Skip to content

C
cpython
Commit 9ab94c18 authored by Guido van Rossum's avatar Guido van Rossum
Browse files
Options

Doc strings and reformatting with 4 spaces bty Mitch Chapman. 

Untabified and minor tweaks by me.
parent 24e62e2c
Show whitespace changes
Inline Side-by-side
Showing with 661 additions and 609 deletions
Lib/rfc822.py
View file @ 9ab94c18
# RFC-822 message manipulation class.
#
# XXX This is only a very rough sketch of a full RFC-822 parser;
# in particular the tokenizing of addresses does not adhere to all the
# quoting rules.
#
# Directions for use:
#
# To create a Message object: first open a file, e.g.:
# fp = open(file, 'r')
# (or use any other legal way of getting an open file object, e.g. use
# sys.stdin or call os.popen()).
# Then pass the open file object to the Message() constructor:
# m = Message(fp)
#
# To get the text of a particular header there are several methods:
# str = m.getheader(name)
# str = m.getrawheader(name)
# where name is the name of the header, e.g. 'Subject'.
# The difference is that getheader() strips the leading and trailing
# whitespace, while getrawheader() doesn't. Both functions retain
# embedded whitespace (including newlines) exactly as they are
# specified in the header, and leave the case of the text unchanged.
#
# For addresses and address lists there are functions
# realname, mailaddress = m.getaddr(name) and
# list = m.getaddrlist(name)
# where the latter returns a list of (realname, mailaddr) tuples.
#
# There is also a method
# time = m.getdate(name)
# which parses a Date-like field and returns a time-compatible tuple,
# i.e. a tuple such as returned by time.localtime() or accepted by
# time.mktime().
#
# See the class definition for lower level access methods.
#
# There are also some utility functions here.
"""RFC-822 message manipulation class.
XXX This is only a very rough sketch of a full RFC-822 parser;
in particular the tokenizing of addresses does not adhere to all the
quoting rules.
Directions for use:
To create a Message object: first open a file, e.g.:
fp = open(file, 'r')
(or use any other legal way of getting an open file object, e.g. use
sys.stdin or call os.popen()).
Then pass the open file object to the Message() constructor:
m = Message(fp)
To get the text of a particular header there are several methods:
str = m.getheader(name)
str = m.getrawheader(name)
where name is the name of the header, e.g. 'Subject'.
The difference is that getheader() strips the leading and trailing
whitespace, while getrawheader() doesn't. Both functions retain
embedded whitespace (including newlines) exactly as they are
specified in the header, and leave the case of the text unchanged.
For addresses and address lists there are functions
realname, mailaddress = m.getaddr(name) and
list = m.getaddrlist(name)
where the latter returns a list of (realname, mailaddr) tuples.
There is also a method
time = m.getdate(name)
which parses a Date-like field and returns a time-compatible tuple,
i.e. a tuple such as returned by time.localtime() or accepted by
time.mktime().
See the class definition for lower level access methods.
There are also some utility functions here.
"""
import re
import string
......@@ -47,10 +47,10 @@ _blanklines = ('\r\n', '\n') # Optimization for islast()
class Message:
# Initialize the class instance and read the headers.
"""Represents a single RFC-822-compliant message."""
def __init__(self, fp, seekable = 1):
"""Initialize the class instance and read the headers."""
self.fp = fp
self.seekable = seekable
self.startofheaders = None
......@@ -70,29 +70,28 @@ class Message:
except IOError:
self.seekable = 0
# Rewind the file to the start of the body (if seekable).
def rewindbody(self):
"""Rewind the file to the start of the body (if seekable)."""
if not self.seekable:
raise IOError, "unseekable file"
self.fp.seek(self.startofbody)
# Read header lines up to the entirely blank line that
# terminates them. The (normally blank) line that ends the
# headers is skipped, but not included in the returned list.
# If a non-header line ends the headers, (which is an error),
# an attempt is made to backspace over it; it is never
# included in the returned list.
#
# The variable self.status is set to the empty string if all
# went well, otherwise it is an error message.
# The variable self.headers is a completely uninterpreted list
# of lines contained in the header (so printing them will
# reproduce the header exactly as it appears in the file).
def readheaders(self):
"""Read header lines.
Read header lines up to the entirely blank line that
terminates them. The (normally blank) line that ends the
headers is skipped, but not included in the returned list.
If a non-header line ends the headers, (which is an error),
an attempt is made to backspace over it; it is never
included in the returned list.
The variable self.status is set to the empty string if all
went well, otherwise it is an error message.
The variable self.headers is a completely uninterpreted list
of lines contained in the header (so printing them will
reproduce the header exactly as it appears in the file).
"""
self.dict = {}
self.unixfrom = ''
self.headers = list = []
......@@ -138,26 +137,28 @@ class Message:
self.status + '; bad seek'
break
# Method to determine whether a line is a legal end of
# RFC-822 headers. You may override this method if your
# application wants to bend the rules, e.g. to strip trailing
# whitespace, or to recognise MH template separators
# ('--------'). For convenience (e.g. for code reading from
# sockets) a line consisting of \r\n also matches.
def islast(self, line):
return line in _blanklines
"""Determine whether a line is a legal end of RFC-822 headers.
