Context Navigation

pcl345.py @ 357

Revision 357, 25.5 kB (checked in by jerome, 18 years ago)
Added missing docstrings, thanks to pylint.
Property svn:eol-style set to `native` Property svn:keywords set to `Auth Date Id Rev`

Rev	Line
[193]	1	#! /usr/bin/env python
	2	# -- coding: ISO-8859-15 --
[191]	3	#
	4	# pkpgcounter : a generic Page Description Language parser
	5	#
[303]	6	# (c) 2003, 2004, 2005, 2006 Jerome Alet <alet@librelogiciel.com>
[191]	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
[211]	19	# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
[191]	20	#
	21	# $Id$
	22	#
[193]	23
[357]	24	"""This modules implements a page counter for PCL3/4/5 documents."""
	25
[193]	26	import sys
[202]	27	import os
[193]	28	import mmap
[305]	29	from struct import unpack
[193]	30
[235]	31	import pdlparser
[253]	32	import pjl
[193]	33
[220]	34	class Parser(pdlparser.PDLParser) :
[193]	35	"""A parser for PCL3, PCL4, PCL5 documents."""
	36	mediasizes = { # ESC&l####A
	37	0 : "Default",
	38	1 : "Executive",
	39	2 : "Letter",
	40	3 : "Legal",
	41	6 : "Ledger",
	42	25 : "A5",
	43	26 : "A4",
	44	27 : "A3",
	45	45 : "JB5",
	46	46 : "JB4",
	47	71 : "HagakiPostcard",
	48	72 : "OufukuHagakiPostcard",
	49	80 : "MonarchEnvelope",
	50	81 : "COM10Envelope",
	51	90 : "DLEnvelope",
	52	91 : "C5Envelope",
	53	100 : "B5Envelope",
	54	101 : "Custom",
	55	}
	56
	57	mediasources = { # ESC&l####H
	58	0 : "Default",
	59	1 : "Main",
	60	2 : "Manual",
	61	3 : "ManualEnvelope",
	62	4 : "Alternate",
	63	5 : "OptionalLarge",
	64	6 : "EnvelopeFeeder",
	65	7 : "Auto",
	66	8 : "Tray1",
	67	}
	68
	69	orientations = { # ESC&l####O
	70	0 : "Portrait",
	71	1 : "Landscape",
	72	2 : "ReversePortrait",
	73	3 : "ReverseLandscape",
	74	}
	75
	76	mediatypes = { # ESC&l####M
	77	0 : "Plain",
	78	1 : "Bond",
	79	2 : "Special",
	80	3 : "Glossy",
	81	4 : "Transparent",
	82	}
	83
[220]	84	def isValid(self) :
	85	"""Returns 1 if data is PCL, else 0."""
	86	if self.firstblock.startswith("\033E\033") or \
	87	(self.firstblock.startswith("\033*rbC") and (not self.lastblock[-3:] == "\f\033@")) or \
	88	self.firstblock.startswith("\033%8\033") or \
[305]	89	(self.firstblock.find("\033%-12345X") != -1) or \
[343]	90	(self.firstblock.find("@PJL ENTER LANGUAGE=PCL\012\015\033") != -1) or \
[305]	91	(self.firstblock.startswith(chr(0xcd)+chr(0xca)) and self.firstblock.find("\033E\033")) :
[252]	92	self.logdebug("DEBUG: Input file is in the PCL3/4/5 format.")
[220]	93	return 1
	94	else :
	95	return 0
	96
[193]	97	def setPageDict(self, pages, number, attribute, value) :
	98	"""Initializes a page dictionnary."""
[294]	99	dic = pages.setdefault(number, { "copies" : 1, "mediasource" : "Main", "mediasize" : "Default", "mediatype" : "Plain", "orientation" : "Portrait", "escaped" : "", "duplex": 0})
[252]	100	dic[attribute] = value
[193]	101
	102	def getJobSize(self) :
	103	"""Count pages in a PCL5 document.
