virtuals-binary-codec 0.1.0__cp313-cp313-macosx_11_0_arm64.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- virtuals_binary_codec/__init__.py +15 -0
- virtuals_binary_codec/binary_codec.cpython-313-darwin.so +0 -0
- virtuals_binary_codec/binary_codec.pyi +14 -0
- virtuals_binary_codec/binary_codec.pyx +344 -0
- virtuals_binary_codec/exceptions.py +50 -0
- virtuals_binary_codec-0.1.0.dist-info/METADATA +63 -0
- virtuals_binary_codec-0.1.0.dist-info/RECORD +10 -0
- virtuals_binary_codec-0.1.0.dist-info/WHEEL +6 -0
- virtuals_binary_codec-0.1.0.dist-info/licenses/LICENSE +201 -0
- virtuals_binary_codec-0.1.0.dist-info/top_level.txt +1 -0
|
@@ -0,0 +1,15 @@
|
|
|
1
|
+
"""Cython-optimized binary key codec for Virtuals."""
|
|
2
|
+
|
|
3
|
+
from __future__ import annotations
|
|
4
|
+
|
|
5
|
+
from .binary_codec import BinaryKeyCodec
|
|
6
|
+
from .exceptions import DecodeError, EncodeError, IntegerOverflowError, KeyCodecError
|
|
7
|
+
|
|
8
|
+
|
|
9
|
+
__all__ = [
|
|
10
|
+
"BinaryKeyCodec",
|
|
11
|
+
"DecodeError",
|
|
12
|
+
"EncodeError",
|
|
13
|
+
"IntegerOverflowError",
|
|
14
|
+
"KeyCodecError",
|
|
15
|
+
]
|
|
Binary file
|
|
@@ -0,0 +1,14 @@
|
|
|
1
|
+
"""Type stubs for binary_codec Cython extension."""
|
|
2
|
+
|
|
3
|
+
__all__ = ["BinaryKeyCodec"]
|
|
4
|
+
|
|
5
|
+
class BinaryKeyCodec:
|
|
6
|
+
"""Binary key codec that preserves lexicographic ordering."""
|
|
7
|
+
|
|
8
|
+
def encode(self, key: tuple[str | int, ...]) -> bytes:
|
|
9
|
+
"""Encode tuple key into binary format preserving lexicographic order."""
|
|
10
|
+
...
|
|
11
|
+
|
|
12
|
+
def decode(self, encoded: bytes) -> tuple[str | int, ...]:
|
|
13
|
+
"""Decode binary data back to original tuple key."""
|
|
14
|
+
...
|
|
@@ -0,0 +1,344 @@
|
|
|
1
|
+
# cython: language_level=3
|
|
2
|
+
# cython: boundscheck=False
|
|
3
|
+
# cython: wraparound=False
|
|
4
|
+
# cython: cdivision=True
|
|
5
|
+
# cython: initializedcheck=False
|
|
6
|
+
# cython: nonecheck=False
|
|
7
|
+
# cython: overflowcheck=False
|
|
8
|
+
"""Optimized Cython implementation of binary key codec."""
|
|
9
|
+
|
|
10
|
+
from libc.stdint cimport int64_t, uint64_t, INT64_MIN, INT64_MAX
|
|
11
|
+
from libc.string cimport memcpy
|
|
12
|
+
from cpython.bytes cimport PyBytes_FromStringAndSize, PyBytes_AS_STRING, PyBytes_GET_SIZE
|
|
13
|
+
from cpython.unicode cimport PyUnicode_AsUTF8String, PyUnicode_DecodeUTF8
|
|
14
|
+
|
|
15
|
+
from .exceptions import (
|
|
16
|
+
IntegerOverflowError,
|
|
17
|
+
EncodeError,
|
|
18
|
+
DecodeError,
|
|
19
|
+
)
|
|
20
|
+
|
|
21
|
+
# Type markers for lexicographic ordering (int < str)
|
|
22
|
+
cdef unsigned char TYPE_INT = 0x01
|
|
23
|
+
cdef unsigned char TYPE_STR = 0x02
|
|
24
|
+
|
|
25
|
+
# Component terminator - using null byte (0x00) to ensure shorter strings sort before
|
|
26
|
+
# longer strings with the same prefix. This is critical for lexicographic ordering.
|
|
27
|
+
cdef unsigned char TERMINATOR = 0x00
|
|
28
|
+
|
|
29
|
+
# Escape byte for null bytes within string content
|
|
30
|
+
# String encoding: \x00 in content -> \x00\xff (escaped), terminator is bare \x00
|
|
31
|
+
cdef unsigned char ESCAPE_BYTE = 0xFF
|
|
32
|
+
|
|
33
|
+
# Integer range constants
|
|
34
|
+
cdef int64_t INT64_MIN_VAL = INT64_MIN
|
|
35
|
+
cdef int64_t INT64_MAX_VAL = INT64_MAX
|
|
36
|
+
cdef uint64_t INT64_BIAS = 0x8000000000000000ULL # 2^63
|
|
37
|
+
|
|
38
|
+
# String constraints
|
|
39
|
+
cdef size_t MAX_STRING_LENGTH = 10 * 1024 * 1024 # 10MB
|
|
40
|
+
|
|
41
|
+
|
|
42
|
+
cdef inline void encode_integer_inline(int64_t value, unsigned char* buffer) noexcept nogil:
|
|
43
|
+
"""Encode integer using bias/offset encoding directly into buffer.
