Mercurial > public > mercurial-scm > hg-stable
annotate mercurial/utils/cborutil.py @ 52709:279e217d6041
typing: lock in the new type annotations detected with the pyupgrade changes
After the changes culminating in 70a75d379daf, pytype was able to detect these
types better (typically changing from something like `Generator[Any, Any, None]`
to `Generator[bytes, Any, None]`). Let's make these explicit so they don't
disappear because of other changes.
author | Matt Harbison <matt_harbison@yahoo.com> |
---|---|
date | Mon, 06 Jan 2025 20:02:17 -0500 |
parents | e627cc25b6f3 |
children | 5e09c6b5b795 |
rev | line source |
---|---|
37711
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
1 # cborutil.py - CBOR extensions |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
2 # |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
3 # Copyright 2018 Gregory Szorc <gregory.szorc@gmail.com> |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
4 # |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
5 # This software may be used and distributed according to the terms of the |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
6 # GNU General Public License version 2 or any later version. |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
7 |
51901
f4733654f144
typing: add `from __future__ import annotations` to most files
Matt Harbison <matt_harbison@yahoo.com>
parents:
49037
diff
changeset
|
8 from __future__ import annotations |
37711
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
9 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
10 import struct |
52709
279e217d6041
typing: lock in the new type annotations detected with the pyupgrade changes
Matt Harbison <matt_harbison@yahoo.com>
parents:
52669
diff
changeset
|
11 import typing |
37711
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
12 |
52709
279e217d6041
typing: lock in the new type annotations detected with the pyupgrade changes
Matt Harbison <matt_harbison@yahoo.com>
parents:
52669
diff
changeset
|
13 if typing.TYPE_CHECKING: |
279e217d6041
typing: lock in the new type annotations detected with the pyupgrade changes
Matt Harbison <matt_harbison@yahoo.com>
parents:
52669
diff
changeset
|
14 from typing import ( |
279e217d6041
typing: lock in the new type annotations detected with the pyupgrade changes
Matt Harbison <matt_harbison@yahoo.com>
parents:
52669
diff
changeset
|
15 Iterator, |
279e217d6041
typing: lock in the new type annotations detected with the pyupgrade changes
Matt Harbison <matt_harbison@yahoo.com>
parents:
52669
diff
changeset
|
16 ) |
39473
8d858fbf2759
cbor: teach the encoder to handle python `long` type for Windows
Matt Harbison <matt_harbison@yahoo.com>
parents:
39440
diff
changeset
|
17 |
37711
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
18 # Very short very of RFC 7049... |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
19 # |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
20 # Each item begins with a byte. The 3 high bits of that byte denote the |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
21 # "major type." The lower 5 bits denote the "subtype." Each major type |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
22 # has its own encoding mechanism. |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
23 # |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
24 # Most types have lengths. However, bytestring, string, array, and map |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
25 # can be indefinite length. These are denotes by a subtype with value 31. |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
26 # Sub-components of those types then come afterwards and are terminated |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
27 # by a "break" byte. |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
28 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
29 MAJOR_TYPE_UINT = 0 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
30 MAJOR_TYPE_NEGINT = 1 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
31 MAJOR_TYPE_BYTESTRING = 2 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
32 MAJOR_TYPE_STRING = 3 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
33 MAJOR_TYPE_ARRAY = 4 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
34 MAJOR_TYPE_MAP = 5 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
35 MAJOR_TYPE_SEMANTIC = 6 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
36 MAJOR_TYPE_SPECIAL = 7 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
37 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
38 SUBTYPE_MASK = 0b00011111 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
39 |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
40 SUBTYPE_FALSE = 20 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
41 SUBTYPE_TRUE = 21 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
42 SUBTYPE_NULL = 22 |
37711
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
43 SUBTYPE_HALF_FLOAT = 25 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
44 SUBTYPE_SINGLE_FLOAT = 26 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
45 SUBTYPE_DOUBLE_FLOAT = 27 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
46 SUBTYPE_INDEFINITE = 31 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
47 |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
48 SEMANTIC_TAG_FINITE_SET = 258 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
49 |
37711
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
50 # Indefinite types begin with their major type ORd with information value 31. |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
51 BEGIN_INDEFINITE_BYTESTRING = struct.pack( |
43554
9f70512ae2cf
cleanup: remove pointless r-prefixes on single-quoted strings
Augie Fackler <augie@google.com>
parents:
43117
diff
changeset
|
52 '>B', MAJOR_TYPE_BYTESTRING << 5 | SUBTYPE_INDEFINITE |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
53 ) |
37711
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
54 BEGIN_INDEFINITE_ARRAY = struct.pack( |
43554
9f70512ae2cf
cleanup: remove pointless r-prefixes on single-quoted strings
Augie Fackler <augie@google.com>
parents:
43117
diff
changeset
|
55 '>B', MAJOR_TYPE_ARRAY << 5 | SUBTYPE_INDEFINITE |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
56 ) |
37711
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
57 BEGIN_INDEFINITE_MAP = struct.pack( |
43554
9f70512ae2cf
cleanup: remove pointless r-prefixes on single-quoted strings
Augie Fackler <augie@google.com>
parents:
43117
diff
changeset
|
58 '>B', MAJOR_TYPE_MAP << 5 | SUBTYPE_INDEFINITE |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
59 ) |
37711
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
60 |
43554
9f70512ae2cf
cleanup: remove pointless r-prefixes on single-quoted strings
Augie Fackler <augie@google.com>
parents:
43117
diff
changeset
|
61 ENCODED_LENGTH_1 = struct.Struct('>B') |
9f70512ae2cf
cleanup: remove pointless r-prefixes on single-quoted strings
Augie Fackler <augie@google.com>
parents:
43117
diff
changeset
|
62 ENCODED_LENGTH_2 = struct.Struct('>BB') |
9f70512ae2cf
cleanup: remove pointless r-prefixes on single-quoted strings
Augie Fackler <augie@google.com>
parents:
43117
diff
changeset
|
63 ENCODED_LENGTH_3 = struct.Struct('>BH') |
9f70512ae2cf
cleanup: remove pointless r-prefixes on single-quoted strings
Augie Fackler <augie@google.com>
parents:
43117
diff
changeset
|
64 ENCODED_LENGTH_4 = struct.Struct('>BL') |
9f70512ae2cf
cleanup: remove pointless r-prefixes on single-quoted strings
Augie Fackler <augie@google.com>
parents:
43117
diff
changeset
|
65 ENCODED_LENGTH_5 = struct.Struct('>BQ') |
37711
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
66 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
67 # The break ends an indefinite length item. |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
68 BREAK = b'\xff' |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
69 BREAK_INT = 255 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
70 |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
71 |
37711
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
72 def encodelength(majortype, length): |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
73 """Obtain a value encoding the major type and its length.""" |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
74 if length < 24: |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
75 return ENCODED_LENGTH_1.pack(majortype << 5 | length) |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
76 elif length < 256: |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
77 return ENCODED_LENGTH_2.pack(majortype << 5 | 24, length) |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
78 elif length < 65536: |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
79 return ENCODED_LENGTH_3.pack(majortype << 5 | 25, length) |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
80 elif length < 4294967296: |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
81 return ENCODED_LENGTH_4.pack(majortype << 5 | 26, length) |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
82 else: |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
83 return ENCODED_LENGTH_5.pack(majortype << 5 | 27, length) |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
84 |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
85 |
37711
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
86 def streamencodebytestring(v): |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
87 yield encodelength(MAJOR_TYPE_BYTESTRING, len(v)) |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
88 yield v |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
89 |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
90 |
37711
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
91 def streamencodebytestringfromiter(it): |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
92 """Convert an iterator of chunks to an indefinite bytestring. |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
93 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
94 Given an input that is iterable and each element in the iterator is |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
95 representable as bytes, emit an indefinite length bytestring. |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
96 """ |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
97 yield BEGIN_INDEFINITE_BYTESTRING |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
98 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
99 for chunk in it: |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
100 yield encodelength(MAJOR_TYPE_BYTESTRING, len(chunk)) |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
101 yield chunk |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
102 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
103 yield BREAK |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
104 |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
105 |
37711
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
106 def streamencodeindefinitebytestring(source, chunksize=65536): |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
107 """Given a large source buffer, emit as an indefinite length bytestring. |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
108 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
109 This is a generator of chunks constituting the encoded CBOR data. |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
110 """ |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
111 yield BEGIN_INDEFINITE_BYTESTRING |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
112 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
113 i = 0 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
114 l = len(source) |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
115 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
116 while True: |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
117 chunk = source[i : i + chunksize] |
37711
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
118 i += len(chunk) |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
119 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
120 yield encodelength(MAJOR_TYPE_BYTESTRING, len(chunk)) |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
121 yield chunk |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
122 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
123 if i >= l: |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
124 break |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
125 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
126 yield BREAK |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
127 |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
128 |
37711
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
129 def streamencodeint(v): |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
