| 1 | #! /usr/bin/env python |
|---|
| 2 | # -*- coding: ISO-8859-15 -*- |
|---|
| 3 | # |
|---|
| 4 | # pkpgcounter : a generic Page Description Language parser |
|---|
| 5 | # |
|---|
| 6 | # (c) 2003, 2004, 2005, 2006, 2007 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 3 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, see <http://www.gnu.org/licenses/>. |
|---|
| 19 | # |
|---|
| 20 | # $Id$ |
|---|
| 21 | # |
|---|
| 22 | |
|---|
| 23 | """This modules implements a page counter for PostScript documents.""" |
|---|
| 24 | |
|---|
| 25 | import sys |
|---|
| 26 | import os |
|---|
| 27 | import tempfile |
|---|
| 28 | import popen2 |
|---|
| 29 | |
|---|
| 30 | import pdlparser |
|---|
| 31 | import inkcoverage |
|---|
| 32 | |
|---|
| 33 | class Parser(pdlparser.PDLParser) : |
|---|
| 34 | """A parser for PostScript documents.""" |
|---|
| 35 | totiffcommands = [ 'gs -sDEVICE=tiff24nc -dPARANOIDSAFER -dNOPAUSE -dBATCH -dQUIET -r%(dpi)i -sOutputFile="%(fname)s" -' ] |
|---|
| 36 | openmode = "rU" |
|---|
| 37 | def isValid(self) : |
|---|
| 38 | """Returns True if data is PostScript, else False.""" |
|---|
| 39 | if self.firstblock.startswith("%!") or \ |
|---|
| 40 | self.firstblock.startswith("\004%!") or \ |
|---|
| 41 | self.firstblock.startswith("\033%-12345X%!PS") or \ |
|---|
| 42 | ((self.firstblock[:128].find("\033%-12345X") != -1) and \ |
|---|
| 43 | ((self.firstblock.find("LANGUAGE=POSTSCRIPT") != -1) or \ |
|---|
| 44 | (self.firstblock.find("LANGUAGE = POSTSCRIPT") != -1) or \ |
|---|
| 45 | (self.firstblock.find("LANGUAGE = Postscript") != -1))) or \ |
|---|
| 46 | (self.firstblock.find("%!PS-Adobe") != -1) : |
|---|
| 47 | self.logdebug("DEBUG: Input file is in the PostScript format.") |
|---|
| 48 | return True |
|---|
| 49 | else : |
|---|
| 50 | return False |
|---|
| 51 | |
|---|
| 52 | def throughGhostScript(self) : |
|---|
| 53 | """Get the count through GhostScript, useful for non-DSC compliant PS files.""" |
|---|
| 54 | self.logdebug("Internal parser sucks, using GhostScript instead...") |
|---|
| 55 | command = 'gs -sDEVICE=bbox -dPARANOIDSAFER -dNOPAUSE -dBATCH -dQUIET - 2>&1 | grep -c "%%HiResBoundingBox:" 2>/dev/null' |
|---|
| 56 | pagecount = 0 |
|---|
| 57 | # we need to reopen the input file in binary mode again, just in case |
|---|
| 58 | # otherwise we might break the original file's contents. |
|---|
| 59 | infile = open(self.filename, "rb") |
|---|
| 60 | try : |
|---|
| 61 | child = popen2.Popen4(command) |
|---|
| 62 | try : |
|---|
| 63 | data = infile.read(pdlparser.MEGABYTE) |
|---|
| 64 | while data : |
|---|
| 65 | child.tochild.write(data) |
|---|
| 66 | data = infile.read(pdlparser.MEGABYTE) |
|---|
| 67 | child.tochild.flush() |
|---|
| 68 | child.tochild.close() |
|---|
| 69 | except (IOError, OSError), msg : |
|---|
| 70 | raise pdlparser.PDLParserError, "Problem during analysis of Binary PostScript document : %s" % msg |
|---|
| 71 | |
|---|
| 72 | pagecount = 0 |
|---|
| 73 | try : |
|---|
| 74 | pagecount = int(child.fromchild.readline().strip()) |
|---|
| 75 | except (IOError, OSError, AttributeError, ValueError), msg : |
|---|
