binhex.py 14.7 KB
Newer Older
1
"""Macintosh binhex compression/decompression.
2

Jack Jansen's avatar
Jack Jansen committed
3 4 5 6 7 8 9 10 11 12 13 14 15
easy interface:
binhex(inputfilename, outputfilename)
hexbin(inputfilename, outputfilename)
"""

#
# Jack Jansen, CWI, August 1995.
#
# The module is supposed to be as compatible as possible. Especially the
# easy interface should work "as expected" on any platform.
# XXXX Note: currently, textfiles appear in mac-form on all platforms.
# We seem to lack a simple character-translate in python.
# (we should probably use ISO-Latin-1 on all but the mac platform).
Jeremy Hylton's avatar
Jeremy Hylton committed
16
# XXXX The simple routines are too simple: they expect to hold the complete
Jack Jansen's avatar
Jack Jansen committed
17
# files in-core. Should be fixed.
18 19
# XXXX It would be nice to handle AppleDouble format on unix
# (for servers serving macs).
Jack Jansen's avatar
Jack Jansen committed
20 21 22 23 24 25 26 27
# XXXX I don't understand what happens when you get 0x90 times the same byte on
# input. The resulting code (xx 90 90) would appear to be interpreted as an
# escaped *value* of 0x90. All coders I've seen appear to ignore this nicety...
#
import sys
import os
import struct
import binascii
Tim Peters's avatar
Tim Peters committed
28

29 30
__all__ = ["binhex","hexbin","Error"]

31 32
class Error(Exception):
    pass
Jack Jansen's avatar
Jack Jansen committed
33 34 35 36 37

# States (what have we written)
[_DID_HEADER, _DID_DATA, _DID_RSRC] = range(3)

# Various constants
38
REASONABLY_LARGE=32768  # Minimal amount we pass the rle-coder
39
LINELEN=64
40
RUNCHAR=chr(0x90)   # run-length introducer
Jack Jansen's avatar
Jack Jansen committed
41 42

#
43
# This code is no longer byte-order dependent
Jack Jansen's avatar
Jack Jansen committed
44 45 46 47

#
# Workarounds for non-mac machines.
if os.name == 'mac':
48 49 50 51 52
    import macfs
    import MacOS
    try:
        openrf = MacOS.openrf
    except AttributeError:
Jeremy Hylton's avatar
Jeremy Hylton committed
53
        # Backward compatibility
54
        openrf = open
Tim Peters's avatar
Tim Peters committed
55

56 57
    def FInfo():
        return macfs.FInfo()
Tim Peters's avatar
Tim Peters committed
58

59 60 61 62 63 64 65 66 67 68 69
    def getfileinfo(name):
        finfo = macfs.FSSpec(name).GetFInfo()
        dir, file = os.path.split(name)
        # XXXX Get resource/data sizes
        fp = open(name, 'rb')
        fp.seek(0, 2)
        dlen = fp.tell()
        fp = openrf(name, '*rb')
        fp.seek(0, 2)
        rlen = fp.tell()
        return file, finfo, dlen, rlen
Tim Peters's avatar
Tim Peters committed
70

71 72 73 74 75 76
    def openrsrc(name, *mode):
        if not mode:
            mode = '*rb'
        else:
            mode = '*' + mode[0]
        return openrf(name, mode)
Jack Jansen's avatar
Jack Jansen committed
77 78

else:
79
    #
80
    # Glue code for non-macintosh usage
81
    #
Tim Peters's avatar
Tim Peters committed
82

83 84 85 86 87 88 89 90 91 92 93 94
    class FInfo:
        def __init__(self):
            self.Type = '????'
            self.Creator = '????'
            self.Flags = 0

    def getfileinfo(name):
        finfo = FInfo()
        # Quick check for textfile
        fp = open(name)
        data = open(name).read(256)
        for c in data:
95
            if not c.isspace() and (c<' ' or ord(c) > 0x7f):
96 97 98 99 100 101 102
                break
        else:
            finfo.Type = 'TEXT'
        fp.seek(0, 2)
        dsize = fp.tell()
        fp.close()
        dir, file = os.path.split(name)
103
        file = file.replace(':', '-', 1)
104 105 106 107 108
        return file, finfo, dsize, 0

    class openrsrc:
        def __init__(self, *args):
            pass
Tim Peters's avatar
Tim Peters committed
109

