[1430] | 1 | #! /usr/bin/env python |
---|
| 2 | # -*- coding: ISO-8859-15 -*- |
---|
| 3 | |
---|
| 4 | # pkpgcounter, a smart software page counter |
---|
| 5 | # |
---|
| 6 | # PyKota - Print Quotas for CUPS and LPRng |
---|
| 7 | # |
---|
| 8 | # (c) 2003-2004 Jerome Alet <alet@librelogiciel.com> |
---|
| 9 | # This program is free software; you can redistribute it and/or modify |
---|
| 10 | # it under the terms of the GNU General Public License as published by |
---|
| 11 | # the Free Software Foundation; either version 2 of the License, or |
---|
| 12 | # (at your option) any later version. |
---|
| 13 | # |
---|
| 14 | # This program is distributed in the hope that it will be useful, |
---|
| 15 | # but WITHOUT ANY WARRANTY; without even the implied warranty of |
---|
| 16 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
---|
| 17 | # GNU General Public License for more details. |
---|
| 18 | # |
---|
| 19 | # You should have received a copy of the GNU General Public License |
---|
| 20 | # along with this program; if not, write to the Free Software |
---|
| 21 | # Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307, USA. |
---|
| 22 | # |
---|
| 23 | # $Id$ |
---|
| 24 | # |
---|
| 25 | # $Log$ |
---|
[1462] | 26 | # Revision 1.8 2004/05/08 15:12:23 jalet |
---|
| 27 | # Improved PCL6 support |
---|
| 28 | # |
---|
[1461] | 29 | # Revision 1.7 2004/05/07 23:08:21 jalet |
---|
| 30 | # Skeleton for PCLXL aka PCL6 |
---|
| 31 | # Added the "potential" fix for rastertoprinter's output |
---|
| 32 | # |
---|
[1456] | 33 | # Revision 1.6 2004/05/06 21:19:27 jalet |
---|
| 34 | # Doesn't exit anymore on the first nul byte |
---|
| 35 | # |
---|
[1451] | 36 | # Revision 1.5 2004/05/06 12:37:29 jalet |
---|
| 37 | # pkpgcounter : comments |
---|
| 38 | # pkprinters : when --add is used, existing printers are now skipped. |
---|
| 39 | # |
---|
[1449] | 40 | # Revision 1.4 2004/05/04 12:21:55 jalet |
---|
| 41 | # Now uses mmap in PCL mode |
---|
| 42 | # |
---|
[1448] | 43 | # Revision 1.3 2004/05/04 04:39:26 jalet |
---|
| 44 | # Better PCL support |
---|
| 45 | # |
---|
[1447] | 46 | # Revision 1.2 2004/05/04 03:14:26 jalet |
---|
| 47 | # fixed copy&paste problem in pkpgcounter |
---|
| 48 | # |
---|
[1430] | 49 | # Revision 1.1 2004/04/08 17:07:42 jalet |
---|
| 50 | # pkpgcounter added |
---|
| 51 | # |
---|
| 52 | # |
---|
| 53 | |
---|
| 54 | import sys |
---|
[1449] | 55 | import os |
---|
| 56 | import mmap |
---|
[1462] | 57 | import struct |
---|
[1430] | 58 | import tempfile |
---|
| 59 | |
---|
[1462] | 60 | def debug(msg) : |
---|
| 61 | """Outputs a debug message on stderr.""" |
---|
| 62 | sys.stderr.write("%s\n" % msg) |
---|
| 63 | sys.stderr.flush() |
---|
| 64 | |
---|
[1430] | 65 | def ispostscript(data) : |
---|
| 66 | """Returns 1 if data is PostScript, else 0.""" |
---|
| 67 | if data.startswith("%!") or \ |
---|
| 68 | data.startswith("\004%!") or \ |
---|
| 69 | data.startswith("\033%-12345X%!PS") or \ |
---|
| 70 | ((data[:128].find("\033%-12345X") != -1) and \ |
---|
| 71 | ((data.find("LANGUAGE=POSTSCRIPT") != -1) or \ |
---|
| 72 | (data.find("LANGUAGE = POSTSCRIPT") != -1) or \ |
---|
| 73 | (data.find("LANGUAGE = Postscript") != -1))) : |
---|
| 74 | return 1 |
---|
| 75 | else : |
---|
| 76 | return 0 |
---|
| 77 | |
---|
[1461] | 78 | def ispcl(data) : |
---|
| 79 | """Returns 1 if data is PCL, else 0.""" |
---|
