[1482] | 1 | # PyKota |
---|
| 2 | # -*- coding: ISO-8859-15 -*- |
---|
| 3 | # |
---|
| 4 | # PyKota - Print Quotas for CUPS and LPRng |
---|
| 5 | # |
---|
| 6 | # (c) 2003-2004 Jerome Alet <alet@librelogiciel.com> |
---|
| 7 | # This program is free software; you can redistribute it and/or modify |
---|
| 8 | # it under the terms of the GNU General Public License as published by |
---|
| 9 | # the Free Software Foundation; either version 2 of the License, or |
---|
| 10 | # (at your option) any later version. |
---|
| 11 | # |
---|
| 12 | # This program is distributed in the hope that it will be useful, |
---|
| 13 | # but WITHOUT ANY WARRANTY; without even the implied warranty of |
---|
| 14 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
---|
| 15 | # GNU General Public License for more details. |
---|
| 16 | # |
---|
| 17 | # You should have received a copy of the GNU General Public License |
---|
| 18 | # along with this program; if not, write to the Free Software |
---|
| 19 | # Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307, USA. |
---|
| 20 | # |
---|
| 21 | # $Id$ |
---|
| 22 | # |
---|
| 23 | # $Log$ |
---|
[1550] | 24 | # Revision 1.7 2004/06/18 17:48:04 jalet |
---|
| 25 | # Added native fast PDF parsing method |
---|
| 26 | # |
---|
[1547] | 27 | # Revision 1.6 2004/06/18 14:00:16 jalet |
---|
| 28 | # Added PDF support in smart PDL analyzer (through GhostScript for now) |
---|
| 29 | # |
---|
[1544] | 30 | # Revision 1.5 2004/06/18 10:09:05 jalet |
---|
| 31 | # Resets file pointer to start of file in all cases |
---|
| 32 | # |
---|
[1543] | 33 | # Revision 1.4 2004/06/18 06:16:14 jalet |
---|
| 34 | # Fixes PostScript detection code for incorrect drivers |
---|
| 35 | # |
---|
[1487] | 36 | # Revision 1.3 2004/05/21 20:40:08 jalet |
---|
| 37 | # All the code for pkpgcounter is now in pdlanalyzer.py |
---|
| 38 | # |
---|
[1485] | 39 | # Revision 1.2 2004/05/19 19:09:36 jalet |
---|
| 40 | # Speed improvement |
---|
| 41 | # |
---|
[1482] | 42 | # Revision 1.1 2004/05/18 09:59:54 jalet |
---|
| 43 | # pkpgcounter is now just a wrapper around the PDLAnalyzer class |
---|
| 44 | # |
---|
| 45 | # |
---|
| 46 | # |
---|
| 47 | |
---|
| 48 | import sys |
---|
[1547] | 49 | import os |
---|
[1482] | 50 | import struct |
---|
| 51 | import tempfile |
---|
[1547] | 52 | import popen2 |
---|
[1482] | 53 | |
---|
[1487] | 54 | KILOBYTE = 1024 |
---|
| 55 | MEGABYTE = 1024 * KILOBYTE |
---|
| 56 | |
---|
| 57 | class PDLAnalyzerError(Exception): |
---|
| 58 | """An exception for PDL Analyzer related stuff.""" |
---|
| 59 | def __init__(self, message = ""): |
---|
| 60 | self.message = message |
---|
| 61 | Exception.__init__(self, message) |
---|
| 62 | def __repr__(self): |
---|
| 63 | return self.message |
---|
| 64 | __str__ = __repr__ |
---|
| 65 | |
---|
[1482] | 66 | class PostScriptAnalyzer : |
---|
| 67 | def __init__(self, infile) : |
---|
| 68 | """Initialize PostScript Analyzer.""" |
---|
| 69 | self.infile = infile |
---|
| 70 | |
---|
| 71 | def getJobSize(self) : |
---|