|
|
44
|
+
|
|
45
|
+
Args:
|
|
46
|
+
value: Integer to encode (must be in int64 range)
|
|
47
|
+
buffer: Output buffer (must have at least 8 bytes available)
|
|
48
|
+
"""
|
|
49
|
+
cdef uint64_t biased_value = <uint64_t>(value + <int64_t>INT64_BIAS)
|
|
50
|
+
|
|
51
|
+
# Write as big-endian (most significant byte first)
|
|
52
|
+
buffer[0] = <unsigned char>((biased_value >> 56) & 0xFF)
|
|
53
|
+
buffer[1] = <unsigned char>((biased_value >> 48) & 0xFF)
|
|
54
|
+
buffer[2] = <unsigned char>((biased_value >> 40) & 0xFF)
|
|
55
|
+
buffer[3] = <unsigned char>((biased_value >> 32) & 0xFF)
|
|
56
|
+
buffer[4] = <unsigned char>((biased_value >> 24) & 0xFF)
|
|
57
|
+
buffer[5] = <unsigned char>((biased_value >> 16) & 0xFF)
|
|
58
|
+
buffer[6] = <unsigned char>((biased_value >> 8) & 0xFF)
|
|
59
|
+
buffer[7] = <unsigned char>(biased_value & 0xFF)
|
|
60
|
+
|
|
61
|
+
|
|
62
|
+
cdef inline int64_t decode_integer_inline(const unsigned char* buffer) noexcept nogil:
|
|
63
|
+
"""Decode integer from buffer using bias/offset encoding.
|
|
64
|
+
|
|
65
|
+
Args:
|
|
66
|
+
buffer: Input buffer (must have at least 8 bytes)
|
|
67
|
+
|
|
68
|
+
Returns:
|
|
69
|
+
Decoded integer value
|
|
70
|
+
"""
|
|
71
|
+
cdef uint64_t biased_value = (
|
|
72
|
+
(<uint64_t>buffer[0] << 56) |
|
|
73
|
+
(<uint64_t>buffer[1] << 48) |
|
|
74
|
+
(<uint64_t>buffer[2] << 40) |
|
|
75
|
+
(<uint64_t>buffer[3] << 32) |
|
|
76
|
+
(<uint64_t>buffer[4] << 24) |
|
|
77
|
+
(<uint64_t>buffer[5] << 16) |
|
|
78
|
+
(<uint64_t>buffer[6] << 8) |
|
|
79
|
+
<uint64_t>buffer[7]
|
|
80
|
+
)
|
|
81
|
+
|
|
82
|
+
# Remove bias to get original signed value
|
|
83
|
+
return <int64_t>(biased_value - INT64_BIAS)
|
|
84
|
+
|
|
85
|
+
|
|
86
|
+
cdef inline Py_ssize_t count_null_bytes(const unsigned char* data, Py_ssize_t length) noexcept nogil:
|
|
87
|
+
"""Count null bytes in data for calculating escaped size."""
|
|
88
|
+
cdef Py_ssize_t count = 0
|
|
89
|
+
cdef Py_ssize_t i
|
|
90
|
+
for i in range(length):
|
|
91
|
+
if data[i] == 0x00:
|
|
92
|
+
count += 1
|
|
93
|
+
return count
|
|
94
|
+
|
|
95
|
+
|
|
96
|
+
cdef inline Py_ssize_t copy_with_escape(unsigned char* dest, const unsigned char* src, Py_ssize_t length) noexcept nogil:
|
|
97
|
+
r"""Copy source to dest, escaping null bytes (\x00 -> \x00\xff).
|
|
98
|
+
|
|
99
|
+
Returns the number of bytes written to dest.
|
|
100
|
+
"""
|
|
101
|
+
cdef Py_ssize_t dest_pos = 0
|
|
102
|
+
cdef Py_ssize_t i
|
|
103
|
+
for i in range(length):
|
|
104
|
+
dest[dest_pos] = src[i]
|
|
105
|
+
dest_pos += 1
|
|
106
|
+
if src[i] == 0x00:
|
|
107
|
+
dest[dest_pos] = ESCAPE_BYTE
|
|
108
|
+
dest_pos += 1
|
|
109
|
+
return dest_pos
|
|
110
|
+
|
|
111
|
+
|
|
112
|
+
cdef class BinaryKeyCodec:
|
|
113
|
+
"""Optimized binary key codec that preserves lexicographic ordering.
|
|
114
|
+
|
|
115
|
+
This Cython implementation provides maximum performance for encoding and
|
|
116
|
+
decoding tuple keys into binary format while maintaining sort order.
