summaryrefslogtreecommitdiff
path: root/libmat2/archive.py
blob: 7b9f3351bc619f5d0123934d3686ff1024e2e5b5 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
import zipfile
import datetime
import tempfile
import os
import logging
import shutil
from typing import Dict, Set, Pattern

from . import abstract, UnknownMemberPolicy, parser_factory

# Make pyflakes happy
assert Set
assert Pattern


class ArchiveBasedAbstractParser(abstract.AbstractParser):
    """ Office files (.docx, .odt, …) are zipped files. """
    # Those are the files that have a format that _isn't_
    # supported by MAT2, but that we want to keep anyway.
    files_to_keep = set()  # type: Set[str]

    # Those are the files that we _do not_ want to keep,
    # no matter if they are supported or not.
    files_to_omit = set() # type: Set[Pattern]

    # what should the parser do if it encounters an unknown file in
    # the archive?
    unknown_member_policy = UnknownMemberPolicy.ABORT # type: UnknownMemberPolicy

    def __init__(self, filename):
        super().__init__(filename)
        try:  # better fail here than later
            zipfile.ZipFile(self.filename)
        except zipfile.BadZipFile:
            raise ValueError

    def _specific_cleanup(self, full_path: str) -> bool:
        """ This method can be used to apply specific treatment
        to files present in the archive."""
        # pylint: disable=unused-argument,no-self-use
        return True  # pragma: no cover

    @staticmethod
    def _clean_zipinfo(zipinfo: zipfile.ZipInfo) -> zipfile.ZipInfo:
        zipinfo.create_system = 3  # Linux
        zipinfo.comment = b''
        zipinfo.date_time = (1980, 1, 1, 0, 0, 0)  # this is as early as a zipfile can be
        return zipinfo

    @staticmethod
    def _get_zipinfo_meta(zipinfo: zipfile.ZipInfo) -> Dict[str, str]:
        metadata = {}
        if zipinfo.create_system == 3:  # this is Linux
            pass
        elif zipinfo.create_system == 2:
            metadata['create_system'] = 'Windows'
        else:
            metadata['create_system'] = 'Weird'

        if zipinfo.comment:
            metadata['comment'] = zipinfo.comment  # type: ignore

        if zipinfo.date_time != (1980, 1, 1, 0, 0, 0):
            metadata['date_time'] = str(datetime.datetime(*zipinfo.date_time))

        return metadata

    def remove_all(self) -> bool:
        # pylint: disable=too-many-branches

        with zipfile.ZipFile(self.filename) as zin,\
             zipfile.ZipFile(self.output_filename, 'w') as zout:

            temp_folder = tempfile.mkdtemp()
            abort = False

            # Since files order is a fingerprint factor,
            # we're iterating (and thus inserting) them in lexicographic order.
            for item in sorted(zin.infolist(), key=lambda z: z.filename):
                if item.filename[-1] == '/':  # `is_dir` is added in Python3.6
                    continue  # don't keep empty folders

                zin.extract(member=item, path=temp_folder)
                full_path = os.path.join(temp_folder, item.filename)

                if self._specific_cleanup(full_path) is False:
                    logging.warning("Something went wrong during deep cleaning of %s",
                                    item.filename)
                    abort = True
                    continue

                if item.filename in self.files_to_keep:
                    # those files aren't supported, but we want to add them anyway
                    pass
                elif any(map(lambda r: r.search(item.filename), self.files_to_omit)):
                    continue
                else: # supported files that we want to first clean, then add
                    tmp_parser, mtype = parser_factory.get_parser(full_path)  # type: ignore
                    if not tmp_parser:
                        if self.unknown_member_policy == UnknownMemberPolicy.OMIT:
                            logging.warning("In file %s, omitting unknown element %s (format: %s)",
                                            self.filename, item.filename, mtype)
                            continue
                        elif self.unknown_member_policy == UnknownMemberPolicy.KEEP:
                            logging.warning("In file %s, keeping unknown element %s (format: %s)",
                                            self.filename, item.filename, mtype)
                        else:
                            logging.error("In file %s, element %s's format (%s) " +
                                          "isn't supported",
                                          self.filename, item.filename, mtype)
                            abort = True
                            continue
                    if tmp_parser:
                        tmp_parser.remove_all()
                        os.rename(tmp_parser.output_filename, full_path)

                zinfo = zipfile.ZipInfo(item.filename)  # type: ignore
                clean_zinfo = self._clean_zipinfo(zinfo)
                with open(full_path, 'rb') as f:
                    zout.writestr(clean_zinfo, f.read())

        shutil.rmtree(temp_folder)
        if abort:
            os.remove(self.output_filename)
            return False
        return True