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 1.47 2004/12/13 20:49:53 jalet |
---|
25 | # Bad typo |
---|
26 | # |
---|
27 | # Revision 1.46 2004/12/13 20:48:33 jalet |
---|
28 | # Outputs debug info to stderr |
---|
29 | # |
---|
30 | # Revision 1.45 2004/12/13 20:39:46 jalet |
---|
31 | # Added a --debug command line option to pkpgcounter, for people interested |
---|
32 | # in seeing what happens, and what will be available in the future :-) |
---|
33 | # |
---|
34 | # Revision 1.44 2004/11/17 15:10:31 jalet |
---|
35 | # Fixed Epson Stylus Photo problem in software accounting |
---|
36 | # |
---|
37 | # Revision 1.43 2004/11/13 20:52:26 jalet |
---|
38 | # Heavy work done on PCL3/4/5 and PCLXL job analyzis |
---|
39 | # |
---|
40 | # Revision 1.42 2004/09/24 21:19:48 jalet |
---|
41 | # Did a pass of PyChecker |
---|
42 | # |
---|
43 | # Revision 1.41 2004/09/04 14:18:55 jalet |
---|
44 | # Support for more laserjet models added. |
---|
45 | # |
---|
46 | # Revision 1.40 2004/09/04 14:01:47 jalet |
---|
47 | # Support for PCL3 (HP Deskjets) added to generic PDL parser |
---|
48 | # |
---|
49 | # Revision 1.39 2004/09/02 23:30:05 jalet |
---|
50 | # Comments |
---|
51 | # |
---|
52 | # Revision 1.38 2004/09/02 22:08:37 jalet |
---|
53 | # First draft of PCL3GUI analyzer. |
---|
54 | # |
---|
55 | # Revision 1.37 2004/09/02 21:22:49 jalet |
---|
56 | # One more PCL tag |
---|
57 | # |
---|
58 | # Revision 1.36 2004/09/01 22:31:49 jalet |
---|
59 | # Some more work on ESC/P2 analyzer to avoid missing \r\n sequences. Not |
---|
60 | # exactly optimal though... |
---|
61 | # |
---|
62 | # Revision 1.35 2004/08/30 23:10:24 jalet |
---|
63 | # Improved the ESC/P2 analyzer so that more GhostScript devices are supported |
---|
64 | # |
---|
65 | # Revision 1.34 2004/08/27 09:08:22 jalet |
---|
66 | # Improvement in PostScript parser to avoid being fooled by clever "students" |
---|
67 | # |
---|
68 | # Revision 1.33 2004/08/27 09:02:34 jalet |
---|
69 | # Forgot to remove some special debugging code... |
---|
70 | # |
---|
71 | # Revision 1.32 2004/08/27 08:58:50 jalet |
---|
72 | # Relax checks for PCL5 header to accomodate strange printer drivers |
---|
73 | # |
---|
74 | # Revision 1.31 2004/08/22 08:25:33 jalet |
---|
75 | # Improved ESC/P2 miniparser thanks to Paulo Silva |
---|
76 | # |
---|
77 | # Revision 1.30 2004/08/21 23:16:57 jalet |
---|
78 | # First draft of ESC/P2 (mini-)parser. |
---|
79 | # |
---|
80 | # Revision 1.29 2004/08/11 16:25:38 jalet |
---|
81 | # Fixed index problem in PCLXL parser when retrieving number of copies for |
---|
82 | # each page |
---|
83 | # |
---|
84 | # Revision 1.28 2004/08/10 23:01:49 jalet |
---|
85 | # Fixed number of copies in PCL5 parser |
---|
86 | # |
---|
87 | # Revision 1.27 2004/08/09 18:14:22 jalet |
---|
88 | # Added workaround for number of copies and some PostScript drivers |
---|
89 | # |
---|
90 | # Revision 1.26 2004/07/22 13:49:51 jalet |
---|
91 | # Added support for binary PostScript through GhostScript if native DSC |
---|
92 | # compliant PostScript analyzer doesn't find any page. This is much |
---|
93 | # slower though, so native analyzer is tried first. |
---|
94 | # |
---|
95 | # Revision 1.25 2004/07/10 14:06:36 jalet |
---|
96 | # Fix for Python2.1 incompatibilities |
---|
97 | # |
---|
98 | # Revision 1.24 2004/07/05 21:00:39 jalet |
---|
99 | # Fix for number of copies for each page in PCLXL parser |
---|
100 | # |
---|
101 | # Revision 1.23 2004/07/03 08:21:59 jalet |
---|
102 | # Testsuite for PDL Analyzer added |
---|
103 | # |
---|
104 | # Revision 1.22 2004/06/29 14:21:41 jalet |
---|
105 | # Smallish optimization |
---|
106 | # |
---|
107 | # Revision 1.21 2004/06/28 23:11:26 jalet |
---|
108 | # Code de-factorization in PCLXL parser |
---|
109 | # |
---|
110 | # Revision 1.20 2004/06/28 22:38:41 jalet |
---|
111 | # Increased speed by a factor of 2 in PCLXL parser |
---|
112 | # |
---|
113 | # Revision 1.19 2004/06/28 21:20:30 jalet |
---|
114 | # PCLXL support now works ! |
---|
115 | # |
---|
116 | # Revision 1.18 2004/06/27 22:59:37 jalet |
---|
117 | # More work on PCLXL parser |
---|
118 | # |
---|
119 | # Revision 1.17 2004/06/26 23:20:01 jalet |
---|
120 | # Additionnal speedup for GhostScript generated PCL5 files |
---|
121 | # |
---|
122 | # Revision 1.16 2004/06/26 15:31:00 jalet |
---|
123 | # mmap reintroduced in PCL5 parser |
---|
124 | # |
---|
125 | # Revision 1.15 2004/06/26 14:14:31 jalet |
---|
126 | # Now uses Psyco if it is available |
---|
127 | # |
---|
128 | # Revision 1.14 2004/06/25 09:50:28 jalet |
---|
129 | # More debug info in PCLXL parser |
---|
130 | # |
---|
131 | # Revision 1.13 2004/06/25 08:10:08 jalet |
---|
132 | # Another fix for PCL5 parser |
---|
133 | # |
---|
134 | # Revision 1.12 2004/06/24 23:09:53 jalet |
---|
135 | # Fix for number of copies in PCL5 parser |
---|
136 | # |
---|
137 | # Revision 1.11 2004/06/23 22:07:50 jalet |
---|
138 | # Fixed PCL5 parser according to the sources of rastertohp |
---|
139 | # |
---|
140 | # Revision 1.10 2004/06/18 22:24:03 jalet |
---|
141 | # Removed old comments |
---|
142 | # |
---|
143 | # Revision 1.9 2004/06/18 22:21:27 jalet |
---|
144 | # Native PDF parser greatly improved. |
---|
145 | # GhostScript based PDF parser completely removed because native code |
---|
146 | # is now portable across Python versions. |
---|
147 | # |
---|
148 | # Revision 1.8 2004/06/18 20:49:46 jalet |
---|
149 | # "ERROR:" prefix added |
---|
150 | # |
---|