| 80 | if data.startswith("\033E\033") or \ |
---|
| 81 | ((data[:128].find("\033%-12345X") != -1) and \ |
---|
| 82 | ((data.find("LANGUAGE=PCL") != -1) or \ |
---|
| 83 | (data.find("LANGUAGE = PCL") != -1) or \ |
---|
| 84 | (data.find("LANGUAGE = Pcl") != -1))) : |
---|
| 85 | return 1 |
---|
| 86 | else : |
---|
| 87 | return 0 |
---|
| 88 | |
---|
| 89 | def ispclxl(data) : |
---|
| 90 | """Returns 1 if data is PCLXL aka PCL6, else 0.""" |
---|
| 91 | if ((data[:128].find("\033%-12345X") != -1) and \ |
---|
| 92 | (data.find(" HP-PCL XL;") != -1) and \ |
---|
| 93 | ((data.find("LANGUAGE=PCLXL") != -1) or \ |
---|
| 94 | (data.find("LANGUAGE = PCLXL") != -1))) : |
---|
| 95 | return 1 |
---|
| 96 | else : |
---|
| 97 | return 0 |
---|
| 98 | |
---|
[1430] | 99 | def postscript(infile) : |
---|
[1461] | 100 | """Count pages in a DSC compliant PostScript document.""" |
---|
[1430] | 101 | pagecount = 0 |
---|
| 102 | pagenum = None |
---|
| 103 | while 1 : |
---|
| 104 | line = infile.readline() |
---|
| 105 | if not line : |
---|
| 106 | break |
---|
| 107 | if line.startswith("%%Page: ") : |
---|
| 108 | pagecount += 1 |
---|
| 109 | return pagecount |
---|
| 110 | |
---|
| 111 | def pcl(infile) : |
---|
[1461] | 112 | """Count pages in a PCL5 document.""" |
---|
[1430] | 113 | # |
---|
| 114 | # Algorithm from pclcount |
---|
| 115 | # (c) 2003, by Eduardo Gielamo Oliveira & Rodolfo Broco Manin |
---|
| 116 | # published under the terms of the GNU General Public Licence v2. |
---|
| 117 | # |
---|
[1449] | 118 | # Backported from C to Python by Jerome Alet, then enhanced |
---|
| 119 | # with more PCL tags detected. I think all the necessary PCL tags |
---|
[1451] | 120 | # are recognized to correctly handle PCL5 files wrt their number |
---|
| 121 | # of pages. The documentation used for this was : |
---|
| 122 | # |
---|
| 123 | # HP PCL/PJL Reference Set |
---|
| 124 | # PCL5 Printer Language Technical Quick Reference Guide |
---|
| 125 | # http://h20000.www2.hp.com/bc/docs/support/SupportManual/bpl13205/bpl13205.pdf |
---|
| 126 | # |
---|
[1449] | 127 | infileno = infile.fileno() |
---|
| 128 | infile = mmap.mmap(infileno, os.fstat(infileno).st_size, access=mmap.ACCESS_READ) |
---|
[1451] | 129 | tagsends = { "&n" : "W", |
---|
| 130 | "&b" : "W", |
---|
| 131 | "*i" : "W", |
---|
| 132 | "*l" : "W", |
---|
| 133 | "*m" : "W", |
---|
| 134 | "*v" : "W", |
---|
| 135 | "*c" : "W", |
---|
| 136 | "(f" : "W", |
---|
| 137 | "*b" : "VW", |
---|
| 138 | "(s" : "W", |
---|
| 139 | ")s" : "W", |
---|
| 140 | "&p" : "X", |
---|
| 141 | "&l" : "X" } |
---|
[1430] | 142 | copies = 1 |
---|
[1461] | 143 | pagecount = resets = 0 |
---|
[1430] | 144 | tag = None |
---|
[1449] | 145 | position = 0 |
---|
[1430] | 146 | while 1 : |
---|
[1449] | 147 | try : |
---|
| 148 | char = infile[position] |
---|
| 149 | except IndexError : # EOF |
---|
| 150 | break |
---|
| 151 | position += 1 |
---|
[1430] | 152 | if char == "\014" : |
---|
| 153 | pagecount += 1 |
---|
| 154 | elif char == "\033" : |
---|
| 155 | # |
---|
[1448] | 156 | # <ESC>*b###W -> Start of a raster data row/block |
---|
| 157 | # <ESC>*b###V -> Start of a raster data plane |
---|
| 158 | # <ESC>*c###W -> Start of a user defined pattern |
---|
| 159 | # <ESC>*i###W -> Start of a viewing illuminant block |
---|
| 160 | # <ESC>*l###W -> Start of a color lookup table |
---|
| 161 | # <ESC>*m###W -> Start of a download dither matrix block |