	104
	105	Should also work for PCL3 and PCL4 documents.
	106
	107	Algorithm from pclcount
	108	(c) 2003, by Eduardo Gielamo Oliveira & Rodolfo Broco Manin
	109	published under the terms of the GNU General Public Licence v2.
	110
	111	Backported from C to Python by Jerome Alet, then enhanced
	112	with more PCL tags detected. I think all the necessary PCL tags
	113	are recognized to correctly handle PCL5 files wrt their number
	114	of pages. The documentation used for this was :
	115
	116	HP PCL/PJL Reference Set
	117	PCL5 Printer Language Technical Quick Reference Guide
	118	http://h20000.www2.hp.com/bc/docs/support/SupportManual/bpl13205/bpl13205.pdf
	119	"""
	120	infileno = self.infile.fileno()
	121	minfile = mmap.mmap(infileno, os.fstat(infileno)[6], prot=mmap.PROT_READ, flags=mmap.MAP_SHARED)
	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	"(s" : "W",
	131	")s" : "W",
	132	"&p" : "X",
	133	# "&l" : "XHAOM", # treated specially
	134	"&a" : "G", # TODO : 0 means next side, 1 front side, 2 back side
	135	"*g" : "W",
	136	"*r" : "sbABC",
	137	"*t" : "R",
	138	# "*b" : "VW", # treated specially because it occurs very often
	139	}
[305]	140	irmarker = chr(0xcd) + chr(0xca) # Marker for Canon ImageRunner printers
	141	irmarker2 = chr(0x10) + chr(0x02)
	142	wasirmarker = 0
	143	hasirmarker = (minfile[:2] == (irmarker))
[193]	144	pagecount = resets = ejects = backsides = startgfx = endgfx = 0
	145	starb = ampl = ispcl3 = escstart = 0
	146	mediasourcecount = mediasizecount = orientationcount = mediatypecount = 0
	147	tag = None
[252]	148	endmark = chr(0x1b) + chr(0x0c) + chr(0x00)
	149	asciilimit = chr(0x80)
[193]	150	pages = {}
	151	pos = 0
	152	try :
[307]	153	try :
	154	while 1 :
	155	if hasirmarker and (minfile[pos:pos+2] == irmarker) :
	156	codop = minfile[pos+2:pos+4]
	157	# self.logdebug("Marker at 0x%08x (%s)" % (pos, wasirmarker))
	158	length = unpack(">H", minfile[pos+8:pos+10])[0]
	159	pos += 20
	160	if codop != irmarker2 :
	161	pos += length
	162	wasirmarker = 1
	163	else :
	164	wasirmarker = 0
	165	char = minfile[pos] ; pos += 1
	166	if char == "\014" :
	167	pagecount += 1
	168	elif char == "\033" :
	169	starb = ampl = 0
	170	if minfile[pos : pos+8] == r"%-12345X" :
	171	endpos = pos + 9
	172	quotes = 0
	173	while (minfile[endpos] not in endmark) and \
	174	((minfile[endpos] < asciilimit) or (quotes % 2)) :
	175	if minfile[endpos] == '"' :
	176	quotes += 1
	177	endpos += 1
	178	self.setPageDict(pages, pagecount, "escaped", minfile[pos : endpos])
	179	pos += (endpos - pos)
	180	else :
	181	#
	182	# <ESC>*b###y#m###v###w... -> PCL3 raster graphics
	183	# <ESC>*b###W -> Start of a raster data row/block
	184	# <ESC>*b###V -> Start of a raster data plane
	185	# <ESC>*c###W -> Start of a user defined pattern
	186	# <ESC>*i###W -> Start of a viewing illuminant block
	187	# <ESC>*l###W -> Start of a color lookup table
	188	# <ESC>*m###W -> Start of a download dither matrix block