| 76 | raise pdlparser.PDLParserError, "Problem during analysis of Binary PostScript document : %s" % msg |
|---|
| 77 | child.fromchild.close() |
|---|
| 78 | |
|---|
| 79 | try : |
|---|
| 80 | child.wait() |
|---|
| 81 | except OSError, msg : |
|---|
| 82 | raise pdlparser.PDLParserError, "Problem during analysis of Binary PostScript document : %s" % msg |
|---|
| 83 | finally : |
|---|
| 84 | infile.close() |
|---|
| 85 | self.logdebug("GhostScript said : %s pages" % pagecount) |
|---|
| 86 | return pagecount * self.copies |
|---|
| 87 | |
|---|
| 88 | def natively(self) : |
|---|
| 89 | """Count pages in a DSC compliant PostScript document.""" |
|---|
| 90 | pagecount = 0 |
|---|
| 91 | self.pages = { 0 : { "copies" : 1 } } |
|---|
| 92 | oldpagenum = None |
|---|
| 93 | previousline = "" |
|---|
| 94 | notrust = 0 |
|---|
| 95 | prescribe = 0 # Kyocera's Prescribe commands |
|---|
| 96 | acrobatmarker = 0 |
|---|
| 97 | pagescomment = None |
|---|
| 98 | for line in self.infile : |
|---|
| 99 | line = line.strip() |
|---|
| 100 | if (not prescribe) and line.startswith(r"%%BeginResource: procset pdf") \ |
|---|
| 101 | and not acrobatmarker : |
|---|
| 102 | notrust = 1 # Let this stuff be managed by GhostScript, but we still extract number of copies |
|---|
| 103 | elif line.startswith(r"%ADOPrintSettings: L") : |
|---|
| 104 | acrobatmarker = 1 |
|---|
| 105 | elif line.startswith("!R!") : |
|---|
| 106 | prescribe = 1 |
|---|
| 107 | elif line.startswith(r"%%Pages: ") : |
|---|
| 108 | try : |
|---|
| 109 | pagescomment = max(pagescomment or 0, int(line.split()[1])) |
|---|
| 110 | except ValueError : |
|---|
| 111 | pass # strange, to say the least |
|---|
| 112 | elif line.startswith(r"%%Page: ") or line.startswith(r"(%%[Page: ") : |
|---|
| 113 | proceed = 1 |
|---|
| 114 | try : |
|---|
| 115 | # treats both "%%Page: x x" and "%%Page: (x-y) z" (probably N-up mode) |
|---|
| 116 | newpagenum = int(line.split(']')[0].split()[-1]) |
|---|
| 117 | except : |
|---|
| 118 | notinteger = 1 # It seems that sometimes it's not an integer but an EPS file name |
|---|
| 119 | else : |
|---|
| 120 | notinteger = 0 |
|---|
| 121 | if newpagenum == oldpagenum : |
|---|
| 122 | proceed = 0 |
|---|
| 123 | else : |
|---|
| 124 | oldpagenum = newpagenum |
|---|
| 125 | if proceed and not notinteger : |
|---|
| 126 | pagecount += 1 |
|---|
| 127 | self.pages[pagecount] = { "copies" : self.pages[pagecount-1]["copies"] } |
|---|
| 128 | elif line.startswith(r"%%Requirements: numcopies(") : |
|---|
| 129 | try : |
|---|
| 130 | number = int(line.split('(')[1].split(')')[0]) |
|---|
| 131 | except : |
|---|
| 132 | pass |
|---|
| 133 | else : |
|---|
| 134 | if number > self.pages[pagecount]["copies"] : |
|---|
| 135 | self.pages[pagecount]["copies"] = number |
|---|
| 136 | elif line.startswith(r"%%BeginNonPPDFeature: NumCopies ") : |
|---|
| 137 | # handle # of copies set by some Windows printer driver |
|---|
| 138 | try : |
|---|
| 139 | number = int(line.split()[2]) |
|---|
| 140 | except : |
|---|
| 141 | pass |
|---|
| 142 | else : |
|---|
| 143 | if number > self.pages[pagecount]["copies"] : |
|---|
| 144 | self.pages[pagecount]["copies"] = number |
