[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 | # $Log$ |
---|
[1577] | 24 | # Revision 1.21 2004/06/28 23:11:26 jalet |
---|
| 25 | # Code de-factorization in PCLXL parser |
---|
| 26 | # |
---|
[1576] | 27 | # Revision 1.20 2004/06/28 22:38:41 jalet |
---|
| 28 | # Increased speed by a factor of 2 in PCLXL parser |
---|
| 29 | # |
---|
[1575] | 30 | # Revision 1.19 2004/06/28 21:20:30 jalet |
---|
| 31 | # PCLXL support now works ! |
---|
| 32 | # |
---|
[1574] | 33 | # Revision 1.18 2004/06/27 22:59:37 jalet |
---|
| 34 | # More work on PCLXL parser |
---|
| 35 | # |
---|
[1573] | 36 | # Revision 1.17 2004/06/26 23:20:01 jalet |
---|
| 37 | # Additionnal speedup for GhostScript generated PCL5 files |
---|
| 38 | # |
---|
[1572] | 39 | # Revision 1.16 2004/06/26 15:31:00 jalet |
---|
| 40 | # mmap reintroduced in PCL5 parser |
---|
| 41 | # |
---|
[1570] | 42 | # Revision 1.15 2004/06/26 14:14:31 jalet |
---|
| 43 | # Now uses Psyco if it is available |
---|
| 44 | # |
---|
[1568] | 45 | # Revision 1.14 2004/06/25 09:50:28 jalet |
---|
| 46 | # More debug info in PCLXL parser |
---|
| 47 | # |
---|
[1567] | 48 | # Revision 1.13 2004/06/25 08:10:08 jalet |
---|
| 49 | # Another fix for PCL5 parser |
---|
| 50 | # |
---|
[1566] | 51 | # Revision 1.12 2004/06/24 23:09:53 jalet |
---|
| 52 | # Fix for number of copies in PCL5 parser |
---|
| 53 | # |
---|
[1564] | 54 | # Revision 1.11 2004/06/23 22:07:50 jalet |
---|
| 55 | # Fixed PCL5 parser according to the sources of rastertohp |
---|
| 56 | # |
---|
[1553] | 57 | # Revision 1.10 2004/06/18 22:24:03 jalet |
---|
| 58 | # Removed old comments |
---|
| 59 | # |
---|
[1552] | 60 | # Revision 1.9 2004/06/18 22:21:27 jalet |
---|
| 61 | # Native PDF parser greatly improved. |
---|
| 62 | # GhostScript based PDF parser completely removed because native code |
---|
| 63 | # is now portable across Python versions. |
---|
| 64 | # |
---|
[1551] | 65 | # Revision 1.8 2004/06/18 20:49:46 jalet |
---|
| 66 | # "ERROR:" prefix added |
---|
| 67 | # |
---|
[1550] | 68 | # Revision 1.7 2004/06/18 17:48:04 jalet |
---|
| 69 | # Added native fast PDF parsing method |
---|
| 70 | # |
---|
[1547] | 71 | # Revision 1.6 2004/06/18 14:00:16 jalet |
---|
| 72 | # Added PDF support in smart PDL analyzer (through GhostScript for now) |
---|
| 73 | # |
---|
[1544] | 74 | # Revision 1.5 2004/06/18 10:09:05 jalet |
---|
| 75 | # Resets file pointer to start of file in all cases |
---|
| 76 | # |
---|
[1543] | 77 | # Revision 1.4 2004/06/18 06:16:14 jalet |
---|
| 78 | # Fixes PostScript detection code for incorrect drivers |
---|
| 79 | # |
---|
[1487] | 80 | # Revision 1.3 2004/05/21 20:40:08 jalet |
---|
| 81 | # All the code for pkpgcounter is now in pdlanalyzer.py |
---|
| 82 | # |
---|
[1485] | 83 | # Revision 1.2 2004/05/19 19:09:36 jalet |
---|
| 84 | # Speed improvement |
---|
| 85 | # |
---|
[1482] | 86 | # Revision 1.1 2004/05/18 09:59:54 jalet |
---|
| 87 | # pkpgcounter is now just a wrapper around the PDLAnalyzer class |
---|
| 88 | # |
---|
| 89 | # |
---|
| 90 | # |
---|
| 91 | |
---|
| 92 | import sys |
---|
[1547] | 93 | import os |
---|
[1552] | 94 | import re |
---|
[1482] | 95 | import struct |
---|
| 96 | import tempfile |
---|