110 111
        def read(self, *args):
            return ''
Tim Peters's avatar
Tim Peters committed
112

113 114
        def write(self, *args):
            pass
Tim Peters's avatar
Tim Peters committed
115

116 117
        def close(self):
            pass
Tim Peters's avatar
Tim Peters committed
118

Jack Jansen's avatar
Jack Jansen committed
119
class _Hqxcoderengine:
120
    """Write data to the coder in 3-byte chunks"""
Tim Peters's avatar
Tim Peters committed
121

122 123 124 125 126 127 128 129 130
    def __init__(self, ofp):
        self.ofp = ofp
        self.data = ''
        self.hqxdata = ''
        self.linelen = LINELEN-1

    def write(self, data):
        self.data = self.data + data
        datalen = len(self.data)
131
        todo = (datalen//3)*3
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
        data = self.data[:todo]
        self.data = self.data[todo:]
        if not data:
            return
        self.hqxdata = self.hqxdata + binascii.b2a_hqx(data)
        self._flush(0)

    def _flush(self, force):
        first = 0
        while first <= len(self.hqxdata)-self.linelen:
            last = first + self.linelen
            self.ofp.write(self.hqxdata[first:last]+'\n')
            self.linelen = LINELEN
            first = last
        self.hqxdata = self.hqxdata[first:]
        if force:
            self.ofp.write(self.hqxdata + ':\n')

    def close(self):
        if self.data:
            self.hqxdata = \
                 self.hqxdata + binascii.b2a_hqx(self.data)
        self._flush(1)
        self.ofp.close()
        del self.ofp
Jack Jansen's avatar
Jack Jansen committed
157 158

class _Rlecoderengine:
159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178
    """Write data to the RLE-coder in suitably large chunks"""

    def __init__(self, ofp):
        self.ofp = ofp
        self.data = ''

    def write(self, data):
        self.data = self.data + data
        if len(self.data) < REASONABLY_LARGE:
            return
        rledata = binascii.rlecode_hqx(self.data)
        self.ofp.write(rledata)
        self.data = ''

    def close(self):
        if self.data:
            rledata = binascii.rlecode_hqx(self.data)
            self.ofp.write(rledata)
        self.ofp.close()
        del self.ofp
Jack Jansen's avatar
Jack Jansen committed
179 180

class BinHex:
181 182 183 184 185 186 187 188 189 190 191
    def __init__(self, (name, finfo, dlen, rlen), ofp):
        if type(ofp) == type(''):
            ofname = ofp
            ofp = open(ofname, 'w')
            if os.name == 'mac':
                fss = macfs.FSSpec(ofname)
                fss.SetCreatorType('BnHq', 'TEXT')
        ofp.write('(This file must be converted with BinHex 4.0)\n\n:')
        hqxer = _Hqxcoderengine(ofp)
        self.ofp = _Rlecoderengine(hqxer)
        self.crc = 0
192
        if finfo is None:
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
            finfo = FInfo()
        self.dlen = dlen
        self.rlen = rlen
        self._writeinfo(name, finfo)
        self.state = _DID_HEADER

    def _writeinfo(self, name, finfo):
        name = name
        nl = len(name)
        if nl > 63:
            raise Error, 'Filename too long'
        d = chr(nl) + name + '\0'
        d2 = finfo.Type + finfo.Creator

