[3410] | 1 | # -*- coding: utf-8 -*- |
---|
[191] | 2 | # |
---|
| 3 | # pkpgcounter : a generic Page Description Language parser |
---|
| 4 | # |
---|
[3474] | 5 | # (c) 2003-2009 Jerome Alet <alet@librelogiciel.com> |
---|
[463] | 6 | # This program is free software: you can redistribute it and/or modify |
---|
[191] | 7 | # it under the terms of the GNU General Public License as published by |
---|
[463] | 8 | # the Free Software Foundation, either version 3 of the License, or |
---|
[191] | 9 | # (at your option) any later version. |
---|
[3436] | 10 | # |
---|
[191] | 11 | # This program is distributed in the hope that it will be useful, |
---|
| 12 | # but WITHOUT ANY WARRANTY; without even the implied warranty of |
---|
| 13 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
---|
| 14 | # GNU General Public License for more details. |
---|
[3436] | 15 | # |
---|
[191] | 16 | # You should have received a copy of the GNU General Public License |
---|
[463] | 17 | # along with this program. If not, see <http://www.gnu.org/licenses/>. |
---|
[191] | 18 | # |
---|
| 19 | # $Id$ |
---|
| 20 | # |
---|
[193] | 21 | |
---|
[357] | 22 | """This modules implements a page counter for PostScript documents.""" |
---|
| 23 | |
---|
[193] | 24 | import sys |
---|
[283] | 25 | import os |
---|
[193] | 26 | |
---|
[235] | 27 | import pdlparser |
---|
[283] | 28 | import inkcoverage |
---|
[193] | 29 | |
---|
[220] | 30 | class Parser(pdlparser.PDLParser) : |
---|
[193] | 31 | """A parser for PostScript documents.""" |
---|
[492] | 32 | totiffcommands = [ 'gs -sDEVICE=tiff24nc -dPARANOIDSAFER -dNOPAUSE -dBATCH -dQUIET -r"%(dpi)i" -sOutputFile="%(outfname)s" "%(infname)s"' ] |
---|
[527] | 33 | required = [ "gs" ] |
---|
[491] | 34 | openmode = "rU" |
---|
[555] | 35 | format = "PostScript" |
---|
[3436] | 36 | def isValid(self) : |
---|
[387] | 37 | """Returns True if data is PostScript, else False.""" |
---|
[522] | 38 | if self.firstblock.startswith("%!") or \ |
---|
| 39 | self.firstblock.startswith("\004%!") or \ |
---|
| 40 | self.firstblock.startswith("\033%-12345X%!PS") or \ |
---|
| 41 | ((self.firstblock[:128].find("\033%-12345X") != -1) and \ |
---|
| 42 | ((self.firstblock.find("LANGUAGE=POSTSCRIPT") != -1) or \ |
---|
| 43 | (self.firstblock.find("LANGUAGE = POSTSCRIPT") != -1) or \ |
---|
| 44 | (self.firstblock.find("LANGUAGE = Postscript") != -1))) or \ |
---|
| 45 | (self.firstblock.find("%!PS-Adobe") != -1) : |
---|
[387] | 46 | return True |
---|
[3436] | 47 | else : |
---|
[387] | 48 | return False |
---|
[3436] | 49 | |
---|
[193] | 50 | def throughGhostScript(self) : |
---|
| 51 | """Get the count through GhostScript, useful for non-DSC compliant PS files.""" |
---|
[252] | 52 | self.logdebug("Internal parser sucks, using GhostScript instead...") |
---|
[527] | 53 | if self.isMissing(self.required) : |
---|
| 54 | raise pdlparser.PDLParserError, "The gs interpreter is nowhere to be found in your PATH (%s)" % os.environ.get("PATH", "") |
---|
[522] | 55 | infname = self.filename |
---|
[521] | 56 | command = 'gs -sDEVICE=bbox -dPARANOIDSAFER -dNOPAUSE -dBATCH -dQUIET "%(infname)s" 2>&1 | grep -c "%%HiResBoundingBox:" 2>/dev/null' |
---|
[491] | 57 | pagecount = 0 |