[1572] | 97 | import mmap |
---|
[1482] | 98 | |
---|
[1487] | 99 | KILOBYTE = 1024 |
---|
| 100 | MEGABYTE = 1024 * KILOBYTE |
---|
| 101 | |
---|
| 102 | class PDLAnalyzerError(Exception): |
---|
| 103 | """An exception for PDL Analyzer related stuff.""" |
---|
| 104 | def __init__(self, message = ""): |
---|
| 105 | self.message = message |
---|
| 106 | Exception.__init__(self, message) |
---|
| 107 | def __repr__(self): |
---|
| 108 | return self.message |
---|
| 109 | __str__ = __repr__ |
---|
| 110 | |
---|
[1482] | 111 | class PostScriptAnalyzer : |
---|
| 112 | def __init__(self, infile) : |
---|
| 113 | """Initialize PostScript Analyzer.""" |
---|
| 114 | self.infile = infile |
---|
| 115 | |
---|
| 116 | def getJobSize(self) : |
---|
| 117 | """Count pages in a DSC compliant PostScript document.""" |
---|
| 118 | pagecount = 0 |
---|
[1552] | 119 | for line in self.infile.xreadlines() : |
---|
[1482] | 120 | if line.startswith("%%Page: ") : |
---|
| 121 | pagecount += 1 |
---|
| 122 | return pagecount |
---|
| 123 | |
---|
[1547] | 124 | class PDFAnalyzer : |
---|
| 125 | def __init__(self, infile) : |
---|
| 126 | """Initialize PDF Analyzer.""" |
---|
| 127 | self.infile = infile |
---|
[1550] | 128 | |
---|
[1552] | 129 | def getJobSize(self) : |
---|
| 130 | """Counts pages in a PDF document.""" |
---|
[1573] | 131 | regexp = re.compile(r"(/Type) ?(/Page)[/ \t\r\n]") |
---|
[1550] | 132 | pagecount = 0 |
---|
[1552] | 133 | for line in self.infile.xreadlines() : |
---|
| 134 | pagecount += len(regexp.findall(line)) |
---|
[1550] | 135 | return pagecount |
---|
[1547] | 136 | |
---|
[1482] | 137 | class PCLAnalyzer : |
---|
| 138 | def __init__(self, infile) : |
---|
| 139 | """Initialize PCL Analyzer.""" |
---|
| 140 | self.infile = infile |
---|
| 141 | |
---|
| 142 | def getJobSize(self) : |
---|
| 143 | """Count pages in a PCL5 document.""" |
---|
| 144 | # |
---|
| 145 | # Algorithm from pclcount |
---|
| 146 | # (c) 2003, by Eduardo Gielamo Oliveira & Rodolfo Broco Manin |
---|
| 147 | # published under the terms of the GNU General Public Licence v2. |
---|
| 148 | # |
---|
| 149 | # Backported from C to Python by Jerome Alet, then enhanced |
---|
| 150 | # with more PCL tags detected. I think all the necessary PCL tags |
---|
| 151 | # are recognized to correctly handle PCL5 files wrt their number |
---|
| 152 | # of pages. The documentation used for this was : |
---|
| 153 | # |
---|
| 154 | # HP PCL/PJL Reference Set |
---|
| 155 | # PCL5 Printer Language Technical Quick Reference Guide |
---|
| 156 | # http://h20000.www2.hp.com/bc/docs/support/SupportManual/bpl13205/bpl13205.pdf |
---|
| 157 | # |
---|
[1572] | 158 | infileno = self.infile.fileno() |
---|
| 159 | minfile = mmap.mmap(infileno, os.fstat(infileno).st_size, access=mmap.ACCESS_READ) |
---|
[1482] | 160 | tagsends = { "&n" : "W", |
---|
| 161 | "&b" : "W", |
---|
| 162 | "*i" : "W", |
---|
| 163 | "*l" : "W", |
---|
| 164 | "*m" : "W", |
---|
| 165 | "*v" : "W", |
---|
| 166 | "*c" : "W", |
---|
| 167 | "(f" : "W", |
---|
| 168 | "(s" : "W", |
---|
| 169 | ")s" : "W", |
---|
| 170 | "&p" : "X", |
---|
[1564] | 171 | "&l" : "XH", |
---|
| 172 | "&a" : "G", |
---|
[1573] | 173 | # "*b" : "VW", # treated specially because it occurs very often |
