root / pkpgcounter / trunk / pkpgpdls / plain.py @ 494

Revision 494, 3.0 kB (checked in by jerome, 16 years ago)

Improved plain text detection.

  • Property svn:eol-style set to native
  • Property svn:keywords set to Author Date Id Revision
RevLine 
[412]1#! /usr/bin/env python
2# -*- coding: ISO-8859-15 -*-
3#
4# pkpgcounter : a generic Page Description Language parser
5#
[443]6# (c) 2003, 2004, 2005, 2006, 2007 Jerome Alet <alet@librelogiciel.com>
[463]7# This program is free software: you can redistribute it and/or modify
[412]8# it under the terms of the GNU General Public License as published by
[463]9# the Free Software Foundation, either version 3 of the License, or
[412]10# (at your option) any later version.
[463]11#
[412]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
[463]18# along with this program.  If not, see <http://www.gnu.org/licenses/>.
[412]19#
20# $Id$
21#
22
23"""This modules implements a page counter for plain text documents."""
24
25import pdlparser
26import version
27
28class Parser(pdlparser.PDLParser) :
29    """A parser for plain text documents."""
[492]30    totiffcommands = [ 'enscript --quiet --portrait --no-header --columns 1 --output - "%(infname)s" | gs -sDEVICE=tiff24nc -dPARANOIDSAFER -dNOPAUSE -dBATCH -dQUIET -r"%(dpi)i" -sOutputFile="%(outfname)s" -',
31                       'a2ps --borders 0 --quiet --portrait --no-header --columns 1 --output - "%(infname)s" | gs -sDEVICE=tiff24nc -dPARANOIDSAFER -dNOPAUSE -dBATCH -dQUIET -r"%(dpi)i" -sOutputFile="%(outfname)s" -',
[428]32                     ] 
[491]33    openmode = "rU"                 
[412]34    def isValid(self) :   
[414]35        """Returns True if data is plain text, else False.
36       
[494]37           It's hard to detect a plain text file, so we just try to
38           extract lines from the first block (sufficiently large).
39           If it's impossible to find one we consider it's not plain text.
[414]40        """   
[494]41        lines = firstblock.split("\r\n")
42        if len(lines) == 1 :
43            lines = lines[0].split("\r")
44            if len(lines) == 1 :
45                lines = lines[0].split("\n")
46        if len(lines) > 1 :
[414]47            self.logdebug("DEBUG: Input file seems to be in the plain text format.")
48            return True
49        else :   
50            return False
[412]51           
52    def getJobSize(self) :
53        """Counts pages in a plain text document."""
54        pagesize = 66   # TODO : Does this vary wrt the default page size ?
55                        # TODO : /etc/papersize and /etc/paper.config
56        pagecount = 0
57        linecount = 0
58        for line in self.infile :
[491]59            if line.endswith("\n") :
[414]60                linecount += 1   
[422]61                if (linecount > pagesize) :
[414]62                    pagecount += 1
63                    linecount = 0
[422]64                else :   
65                    cnt = line.count("\f")
66                    if cnt :
67                        pagecount += cnt
68                        linecount = 0
[414]69            else :       
70                raise pdlparser.PDLParserError, "Unsupported file format. Please send the file to %s" % version.__authoremail__
71        return pagecount + 1    # NB : empty files are catched in isValid()
Note: See TracBrowser for help on using the browser.