| 72 | """Count pages in a DSC compliant PostScript document.""" |
---|
| 73 | pagecount = 0 |
---|
| 74 | while 1 : |
---|
| 75 | line = self.infile.readline() |
---|
| 76 | if not line : |
---|
| 77 | break |
---|
| 78 | if line.startswith("%%Page: ") : |
---|
| 79 | pagecount += 1 |
---|
| 80 | return pagecount |
---|
| 81 | |
---|
[1547] | 82 | class PDFAnalyzer : |
---|
| 83 | def __init__(self, infile) : |
---|
| 84 | """Initialize PDF Analyzer.""" |
---|
| 85 | self.infile = infile |
---|
[1550] | 86 | try : |
---|
| 87 | if float(sys.version[:3]) >= 2.3 : |
---|
| 88 | self.getJobSize = self.native_getJobSize |
---|
| 89 | else : |
---|
| 90 | self.getJobSize = self.gs_getJobSize |
---|
| 91 | except : |
---|
| 92 | self.getJobSize = self.gs_getJobSize |
---|
| 93 | |
---|
| 94 | def native_getJobSize(self) : |
---|
| 95 | """Counts pages in a PDF document natively.""" |
---|
| 96 | pagecount = 0 |
---|
| 97 | content = [] |
---|
| 98 | while 1 : |
---|
| 99 | line = self.infile.readline() |
---|
| 100 | if not line : |
---|
| 101 | break |
---|
| 102 | line = line.strip() |
---|
| 103 | content.append(line) |
---|
| 104 | if line.endswith("endobj") : |
---|
| 105 | pagecount += " /".join([x.strip() for x in " ".join(content).split("/")]).count(" /Type /Page ") |
---|
| 106 | content = [] |
---|
| 107 | return pagecount |
---|
[1547] | 108 | |
---|
[1550] | 109 | def gs_getJobSize(self) : |
---|
| 110 | """Counts pages in a PDF document using GhostScript to convert PDF to PS.""" |
---|
[1547] | 111 | MEGABYTE = 1024*1024 |
---|
| 112 | child = popen2.Popen4("gs -q -dNOPAUSE -dBATCH -dSAFER -sDEVICE=pswrite -sOutputFile=- -c save pop -f - 2>/dev/null") |
---|
| 113 | try : |
---|
| 114 | data = self.infile.read(MEGABYTE) |
---|
| 115 | while data : |
---|
| 116 | child.tochild.write(data) |
---|
| 117 | data = self.infile.read(MEGABYTE) |
---|
| 118 | child.tochild.flush() |
---|
| 119 | child.tochild.close() |
---|
| 120 | except (IOError, OSError), msg : |
---|
| 121 | raise PDLAnalyzerError, "Unable to convert PDF input to PS with GhostScript : %s" % msg |
---|
| 122 | |
---|
| 123 | psanalyzer = PostScriptAnalyzer(child.fromchild) |
---|
| 124 | pagecount = psanalyzer.getJobSize() |
---|
| 125 | child.fromchild.close() |
---|
| 126 | try : |
---|
| 127 | retcode = child.wait() |
---|
| 128 | except OSError, msg : |
---|
| 129 | self.filter.logger.log_message(_("Problem while waiting for PDF to PS converter (GhostScript pid %s) to exit : %s") % (child.pid, msg)) |
---|
| 130 | else : |
---|
| 131 | if os.WIFEXITED(retcode) : |
---|
| 132 | status = os.WEXITSTATUS(retcode) |
---|
| 133 | else : |
---|
| 134 | status = retcode |
---|
| 135 | if status : |
---|
| 136 | raise PDLAnalyzerError, "PDF to PS converter (GhostScript pid %s) exit code is %s" % (child.pid, repr(status)) |
---|
| 137 | return pagecount |
---|
| 138 | |
---|
[1482] | 139 | class PCLAnalyzer : |
---|
| 140 | def __init__(self, infile) : |
---|
| 141 | """Initialize PCL Analyzer.""" |
---|
| 142 | self.infile = infile |
---|
| 143 | |
---|
[1485] | 144 | def skip(self, nb) : |