---|
[1564] | 174 | } |
---|
[1567] | 175 | pagecount = resets = ejects = backsides = 0 |
---|
[1482] | 176 | tag = None |
---|
[1566] | 177 | copies = {} |
---|
[1572] | 178 | pos = 0 |
---|
| 179 | try : |
---|
| 180 | while 1 : |
---|
| 181 | char = minfile[pos] ; pos += 1 |
---|
| 182 | if char == "\014" : |
---|
| 183 | pagecount += 1 |
---|
| 184 | elif char == "\033" : |
---|
| 185 | # |
---|
| 186 | # <ESC>*b###W -> Start of a raster data row/block |
---|
| 187 | # <ESC>*b###V -> Start of a raster data plane |
---|
| 188 | # <ESC>*c###W -> Start of a user defined pattern |
---|
| 189 | # <ESC>*i###W -> Start of a viewing illuminant block |
---|
| 190 | # <ESC>*l###W -> Start of a color lookup table |
---|
| 191 | # <ESC>*m###W -> Start of a download dither matrix block |
---|
| 192 | # <ESC>*v###W -> Start of a configure image data block |
---|
| 193 | # <ESC>(s###W -> Start of a characters description block |
---|
| 194 | # <ESC>)s###W -> Start of a fonts description block |
---|
| 195 | # <ESC>(f###W -> Start of a symbol set block |
---|
| 196 | # <ESC>&b###W -> Start of configuration data block |
---|
| 197 | # <ESC>&l###X -> Number of copies for current page |
---|
| 198 | # <ESC>&n###W -> Starts an alphanumeric string ID block |
---|
| 199 | # <ESC>&p###X -> Start of a non printable characters block |
---|
| 200 | # <ESC>&a2G -> Back side when duplex mode as generated by rastertohp |
---|
| 201 | # <ESC>&l0H -> Eject if NumPlanes > 1, as generated by rastertohp |
---|
| 202 | # |
---|
| 203 | tagstart = minfile[pos] ; pos += 1 |
---|
| 204 | if tagstart in "E9=YZ" : # one byte PCL tag |
---|
| 205 | if tagstart == "E" : |
---|
| 206 | resets += 1 |
---|
| 207 | continue # skip to next tag |
---|
| 208 | tag = tagstart + minfile[pos] ; pos += 1 |
---|
[1573] | 209 | if tag == "*b" : |
---|
| 210 | tagend = "VW" |
---|
[1572] | 211 | else : |
---|
[1573] | 212 | try : |
---|
| 213 | tagend = tagsends[tag] |
---|
| 214 | except KeyError : |
---|
| 215 | continue # Unsupported PCL tag |
---|
| 216 | # Now read the numeric argument |
---|
| 217 | size = 0 |
---|
| 218 | while 1 : |
---|
| 219 | char = minfile[pos] ; pos += 1 |
---|
| 220 | if not char.isdigit() : |
---|
| 221 | break |
---|
| 222 | size = (size * 10) + int(char) |
---|
| 223 | if char in tagend : |
---|
| 224 | if (tag == "&l") and (char == "X") : # copies for current page |
---|
| 225 | copies[pagecount] = size |
---|
| 226 | elif (tag == "&l") and (char == "H") and (size == 0) : |
---|
| 227 | ejects += 1 # Eject |
---|
| 228 | elif (tag == "&a") and (size == 2) : |
---|
| 229 | backsides += 1 # Back side in duplex mode |
---|
| 230 | else : |
---|
| 231 | # we just ignore the block. |
---|
| 232 | if tag == "&n" : |
---|
| 233 | # we have to take care of the operation id byte |
---|
| 234 | # which is before the string itself |
---|
| 235 | size += 1 |
---|
| 236 | pos += size |
---|
[1572] | 237 | except IndexError : # EOF ? |
---|
| 238 | minfile.close() # reached EOF |
---|
[1482] | 239 | |
---|
[1567] | 240 | # if pagecount is still 0, we will use the number |
---|
[1482] | 241 | # of resets instead of the number of form feed characters. |
---|
| 242 | # but the number of resets is always at least 2 with a valid |