# Look through the list of headers and find all lines matching
# a given header name (and their continuation lines).
# A list of the lines is returned, without interpretation.
# If the header does not occur, an empty list is returned.
# If the header occurs multiple times, all occurrences are
# returned. Case is not important in the header name.
You may override this method if your application wants
to bend the rules, e.g. to strip trailing whitespace,
or to recognise MH template separators ('--------').
For convenience (e.g. for code reading from sockets) a
line consisting of \r\n also matches.
"""
return line in _blanklines
def getallmatchingheaders(self, name):
"""Find all header lines matching a given header name.
Look through the list of headers and find all lines
matching a given header name (and their continuation
lines). A list of the lines is returned, without
interpretation. If the header does not occur, an
empty list is returned. If the header occurs multiple
times, all occurrences are returned. Case is not
important in the header name.
"""
name = string.lower(name) + ':'
n = len(name)
list = []
......@@ -171,11 +172,13 @@ class Message:
list.append(line)
return list
# Similar, but return only the first matching header (and its
# continuation lines).
def getfirstmatchingheader(self, name):
"""Get the first header line matching name.
This is similar to getallmatchingheaders, but it returns
only the first matching header (and its continuation
lines).
"""
name = string.lower(name) + ':'
n = len(name)
list = []
......@@ -190,37 +193,41 @@ class Message:
list.append(line)
return list
def getrawheader(self, name):
"""A higher-level interface to getfirstmatchingheader().
# A higher-level interface to getfirstmatchingheader().
# Return a string containing the literal text of the header
# but with the keyword stripped. All leading, trailing and
# embedded whitespace is kept in the string, however.
# Return None if the header does not occur.
Return a string containing the literal text of the
header but with the keyword stripped. All leading,
trailing and embedded whitespace is kept in the
string, however.
Return None if the header does not occur.
"""
def getrawheader(self, name):
list = self.getfirstmatchingheader(name)
if not list:
return None
list[0] = list[0][len(name) + 1:]
return string.joinfields(list, '')
# The normal interface: return a stripped version of the
# header value with a name, or None if it doesn't exist. This
# uses the dictionary version which finds the *last* such
# header.
def getheader(self, name):
"""Get the header value for a name.
This is the normal interface: it return a stripped
version of the header value for a given header name,
or None if it doesn't exist. This uses the dictionary
version which finds the *last* such header.
"""
try:
return self.dict[string.lower(name)]
except KeyError:
return None
# Retrieve a single address from a header as a tuple, e.g.
# ('Guido van Rossum', 'guido@cwi.nl').
def getaddr(self, name):
"""Get a single address from a header, as a tuple.
An example return value:
('Guido van Rossum', 'guido@cwi.nl')
"""
# New, by Ben Escoto
alist = self.getaddrlist(name)
if alist:
......@@ -228,10 +235,12 @@ class Message:
else:
return (None, None)
# Retrieve a list of addresses from a header, where each
# address is a tuple as returned by getaddr().
def getaddrlist(self, name):
"""Get a list of addresses from a header.
Retrieves a list of addresses from a header, where each
address is a tuple as returned by getaddr().
"""
# New, by Ben Escoto
try:
data = self[name]
......@@ -240,22 +249,25 @@ class Message:
a = AddrlistClass(data)
return a.getaddrlist()
# Retrieve a date field from a header as a tuple compatible
# with time.mktime().
def getdate(self, name):
"""Retrieve a date field from a header.
Retrieves a date field from the named header, returning
a tuple compatible with time.mktime().
"""
try:
data = self[name]
except KeyError:
return None
return parsedate(data)
# Retrieve a date field from a header as a 10-tuple.
# The first 9 elements make up a tuple compatible
# with time.mktime(), and the 10th is the offset
# of the poster's time zone from GMT/UTC.
def getdate_tz(self, name):
"""Retrieve a date field from a header as a 10-tuple.
The first 9 elements make up a tuple compatible with
time.mktime(), and the 10th is the offset of the poster's
time zone from GMT/UTC.
"""
try:
data = self[name]
except KeyError:
......@@ -266,21 +278,30 @@ class Message:
# Access as a dictionary (only finds *last* header of each type):
def __len__(self):
"""Get the number of headers in a message."""
return len(self.dict)
def __getitem__(self, name):
"""Get a specific header, as from a dictionary."""
return self.dict[string.lower(name)]
def has_key(self, name):
"""Determine whether a message contains the named header."""
return self.dict.has_key(string.lower(name))
def keys(self):
"""Get all of a message's header field names."""
return self.dict.keys()
def values(self):
"""Get all of a message's header field values."""
return self.dict.values()
def items(self):
"""Get all of a message's headers.
Returns a list of name, value tuples.
