMessage} is used as
+the default message representation. If \var{create} is \code{True}, the mailbox
+is created if it does not exist.
\end{classdesc}
MMDF is a single-file mailbox format invented for the Multichannel Memorandum
@@ -1010,7 +1015,8 @@
\begin{methoddesc}{set_visible}{visible}
Set the message's visible headers to be the same as the headers in
\var{message}. Parameter \var{visible} should be a \class{Message} instance, an
-\class{email.Message.Message} instance, a string, or a file-like object.
+\class{email.Message.Message} instance, a string, or a file-like object (which
+should be open in text mode).
\end{methoddesc}
\begin{methoddesc}{update_visible}{}
Index: mailbox.py
===================================================================
RCS file: /cvsroot/python/python/nondist/sandbox/mailbox/mailbox.py,v
retrieving revision 1.15
retrieving revision 1.16
diff -u -d -r1.15 -r1.16
--- mailbox.py 22 Aug 2005 20:19:28 -0000 1.15
+++ mailbox.py 23 Aug 2005 03:43:11 -0000 1.16
@@ -183,30 +183,30 @@
raise NotImplementedError('Method must be implemented by subclass')
def _dump_message(self, message, target, mangle_from_=False):
+ # Most files are opened in binary mode to allow predictable seeking.
+ # To get native line endings on disk, the user-friendly \n line endings
+ # used in strings and by email.Message are translated here.
"""Dump message contents to target file."""
if isinstance(message, email.Message.Message):
- generator = email.Generator.Generator(target, mangle_from_, 0)
- generator.flatten(message)
+ buffer = StringIO.StringIO()
+ gen = email.Generator.Generator(buffer, mangle_from_, 0)
+ gen.flatten(message)
+ buffer.seek(0)
+ target.write(buffer.read().replace('\n', os.linesep))
elif isinstance(message, str):
if mangle_from_:
- message = message.replace(os.linesep + 'From ',
- os.linesep + '>From ')
+ message = message.replace('\nFrom ', '\n>From ')
+ message = message.replace('\n', os.linesep)
target.write(message)
elif hasattr(message, 'read'):
- if mangle_from_:
- while True:
- line = message.readline()
- if line == '':
- break
- if line.startswith('From '):
- line = '>From ' + line[5:]
- target.write(line)
- else:
- while True:
- buffer = message.read(4096) # Buffer size is arbitrary.
- if buffer == '':
- break
- target.write(buffer)
+ while True:
+ line = message.readline()
+ if line == '':
+ break
+ if mangle_from_ and line.startswith('From '):
+ line = '>From ' + line[5:]
+ line = line.replace('\n', os.linesep)
+ target.write(line)
else:
raise TypeError('Invalid message type: %s' % type(message))
@@ -294,7 +294,7 @@
def get_message(self, key):
"""Return a Message representation or raise a KeyError."""
subpath = self._lookup(key)
- f = file(os.path.join(self._path, subpath), 'rb')
+ f = file(os.path.join(self._path, subpath), 'r')
try:
msg = MaildirMessage(f)
finally:
@@ -308,7 +308,7 @@
def get_string(self, key):
"""Return a string representation or raise a KeyError."""
- f = file(os.path.join(self._path, self._lookup(key)), 'rb')
+ f = file(os.path.join(self._path, self._lookup(key)), 'r')
try:
return f.read()
finally:
@@ -627,9 +627,10 @@
"""Return a Message representation or raise a KeyError."""
start, stop = self._lookup(key)
self._file.seek(start)
- from_line = self._file.readline()
- msg = self._message_factory(self._file.read(stop - self._file.tell()))
- msg.set_from(from_line[5:-len(os.linesep)])
+ from_line = self._file.readline().replace(os.linesep, '')
+ string = self._file.read(stop - self._file.tell())
+ msg = self._message_factory(string.replace(os.linesep, '\n'))
+ msg.set_from(from_line[5:])
return msg
def get_string(self, key, from_=False):
@@ -638,7 +639,8 @@
self._file.seek(start)
if not from_:
self._file.readline()
- return self._file.read(stop - self._file.tell())
+ string = self._file.read(stop - self._file.tell())
+ return string.replace(os.linesep, '\n')
def get_file(self, key, from_=False):
"""Return a file-like representation or raise a KeyError."""