151 | # Revision 1.7 2004/06/18 17:48:04 jalet |
---|
152 | # Added native fast PDF parsing method |
---|
153 | # |
---|
154 | # Revision 1.6 2004/06/18 14:00:16 jalet |
---|
155 | # Added PDF support in smart PDL analyzer (through GhostScript for now) |
---|
156 | # |
---|
157 | # Revision 1.5 2004/06/18 10:09:05 jalet |
---|
158 | # Resets file pointer to start of file in all cases |
---|
159 | # |
---|
160 | # Revision 1.4 2004/06/18 06:16:14 jalet |
---|
161 | # Fixes PostScript detection code for incorrect drivers |
---|
162 | # |
---|
163 | # Revision 1.3 2004/05/21 20:40:08 jalet |
---|
164 | # All the code for pkpgcounter is now in pdlanalyzer.py |
---|
165 | # |
---|
166 | # Revision 1.2 2004/05/19 19:09:36 jalet |
---|
167 | # Speed improvement |
---|
168 | # |
---|
169 | # Revision 1.1 2004/05/18 09:59:54 jalet |
---|
170 | # pkpgcounter is now just a wrapper around the PDLAnalyzer class |
---|
171 | # |
---|
172 | # |
---|
173 | # |
---|
174 | |
---|
175 | import sys |
---|
176 | import os |
---|
177 | import re |
---|
178 | from struct import unpack |
---|
179 | import tempfile |
---|
180 | import mmap |
---|
181 | import popen2 |
---|
182 | |
---|
183 | KILOBYTE = 1024 |
---|
184 | MEGABYTE = 1024 * KILOBYTE |
---|
185 | LASTBLOCKSIZE = int(KILOBYTE / 4) |
---|
186 | |
---|
187 | class PDLAnalyzerError(Exception): |
---|
188 | """An exception for PDL Analyzer related stuff.""" |
---|
189 | def __init__(self, message = ""): |
---|
190 | self.message = message |
---|
191 | Exception.__init__(self, message) |
---|
192 | def __repr__(self): |
---|
193 | return self.message |
---|
194 | __str__ = __repr__ |
---|
195 | |
---|
196 | class PostScriptAnalyzer : |
---|
197 | """A class to parse PostScript documents.""" |
---|
198 | def __init__(self, infile, debug=0) : |
---|
199 | """Initialize PostScript Analyzer.""" |
---|
200 | self.debug = debug |
---|
201 | self.infile = infile |
---|
202 | self.copies = 1 |
---|
203 | |
---|
204 | def throughGhostScript(self) : |
---|
205 | """Get the count through GhostScript, useful for non-DSC compliant PS files.""" |
---|
206 | if self.debug : |
---|
207 | sys.stderr.write("Internal parser sucks, using GhostScript instead...\n") |
---|
208 | self.infile.seek(0) |
---|
209 | command = 'gs -sDEVICE=bbox -dNOPAUSE -dBATCH -dQUIET - 2>&1 | grep -c "%%HiResBoundingBox:" 2>/dev/null' |
---|
210 | child = popen2.Popen4(command) |
---|
211 | try : |
---|
212 | data = self.infile.read(MEGABYTE) |
---|
213 | while data : |
---|
214 | child.tochild.write(data) |
---|
215 | data = self.infile.read(MEGABYTE) |
---|
216 | child.tochild.flush() |
---|
217 | child.tochild.close() |
---|
218 | except (IOError, OSError), msg : |
---|
219 | raise PDLAnalyzerError, "Problem during analysis of Binary PostScript document : %s" % msg |
---|
220 | |
---|
221 | pagecount = 0 |
---|
222 | try : |
---|
223 | pagecount = int(child.fromchild.readline().strip()) |
---|
224 | except (IOError, OSError, AttributeError, ValueError), msg : |
---|
225 | raise PDLAnalyzerError, "Problem during analysis of Binary PostScript document : %s" % msg |
---|
226 | child.fromchild.close() |
---|
227 | |
---|
228 | try : |
---|
229 | child.wait() |
---|
230 | except OSError, msg : |
---|
231 | raise PDLAnalyzerError, "Problem during analysis of Binary PostScript document : %s" % msg |
---|
232 | return pagecount * self.copies |
---|
233 | |
---|
234 | def natively(self) : |
---|
235 | """Count pages in a DSC compliant PostScript document.""" |
---|
236 | self.infile.seek(0) |
---|
237 | pagecount = 0 |
---|
238 | for line in self.infile.xreadlines() : |
---|
239 | if line.startswith("%%Page: ") : |
---|
240 | pagecount += 1 |
---|
241 | elif line.startswith("%%BeginNonPPDFeature: NumCopies ") : |
---|
242 | # handle # of copies set by some Windows printer driver |
---|
243 | try : |
---|
244 | number = int(line.strip().split()[2]) |
---|
245 | except : |
---|
246 | pass |
---|
247 | else : |
---|
248 | if number > self.copies : |
---|
249 | self.copies = number |
---|
250 | elif line.startswith("1 dict dup /NumCopies ") : |
---|
251 | # handle # of copies set by mozilla/kprinter |
---|
252 | try : |
---|
253 | number = int(line.strip().split()[4]) |
---|
254 | except : |
---|
255 | pass |
---|
256 | else : |
---|
257 | if number > self.copies : |
---|
258 | self.copies = number |
---|
259 | return pagecount * self.copies |
---|
260 | |
---|
261 | def getJobSize(self) : |
---|
262 | """Count pages in PostScript document.""" |
---|
263 | return self.natively() or self.throughGhostScript() |
---|
264 | |
---|
265 | class PDFAnalyzer : |
---|
266 | """A class to parse PDF documents.""" |
---|
267 | def __init__(self, infile, debug=0) : |
---|
268 | """Initialize PDF Analyzer.""" |
---|
269 | self.debug = debug |
---|
270 | self.infile = infile |
---|
271 | |
---|
272 | def getJobSize(self) : |
---|
273 | """Counts pages in a PDF document.""" |
---|
274 | regexp = re.compile(r"(/Type) ?(/Page)[/ \t\r\n]") |
---|
275 | pagecount = 0 |
---|
276 | for line in self.infile.xreadlines() : |
---|
277 | pagecount += len(regexp.findall(line)) |
---|
278 | return pagecount |
---|
279 | |
---|
280 | class ESCP2Analyzer : |
---|
281 | """A class to parse ESC/P2 documents.""" |
---|
282 | def __init__(self, infile, debug=0) : |
---|
283 | """Initialize ESC/P2 Analyzer.""" |
---|
284 | self.debug = debug |
---|
285 | self.infile = infile |
---|
286 | |
---|
287 | def getJobSize(self) : |
---|
288 | """Counts pages in an ESC/P2 document.""" |
---|
