_parseaddr.py 16.8 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15
# Copyright (C) 2002-2007 Python Software Foundation
# Contact: email-sig@python.org

"""Email address parsing code.

Lifted directly from rfc822.py.  This should eventually be rewritten.
"""

__all__ = [
    'mktime_tz',
    'parsedate',
    'parsedate_tz',
    'quote',
    ]

16
import time, calendar
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

SPACE = ' '
EMPTYSTRING = ''
COMMASPACE = ', '

# Parse a date field
_monthnames = ['jan', 'feb', 'mar', 'apr', 'may', 'jun', 'jul',
               'aug', 'sep', 'oct', 'nov', 'dec',
               'january', 'february', 'march', 'april', 'may', 'june', 'july',
               'august', 'september', 'october', 'november', 'december']

_daynames = ['mon', 'tue', 'wed', 'thu', 'fri', 'sat', 'sun']

# The timezone table does not include the military time zones defined
# in RFC822, other than Z.  According to RFC1123, the description in
# RFC822 gets the signs wrong, so we can't rely on any such time
# zones.  RFC1123 recommends that numeric timezone indicators be used
# instead of timezone names.

_timezones = {'UT':0, 'UTC':0, 'GMT':0, 'Z':0,
              'AST': -400, 'ADT': -300,  # Atlantic (used in Canada)
              'EST': -500, 'EDT': -400,  # Eastern
              'CST': -600, 'CDT': -500,  # Central
              'MST': -700, 'MDT': -600,  # Mountain
              'PST': -800, 'PDT': -700   # Pacific
              }


def parsedate_tz(data):
    """Convert a date string to a time tuple.

    Accounts for military timezones.
49 50
    """
    res = _parsedate_tz(data)
51 52
    if not res:
        return
53 54 55 56 57 58 59 60 61 62 63 64 65
    if res[9] is None:
        res[9] = 0
    return tuple(res)

def _parsedate_tz(data):
    """Convert date to extended time tuple.

    The last (additional) element is the time zone offset in seconds, except if
    the timezone was specified as -0000.  In that case the last element is
    None.  This indicates a UTC timestamp that explicitly declaims knowledge of
    the source timezone, as opposed to a +0000 timestamp that indicates the
    source timezone really was UTC.

