commit fcee973a7a96c51c1b9b7c83a260470f1fcb0b64
Author: Sviatoslav Tsariov <slava982007@gmail.com>
Date:   Thu Sep 7 18:14:18 2023 +0300

    Initial commit

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..2168688
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,134 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+*.json
+.vscode
+.token
+responses
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..e69de29
diff --git a/downloader/.env.example b/downloader/.env.example
new file mode 100644
index 0000000..eaebe28
--- /dev/null
+++ b/downloader/.env.example
@@ -0,0 +1,13 @@
+APP_PORT=
+
+MONGO_USER=
+MONGO_PASS=
+MONGO_HOST=
+MONGO_PORT=
+MONGO_DB=
+MONGO_COLLECTION=
+
+STARS_MIN=
+STARS_MAX=
+
+GITHUB_TOKEN=
diff --git a/downloader/app.py b/downloader/app.py
new file mode 100644
index 0000000..797d772
--- /dev/null
+++ b/downloader/app.py
@@ -0,0 +1,117 @@
+from flask import Flask, request, jsonify
+from pymongo import MongoClient, DESCENDING, TEXT
+from datetime import datetime
+
+from config import App, Mongo, Parser
+from collect import split_by_days
+
+app = Flask(__name__)
+client = MongoClient(f'mongodb://{Mongo.Username}:{Mongo.Password}@{Mongo.Host}:{Mongo.Port}') # MongoDB connection string
+
+db = client[Mongo.Database]  # Database name
+
+if Mongo.Collection not in db.list_collection_names():
+  db.create_collection(Mongo.Collection)
+
+collection = db[Mongo.Collection]  # Collection name
+
+# Specify the field and options for the index
+stars_index_key = [('stargazers.totalCount', DESCENDING)]
+repo_name_index_key = [('nameWithOwner')]
+
+if 'stars' not in collection.index_information():
+    collection.create_index(stars_index_key, name='stars')
+
+if 'repoName' not in collection.index_information():
+    collection.create_index(repo_name_index_key, unique=True, name='repoName')
+
+@app.route('/')
+def hello():
+    return 'Hello, World!'
+
+# Create a new repository
+@app.route('/repositories', methods=['POST'])
+def create_repository():
+    data = request.get_json()
+    result = collection.insert_one(data)
+    return jsonify({'message': 'Repository created', 'id': str(result.inserted_id)}), 201
+
+# Read all repositories with pagination
+@app.route('/repositories', methods=['GET'])
+def get_all_repositories():
+    page = int(request.args.get('page', 1))  # Get the page number (default: 1)
+    page_size = int(request.args.get('page_size', 10))  # Get the page size (default: 10)
+
+    # Get the start and end values for the stargazers.totalCount range from query parameters
+    start_value = int(request.args.get('start_value', Parser.MinStars))
+    end_value = int(request.args.get('end_value', Parser.MaxStars))
+
+    search_filter = None
+    if start_value and end_value:
+        search_filter = {
+            'stargazers.totalCount': {
+                '$gte': start_value,
+                '$lte': end_value
+            }
+        }
+    
+    # Calculate the skip value based on the page and page_size
+    skip = (page - 1) * page_size
+    
+    # Retrieve repositories with pagination
+    repositories = list(collection.find(search_filter).skip(skip).limit(page_size))
+    
+    # Convert ObjectId to string for JSON serialization for each repository
+    for repo in repositories:
+        repo['_id'] = str(repo['_id'])
+    
+    return jsonify(repositories), 200
+
+# Read a specific repository by ID
+@app.route('/repositories/<repository_id>', methods=['GET'])
+def get_repository(repository_id):
+    repository = collection.find_one({'_id': repository_id})
+    if repository:
+        return jsonify(repository), 200
+    else:
+        return jsonify({'message': 'Repository not found'}), 404
+
+# Update a repository by ID
+@app.route('/repositories/<repository_id>', methods=['PUT'])
+def update_repository(repository_id):
+    data = request.get_json()
+    result = collection.update_one({'_id': repository_id}, {'$set': data})
+    if result.modified_count > 0:
+        return jsonify({'message': 'Repository updated'}), 200
+    else:
+        return jsonify({'message': 'Repository not found'}), 404
+
+# Delete a repository by ID
+@app.route('/repositories/<repository_id>', methods=['DELETE'])