|
|
117
|
+
|
|
118
|
+
Features:
|
|
119
|
+
- Zero Python overhead in hot paths
|
|
120
|
+
- Direct memory operations
|
|
121
|
+
- Inline integer encoding/decoding
|
|
122
|
+
- Efficient buffer management
|
|
123
|
+
- Preserves lexicographic ordering
|
|
124
|
+
- Uses null byte (0x00) terminator with escaping for correct string ordering
|
|
125
|
+
|
|
126
|
+
Encoding format:
|
|
127
|
+
- Each component: TYPE_MARKER + ENCODED_VALUE + TERMINATOR
|
|
128
|
+
- Integers: TYPE_INT (0x01) + 8_BYTES + TERMINATOR (0x00)
|
|
129
|
+
- Strings: TYPE_STR (0x02) + ESCAPED_UTF8_BYTES + TERMINATOR (0x00)
|
|
130
|
+
|
|
131
|
+
String escaping:
|
|
132
|
+
- Null bytes in content: 0x00 -> 0x00 0xFF (escaped)
|
|
133
|
+
- Terminator is bare 0x00 (not escaped)
|
|
134
|
+
- This ensures shorter strings sort before longer strings with same prefix
|
|
135
|
+
"""
|
|
136
|
+
|
|
137
|
+
def encode(self, tuple key):
|
|
138
|
+
"""Encode tuple key into binary format preserving lexicographic order.
|
|
139
|
+
|
|
140
|
+
Args:
|
|
141
|
+
key: Tuple containing strings and/or integers
|
|
142
|
+
|
|
143
|
+
Returns:
|
|
144
|
+
Binary encoded key (bytes)
|
|
145
|
+
|
|
146
|
+
Raises:
|
|
147
|
+
IntegerOverflowError: If integer is outside int64 range
|
|
148
|
+
EncodeError: If encoding fails
|
|
149
|
+
"""
|
|
150
|
+
if not key:
|
|
151
|
+
raise EncodeError("Empty tuple not allowed as key")
|
|
152
|
+
|
|
153
|
+
cdef Py_ssize_t num_components = len(key)
|
|
154
|
+
cdef Py_ssize_t i
|
|
155
|
+
cdef object component
|
|
156
|
+
cdef int64_t int_val
|
|
157
|
+
cdef bytes str_bytes
|
|
158
|
+
cdef const unsigned char* str_data
|
|
159
|
+
cdef Py_ssize_t str_len
|
|
160
|
+
cdef Py_ssize_t null_count
|
|
161
|
+
|
|
162
|
+
# First pass: calculate exact size (accounting for null byte escaping)
|
|
163
|
+
cdef Py_ssize_t total_size = 0
|
|
164
|
+
for i in range(num_components):
|
|
165
|
+
component = key[i]
|
|
166
|
+
|
|
167
|
+
if isinstance(component, int):
|
|
168
|
+
# Check bounds
|
|
169
|
+
try:
|
|
170
|
+
int_val = <int64_t>component
|
|
171
|
+
except OverflowError:
|
|
172
|
+
raise IntegerOverflowError(component)
|
|
173
|
+
|
|
174
|
+
if int_val < INT64_MIN_VAL or int_val > INT64_MAX_VAL:
|
|
175
|
+
raise IntegerOverflowError(int_val, INT64_MIN_VAL, INT64_MAX_VAL)
|
|
176
|
+
total_size += 1 + 8 + 1 # type + 8 bytes + terminator
|
|
177
|
+
|
|
178
|
+
elif isinstance(component, str):
|
|
179
|
+
str_bytes = PyUnicode_AsUTF8String(component)
|
|
180
|
+
str_data = <const unsigned char*>PyBytes_AS_STRING(str_bytes)
|
|
181
|
+
str_len = PyBytes_GET_SIZE(str_bytes)
|
|
182
|
+
|
|
183
|
+
# Check string length bounds
|
|
184
|
+
if str_len == 0:
|
|
185
|
+
raise EncodeError(f"Empty string at index {i} not allowed")
|
|
186
|
+
if str_len > MAX_STRING_LENGTH:
|
|
187
|
+
raise EncodeError(
|
|
188
|
+
f"String at index {i} too long: {str_len} bytes "
|
|
189
|
+
f"(max {MAX_STRING_LENGTH})"
|
|
190
|
+
)
|
|
191
|
+
|
|
192
|
+
# Count null bytes for escape sizing
|
|
193
|
+
null_count = count_null_bytes(str_data, str_len)
|
|
194
|
+
# type + utf8 bytes + escape bytes for nulls + terminator
|
|
195
|
+
total_size += 1 + str_len + null_count + 1
|
|
196
|
+
else:
|
|
197
|
+
raise EncodeError(
|
|
198
|
+
f"Component at index {i} must be str or int, "
|
|
199
