| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216 |
- #!/usr/bin/python3
- # -*- coding: utf-8 -*-
- # Copyright (C) 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):
- #
- import zipfile
- from xml.sax import make_parser,handler
- from xml.sax.xmlreader import InputSource
- import xml.sax.saxutils
- import sys
- from odf.opendocument import OpenDocument
- from odf import element, grammar
- from odf.namespaces import *
- from odf.attrconverters import attrconverters, cnv_string
- from io import BytesIO
- if sys.version_info[0]==3: unicode=str
- extension_attributes = {
- "OpenOffice.org" : {
- (METANS,u'template'): (
- (XLINKNS,u'role'),
- ),
- (STYLENS,u'graphic-properties'): (
- (STYLENS,u'background-transparency'),
- ),
- (STYLENS,u'paragraph-properties'): (
- (TEXTNS,u'enable-numbering'),
- (STYLENS,u'join-border'),
- ),
- (STYLENS,u'table-cell-properties'): (
- (STYLENS,u'writing-mode'),
- ),
- (STYLENS,u'table-row-properties'): (
- (STYLENS,u'keep-together'),
- ),
- },
- "KOffice" : {
- (STYLENS,u'graphic-properties'): (
- (KOFFICENS,u'frame-behavior-on-new-page'),
- ),
- (DRAWNS,u'page'): (
- (KOFFICENS,u'name'),
- ),
- (PRESENTATIONNS,u'show-shape'): (
- (KOFFICENS,u'order-id'),
- ),
- (PRESENTATIONNS,u'hide-shape'): (
- (KOFFICENS,u'order-id'),
- ),
- (CHARTNS,u'legend'): (
- (KOFFICENS,u'title'),
- ),
- }
- }
- printed_errors = []
- def print_error(str):
- if str not in printed_errors:
- printed_errors.append(str)
- print (str)
- def chop_arg(arg):
- if len(arg) > 20:
- return "%s..." % arg[0:20]
- return arg
- def make_qname(tag):
- return "%s:%s" % (nsdict.get(tag[0],tag[0]), tag[1])
- def allowed_attributes(tag):
- return grammar.allowed_attributes.get(tag)
- class ODFElementHandler(handler.ContentHandler):
- """ Extract headings from content.xml of an ODT file """
- def __init__(self, document):
- self.doc = document
- self.tagstack = []
- self.data = []
- self.currtag = None
- def characters(self, data):
- self.data.append(data)
- def startElementNS(self, tag, qname, attrs):
- """ Pseudo-create an element
- """
- allowed_attrs = grammar.allowed_attributes.get(tag)
- attrdict = {}
- for (att,value) in attrs.items():
- prefix = nsdict.get(att[0],att[0])
- # Check if it is a known extension
- notan_extension = True
- for product, ext_attrs in extension_attributes.items():
- allowed_ext_attrs = ext_attrs.get(tag)
- if allowed_ext_attrs and att in allowed_ext_attrs:
- print_error("Warning: Attribute %s in element <%s> is illegal - %s extension" % ( make_qname(att), make_qname(tag), product))
- notan_extension = False
- # Check if it is an allowed attribute
- if notan_extension and allowed_attrs and att not in allowed_attrs:
- print_error("Error: Attribute %s:%s is not allowed in element <%s>" % ( prefix, att[1], make_qname(tag)))
- # Check the value
- try:
- convert = attrconverters.get(att, cnv_string)
- convert(att, value, tag)
- except ValueError as res:
- print_error("Error: Bad value '%s' for attribute %s:%s in tag: <%s> - %s" %
- (chop_arg(value), prefix, att[1], make_qname(tag), res))
- self.tagstack.append(tag)
- self.data = []
- # Check that the parent allows this child element
- if tag not in ( (OFFICENS, 'document'), (OFFICENS, 'document-content'), (OFFICENS, 'document-styles'),
- (OFFICENS, 'document-meta'), (OFFICENS, 'document-settings'),
- (MANIFESTNS,'manifest')):
- try:
- parent = self.tagstack[-2]
- allowed_children = grammar.allowed_children.get(parent)
- except:
- print_error("Error: This document starts with the wrong tag: <%s>" % make_qname(tag))
- allowed_children = None
- if allowed_children and tag not in allowed_children:
- print_error("Error: Element %s is not allowed in element %s" % ( make_qname(tag), make_qname(parent)))
- # Test that all mandatory attributes have been added.
- required = grammar.required_attributes.get(tag)
- if required:
- for r in required:
- if attrs.get(r) is None:
- print_error("Error: Required attribute missing: %s in <%s>" % (make_qname(r), make_qname(tag)))
- def endElementNS(self, tag, qname):
- self.currtag = self.tagstack.pop()
- str = ''.join(self.data).strip()
- # Check that only elements that can take text have text
- # But only elements we know exist in grammar
- if tag in grammar.allowed_children:
- if str != '' and tag not in grammar.allows_text:
- print_error("Error: %s does not allow text data" % make_qname(tag))
- self.data = []
- class ODFDTDHandler(handler.DTDHandler):
- def notationDecl(self, name, public_id, system_id):
- """ Ignore DTDs """
- print_error("Warning: ODF doesn't use DOCTYPEs")
- def exitwithusage(exitcode=2):
- """ print out usage information """
- sys.stderr.write("Usage: %s inputfile\n" % sys.argv[0])
- sys.stderr.write("\tInputfile must be OpenDocument format\n")
- sys.exit(exitcode)
- def lint(odffile):
- if not zipfile.is_zipfile(odffile):
- print_error("Error: This is not a zipped file")
- return
- zfd = zipfile.ZipFile(odffile)
- try:
- mimetype = zfd.read('mimetype')
- except:
- mimetype=''
- d = OpenDocument(unicode(mimetype))
- first = True
- for zi in zfd.infolist():
- if first:
- if zi.filename == 'mimetype':
- if zi.compress_type != zipfile.ZIP_STORED:
- print_error("Error: The 'mimetype' member must be stored - not deflated")
- if zi.comment != "":
- print_error("Error: The 'mimetype' member must not have extra header info")
- else:
- print_error("Warning: The first member in the archive should be the mimetype")
- first = False
- if zi.filename in ('META-INF/manifest.xml', 'content.xml', 'meta.xml', 'styles.xml', 'settings.xml'):
- content = zfd.read(zi.filename)
- parser = make_parser()
- parser.setFeature(handler.feature_namespaces, True)
- parser.setFeature(handler.feature_external_ges, False)
- parser.setContentHandler(ODFElementHandler(d))
- dtdh = ODFDTDHandler()
- parser.setDTDHandler(dtdh)
- parser.setErrorHandler(handler.ErrorHandler())
- inpsrc = InputSource()
- if not isinstance(content, str):
- content=content
- inpsrc.setByteStream(BytesIO(content))
- parser.parse(inpsrc)
- if len(sys.argv) != 2:
- exitwithusage()
- lint(unicode(sys.argv[1]))
- # Local Variables: ***
- # mode: python ***
- # End: ***
|