289 | # with Gimpprint, at least, for each page there |
---|
290 | # are two Reset Printer sequences (ESC + @) |
---|
291 | marker1 = "\033@" |
---|
292 | |
---|
293 | # with other software or printer driver, we |
---|
294 | # may prefer to search for "\r\n\fESCAPE" |
---|
295 | # or "\r\fESCAPE" |
---|
296 | marker2r = "\r\f\033" |
---|
297 | marker2rn = "\r\n\f\033" |
---|
298 | |
---|
299 | # and ghostscript's stcolor for example seems to |
---|
300 | # output ESC + @ + \f for each page plus one |
---|
301 | marker3 = "\033@\f" |
---|
302 | |
---|
303 | # while ghostscript's escp driver outputs instead |
---|
304 | # \f + ESC + @ |
---|
305 | marker4 = "\f\033@" |
---|
306 | |
---|
307 | data = self.infile.read() |
---|
308 | pagecount1 = data.count(marker1) |
---|
309 | pagecount2 = max(data.count(marker2r), data.count(marker2rn)) |
---|
310 | pagecount3 = data.count(marker3) |
---|
311 | pagecount4 = data.count(marker4) |
---|
312 | |
---|
313 | if pagecount2 : |
---|
314 | return pagecount2 |
---|
315 | elif pagecount3 > 1 : |
---|
316 | return pagecount3 - 1 |
---|
317 | elif pagecount4 : |
---|
318 | return pagecount4 |
---|
319 | else : |
---|
320 | return int(pagecount1 / 2) |
---|
321 | |
---|
322 | class PCLAnalyzer : |
---|
323 | """A class to parse PCL3, PCL4, PCL5 documents.""" |
---|
324 | mediasizes = { # ESC&l####A |
---|
325 | 0 : "Default", |
---|
326 | 1 : "Executive", |
---|
327 | 2 : "Letter", |
---|
328 | 3 : "Legal", |
---|
329 | 6 : "Ledger", |
---|
330 | 25 : "A5", |
---|
331 | 26 : "A4", |
---|
332 | 27 : "A3", |
---|
333 | 45 : "JB5", |
---|
334 | 46 : "JB4", |
---|
335 | 71 : "HagakiPostcard", |
---|
336 | 72 : "OufukuHagakiPostcard", |
---|
337 | 80 : "MonarchEnvelope", |
---|
338 | 81 : "COM10Envelope", |
---|
339 | 90 : "DLEnvelope", |
---|
340 | 91 : "C5Envelope", |
---|
341 | 100 : "B5Envelope", |
---|
342 | 101 : "Custom", |
---|
343 | } |
---|
344 | |
---|
345 | mediasources = { # ESC&l####H |
---|
346 | 0 : "Default", |
---|
347 | 1 : "Main", |
---|
348 | 2 : "Manual", |
---|
349 | 3 : "ManualEnvelope", |
---|
350 | 4 : "Alternate", |
---|
351 | 5 : "OptionalLarge", |
---|
352 | 6 : "EnvelopeFeeder", |
---|
353 | 7 : "Auto", |
---|
354 | 8 : "Tray1", |
---|
355 | } |
---|
356 | |
---|
357 | orientations = { # ESC&l####O |
---|
358 | 0 : "Portrait", |
---|
359 | 1 : "Landscape", |
---|
360 | 2 : "ReversePortrait", |
---|
361 | 3 : "ReverseLandscape", |
---|
362 | } |
---|
363 | |
---|
364 | mediatypes = { # ESC&l####M |
---|
365 | 0 : "Plain", |
---|
366 | 1 : "Bond", |
---|
367 | 2 : "Special", |
---|
368 | 3 : "Glossy", |
---|
369 | 4 : "Transparent", |
---|
370 | } |
---|
371 | |
---|
372 | |
---|
373 | def __init__(self, infile, debug=0) : |
---|
374 | """Initialize PCL Analyzer.""" |
---|
375 | self.debug = debug |
---|
376 | self.infile = infile |
---|
377 | |
---|
378 | def setPageDict(self, pages, number, attribute, value) : |
---|
379 | """Initializes a page dictionnary.""" |
---|
380 | dict = pages.setdefault(number, { "copies" : 1, "mediasource" : "Main", "mediasize" : "Default", "mediatype" : "Plain", "orientation" : "Portrait"}) |
---|
381 | dict[attribute] = value |
---|
382 | |
---|
383 | def getJobSize(self) : |
---|
384 | """Count pages in a PCL5 document. |
---|
385 | |
---|
386 | Should also work for PCL3 and PCL4 documents. |
---|
387 | |
---|
388 | Algorithm from pclcount |
---|
389 | (c) 2003, by Eduardo Gielamo Oliveira & Rodolfo Broco Manin |
---|
390 | published under the terms of the GNU General Public Licence v2. |
---|
391 | |
---|
392 | Backported from C to Python by Jerome Alet, then enhanced |
---|
393 | with more PCL tags detected. I think all the necessary PCL tags |
---|
394 | are recognized to correctly handle PCL5 files wrt their number |
---|
395 | of pages. The documentation used for this was : |
---|
396 | |
---|
397 | HP PCL/PJL Reference Set |
---|
398 | PCL5 Printer Language Technical Quick Reference Guide |
---|
399 | http://h20000.www2.hp.com/bc/docs/support/SupportManual/bpl13205/bpl13205.pdf |
---|
400 | """ |
---|
401 | infileno = self.infile.fileno() |
---|
402 | minfile = mmap.mmap(infileno, os.fstat(infileno)[6], prot=mmap.PROT_READ, flags=mmap.MAP_SHARED) |
---|
403 | tagsends = { "&n" : "W", |
---|
404 | "&b" : "W", |
---|
405 | "*i" : "W", |
---|
406 | "*l" : "W", |
---|
407 | "*m" : "W", |
---|
408 | "*v" : "W", |
---|
409 | "*c" : "W", |
---|
410 | "(f" : "W", |
---|
411 | "(s" : "W", |
---|
412 | ")s" : "W", |
---|
413 | "&p" : "X", |
---|
414 | # "&l" : "XHAOM", # treated specially |
---|
415 | "&a" : "G", # TODO : 0 means next side, 1 front side, 2 back side |
---|
416 | "*g" : "W", |
---|
417 | "*r" : "sbABC", |
---|
418 | # "*b" : "VW", # treated specially because it occurs very often |
---|
419 | } |
---|
420 | pagecount = resets = ejects = backsides = startgfx = endgfx = 0 |
---|
421 | starb = ampl = ispcl3 = 0 |
---|
422 | tag = None |
---|
423 | pages = {} |
---|
424 | pos = 0 |
---|
425 | try : |
---|
426 | while 1 : |
---|
427 | char = minfile[pos] ; pos += 1 |
---|
428 | if char == "\014" : |
---|
429 | pagecount += 1 |
---|
430 | elif char == "\033" : |
---|
431 | starb = ampl = 0 |
---|
432 | # |
---|
433 | # <ESC>*b###y#m###v###w... -> PCL3 raster graphics |
---|
434 | # <ESC>*b###W -> Start of a raster data row/block |
---|
435 | # <ESC>*b###V -> Start of a raster data plane |
---|
436 | # <ESC>*c###W -> Start of a user defined pattern |
---|
437 | # <ESC>*i###W -> Start of a viewing illuminant block |
---|
438 | # <ESC>*l###W -> Start of a color lookup table |
