github issues to spreadsheet

clean.sh

#!/bin/bash
jq -s 'add | map({user: .user.login,
                  milestone: .milestone.title,
                                  labels: .labels | map(.name) | join("|"),
                  created_at,
                  closed_at,
                  updated_at,
                  state,
                  comments,
                  title,
                                  refers: (select(.body) | .body + " " + .title | [match("(?:(?<=\\s)|^)#[0-9]+(?=\\s|$)"; "g") | .string] | unique | join("|")),
                  number,
                  pull_request: (.pull_request != null)
              } + (.labels | map({("_label:" + .name): true}) | add))' $@

fetch.sh

#!/bin/bash
# FIXME: terminating condition may not be succeeding atm
page=1
while [ -n "$page" ]
do
	while [ ! -s issues.$page.json ]
	do
		curl -D heads "$@" "https://api.github.com/repos/scikit-learn/scikit-learn/issues?state=all&per_page=100&page=$page" > issues.$page.json
		sleep 10
	done
	page=$(grep '^Link:' heads | grep -oE '[0-9]+>; rel="next"' | grep -oE '[0-9]+')
done

json-to-csv.py

#!/usr/bin/env python
import sys
import pandas as pd
pd.read_json(sys.stdin).set_index('number').to_csv(sys.stdout)