        # Force all structs to be packed with big-endian
        d3 = struct.pack('>h', finfo.Flags)
        d4 = struct.pack('>ii', self.dlen, self.rlen)
        info = d + d2 + d3 + d4
        self._write(info)
        self._writecrc()

    def _write(self, data):
        self.crc = binascii.crc_hqx(data, self.crc)
        self.ofp.write(data)

    def _writecrc(self):
        # XXXX Should this be here??
        # self.crc = binascii.crc_hqx('\0\0', self.crc)
        self.ofp.write(struct.pack('>h', self.crc))
        self.crc = 0

    def write(self, data):
        if self.state != _DID_HEADER:
            raise Error, 'Writing data at the wrong time'
        self.dlen = self.dlen - len(data)
        self._write(data)

    def close_data(self):
231
        if self.dlen != 0:
232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248
            raise Error, 'Incorrect data size, diff='+`self.rlen`
        self._writecrc()
        self.state = _DID_DATA

    def write_rsrc(self, data):
        if self.state < _DID_DATA:
            self.close_data()
        if self.state != _DID_DATA:
            raise Error, 'Writing resource data at the wrong time'
        self.rlen = self.rlen - len(data)
        self._write(data)

    def close(self):
        if self.state < _DID_DATA:
            self.close_data()
        if self.state != _DID_DATA:
            raise Error, 'Close at the wrong time'
249
        if self.rlen != 0:
250 251 252 253 254 255
            raise Error, \
                  "Incorrect resource-datasize, diff="+`self.rlen`
        self._writecrc()
        self.ofp.close()
        self.state = None
        del self.ofp
Tim Peters's avatar
Tim Peters committed
256

Jack Jansen's avatar
Jack Jansen committed
257
def binhex(inp, out):
258 259 260
    """(infilename, outfilename) - Create binhex-encoded copy of a file"""
    finfo = getfileinfo(inp)
    ofp = BinHex(finfo, out)
Tim Peters's avatar
Tim Peters committed
261

262 263 264 265 266 267 268 269 270 271 272 273 274 275 276
    ifp = open(inp, 'rb')
    # XXXX Do textfile translation on non-mac systems
    while 1:
        d = ifp.read(128000)
        if not d: break
        ofp.write(d)
    ofp.close_data()
    ifp.close()

    ifp = openrsrc(inp, 'rb')
    while 1:
        d = ifp.read(128000)
        if not d: break
        ofp.write_rsrc(d)
    ofp.close()
Tim Peters's avatar
Tim Peters committed
277
    ifp.close()
Jack Jansen's avatar
Jack Jansen committed
278 279

class _Hqxdecoderengine:
280
    """Read data via the decoder in 4-byte chunks"""
Tim Peters's avatar
Tim Peters committed
281

282 283 284 285 286 287 288 289 290
    def __init__(self, ifp):
        self.ifp = ifp
        self.eof = 0

    def read(self, totalwtd):
        """Read at least wtd bytes (or until EOF)"""
        decdata = ''
        wtd = totalwtd
        #
Tim Peters's avatar
Tim Peters committed
291
        # The loop here is convoluted, since we don't really now how
292 293 294
        # much to decode: there may be newlines in the incoming data.
        while wtd > 0:
            if self.eof: return decdata
295
            wtd = ((wtd+2)//3)*4
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
            data = self.ifp.read(wtd)
            #
            # Next problem: there may not be a complete number of
            # bytes in what we pass to a2b. Solve by yet another
            # loop.
            #
            while 1:
                try:
                    decdatacur, self.eof = \
                            binascii.a2b_hqx(data)
                    break
                except binascii.Incomplete:
                    pass
                newdata = self.ifp.read(1)
                if not newdata:
                    raise Error, \
                          'Premature EOF on binhex file'
                data = data + newdata
            decdata = decdata + decdatacur
            wtd = totalwtd - len(decdata)
            if not decdata and not self.eof:
                raise Error, 'Premature EOF on binhex file'
        return decdata

    def close(self):
        self.ifp.close()
Jack Jansen's avatar
Jack Jansen committed
322 323

class _Rledecoderengine:
324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345
    """Read data via the RLE-coder"""

