forked from docarray/docarray
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathhelper.py
More file actions
309 lines (240 loc) · 8.57 KB
/
helper.py
File metadata and controls
309 lines (240 loc) · 8.57 KB
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
306
307
308
309
import os
import random
import sys
import uuid
import warnings
from typing import Any, Dict, Optional, Sequence
__windows__ = sys.platform == 'win32'
__resources_path__ = os.path.join(
os.path.dirname(
sys.modules.get('docarray').__file__ if 'docarray' in sys.modules else __file__
),
'resources',
)
def typename(obj):
"""
Get the typename of object.
:param obj: Target object.
:return: Typename of the obj.
"""
if not isinstance(obj, type):
obj = obj.__class__
try:
return f'{obj.__module__}.{obj.__name__}'
except AttributeError:
return str(obj)
def deprecate_by(new_fn):
"""A helper function to label deprecated function
Usage: old_fn_name = deprecate_by(new_fn)
:param new_fn: the new function
:return: a wrapped function with old function name
"""
def _f(*args, **kwargs):
import inspect
old_fn_name = inspect.stack()[1][4][0].strip().split("=")[0].strip()
warnings.warn(
f'`{old_fn_name}` is renamed to `{new_fn.__name__}` with the same usage, please use the latter instead. '
f'The old function will be removed soon.',
DeprecationWarning,
)
return new_fn(*args, **kwargs)
return _f
def dunder_get(_dict: Any, key: str) -> Any:
"""Returns value for a specified dunderkey
A "dunderkey" is just a fieldname that may or may not contain
double underscores (dunderscores!) for referencing nested keys in
a dict. eg::
>>> data = {'a': {'b': 1}}
>>> dunder_get(data, 'a__b')
1
key 'b' can be referrenced as 'a__b'
:param _dict : (dict, list, struct or object) which we want to index into
:param key : (str) that represents a first level or nested key in the dict
:return: (mixed) value corresponding to the key
"""
if not _dict:
return None
try:
part1, part2 = key.split('__', 1)
except ValueError:
part1, part2 = key, ''
try:
part1 = int(part1) # parse int parameter
except ValueError:
pass
if isinstance(part1, int):
result = _dict[part1]
elif isinstance(_dict, dict):
if part1 in _dict:
result = _dict[part1]
else:
result = None
elif isinstance(_dict, Sequence):
result = _dict[part1]
else:
result = getattr(_dict, part1)
return dunder_get(result, part2) if part2 else result
def random_identity(use_uuid1: bool = False) -> str:
"""
Generate random UUID.
..note::
A MAC address or time-based ordering (UUID1) can afford increased database performance, since it's less work
to sort numbers closer-together than those distributed randomly (UUID4) (see here).
A second related issue, is that using UUID1 can be useful in debugging, even if origin data is lost or not
explicitly stored.
:param use_uuid1: use UUID1 instead of UUID4. This is the default Document ID generator.
:return: A random UUID.
"""
return random_uuid(use_uuid1).hex
def random_uuid(use_uuid1: bool = False) -> uuid.UUID:
"""
Get a random UUID.
:param use_uuid1: Use UUID1 if True, else use UUID4.
:return: A random UUID.
"""
return uuid.uuid1() if use_uuid1 else uuid.uuid4()
def download_mermaid_url(mermaid_url, output) -> None:
"""
Download the jpg image from mermaid_url.
:param mermaid_url: The URL of the image.
:param output: A filename specifying the name of the image to be created, the suffix svg/jpg determines the file type of the output image.
"""
from urllib.request import Request, urlopen
try:
req = Request(mermaid_url, headers={'User-Agent': 'Mozilla/5.0'})
with open(output, 'wb') as fp:
fp.write(urlopen(req).read())
except:
raise RuntimeError('Invalid or too-complicated graph')
def get_request_header() -> Dict:
"""Return the header of request.
:return: request header
"""
return {k: str(v) for k, v in get_full_version().items()}
def get_full_version() -> Dict:
"""
Get the version of libraries used in Jina and environment variables.
