michaeldorner

from urllib3 import BaseHTTPResponse, Retry
import time

class GitHubRetry(Retry):
    def get_retry_after(self, response: BaseHTTPResponse) -> float | None:
        if 'X-RateLimit-Remaining' in response.headers and 'X-RateLimit-Reset' in response.headers:
            remaining_requests = int(response.headers['X-RateLimit-Remaining'])
            if remaining_requests > 0:
                return None
            else:

michaeldorner

\documentclass[margin=1cm]{standalone}
\usepackage{tikz}

\definecolor{ACMYellow}{RGB}{255, 214, 0}
\definecolor{ACMOrange}{RGB}{252, 146, 0}
\definecolor{ACMRed}{RGB}{253, 27, 20}
\definecolor{ACMLightBlue}{RGB}{131, 206, 226}
\definecolor{ACMGreen}{RGB}{166, 188, 9}
\definecolor{ACMPurple}{RGB}{101, 1, 107}
\definecolor{ACMDarkBlue}{RGB}{9, 53, 122}

michaeldorner

from pathlib import Path

lines_not_200 = []
log_file_dir = '.'
for log_file in Path(log_file_dir).glob('*.log'):
    with open(log_file, 'r') as f:
        for line in f.readlines():
            if not line.startswith('INFO:root:HTTP status 200'):
                lines_not_200 += [line]

michaeldorner

import timeit
import pandas as pd
import matplotlib.pyplot as plt

# measuring

numpy_results = {}
python_results = {}

config = {'number': 100, 'repeat': 100}

michaeldorner

import bz2

import orjson
from requests.adapters import HTTPAdapter, Retry
from requests_cache import CachedSession, SerializerPipeline, Stage, serializers
from requests_futures.sessions import FuturesSession

SERIALIZER = SerializerPipeline([
    serializers.preconf.orjson_preconf_stage,
    orjson,

michaeldorner

import shutil
from pathlib import Path

data_dir = './data' # please speficy the data dir

for path in Path(data_dir).rglob('timeline'):
    print(path)
    shutil.rmtree(path)

michaeldorner

# pylint: disable=locally-disabled, multiple-statements, line-too-long, missing-module-docstring, no-member, missing-class-docstring, missing-function-docstring

import argparse
from pathlib import Path
import hashlib
import bz2
import logging
from datetime import datetime

import orjson

michaeldorner

# pylint: disable=locally-disabled, multiple-statements, line-too-long, missing-module-docstring, no-member, missing-class-docstring, missing-function-docstring

import argparse
from pathlib import Path
from datetime import datetime
import logging
import bz2
from concurrent.futures import as_completed
from urllib.parse import urlparse, parse_qs

michaeldorner

import requests
import json

api_url = 'review.gerrithub.io' # or, for example, 'android-review.googlesource.com'
test_pages = [1, 100, 1000, 10000]

changes = []
for page in test_pages:
    response = requests.get(f'https://{api_url}/changes/?o=MESSAGES&o=DETAILED_ACCOUNTS', timeout=10*60, params={'S': 0})
    changes += json.loads(response.text[len("]}\\\'\n"):])

michaeldorner

from agithub.GitHub import GitHub
import pandas as pd

token = ""

client = GitHub(token=token, paginate=True)

for repo in ['echarts']:
    status, issues = client.repos['apache'][repo].issues.get(state='open')
    assert status==200, str(status)