File: query_repodata.py

package info (click to toggle)
python-msgspec 0.19.0-3
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid
  • size: 7,592 kB
  • sloc: javascript: 23,944; ansic: 20,592; python: 20,470; makefile: 29; sh: 19
file content (79 lines) | stat: -rw-r--r-- 2,101 bytes parent folder | download | duplicates (2)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
import json
import time

import orjson
import requests
import simdjson
import ujson

import msgspec


def query_msgspec(data: bytes) -> list[tuple[int, str]]:
    # Use Struct types to define the JSON schema. For efficiency we only define
    # the fields we actually need.
    class Package(msgspec.Struct):
        name: str
        size: int

    class RepoData(msgspec.Struct):
        packages: dict[str, Package]

    # Decode the data as a `RepoData` type
    repo_data = msgspec.json.decode(data, type=RepoData)

    # Sort packages by `size`, and return the top 10
    return sorted(
        ((p.size, p.name) for p in repo_data.packages.values()), reverse=True
    )[:10]


def query_orjson(data: bytes) -> list[tuple[int, str]]:
    repo_data = orjson.loads(data)
    return sorted(
        ((p["size"], p["name"]) for p in repo_data["packages"].values()), reverse=True
    )[:10]


def query_json(data: bytes) -> list[tuple[int, str]]:
    repo_data = json.loads(data)
    return sorted(
        ((p["size"], p["name"]) for p in repo_data["packages"].values()), reverse=True
    )[:10]


def query_ujson(data: bytes) -> list[tuple[int, str]]:
    repo_data = ujson.loads(data)
    return sorted(
        ((p["size"], p["name"]) for p in repo_data["packages"].values()), reverse=True
    )[:10]


def query_simdjson(data: bytes) -> list[tuple[int, str]]:
    repo_data = simdjson.Parser().parse(data)
    return sorted(
        ((p["size"], p["name"]) for p in repo_data["packages"].values()), reverse=True
    )[:10]


# Download the current_repodata.json file
resp = requests.get(
    "https://conda.anaconda.org/conda-forge/noarch/current_repodata.json"
)
resp.raise_for_status()
data = resp.content

libraries = [
    ("json", query_json),
    ("ujson", query_ujson),
    ("orjson", query_orjson),
    ("simdjson", query_simdjson),
    ("msgspec", query_msgspec),
]

# Run the query with each JSON library, timing the execution
for lib, func in libraries:
    start = time.perf_counter()
    func(data)
    stop = time.perf_counter()
    print(f"{lib}: {(stop - start) * 1000:.2f} ms")