---|
| 243 | # pcl file : one at the very start and one at the very end |
---|
| 244 | # of the job's data. So we substract 2 from the number of |
---|
| 245 | # resets. And since on our test data we needed to substract |
---|
| 246 | # 1 more, we finally substract 3, and will test several |
---|
| 247 | # PCL files with this. If resets < 2, then the file is |
---|
[1567] | 248 | # probably not a valid PCL file, so we use 0 |
---|
| 249 | if not pagecount : |
---|
| 250 | pagecount = (pagecount or ((resets - 3) * (resets > 2))) |
---|
| 251 | else : |
---|
| 252 | # here we add counters for other ways new pages may have |
---|
| 253 | # been printed and ejected by the printer |
---|
| 254 | pagecount += ejects + backsides |
---|
[1482] | 255 | |
---|
[1566] | 256 | # now handle number of copies for each page (may differ). |
---|
| 257 | # in duplex mode, number of copies may be sent only once. |
---|
| 258 | for pnum in range(pagecount) : |
---|
| 259 | # if no number of copies defined, take the preceding one else 1. |
---|
| 260 | nb = copies.get(pnum, copies.get(pnum-1, 1)) |
---|
| 261 | pagecount += (nb - 1) |
---|
| 262 | return pagecount |
---|
| 263 | |
---|
[1482] | 264 | class PCLXLAnalyzer : |
---|
| 265 | def __init__(self, infile) : |
---|
| 266 | """Initialize PCLXL Analyzer.""" |
---|
[1575] | 267 | # raise PDLAnalyzerError, "PCLXL (aka PCL6) is not supported yet." |
---|
[1482] | 268 | self.infile = infile |
---|
[1577] | 269 | self.endianness = None |
---|
[1482] | 270 | found = 0 |
---|
| 271 | while not found : |
---|
| 272 | line = self.infile.readline() |
---|
| 273 | if not line : |
---|
| 274 | break |
---|
| 275 | if line[1:12] == " HP-PCL XL;" : |
---|
| 276 | found = 1 |
---|
[1574] | 277 | endian = ord(line[0]) |
---|
| 278 | if endian == 0x29 : |
---|
[1575] | 279 | self.littleEndian() |
---|
[1574] | 280 | elif endian == 0x28 : |
---|
[1575] | 281 | self.bigEndian() |
---|
| 282 | # elif endian == 0x27 : TODO : What can we do here ? |
---|
| 283 | # |
---|
[1574] | 284 | else : |
---|
| 285 | raise PDLAnalyzerError, "No endianness marker 0x%02x at start !" % endian |
---|
[1482] | 286 | if not found : |
---|
[1487] | 287 | raise PDLAnalyzerError, "This file doesn't seem to be PCLXL (aka PCL6)" |
---|
[1482] | 288 | else : |
---|
[1575] | 289 | # Initialize table of tags |
---|
| 290 | self.tags = [ 0 ] * 256 |
---|
[1574] | 291 | |
---|
[1575] | 292 | # GhostScript's sources tell us that HP printers |
---|
| 293 | # only accept little endianness, but we can handle both. |
---|
| 294 | self.tags[0x28] = self.bigEndian # BigEndian |
---|
| 295 | self.tags[0x29] = self.littleEndian # LittleEndian |
---|
[1574] | 296 | |
---|
[1482] | 297 | self.tags[0x43] = self.beginPage # BeginPage |
---|
| 298 | |
---|
[1575] | 299 | self.tags[0xc0] = 1 # ubyte |
---|
| 300 | self.tags[0xc1] = 2 # uint16 |
---|
| 301 | self.tags[0xc2] = 4 # uint32 |
---|
| 302 | self.tags[0xc3] = 2 # sint16 |
---|
| 303 | self.tags[0xc4] = 4 # sint32 |
---|
| 304 | self.tags[0xc5] = 4 # real32 |
---|
[1574] | 305 | |
---|
[1482] | 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 | |
---|
[1575] | 313 | self.tags[0xd0] = 2 # ubyte_xy |
---|
