[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 | # $Log$ |
---|
[1551] | 24 | # Revision 1.8 2004/06/18 20:49:46 jalet |
---|
| 25 | # "ERROR:" prefix added |
---|
| 26 | # |
---|
[1550] | 27 | # Revision 1.7 2004/06/18 17:48:04 jalet |
---|
| 28 | # Added native fast PDF parsing method |
---|
| 29 | # |
---|
[1547] | 30 | # Revision 1.6 2004/06/18 14:00:16 jalet |
---|
| 31 | # Added PDF support in smart PDL analyzer (through GhostScript for now) |
---|
| 32 | # |
---|
[1544] | 33 | # Revision 1.5 2004/06/18 10:09:05 jalet |
---|
| 34 | # Resets file pointer to start of file in all cases |
---|
| 35 | # |
---|
[1543] | 36 | # Revision 1.4 2004/06/18 06:16:14 jalet |
---|
| 37 | # Fixes PostScript detection code for incorrect drivers |
---|
| 38 | # |
---|
[1487] | 39 | # Revision 1.3 2004/05/21 20:40:08 jalet |
---|
| 40 | # All the code for pkpgcounter is now in pdlanalyzer.py |
---|
| 41 | # |
---|
[1485] | 42 | # Revision 1.2 2004/05/19 19:09:36 jalet |
---|
| 43 | # Speed improvement |
---|
| 44 | # |
---|
[1482] | 45 | # Revision 1.1 2004/05/18 09:59:54 jalet |
---|
| 46 | # pkpgcounter is now just a wrapper around the PDLAnalyzer class |
---|
| 47 | # |
---|
| 48 | # |
---|
| 49 | # |
---|
| 50 | |
---|
| 51 | import sys |
---|
[1547] | 52 | import os |
---|
[1482] | 53 | import struct |
---|
| 54 | import tempfile |
---|
[1547] | 55 | import popen2 |
---|
[1482] | 56 | |
---|
[1487] | 57 | KILOBYTE = 1024 |
---|
| 58 | MEGABYTE = 1024 * KILOBYTE |
---|
| 59 | |
---|
| 60 | class PDLAnalyzerError(Exception): |
---|
| 61 | """An exception for PDL Analyzer related stuff.""" |
---|
| 62 | def __init__(self, message = ""): |
---|
| 63 | self.message = message |
---|
| 64 | Exception.__init__(self, message) |
---|
| 65 | def __repr__(self): |
---|
| 66 | return self.message |
---|
| 67 | __str__ = __repr__ |
---|
| 68 | |
---|
[1482] | 69 | class PostScriptAnalyzer : |
---|
| 70 | def __init__(self, infile) : |
---|
| 71 | """Initialize PostScript Analyzer.""" |
---|
| 72 | self.infile = infile |
---|
| 73 | |
---|
| 74 | def getJobSize(self) : |
---|
| 75 | """Count pages in a DSC compliant PostScript document.""" |
---|
| 76 | pagecount = 0 |
---|
| 77 | while 1 : |
---|
| 78 | line = self.infile.readline() |
---|
| 79 | if not line : |
---|
| 80 | break |
---|
| 81 | if line.startswith("%%Page: ") : |
---|
| 82 | pagecount += 1 |
---|
| 83 | return pagecount |
---|
| 84 | |
---|
[1547] | 85 | class PDFAnalyzer : |
---|
| 86 | def __init__(self, infile) : |
---|
| 87 | """Initialize PDF Analyzer.""" |
---|
| 88 | self.infile = infile |
---|
[1550] | 89 | try : |
---|
| 90 | if float(sys.version[:3]) >= 2.3 : |
---|
| 91 | self.getJobSize = self.native_getJobSize |
---|
| 92 | else : |
---|
| 93 | self.getJobSize = self.gs_getJobSize |
---|
| 94 | except : |
---|
| 95 | self.getJobSize = self.gs_getJobSize |
---|
| 96 | |
---|
| 97 | def native_getJobSize(self) : |
---|