	189	# <ESC>*v###W -> Start of a configure image data block
	190	# <ESC>*r1A -> Start Gfx
	191	# <ESC>(s###W -> Start of a characters description block
	192	# <ESC>)s###W -> Start of a fonts description block
	193	# <ESC>(f###W -> Start of a symbol set block
	194	# <ESC>&b###W -> Start of configuration data block
	195	# <ESC>&l###X -> Number of copies for current page
	196	# <ESC>&n###W -> Starts an alphanumeric string ID block
	197	# <ESC>&p###X -> Start of a non printable characters block
	198	# <ESC>&a2G -> Back side when duplex mode as generated by rastertohp
	199	# <ESC>*g###W -> Needed for planes in PCL3 output
	200	# <ESC>&l###H (or only 0 ?) -> Eject if NumPlanes > 1, as generated by rastertohp. Also defines mediasource
	201	# <ESC>&l###A -> mediasize
	202	# <ESC>&l###O -> orientation
	203	# <ESC>&l###M -> mediatype
	204	# <ESC>*t###R -> gfx resolution
	205	#
	206	tagstart = minfile[pos] ; pos += 1
	207	if tagstart in "E9=YZ" : # one byte PCL tag
	208	if tagstart == "E" :
	209	resets += 1
	210	continue # skip to next tag
	211	tag = tagstart + minfile[pos] ; pos += 1
	212	if tag == "*b" :
	213	starb = 1
	214	tagend = "VW"
	215	elif tag == "&l" :
	216	ampl = 1
	217	tagend = "XHAOM"
	218	else :
	219	try :
	220	tagend = tagsends[tag]
	221	except KeyError :
	222	continue # Unsupported PCL tag
	223	# Now read the numeric argument
	224	size = 0
	225	while 1 :
	226	char = minfile[pos] ; pos += 1
	227	if not char.isdigit() :
	228	break
	229	size = (size * 10) + int(char)
	230	if char in tagend :
	231	if tag == "&l" :
	232	if char == "X" :
	233	self.setPageDict(pages, pagecount, "copies", size)
	234	elif char == "H" :
	235	self.setPageDict(pages, pagecount, "mediasource", self.mediasources.get(size, str(size)))
	236	mediasourcecount += 1
	237	ejects += 1
	238	elif char == "A" :
	239	self.setPageDict(pages, pagecount, "mediasize", self.mediasizes.get(size, str(size)))
	240	mediasizecount += 1
	241	elif char == "O" :
	242	self.setPageDict(pages, pagecount, "orientation", self.orientations.get(size, str(size)))
	243	orientationcount += 1
	244	elif char == "M" :
	245	self.setPageDict(pages, pagecount, "mediatype", self.mediatypes.get(size, str(size)))
	246	mediatypecount += 1
	247	elif tag == "*r" :
	248	# Special tests for PCL3
	249	if (char == "s") and size :
	250	while 1 :
	251	char = minfile[pos] ; pos += 1
	252	if char == "A" :
	253	break
	254	elif (char == "b") and (minfile[pos] == "C") and not size :
	255	ispcl3 = 1 # Certainely a PCL3 file
	256	startgfx += (char == "A") and (minfile[pos - 2] in ("0", "1", "2", "3")) # Start Gfx
	257	endgfx += (not size) and (char in ("C", "B")) # End Gfx
	258	elif tag == "*t" :
	259	escstart += 1
	260	elif (tag == "&a") and (size == 2) :
	261	# We are on the backside, so mark current page as duplex
	262	self.setPageDict(pages, pagecount, "duplex", 1)
	263	backsides += 1 # Back side in duplex mode
	264	else :
	265	# we just ignore the block.