| 314 | self.tags[0xd1] = 4 # uint16_xy |
---|
| 315 | self.tags[0xd2] = 8 # uint32_xy |
---|
| 316 | self.tags[0xd3] = 4 # sint16_xy |
---|
| 317 | self.tags[0xd4] = 8 # sint32_xy |
---|
| 318 | self.tags[0xd5] = 8 # real32_xy |
---|
[1482] | 319 | |
---|
[1575] | 320 | self.tags[0xe0] = 4 # ubyte_box |
---|
| 321 | self.tags[0xe1] = 8 # uint16_box |
---|
| 322 | self.tags[0xe2] = 16 # uint32_box |
---|
| 323 | self.tags[0xe3] = 8 # sint16_box |
---|
| 324 | self.tags[0xe4] = 16 # sint32_box |
---|
| 325 | self.tags[0xe5] = 16 # real32_box |
---|
[1482] | 326 | |
---|
[1575] | 327 | self.tags[0xf8] = 1 # attr_ubyte |
---|
| 328 | self.tags[0xf9] = 2 # attr_uint16 |
---|
[1482] | 329 | |
---|
| 330 | self.tags[0xfa] = self.embeddedData # dataLength |
---|
| 331 | self.tags[0xfb] = self.embeddedDataSmall # dataLengthByte |
---|
| 332 | |
---|
| 333 | def beginPage(self) : |
---|
| 334 | """Indicates the beginning of a new page.""" |
---|
| 335 | self.pagecount += 1 |
---|
[1575] | 336 | return 0 |
---|
[1482] | 337 | |
---|
[1577] | 338 | def array_8(self) : |
---|
| 339 | """Handles byte arrays.""" |
---|
[1576] | 340 | pos = self.pos |
---|
| 341 | datatype = self.minfile[pos] |
---|
| 342 | pos += 1 |
---|
[1575] | 343 | length = self.tags[ord(datatype)] |
---|
[1576] | 344 | if callable(length) : |
---|
| 345 | self.pos = pos |
---|
[1575] | 346 | length = length() |
---|
[1576] | 347 | pos = self.pos |
---|
[1575] | 348 | posl = pos + length |
---|
| 349 | sarraysize = self.minfile[pos:posl] |
---|
| 350 | self.pos = posl |
---|
| 351 | if length == 1 : |
---|
[1577] | 352 | return struct.unpack(self.endianness + "B", sarraysize)[0] |
---|
[1575] | 353 | elif length == 2 : |
---|
[1577] | 354 | return struct.unpack(self.endianness + "H", sarraysize)[0] |
---|
[1575] | 355 | elif length == 4 : |
---|
[1577] | 356 | return struct.unpack(self.endianness + "I", sarraysize)[0] |
---|
[1575] | 357 | else : |
---|
| 358 | raise PDLAnalyzerError, "Error on array size at %s" % self.pos |
---|
[1482] | 359 | |
---|
| 360 | def array_16(self) : |
---|
| 361 | """Handles byte arrays.""" |
---|
[1577] | 362 | pos = self.pos |
---|
| 363 | datatype = self.minfile[pos] |
---|
| 364 | pos += 1 |
---|
| 365 | length = self.tags[ord(datatype)] |
---|
| 366 | if callable(length) : |
---|
| 367 | self.pos = pos |
---|
| 368 | length = length() |
---|
| 369 | pos = self.pos |
---|
| 370 | posl = pos + length |
---|
| 371 | sarraysize = self.minfile[pos:posl] |
---|
| 372 | self.pos = posl |
---|
| 373 | if length == 1 : |
---|
| 374 | return 2 * struct.unpack(self.endianness + "B", sarraysize)[0] |
---|
| 375 | elif length == 2 : |
---|
| 376 | return 2 * struct.unpack(self.endianness + "H", sarraysize)[0] |
---|
| 377 | elif length == 4 : |
---|
| 378 | return 2 * struct.unpack(self.endianness + "I", sarraysize)[0] |
---|
| 379 | else : |
---|
| 380 | raise PDLAnalyzerError, "Error on array size at %s" % self.pos |
---|
[1482] | 381 | |
---|
| 382 | def array_32(self) : |
---|
| 383 | """Handles byte arrays.""" |
---|
[1577] | 384 | pos = self.pos |
---|
| 385 | datatype = self.minfile[pos] |
---|
| 386 | pos += 1 |
---|
| 387 | length = self.tags[ord(datatype)] |
---|
| 388 | if callable(length) : |
---|
| 389 | self.pos = pos |