| 98 | """Counts pages in a PDF document natively.""" |
---|
| 99 | pagecount = 0 |
---|
| 100 | content = [] |
---|
| 101 | while 1 : |
---|
| 102 | line = self.infile.readline() |
---|
| 103 | if not line : |
---|
| 104 | break |
---|
| 105 | line = line.strip() |
---|
| 106 | content.append(line) |
---|
| 107 | if line.endswith("endobj") : |
---|
| 108 | pagecount += " /".join([x.strip() for x in " ".join(content).split("/")]).count(" /Type /Page ") |
---|
| 109 | content = [] |
---|
| 110 | return pagecount |
---|
[1547] | 111 | |
---|
[1550] | 112 | def gs_getJobSize(self) : |
---|
| 113 | """Counts pages in a PDF document using GhostScript to convert PDF to PS.""" |
---|
[1547] | 114 | MEGABYTE = 1024*1024 |
---|
| 115 | child = popen2.Popen4("gs -q -dNOPAUSE -dBATCH -dSAFER -sDEVICE=pswrite -sOutputFile=- -c save pop -f - 2>/dev/null") |
---|
| 116 | try : |
---|
| 117 | data = self.infile.read(MEGABYTE) |
---|
| 118 | while data : |
---|
| 119 | child.tochild.write(data) |
---|
| 120 | data = self.infile.read(MEGABYTE) |
---|
| 121 | child.tochild.flush() |
---|
| 122 | child.tochild.close() |
---|
| 123 | except (IOError, OSError), msg : |
---|
| 124 | raise PDLAnalyzerError, "Unable to convert PDF input to PS with GhostScript : %s" % msg |
---|
| 125 | |
---|
| 126 | psanalyzer = PostScriptAnalyzer(child.fromchild) |
---|
| 127 | pagecount = psanalyzer.getJobSize() |
---|
| 128 | child.fromchild.close() |
---|
| 129 | try : |
---|
| 130 | retcode = child.wait() |
---|
| 131 | except OSError, msg : |
---|
| 132 | self.filter.logger.log_message(_("Problem while waiting for PDF to PS converter (GhostScript pid %s) to exit : %s") % (child.pid, msg)) |
---|
| 133 | else : |
---|
| 134 | if os.WIFEXITED(retcode) : |
---|
| 135 | status = os.WEXITSTATUS(retcode) |
---|
| 136 | else : |
---|
| 137 | status = retcode |
---|
| 138 | if status : |
---|
| 139 | raise PDLAnalyzerError, "PDF to PS converter (GhostScript pid %s) exit code is %s" % (child.pid, repr(status)) |
---|
| 140 | return pagecount |
---|
| 141 | |
---|
[1482] | 142 | class PCLAnalyzer : |
---|
| 143 | def __init__(self, infile) : |
---|
| 144 | """Initialize PCL Analyzer.""" |
---|
| 145 | self.infile = infile |
---|
| 146 | |
---|
[1485] | 147 | def skip(self, nb) : |
---|
| 148 | """Reads a new datablock.""" |
---|
| 149 | newpos = self.pos + nb |
---|
| 150 | if newpos >= self.len : |
---|
| 151 | oldlen = self.len |
---|
[1487] | 152 | self.data = self.infile.read(MEGABYTE) |
---|
[1485] | 153 | self.len = len(self.data) |
---|
| 154 | if not self.len : |
---|
| 155 | return |
---|
| 156 | self.pos = newpos - oldlen |
---|
| 157 | else : |
---|
| 158 | self.pos = newpos |
---|
| 159 | |
---|
| 160 | def readone(self) : |
---|
| 161 | """Reads a new byte.""" |
---|
| 162 | if self.pos < self.len : |
---|
| 163 | char = self.data[self.pos] |
---|
| 164 | else : |
---|
[1487] | 165 | self.data = self.infile.read(MEGABYTE) |
---|
[1485] | 166 | self.len = len(self.data) |