    def __init__(self, ifp):
        self.ifp = ifp
        self.pre_buffer = ''
        self.post_buffer = ''
        self.eof = 0

    def read(self, wtd):
        if wtd > len(self.post_buffer):
            self._fill(wtd-len(self.post_buffer))
        rv = self.post_buffer[:wtd]
        self.post_buffer = self.post_buffer[wtd:]
        return rv

    def _fill(self, wtd):
        self.pre_buffer = self.pre_buffer + self.ifp.read(wtd+4)
        if self.ifp.eof:
            self.post_buffer = self.post_buffer + \
                binascii.rledecode_hqx(self.pre_buffer)
            self.pre_buffer = ''
            return
Tim Peters's avatar
Tim Peters committed
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
        #
        # Obfuscated code ahead. We have to take care that we don't
        # end up with an orphaned RUNCHAR later on. So, we keep a couple
        # of bytes in the buffer, depending on what the end of
        # the buffer looks like:
        # '\220\0\220' - Keep 3 bytes: repeated \220 (escaped as \220\0)
        # '?\220' - Keep 2 bytes: repeated something-else
        # '\220\0' - Escaped \220: Keep 2 bytes.
        # '?\220?' - Complete repeat sequence: decode all
        # otherwise: keep 1 byte.
        #
        mark = len(self.pre_buffer)
        if self.pre_buffer[-3:] == RUNCHAR + '\0' + RUNCHAR:
            mark = mark - 3
        elif self.pre_buffer[-1] == RUNCHAR:
            mark = mark - 2
        elif self.pre_buffer[-2:] == RUNCHAR + '\0':
            mark = mark - 2
        elif self.pre_buffer[-2] == RUNCHAR:
            pass # Decode all
        else:
            mark = mark - 1

        self.post_buffer = self.post_buffer + \
            binascii.rledecode_hqx(self.pre_buffer[:mark])
        self.pre_buffer = self.pre_buffer[mark:]

    def close(self):
        self.ifp.close()
Jack Jansen's avatar
Jack Jansen committed
376 377

class HexBin:
378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395
    def __init__(self, ifp):
        if type(ifp) == type(''):
            ifp = open(ifp)
        #
        # Find initial colon.
        #
        while 1:
            ch = ifp.read(1)
            if not ch:
                raise Error, "No binhex data found"
            # Cater for \r\n terminated lines (which show up as \n\r, hence
            # all lines start with \r)
            if ch == '\r':
                continue
            if ch == ':':
                break
            if ch != '\n':
                dummy = ifp.readline()
Tim Peters's avatar
Tim Peters committed
396

397 398 399 400
        hqxifp = _Hqxdecoderengine(ifp)
        self.ifp = _Rledecoderengine(hqxifp)
        self.crc = 0
        self._readheader()
Tim Peters's avatar
Tim Peters committed
401

402 403 404 405
    def _read(self, len):
        data = self.ifp.read(len)
        self.crc = binascii.crc_hqx(data, self.crc)
        return data
Tim Peters's avatar
Tim Peters committed
406

407 408 409 410 411 412 413 414 415 416 417 418 419 420 421
    def _checkcrc(self):
        filecrc = struct.unpack('>h', self.ifp.read(2))[0] & 0xffff
        #self.crc = binascii.crc_hqx('\0\0', self.crc)
        # XXXX Is this needed??
        self.crc = self.crc & 0xffff
        if filecrc != self.crc:
            raise Error, 'CRC error, computed %x, read %x' \
                  %(self.crc, filecrc)
        self.crc = 0

    def _readheader(self):
        len = self._read(1)
        fname = self._read(ord(len))
        rest = self._read(1+4+4+2+4+4)
        self._checkcrc()
Tim Peters's avatar
Tim Peters committed
422

423 424 425 426 427
        type = rest[1:5]
        creator = rest[5:9]
        flags = struct.unpack('>h', rest[9:11])[0]
        self.dlen = struct.unpack('>l', rest[11:15])[0]
        self.rlen = struct.unpack('>l', rest[15:19])[0]
Tim Peters's avatar
Tim Peters committed
428

