root / pykota / trunk / bin / pkpgcounter @ 1461

#! /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 1.7  2004/05/07 23:08:21  jalet
# Skeleton for PCLXL aka PCL6
# Added the "potential" fix for rastertoprinter's output
#
# Revision 1.6  2004/05/06 21:19:27  jalet
# Doesn't exit anymore on the first nul byte
#
# Revision 1.5  2004/05/06 12:37:29  jalet
# pkpgcounter : comments
# pkprinters : when --add is used, existing printers are now skipped.
#
# Revision 1.4  2004/05/04 12:21:55  jalet
# Now uses mmap in PCL mode
#
# Revision 1.3  2004/05/04 04:39:26  jalet
# Better PCL support
#
# 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 os
import mmap
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 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 ispclxl(data) :    
    """Returns 1 if data is PCLXL aka PCL6, else 0."""
    if ((data[:128].find("\033%-12345X") != -1) and \
         (data.find(" HP-PCL XL;") != -1) and \
         ((data.find("LANGUAGE=PCLXL") != -1) or \
          (data.find("LANGUAGE = PCLXL") != -1))) :
        return 1
    else :    
        return 0
    
def postscript(infile) :
    """Count pages in a DSC compliant PostScript document."""
    pagecount = 0
    pagenum = None
    while 1 :
        line = infile.readline()
        if not line :
            break
        if line.startswith("%%Page: ") :
            pagecount += 1
    return pagecount
    
def pcl(infile) :    
    """Count pages in a PCL5 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, then enhanced
    # with more PCL tags detected. I think all the necessary PCL tags
    # are recognized to correctly handle PCL5 files wrt their number
    # of pages. The documentation used for this was :
    #
    # HP PCL/PJL Reference Set
    # PCL5 Printer Language Technical Quick Reference Guide
    # http://h20000.www2.hp.com/bc/docs/support/SupportManual/bpl13205/bpl13205.pdf 
    #
    infileno = infile.fileno()
    infile = mmap.mmap(infileno, os.fstat(infileno).st_size, access=mmap.ACCESS_READ)
    tagsends = { "&n" : "W", 
                 "&b" : "W", 
                 "*i" : "W", 
                 "*l" : "W", 
                 "*m" : "W", 
                 "*v" : "W", 
                 "*c" : "W", 
                 "(f" : "W", 
                 "*b" : "VW",
                 "(s" : "W", 
                 ")s" : "W", 
                 "&p" : "X", 
                 "&l" : "X" } 
    copies = 1
    pagecount = resets = 0
    tag = None
    position = 0
    while 1 :
        try :
            char = infile[position]
        except IndexError :     # EOF    
            break
        position += 1
        if char == "\014" :    
            pagecount += 1
        elif char == "\033" :    
            #
            #     <ESC>*b###W -> Start of a raster data row/block
            #     <ESC>*b###V -> Start of a raster data plane
            #     <ESC>*c###W -> Start of a user defined pattern
            #     <ESC>*i###W -> Start of a viewing illuminant block
            #     <ESC>*l###W -> Start of a color lookup table
            #     <ESC>*m###W -> Start of a download dither matrix block
            #     <ESC>*v###W -> Start of a configure image data block
            #     <ESC>(s###W -> Start of a characters description block
            #     <ESC>)s###W -> Start of a fonts description block
            #     <ESC>(f###W -> Start of a symbol set block
            #     <ESC>&b###W -> Start of configuration data block
            #     <ESC>&l###X -> Number of copies
            #     <ESC>&n###W -> Starts an alphanumeric string ID block
            #     <ESC>&p###X -> Start of a non printable characters block
            #
            tagstart = infile[position]
            position += 1
            if tagstart in "E9=YZ" : # one byte PCL tag
                if tagstart == "E" :
                    resets += 1
                continue             # skip to next tag
            tag = tagstart + infile[position]
            position += 1
            try :
                tagend = tagsends[tag]
            except KeyError :    
                pass    # Unsupported PCL tag
            else :    
                # Now read the numeric argument
                size = 0
                while 1 :
                    char = infile[position]
                    position += 1
                    if not char.isdigit() :
                        break
                    size = (size * 10) + int(char)    
                if char in tagend :    
                    if tag == "&l" :
                        copies = size
                    else :    
                        # doing a read will prevent the seek 
                        # for unseekable streams. 
                        # we just ignore the block anyway.
                        if tag == "&n" : 
                            # we have to take care of the operation id byte
                            # which is before the string itself
                            size += 1
                        position += size    
                        
    # if pagecount is still 0, we will return the number
    # of resets instead of the number of form feed characters.
    # but the number of resets is always at least 2 with a valid
    # pcl file : one at the very start and one at the very end
    # of the job's data. So we substract 2 from the number of
    # resets. And since on our test data we needed to substract
    # 1 more, we finally substract 3, and will test several
    # PCL files with this. If resets < 2, then the file is
    # probably not a valid PCL file, so we return 0
    if not pagecount :
        return copies * (resets - 3) * (resets > 2)
    else :
        return copies * pagecount

def pclxl(infile) :     
    """Count pages in a PCL6 aka PCLXL document."""
    raise TypeError, "Sorry but PCL6, aka PCLXL, is not supported yet.\n"
    
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 ispclxl(firstblock) :    
        size = pclxl(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