diff options
author | thegeorg <thegeorg@yandex-team.com> | 2024-02-19 02:38:52 +0300 |
---|---|---|
committer | thegeorg <thegeorg@yandex-team.com> | 2024-02-19 02:50:43 +0300 |
commit | d96fa07134c06472bfee6718b5cfd1679196fc99 (patch) | |
tree | 31ec344fa9d3ff8dc038692516b6438dfbdb8a2d /contrib/tools/python3/Lib/email/parser.py | |
parent | 452cf9e068aef7110e35e654c5d47eb80111ef89 (diff) | |
download | ydb-d96fa07134c06472bfee6718b5cfd1679196fc99.tar.gz |
Sync contrib/tools/python3 layout with upstream
* Move src/ subdir contents to the top of the layout
* Rename self-written lib -> lib2 to avoid CaseFolding warning from the VCS
* Regenerate contrib/libs/python proxy-headers accordingly
4ccc62ac1511abcf0fed14ccade38e984e088f1e
Diffstat (limited to 'contrib/tools/python3/Lib/email/parser.py')
-rw-r--r-- | contrib/tools/python3/Lib/email/parser.py | 127 |
1 files changed, 127 insertions, 0 deletions
diff --git a/contrib/tools/python3/Lib/email/parser.py b/contrib/tools/python3/Lib/email/parser.py new file mode 100644 index 00000000000..06d99b17f2f --- /dev/null +++ b/contrib/tools/python3/Lib/email/parser.py @@ -0,0 +1,127 @@ +# 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', 'BytesParser', 'BytesHeaderParser', + 'FeedParser', 'BytesFeedParser'] + +from io import StringIO, TextIOWrapper + +from email.feedparser import FeedParser, BytesFeedParser +from email._policybase import compat32 + + +class Parser: + def __init__(self, _class=None, *, policy=compat32): + """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 preceded 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. + + The policy keyword specifies a policy object that controls a number of + aspects of the parser's operation. The default policy maintains + backward compatibility. + + """ + self._class = _class + self.policy = policy + + 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, policy=self.policy) + if headersonly: + feedparser._set_headersonly() + while data := fp.read(8192): + 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) + + +class BytesParser: + + def __init__(self, *args, **kw): + """Parser of binary 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 input must be formatted as a block of RFC 2822 headers and header + continuation lines, optionally preceded by a `Unix-from' header. The + header block is terminated either by the end of the input 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. + """ + self.parser = Parser(*args, **kw) + + def parse(self, fp, headersonly=False): + """Create a message structure from the data in a binary 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. + """ + fp = TextIOWrapper(fp, encoding='ascii', errors='surrogateescape') + try: + return self.parser.parse(fp, headersonly) + finally: + fp.detach() + + + def parsebytes(self, text, headersonly=False): + """Create a message structure from a byte 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. + """ + text = text.decode('ASCII', errors='surrogateescape') + return self.parser.parsestr(text, headersonly) + + +class BytesHeaderParser(BytesParser): + def parse(self, fp, headersonly=True): + return BytesParser.parse(self, fp, headersonly=True) + + def parsebytes(self, text, headersonly=True): + return BytesParser.parsebytes(self, text, headersonly=True) |