home
***
CD-ROM
|
disk
|
FTP
|
other
***
search
/
The Datafile PD-CD 5
/
DATAFILE_PDCD5.iso
/
utilities
/
p
/
python
/
!Python
/
Lib
/
NetLib
/
py
/
rfc822
< prev
next >
Wrap
Text File
|
1996-07-30
|
11KB
|
459 lines
# 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 regex
import string
import time
_blanklines = ('\r\n', '\n') # Optimization for islast()
class Message:
# Initialize the class instance and read the headers.
def __init__(self, fp, seekable = 1):
self.fp = fp
self.seekable = seekable
self.startofheaders = None
self.startofbody = None
#
if self.seekable:
try:
self.startofheaders = self.fp.tell()
except IOError:
self.seekable = 0
#
self.readheaders()
#
if self.seekable:
try:
self.startofbody = self.fp.tell()
except IOError:
self.seekable = 0
# Rewind the file to the start of the body (if seekable).
def rewindbody(self):
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):
self.dict = {}
self.unixfrom = ''
self.headers = list = []
self.status = ''
headerseen = ""
firstline = 1
while 1:
line = self.fp.readline()
if not line:
self.status = 'EOF in headers'
break
# Skip unix From name time lines
if firstline and line[:5] == 'From ':
self.unixfrom = self.unixfrom + line
continue
firstline = 0
if self.islast(line):
break
elif headerseen and line[0] in ' \t':
# It's a continuation line.
list.append(line)
x = (self.dict[headerseen] + "\n " +
string.strip(line))
self.dict[headerseen] = string.strip(x)
elif ':' in line:
# It's a header line.
list.append(line)
i = string.find(line, ':')
headerseen = string.lower(line[:i])
self.dict[headerseen] = string.strip(
line[i+1:])
else:
# It's not a header line; stop here.
if not headerseen:
self.status = 'No headers'
else:
self.status = 'Bad header'
# Try to undo the read.
if self.seekable:
self.fp.seek(-len(line), 1)
else:
self.status = \
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
# 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.
def getallmatchingheaders(self, name):
name = string.lower(name) + ':'
n = len(name)
list = []
hit = 0
for line in self.headers:
if string.lower(line[:n]) == name:
hit = 1
elif line[:1] not in string.whitespace:
hit = 0
if hit:
list.append(line)
return list
# Similar, but return only the first matching header (and its
# continuation lines).
def getfirstmatchingheader(self, name):
name = string.lower(name) + ':'
n = len(name)
list = []
hit = 0
for line in self.headers:
if hit:
if line[:1] not in string.whitespace:
break
elif string.lower(line[:n]) == name:
hit = 1
if hit:
list.append(line)
return list
# 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.
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):
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):
try:
data = self[name]
except KeyError:
return None, None
return parseaddr(data)
# Retrieve a list of addresses from a header, where each
# address is a tuple as returned by getaddr().
def getaddrlist(self, name):
# XXX This function is not really correct. The split
# on ',' might fail in the case of commas within
# quoted strings.
try:
data = self[name]
except KeyError:
return []
data = string.splitfields(data, ',')
for i in range(len(data)):
data[i] = parseaddr(data[i])
return data
# Retrieve a date field from a header as a tuple compatible
# with time.mktime().
def getdate(self, name):
try:
data = self[name]
except KeyError:
return None
return parsedate(data)
# Access as a dictionary (only finds *last* header of each type):
def __len__(self):
return len(self.dict)
def __getitem__(self, name):
return self.dict[string.lower(name)]
def has_key(self, name):
return self.dict.has_key(string.lower(name))
def keys(self):
return self.dict.keys()
def values(self):
return self.dict.values()
def items(self):
return self.dict.items()
# Utility functions
# -----------------
# XXX Should fix these to be really conformant.
# XXX The inverses of the parse functions may also be useful.
# Remove quotes from a string.
def unquote(str):
if len(str) > 1:
if str[0] == '"' and str[-1:] == '"':
return str[1:-1]
if str[0] == '<' and str[-1:] == '>':
return str[1:-1]
return str
# Parse an address into (name, address) tuple
def parseaddr(address):
import string
str = ''
email = ''
comment = ''
backslash = 0
dquote = 0
space = 0
paren = 0
bracket = 0
seen_bracket = 0
for c in address:
if backslash:
str = str + c
backslash = 0
continue
if c == '\\':
backslash = 1
continue
if dquote:
if c == '"':
dquote = 0
else:
str = str