130 if v >= 18446744073709551616 or v < -18446744073709551616: |
43077
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
131 raise ValueError(b'big integers not supported') |
37711
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
132 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
133 if v >= 0: |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
134 yield encodelength(MAJOR_TYPE_UINT, v) |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
135 else: |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
136 yield encodelength(MAJOR_TYPE_NEGINT, abs(v) - 1) |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
137 |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
138 |
52709
279e217d6041
typing: lock in the new type annotations detected with the pyupgrade changes
Matt Harbison <matt_harbison@yahoo.com>
parents:
52669
diff
changeset
|
139 def streamencodearray(l) -> Iterator[bytes]: |
37711
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
140 """Encode a known size iterable to an array.""" |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
141 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
142 yield encodelength(MAJOR_TYPE_ARRAY, len(l)) |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
143 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
144 for i in l: |
52669
e627cc25b6f3
pyupgrade: rewrite `yield` statements in a loop to `yield from`
Matt Harbison <matt_harbison@yahoo.com>
parents:
52659
diff
changeset
|
145 yield from streamencode(i) |
37711
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
146 |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
147 |
52709
279e217d6041
typing: lock in the new type annotations detected with the pyupgrade changes
Matt Harbison <matt_harbison@yahoo.com>
parents:
52669
diff
changeset
|
148 def streamencodearrayfromiter(it) -> Iterator[bytes]: |
37711
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
149 """Encode an iterator of items to an indefinite length array.""" |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
150 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
151 yield BEGIN_INDEFINITE_ARRAY |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
152 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
153 for i in it: |
52669
e627cc25b6f3
pyupgrade: rewrite `yield` statements in a loop to `yield from`
Matt Harbison <matt_harbison@yahoo.com>
parents:
52659
diff
changeset
|
154 yield from streamencode(i) |
37711
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
155 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
156 yield BREAK |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
157 |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
158 |
37942
2ae6a3134362
cborutil: port to Python 3
Augie Fackler <augie@google.com>
parents:
37711
diff
changeset
|
159 def _mixedtypesortkey(v): |
2ae6a3134362
cborutil: port to Python 3
Augie Fackler <augie@google.com>
parents:
37711
diff
changeset
|
160 return type(v).__name__, v |
2ae6a3134362
cborutil: port to Python 3
Augie Fackler <augie@google.com>
parents:
37711
diff
changeset
|
161 |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
162 |
37711
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
163 def streamencodeset(s): |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
164 # https://www.iana.org/assignments/cbor-tags/cbor-tags.xhtml defines |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
165 # semantic tag 258 for finite sets. |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
166 yield encodelength(MAJOR_TYPE_SEMANTIC, SEMANTIC_TAG_FINITE_SET) |
37711
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
167 |
52669
e627cc25b6f3
pyupgrade: rewrite `yield` statements in a loop to `yield from`
Matt Harbison <matt_harbison@yahoo.com>
parents:
52659
diff
changeset
|
168 yield from streamencodearray(sorted(s, key=_mixedtypesortkey)) |
37711
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
169 |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
170 |
52709
279e217d6041
typing: lock in the new type annotations detected with the pyupgrade changes
Matt Harbison <matt_harbison@yahoo.com>
parents:
52669
diff
changeset
|
171 def streamencodemap(d) -> Iterator[bytes]: |
37711
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
172 """Encode dictionary to a generator. |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
173 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
174 Does not supporting indefinite length dictionaries. |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
175 """ |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
176 yield encodelength(MAJOR_TYPE_MAP, len(d)) |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
177 |
49004
f254fc73d956
global: bulk replace simple pycompat.iteritems(x) with x.items()
Gregory Szorc <gregory.szorc@gmail.com>
parents:
48966
diff
changeset
|
178 for key, value in sorted(d.items(), key=lambda x: _mixedtypesortkey(x[0])): |
52669
e627cc25b6f3
pyupgrade: rewrite `yield` statements in a loop to `yield from`
Matt Harbison <matt_harbison@yahoo.com>
parents:
52659
diff
changeset
|
179 yield from streamencode(key) |
e627cc25b6f3
pyupgrade: rewrite `yield` statements in a loop to `yield from`
Matt Harbison <matt_harbison@yahoo.com>
parents:
52659
diff
changeset
|
180 yield from streamencode(value) |
37711
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
181 |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
182 |
52709
279e217d6041
typing: lock in the new type annotations detected with the pyupgrade changes
Matt Harbison <matt_harbison@yahoo.com>
parents:
52669
diff
changeset
|
183 def streamencodemapfromiter(it) -> Iterator[bytes]: |
37711
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
184 """Given an iterable of (key, value), encode to an indefinite length map.""" |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
185 yield BEGIN_INDEFINITE_MAP |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
186 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
187 for key, value in it: |
52669
e627cc25b6f3
pyupgrade: rewrite `yield` statements in a loop to `yield from`
Matt Harbison <matt_harbison@yahoo.com>
parents:
52659
diff
changeset
|
188 yield from streamencode(key) |
e627cc25b6f3
pyupgrade: rewrite `yield` statements in a loop to `yield from`
Matt Harbison <matt_harbison@yahoo.com>
parents:
52659
diff
changeset
|
189 yield from streamencode(value) |
37711
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
190 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
191 yield BREAK |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
192 |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
193 |
37711
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
194 def streamencodebool(b): |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
195 # major type 7, simple value 20 and 21. |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
196 yield b'\xf5' if b else b'\xf4' |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
197 |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
198 |
37711
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
199 def streamencodenone(v): |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
200 # major type 7, simple value 22. |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
201 yield b'\xf6' |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
202 |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
203 |
37711
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
204 STREAM_ENCODERS = { |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
205 bytes: streamencodebytestring, |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
206 int: streamencodeint, |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
207 list: streamencodearray, |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
208 tuple: streamencodearray, |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
209 dict: streamencodemap, |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
210 set: streamencodeset, |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
211 bool: streamencodebool, |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
212 type(None): streamencodenone, |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
213 } |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
214 |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
215 |
37711
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
216 def streamencode(v): |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
217 """Encode a value in a streaming manner. |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
218 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
219 Given an input object, encode it to CBOR recursively. |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
220 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
221 Returns a generator of CBOR encoded bytes. There is no guarantee |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
222 that each emitted chunk fully decodes to a value or sub-value. |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
223 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
224 Encoding is deterministic - unordered collections are sorted. |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
225 """ |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
226 fn = STREAM_ENCODERS.get(v.__class__) |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
227 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
228 if not fn: |
42176
b6387a65851d
cborutil: fix streamencode() to handle subtypes
Yuya Nishihara <yuya@tcha.org>
parents:
40125
diff
changeset
|
229 # handle subtypes such as encoding.localstr and util.sortdict |
b6387a65851d
cborutil: fix streamencode() to handle subtypes
Yuya Nishihara <yuya@tcha.org>
parents:
40125
diff
changeset
|
230 for ty in STREAM_ENCODERS: |
b6387a65851d
cborutil: fix streamencode() to handle subtypes
Yuya Nishihara <yuya@tcha.org>
parents:
40125
diff
changeset
|
231 if not isinstance(v, ty): |
b6387a65851d
cborutil: fix streamencode() to handle subtypes
Yuya Nishihara <yuya@tcha.org>
parents:
40125
diff
changeset
|
232 continue |
b6387a65851d
cborutil: fix streamencode() to handle subtypes
Yuya Nishihara <yuya@tcha.org>
parents:
40125
diff
changeset
|
233 fn = STREAM_ENCODERS[ty] |
b6387a65851d
cborutil: fix streamencode() to handle subtypes
Yuya Nishihara <yuya@tcha.org>
parents:
40125
diff
changeset
|
234 break |
b6387a65851d
cborutil: fix streamencode() to handle subtypes
Yuya Nishihara <yuya@tcha.org>
parents:
40125
diff
changeset
|
235 |
b6387a65851d
cborutil: fix streamencode() to handle subtypes
Yuya Nishihara <yuya@tcha.org>
parents:
40125
diff
changeset
|
236 if not fn: |
52659
fb8932685031
cborutil: fix an error interpolating str into bytes
Matt Harbison <matt_harbison@yahoo.com>
parents:
51915
diff
changeset
|
237 raise ValueError('do not know how to encode %s' % type(v)) |
37711
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
238 |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
239 return fn(v) |
65a23cc8e75b
cborutil: implement support for streaming encoding, bytestring decoding
Gregory Szorc <gregory.szorc@gmail.com>
parents:
diff
changeset
|
240 |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
241 |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
242 class CBORDecodeError(Exception): |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
243 """Represents an error decoding CBOR.""" |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
244 |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
245 |
49033
bce8f66d3045
cborutil: remove Python 2 definition of _elementtointeger()
Gregory Szorc <gregory.szorc@gmail.com>
parents:
49023
diff
changeset
|
246 def _elementtointeger(b, i): |
bce8f66d3045
cborutil: remove Python 2 definition of _elementtointeger()
Gregory Szorc <gregory.szorc@gmail.com>
parents:
49023
diff
changeset
|
247 return b[i] |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
248 |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
249 |
43554
9f70512ae2cf
cleanup: remove pointless r-prefixes on single-quoted strings
Augie Fackler <augie@google.com>
parents:
43117
diff
changeset
|
250 STRUCT_BIG_UBYTE = struct.Struct('>B') |
43077
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
251 STRUCT_BIG_USHORT = struct.Struct(b'>H') |
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
252 STRUCT_BIG_ULONG = struct.Struct(b'>L') |
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
253 STRUCT_BIG_ULONGLONG = struct.Struct(b'>Q') |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
254 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
255 SPECIAL_NONE = 0 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
256 SPECIAL_START_INDEFINITE_BYTESTRING = 1 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
