diff options
Diffstat (limited to 'Doc/lib')
68 files changed, 1431 insertions, 1126 deletions
diff --git a/Doc/lib/compiler.tex b/Doc/lib/compiler.tex index e619a9a..f0926e7 100644 --- a/Doc/lib/compiler.tex +++ b/Doc/lib/compiler.tex @@ -40,9 +40,9 @@ modules contained in the package. \begin{funcdesc}{parse}{buf} Returns an abstract syntax tree for the Python source code in \var{buf}. -The function raises SyntaxError if there is an error in the source -code. The return value is a \class{compiler.ast.Module} instance that -contains the tree. +The function raises \exception{SyntaxError} if there is an error in the +source code. The return value is a \class{compiler.ast.Module} instance +that contains the tree. \end{funcdesc} \begin{funcdesc}{parseFile}{path} diff --git a/Doc/lib/email-dir.py b/Doc/lib/email-dir.py index 2d89a2f..c04f57d 100644 --- a/Doc/lib/email-dir.py +++ b/Doc/lib/email-dir.py @@ -1,83 +1,69 @@ #!/usr/bin/env python -"""Send the contents of a directory as a MIME message. +"""Send the contents of a directory as a MIME message.""" -Usage: dirmail [options] from to [to ...]* - -Options: - -h / --help - Print this message and exit. - - -d directory - --directory=directory - Mail the contents of the specified directory, otherwise use the - current directory. Only the regular files in the directory are sent, - and we don't recurse to subdirectories. - -`from' is the email address of the sender of the message. - -`to' is the email address of the recipient of the message, and multiple -recipients may be given. - -The email is sent by forwarding to your local SMTP server, which then does the -normal delivery process. Your local machine must be running an SMTP server. -""" - -import sys import os -import getopt +import sys import smtplib # For guessing MIME type based on file name extension import mimetypes -from email import Encoders -from email.Message import Message -from email.MIMEAudio import MIMEAudio -from email.MIMEBase import MIMEBase -from email.MIMEMultipart import MIMEMultipart -from email.MIMEImage import MIMEImage -from email.MIMEText import MIMEText - -COMMASPACE = ', ' +from optparse import OptionParser +from email import encoders +from email.message import Message +from email.mime.audio import MIMEAudio +from email.mime.base import MIMEBase +from email.mime.image import MIMEImage +from email.mime.multipart import MIMEMultipart +from email.mime.text import MIMEText -def usage(code, msg=''): - print >> sys.stderr, __doc__ - if msg: - print >> sys.stderr, msg - sys.exit(code) +COMMASPACE = ', ' def main(): - try: - opts, args = getopt.getopt(sys.argv[1:], 'hd:', ['help', 'directory=']) - except getopt.error, msg: - usage(1, msg) - - dir = os.curdir - for opt, arg in opts: - if opt in ('-h', '--help'): - usage(0) - elif opt in ('-d', '--directory'): - dir = arg - - if len(args) < 2: - usage(1) - - sender = args[0] - recips = args[1:] - + parser = OptionParser(usage="""\ +Send the contents of a directory as a MIME message. + +Usage: %prog [options] + +Unless the -o option is given, the email is sent by forwarding to your local +SMTP server, which then does the normal delivery process. Your local machine +must be running an SMTP server. +""") + parser.add_option('-d', '--directory', + type='string', action='store', + help="""Mail the contents of the specified directory, + otherwise use the current directory. Only the regular + files in the directory are sent, and we don't recurse to + subdirectories.""") + parser.add_option('-o', '--output', + type='string', action='store', metavar='FILE', + help="""Print the composed message to FILE instead of + sending the message to the SMTP server.""") + parser.add_option('-s', '--sender', + type='string', action='store', metavar='SENDER', + help='The value of the From: header (required)') + parser.add_option('-r', '--recipient', + type='string', action='append', metavar='RECIPIENT', + default=[], dest='recipients', + help='A To: header value (at least one required)') + opts, args = parser.parse_args() + if not opts.sender or not opts.recipients: + parser.print_help() + sys.exit(1) + directory = opts.directory + if not directory: + directory = '.' # Create the enclosing (outer) message outer = MIMEMultipart() - outer['Subject'] = 'Contents of directory %s' % os.path.abspath(dir) - outer['To'] = COMMASPACE.join(recips) - outer['From'] = sender + outer['Subject'] = 'Contents of directory %s' % os.path.abspath(directory) + outer['To'] = COMMASPACE.join(opts.recipients) + outer['From'] = opts.sender outer.preamble = 'You will not see this in a MIME-aware mail reader.\n' - # To guarantee the message ends with a newline - outer.epilogue = '' - for filename in os.listdir(dir): - path = os.path.join(dir, filename) + for filename in os.listdir(directory): + path = os.path.join(directory, filename) if not os.path.isfile(path): continue # Guess the content type based on the file's extension. Encoding @@ -108,16 +94,21 @@ def main(): msg.set_payload(fp.read()) fp.close() # Encode the payload using Base64 - Encoders.encode_base64(msg) + encoders.encode_base64(msg) # Set the filename parameter msg.add_header('Content-Disposition', 'attachment', filename=filename) outer.attach(msg) - - # Now send the message - s = smtplib.SMTP() - s.connect() - s.sendmail(sender, recips, outer.as_string()) - s.close() + # Now send or store the message + composed = outer.as_string() + if opts.output: + fp = open(opts.output, 'w') + fp.write(composed) + fp.close() + else: + s = smtplib.SMTP() + s.connect() + s.sendmail(opts.sender, opts.recipients, composed) + s.close() if __name__ == '__main__': diff --git a/Doc/lib/email-mime.py b/Doc/lib/email-mime.py index 048a59f..5097253 100644 --- a/Doc/lib/email-mime.py +++ b/Doc/lib/email-mime.py @@ -2,8 +2,8 @@ import smtplib # Here are the email package modules we'll need -from email.MIMEImage import MIMEImage -from email.MIMEMultipart import MIMEMultipart +from email.mime.image import MIMEImage +from email.mime.multipart import MIMEMultipart COMMASPACE = ', ' @@ -15,8 +15,6 @@ msg['Subject'] = 'Our family reunion' msg['From'] = me msg['To'] = COMMASPACE.join(family) msg.preamble = 'Our family reunion' -# Guarantees the message ends in a newline -msg.epilogue = '' # Assume we know that the image files are all in PNG format for file in pngfiles: diff --git a/Doc/lib/email-simple.py b/Doc/lib/email-simple.py index a445f1b..44152a4 100644 --- a/Doc/lib/email-simple.py +++ b/Doc/lib/email-simple.py @@ -2,7 +2,7 @@ import smtplib # Import the email modules we'll need -from email.MIMEText import MIMEText +from email.mime.text import MIMEText # Open a plain text file for reading. For this example, assume that # the text file contains only ASCII characters. diff --git a/Doc/lib/email-unpack.py b/Doc/lib/email-unpack.py index b166fdb..fc05d99 100644 --- a/Doc/lib/email-unpack.py +++ b/Doc/lib/email-unpack.py @@ -1,59 +1,44 @@ #!/usr/bin/env python -"""Unpack a MIME message into a directory of files. +"""Unpack a MIME message into a directory of files.""" -Usage: unpackmail [options] msgfile - -Options: - -h / --help - Print this message and exit. - - -d directory - --directory=directory - Unpack the MIME message into the named directory, which will be - created if it doesn't already exist. - -msgfile is the path to the file containing the MIME message. -""" - -import sys import os -import getopt +import sys +import email import errno import mimetypes -import email - -def usage(code, msg=''): - print >> sys.stderr, __doc__ - if msg: - print >> sys.stderr, msg - sys.exit(code) +from optparse import OptionParser def main(): - try: - opts, args = getopt.getopt(sys.argv[1:], 'hd:', ['help', 'directory=']) - except getopt.error, msg: - usage(1, msg) - - dir = os.curdir - for opt, arg in opts: - if opt in ('-h', '--help'): - usage(0) - elif opt in ('-d', '--directory'): - dir = arg + parser = OptionParser(usage="""\ +Unpack a MIME message into a directory of files. + +Usage: %prog [options] msgfile +""") + parser.add_option('-d', '--directory', + type='string', action='store', + help="""Unpack the MIME message into the named + directory, which will be created if it doesn't already + exist.""") + opts, args = parser.parse_args() + if not opts.directory: + parser.print_help() + sys.exit(1) try: msgfile = args[0] except IndexError: - usage(1) + parser.print_help() + sys.exit(1) try: - os.mkdir(dir) + os.mkdir(opts.directory) except OSError, e: # Ignore directory exists error - if e.errno <> errno.EEXIST: raise + if e.errno <> errno.EEXIST: + raise fp = open(msgfile) msg = email.message_from_file(fp) @@ -74,8 +59,8 @@ def main(): ext = '.bin' filename = 'part-%03d%s' % (counter, ext) counter += 1 - fp = open(os.path.join(dir, filename), 'wb') - fp.write(part.get_payload(decode=1)) + fp = open(os.path.join(opts.directory, filename), 'wb') + fp.write(part.get_payload(decode=True)) fp.close() diff --git a/Doc/lib/email.tex b/Doc/lib/email.tex index 3a90e22..6853325 100644 --- a/Doc/lib/email.tex +++ b/Doc/lib/email.tex @@ -1,4 +1,4 @@ -% Copyright (C) 2001-2004 Python Software Foundation +% Copyright (C) 2001-2006 Python Software Foundation % Author: barry@python.org (Barry Warsaw) \section{\module{email} --- @@ -18,10 +18,10 @@ subsumes most of the functionality in several older standard modules such as \refmodule{rfc822}, \refmodule{mimetools}, \refmodule{multifile}, and other non-standard packages such as \module{mimecntl}. It is specifically \emph{not} designed to do any -sending of email messages to SMTP (\rfc{2821}) servers; that is the -function of the \refmodule{smtplib} module. The \module{email} -package attempts to be as RFC-compliant as possible, supporting in -addition to \rfc{2822}, such MIME-related RFCs as +sending of email messages to SMTP (\rfc{2821}), NNTP, or other servers; those +are functions of modules such as \refmodule{smtplib} and \refmodule{nntplib}. +The \module{email} package attempts to be as RFC-compliant as possible, +supporting in addition to \rfc{2822}, such MIME-related RFCs as \rfc{2045}, \rfc{2046}, \rfc{2047}, and \rfc{2231}. The primary distinguishing feature of the \module{email} package is @@ -41,7 +41,7 @@ The following sections describe the functionality of the should be common in applications: an email message is read as flat text from a file or other source, the text is parsed to produce the object structure of the email message, this structure is manipulated, -and finally rendered back into flat text. +and finally, the object tree is rendered back into flat text. It is perfectly feasible to create the object structure out of whole cloth --- i.e. completely from scratch. From there, a similar @@ -56,6 +56,7 @@ package, a section on differences and porting is provided. \begin{seealso} \seemodule{smtplib}{SMTP protocol client} + \seemodule{nntplib}{NNTP protocol client} \end{seealso} \subsection{Representing an email message} @@ -88,22 +89,51 @@ package, a section on differences and porting is provided. \subsection{Iterators} \input{emailiter} -\subsection{Package History} +\subsection{Package History\label{email-pkg-history}} -Version 1 of the \module{email} package was bundled with Python -releases up to Python 2.2.1. Version 2 was developed for the Python -2.3 release, and backported to Python 2.2.2. It was also available as -a separate distutils-based package, and is compatible back to Python 2.1. +This table describes the release history of the email package, corresponding +to the version of Python that the package was released with. For purposes of +this document, when you see a note about change or added versions, these refer +to the Python version the change was made it, \emph{not} the email package +version. This table also describes the Python compatibility of each version +of the package. -\module{email} version 3.0 was released with Python 2.4 and as a separate -distutils-based package. It is compatible back to Python 2.3. +\begin{tableiii}{l|l|l}{constant}{email version}{distributed with}{compatible with} +\lineiii{1.x}{Python 2.2.0 to Python 2.2.1}{\emph{no longer supported}} +\lineiii{2.5}{Python 2.2.2+ and Python 2.3}{Python 2.1 to 2.5} +\lineiii{3.0}{Python 2.4}{Python 2.3 to 2.5} +\lineiii{4.0}{Python 2.5}{Python 2.3 to 2.5} +\end{tableiii} -Here are the differences between \module{email} version 3 and version 2: +Here are the major differences between \module{email} verson 4 and version 3: + +\begin{itemize} +\item All modules have been renamed according to \pep{8} standards. For + example, the version 3 module \module{email.Message} was renamed to + \module{email.message} in version 4. + +\item A new subpackage \module{email.mime} was added and all the version 3 + \module{email.MIME*} modules were renamed and situated into the + \module{email.mime} subpackage. For example, the version 3 module + \module{email.MIMEText} was renamed to \module{email.mime.text}. + + \emph{Note that the version 3 names will continue to work until Python + 2.6}. + +\item The \module{email.mime.application} module was added, which contains the + \class{MIMEApplication} class. + +\item Methods that were deprecated in version 3 have been removed. These + include \method{Generator.__call__()}, \method{Message.get_type()}, + \method{Message.get_main_type()}, \method{Message.get_subtype()}. +\end{itemize} + +Here are the major differences between \module{email} version 3 and version 2: \begin{itemize} \item The \class{FeedParser} class was introduced, and the \class{Parser} class was implemented in terms of the \class{FeedParser}. All parsing - there for is non-strict, and parsing will make a best effort never to + therefore is non-strict, and parsing will make a best effort never to raise an exception. Problems found while parsing messages are stored in the message's \var{defect} attribute. @@ -117,7 +147,7 @@ Here are the differences between \module{email} version 3 and version 2: \method{Generator.__call__()}, \method{Message.get_type()}, \method{Message.get_main_type()}, \method{Message.get_subtype()}, and the \var{strict} argument to the \class{Parser} class. These are - expected to be removed in email 3.1. + expected to be removed in future versions. \item Support for Pythons earlier than 2.3 has been removed. \end{itemize} @@ -278,12 +308,12 @@ The \class{Message} class has the following differences: \item The method \method{getpayloadastext()} was removed. Similar functionality is supported by the \class{DecodedGenerator} class in the - \refmodule{email.Generator} module. + \refmodule{email.generator} module. \item The method \method{getbodyastext()} was removed. You can get similar functionality by creating an iterator with \function{typed_subpart_iterator()} in the - \refmodule{email.Iterators} module. + \refmodule{email.iterators} module. \end{itemize} The \class{Parser} class has no differences in its public interface. @@ -295,7 +325,7 @@ notification\footnote{Delivery Status Notifications (DSN) are defined in \rfc{1894}.}. The \class{Generator} class has no differences in its public -interface. There is a new class in the \refmodule{email.Generator} +interface. There is a new class in the \refmodule{email.generator} module though, called \class{DecodedGenerator} which provides most of the functionality previously available in the \method{Message.getpayloadastext()} method. @@ -329,11 +359,11 @@ The following modules and classes have been changed: \module{mimelib} provided some utility functions in its \module{address} and \module{date} modules. All of these functions -have been moved to the \refmodule{email.Utils} module. +have been moved to the \refmodule{email.utils} module. The \code{MsgReader} class/module has been removed. Its functionality is most closely supported in the \function{body_line_iterator()} -function in the \refmodule{email.Iterators} module. +function in the \refmodule{email.iterators} module. \subsection{Examples} diff --git a/Doc/lib/emailcharsets.tex b/Doc/lib/emailcharsets.tex index 18f2a01..e0be68a 100644 --- a/Doc/lib/emailcharsets.tex +++ b/Doc/lib/emailcharsets.tex @@ -1,4 +1,4 @@ -\declaremodule{standard}{email.Charset} +\declaremodule{standard}{email.charset} \modulesynopsis{Character Sets} This module provides a class \class{Charset} for representing @@ -7,6 +7,8 @@ well as a character set registry and several convenience methods for manipulating this registry. Instances of \class{Charset} are used in several other modules within the \module{email} package. +Import this class from the \module{email.charset} module. + \versionadded{2.2.2} \begin{classdesc}{Charset}{\optional{input_charset}} @@ -153,7 +155,7 @@ input charset to the output charset automatically. This is not useful for multibyte character sets, which have line length issues (multibyte characters must be split on a character, not a byte boundary); use the higher-level \class{Header} class to deal with these issues (see -\refmodule{email.Header}). \var{convert} defaults to \code{False}. +\refmodule{email.header}). \var{convert} defaults to \code{False}. The type of encoding (base64 or quoted-printable) will be based on the \var{header_encoding} attribute. @@ -188,7 +190,7 @@ This method allows you to compare two \class{Charset} instances for equality. This method allows you to compare two \class{Charset} instances for inequality. \end{methoddesc} -The \module{email.Charset} module also provides the following +The \module{email.charset} module also provides the following functions for adding new entries to the global character set, alias, and codec registries: diff --git a/Doc/lib/emailencoders.tex b/Doc/lib/emailencoders.tex index a49e04d..3d05c2a 100644 --- a/Doc/lib/emailencoders.tex +++ b/Doc/lib/emailencoders.tex @@ -1,4 +1,4 @@ -\declaremodule{standard}{email.Encoders} +\declaremodule{standard}{email.encoders} \modulesynopsis{Encoders for email message payloads.} When creating \class{Message} objects from scratch, you often need to @@ -7,7 +7,7 @@ This is especially true for \mimetype{image/*} and \mimetype{text/*} type messages containing binary data. The \module{email} package provides some convenient encodings in its -\module{Encoders} module. These encoders are actually used by the +\module{encoders} module. These encoders are actually used by the \class{MIMEAudio} and \class{MIMEImage} class constructors to provide default encodings. All encoder functions take exactly one argument, the message object to encode. They usually extract the payload, encode it, and reset the diff --git a/Doc/lib/emailexc.tex b/Doc/lib/emailexc.tex index 6ac0889..3cef1d5 100644 --- a/Doc/lib/emailexc.tex +++ b/Doc/lib/emailexc.tex @@ -1,8 +1,8 @@ -\declaremodule{standard}{email.Errors} +\declaremodule{standard}{email.errors} \modulesynopsis{The exception classes used by the email package.} The following exception classes are defined in the -\module{email.Errors} module: +\module{email.errors} module: \begin{excclassdesc}{MessageError}{} This is the base class for all exceptions that the \module{email} @@ -59,7 +59,7 @@ problem was found, so for example, if a message nested inside a \mimetype{multipart/alternative} had a malformed header, that nested message object would have a defect, but the containing messages would not. -All defect classes are subclassed from \class{email.Errors.MessageDefect}, but +All defect classes are subclassed from \class{email.errors.MessageDefect}, but this class is \emph{not} an exception! \versionadded[All the defect classes were added]{2.4} diff --git a/Doc/lib/emailgenerator.tex b/Doc/lib/emailgenerator.tex index 330abc0..3415442 100644 --- a/Doc/lib/emailgenerator.tex +++ b/Doc/lib/emailgenerator.tex @@ -1,4 +1,4 @@ -\declaremodule{standard}{email.Generator} +\declaremodule{standard}{email.generator} \modulesynopsis{Generate flat text email messages from a message structure.} One of the most common tasks is to generate the flat text of the email @@ -8,7 +8,7 @@ module or the \refmodule{nntplib} module, or print the message on the console. Taking a message object structure and producing a flat text document is the job of the \class{Generator} class. -Again, as with the \refmodule{email.Parser} module, you aren't limited +Again, as with the \refmodule{email.parser} module, you aren't limited to the functionality of the bundled generator; you could write one from scratch yourself. However the bundled generator knows how to generate most email in a standards-compliant way, should handle MIME @@ -17,7 +17,8 @@ transformation from flat text, to a message structure via the \class{Parser} class, and back to flat text, is idempotent (the input is identical to the output). -Here are the public methods of the \class{Generator} class: +Here are the public methods of the \class{Generator} class, imported from the +\module{email.generator} module: \begin{classdesc}{Generator}{outfp\optional{, mangle_from_\optional{, maxheaderlen}}} @@ -40,7 +41,7 @@ mailbox format files. Optional \var{maxheaderlen} specifies the longest length for a non-continued header. When a header line is longer than \var{maxheaderlen} (in characters, with tabs expanded to 8 spaces), -the header will be split as defined in the \module{email.Header} +the header will be split as defined in the \module{email.header.Header} class. Set to zero to disable header wrapping. The default is 78, as recommended (but not required) by \rfc{2822}. \end{classdesc} @@ -81,9 +82,9 @@ be used in extended print statements. As a convenience, see the methods \method{Message.as_string()} and \code{str(aMessage)}, a.k.a. \method{Message.