|
+
f"got {type(component).__name__}"
|
|
200
|
+
)
|
|
201
|
+
|
|
202
|
+
# Allocate output buffer
|
|
203
|
+
cdef bytes result = PyBytes_FromStringAndSize(NULL, total_size)
|
|
204
|
+
cdef unsigned char* buffer = <unsigned char*>PyBytes_AS_STRING(result)
|
|
205
|
+
cdef Py_ssize_t pos = 0
|
|
206
|
+
|
|
207
|
+
# Second pass: encode into buffer
|
|
208
|
+
for i in range(num_components):
|
|
209
|
+
component = key[i]
|
|
210
|
+
|
|
211
|
+
if isinstance(component, int):
|
|
212
|
+
int_val = <int64_t>component
|
|
213
|
+
|
|
214
|
+
# Write type marker
|
|
215
|
+
buffer[pos] = TYPE_INT
|
|
216
|
+
pos += 1
|
|
217
|
+
|
|
218
|
+
# Encode integer
|
|
219
|
+
encode_integer_inline(int_val, &buffer[pos])
|
|
220
|
+
pos += 8
|
|
221
|
+
|
|
222
|
+
# Write terminator
|
|
223
|
+
buffer[pos] = TERMINATOR
|
|
224
|
+
pos += 1
|
|
225
|
+
|
|
226
|
+
else: # isinstance(component, str)
|
|
227
|
+
str_bytes = PyUnicode_AsUTF8String(component)
|
|
228
|
+
str_data = <const unsigned char*>PyBytes_AS_STRING(str_bytes)
|
|
229
|
+
str_len = PyBytes_GET_SIZE(str_bytes)
|
|
230
|
+
|
|
231
|
+
# Write type marker
|
|
232
|
+
buffer[pos] = TYPE_STR
|
|
233
|
+
pos += 1
|
|
234
|
+
|
|
235
|
+
# Copy string bytes with null byte escaping
|
|
236
|
+
pos += copy_with_escape(&buffer[pos], str_data, str_len)
|
|
237
|
+
|
|
238
|
+
# Write terminator
|
|
239
|
+
buffer[pos] = TERMINATOR
|
|
240
|
+
pos += 1
|
|
241
|
+
|
|
242
|
+
return result
|
|
243
|
+
|
|
244
|
+
def decode(self, bytes encoded):
|
|
245
|
+
"""Decode binary data back to original tuple key.
|
|
246
|
+
|
|
247
|
+
Args:
|
|
248
|
+
encoded: Previously encoded binary key
|
|
249
|
+
|
|
250
|
+
Returns:
|
|
251
|
+
Original tuple key
|
|
252
|
+
|
|
253
|
+
Raises:
|
|
254
|
+
DecodeError: If data is invalid or corrupted
|
|
255
|
+
"""
|
|
256
|
+
if not encoded:
|
|
257
|
+
raise DecodeError("Empty encoded key")
|
|
258
|
+
|
|
259
|
+
cdef const unsigned char* data = <const unsigned char*>PyBytes_AS_STRING(encoded)
|
|
260
|
+
cdef Py_ssize_t data_len = PyBytes_GET_SIZE(encoded)
|
|
261
|
+
cdef Py_ssize_t pos = 0
|
|
262
|
+
|
|
263
|
+
cdef list result = []
|
|
264
|
+
cdef unsigned char type_marker
|
|
265
|
+
cdef int64_t int_val
|
|
266
|
+
cdef Py_ssize_t str_start, str_end
|
|
267
|
+
cdef bytes str_bytes
|
|
268
|
+
cdef str decoded_str
|
|
269
|
+
|
|
270
|
+
while pos < data_len:
|
|
271
|
+
# Read type marker
|
|
272
|
+
if pos >= data_len:
|
|
273
|
+
raise DecodeError("Unexpected end of data while reading type marker")
|
|
274
|
+
|
|
275
|
+
type_marker = data[pos]
|
|
276
|
+
pos += 1
|
|
277
|
+
|
|
278
|
+
if type_marker == TYPE_INT:
|
|
279
|
+
# Check we have enough bytes for integer
|
|
280
|
+
if pos + 8 > data_len:
|
|
281
|
+
raise DecodeError(
|
|
282
|
+
f"Insufficient bytes for integer at offset {pos - 1}"
|
|
283
|
+
)
|
|
284
|
+
|
|
285
|
+
# Decode integer
|
|
286
|
+
int_val = decode_integer_inline(&data[pos])
|
|
287
|
+
result.append(int_val)
|
|
288
|
+
pos += 8
|
|
289
|
+
|
|
290
|
+
# Check terminator
|
|
291
|
+
if pos >= data_len or data[pos] != TERMINATOR:
|
|
292
|
+
raise DecodeError(
|
|
293
|
+
f"Missing terminator after integer at position {pos}"
|
|
294
|
+
)
|
|
295
|
+
pos += 1
|
|
296
|
+
|
|
297
|
+
elif type_marker == TYPE_STR:
|
|
298
|
+