257 SPECIAL_START_ARRAY = 2 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
258 SPECIAL_START_MAP = 3 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
259 SPECIAL_START_SET = 4 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
260 SPECIAL_INDEFINITE_BREAK = 5 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
261 |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
262 |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
263 def decodeitem(b, offset=0): |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
264 """Decode a new CBOR value from a buffer at offset. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
265 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
266 This function attempts to decode up to one complete CBOR value |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
267 from ``b`` starting at offset ``offset``. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
268 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
269 The beginning of a collection (such as an array, map, set, or |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
270 indefinite length bytestring) counts as a single value. For these |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
271 special cases, a state flag will indicate that a special value was seen. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
272 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
273 When called, the function either returns a decoded value or gives |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
274 a hint as to how many more bytes are needed to do so. By calling |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
275 the function repeatedly given a stream of bytes, the caller can |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
276 build up the original values. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
277 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
278 Returns a tuple with the following elements: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
279 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
280 * Bool indicating whether a complete value was decoded. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
281 * A decoded value if first value is True otherwise None |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
282 * Integer number of bytes. If positive, the number of bytes |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
283 read. If negative, the number of bytes we need to read to |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
284 decode this value or the next chunk in this value. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
285 * One of the ``SPECIAL_*`` constants indicating special treatment |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
286 for this value. ``SPECIAL_NONE`` means this is a fully decoded |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
287 simple value (such as an integer or bool). |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
288 """ |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
289 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
290 initial = _elementtointeger(b, offset) |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
291 offset += 1 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
292 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
293 majortype = initial >> 5 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
294 subtype = initial & SUBTYPE_MASK |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
295 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
296 if majortype == MAJOR_TYPE_UINT: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
297 complete, value, readcount = decodeuint(subtype, b, offset) |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
298 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
299 if complete: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
300 return True, value, readcount + 1, SPECIAL_NONE |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
301 else: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
302 return False, None, readcount, SPECIAL_NONE |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
303 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
304 elif majortype == MAJOR_TYPE_NEGINT: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
305 # Negative integers are the same as UINT except inverted minus 1. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
306 complete, value, readcount = decodeuint(subtype, b, offset) |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
307 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
308 if complete: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
309 return True, -value - 1, readcount + 1, SPECIAL_NONE |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
310 else: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
311 return False, None, readcount, SPECIAL_NONE |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
312 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
313 elif majortype == MAJOR_TYPE_BYTESTRING: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
314 # Beginning of bytestrings are treated as uints in order to |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
315 # decode their length, which may be indefinite. |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
316 complete, size, readcount = decodeuint( |
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
317 subtype, b, offset, allowindefinite=True |
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
318 ) |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
319 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
320 # We don't know the size of the bytestring. It must be a definitive |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
321 # length since the indefinite subtype would be encoded in the initial |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
322 # byte. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
323 if not complete: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
324 return False, None, readcount, SPECIAL_NONE |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
325 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
326 # We know the length of the bytestring. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
327 if size is not None: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
328 # And the data is available in the buffer. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
329 if offset + readcount + size <= len(b): |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
330 value = b[offset + readcount : offset + readcount + size] |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
331 return True, value, readcount + size + 1, SPECIAL_NONE |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
332 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
333 # And we need more data in order to return the bytestring. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
334 else: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
335 wanted = len(b) - offset - readcount - size |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
336 return False, None, wanted, SPECIAL_NONE |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
337 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
338 # It is an indefinite length bytestring. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
339 else: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
340 return True, None, 1, SPECIAL_START_INDEFINITE_BYTESTRING |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
341 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
342 elif majortype == MAJOR_TYPE_STRING: |
43077
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
343 raise CBORDecodeError(b'string major type not supported') |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
344 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
345 elif majortype == MAJOR_TYPE_ARRAY: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
346 # Beginning of arrays are treated as uints in order to decode their |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
347 # length. We don't allow indefinite length arrays. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
348 complete, size, readcount = decodeuint(subtype, b, offset) |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
349 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
350 if complete: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
351 return True, size, readcount + 1, SPECIAL_START_ARRAY |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
352 else: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
353 return False, None, readcount, SPECIAL_NONE |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
354 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
355 elif majortype == MAJOR_TYPE_MAP: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
356 # Beginning of maps are treated as uints in order to decode their |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
357 # number of elements. We don't allow indefinite length arrays. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
358 complete, size, readcount = decodeuint(subtype, b, offset) |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
359 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
360 if complete: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
361 return True, size, readcount + 1, SPECIAL_START_MAP |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
362 else: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
363 return False, None, readcount, SPECIAL_NONE |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
364 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
365 elif majortype == MAJOR_TYPE_SEMANTIC: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
366 # Semantic tag value is read the same as a uint. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
367 complete, tagvalue, readcount = decodeuint(subtype, b, offset) |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
368 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
369 if not complete: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
370 return False, None, readcount, SPECIAL_NONE |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
371 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
372 # This behavior here is a little wonky. The main type being "decorated" |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
373 # by this semantic tag follows. A more robust parser would probably emit |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
374 # a special flag indicating this as a semantic tag and let the caller |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
375 # deal with the types that follow. But since we don't support many |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
376 # semantic tags, it is easier to deal with the special cases here and |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
377 # hide complexity from the caller. If we add support for more semantic |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
378 # tags, we should probably move semantic tag handling into the caller. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
379 if tagvalue == SEMANTIC_TAG_FINITE_SET: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
380 if offset + readcount >= len(b): |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
381 return False, None, -1, SPECIAL_NONE |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
382 |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
383 complete, size, readcount2, special = decodeitem( |
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
384 b, offset + readcount |
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
385 ) |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
386 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
387 if not complete: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
388 return False, None, readcount2, SPECIAL_NONE |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
389 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
390 if special != SPECIAL_START_ARRAY: |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
391 raise CBORDecodeError( |
43117
8ff1ecfadcd1
cleanup: join string literals that are already on one line
Martin von Zweigbergk <martinvonz@google.com>
parents:
43106
diff
changeset
|
392 b'expected array after finite set semantic tag' |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
393 ) |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
394 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
395 return True, size, readcount + readcount2 + 1, SPECIAL_START_SET |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
396 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
397 else: |
43077