---|
| 167 | self.pos = 0 |
---|
| 168 | if not self.len : |
---|
| 169 | return |
---|
| 170 | char = self.data[0] |
---|
| 171 | self.pos += 1 |
---|
| 172 | return char |
---|
| 173 | |
---|
[1482] | 174 | def getJobSize(self) : |
---|
| 175 | """Count pages in a PCL5 document.""" |
---|
| 176 | # |
---|
| 177 | # Algorithm from pclcount |
---|
| 178 | # (c) 2003, by Eduardo Gielamo Oliveira & Rodolfo Broco Manin |
---|
| 179 | # published under the terms of the GNU General Public Licence v2. |
---|
| 180 | # |
---|
| 181 | # Backported from C to Python by Jerome Alet, then enhanced |
---|
| 182 | # with more PCL tags detected. I think all the necessary PCL tags |
---|
| 183 | # are recognized to correctly handle PCL5 files wrt their number |
---|
| 184 | # of pages. The documentation used for this was : |
---|
| 185 | # |
---|
| 186 | # HP PCL/PJL Reference Set |
---|
| 187 | # PCL5 Printer Language Technical Quick Reference Guide |
---|
| 188 | # http://h20000.www2.hp.com/bc/docs/support/SupportManual/bpl13205/bpl13205.pdf |
---|
| 189 | # |
---|
| 190 | tagsends = { "&n" : "W", |
---|
| 191 | "&b" : "W", |
---|
| 192 | "*i" : "W", |
---|
| 193 | "*l" : "W", |
---|
| 194 | "*m" : "W", |
---|
| 195 | "*v" : "W", |
---|
| 196 | "*c" : "W", |
---|
| 197 | "(f" : "W", |
---|
| 198 | "*b" : "VW", |
---|
| 199 | "(s" : "W", |
---|
| 200 | ")s" : "W", |
---|
| 201 | "&p" : "X", |
---|
| 202 | "&l" : "X" } |
---|
[1485] | 203 | self.data = [] |
---|
| 204 | self.pos = self.len = 0 |
---|
[1482] | 205 | copies = 1 |
---|
| 206 | pagecount = resets = 0 |
---|
| 207 | tag = None |
---|
| 208 | while 1 : |
---|
[1485] | 209 | char = self.readone() |
---|
[1482] | 210 | if not char : # EOF ? |
---|
| 211 | break |
---|
| 212 | if char == "\014" : |
---|
| 213 | pagecount += 1 |
---|
| 214 | elif char == "\033" : |
---|
| 215 | # |
---|
| 216 | # <ESC>*b###W -> Start of a raster data row/block |
---|
| 217 | # <ESC>*b###V -> Start of a raster data plane |
---|
| 218 | # <ESC>*c###W -> Start of a user defined pattern |
---|
| 219 | # <ESC>*i###W -> Start of a viewing illuminant block |
---|
| 220 | # <ESC>*l###W -> Start of a color lookup table |
---|
| 221 | # <ESC>*m###W -> Start of a download dither matrix block |
---|
| 222 | # <ESC>*v###W -> Start of a configure image data block |
---|
| 223 | # <ESC>(s###W -> Start of a characters description block |
---|
| 224 | # <ESC>)s###W -> Start of a fonts description block |
---|
| 225 | # <ESC>(f###W -> Start of a symbol set block |
---|
| 226 | # <ESC>&b###W -> Start of configuration data block |
---|
| 227 | # <ESC>&l###X -> Number of copies |
---|
| 228 | # <ESC>&n###W -> Starts an alphanumeric string ID block |
---|
| 229 | # <ESC>&p###X -> Start of a non printable characters block |
---|
| 230 | # |
---|
[1485] | 231 | tagstart = self.readone() |
---|
[1482] | 232 | if tagstart in "E9=YZ" : # one byte PCL tag |
---|
| 233 | if tagstart == "E" : |
---|
