diff options
author | Guido van Rossum <guido@python.org> | 2007-08-30 01:15:14 (GMT) |
---|---|---|
committer | Guido van Rossum <guido@python.org> | 2007-08-30 01:15:14 (GMT) |
commit | 8b3febef2f96c35e9aad9db2ef499db040fdefae (patch) | |
tree | 6bc3322d80780a8d57d845b350aad9fbe250d5de /Lib/email/parser.py | |
parent | 21b731fb7798218a0e59e6db204d1d43d2a1e820 (diff) | |
download | cpython-8b3febef2f96c35e9aad9db2ef499db040fdefae.zip cpython-8b3febef2f96c35e9aad9db2ef499db040fdefae.tar.gz cpython-8b3febef2f96c35e9aad9db2ef499db040fdefae.tar.bz2 |
Copying the email package back, despite its failings.
Diffstat (limited to 'Lib/email/parser.py')
-rw-r--r-- | Lib/email/parser.py | 95 |
1 files changed, 95 insertions, 0 deletions
diff --git a/Lib/email/parser.py b/Lib/email/parser.py new file mode 100644 index 0000000..439a4a0 --- /dev/null +++ b/Lib/email/parser.py @@ -0,0 +1,95 @@ +# Copyright (C) 2001-2007 Python Software Foundation +# Author: Barry Warsaw, Thomas Wouters, Anthony Baxter +# Contact: email-sig@python.org + +"""A parser of RFC 2822 and MIME email messages.""" + +__all__ = ['Parser', 'HeaderParser'] + +import warnings +from io import StringIO + +from email.feedparser import FeedParser +from email.message import Message + + + +class Parser: + def __init__(self, *args, **kws): + """Parser of RFC 2822 and MIME email messages. + + Creates an in-memory object tree representing the email message, which + can then be manipulated and turned over to a Generator to return the + textual representation of the message. + + The string must be formatted as a block of RFC 2822 headers and header + continuation lines, optionally preceeded by a `Unix-from' header. The + header block is terminated either by the end of the string or by a + blank line. + + _class is the class to instantiate for new message objects when they + must be created. This class must have a constructor that can take + zero arguments. Default is Message.Message. + """ + if len(args) >= 1: + if '_class' in kws: + raise TypeError("Multiple values for keyword arg '_class'") + kws['_class'] = args[0] + if len(args) == 2: + if 'strict' in kws: + raise TypeError("Multiple values for keyword arg 'strict'") + kws['strict'] = args[1] + if len(args) > 2: + raise TypeError('Too many arguments') + if '_class' in kws: + self._class = kws['_class'] + del kws['_class'] + else: + self._class = Message + if 'strict' in kws: + warnings.warn("'strict' argument is deprecated (and ignored)", + DeprecationWarning, 2) + del kws['strict'] + if kws: + raise TypeError('Unexpected keyword arguments') + + def parse(self, fp, headersonly=False): + """Create a message structure from the data in a file. + + Reads all the data from the file and returns the root of the message + structure. Optional headersonly is a flag specifying whether to stop + parsing after reading the headers or not. The default is False, + meaning it parses the entire contents of the file. + """ + feedparser = FeedParser(self._class) + if headersonly: + feedparser._set_headersonly() + while True: + data = fp.read(8192) + if not data: + break + # XXX When Guido fixes TextIOWrapper.read() to act just like + # .readlines(), this... + feedparser.feed(str(data)) + # ...gets reverted back to + #feedparser.feed(data) + return feedparser.close() + + def parsestr(self, text, headersonly=False): + """Create a message structure from a string. + + Returns the root of the message structure. Optional headersonly is a + flag specifying whether to stop parsing after reading the headers or + not. The default is False, meaning it parses the entire contents of + the file. + """ + return self.parse(StringIO(text), headersonly=headersonly) + + + +class HeaderParser(Parser): + def parse(self, fp, headersonly=True): + return Parser.parse(self, fp, True) + + def parsestr(self, text, headersonly=True): + return Parser.parsestr(self, text, True) |