429 430 431 432 433
        self.FName = fname
        self.FInfo = FInfo()
        self.FInfo.Creator = creator
        self.FInfo.Type = type
        self.FInfo.Flags = flags
Tim Peters's avatar
Tim Peters committed
434

435
        self.state = _DID_HEADER
Tim Peters's avatar
Tim Peters committed
436

437 438 439 440 441 442 443 444 445 446 447 448 449
    def read(self, *n):
        if self.state != _DID_HEADER:
            raise Error, 'Read data at wrong time'
        if n:
            n = n[0]
            n = min(n, self.dlen)
        else:
            n = self.dlen
        rv = ''
        while len(rv) < n:
            rv = rv + self._read(n-len(rv))
        self.dlen = self.dlen - n
        return rv
Tim Peters's avatar
Tim Peters committed
450

451 452 453 454 455 456 457
    def close_data(self):
        if self.state != _DID_HEADER:
            raise Error, 'close_data at wrong time'
        if self.dlen:
            dummy = self._read(self.dlen)
        self._checkcrc()
        self.state = _DID_DATA
Tim Peters's avatar
Tim Peters committed
458

459 460 461 462 463 464 465 466 467 468 469 470
    def read_rsrc(self, *n):
        if self.state == _DID_HEADER:
            self.close_data()
        if self.state != _DID_DATA:
            raise Error, 'Read resource data at wrong time'
        if n:
            n = n[0]
            n = min(n, self.rlen)
        else:
            n = self.rlen
        self.rlen = self.rlen - n
        return self._read(n)
Tim Peters's avatar
Tim Peters committed
471

472 473 474 475 476 477
    def close(self):
        if self.rlen:
            dummy = self.read_rsrc(self.rlen)
        self._checkcrc()
        self.state = _DID_RSRC
        self.ifp.close()
Tim Peters's avatar
Tim Peters committed
478

Jack Jansen's avatar
Jack Jansen committed
479
def hexbin(inp, out):
480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496
    """(infilename, outfilename) - Decode binhexed file"""
    ifp = HexBin(inp)
    finfo = ifp.FInfo
    if not out:
        out = ifp.FName
    if os.name == 'mac':
        ofss = macfs.FSSpec(out)
        out = ofss.as_pathname()

    ofp = open(out, 'wb')
    # XXXX Do translation on non-mac systems
    while 1:
        d = ifp.read(128000)
        if not d: break
        ofp.write(d)
    ofp.close()
    ifp.close_data()
Tim Peters's avatar
Tim Peters committed
497

498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513
    d = ifp.read_rsrc(128000)
    if d:
        ofp = openrsrc(out, 'wb')
        ofp.write(d)
        while 1:
            d = ifp.read_rsrc(128000)
            if not d: break
            ofp.write(d)
        ofp.close()

    if os.name == 'mac':
        nfinfo = ofss.GetFInfo()
        nfinfo.Creator = finfo.Creator
        nfinfo.Type = finfo.Type
        nfinfo.Flags = finfo.Flags
        ofss.SetFInfo(nfinfo)
Tim Peters's avatar
Tim Peters committed
514

515
    ifp.close()
Jack Jansen's avatar
Jack Jansen committed
516 517

def _test():
518 519 520 521 522 523 524 525 526 527 528
    if os.name == 'mac':
        fss, ok = macfs.PromptGetFile('File to convert:')
        if not ok:
            sys.exit(0)
        fname = fss.as_pathname()
    else:
        fname = sys.argv[1]
    binhex(fname, fname+'.hqx')
    hexbin(fname+'.hqx', fname+'.viahqx')
    #hexbin(fname, fname+'.unpacked')
    sys.exit(1)
Tim Peters's avatar
Tim Peters committed
529

Jack Jansen's avatar
Jack Jansen committed
530
if __name__ == '__main__':
531
    _test()