File: GSGW.py

package info (click to toggle)
python-pymzml 2.5.2%2Brepack1-1
  • links: PTS, VCS
  • area: main
  • in suites: bookworm
  • size: 27,792 kB
  • sloc: python: 6,495; pascal: 341; makefile: 233; sh: 30
file content (305 lines) | stat: -rwxr-xr-x 10,361 bytes parent folder | download | duplicates (2)
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
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
#!/usr/bin/env python
# -*- coding: latin-1 -*-
"""
Writer class for indexed gzipped files
"""

# Python mzML module - pymzml
# Copyright (C) 2010-2019 M. Kösters, C. Fufezan
#     The MIT License (MIT)

#     Permission is hereby granted, free of charge, to any person obtaining a copy
#     of this software and associated documentation files (the "Software"), to deal
#     in the Software without restriction, including without limitation the rights
#     to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
#     copies of the Software, and to permit persons to whom the Software is
#     furnished to do so, subject to the following conditions:

#     The above copyright notice and this permission notice shall be included in all
#     copies or substantial portions of the Software.

#     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
#     IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
#     FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
#     AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
#     LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
#     OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
#     SOFTWARE.

import struct
import time
import zlib
from collections import OrderedDict


class GSGW(object):
    """

    Generalized Gzip writer class with random access to indexed offsets.

    Keyword Arguments:
        file (string)        : Filename for the resulting file
        max_idx (int)        : max number of indices which can be saved in
                                this file
        max_idx_len (int)    : maximal length of the index in bytes, must
                                be between 1 and 255
        max_offset_len (int) : maximal length of the offset in bytes
        output_path (str)    : path to the output file

    """

    def __init__(
        self,
        file=None,
        max_idx=10000,
        max_idx_len=8,
        max_offset_len=8,
        output_path="./test.dat.igzip",
        comp_str=-1,
    ):
        self.Lock = False
        self._format_version = 1  # max 255!!!
        self.file_name = output_path
        self.max_idx_num = max_idx
        self.max_idx_len = max_idx_len
        self.max_offset_len = max_offset_len
        self.generic_header = OrderedDict(
            [
                ("MAGIC_BYTE_1", b"\x1f"),
                ("MAGIC_BYTE_2", b"\x8b"),
                ("COMPRESSION", b"\x08"),
                ("FLAGS", b"\x00"),
                ("DATE", b"\x00\x00\x00\x00"),
                ("XFL", b"\x02"),
                ("OS", b"\x03"),
            ]
        )
        self.index = OrderedDict()
        self.first_header_set = False
        self._file_out = None
        self._encoding = "latin-1"
        # magic bytes. FU+version
        self.index_magic_bytes = b"FU" + struct.pack("<B", self._format_version)
        self.crc32 = 0
        self.isize = 0
        self.comp_str = comp_str

    def __del__(self):
        """
        Close the file object properly after this object is deleted
        """
        self.file_out.close()

    def close(self):
        """
        Close the internal file object.
        """
        self.file_out.close()

    @property
    def file_out(self):
        """
        Output filehandler
        """
        if self._file_out is None:
            self._file_out = open(self.file_name, "wb")
        return self._file_out

    @property
    def encoding(self):
        """
        Returns the encoding used for this file
        """
        return self._encoding

    @encoding.setter
    def encoding(self, encoding):
        """
        Set the file encoding for the output file.
        """
        assert type(encoding) == str, "encoding must be a string"
        self._encoding = encoding

    def _write_gen_header(self, Index=False, FLAGS=None):
        """
        Write a valid gzip header with creation time, user defined flag fields
        and allocated index.

        Keyword Arguments:
            Index (bool)           : whether to or not to write an
                                        index into this header.
            FLAGS (list, optional) : list of flags (FTEXT, FHCRC, FEXTRA,
                                        FNAME) to set for this header.

        Returns:
            offset (int): byte offset of the file pointer
        """
        if FLAGS is None:
            FLAGS = []
        FTEXT, FHCRC, FEXTRA, FNAME = 1, 2, 4, 8  # extra field bit flags
        current_time = int(time.time())
        time_byte = struct.pack("<L", current_time)
        self.generic_header["DATE"] = time_byte
        if Index:
            self.generic_header["FLAGS"] = b"\x10"
        if FLAGS is not None:
            if "FTEXT" in FLAGS:
                self.generic_header["FLAGS"] = self.generic_header["FLAGS"] & FTEXT

            if "FHCRC" in FLAGS:
                header_crc32 = 0
                self.generic_header["FLAGS"] = self.generic_header["FLAGS"] & FHCRC
                for byte in self.generic_header.values():
                    header_crc32 = zlib.crc32(byte, header_crc32)