+def delete_repository(repository_id):
+    result = collection.delete_one({'_id': repository_id})
+    if result.deleted_count > 0:
+        return jsonify({'message': 'Repository deleted'}), 200
+    else:
+        return jsonify({'message': 'Repository not found'}), 404
+
+# Parse repositories according to min and max stars from env
+@app.route('/parse', methods=['GET'])
+def parse():
+    stars_start = Parser.MinStars
+    stars_finish = Parser.MaxStars
+
+    if stars_start is None or stars_finish is None:
+        return jsonify({'message': 'Invalid input. Both stars_start and stars_finish should be numbers.'}), 400 
+   
+    stars = f'{stars_start}..{stars_finish}'
+    split_by_days(stars, datetime(2007, 1, 1), datetime(2024, 2, 2))
+    try:
+        return jsonify({'message': 'Data parsed'}, 200)
+    except Exception as e:
+        return jsonify({'message': 'Data not parsed', 'stack': str(e)}, 500)
+    
+
+if __name__ == '__main__':
+    app.run(debug=True, port=App.Port)
+
diff --git a/downloader/collect.py b/downloader/collect.py
new file mode 100644
index 0000000..0fb9d66
--- /dev/null
+++ b/downloader/collect.py
@@ -0,0 +1,235 @@
+#!/usr/bin/env python
+
+"""Collect data on the most-starred repos using GitHub's GraphQL API."""
+
+import json
+import os
+import requests
+import time
+from datetime import datetime, timedelta
+
+from config import Parser
+
+token = Parser.GithubToken
+
+def query(payload, variables=None):
+    r = requests.post(
+        'https://api.github.com/graphql',
+        headers={'Authorization': f'bearer {token}'},
+        json={"query": payload, "variables": variables or {}}
+    )
+    r.raise_for_status()
+    return r.json()
+
+repo_query = '''
+query popular_repos($start: String, $num: Int!){
+  rateLimit {
+    cost
+    remaining
+    resetAt
+  }
+  search(query: "is:public %s", type: REPOSITORY, first: $num, after: $start) {
+    repositoryCount
+    pageInfo {
+      hasNextPage
+      endCursor
+    }
+    edges {
+      node {
+        ... on Repository {
+          nameWithOwner
+          createdAt
+          forkCount
+          isFork
+          updatedAt
+          primaryLanguage {
+            name
+          }
+          stargazers {
+            totalCount
+          }
+          watchers {
+            totalCount
+          }
+        }
+      }
+    }
+  }
+}
+'''
+
+count_query = '''
+query {
+  rateLimit {
+    cost
+    remaining
+    resetAt
+  }
+  search(query: "is:public %s", type: REPOSITORY, first: 1) {
+    repositoryCount
+  }
+}
+'''
+
+def get_repos(q, cursor, num):
+    return query(repo_query % q, {'start': cursor, 'num': num})['data']
+
+
+def get_count(q):
+    return query(count_query % q)['data']['search']['repositoryCount']
+
+
+def scrape(q, out_file):
+    path = f'responses/{out_file}'
+    if os.path.exists(path):
+        print('Skipping', path, 'already exists')
+        return
+    all_repos = []
+    cursor = None
+    print('Creating', path)
+    while True:
+        r = get_repos(q, cursor, 100)
+        search = r['search']
+        pi = search['pageInfo']
+        cursor = pi['endCursor']
+        has_next = pi['hasNextPage']
+        total = search['repositoryCount']
+        if total > 2000:
+            raise ValueError(f'Too many results for {q}: {total}')
+        all_repos += [e['node'] for e in search['edges']]
+        print(r['rateLimit'])
+        print(len(all_repos), ' / ', total, cursor)
+        if not has_next or r['rateLimit']['remaining'] < 10:
+            break
+    #print(all_repos)
+    from pymongo import MongoClient
+    client = MongoClient("mongodb://admin:admin@localhost:27017")
+    db = client['git']
+    collection = db['repos']
+    for repo in all_repos:
+      entity = {}
+      filter_dict = {}
+   
+      for key, value in repo.items():
+        if key == "nameWithOwner":
+          filter_dict[key] = value
+        else:
+          entity[key] = value
+
+      collection.update_one(filter_dict, {"$set": entity}, upsert=True)
+    
+    with open(path, 'w') as out:
+        print(out)
+        #json.dump(all_repos, out)
+    time.sleep(4)
+
+
+def scrape_star_range(low, high):
+    """Scrape a simple star range [low, high]."""
+    out_file = f'repos.stars={low}..{high}.json'
+    q = 'stars:%d..%d' % (low, high)
+    scrape(q, out_file)
+
+
+def scrape_breaks():
+    breaks = json.load(open('breaks.json'))
+    for hi, lo in zip(breaks[:-1], breaks[1:]):
+        scrape_star_range(lo, hi - 1)
+
+
+def scrape_star_dates():
+    for stars in range(123, 15, -1):
+        out_file = f'repos.star={stars}.-2015.json'
+        q = 'stars:%d created:<=2015' % stars
+        scrape(q, out_file)
+
+        out_file = f'repos.star={stars}.2016-.json'
+        q = 'stars:%d created:>=2016' % stars
+        scrape(q, out_file)
+
+
+def query_for_star_years(stars, start, end):
+    q = 'stars:%s' % stars
+    if start == 2010 and end == 2023:
+        return q
+    elif start == 2010:
+        return f'{q} created:<={end}'
+    elif end == 2023:
+        return f'{q} created:>={start}'
+    else:
+        return f'{q} created:{start}..{end}'
+
+
+def split_interval(a, b):
+    d = int((b - a) / 2)
+    return [(a, a + d), (a + d + 1, b)]
+
+
+def split_by_year(stars, start, end):
+    if start == 2010 and end == 2023:
+        c = 1001  # we know this will fail.
+    elif start == end:
+        split_by_days(
+            stars,
+            datetime(start, 1, 1),
+            datetime(start, 12, 31)
+        )
+        return
+    else:
+        q = query_for_star_years(stars, start, end)
+        c = get_count(q)
+    if c <= 1000:
+        out_file = f'repos.star={stars}.{start}-{end}.json'
+        print(f'query: {q}')
+        scrape(q, out_file)
+    else:
+        if start == end:
+            raise ValueError(f'Can\'t split any more for {stars} / {start}')
+        print(f'{stars} {start}..{end} -> {c}, will split')
+        for a, b in split_interval(start, end):
+            split_by_year(stars, a, b)
+
+
+def split_by_days(stars, day_start, day_end):
+    start_fmt = day_start.strftime('%Y-%m-%d')
+    end_fmt = day_end.strftime('%Y-%m-%d')
+    q = query_for_star_years(stars, start_fmt, end_fmt)
+    c = get_count(q)
+    if c <= 1000:
+        out_file = f'repos.star={stars}.{start_fmt}-{end_fmt}.json'
+        print(f'query: {q}')
+        scrape(q, out_file)
+    else:
+        days = (day_end - day_start).days
+        if days == 0:
+            raise ValueError(f'Can\'t split any more: {stars} / {day_start} .. {day_end}')
+        for a, b in split_interval(0, days):
+            dt_a = day_start + timedelta(days=a)
+            dt_b = day_start + timedelta(days=b)
+            split_by_days(stars, dt_a, dt_b)
+
+
+def scrape_star_dates_split():
+    #for stars in range(83, 15, -1):
+    for stars in range(40, 15, -1):
+        split_by_year(stars, 2010, 2023)
+
+
+def scrape_range_days():
+    # Scrape from a low star range up, splitting by creation date (which never changes).
+    # ranges = [(15, 20), (21, 25), (26, 30), (31, 35), (36, 40), (41, 45), (46, 49)]
+    #ranges = [(50, 60), (61, 70), (71, 80), (81, 90), (91, 100)]
+    #ranges = ranges + [(100, 119), (120, 139), (140, 159), (160, 179), (180, 200)]
+    #ranges = ranges + [(201, 225), (226, 250), (251, 300), (301, 400), (401, 500)]
+    #ranges = ranges + [(501, 700), (701, 1000), (1001, 1500), (1501, 5000), (5001, 1_000_000)]
+    ranges = [(1001, 1500), (1501, 5000), (5001, 1_000_000)]
+    for a, b in ranges:
+        stars = f'{a}..{b}'
+        split_by_days(stars, datetime(2007, 1, 1), datetime(2024, 2, 2))
+
+
+#if __name__ == '__main__':
+    # scrape_breaks()
+    # scrape_star_dates()
+    # scrape_star_dates_split()
+    #scrape_range_days()
diff --git a/downloader/config.py b/downloader/config.py
new file mode 100644
index 0000000..c13a279
--- /dev/null
+++ b/downloader/config.py
@@ -0,0 +1,29 @@
+from utils.libs.decouple import config, UndefinedValueError
+from utils.utils import str_to_bool
+from utils.logger import logger
+
+def set_conf_value(key):
+  try:
+    value = config(key)
+    if value == '':
+      logger.warn(f'WARNING: The variable {key} is an empty string.')
+    return value
+  except (UndefinedValueError):
+    logger.warn(f'WARNING: Please set the variable {key} in the .env file based on .env.example.')
+    return None
+
+class App:
+  Port=set_conf_value('APP_PORT') or 5000
+
+class Mongo:
+  Username=set_conf_value('MONGO_USER')
+  Password=set_conf_value('MONGO_PASS')
+  Host=set_conf_value('MONGO_HOST')
+  Port=set_conf_value('MONGO_PORT')
+  Database=set_conf_value('MONGO_DB') or 'git'
+  Collection=set_conf_value('MONGO_COLLECTION') or 'repos'
+
+class Parser:
+  MinStars=set_conf_value('STARS_MIN')
+  MaxStars=set_conf_value('STARS_MAX')
+  GithubToken=set_conf_value('GITHUB_TOKEN')
diff --git a/downloader/utils/libs/decouple.py b/downloader/utils/libs/decouple.py
new file mode 100644
index 0000000..f05abd4
--- /dev/null
+++ b/downloader/utils/libs/decouple.py
@@ -0,0 +1,314 @@
+# coding: utf-8
+import os
+import sys
+import string
+from shlex import shlex
+from io import open
+from collections import OrderedDict
+
+# Useful for very coarse version differentiation.
+PYVERSION = sys.version_info
+
+if PYVERSION >= (3, 0, 0):
+  from configparser import ConfigParser
+  text_type = str
+else:
+  from ConfigParser import SafeConfigParser as ConfigParser
+  text_type = unicode
+
+if PYVERSION >= (3, 2, 0):
+  def read_config(parser, file): return parser.read_file(file)
+else:
+  def read_config(parser, file): return parser.readfp(file)
+
+
+DEFAULT_ENCODING = 'UTF-8'
+
+
+# Python 3.10 don't have strtobool anymore. So we move it here.
+TRUE_VALUES = {"y", "yes", "t", "true", "on", "1"}
+FALSE_VALUES = {"n", "no", "f", "false", "off", "0"}
+
+def strtobool(value):
+  if isinstance(value, bool):
+    return value
+  value = value.lower()
+
+  if value in TRUE_VALUES:
+    return True
+  elif value in FALSE_VALUES:
+    return False
+
+  raise ValueError("Invalid truth value: " + value)
+
+
+class UndefinedValueError(Exception):
+  pass
+
+
+class Undefined(object):
+  """
+  Class to represent undefined type.
+  """
+  pass
+
+
+# Reference instance to represent undefined values
+undefined = Undefined()
+
+
+class Config(object):
+  """
+  Handle .env file format used by Foreman.
+  """
+
+  def __init__(self, repository):
+    self.repository = repository
+
+  def _cast_boolean(self, value):
+    """
+    Helper to convert config values to boolean as ConfigParser do.
+    """
+    value = str(value)
+    return bool(value) if value == '' else bool(strtobool(value))
+
+  @staticmethod
+  def _cast_do_nothing(value):
+    return value
+
+  def get(self, option, default=undefined, cast=undefined):
+    """
+    Return the value for option or default if defined.
+    """
+
+    # We can't avoid __contains__ because value may be empty.
+    if option in os.environ:
+      value = os.environ[option]
+    elif option in self.repository:
+      value = self.repository[option]
+    else:
+      if isinstance(default, Undefined):
+        raise UndefinedValueError(
+            '{} not found. Declare it as envvar or define a default value.'.format(option))
+
+      value = default
+
+    if isinstance(cast, Undefined):
+      cast = self._cast_do_nothing
+    elif cast is bool:
+      cast = self._cast_boolean
+
+    return cast(value)
+
+  def __call__(self, *args, **kwargs):
+    """
+    Convenient shortcut to get.
+    """
+    return self.get(*args, **kwargs)
+
+
+class RepositoryEmpty(object):
+  def __init__(self, source='', encoding=DEFAULT_ENCODING):
+    pass
+
+  def __contains__(self, key):
+    return False
+
+  def __getitem__(self, key):
+    return None
+
+
+class RepositoryIni(RepositoryEmpty):
+  """
+  Retrieves option keys from .ini files.
+  """
+  SECTION = 'settings'
+
+  def __init__(self, source, encoding=DEFAULT_ENCODING):
+    self.parser = ConfigParser()
+    with open(source, encoding=encoding) as file_:
+      read_config(self.parser, file_)
+
+  def __contains__(self, key):
+    return (key in os.environ or
+            self.parser.has_option(self.SECTION, key))
+
+  def __getitem__(self, key):
+    return self.parser.get(self.SECTION, key)
+
+
+class RepositoryEnv(RepositoryEmpty):
+  """
+  Retrieves option keys from .env files with fall back to os.environ.
+  """
+
+  def __init__(self, source, encoding=DEFAULT_ENCODING):
+    self.data = {}
+
+    with open(source, encoding=encoding) as file_:
+      for line in file_:
+        line = line.strip()
+        if not line or line.startswith('#') or '=' not in line:
+          continue
+        k, v = line.split('=', 1)
+        k = k.strip()
+        v = v.strip()
+        if len(v) >= 2 and ((v[0] == "'" and v[-1] == "'") or (v[0] == '"' and v[-1] == '"')):
+          v = v[1:-1]
+        self.data[k] = v
+
+  def __contains__(self, key):
+    return key in os.environ or key in self.data
+
+  def __getitem__(self, key):
+    return self.data[key]
+
+
+class RepositorySecret(RepositoryEmpty):
+  """
+  Retrieves option keys from files,
+  where title of file is a key, content of file is a value
+  e.g. Docker swarm secrets
+  """
+
+  def __init__(self, source='/run/secrets/'):
+    self.data = {}
+
+    ls = os.listdir(source)
+    for file in ls:
+      with open(os.path.join(source, file), 'r') as f:
+        self.data[file] = f.read()
+
+  def __contains__(self, key):
+    return key in os.environ or key in self.data
+
+  def __getitem__(self, key):
+    return self.data[key]
+
+
+class AutoConfig(object):
+  """
+  Autodetects the config file and type.