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
398 raise CBORDecodeError(b'semantic tag %d not allowed' % tagvalue) |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
399 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
400 elif majortype == MAJOR_TYPE_SPECIAL: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
401 # Only specific values for the information field are allowed. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
402 if subtype == SUBTYPE_FALSE: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
403 return True, False, 1, SPECIAL_NONE |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
404 elif subtype == SUBTYPE_TRUE: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
405 return True, True, 1, SPECIAL_NONE |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
406 elif subtype == SUBTYPE_NULL: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
407 return True, None, 1, SPECIAL_NONE |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
408 elif subtype == SUBTYPE_INDEFINITE: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
409 return True, None, 1, SPECIAL_INDEFINITE_BREAK |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
410 # If value is 24, subtype is in next byte. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
411 else: |
43077
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
412 raise CBORDecodeError(b'special type %d not allowed' % subtype) |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
413 else: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
414 assert False |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
415 |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
416 |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
417 def decodeuint(subtype, b, offset=0, allowindefinite=False): |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
418 """Decode an unsigned integer. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
419 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
420 ``subtype`` is the lower 5 bits from the initial byte CBOR item |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
421 "header." ``b`` is a buffer containing bytes. ``offset`` points to |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
422 the index of the first byte after the byte that ``subtype`` was |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
423 derived from. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
424 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
425 ``allowindefinite`` allows the special indefinite length value |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
426 indicator. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
427 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
428 Returns a 3-tuple of (successful, value, count). |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
429 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
430 The first element is a bool indicating if decoding completed. The 2nd |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
431 is the decoded integer value or None if not fully decoded or the subtype |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
432 is 31 and ``allowindefinite`` is True. The 3rd value is the count of bytes. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
433 If positive, it is the number of additional bytes decoded. If negative, |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
434 it is the number of additional bytes needed to decode this value. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
435 """ |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
436 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
437 # Small values are inline. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
438 if subtype < 24: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
439 return True, subtype, 0 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
440 # Indefinite length specifier. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
441 elif subtype == 31: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
442 if allowindefinite: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
443 return True, None, 0 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
444 else: |
43077
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
445 raise CBORDecodeError(b'indefinite length uint not allowed here') |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
446 elif subtype >= 28: |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
447 raise CBORDecodeError( |
43077
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
448 b'unsupported subtype on integer type: %d' % subtype |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
449 ) |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
450 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
451 if subtype == 24: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
452 s = STRUCT_BIG_UBYTE |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
453 elif subtype == 25: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
454 s = STRUCT_BIG_USHORT |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
455 elif subtype == 26: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
456 s = STRUCT_BIG_ULONG |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
457 elif subtype == 27: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
458 s = STRUCT_BIG_ULONGLONG |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
459 else: |
43077
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
460 raise CBORDecodeError(b'bounds condition checking violation') |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
461 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
462 if len(b) - offset >= s.size: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
463 return True, s.unpack_from(b, offset)[0], s.size |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
464 else: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
465 return False, None, len(b) - offset - s.size |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
466 |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
467 |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
468 class bytestringchunk(bytes): |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
469 """Represents a chunk/segment in an indefinite length bytestring. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
470 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
471 This behaves like a ``bytes`` but in addition has the ``isfirst`` |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
472 and ``islast`` attributes indicating whether this chunk is the first |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
473 or last in an indefinite length bytestring. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
474 """ |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
475 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
476 def __new__(cls, v, first=False, last=False): |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
477 self = bytes.__new__(cls, v) |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
478 self.isfirst = first |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
479 self.islast = last |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
480 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
481 return self |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
482 |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
483 |
49037
642e31cb55f0
py3: use class X: instead of class X(object):
Gregory Szorc <gregory.szorc@gmail.com>
parents:
49033
diff
changeset
|
484 class sansiodecoder: |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
485 """A CBOR decoder that doesn't perform its own I/O. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
486 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
487 To use, construct an instance and feed it segments containing |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
488 CBOR-encoded bytes via ``decode()``. The return value from ``decode()`` |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
489 indicates whether a fully-decoded value is available, how many bytes |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
490 were consumed, and offers a hint as to how many bytes should be fed |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
491 in next time to decode the next value. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
492 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
493 The decoder assumes it will decode N discrete CBOR values, not just |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
494 a single value. i.e. if the bytestream contains uints packed one after |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
495 the other, the decoder will decode them all, rather than just the initial |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
496 one. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
497 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
498 When ``decode()`` indicates a value is available, call ``getavailable()`` |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
499 to return all fully decoded values. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
500 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
501 ``decode()`` can partially decode input. It is up to the caller to keep |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
502 track of what data was consumed and to pass unconsumed data in on the |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
503 next invocation. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
504 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
505 The decoder decodes atomically at the *item* level. See ``decodeitem()``. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
506 If an *item* cannot be fully decoded, the decoder won't record it as |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
507 partially consumed. Instead, the caller will be instructed to pass in |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
508 the initial bytes of this item on the next invocation. This does result |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
509 in some redundant parsing. But the overhead should be minimal. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
510 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
511 This decoder only supports a subset of CBOR as required by Mercurial. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
512 It lacks support for: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
513 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
514 * Indefinite length arrays |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
515 * Indefinite length maps |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
516 * Use of indefinite length bytestrings as keys or values within |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
517 arrays, maps, or sets. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
518 * Nested arrays, maps, or sets within sets |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
519 * Any semantic tag that isn't a mathematical finite set |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
520 * Floating point numbers |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
521 * Undefined special value |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
522 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
523 CBOR types are decoded to Python types as follows: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
524 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
525 uint -> int |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
526 negint -> int |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
527 bytestring -> bytes |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
528 map -> dict |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
529 array -> list |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
530 True -> bool |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
531 False -> bool |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
532 null -> None |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
533 indefinite length bytestring chunk -> [bytestringchunk] |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
534 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
535 The only non-obvious mapping here is an indefinite length bytestring |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
536 to the ``bytestringchunk`` type. This is to facilitate streaming |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
537 indefinite length bytestrings out of the decoder and to differentiate |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
538 a regular bytestring from an indefinite length bytestring. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