---|
| 162 | # <ESC>*v###W -> Start of a configure image data block |
---|
[1430] | 163 | # <ESC>(s###W -> Start of a characters description block |
---|
| 164 | # <ESC>)s###W -> Start of a fonts description block |
---|
[1448] | 165 | # <ESC>(f###W -> Start of a symbol set block |
---|
| 166 | # <ESC>&b###W -> Start of configuration data block |
---|
| 167 | # <ESC>&l###X -> Number of copies |
---|
| 168 | # <ESC>&n###W -> Starts an alphanumeric string ID block |
---|
[1430] | 169 | # <ESC>&p###X -> Start of a non printable characters block |
---|
| 170 | # |
---|
[1449] | 171 | tagstart = infile[position] |
---|
| 172 | position += 1 |
---|
[1448] | 173 | if tagstart in "E9=YZ" : # one byte PCL tag |
---|
[1461] | 174 | if tagstart == "E" : |
---|
| 175 | resets += 1 |
---|
[1448] | 176 | continue # skip to next tag |
---|
[1449] | 177 | tag = tagstart + infile[position] |
---|
| 178 | position += 1 |
---|
[1430] | 179 | try : |
---|
| 180 | tagend = tagsends[tag] |
---|
| 181 | except KeyError : |
---|
| 182 | pass # Unsupported PCL tag |
---|
| 183 | else : |
---|
| 184 | # Now read the numeric argument |
---|
| 185 | size = 0 |
---|
| 186 | while 1 : |
---|
[1449] | 187 | char = infile[position] |
---|
| 188 | position += 1 |
---|
[1430] | 189 | if not char.isdigit() : |
---|
| 190 | break |
---|
| 191 | size = (size * 10) + int(char) |
---|
[1448] | 192 | if char in tagend : |
---|
[1430] | 193 | if tag == "&l" : |
---|
| 194 | copies = size |
---|
| 195 | else : |
---|
| 196 | # doing a read will prevent the seek |
---|
| 197 | # for unseekable streams. |
---|
| 198 | # we just ignore the block anyway. |
---|
[1448] | 199 | if tag == "&n" : |
---|
| 200 | # we have to take care of the operation id byte |
---|
| 201 | # which is before the string itself |
---|
| 202 | size += 1 |
---|
[1449] | 203 | position += size |
---|
[1461] | 204 | |
---|
| 205 | # if pagecount is still 0, we will return the number |
---|
| 206 | # of resets instead of the number of form feed characters. |
---|
| 207 | # but the number of resets is always at least 2 with a valid |
---|
| 208 | # pcl file : one at the very start and one at the very end |
---|
| 209 | # of the job's data. So we substract 2 from the number of |
---|
| 210 | # resets. And since on our test data we needed to substract |
---|
| 211 | # 1 more, we finally substract 3, and will test several |
---|
| 212 | # PCL files with this. If resets < 2, then the file is |
---|
| 213 | # probably not a valid PCL file, so we return 0 |
---|
| 214 | if not pagecount : |
---|
| 215 | return copies * (resets - 3) * (resets > 2) |
---|
| 216 | else : |
---|
| 217 | return copies * pagecount |
---|
[1430] | 218 | |
---|
[1462] | 219 | class PCLXLParser : |
---|
| 220 | def __init__(self, infile) : |
---|
| 221 | """Initialize PCLXL parser.""" |
---|
| 222 | self.infile = infile |
---|
| 223 | self.islittleendian = None |
---|
| 224 | found = 0 |
---|
| 225 | while not found : |
---|
| 226 | line = self.infile.readline() |
---|
| 227 | if not line : |
---|
| 228 | break |
---|
| 229 | if line[1:12] == " HP-PCL XL;" : |
---|
| 230 | found = 1 |
---|
| 231 | if line[0] == ")" : |
---|
| 232 | self.littleendian() |
---|
| 233 | elif line[0] == "(" : |
---|
| 234 | self.bigendian() |
---|
| 235 | if not found : |
---|
| 236 | raise TypeError, "This file doesn't seem to be PCLXL (aka PCL6)" |
---|
| 237 | else : |