# Find next UNESCAPED terminator (bare \x00, not \x00\xff)
|
|
299
|
+
str_start = pos
|
|
300
|
+
str_end = -1
|
|
301
|
+
|
|
302
|
+
while pos < data_len:
|
|
303
|
+
if data[pos] == TERMINATOR:
|
|
304
|
+
# Check if this is an escaped null (\x00\xff) or real terminator
|
|
305
|
+
if pos + 1 < data_len and data[pos + 1] == ESCAPE_BYTE:
|
|
306
|
+
# This is an escaped null byte, skip both bytes
|
|
307
|
+
pos += 2
|
|
308
|
+
else:
|
|
309
|
+
# This is the real terminator
|
|
310
|
+
str_end = pos
|
|
311
|
+
break
|
|
312
|
+
else:
|
|
313
|
+
pos += 1
|
|
314
|
+
|
|
315
|
+
if str_end == -1:
|
|
316
|
+
raise DecodeError(
|
|
317
|
+
f"Missing terminator after string at position {str_start - 1}"
|
|
318
|
+
)
|
|
319
|
+
|
|
320
|
+
# Get escaped string bytes and unescape them
|
|
321
|
+
str_bytes = encoded[str_start:str_end]
|
|
322
|
+
# Unescape: \x00\xff -> \x00
|
|
323
|
+
str_bytes = str_bytes.replace(b"\x00\xff", b"\x00")
|
|
324
|
+
try:
|
|
325
|
+
decoded_str = PyUnicode_DecodeUTF8(
|
|
326
|
+
PyBytes_AS_STRING(str_bytes),
|
|
327
|
+
PyBytes_GET_SIZE(str_bytes),
|
|
328
|
+
NULL # Use default error handling (strict)
|
|
329
|
+
)
|
|
330
|
+
result.append(decoded_str)
|
|
331
|
+
except UnicodeDecodeError as e:
|
|
332
|
+
raise DecodeError(f"Invalid UTF-8 in encoded string: {e}")
|
|
333
|
+
|
|
334
|
+
pos = str_end + 1
|
|
335
|
+
|
|
336
|
+
else:
|
|
337
|
+
raise DecodeError(
|
|
338
|
+
f"Invalid type marker at position {pos - 1}: 0x{type_marker:02x}"
|
|
339
|
+
)
|
|
340
|
+
|
|
341
|
+
return tuple(result)
|
|
342
|
+
|
|
343
|
+
|
|
344
|
+
__all__ = ['BinaryKeyCodec']
|
|
@@ -0,0 +1,50 @@
|
|
|
1
|
+
"""Exception classes for binary key codec."""
|
|
2
|
+
|
|
3
|
+
from __future__ import annotations
|
|
4
|
+
|
|
5
|
+
|
|
6
|
+
__all__ = [
|
|
7
|
+
"DecodeError",
|
|
8
|
+
"EncodeError",
|
|
9
|
+
"IntegerOverflowError",
|
|
10
|
+
"KeyCodecError",
|
|
11
|
+
]
|
|
12
|
+
|
|
13
|
+
|
|
14
|
+
class KeyCodecError(Exception):
|
|
15
|
+
"""Base exception for all key codec errors."""
|
|
16
|
+
|
|
17
|
+
pass
|
|
18
|
+
|
|
19
|
+
|
|
20
|
+
class EncodeError(KeyCodecError):
|
|
21
|
+
"""Raised when encoding a key fails."""
|
|
22
|
+
|
|
23
|
+
pass
|
|
24
|
+
|
|
25
|
+
|
|
26
|
+
class DecodeError(KeyCodecError):
|
|
27
|
+
"""Raised when decoding an encoded key fails."""
|
|
28
|
+
|
|
29
|
+
pass
|
|
30
|
+
|
|
31
|
+
|
|
32
|
+
class IntegerOverflowError(EncodeError):
|
|
33
|
+
"""Raised when an integer value exceeds the codec's supported range."""
|
|
34
|
+
|
|
35
|
+
def __init__( # noqa: D107
|
|
36
|
+
self,
|
|
37
|
+
value: int | None = None,
|
|
38
|
+
min_value: int | None = None,
|
|
39
|
+
max_value: int | None = None,
|
|
40
|
+
) -> None:
|
|
41
|
+
if value is not None:
|
|
42
|
+
self.value = value
|
|
43
|
+
self.min_value = min_value
|
|
44
|
+
self.max_value = max_value
|
|
45
|
+
super().__init__(
|
|
46
|
+
f"Integer {value} out of supported range"
|
|
47
|
+
f"{f' [{min_value}, {max_value}]' if min_value is not None and max_value is not None else ''}"
|
|
48
|
+
)
|
|
49
|
+
else:
|
|
50
|
+
super().__init__("Integer value out of supported range")
|
|
@@ -0,0 +1,63 @@
|
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: virtuals-binary-codec
|
|
3
|
+
Version: 0.1.0
|
|
4
|
+
Summary: Cython-optimized binary key codec for Virtuals.