---|
439 | # <ESC>*m###W -> Start of a download dither matrix block |
---|
440 | # <ESC>*v###W -> Start of a configure image data block |
---|
441 | # <ESC>*r1A -> Start Gfx |
---|
442 | # <ESC>(s###W -> Start of a characters description block |
---|
443 | # <ESC>)s###W -> Start of a fonts description block |
---|
444 | # <ESC>(f###W -> Start of a symbol set block |
---|
445 | # <ESC>&b###W -> Start of configuration data block |
---|
446 | # <ESC>&l###X -> Number of copies for current page |
---|
447 | # <ESC>&n###W -> Starts an alphanumeric string ID block |
---|
448 | # <ESC>&p###X -> Start of a non printable characters block |
---|
449 | # <ESC>&a2G -> Back side when duplex mode as generated by rastertohp |
---|
450 | # <ESC>*g###W -> Needed for planes in PCL3 output |
---|
451 | # <ESC>&l###H (or only 0 ?) -> Eject if NumPlanes > 1, as generated by rastertohp. Also defines mediasource |
---|
452 | # <ESC>&l###A -> mediasize |
---|
453 | # <ESC>&l###O -> orientation |
---|
454 | # <ESC>&l###M -> mediatype |
---|
455 | # |
---|
456 | tagstart = minfile[pos] ; pos += 1 |
---|
457 | if tagstart in "E9=YZ" : # one byte PCL tag |
---|
458 | if tagstart == "E" : |
---|
459 | resets += 1 |
---|
460 | continue # skip to next tag |
---|
461 | tag = tagstart + minfile[pos] ; pos += 1 |
---|
462 | if tag == "*b" : |
---|
463 | starb = 1 |
---|
464 | tagend = "VW" |
---|
465 | elif tag == "&l" : |
---|
466 | ampl = 1 |
---|
467 | tagend = "XHAOM" |
---|
468 | else : |
---|
469 | try : |
---|
470 | tagend = tagsends[tag] |
---|
471 | except KeyError : |
---|
472 | continue # Unsupported PCL tag |
---|
473 | # Now read the numeric argument |
---|
474 | size = 0 |
---|
475 | while 1 : |
---|
476 | char = minfile[pos] ; pos += 1 |
---|
477 | if not char.isdigit() : |
---|
478 | break |
---|
479 | size = (size * 10) + int(char) |
---|
480 | if char in tagend : |
---|
481 | if tag == "&l" : |
---|
482 | if char == "X" : |
---|
483 | self.setPageDict(pages, pagecount, "copies", size) |
---|
484 | elif char == "H" : |
---|
485 | self.setPageDict(pages, pagecount, "mediasource", self.mediasources.get(size, str(size))) |
---|
486 | ejects += 1 |
---|
487 | elif char == "A" : |
---|
488 | self.setPageDict(pages, pagecount, "mediasize", self.mediasizes.get(size, str(size))) |
---|
489 | elif char == "O" : |
---|
490 | self.setPageDict(pages, pagecount, "orientation", self.orientations.get(size, str(size))) |
---|
491 | elif char == "M" : |
---|
492 | self.setPageDict(pages, pagecount, "mediatype", self.mediatypes.get(size, str(size))) |
---|
493 | elif tag == "*r" : |
---|
494 | # Special tests for PCL3 |
---|
495 | if (char == "s") and size : |
---|
496 | while 1 : |
---|
497 | char = minfile[pos] ; pos += 1 |
---|
498 | if char == "A" : |
---|
499 | break |
---|
500 | elif (char == "b") and (minfile[pos] == "C") and not size : |
---|
501 | ispcl3 = 1 # Certainely a PCL3 file |
---|
502 | startgfx += (char == "A") and (minfile[pos - 2] in ("0", "1", "2", "3")) # Start Gfx |
---|
503 | endgfx += (not size) and (char in ("C", "B")) # End Gfx |
---|
504 | elif (tag == "&a") and (size == 2) : |
---|
505 | backsides += 1 # Back side in duplex mode |
---|
506 | else : |
---|
507 | # we just ignore the block. |
---|
508 | if tag == "&n" : |
---|
509 | # we have to take care of the operation id byte |
---|
510 | # which is before the string itself |
---|
511 | size += 1 |
---|
512 | pos += size |
---|
513 | else : |
---|
514 | if starb : |
---|
515 | # special handling of PCL3 in which |
---|
516 | # *b introduces combined ESCape sequences |
---|
517 | size = 0 |
---|
518 | while 1 : |
---|
519 | char = minfile[pos] ; pos += 1 |
---|
520 | if not char.isdigit() : |
---|
521 | break |
---|
522 | size = (size * 10) + int(char) |
---|
523 | if char in ("w", "v") : |
---|
524 | ispcl3 = 1 # certainely a PCL3 document |
---|
525 | pos += size - 1 |
---|
526 | elif char in ("y", "m") : |
---|
527 | ispcl3 = 1 # certainely a PCL3 document |
---|
528 | pos -= 1 # fix position : we were ahead |
---|
529 | elif ampl : |
---|
530 | # special handling of PCL3 in which |
---|
531 | # &l introduces combined ESCape sequences |
---|
532 | size = 0 |
---|
533 | while 1 : |
---|
534 | char = minfile[pos] ; pos += 1 |
---|
535 | if not char.isdigit() : |
---|
536 | break |
---|
537 | size = (size * 10) + int(char) |
---|
538 | if char in ("a", "o", "h", "m") : |
---|
539 | ispcl3 = 1 # certainely a PCL3 document |
---|
540 | pos -= 1 # fix position : we were ahead |
---|
541 | if char == "h" : |
---|
542 | self.setPageDict(pages, pagecount, "mediasource", self.mediasources.get(size, str(size))) |
---|
543 | elif char == "a" : |
---|
544 | self.setPageDict(pages, pagecount, "mediasize", self.mediasizes.get(size, str(size))) |
---|
545 | elif char == "o" : |
---|
546 | self.setPageDict(pages, pagecount, "orientation", self.orientations.get(size, str(size))) |
---|
547 | elif char == "m" : |
---|
548 | self.setPageDict(pages, pagecount, "mediatype", self.mediatypes.get(size, str(size))) |
---|
549 | except IndexError : # EOF ? |
---|
550 | minfile.close() # reached EOF |
---|
551 | |
---|
552 | # if pagecount is still 0, we will use the number |
---|
553 | # of resets instead of the number of form feed characters. |
---|
554 | # but the number of resets is always at least 2 with a valid |
---|
555 | # pcl file : one at the very start and one at the very end |
---|
556 | # of the job's data. So we substract 2 from the number of |
---|
557 | # resets. And since on our test data we needed to substract |