@@ -652,10 +654,10 @@
"""Format a message and blindly write to self._file."""
from_line = None
if isinstance(message, str) and message.startswith('From '):
- newline = message.find(os.linesep)
+ newline = message.find('\n')
if newline != -1:
from_line = message[:newline]
- message = message[newline + len(os.linesep):]
+ message = message[newline + 1:]
else:
from_line = message
message = ''
@@ -836,9 +838,9 @@
"""Return a Message representation or raise a KeyError."""
try:
if self._locked:
- f = file(os.path.join(self._path, str(key)), 'rb+')
+ f = file(os.path.join(self._path, str(key)), 'r+')
else:
- f = file(os.path.join(self._path, str(key)), 'rb')
+ f = file(os.path.join(self._path, str(key)), 'r')
except IOError, e:
if e.errno == errno.ENOENT:
raise KeyError('No message with key: %s' % key)
@@ -863,9 +865,9 @@
"""Return a string representation or raise a KeyError."""
try:
if self._locked:
- f = file(os.path.join(self._path, str(key)), 'rb+')
+ f = file(os.path.join(self._path, str(key)), 'r+')
else:
- f = file(os.path.join(self._path, str(key)), 'rb')
+ f = file(os.path.join(self._path, str(key)), 'r')
except IOError, e:
if e.errno == errno.ENOENT:
raise KeyError('No message with key: %s' % key)
@@ -961,7 +963,7 @@
def get_sequences(self):
"""Return a name-to-key-list dictionary to define each sequence."""
results = {}
- f = file(os.path.join(self._path, '.mh_sequences'), 'rb')
+ f = file(os.path.join(self._path, '.mh_sequences'), 'r')
try:
all_keys = set(self.keys())
for line in f:
@@ -987,7 +989,7 @@
def set_sequences(self, sequences):
"""Set sequences using the given name-to-key-list dictionary."""
- f = file(os.path.join(self._path, '.mh_sequences'), 'rb+')
+ f = file(os.path.join(self._path, '.mh_sequences'), 'r+')
try:
os.close(os.open(f.name, os.O_WRONLY | os.O_TRUNC))
for name, keys in sequences.iteritems():
@@ -1008,9 +1010,9 @@
f.write(' %s' % key)
prev = key
if completing:
- f.write(str(prev) + os.linesep)
+ f.write(str(prev) + '\n')
else:
- f.write(os.linesep)
+ f.write('\n')
finally:
f.close()
@@ -1022,7 +1024,7 @@
for key in self.iterkeys():
if key - 1 != prev:
changes.append((key, prev + 1))
- f = file(os.path.join(self._path, str(key)), 'rb+')
+ f = file(os.path.join(self._path, str(key)), 'r+')
try:
if self._locked:
_lock_file(f)
@@ -1105,14 +1107,15 @@
line = self._file.readline()
if line == '*** EOOH ***' + os.linesep or line == '':
break
- original_headers.write(line)
+ original_headers.write(line.replace(os.linesep, '\n'))
visible_headers = StringIO.StringIO()
while True:
line = self._file.readline()
if line == os.linesep or line == '':
break
- visible_headers.write(line)
- body = self._file.read(stop - self._file.tell())
+ visible_headers.write(line.replace(os.linesep, '\n'))
+ body = self._file.read(stop - self._file.tell()).replace(os.linesep,
+ '\n')
msg = BabylMessage(original_headers.getvalue() + body)
msg.set_visible(visible_headers.getvalue())
if key in self._labels:
@@ -1129,13 +1132,14 @@
line = self._file.readline()
if line == '*** EOOH ***' + os.linesep or line == '':
break
- original_headers.write(line)
+ original_headers.write(line.replace(os.linesep, '\n'))
while True:
line = self._file.readline()
if line == os.linesep or line == '':
break
return original_headers.getvalue() + \
- self._file.read(stop - self._file.tell())
+ self._file.read(stop - self._file.tell()).replace(os.linesep,
+ '\n')
def get_file(self, key):
"""Return a file-like representation or raise a KeyError."""
@@ -1213,49 +1217,57 @@
else:
self._file.write('1,,' + os.linesep)
if isinstance(message, email.Message.Message):
- pseudofile = StringIO.StringIO()
- ps_generator = email.Generator.Generator(pseudofile, False, 0)
- ps_generator.flatten(message)
- pseudofile.seek(0)
+ orig_buffer = StringIO.StringIO()
+ orig_generator = email.Generator.Generator(orig_buffer, False, 0)
+ orig_generator.flatten(message)
+ orig_buffer.seek(0)
while True:
- line = pseudofile.readline()
- self._file.write(line)
- if line == os.linesep or line == '':
+ line = orig_buffer.readline()
+ self._file.write(line.replace('\n', os.linesep))
+ if line == '\n' or line == '':
break
self._file.write('*** EOOH ***' + os.linesep)
if isinstance(message, BabylMessage):
- generator = email.Generator.Generator(self._file, False, 0)
- generator.flatten(message.get_visible())
+ vis_buffer = StringIO.StringIO()
+ vis_generator = email.Generator.Generator(vis_buffer, False, 0)
+ vis_generator.flatten(message.get_visible())
+ while True:
+ line = vis_buffer.readline()
+ self._file.write(line.replace('\n', os.linesep))
+ if line == '\n' or line == '':
+ break
else:
- pseudofile.seek(0)
+ orig_buffer.seek(0)
while True:
- line = pseudofile.readline()
- self._file.write(line)
- if line == os.linesep or line == '':
+ line = orig_buffer.readline()
+ self._file.write(line.replace('\n', os.linesep))
+ if line == '\n' or line == '':
break
while True:
- buffer = pseudofile.read(4096) # Buffer size is arbitrary.
