| 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 | # $Log$ |
|---|
| 24 | # Revision 1.10 2004/06/18 22:24:03 jalet |
|---|
| 25 | # Removed old comments |
|---|
| 26 | # |
|---|
| 27 | # Revision 1.9 2004/06/18 22:21:27 jalet |
|---|
| 28 | # Native PDF parser greatly improved. |
|---|
| 29 | # GhostScript based PDF parser completely removed because native code |
|---|
| 30 | # is now portable across Python versions. |
|---|
| 31 | # |
|---|
| 32 | # Revision 1.8 2004/06/18 20:49:46 jalet |
|---|
| 33 | # "ERROR:" prefix added |
|---|
| 34 | # |
|---|
| 35 | # Revision 1.7 2004/06/18 17:48:04 jalet |
|---|
| 36 | # Added native fast PDF parsing method |
|---|
| 37 | # |
|---|
| 38 | # Revision 1.6 2004/06/18 14:00:16 jalet |
|---|
| 39 | # Added PDF support in smart PDL analyzer (through GhostScript for now) |
|---|
| 40 | # |
|---|
| 41 | # Revision 1.5 2004/06/18 10:09:05 jalet |
|---|
| 42 | # Resets file pointer to start of file in all cases |
|---|
| 43 | # |
|---|
| 44 | # Revision 1.4 2004/06/18 06:16:14 jalet |
|---|
| 45 | # Fixes PostScript detection code for incorrect drivers |
|---|
| 46 | # |
|---|
| 47 | # Revision 1.3 2004/05/21 20:40:08 jalet |
|---|
| 48 | # All the code for pkpgcounter is now in pdlanalyzer.py |
|---|
| 49 | # |
|---|
| 50 | # Revision 1.2 2004/05/19 19:09:36 jalet |
|---|
| 51 | # Speed improvement |
|---|
| 52 | # |
|---|
| 53 | # Revision 1.1 2004/05/18 09:59:54 jalet |
|---|
| 54 | # pkpgcounter is now just a wrapper around the PDLAnalyzer class |
|---|
| 55 | # |
|---|
| 56 | # |
|---|
| 57 | # |
|---|
| 58 | |
|---|
| 59 | import sys |
|---|
| 60 | import os |
|---|
| 61 | import re |
|---|
| 62 | import struct |
|---|
| 63 | import tempfile |
|---|
| 64 | import popen2 |
|---|
| 65 | |
|---|
| 66 | KILOBYTE = 1024 |
|---|
| 67 | MEGABYTE = 1024 * KILOBYTE |
|---|
| 68 | |
|---|
| 69 | class PDLAnalyzerError(Exception): |
|---|
| 70 | """An exception for PDL Analyzer related stuff.""" |
|---|
| 71 | def __init__(self, message = ""): |
|---|
| 72 | self.message = message |
|---|
| 73 | Exception.__init__(self, message) |
|---|
| 74 | def __repr__(self): |
|---|
| 75 | return self.message |
|---|
| 76 | __str__ = __repr__ |
|---|
| 77 | |
|---|
| 78 | class PostScriptAnalyzer : |
|---|
| 79 | def __init__(self, infile) : |
|---|
| 80 | """Initialize PostScript Analyzer.""" |
|---|
| 81 | self.infile = infile |
|---|
| 82 | |
|---|
| 83 | def getJobSize(self) : |
|---|
| 84 | """Count pages in a DSC compliant PostScript document.""" |
|---|
| 85 | pagecount = 0 |
|---|
| 86 | for line in self.infile.xreadlines() : |
|---|
| 87 | if line.startswith("%%Page: ") : |
|---|
| 88 | pagecount += 1 |
|---|
| 89 | return pagecount |
|---|
| 90 | |
|---|
| 91 | class PDFAnalyzer : |
|---|
| 92 | def __init__(self, infile) : |
|---|
| 93 | """Initialize PDF Analyzer.""" |
|---|
| 94 | self.infile = infile |
|---|
| 95 | |
|---|
| 96 | def getJobSize(self) : |
|---|
| 97 | """Counts pages in a PDF document.""" |
|---|
| 98 | regexp = re.compile(r"(/Type) ?(/Page)[/ \r\n]") |
|---|
| 99 | pagecount = 0 |
