diff --git a/Doc/lib/libmailbox.tex b/Doc/lib/libmailbox.tex index 75ea7e124d6..961b05019ec 100644 --- a/Doc/lib/libmailbox.tex +++ b/Doc/lib/libmailbox.tex @@ -25,22 +25,29 @@ Maildir, mbox, MH, Babyl, and MMDF. A mailbox, which may be inspected and modified. \end{classdesc*} +The \class{Mailbox} class defines an interface and +is not intended to be instantiated. Instead, format-specific +subclasses should inherit from \class{Mailbox} and your code +should instantiate a particular subclass. + The \class{Mailbox} interface is dictionary-like, with small keys -corresponding to messages. Keys are issued by the \class{Mailbox} instance -with which they will be used and are only meaningful to that \class{Mailbox} -instance. A key continues to identify a message even if the corresponding -message is modified, such as by replacing it with another message. Messages may -be added to a \class{Mailbox} instance using the set-like method -\method{add()} and removed using a \code{del} statement or the set-like methods -\method{remove()} and \method{discard()}. +corresponding to messages. Keys are issued by the \class{Mailbox} +instance with which they will be used and are only meaningful to that +\class{Mailbox} instance. A key continues to identify a message even +if the corresponding message is modified, such as by replacing it with +another message. + +Messages may be added to a \class{Mailbox} instance using the set-like +method \method{add()} and removed using a \code{del} statement or the +set-like methods \method{remove()} and \method{discard()}. \class{Mailbox} interface semantics differ from dictionary semantics in some -noteworthy ways. Each time a message is requested, a new representation -(typically a \class{Message} instance) is generated, based upon the current -state of the mailbox. Similarly, when a message is added to a \class{Mailbox} -instance, the provided message representation's contents are copied. In neither -case is a reference to the message representation kept by the \class{Mailbox} -instance. +noteworthy ways. Each time a message is requested, a new +representation (typically a \class{Message} instance) is generated +based upon the current state of the mailbox. Similarly, when a message +is added to a \class{Mailbox} instance, the provided message +representation's contents are copied. In neither case is a reference +to the message representation kept by the \class{Mailbox} instance. The default \class{Mailbox} iterator iterates over message representations, not keys as the default dictionary iterator does. Moreover, modification of a @@ -51,9 +58,14 @@ skipped, though using a key from an iterator may result in a \exception{KeyError} exception if the corresponding message is subsequently removed. -\class{Mailbox} itself is intended to define an interface and to be inherited -from by format-specific subclasses but is not intended to be instantiated. -Instead, you should instantiate a subclass. +Be very cautious when modifying mailboxes that might also be changed +by some other process. The safest mailbox format to use for such +tasks is Maildir; try to avoid using single-file formats such as mbox +for concurrent writing. If you're modifying a mailbox, no matter what +the format, you must lock it by calling the \method{lock()} and +\method{unlock()} methods before making any changes. Failing to lock +the mailbox runs the risk of losing data if some other process makes +changes to the mailbox while your Python code is running. \class{Mailbox} instances have the following methods: @@ -202,15 +214,16 @@ general it is incorrect for \var{arg} to be a \class{Mailbox} instance. \begin{methoddesc}{flush}{} Write any pending changes to the filesystem. For some \class{Mailbox} -subclasses, changes are always written immediately and this method does -nothing. +subclasses, changes are always written immediately and \method{flush()} does +nothing, but you should still make a habit of calling this method. \end{methoddesc} \begin{methoddesc}{lock}{} Acquire an exclusive advisory lock on the mailbox so that other processes know not to modify it. An \exception{ExternalClashError} is raised if the lock is not available. The particular locking mechanisms used depend upon the mailbox -format. +format. You should \emph{always} lock the mailbox before making any +modifications to its contents. \end{methoddesc} \begin{methoddesc}{unlock}{} @@ -1373,36 +1386,55 @@ of the format-specific information that can be converted: \begin{verbatim} import mailbox destination = mailbox.MH('~/Mail') +destination.lock() for message in mailbox.Babyl('~/RMAIL'): destination.add(MHMessage(message)) +destination.flush() +destination.unlock() \end{verbatim} -An example of sorting mail from numerous mailing lists, being careful to avoid -mail corruption due to concurrent modification by other programs, mail loss due -to interruption of the program, or premature termination due to malformed -messages in the mailbox: +This example sorts mail from several mailing lists into different +mailboxes, being careful to avoid mail corruption due to concurrent +modification by other programs, mail loss due to interruption of the +program, or premature termination due to malformed messages in the +mailbox: \begin{verbatim} import mailbox import email.Errors + list_names = ('python-list', 'python-dev', 'python-bugs') + boxes = dict((name, mailbox.mbox('~/email/%s' % name)) for name in list_names) -inbox = mailbox.Maildir('~/Maildir', None) +inbox = mailbox.Maildir('~/Maildir', factory=None) + for key in inbox.iterkeys(): try: message = inbox[key] except email.Errors.MessageParseError: continue # The message is malformed. Just leave it. + for name in list_names: list_id = message['list-id'] if list_id and name in list_id: + # Get mailbox to use box = boxes[name] + + # Write copy to disk before removing original. + # If there's a crash, you might duplicate a message, but + # that's better than losing a message completely. box.lock() box.add(message) - box.flush() # Write copy to disk before removing original. + box.flush() box.unlock() + + # Remove original message + inbox.lock() inbox.discard(key) + inbox.flush() + inbox.unlock() break # Found destination, so stop looking. + for box in boxes.itervalues(): box.close() \end{verbatim}