+ buffer = orig_buffer.read(4096) # Buffer size is arbitrary.
if buffer == '':
break
- self._file.write(buffer)
+ self._file.write(buffer.replace('\n', os.linesep))
elif isinstance(message, str):
- body_start = message.find(os.linesep + os.linesep) + \
- 2 * len(os.linesep)
- if body_start - 2 * len(os.linesep) != -1:
- self._file.write(message[:body_start])
+ body_start = message.find('\n\n') + 2
+ if body_start - 2 != -1:
+ self._file.write(message[:body_start].replace('\n',
+ os.linesep))
self._file.write('*** EOOH ***' + os.linesep)
- self._file.write(message[:body_start])
- self._file.write(message[body_start:])
+ self._file.write(message[:body_start].replace('\n',
+ os.linesep))
+ self._file.write(message[body_start:].replace('\n',
+ os.linesep))
else:
self._file.write('*** EOOH ***' + os.linesep + os.linesep)
- self._file.write(message)
+ self._file.write(message.replace('\n', os.linesep))
elif hasattr(message, 'readline'):
original_pos = message.tell()
first_pass = True
while True:
line = message.readline()
- self._file.write(line)
- if line == os.linesep or line == '':
+ self._file.write(line.replace('\n', os.linesep))
+ if line == '\n' or line == '':
self._file.write('*** EOOH ***' + os.linesep)
if first_pass:
first_pass = False
@@ -1266,7 +1278,7 @@
buffer = message.read(4096) # Buffer size is arbitrary.
if buffer == '':
break
- self._file.write(buffer)
+ self._file.write(buffer.replace('\n', os.linesep))
else:
raise TypeError('Invalid message type: %s' % type(message))
stop = self._file.tell()
Index: test_mailbox.py
===================================================================
RCS file: /cvsroot/python/python/nondist/sandbox/mailbox/test_mailbox.py,v
retrieving revision 1.10
retrieving revision 1.11
diff -u -d -r1.10 -r1.11
--- test_mailbox.py 22 Aug 2005 20:19:28 -0000 1.10
+++ test_mailbox.py 23 Aug 2005 03:43:11 -0000 1.11
@@ -49,7 +49,7 @@
class TestMailbox(TestBase):
_factory = None # Overridden by subclasses to reuse tests
- _template = 'From: foo' + os.linesep + os.linesep + '%s'
+ _template = 'From: foo\n\n%s'
def setUp(self):
self._path = test_support.TESTFN
@@ -72,8 +72,7 @@
self.assert_(len(self._box) == 4)
keys.append(self._box.add(_sample_message))
self.assert_(len(self._box) == 5)
- self.assert_(self._box.get_string(keys[0]) == self._template % 0,
- self._box.get_string(keys[0]))
+ self.assert_(self._box.get_string(keys[0]) == self._template % 0)
for i in (1, 2, 3, 4):
self._check_sample(self._box[keys[i]])
@@ -167,8 +166,10 @@
# Get file representations of messages
key0 = self._box.add(self._template % 0)
key1 = self._box.add(_sample_message)
- self.assert_(self._box.get_file(key0).read() == self._template % 0)
- self.assert_(self._box.get_file(key1).read() == _sample_message)
+ self.assert_(self._box.get_file(key0).read().replace(os.linesep, '\n')
+ == self._template % 0)
+ self.assert_(self._box.get_file(key1).read().replace(os.linesep, '\n')
+ == _sample_message)
def test_iterkeys(self):
# Get keys using iterkeys()
@@ -408,7 +409,8 @@
_sample_message, StringIO.StringIO(_sample_message)):
output = StringIO.StringIO()
self._box._dump_message(input, output)
- self.assert_(output.getvalue() == _sample_message)
+ self.assert_(output.getvalue() ==
+ _sample_message.replace('\n', os.linesep))
output = StringIO.StringIO()
self.assertRaises(TypeError,
lambda: self._box._dump_message(None, output))
@@ -677,16 +679,14 @@
def test_add_from_string(self):
# Add a string starting with 'From ' to the mailbox
- key = self._box.add('From foo at bar blah%sFrom: foo%s%s0' %
- (os.linesep, os.linesep, os.linesep))
+ key = self._box.add('From foo at bar blah\nFrom: foo\n\n0')
self.assert_(self._box[key].get_from() == 'foo at bar blah')
self.assert_(self._box[key].get_payload() == '0')
def test_add_mbox_or_mmdf_message(self):
# Add an mboxMessage or MMDFMessage
for class_ in (mailbox.mboxMessage, mailbox.MMDFMessage):
- msg = class_('From foo at bar blah%sFrom: foo%s%s0' %
- (os.linesep, os.linesep, os.linesep))
+ msg = class_('From foo at bar blah\nFrom: foo\n\n0')
key = self._box.add(msg)
def test_open_close_open(self):
More information about the Python-checkins
mailing list