add PackageReader.from_file()

Steve Canny · Steve Canny · commit 492b5c0bd4a8 · 2013-08-05T14:56:07.000-07:00
diff --git a/opc/phys_pkg.py b/opc/phys_pkg.py
@@ -24,3 +24,16 @@ class ZipPkgReader(object):
     """
     Implements |PhysPkgReader| interface for a zip file OPC package.
     """
+    def __init__(self, pkg_file):
+        super(ZipPkgReader, self).__init__()
+
+    def close(self):
+        """
+        Close the zip archive, releasing any resources it is using.
+        """
+
+    @property
+    def content_types_xml(self):
+        """
+        Return the `[Content_Types].xml` blob from the zip package.
+        """
diff --git a/opc/pkgreader.py b/opc/pkgreader.py
@@ -12,14 +12,55 @@
 (OPC) package.
 """
 
+from opc.packuri import PACKAGE_URI
+from opc.phys_pkg import PhysPkgReader
+
 
 class PackageReader(object):
     """
     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__()
+
     @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)
+
+    @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*.
+        """
+
+    @staticmethod
+    def _srels_for(phys_reader, source_uri):
+        """
+        Return |_SerializedRelationshipCollection| instance populated with
+        relationships for source identified by *source_uri*.
+        """
+
+
+class _ContentTypeMap(object):
+    """
+    Value type providing dictionary semantics for looking up content type by
+    part name, e.g. ``content_type = cti['/ppt/presentation.xml']``.
+    """
+    @staticmethod
+    def from_xml(content_types_xml):
+        """
+        Return a new |_ContentTypeMap| instance populated with the contents
+        of *content_types_xml*.
+        """
diff --git a/tests/test_pkgreader.py b/tests/test_pkgreader.py
@@ -0,0 +1,64 @@
+# -*- coding: utf-8 -*-
+#
+# test_pkgreader.py
+#
+# Copyright (C) 2013 Steve Canny scanny@cisco.com
+#
+# This module is part of python-pptx and is released under the MIT License:
+# http://www.opensource.org/licenses/mit-license.php
+
+"""Test suite for opc.pkgreader module."""
+
+import pytest
+
+from mock import Mock, patch
+
+from opc.phys_pkg import ZipPkgReader
+from opc.pkgreader import _ContentTypeMap, PackageReader
+
+from .unitutil import initializer_mock, method_mock
+
+
+class DescribePackageReader(object):
+
+    @pytest.fixture
+    def from_xml(self, request):
+        return method_mock(_ContentTypeMap, 'from_xml', request)
+
+    @pytest.fixture
+    def init(self, request):
+        return initializer_mock(PackageReader, request)
+
+    @pytest.fixture
+    def _load_serialized_parts(self, request):
+        return method_mock(PackageReader, '_load_serialized_parts', request)
+
+    @pytest.fixture
+    def PhysPkgReader_(self, request):
+        _patch = patch('opc.pkgreader.PhysPkgReader', spec_set=ZipPkgReader)
+        request.addfinalizer(_patch.stop)
+        return _patch.start()
+
+    @pytest.fixture
+    def _srels_for(self, request):
+        return method_mock(PackageReader, '_srels_for', request)
+
+    def it_can_construct_from_pkg_file(self, init, PhysPkgReader_, from_xml,
+                                       _srels_for, _load_serialized_parts):
+        # mockery ----------------------
+        phys_reader = PhysPkgReader_.return_value
+        content_types = from_xml.return_value
+        pkg_srels = _srels_for.return_value
+        sparts = _load_serialized_parts.return_value
+        pkg_file = Mock(name='pkg_file')
+        # exercise ---------------------
+        pkg_reader = PackageReader.from_file(pkg_file)
+        # verify -----------------------
+        PhysPkgReader_.assert_called_once_with(pkg_file)
+        from_xml.assert_called_once_with(phys_reader.content_types_xml)
+        _srels_for.assert_called_once_with(phys_reader, '/')
+        _load_serialized_parts.assert_called_once_with(phys_reader, pkg_srels,
+                                                       content_types)
+        phys_reader.close.assert_called_once_with()
+        init.assert_called_once_with(content_types, pkg_srels, sparts)
+        assert isinstance(pkg_reader, PackageReader)
