From eac51dbc9964cac28bb83e7d12370cf87ff2b0c5 Mon Sep 17 00:00:00 2001
From: jvoisin
Date: Sun, 1 Apr 2018 01:04:06 +0200
Subject: Refactor office document handling

---
 src/libreoffice.py | 68 ------------------------------------------------------
 1 file changed, 68 deletions(-)
 delete mode 100644 src/libreoffice.py

(limited to 'src/libreoffice.py')

diff --git a/src/libreoffice.py b/src/libreoffice.py
deleted file mode 100644
index 809ae3c..0000000
--- a/src/libreoffice.py
+++ /dev/null
@@ -1,68 +0,0 @@
-import re
-import subprocess
-import json
-import zipfile
-import tempfile
-import shutil
-import os
-
-from . import abstract, parser_factory
-
-class LibreOfficeParser(abstract.AbstractParser):
-    mimetypes = {
-            'application/vnd.oasis.opendocument.text',
-            'application/vnd.oasis.opendocument.spreadsheet',
-            'application/vnd.oasis.opendocument.presentation',
-            'application/vnd.oasis.opendocument.graphics',
-            'application/vnd.oasis.opendocument.chart'
-    }
-
-    def get_meta(self):
-        """
-        Yes, I know that parsing xml with regexp ain't pretty,
-        be my guest and fix it if you want.
-        """
-        metadata = {}
-        zipin = zipfile.ZipFile(self.filename)
-        for item in zipin.namelist():
-            if item == 'meta.xml':
-                content = zipin.read(item).decode('utf-8')
-                for (key, value) in re.findall(r"<((?:meta|dc).+?)>(.+)</\1>", content, re.I):
-                    metadata[key] = value
-                if not metadata:  # better safe than sorry
-                    metadata[item] = 'harmful content'
-        zipin.close()
-        return metadata
-
-    def __clean_zipinfo(self, zipinfo:zipfile.ZipInfo) -> zipfile.ZipInfo:
-        zipinfo.compress_type = zipfile.ZIP_DEFLATED
-        zipinfo.create_system = 3  # Linux
-        zipinfo.comment = b''
-        zipinfo.date_time = (1980, 1, 1, 0, 0, 0)
-        return zipinfo
-
-    def remove_all(self):
-        zin = zipfile.ZipFile(self.filename, 'r')
-        zout = zipfile.ZipFile(self.output_filename, 'w')
-        temp_folder = tempfile.mkdtemp()
-
-        for item in zin.infolist():
-            if item.filename[-1] == '/':
-                continue  # `is_dir` is added in Python3.6
-            elif item.filename == 'meta.xml':
-                continue  # don't keep metadata files
-
-            zin.extract(member=item, path=temp_folder)
-            tmp_parser = parser_factory.get_parser(os.path.join(temp_folder, item.filename))
-            if tmp_parser is None:
-                print("%s isn't supported" % item.filename)
-                continue
-            tmp_parser.remove_all()
-            zinfo = zipfile.ZipInfo(item.filename)
-            item = self.__clean_zipinfo(item)
-            with open(tmp_parser.output_filename, 'rb') as f:
-                zout.writestr(zinfo, f.read())
-        shutil.rmtree(temp_folder)
-        zout.close()
-        zin.close()
-        return True
-- 
cgit v1.3