|---|
| 100 | for line in self.infile.xreadlines() : |
|---|
| 101 | pagecount += len(regexp.findall(line)) |
|---|
| 102 | return pagecount |
|---|
| 103 | |
|---|
| 104 | class PCLAnalyzer : |
|---|
| 105 | def __init__(self, infile) : |
|---|
| 106 | """Initialize PCL Analyzer.""" |
|---|
| 107 | self.infile = infile |
|---|
| 108 | |
|---|
| 109 | def skip(self, nb) : |
|---|
| 110 | """Reads a new datablock.""" |
|---|
| 111 | newpos = self.pos + nb |
|---|
| 112 | if newpos >= self.len : |
|---|
| 113 | oldlen = self.len |
|---|
| 114 | self.data = self.infile.read(MEGABYTE) |
|---|
| 115 | self.len = len(self.data) |
|---|
| 116 | if not self.len : |
|---|
| 117 | return |
|---|
| 118 | self.pos = newpos - oldlen |
|---|
| 119 | else : |
|---|
| 120 | self.pos = newpos |
|---|
| 121 | |
|---|
| 122 | def readone(self) : |
|---|
| 123 | """Reads a new byte.""" |
|---|
| 124 | if self.pos < self.len : |
|---|
| 125 | char = self.data[self.pos] |
|---|
| 126 | else : |
|---|
| 127 | self.data = self.infile.read(MEGABYTE) |
|---|
| 128 | self.len = len(self.data) |
|---|
| 129 | self.pos = 0 |
|---|
| 130 | if not self.len : |
|---|
| 131 | return |
|---|
| 132 | char = self.data[0] |
|---|
| 133 | self.pos += 1 |
|---|
| 134 | return char |
|---|
| 135 | |
|---|
| 136 | def getJobSize(self) : |
|---|
| 137 | """Count pages in a PCL5 document.""" |
|---|
| 138 | # |
|---|
| 139 | # Algorithm from pclcount |
|---|
| 140 | # (c) 2003, by Eduardo Gielamo Oliveira & Rodolfo Broco Manin |
|---|
| 141 | # published under the terms of the GNU General Public Licence v2. |
|---|
| 142 | # |
|---|
| 143 | # Backported from C to Python by Jerome Alet, then enhanced |
|---|
| 144 | # with more PCL tags detected. I think all the necessary PCL tags |
|---|
| 145 | # are recognized to correctly handle PCL5 files wrt their number |
|---|
| 146 | # of pages. The documentation used for this was : |
|---|
| 147 | # |
|---|
| 148 | # HP PCL/PJL Reference Set |
|---|
| 149 | # PCL5 Printer Language Technical Quick Reference Guide |
|---|
| 150 | # http://h20000.www2.hp.com/bc/docs/support/SupportManual/bpl13205/bpl13205.pdf |
|---|
| 151 | # |
|---|
| 152 | tagsends = { "&n" : "W", |
|---|
| 153 | "&b" : "W", |
|---|
| 154 | "*i" : "W", |
|---|
| 155 | "*l" : "W", |
|---|
| 156 | "*m" : "W", |
|---|
| 157 | "*v" : "W", |
|---|
| 158 | "*c" : "W", |
|---|
| 159 | "(f" : "W", |
|---|
| 160 | "*b" : "VW", |
|---|
| 161 | "(s" : "W", |
|---|
| 162 | ")s" : "W", |
|---|
| 163 | "&p" : "X", |
|---|
| 164 | "&l" : "X" } |
|---|
| 165 | self.data = [] |
|---|
| 166 | self.pos = self.len = 0 |
|---|
| 167 | copies = 1 |
|---|
| 168 | pagecount = resets = 0 |
|---|
| 169 | tag = None |
|---|
| 170 | while 1 : |
|---|
| 171 | char = self.readone() |
|---|
| 172 | if not char : # EOF ? |
|---|
| 173 | break |
|---|
| 174 | if char == "\014" : |
|---|
| 175 | pagecount += 1 |
|---|
| 176 | elif char == "\033" : |
|---|
| 177 | # |
|---|
| 178 | # <ESC>*b###W -> Start of a raster data row/block |
|---|
| 179 | # <ESC>*b###V -> Start of a raster data plane |
|---|