__str__()}, which simplify the generation of a formatted string representation of a -message object. For more detail, see \refmodule{email.Message}. +message object. For more detail, see \refmodule{email.message}. -The \module{email.Generator} module also provides a derived class, +The \module{email.generator} module also provides a derived class, called \class{DecodedGenerator} which is like the \class{Generator} base class, except that non-\mimetype{text} parts are substituted with a format string representing the part. @@ -128,13 +129,5 @@ The default value for \var{fmt} is \code{None}, meaning \versionadded{2.2.2} \end{classdesc} -\subsubsection{Deprecated methods} - -The following methods are deprecated in \module{email} version 2. -They are documented here for completeness. - -\begin{methoddesc}[Generator]{__call__}{msg\optional{, unixfrom}} -This method is identical to the \method{flatten()} method. - -\deprecated{2.2.2}{Use the \method{flatten()} method instead.} -\end{methoddesc} +\versionchanged[The previously deprecated method \method{__call__()} was +removed]{2.5} diff --git a/Doc/lib/emailheaders.tex b/Doc/lib/emailheaders.tex index 2795644b..524d08c 100644 --- a/Doc/lib/emailheaders.tex +++ b/Doc/lib/emailheaders.tex @@ -1,4 +1,4 @@ -\declaremodule{standard}{email.Header} +\declaremodule{standard}{email.header} \modulesynopsis{Representing non-ASCII headers} \rfc{2822} is the base standard that describes the format of email @@ -15,17 +15,18 @@ slew of RFCs have been written describing how to encode email containing non-\ASCII{} characters into \rfc{2822}-compliant format. These RFCs include \rfc{2045}, \rfc{2046}, \rfc{2047}, and \rfc{2231}. The \module{email} package supports these standards in its -\module{email.Header} and \module{email.Charset} modules. +\module{email.header} and \module{email.charset} modules. If you want to include non-\ASCII{} characters in your email headers, say in the \mailheader{Subject} or \mailheader{To} fields, you should use the \class{Header} class and assign the field in the \class{Message} object to an instance of \class{Header} instead of -using a string for the header value. For example: +using a string for the header value. Import the \class{Header} class from the +\module{email.header} module. For example: \begin{verbatim} ->>> from email.Message import Message ->>> from email.Header import Header +>>> from email.message import Message +>>> from email.header import Header >>> msg = Message() >>> h = Header('p\xf6stal', 'iso-8859-1') >>> msg['Subject'] = h @@ -87,7 +88,7 @@ Optional \var{errors} is passed straight through to the Append the string \var{s} to the MIME header. Optional \var{charset}, if given, should be a \class{Charset} instance -(see \refmodule{email.Charset}) or the name of a character set, which +(see \refmodule{email.charset}) or the name of a character set, which will be converted to a \class{Charset} instance. A value of \code{None} (the default) means that the \var{charset} given in the constructor is used. @@ -139,7 +140,7 @@ This method allows you to compare two \class{Header} instances for equality. This method allows you to compare two \class{Header} instances for inequality. \end{methoddesc} -The \module{email.Header} module also provides the following +The \module{email.header} module also provides the following convenient functions. \begin{funcdesc}{decode_header}{header} @@ -155,7 +156,7 @@ encoded string. Here's an example: \begin{verbatim} ->>> from email.Header import decode_header +>>> from email.header import decode_header >>> decode_header('=?iso-8859-1?q?p=F6stal?=') [('p\xf6stal', 'iso-8859-1')] \end{verbatim} diff --git a/Doc/lib/emailiter.tex b/Doc/lib/emailiter.tex index d1a8f98..ef8ef6f 100644 --- a/Doc/lib/emailiter.tex +++ b/Doc/lib/emailiter.tex @@ -1,8 +1,8 @@ -\declaremodule{standard}{email.Iterators} +\declaremodule{standard}{email.iterators} \modulesynopsis{Iterate over a message object tree.} Iterating over a message object tree is fairly easy with the -\method{Message.walk()} method. The \module{email.Iterators} module +\method{Message.walk()} method. The \module{email.iterators} module provides some useful higher level iterations over message object trees. diff --git a/Doc/lib/emailmessage.tex b/Doc/lib/emailmessage.tex index 9b41852..7bd7dd8 100644 --- a/Doc/lib/emailmessage.tex +++ b/Doc/lib/emailmessage.tex @@ -1,10 +1,11 @@ -\declaremodule{standard}{email.Message} +\declaremodule{standard}{email.message} \modulesynopsis{The base class representing email messages.} The central class in the \module{email} package is the -\class{Message} class; it is the base class for the \module{email} -object model. \class{Message} provides the core functionality for -setting and querying header fields, and for accessing message bodies. +\class{Message} class, imported from the \module{email.message} module. It is +the base class for the \module{email} object model. \class{Message} provides +the core functionality for setting and querying header fields, and for +accessing message bodies. Conceptually, a \class{Message} object consists of \emph{headers} and \emph{payloads}. Headers are \rfc{2822} style field names and @@ -45,7 +46,7 @@ begin with \code{From }. For more flexibility, instantiate a \begin{verbatim} from cStringIO import StringIO -from email.Generator import Generator +from email.generator import Generator fp = StringIO() g = Generator(fp, mangle_from_=False, maxheaderlen=60) g.flatten(msg) @@ -119,7 +120,7 @@ client's responsibility to ensure the payload invariants. Optional \begin{methoddesc}[Message]{set_charset}{charset} Set the character set of the payload to \var{charset}, which can -either be a \class{Charset} instance (see \refmodule{email.Charset}), a +either be a \class{Charset} instance (see \refmodule{email.charset}), a string naming a character set, or \code{None}. If it is a string, it will be converted to a \class{Charset} instance. If \var{charset} is \code{None}, the @@ -128,8 +129,8 @@ or \code{None}. If it is a string, it will be converted to a \exception{TypeError}. The message will be assumed to be of type \mimetype{text/*} encoded with -\code{charset.input_charset}. It will be converted to -\code{charset.output_charset} +\var{charset.input_charset}. It will be converted to +\var{charset.output_charset} and encoded properly, if needed, when generating the plain text representation of the message. MIME headers (\mailheader{MIME-Version}, \mailheader{Content-Type}, @@ -513,6 +514,9 @@ message/rfc822 \end{verbatim} \end{methoddesc} +\versionchanged[The previously deprecated methods \method{get_type()}, +\method{get_main_type()}, and \method{get_subtype()} were removed]{2.5} + \class{Message} objects can also optionally contain two instance attributes, which can be used when generating the plain text of a MIME message. @@ -532,7 +536,7 @@ to the message's \var{preamble} attribute. When the \class{Generator} is writing out the plain text representation of a MIME message, and it finds the message has a \var{preamble} attribute, it will write this text in the area between the headers and the first boundary. See -\refmodule{email.Parser} and \refmodule{email.Generator} for details. +\refmodule{email.parser} and \refmodule{email.generator} for details. Note that if the message object has no preamble, the \var{preamble} attribute will be \code{None}. @@ -543,58 +547,15 @@ The \var{epilogue} attribute acts the same way as the \var{preamble} attribute, except that it contains text that appears between the last boundary and the end of the message. -One note: when generating the flat text for a \mimetype{multipart} -message that has no \var{epilogue} (using the standard -\class{Generator} class), no newline is added after the closing -boundary line. If the message object has an \var{epilogue} and its -value does not start with a newline, a newline is printed after the -closing boundary. This seems a little clumsy, but it makes the most -practical sense. The upshot is that if you want to ensure that a -newline get printed after your closing \mimetype{multipart} boundary, -set the \var{epilogue} to the empty string. +\versionchanged[You do not need to set the epilogue to the empty string in +order for the \class{Generator} to print a newline at the end of the +file]{2.5} \end{datadesc} \begin{datadesc}{defects} The \var{defects} attribute contains a list of all the problems found when -parsing this message. See \refmodule{email.Errors} for a detailed description +parsing this message. See \refmodule{email.errors} for a detailed description of the possible parsing defects. \versionadded{2.4} \end{datadesc} - -\subsubsection{Deprecated methods} - -\versionchanged[The \method{add_payload()} method was removed; use the -\method{attach()} method instead]{2.4} - -The following methods are deprecated. They are documented here for -completeness. - -\begin{methoddesc}[Message]{get_type}{\optional{failobj}} -Return the message's content type, as a string of the form -\mimetype{maintype/subtype} as taken from the -\mailheader{Content-Type} header. -The returned string is coerced to lowercase. - -If there is no \mailheader{Content-Type} header in the message, -\var{failobj} is returned (defaults to \code{None}). - -\deprecated{2.2.2}{Use the \method{get_content_type()} method instead.} -\end{methoddesc} - -\begin{methoddesc}[Message]{get_main_type}{\optional{failobj}} -Return the message's \emph{main} content type. This essentially returns the -\var{maintype} part of the string returned by \method{get_type()}, with the -same semantics for \var{failobj}. - -\deprecated{2.2.2}{Use the \method{get_content_maintype()} method instead.} -\end{methoddesc} - -\begin{methoddesc}[Message]{get_subtype}{\optional{failobj}} -Return the message's sub-content type. This essentially returns the -\var{subtype} part of the string returned by \method{get_type()}, with the -same semantics for \var{failobj}. - -\deprecated{2.2.2}{Use the \method{get_content_subtype()} method instead.} -\end{methoddesc} - diff --git a/Doc/lib/emailmimebase.tex b/Doc/lib/emailmimebase.tex index 070c9a2..4735be3 100644 --- a/Doc/lib/emailmimebase.tex +++ b/Doc/lib/emailmimebase.tex @@ -1,3 +1,11 @@ +\declaremodule{standard}{email.mime} +\declaremodule{standard}{email.mime.base} +\declaremodule{standard}{email.mime.nonmultipart} +\declaremodule{standard}{email.mime.multipart} +\declaremodule{standard}{email.mime.audio} +\declaremodule{standard}{email.mime.image} +\declaremodule{standard}{email.mime.message} +\declaremodule{standard}{email.mime.text} Ordinarily, you get a message object structure by passing a file or some text to a parser, which parses the text and returns the root message object. However you can also build a complete message @@ -6,26 +14,16 @@ hand. In fact, you can also take an existing structure and add new \class{Message} objects, move them around, etc. This makes a very convenient interface for slicing-and-dicing MIME messages. -You can create a new object structure by creating \class{Message} -instances, adding attachments and all the appropriate headers manually. -For MIME messages though, the \module{email} package provides some -convenient subclasses to make things easier. Each of these classes -should be imported from a module with the same name as the class, from -within the \module{email} package. E.g.: - -\begin{verbatim} -import email.MIMEImage.MIMEImage -\end{verbatim} - -or - -\begin{verbatim} -from email.MIMEText import MIMEText -\end{verbatim} +You can create a new object structure by creating \class{Message} instances, +adding attachments and all the appropriate headers manually. For MIME +messages though, the \module{email} package provides some convenient +subclasses to make things easier. Here are the classes: \begin{classdesc}{MIMEBase}{_maintype, _subtype, **_params} +Module: \module{email.mime.base} + This is the base class for all the MIME-specific subclasses of \class{Message}. Ordinarily you won't create instances specifically of \class{MIMEBase}, although you could. \class{MIMEBase} is provided @@ -45,6 +43,8 @@ The \class{MIMEBase} class always adds a \mailheader{Content-Type} header \end{classdesc} \begin{classdesc}{MIMENonMultipart}{} +Module: \module{email.mime.nonmultipart} + A subclass of \class{MIMEBase}, this is an intermediate base class for MIME messages that are not \mimetype{multipart}. The primary purpose of this class is to prevent the use of the \method{attach()} method, @@ -57,6 +57,7 @@ exception is raised. \begin{classdesc}{MIMEMultipart}{\optional{subtype\optional{, boundary\optional{, _subparts\optional{, _params}}}}} +Module: \module{email.mime.multipart} A subclass of \class{MIMEBase}, this is an intermediate base class for MIME messages that are \mimetype{multipart}. Optional \var{_subtype} @@ -80,8 +81,31 @@ argument, which is a keyword dictionary. \versionadded{2.2.2} \end{classdesc} +\begin{classdesc}{MIMEApplication}{_data\optional{, _subtype\optional{, + _encoder\optional{, **_params}}}} +Module: \module{email.mime.application} + +A subclass of \class{MIMENonMultipart}, the \class{MIMEApplication} class is +used to represent MIME message objects of major type \mimetype{application}. +\var{_data} is a string containing the raw byte data. Optional \var{_subtype} +specifies the MIME subtype and defaults to \mimetype{octet-stream}. + +Optional \var{_encoder} is a callable (i.e. function) which will +perform the actual encoding of the data for transport. This +callable takes one argument, which is the \class{MIMEApplication} instance. +It should use \method{get_payload()} and \method{set_payload()} to +change the payload to encoded form. It should also add any +\mailheader{Content-Transfer-Encoding} or other headers to the message +object as necessary. The default encoding is base64. See the +\refmodule{email.encoders} module for a list of the built-in encoders. + +\var{_params} are passed straight through to the base class constructor. +\versionadded{2.5} +\end{classdesc} + \begin{classdesc}{MIMEAudio}{_audiodata\optional{, _subtype\optional{, _encoder\optional{, **_params}}}} +Module: \module{email.mime.audio} A subclass of \class{MIMENonMultipart}, the \class{MIMEAudio} class is used to create MIME message objects of major type \mimetype{audio}. @@ -100,13 +124,14 @@ It should use \method{get_payload()} and \method{set_payload()} to change the payload to encoded form. It should also add any \mailheader{Content-Transfer-Encoding} or other headers to the message object as necessary. The default encoding is base64. See the -\refmodule{email.Encoders} module for a list of the built-in encoders. +\refmodule{email.encoders} module for a list of the built-in encoders. \var{_params} are passed straight through to the base class constructor. \end{classdesc} \begin{classdesc}{MIMEImage}{_imagedata\optional{, _subtype\optional{, _encoder\optional{, **_params}}}} +Module: \module{email.mime.image} A subclass of \class{MIMENonMultipart}, the \class{MIMEImage} class is used to create MIME message objects of major type \mimetype{image}. @@ -125,13 +150,15 @@ It should use \method{get_payload()} and \method{set_payload()} to change the payload to encoded form. It should also add any \mailheader{Content-Transfer-Encoding} or other headers to the message object as necessary. The default encoding is base64. See the -\refmodule{email.Encoders} module for a list of the built-in encoders. +\refmodule{email.encoders} module for a list of the built-in encoders. \var{_params} are passed straight through to the \class{MIMEBase} constructor. \end{classdesc} \begin{classdesc}{MIMEMessage}{_msg\optional{, _subtype}} +Module: \module{email.mime.message} + A subclass of \class{MIMENonMultipart}, the \class{MIMEMessage} class is used to create MIME objects of main type \mimetype{message}. \var{_msg} is used as the payload, and must be an instance of class @@ -143,6 +170,8 @@ to \mimetype{rfc822}. \end{classdesc} \begin{classdesc}{MIMEText}{_text\optional{, _subtype\optional{, _charset}}} +Module: \module{email.mime.text} + A subclass of \class{MIMENonMultipart}, the \class{MIMEText} class is used to create MIME objects of major type \mimetype{text}. \var{_text} is the string for the payload. \var{_subtype} is the diff --git a/Doc/lib/emailparser.tex b/Doc/lib/emailparser.tex index 5fac92f..609fa40 100644 --- a/Doc/lib/emailparser.tex +++ b/Doc/lib/emailparser.tex @@ -1,4 +1,4 @@ -\declaremodule{standard}{email.Parser} +\declaremodule{standard}{email.parser} \modulesynopsis{Parse flat text email messages to produce a message object structure.} @@ -41,9 +41,10 @@ message object trees any way it finds necessary. \versionadded{2.4} -The \class{FeedParser} provides an API that is conducive to incremental -parsing of email messages, such as would be necessary when reading the text of -an email message from a source that can block (e.g. a socket). The +The \class{FeedParser}, imported from the \module{email.feedparser} module, +provides an API that is conducive to incremental parsing of email messages, +such as would be necessary when reading the text of an email message from a +source that can block (e.g. a socket). The \class{FeedParser} can of course be used to parse an email message fully contained in a string or a file, but the classic \class{Parser} API may be more convenient for such use cases. The semantics and results of the two @@ -56,14 +57,14 @@ accurate when parsing standards-compliant messages, and it does a very good job of parsing non-compliant messages, providing information about how a message was deemed broken. It will populate a message object's \var{defects} attribute with a list of any problems it found in a message. See the -\refmodule{email.Errors} module for the list of defects that it can find. +\refmodule{email.errors} module for the list of defects that it can find. Here is the API for the \class{FeedParser}: \begin{classdesc}{FeedParser}{\optional{_factory}} Create a \class{FeedParser} instance. Optional \var{_factory} is a no-argument callable that will be called whenever a new message object is -needed. It defaults to the \class{email.Message.Message} class. +needed. It defaults to the \class{email.message.Message} class. \end{classdesc} \begin{methoddesc}[FeedParser]{feed}{data} @@ -82,21 +83,22 @@ more data to a closed \class{FeedParser}. \subsubsection{Parser class API} -The \class{Parser} provides an API that can be used to parse a message when -the complete contents of the message are available in a string or file. The -\module{email.Parser} module also provides a second class, called +The \class{Parser} class, imported from the \module{email.parser} module, +provides an API that can be used to parse a message when the complete contents +of the message are available in a string or file. The +\module{email.parser} module also provides a second class, called \class{HeaderParser} which can be used if you're only interested in the headers of the message. \class{HeaderParser} can be much faster in these situations, since it does not attempt to parse the message body, instead setting the payload to the raw body as a string. \class{HeaderParser} has the same API as the \class{Parser} class. -\begin{classdesc}{Parser}{\optional{_class\optional{, strict}}} +\begin{classdesc}{Parser}{\optional{_class}} The constructor for the \class{Parser} class takes an optional argument \var{_class}. This must be a callable factory (such as a function or a class), and it is used whenever a sub-message object needs to be created. It defaults to \class{Message} (see -\refmodule{email.Message}). The factory will be called without +\refmodule{email.message}). The factory will be called without arguments. The optional \var{strict} flag is ignored. \deprecated{2.4}{Because the @@ -201,6 +203,6 @@ Here are some notes on the parsing semantics: \method{is_multipart()} method may return \code{False}. If such messages were parsed with the \class{FeedParser}, they will have an instance of the \class{MultipartInvariantViolationDefect} class in their - \var{defects} attribute list. See \refmodule{email.Errors} for + \var{defects} attribute list. See \refmodule{email.errors} for details. \end{itemize} diff --git a/Doc/lib/emailutil.tex b/Doc/lib/emailutil.tex index 491a2b9..fe96473 100644 --- a/Doc/lib/emailutil.tex +++ b/Doc/lib/emailutil.tex @@ -1,7 +1,7 @@ -\declaremodule{standard}{email.Utils} +\declaremodule{standard}{email.utils} \modulesynopsis{Miscellaneous email package utilities.} -There are several useful utilities provided in the \module{email.Utils} +There are several useful utilities provided in the \module{email.utils} module: \begin{funcdesc}{quote}{str} @@ -38,7 +38,7 @@ values as might be returned by \method{Message.get_all()}. Here's a simple example that gets all the recipients of a message: \begin{verbatim} -from email.Utils import getaddresses +from email.utils import getaddresses tos = msg.get_all('to', []) ccs = msg.get_all('cc', []) diff --git a/Doc/lib/lib.tex b/Doc/lib/lib.tex index fad8fe7..eac35de 100644 --- a/Doc/lib/lib.tex +++ b/Doc/lib/lib.tex @@ -87,7 +87,6 @@ and how to embed it in other applications. \input{libstrings} % String Services \input{libstring} \input{libre} -\input{libreconvert} \input{libstruct} % XXX also/better in File Formats? \input{libdifflib} \input{libstringio} @@ -372,6 +371,7 @@ and how to embed it in other applications. \input{libbltin} % really __builtin__ \input{libmain} % really __main__ \input{libwarnings} +\input{libcontextlib} \input{libatexit} \input{libtraceback} \input{libfuture} % really __future__ @@ -395,6 +395,7 @@ and how to embed it in other applications. \input{libzipimport} \input{libpkgutil} \input{libmodulefinder} +\input{librunpy} % ============= @@ -454,8 +455,6 @@ and how to embed it in other applications. %\input{libcmpcache} %\input{libcmp} %\input{libni} -%\input{libregex} -%\input{libregsub} \chapter{Reporting Bugs} \input{reportingbugs} diff --git a/Doc/lib/libarray.tex b/Doc/lib/libarray.tex index 897310d..eaf5888 100644 --- a/Doc/lib/libarray.tex +++ b/Doc/lib/libarray.tex @@ -139,8 +139,8 @@ file using the \method{fromfile()} method). \end{methoddesc} \begin{methoddesc}[array]{fromunicode}{s} -Extends this array with data from the given unicode string. -The array must be a type 'u' array; otherwise a ValueError +Extends this array with data from the given unicode string. The array +must be a type \code{'u'} array; otherwise a \exception{ValueError} is raised. Use \samp{array.fromstring(ustr.decode(enc))} to append Unicode data to an array of some other type. \end{methoddesc} @@ -197,8 +197,8 @@ be written to a file by the \method{tofile()} method.) \begin{methoddesc}[array]{tounicode}{} Convert the array to a unicode string. The array must be -a type 'u' array; otherwise a ValueError is raised. Use -array.tostring().decode(enc) to obtain a unicode string +a type \code{'u'} array; otherwise a \exception{ValueError} is raised. +Use \samp{array.tostring().decode(enc)} to obtain a unicode string from an array of some other type. \end{methoddesc} diff --git a/Doc/lib/libast.tex b/Doc/lib/libast.tex index b3c3148..b2956ae 100644 --- a/Doc/lib/libast.tex +++ b/Doc/lib/libast.tex @@ -47,11 +47,11 @@ question mark), the value might be \code{None}. If the attributes can have zero-or-more values (marked with an asterisk), the values are represented as Python lists. -\subsection{Abstract Grammar} +\section{Abstract Grammar} The module defines a string constant \code{__version__} which is the decimal subversion revision number of the file shown below. The abstract grammar is currently defined as follows: -\verbatiminput{../../Parser/Python.asdl}