	266	if tag == "&n" :
	267	# we have to take care of the operation id byte
	268	# which is before the string itself
	269	size += 1
	270	pos += size
	271	else :
	272	if starb :
	273	# special handling of PCL3 in which
	274	# *b introduces combined ESCape sequences
	275	size = 0
	276	while 1 :
	277	char = minfile[pos] ; pos += 1
	278	if not char.isdigit() :
	279	break
	280	size = (size * 10) + int(char)
	281	if char in ("w", "v") :
	282	ispcl3 = 1 # certainely a PCL3 document
	283	pos += size - 1
	284	elif char in ("y", "m") :
	285	ispcl3 = 1 # certainely a PCL3 document
	286	pos -= 1 # fix position : we were ahead
	287	elif ampl :
	288	# special handling of PCL3 in which
	289	# &l introduces combined ESCape sequences
	290	size = 0
	291	while 1 :
	292	char = minfile[pos] ; pos += 1
	293	if not char.isdigit() :
	294	break
	295	size = (size * 10) + int(char)
	296	if char in ("a", "o", "h", "m") :
	297	ispcl3 = 1 # certainely a PCL3 document
	298	pos -= 1 # fix position : we were ahead
	299	if char == "h" :
[305]	300	self.setPageDict(pages, pagecount, "mediasource", self.mediasources.get(size, str(size)))
	301	mediasourcecount += 1
[307]	302	elif char == "a" :
[305]	303	self.setPageDict(pages, pagecount, "mediasize", self.mediasizes.get(size, str(size)))
	304	mediasizecount += 1
[307]	305	elif char == "o" :
[305]	306	self.setPageDict(pages, pagecount, "orientation", self.orientations.get(size, str(size)))
	307	orientationcount += 1
[307]	308	elif char == "m" :
[305]	309	self.setPageDict(pages, pagecount, "mediatype", self.mediatypes.get(size, str(size)))
	310	mediatypecount += 1
[307]	311	except IndexError : # EOF ?
	312	pass
	313	finally :
	314	minfile.close()
[193]	315
	316	# if pagecount is still 0, we will use the number
	317	# of resets instead of the number of form feed characters.
	318	# but the number of resets is always at least 2 with a valid
	319	# pcl file : one at the very start and one at the very end
	320	# of the job's data. So we substract 2 from the number of
	321	# resets. And since on our test data we needed to substract
	322	# 1 more, we finally substract 3, and will test several
	323	# PCL files with this. If resets < 2, then the file is
	324	# probably not a valid PCL file, so we use 0
	325
	326	if self.debug :
	327	sys.stderr.write("pagecount : %s\n" % pagecount)
	328	sys.stderr.write("resets : %s\n" % resets)
	329	sys.stderr.write("ejects : %s\n" % ejects)
	330	sys.stderr.write("backsides : %s\n" % backsides)
	331	sys.stderr.write("startgfx : %s\n" % startgfx)
	332	sys.stderr.write("endgfx : %s\n" % endgfx)
	333	sys.stderr.write("mediasourcecount : %s\n" % mediasourcecount)
	334	sys.stderr.write("mediasizecount : %s\n" % mediasizecount)
	335	sys.stderr.write("orientationcount : %s\n" % orientationcount)
	336	sys.stderr.write("mediatypecount : %s\n" % mediatypecount)
	337	sys.stderr.write("escstart : %s\n" % escstart)
[305]	338	sys.stderr.write("hasirmarker : %s\n" % hasirmarker)