539 """ |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
540 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
541 _STATE_NONE = 0 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
542 _STATE_WANT_MAP_KEY = 1 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
543 _STATE_WANT_MAP_VALUE = 2 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
544 _STATE_WANT_ARRAY_VALUE = 3 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
545 _STATE_WANT_SET_VALUE = 4 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
546 _STATE_WANT_BYTESTRING_CHUNK_FIRST = 5 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
547 _STATE_WANT_BYTESTRING_CHUNK_SUBSEQUENT = 6 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
548 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
549 def __init__(self): |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
550 # TODO add support for limiting size of bytestrings |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
551 # TODO add support for limiting number of keys / values in collections |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
552 # TODO add support for limiting size of buffered partial values |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
553 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
554 self.decodedbytecount = 0 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
555 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
556 self._state = self._STATE_NONE |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
557 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
558 # Stack of active nested collections. Each entry is a dict describing |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
559 # the collection. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
560 self._collectionstack = [] |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
561 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
562 # Fully decoded key to use for the current map. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
563 self._currentmapkey = None |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
564 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
565 # Fully decoded values available for retrieval. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
566 self._decodedvalues = [] |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
567 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
568 @property |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
569 def inprogress(self): |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
570 """Whether the decoder has partially decoded a value.""" |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
571 return self._state != self._STATE_NONE |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
572 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
573 def decode(self, b, offset=0): |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
574 """Attempt to decode bytes from an input buffer. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
575 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
576 ``b`` is a collection of bytes and ``offset`` is the byte |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
577 offset within that buffer from which to begin reading data. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
578 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
579 ``b`` must support ``len()`` and accessing bytes slices via |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
580 ``__slice__``. Typically ``bytes`` instances are used. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
581 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
582 Returns a tuple with the following fields: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
583 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
584 * Bool indicating whether values are available for retrieval. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
585 * Integer indicating the number of bytes that were fully consumed, |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
586 starting from ``offset``. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
587 * Integer indicating the number of bytes that are desired for the |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
588 next call in order to decode an item. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
589 """ |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
590 if not b: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
591 return bool(self._decodedvalues), 0, 0 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
592 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
593 initialoffset = offset |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
594 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
595 # We could easily split the body of this loop into a function. But |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
596 # Python performance is sensitive to function calls and collections |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
597 # are composed of many items. So leaving as a while loop could help |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
598 # with performance. One thing that may not help is the use of |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
599 # if..elif versus a lookup/dispatch table. There may be value |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
600 # in switching that. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
601 while offset < len(b): |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
602 # Attempt to decode an item. This could be a whole value or a |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
603 # special value indicating an event, such as start or end of a |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
604 # collection or indefinite length type. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
605 complete, value, readcount, special = decodeitem(b, offset) |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
606 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
607 if readcount > 0: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
608 self.decodedbytecount += readcount |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
609 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
610 if not complete: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
611 assert readcount < 0 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
612 return ( |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
613 bool(self._decodedvalues), |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
614 offset - initialoffset, |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
615 -readcount, |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
616 ) |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
617 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
618 offset += readcount |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
619 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
620 # No nested state. We either have a full value or beginning of a |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
621 # complex value to deal with. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
622 if self._state == self._STATE_NONE: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
623 # A normal value. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
624 if special == SPECIAL_NONE: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
625 self._decodedvalues.append(value) |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
626 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
627 elif special == SPECIAL_START_ARRAY: |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
628 self._collectionstack.append( |
45957
89a2afe31e82
formating: upgrade to black 20.8b1
Augie Fackler <raf@durin42.com>
parents:
43554
diff
changeset
|
629 { |
89a2afe31e82
formating: upgrade to black 20.8b1
Augie Fackler <raf@durin42.com>
parents:
43554
diff
changeset
|
630 b'remaining': value, |
89a2afe31e82
formating: upgrade to black 20.8b1
Augie Fackler <raf@durin42.com>
parents:
43554
diff
changeset
|
631 b'v': [], |
89a2afe31e82
formating: upgrade to black 20.8b1
Augie Fackler <raf@durin42.com>
parents:
43554
diff
changeset
|
632 } |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
633 ) |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
634 self._state = self._STATE_WANT_ARRAY_VALUE |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
635 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
636 elif special == SPECIAL_START_MAP: |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
637 self._collectionstack.append( |
45957
89a2afe31e82
formating: upgrade to black 20.8b1
Augie Fackler <raf@durin42.com>
parents:
43554
diff
changeset
|
638 { |
89a2afe31e82
formating: upgrade to black 20.8b1
Augie Fackler <raf@durin42.com>
parents:
43554
diff
changeset
|
639 b'remaining': value, |
89a2afe31e82
formating: upgrade to black 20.8b1
Augie Fackler <raf@durin42.com>
parents:
43554
diff
changeset
|
640 b'v': {}, |
89a2afe31e82
formating: upgrade to black 20.8b1
Augie Fackler <raf@durin42.com>
parents:
43554
diff
changeset
|
641 } |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
642 ) |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
643 self._state = self._STATE_WANT_MAP_KEY |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
644 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
645 elif special == SPECIAL_START_SET: |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
646 self._collectionstack.append( |
45957
89a2afe31e82
formating: upgrade to black 20.8b1
Augie Fackler <raf@durin42.com>
parents:
43554
diff
changeset
|
647 { |
89a2afe31e82
formating: upgrade to black 20.8b1
Augie Fackler <raf@durin42.com>
parents:
43554
diff
changeset
|
648 b'remaining': value, |
89a2afe31e82
formating: upgrade to black 20.8b1
Augie Fackler <raf@durin42.com>
parents:
43554
diff
changeset
|
649 b'v': set(), |
89a2afe31e82
formating: upgrade to black 20.8b1
Augie Fackler <raf@durin42.com>
parents:
43554
diff
changeset
|
650 } |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
651 ) |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
652 self._state = self._STATE_WANT_SET_VALUE |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
653 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
654 elif special == SPECIAL_START_INDEFINITE_BYTESTRING: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
655 self._state = self._STATE_WANT_BYTESTRING_CHUNK_FIRST |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
656 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
657 else: |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
658 raise CBORDecodeError( |
43077
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
659 b'unhandled special state: %d' % special |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
660 ) |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
661 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
662 # This value becomes an element of the current array. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
663 elif self._state == self._STATE_WANT_ARRAY_VALUE: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
664 # Simple values get appended. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
665 if special == SPECIAL_NONE: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
666 c = self._collectionstack[-1] |
43077
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
667 c[b'v'].append(value) |
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
668 c[b'remaining'] -= 1 |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
669 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
670 # self._state doesn't need changed. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
671 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
672 # An array nested within an array. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
673 elif special == SPECIAL_START_ARRAY: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
674 lastc = self._collectionstack[-1] |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
675 newvalue = [] |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
676 |
43077
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
677 lastc[b'v'].append(newvalue) |
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
678 lastc[b'remaining'] -= 1 |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
679 |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
680 self._collectionstack.append( |
45957
89a2afe31e82
formating: upgrade to black 20.8b1
Augie Fackler <raf@durin42.com>
parents:
43554
diff
changeset
|
681 { |
89a2afe31e82
formating: upgrade to black 20.8b1
Augie Fackler <raf@durin42.com>
parents:
43554
diff
changeset
|
682 b'remaining': value, |
89a2afe31e82
formating: upgrade to black 20.8b1
