root / pykota / trunk / bin / pkpgcounter @ 1447

#! /usr/bin/env python
# -*- coding: ISO-8859-15 -*-

# pkpgcounter, a smart software page counter
#
# PyKota - Print Quotas for CUPS and LPRng
#
# (c) 2003-2004 Jerome Alet <alet@librelogiciel.com>
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
# 
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307, USA.
#
# $Id$
#
# $Log$
# Revision 1.2  2004/05/04 03:14:26  jalet
# fixed copy&paste problem in pkpgcounter
#
# Revision 1.1  2004/04/08 17:07:42  jalet
# pkpgcounter added
#
#

import sys
import tempfile

def ispostscript(data) :    
    """Returns 1 if data is PostScript, else 0."""
    if data.startswith("%!") or \
       data.startswith("\004%!") or \
       data.startswith("\033%-12345X%!PS") or \
       ((data[:128].find("\033%-12345X") != -1) and \
         ((data.find("LANGUAGE=POSTSCRIPT") != -1) or \
          (data.find("LANGUAGE = POSTSCRIPT") != -1) or \
          (data.find("LANGUAGE = Postscript") != -1))) :
        return 1
    else :    
        return 0
    
def postscript(infile) :
    """Count pages in a PostScript document."""
    pagecount = 0
    pagenum = None
    while 1 :
        line = infile.readline()
        if not line :
            break
        if line.startswith("%%Page: ") :
            pagecount += 1
    return pagecount
    
def ispcl(data) :    
    """Returns 1 if data is PCL, else 0."""
    if data.startswith("\033E\033") or \
       ((data[:128].find("\033%-12345X") != -1) and \
         ((data.find("LANGUAGE=PCL") != -1) or \
          (data.find("LANGUAGE = PCL") != -1) or \
          (data.find("LANGUAGE = Pcl") != -1))) :
        return 1
    else :    
        return 0
    
def pcl(infile) :    
    """Count pages in a PostScript document."""
    #
    # Algorithm from pclcount
    # (c) 2003, by Eduardo Gielamo Oliveira & Rodolfo Broco Manin 
    # published under the terms of the GNU General Public Licence v2.
    # 
    # Backported from C to Python by Jerome Alet
    # 
    tagsends = { "*b" : "W", "(s" : "W", ")s" : "W", "&p" : "X", "&l" : "X" } 
    copies = 1
    pagecount = 0
    tag = None
    while 1 :
        char = infile.read(1)   # TODO : speed this up if possible
        if not char :
            break
        if char == "\014" :    
            pagecount += 1
        elif char == "\033" :    
            #
            #     <ESC>*b###W -> Start of a binary block
            #     <ESC>(s###W -> Start of a characters description block
            #     <ESC>)s###W -> Start of a fonts description block
            #     <ESC>&p###X -> Start of a non printable characters block
            #     <ESC>&l###X -> Number of copies
            #
            tag = infile.read(2)
            try :
                tagend = tagsends[tag]
            except KeyError :    
                pass    # Unsupported PCL tag
            else :    
                # Now read the numeric argument
                size = 0
                while 1 :
                    char = infile.read(1)
                    if not char.isdigit() :
                        break
                    size = (size * 10) + int(char)    
                if char == tagend :    
                    if tag == "&l" :
                        copies = size
                    else :    
                        # doing a read will prevent the seek 
                        # for unseekable streams. 
                        # we just ignore the block anyway.
                        infile.read(size) 
    return copies * pagecount        

def smartpagecounter(filename) :
    """Autodetects file format and returns number of pages."""
    if filename == "-" :
        # we must read from stdin
        # but since stdin is not seekable, we have to use a temporary
        # file instead.
        infile = tempfile.TemporaryFile()
        while 1 :
            data = sys.stdin.read(256 * 1024) 
            if not data :
                break
            infile.write(data)
        infile.flush()    
        infile.seek(0)
    else :    
        # normal file
        infile = open(filename, "rb")
        
    # Try to detect file type by reading first block of datas    
    firstblock = infile.read(1024)
    infile.seek(0)
    if ispostscript(firstblock) :
        size = postscript(infile)
    elif ispcl(firstblock) :    
        size = pcl(infile)
    else :    
        sys.stderr.write("ERROR : Unknown file format for %s\n" % filename)
        size = 0
    infile.close()    
    return size
    
if __name__ == "__main__" :    
    if len(sys.argv) < 2 :
        sys.argv.append("-")
        
    totalsize = 0    
    for arg in sys.argv[1:] :
        totalsize += smartpagecounter(arg)
    print "%s" % totalsize