---|
| 390 | length = length() |
---|
| 391 | pos = self.pos |
---|
| 392 | posl = pos + length |
---|
| 393 | sarraysize = self.minfile[pos:posl] |
---|
| 394 | self.pos = posl |
---|
| 395 | if length == 1 : |
---|
| 396 | return 4 * struct.unpack(self.endianness + "B", sarraysize)[0] |
---|
| 397 | elif length == 2 : |
---|
| 398 | return 4 * struct.unpack(self.endianness + "H", sarraysize)[0] |
---|
| 399 | elif length == 4 : |
---|
| 400 | return 4 * struct.unpack(self.endianness + "I", sarraysize)[0] |
---|
| 401 | else : |
---|
| 402 | raise PDLAnalyzerError, "Error on array size at %s" % self.pos |
---|
[1482] | 403 | |
---|
| 404 | def embeddedDataSmall(self) : |
---|
| 405 | """Handle small amounts of data.""" |
---|
[1576] | 406 | pos = self.pos |
---|
| 407 | length = ord(self.minfile[pos]) |
---|
| 408 | self.pos = pos + 1 |
---|
[1575] | 409 | return length |
---|
[1482] | 410 | |
---|
| 411 | def embeddedData(self) : |
---|
| 412 | """Handle normal amounts of data.""" |
---|
[1577] | 413 | fmt = self.endianness + "I" |
---|
[1575] | 414 | pos = self.pos |
---|
| 415 | pos4 = pos + 4 |
---|
| 416 | data = self.minfile[pos:pos4] |
---|
| 417 | self.pos = pos4 |
---|
| 418 | return struct.unpack(fmt, data)[0] |
---|
[1482] | 419 | |
---|
[1575] | 420 | def littleEndian(self) : |
---|
[1482] | 421 | """Toggles to little endianness.""" |
---|
[1577] | 422 | self.endianness = "<" # little endian |
---|
[1575] | 423 | return 0 |
---|
[1482] | 424 | |
---|
[1575] | 425 | def bigEndian(self) : |
---|
[1482] | 426 | """Toggles to big endianness.""" |
---|
[1577] | 427 | self.endianness = ">" # big endian |
---|
[1575] | 428 | return 0 |
---|
[1482] | 429 | |
---|
| 430 | def getJobSize(self) : |
---|
| 431 | """Counts pages in a PCLXL (PCL6) document.""" |
---|
[1575] | 432 | infileno = self.infile.fileno() |
---|
[1576] | 433 | self.minfile = minfile = mmap.mmap(infileno, os.fstat(infileno).st_size, access=mmap.ACCESS_READ) |
---|
| 434 | tags = self.tags |
---|
[1482] | 435 | self.pagecount = 0 |
---|
[1576] | 436 | self.pos = pos = self.infile.tell() |
---|
[1575] | 437 | try : |
---|
| 438 | while 1 : |
---|
[1576] | 439 | char = minfile[pos] |
---|
| 440 | pos += 1 |
---|
| 441 | length = tags[ord(char)] |
---|
| 442 | if not length : |
---|
[1575] | 443 | continue |
---|
| 444 | if callable(length) : |
---|
[1576] | 445 | self.pos = pos |
---|
[1575] | 446 | length = length() |
---|
[1576] | 447 | pos = self.pos |
---|
| 448 | pos += length |
---|
[1575] | 449 | except IndexError : # EOF ? |
---|
| 450 | self.minfile.close() # reached EOF |
---|
[1482] | 451 | return self.pagecount |
---|
[1487] | 452 | |
---|
[1482] | 453 | class PDLAnalyzer : |
---|
| 454 | """Generic PDL Analyzer class.""" |
---|
| 455 | def __init__(self, filename) : |
---|
[1487] | 456 | """Initializes the PDL analyzer. |
---|
| 457 | |
---|
| 458 | filename is the name of the file or '-' for stdin. |
---|
| 459 | filename can also be a file-like object which |
---|
| 460 | supports read() and seek(). |
---|
| 461 | """ |
---|
[1482] | 462 | self.filename = filename |
---|
[1570] | 463 | try : |
---|
| 464 | import psyco |
---|
| 465 | except ImportError : |
---|
| 466 | pass # Psyco is not installed |