---|
| 145 | """Reads a new datablock.""" |
---|
| 146 | newpos = self.pos + nb |
---|
| 147 | if newpos >= self.len : |
---|
| 148 | oldlen = self.len |
---|
[1487] | 149 | self.data = self.infile.read(MEGABYTE) |
---|
[1485] | 150 | self.len = len(self.data) |
---|
| 151 | if not self.len : |
---|
| 152 | return |
---|
| 153 | self.pos = newpos - oldlen |
---|
| 154 | else : |
---|
| 155 | self.pos = newpos |
---|
| 156 | |
---|
| 157 | def readone(self) : |
---|
| 158 | """Reads a new byte.""" |
---|
| 159 | if self.pos < self.len : |
---|
| 160 | char = self.data[self.pos] |
---|
| 161 | else : |
---|
[1487] | 162 | self.data = self.infile.read(MEGABYTE) |
---|
[1485] | 163 | self.len = len(self.data) |
---|
| 164 | self.pos = 0 |
---|
| 165 | if not self.len : |
---|
| 166 | return |
---|
| 167 | char = self.data[0] |
---|
| 168 | self.pos += 1 |
---|
| 169 | return char |
---|
| 170 | |
---|
[1482] | 171 | def getJobSize(self) : |
---|
| 172 | """Count pages in a PCL5 document.""" |
---|
| 173 | # |
---|
| 174 | # Algorithm from pclcount |
---|
| 175 | # (c) 2003, by Eduardo Gielamo Oliveira & Rodolfo Broco Manin |
---|
| 176 | # published under the terms of the GNU General Public Licence v2. |
---|
| 177 | # |
---|
| 178 | # Backported from C to Python by Jerome Alet, then enhanced |
---|
| 179 | # with more PCL tags detected. I think all the necessary PCL tags |
---|
| 180 | # are recognized to correctly handle PCL5 files wrt their number |
---|
| 181 | # of pages. The documentation used for this was : |
---|
| 182 | # |
---|
| 183 | # HP PCL/PJL Reference Set |
---|
| 184 | # PCL5 Printer Language Technical Quick Reference Guide |
---|
| 185 | # http://h20000.www2.hp.com/bc/docs/support/SupportManual/bpl13205/bpl13205.pdf |
---|
| 186 | # |
---|
| 187 | tagsends = { "&n" : "W", |
---|
| 188 | "&b" : "W", |
---|
| 189 | "*i" : "W", |
---|
| 190 | "*l" : "W", |
---|
| 191 | "*m" : "W", |
---|
| 192 | "*v" : "W", |
---|
| 193 | "*c" : "W", |
---|
| 194 | "(f" : "W", |
---|
| 195 | "*b" : "VW", |
---|
| 196 | "(s" : "W", |
---|
| 197 | ")s" : "W", |
---|
| 198 | "&p" : "X", |
---|
| 199 | "&l" : "X" } |
---|
[1485] | 200 | self.data = [] |
---|
| 201 | self.pos = self.len = 0 |
---|
[1482] | 202 | copies = 1 |
---|
| 203 | pagecount = resets = 0 |
---|
| 204 | tag = None |
---|
| 205 | while 1 : |
---|
[1485] | 206 | char = self.readone() |
---|
[1482] | 207 | if not char : # EOF ? |
---|
| 208 | break |
---|
| 209 | if char == "\014" : |
---|
| 210 | pagecount += 1 |
---|
| 211 | elif char == "\033" : |
---|
| 212 | # |
---|
| 213 | # <ESC>*b###W -> Start of a raster data row/block |
---|
| 214 | # <ESC>*b###V -> Start of a raster data plane |
---|
| 215 | # <ESC>*c###W -> Start of a user defined pattern |
---|
| 216 | # <ESC>*i###W -> Start of a viewing illuminant block |
---|
| 217 | # <ESC>*l###W -> Start of a color lookup table |
---|
| 218 | # <ESC>*m###W -> Start of a download dither matrix block |
---|
| 219 | # <ESC>*v###W -> Start of a configure image data block |
---|