Augie Fackler <raf@durin42.com>
parents:
43554
diff
changeset
|
683 b'v': newvalue, |
89a2afe31e82
formating: upgrade to black 20.8b1
Augie Fackler <raf@durin42.com>
parents:
43554
diff
changeset
|
684 } |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
685 ) |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
686 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
687 # self._state doesn't need changed. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
688 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
689 # A map nested within an array. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
690 elif special == SPECIAL_START_MAP: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
691 lastc = self._collectionstack[-1] |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
692 newvalue = {} |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
693 |
43077
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
694 lastc[b'v'].append(newvalue) |
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
695 lastc[b'remaining'] -= 1 |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
696 |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
697 self._collectionstack.append( |
43077
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
698 {b'remaining': value, b'v': newvalue} |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
699 ) |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
700 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
701 self._state = self._STATE_WANT_MAP_KEY |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
702 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
703 elif special == SPECIAL_START_SET: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
704 lastc = self._collectionstack[-1] |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
705 newvalue = set() |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
706 |
43077
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
707 lastc[b'v'].append(newvalue) |
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
708 lastc[b'remaining'] -= 1 |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
709 |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
710 self._collectionstack.append( |
45957
89a2afe31e82
formating: upgrade to black 20.8b1
Augie Fackler <raf@durin42.com>
parents:
43554
diff
changeset
|
711 { |
89a2afe31e82
formating: upgrade to black 20.8b1
Augie Fackler <raf@durin42.com>
parents:
43554
diff
changeset
|
712 b'remaining': value, |
89a2afe31e82
formating: upgrade to black 20.8b1
Augie Fackler <raf@durin42.com>
parents:
43554
diff
changeset
|
713 b'v': newvalue, |
89a2afe31e82
formating: upgrade to black 20.8b1
Augie Fackler <raf@durin42.com>
parents:
43554
diff
changeset
|
714 } |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
715 ) |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
716 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
717 self._state = self._STATE_WANT_SET_VALUE |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
718 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
719 elif special == SPECIAL_START_INDEFINITE_BYTESTRING: |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
720 raise CBORDecodeError( |
43077
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
721 b'indefinite length bytestrings ' |
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
722 b'not allowed as array values' |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
723 ) |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
724 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
725 else: |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
726 raise CBORDecodeError( |
43077
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
727 b'unhandled special item when ' |
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
728 b'expecting array value: %d' % special |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
729 ) |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
730 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
731 # This value becomes the key of the current map instance. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
732 elif self._state == self._STATE_WANT_MAP_KEY: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
733 if special == SPECIAL_NONE: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
734 self._currentmapkey = value |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
735 self._state = self._STATE_WANT_MAP_VALUE |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
736 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
737 elif special == SPECIAL_START_INDEFINITE_BYTESTRING: |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
738 raise CBORDecodeError( |
43077
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
739 b'indefinite length bytestrings ' |
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
740 b'not allowed as map keys' |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
741 ) |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
742 |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
743 elif special in ( |
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
744 SPECIAL_START_ARRAY, |
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
745 SPECIAL_START_MAP, |
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
746 SPECIAL_START_SET, |
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
747 ): |
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
748 raise CBORDecodeError( |
43117
8ff1ecfadcd1
cleanup: join string literals that are already on one line
Martin von Zweigbergk <martinvonz@google.com>
parents:
43106
diff
changeset
|
749 b'collections not supported as map keys' |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
750 ) |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
751 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
752 # We do not allow special values to be used as map keys. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
753 else: |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
754 raise CBORDecodeError( |
43077
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
755 b'unhandled special item when ' |
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
756 b'expecting map key: %d' % special |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
757 ) |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
758 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
759 # This value becomes the value of the current map key. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
760 elif self._state == self._STATE_WANT_MAP_VALUE: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
761 # Simple values simply get inserted into the map. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
762 if special == SPECIAL_NONE: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
763 lastc = self._collectionstack[-1] |
43077
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
764 lastc[b'v'][self._currentmapkey] = value |
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
765 lastc[b'remaining'] -= 1 |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
766 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
767 self._state = self._STATE_WANT_MAP_KEY |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
768 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
769 # A new array is used as the map value. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
770 elif special == SPECIAL_START_ARRAY: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
771 lastc = self._collectionstack[-1] |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
772 newvalue = [] |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
773 |
43077
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
774 lastc[b'v'][self._currentmapkey] = newvalue |
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
775 lastc[b'remaining'] -= 1 |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
776 |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
777 self._collectionstack.append( |
45957
89a2afe31e82
formating: upgrade to black 20.8b1
Augie Fackler <raf@durin42.com>
parents:
43554
diff
changeset
|
778 { |
89a2afe31e82
formating: upgrade to black 20.8b1
Augie Fackler <raf@durin42.com>
parents:
43554
diff
changeset
|
779 b'remaining': value, |
89a2afe31e82
formating: upgrade to black 20.8b1
Augie Fackler <raf@durin42.com>
parents:
43554
diff
changeset
|
780 b'v': newvalue, |
89a2afe31e82
formating: upgrade to black 20.8b1
Augie Fackler <raf@durin42.com>
parents:
43554
diff
changeset
|
781 } |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
782 ) |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
783 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
784 self._state = self._STATE_WANT_ARRAY_VALUE |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
785 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
786 # A new map is used as the map value. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
787 elif special == SPECIAL_START_MAP: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
788 lastc = self._collectionstack[-1] |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
789 newvalue = {} |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
790 |
43077
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
791 lastc[b'v'][self._currentmapkey] = newvalue |
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
792 lastc[b'remaining'] -= 1 |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
793 |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
794 self._collectionstack.append( |
45957
89a2afe31e82
formating: upgrade to black 20.8b1
Augie Fackler <raf@durin42.com>
parents:
43554
diff
changeset
|
795 { |
89a2afe31e82
formating: upgrade to black 20.8b1
Augie Fackler <raf@durin42.com>
parents:
43554
diff
changeset
|
796 b'remaining': value, |
89a2afe31e82
formating: upgrade to black 20.8b1
Augie Fackler <raf@durin42.com>
parents:
43554
diff
changeset
|
797 b'v': newvalue, |
89a2afe31e82
formating: upgrade to black 20.8b1
Augie Fackler <raf@durin42.com>
parents:
43554
diff
changeset
|
798 } |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
799 ) |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
800 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
801 self._state = self._STATE_WANT_MAP_KEY |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
802 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
803 # A new set is used as the map value. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
804 elif special == SPECIAL_START_SET: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
805 lastc = self._collectionstack[-1] |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
806 newvalue = set() |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
807 |
43077
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
808 lastc[b'v'][self._currentmapkey] = newvalue |
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
809 lastc[b'remaining'] -= 1 |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
810 |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
811 self._collectionstack.append( |
45957
89a2afe31e82
formating: upgrade to black 20.8b1
Augie Fackler <raf@durin42.com>
parents:
43554
diff
changeset
|
812 { |
89a2afe31e82
formating: upgrade to black 20.8b1
Augie Fackler <raf@durin42.com>
parents:
43554
diff
changeset
|
813 b'remaining': value, |
89a2afe31e82
formating: upgrade to black 20.8b1
Augie Fackler <raf@durin42.com>
parents:
43554
diff
changeset
|
814 b'v': newvalue, |
89a2afe31e82
formating: upgrade to black 20.8b1
Augie Fackler <raf@durin42.com>
parents:
43554
diff
changeset
|
815 } |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
816 ) |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
817 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
818 self._state = self._STATE_WANT_SET_VALUE |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
819 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
820 elif special == SPECIAL_START_INDEFINITE_BYTESTRING: |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
821 raise CBORDecodeError( |
43077
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
822 b'indefinite length bytestrings not ' |
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
823 b'allowed as map values' |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
824 ) |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
825 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
826 else: |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
827 raise CBORDecodeError( |
43077
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
828 b'unhandled special item when ' |
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
829 b'expecting map value: %d' % special |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
830 ) |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