---|
558 | # 1 more, we finally substract 3, and will test several |
---|
559 | # PCL files with this. If resets < 2, then the file is |
---|
560 | # probably not a valid PCL file, so we use 0 |
---|
561 | if not pagecount : |
---|
562 | pagecount = (pagecount or ((resets - 3) * (resets > 2))) |
---|
563 | else : |
---|
564 | # here we add counters for other ways new pages may have |
---|
565 | # been printed and ejected by the printer |
---|
566 | pagecount += ejects + backsides |
---|
567 | |
---|
568 | # now handle number of copies for each page (may differ). |
---|
569 | # in duplex mode, number of copies may be sent only once. |
---|
570 | for pnum in range(pagecount) : |
---|
571 | # if no number of copies defined, take the preceding one else the one set before any page else 1. |
---|
572 | page = pages.get(pnum, pages.get(pnum - 1, pages.get(0, { "copies" : 1 }))) |
---|
573 | pagecount += (page["copies"] - 1) |
---|
574 | |
---|
575 | # in PCL3 files, there's one Start Gfx tag per page |
---|
576 | if ispcl3 : |
---|
577 | if endgfx == int(startgfx / 2) : # special case for cdj1600 |
---|
578 | pagecount = endgfx |
---|
579 | elif startgfx : |
---|
580 | pagecount = startgfx |
---|
581 | elif endgfx : |
---|
582 | pagecount = endgfx |
---|
583 | |
---|
584 | if self.debug : |
---|
585 | for pnum in range(pagecount) : |
---|
586 | # if no number of copies defined, take the preceding one else the one set before any page else 1. |
---|
587 | page = pages.get(pnum, pages.get(pnum - 1, pages.get(0, { "copies" : 1, "mediasource" : "Main", "mediasize" : "Default", "mediatype" : "Plain", "orientation" : "Portrait"}))) |
---|
588 | sys.stderr.write("%s*%s*%s*%s*%s\n" % (page["copies"], page["mediatype"], page["mediasize"], page["orientation"], page["mediasource"])) |
---|
589 | |
---|
590 | return pagecount |
---|
591 | |
---|
592 | class PCLXLAnalyzer : |
---|
593 | """A class to parse PCL6 (aka XL) documents.""" |
---|
594 | mediasizes = { |
---|
595 | 0 : "Letter", |
---|
596 | 1 : "Legal", |
---|
597 | 2 : "A4", |
---|
598 | 3 : "Executive", |
---|
599 | 4 : "Ledger", |
---|
600 | 5 : "A3", |
---|
601 | 6 : "COM10Envelope", |
---|
602 | 7 : "MonarchEnvelope", |
---|
603 | 8 : "C5Envelope", |
---|
604 | 9 : "DLEnvelope", |
---|
605 | 10 : "JB4", |
---|
606 | 11 : "JB5", |
---|
607 | 12 : "B5Envelope", |
---|
608 | 14 : "JPostcard", |
---|
609 | 15 : "JDoublePostcard", |
---|
610 | 16 : "A5", |
---|
611 | 17 : "A6", |
---|
612 | 18 : "JB6", |
---|
613 | } |
---|
614 | |
---|
615 | mediasources = { |
---|
616 | 0 : "Default", |
---|
617 | 1 : "Auto", |
---|
618 | 2 : "Manual", |
---|
619 | 3 : "MultiPurpose", |
---|
620 | 4 : "UpperCassette", |
---|
621 | 5 : "LowerCassette", |
---|
622 | 6 : "EnvelopeTray", |
---|
623 | 7 : "ThirdCassette", |
---|
624 | } |
---|
625 | |
---|
626 | orientations = { |
---|
627 | 0 : "Portrait", |
---|
628 | 1 : "Landscape", |
---|
629 | 2 : "ReversePortrait", |
---|
630 | 3 : "ReverseLandscape", |
---|
631 | } |
---|
632 | |
---|
633 | def __init__(self, infile, debug=0) : |
---|
634 | """Initialize PCLXL Analyzer.""" |
---|
635 | self.debug = debug |
---|
636 | self.infile = infile |
---|
637 | self.endianness = None |
---|
638 | found = 0 |
---|
639 | while not found : |
---|
640 | line = self.infile.readline() |
---|
641 | if not line : |
---|
642 | break |
---|
643 | if line[1:12] == " HP-PCL XL;" : |
---|
644 | found = 1 |
---|
645 | endian = ord(line[0]) |
---|
646 | if endian == 0x29 : |
---|
647 | self.littleEndian() |
---|
648 | elif endian == 0x28 : |
---|
649 | self.bigEndian() |
---|
650 | # elif endian == 0x27 : # TODO : This is the ESC code : parse it for PJL statements ! |
---|
651 | # |
---|
652 | else : |
---|
653 | raise PDLAnalyzerError, "Unknown endianness marker 0x%02x at start !" % endian |
---|
654 | if not found : |
---|
655 | raise PDLAnalyzerError, "This file doesn't seem to be PCLXL (aka PCL6)" |
---|
656 | else : |
---|
657 | # Initialize table of tags |
---|
658 | self.tags = [ 0 ] * 256 |
---|
659 | |
---|
660 | # GhostScript's sources tell us that HP printers |
---|
661 | # only accept little endianness, but we can handle both. |
---|
662 | self.tags[0x28] = self.bigEndian # BigEndian |
---|
663 | self.tags[0x29] = self.littleEndian # LittleEndian |
---|
664 | |
---|
665 | self.tags[0x43] = self.beginPage # BeginPage |
---|
666 | self.tags[0x44] = self.endPage # EndPage |
---|
667 | |
---|
668 | self.tags[0xc0] = 1 # ubyte |
---|
669 | self.tags[0xc1] = 2 # uint16 |
---|
670 | self.tags[0xc2] = 4 # uint32 |
---|
671 | self.tags[0xc3] = 2 # sint16 |
---|
672 | self.tags[0xc4] = 4 # sint32 |
---|
673 | self.tags[0xc5] = 4 # real32 |
---|
674 | |
---|
675 | self.tags[0xc8] = self.array_8 # ubyte_array |
---|
676 | self.tags[0xc9] = self.array_16 # uint16_array |
---|
677 | self.tags[0xca] = self.array_32 # uint32_array |
---|
678 | self.tags[0xcb] = self.array_16 # sint16_array |
---|
679 | self.tags[0xcc] = self.array_32 # sint32_array |
---|
680 | self.tags[0xcd] = self.array_32 # real32_array |
---|
681 | |
---|
682 | self.tags[0xd0] = 2 # ubyte_xy |
---|
683 | self.tags[0xd1] = 4 # uint16_xy |
---|
684 | self.tags[0xd2] = 8 # uint32_xy |
---|
685 | self.tags[0xd3] = 4 # sint16_xy |
---|
686 | self.tags[0xd4] = 8 # sint32_xy |
---|
687 | self.tags[0xd5] = 8 # real32_xy |
---|
688 | |
---|
689 | self.tags[0xe0] = 4 # ubyte_box |
---|
690 | self.tags[0xe1] = 8 # uint16_box |
---|
691 | self.tags[0xe2] = 16 # uint32_box |
---|