| 180 | # <ESC>*c###W -> Start of a user defined pattern |
|---|
| 181 | # <ESC>*i###W -> Start of a viewing illuminant block |
|---|
| 182 | # <ESC>*l###W -> Start of a color lookup table |
|---|
| 183 | # <ESC>*m###W -> Start of a download dither matrix block |
|---|
| 184 | # <ESC>*v###W -> Start of a configure image data block |
|---|
| 185 | # <ESC>(s###W -> Start of a characters description block |
|---|
| 186 | # <ESC>)s###W -> Start of a fonts description block |
|---|
| 187 | # <ESC>(f###W -> Start of a symbol set block |
|---|
| 188 | # <ESC>&b###W -> Start of configuration data block |
|---|
| 189 | # <ESC>&l###X -> Number of copies |
|---|
| 190 | # <ESC>&n###W -> Starts an alphanumeric string ID block |
|---|
| 191 | # <ESC>&p###X -> Start of a non printable characters block |
|---|
| 192 | # |
|---|
| 193 | tagstart = self.readone() |
|---|
| 194 | if tagstart in "E9=YZ" : # one byte PCL tag |
|---|
| 195 | if tagstart == "E" : |
|---|
| 196 | resets += 1 |
|---|
| 197 | continue # skip to next tag |
|---|
| 198 | tag = tagstart + self.readone() |
|---|
| 199 | try : |
|---|
| 200 | tagend = tagsends[tag] |
|---|
| 201 | except KeyError : |
|---|
| 202 | pass # Unsupported PCL tag |
|---|
| 203 | else : |
|---|
| 204 | # Now read the numeric argument |
|---|
| 205 | size = 0 |
|---|
| 206 | while 1 : |
|---|
| 207 | char = self.readone() |
|---|
| 208 | if not char.isdigit() : |
|---|
| 209 | break |
|---|
| 210 | size = (size * 10) + int(char) |
|---|
| 211 | if char in tagend : |
|---|
| 212 | if tag == "&l" : |
|---|
| 213 | copies = size |
|---|
| 214 | else : |
|---|
| 215 | # doing a read will prevent the seek |
|---|
| 216 | # for unseekable streams. |
|---|
| 217 | # we just ignore the block anyway. |
|---|
| 218 | if tag == "&n" : |
|---|
| 219 | # we have to take care of the operation id byte |
|---|
| 220 | # which is before the string itself |
|---|
| 221 | size += 1 |
|---|
| 222 | self.skip(size) |
|---|
| 223 | |
|---|
| 224 | # if pagecount is still 0, we will return the number |
|---|
| 225 | # of resets instead of the number of form feed characters. |
|---|
| 226 | # but the number of resets is always at least 2 with a valid |
|---|
| 227 | # pcl file : one at the very start and one at the very end |
|---|
| 228 | # of the job's data. So we substract 2 from the number of |
|---|
| 229 | # resets. And since on our test data we needed to substract |
|---|
| 230 | # 1 more, we finally substract 3, and will test several |
|---|
| 231 | # PCL files with this. If resets < 2, then the file is |
|---|
| 232 | # probably not a valid PCL file, so we return 0 |
|---|
| 233 | return copies * (pagecount or ((resets - 3) * (resets > 2))) |
|---|
| 234 | |
|---|
| 235 | class PCLXLAnalyzer : |
|---|
| 236 | def __init__(self, infile) : |
|---|
| 237 | """Initialize PCLXL Analyzer.""" |
|---|
| 238 | raise PDLAnalyzerError, "PCLXL (aka PCL6) is not supported yet." |
|---|
| 239 | self.infile = infile |
|---|
| 240 | self.islittleendian = None |
|---|
| 241 | found = 0 |
|---|
| 242 | while not found : |
|---|