| 234 | resets += 1 |
---|
| 235 | continue # skip to next tag |
---|
[1485] | 236 | tag = tagstart + self.readone() |
---|
[1482] | 237 | try : |
---|
| 238 | tagend = tagsends[tag] |
---|
| 239 | except KeyError : |
---|
| 240 | pass # Unsupported PCL tag |
---|
| 241 | else : |
---|
| 242 | # Now read the numeric argument |
---|
| 243 | size = 0 |
---|
| 244 | while 1 : |
---|
[1485] | 245 | char = self.readone() |
---|
[1482] | 246 | if not char.isdigit() : |
---|
| 247 | break |
---|
| 248 | size = (size * 10) + int(char) |
---|
| 249 | if char in tagend : |
---|
| 250 | if tag == "&l" : |
---|
| 251 | copies = size |
---|
| 252 | else : |
---|
| 253 | # doing a read will prevent the seek |
---|
| 254 | # for unseekable streams. |
---|
| 255 | # we just ignore the block anyway. |
---|
| 256 | if tag == "&n" : |
---|
| 257 | # we have to take care of the operation id byte |
---|
| 258 | # which is before the string itself |
---|
| 259 | size += 1 |
---|
[1485] | 260 | self.skip(size) |
---|
[1482] | 261 | |
---|
| 262 | # if pagecount is still 0, we will return the number |
---|
| 263 | # of resets instead of the number of form feed characters. |
---|
| 264 | # but the number of resets is always at least 2 with a valid |
---|
| 265 | # pcl file : one at the very start and one at the very end |
---|
| 266 | # of the job's data. So we substract 2 from the number of |
---|
| 267 | # resets. And since on our test data we needed to substract |
---|
| 268 | # 1 more, we finally substract 3, and will test several |
---|
| 269 | # PCL files with this. If resets < 2, then the file is |
---|
| 270 | # probably not a valid PCL file, so we return 0 |
---|
[1487] | 271 | return copies * (pagecount or ((resets - 3) * (resets > 2))) |
---|
[1482] | 272 | |
---|
| 273 | class PCLXLAnalyzer : |
---|
| 274 | def __init__(self, infile) : |
---|
| 275 | """Initialize PCLXL Analyzer.""" |
---|
[1487] | 276 | raise PDLAnalyzerError, "PCLXL (aka PCL6) is not supported yet." |
---|
[1482] | 277 | self.infile = infile |
---|
| 278 | self.islittleendian = None |
---|
| 279 | found = 0 |
---|
| 280 | while not found : |
---|
| 281 | line = self.infile.readline() |
---|
| 282 | if not line : |
---|
| 283 | break |
---|
| 284 | if line[1:12] == " HP-PCL XL;" : |
---|
| 285 | found = 1 |
---|
| 286 | if line[0] == ")" : |
---|
| 287 | self.littleendian() |
---|
| 288 | elif line[0] == "(" : |
---|
| 289 | self.bigendian() |
---|
| 290 | if not found : |
---|
[1487] | 291 | raise PDLAnalyzerError, "This file doesn't seem to be PCLXL (aka PCL6)" |
---|
[1482] | 292 | else : |
---|
[1487] | 293 | self.tags = [lambda: None] * 256 |
---|
[1482] | 294 | self.tags[0x28] = self.bigendian # big endian |
---|
| 295 | self.tags[0x29] = self.littleendian # big endian |
---|
| 296 | self.tags[0x43] = self.beginPage # BeginPage |
---|
| 297 | self.tags[0x44] = self.endPage # EndPage |
---|
| 298 | |
---|
[1487] | 299 | self.tags[0xc0] = lambda: 1 # ubyte |
