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
|
#!/usr/bin/env python
"""
Additional functions for converting file etc.
@author M. Kösters
"""
# 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.
from pymzml.utils.GSGW import GSGW
import pymzml.regex_patterns as regex_patterns
import re
import gzip
def index_gzip(pathIn, pathOut, max_idx=10000, idx_len=8, verbose=False, comp_str=-1):
"""
Convert an mzml file (can be gzipped) into an indexed, gzipped mzML file.
Arguments:
pathIn (str): path to an mzML input File.
pathOut (str): path were the index gzip will be created.
Keyword Arguments:
max_idx (int): number of indexes which can be saved.
idx_len (int): character len of on key
verbose (boolean): print progress while parsing input.
comp_str(int): compression strength of zlib compression,
needs to be 1 <= x <= 9
"""
if pathIn.endswith("gz"):
fileOpen = gzip.open
elif pathIn.lower().endswith("mzml"):
fileOpen = open
with GSGW(
output_path=pathOut,
max_idx=max_idx,
max_idx_len=idx_len,
max_offset_len=idx_len,
comp_str=comp_str,
) as Writer:
with fileOpen(pathIn, "rt") as Reader:
data = ""
for line in Reader:
if line.strip().startswith("</spectrum>"):
data += line
Writer.add_data(data, nativeID)
if verbose:
print("NativeID : {0}".format(nativeID), end="\r")
data = ""
elif line.strip().startswith("<spectrum "):
data += line
lineID = re.search(regex_patterns.SPECTRUM_TAG_PATTERN, line).group(
"index"
)
nativeID = int(
regex_patterns.SPECTRUM_ID_PATTERN.search(lineID).group(1)
)
elif line.strip().startswith("<chromatogram "):
data += line
nativeID = re.search(
regex_patterns.CHROMATOGRAM_ID_PATTERN, line
).group(1)
print("found chromatogram")
elif line.strip().startswith("<spectrumL"):
data += line
Writer.add_data(data, "Head")
if verbose:
print("NativeID :", "Head")
data = ""
elif line.strip().startswith("<chromatogramL"):
data += line
Writer.add_data(data, "junk")
if verbose:
print("NativeID :", "junk")
data = ""
elif line.strip().startswith("</chromatogram>"):
data += line
Writer.add_data(data, nativeID)
if verbose:
print("found chromatogram")
print("NativeID: {0}".format(nativeID))
data = ""
else:
data += line
if data:
Writer.add_data(data, "tail")
if verbose:
print("NativeID :", "tail")
# print(Writer.index.items())
Writer.write_index()
return
def index(pathIn, pathOut, max_idx=10000, idx_len=8, verbose=False, comp_str=-1):
"""
Convert an mzml file (can be gzipped) into an indexed, gzipped mzML file.
Arguments:
pathIn (str): path to input File.
pathOut (str): path were output should be created.
Keyword Arguments:
max_idx (int): number of indexes which can be saved.
idx_len (int): character len of on key
verbose (boolean): print progress while parsing input.
comp_str(int): compression strength of zlib compression,
needs to be 1 <= x <= 9
"""
import gzip
with GSGW(
output_path=pathOut,
max_idx_len=idx_len,
max_offset_len=idx_len,
comp_str=comp_str,
) as Writer:
with gzip.open(pathIn, "rt") as Reader:
data = ""
for line in Reader:
if line.strip().startswith("</spectrum>"):
data += line
Writer.add_data(data, nativeID)
if verbose:
pass
data = ""
elif line.strip().startswith("<spectrum "):
data += line
lineID = re.search(regex_patterns.SPECTRUM_TAG_PATTERN, line).group(
"index"
)
nativeID = int(
regex_patterns.SPECTRUM_ID_PATTERN.search(lineID).group(0)
)
elif line.strip().startswith("<chromatogram "):
data += line
nativeID = re.search(
regex_patterns.CHROMATOGRAM_ID_PATTERN, line
).group(1)
elif line.strip().startswith("<spectrumL"):
data += line
Writer.add_data(data, "Head")
if verbose:
print("NativeID :", "Head")
data = ""
elif line.strip().startswith("<chromatogramL"):
data += line
Writer.add_data(data, "junk")
if verbose:
print("NativeID :", "junk")
data = ""
elif line.strip().startswith("</chromatogram>"):
data += line
Writer.add_data(data, nativeID)
if verbose:
print("found chromo")
print("NativeID :", nativeID, end="\r")
data = ""
else:
data += line
if data:
Writer.add_data(data, "tail")
if verbose:
print("NativeID :", "tail")
Writer.write_index()
def make_obo_mapping(obo, reversed=False):
# NOT sure what this is for ...
mapping = {}
with open(obo) as obo_file:
for line in obo_file:
if line.startswith("id: "):
id = line.split()[-1]
elif line.startswith("name: "):
mapping[id] = " ".join(line.split()[1:])
if reversed:
mapping = {y: x for x, y in mapping.items()}
return mapping
if __name__ == "__main__":
print(__doc__)
|