---|
| 467 | else : |
---|
| 468 | # Psyco is installed, tell it to compile |
---|
| 469 | # the CPU intensive methods : PCL and PCLXL |
---|
| 470 | # parsing will greatly benefit from this, |
---|
| 471 | # for PostScript and PDF the difference is |
---|
| 472 | # barely noticeable since they are already |
---|
| 473 | # almost optimal, and much more speedy anyway. |
---|
| 474 | psyco.bind(PostScriptAnalyzer.getJobSize) |
---|
| 475 | psyco.bind(PDFAnalyzer.getJobSize) |
---|
| 476 | psyco.bind(PCLAnalyzer.getJobSize) |
---|
| 477 | psyco.bind(PCLXLAnalyzer.getJobSize) |
---|
[1482] | 478 | |
---|
| 479 | def getJobSize(self) : |
---|
| 480 | """Returns the job's size.""" |
---|
| 481 | self.openFile() |
---|
[1487] | 482 | try : |
---|
| 483 | pdlhandler = self.detectPDLHandler() |
---|
| 484 | except PDLAnalyzerError, msg : |
---|
| 485 | self.closeFile() |
---|
| 486 | raise PDLAnalyzerError, "ERROR : Unknown file format for %s (%s)" % (self.filename, msg) |
---|
| 487 | else : |
---|
[1482] | 488 | try : |
---|
| 489 | size = pdlhandler(self.infile).getJobSize() |
---|
| 490 | finally : |
---|
| 491 | self.closeFile() |
---|
| 492 | return size |
---|
| 493 | |
---|
| 494 | def openFile(self) : |
---|
| 495 | """Opens the job's data stream for reading.""" |
---|
[1550] | 496 | self.mustclose = 0 # by default we don't want to close the file when finished |
---|
[1487] | 497 | if hasattr(self.filename, "read") and hasattr(self.filename, "seek") : |
---|
| 498 | # filename is in fact a file-like object |
---|
[1550] | 499 | infile = self.filename |
---|
[1487] | 500 | elif self.filename == "-" : |
---|
[1482] | 501 | # we must read from stdin |
---|
[1550] | 502 | infile = sys.stdin |
---|
[1482] | 503 | else : |
---|
| 504 | # normal file |
---|
[1553] | 505 | self.infile = open(self.filename, "rb") |
---|
[1550] | 506 | self.mustclose = 1 |
---|
| 507 | return |
---|
[1482] | 508 | |
---|
[1550] | 509 | # Use a temporary file, always seekable contrary to standard input. |
---|
[1553] | 510 | self.infile = tempfile.TemporaryFile(mode="w+b") |
---|
[1550] | 511 | while 1 : |
---|
| 512 | data = infile.read(MEGABYTE) |
---|
| 513 | if not data : |
---|
| 514 | break |
---|
| 515 | self.infile.write(data) |
---|
| 516 | self.infile.flush() |
---|
| 517 | self.infile.seek(0) |
---|
| 518 | |
---|
[1482] | 519 | def closeFile(self) : |
---|
[1487] | 520 | """Closes the job's data stream if we can close it.""" |
---|
| 521 | if self.mustclose : |
---|
| 522 | self.infile.close() |
---|
[1544] | 523 | else : |
---|
| 524 | # if we don't have to close the file, then |
---|
| 525 | # ensure the file pointer is reset to the |
---|
| 526 | # start of the file in case the process wants |
---|
| 527 | # to read the file again. |
---|
| 528 | try : |
---|
| 529 | self.infile.seek(0) |
---|
| 530 | except : |
---|
| 531 | pass # probably stdin, which is not seekable |
---|
[1482] | 532 | |
---|
| 533 | def isPostScript(self, data) : |
---|
| 534 | """Returns 1 if data is PostScript, else 0.""" |
---|
| 535 | if data.startswith("%!") or \ |
---|
| 536 | data.startswith("\004%!") or \ |
---|
| 537 | data.startswith("\033%-12345X%!PS") or \ |
---|
| 538 | ((data[:128].find("\033%-12345X") != -1) and \ |