---|
| 300 | self.tags[0xc1] = lambda: 2 # uint16 |
---|
| 301 | self.tags[0xc2] = lambda: 4 # uint32 |
---|
| 302 | self.tags[0xc3] = lambda: 2 # sint16 |
---|
| 303 | self.tags[0xc4] = lambda: 4 # sint32 |
---|
| 304 | self.tags[0xc5] = lambda: 4 # real32 |
---|
[1482] | 305 | |
---|
| 306 | self.tags[0xc8] = self.array_8 # ubyte_array |
---|
| 307 | self.tags[0xc9] = self.array_16 # uint16_array |
---|
| 308 | self.tags[0xca] = self.array_32 # uint32_array |
---|
| 309 | self.tags[0xcb] = self.array_16 # sint16_array |
---|
| 310 | self.tags[0xcc] = self.array_32 # sint32_array |
---|
| 311 | self.tags[0xcd] = self.array_32 # real32_array |
---|
| 312 | |
---|
[1487] | 313 | self.tags[0xd0] = lambda: 2 # ubyte_xy |
---|
| 314 | self.tags[0xd1] = lambda: 4 # uint16_xy |
---|
| 315 | self.tags[0xd2] = lambda: 8 # uint32_xy |
---|
| 316 | self.tags[0xd3] = lambda: 4 # sint16_xy |
---|
| 317 | self.tags[0xd4] = lambda: 8 # sint32_xy |
---|
| 318 | self.tags[0xd5] = lambda: 8 # real32_xy |
---|
[1482] | 319 | |
---|
[1487] | 320 | self.tags[0xd0] = lambda: 4 # ubyte_box |
---|
| 321 | self.tags[0xd1] = lambda: 8 # uint16_box |
---|
| 322 | self.tags[0xd2] = lambda: 16 # uint32_box |
---|
| 323 | self.tags[0xd3] = lambda: 8 # sint16_box |
---|
| 324 | self.tags[0xd4] = lambda: 16 # sint32_box |
---|
| 325 | self.tags[0xd5] = lambda: 16 # real32_box |
---|
[1482] | 326 | |
---|
[1487] | 327 | self.tags[0xf8] = lambda: 1 # attr_ubyte |
---|
| 328 | self.tags[0xf9] = lambda: 2 # attr_uint16 |
---|
[1482] | 329 | |
---|
| 330 | self.tags[0xfa] = self.embeddedData # dataLength |
---|
| 331 | self.tags[0xfb] = self.embeddedDataSmall # dataLengthByte |
---|
| 332 | |
---|
| 333 | def debug(self, msg) : |
---|
| 334 | """Outputs a debug message on stderr.""" |
---|
| 335 | sys.stderr.write("%s\n" % msg) |
---|
| 336 | sys.stderr.flush() |
---|
| 337 | |
---|
| 338 | def beginPage(self) : |
---|
| 339 | """Indicates the beginning of a new page.""" |
---|
| 340 | self.pagecount += 1 |
---|
| 341 | self.debug("Begin page %i at %s" % (self.pagecount, self.infile.tell())) |
---|
| 342 | |
---|
| 343 | def endPage(self) : |
---|
| 344 | """Indicates the end of a page.""" |
---|
| 345 | self.debug("End page %i at %s" % (self.pagecount, self.infile.tell())) |
---|
| 346 | |
---|
| 347 | def handleArray(self, itemsize) : |
---|
| 348 | """Handles arrays.""" |
---|
[1487] | 349 | pos = self.infile.tell() |
---|
[1482] | 350 | datatype = self.infile.read(1) |
---|
[1487] | 351 | length = self.tags[ord(datatype)]() |
---|
| 352 | if length is None : |
---|
| 353 | self.debug("Bogus array length at %s" % pos) |
---|
[1482] | 354 | else : |
---|
[1487] | 355 | sarraysize = self.infile.read(length) |
---|
| 356 | if self.islittleendian : |
---|
| 357 | fmt = "<" |
---|
| 358 | else : |
---|
| 359 | fmt = ">" |
---|
| 360 | if length == 1 : |
---|
| 361 | fmt += "B" |
---|
| 362 | elif length == 2 : |
---|
| 363 | fmt += "H" |
---|