[193]	339
[305]	340	if hasirmarker :
	341	self.logdebug("Rule #20 (probably a Canon ImageRunner)")
	342	pagecount += 1
	343	elif (orientationcount == (pagecount - 1)) and (resets == 1) :
[285]	344	if resets == ejects == startgfx == mediasourcecount == escstart == 1 :
	345	self.logdebug("Rule #19")
	346	else :
	347	self.logdebug("Rule #1")
	348	pagecount -= 1
[265]	349	elif pagecount and (pagecount == orientationcount) :
[267]	350	self.logdebug("Rule #2")
[262]	351	elif resets == ejects == mediasourcecount == mediasizecount == escstart == 1 :
[267]	352	#if ((startgfx and endgfx) and (startgfx != endgfx)) or (startgfx == endgfx == 0) :
	353	if (startgfx and endgfx) or (startgfx == endgfx == 0) :
	354	self.logdebug("Rule #3")
[262]	355	pagecount = orientationcount
[265]	356	elif (endgfx and not startgfx) and (pagecount > orientationcount) :
[267]	357	self.logdebug("Rule #4")
[265]	358	pagecount = orientationcount
[262]	359	else :
[267]	360	self.logdebug("Rule #5")
[262]	361	pagecount += 1
	362	elif (ejects == mediasourcecount == orientationcount) and (startgfx == endgfx) :
[267]	363	if (resets == 2) and (orientationcount == (pagecount - 1)) and (orientationcount > 1) :
	364	self.logdebug("Rule #6")
	365	pagecount = orientationcount
[249]	366	elif pagecount == mediasourcecount == escstart :
[267]	367	self.logdebug("Rule #7")
[255]	368	elif resets == startgfx == endgfx == mediasizecount == orientationcount == escstart == 1 :
[267]	369	self.logdebug("Rule #8")
[255]	370	elif resets == startgfx == endgfx == (pagecount - 1) :
[267]	371	self.logdebug("Rule #9")
[193]	372	elif (not startgfx) and (not endgfx) :
[267]	373	self.logdebug("Rule #10")
[256]	374	elif (resets == 2) and (startgfx == endgfx) and (mediasourcecount == 1) :
[267]	375	if orientationcount == (pagecount - 1) :
	376	self.logdebug("Rule #11")
	377	pagecount = orientationcount
[285]	378	elif not pagecount :
	379	self.logdebug("Rule #17")
	380	pagecount = ejects
[256]	381	elif (resets == 1) and (startgfx == endgfx) and (mediasourcecount == 0) :
[265]	382	if (startgfx > 1) and (startgfx != (pagecount - 1)) :
[267]	383	self.logdebug("Rule #12")
[265]	384	pagecount -= 1
[285]	385	else :
	386	self.logdebug("Rule #18")
[193]	387	elif startgfx == endgfx :
[267]	388	self.logdebug("Rule #13")
[193]	389	pagecount = startgfx
	390	elif startgfx == (endgfx - 1) :
[267]	391	self.logdebug("Rule #14")
[193]	392	pagecount = startgfx
[210]	393	elif (startgfx == 1) and not endgfx :
[267]	394	self.logdebug("Rule #15")
[210]	395	pass
[193]	396	else :
[267]	397	self.logdebug("Rule #16")
[193]	398	pagecount = abs(startgfx - endgfx)
	399
[253]	400	defaultpjlcopies = 1
	401	defaultduplexmode = "Simplex"
	402	defaultpapersize = ""
	403	oldpjlcopies = -1
	404	oldduplexmode = ""
	405	oldpapersize = ""
[252]	406	for pnum in range(pagecount) :
	407	# if no number of copies defined, take the preceding one else the one set before any page else 1.