| 243 | line = self.infile.readline() |
|---|
| 244 | if not line : |
|---|
| 245 | break |
|---|
| 246 | if line[1:12] == " HP-PCL XL;" : |
|---|
| 247 | found = 1 |
|---|
| 248 | if line[0] == ")" : |
|---|
| 249 | self.littleendian() |
|---|
| 250 | elif line[0] == "(" : |
|---|
| 251 | self.bigendian() |
|---|
| 252 | if not found : |
|---|
| 253 | raise PDLAnalyzerError, "This file doesn't seem to be PCLXL (aka PCL6)" |
|---|
| 254 | else : |
|---|
| 255 | self.tags = [lambda: None] * 256 |
|---|
| 256 | self.tags[0x28] = self.bigendian # big endian |
|---|
| 257 | self.tags[0x29] = self.littleendian # big endian |
|---|
| 258 | self.tags[0x43] = self.beginPage # BeginPage |
|---|
| 259 | self.tags[0x44] = self.endPage # EndPage |
|---|
| 260 | |
|---|
| 261 | self.tags[0xc0] = lambda: 1 # ubyte |
|---|
| 262 | self.tags[0xc1] = lambda: 2 # uint16 |
|---|
| 263 | self.tags[0xc2] = lambda: 4 # uint32 |
|---|
| 264 | self.tags[0xc3] = lambda: 2 # sint16 |
|---|
| 265 | self.tags[0xc4] = lambda: 4 # sint32 |
|---|
| 266 | self.tags[0xc5] = lambda: 4 # real32 |
|---|
| 267 | |
|---|
| 268 | self.tags[0xc8] = self.array_8 # ubyte_array |
|---|
| 269 | self.tags[0xc9] = self.array_16 # uint16_array |
|---|
| 270 | self.tags[0xca] = self.array_32 # uint32_array |
|---|
| 271 | self.tags[0xcb] = self.array_16 # sint16_array |
|---|
| 272 | self.tags[0xcc] = self.array_32 # sint32_array |
|---|
| 273 | self.tags[0xcd] = self.array_32 # real32_array |
|---|
| 274 | |
|---|
| 275 | self.tags[0xd0] = lambda: 2 # ubyte_xy |
|---|
| 276 | self.tags[0xd1] = lambda: 4 # uint16_xy |
|---|
| 277 | self.tags[0xd2] = lambda: 8 # uint32_xy |
|---|
| 278 | self.tags[0xd3] = lambda: 4 # sint16_xy |
|---|
| 279 | self.tags[0xd4] = lambda: 8 # sint32_xy |
|---|
| 280 | self.tags[0xd5] = lambda: 8 # real32_xy |
|---|
| 281 | |
|---|
| 282 | self.tags[0xd0] = lambda: 4 # ubyte_box |
|---|
| 283 | self.tags[0xd1] = lambda: 8 # uint16_box |
|---|
| 284 | self.tags[0xd2] = lambda: 16 # uint32_box |
|---|
| 285 | self.tags[0xd3] = lambda: 8 # sint16_box |
|---|
| 286 | self.tags[0xd4] = lambda: 16 # sint32_box |
|---|
| 287 | self.tags[0xd5] = lambda: 16 # real32_box |
|---|
| 288 | |
|---|
| 289 | self.tags[0xf8] = lambda: 1 # attr_ubyte |
|---|
| 290 | self.tags[0xf9] = lambda: 2 # attr_uint16 |
|---|
| 291 | |
|---|
| 292 | self.tags[0xfa] = self.embeddedData # dataLength |
|---|
| 293 | self.tags[0xfb] = self.embeddedDataSmall # dataLengthByte |
|---|
| 294 | |
|---|
| 295 | def debug(self, msg) : |
|---|
| 296 | """Outputs a debug message on stderr.""" |
|---|
| 297 | sys.stderr.write("%s\n" % msg) |
|---|
| 298 | sys.stderr.flush() |
|---|
| 299 | |
|---|
| 300 | def beginPage(self) : |
|---|
| 301 | """Indicates the beginning of a new page.""" |
|---|
| 302 | self.pagecount += 1 |
|---|
| 303 | self.debug("Begin page %i at %s" % (self.pagecount, self.infile.tell())) |
|---|
| 304 | |
|---|
| 305 | def endPage(self) : |
|---|
| 306 | """Indicates the end of a page.""" |
|---|
| 307 | self.debug("End page %i at %s" % (self.pagecount, self.infile.tell())) |
|---|