| 364 | elif length == 4 : |
---|
| 365 | fmt += "I" |
---|
| 366 | else : |
---|
| 367 | raise PDLAnalyzerError, "Error on array size at %s" % self.infile.tell() |
---|
| 368 | arraysize = struct.unpack(fmt, sarraysize)[0] |
---|
| 369 | self.debug("Array at %s, itemsize %s, datatype 0x%02x, size %s" % (pos, itemsize, ord(datatype), arraysize)) |
---|
| 370 | return arraysize * itemsize |
---|
[1482] | 371 | |
---|
| 372 | def array_8(self) : |
---|
| 373 | """Handles byte arrays.""" |
---|
| 374 | return self.handleArray(1) |
---|
| 375 | |
---|
| 376 | def array_16(self) : |
---|
| 377 | """Handles byte arrays.""" |
---|
| 378 | return self.handleArray(2) |
---|
| 379 | |
---|
| 380 | def array_32(self) : |
---|
| 381 | """Handles byte arrays.""" |
---|
| 382 | return self.handleArray(4) |
---|
| 383 | |
---|
| 384 | def embeddedDataSmall(self) : |
---|
| 385 | """Handle small amounts of data.""" |
---|
[1487] | 386 | pos = self.infile.tell() |
---|
| 387 | val = ord(self.infile.read(1)) |
---|
| 388 | self.debug("smalldatablock at %s (0x%02x)" % (pos, val)) |
---|
| 389 | return val |
---|
[1482] | 390 | |
---|
| 391 | def embeddedData(self) : |
---|
| 392 | """Handle normal amounts of data.""" |
---|
| 393 | if self.islittleendian : |
---|
| 394 | fmt = "<I" |
---|
| 395 | else : |
---|
| 396 | fmt = ">I" |
---|
[1487] | 397 | pos = self.infile.tell() |
---|
| 398 | val = struct.unpack(fmt, self.infile.read(4))[0] |
---|
| 399 | self.debug("datablock at %s (0x%08x)" % (pos, val)) |
---|
| 400 | return val |
---|
[1482] | 401 | |
---|
| 402 | def littleendian(self) : |
---|
| 403 | """Toggles to little endianness.""" |
---|
| 404 | self.islittleendian = 1 # little endian |
---|
| 405 | |
---|
| 406 | def bigendian(self) : |
---|
| 407 | """Toggles to big endianness.""" |
---|
| 408 | self.islittleendian = 0 # big endian |
---|
| 409 | |
---|
| 410 | def getJobSize(self) : |
---|
| 411 | """Counts pages in a PCLXL (PCL6) document.""" |
---|
| 412 | self.pagecount = 0 |
---|
| 413 | while 1 : |
---|
| 414 | char = self.infile.read(1) |
---|
| 415 | if not char : |
---|
| 416 | break |
---|
| 417 | index = ord(char) |
---|
[1487] | 418 | length = self.tags[index]() |
---|
| 419 | if length : |
---|
| 420 | self.infile.read(length) |
---|
[1482] | 421 | return self.pagecount |
---|
[1487] | 422 | |
---|
[1482] | 423 | class PDLAnalyzer : |
---|
| 424 | """Generic PDL Analyzer class.""" |
---|
| 425 | def __init__(self, filename) : |
---|
[1487] | 426 | """Initializes the PDL analyzer. |
---|
| 427 | |
---|
| 428 | filename is the name of the file or '-' for stdin. |
---|
| 429 | filename can also be a file-like object which |
---|
| 430 | supports read() and seek(). |
---|
| 431 | """ |
---|
[1482] | 432 | self.filename = filename |
---|
| 433 | |
---|
| 434 | def getJobSize(self) : |
---|
| 435 | """Returns the job's size.""" |
---|
| 436 | self.openFile() |
---|
[1487] | 437 | try : |
---|