[294]	408	page = pages.get(pnum, pages.get(pnum - 1, pages.get(0, { "copies" : 1, "mediasource" : "Main", "mediasize" : "Default", "mediatype" : "Plain", "orientation" : "Portrait", "escaped" : "", "duplex": 0})))
[252]	409	pjlstuff = page["escaped"]
[253]	410	if pjlstuff :
	411	pjlparser = pjl.PJLParser(pjlstuff)
	412	nbdefaultcopies = int(pjlparser.default_variables.get("COPIES", -1))
	413	nbcopies = int(pjlparser.environment_variables.get("COPIES", -1))
	414	nbdefaultqty = int(pjlparser.default_variables.get("QTY", -1))
	415	nbqty = int(pjlparser.environment_variables.get("QTY", -1))
	416	if nbdefaultcopies > -1 :
	417	defaultpjlcopies = nbdefaultcopies
	418	if nbdefaultqty > -1 :
	419	defaultpjlcopies = nbdefaultqty
	420	if nbcopies > -1 :
	421	pjlcopies = nbcopies
	422	elif nbqty > -1 :
	423	pjlcopies = nbqty
[252]	424	else :
[253]	425	if oldpjlcopies == -1 :
	426	pjlcopies = defaultpjlcopies
	427	else :
	428	pjlcopies = oldpjlcopies
[294]	429	if page["duplex"] :
	430	duplexmode = "Duplex"
	431	else :
	432	defaultdm = pjlparser.default_variables.get("DUPLEX", "")
	433	if defaultdm :
	434	if defaultdm.upper() == "ON" :
	435	defaultduplexmode = "Duplex"
	436	else :
	437	defaultduplexmode = "Simplex"
	438	envdm = pjlparser.environment_variables.get("DUPLEX", "")
	439	if envdm :
	440	if envdm.upper() == "ON" :
	441	duplexmode = "Duplex"
	442	else :
	443	duplexmode = "Simplex"
	444	else :
	445	duplexmode = oldduplexmode or defaultduplexmode
[253]	446	defaultps = pjlparser.default_variables.get("PAPER", "")
	447	if defaultps :
	448	defaultpapersize = defaultps
	449	envps = pjlparser.environment_variables.get("PAPER", "")
	450	if envps :
	451	papersize = envps
	452	else :
	453	if not oldpapersize :
	454	papersize = defaultpapersize
	455	else :
	456	papersize = oldpapersize
	457	else :
	458	if oldpjlcopies == -1 :
	459	pjlcopies = defaultpjlcopies
	460	else :
	461	pjlcopies = oldpjlcopies
[294]	462
	463	duplexmode = (page["duplex"] and "Duplex") or oldduplexmode or defaultduplexmode
[253]	464	if not oldpapersize :
	465	papersize = defaultpapersize
	466	else :
	467	papersize = oldpapersize
	468	papersize = oldpapersize or page["mediasize"]
	469	if page["mediasize"] != "Default" :
	470	papersize = page["mediasize"]
	471	if not duplexmode :
	472	duplexmode = oldduplexmode or defaultduplexmode
	473	oldpjlcopies = pjlcopies
	474	oldduplexmode = duplexmode
	475	oldpapersize = papersize
[252]	476	copies = pjlcopies * page["copies"]
	477	pagecount += (copies - 1)
[253]	478	self.logdebug("%s%s%s%s%s%sBW" % (copies, \
[252]	479	page["mediatype"], \
[253]	480	papersize, \
[252]	481	page["orientation"], \
[253]	482	page["mediasource"], \
	483	duplexmode))
[193]	484
	485	return pagecount
	486
	487	def test() :
	488	"""Test function."""
[196]	489	if (len(sys.argv) < 2) or ((not sys.stdin.isatty()) and ("-" not in sys.argv[1:])) :
	490	sys.argv.append("-")
	491	totalsize = 0
	492	for arg in sys.argv[1:] :
	493	if arg == "-" :
	494	infile = sys.stdin
	495	mustclose = 0
	496	else :
	497	infile = open(arg, "rb")
	498	mustclose = 1
	499	try :
[220]	500	parser = Parser(infile, debug=1)
[196]	501	totalsize += parser.getJobSize()
[200]	502	except pdlparser.PDLParserError, msg :
[196]	503	sys.stderr.write("ERROR: %s\n" % msg)
	504	sys.stderr.flush()
	505	if mustclose :
	506	infile.close()
	507	print "%s" % totalsize
[193]	508
	509	if __name__ == "__main__" :
	510	test()

Note: See TracBrowser for help on using the browser.

Context Navigation

root / pkpgcounter / trunk / pkpgpdls / pcl345.py @ 357

Download in other formats: