import json
import os
import re

with open('Programming_Languages_Extensions.json') as user_file:
  parsed_json = json.load(user_file)

def get_extension(s: str) -> str:
    m = re.search('\.\w*$', s)
    if m:
        return m.group(0)
    else:
        return ""

def get_lang(ext: str) -> str:
    for i in parsed_json:
        current_extensions = i["extensions"]
        if ext in current_extensions:
            return str(i["name"])

    return "NONE"

def get_type(ext: str) -> str:
    for i in parsed_json:
        current_extensions = i["extensions"]
        if ext in current_extensions:
            return str(i["type"])

    return "NONE"

search_dir = "."
regex = re.compile('\w+\.\w*$')
matches = []
for root, dirs, files in os.walk(search_dir):
  for file in files:
    if regex.match(file):
        matches += [root + "/" + file]


lang_counts = {}
for file in matches:
    with open(file, "rb") as f:
        num_lines = sum(1 for _ in f)
    ext = get_extension(file)
    lang = get_lang(ext)
    if get_type(ext) != "programming": continue
    if lang == "NONE":
        lang_counts[ext] = (num_lines, 1)
    elif lang not in lang_counts:
        lang_counts[lang] = (num_lines, 1)
    else:
        old = lang_counts[lang]
        lang_counts[lang] = (old[0] + num_lines, old[1] + 1)

important_languages = ["C++", "Haskell", "APL", "Python", "Rust", "Hare"]

{k: v for k, v in sorted(lang_counts.items(), key=lambda item: item[1][1] / float(item[1][0]))}

print("Language,percent")
for lang in lang_counts:
    if lang in important_languages:
        d = lang_counts[lang]
        print(lang, float(d[0]) / d[1], sep = ",")