692 | self.tags[0xe3] = 8 # sint16_box |
---|
693 | self.tags[0xe4] = 16 # sint32_box |
---|
694 | self.tags[0xe5] = 16 # real32_box |
---|
695 | |
---|
696 | self.tags[0xf8] = 1 # attr_ubyte |
---|
697 | self.tags[0xf9] = 2 # attr_uint16 |
---|
698 | |
---|
699 | self.tags[0xfa] = self.embeddedData # dataLength |
---|
700 | self.tags[0xfb] = self.embeddedDataSmall # dataLengthByte |
---|
701 | |
---|
702 | def beginPage(self) : |
---|
703 | """Indicates the beginning of a new page, and extracts media information.""" |
---|
704 | self.pagecount += 1 |
---|
705 | |
---|
706 | # Default values |
---|
707 | mediatypelabel = "Plain" |
---|
708 | mediasourcelabel = "Main" |
---|
709 | mediasizelabel = "Default" |
---|
710 | orientationlabel = "Portrait" |
---|
711 | |
---|
712 | # Now go upstream to decode media type, size, source, and orientation |
---|
713 | # this saves time because we don't need a complete parser ! |
---|
714 | minfile = self.minfile |
---|
715 | pos = self.pos - 2 |
---|
716 | while pos > 0 : # safety check : don't go back to far ! |
---|
717 | val = ord(minfile[pos]) |
---|
718 | if val in (0x44, 0x48, 0x41) : # if previous endPage or openDataSource or beginSession (first page) |
---|
719 | break |
---|
720 | if val == 0x26 : |
---|
721 | mediasource = ord(minfile[pos - 2]) |
---|
722 | mediasourcelabel = self.mediasources.get(mediasource, str(mediasource)) |
---|
723 | pos = pos - 4 |
---|
724 | elif val == 0x25 : |
---|
725 | mediasize = ord(minfile[pos - 2]) |
---|
726 | mediasizelabel = self.mediasizes.get(mediasize, str(mediasize)) |
---|
727 | pos = pos - 4 |
---|
728 | elif val == 0x28 : |
---|
729 | orientation = ord(minfile[pos - 2]) |
---|
730 | orienationlabel = self.orientations.get(orientation, str(orientation)) |
---|
731 | pos = pos - 4 |
---|
732 | elif val == 0x27 : |
---|
733 | savepos = pos |
---|
734 | pos = pos - 1 |
---|
735 | while pos > 0 : # safety check : don't go back to far ! |
---|
736 | val = ord(minfile[pos]) |
---|
737 | pos -= 1 |
---|
738 | if val == 0xc8 : |
---|
739 | break |
---|
740 | mediatypelabel = minfile[pos:savepos] # TODO : INCORRECT, WE HAVE TO STRIP OUT THE UBYTE ARRAY'S LENGTH !!! |
---|
741 | # else : TODO : CUSTOM MEDIA SIZE AND UNIT ! |
---|
742 | else : |
---|
743 | pos = pos - 2 # ignored |
---|
744 | self.pages[self.pagecount] = { "copies" : 1, |
---|
745 | "orientation" : orientationlabel, |
---|
746 | "mediatype" : mediatypelabel, |
---|
747 | "mediasize" : mediasizelabel, |
---|
748 | "mediasource" : mediasourcelabel, |
---|
749 | } |
---|
750 | return 0 |
---|
751 | |
---|
752 | def endPage(self) : |
---|
753 | """Indicates the end of a page.""" |
---|
754 | pos = self.pos |
---|
755 | minfile = self.minfile |
---|
756 | if (ord(minfile[pos-3]) == 0xf8) and (ord(minfile[pos-2]) == 0x31) : |
---|
757 | # The EndPage operator may be preceded by a PageCopies attribute |
---|
758 | # So set number of copies for current page. |
---|
759 | # From what I read in PCLXL documentation, the number |
---|
760 | # of copies is an unsigned 16 bits integer |
---|
761 | self.pages[self.pagecount]["copies"] = unpack(self.endianness + "H", minfile[pos-5:pos-3])[0] |
---|
762 | return 0 |
---|
763 | |
---|
764 | def array_8(self) : |
---|
765 | """Handles byte arrays.""" |
---|
766 | pos = self.pos |
---|
767 | datatype = self.minfile[pos] |
---|
768 | pos += 1 |
---|
769 | length = self.tags[ord(datatype)] |
---|
770 | if callable(length) : |
---|
771 | self.pos = pos |
---|
772 | length = length() |
---|
773 | pos = self.pos |
---|
774 | posl = pos + length |
---|
775 | self.pos = posl |
---|
776 | if length == 1 : |
---|
777 | return unpack("B", self.minfile[pos:posl])[0] |
---|
778 | elif length == 2 : |
---|
779 | return unpack(self.endianness + "H", self.minfile[pos:posl])[0] |
---|
780 | elif length == 4 : |
---|
781 | return unpack(self.endianness + "I", self.minfile[pos:posl])[0] |
---|
782 | else : |
---|
783 | raise PDLAnalyzerError, "Error on array size at %s" % self.pos |
---|
784 | |
---|
785 | def array_16(self) : |
---|
786 | """Handles byte arrays.""" |
---|
787 | pos = self.pos |
---|
788 | datatype = self.minfile[pos] |
---|
789 | pos += 1 |
---|
790 | length = self.tags[ord(datatype)] |
---|
791 | if callable(length) : |
---|
792 | self.pos = pos |
---|
793 | length = length() |
---|
794 | pos = self.pos |
---|
795 | posl = pos + length |
---|
796 | self.pos = posl |
---|
797 | if length == 1 : |
---|
798 | return 2 * unpack("B", self.minfile[pos:posl])[0] |
---|
799 | elif length == 2 : |
---|
800 | return 2 * unpack(self.endianness + "H", self.minfile[pos:posl])[0] |
---|
801 | elif length == 4 : |
---|
802 | return 2 * unpack(self.endianness + "I", self.minfile[pos:posl])[0] |
---|
803 | else : |
---|
804 | raise PDLAnalyzerError, "Error on array size at %s" % self.pos |
---|
805 | |
---|
806 | def array_32(self) : |
---|
807 | """Handles byte arrays.""" |
---|
808 | pos = self.pos |
---|
809 | datatype = self.minfile[pos] |
---|
810 | pos += 1 |
---|
811 | length = self.tags[ord(datatype)] |
---|
812 | if callable(length) : |
---|
813 | self.pos = pos |
---|
814 | length = length() |
---|
815 | pos = self.pos |
---|
816 | posl = pos + length |
---|
817 | self.pos = posl |
---|
818 | if length == 1 : |
---|
819 | return 4 * unpack("B", self.minfile[pos:posl])[0] |
---|
820 | elif length == 2 : |
---|
821 | return 4 * unpack(self.endianness + "H", self.minfile[pos:posl])[0] |
---|
822 | elif length == 4 : |
---|
823 | return 4 * unpack(self.endianness + "I", self.minfile[pos:posl])[0] |