\ No newline at end of file +\verbatiminput{../../Parser/Python.asdl} diff --git a/Doc/lib/libaudioop.tex b/Doc/lib/libaudioop.tex index 76bcdbf..52c6f3d 100644 --- a/Doc/lib/libaudioop.tex +++ b/Doc/lib/libaudioop.tex @@ -12,9 +12,10 @@ is the same format as used by the \refmodule{al} and \refmodule{sunaudiodev} modules. All scalar items are integers, unless specified otherwise. % This para is mostly here to provide an excuse for the index entries... -This module provides support for u-LAW and Intel/DVI ADPCM encodings. +This module provides support for a-LAW, u-LAW and Intel/DVI ADPCM encodings. \index{Intel/DVI ADPCM} \index{ADPCM, Intel/DVI} +\index{a-LAW} \index{u-LAW} A few of the more complicated operations only take 16-bit samples, @@ -42,6 +43,13 @@ Return a tuple \code{(\var{sample}, \var{newstate})} where the sample has the width specified in \var{width}. \end{funcdesc} +\begin{funcdesc}{alaw2lin}{fragment, width} +Convert sound fragments in a-LAW encoding to linearly encoded sound +fragments. a-LAW encoding always uses 8 bits samples, so \var{width} +refers only to the sample width of the output fragment here. +\versionadded{2.5} +\end{funcdesc} + \begin{funcdesc}{avg}{fragment, width} Return the average over all samples in the fragment. \end{funcdesc} @@ -98,10 +106,6 @@ The routine takes time proportional to \code{len(\var{fragment})}. Return the value of sample \var{index} from the fragment. \end{funcdesc} -\begin{funcdesc}{lin2lin}{fragment, width, newwidth} -Convert samples between 1-, 2- and 4-byte formats. -\end{funcdesc} - \begin{funcdesc}{lin2adpcm}{fragment, width, state} Convert samples to 4 bit Intel/DVI ADPCM encoding. ADPCM coding is an adaptive coding scheme, whereby each 4 bit number is the difference @@ -117,6 +121,18 @@ passed as the state. \var{adpcmfrag} is the ADPCM coded fragment packed 2 4-bit values per byte. \end{funcdesc} +\begin{funcdesc}{lin2alaw}{fragment, width} +Convert samples in the audio fragment to a-LAW encoding and return +this as a Python string. a-LAW is an audio encoding format whereby +you get a dynamic range of about 13 bits using only 8 bit samples. It +is used by the Sun audio hardware, among others. +\versionadded{2.5} +\end{funcdesc} + +\begin{funcdesc}{lin2lin}{fragment, width, newwidth} +Convert samples between 1-, 2- and 4-byte formats. +\end{funcdesc} + \begin{funcdesc}{lin2ulaw}{fragment, width} Convert samples in the audio fragment to u-LAW encoding and return this as a Python string. u-LAW is an audio encoding format whereby diff --git a/Doc/lib/libbsddb.tex b/Doc/lib/libbsddb.tex index fa7bb4b..a5cda6d 100644 --- a/Doc/lib/libbsddb.tex +++ b/Doc/lib/libbsddb.tex @@ -15,9 +15,8 @@ other objects as keys or to store other kinds of objects the user must serialize them somehow, typically using \function{marshal.dumps()} or \function{pickle.dumps}. -Starting with Python 2.3 the \module{bsddb} module requires the -Berkeley DB library version 3.2 or later (it is known to work with 3.2 -through 4.3 at the time of this writing). +The \module{bsddb} module requires a Berkeley DB library version from +3.3 thru 4.4. \begin{seealso} \seeurl{http://pybsddb.sourceforge.net/}{Website with documentation diff --git a/Doc/lib/libcalendar.tex b/Doc/lib/libcalendar.tex index bf3a7d6..acfd2da 100644 --- a/Doc/lib/libcalendar.tex +++ b/Doc/lib/libcalendar.tex @@ -15,12 +15,177 @@ convention). Use \function{setfirstweekday()} to set the first day of the week to Sunday (6) or to any other weekday. Parameters that specify dates are given as integers. -Most of these functions rely on the \module{datetime} module which -uses an idealized calendar, the current Gregorian calendar indefinitely -extended in both directions. This matches the definition of the -"proleptic Gregorian" calendar in Dershowitz and Reingold's book -"Calendrical Calculations", where it's the base calendar for all -computations. +Most of these functions and classses rely on the \module{datetime} +module which uses an idealized calendar, the current Gregorian +calendar indefinitely extended in both directions. This matches +the definition of the "proleptic Gregorian" calendar in Dershowitz +and Reingold's book "Calendrical Calculations", where it's the +base calendar for all computations. + +\begin{classdesc}{Calendar}{\optional{firstweekday}} +Creates a \class{Calendar} object. \var{firstweekday} is an integer +specifying the first day of the week. \code{0} is Monday (the default), +\code{6} is Sunday. + +A \class{Calendar} object provides several methods that can +be used for preparing the calendar data for formatting. This +class doesn't do any formatting itself. This is the job of +subclasses. +\versionadded{2.5} +\end{classdesc} + +\class{Calendar} instances have the following methods: + +\begin{methoddesc}{iterweekdays}{weekday} +Return an iterator for the week day numbers that will be used +for one week. The first number from the iterator will be the +same as the number returned by \method{firstweekday()}. +\end{methoddesc} + +\begin{methoddesc}{itermonthdates}{year, month} +Return an iterator for the month \var{month} (1-12) in the +year \var{year}. This iterator will return all days (as +\class{datetime.date} objects) for the month and all days +before the start of the month or after the end of the month +that are required to get a complete week. +\end{methoddesc} + +\begin{methoddesc}{itermonthdays2}{year, month} +Return an iterator for the month \var{month} in the year +\var{year} similar to \method{itermonthdates()}. Days returned +will be tuples consisting of a day number and a week day +number. +\end{methoddesc} + +\begin{methoddesc}{itermonthdays}{year, month} +Return an iterator for the month \var{month} in the year +\var{year} similar to \method{itermonthdates()}. Days returned +will simply be day numbers. +\end{methoddesc} + +\begin{methoddesc}{monthdatescalendar}{year, month} +Return a list of the weeks in the month \var{month} of +the \var{year} as full weeks. Weeks are lists of seven +\class{datetime.date} objects. +\end{methoddesc} + +\begin{methoddesc}{monthdays2calendar}{year, month} +Return a list of the weeks in the month \var{month} of +the \var{year} as full weeks. Weeks are lists of seven +tuples of day numbers and weekday numbers. +\end{methoddesc} + +\begin{methoddesc}{monthdayscalendar}{year, month} +Return a list of the weeks in the month \var{month} of +the \var{year} as full weeks. Weeks are lists of seven +day numbers. +\end{methoddesc} + +\begin{methoddesc}{yeardatescalendar}{year, month\optional{, width}} +Return the data for the specified year ready for formatting. The return +value is a list of month rows. Each month row contains up to \var{width} +months (defaulting to 3). Each month contains between 4 and 6 weeks and +each week contains 1--7 days. Days are \class{datetime.date} objects. +\end{methoddesc} + +\begin{methoddesc}{yeardays2calendar}{year, month\optional{, width}} +Return the data for the specified year ready for formatting (similar to +\method{yeardatescalendar()}). Entries in the week lists are tuples of +day numbers and weekday numbers. Day numbers outside this month are zero. +\end{methoddesc} + +\begin{methoddesc}{yeardayscalendar}{year, month\optional{, width}} +Return the data for the specified year ready for formatting (similar to +\method{yeardatescalendar()}). Entries in the week lists are day numbers. +Day numbers outside this month are zero. +\end{methoddesc} + + +\begin{classdesc}{TextCalendar}{\optional{firstweekday}} +This class can be used to generate plain text calendars. + +\versionadded{2.5} +\end{classdesc} + +\class{TextCalendar} instances have the following methods: + +\begin{methoddesc}{formatmonth}{theyear, themonth\optional{, w\optional{, l}}} +Return a month's calendar in a multi-line string. If \var{w} is +provided, it specifies the width of the date columns, which are +centered. If \var{l} is given, it specifies the number of lines that +each week will use. Depends on the first weekday as set by +\function{setfirstweekday()}. +\end{methoddesc} + +\begin{methoddesc}{prmonth}{theyear, themonth\optional{, w\optional{, l}}} +Print a month's calendar as returned by \method{formatmonth()}. +\end{methoddesc} + +\begin{methoddesc}{formatyear}{theyear, themonth\optional{, w\optional{, + l\optional{, c\optional{, m}}}}} +Return a \var{m}-column calendar for an entire year as a multi-line string. +Optional parameters \var{w}, \var{l}, and \var{c} are for date column +width, lines per week, and number of spaces between month columns, +respectively. Depends on the first weekday as set by +\method{setfirstweekday()}. The earliest year for which a calendar can +be generated is platform-dependent. +\end{methoddesc} + +\begin{methoddesc}{pryear}{theyear\optional{, w\optional{, l\optional{, + c\optional{, m}}}}} +Print the calendar for an entire year as returned by \method{formatyear()}. +\end{methoddesc} + + +\begin{classdesc}{HTMLCalendar}{\optional{firstweekday}} +This class can be used to generate HTML calendars. + +\versionadded{2.5} +\end{classdesc} + +\class{HTMLCalendar} instances have the following methods: + +\begin{methoddesc}{formatmonth}{theyear, themonth\optional{, withyear}} +Return a month's calendar as an HTML table. If \var{withyear} is +true the year will be included in the header, otherwise just the +month name will be used. +\end{methoddesc} + +\begin{methoddesc}{formatyear}{theyear, themonth\optional{, width}} +Return a year's calendar as an HTML table. \var{width} (defaulting to 3) +specifies the number of months per row. +\end{methoddesc} + +\begin{methoddesc}{formatyearpage}{theyear, themonth\optional{, + width\optional{, css\optional{, encoding}}}} +Return a year's calendar as a complete HTML page. \var{width} +(defaulting to 3) specifies the number of months per row. \var{css} +is the name for the cascading style sheet to be used. \constant{None} +can be passed if no style sheet should be used. \var{encoding} +specifies the encoding to be used for the output (defaulting +to the system default encoding). +\end{methoddesc} + + +\begin{classdesc}{LocaleTextCalendar}{\optional{firstweekday\optional{, locale}}} +This subclass of \class{TextCalendar} can be passed a locale name in the +constructor and will return month and weekday names in the specified locale. +If this locale includes an encoding all strings containing month and weekday +names will be returned as unicode. +\versionadded{2.5} +\end{classdesc} + + +\begin{classdesc}{LocaleHTMLCalendar}{\optional{firstweekday\optional{, locale}}} +This subclass of \class{HTMLCalendar} can be passed a locale name in the +constructor and will return month and weekday names in the specified locale. +If this locale includes an encoding all strings containing month and weekday +names will be returned as unicode. +\versionadded{2.5} +\end{classdesc} + + +For simple text calendars this module provides the following functions. \begin{funcdesc}{setfirstweekday}{weekday} Sets the weekday (\code{0} is Monday, \code{6} is Sunday) to start @@ -80,11 +245,8 @@ Prints a month's calendar as returned by \function{month()}. \end{funcdesc} \begin{funcdesc}{month}{theyear, themonth\optional{, w\optional{, l}}} -Returns a month's calendar in a multi-line string. If \var{w} is -provided, it specifies the width of the date columns, which are -centered. If \var{l} is given, it specifies the number of lines that -each week will use. Depends on the first weekday as set by -\function{setfirstweekday()}. +Returns a month's calendar in a multi-line string using the +\method{formatmonth} of the \class{TextCalendar} class. \versionadded{2.0} \end{funcdesc} @@ -94,12 +256,8 @@ Prints the calendar for an entire year as returned by \end{funcdesc} \begin{funcdesc}{calendar}{year\optional{, w\optional{, l\optional{c}}}} -Returns a 3-column calendar for an entire year as a multi-line string. -Optional parameters \var{w}, \var{l}, and \var{c} are for date column -width, lines per week, and number of spaces between month columns, -respectively. Depends on the first weekday as set by -\function{setfirstweekday()}. The earliest year for which a calendar can -be generated is platform-dependent. +Returns a 3-column calendar for an entire year as a multi-line string +using the \method{formatyear} of the \class{TextCalendar} class. \versionadded{2.0} \end{funcdesc} diff --git a/Doc/lib/libcgi.tex b/Doc/lib/libcgi.tex index cd6f58a..1dd7e03 100644 --- a/Doc/lib/libcgi.tex +++ b/Doc/lib/libcgi.tex @@ -323,7 +323,7 @@ not included. The optional argument \var{strict_parsing} is a flag indicating what to do with parsing errors. If false (the default), errors -are silently ignored. If true, errors raise a ValueError +are silently ignored. If true, errors raise a \exception{ValueError} exception. Use the \function{\refmodule{urllib}.urlencode()} function to convert @@ -347,7 +347,7 @@ not included. The optional argument \var{strict_parsing} is a flag indicating what to do with parsing errors. If false (the default), errors -are silently ignored. If true, errors raise a ValueError +are silently ignored. If true, errors raise a \exception{ValueError} exception. Use the \function{\refmodule{urllib}.urlencode()} function to convert diff --git a/Doc/lib/libcodecs.tex b/Doc/lib/libcodecs.tex index 1806ef0..8a2417e 100644 --- a/Doc/lib/libcodecs.tex +++ b/Doc/lib/libcodecs.tex @@ -112,6 +112,7 @@ class or factory function. Raises a \exception{LookupError} in case the encoding cannot be found or the codec doesn't support an incremental encoder. +\versionadded{2.5} \end{funcdesc} \begin{funcdesc}{getincrementaldecoder}{encoding} @@ -120,6 +121,7 @@ class or factory function. Raises a \exception{LookupError} in case the encoding cannot be found or the codec doesn't support an incremental decoder. +\versionadded{2.5} \end{funcdesc} \begin{funcdesc}{getreader}{encoding} @@ -150,7 +152,7 @@ unencodable part of the input and a position where encoding should continue. The encoder will encode the replacement and continue encoding the original input at the specified position. Negative position values will be treated as being relative to the end of the input string. If the -resulting position is out of bound an IndexError will be raised. +resulting position is out of bound an \exception{IndexError} will be raised. Decoding and translating works similar, except \exception{UnicodeDecodeError} or \exception{UnicodeTranslateError} will be passed to the handler and @@ -229,12 +231,14 @@ an encoding error occurs. Uses an incremental encoder to iteratively encode the input provided by \var{iterable}. This function is a generator. \var{errors} (as well as any other keyword argument) is passed through to the incremental encoder. +\versionadded{2.5} \end{funcdesc} \begin{funcdesc}{iterdecode}{iterable, encoding\optional{, errors}} Uses an incremental decoder to iteratively decode the input provided by \var{iterable}. This function is a generator. \var{errors} (as well as any other keyword argument) is passed through to the incremental encoder. +\versionadded{2.5} \end{funcdesc} The module also provides the following constants which are useful @@ -355,6 +359,8 @@ encoded/decoded with the stateless encoder/decoder. \subsubsection{IncrementalEncoder Objects \label{incremental-encoder-objects}} +\versionadded{2.5} + The \class{IncrementalEncoder} class is used for encoding an input in multiple steps. It defines the following methods which every incremental encoder must define in order to be compatible to the Python codec registry. @@ -437,6 +443,10 @@ define in order to be compatible to the Python codec registry. Decodes \var{object} (taking the current state of the decoder into account) and returns the resulting decoded object. If this is the last call to \method{decode} \var{final} must be true (the default is false). + If \var{final} is true the decoder must decode the input completely and must + flush all buffers. If this isn't possible (e.g. because of incomplete byte + sequences at the end of the input) it must initiate error handling just like + in the stateless case (which might raise an exception). \end{methoddesc} \begin{methoddesc}{reset}{} @@ -690,10 +700,10 @@ transformation can be done (these methods are also called encodings). The simplest method is to map the codepoints 0-255 to the bytes \code{0x0}-\code{0xff}. This means that a unicode object that contains codepoints above \code{U+00FF} can't be encoded with this method (which -is called \code{'latin-1'} or \code{'iso-8859-1'}). unicode.encode() will -raise a UnicodeEncodeError that looks like this: \samp{UnicodeEncodeError: -'latin-1' codec can't encode character u'\e u1234' in position 3: ordinal -not in range(256)}. +is called \code{'latin-1'} or \code{'iso-8859-1'}). +\function{unicode.encode()} will raise a \exception{UnicodeEncodeError} +that looks like this: \samp{UnicodeEncodeError: 'latin-1' codec can't +encode character u'\e u1234' in position 3: ordinal not in range(256)}. There's another group of encodings (the so called charmap encodings) that choose a different subset of all unicode code points and how @@ -1220,7 +1230,7 @@ listed as operand type in the table. \lineiv{rot_13} {rot13} - {byte string} + {Unicode string} {Returns the Caesar-cypher encryption of the operand} \lineiv{string_escape} diff --git a/Doc/lib/libcollections.tex b/Doc/lib/libcollections.tex index 542ef6b..d9bfa39 100644 --- a/Doc/lib/libcollections.tex +++ b/Doc/lib/libcollections.tex @@ -10,9 +10,11 @@ This module implements high-performance container datatypes. Currently, there are two datatypes, deque and defaultdict. -Future additions may include B-trees and Fibonacci heaps. +Future additions may include balanced trees and ordered dictionaries. \versionchanged[Added defaultdict]{2.5} +\subsection{\class{deque} objects \label{deque-objects}} + \begin{funcdesc}{deque}{\optional{iterable}} Returns a new deque objected initialized left-to-right (using \method{append()}) with data from \var{iterable}. If \var{iterable} @@ -137,7 +139,7 @@ IndexError: pop from an empty deque deque(['c', 'b', 'a']) \end{verbatim} -\subsection{Recipes \label{deque-recipes}} +\subsubsection{Recipes \label{deque-recipes}} This section shows various approaches to working with deques. @@ -215,6 +217,8 @@ def maketree(iterable): +\subsection{\class{defaultdict} objects \label{defaultdict-objects}} + \begin{funcdesc}{defaultdict}{\optional{default_factory\optional{, ...