66
    """
67 68
    if not data:
        return
69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85
    data = data.split()
    # The FWS after the comma after the day-of-week is optional, so search and
    # adjust for this.
    if data[0].endswith(',') or data[0].lower() in _daynames:
        # There's a dayname here. Skip it
        del data[0]
    else:
        i = data[0].rfind(',')
        if i >= 0:
            data[0] = data[0][i+1:]
    if len(data) == 3: # RFC 850 date, deprecated
        stuff = data[0].split('-')
        if len(stuff) == 3:
            data = stuff + data[1:]
    if len(data) == 4:
        s = data[3]
        i = s.find('+')
86 87
        if i == -1:
            i = s.find('-')
88
        if i > 0:
89
            data[3:] = [s[:i], s[i:]]
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
        else:
            data.append('') # Dummy tz
    if len(data) < 5:
        return None
    data = data[:5]
    [dd, mm, yy, tm, tz] = data
    mm = mm.lower()
    if mm not in _monthnames:
        dd, mm = mm, dd.lower()
        if mm not in _monthnames:
            return None
    mm = _monthnames.index(mm) + 1
    if mm > 12:
        mm -= 12
    if dd[-1] == ',':
        dd = dd[:-1]
    i = yy.find(':')
    if i > 0:
        yy, tm = tm, yy
    if yy[-1] == ',':
        yy = yy[:-1]
    if not yy[0].isdigit():
        yy, tz = tz, yy
    if tm[-1] == ',':
        tm = tm[:-1]
    tm = tm.split(':')
    if len(tm) == 2:
        [thh, tmm] = tm
        tss = '0'
    elif len(tm) == 3:
        [thh, tmm, tss] = tm
121 122 123 124 125 126 127 128
    elif len(tm) == 1 and '.' in tm[0]:
        # Some non-compliant MUAs use '.' to separate time elements.
        tm = tm[0].split('.')
        if len(tm) == 2:
            [thh, tmm] = tm
            tss = 0
        elif len(tm) == 3:
            [thh, tmm, tss] = tm
129 130 131 132 133 134 135 136 137 138
    else:
        return None
    try:
        yy = int(yy)
        dd = int(dd)
        thh = int(thh)
        tmm = int(tmm)
        tss = int(tss)
    except ValueError:
        return None
139 140 141 142 143 144 145 146 147 148 149 150
    # Check for a yy specified in two-digit format, then convert it to the
    # appropriate four-digit format, according to the POSIX standard. RFC 822
    # calls for a two-digit yy, but RFC 2822 (which obsoletes RFC 822)
    # mandates a 4-digit yy. For more information, see the documentation for
    # the time module.
    if yy < 100:
        # The year is between 1969 and 1999 (inclusive).
        if yy > 68:
            yy += 1900
        # The year is between 2000 and 2068 (inclusive).
        else:
            yy += 2000
151 152 153 154 155 156 157 158 159
    tzoffset = None
    tz = tz.upper()
    if tz in _timezones:
        tzoffset = _timezones[tz]
    else:
        try:
            tzoffset = int(tz)
        except ValueError:
            pass
160 161
        if tzoffset==0 and tz.startswith('-'):
            tzoffset = None
162 163 164 165 166 167 168 169 170
    # Convert a timezone offset into seconds ; -0500 -> -18000
    if tzoffset:
        if tzoffset < 0:
            tzsign = -1
            tzoffset = -tzoffset
        else:
            tzsign = 1
        tzoffset = tzsign * ( (tzoffset//100)*3600 + (tzoffset % 100)*60)
    # Daylight Saving Time flag is set to -1, since DST is unknown.
171
    return [yy, mm, dd, thh, tmm, tss, 0, 1, -1, tzoffset]
172 173 174 175 176 177 178 179 180 181 182 183


def parsedate(data):
    """Convert a time string to a time tuple."""
    t = parsedate_tz(data)
    if isinstance(t, tuple):
        return t[:9]
    else:
        return t


def mktime_tz(data):
184
    """Turn a 10-tuple as returned by parsedate_tz() into a POSIX timestamp."""
185 186 187 188
    if data[9] is None:
        # No zone info, so localtime is better assumption than GMT
        return time.mktime(data[:8] + (-1,))
    else:
189 190
        t = calendar.timegm(data)
        return t - data[9]
191 192 193


def quote(str):
194 195 196 197 198 199
    """Prepare string to be used in a quoted string.

    Turns backslash and double quote characters into quoted pairs.  These
    are the only characters that need to be quoted inside a quoted string.
    Does not add the surrounding double quotes.
    """
200 201 202 203 204 205 206 207 208 209
    return str.replace('\\', '\\\\').replace('"', '\\"')


class AddrlistClass:
    """Address parser class by Ben Escoto.

    To understand what this class does, it helps to have a copy of RFC 2822 in
    front of you.

    Note: this class interface is deprecated and may be removed in the future.
Florent Xicluna's avatar
Florent Xicluna committed
210
    Use email.utils.AddressList instead.
211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232
    """

    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'
        self.CR = '\r\n'
        self.FWS = self.LWS + self.CR
        self.atomends = self.specials + self.LWS + self.CR
        # Note that RFC 2822 now specifies `.' as obs-phrase, meaning that it
        # is obsolete syntax.  RFC 2822 requires that we recognize obsolete
        # syntax, so allow dots in phrases.
        self.phraseends = self.atomends.replace('.', '')
        self.field = field
        self.commentlist = []

    def gotonext(self):
233 234
        """Skip white space and extract comments."""
        wslist = []
235 236
        while self.pos < len(self.field):
            if self.field[self.pos] in self.LWS + '\n\r':
237 238
                if self.field[self.pos] not in '\n\r':
                    wslist.append(self.field[self.pos])
239 240 241 242 243
                self.pos += 1
            elif self.field[self.pos] == '(':
                self.commentlist.append(self.getcomment())
            else:
                break
244
        return EMPTYSTRING.join(wslist)
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

    def getaddrlist(self):
        """Parse all addresses.