| 220 | # <ESC>(s###W -> Start of a characters description block |
---|
| 221 | # <ESC>)s###W -> Start of a fonts description block |
---|
| 222 | # <ESC>(f###W -> Start of a symbol set block |
---|
| 223 | # <ESC>&b###W -> Start of configuration data block |
---|
| 224 | # <ESC>&l###X -> Number of copies |
---|
| 225 | # <ESC>&n###W -> Starts an alphanumeric string ID block |
---|
| 226 | # <ESC>&p###X -> Start of a non printable characters block |
---|
| 227 | # |
---|
[1485] | 228 | tagstart = self.readone() |
---|
[1482] | 229 | if tagstart in "E9=YZ" : # one byte PCL tag |
---|
| 230 | if tagstart == "E" : |
---|
| 231 | resets += 1 |
---|
| 232 | continue # skip to next tag |
---|
[1485] | 233 | tag = tagstart + self.readone() |
---|
[1482] | 234 | try : |
---|
| 235 | tagend = tagsends[tag] |
---|
| 236 | except KeyError : |
---|
| 237 | pass # Unsupported PCL tag |
---|
| 238 | else : |
---|
| 239 | # Now read the numeric argument |
---|
| 240 | size = 0 |
---|
| 241 | while 1 : |
---|
[1485] | 242 | char = self.readone() |
---|
[1482] | 243 | if not char.isdigit() : |
---|
| 244 | break |
---|
| 245 | size = (size * 10) + int(char) |
---|
| 246 | if char in tagend : |
---|
| 247 | if tag == "&l" : |
---|
| 248 | copies = size |
---|
| 249 | else : |
---|
| 250 | # doing a read will prevent the seek |
---|
| 251 | # for unseekable streams. |
---|
| 252 | # we just ignore the block anyway. |
---|
| 253 | if tag == "&n" : |
---|
| 254 | # we have to take care of the operation id byte |
---|
| 255 | # which is before the string itself |
---|
| 256 | size += 1 |
---|
[1485] | 257 | self.skip(size) |
---|
[1482] | 258 | |
---|
| 259 | # if pagecount is still 0, we will return the number |
---|
| 260 | # of resets instead of the number of form feed characters. |
---|
| 261 | # but the number of resets is always at least 2 with a valid |
---|
| 262 | # pcl file : one at the very start and one at the very end |
---|
| 263 | # of the job's data. So we substract 2 from the number of |
---|
| 264 | # resets. And since on our test data we needed to substract |
---|
| 265 | # 1 more, we finally substract 3, and will test several |
---|
| 266 | # PCL files with this. If resets < 2, then the file is |
---|
| 267 | # probably not a valid PCL file, so we return 0 |
---|
[1487] | 268 | return copies * (pagecount or ((resets - 3) * (resets > 2))) |
---|
[1482] | 269 | |
---|
| 270 | class PCLXLAnalyzer : |
---|
| 271 | def __init__(self, infile) : |
---|
| 272 | """Initialize PCLXL Analyzer.""" |
---|
[1487] | 273 | raise PDLAnalyzerError, "PCLXL (aka PCL6) is not supported yet." |
---|
[1482] | 274 | self.infile = infile |
---|
| 275 | self.islittleendian = None |
---|
| 276 | found = 0 |
---|
| 277 | while not found : |
---|
| 278 | line = self.infile.readline() |
---|
| 279 | if not line : |
---|
| 280 | break |
---|
| 281 | if line[1:12] == " HP-PCL XL;" : |
---|
| 282 | found = 1 |
---|
| 283 | if line[0] == ")" : |
---|
| 284 | self.littleendian() |
---|
| 285 | elif line[0] == "(" : |
---|
| 286 | self.bigendian() |
---|
| 287 | if not found : |
---|