| 308 | |
|---|
| 309 | def handleArray(self, itemsize) : |
|---|
| 310 | """Handles arrays.""" |
|---|
| 311 | pos = self.infile.tell() |
|---|
| 312 | datatype = self.infile.read(1) |
|---|
| 313 | length = self.tags[ord(datatype)]() |
|---|
| 314 | if length is None : |
|---|
| 315 | self.debug("Bogus array length at %s" % pos) |
|---|
| 316 | else : |
|---|
| 317 | sarraysize = self.infile.read(length) |
|---|
| 318 | if self.islittleendian : |
|---|
| 319 | fmt = "<" |
|---|
| 320 | else : |
|---|
| 321 | fmt = ">" |
|---|
| 322 | if length == 1 : |
|---|
| 323 | fmt += "B" |
|---|
| 324 | elif length == 2 : |
|---|
| 325 | fmt += "H" |
|---|
| 326 | elif length == 4 : |
|---|
| 327 | fmt += "I" |
|---|
| 328 | else : |
|---|
| 329 | raise PDLAnalyzerError, "Error on array size at %s" % self.infile.tell() |
|---|
| 330 | arraysize = struct.unpack(fmt, sarraysize)[0] |
|---|
| 331 | self.debug("Array at %s, itemsize %s, datatype 0x%02x, size %s" % (pos, itemsize, ord(datatype), arraysize)) |
|---|
| 332 | return arraysize * itemsize |
|---|
| 333 | |
|---|
| 334 | def array_8(self) : |
|---|
| 335 | """Handles byte arrays.""" |
|---|
| 336 | return self.handleArray(1) |
|---|
| 337 | |
|---|
| 338 | def array_16(self) : |
|---|
| 339 | """Handles byte arrays.""" |
|---|
| 340 | return self.handleArray(2) |
|---|
| 341 | |
|---|
| 342 | def array_32(self) : |
|---|
| 343 | """Handles byte arrays.""" |
|---|
| 344 | return self.handleArray(4) |
|---|
| 345 | |
|---|
| 346 | def embeddedDataSmall(self) : |
|---|
| 347 | """Handle small amounts of data.""" |
|---|
| 348 | pos = self.infile.tell() |
|---|
| 349 | val = ord(self.infile.read(1)) |
|---|
| 350 | self.debug("smalldatablock at %s (0x%02x)" % (pos, val)) |
|---|
| 351 | return val |
|---|
| 352 | |
|---|
| 353 | def embeddedData(self) : |
|---|
| 354 | """Handle normal amounts of data.""" |
|---|
| 355 | if self.islittleendian : |
|---|
| 356 | fmt = "<I" |
|---|
| 357 | else : |
|---|
| 358 | fmt = ">I" |
|---|
| 359 | pos = self.infile.tell() |
|---|
| 360 | val = struct.unpack(fmt, self.infile.read(4))[0] |
|---|
| 361 | self.debug("datablock at %s (0x%08x)" % (pos, val)) |
|---|
| 362 | return val |
|---|
| 363 | |
|---|
| 364 | def littleendian(self) : |
|---|
| 365 | """Toggles to little endianness.""" |
|---|
| 366 | self.islittleendian = 1 # little endian |
|---|
| 367 | |
|---|
| 368 | def bigendian(self) : |
|---|
| 369 | """Toggles to big endianness.""" |
|---|
| 370 | self.islittleendian = 0 # big endian |
|---|
| 371 | |
|---|
| 372 | def getJobSize(self) : |
|---|
| 373 | """Counts pages in a PCLXL (PCL6) document.""" |
|---|
| 374 | self.pagecount = 0 |
|---|
| 375 | while 1 : |
|---|
| 376 | char = self.infile.read(1) |
|---|
| 377 | if not char : |
|---|
| 378 | break |
|---|
| 379 | index = ord(char) |
|---|
| 380 | length = self.tags[index]() |
|---|
| 381 | if length : |
|---|
| 382 | self.infile.read(length) |
|---|
| 383 | return self.pagecount |
|---|
| 384 | |
|---|
| 385 | class PDLAnalyzer : |
|---|
| 386 | """Generic PDL Analyzer class.""" |
|---|