---|
| 539 | ((data.find("LANGUAGE=POSTSCRIPT") != -1) or \ |
---|
| 540 | (data.find("LANGUAGE = POSTSCRIPT") != -1) or \ |
---|
[1543] | 541 | (data.find("LANGUAGE = Postscript") != -1))) or \ |
---|
| 542 | (data.find("%!PS-Adobe") != -1) : |
---|
[1482] | 543 | return 1 |
---|
| 544 | else : |
---|
| 545 | return 0 |
---|
| 546 | |
---|
[1547] | 547 | def isPDF(self, data) : |
---|
| 548 | """Returns 1 if data is PDF, else 0.""" |
---|
| 549 | if data.startswith("%PDF-") or \ |
---|
| 550 | data.startswith("\033%-12345X%PDF-") or \ |
---|
| 551 | ((data[:128].find("\033%-12345X") != -1) and (data.upper().find("LANGUAGE=PDF") != -1)) or \ |
---|
| 552 | (data.find("%PDF-") != -1) : |
---|
| 553 | return 1 |
---|
| 554 | else : |
---|
| 555 | return 0 |
---|
| 556 | |
---|
[1482] | 557 | def isPCL(self, data) : |
---|
| 558 | """Returns 1 if data is PCL, else 0.""" |
---|
| 559 | if data.startswith("\033E\033") or \ |
---|
| 560 | ((data[:128].find("\033%-12345X") != -1) and \ |
---|
| 561 | ((data.find("LANGUAGE=PCL") != -1) or \ |
---|
| 562 | (data.find("LANGUAGE = PCL") != -1) or \ |
---|
| 563 | (data.find("LANGUAGE = Pcl") != -1))) : |
---|
| 564 | return 1 |
---|
| 565 | else : |
---|
| 566 | return 0 |
---|
| 567 | |
---|
| 568 | def isPCLXL(self, data) : |
---|
| 569 | """Returns 1 if data is PCLXL aka PCL6, else 0.""" |
---|
| 570 | if ((data[:128].find("\033%-12345X") != -1) and \ |
---|
| 571 | (data.find(" HP-PCL XL;") != -1) and \ |
---|
| 572 | ((data.find("LANGUAGE=PCLXL") != -1) or \ |
---|
| 573 | (data.find("LANGUAGE = PCLXL") != -1))) : |
---|
| 574 | return 1 |
---|
| 575 | else : |
---|
| 576 | return 0 |
---|
| 577 | |
---|
| 578 | def detectPDLHandler(self) : |
---|
| 579 | """Tries to autodetect the document format. |
---|
| 580 | |
---|
| 581 | Returns the correct PDL handler class or None if format is unknown |
---|
| 582 | """ |
---|
| 583 | # Try to detect file type by reading first block of datas |
---|
| 584 | self.infile.seek(0) |
---|
[1487] | 585 | firstblock = self.infile.read(KILOBYTE) |
---|
[1482] | 586 | self.infile.seek(0) |
---|
| 587 | if self.isPostScript(firstblock) : |
---|
| 588 | return PostScriptAnalyzer |
---|
| 589 | elif self.isPCLXL(firstblock) : |
---|
| 590 | return PCLXLAnalyzer |
---|
| 591 | elif self.isPCL(firstblock) : |
---|
| 592 | return PCLAnalyzer |
---|
[1547] | 593 | elif self.isPDF(firstblock) : |
---|
| 594 | return PDFAnalyzer |
---|
[1487] | 595 | else : |
---|
| 596 | raise PDLAnalyzerError, "Analysis of first data block failed." |
---|
| 597 | |
---|
| 598 | def main() : |
---|
| 599 | """Entry point for PDL Analyzer.""" |
---|
| 600 | if (len(sys.argv) < 2) or ((not sys.stdin.isatty()) and ("-" not in sys.argv[1:])) : |
---|
| 601 | sys.argv.append("-") |
---|
| 602 | |
---|
| 603 | totalsize = 0 |
---|
| 604 | for arg in sys.argv[1:] : |
---|
| 605 | try : |
---|
| 606 | parser = PDLAnalyzer(arg) |
---|
| 607 | totalsize += parser.getJobSize() |
---|
| 608 | except PDLAnalyzerError, msg : |
---|
[1551] | 609 | sys.stderr.write("ERROR: %s\n" % msg) |
---|
[1487] | 610 | sys.stderr.flush() |
---|
| 611 | print "%s" % totalsize |
---|
| 612 | |
---|
| 613 | if __name__ == "__main__" : |
---|
[1577] | 614 | main() |
---|