        Returns a list containing all of the addresses.
        """
        result = []
        while self.pos < len(self.field):
            ad = self.getaddress()
            if ad:
                result += ad
            else:
                result.append(('', ''))
        return result

    def getaddress(self):
        """Parse the next address."""
        self.commentlist = []
        self.gotonext()

        oldpos = self.pos
        oldcl = self.commentlist
        plist = self.getphraselist()

        self.gotonext()
        returnlist = []

        if self.pos >= len(self.field):
            # Bad email address technically, no domain.
            if plist:
                returnlist = [(SPACE.join(self.commentlist), plist[0])]

        elif self.field[self.pos] in '.@':
            # email address is just an addrspec
            # this isn't very efficient since we start over
            self.pos = oldpos
            self.commentlist = oldcl
            addrspec = self.getaddrspec()
            returnlist = [(SPACE.join(self.commentlist), addrspec)]

        elif self.field[self.pos] == ':':
            # address is a group
            returnlist = []

            fieldlen = len(self.field)
            self.pos += 1
            while self.pos < len(self.field):
                self.gotonext()
                if self.pos < fieldlen and self.field[self.pos] == ';':
                    self.pos += 1
                    break
                returnlist = returnlist + self.getaddress()

        elif self.field[self.pos] == '<':
            # Address is a phrase then a route addr
            routeaddr = self.getrouteaddr()

            if self.commentlist:
                returnlist = [(SPACE.join(plist) + ' (' +
                               ' '.join(self.commentlist) + ')', routeaddr)]
            else:
                returnlist = [(SPACE.join(plist), routeaddr)]

        else:
            if plist:
                returnlist = [(SPACE.join(self.commentlist), plist[0])]
            elif self.field[self.pos] in self.specials:
                self.pos += 1

        self.gotonext()
        if self.pos < len(self.field) and self.field[self.pos] == ',':
            self.pos += 1
        return returnlist

    def getrouteaddr(self):
        """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

        expectroute = False
        self.pos += 1
        self.gotonext()
        adlist = ''
        while self.pos < len(self.field):
            if expectroute:
                self.getdomain()
                expectroute = False
            elif self.field[self.pos] == '>':
                self.pos += 1
                break
            elif self.field[self.pos] == '@':
                self.pos += 1
                expectroute = True
            elif self.field[self.pos] == ':':
                self.pos += 1
            else:
                adlist = self.getaddrspec()
                self.pos += 1
                break
            self.gotonext()

        return adlist

    def getaddrspec(self):
        """Parse an RFC 2822 addr-spec."""
        aslist = []

        self.gotonext()
        while self.pos < len(self.field):
357
            preserve_ws = True
358
            if self.field[self.pos] == '.':
359 360
                if aslist and not aslist[-1].strip():
                    aslist.pop()
361 362
                aslist.append('.')
                self.pos += 1
363
                preserve_ws = False
364
            elif self.field[self.pos] == '"':
365
                aslist.append('"%s"' % quote(self.getquote()))
366
            elif self.field[self.pos] in self.atomends:
367 368
                if aslist and not aslist[-1].strip():
                    aslist.pop()
369 370 371
                break
            else:
                aslist.append(self.getatom())
372 373 374
            ws = self.gotonext()
            if preserve_ws and ws:
                aslist.append(ws)
375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540

        if self.pos >= len(self.field) or self.field[self.pos] != '@':
            return EMPTYSTRING.join(aslist)

