debian-python-odf/odfimgimport/odfimgimport

#!/usr/bin/python3
# -*- coding: utf-8 -*-
# Copyright (C) 2007-2009 Søren Roug, European Environment Agency
#
# This is free software.  You may redistribute it under the terms
# of the Apache license and the GNU General Public License Version
# 2 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., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
#
# Contributor(s):
#
from __future__ import print_function

import zipfile, sys, getopt, mimetypes
try:
    from urllib2 import urlopen, quote, unquote
except ImportError:
    from urllib.request import urlopen, quote, unquote
try:
    from urlparse import urlunsplit, urlsplit
except ImportError:
    from urllib.parse import urlunsplit, urlsplit
from odf.opendocument import load
from odf.draw import Image

if sys.version_info[0]==3: unicode=str

#sys.tracebacklimit = 0

# Variable to count the number of retrieval failures
failures = 0

# Set to one if quiet behaviour is wanted
quiet = 0

# If set will write every url to import
verbose = 0

# Dictionary with new pictures. Key is original file path
# Item is newfilename
newpictures = {}
doc = None

def importpicture(href):
    """ Add the picture to the ZIP file
        Returns the new path name to the file in the zip archive
        If it is unable to import, then it returns the original href
        Sideeffect: add line to manifest
    """
    global doc, newpictures, failures, verbose

    # Check that it is not already in the manifest
    if href in doc.Pictures: return href

    image = None
    if verbose: print ("Importing", href, file=sys.stderr)
    if href[:7] == "http://" or href[:8] == "https://" or href[:6] == "ftp://":
        # There is a bug in urlopen: It can't open urls with non-ascii unicode
        # characters. Convert to UTF-8 and then use percent encoding
        try:
            goodhref = href.encode('ascii')
        except:
            o = list(urlsplit(href))
            o[2] = quote(o[2].encode('utf-8'))
            goodhref = urlunsplit(o)
        if goodhref in newpictures:
            if verbose: print ("already imported", file=sys.stderr)
            return newpictures[goodhref]  # Already imported
        try:
            f = urlopen(goodhref.decode("utf-8"))
            image = f.read()
            headers = f.info()
            f.close()
            # Get the mimetype from the headerlines
            c_t = headers['Content-Type'].split(';')[0].strip()
            if c_t: mediatype = c_t.split(';')[0].strip()
            if verbose: print ("OK", file=sys.stderr)
        except:
            failures += 1
            if verbose: print ("failed", file=sys.stderr)
            return href
        # Remove query string
        try: href= href[:href.rindex('?')]
        except: pass
        try:
            lastslash = href[href.rindex('/'):]
            ext = lastslash[lastslash.rindex('.'):]
        except: ext = mimetypes.guess_extension(mediatype)
    # Everything is a simple path.
    else:
        goodhref = href
        if href[:3] == '../':
            if directory is None:
                goodhref = unquote(href[3:])
            else:
                goodhref = unquote(directory + href[2:])
        if goodhref in newpictures:
            if verbose: print ("already imported", file=sys.stderr)
            return newpictures[goodhref]  # Already imported
        mediatype, encoding = mimetypes.guess_type(goodhref)
        if mediatype is None:
            mediatype = ''
            try: ext = goodhref[goodhref.rindex('.'):]
            except: ext=''
        else:
            ext = mimetypes.guess_extension(mediatype)
        try:
            image = file(goodhref).read()
            if verbose: print ("OK", file=sys.stderr)
        except:
            failures += 1
            if verbose: print ("failed", file=sys.stderr)
            return href
    # If we have a picture to import, the image variable contains it
    # and manifestfn, ext and mediatype has a value
    if image:
        manifestfn = doc.addPictureFromString(image, unicode(mediatype))
        newpictures[goodhref] = manifestfn
        return manifestfn

    if verbose: print ("not imported", file=sys.stderr)
    return href

def exitwithusage(exitcode=2):
    """ Print out usage information and exit """
    print ("Usage: %s [-q] [-v] [-o output] [inputfile]" % sys.argv[0], file=sys.stderr)
    print ("\tInputfile must be OpenDocument format", file=sys.stderr)
    sys.exit(exitcode)

outputfile = None
writefile = True

try:
    opts, args = getopt.getopt(sys.argv[1:], "qvo:")
except getopt.GetoptError:
    exitwithusage()

for o, a in opts:
    if o == "-o":
        outputfile = a
        writefile = True
    if o == "-q":
        quiet = 1
    if o == "-v":
        verbose = 1

if len(args) == 0:
    try:
        doc = load(sys.stdin)
        directory = None
    except:
        print ("Couldn't open OpenDocument file", file=sys.stderr)
        exitwithusage()
else:
    fn = unicode(args[0])
    if not zipfile.is_zipfile(fn):
        exitwithusage()
    dirinx = max(fn.rfind('\\'), fn.rfind('/'))
    if dirinx >= 0: directory = fn[:dirinx]
    else: directory = "."
    doc = load(fn)

for image in doc.getElementsByType(Image):
    href = image.getAttribute('href')
    newhref = importpicture(href)
    image.setAttribute('href',newhref)

if writefile:
    if outputfile is None:
        doc.save(fn)
    else:
        doc.save(unicode(outputfile))


if quiet == 0 and failures > 0:
    print ("Couldn't import %d image(s)" % failures, file=sys.stderr)
sys.exit( int(failures > 0) )


# Local Variables: ***
# mode: python     ***
# End:             ***