---|
824 | else : |
---|
825 | raise PDLAnalyzerError, "Error on array size at %s" % self.pos |
---|
826 | |
---|
827 | def embeddedDataSmall(self) : |
---|
828 | """Handle small amounts of data.""" |
---|
829 | pos = self.pos |
---|
830 | length = ord(self.minfile[pos]) |
---|
831 | self.pos = pos + 1 |
---|
832 | return length |
---|
833 | |
---|
834 | def embeddedData(self) : |
---|
835 | """Handle normal amounts of data.""" |
---|
836 | pos = self.pos |
---|
837 | pos4 = pos + 4 |
---|
838 | self.pos = pos4 |
---|
839 | return unpack(self.endianness + "I", self.minfile[pos:pos4])[0] |
---|
840 | |
---|
841 | def littleEndian(self) : |
---|
842 | """Toggles to little endianness.""" |
---|
843 | self.endianness = "<" # little endian |
---|
844 | return 0 |
---|
845 | |
---|
846 | def bigEndian(self) : |
---|
847 | """Toggles to big endianness.""" |
---|
848 | self.endianness = ">" # big endian |
---|
849 | return 0 |
---|
850 | |
---|
851 | def getJobSize(self) : |
---|
852 | """Counts pages in a PCLXL (PCL6) document. |
---|
853 | |
---|
854 | Algorithm by Jerome Alet. |
---|
855 | |
---|
856 | The documentation used for this was : |
---|
857 | |
---|
858 | HP PCL XL Feature Reference |
---|
859 | Protocol Class 2.0 |
---|
860 | http://www.hpdevelopersolutions.com/downloads/64/358/xl_ref20r22.pdf |
---|
861 | """ |
---|
862 | infileno = self.infile.fileno() |
---|
863 | self.pages = {} |
---|
864 | self.minfile = minfile = mmap.mmap(infileno, os.fstat(infileno)[6], prot=mmap.PROT_READ, flags=mmap.MAP_SHARED) |
---|
865 | tags = self.tags |
---|
866 | self.pagecount = 0 |
---|
867 | self.pos = pos = self.infile.tell() |
---|
868 | try : |
---|
869 | while 1 : |
---|
870 | char = minfile[pos] |
---|
871 | pos += 1 |
---|
872 | length = tags[ord(char)] |
---|
873 | if not length : |
---|
874 | continue |
---|
875 | if callable(length) : |
---|
876 | self.pos = pos |
---|
877 | length = length() |
---|
878 | pos = self.pos |
---|
879 | pos += length |
---|
880 | except IndexError : # EOF ? |
---|
881 | self.minfile.close() # reached EOF |
---|
882 | |
---|
883 | # now handle number of copies for each page (may differ). |
---|
884 | for pnum in range(1, self.pagecount + 1) : |
---|
885 | # if no number of copies defined, take 1, as explained |
---|
886 | # in PCLXL documentation. |
---|
887 | # NB : is number of copies is 0, the page won't be output |
---|
888 | # but the formula below is still correct : we want |
---|
889 | # to decrease the total number of pages in this case. |
---|
890 | page = self.pages.get(pnum, 1) |
---|
891 | copies = page["copies"] |
---|
892 | self.pagecount += (copies - 1) |
---|
893 | if self.debug : |
---|
894 | sys.stderr.write("%s*%s*%s*%s*%s\n" % (copies, page["mediatype"], page["mediasize"], page["orientation"], page["mediasource"])) |
---|
895 | |
---|
896 | return self.pagecount |
---|
897 | |
---|
898 | class PDLAnalyzer : |
---|
899 | """Generic PDL Analyzer class.""" |
---|
900 | def __init__(self, filename, debug=0) : |
---|
901 | """Initializes the PDL analyzer. |
---|
902 | |
---|
903 | filename is the name of the file or '-' for stdin. |
---|
904 | filename can also be a file-like object which |
---|
905 | supports read() and seek(). |
---|
906 | """ |
---|
907 | self.debug = debug |
---|
908 | self.filename = filename |
---|
909 | try : |
---|
910 | import psyco |
---|
911 | except ImportError : |
---|
912 | pass # Psyco is not installed |
---|
913 | else : |
---|
914 | # Psyco is installed, tell it to compile |
---|
915 | # the CPU intensive methods : PCL and PCLXL |
---|
916 | # parsing will greatly benefit from this, |
---|
917 | # for PostScript and PDF the difference is |
---|
918 | # barely noticeable since they are already |
---|
919 | # almost optimal, and much more speedy anyway. |
---|
920 | psyco.bind(PostScriptAnalyzer.getJobSize) |
---|
921 | psyco.bind(PDFAnalyzer.getJobSize) |
---|
922 | psyco.bind(ESCP2Analyzer.getJobSize) |
---|
923 | psyco.bind(PCLAnalyzer.getJobSize) |
---|
924 | psyco.bind(PCLXLAnalyzer.getJobSize) |
---|
925 | |
---|
926 | def getJobSize(self) : |
---|
927 | """Returns the job's size.""" |
---|
928 | self.openFile() |
---|
929 | try : |
---|
930 | pdlhandler = self.detectPDLHandler() |
---|
931 | except PDLAnalyzerError, msg : |
---|
932 | self.closeFile() |
---|
933 | raise PDLAnalyzerError, "ERROR : Unknown file format for %s (%s)" % (self.filename, msg) |
---|
934 | else : |
---|
935 | try : |
---|
936 | size = pdlhandler(self.infile, self.debug).getJobSize() |
---|
937 | finally : |
---|
938 | self.closeFile() |
---|
939 | return size |
---|
940 | |
---|
941 | def openFile(self) : |
---|
942 | """Opens the job's data stream for reading.""" |
---|
943 | self.mustclose = 0 # by default we don't want to close the file when finished |
---|
944 | if hasattr(self.filename, "read") and hasattr(self.filename, "seek") : |
---|
945 | # filename is in fact a file-like object |
---|
946 | infile = self.filename |
---|
947 | elif self.filename == "-" : |
---|
948 | # we must read from stdin |
---|
949 | infile = sys.stdin |
---|
950 | else : |
---|
951 | # normal file |
---|
952 | self.infile = open(self.filename, "rb") |
---|
953 | self.mustclose = 1 |
---|
954 | return |
---|
955 | |
---|
956 | # Use a temporary file, always seekable contrary to standard input. |
---|
957 | self.infile = tempfile.TemporaryFile(mode="w+b") |
---|
958 | while 1 : |
---|
959 | data = infile.read(MEGABYTE) |
---|
960 | if not data : |
---|
961 | break |
---|
