Latest Sub 10 WCA

# acampos@worldcubeassociation.org
# program made after a request from Vasco Vasconcelos
# place this program alongside with the tsv (unziped) export from
# https://www.worldcubeassociation.org/results/misc/WCA_export.tsv.zip
# and run it with
# python program.py
# it takes about 9 min on my computer

import csv
from datetime import date

def competition_date(competition_id):
    with open('WCA_export_Competitions.tsv','rb') as tsvin:
        tsvin = csv.reader(tsvin, delimiter='\t')

        for line in tsvin:
            if line[0] == competition_id:
                end_day = int(line[9])
                end_month = int(line[8])
                year = int(line[5])

                return date(year, end_month, end_day)

        return None

def show_results(labels, results_list, list_of_lists, limit = float("inf"), direction = "asc"):
    """Labels is intuitive. Results_list is the main order list and list_of_lists are other lists that are gonna be ordered as well (eg.: country, name, etc). You can set limit if you wish. Direction = 'asc' if you wanna the lower results first; direction = 'des' if you wanna bigger results first."""

    pos = 1

    prev = None

    out = "Pos"
    for x in labels:
        out += "\t"+x
    print out

    temp = []
    if direction == "asc":
        temp = sorted(zip(results_list, range(len(results_list))))
    elif direction == "des":
        temp = sorted(zip(results_list, range(len(results_list))))[::-1]

    for a, b in temp:
        out = ""
        if a != prev:
            if pos > limit:
                break
            out+="%s)\t"%pos
        else:
            out += "---\t"
        out += str(a)+"\t"
        for x in list_of_lists:
            out += str(x[b])+"\t"
        print out.strip()
        prev = a
        pos += 1

def latest_sub10():

    LIMIT = 50
    id_list = []
    name_list = []
    country_list = []
    first_competition_name = []
    sub10_competition_name = []
    first_competition_date = []
    sub10_competition_date = []
    day_diff = []

    with open('WCA_export_Results.tsv','rb') as tsvin:
        tsvin = csv.reader(tsvin, delimiter='\t')

        prev = None
        this_date = None
        for line in tsvin:

            event = line[1]

            if event != "333":
                continue

            competition_id = line[0]
            if prev != competition_id:
                this_date = competition_date(competition_id)
            prev = competition_id

            this_id = line[7]

            i = -1 # also works if we include a new competitor, since -1 is the lastest on python
            try:
                i = id_list.index(this_id)
            except:
                name = line[6]
                country = line[8]

                id_list.append(this_id)
                name_list.append(name)
                country_list.append(country)
                first_competition_name.append(competition_id)
                day_diff.append(-1)

                first_competition_date.append(this_date)

                sub10_competition_name.append(None)
                sub10_competition_date.append(None)

            best = line[4]

            if best in ["-2", "-1"]:
                continue
            else:
                best = int(best)
                if best < 1000 and (sub10_competition_name[i] == None or (sub10_competition_date[i]-this_date).days>0):
                    sub10_competition_name[i] = line[0]
                    sub10_competition_date[i] = this_date

            if (first_competition_date[i]-this_date).days>0:
                first_competition_date[i] = this_date
                first_competition_name[i] = competition_id

    for i in range(len(id_list)):
        if sub10_competition_name[i] != None:
            delta = sub10_competition_date[i] - first_competition_date[i]
            day_diff[i] = delta.days

    list_of_lists = [name_list, country_list, first_competition_name, sub10_competition_name]
    labels = ["Days", "Name", "Country", "1st comp", "1st sub10 comp"]
    show_results(labels, day_diff, list_of_lists, LIMIT, "des")

latest_sub10()