| 438 | pdlhandler = self.detectPDLHandler() |
---|
| 439 | except PDLAnalyzerError, msg : |
---|
| 440 | self.closeFile() |
---|
| 441 | raise PDLAnalyzerError, "ERROR : Unknown file format for %s (%s)" % (self.filename, msg) |
---|
| 442 | else : |
---|
[1482] | 443 | try : |
---|
| 444 | size = pdlhandler(self.infile).getJobSize() |
---|
| 445 | finally : |
---|
| 446 | self.closeFile() |
---|
| 447 | return size |
---|
| 448 | |
---|
| 449 | def openFile(self) : |
---|
| 450 | """Opens the job's data stream for reading.""" |
---|
[1550] | 451 | self.mustclose = 0 # by default we don't want to close the file when finished |
---|
[1487] | 452 | if hasattr(self.filename, "read") and hasattr(self.filename, "seek") : |
---|
| 453 | # filename is in fact a file-like object |
---|
[1550] | 454 | infile = self.filename |
---|
[1487] | 455 | elif self.filename == "-" : |
---|
[1482] | 456 | # we must read from stdin |
---|
[1550] | 457 | infile = sys.stdin |
---|
[1482] | 458 | else : |
---|
| 459 | # normal file |
---|
[1550] | 460 | self.infile = open(self.filename, "rbU") # TODO : "U" mode only works in 2.3, is ignored in 2.1 and 2.2 |
---|
| 461 | self.mustclose = 1 |
---|
| 462 | return |
---|
[1482] | 463 | |
---|
[1550] | 464 | # Use a temporary file, always seekable contrary to standard input. |
---|
| 465 | # This also has the benefit to let us use the "U" mode (new in Python 2.3) |
---|
| 466 | self.infile = tempfile.TemporaryFile(mode="w+bU") # TODO : "U" mode only works in 2.3, is ignored in 2.1 and 2.2 |
---|
| 467 | while 1 : |
---|
| 468 | data = infile.read(MEGABYTE) |
---|
| 469 | if not data : |
---|
| 470 | break |
---|
| 471 | self.infile.write(data) |
---|
| 472 | self.infile.flush() |
---|
| 473 | self.infile.seek(0) |
---|
| 474 | |
---|
[1482] | 475 | def closeFile(self) : |
---|
[1487] | 476 | """Closes the job's data stream if we can close it.""" |
---|
| 477 | if self.mustclose : |
---|
| 478 | self.infile.close() |
---|
[1544] | 479 | else : |
---|
| 480 | # if we don't have to close the file, then |
---|
| 481 | # ensure the file pointer is reset to the |
---|
| 482 | # start of the file in case the process wants |
---|
| 483 | # to read the file again. |
---|
| 484 | try : |
---|
| 485 | self.infile.seek(0) |
---|
| 486 | except : |
---|
| 487 | pass # probably stdin, which is not seekable |
---|
[1482] | 488 | |
---|
| 489 | def isPostScript(self, data) : |
---|
| 490 | """Returns 1 if data is PostScript, else 0.""" |
---|
| 491 | if data.startswith("%!") or \ |
---|
| 492 | data.startswith("\004%!") or \ |
---|
| 493 | data.startswith("\033%-12345X%!PS") or \ |
---|
| 494 | ((data[:128].find("\033%-12345X") != -1) and \ |
---|
| 495 | ((data.find("LANGUAGE=POSTSCRIPT") != -1) or \ |
---|
| 496 | (data.find("LANGUAGE = POSTSCRIPT") != -1) or \ |
---|
[1543] | 497 | (data.find("LANGUAGE = Postscript") != -1))) or \ |
---|
| 498 | (data.find("%!PS-Adobe") != -1) : |
---|
[1482] | 499 | return 1 |
---|