---|
| 238 | self.tags = [None] * 256 |
---|
| 239 | self.tags[0x28] = self.bigendian # big endian |
---|
| 240 | self.tags[0x29] = self.littleendian # big endian |
---|
| 241 | self.tags[0x43] = self.beginPage # BeginPage |
---|
| 242 | self.tags[0x44] = self.endPage # EndPage |
---|
| 243 | |
---|
| 244 | self.tags[0xc0] = 1 # ubyte |
---|
| 245 | self.tags[0xc1] = 2 # uint16 |
---|
| 246 | self.tags[0xc2] = 4 # uint32 |
---|
| 247 | self.tags[0xc3] = 2 # sint16 |
---|
| 248 | self.tags[0xc4] = 4 # sint32 |
---|
| 249 | self.tags[0xc5] = 4 # real32 |
---|
| 250 | |
---|
| 251 | self.tags[0xc8] = self.array_8 # ubyte_array |
---|
| 252 | self.tags[0xc9] = self.array_16 # uint16_array |
---|
| 253 | self.tags[0xca] = self.array_32 # uint32_array |
---|
| 254 | self.tags[0xcb] = self.array_16 # sint16_array |
---|
| 255 | self.tags[0xcc] = self.array_32 # sint32_array |
---|
| 256 | self.tags[0xcd] = self.array_32 # real32_array |
---|
| 257 | |
---|
| 258 | self.tags[0xd0] = 2 # ubyte_xy |
---|
| 259 | self.tags[0xd1] = 4 # uint16_xy |
---|
| 260 | self.tags[0xd2] = 8 # uint32_xy |
---|
| 261 | self.tags[0xd3] = 4 # sint16_xy |
---|
| 262 | self.tags[0xd4] = 8 # sint32_xy |
---|
| 263 | self.tags[0xd5] = 8 # real32_xy |
---|
| 264 | |
---|
| 265 | self.tags[0xd0] = 4 # ubyte_box |
---|
| 266 | self.tags[0xd1] = 8 # uint16_box |
---|
| 267 | self.tags[0xd2] = 16 # uint32_box |
---|
| 268 | self.tags[0xd3] = 8 # sint16_box |
---|
| 269 | self.tags[0xd4] = 16 # sint32_box |
---|
| 270 | self.tags[0xd5] = 16 # real32_box |
---|
| 271 | |
---|
| 272 | self.tags[0xf8] = 1 # attr_ubyte |
---|
| 273 | self.tags[0xf9] = 2 # attr_uint16 |
---|
| 274 | |
---|
| 275 | self.tags[0xfa] = self.embeddedData # dataLength |
---|
| 276 | self.tags[0xfb] = self.embeddedDataSmall # dataLengthByte |
---|
| 277 | |
---|
| 278 | def beginPage(self) : |
---|
| 279 | """Indicates the beginning of a new page.""" |
---|
| 280 | self.pagecount += 1 |
---|
| 281 | debug("Begin page %i at %s" % (self.pagecount, self.infile.tell())) |
---|
| 282 | |
---|
| 283 | def endPage(self) : |
---|
| 284 | """Indicates the end of a page.""" |
---|
| 285 | debug("End page %i at %s" % (self.pagecount, self.infile.tell())) |
---|
| 286 | |
---|
| 287 | def handleArray(self, itemsize) : |
---|
| 288 | """Handles arrays.""" |
---|
| 289 | datatype = self.infile.read(1) |
---|
| 290 | length = self.tags[ord(datatype)] |
---|
| 291 | sarraysize = self.infile.read(length) |
---|
| 292 | if self.islittleendian : |
---|
| 293 | fmt = "<" |
---|
| 294 | else : |
---|
| 295 | fmt = ">" |
---|
| 296 | if length == 1 : |
---|
| 297 | fmt += "B" |
---|
| 298 | elif length == 2 : |
---|
| 299 | fmt += "H" |
---|
| 300 | elif length == 4 : |
---|
| 301 | fmt += "I" |
---|
| 302 | else : |
---|
| 303 | raise TypeError, "Error on array size at %s" % self.infile.tell() |
---|
| 304 | arraysize = struct.unpack(fmt, sarraysize)[0] |
---|
| 305 | return arraysize * itemsize |
---|
| 306 | |
---|
| 307 | def array_8(self) : |
---|
| 308 | """Handles byte arrays.""" |
---|
| 309 | return self.handleArray(1) |
---|
| 310 | |
---|
| 311 | def array_16(self) : |
---|
| 312 | """Handles byte arrays.""" |
---|
| 313 | return self.handleArray(2) |
---|
| 314 | |
---|
| 315 | def array_32(self) : |
---|
| 316 | """Handles byte arrays.""" |
---|
| 317 | return self.handleArray(4) |
---|
| 318 | |
---|
| 319 | def embeddedDataSmall(self) : |