"""
return self.dict.items()
......@@ -292,9 +313,8 @@ class Message:
# XXX The inverses of the parse functions may also be useful.
# Remove quotes from a string.
def unquote(str):
"""Remove quotes from a string."""
if len(str) > 1:
if str[0] == '"' and str[-1:] == '"':
return str[1:-1]
......@@ -303,9 +323,8 @@ def unquote(str):
return str
# Add quotes around a string.
def quote(str):
"""Add quotes around a string."""
return '"%s"' % string.join(
string.split(
string.join(
......@@ -315,9 +334,8 @@ def quote(str):
'\\"')
# External interface to parse an address
def parseaddr(address):
"""Parse an address into a (realname, mailaddr) tuple."""
a = AddrlistClass(address)
list = a.getaddrlist()
if not list:
......@@ -326,12 +344,19 @@ def parseaddr(address):
return list[0]
# Address parser class by Ben Escoto
class AddrlistClass:
"""Address parser class by Ben Escoto.
To understand what this class does, it helps to have a copy of
RFC-822 in front of you.
"""
def __init__(self, field):
"""Initialize a new instance.
`field' is an unparsed address header field, containing
one or more addresses.
"""
self.specials = '()<>@,:;.\"[]'
self.pos = 0
self.LWS = ' \t'
......@@ -341,9 +366,8 @@ class AddrlistClass:
self.field = field
self.commentlist = []
def gotonext(self):
"""Parse up to the start of the next address."""
while self.pos < len(self.field):
if self.field[self.pos] in self.LWS + '\n\r':
self.pos = self.pos + 1
......@@ -352,13 +376,17 @@ class AddrlistClass:
else: break
def getaddrlist(self):
"""Parse all addresses.
Returns a list containing all of the addresses.
"""
ad = self.getaddress()
if ad:
return ad + self.getaddrlist()
else: return []
def getaddress(self):
"""Parse the next address."""
self.commentlist = []
self.gotonext()
......@@ -412,9 +440,11 @@ class AddrlistClass:
self.pos = self.pos + 1
return returnlist
def getrouteaddr(self):
# This just skips all the route stuff and returns the addrspec
"""Parse a route address (Return-path value).
This method just skips all the route stuff and returns the addrspec.
"""
if self.field[self.pos] != '<':
return
......@@ -442,9 +472,8 @@ class AddrlistClass:
return adlist
def getaddrspec(self):
"""Parse an RFC-822 addr-spec."""
aslist = []
self.gotonext()
......@@ -467,9 +496,8 @@ class AddrlistClass:
self.gotonext()
return string.join(aslist, '') + self.getdomain()
def getdomain(self):
"""Get the complete domain name from an address."""
sdlist = []
while self.pos < len(self.field):
if self.field[self.pos] in self.LWS:
......@@ -487,9 +515,19 @@ class AddrlistClass:
return string.join(sdlist, '')
def getdelimited(self, beginchar, endchars, allowcomments = 1):
"""Parse a header fragment delimited by special characters.
`beginchar' is the start character for the fragment.
If self is not looking at an instance of `beginchar' then
getdelimited returns the empty string.
`endchars' is a sequence of allowable end-delimiting characters.
Parsing stops when one of these is encountered.
If `allowcomments' is non-zero, embedded RFC-822 comments
are allowed within the parsed fragment.
"""
if self.field[self.pos] != beginchar:
return ''
......@@ -514,17 +552,19 @@ class AddrlistClass:
return string.join(slist, '')
def getquote(self):
"""Get a quote-delimited fragment from self's field."""
return self.getdelimited('"', '"\r', 0)
def getcomment(self):
"""Get a parenthesis-delimited fragment from self's field."""
return self.getdelimited('(', ')\r', 1)
def getdomainliteral(self):
"""Parse an RFC-822 domain-literal."""
return self.getdelimited('[', ']\r', 0)
def getatom(self):
"""Parse an RFC-822 atom."""
atomlist = ['']
while self.pos < len(self.field):
......@@ -535,9 +575,12 @@ class AddrlistClass:
return string.join(atomlist, '')
def getphraselist(self):
"""Parse a sequence of RFC-822 phrases.
A phrase is a sequence of words, which are in turn either
RFC-822 atoms or quoted-strings.
"""
plist = []
while self.pos < len(self.field):
......@@ -574,7 +617,12 @@ _timezones = {'UT':0, 'UTC':0, 'GMT':0, 'Z':0,
'PST':-800, 'PDT':-700 # Pacific
}
def parsedate_tz(data):
"""Convert a date string to a time tuple.
Accounts for military timezones.
"""
data = string.split(data)
if data[0][-1] == ',' or data[0] in _daynames:
# There's a dayname here. Skip it
......@@ -630,12 +678,15 @@ def parsedate_tz(data):
tuple = (yy, mm, dd, thh, tmm, tss, 0, 0, 0, tzoffset)
return tuple
def parsedate(data):
"""Convert a time string to a time tuple."""
t=parsedate_tz(data)
if type(t)==type( () ):
return t[:9]
else: return t
def mktime_tz(data):
"""Turn a 10-tuple as returned by parsedate_tz() into a UTC timestamp.
......@@ -648,6 +699,7 @@ def mktime_tz(data):
t = time.mktime(data[:8] + (0,))
return t + data[9] - time.timezone
# When used as script, run a small test program.
# The first command line argument must be a filename containing one
# message in RFC-822 format.
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7