|
|
5
|
+
Author-email: Gor Arakelyan <gorarkln@gmail.com>
|
|
6
|
+
License-Expression: Apache-2.0
|
|
7
|
+
Project-URL: Homepage, https://github.com/nustackdev/virtuals
|
|
8
|
+
Project-URL: Repository, https://github.com/nustackdev/virtuals
|
|
9
|
+
Project-URL: Issues, https://github.com/nustackdev/virtuals/issues
|
|
10
|
+
Project-URL: PyPI, https://pypi.org/project/virtuals-binary-codec/
|
|
11
|
+
Keywords: virtuals,codec,binary,cython,key-value
|
|
12
|
+
Classifier: Development Status :: 3 - Alpha
|
|
13
|
+
Classifier: Intended Audience :: Developers
|
|
14
|
+
Classifier: Operating System :: OS Independent
|
|
15
|
+
Classifier: Programming Language :: Python :: 3
|
|
16
|
+
Classifier: Programming Language :: Python :: 3.10
|
|
17
|
+
Classifier: Programming Language :: Python :: 3.11
|
|
18
|
+
Classifier: Programming Language :: Python :: 3.12
|
|
19
|
+
Classifier: Programming Language :: Python :: 3.13
|
|
20
|
+
Classifier: Programming Language :: Python :: 3.14
|
|
21
|
+
Classifier: Programming Language :: Python :: Implementation :: CPython
|
|
22
|
+
Classifier: Programming Language :: Cython
|
|
23
|
+
Classifier: Topic :: Software Development :: Libraries :: Python Modules
|
|
24
|
+
Requires-Python: >=3.10
|
|
25
|
+
Description-Content-Type: text/markdown
|
|
26
|
+
License-File: LICENSE
|
|
27
|
+
Provides-Extra: dev
|
|
28
|
+
Requires-Dist: Cython>=3.0.0; extra == "dev"
|
|
29
|
+
Requires-Dist: setuptools>=68.0; extra == "dev"
|
|
30
|
+
Provides-Extra: test
|
|
31
|
+
Requires-Dist: pytest>=7.0.0; extra == "test"
|
|
32
|
+
Dynamic: license-file
|
|
33
|
+
|
|
34
|
+
# virtuals-binary-codec
|
|
35
|
+
|
|
36
|
+
Cython-optimized binary key codec for [Virtuals](https://github.com/nustackdev/virtuals).
|
|
37
|
+
|
|
38
|
+
Encodes tuple keys into binary format while preserving lexicographic ordering. Supports mixed integer and string components.
|
|
39
|
+
|
|
40
|
+
## Install
|
|
41
|
+
|
|
42
|
+
```
|
|
43
|
+
pip install virtuals-binary-codec
|
|
44
|
+
```
|
|
45
|
+
|
|
46
|
+
Or as part of Virtuals:
|
|
47
|
+
|
|
48
|
+
```
|
|
49
|
+
pip install virtuals-py[binary]
|
|
50
|
+
```
|
|
51
|
+
|
|
52
|
+
## Usage
|
|
53
|
+
|
|
54
|
+
```python
|
|
55
|
+
from virtuals_binary_codec import BinaryKeyCodec
|
|
56
|
+
|
|
57
|
+
codec = BinaryKeyCodec()
|
|
58
|
+
encoded = codec.encode(("users", 42, "profile"))
|
|
59
|
+
decoded = codec.decode(encoded)
|
|
60
|
+
assert decoded == ("users", 42, "profile")
|
|
61
|
+
```
|
|
62
|
+
|
|
63
|
+
Virtuals automatically uses this codec when installed. Without it, Virtuals falls back to a pure Python implementation.
|
|
@@ -0,0 +1,10 @@
|
|
|
1
|
+
virtuals_binary_codec-0.1.0.dist-info/RECORD,,
|
|
2
|
+
virtuals_binary_codec-0.1.0.dist-info/WHEEL,sha256=I7C6oPU9_YXUwpeWU-HCMP--1MGENZx31r2O4ozCW_U,136
|
|
3
|
+
virtuals_binary_codec-0.1.0.dist-info/top_level.txt,sha256=iKCXgp2qhJDwjutPb0DsG3nRmQjVzlXenDeG0R4sVvw,22
|
|
4
|
+
virtuals_binary_codec-0.1.0.dist-info/METADATA,sha256=l-0y9VYPxJs3lFkXEHjQE-NG4mz6bLoGEm8T_kAQHBQ,2133
|
|
5
|
+
virtuals_binary_codec-0.1.0.dist-info/licenses/LICENSE,sha256=aJSBYDIiIbyXAthmOf9iaKLLG70zXk_BfpY3y4BTYxM,11285
|
|
6
|
+
virtuals_binary_codec/binary_codec.pyi,sha256=uPwpKDrrZ8LAm_WXzv4T6mj895nY6SErH8Zxj3qyNQQ,462
|
|
7
|
+
virtuals_binary_codec/binary_codec.cpython-313-darwin.so,sha256=Z25ra9EY49mNkJWf4G7_AnaDQ55hq-H0Vu1gBwCLGg0,133776
|
|
8
|
+
virtuals_binary_codec/__init__.py,sha256=lRGQMw_zANauir6RAPc1A8cvmt_YnPrQooBJPqu1aU8,343
|
|
9
|
+
virtuals_binary_codec/binary_codec.pyx,sha256=50c_dw-tzhh6cmA5EFa5dQvspiONMYcrJXO3QSByoXI,12159
|
|
10
|
+
virtuals_binary_codec/exceptions.py,sha256=1TQt0HoeWZIuJaTBgl8jSPaCDoQMynAMiSywpC0ba0k,1195
|
|
@@ -0,0 +1,201 @@
|
|
|
1
|
+
Apache License
|
|
2
|
+
Version 2.0, January 2004
|
|
3
|
+
http://www.apache.org/licenses/
|
|
4
|
+
|
|
5
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
|
6
|
+
|
|
7
|
+
1. Definitions.
|
|
8
|
+
|
|
9
|
+
"License" shall mean the terms and conditions for use, reproduction,
|
|
10
|
+
and distribution as defined by Sections 1 through 9 of this document.
|
|
11
|
+
|
|
12
|
+
"Licensor" shall mean the copyright owner or entity authorized by
|
|
13
|
+
the copyright owner that is granting the License.
