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