[1487] | 288 | raise PDLAnalyzerError, "This file doesn't seem to be PCLXL (aka PCL6)" |
---|
[1482] | 289 | else : |
---|
[1487] | 290 | self.tags = [lambda: None] * 256 |
---|
[1482] | 291 | self.tags[0x28] = self.bigendian # big endian |
---|
| 292 | self.tags[0x29] = self.littleendian # big endian |
---|
| 293 | self.tags[0x43] = self.beginPage # BeginPage |
---|
| 294 | self.tags[0x44] = self.endPage # EndPage |
---|
| 295 | |
---|
[1487] | 296 | self.tags[0xc0] = lambda: 1 # ubyte |
---|
| 297 | self.tags[0xc1] = lambda: 2 # uint16 |
---|
| 298 | self.tags[0xc2] = lambda: 4 # uint32 |
---|
| 299 | self.tags[0xc3] = lambda: 2 # sint16 |
---|
| 300 | self.tags[0xc4] = lambda: 4 # sint32 |
---|
| 301 | self.tags[0xc5] = lambda: 4 # real32 |
---|
[1482] | 302 | |
---|
| 303 | self.tags[0xc8] = self.array_8 # ubyte_array |
---|
| 304 | self.tags[0xc9] = self.array_16 # uint16_array |
---|
| 305 | self.tags[0xca] = self.array_32 # uint32_array |
---|
| 306 | self.tags[0xcb] = self.array_16 # sint16_array |
---|
| 307 | self.tags[0xcc] = self.array_32 # sint32_array |
---|
| 308 | self.tags[0xcd] = self.array_32 # real32_array |
---|
| 309 | |
---|
[1487] | 310 | self.tags[0xd0] = lambda: 2 # ubyte_xy |
---|
| 311 | self.tags[0xd1] = lambda: 4 # uint16_xy |
---|
| 312 | self.tags[0xd2] = lambda: 8 # uint32_xy |
---|
| 313 | self.tags[0xd3] = lambda: 4 # sint16_xy |
---|
| 314 | self.tags[0xd4] = lambda: 8 # sint32_xy |
---|
| 315 | self.tags[0xd5] = lambda: 8 # real32_xy |
---|
[1482] | 316 | |
---|
[1487] | 317 | self.tags[0xd0] = lambda: 4 # ubyte_box |
---|
| 318 | self.tags[0xd1] = lambda: 8 # uint16_box |
---|
| 319 | self.tags[0xd2] = lambda: 16 # uint32_box |
---|
| 320 | self.tags[0xd3] = lambda: 8 # sint16_box |
---|
| 321 | self.tags[0xd4] = lambda: 16 # sint32_box |
---|
| 322 | self.tags[0xd5] = lambda: 16 # real32_box |
---|
[1482] | 323 | |
---|
[1487] | 324 | self.tags[0xf8] = lambda: 1 # attr_ubyte |
---|
| 325 | self.tags[0xf9] = lambda: 2 # attr_uint16 |
---|
[1482] | 326 | |
---|
| 327 | self.tags[0xfa] = self.embeddedData # dataLength |
---|
| 328 | self.tags[0xfb] = self.embeddedDataSmall # dataLengthByte |
---|
| 329 | |
---|
| 330 | def debug(self, msg) : |
---|
| 331 | """Outputs a debug message on stderr.""" |
---|
| 332 | sys.stderr.write("%s\n" % msg) |
---|
| 333 | sys.stderr.flush() |
---|
| 334 | |
---|
| 335 | def beginPage(self) : |
---|
| 336 | """Indicates the beginning of a new page.""" |
---|
| 337 | self.pagecount += 1 |
---|
| 338 | self.debug("Begin page %i at %s" % (self.pagecount, self.infile.tell())) |
---|
| 339 | |
---|
| 340 | def endPage(self) : |
---|
| 341 | """Indicates the end of a page.""" |
---|
| 342 | self.debug("End page %i at %s" % (self.pagecount, self.infile.tell())) |
---|
| 343 | |
---|
| 344 | def handleArray(self, itemsize) : |
---|
| 345 | """Handles arrays.""" |
---|
[1487] | 346 | pos = self.infile.tell() |
---|
[1482] | 347 | datatype = self.infile.read(1) |
---|
[1487] | 348 | length = self.tags[ord(datatype)]() |
---|
| 349 | if length is None : |
---|