+
+  Parameters
+  ----------
+  search_path : str, optional
+      Initial search path. If empty, the default search path is the
+      caller's path.
+
+  """
+  SUPPORTED = OrderedDict([
+      ('settings.ini', RepositoryIni),
+      ('.env', RepositoryEnv),
+  ])
+
+  encoding = DEFAULT_ENCODING
+
+  def __init__(self, search_path=None):
+    self.search_path = search_path
+    self.config = None
+
+  def _find_file(self, path):
+    # look for all files in the current path
+    for configfile in self.SUPPORTED:
+      filename = os.path.join(path, configfile)
+      if os.path.isfile(filename):
+        return filename
+
+    # search the parent
+    parent = os.path.dirname(path)
+    if parent and parent != os.path.abspath(os.sep):
+      return self._find_file(parent)
+
+    # reached root without finding any files.
+    return ''
+
+  def _load(self, path):
+    # Avoid unintended permission errors
+    try:
+      filename = self._find_file(os.path.abspath(path))
+    except Exception:
+      filename = ''
+    Repository = self.SUPPORTED.get(os.path.basename(filename), RepositoryEmpty)
+
+    self.config = Config(Repository(filename, encoding=self.encoding))
+
+  def _caller_path(self):
+    # MAGIC! Get the caller's module path.
+    frame = sys._getframe()
+    path = os.path.dirname(frame.f_back.f_back.f_code.co_filename)
+    return path
+
+  def __call__(self, *args, **kwargs):
+    if not self.config:
+      self._load(self.search_path or self._caller_path())
+
+    return self.config(*args, **kwargs)
+
+
+# A pré-instantiated AutoConfig to improve decouple's usability
+# now just import config and start using with no configuration.
+config = AutoConfig()
+
+# Helpers
+
+class Csv(object):
+  """
+  Produces a csv parser that return a list of transformed elements.
+  """
+
+  def __init__(self, cast=text_type, delimiter=',', strip=string.whitespace, post_process=list):
+    """
+    Parameters:
+    cast -- callable that transforms the item just before it's added to the list.
+    delimiter -- string of delimiters chars passed to shlex.
+    strip -- string of non-relevant characters to be passed to str.strip after the split.
+    post_process -- callable to post process all casted values. Default is `list`.
+    """
+    self.cast = cast
+    self.delimiter = delimiter
+    self.strip = strip
+    self.post_process = post_process
+
+  def __call__(self, value):
+    """The actual transformation"""
+    if value is None:
+      return self.post_process()
+
+    def transform(s): return self.cast(s.strip(self.strip))
+
+    splitter = shlex(value, posix=True)
+    splitter.whitespace = self.delimiter
+    splitter.whitespace_split = True
+
+    return self.post_process(transform(s) for s in splitter)
+
+
+class Choices(object):
+  """
+  Allows for cast and validation based on a list of choices.
+  """
+
+  def __init__(self, flat=None, cast=text_type, choices=None):
+    """
+    Parameters:
+    flat -- a flat list of valid choices.
+    cast -- callable that transforms value before validation.
+    choices -- tuple of Django-like choices.