|---|
| 145 | elif line.startswith("1 dict dup /NumCopies ") : |
|---|
| 146 | # handle # of copies set by mozilla/kprinter |
|---|
| 147 | try : |
|---|
| 148 | number = int(line.split()[4]) |
|---|
| 149 | except : |
|---|
| 150 | pass |
|---|
| 151 | else : |
|---|
| 152 | if number > self.pages[pagecount]["copies"] : |
|---|
| 153 | self.pages[pagecount]["copies"] = number |
|---|
| 154 | elif line.startswith("{ pop 1 dict dup /NumCopies ") : |
|---|
| 155 | # handle # of copies set by firefox/kprinter/cups (alternate syntax) |
|---|
| 156 | try : |
|---|
| 157 | number = int(line.split()[6]) |
|---|
| 158 | except : |
|---|
| 159 | pass |
|---|
| 160 | else : |
|---|
| 161 | if number > self.pages[pagecount]["copies"] : |
|---|
| 162 | self.pages[pagecount]["copies"] = number |
|---|
| 163 | elif line.startswith("/languagelevel where{pop languagelevel}{1}ifelse 2 ge{1 dict dup/NumCopies") : |
|---|
| 164 | try : |
|---|
| 165 | number = int(previousline[2:]) |
|---|
| 166 | except : |
|---|
| 167 | pass |
|---|
| 168 | else : |
|---|
| 169 | if number > self.pages[pagecount]["copies"] : |
|---|
| 170 | self.pages[pagecount]["copies"] = number |
|---|
| 171 | elif line.startswith("/#copies ") : |
|---|
| 172 | try : |
|---|
| 173 | number = int(line.split()[1]) |
|---|
| 174 | except : |
|---|
| 175 | pass |
|---|
| 176 | else : |
|---|
| 177 | if number > self.pages[pagecount]["copies"] : |
|---|
| 178 | self.pages[pagecount]["copies"] = number |
|---|
| 179 | elif line.startswith(r"%RBINumCopies: ") : |
|---|
| 180 | try : |
|---|
| 181 | number = int(line.split()[1]) |
|---|
| 182 | except : |
|---|
| 183 | pass |
|---|
| 184 | else : |
|---|
| 185 | if number > self.pages[pagecount]["copies"] : |
|---|
| 186 | self.pages[pagecount]["copies"] = number |
|---|
| 187 | previousline = line |
|---|
| 188 | |
|---|
| 189 | # extract max number of copies to please the ghostscript parser, just |
|---|
| 190 | # in case we will use it later |
|---|
| 191 | self.copies = max([ v["copies"] for (k, v) in self.pages.items() ]) |
|---|
| 192 | |
|---|
| 193 | # now apply the number of copies to each page |
|---|
| 194 | if not pagecount and pagescomment : |
|---|
| 195 | pagecount = pagescomment |
|---|
| 196 | for pnum in range(1, pagecount + 1) : |
|---|
| 197 | page = self.pages.get(pnum, self.pages.get(1, self.pages.get(0, { "copies" : 1 }))) |
|---|
| 198 | copies = page["copies"] |
|---|
| 199 | pagecount += (copies - 1) |
|---|
| 200 | self.logdebug("%s * page #%s" % (copies, pnum)) |
|---|
| 201 | |
|---|
| 202 | self.logdebug("Internal parser said : %s pages" % pagecount) |
|---|
| 203 | return (pagecount, notrust) |
|---|
| 204 | |
|---|
| 205 | def getJobSize(self) : |
|---|
| 206 | """Count pages in PostScript document.""" |
|---|
| 207 | self.copies = 1 |
|---|
| 208 | (nbpages, notrust) = self.natively() |
|---|
| 209 | newnbpages = nbpages |
|---|
| 210 | if notrust or not nbpages : |
|---|
| 211 | try : |
|---|
| 212 | newnbpages = self.throughGhostScript() |
|---|
| 213 | except pdlparser.PDLParserError, msg : |
|---|
| 214 | self.logdebug(msg) |
|---|
| 215 | return max(nbpages, newnbpages) |
|---|