        aslist.append('@')
        self.pos += 1
        self.gotonext()
        return EMPTYSTRING.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:
                self.pos += 1
            elif self.field[self.pos] == '(':
                self.commentlist.append(self.getcomment())
            elif self.field[self.pos] == '[':
                sdlist.append(self.getdomainliteral())
            elif self.field[self.pos] == '.':
                self.pos += 1
                sdlist.append('.')
            elif self.field[self.pos] in self.atomends:
                break
            else:
                sdlist.append(self.getatom())
        return EMPTYSTRING.join(sdlist)

    def getdelimited(self, beginchar, endchars, allowcomments=True):
        """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 2822 comments are allowed
        within the parsed fragment.
        """
        if self.field[self.pos] != beginchar:
            return ''

        slist = ['']
        quote = False
        self.pos += 1
        while self.pos < len(self.field):
            if quote:
                slist.append(self.field[self.pos])
                quote = False
            elif self.field[self.pos] in endchars:
                self.pos += 1
                break
            elif allowcomments and self.field[self.pos] == '(':
                slist.append(self.getcomment())
                continue        # have already advanced pos from getcomment
            elif self.field[self.pos] == '\\':
                quote = True
            else:
                slist.append(self.field[self.pos])
            self.pos += 1

        return EMPTYSTRING.join(slist)

    def getquote(self):
        """Get a quote-delimited fragment from self's field."""
        return self.getdelimited('"', '"\r', False)

    def getcomment(self):
        """Get a parenthesis-delimited fragment from self's field."""
        return self.getdelimited('(', ')\r', True)

    def getdomainliteral(self):
        """Parse an RFC 2822 domain-literal."""
        return '[%s]' % self.getdelimited('[', ']\r', False)

    def getatom(self, atomends=None):
        """Parse an RFC 2822 atom.

        Optional atomends specifies a different set of end token delimiters
        (the default is to use self.atomends).  This is used e.g. in
        getphraselist() since phrase endings must not include the `.' (which
        is legal in phrases)."""
        atomlist = ['']
        if atomends is None:
            atomends = self.atomends

        while self.pos < len(self.field):
            if self.field[self.pos] in atomends:
                break
            else:
                atomlist.append(self.field[self.pos])
            self.pos += 1

        return EMPTYSTRING.join(atomlist)

    def getphraselist(self):
        """Parse a sequence of RFC 2822 phrases.

        A phrase is a sequence of words, which are in turn either RFC 2822
        atoms or quoted-strings.  Phrases are canonicalized by squeezing all
        runs of continuous whitespace into one space.
        """
        plist = []

        while self.pos < len(self.field):
            if self.field[self.pos] in self.FWS:
                self.pos += 1
            elif self.field[self.pos] == '"':
                plist.append(self.getquote())
            elif self.field[self.pos] == '(':
                self.commentlist.append(self.getcomment())
            elif self.field[self.pos] in self.phraseends:
                break
            else:
                plist.append(self.getatom(self.phraseends))

        return plist

class AddressList(AddrlistClass):
    """An AddressList encapsulates a list of parsed RFC 2822 addresses."""
    def __init__(self, field):
        AddrlistClass.__init__(self, field)
        if field:
            self.addresslist = self.getaddrlist()
        else:
            self.addresslist = []

    def __len__(self):
        return len(self.addresslist)

    def __add__(self, other):
        # Set union
        newaddr = AddressList(None)
        newaddr.addresslist = self.addresslist[:]
        for x in other.addresslist:
            if not x in self.addresslist:
                newaddr.addresslist.append(x)
        return newaddr

    def __iadd__(self, other):
        # Set union, in-place
        for x in other.addresslist:
            if not x in self.addresslist:
                self.addresslist.append(x)
        return self

    def __sub__(self, other):
        # Set difference
        newaddr = AddressList(None)
        for x in self.addresslist:
            if not x in other.addresslist:
                newaddr.addresslist.append(x)
        return newaddr

    def __isub__(self, other):
        # Set difference, in-place
        for x in other.addresslist:
            if x in self.addresslist:
                self.addresslist.remove(x)
        return self

    def __getitem__(self, index):
        # Make indexing, slices, and 'in' work
        return self.addresslist[index]