831 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
832 self._currentmapkey = None |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
833 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
834 # This value is added to the current set. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
835 elif self._state == self._STATE_WANT_SET_VALUE: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
836 if special == SPECIAL_NONE: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
837 lastc = self._collectionstack[-1] |
43077
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
838 lastc[b'v'].add(value) |
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
839 lastc[b'remaining'] -= 1 |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
840 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
841 elif special == SPECIAL_START_INDEFINITE_BYTESTRING: |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
842 raise CBORDecodeError( |
43077
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
843 b'indefinite length bytestrings not ' |
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
844 b'allowed as set values' |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
845 ) |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
846 |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
847 elif special in ( |
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
848 SPECIAL_START_ARRAY, |
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
849 SPECIAL_START_MAP, |
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
850 SPECIAL_START_SET, |
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
851 ): |
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
852 raise CBORDecodeError( |
43117
8ff1ecfadcd1
cleanup: join string literals that are already on one line
Martin von Zweigbergk <martinvonz@google.com>
parents:
43106
diff
changeset
|
853 b'collections not allowed as set values' |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
854 ) |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
855 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
856 # We don't allow non-trivial types to exist as set values. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
857 else: |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
858 raise CBORDecodeError( |
43077
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
859 b'unhandled special item when ' |
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
860 b'expecting set value: %d' % special |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
861 ) |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
862 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
863 # This value represents the first chunk in an indefinite length |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
864 # bytestring. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
865 elif self._state == self._STATE_WANT_BYTESTRING_CHUNK_FIRST: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
866 # We received a full chunk. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
867 if special == SPECIAL_NONE: |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
868 self._decodedvalues.append( |
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
869 bytestringchunk(value, first=True) |
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
870 ) |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
871 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
872 self._state = self._STATE_WANT_BYTESTRING_CHUNK_SUBSEQUENT |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
873 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
874 # The end of stream marker. This means it is an empty |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
875 # indefinite length bytestring. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
876 elif special == SPECIAL_INDEFINITE_BREAK: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
877 # We /could/ convert this to a b''. But we want to preserve |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
878 # the nature of the underlying data so consumers expecting |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
879 # an indefinite length bytestring get one. |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
880 self._decodedvalues.append( |
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
881 bytestringchunk(b'', first=True, last=True) |
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
882 ) |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
883 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
884 # Since indefinite length bytestrings can't be used in |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
885 # collections, we must be at the root level. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
886 assert not self._collectionstack |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
887 self._state = self._STATE_NONE |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
888 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
889 else: |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
890 raise CBORDecodeError( |
43077
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
891 b'unexpected special value when ' |
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
892 b'expecting bytestring chunk: %d' % special |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
893 ) |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
894 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
895 # This value represents the non-initial chunk in an indefinite |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
896 # length bytestring. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
897 elif self._state == self._STATE_WANT_BYTESTRING_CHUNK_SUBSEQUENT: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
898 # We received a full chunk. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
899 if special == SPECIAL_NONE: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
900 self._decodedvalues.append(bytestringchunk(value)) |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
901 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
902 # The end of stream marker. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
903 elif special == SPECIAL_INDEFINITE_BREAK: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
904 self._decodedvalues.append(bytestringchunk(b'', last=True)) |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
905 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
906 # Since indefinite length bytestrings can't be used in |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
907 # collections, we must be at the root level. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
908 assert not self._collectionstack |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
909 self._state = self._STATE_NONE |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
910 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
911 else: |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
912 raise CBORDecodeError( |
43077
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
913 b'unexpected special value when ' |
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
914 b'expecting bytestring chunk: %d' % special |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
915 ) |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
916 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
917 else: |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
918 raise CBORDecodeError( |
43077
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
919 b'unhandled decoder state: %d' % self._state |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
920 ) |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
921 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
922 # We could have just added the final value in a collection. End |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
923 # all complete collections at the top of the stack. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
924 while True: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
925 # Bail if we're not waiting on a new collection item. |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
926 if self._state not in ( |
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
927 self._STATE_WANT_ARRAY_VALUE, |
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
928 self._STATE_WANT_MAP_KEY, |
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
929 self._STATE_WANT_SET_VALUE, |
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
930 ): |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
931 break |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
932 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
933 # Or we are expecting more items for this collection. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
934 lastc = self._collectionstack[-1] |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
935 |
43077
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
936 if lastc[b'remaining']: |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
937 break |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
938 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
939 # The collection at the top of the stack is complete. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
940 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
941 # Discard it, as it isn't needed for future items. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
942 self._collectionstack.pop() |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
943 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
944 # If this is a nested collection, we don't emit it, since it |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
945 # will be emitted by its parent collection. But we do need to |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
946 # update state to reflect what the new top-most collection |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
947 # on the stack is. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
948 if self._collectionstack: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
949 self._state = { |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
950 list: self._STATE_WANT_ARRAY_VALUE, |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
951 dict: self._STATE_WANT_MAP_KEY, |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
952 set: self._STATE_WANT_SET_VALUE, |
43077
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
953 }[type(self._collectionstack[-1][b'v'])] |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
954 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
955 # If this is the root collection, emit it. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
956 else: |
43077
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
957 self._decodedvalues.append(lastc[b'v']) |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
958 self._state = self._STATE_NONE |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
959 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
960 return ( |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
961 bool(self._decodedvalues), |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
962 offset - initialoffset, |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
963 0, |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
964 ) |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
965 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
966 def getavailable(self): |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
967 """Returns an iterator over fully decoded values. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
968 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
969 Once values are retrieved, they won't be available on the next call. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
970 """ |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
971 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
972 l = list(self._decodedvalues) |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
973 self._decodedvalues = [] |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
974 return l |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
975 |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
976 |
49037
642e31cb55f0
py3: use class X: instead of class X(object):
Gregory Szorc <gregory.szorc@gmail.com>
parents:
49033
diff
changeset
|
977 class bufferingdecoder: |
39440
babad5ebaf0a
cborutil: add a buffering decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39439
diff
changeset
|
978 """A CBOR decoder that buffers undecoded input. |
babad5ebaf0a
cborutil: add a buffering decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39439
diff
changeset
|
979 |
babad5ebaf0a
cborutil: add a buffering decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39439