            if "FEXTRA" in FLAGS:
                self.generic_header["FLAGS"] = self.generic_header["FLAGS"] & FEXTRA

            if "FNAME" in FLAGS:
                self.generic_header["FLAGS"] = self.generic_header["FLAGS"] & FNAME

        for value in self.generic_header.values():
            self.file_out.write(value)
        if "FEXTRA" in FLAGS:
            # WRITE EXTRA FIELD
            pass

        if "FNAME" in FLAGS:
            # WRITE FNAME FIELD
            fName = self.file_name.split("/")[-1]

        if Index:
            self.generic_header["FLAGS"] = b"\x00"
            self.file_out.write(self.index_magic_bytes)
            self.file_out.write(struct.pack("<B", self.max_idx_len))
            self.file_out.write(struct.pack("<B", self.max_offset_len))
            self.index_offset = self.file_out.tell()
            self._allocate_index_bytes()

        if "FHCRC" in FLAGS:
            # WRITE checksum for header
            pass

        return self.file_out.tell()

    def _allocate_index_bytes(self):
        """
        Allocate 'self.max_index_num' bytes of length 'self.max_idx_len'
        in the header for inserting the index later on.
        """
        id_placeholder = self.max_idx_len * b"\x01"
        offset_placeholder = self.max_offset_len * b"\x01"
        for i in range(self.max_idx_num):
            self.file_out.write(id_placeholder)
            self.file_out.write(offset_placeholder)
        self.file_out.write(b"\x00")
        return

    def _write_data(self, data):
        """
        Write data into file-stream.

        Arguments:
            data (str): uncompressed data
        """
        Compressor = zlib.compressobj(
            self.comp_str, zlib.DEFLATED, -zlib.MAX_WBITS, zlib.DEF_MEM_LEVEL, 0
        )
        # compress data and flush (includes writing crc32 and isize)
        if isinstance(data, bytes) is False:
            data = bytes(data, "latin-1")
        self.crc32 = zlib.crc32(data)
        self.isize = len(data) % 2 ** 32
        comp_data = Compressor.compress(data) + Compressor.flush()
        self.file_out.write(comp_data)
        self.file_out.write(struct.pack("<L", self.crc32))
        self.file_out.write(struct.pack("<L", self.isize))
        return

    def add_data(self, data, identifier):
        """
        Create a new gzip member with compressed 'data' indexed with 'index'.

        Arguments:
            data (str)         : uncompressed data to write to file
            index (str or int) : unique index for the data
        """
        if self.Lock is False:
            if len(self.index) + 1 > self.max_idx_num:
                print(
                    """
    WARNING: Reached maximum number of indexed data blocks
    '({0}), cannot add any more data!
                    """.format(
                        self.max_idx_num
                    )
                )
                return False

            if not self.first_header_set:
                self._write_gen_header(Index=True)
                self.first_header_set = True
            else:
                # do we need this?
                self._write_gen_header(Index=False)

            self.index[identifier] = self.file_out.tell()
            self._write_data(data)
            return
        else:
            raise Exception("Cant add any more data if index is already written")

    def _write_identifier(self, identifier):
        """
        Convert and write the identifier into output file.

        Arguments:
            identifier (str or int): identifier to write into index
        """
        id_format = "{0:\xAC>" + str(self.max_idx_len) + "}"
        identifier = str(identifier)
        identifier = id_format.format(identifier).encode("latin-1")
        self.file_out.write(identifier)
        return

    def _write_offset(self, offset):
        """
        Convert and write offset to output file.

        Arguments:
            offset (int): offset which will be formatted and written
                into file index
        """
        offset_format = "{0:\xAC>" + str(self.max_offset_len) + "}"
        offset = str(offset)
        offset = offset_format.format(offset).encode("latin-1")
        self.file_out.write(offset)
        return

    def write_index(self):
        """
        Only called after all the data is written, i.e. all calls to
        :func:`~GSGW.add_data` have been done.

        Seek back to the beginning of the file and write the index into the
        allocated comment bytes (see _write_gen_header(Index=True)).
        """
        self.Lock = True
        self.file_out.seek(self.index_offset)
        for identifier, offset in self.index.items():
            self._write_identifier(identifier)
            self._write_offset(offset)

    def __enter__(self):
        """
        Enable the with syntax for this class (entry point).
        """
        return self

    def __exit__(self, exc_type, exc_value, traceback):
        """Destructor when using this class with 'with .. as'."""
        self.file_out.close()


if __name__ == "__main__":
    print(__doc__)