}}} Returns a new dictionary-like object. \class{defaultdict} is a subclass of the builtin \class{dict} class. It overrides one method and adds one @@ -255,3 +259,79 @@ the standard \class{dict} operations: from the first argument to the constructor, if present, or to \code{None}, if absent. \end{datadesc} + + +\subsubsection{\class{defaultdict} Examples \label{defaultdict-examples}} + +Using \class{list} as the \member{default_factory}, it is easy to group +a sequence of key-value pairs into a dictionary of lists: + +\begin{verbatim} +>>> s = [('yellow', 1), ('blue', 2), ('yellow', 3), ('blue', 4), ('red', 1)] +>>> d = defaultdict(list) +>>> for k, v in s: + d[k].append(v) + +>>> d.items() +[('blue', [2, 4]), ('red', [1]), ('yellow', [1, 3])] +\end{verbatim} + +When each key is encountered for the first time, it is not already in the +mapping; so an entry is automatically created using the +\member{default_factory} function which returns an empty \class{list}. The +\method{list.append()} operation then attaches the value to the new list. When +keys are encountered again, the look-up proceeds normally (returning the list +for that key) and the \method{list.append()} operation adds another value to +the list. This technique is simpler and faster than an equivalent technique +using \method{dict.setdefault()}: + +\begin{verbatim} +>>> d = {} +>>> for k, v in s: + d.setdefault(k, []).append(v) + +>>> d.items() +[('blue', [2, 4]), ('red', [1]), ('yellow', [1, 3])] +\end{verbatim} + +Setting the \member{default_factory} to \class{int} makes the +\class{defaultdict} useful for counting (like a bag or multiset in other +languages): + +\begin{verbatim} +>>> s = 'mississippi' +>>> d = defaultdict(int) +>>> for k in s: + d[k] += 1 + +>>> d.items() +[('i', 4), ('p', 2), ('s', 4), ('m', 1)] +\end{verbatim} + +When a letter is first encountered, it is missing from the mapping, so the +\member{default_factory} function calls \function{int()} to supply a default +count of zero. The increment operation then builds up the count for each +letter. This technique makes counting simpler and faster than an equivalent +technique using \method{dict.get()}: + +\begin{verbatim} +>>> d = {} +>>> for k in s: + d[k] = d.get(k, 0) + 1 + +>>> d.items() +[('i', 4), ('p', 2), ('s', 4), ('m', 1)] +\end{verbatim} + +Setting the \member{default_factory} to \class{set} makes the +\class{defaultdict} useful for building a dictionary of sets: + +\begin{verbatim} +>>> s = [('red', 1), ('blue', 2), ('red', 3), ('blue', 4), ('red', 1), ('blue', 4)] +>>> d = defaultdict(set) +>>> for k, v in s: + d[k].add(v) + +>>> d.items() +[('blue', set([2, 4])), ('red', set([1, 3]))] +\end{verbatim} diff --git a/Doc/lib/libcontextlib.tex b/Doc/lib/libcontextlib.tex new file mode 100644 index 0000000..46f9cdd --- /dev/null +++ b/Doc/lib/libcontextlib.tex @@ -0,0 +1,144 @@ +\section{\module{contextlib} --- + Utilities for \keyword{with}-statement contexts.} + +\declaremodule{standard}{contextlib} +\modulesynopsis{Utilities for \keyword{with}-statement contexts.} + +\versionadded{2.5} + +This module provides utilities for common tasks involving the +\keyword{with} statement. + +Functions provided: + +\begin{funcdesc}{contextmanager}{func} +This function is a decorator that can be used to define context managers +for use with the \keyword{with} statement, without needing to create a +class or separate \method{__enter__()} and \method{__exit__()} methods. + +A simple example: + +\begin{verbatim} +from __future__ import with_statement +from contextlib import contextmanager + +@contextmanager +def tag(name): + print "<%s>" % name + yield + print "</%s>" % name + +>>> with tag("h1"): +... print "foo" +... +<h1> +foo +</h1> +\end{verbatim} + +When called, the decorated function must return a generator-iterator. +This iterator must yield exactly one value, which will be bound to the +targets in the \keyword{with} statement's \keyword{as} clause, if any. + +At the point where the generator yields, the block nested in the +\keyword{with} statement is executed. The generator is then resumed +after the block is exited. If an unhandled exception occurs in the +block, it is reraised inside the generator at the point where the yield +occurred. Thus, you can use a +\keyword{try}...\keyword{except}...\keyword{finally} statement to trap +the error (if any), or ensure that some cleanup takes place. + +Note that you can use \code{@contextmanager} to define a context +manager's \method{__context__} method. This is usually more convenient +than creating another class just to serve as a context. For example: + +\begin{verbatim} +from __future__ import with_statement +from contextlib import contextmanager + +class Tag: + def __init__(self, name): + self.name = name + + @contextmanager + def __context__(self): + print "<%s>" % self.name + yield self + print "</%s>" % self.name + +h1 = Tag("h1") + +>>> with h1 as me: +... print "hello from", me +<h1> +hello from <__main__.Tag instance at 0x402ce8ec> +</h1> +\end{verbatim} +\end{funcdesc} + +\begin{funcdesc}{nested}{ctx1\optional{, ctx2\optional{, ...}}} +Combine multiple context managers into a single nested context manager. + +Code like this: + +\begin{verbatim} +from contextlib import nested + +with nested(A, B, C) as (X, Y, Z): + do_something() +\end{verbatim} + +is equivalent to this: + +\begin{verbatim} +with A as X: + with B as Y: + with C as Z: + do_something() +\end{verbatim} + +Note that if one of the nested contexts' \method{__exit__()} method +raises an exception, any previous exception state will be lost; the new +exception will be passed to the outer contexts' \method{__exit__()} +method(s), if any. In general, \method{__exit__()} methods should avoid +raising exceptions, and in particular they should not re-raise a +passed-in exception. +\end{funcdesc} + +\label{context-closing} +\begin{funcdesc}{closing}{thing} +Return a context manager that closes \var{thing} upon completion of the +block. This is basically equivalent to: + +\begin{verbatim} +from contextlib import contextmanager + +@contextmanager +def closing(thing): + try: + yield thing + finally: + thing.close() +\end{verbatim} + +And lets you write code like this: +\begin{verbatim} +from __future__ import with_statement +from contextlib import closing +import codecs + +with closing(codecs.open("foo", encoding="utf8")) as f: + for line in f: + print line.encode("latin1") +\end{verbatim} + +without needing to explicitly close \code{f}. Even if an error occurs, +\code{f.close()} will be called when the \keyword{with} block is exited. + +\end{funcdesc} + +\begin{seealso} + \seepep{0343}{The "with" statement} + {The specification, background, and examples for the + Python \keyword{with} statement.} +\end{seealso} diff --git a/Doc/lib/libcookielib.tex b/Doc/lib/libcookielib.tex index a35f97d..ef2d833 100644 --- a/Doc/lib/libcookielib.tex +++ b/Doc/lib/libcookielib.tex @@ -249,7 +249,7 @@ anyway, unless you ask otherwise by passing a true ignore_discard=\constant{False}, ignore_expires=\constant{False}} Save cookies to a file. -This base class raises \class{NotImplementedError}. Subclasses may +This base class raises \exception{NotImplementedError}. Subclasses may leave this method unimplemented. \var{filename} is the name of file in which to save cookies. If diff --git a/Doc/lib/libcsv.tex b/Doc/lib/libcsv.tex index ba0df4f..65053c7 100644 --- a/Doc/lib/libcsv.tex +++ b/Doc/lib/libcsv.tex @@ -33,8 +33,9 @@ form using the \class{DictReader} and \class{DictWriter} classes. \begin{notice} This version of the \module{csv} module doesn't support Unicode input. Also, there are currently some issues regarding \ASCII{} NUL - characters. Accordingly, all input should generally be printable - \ASCII{} to be safe. These restrictions will be removed in the future. + characters. Accordingly, all input should be UTF-8 or printable + \ASCII{} to be safe; see the examples in section~\ref{csv-examples}. + These restrictions will be removed in the future. \end{notice} \begin{seealso} @@ -365,7 +366,7 @@ A read-only description of the dialect in use by the writer. -\subsection{Examples} +\subsection{Examples\label{csv-examples}} The simplest example of reading a CSV file: @@ -426,37 +427,99 @@ for row in csv.reader(['one,two,three']): \end{verbatim} The \module{csv} module doesn't directly support reading and writing -Unicode, but it is 8-bit clean save for some problems with \ASCII{} NUL -characters, so you can write classes that handle the encoding and decoding -for you as long as you avoid encodings like utf-16 that use NULs: +Unicode, but it is 8-bit-clean save for some problems with \ASCII{} NUL +characters. So you can write functions or classes that handle the +encoding and decoding for you as long as you avoid encodings like +UTF-16 that use NULs. UTF-8 is recommended. + +\function{unicode_csv_reader} below is a generator that wraps +\class{csv.reader} to handle Unicode CSV data (a list of Unicode +strings). \function{utf_8_encoder} is a generator that encodes the +Unicode strings as UTF-8, one string (or row) at a time. The encoded +strings are parsed by the CSV reader, and +\function{unicode_csv_reader} decodes the UTF-8-encoded cells back +into Unicode: \begin{verbatim} import csv +def unicode_csv_reader(unicode_csv_data, dialect=csv.excel, **kwargs): + # csv.py doesn't do Unicode; encode temporarily as UTF-8: + csv_reader = csv.reader(utf_8_encoder(unicode_csv_data), + dialect=dialect, **kwargs) + for row in csv_reader: + # decode UTF-8 back to Unicode, cell by cell: + yield [unicode(cell, 'utf-8') for cell in row] + +def utf_8_encoder(unicode_csv_data): + for line in unicode_csv_data: + yield line.encode('utf-8') +\end{verbatim} + +For all other encodings the following \class{UnicodeReader} and +\class{UnicodeWriter} classes can be used. They take an additional +\var{encoding} parameter in their constructor and make sure that the data +passes the real reader or writer encoded as UTF-8: + +\begin{verbatim} +import csv, codecs, cStringIO + +class UTF8Recoder: + """ + Iterator that reads an encoded stream and reencodes the input to UTF-8 + """ + def __init__(self, f, encoding): + self.reader = codecs.getreader(encoding)(f) + + def __iter__(self): + return self + + def next(self): + return self.reader.next().encode("utf-8") + class UnicodeReader: + """ + A CSV reader which will iterate over lines in the CSV file "f", + which is encoded in the given encoding. + """ + def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds): + f = UTF8Recoder(f, encoding) self.reader = csv.reader(f, dialect=dialect, **kwds) - self.encoding = encoding def next(self): row = self.reader.next() - return [unicode(s, self.encoding) for s in row] + return [unicode(s, "utf-8") for s in row] def __iter__(self): return self class UnicodeWriter: + """ + A CSV writer which will write rows to CSV file "f", + which is encoded in the given encoding. + """ + def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds): - self.writer = csv.writer(f, dialect=dialect, **kwds) - self.encoding = encoding + # Redirect output to a queue + self.queue = cStringIO.StringIO() + self.writer = csv.writer(self.queue, dialect=dialect, **kwds) + self.stream = f + self.encoder = codecs.getincrementalencoder(encoding)() def writerow(self, row): - self.writer.writerow([s.encode(self.encoding) for s in row]) + self.writer.writerow([s.encode("utf-8") for s in row]) + # Fetch UTF-8 output from the queue ... + data = self.queue.getvalue() + data = data.decode("utf-8") + # ... and reencode it into the target encoding + data = self.encoder.encode(data) + # write to the target stream + self.stream.write(data) + # empty queue + self.queue.truncate(0) def writerows(self, rows): for row in rows: self.writerow(row) \end{verbatim} - -They should work just like the \class{csv.reader} and \class{csv.writer} -classes but add an \var{encoding} parameter. diff --git a/Doc/lib/libdatetime.tex b/Doc/lib/libdatetime.tex index 4bba553..cae5d60 100644 --- a/Doc/lib/libdatetime.tex +++ b/Doc/lib/libdatetime.tex @@ -504,7 +504,7 @@ Instance methods: Return a string representing the date, controlled by an explicit format string. Format codes referring to hours, minutes or seconds will see 0 values. - See the section on \method{strftime()} behavior. + See section~\ref{strftime-behavior} -- \method{strftime()} behavior. \end{methoddesc} @@ -970,8 +970,8 @@ Instance methods: \begin{methoddesc}{strftime}{format} Return a string representing the date and time, controlled by an - explicit format string. See the section on \method{strftime()} - behavior. + explicit format string. See section~\ref{strftime-behavior} -- + \method{strftime()} behavior. \end{methoddesc} @@ -1100,7 +1100,8 @@ Instance methods: \begin{methoddesc}{strftime}{format} Return a string representing the time, controlled by an explicit - format string. See the section on \method{strftime()} behavior. + format string. See section~\ref{strftime-behavior} -- + \method{strftime()} behavior. \end{methoddesc} \begin{methoddesc}{utcoffset}{} @@ -1368,7 +1369,7 @@ representing only EST (fixed offset -5 hours), or only EDT (fixed offset -4 hours)). -\subsection{\method{strftime()} Behavior} +\subsection{\method{strftime()} Behavior\label{strftime-behavior}} \class{date}, \class{datetime}, and \class{time} objects all support a \code{strftime(\var{format})} diff --git a/Doc/lib/libdecimal.tex b/Doc/lib/libdecimal.tex index 092f038..ffc3363 100644 --- a/Doc/lib/libdecimal.tex +++ b/Doc/lib/libdecimal.tex @@ -442,9 +442,33 @@ the \function{getcontext()} and \function{setcontext()} functions: Set the current context for the active thread to \var{c}. \end{funcdesc} -New contexts can formed using the \class{Context} constructor described below. -In addition, the module provides three pre-made contexts: +Beginning with Python 2.5, you can also use the \keyword{with} statement +to temporarily change the active context. For example the following code +increases the current decimal precision by 2 places, performs a +calculation, and then automatically restores the previous context: +\begin{verbatim} +from __future__ import with_statement +import decimal + +with decimal.getcontext() as ctx: + ctx.prec += 2 # add 2 more digits of precision + calculate_something() +\end{verbatim} + +The context that's active in the body of the \keyword{with} statement is +a \emph{copy} of the context you provided to the \keyword{with} +statement, so modifying its attributes doesn't affect anything except +that temporary copy. + +You can use any decimal context in a \keyword{with} statement, but if +you just want to make a temporary change to some aspect of the current +context, it's easiest to just use \function{getcontext()} as shown +above. + +New contexts can also be created using the \class{Context} constructor +described below. In addition, the module provides three pre-made +contexts: \begin{classdesc*}{BasicContext} This is a standard context defined by the General Decimal Arithmetic diff --git a/Doc/lib/libfuncs.tex b/Doc/lib/libfuncs.tex index 0be3aa9..c0352d3 100644 --- a/Doc/lib/libfuncs.tex +++ b/Doc/lib/libfuncs.tex @@ -6,7 +6,7 @@ are always available. They are listed here in alphabetical order. \setindexsubitem{(built-in function)} -\begin{funcdesc}{__import__}{name\optional{, globals\optional{, locals\optional{, fromlist}}}} +\begin{funcdesc}{__import__}{name\optional{, globals\optional{, locals\optional{, fromlist\optional{, level}}}}} This function is invoked by the \keyword{import}\stindex{import} statement. It mainly exists so that you can replace it with another function that has a compatible interface, in order to change the @@ -20,9 +20,9 @@ are always available. They are listed here in alphabetical order. For example, the statement \samp{import spam} results in the following call: \code{__import__('spam',} \code{globals(),} - \code{locals(), [])}; the statement \samp{from spam.ham import eggs} + \code{locals(), [], -1)}; the statement \samp{from spam.ham import eggs} results in \samp{__import__('spam.ham', globals(), locals(), - ['eggs'])}. Note that even though \code{locals()} and + ['eggs'], -1)}. Note that even though \code{locals()} and \code{['eggs']} are passed in as arguments, the \function{__import__()} function does not set the local variable named \code{eggs}; this is done by subsequent code that is generated @@ -52,6 +52,15 @@ def my_import(name): mod = getattr(mod, comp) return mod \end{verbatim} + + \var{level} specifies whether to use absolute or relative imports. + The default is \code{-1} which indicates both absolute and relative + imports will be attempted. \code{0} means only perform absolute imports. + Positive values for \var{level} indicate the number of parent directories + to search relative to the directory of the module calling + \function{__import__}. +\versionchanged[The level parameter was added]{2.5} +\versionchanged[Keyword support for parameters was added]{2.5} \end{funcdesc} \begin{funcdesc}{abs}{x} @@ -683,7 +692,7 @@ class C: \end{funcdesc} \begin{funcdesc}{object}{} - Return a new featureless object. \function{object()} is a base + Return a new featureless object. \class{object} is a base for all new style classes. It has the methods that are common to all instances of new style classes. \versionadded{2.2} @@ -718,8 +727,11 @@ class C: \begin{funcdesc}{pow}{x, y\optional{, z}} Return \var{x} to the power \var{y}; if \var{z} is present, return \var{x} to the power \var{y}, modulo \var{z} (computed more - efficiently than \code{pow(\var{x}, \var{y}) \%\ \var{z}}). The - arguments must have numeric types. With mixed operand types, the + efficiently than \code{pow(\var{x}, \var{y}) \%\ \var{z}}). + The two-argument form \code{pow(\var{x}, \var{y})} is equivalent to using + the power operator: \code{\var{x}**\var{y}}. + + The arguments must have numeric types. With mixed operand types, the coercion rules for binary arithmetic operators apply. For int and long int operands, the result has the same type as the operands (after coercion) unless the second argument is negative; in that diff --git a/Doc/lib/libgc.tex b/Doc/lib/libgc.tex index 54ca26c..0d3408b 100644 --- a/Doc/lib/libgc.tex +++ b/Doc/lib/libgc.tex @@ -35,7 +35,8 @@ Returns true if automatic collection is enabled. \begin{funcdesc}{collect}{\optional{generation}} With no arguments, run a full collection. The optional argument \var{generation} may be an integer specifying which generation to collect -(from 0 to 2). A ValueError is raised if the generation number is invalid. +(from 0 to 2). A \exception{ValueError} is raised if the generation number +is invalid. The number of unreachable objects found is returned. \versionchanged[The optional \var{generation} argument was added]{2.5} diff --git a/Doc/lib/libgetpass.tex b/Doc/lib/libgetpass.tex index 28bfe8f..1d177d3 100644 --- a/Doc/lib/libgetpass.tex +++ b/Doc/lib/libgetpass.tex @@ -11,11 +11,15 @@ The \module{getpass} module provides two functions: -\begin{funcdesc}{getpass}{\optional{prompt}} +\begin{funcdesc}{getpass}{\optional{prompt\optional{, stream}}} Prompt the user for a password without echoing. The user is prompted using the string \var{prompt}, which defaults to - \code{'Password: '}. + \code{'Password: '}. On \UNIX, the prompt is written to the + file-like object \var{stream}, which defaults to + \code{sys.stdout} (this argument is ignored on Windows). + Availability: Macintosh, \UNIX, Windows. + \versionadded[The \var{stream} parameter]{2.5} \end{funcdesc} diff --git a/Doc/lib/libhashlib.tex b/Doc/lib/libhashlib.tex index e9d0b57..62e3fc4 100644 --- a/Doc/lib/libhashlib.tex +++ b/Doc/lib/libhashlib.tex @@ -31,7 +31,7 @@ of the strings fed to it so far using the \method{digest()} or Constructors for hash algorithms that are always present in this module are \function{md5()}, \function{sha1()}, \function{sha224()}, \function{sha256()}, \function{sha384()}, and \function{sha512()}. Additional algorithms may also -be available depending upon the OpenSSL library python uses on your platform. +be available depending upon the OpenSSL library that Python uses on your platform. \index{OpenSSL} For example, to obtain the digest of the string \code{'Nobody inspects diff --git a/Doc/lib/libitertools.tex b/Doc/lib/libitertools.tex index 421d647..20bbc8d 100644 --- a/Doc/lib/libitertools.tex +++ b/Doc/lib/libitertools.tex @@ -276,12 +276,30 @@ by functions or loops that truncate the stream. def izip(*iterables): iterables = map(iter, iterables) while iterables: - result = [i.next() for i in iterables] + result = [it.next() for it in iterables] yield tuple(result) \end{verbatim} \versionchanged[When no iterables are specified, returns a zero length - iterator instead of raising a TypeError exception]{2.4} + iterator instead of raising a \exception{TypeError} + exception]{2.4} + + Note, the left-to-right evaluation order of the iterables is guaranteed. + This makes possible an idiom for clustering a data series into n-length + groups using \samp{izip(*[iter(s)]*n)}. For data that doesn't fit + n-length groups exactly, the last tuple can be pre-padded with fill + values using \samp{izip(*[chain(s, [None]*(n-1))]*n)}. + + Note, when \function{izip()} is used with unequal length inputs, subsequent + iteration over the longer iterables cannot reliably be continued after + \function{izip()} terminates. Potentially, up to one entry will be missing + from each of the left-over iterables. This occurs because a value is fetched + from each iterator in-turn, but the process ends when one of the iterators + terminates. This leaves