| 387 | def __init__(self, filename) : |
|---|
| 388 | """Initializes the PDL analyzer. |
|---|
| 389 | |
|---|
| 390 | filename is the name of the file or '-' for stdin. |
|---|
| 391 | filename can also be a file-like object which |
|---|
| 392 | supports read() and seek(). |
|---|
| 393 | """ |
|---|
| 394 | self.filename = filename |
|---|
| 395 | |
|---|
| 396 | def getJobSize(self) : |
|---|
| 397 | """Returns the job's size.""" |
|---|
| 398 | self.openFile() |
|---|
| 399 | try : |
|---|
| 400 | pdlhandler = self.detectPDLHandler() |
|---|
| 401 | except PDLAnalyzerError, msg : |
|---|
| 402 | self.closeFile() |
|---|
| 403 | raise PDLAnalyzerError, "ERROR : Unknown file format for %s (%s)" % (self.filename, msg) |
|---|
| 404 | else : |
|---|
| 405 | try : |
|---|
| 406 | size = pdlhandler(self.infile).getJobSize() |
|---|
| 407 | finally : |
|---|
| 408 | self.closeFile() |
|---|
| 409 | return size |
|---|
| 410 | |
|---|
| 411 | def openFile(self) : |
|---|
| 412 | """Opens the job's data stream for reading.""" |
|---|
| 413 | self.mustclose = 0 # by default we don't want to close the file when finished |
|---|
| 414 | if hasattr(self.filename, "read") and hasattr(self.filename, "seek") : |
|---|
| 415 | # filename is in fact a file-like object |
|---|
| 416 | infile = self.filename |
|---|
| 417 | elif self.filename == "-" : |
|---|
| 418 | # we must read from stdin |
|---|
| 419 | infile = sys.stdin |
|---|
| 420 | else : |
|---|
| 421 | # normal file |
|---|
| 422 | self.infile = open(self.filename, "rb") |
|---|
| 423 | self.mustclose = 1 |
|---|
| 424 | return |
|---|
| 425 | |
|---|
| 426 | # Use a temporary file, always seekable contrary to standard input. |
|---|
| 427 | self.infile = tempfile.TemporaryFile(mode="w+b") |
|---|
| 428 | while 1 : |
|---|
| 429 | data = infile.read(MEGABYTE) |
|---|
| 430 | if not data : |
|---|
| 431 | break |
|---|
| 432 | self.infile.write(data) |
|---|
| 433 | self.infile.flush() |
|---|
| 434 | self.infile.seek(0) |
|---|
| 435 | |
|---|
| 436 | def closeFile(self) : |
|---|
| 437 | """Closes the job's data stream if we can close it.""" |
|---|
| 438 | if self.mustclose : |
|---|
| 439 | self.infile.close() |
|---|
| 440 | else : |
|---|
| 441 | # if we don't have to close the file, then |
|---|
| 442 | # ensure the file pointer is reset to the |
|---|
| 443 | # start of the file in case the process wants |
|---|
| 444 | # to read the file again. |
|---|
| 445 | try : |
|---|
| 446 | self.infile.seek(0) |
|---|
| 447 | except : |
|---|
| 448 | pass # probably stdin, which is not seekable |
|---|
| 449 | |
|---|
| 450 | def isPostScript(self, data) : |
|---|
| 451 | """Returns 1 if data is PostScript, else 0.""" |
|---|
| 452 | if data.startswith("%!") or \ |
|---|
| 453 | data.startswith("\004%!") or \ |
|---|
| 454 | data.startswith("\033%-12345X%!PS") or \ |
|---|
| 455 | ((data[:128].find("\033%-12345X") != -1) and \ |
|---|
| 456 | ((data.find("LANGUAGE=POSTSCRIPT") != -1) or \ |
|---|
| 457 | (data.find("LANGUAGE = POSTSCRIPT") != -1) or \ |
|---|