:return: Version information and environment variables
"""
import google.protobuf, platform
from . import __version__
from google.protobuf.internal import api_implementation
from uuid import getnode
return {
'docarray': __version__,
'protobuf': google.protobuf.__version__,
'proto-backend': api_implementation._default_implementation_type,
'python': platform.python_version(),
'platform': platform.system(),
'platform-release': platform.release(),
'platform-version': platform.version(),
'architecture': platform.machine(),
'processor': platform.processor(),
'uid': getnode(),
'session-id': str(random_uuid(use_uuid1=True)),
}
def random_port() -> Optional[int]:
"""
Get a random available port number from '49153' to '65535'.
:return: A random port.
"""
import threading
import multiprocessing
from contextlib import closing
import socket
def _get_port(port=0):
with multiprocessing.Lock():
with threading.Lock():
with closing(socket.socket(socket.AF_INET, socket.SOCK_STREAM)) as s:
try:
s.bind(('', port))
s.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
return s.getsockname()[1]
except OSError:
pass
_port = None
if 'JINA_RANDOM_PORT_MIN' in os.environ or 'JINA_RANDOM_PORT_MAX' in os.environ:
min_port = int(os.environ.get('JINA_RANDOM_PORT_MIN', '49153'))
max_port = int(os.environ.get('JINA_RANDOM_PORT_MAX', '65535'))
all_ports = list(range(min_port, max_port + 1))
random.shuffle(all_ports)
for _port in all_ports:
if _get_port(_port) is not None:
break
else:
raise OSError(
f'can not find an available port between [{min_port}, {max_port}].'
)
else:
_port = _get_port()
return int(_port)
class cached_property:
"""The decorator to cache property of a class."""
def __init__(self, func):
"""
Create the :class:`cached_property`.
:param func: Cached function.
"""
self.func = func
def __get__(self, obj, cls):
cached_value = obj.__dict__.get(f'CACHED_{self.func.__name__}', None)
if cached_value is not None:
return cached_value
value = obj.__dict__[f'CACHED_{self.func.__name__}'] = self.func(obj)
return value
def __delete__(self, obj):
cached_value = obj.__dict__.get(f'CACHED_{self.func.__name__}', None)
if cached_value is not None:
if hasattr(cached_value, 'close'):
cached_value.close()
del obj.__dict__[f'CACHED_{self.func.__name__}']
def compress_bytes(data: bytes, algorithm: Optional[str] = None) -> bytes:
if algorithm == 'lz4':
import lz4.frame
data = lz4.frame.compress(data)
elif algorithm == 'bz2':
import bz2
data = bz2.compress(data)
elif algorithm == 'lzma':
import lzma
data = lzma.compress(data)
elif algorithm == 'zlib':
import zlib
data = zlib.compress(data)
elif algorithm == 'gzip':
import gzip
data = gzip.compress(data)
return data
def decompress_bytes(data: bytes, algorithm: Optional[str] = None) -> bytes:
if algorithm == 'lz4':
import lz4.frame
data = lz4.frame.decompress(data)
elif algorithm == 'bz2':
import bz2
data = bz2.decompress(data)
elif algorithm == 'lzma':
import lzma
data = lzma.decompress(data)
elif algorithm == 'zlib':
import zlib
data = zlib.decompress(data)
elif algorithm == 'gzip':
import gzip
data = gzip.decompress(data)
return data
def get_compress_ctx(algorithm: Optional[str] = None, mode: str = 'wb'):
if algorithm == 'lz4':
import lz4.frame
compress_ctx = lambda x: lz4.frame.LZ4FrameFile(x, mode)
elif algorithm == 'gzip':
import gzip
compress_ctx = lambda x: gzip.GzipFile(fileobj=x, mode=mode)
elif algorithm == 'bz2':
import bz2
compress_ctx = lambda x: bz2.BZ2File(x, mode)
elif algorithm == 'lzma':
import lzma
compress_ctx = lambda x: lzma.LZMAFile(x, mode)
else:
compress_ctx = None
return compress_ctx