| 350 | self.debug("Bogus array length at %s" % pos) |
---|
[1482] | 351 | else : |
---|
[1487] | 352 | sarraysize = self.infile.read(length) |
---|
| 353 | if self.islittleendian : |
---|
| 354 | fmt = "<" |
---|
| 355 | else : |
---|
| 356 | fmt = ">" |
---|
| 357 | if length == 1 : |
---|
| 358 | fmt += "B" |
---|
| 359 | elif length == 2 : |
---|
| 360 | fmt += "H" |
---|
| 361 | elif length == 4 : |
---|
| 362 | fmt += "I" |
---|
| 363 | else : |
---|
| 364 | raise PDLAnalyzerError, "Error on array size at %s" % self.infile.tell() |
---|
| 365 | arraysize = struct.unpack(fmt, sarraysize)[0] |
---|
| 366 | self.debug("Array at %s, itemsize %s, datatype 0x%02x, size %s" % (pos, itemsize, ord(datatype), arraysize)) |
---|
| 367 | return arraysize * itemsize |
---|
[1482] | 368 | |
---|
| 369 | def array_8(self) : |
---|
| 370 | """Handles byte arrays.""" |
---|
| 371 | return self.handleArray(1) |
---|
| 372 | |
---|
| 373 | def array_16(self) : |
---|
| 374 | """Handles byte arrays.""" |
---|
| 375 | return self.handleArray(2) |
---|
| 376 | |
---|
| 377 | def array_32(self) : |
---|
| 378 | """Handles byte arrays.""" |
---|
| 379 | return self.handleArray(4) |
---|
| 380 | |
---|
| 381 | def embeddedDataSmall(self) : |
---|
| 382 | """Handle small amounts of data.""" |
---|
[1487] | 383 | pos = self.infile.tell() |
---|
| 384 | val = ord(self.infile.read(1)) |
---|
| 385 | self.debug("smalldatablock at %s (0x%02x)" % (pos, val)) |
---|
| 386 | return val |
---|
[1482] | 387 | |
---|
| 388 | def embeddedData(self) : |
---|
| 389 | """Handle normal amounts of data.""" |
---|
| 390 | if self.islittleendian : |
---|
| 391 | fmt = "<I" |
---|
| 392 | else : |
---|
| 393 | fmt = ">I" |
---|
[1487] | 394 | pos = self.infile.tell() |
---|
| 395 | val = struct.unpack(fmt, self.infile.read(4))[0] |
---|
| 396 | self.debug("datablock at %s (0x%08x)" % (pos, val)) |
---|
| 397 | return val |
---|
[1482] | 398 | |
---|
| 399 | def littleendian(self) : |
---|
| 400 | """Toggles to little endianness.""" |
---|
| 401 | self.islittleendian = 1 # little endian |
---|
| 402 | |
---|
| 403 | def bigendian(self) : |
---|
| 404 | """Toggles to big endianness.""" |
---|
| 405 | self.islittleendian = 0 # big endian |
---|
| 406 | |
---|
| 407 | def getJobSize(self) : |
---|
| 408 | """Counts pages in a PCLXL (PCL6) document.""" |
---|
| 409 | self.pagecount = 0 |
---|
| 410 | while 1 : |
---|
| 411 | char = self.infile.read(1) |
---|
| 412 | if not char : |
---|
| 413 | break |
---|
| 414 | index = ord(char) |
---|
[1487] | 415 | length = self.tags[index]() |
---|
| 416 | if length : |
---|
| 417 | self.infile.read(length) |
---|
[1482] | 418 | return self.pagecount |
---|
[1487] | 419 | |
---|
[1482] | 420 | class PDLAnalyzer : |
---|
| 421 | """Generic PDL Analyzer class.""" |
---|
| 422 | def __init__(self, filename) : |
---|
[1487] | 423 | """Initializes the PDL analyzer. |
---|
| 424 | |
---|
| 425 | filename is the name of the file or '-' for stdin. |
---|
| 426 | filename can also be a file-like object which |
---|
| 427 | supports read() and seek(). |