---|
[521] | 58 | fromchild = os.popen(command % locals(), "r") |
---|
[193] | 59 | try : |
---|
[491] | 60 | try : |
---|
[521] | 61 | pagecount = int(fromchild.readline().strip()) |
---|
[491] | 62 | except (IOError, OSError, AttributeError, ValueError), msg : |
---|
| 63 | raise pdlparser.PDLParserError, "Problem during analysis of Binary PostScript document : %s" % msg |
---|
[3436] | 64 | finally : |
---|
[521] | 65 | if fromchild.close() is not None : |
---|
| 66 | raise pdlparser.PDLParserError, "Problem during analysis of Binary PostScript document" |
---|
[3436] | 67 | self.logdebug("GhostScript said : %s pages" % pagecount) |
---|
[193] | 68 | return pagecount * self.copies |
---|
[3436] | 69 | |
---|
| 70 | def setcopies(self, pagenum, txtvalue) : |
---|
[561] | 71 | """Tries to extract a number of copies from a textual value and set the instance attributes accordingly.""" |
---|
| 72 | try : |
---|
| 73 | number = int(txtvalue) |
---|
[3436] | 74 | except (ValueError, TypeError) : |
---|
[561] | 75 | pass |
---|
[3436] | 76 | else : |
---|
[561] | 77 | if number > self.pages[pagenum]["copies"] : |
---|
| 78 | self.pages[pagenum]["copies"] = number |
---|
[3436] | 79 | |
---|
[193] | 80 | def natively(self) : |
---|
| 81 | """Count pages in a DSC compliant PostScript document.""" |
---|
| 82 | pagecount = 0 |
---|
[273] | 83 | self.pages = { 0 : { "copies" : 1 } } |
---|
[263] | 84 | oldpagenum = None |
---|
[252] | 85 | previousline = "" |
---|
[521] | 86 | notrust = False |
---|
| 87 | prescribe = False # Kyocera's Prescribe commands |
---|
| 88 | acrobatmarker = False |
---|
[444] | 89 | pagescomment = None |
---|
[491] | 90 | for line in self.infile : |
---|
| 91 | line = line.strip() |
---|
[561] | 92 | parts = line.split() |
---|
| 93 | nbparts = len(parts) |
---|
[562] | 94 | if nbparts >= 1 : |
---|
| 95 | part0 = parts[0] |
---|
[3436] | 96 | else : |
---|
[562] | 97 | part0 = "" |
---|
[561] | 98 | if part0 == r"%ADOPrintSettings:" : |
---|
[521] | 99 | acrobatmarker = True |
---|
[3436] | 100 | elif part0 == "!R!" : |
---|
[521] | 101 | prescribe = True |
---|
[561] | 102 | elif part0 == r"%%Pages:" : |
---|
[444] | 103 | try : |
---|
[561] | 104 | pagescomment = max(pagescomment or 0, int(parts[1])) |
---|
[444] | 105 | except ValueError : |
---|
| 106 | pass # strange, to say the least |
---|
[561] | 107 | elif (part0 == r"%%BeginNonPPDFeature:") \ |
---|
| 108 | and (nbparts > 2) \ |
---|
| 109 | and (parts[1] == "NumCopies") : |
---|
| 110 | self.setcopies(pagecount, parts[2]) |
---|
| 111 | elif (part0 == r"%%Requirements:") \ |
---|
| 112 | and (nbparts > 1) \ |
---|
| 113 | and (parts[1] == "numcopies(") : |
---|
[263] | 114 | try : |
---|
[561] | 115 | self.setcopies(pagecount, line.split('(')[1].split(')')[0]) |
---|
| 116 | except IndexError : |
---|
| 117 | pass |
---|
| 118 | elif part0 == "/#copies" : |
---|
| 119 | if nbparts > 1 : |
---|
| 120 | self.setcopies(pagecount, parts[1]) |
---|
[3436] | 121 | elif part0 == r"%RBINumCopies:" : |
---|
[561] | 122 | if nbparts > 1 : |
---|
| 123 | self.setcopies(pagecount, parts[1]) |
---|
| 124 | elif (parts[:4] == ["1", "dict", "dup", "/NumCopies"]) \ |
---|
| 125 | and (nbparts > 4) : |
---|
