Analyze Fenix data with CSV

gistfile1.txt

#!/usr/bin/env python3

"""
This script is used to check top locales for Fenix in specific countries,
and try to find a best match in Pontoon locales.

It expects a CSV file stored as "android_data.csv" from this query
https://sql.telemetry.mozilla.org/queries/89302

"""

import csv
import json
import os
from collections import defaultdict
from urllib.parse import quote as urlquote
from urllib.request import urlopen


def getPontoonBestMatch(locale, pontoon_locales):
    # Perfect match
    if locale in pontoon_locales:
        return locale

    # Match with region code
    locale_no_region = locale.split("-")[0]
    if locale_no_region in pontoon_locales:
        return locale_no_region

    # Return mapped locales in some cases, otherwise "N/A"
    map_locales = {
        "en": "en-US",
        "es": "es-ES",
    }

    return map_locales.get(locale_no_region, "N/A")


def main():
    # Get completion stats for locales from Pontoon
    query = """
{
  firefox: project(slug: "firefox-for-android") {
    localizations {
        locale {
            code
        },
        missingStrings,
        totalStrings
    }
  }
}
"""
    pontoon_stats = {}
    try:
        print("Reading Pontoon stats...")
        url = "https://pontoon.mozilla.org/graphql?query={}".format(urlquote(query))
        response = urlopen(url)
        json_data = json.load(response)
        for project, project_data in json_data["data"].items():
            for element in project_data["localizations"]:
                locale = element["locale"]["code"]
                pontoon_stats[locale] = round(
                    (float(element["totalStrings"] - element["missingStrings"]))
                    / element["totalStrings"],
                    4,
                )
    except Exception as e:
        print(e)

    # Add en-US as 100%
    pontoon_stats["en-US"] = 1

    # Get data from CSV file
    csv_stats = defaultdict(dict)
    with open("android_data.csv", newline="") as csv_file:
        reader = csv.DictReader(csv_file)
        for row in reader:
            country_name = row["name"]
            # Only store 5 top locales
            if len(csv_stats[country_name]) >= 5:
                continue
            # Ignore empty locale
            if row["locale"] == "":
                continue
            csv_stats[country_name][row["locale"]] = row["client_count"]

    # Put stats together
    csv_output = ["Country,Locale,Users,Pontoon Locale,Fenix Completion\n"]
    for country, locales in csv_stats.items():
        for locale, locale_users in locales.items():
            pontoon_locale = getPontoonBestMatch(locale, pontoon_stats.keys())
            pontoon_completion = pontoon_stats.get(pontoon_locale, 0)
            csv_output.append(
                f"{country},{locale},{locale_users},{pontoon_locale},{pontoon_completion}\n"
            )

    print("Writing output.csv file")
    with open("output.csv", "w") as f:
        f.writelines(csv_output)


if __name__ == "__main__":
    main()