the last fetched values in limbo (they cannot be + returned in a final, incomplete tuple and they are cannot be pushed back + into the iterator for retrieval with \code{it.next()}). In general, + \function{izip()} should only be used with unequal length inputs when you + don't care about trailing, unmatched values from the longer iterables. \end{funcdesc} \begin{funcdesc}{repeat}{object\optional{, times}} @@ -517,4 +535,9 @@ def pairwise(iterable): pass return izip(a, b) +def grouper(n, iterable, padvalue=None): + "grouper(3, 'abcdefg', 'x') --> ('a','b','c'), ('d','e','f'), ('g','x','x')" + return izip(*[chain(iterable, repeat(padvalue, n-1))]*n) + + \end{verbatim} diff --git a/Doc/lib/liblinecache.tex b/Doc/lib/liblinecache.tex index c022ba9..1477d3c 100644 --- a/Doc/lib/liblinecache.tex +++ b/Doc/lib/liblinecache.tex @@ -15,7 +15,7 @@ the formatted traceback. The \module{linecache} module defines the following functions: -\begin{funcdesc}{getline}{filename, lineno} +\begin{funcdesc}{getline}{filename, lineno\optional{, module_globals}} Get line \var{lineno} from file named \var{filename}. This function will never throw an exception --- it will return \code{''} on errors (the terminating newline character will be included for lines that are @@ -23,7 +23,11 @@ found). If a file named \var{filename} is not found, the function will look for it in the module\indexiii{module}{search}{path} search path, -\code{sys.path}. +\code{sys.path}, after first checking for a \pep{302} \code{__loader__} +in \var{module_globals}, in case the module was imported from a zipfile +or other non-filesystem import source. + +\versionadded[The \var{module_globals} parameter was added]{2.5} \end{funcdesc} \begin{funcdesc}{clearcache}{} diff --git a/Doc/lib/libnntplib.tex b/Doc/lib/libnntplib.tex index 7f14dee..10330ed 100644 --- a/Doc/lib/libnntplib.tex +++ b/Doc/lib/libnntplib.tex @@ -68,48 +68,48 @@ flag \var{readermode} is true, then a \samp{mode reader} command is sent before authentication is performed. Reader mode is sometimes necessary if you are connecting to an NNTP server on the local machine and intend to call reader-specific commands, such as \samp{group}. If -you get unexpected \code{NNTPPermanentError}s, you might need to set +you get unexpected \exception{NNTPPermanentError}s, you might need to set \var{readermode}. \var{readermode} defaults to \code{None}. \var{usenetrc} defaults to \code{True}. \versionchanged[\var{usenetrc} argument added]{2.4} \end{classdesc} -\begin{classdesc}{NNTPError}{} -Derived from the standard exception \code{Exception}, this is the base -class for all exceptions raised by the \code{nntplib} module. -\end{classdesc} +\begin{excdesc}{NNTPError} +Derived from the standard exception \exception{Exception}, this is the +base class for all exceptions raised by the \module{nntplib} module. +\end{excdesc} -\begin{classdesc}{NNTPReplyError}{} +\begin{excdesc}{NNTPReplyError} Exception raised when an unexpected reply is received from the server. For backwards compatibility, the exception \code{error_reply} is equivalent to this class. -\end{classdesc} +\end{excdesc} -\begin{classdesc}{NNTPTemporaryError}{} +\begin{excdesc}{NNTPTemporaryError} Exception raised when an error code in the range 400--499 is received. For backwards compatibility, the exception \code{error_temp} is equivalent to this class. -\end{classdesc} +\end{excdesc} -\begin{classdesc}{NNTPPermanentError}{} +\begin{excdesc}{NNTPPermanentError} Exception raised when an error code in the range 500--599 is received. For backwards compatibility, the exception \code{error_perm} is equivalent to this class. -\end{classdesc} +\end{excdesc} -\begin{classdesc}{NNTPProtocolError}{} +\begin{excdesc}{NNTPProtocolError} Exception raised when a reply is received from the server that does not begin with a digit in the range 1--5. For backwards compatibility, the exception \code{error_proto} is equivalent to this class. -\end{classdesc} +\end{excdesc} -\begin{classdesc}{NNTPDataError}{} +\begin{excdesc}{NNTPDataError} Exception raised when there is some error in the response data. For backwards compatibility, the exception \code{error_data} is equivalent to this class. -\end{classdesc} +\end{excdesc} \subsection{NNTP Objects \label{nntp-objects}} diff --git a/Doc/lib/liboptparse.tex b/Doc/lib/liboptparse.tex index 4ab325b..8aca501 100644 --- a/Doc/lib/liboptparse.tex +++ b/Doc/lib/liboptparse.tex @@ -100,8 +100,8 @@ options; the traditional \UNIX{} syntax is a hyphen (``-'') followed by a single letter, e.g. \code{"-x"} or \code{"-F"}. Also, traditional \UNIX{} syntax allows multiple options to be merged into a single argument, e.g. \code{"-x -F"} is equivalent to \code{"-xF"}. The GNU project -introduced \code{"-{}-"} followed by a series of hyphen-separated words, -e.g. \code{"-{}-file"} or \code{"-{}-dry-run"}. These are the only two option +introduced \code{"{--}"} followed by a series of hyphen-separated words, +e.g. \code{"{--}file"} or \code{"{--}dry-run"}. These are the only two option syntaxes provided by \module{optparse}. Some other option syntaxes that the world has seen include: @@ -170,7 +170,7 @@ For example, consider this hypothetical command-line: prog -v --report /tmp/report.txt foo bar \end{verbatim} -\code{"-v"} and \code{"-{}-report"} are both options. Assuming that +\code{"-v"} and \code{"{--}report"} are both options. Assuming that \longprogramopt{report} takes one argument, \code{"/tmp/report.txt"} is an option argument. \code{"foo"} and \code{"bar"} are positional arguments. @@ -587,7 +587,7 @@ programmer errors and user errors. Programmer errors are usually erroneous calls to \code{parse.add{\_}option()}, e.g. invalid option strings, unknown option attributes, missing option attributes, etc. These are dealt with in the usual way: raise an exception (either -\code{optparse.OptionError} or \code{TypeError}) and let the program crash. +\exception{optparse.OptionError} or \exception{TypeError}) and let the program crash. Handling user errors is much more important, since they are guaranteed to happen no matter how stable your code is. \module{optparse} can automatically @@ -1019,9 +1019,9 @@ callback) as-is. Integer arguments are passed to \code{int()} to convert them to Python integers. If \code{int()} fails, so will \module{optparse}, although with a more -useful error message. (Internally, \module{optparse} raises OptionValueError; -OptionParser catches this exception higher up and terminates your -program with a useful error message.) +useful error message. (Internally, \module{optparse} raises +\exception{OptionValueError}; OptionParser catches this exception higher +up and terminates your program with a useful error message.) Likewise, \code{float} arguments are passed to \code{float()} for conversion, \code{long} arguments to \code{long()}, and \code{complex} arguments to @@ -1032,7 +1032,7 @@ arguments. option attribute (a sequence of strings) defines the set of allowed option arguments. \code{optparse.option.check{\_}choice()} compares user-supplied option arguments against this master list and raises -OptionValueError if an invalid string is given. +\exception{OptionValueError} if an invalid string is given. \subsubsection{Querying and manipulating your option parser\label{optparse-querying-manipulating-option-parser}} @@ -1052,7 +1052,7 @@ that option is removed. If that option provided any other option strings, all of those option strings become invalid. If \code{opt{\_}str} does not occur in any option belonging to this -OptionParser, raises ValueError. +OptionParser, raises \exception{ValueError}. \end{description} @@ -1087,7 +1087,7 @@ The available conflict-handling mechanisms are: \begin{description} \item[\code{error} (default)] assume option conflicts are a programming error and raise -OptionConflictError +\exception{OptionConflictError} \item[\code{resolve}] resolve option conflicts intelligently (see below) \end{description} @@ -1260,7 +1260,7 @@ is a dictionary of arbitrary keyword arguments supplied via \subsubsection{Raising errors in a callback\label{optparse-raising-errors-in-callback}} -The callback function should raise OptionValueError if there are any +The callback function should raise \exception{OptionValueError} if there are any problems with the option or its argument(s). \module{optparse} catches this and terminates the program, printing the error message you supply to stderr. Your message should be clear, concise, accurate, and mention diff --git a/Doc/lib/libos.tex b/Doc/lib/libos.tex index 9af5889..9ded3ae 100644 --- a/Doc/lib/libos.tex +++ b/Doc/lib/libos.tex @@ -343,6 +343,10 @@ Availability: Macintosh, \UNIX, Windows. \versionchanged[When specified, the \var{mode} argument must now start with one of the letters \character{r}, \character{w}, or \character{a}, otherwise a \exception{ValueError} is raised]{2.3} +\versionchanged[On \UNIX, when the \var{mode} argument starts with + \character{a}, the \var{O_APPEND} flag is set on the file descriptor + (which the \cfunction{fdopen()} implementation already does on most + platforms)]{2.5} \end{funcdesc} \begin{funcdesc}{popen}{command\optional{, mode\optional{, bufsize}}} @@ -547,7 +551,8 @@ documentation; flag constants (like \constant{O_RDONLY} and This function is intended for low-level I/O. For normal usage, use the built-in function \function{open()}, which returns a ``file object'' with \method{read()} and \method{write()} methods (and many -more). +more). To wrap a file descriptor in a ``file object'', use +\function{fdopen()}. \end{notice} \end{funcdesc} @@ -1731,6 +1736,27 @@ The \function{spawn()} functions called with \constant{P_NOWAIT} return suitable process handles. \end{funcdesc} +\begin{funcdesc}{wait3}{\optional{options}} +Similar to \function{waitpid()}, except no process id argument is given and +a 3-element tuple containing the child's process id, exit status indication, +and resource usage information is returned. Refer to +\module{resource}.\function{getrusage()} +for details on resource usage information. The option argument is the same +as that provided to \function{waitpid()} and \function{wait4()}. +Availability: \UNIX. +\versionadded{2.5} +\end{funcdesc} + +\begin{funcdesc}{wait4}{pid, options} +Similar to \function{waitpid()}, except a 3-element tuple, containing the +child's process id, exit status indication, and resource usage information +is returned. Refer to \module{resource}.\function{getrusage()} for details +on resource usage information. The arguments to \function{wait4()} are +the same as those provided to \function{waitpid()}. +Availability: \UNIX. +\versionadded{2.5} +\end{funcdesc} + \begin{datadesc}{WNOHANG} The option for \function{waitpid()} to return immediately if no child process status is available immediately. The function returns @@ -1818,14 +1844,14 @@ Return string-valued system configuration values. string which is the name of a defined system value; these names are specified in a number of standards (\POSIX, \UNIX{} 95, \UNIX{} 98, and others). Some platforms define additional names as well. The names -known to the host operating system are given in the +known to the host operating system are given as the keys of the \code{confstr_names} dictionary. For configuration variables not included in that mapping, passing an integer for \var{name} is also accepted. Availability: Macintosh, \UNIX. -If the configuration value specified by \var{name} isn't defined, the -empty string is returned. +If the configuration value specified by \var{name} isn't defined, +\code{None} is returned. If \var{name} is a string and is not known, \exception{ValueError} is raised. If a specific value for \var{name} is not supported by the diff --git a/Doc/lib/libossaudiodev.tex b/Doc/lib/libossaudiodev.tex index ec79e9e..223cf28 100644 --- a/Doc/lib/libossaudiodev.tex +++ b/Doc/lib/libossaudiodev.tex @@ -311,7 +311,7 @@ The mixer object provides two file-like methods: \begin{methoddesc}[mixer device]{close}{} This method closes the open mixer device file. Any further attempts to -use the mixer after this file is closed will raise an IOError. +use the mixer after this file is closed will raise an \exception{IOError}. \end{methoddesc} \begin{methoddesc}[mixer device]{fileno}{} diff --git a/Doc/lib/libpdb.tex b/Doc/lib/libpdb.tex index 6301175..a5b36a6 100644 --- a/Doc/lib/libpdb.tex +++ b/Doc/lib/libpdb.tex @@ -240,6 +240,45 @@ Condition is an expression which must evaluate to true before the breakpoint is honored. If condition is absent, any existing condition is removed; i.e., the breakpoint is made unconditional. +\item[commands \optional{\var{bpnumber}}] + +Specify a list of commands for breakpoint number \var{bpnumber}. The +commands themselves appear on the following lines. Type a line +containing just 'end' to terminate the commands. An example: + +\begin{verbatim} +(Pdb) commands 1 +(com) print some_variable +(com) end +(Pdb) +\end{verbatim} + +To remove all commands from a breakpoint, type commands and +follow it immediately with end; that is, give no commands. + +With no \var{bpnumber} argument, commands refers to the last +breakpoint set. + +You can use breakpoint commands to start your program up again. +Simply use the continue command, or step, or any other +command that resumes execution. + +Specifying any command resuming execution (currently continue, +step, next, return, jump, quit and their abbreviations) terminates +the command list (as if that command was immediately followed by end). +This is because any time you resume execution +(even with a simple next or step), you may encounter· +another breakpoint--which could have its own command list, leading to +ambiguities about which list to execute. + + If you use the 'silent' command in the command list, the +usual message about stopping at a breakpoint is not printed. This may +be desirable for breakpoints that are to print a specific message and +then continue. If none of the other commands print anything, you +see no sign that the breakpoint was reached. + +\versionadded{2.5} + \item[s(tep)] Execute the current line, stop at the first possible occasion diff --git a/Doc/lib/libprofile.tex b/Doc/lib/libprofile.tex index afc9694..9ff5ba0 100644 --- a/Doc/lib/libprofile.tex +++ b/Doc/lib/libprofile.tex @@ -124,7 +124,7 @@ layer on top of the internal \module{_lsprof} module. The %\end{description} -\section{Instant Users Manual \label{profile-instant}} +\section{Instant User's Manual \label{profile-instant}} This section is provided for users that ``don't want to read the manual.'' It provides a very brief overview, and allows a user to @@ -391,17 +391,17 @@ Analysis of the profiler data is done using this class from the % (This \stmodindex use may be hard to change ;-( ) \stmodindex{pstats} -\begin{classdesc}{Stats}{filename\optional{, \moreargs}} +\begin{classdesc}{Stats}{filename\optional{, \moreargs\optional{, stream=sys.stdout}}} This class constructor creates an instance of a ``statistics object'' from a \var{filename} (or set of filenames). \class{Stats} objects are -manipulated by methods, in order to print useful reports. - -The file selected by the above constructor must have been created by -the corresponding version of \module{profile} or \module{cProfile}. -To be specific, there is -\emph{no} file compatibility guaranteed with future versions of this -profiler, and there is no compatibility with files produced by other -profilers. +manipulated by methods, in order to print useful reports. You may specify +an alternate output stream by giving the keyword argument, \code{stream}. + +The file selected by the above constructor must have been created by the +corresponding version of \module{profile} or \module{cProfile}. To be +specific, there is \emph{no} file compatibility guaranteed with future +versions of this profiler, and there is no compatibility with files produced +by other profilers. %(such as the old system profiler). If several files are provided, all the statistics for identical diff --git a/Doc/lib/libpycompile.tex b/Doc/lib/libpycompile.tex index 0458191..85f0aaa 100644 --- a/Doc/lib/libpycompile.tex +++ b/Doc/lib/libpycompile.tex @@ -30,9 +30,10 @@ Exception raised when an error occurs while attempting to compile the file. \code{+} \code{'c'} (\code{'o'} if optimization is enabled in the current interpreter). If \var{dfile} is specified, it is used as the name of the source file in error messages instead of \var{file}. - If \var{doraise} = True, a PyCompileError is raised when an error is - encountered while compiling \var{file}. If \var{doraise} = False (the default), - an error string is written to sys.stderr, but no exception is raised. + If \var{doraise} is true, a \exception{PyCompileError} is raised when + an error is encountered while compiling \var{file}. If \var{doraise} + is false (the default), an error string is written to \code{sys.stderr}, + but no exception is raised. \end{funcdesc} \begin{funcdesc}{main}{\optional{args}} diff --git a/Doc/lib/libqueue.tex b/Doc/lib/libqueue.tex index f1d892a..95ad47f 100644 --- a/Doc/lib/libqueue.tex +++ b/Doc/lib/libqueue.tex @@ -1,3 +1,4 @@ + \section{\module{Queue} --- A synchronized queue class} @@ -94,3 +95,51 @@ immediately available, else raise the \exception{Empty} exception \begin{methoddesc}{get_nowait}{} Equivalent to \code{get(False)}. \end{methoddesc} + +Two methods are offered to support tracking whether enqueued tasks have +been fully processed by daemon consumer threads. + +\begin{methoddesc}{task_done}{} +Indicate that a formerly enqueued task is complete. Used by queue consumer +threads. For each \method{get()} used to fetch a task, a subsequent call to +\method{task_done()} tells the queue that the processing on the task is complete. + +If a \method{join()} is currently blocking, it will resume when all items +have been processed (meaning that a \method{task_done()} call was received +for every item that had been \method{put()} into the queue). + +Raises a \exception{ValueError} if called more times than there were items +placed in the queue. +\versionadded{2.5} +\end{methoddesc} + +\begin{methoddesc}{join}{} +Blocks until all items in the queue have been gotten and processed. + +The count of unfinished tasks goes up whenever an item is added to the +queue. The count goes down whenever a consumer thread calls \method{task_done()} +to indicate that the item was retrieved and all work on it is complete. +When the count of unfinished tasks drops to zero, join() unblocks. +\versionadded{2.5} +\end{methoddesc} + +Example of how to wait for enqueued tasks to be completed: + +\begin{verbatim} + def worker(): + while True: + item = q.get() + do_work(item) + q.task_done() + + q = Queue() + for i in range(num_worker_threads): + t = Thread(target=worker) + t.setDaemon(True) + t.start() + + for item in source(): + q.put(item) + + q.join() # block until all tasks are done +\end{verbatim} diff --git a/Doc/lib/libre.tex b/Doc/lib/libre.tex index 8e6513a..1404e09 100644 --- a/Doc/lib/libre.tex +++ b/Doc/lib/libre.tex @@ -566,9 +566,6 @@ ignored. >>> re.split('\W+', 'Words, words, words.', 1) ['Words', 'words, words.'] \end{verbatim} - - This function combines and extends the functionality of - the old \function{regsub.split()} and \function{regsub.splitx()}. \end{funcdesc} \begin{funcdesc}{findall}{pattern, string\optional{, flags}} @@ -934,7 +931,7 @@ The equivalent regular expression would be \leftline{\strong{Avoiding recursion}} If you create regular expressions that require the engine to perform a -lot of recursion, you may encounter a RuntimeError exception with +lot of recursion, you may encounter a \exception{RuntimeError} exception with the message \code{maximum recursion limit} exceeded. For example, \begin{verbatim} @@ -943,7 +940,7 @@ the message \code{maximum recursion limit} exceeded. For example, >>> re.match('Begin (\w| )*? end', s).end() Traceback (most recent call last): File "<stdin>", line 1, in ? - File "/usr/local/lib/python2.3/sre.py", line 132, in match + File "/usr/local/lib/python2.5/re.py", line 132, in match return _compile(pattern, flags).match(string) RuntimeError: maximum recursion limit exceeded \end{verbatim} diff --git a/Doc/lib/libreconvert.tex b/Doc/lib/libreconvert.tex deleted file mode 100644 index 29c6e52..0000000 --- a/Doc/lib/libreconvert.tex +++ /dev/null @@ -1,80 +0,0 @@ -\section{\module{reconvert} --- - Convert regular expressions from regex to re form} -\declaremodule{standard}{reconvert} -\moduleauthor{Andrew M. Kuchling}{amk@amk.ca} -\sectionauthor{Skip Montanaro}{skip@pobox.com} - - -\modulesynopsis{Convert regex-, emacs- or sed-style regular expressions -to re-style syntax.} - - -This module provides a facility to convert regular expressions from the -syntax used by the deprecated \module{regex} module to those used by the -newer \module{re} module. Because of similarity between the regular -expression syntax of \code{sed(1)} and \code{emacs(1)} and the -\module{regex} module, it is also helpful to convert patterns written for -those tools to \module{re} patterns. - -When used as a script, a Python string literal (or any other expression -evaluating to a string) is read from stdin, and the translated expression is -written to stdout as a string literal. Unless stdout is a tty, no trailing -newline is written to stdout. This is done so that it can be used with -Emacs \code{C-U M-|} (shell-command-on-region) which filters the region -through the shell command. - -\begin{seealso} - \seetitle{Mastering Regular Expressions}{Book on regular expressions - by Jeffrey Friedl, published by O'Reilly. The second - edition of the book no longer covers Python at all, - but the first edition covered writing good regular expression - patterns in great detail.} -\end{seealso} - -\subsection{Module Contents} -\nodename{Contents of Module reconvert} - -The module defines two functions and a handful of constants. - -\begin{funcdesc}{convert}{pattern\optional{, syntax=None}} - Convert a \var{pattern} representing a \module{regex}-stype regular - expression into a \module{re}-style regular expression. The optional - \var{syntax} parameter is a bitwise-or'd set of flags that control what - constructs are converted. See below for a description of the various - constants. -\end{funcdesc} - -\begin{funcdesc}{quote}{s\optional{, quote=None}} - Convert a string object to a quoted string literal. - - This is similar to \function{repr} but will return a "raw" string (r'...' - or r"...") when the string contains backslashes, instead of doubling all - backslashes. The resulting string does not always evaluate to the same - string as the original; however it will do just the right thing when passed - into re.compile(). - - The optional second argument forces the string quote; it must be a single - character which is a valid Python string quote. Note that prior to Python - 2.5 this would not accept triple-quoted string delimiters. -\end{funcdesc} - -\begin{datadesc}{RE_NO_BK_PARENS} - Suppress paren conversion. This should be omitted when converting - \code{sed}-style or \code{emacs}-style regular expressions. -\end{datadesc} - -\begin{datadesc}{RE_NO_BK_VBAR} - Suppress vertical bar conversion. This should be omitted when converting - \code{sed}-style or \code{emacs}-style regular expressions. -\end{datadesc} - -\begin{datadesc}{RE_BK_PLUS_QM} - Enable conversion of \code{+} and \code{?} characters. This should be - added to the \var{syntax} arg of \function{convert} when converting - \code{sed}-style regular expressions and omitted when converting - \code{emacs}-style regular expressions. -\end{datadesc} - -\begin{datadesc}{RE_NEWLINE_OR} - When set, newline characters are replaced by \code{|}. -\end{datadesc} diff --git a/Doc/lib/libregex.tex b/Doc/lib/libregex.tex deleted file mode 100644 index 0982f81..0000000 --- a/Doc/lib/libregex.tex +++ /dev/null @@ -1,370 +0,0 @@ -\section{\module{regex} --- - Regular expression operations} -\declaremodule{builtin}{regex} - -\modulesynopsis{Regular expression search and match operations. - \strong{Obsolete!}} - - -This module provides regular expression matching operations similar to -those found in Emacs. - -\strong{Obsolescence note:} -This module is obsolete as of Python version 1.5; it is still being -maintained because much existing code still uses it. All new code in -need of regular expressions should use the new -\code{re}\refstmodindex{re} module, which supports the more powerful -and regular Perl-style regular expressions. Existing code should be -converted. The standard library module -\code{reconvert}\refstmodindex{reconvert} helps in converting -\code{regex} style regular expressions to \code{re}\refstmodindex{re} -style regular expressions. (For more conversion help, see Andrew -Kuchling's\index{Kuchling, Andrew} ``\module{regex-to-re} HOWTO'' at -\url{http://www.python.org/doc/howto/regex-to-re/}.) - -By default the patterns are Emacs-style regular expressions -(with one exception). There is -a way to change the syntax to match that of several well-known -\UNIX{} utilities. The exception is that Emacs' \samp{\e s} -pattern is not supported, since the original implementation references -the Emacs syntax tables. - -This module is 8-bit clean: both patterns and strings may contain null -bytes and characters whose high bit is set. - -\strong{Please note:} There is a little-known fact about Python string -literals which means that you don't usually have to worry about -doubling backslashes, even though they are used to escape special -characters in string literals as well as in regular expressions. This -is because Python doesn't remove backslashes from string literals if -they are followed by an unrecognized escape character. -\emph{However}, if you want to include a literal \dfn{backslash} in a -regular expression represented as a string literal, you have to -\emph{quadruple} it or enclose it in a singleton character class. -E.g.\ to extract \LaTeX\ \samp{\e section\{\textrm{\ldots}\}} headers -from a document, you can use this pattern: -\code{'[\e ]section\{\e (.*\e )\}'}. \emph{Another exception:} -the escape sequence \samp{\e b} is significant in string literals -(where it means the ASCII bell character) as well as in Emacs regular -expressions (where it stands for a word boundary), so in order to -search for a word boundary, you should use the pattern \code{'\e \e b'}. -Similarly, a backslash followed by a digit 0-7 should be doubled to -avoid interpretation as an octal escape. - -\subsection{Regular Expressions} - -A regular expression (or RE) specifies a set of strings that matches -it; the functions in this module let you check if a particular string -matches a given regular expression (or if a given regular expression -matches a particular string, which comes down to the same thing). - -Regular expressions can be concatenated to form new regular -expressions; if \emph{A} and \emph{B} are both regular expressions, -then \emph{AB} is also an regular expression. If a string \emph{p} -matches A and another string \emph{q} matches B, the string \emph{pq} -will match AB. Thus, complex expressions can easily be constructed -from simpler ones like the primitives described here. For details of -the theory and implementation of regular expressions, consult almost -any textbook about compiler construction. - -% XXX The reference could be made more specific, say to -% "Compilers: Principles, Techniques and Tools", by Alfred V. Aho, -% Ravi Sethi, and Jeffrey D. Ullman, or some FA text. - -A brief explanation of the format of regular expressions follows. - -Regular expressions can contain both special and ordinary characters. -Ordinary characters, like '\code{A}', '\code{a}', or '\code{0}', are -the simplest regular expressions; they simply match themselves. You -can concatenate ordinary characters, so '\code{last}' matches the -characters 'last'. (In the rest of this section, we'll write RE's in -\code{this special font}, usually without quotes, and strings to be -matched 'in single quotes'.) - -Special characters either stand for classes of ordinary characters, or -affect how the regular expressions around them are interpreted. - -The special characters are: -\begin{itemize} -\item[\code{.}] (Dot.) Matches any character except a newline. -\item[\code{\^}] (Caret.) Matches the start of the string. -\item[\code{\$}] Matches the end of the string. -\code{foo} matches both 'foo' and 'foobar', while the regular -expression '\code{foo\$}' matches only 'foo'. -\item[\code{*}] Causes the resulting RE to -match 0 or more repetitions of the preceding RE. \code{ab*} will -match 'a', 'ab', or 'a' followed by any number of 'b's. -\item[\code{+}] Causes the -resulting RE to match 1 or more repetitions of the preceding RE. -\code{ab+} will match 'a' followed by any non-zero number of 'b's; it -will not match just 'a'. -\item[\code{?}] Causes the resulting RE to -match 0 or 1 repetitions of the preceding RE. \code{ab?} will -match either 'a' or 'ab'. - -\item[\code{\e}] Either escapes special characters (permitting you to match -characters like '*?+\&\$'), or signals a special sequence; special -sequences are discussed below. Remember that Python also uses the -backslash as an escape sequence in string literals; if the escape -sequence isn't recognized by Python's parser, the backslash and -subsequent character are included in the resulting string. However, -if Python would recognize the resulting sequence, the backslash should -be repeated twice. - -\item[\code{[]}] Used to indicate a set of characters. Characters can -be listed individually, or a range is indicated by giving two -characters and separating them by a '-'. Special characters are -not active inside sets. For example, \code{[akm\$]} -will match any of the characters 'a', 'k', 'm', or '\$'; \code{[a-z]} will -match any lowercase letter. - -If you want to include a \code{]} inside a -set, it must be the first character of the set; to include a \code{-}, -place it as the first or last character. - -Characters \emph{not} within a range can be matched by including a -\code{\^} as the first character of the set; \code{\^} elsewhere will -simply match the '\code{\^}' character. -\end{itemize} - -The special sequences consist of '\code{\e}' and a character -from the list below. If the ordinary character is not on the list, -then the resulting RE will match the second character. For example, -\code{\e\$} matches the character '\$'. Ones where the backslash -should be doubled in string literals are indicated. - -\begin{itemize} -\item[\code{\e|}]\code{A\e|B}, where A and B can be arbitrary REs, -creates a regular expression that will match either A or B. This can -be used inside groups (see below) as well. -% -\item[\code{\e( \e)}] Indicates the start and end of a group; the -contents of a group can be matched later in the string with the -\code{\e [1-9]} special sequence, described next. -\end{itemize} - -\begin{fulllineitems} -\item[\code{\e \e 1, ... \e \e 7, \e 8, \e 9}] -Matches the contents of the group of the same -number. For example, \code{\e (.+\e ) \e \e 1} matches 'the the' or -'55 55', but not 'the end' (note the space after the group). This -special sequence can only be used to match one of the first 9 groups; -groups with higher numbers can be matched using the \code{\e v} -sequence. (\code{\e 8} and \code{\e 9} don't need a double backslash -because they are not octal digits.) -\end{fulllineitems} - -\begin{itemize} -\item[\code{\e \e b}] Matches the empty string, but only at the -beginning or end of a word. A word is defined as a sequence of -alphanumeric characters, so the end of a word is indicated by -whitespace or a non-alphanumeric character. -% -\item[\code{\e B}] Matches the empty string, but when it is \emph{not} at the -beginning or end of a word. -% -\item[\code{\e v}] Must be followed by a two digit decimal number, and -matches the contents of the group of the same number. The group -number must be between 1 and 99, inclusive. -% -\item[\code{\e w}]Matches any alphanumeric character; this is -equivalent to the set \code{[a-zA-Z0-9]}. -% -\item[\code{\e W}] Matches any non-alphanumeric character; this is -equivalent to the set \code{[\^a-zA-Z0-9]}. -\item[\code{\e <}] Matches the empty string, but only at the beginning of a -word. A word is defined as a sequence of alphanumeric characters, so -the end of a word is indicated by whitespace or a non-alphanumeric -character. -\item[\code{\e >}] Matches the empty string, but only at the end of a -word. - -\item[\code{\e \e \e \e}] Matches a literal backslash. - -% In Emacs, the following two are start of buffer/end of buffer. In -% Python they seem to be synonyms for ^$. -\item[\code{\e `}] Like \code{\^}, this only matches at the start of the -string. -\item[\code{\e \e '}] Like \code{\$}, this only matches at the end of -the string. -% end of buffer -\end{itemize} - -\subsection{Module Contents} -\nodename{Contents of Module regex} - -The module defines these functions, and an exception: - - -\begin{funcdesc}{match}{pattern, string} - Return how many characters at the beginning of \var{string} match - the regular expression \var{pattern}. Return \code{-1} if the - string does not match the pattern (this is different from a - zero-length match!). -\end{funcdesc} - -\begin{funcdesc}{search}{pattern, string} - Return the first position in \var{string} that matches the regular - expression \var{pattern}. Return \code{-1} if no position in the string - matches the pattern (this is different from a zero-length match - anywhere!). -\end{funcdesc} - -\begin{funcdesc}{compile}{pattern\optional{, translate}} - Compile a regular expression pattern into a regular expression - object, which can be used for matching using its \code{match()} and - \code{search()} methods, described below. The optional argument - \var{translate}, if present, must be a 256-character string - indicating how characters (both of the pattern and of the strings to - be matched) are translated before comparing them; the \var{i}-th - element of the string gives the translation for the character with - \ASCII{} code \var{i}. This can be used to implement - case-insensitive matching; see the \code{casefold} data item below. - - The sequence - -\begin{verbatim} -prog = regex.compile(pat) -result = prog.match(str) -\end{verbatim} -% -is equivalent to - -\begin{verbatim} -result = regex.match(pat, str) -\end{verbatim} - -but the version using \code{compile()} is more efficient when multiple -regular expressions are used concurrently in a single program. (The -compiled version of the last pattern passed to \code{regex.match()} or -\code{regex.search()} is cached, so programs that use only a single -regular expression at a time needn't worry about compiling regular -expressions.) -\end{funcdesc} - -\begin{funcdesc}{set_syntax}{flags} - Set the syntax to be used by future calls to \code{compile()}, - \code{match()} and \code{search()}. (Already compiled expression - objects are not affected.) The argument is an integer which is the - OR of several flag bits. The return value is the previous value of - the syntax flags. Names for the flags are defined in the standard - module \code{regex_syntax}\refstmodindex{regex_syntax}; read the - file \file{regex_syntax.py} for more information. -\end{funcdesc} - -\begin{funcdesc}{get_syntax}{} - Returns the current value of the syntax flags as an integer. -\end{funcdesc} - -\begin{funcdesc}{symcomp}{pattern\optional{, translate}} -This is like \code{compile()}, but supports symbolic group names: if a -parenthesis-enclosed group begins with a group name in angular -brackets, e.g. \code{'\e(<id>[a-z][a-z0-9]*\e)'}, the group can -be referenced by its name in arguments to the \code{group()} method of -the resulting compiled regular expression object, like this: -\code{p.group('id')}. Group names may contain alphanumeric characters -and \code{'_'} only. -\end{funcdesc} - -\begin{excdesc}{error} - Exception raised when a string passed to one of the functions here - is not a valid regular expression (e.g., unmatched parentheses) or - when some other error occurs during compilation or matching. (It is - never an error if a string contains no match for a pattern.) -\end{excdesc} - -\begin{datadesc}{casefold} -A string suitable to pass as the \var{translate} argument to -\code{compile()} to map all upper case characters to their lowercase -equivalents. -\end{datadesc} - -\noindent -Compiled regular expression objects support these methods: - -\setindexsubitem{(regex method)} -\begin{funcdesc}{match}{string\optional{, pos}} - Return how many characters at the beginning of \var{string} match - the compiled regular expression. Return \code{-1} if the string - does not match the pattern (this is different from a zero-length - match!). - - The optional second parameter, \var{pos}, gives an index in the string - where the search is to start; it defaults to \code{0}. This is not - completely equivalent to slicing the string; the \code{'\^'} pattern - character matches at the real beginning of the string and at positions - just after a newline, not necessarily at the index where the search - is to start. -\end{funcdesc} - -\begin{funcdesc}{search}{string\optional{, pos}} - Return the first position in \var{string} that matches the regular - expression \code{pattern}. Return \code{-1} if no position in the - string matches the pattern (this is different from a zero-length - match anywhere!). - - The optional second parameter has the same meaning as for the - \code{match()} method. -\end{funcdesc} - -\begin{funcdesc}{group}{index, index, ...} -This method is only valid when the last call to the \code{match()} -or \code{search()} method found a match. It returns one or more -groups of the match. If there is a single \var{index} argument, -the result is a single string; if there are multiple arguments, the -result is a tuple with one item per argument. If the \var{index} is -zero, the corresponding return value is the entire matching string; if -it is in the inclusive range [1..99], it is the string matching the -corresponding parenthesized group (using the default syntax, -groups are parenthesized using \code{{\e}(} and \code{{\e})}). If no -such group exists, the corresponding result is \code{None}. - -If the regular expression was compiled by \code{symcomp()} instead of -\code{compile()}, the \var{index} arguments may also be strings -identifying groups by their group name. -\end{funcdesc} - -\noindent -Compiled regular expressions support these data attributes: - -\setindexsubitem{(regex attribute)} - -\begin{datadesc}{regs} -When the last call to the \code{match()} or \code{search()} method found a -match, this is a tuple of pairs of indexes corresponding to the -beginning and end of all parenthesized groups in the pattern. Indices -are relative to the string argument passed to \code{match()} or -\code{search()}. The 0-th tuple gives the beginning and end or the -whole pattern. When the last match or search failed, this is -\code{None}. -\end{datadesc} - -\begin{datadesc}{last} -When the last call to the \code{match()} or \code{search()} method found a -match, this is the string argument passed to that method. When the -last match or search failed, this is \code{None}. -\end{datadesc} - -\begin{datadesc}{translate} -This is the value of the \var{translate} argument to -\code{regex.compile()} that created this regular expression object. If -the \var{translate} argument was omitted in the \code{regex.compile()} -call, this is \code{None}. -\end{datadesc} - -\begin{datadesc}{givenpat} -The regular expression pattern as passed to \code{compile()} or -\code{symcomp()}. -\end{datadesc} - -\begin{datadesc}{realpat} -The regular expression after stripping the group names for regular -expressions compiled with \code{symcomp()}. Same as \code{givenpat} -otherwise. -\end{datadesc} - -\begin{datadesc}{groupindex} -A dictionary giving the mapping from symbolic group names to numerical -group indexes for regular expressions compiled with \code{symcomp()}. -\code{None} otherwise. -\end{datadesc} diff --git a/Doc/lib/libregsub.tex b/Doc/lib/libregsub.tex deleted file mode 100644 index b41b700..0000000 --- a/Doc/lib/libregsub.tex +++ /dev/null @@ -1,74 +0,0 @@ -\section{\module{regsub} --- - String operations using regular expressions} - -\declaremodule{standard}{regsub} -\modulesynopsis{Substitution and splitting operations that use - regular expressions. \strong{Obsolete!}} - - -This module defines a number of functions useful for working with -regular expressions (see built-in module \refmodule{regex}). - -Warning: these functions are not thread-safe. - -\strong{Obsolescence note:} -This module is obsolete as of Python version 1.5; it is still being -maintained because much existing code still uses it. All new code in -need of regular expressions should use the new \refmodule{re} module, which -supports the more powerful and regular Perl-style regular expressions. -Existing code should be converted. The standard library module -\module{reconvert} helps in converting \refmodule{regex} style regular -expressions to \refmodule{re} style regular expressions. (For more -conversion help, see Andrew Kuchling's\index{Kuchling, Andrew} -``regex-to-re HOWTO'' at -\url{http://www.python.org/doc/howto/regex-to-re/}.) - - -\begin{funcdesc}{sub}{pat, repl, str} -Replace the first occurrence of pattern \var{pat} in string -\var{str} by replacement \var{repl}. If the pattern isn't found, -the string is returned unchanged. The pattern may be a string or an -already compiled pattern. The replacement may contain references -\samp{\e \var{digit}} to subpatterns and escaped backslashes. -\end{funcdesc} - -\begin{funcdesc}{gsub}{pat, repl, str} -Replace all (non-overlapping) occurrences of pattern \var{pat} in -string \var{str} by replacement \var{repl}. The same rules as for -\code{sub()} apply. Empty matches for the pattern are replaced only -when not adjacent to a previous match, so e.g. -\code{gsub('', '-', 'abc')} returns \code{'-a-b-c-'}. -\end{funcdesc} - -\begin{funcdesc}{split}{str, pat\optional{, maxsplit}} -Split the string \var{str} in fields separated by delimiters matching -the pattern \var{pat}, and return a list containing the fields. Only -non-empty matches for the pattern are considered, so e.g. -\code{split('a:b', ':*')} returns \code{['a', 'b']} and -\code{split('abc', '')} returns \code{['abc']}. The \var{maxsplit} -defaults to 0. If it is nonzero, only \var{maxsplit} number of splits -occur, and the remainder of the string is returned as the final -element of the list. -\end{funcdesc} - -\begin{funcdesc}{splitx}{str, pat\optional{, maxsplit}} -Split the string \var{str} in fields separated by delimiters matching -the pattern \var{pat}, and return a list containing the fields as well -as the separators. For example, \code{splitx('a:::b', ':*')} returns -\code{['a', ':::', 'b']}. Otherwise, this function behaves the same -as \code{split}. -\end{funcdesc} - -\begin{funcdesc}{capwords}{s\optional{, pat}} -Capitalize words separated by optional pattern \var{pat}. The default -pattern uses any characters except letters, digits and underscores as -word delimiters. Capitalization is done by changing the first -character of each word to upper case. -\end{funcdesc} - -\begin{funcdesc}{clear_cache}{} -The regsub module maintains a cache of compiled regular expressions, -keyed on the regular expression string and the syntax of the regex -module at the time the expression was compiled. This function clears -that cache. -\end{funcdesc} diff --git a/Doc/lib/librunpy.tex b/Doc/lib/librunpy.tex new file mode 100644 index 0000000..4be9901 --- /dev/null +++ b/Doc/lib/librunpy.tex @@ -0,0 +1,74 @@ +\section{\module{runpy} --- + Locating and executing Python modules.} + +\declaremodule{standard}{runpy} % standard library, in Python + +\moduleauthor{Nick Coghlan}{ncoghlan@gmail.com} + +\modulesynopsis{Locate and execute Python modules as scripts} + +\versionadded{2.5} + +The \module{runpy} module is used to locate and run Python modules +without importing them first. It's main use is to implement the +\programopt{-m} command line switch that allows scripts to be located +using the Python module namespace rather than the filesystem. + +When executed as a script, the module effectively operates as follows: +\begin{verbatim} + del sys.argv[0] # Remove the runpy module from the arguments + run_module(sys.argv[0], run_name="__main__", alter_sys=True) +\end{verbatim} + +The \module{runpy} module provides a single function: + +\begin{funcdesc}{run_module}{mod_name\optional{, init_globals} +\optional{, run_name}\optional{, alter_sys}} +Execute the code of the specified module and return the resulting +module globals dictionary. The module's code is first located using +the standard import mechanism (refer to PEP 302 for details) and +then executed in a fresh module namespace. + +The optional dictionary argument \var{init_globals} may be used to +pre-populate the globals dictionary before the code is executed. +The supplied dictionary will not be modified. If any of the special +global variables below are defined in the supplied dictionary, those +definitions are overridden by the \code{run_module} function. + +The special global variables \code{__name__}, \code{__file__}, +\code{__loader__} and \code{__builtins__} are set in the globals +dictionary before the module code is executed. + +\code{__name__} is set to \var{run_name} if this optional argument is +supplied, and the \var{mod_name} argument otherwise. + +\code{__loader__} is set to the PEP 302 module loader used to retrieve +the code for the module (This loader may be a wrapper around the +standard import mechanism). + +\code{__file__} is set to the name provided by the module loader. If +the loader does not make filename information available, this +variable is set to \code{None}. + +\code{__builtins__} is automatically initialised with a reference to +the top level namespace of the \module{__builtin__} module. + +If the argument \var{alter_sys} is supplied and evaluates to +\code{True}, then \code{sys.argv[0]} is updated with the value of +\code{__file__} and \code{sys.modules[__name__]} is updated with a +temporary module object for the module being executed. Both +\code{sys.argv[0]} and \code{sys.modules[__name__]} are restored to +their original values before the function returns. + +Note that this manipulation of \module{sys} is not thread-safe. Other +threads may see the partially initialised module, as well as the +altered list of arguments. It is recommended that the \module{sys} +module be left alone when invoking this function from threaded code. +\end{funcdesc} + +\begin{seealso} + +\seepep{338}{Executing modules as scripts}{PEP written and +implemented by Nick Coghlan.} + +\end{seealso} diff --git a/Doc/lib/libsets.tex b/Doc/lib/libsets.tex index dd85ec7..22bf34b 100644 --- a/Doc/lib/libsets.tex +++ b/Doc/lib/libsets.tex @@ -151,12 +151,13 @@ but not found in \class{ImmutableSet}: \lineiii{\var{s}.add(\var{x})}{} {add element \var{x} to set \var{s}} \lineiii{\var{s}.remove(\var{x})}{} - {remove \var{x} from set \var{s}; raises KeyError if not present} + {remove \var{x} from set \var{s}; raises \exception{KeyError} + if not present} \lineiii{\var{s}.discard(\var{x})}{} {removes \var{x} from set \var{s} if present} \lineiii{\var{s}.pop()}{} {remove and return an arbitrary element from \var{s}; raises - KeyError if empty} + \exception{KeyError} if empty} \lineiii{\var{s}.clear()}{} {remove all elements from set \var{s}} \end{tableiii} diff --git a/Doc/lib/libsgmllib.tex b/Doc/lib/libsgmllib.tex index 27bf0b0..1578313 100644 --- a/Doc/lib/libsgmllib.tex +++ b/Doc/lib/libsgmllib.tex @@ -95,12 +95,22 @@ lower case, and the \var{method} argument is the bound method which should be used to support semantic interpretation of the start tag. The \var{attributes} argument is a list of \code{(\var{name}, \var{value})} pairs containing the attributes found inside the tag's -\code{<>} brackets. The \var{name} has been translated to lower case -and double quotes and backslashes in the \var{value} have been interpreted. +\code{<>} brackets. + +The \var{name} has been translated to lower case. +Double quotes and backslashes in the \var{value} have been interpreted, +as well as known character references and known entity references +terminated by a semicolon (normally, entity references can be terminated +by any non-alphanumerical character, but this would break the very +common case of \code{<A HREF="url?spam=1\&eggs=2">} when \code{eggs} +is a valid entity name). + For instance, for the tag \code{<A HREF="http://www.cwi.nl/">}, this method would be called as \samp{unknown_starttag('a', [('href', 'http://www.cwi.nl/')])}. The base implementation simply calls \var{method} with \var{attributes} as the only argument. +\versionadded[Handling of entity and character references within + attribute values]{2.5} \end{methoddesc} \begin{methoddesc}{handle_endtag}{tag, method} diff --git a/Doc/lib/libshutil.tex b/Doc/lib/libshutil.tex index a217150..449d741 100644 --- a/Doc/lib/libshutil.tex +++ b/Doc/lib/libshutil.tex @@ -73,18 +73,18 @@ file type and creator codes will not be correct. If \var{symlinks} is true, symbolic links in the source tree are represented as symbolic links in the new tree; if false or omitted, the contents of the linked files are copied to - the new tree. If exception(s) occur, an Error is raised + the new tree. If exception(s) occur, an \exception{Error} is raised with a list of reasons. The source code for this should be considered an example rather than a tool. - \versionchanged[Error is raised if any exceptions occur during copying, - rather than printing a message]{2.3} + \versionchanged[\exception{Error} is raised if any exceptions occur during + copying, rather than printing a message]{2.3} \versionchanged[Create intermediate directories needed to create \var{dst}, - rather than raising an error. Copy permissions and times of directories using - \function{copystat()}]{2.5} + rather than raising an error. Copy permissions and times of + directories using \function{copystat()}]{2.5} \end{funcdesc} diff --git a/Doc/lib/libsignal.tex b/Doc/lib/libsignal.tex index f168b6d..cfdb4dd 100644 --- a/Doc/lib/libsignal.tex +++ b/Doc/lib/libsignal.tex @@ -100,7 +100,7 @@ The \module{signal} module defines the following functions: Any previously scheduled alarm is canceled (only one alarm can be scheduled at any time). The returned value is then the number of seconds before any previously set alarm was to have been delivered. - If \var{time} is zero, no alarm id scheduled, and any scheduled + If \var{time} is zero, no alarm is scheduled, and any scheduled alarm is canceled. The return value is the number of seconds remaining before a previously scheduled alarm. If the return value is zero, no alarm is currently scheduled. (See the \UNIX{} man page diff --git a/Doc/lib/libsocket.tex b/Doc/lib/libsocket.tex index cc7bd75..c7b656d 100644 --- a/Doc/lib/libsocket.tex +++ b/Doc/lib/libsocket.tex @@ -317,10 +317,11 @@ Availability: \UNIX. \versionadded{2.4} \end{funcdesc} \begin{funcdesc}{fromfd}{fd, family, type\optional{, proto}} -Build a socket object from an existing file descriptor (an integer as -returned by a file object's \method{fileno()} method). Address family, -socket type and protocol number are as for the \function{socket()} function -above. The file descriptor should refer to a socket, but this is not +Duplicate the file descriptor \var{fd} (an integer as returned by a file +object's \method{fileno()} method) and build a socket object from the +result. Address family, socket type and protocol number are as for the +\function{socket()} function above. +The file descriptor should refer to a socket, but this is not checked --- subsequent operations on the object may fail if the file descriptor is invalid. This function is rarely needed, but can be used to get or set socket options on a socket passed to a program as @@ -626,7 +627,7 @@ timeouts on socket operations. \end{methoddesc} \begin{methoddesc}[socket]{gettimeout}{} -Returns the timeout in floating seconds associated with socket +Return the timeout in floating seconds associated with socket operations, or \code{None} if no timeout is set. This reflects the last call to \method{setblocking()} or \method{settimeout()}. \versionadded{2.3} @@ -677,6 +678,25 @@ use \method{recv()} and \method{send()} without \var{flags} argument instead. +Socket objects also have these (read-only) attributes that correspond +to the values given to the \class{socket} constructor. + +\begin{memberdesc}[socket]{family} +The socket family. +\versionadded{2.5} +\end{memberdesc} + +\begin{memberdesc}[socket]{type} +The socket type. +\versionadded{2.5} +\end{memberdesc} + +\begin{memberdesc}[socket]{proto} +The socket protocol. +\versionadded{2.5} +\end{memberdesc} + + \subsection{SSL Objects \label{ssl-objects}} SSL objects have the following methods. diff --git a/Doc/lib/libstdtypes.tex b/Doc/lib/libstdtypes.tex index d2a0425..8d011fd 100644 --- a/Doc/lib/libstdtypes.tex +++ b/Doc/lib/libstdtypes.tex @@ -185,10 +185,12 @@ There are four distinct numeric types: \dfn{plain integers}, In addition, Booleans are a subtype of plain integers. Plain integers (also just called \dfn{integers}) are implemented using \ctype{long} in C, which gives them at least 32 -bits of precision. Long integers have unlimited precision. Floating -point numbers are implemented using \ctype{double} in C. All bets on -their precision are off unless you happen to know the machine you are -working with. +bits of precision (\code{sys.maxint} is always set to the maximum +plain integer value for the current platform, the minimum value is +\code{-sys.maxint - 1}). Long integers have unlimited precision. +Floating point numbers are implemented using \ctype{double} in C. +All bets on their precision are off unless you happen to know the +machine you are working with. \obindex{numeric} \obindex{Boolean} \obindex{integer} @@ -249,6 +251,7 @@ comparison operations): \hline \lineiii{\var{x} * \var{y}}{product of \var{x} and \var{y}}{} \lineiii{\var{x} / \var{y}}{quotient of \var{x} and \var{y}}{(1)} + \lineiii{\var{x} // \var{y}}{(floored) quotient of \var{x} and \var{y}}{(5)} \lineiii{\var{x} \%{} \var{y}}{remainder of \code{\var{x} / \var{y}}}{(4)} \hline \lineiii{-\var{x}}{\var{x} negated}{} @@ -299,6 +302,9 @@ Complex floor division operator, modulo operator, and \function{divmod()}. \deprecated{2.3}{Instead convert to float using \function{abs()} if appropriate.} +\item[(5)] +Also referred to as integer division. The resultant value is a whole integer, +though the result's type is not necessarily int. \end{description} % XXXJH exceptions: overflow (when? what operations?) zerodivision @@ -1278,7 +1284,8 @@ that do not apply to immutable instances of \class{frozenset}: \lineiii{\var{s}.add(\var{x})}{} {add element \var{x} to set \var{s}} \lineiii{\var{s}.remove(\var{x})}{} - {remove \var{x} from set \var{s}; raises KeyError if not present} + {remove \var{x} from set \var{s}; raises \exception{KeyError} + if not present} \lineiii{\var{s}.discard(\var{x})}{} {removes \var{x} from set \var{s} if present} \lineiii{\var{s}.pop()}{} @@ -1495,6 +1502,38 @@ Files have the following methods: Any operation which requires that the file be open will raise a \exception{ValueError} after the file has been closed. Calling \method{close()} more than once is allowed. + + As of Python 2.5, you can avoid having to call this method explicitly + if you use the \keyword{with} statement. For example, the following + code will automatically close \code{f} when the \keyword{with} block + is exited: + +\begin{verbatim} +from __future__ import with_statement + +with open("hello.txt") as f: + for line in f: + print line +\end{verbatim} + + In older versions of Python, you would have needed to do this to get + the same effect: + +\begin{verbatim} +f = open("hello.txt") +try: + for line in f: + print line +finally: + f.close() +\end{verbatim} + + \note{Not all ``file-like'' types in Python support use as a context + manager for the \keyword{with} statement. If your code is intended to + work with any file-like object, you can use the \function{closing()} + function in the \module{contextlib} module instead of using the object + directly. See section~\ref{context-closing} for details.} + \end{methoddesc} \begin{methoddesc}[file]{flush}{} @@ -1783,14 +1822,14 @@ class, respectively. When a method is unbound, its \code{im_self} attribute will be \code{None} and if called, an explicit \code{self} object must be passed as the first argument. In this case, \code{self} must be an instance of the unbound method's class (or a -subclass of that class), otherwise a \code{TypeError} is raised. +subclass of that class), otherwise a \exception{TypeError} is raised. Like function objects, methods objects support getting arbitrary attributes. However, since method attributes are actually stored on the underlying function object (\code{meth.im_func}), setting method attributes on either bound or unbound methods is disallowed. Attempting to set a method attribute results in a -\code{TypeError} being raised. In order to set a method attribute, +\exception{TypeError} being raised. In order to set a method attribute, you need to explicitly set it on the underlying function object: \begin{verbatim} diff --git a/Doc/lib/libsubprocess.tex b/Doc/lib/libsubprocess.tex index f48b29b..4417797 100644 --- a/Doc/lib/libsubprocess.tex +++ b/Doc/lib/libsubprocess.tex @@ -135,8 +135,8 @@ The arguments are the same as for the Popen constructor. Example: \begin{funcdesc}{check_call}{*popenargs, **kwargs} Run command with arguments. Wait for command to complete. If the exit -code was zero then return, otherwise raise CalledProcessError. The -CalledProcessError object will have the return code in the +code was zero then return, otherwise raise \exception{CalledProcessError.} +The \exception{CalledProcessError} object will have the return code in the \member{errno} attribute. The arguments are the same as for the Popen constructor. Example: diff --git a/Doc/lib/libthread.tex b/Doc/lib/libthread.tex index 4914948d..9e0c202 100644 --- a/Doc/lib/libthread.tex +++ b/Doc/lib/libthread.tex @@ -100,6 +100,19 @@ Return the status of the lock:\ \code{True} if it has been acquired by some thread, \code{False} if not. \end{methoddesc} +In addition to these methods, lock objects can also be used via the +\keyword{with} statement, e.g.: + +\begin{verbatim} +from __future__ import with_statement +import thread + +a_lock = thread.allocate_lock() + +with a_lock: + print "a_lock is locked while this executes" +\end{verbatim} + \strong{Caveats:} \begin{itemize} diff --git a/Doc/lib/libthreading.tex b/Doc/lib/libthreading.tex index 33839a4..8fb3137 100644 --- a/Doc/lib/libthreading.tex +++ b/Doc/lib/libthreading.tex @@ -675,3 +675,26 @@ keyword arguments \var{kwargs}, after \var{interval} seconds have passed. Stop the timer, and cancel the execution of the timer's action. This will only work if the timer is still in its waiting stage. \end{methoddesc} + +\subsection{Using locks, conditions, and semaphores in the \keyword{with} +statement \label{with-locks}} + +All of the objects provided by this module that have \method{acquire()} and +\method{release()} methods can be used as context managers for a \keyword{with} +statement. The \method{acquire()} method will be called when the block is +entered, and \method{release()} will be called when the block is exited. + +Currently, \class{Lock}, \class{RLock}, \class{Condition}, \class{Semaphore}, +and \class{BoundedSemaphore} objects may be used as \keyword{with} +statement context managers. For example: + +\begin{verbatim} +from __future__ import with_statement +import threading + +some_rlock = threading.RLock() + +with some_rlock: + print "some_rlock is locked while this executes" +\end{verbatim} + diff --git a/Doc/lib/libundoc.tex b/Doc/lib/libundoc.tex index 6cef183..df78152 100644 --- a/Doc/lib/libundoc.tex +++ b/Doc/lib/libundoc.tex @@ -42,15 +42,15 @@ document these. \begin{description} \item[\module{ntpath}] --- Implementation of \module{os.path} on Win32, Win64, WinCE, and -OS/2 platforms. + OS/2 platforms. \item[\module{posixpath}] --- Implementation of \module{os.path} on \POSIX. \item[\module{bsddb185}] --- Backwards compatibility module for systems which still use the Berkeley -DB 1.85 module. It is normally only available on certain BSD Unix-based -systems. It should never be used directly. + DB 1.85 module. It is normally only available on certain BSD Unix-based + systems. It should never be used directly. \end{description} @@ -62,14 +62,14 @@ systems. It should never be used directly. \item[\module{linuxaudiodev}] --- Play audio data on the Linux audio device. Replaced in Python 2.3 -by the \module{ossaudiodev} module. + by the \module{ossaudiodev} module. \item[\module{sunaudio}] --- Interpret Sun audio headers (may become obsolete or a tool/demo). \item[\module{toaiff}] --- Convert "arbitrary" sound files to AIFF files; should probably -become a tool or demo. Requires the external program \program{sox}. + become a tool or demo. Requires the external program \program{sox}. \end{description} @@ -78,12 +78,13 @@ become a tool or demo. Requires the external program \program{sox}. These modules are not normally available for import; additional work must be done to make them available. -Those which are written in Python will be installed into the directory -\file{lib-old/} installed as part of the standard library. To use -these, the directory must be added to \code{sys.path}, possibly using -\envvar{PYTHONPATH}. +%%% lib-old is empty as of Python 2.5 +% Those which are written in Python will be installed into the directory +% \file{lib-old/} installed as part of the standard library. To use +% these, the directory must be added to \code{sys.path}, possibly using +% \envvar{PYTHONPATH}. -Obsolete extension modules written in C are not built by default. +These extension modules written in C are not built by default. Under \UNIX, these must be enabled by uncommenting the appropriate lines in \file{Modules/Setup} in the build tree and either rebuilding Python if the modules are statically linked, or building and @@ -92,122 +93,11 @@ installing the shared object if using dynamically-loaded extensions. % XXX need Windows instructions! \begin{description} -\item[\module{addpack}] ---- Alternate approach to packages. Use the built-in package support -instead. - -\item[\module{cmp}] ---- File comparison function. Use the newer \refmodule{filecmp} instead. - -\item[\module{cmpcache}] ---- Caching version of the obsolete \module{cmp} module. Use the -newer \refmodule{filecmp} instead. - -\item[\module{codehack}] ---- Extract function name or line number from a function -code object (these are now accessible as attributes: -\member{co.co_name}, \member{func.func_name}, -\member{co.co_firstlineno}). - -\item[\module{dircmp}] ---- Class to build directory diff tools on (may become a demo or tool). -\deprecated{2.0}{The \refmodule{filecmp} module replaces -\module{dircmp}.