| 126 | # handle # of copies set by mozilla/kprinter |
---|
| 127 | self.setcopies(pagecount, parts[4]) |
---|
| 128 | elif (parts[:6] == ["{", "pop", "1", "dict", "dup", "/NumCopies"]) \ |
---|
| 129 | and (nbparts > 6) : |
---|
| 130 | # handle # of copies set by firefox/kprinter/cups (alternate syntax) |
---|
| 131 | self.setcopies(pagecount, parts[6]) |
---|
| 132 | elif (part0 == r"%%Page:") or (part0 == r"(%%[Page:") : |
---|
| 133 | proceed = True |
---|
| 134 | try : |
---|
[437] | 135 | # treats both "%%Page: x x" and "%%Page: (x-y) z" (probably N-up mode) |
---|
| 136 | newpagenum = int(line.split(']')[0].split()[-1]) |
---|
[3436] | 137 | except : |
---|
[561] | 138 | notinteger = True # It seems that sometimes it's not an integer but an EPS file name |
---|
[3436] | 139 | else : |
---|
[561] | 140 | notinteger = False |
---|
[263] | 141 | if newpagenum == oldpagenum : |
---|
[561] | 142 | proceed = False |
---|
[263] | 143 | else : |
---|
| 144 | oldpagenum = newpagenum |
---|
[3436] | 145 | if proceed and not notinteger : |
---|
[263] | 146 | pagecount += 1 |
---|
[273] | 147 | self.pages[pagecount] = { "copies" : self.pages[pagecount-1]["copies"] } |
---|
[561] | 148 | elif (not prescribe) \ |
---|
| 149 | and (parts[:3] == [r"%%BeginResource:", "procset", "pdf"]) \ |
---|
| 150 | and not acrobatmarker : |
---|
| 151 | notrust = True # Let this stuff be managed by GhostScript, but we still extract number of copies |
---|
[248] | 152 | elif line.startswith("/languagelevel where{pop languagelevel}{1}ifelse 2 ge{1 dict dup/NumCopies") : |
---|
[561] | 153 | self.setcopies(pagecount, previousline[2:]) |
---|
| 154 | elif (nbparts > 1) and (parts[1] == "@copies") : |
---|
| 155 | self.setcopies(pagecount, part0) |
---|
[248] | 156 | previousline = line |
---|
[3436] | 157 | |
---|
| 158 | # extract max number of copies to please the ghostscript parser, just |
---|
[248] | 159 | # in case we will use it later |
---|
[273] | 160 | self.copies = max([ v["copies"] for (k, v) in self.pages.items() ]) |
---|
[3436] | 161 | |
---|
[248] | 162 | # now apply the number of copies to each page |
---|
[3436] | 163 | if not pagecount and pagescomment : |
---|
[448] | 164 | pagecount = pagescomment |
---|
[248] | 165 | for pnum in range(1, pagecount + 1) : |
---|
[448] | 166 | page = self.pages.get(pnum, self.pages.get(1, self.pages.get(0, { "copies" : 1 }))) |
---|
[248] | 167 | copies = page["copies"] |
---|
| 168 | pagecount += (copies - 1) |
---|
[252] | 169 | self.logdebug("%s * page #%s" % (copies, pnum)) |
---|
[3436] | 170 | |
---|
[273] | 171 | self.logdebug("Internal parser said : %s pages" % pagecount) |
---|
[384] | 172 | return (pagecount, notrust) |
---|
[3436] | 173 | |
---|
| 174 | def getJobSize(self) : |
---|
[193] | 175 | """Count pages in PostScript document.""" |
---|
[202] | 176 | self.copies = 1 |
---|
[384] | 177 | (nbpages, notrust) = self.natively() |
---|
| 178 | newnbpages = nbpages |
---|
[444] | 179 | if notrust or not nbpages : |
---|
[384] | 180 | try : |
---|
| 181 | newnbpages = self.throughGhostScript() |
---|
| 182 | except pdlparser.PDLParserError, msg : |
---|
| 183 | self.logdebug(msg) |
---|
[3436] | 184 | return max(nbpages, newnbpages) |
---|