omf-import

#! /usr/bin/python
# 
# This file is part of the Lampadas Documentation System.
# 
# Copyright (c) 2000, 2001, 2002 David Merrill <david@lupercalia.net>.
#
# 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
#
from Globals import *
import sys
import os
import fnmatch
from xml.dom.minidom import parse

IGNORE_NODES = ('omf',
                'resource',
                'subject',
                'format',
                'person',
                '#text')

class Creator:

    def __init__(self):
        self.firstname = ''
        self.lastname = ''
        self.email = ''

class OMF:

    def __init__(self):
        self.title = ''
        self.description = ''
        self.type = ''
        self.filename = ''
        self.lang = ''
        self.categories = []
        self.creators = []
        
    def read_dom(self, dom):
        for node in dom.childNodes:
            self.handle_node(node)

    def handle_node(self, node):
        node.nodeName = string.lower(node.nodeName)
        if node.nodeName in IGNORE_NODES:
            pass
        elif node.nodeName=='title':
            self.title = self.get_node_text(node)
        elif node.nodeName=='description':
            self.description = self.get_node_text(node)
        elif node.nodeName=='type':
            self.type = self.get_node_text(node)
        elif node.nodeName=='category':
            self.categories = self.categories + [self.get_node_text(node)]
        elif node.nodeName=='identifier':
            self.filename = self.get_attribute_text(node, 'url')
        elif node.nodeName=='language':
            self.lang = self.get_attribute_text(node, 'code')
        elif node.nodeName=='creator':
            creator = Creator()
            self.creators = self.creators + [creator]
        elif node.nodeName=='firstname' and node.parentNode.nodeName=='person' and node.parentNode.parentNode.nodeName=='creator':
            self.creators[-1].firstname = self.get_node_text(node)
        elif node.nodeName=='lastname' and node.parentNode.nodeName=='person' and node.parentNode.parentNode.nodeName=='creator':
            self.creators[-1].lastname = self.get_node_text(node)
        elif node.nodeName=='email' and node.parentNode.nodeName=='person' and node.parentNode.parentNode.nodeName=='creator':
            self.creators[-1].lastname = self.get_node_text(node)
        else:
            print 'ERROR, unrecognized element: %s' % node.nodeName
            sys.exit(1)
            
        for child in node.childNodes:
            self.handle_node(child)
        
    def get_node_text(self, node):
        value = ''
        for child in node.childNodes:
            if child.nodeType==node.TEXT_NODE:
                value = value + child.data
        value = trim(value)
        return value
        
    def get_attribute_text(self, node, name):
        value = ''
        if node.hasAttributes:
            len = node.attributes.length
            for item in range(len):
                attribute = node.attributes.item(item)
                if attribute.name==name:
                    value = attribute.value
        return value

    def print_debug(self):
        print 'title:       %s' % self.title
        print 'type:        %s' % self.type
        print 'description: %s' % self.description
        print 'categories:  %s' % self.categories
        print 'filename:    %s' % self.filename
        print 'language:    %s' % self.lang

def callback(arg, directory, filenames):
    for filename in filenames:
        if fnmatch.fnmatch(filename, arg):
            print 'Reading omf: %s/%s' % (directory, filename)
            omf = OMF()
            dom = parse(directory + '/' + filename)
            omf.read_dom(dom)
            if omf.filename > '':
                omf.filename = 'file://' + directory + '/' + omf.filename
            omf.print_debug()

            # Not all versions of Python do garbage collection
            # on circular references, so unlink dom manually.
            dom.unlink()

def usage():
    print """Usage: gnome-import [OMF-DIR] [FILESPEC}

    OMF-DIR is a directory where we start recursively processing
    OMF files.

    FILESPEC is the glob used to scan files, e.g., *.omf.
    Your shell might require you to wrap it in quotes to avoid
    glob expansion.
    """
    sys.exit()


# Options passed on the command line
if len(sys.argv) <> 3:
    usage()
gnome_dir = sys.argv[1]
filespec = sys.argv[2]

# Read in the omf files.
os.path.walk(gnome_dir, callback, filespec)