---|
| 428 | """ |
---|
[1482] | 429 | self.filename = filename |
---|
| 430 | |
---|
| 431 | def getJobSize(self) : |
---|
| 432 | """Returns the job's size.""" |
---|
| 433 | self.openFile() |
---|
[1487] | 434 | try : |
---|
| 435 | pdlhandler = self.detectPDLHandler() |
---|
| 436 | except PDLAnalyzerError, msg : |
---|
| 437 | self.closeFile() |
---|
| 438 | raise PDLAnalyzerError, "ERROR : Unknown file format for %s (%s)" % (self.filename, msg) |
---|
| 439 | else : |
---|
[1482] | 440 | try : |
---|
| 441 | size = pdlhandler(self.infile).getJobSize() |
---|
| 442 | finally : |
---|
| 443 | self.closeFile() |
---|
| 444 | return size |
---|
| 445 | |
---|
| 446 | def openFile(self) : |
---|
| 447 | """Opens the job's data stream for reading.""" |
---|
[1550] | 448 | self.mustclose = 0 # by default we don't want to close the file when finished |
---|
[1487] | 449 | if hasattr(self.filename, "read") and hasattr(self.filename, "seek") : |
---|
| 450 | # filename is in fact a file-like object |
---|
[1550] | 451 | infile = self.filename |
---|
[1487] | 452 | elif self.filename == "-" : |
---|
[1482] | 453 | # we must read from stdin |
---|
[1550] | 454 | infile = sys.stdin |
---|
[1482] | 455 | else : |
---|
| 456 | # normal file |
---|
[1550] | 457 | self.infile = open(self.filename, "rbU") # TODO : "U" mode only works in 2.3, is ignored in 2.1 and 2.2 |
---|
| 458 | self.mustclose = 1 |
---|
| 459 | return |
---|
[1482] | 460 | |
---|
[1550] | 461 | # Use a temporary file, always seekable contrary to standard input. |
---|
| 462 | # This also has the benefit to let us use the "U" mode (new in Python 2.3) |
---|
| 463 | self.infile = tempfile.TemporaryFile(mode="w+bU") # TODO : "U" mode only works in 2.3, is ignored in 2.1 and 2.2 |
---|
| 464 | while 1 : |
---|
| 465 | data = infile.read(MEGABYTE) |
---|
| 466 | if not data : |
---|
| 467 | break |
---|
| 468 | self.infile.write(data) |
---|
| 469 | self.infile.flush() |
---|
| 470 | self.infile.seek(0) |
---|
| 471 | |
---|
[1482] | 472 | def closeFile(self) : |
---|
[1487] | 473 | """Closes the job's data stream if we can close it.""" |
---|
| 474 | if self.mustclose : |
---|
| 475 | self.infile.close() |
---|
[1544] | 476 | else : |
---|
| 477 | # if we don't have to close the file, then |
---|
| 478 | # ensure the file pointer is reset to the |
---|
| 479 | # start of the file in case the process wants |
---|
| 480 | # to read the file again. |
---|
| 481 | try : |
---|
| 482 | self.infile.seek(0) |
---|
| 483 | except : |
---|
| 484 | pass # probably stdin, which is not seekable |
---|
[1482] | 485 | |
---|
| 486 | def isPostScript(self, data) : |
---|
| 487 | """Returns 1 if data is PostScript, else 0.""" |
---|
| 488 | if data.startswith("%!") or \ |
---|
| 489 | data.startswith("\004%!") or \ |
---|
| 490 | data.startswith("\033%-12345X%!PS") or \ |
---|
| 491 | ((data[:128].find("\033%-12345X") != -1) and \ |
---|
| 492 | ((data.find("LANGUAGE=POSTSCRIPT") != -1) or \ |
---|
| 493 | (data.find("LANGUAGE = POSTSCRIPT") != -1) or \ |
---|
