From 25230107c4ecdecdbab7f3704e29d5f358252e97 Mon Sep 17 00:00:00 2001
From: jvoisin <julien.voisin@dustri.org>
Date: Tue, 18 Sep 2018 16:56:58 +0200
Subject: [PATCH] Yay, it's working!
---
libmat2/office.py | 41 +++++++++++++++++++++++++++++++----------
1 file changed, 31 insertions(+), 10 deletions(-)
diff --git a/libmat2/office.py b/libmat2/office.py
index f987c71..5c2c996 100644
--- a/libmat2/office.py
+++ b/libmat2/office.py
@@ -1,3 +1,4 @@
+import logging
import os
import re
import zipfile
@@ -14,8 +15,15 @@ assert Pattern
def _parse_xml(full_path: str):
""" This function parses XML, with namespace support. """
+ cpt = 0
namespace_map = dict()
for _, (key, value) in ET.iterparse(full_path, ("start-ns", )):
+ # The ns[0-9]+ namespaces are reserved for interal usage, so
+ # we have to use an other nomenclature.
+ if re.match('^ns[0-9]+$', key):
+ key = 'mat%d' % cpt
+ cpt += 1
+
namespace_map[key] = value
ET.register_namespace(key, value)
@@ -23,16 +31,16 @@ def _parse_xml(full_path: str):
def _sort_xml_attributes(full_path: str) -> bool:
+ """ Sort xml attributes lexicographically,
+ because it's possible to fingerprint producers (MS Office, Libreoffice, …)
+ since they are all using different orders.
+ """
tree = ET.parse(full_path)
root = tree.getroot()
for c in root:
c[:] = sorted(c, key=lambda child: (child.tag, child.get('desc')))
- print('CLENAING %s' % full_path)
- xmlstr = ET.tostring(root, encoding="utf-8", method="xml")
- print(xmlstr.decode("utf-8"))
-
tree.write(full_path, xml_declaration=True)
return True
@@ -64,7 +72,8 @@ class MSOfficeParser(ArchiveBasedAbstractParser):
"""
try:
tree, namespace = _parse_xml(full_path)
- except ET.ParseError:
+ except ET.ParseError as e:
+ logging.error("Unable to parse %s: %s", full_path, e)
return False
# Revisions are either deletions (`w:del`) or
@@ -98,6 +107,9 @@ class MSOfficeParser(ArchiveBasedAbstractParser):
return True
def _specific_cleanup(self, full_path: str) -> bool:
+ if os.stat(full_path).st_size == 0: # Don't process empty files
+ return True
+
if full_path.endswith('/word/document.xml'):
# this file contains the revisions
return self.__remove_revisions(full_path)
@@ -154,7 +166,8 @@ class LibreOfficeParser(ArchiveBasedAbstractParser):
def __remove_revisions(full_path: str) -> bool:
try:
tree, namespace = _parse_xml(full_path)
- except ET.ParseError:
+ except ET.ParseError as e:
+ logging.error("Unable to parse %s: %s", full_path, e)
return False
if 'office' not in namespace.keys(): # no revisions in the current file
@@ -169,11 +182,19 @@ class LibreOfficeParser(ArchiveBasedAbstractParser):
return True
def _specific_cleanup(self, full_path: str) -> bool:
- if os.path.basename(full_path).endswith('.xml'):
- _sort_xml_attributes(full_path)
+ if os.stat(full_path).st_size == 0: # Don't process empty files
+ return True
- if os.path.basename(full_path) == 'content.xml':
- return self.__remove_revisions(full_path)
+ if os.path.basename(full_path).endswith('.xml'):
+ if os.path.basename(full_path) == 'content.xml':
+ if self.__remove_revisions(full_path) is False:
+ return False
+
+ try:
+ _sort_xml_attributes(full_path)
+ except ET.ParseError as e:
+ logging.error("Unable to parse %s: %s", full_path, e)
+ return False
return True
def get_meta(self) -> Dict[str, str]:
--
GitLab