} - -\item[\module{dump}] ---- Print python code that reconstructs a variable. - -\item[\module{fmt}] ---- Text formatting abstractions (too slow). - -\item[\module{lockfile}] ---- Wrapper around FCNTL file locking (use -\function{fcntl.lockf()}/\function{flock()} instead; see \refmodule{fcntl}). - -\item[\module{newdir}] ---- New \function{dir()} function (the standard \function{dir()} is -now just as good). - -\item[\module{Para}] ---- Helper for \module{fmt}. - -\item[\module{poly}] ---- Polynomials. - -\item[\module{rand}] ---- Old interface to the random number generator. - -\item[\module{regex}] ---- Emacs-style regular expression support; may still be used in some -old code (extension module). Refer to the -\citetitle[http://www.python.org/doc/1.6/lib/module-regex.html]{Python -1.6 Documentation} for documentation. - -\item[\module{regsub}] ---- Regular expression based string replacement utilities, for use -with \module{regex} (extension module). Refer to the -\citetitle[http://www.python.org/doc/1.6/lib/module-regsub.html]{Python -1.6 Documentation} for documentation. - -\item[\module{statcache}] ---- Caches the results of os.stat(). Using the cache can be fragile -and error-prone, just use \code{os.stat()} directly. - -\item[\module{tb}] ---- Print tracebacks, with a dump of local variables (use -\function{pdb.pm()} or \refmodule{traceback} instead). - \item[\module{timing}] ---- Measure time intervals to high resolution (use -\function{time.clock()} instead). (This is an extension module.) - -\item[\module{tzparse}] ---- Parse a timezone specification (unfinished; may disappear in the -future, and does not work when the \envvar{TZ} environment variable is -not set). - -\item[\module{util}] ---- Useful functions that don't fit elsewhere. - -\item[\module{whatsound}] ---- Recognize sound files; use \refmodule{sndhdr} instead. - -\item[\module{whrandom}] ---- Old random number generator. Use \module{random} instead. - -\item[\module{zmod}] ---- Compute properties of mathematical ``fields.'' +--- Measure time intervals to high resolution (use \function{time.clock()} + instead). \end{description} - -The following modules are obsolete, but are likely to re-surface as -tools or scripts: - -\begin{description} -\item[\module{find}] ---- Find files matching pattern in directory tree. - -\item[\module{grep}] ---- \program{grep} implementation in Python. - -\item[\module{packmail}] ---- Create a self-unpacking \UNIX{} shell archive. -\end{description} - - -The following modules were documented in previous versions of this -manual, but are now considered obsolete. The source for the -documentation is still available as part of the documentation source -archive. - -\begin{description} -\item[\module{ni}] ---- Import modules in ``packages.'' Basic package support is now -built in. The built-in support is very similar to what is provided in -this module. -\end{description} - - \section{SGI-specific Extension modules} The following are SGI specific, and may be out of touch with the @@ -219,5 +109,5 @@ current version of reality. \item[\module{sv}] --- Interface to the ``simple video'' board on SGI Indigo -(obsolete hardware). + (obsolete hardware). \end{description} diff --git a/Doc/lib/liburllib2.tex b/Doc/lib/liburllib2.tex index 706c54b..e0c4568 100644 --- a/Doc/lib/liburllib2.tex +++ b/Doc/lib/liburllib2.tex @@ -384,7 +384,7 @@ determined by sorting the handler instances. \method{\var{protocol}_open()} are called to handle the request. This stage ends when a handler either returns a non-\constant{None} value (ie. a response), or raises an exception - (usually URLError). Exceptions are allowed to propagate. + (usually \exception{URLError}). Exceptions are allowed to propagate. In fact, the above algorithm is first tried for methods named \method{default_open}. If all such methods return diff --git a/Doc/lib/liburlparse.tex b/Doc/lib/liburlparse.tex index 8f80d6b..f18efe9 100644 --- a/Doc/lib/liburlparse.tex +++ b/Doc/lib/liburlparse.tex @@ -23,50 +23,76 @@ draft!). It supports the following URL schemes: \code{file}, \code{ftp}, \code{gopher}, \code{hdl}, \code{http}, \code{https}, \code{imap}, \code{mailto}, \code{mms}, \code{news}, \code{nntp}, \code{prospero}, \code{rsync}, \code{rtsp}, \code{rtspu}, -\code{sftp}, \code{shttp}, \code{sip}, \code{snews}, \code{svn}, +\code{sftp}, \code{shttp}, \code{sip}, \code{sips}, \code{snews}, \code{svn}, \code{svn+ssh}, \code{telnet}, \code{wais}. -\versionadded[Support for the \code{sftp} scheme]{2.5} + +\versionadded[Support for the \code{sftp} and \code{sips} schemes]{2.5} The \module{urlparse} module defines the following functions: -\begin{funcdesc}{urlparse}{urlstring\optional{, default_scheme\optional{, allow_fragments}}} -Parse a URL into 6 components, returning a 6-tuple: (addressing -scheme, network location, path, parameters, query, fragment -identifier). This corresponds to the general structure of a URL: +\begin{funcdesc}{urlparse}{urlstring\optional{, + default_scheme\optional{, allow_fragments}}} +Parse a URL into six components, returning a 6-tuple. This +corresponds to the general structure of a URL: \code{\var{scheme}://\var{netloc}/\var{path};\var{parameters}?\var{query}\#\var{fragment}}. Each tuple item is a string, possibly empty. -The components are not broken up in smaller parts (e.g. the network +The components are not broken up in smaller parts (for example, the network location is a single string), and \% escapes are not expanded. -The delimiters as shown above are not part of the tuple items, +The delimiters as shown above are not part of the result, except for a leading slash in the \var{path} component, which is -retained if present. - -Example: - -\begin{verbatim} -urlparse('http://www.cwi.nl:80/%7Eguido/Python.html') -\end{verbatim} - -yields the tuple +retained if present. For example: \begin{verbatim} +>>> from urlparse import urlparse +>>> o = urlparse('http://www.cwi.nl:80/%7Eguido/Python.html') +>>> o ('http', 'www.cwi.nl:80', '/%7Eguido/Python.html', '', '', '') +>>> o.scheme +'http' +>>> o.port +80 +>>> o.geturl() +'http://www.cwi.nl:80/%7Eguido/Python.html' \end{verbatim} If the \var{default_scheme} argument is specified, it gives the -default addressing scheme, to be used only if the URL string does not +default addressing scheme, to be used only if the URL does not specify one. The default value for this argument is the empty string. -If the \var{allow_fragments} argument is zero, fragment identifiers +If the \var{allow_fragments} argument is false, fragment identifiers are not allowed, even if the URL's addressing scheme normally does -support them. The default value for this argument is \code{1}. +support them. The default value for this argument is \constant{True}. + +The return value is actually an instance of a subclass of +\pytype{tuple}. This class has the following additional read-only +convenience attributes: + +\begin{tableiv}{l|c|l|c}{member}{Attribute}{Index}{Value}{Value if not present} + \lineiv{scheme} {0} {URL scheme specifier} {empty string} + \lineiv{netloc} {1} {Network location part} {empty string} + \lineiv{path} {2} {Hierarchical path} {empty string} + \lineiv{params} {3} {Parameters for last path element} {empty string} + \lineiv{query} {4} {Query component} {empty string} + \lineiv{fragment}{5} {Fragment identifier} {empty string} + \lineiv{username}{ } {User name} {\constant{None}} + \lineiv{password}{ } {Password} {\constant{None}} + \lineiv{hostname}{ } {Host name (lower case)} {\constant{None}} + \lineiv{port} { } {Port number as integer, if present} {\constant{None}} +\end{tableiv} + +See section~\ref{urlparse-result-object}, ``Results of +\function{urlparse()} and \function{urlsplit()},'' for more +information on the result object. + +\versionchanged[Added attributes to return value]{2.5} \end{funcdesc} -\begin{funcdesc}{urlunparse}{tuple} -Construct a URL string from a tuple as returned by \code{urlparse()}. +\begin{funcdesc}{urlunparse}{parts} +Construct a URL from a tuple as returned by \code{urlparse()}. +The \var{parts} argument be any six-item iterable. This may result in a slightly different, but equivalent URL, if the -URL that was parsed originally had redundant delimiters, e.g. a ? with -an empty query (the draft states that these are equivalent). +URL that was parsed originally had unnecessary delimiters (for example, +a ? with an empty query; the RFC states that these are equivalent). \end{funcdesc} \begin{funcdesc}{urlsplit}{urlstring\optional{, @@ -79,12 +105,38 @@ the URL (see \rfc{2396}) is wanted. A separate function is needed to separate the path segments and parameters. This function returns a 5-tuple: (addressing scheme, network location, path, query, fragment identifier). + +The return value is actually an instance of a subclass of +\pytype{tuple}. This class has the following additional read-only +convenience attributes: + +\begin{tableiv}{l|c|l|c}{member}{Attribute}{Index}{Value}{Value if not present} + \lineiv{scheme} {0} {URL scheme specifier} {empty string} + \lineiv{netloc} {1} {Network location part} {empty string} + \lineiv{path} {2} {Hierarchical path} {empty string} + \lineiv{query} {3} {Query component} {empty string} + \lineiv{fragment} {4} {Fragment identifier} {empty string} + \lineiv{username} { } {User name} {\constant{None}} + \lineiv{password} { } {Password} {\constant{None}} + \lineiv{hostname} { } {Host name (lower case)} {\constant{None}} + \lineiv{port} { } {Port number as integer, if present} {\constant{None}} +\end{tableiv} + +See section~\ref{urlparse-result-object}, ``Results of +\function{urlparse()} and \function{urlsplit()},'' for more +information on the result object. + \versionadded{2.2} +\versionchanged[Added attributes to return value]{2.5} \end{funcdesc} -\begin{funcdesc}{urlunsplit}{tuple} +\begin{funcdesc}{urlunsplit}{parts} Combine the elements of a tuple as returned by \function{urlsplit()} into a complete URL as a string. +The \var{parts} argument be any five-item iterable. +This may result in a slightly different, but equivalent URL, if the +URL that was parsed originally had unnecessary delimiters (for example, +a ? with an empty query; the RFC states that these are equivalent). \versionadded{2.2} \end{funcdesc} @@ -93,22 +145,16 @@ Construct a full (``absolute'') URL by combining a ``base URL'' (\var{base}) with a ``relative URL'' (\var{url}). Informally, this uses components of the base URL, in particular the addressing scheme, the network location and (part of) the path, to provide missing -components in the relative URL. - -Example: - -\begin{verbatim} -urljoin('http://www.cwi.nl/%7Eguido/Python.html', 'FAQ.html') -\end{verbatim} - -yields the string +components in the relative URL. For example: \begin{verbatim} +>>> from urlparse import urljoin +>>> urljoin('http://www.cwi.nl/%7Eguido/Python.html', 'FAQ.html') 'http://www.cwi.nl/%7Eguido/FAQ.html' \end{verbatim} -The \var{allow_fragments} argument has the same meaning as for -\code{urlparse()}. +The \var{allow_fragments} argument has the same meaning and default as +for \function{urlparse()}. \end{funcdesc} \begin{funcdesc}{urldefrag}{url} @@ -133,3 +179,61 @@ in \var{url}, returns \var{url} unmodified and an empty string. both Uniform Resource Names (URNs) and Uniform Resource Locators (URLs).} \end{seealso} + + +\subsection{Results of \function{urlparse()} and \function{urlsplit()} + \label{urlparse-result-object}} + +The result objects from the \function{urlparse()} and +\function{urlsplit()} functions are subclasses of the \pytype{tuple} +type. These subclasses add the attributes described in those +functions, as well as provide an additional method: + +\begin{methoddesc}[ParseResult]{geturl}{} + Return the re-combined version of the original URL as a string. + This may differ from the original URL in that the scheme will always + be normalized to lower case and empty components may be dropped. + Specifically, empty parameters, queries, and fragment identifiers + will be removed. + + The result of this method is a fixpoint if passed back through the + original parsing function: + +\begin{verbatim} +>>> import urlparse +>>> url = 'HTTP://www.Python.org/doc/#' + +>>> r1 = urlparse.urlsplit(url) +>>> r1.geturl() +'http://www.Python.org/doc/' + +>>> r2 = urlparse.urlsplit(r1.geturl()) +>>> r2.geturl() +'http://www.Python.org/doc/' +\end{verbatim} + +\versionadded{2.5} +\end{methoddesc} + +The following classes provide the implementations of the parse results:: + +\begin{classdesc*}{BaseResult} + Base class for the concrete result classes. This provides most of + the attribute definitions. It does not provide a \method{geturl()} + method. It is derived from \class{tuple}, but does not override the + \method{__init__()} or \method{__new__()} methods. +\end{classdesc*} + + +\begin{classdesc}{ParseResult}{scheme, netloc, path, params, query, fragment} + Concrete class for \function{urlparse()} results. The + \method{__new__()} method is overridden to support checking that the + right number of arguments are passed. +\end{classdesc} + + +\begin{classdesc}{SplitResult}{scheme, netloc, path, query, fragment} + Concrete class for \function{urlsplit()} results. The + \method{__new__()} method is overridden to support checking that the + right number of arguments are passed. +\end{classdesc} diff --git a/Doc/lib/libwarnings.tex b/Doc/lib/libwarnings.tex index 8655451..7b829a0 100644 --- a/Doc/lib/libwarnings.tex +++ b/Doc/lib/libwarnings.tex @@ -169,7 +169,8 @@ the latter would defeat the purpose of the warning message). \end{funcdesc} \begin{funcdesc}{warn_explicit}{message, category, filename, - lineno\optional{, module\optional{, registry}}} + lineno\optional{, module\optional{, registry\optional{, + module_globals}}}} This is a low-level interface to the functionality of \function{warn()}, passing in explicitly the message, category, filename and line number, and optionally the module name and the @@ -179,6 +180,11 @@ stripped; if no registry is passed, the warning is never suppressed. \var{message} must be a string and \var{category} a subclass of \exception{Warning} or \var{message} may be a \exception{Warning} instance, in which case \var{category} will be ignored. + +\var{module_globals}, if supplied, should be the global namespace in use +by the code for which the warning is issued. (This argument is used to +support displaying source for modules found in zipfiles or other +non-filesystem import sources, and was added in Python 2.5.) \end{funcdesc} \begin{funcdesc}{showwarning}{message, category, filename, diff --git a/Doc/lib/libxmlrpclib.tex b/Doc/lib/libxmlrpclib.tex index 0fb88c5..1c36f99 100644 --- a/Doc/lib/libxmlrpclib.tex +++ b/Doc/lib/libxmlrpclib.tex @@ -203,7 +203,7 @@ It also supports certain of Python's built-in operators through \subsection{Binary Objects \label{binary-objects}} -This class may initialized from string data (which may include NULs). +This class may be initialized from string data (which may include NULs). The primary access to the content of a \class{Binary} object is provided by an attribute: @@ -303,10 +303,6 @@ Convert any Python value to one of the XML-RPC Boolean constants, \code{True} or \code{False}. \end{funcdesc} -\begin{funcdesc}{binary}{data} -Trivially convert any Python string to a \class{Binary} object. -\end{funcdesc} - \begin{funcdesc}{dumps}{params\optional{, methodname\optional{, methodresponse\optional{, encoding\optional{, allow_none}}}}} diff --git a/Doc/lib/libzipfile.tex b/Doc/lib/libzipfile.tex index 32ca3e0..4e06ef6 100644 --- a/Doc/lib/libzipfile.tex +++ b/Doc/lib/libzipfile.tex @@ -141,10 +141,17 @@ cat myzip.zip >> python.exe Write the file named \var{filename} to the archive, giving it the archive name \var{arcname} (by default, this will be the same as \var{filename}, but without a drive letter and with leading path - separators removed). If given, \var{compress_type} overrides the value - given for the \var{compression} parameter to the constructor for - the new entry. The archive must be open with mode \code{'w'} or - \code{'a'}. + separators removed). If given, \var{compress_type} overrides the + value given for the \var{compression} parameter to the constructor + for the new entry. The archive must be open with mode \code{'w'} + or \code{'a'}. + + \note{There is no official file name encoding for ZIP files. + If you have unicode file names, please convert them to byte strings + in your desired encoding before passing them to \method{write()}. + WinZip interprets all file names as encoded in CP437, also known + as DOS Latin.} + \note{Archive names should be relative to the archive root, that is, they should not start with a path separator.} \end{methoddesc} diff --git a/Doc/lib/libzipimport.tex b/Doc/lib/libzipimport.tex index 0a60b29..770ea21 100644 --- a/Doc/lib/libzipimport.tex +++ b/Doc/lib/libzipimport.tex @@ -69,8 +69,8 @@ The available attributes of this module are: \begin{classdesc}{zipimporter}{archivepath} Create a new zipimporter instance. \var{archivepath} must be a path to - a zipfile. \class{ZipImportError} is raised if \var{archivepath} doesn't - point to a valid ZIP archive. + a zipfile. \exception{ZipImportError} is raised if \var{archivepath} + doesn't point to a valid ZIP archive. \end{classdesc} \begin{methoddesc}{find_module}{fullname\optional{, path}} @@ -83,7 +83,7 @@ The available attributes of this module are: \begin{methoddesc}{get_code}{fullname} Return the code object for the specified module. Raise - \class{ZipImportError} if the module couldn't be found. + \exception{ZipImportError} if the module couldn't be found. \end{methoddesc} \begin{methoddesc}{get_data}{pathname} @@ -93,20 +93,20 @@ The available attributes of this module are: \begin{methoddesc}{get_source}{fullname} Return the source code for the specified module. Raise - \class{ZipImportError} if the module couldn't be found, return + \exception{ZipImportError} if the module couldn't be found, return \constant{None} if the archive does contain the module, but has no source for it. \end{methoddesc} \begin{methoddesc}{is_package}{fullname} Return True if the module specified by \var{fullname} is a package. - Raise \class{ZipImportError} if the module couldn't be found. + Raise \exception{ZipImportError} if the module couldn't be found. \end{methoddesc} \begin{methoddesc}{load_module}{fullname} Load the module specified by \var{fullname}. \var{fullname} must be the fully qualified (dotted) module name. It returns the imported - module, or raises \class{ZipImportError} if it wasn't found. + module, or raises \exception{ZipImportError} if it wasn't found. \end{methoddesc} \subsection{Examples} diff --git a/Doc/lib/libzlib.tex b/Doc/lib/libzlib.tex index 2df8b85..dfbb43d 100644 --- a/Doc/lib/libzlib.tex +++ b/Doc/lib/libzlib.tex @@ -166,11 +166,14 @@ continue. If \var{max_length} is not supplied then the whole input is decompressed, and \member{unconsumed_tail} is an empty string. \end{methoddesc} -\begin{methoddesc}[Decompress]{flush}{} +\begin{methoddesc}[Decompress]{flush}{\optional{length}} All pending input is processed, and a string containing the remaining uncompressed output is returned. After calling \method{flush()}, the \method{decompress()} method cannot be called again; the only realistic action is to delete the object. + +The optional parameter \var{length} sets the initial size of the +output buffer. \end{methoddesc} \begin{seealso} diff --git a/Doc/lib/mimelib.tex b/Doc/lib/mimelib.tex index 67de597..491d844 100644 --- a/Doc/lib/mimelib.tex +++ b/Doc/lib/mimelib.tex @@ -12,9 +12,9 @@ \authoraddress{\email{barry@python.org}} \date{\today} -\release{3.0} % software release, not documentation +\release{4.0} % software release, not documentation \setreleaseinfo{} % empty for final release -\setshortversion{3.0} % major.minor only for software +\setshortversion{4.0} % major.minor only for software \begin{document} @@ -38,11 +38,11 @@ The \module{email} package provides classes and utilities to create, parse, generate, and modify email messages, conforming to all the relevant email and MIME related RFCs. -This document describes version 3.0 of the \module{email} package, which is -distributed with Python 2.4 and is available as a standalone distutils-based -package for use with Python 2.3. \module{email} 3.0 is not compatible with -Python versions earlier than 2.3. For more information about the -\module{email} package, including download links and mailing lists, see +This document describes version 4.0 of the \module{email} package, which is +distributed with Python 2.5 and is available as a standalone distutils-based +package for use with earlier Python versions. \module{email} 4.0 is not +compatible with Python versions earlier than 2.3. For more information about +the \module{email} package, including download links and mailing lists, see \ulink{Python's email SIG}{http://www.python.org/sigs/email-sig}. The documentation that follows was written for the Python project, so @@ -51,7 +51,8 @@ package documentation, there are a few notes to be aware of: \begin{itemize} \item Deprecation and ``version added'' notes are relative to the - Python version a feature was added or deprecated. + Python version a feature was added or deprecated. See + the package history in section \ref{email-pkg-history} for details. \item If you're reading this documentation as part of the standalone \module{email} package, some of the internal links to diff --git a/Doc/lib/xmldomminidom.tex b/Doc/lib/xmldomminidom.tex index f7657eb..093915f 100644 --- a/Doc/lib/xmldomminidom.tex +++ b/Doc/lib/xmldomminidom.tex @@ -165,7 +165,7 @@ XML. With an explicit \var{encoding} argument, the result is a byte string in the specified encoding. It is recommended that this argument is -always specified. To avoid UnicodeError exceptions in case of +always specified. To avoid \exception{UnicodeError} exceptions in case of unrepresentable text data, the encoding argument should be specified as "utf-8". |