|
|
14
|
+
|
|
15
|
+
"Legal Entity" shall mean the union of the acting entity and all
|
|
16
|
+
other entities that control, are controlled by, or are under common
|
|
17
|
+
control with that entity. For the purposes of this definition,
|
|
18
|
+
"control" means (i) the power, direct or indirect, to cause the
|
|
19
|
+
direction or management of such entity, whether by contract or
|
|
20
|
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
|
21
|
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
|
22
|
+
|
|
23
|
+
"You" (or "Your") shall mean an individual or Legal Entity
|
|
24
|
+
exercising permissions granted by this License.
|
|
25
|
+
|
|
26
|
+
"Source" form shall mean the preferred form for making modifications,
|
|
27
|
+
including but not limited to software source code, documentation
|
|
28
|
+
source, and configuration files.
|
|
29
|
+
|
|
30
|
+
"Object" form shall mean any form resulting from mechanical
|
|
31
|
+
transformation or translation of a Source form, including but
|
|
32
|
+
not limited to compiled object code, generated documentation,
|
|
33
|
+
and conversions to other media types.
|
|
34
|
+
|
|
35
|
+
"Work" shall mean the work of authorship, whether in Source or
|
|
36
|
+
Object form, made available under the License, as indicated by a
|
|
37
|
+
copyright notice that is included in or attached to the work
|
|
38
|
+
(an example is provided in the Appendix below).
|
|
39
|
+
|
|
40
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
|
41
|
+
form, that is based on (or derived from) the Work and for which the
|
|
42
|
+
editorial revisions, annotations, elaborations, or other modifications
|
|
43
|
+
represent, as a whole, an original work of authorship. For the purposes
|
|
44
|
+
of this License, Derivative Works shall not include works that remain
|
|
45
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
|
46
|
+
the Work and Derivative Works thereof.
|
|
47
|
+
|
|
48
|
+
"Contribution" shall mean any work of authorship, including
|
|
49
|
+
the original version of the Work and any modifications or additions
|
|
50
|
+
to that Work or Derivative Works thereof, that is intentionally
|
|
51
|
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
|
52
|
+
or by an individual or Legal Entity authorized to submit on behalf of
|
|
53
|
+
the copyright owner. For the purposes of this definition, "submitted"
|
|
54
|
+
means any form of electronic, verbal, or written communication sent
|
|
55
|
+
to the Licensor or its representatives, including but not limited to
|
|
56
|
+
communication on electronic mailing lists, source code control systems,
|
|
57
|
+
and issue tracking systems that are managed by, or on behalf of, the
|
|
58
|
+
Licensor for the purpose of discussing and improving the Work, but
|
|
59
|
+
excluding communication that is conspicuously marked or otherwise
|
|
60
|
+
designated in writing by the copyright owner as "Not a Contribution."
|
|
61
|
+
|
|
62
|
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
|
63
|
+
on behalf of whom a Contribution has been received by Licensor and
|
|
64
|
+
subsequently incorporated within the Work.
|
|
65
|
+
|
|
66
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
|
67
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
68
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
69
|
+
copyright license to reproduce, prepare Derivative Works of,
|
|
70
|
+
publicly display, publicly perform, sublicense, and distribute the
|
|
71
|
+
Work and such Derivative Works in Source or Object form.
|
|
72
|
+
|
|
73
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
|
74
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
75
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
76
|
+
(except as stated in this section) patent license to make, have made,
|
|
77
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
|
78
|
+
where such license applies only to those patent claims licensable
|
|
79
|
+
by such Contributor that are necessarily infringed by their
|
|
80
|
+
Contribution(s) alone or by combination of their Contribution(s)
|
|
81
|
+
with the Work to which such Contribution(s) was submitted. If You
|
|
82
|
+
institute patent litigation against any entity (including a
|
|
83
|
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
|
84
|
+
or a Contribution incorporated within the Work constitutes direct
|
|
85
|
+
or contributory patent infringement, then any patent licenses
|
|
86
|
+
granted to You under this License for that Work shall terminate
|
|
87
|
+
as of the date such litigation is filed.
|
|
88
|
+
|
|
89
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
|
90
|
+
Work or Derivative Works thereof in any medium, with or without
|
|
91
|
+
modifications, and in Source or Object form, provided that You
|
|
92
|
+
meet the following conditions:
|
|
93
|
+
|
|
94
|
+
(a) You must give any other recipients of the Work or
|
|
95
|
+
Derivative Works a copy of this License; and
|
|
96
|
+
|
|
97
|
+
(b) You must cause any modified files to carry prominent notices
|
|
98
|
+
stating that You changed the files; and
|
|
99
|
+
|
|
100
|
+
(c) You must retain, in the Source form of any Derivative Works
|
|
101
|
+
that You distribute, all copyright, patent, trademark, and
|
|
102
|
+
attribution notices from the Source form of the Work,
|
|
103
|
+
excluding those notices that do not pertain to any part of
|
|
104
|
+
the Derivative Works; and
|
|
105
|
+
|
|
106
|
+
(d) If the Work includes a "NOTICE" text file as part of its
|
|
107
|
+
distribution, then any Derivative Works that You distribute must
|
|
108
|
+
include a readable copy of the attribution notices contained
|
|
109
|
+
within such NOTICE file, excluding those notices that do not
|
|
110
|
+
pertain to any part of the Derivative Works, in at least one
|
|
111
|
+
of the following places: within a NOTICE text file distributed
|
|
112
|
+
as part of the Derivative Works; within the Source form or
|
|
113
|
+
documentation, if provided along with the Derivative Works; or,
|
|
114
|
+
within a display generated by the Derivative Works, if and
|
|
115
|
+
wherever such third-party notices normally appear. The contents
|
|
116
|
+
of the NOTICE file are for informational purposes only and
|
|
117
|
+
do not modify the License. You may add Your own attribution
|
|
118
|
+
notices within Derivative Works that You distribute, alongside
|
|
119
|
+
or as an addendum to the NOTICE text from the Work, provided
|
|
120
|
+
that such additional attribution notices cannot be construed
|
|
121
|
+
as modifying the License.