[1543] | 494 | (data.find("LANGUAGE = Postscript") != -1))) or \ |
---|
| 495 | (data.find("%!PS-Adobe") != -1) : |
---|
[1482] | 496 | return 1 |
---|
| 497 | else : |
---|
| 498 | return 0 |
---|
| 499 | |
---|
[1547] | 500 | def isPDF(self, data) : |
---|
| 501 | """Returns 1 if data is PDF, else 0.""" |
---|
| 502 | if data.startswith("%PDF-") or \ |
---|
| 503 | data.startswith("\033%-12345X%PDF-") or \ |
---|
| 504 | ((data[:128].find("\033%-12345X") != -1) and (data.upper().find("LANGUAGE=PDF") != -1)) or \ |
---|
| 505 | (data.find("%PDF-") != -1) : |
---|
| 506 | return 1 |
---|
| 507 | else : |
---|
| 508 | return 0 |
---|
| 509 | |
---|
[1482] | 510 | def isPCL(self, data) : |
---|
| 511 | """Returns 1 if data is PCL, else 0.""" |
---|
| 512 | if data.startswith("\033E\033") or \ |
---|
| 513 | ((data[:128].find("\033%-12345X") != -1) and \ |
---|
| 514 | ((data.find("LANGUAGE=PCL") != -1) or \ |
---|
| 515 | (data.find("LANGUAGE = PCL") != -1) or \ |
---|
| 516 | (data.find("LANGUAGE = Pcl") != -1))) : |
---|
| 517 | return 1 |
---|
| 518 | else : |
---|
| 519 | return 0 |
---|
| 520 | |
---|
| 521 | def isPCLXL(self, data) : |
---|
| 522 | """Returns 1 if data is PCLXL aka PCL6, else 0.""" |
---|
| 523 | if ((data[:128].find("\033%-12345X") != -1) and \ |
---|
| 524 | (data.find(" HP-PCL XL;") != -1) and \ |
---|
| 525 | ((data.find("LANGUAGE=PCLXL") != -1) or \ |
---|
| 526 | (data.find("LANGUAGE = PCLXL") != -1))) : |
---|
| 527 | return 1 |
---|
| 528 | else : |
---|
| 529 | return 0 |
---|
| 530 | |
---|
| 531 | def detectPDLHandler(self) : |
---|
| 532 | """Tries to autodetect the document format. |
---|
| 533 | |
---|
| 534 | Returns the correct PDL handler class or None if format is unknown |
---|
| 535 | """ |
---|
| 536 | # Try to detect file type by reading first block of datas |
---|
| 537 | self.infile.seek(0) |
---|
[1487] | 538 | firstblock = self.infile.read(KILOBYTE) |
---|
[1482] | 539 | self.infile.seek(0) |
---|
| 540 | if self.isPostScript(firstblock) : |
---|
| 541 | return PostScriptAnalyzer |
---|
| 542 | elif self.isPCLXL(firstblock) : |
---|
| 543 | return PCLXLAnalyzer |
---|
| 544 | elif self.isPCL(firstblock) : |
---|
| 545 | return PCLAnalyzer |
---|
[1547] | 546 | elif self.isPDF(firstblock) : |
---|
| 547 | return PDFAnalyzer |
---|
[1487] | 548 | else : |
---|
| 549 | raise PDLAnalyzerError, "Analysis of first data block failed." |
---|
| 550 | |
---|
| 551 | def main() : |
---|
| 552 | """Entry point for PDL Analyzer.""" |
---|
| 553 | if (len(sys.argv) < 2) or ((not sys.stdin.isatty()) and ("-" not in sys.argv[1:])) : |
---|
| 554 | sys.argv.append("-") |
---|
| 555 | |
---|
| 556 | totalsize = 0 |
---|
| 557 | for arg in sys.argv[1:] : |
---|
| 558 | try : |
---|
| 559 | parser = PDLAnalyzer(arg) |
---|
| 560 | totalsize += parser.getJobSize() |
---|
| 561 | except PDLAnalyzerError, msg : |
---|
| 562 | sys.stderr.write("%s\n" % msg) |
---|
| 563 | sys.stderr.flush() |
---|
| 564 | print "%s" % totalsize |
---|
| 565 | |
---|
| 566 | if __name__ == "__main__" : |
---|
| 567 | main() |
---|