Fix #88 and add zipfile test

HISTORY.rst

@@ -13,6 +13,7 @@ tnefparse 1.4.0 (unreleased)
 - fix `test_zip` deprecation warning for bytes (1nF0rmed)
 - correctly handle attachments of embedded objects (jrideout)
 - add expirimental support for parsing embedded message objects (jrideout)
+- zipped output now uses long filename when possible (jrideout)
 
 tnefparse 1.3.1 (2020-09-30)
 =============================

tests/test_cmdline.py

@@ -31,13 +31,13 @@ def test_cmdline_attch_extract(script_runner):
 
 def test_cmdline_zip_extract(script_runner):
     tmpdir = tempfile.mkdtemp()
-    ret = script_runner.run('tnefparse', '-z', '-p', tmpdir, 'tests/examples/one-file.tnef')
+    ret = script_runner.run('tnefparse', '-z', '-p', tmpdir, 'tests/examples/duplicate_filename.tnef')
     assert os.path.isfile(tmpdir + '/attachments.zip')
     assert ret.stderr == 'Successfully wrote attachments.zip\n'
     with open(tmpdir + '/attachments.zip', 'rb') as zip_fp:
         zip_stream = io.BytesIO(zip_fp.read())
     zip_file = zipfile.ZipFile(zip_stream)
-    assert zip_file.namelist() == ['AUTHORS']
+    assert zip_file.namelist() == ['file_abcdefgh.txt', 'file_abcdefgh-2.txt', 'VIA_Nytt_14021.htm']
     assert ret.success
     shutil.rmtree(tmpdir)
 
@@ -85,7 +85,7 @@ def test_dump(script_runner):
     ret = script_runner.run('tnefparse', '-d', 'tests/examples/two-files.tnef')
     assert ret.success
     dump = json.loads(ret.stdout)
-    assert sorted(list(dump.keys())) == ['attachments', 'attributes', 'extended_attributes']
+    assert sorted(dump.keys()) == ['attachments', 'attributes', 'extended_attributes']
     assert len(dump['attachments']) == 2
 
 

tnefparse/mapi.py

@@ -148,12 +148,13 @@ def parse_property(data, offset, attr_name, attr_type, codepage, is_multi):
             r = length % 4
             if r != 0:
                 length += 4 - r
+
+            item = data[offset: offset + length]
             if attr_type == SZMAPI_UNICODE_STRING:
-                attr_data.append(data[offset: offset + length].decode('utf-16'))
+                item = item.decode('utf-16')
             elif attr_type == SZMAPI_STRING:
-                attr_data.append(data[offset: offset + length].decode(codepage))
-            else:
-                attr_data.append(data[offset: offset + length])
+                item = item.decode(codepage)
+            attr_data.append(item)
             offset += length
 
     else:

tnefparse/tnef.py

@@ -3,11 +3,11 @@
 import logging
 import os
 import warnings
-from typing import Union
-from zipfile import ZipFile, ZIP_DEFLATED, ZIP_STORED
-from io import BytesIO
 from datetime import datetime
+from io import BytesIO
+from typing import Union
 from uuid import UUID
+from zipfile import ZipFile, ZIP_DEFLATED, ZIP_STORED
 
 from . import properties as Attribute
 from .codepage import Codepage
@@ -331,7 +331,7 @@ def __init__(self, data, do_checksum=True):
                 logger.debug("Unhandled TNEF Object: %s", obj)
 
     def has_body(self):
-        return True if (self.body or self.htmlbody or self._rtfbody) else False
+        return any((self.body, self.htmlbody, self._rtfbody))
 
     @property
     def rtfbody(self):
@@ -377,9 +377,7 @@ def get_data(a):
             if o.name == TNEF.ATTRECIPTABLE:
                 data = []
                 for recipient in o.data:
-                    rec = {}
-                    for att in recipient:
-                        rec[att.name_str] = get_data(att)
+                    rec = {att.name_str: get_data(att) for att in recipient}
                     data.append(rec)
             out['attributes'][o.name_str] = data
         for att in self.mapiprops:
@@ -410,21 +408,20 @@ def to_zip(tnef: Union[TNEF, bytes], default_name='no-name', deflate=True):
     # Extract attachments found in the TNEF object
     tozip = {}
     for attachment in tnef.attachments:
-        filename = attachment.name or default_name
-        L = len(tozip.get(filename, []))
-        if L > 0:
+        filename = attachment.long_filename() or default_name
+        if tozip.get(filename):
             # uniqify this file name by adding -<num> before the extension
+            length = len(tozip.get(filename))
             root, ext = os.path.splitext(filename)
-            tozip[filename].append((attachment.data, str("%s-%d%s" % (root, L + 1, ext))))
+            tozip[filename].append((f"{root}-{length + 1}{ext}", attachment.data))
         else:
-            tozip[filename] = [(attachment.data, filename)]
+            tozip[filename] = [(filename, attachment.data)]
 
     # Add each attachment to the zip file
     sfp = BytesIO()
     with ZipFile(sfp, "w", ZIP_DEFLATED if deflate else ZIP_STORED) as zf:
-        for filename, entries in list(tozip.items()):
-            for entry in entries:
-                data, name = entry
+        for entries in tozip.values():
+            for name, data in entries:
                 zf.writestr(name, data)
 
     # Return the binary data for the zip file

tnefparse/util.py

@@ -44,7 +44,7 @@ def systime(byte_arr, offset=0):
         return datetime.utcfromtimestamp((ft - EPOCH_AS_FILETIME) / HUNDREDS_OF_NANOSECONDS)
     except:  # noqa: E722
         microseconds = ft / 10
-        return (datetime(1601, 1, 1) + timedelta(microseconds=microseconds))
+        return datetime(1601, 1, 1) + timedelta(microseconds=microseconds)
 
 
 def apptime(byte_arr, offset=0):