| 500 | else : |
---|
| 501 | return 0 |
---|
| 502 | |
---|
[1547] | 503 | def isPDF(self, data) : |
---|
| 504 | """Returns 1 if data is PDF, else 0.""" |
---|
| 505 | if data.startswith("%PDF-") or \ |
---|
| 506 | data.startswith("\033%-12345X%PDF-") or \ |
---|
| 507 | ((data[:128].find("\033%-12345X") != -1) and (data.upper().find("LANGUAGE=PDF") != -1)) or \ |
---|
| 508 | (data.find("%PDF-") != -1) : |
---|
| 509 | return 1 |
---|
| 510 | else : |
---|
| 511 | return 0 |
---|
| 512 | |
---|
[1482] | 513 | def isPCL(self, data) : |
---|
| 514 | """Returns 1 if data is PCL, else 0.""" |
---|
| 515 | if data.startswith("\033E\033") or \ |
---|
| 516 | ((data[:128].find("\033%-12345X") != -1) and \ |
---|
| 517 | ((data.find("LANGUAGE=PCL") != -1) or \ |
---|
| 518 | (data.find("LANGUAGE = PCL") != -1) or \ |
---|
| 519 | (data.find("LANGUAGE = Pcl") != -1))) : |
---|
| 520 | return 1 |
---|
| 521 | else : |
---|
| 522 | return 0 |
---|
| 523 | |
---|
| 524 | def isPCLXL(self, data) : |
---|
| 525 | """Returns 1 if data is PCLXL aka PCL6, else 0.""" |
---|
| 526 | if ((data[:128].find("\033%-12345X") != -1) and \ |
---|
| 527 | (data.find(" HP-PCL XL;") != -1) and \ |
---|
| 528 | ((data.find("LANGUAGE=PCLXL") != -1) or \ |
---|
| 529 | (data.find("LANGUAGE = PCLXL") != -1))) : |
---|
| 530 | return 1 |
---|
| 531 | else : |
---|
| 532 | return 0 |
---|
| 533 | |
---|
| 534 | def detectPDLHandler(self) : |
---|
| 535 | """Tries to autodetect the document format. |
---|
| 536 | |
---|
| 537 | Returns the correct PDL handler class or None if format is unknown |
---|
| 538 | """ |
---|
| 539 | # Try to detect file type by reading first block of datas |
---|
| 540 | self.infile.seek(0) |
---|
[1487] | 541 | firstblock = self.infile.read(KILOBYTE) |
---|
[1482] | 542 | self.infile.seek(0) |
---|
| 543 | if self.isPostScript(firstblock) : |
---|
| 544 | return PostScriptAnalyzer |
---|
| 545 | elif self.isPCLXL(firstblock) : |
---|
| 546 | return PCLXLAnalyzer |
---|
| 547 | elif self.isPCL(firstblock) : |
---|
| 548 | return PCLAnalyzer |
---|
[1547] | 549 | elif self.isPDF(firstblock) : |
---|
| 550 | return PDFAnalyzer |
---|
[1487] | 551 | else : |
---|
| 552 | raise PDLAnalyzerError, "Analysis of first data block failed." |
---|
| 553 | |
---|
| 554 | def main() : |
---|
| 555 | """Entry point for PDL Analyzer.""" |
---|
| 556 | if (len(sys.argv) < 2) or ((not sys.stdin.isatty()) and ("-" not in sys.argv[1:])) : |
---|
| 557 | sys.argv.append("-") |
---|
| 558 | |
---|
| 559 | totalsize = 0 |
---|
| 560 | for arg in sys.argv[1:] : |
---|
| 561 | try : |
---|
| 562 | parser = PDLAnalyzer(arg) |
---|
| 563 | totalsize += parser.getJobSize() |
---|
| 564 | except PDLAnalyzerError, msg : |
---|
[1551] | 565 | sys.stderr.write("ERROR: %s\n" % msg) |
---|
[1487] | 566 | sys.stderr.flush() |
---|
| 567 | print "%s" % totalsize |
---|
| 568 | |
---|
| 569 | if __name__ == "__main__" : |
---|
| 570 | main() |
---|