Class PackageReader

src/docx/opc/pkgreader.py:10–83

Provides access to the contents of a zip-format OPC package via its :attr:`serialized_parts` and :attr:`pkg_srels` attributes.

class PackageReader:
    """Provides access to the contents of a zip-format OPC package via its
    :attr:`serialized_parts` and :attr:`pkg_srels` attributes."""

    def __init__(self, content_types, pkg_srels, sparts):
        super(PackageReader, self).__init__()
        self._pkg_srels = pkg_srels
        self._sparts = sparts

    @staticmethod
    def from_file(pkg_file):
        """Return a |PackageReader| instance loaded with contents of `pkg_file`."""
        phys_reader = PhysPkgReader(pkg_file)
        content_types = _ContentTypeMap.from_xml(phys_reader.content_types_xml)
        pkg_srels = PackageReader._srels_for(phys_reader, PACKAGE_URI)
        sparts = PackageReader._load_serialized_parts(phys_reader, pkg_srels, content_types)
        phys_reader.close()
        return PackageReader(content_types, pkg_srels, sparts)

    def iter_sparts(self):
        """Generate a 4-tuple `(partname, content_type, reltype, blob)` for each of the
        serialized parts in the package."""
        for s in self._sparts:
            yield (s.partname, s.content_type, s.reltype, s.blob)

    def iter_srels(self):
        """Generate a 2-tuple `(source_uri, srel)` for each of the relationships in the
        package."""
        for srel in self._pkg_srels:
            yield (PACKAGE_URI, srel)
        for spart in self._sparts:
            for srel in spart.srels:
                yield (spart.partname, srel)

    @staticmethod
    def _load_serialized_parts(phys_reader, pkg_srels, content_types):
        """Return a list of |_SerializedPart| instances corresponding to the parts in
        `phys_reader` accessible by walking the relationship graph starting with
        `pkg_srels`."""
        sparts = []
        part_walker = PackageReader._walk_phys_parts(phys_reader, pkg_srels)
        for partname, blob, reltype, srels in part_walker:
            content_type = content_types[partname]
            spart = _SerializedPart(partname, content_type, reltype, blob, srels)
            sparts.append(spart)
        return tuple(sparts)

    @staticmethod
    def _srels_for(phys_reader, source_uri):
        """Return |_SerializedRelationships| instance populated with relationships for
        source identified by `source_uri`."""
        rels_xml = phys_reader.rels_xml_for(source_uri)
        return _SerializedRelationships.load_from_xml(source_uri.baseURI, rels_xml)

    @staticmethod
    def _walk_phys_parts(phys_reader, srels, visited_partnames=None):
        """Generate a 4-tuple `(partname, blob, reltype, srels)` for each of the parts
        in `phys_reader` by walking the relationship graph rooted at srels."""