diff
changeset
|
980 This is a glorified wrapper around ``sansiodecoder`` that adds a buffering |
babad5ebaf0a
cborutil: add a buffering decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39439
diff
changeset
|
981 layer. All input that isn't consumed by ``sansiodecoder`` will be buffered |
babad5ebaf0a
cborutil: add a buffering decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39439
diff
changeset
|
982 and concatenated with any new input that arrives later. |
babad5ebaf0a
cborutil: add a buffering decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39439
diff
changeset
|
983 |
babad5ebaf0a
cborutil: add a buffering decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39439
diff
changeset
|
984 TODO consider adding limits as to the maximum amount of data that can |
babad5ebaf0a
cborutil: add a buffering decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39439
diff
changeset
|
985 be buffered. |
babad5ebaf0a
cborutil: add a buffering decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39439
diff
changeset
|
986 """ |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
987 |
39440
babad5ebaf0a
cborutil: add a buffering decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39439
diff
changeset
|
988 def __init__(self): |
babad5ebaf0a
cborutil: add a buffering decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39439
diff
changeset
|
989 self._decoder = sansiodecoder() |
40031
62160d3077cd
cborutil: change buffering strategy
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39473
diff
changeset
|
990 self._chunks = [] |
62160d3077cd
cborutil: change buffering strategy
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39473
diff
changeset
|
991 self._wanted = 0 |
39440
babad5ebaf0a
cborutil: add a buffering decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39439
diff
changeset
|
992 |
babad5ebaf0a
cborutil: add a buffering decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39439
diff
changeset
|
993 def decode(self, b): |
babad5ebaf0a
cborutil: add a buffering decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39439
diff
changeset
|
994 """Attempt to decode bytes to CBOR values. |
babad5ebaf0a
cborutil: add a buffering decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39439
diff
changeset
|
995 |
babad5ebaf0a
cborutil: add a buffering decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39439
diff
changeset
|
996 Returns a tuple with the following fields: |
babad5ebaf0a
cborutil: add a buffering decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39439
diff
changeset
|
997 |
babad5ebaf0a
cborutil: add a buffering decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39439
diff
changeset
|
998 * Bool indicating whether new values are available for retrieval. |
babad5ebaf0a
cborutil: add a buffering decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39439
diff
changeset
|
999 * Integer number of bytes decoded from the new input. |
babad5ebaf0a
cborutil: add a buffering decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39439
diff
changeset
|
1000 * Integer number of bytes wanted to decode the next value. |
babad5ebaf0a
cborutil: add a buffering decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39439
diff
changeset
|
1001 """ |
40125
b638219a23c3
cborutil: cast bytearray to bytes
Gregory Szorc <gregory.szorc@gmail.com>
parents:
40031
diff
changeset
|
1002 # We /might/ be able to support passing a bytearray all the |
b638219a23c3
cborutil: cast bytearray to bytes
Gregory Szorc <gregory.szorc@gmail.com>
parents:
40031
diff
changeset
|
1003 # way through. For now, let's cheat. |
b638219a23c3
cborutil: cast bytearray to bytes
Gregory Szorc <gregory.szorc@gmail.com>
parents:
40031
diff
changeset
|
1004 if isinstance(b, bytearray): |
b638219a23c3
cborutil: cast bytearray to bytes
Gregory Szorc <gregory.szorc@gmail.com>
parents:
40031
diff
changeset
|
1005 b = bytes(b) |
b638219a23c3
cborutil: cast bytearray to bytes
Gregory Szorc <gregory.szorc@gmail.com>
parents:
40031
diff
changeset
|
1006 |
40031
62160d3077cd
cborutil: change buffering strategy
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39473
diff
changeset
|
1007 # Our strategy for buffering is to aggregate the incoming chunks in a |
62160d3077cd
cborutil: change buffering strategy
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39473
diff
changeset
|
1008 # list until we've received enough data to decode the next item. |
62160d3077cd
cborutil: change buffering strategy
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39473
diff
changeset
|
1009 # This is slightly more complicated than using an ``io.BytesIO`` |
62160d3077cd
cborutil: change buffering strategy
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39473
diff
changeset
|
1010 # or continuously concatenating incoming data. However, because it |
62160d3077cd
cborutil: change buffering strategy
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39473
diff
changeset
|
1011 # isn't constantly reallocating backing memory for a growing buffer, |
62160d3077cd
cborutil: change buffering strategy
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39473
diff
changeset
|
1012 # it prevents excessive memory thrashing and is significantly faster, |
62160d3077cd
cborutil: change buffering strategy
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39473
diff
changeset
|
1013 # especially in cases where the percentage of input chunks that don't |
62160d3077cd
cborutil: change buffering strategy
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39473
diff
changeset
|
1014 # decode into a full item is high. |
39440
babad5ebaf0a
cborutil: add a buffering decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39439
diff
changeset
|
1015 |
40031
62160d3077cd
cborutil: change buffering strategy
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39473
diff
changeset
|
1016 if self._chunks: |
62160d3077cd
cborutil: change buffering strategy
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39473
diff
changeset
|
1017 # A previous call said we needed N bytes to decode the next item. |
62160d3077cd
cborutil: change buffering strategy
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39473
diff
changeset
|
1018 # But this call doesn't provide enough data. We buffer the incoming |
62160d3077cd
cborutil: change buffering strategy
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39473
diff
changeset
|
1019 # chunk without attempting to decode. |
62160d3077cd
cborutil: change buffering strategy
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39473
diff
changeset
|
1020 if len(b) < self._wanted: |
62160d3077cd
cborutil: change buffering strategy
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39473
diff
changeset
|
1021 self._chunks.append(b) |
62160d3077cd
cborutil: change buffering strategy
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39473
diff
changeset
|
1022 self._wanted -= len(b) |
62160d3077cd
cborutil: change buffering strategy
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39473
diff
changeset
|
1023 return False, 0, self._wanted |
62160d3077cd
cborutil: change buffering strategy
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39473
diff
changeset
|
1024 |
62160d3077cd
cborutil: change buffering strategy
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39473
diff
changeset
|
1025 # Else we may have enough data to decode the next item. Aggregate |
62160d3077cd
cborutil: change buffering strategy
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39473
diff
changeset
|
1026 # old data with new and reset the buffer. |
62160d3077cd
cborutil: change buffering strategy
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39473
diff
changeset
|
1027 newlen = len(b) |
62160d3077cd
cborutil: change buffering strategy
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39473
diff
changeset
|
1028 self._chunks.append(b) |
62160d3077cd
cborutil: change buffering strategy
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39473
diff
changeset
|
1029 b = b''.join(self._chunks) |
62160d3077cd
cborutil: change buffering strategy
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39473
diff
changeset
|
1030 self._chunks = [] |
62160d3077cd
cborutil: change buffering strategy
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39473
diff
changeset
|
1031 oldlen = len(b) - newlen |
62160d3077cd
cborutil: change buffering strategy
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39473
diff
changeset
|
1032 |
39440
babad5ebaf0a
cborutil: add a buffering decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39439
diff
changeset
|
1033 else: |
babad5ebaf0a
cborutil: add a buffering decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39439
diff
changeset
|
1034 oldlen = 0 |
babad5ebaf0a
cborutil: add a buffering decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39439
diff
changeset
|
1035 |
babad5ebaf0a
cborutil: add a buffering decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39439
diff
changeset
|
1036 available, readcount, wanted = self._decoder.decode(b) |
40031
62160d3077cd
cborutil: change buffering strategy
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39473
diff
changeset
|
1037 self._wanted = wanted |
39440
babad5ebaf0a
cborutil: add a buffering decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39439
diff
changeset
|
1038 |
babad5ebaf0a
cborutil: add a buffering decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39439
diff
changeset
|
1039 if readcount < len(b): |
40031
62160d3077cd
cborutil: change buffering strategy
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39473
diff
changeset
|
1040 self._chunks.append(b[readcount:]) |
39440
babad5ebaf0a
cborutil: add a buffering decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39439
diff
changeset
|
1041 |
babad5ebaf0a
cborutil: add a buffering decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39439
diff
changeset
|
1042 return available, readcount - oldlen, wanted |
babad5ebaf0a
cborutil: add a buffering decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39439
diff
changeset
|
1043 |
babad5ebaf0a
cborutil: add a buffering decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39439
diff
changeset
|
1044 def getavailable(self): |
babad5ebaf0a
cborutil: add a buffering decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39439
diff
changeset
|
1045 return self._decoder.getavailable() |
babad5ebaf0a
cborutil: add a buffering decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39439
diff
changeset
|
1046 |
43076
2372284d9457
formatting: blacken the codebase
Augie Fackler <augie@google.com>
parents:
42176
diff
changeset
|
1047 |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
1048 def decodeall(b): |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
1049 """Decode all CBOR items present in an iterable of bytes. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
1050 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
1051 In addition to regular decode errors, raises CBORDecodeError if the |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
1052 entirety of the passed buffer does not fully decode to complete CBOR |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
1053 values. This includes failure to decode any value, incomplete collection |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
1054 types, incomplete indefinite length items, and extra data at the end of |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
1055 the buffer. |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
1056 """ |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
1057 if not b: |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
1058 return [] |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
1059 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
1060 decoder = sansiodecoder() |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
1061 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
1062 havevalues, readcount, wantbytes = decoder.decode(b) |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
1063 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
1064 if readcount != len(b): |
43077
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
1065 raise CBORDecodeError(b'input data not fully consumed') |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
1066 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
1067 if decoder.inprogress: |
43077
687b865b95ad
formatting: byteify all mercurial/ and hgext/ string literals
Augie Fackler <augie@google.com>
parents:
43076
diff
changeset
|
1068 raise CBORDecodeError(b'input data not complete') |
39438
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
1069 |
aeb551a3bb8a
cborutil: implement sans I/O decoder
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37942
diff
changeset
|
1070 return decoder.getavailable() |