---|
| 320 | """Handle small amounts of data.""" |
---|
| 321 | return ord(self.infile.read(1)) |
---|
| 322 | |
---|
| 323 | def embeddedData(self) : |
---|
| 324 | """Handle normal amounts of data.""" |
---|
| 325 | if self.islittleendian : |
---|
| 326 | fmt = "<I" |
---|
| 327 | else : |
---|
| 328 | fmt = ">I" |
---|
| 329 | return struct.unpack(fmt, self.infile.read(4))[0] |
---|
| 330 | |
---|
| 331 | def littleendian(self) : |
---|
| 332 | """Toggles to little endianness.""" |
---|
| 333 | self.islittleendian = 1 # little endian |
---|
| 334 | |
---|
| 335 | def bigendian(self) : |
---|
| 336 | """Toggles to big endianness.""" |
---|
| 337 | self.islittleendian = 0 # big endian |
---|
| 338 | |
---|
| 339 | def pagecount(self) : |
---|
| 340 | """Counts pages in a PCLXL (PCL6) document.""" |
---|
| 341 | self.pagecount = 0 |
---|
| 342 | while 1 : |
---|
| 343 | pos = self.infile.tell() |
---|
| 344 | char = self.infile.read(1) |
---|
| 345 | if not char : |
---|
| 346 | break |
---|
| 347 | index = ord(char) |
---|
| 348 | length = self.tags[index] |
---|
| 349 | if length is not None : |
---|
| 350 | if not length : |
---|
| 351 | debug("Unrecognized tag 0x%02x at %s\n" % (index, self.infile.tell())) |
---|
| 352 | elif callable(length) : |
---|
| 353 | length = length() |
---|
| 354 | if length : |
---|
| 355 | self.infile.read(length) |
---|
| 356 | return self.pagecount |
---|
| 357 | |
---|
[1461] | 358 | def pclxl(infile) : |
---|
| 359 | """Count pages in a PCL6 aka PCLXL document.""" |
---|
[1462] | 360 | parser = PCLXLParser(infile) |
---|
| 361 | return parser.pagecount() |
---|
[1461] | 362 | |
---|
[1430] | 363 | def smartpagecounter(filename) : |
---|
| 364 | """Autodetects file format and returns number of pages.""" |
---|
| 365 | if filename == "-" : |
---|
| 366 | # we must read from stdin |
---|
| 367 | # but since stdin is not seekable, we have to use a temporary |
---|
| 368 | # file instead. |
---|
| 369 | infile = tempfile.TemporaryFile() |
---|
| 370 | while 1 : |
---|
| 371 | data = sys.stdin.read(256 * 1024) |
---|
| 372 | if not data : |
---|
| 373 | break |
---|
| 374 | infile.write(data) |
---|
| 375 | infile.flush() |
---|
| 376 | infile.seek(0) |
---|
| 377 | else : |
---|
| 378 | # normal file |
---|
| 379 | infile = open(filename, "rb") |
---|
| 380 | |
---|
| 381 | # Try to detect file type by reading first block of datas |
---|
| 382 | firstblock = infile.read(1024) |
---|
| 383 | infile.seek(0) |
---|
| 384 | if ispostscript(firstblock) : |
---|
| 385 | size = postscript(infile) |
---|
[1461] | 386 | elif ispclxl(firstblock) : |
---|
[1462] | 387 | raise TypeError, "PCLXL (aka PCL6) is not supported yet." |
---|
[1461] | 388 | size = pclxl(infile) |
---|
[1430] | 389 | elif ispcl(firstblock) : |
---|
| 390 | size = pcl(infile) |
---|
| 391 | else : |
---|
| 392 | sys.stderr.write("ERROR : Unknown file format for %s\n" % filename) |
---|
| 393 | size = 0 |
---|
| 394 | infile.close() |
---|
| 395 | return size |
---|
| 396 | |
---|
| 397 | if __name__ == "__main__" : |
---|
| 398 | if len(sys.argv) < 2 : |
---|
| 399 | sys.argv.append("-") |
---|
| 400 | |
---|
| 401 | totalsize = 0 |
---|
| 402 | for arg in sys.argv[1:] : |
---|
[1462] | 403 | try : |
---|
| 404 | totalsize += smartpagecounter(arg) |
---|
| 405 | except TypeError, msg : |
---|
| 406 | debug(msg) |
---|
[1430] | 407 | print "%s" % totalsize |
---|