|
|
122
|
+
|
|
123
|
+
You may add Your own copyright statement to Your modifications and
|
|
124
|
+
may provide additional or different license terms and conditions
|
|
125
|
+
for use, reproduction, or distribution of Your modifications, or
|
|
126
|
+
for any such Derivative Works as a whole, provided Your use,
|
|
127
|
+
reproduction, and distribution of the Work otherwise complies with
|
|
128
|
+
the conditions stated in this License.
|
|
129
|
+
|
|
130
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
|
131
|
+
any Contribution intentionally submitted for inclusion in the Work
|
|
132
|
+
by You to the Licensor shall be under the terms and conditions of
|
|
133
|
+
this License, without any additional terms or conditions.
|
|
134
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
|
135
|
+
the terms of any separate license agreement you may have executed
|
|
136
|
+
with Licensor regarding such Contributions.
|
|
137
|
+
|
|
138
|
+
6. Trademarks. This License does not grant permission to use the trade
|
|
139
|
+
names, trademarks, service marks, or product names of the Licensor,
|
|
140
|
+
except as required for describing the origin of the Work and
|
|
141
|
+
reproducing the content of the NOTICE file.
|
|
142
|
+
|
|
143
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
|
144
|
+
agreed to in writing, Licensor provides the Work (and each
|
|
145
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
|
146
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
|
147
|
+
implied, including, without limitation, any warranties or conditions
|
|
148
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
|
149
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
|
150
|
+
appropriateness of using or redistributing the Work and assume any
|
|
151
|
+
risks associated with Your exercise of permissions under this License.
|
|
152
|
+
|
|
153
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
|
154
|
+
whether in tort (including negligence), contract, or otherwise,
|
|
155
|
+
unless required by applicable law (such as deliberate and grossly
|
|
156
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
|
157
|
+
liable to You for damages, including any direct, indirect, special,
|
|
158
|
+
incidental, or consequential damages of any character arising as a
|
|
159
|
+
result of this License or out of the use or inability to use the
|
|
160
|
+
Work (including but not limited to damages for loss of goodwill,
|
|
161
|
+
work stoppage, computer failure or malfunction, or any and all
|
|
162
|
+
other commercial damages or losses), even if such Contributor
|
|
163
|
+
has been advised of the possibility of such damages.
|
|
164
|
+
|
|
165
|
+
9. Accepting Warranty or Support. While redistributing
|
|
166
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
|
167
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
|
168
|
+
or other liability obligations and/or rights consistent with this
|
|
169
|
+
License. However, in accepting such obligations, You may act only
|
|
170
|
+
on Your own behalf and on Your sole responsibility, not on behalf
|
|
171
|
+
of any other Contributor, and only if You agree to indemnify,
|
|
172
|
+
defend, and hold each Contributor harmless for any liability
|
|
173
|
+
incurred by, or claims asserted against, such Contributor by reason
|
|
174
|
+
of your accepting any such warranty or support.
|
|
175
|
+
|
|
176
|
+
END OF TERMS AND CONDITIONS
|
|
177
|
+
|
|
178
|
+
APPENDIX: How to apply the Apache License to your work.
|
|
179
|
+
|
|
180
|
+
To apply the Apache License to your work, attach the following
|
|
181
|
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
|
182
|
+
replaced with your own identifying information. (Don't include
|
|
183
|
+
the brackets!) The text should be enclosed in the appropriate
|
|
184
|
+
comment syntax for the file format. We also recommend that a
|
|
185
|
+
file or class name and description of purpose be included on the
|
|
186
|
+
same "printed page" as the copyright notice for easier
|
|
187
|
+
identification within third-party archives.
|
|
188
|
+
|
|
189
|
+
Copyright 2026 Gor Arakelyan
|
|
190
|
+
|
|
191
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
|
192
|
+
you may not use this file except in compliance with the License.
|
|
193
|
+
You may obtain a copy of the License at
|
|
194
|
+
|
|
195
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
|
196
|
+
|
|
197
|
+
Unless required by applicable law or agreed to in writing, software
|
|
198
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
|
199
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
200
|
+
See the License for the specific language governing permissions and
|
|
201
|
+
limitations under the License.
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
virtuals_binary_codec
|