962 | self.infile.write(data) |
---|
963 | self.infile.flush() |
---|
964 | self.infile.seek(0) |
---|
965 | |
---|
966 | def closeFile(self) : |
---|
967 | """Closes the job's data stream if we can close it.""" |
---|
968 | if self.mustclose : |
---|
969 | self.infile.close() |
---|
970 | else : |
---|
971 | # if we don't have to close the file, then |
---|
972 | # ensure the file pointer is reset to the |
---|
973 | # start of the file in case the process wants |
---|
974 | # to read the file again. |
---|
975 | try : |
---|
976 | self.infile.seek(0) |
---|
977 | except : |
---|
978 | pass # probably stdin, which is not seekable |
---|
979 | |
---|
980 | def isPostScript(self, sdata, edata) : |
---|
981 | """Returns 1 if data is PostScript, else 0.""" |
---|
982 | if sdata.startswith("%!") or \ |
---|
983 | sdata.startswith("\004%!") or \ |
---|
984 | sdata.startswith("\033%-12345X%!PS") or \ |
---|
985 | ((sdata[:128].find("\033%-12345X") != -1) and \ |
---|
986 | ((sdata.find("LANGUAGE=POSTSCRIPT") != -1) or \ |
---|
987 | (sdata.find("LANGUAGE = POSTSCRIPT") != -1) or \ |
---|
988 | (sdata.find("LANGUAGE = Postscript") != -1))) or \ |
---|
989 | (sdata.find("%!PS-Adobe") != -1) : |
---|
990 | if self.debug : |
---|
991 | sys.stderr.write("%s is a PostScript file\n" % str(self.filename)) |
---|
992 | return 1 |
---|
993 | else : |
---|
994 | return 0 |
---|
995 | |
---|
996 | def isPDF(self, sdata, edata) : |
---|
997 | """Returns 1 if data is PDF, else 0.""" |
---|
998 | if sdata.startswith("%PDF-") or \ |
---|
999 | sdata.startswith("\033%-12345X%PDF-") or \ |
---|
1000 | ((sdata[:128].find("\033%-12345X") != -1) and (sdata.upper().find("LANGUAGE=PDF") != -1)) or \ |
---|
1001 | (sdata.find("%PDF-") != -1) : |
---|
1002 | if self.debug : |
---|
1003 | sys.stderr.write("%s is a PDF file\n" % str(self.filename)) |
---|
1004 | return 1 |
---|
1005 | else : |
---|
1006 | return 0 |
---|
1007 | |
---|
1008 | def isPCL(self, sdata, edata) : |
---|
1009 | """Returns 1 if data is PCL, else 0.""" |
---|
1010 | if sdata.startswith("\033E\033") or \ |
---|
1011 | (sdata.startswith("\033*rbC") and (not edata[-3:] == "\f\033@")) or \ |
---|
1012 | sdata.startswith("\033%8\033") or \ |
---|
1013 | (sdata.find("\033%-12345X") != -1) : |
---|
1014 | if self.debug : |
---|
1015 | sys.stderr.write("%s is a PCL3/4/5 file\n" % str(self.filename)) |
---|
1016 | return 1 |
---|
1017 | else : |
---|
1018 | return 0 |
---|
1019 | |
---|
1020 | def isPCLXL(self, sdata, edata) : |
---|
1021 | """Returns 1 if data is PCLXL aka PCL6, else 0.""" |
---|
1022 | if ((sdata[:128].find("\033%-12345X") != -1) and \ |
---|
1023 | (sdata.find(" HP-PCL XL;") != -1) and \ |
---|
1024 | ((sdata.find("LANGUAGE=PCLXL") != -1) or \ |
---|
1025 | (sdata.find("LANGUAGE = PCLXL") != -1))) : |
---|
1026 | if self.debug : |
---|
1027 | sys.stderr.write("%s is a PCLXL (aka PCL6) file\n" % str(self.filename)) |
---|
1028 | return 1 |
---|
1029 | else : |
---|
1030 | return 0 |
---|
1031 | |
---|
1032 | def isESCP2(self, sdata, edata) : |
---|
1033 | """Returns 1 if data is ESC/P2, else 0.""" |
---|
1034 | if sdata.startswith("\033@") or \ |
---|
1035 | sdata.startswith("\033*") or \ |
---|
1036 | sdata.startswith("\n\033@") or \ |
---|
1037 | sdata.startswith("\0\0\0\033\1@EJL") : # ESC/P Raster ??? Seen on Stylus Photo 1284 |
---|
1038 | if self.debug : |
---|
1039 | sys.stderr.write("%s is an ESC/P2 file\n" % str(self.filename)) |
---|
1040 | return 1 |
---|
1041 | else : |
---|
1042 | return 0 |
---|
1043 | |
---|
1044 | def detectPDLHandler(self) : |
---|
1045 | """Tries to autodetect the document format. |
---|
1046 | |
---|
1047 | Returns the correct PDL handler class or None if format is unknown |
---|
1048 | """ |
---|
1049 | # Try to detect file type by reading first block of datas |
---|
1050 | self.infile.seek(0) |
---|
1051 | firstblock = self.infile.read(4 * KILOBYTE) |
---|
1052 | try : |
---|
1053 | self.infile.seek(-LASTBLOCKSIZE, 2) |
---|
1054 | except IOError : |
---|
1055 | lastblock = "" |
---|
1056 | else : |
---|
1057 | lastblock = self.infile.read(LASTBLOCKSIZE) |
---|
1058 | self.infile.seek(0) |
---|
1059 | if self.isPostScript(firstblock, lastblock) : |
---|
1060 | return PostScriptAnalyzer |
---|
1061 | elif self.isPCLXL(firstblock, lastblock) : |
---|
1062 | return PCLXLAnalyzer |
---|
1063 | elif self.isPDF(firstblock, lastblock) : |
---|
1064 | return PDFAnalyzer |
---|
1065 | elif self.isPCL(firstblock, lastblock) : |
---|
1066 | return PCLAnalyzer |
---|
1067 | elif self.isESCP2(firstblock, lastblock) : |
---|
1068 | return ESCP2Analyzer |
---|
1069 | else : |
---|
1070 | raise PDLAnalyzerError, "Analysis of first data block failed." |
---|
1071 | |
---|
1072 | def main() : |
---|
1073 | """Entry point for PDL Analyzer.""" |
---|
1074 | if (len(sys.argv) < 2) or ((not sys.stdin.isatty()) and ("-" not in sys.argv[1:])) : |
---|
1075 | sys.argv.append("-") |
---|
1076 | |
---|
1077 | totalsize = 0 |
---|
1078 | debug = 0 |
---|
1079 | minindex = 1 |
---|
1080 | if sys.argv[1] == "--debug" : |
---|
1081 | minindex = 2 |
---|
1082 | debug = 1 |
---|
1083 | for arg in sys.argv[minindex:] : |
---|
1084 | try : |
---|
1085 | parser = PDLAnalyzer(arg, debug) |
---|
1086 | totalsize += parser.getJobSize() |
---|
1087 | except PDLAnalyzerError, msg : |
---|
1088 | sys.stderr.write("ERROR: %s\n" % msg) |
---|
1089 | sys.stderr.flush() |
---|
1090 | print "%s" % totalsize |
---|
1091 | |
---|
1092 | if __name__ == "__main__" : |
---|
1093 | main() |
---|