Source

cpython-withatomic / Lib / rfc822.py

The branch 'legacy-trunk' does not exist.
  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
# 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 + c
			continue
		if c == '"':
			dquote = 1
			continue
		if c in string.whitespace:
			space = 1
			continue
		if space:
			str = str + ' '
			space = 0
		if paren:
			if c == '(':
				paren = paren + 1
				str = str + c
				continue
			if c == ')':
				paren = paren - 1
				if paren == 0:
					comment = comment + str
					str = ''
					continue
		if c == '(':
			paren = paren + 1
			if bracket:
				email = email + str
				str = ''
			elif not seen_bracket:
				email = email + str
				str = ''
			continue
		if bracket:
			if c == '>':
				bracket = 0
				email = email + str
				str = ''
				continue
		if c == '<':
			bracket = 1
			seen_bracket = 1
			comment = comment + str
			str = ''
			email = ''
			continue
		if c == '#' and not bracket and not paren:
			# rest is comment
			break
		str = str + c
	if str:
		if seen_bracket:
			if bracket:
				email = str
			else:
				comment = comment + str
		else:
			if paren:
				comment = comment + str
			else:
				email = email + str
	return string.strip(comment), string.strip(email)


# Parse a date field

_monthnames = ['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul',
	  'Aug', 'Sep', 'Oct', 'Nov', 'Dec']

def parsedate(data):
	# XXX This still mostly ignores timezone matters at the moment...
	data = string.split(data)
	if data[0][-1] == ',':
		# There's a dayname here. Skip it
		del data[0]
	if len(data) == 4:
		s = data[3]
		i = string.find(s, '+')
		if i > 0:
			data[3:] = [s[:i], s[i+1:]]
		else:
			data.append('') # Dummy tz
	if len(data) < 5:
		return None
	data = data[:5]
	[dd, mm, yy, tm, tz] = data
	if not mm in _monthnames:
		return None
	mm = _monthnames.index(mm)+1
	tm = string.splitfields(tm, ':')
	if len(tm) == 2:
		[thh, tmm] = tm
		tss = '0'
	else:
		[thh, tmm, tss] = tm
	try:
		yy = string.atoi(yy)
		dd = string.atoi(dd)
		thh = string.atoi(thh)
		tmm = string.atoi(tmm)
		tss = string.atoi(tss)
	except string.atoi_error:
		return None
	tuple = (yy, mm, dd, thh, tmm, tss, 0, 0, 0)
	return tuple


# 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.

if __name__ == '__main__':
	import sys, os
	file = os.path.join(os.environ['HOME'], 'Mail/drafts/,1')
	if sys.argv[1:]: file = sys.argv[1]
	f = open(file, 'r')
	m = Message(f)
	print 'From:', m.getaddr('from')
	print 'To:', m.getaddrlist('to')
	print 'Subject:', m.getheader('subject')
	print 'Date:', m.getheader('date')
	date = m.getdate('date')
	if date:
		print 'ParsedDate:', time.asctime(date)
	else:
		print 'ParsedDate:', None
	m.rewindbody()
	n = 0
	while f.readline():
		n = n + 1
	print 'Lines:', n
	print '-'*70
	print 'len =', len(m)
	if m.has_key('Date'): print 'Date =', m['Date']
	if m.has_key('X-Nonsense'): pass
	print 'keys =', m.keys()
	print 'values =', m.values()
	print 'items =', m.items()