| 458 | (data.find("LANGUAGE = Postscript") != -1))) or \ |
|---|
| 459 | (data.find("%!PS-Adobe") != -1) : |
|---|
| 460 | return 1 |
|---|
| 461 | else : |
|---|
| 462 | return 0 |
|---|
| 463 | |
|---|
| 464 | def isPDF(self, data) : |
|---|
| 465 | """Returns 1 if data is PDF, else 0.""" |
|---|
| 466 | if data.startswith("%PDF-") or \ |
|---|
| 467 | data.startswith("\033%-12345X%PDF-") or \ |
|---|
| 468 | ((data[:128].find("\033%-12345X") != -1) and (data.upper().find("LANGUAGE=PDF") != -1)) or \ |
|---|
| 469 | (data.find("%PDF-") != -1) : |
|---|
| 470 | return 1 |
|---|
| 471 | else : |
|---|
| 472 | return 0 |
|---|
| 473 | |
|---|
| 474 | def isPCL(self, data) : |
|---|
| 475 | """Returns 1 if data is PCL, else 0.""" |
|---|
| 476 | if data.startswith("\033E\033") or \ |
|---|
| 477 | ((data[:128].find("\033%-12345X") != -1) and \ |
|---|
| 478 | ((data.find("LANGUAGE=PCL") != -1) or \ |
|---|
| 479 | (data.find("LANGUAGE = PCL") != -1) or \ |
|---|
| 480 | (data.find("LANGUAGE = Pcl") != -1))) : |
|---|
| 481 | return 1 |
|---|
| 482 | else : |
|---|
| 483 | return 0 |
|---|
| 484 | |
|---|
| 485 | def isPCLXL(self, data) : |
|---|
| 486 | """Returns 1 if data is PCLXL aka PCL6, else 0.""" |
|---|
| 487 | if ((data[:128].find("\033%-12345X") != -1) and \ |
|---|
| 488 | (data.find(" HP-PCL XL;") != -1) and \ |
|---|
| 489 | ((data.find("LANGUAGE=PCLXL") != -1) or \ |
|---|
| 490 | (data.find("LANGUAGE = PCLXL") != -1))) : |
|---|
| 491 | return 1 |
|---|
| 492 | else : |
|---|
| 493 | return 0 |
|---|
| 494 | |
|---|
| 495 | def detectPDLHandler(self) : |
|---|
| 496 | """Tries to autodetect the document format. |
|---|
| 497 | |
|---|
| 498 | Returns the correct PDL handler class or None if format is unknown |
|---|
| 499 | """ |
|---|
| 500 | # Try to detect file type by reading first block of datas |
|---|
| 501 | self.infile.seek(0) |
|---|
| 502 | firstblock = self.infile.read(KILOBYTE) |
|---|
| 503 | self.infile.seek(0) |
|---|
| 504 | if self.isPostScript(firstblock) : |
|---|
| 505 | return PostScriptAnalyzer |
|---|
| 506 | elif self.isPCLXL(firstblock) : |
|---|
| 507 | return PCLXLAnalyzer |
|---|
| 508 | elif self.isPCL(firstblock) : |
|---|
| 509 | return PCLAnalyzer |
|---|
| 510 | elif self.isPDF(firstblock) : |
|---|
| 511 | return PDFAnalyzer |
|---|
| 512 | else : |
|---|
| 513 | raise PDLAnalyzerError, "Analysis of first data block failed." |
|---|
| 514 | |
|---|
| 515 | def main() : |
|---|
| 516 | """Entry point for PDL Analyzer.""" |
|---|
| 517 | if (len(sys.argv) < 2) or ((not sys.stdin.isatty()) and ("-" not in sys.argv[1:])) : |
|---|
| 518 | sys.argv.append("-") |
|---|
| 519 | |
|---|
| 520 | totalsize = 0 |
|---|
| 521 | for arg in sys.argv[1:] : |
|---|
| 522 | try : |
|---|
| 523 | parser = PDLAnalyzer(arg) |
|---|
| 524 | totalsize += parser.getJobSize() |
|---|
| 525 | except PDLAnalyzerError, msg : |
|---|
| 526 | sys.stderr.write("ERROR: %s\n" % msg) |
|---|
| 527 | sys.stderr.flush() |
|---|
| 528 | print "%s" % totalsize |
|---|
| 529 | |
|---|
| 530 | if __name__ == "__main__" : |
|---|
| 531 | main() |
|---|