+    """
+    self.flat = flat or []
+    self.cast = cast
+    self.choices = choices or []
+
+    self._valid_values = []
+    self._valid_values.extend(self.flat)
+    self._valid_values.extend([value for value, _ in self.choices])
+
+  def __call__(self, value):
+    transform = self.cast(value)
+    if transform not in self._valid_values:
+      raise ValueError((
+          'Value not in list: {!r}; valid values are {!r}'
+      ).format(value, self._valid_values))
+    else:
+      return transform
diff --git a/downloader/utils/libs/loggedRequests.py b/downloader/utils/libs/loggedRequests.py
new file mode 100644
index 0000000..4904072
--- /dev/null
+++ b/downloader/utils/libs/loggedRequests.py
@@ -0,0 +1,264 @@
+import re
+import requests
+from http import HTTPStatus
+import json as JSON
+
+from infra.config import BaseUri, Settings
+from utils.logger import logger, bcolors
+from utils.singleton import SingletonMeta
+
+swagger_api_json_endpoint = '/api-json'
+api_info_urls = {
+  BaseUri.Iguana: 'Iguana',
+  BaseUri.Pyrador: 'Pyrador',
+  BaseUri.Zoo: 'Zoo'
+}
+excluded_endpoints = [
+  ('POST', BaseUri.Iguana + '/api/v1/test/controller'),
+  ('GET', BaseUri.Iguana + '/api/v1/test/controller'),
+  ('DELETE', BaseUri.Iguana + '/api/v1/test/controller'),
+  ('GET', BaseUri.Iguana + '/api/v1/health'),
+  ('GET', BaseUri.Iguana + '/api/v1/metrics'),
+  ('GET', BaseUri.Iguana + '/api/v1/settings'),
+  ('POST', BaseUri.Iguana + '/api/v1/settings'),
+  ('PUT', BaseUri.Iguana + '/api/v1/settings'),
+  ('GET', BaseUri.Iguana + '/api/v1/activity'),
+  ('GET', BaseUri.Iguana + '/api/v1/activity/{activity_id}'),
+  ('POST', BaseUri.Iguana + '/api/v1/doorlock'),
+  ('PUT', BaseUri.Iguana + '/api/v1/profile/set-account-number'),
+  ('PUT', BaseUri.Iguana + '/api/v1/profile/address'),
+  ('PUT', BaseUri.Iguana + '/api/v1/profile/contact'),
+  ('POST', BaseUri.Iguana + '/api/v1/profile/set-firebase-token'),
+  ('PUT', BaseUri.Iguana + '/api/v1/profile/balance'),
+  ('GET', BaseUri.Iguana + '/api/v1/providable-service/{place_id}'),
+  ('POST', BaseUri.Iguana + '/api/v1/light-device/toggle'),
+  ('GET', BaseUri.Iguana + '/api/v1/light-device/state/{device_id}'),
+  ('PUT', BaseUri.Iguana + '/api/v1/user-place/{place_id}'),
+  ('GET', BaseUri.Iguana + '/api/v1/user-place/{place_id}/services'),
+  ('PUT', BaseUri.Iguana + '/api/v1/user-place/set/status'),
+  ('POST', BaseUri.Iguana + '/api/v1/profile/device/to/service'),
+  ('DELETE', BaseUri.Iguana + '/api/v1/profile/device/from/service'),
+  ('GET', BaseUri.Iguana + '/api/v1/profile/place/{place_id}/service/devices/{device_category}'),
+  ('POST', BaseUri.Iguana + '/api/v1/room'),
+  ('GET', BaseUri.Iguana + '/api/v1/room/by/place/{parent_id}'),
+  ('PUT', BaseUri.Iguana + '/api/v1/room/{id}'),
+  ('DELETE', BaseUri.Iguana + '/api/v1/room/{id}'),
+  ('GET', BaseUri.Iguana + '/api/v1/device/list/{type}'),
+  ('DELETE', BaseUri.Iguana + '/api/v1/user-place/qrcode'),
+  ('POST', BaseUri.Iguana + '/api/v1/billing'),
+  ('POST', BaseUri.Iguana + '/api/v1/intercom/acceptCall'), # TODO: test it with notifications
+  ('POST', BaseUri.Iguana + '/api/v1/upload/avatar'), # TODO: unable to test
+  ('POST', BaseUri.Zoo + '/api/v1/notifications/send-notification'),
+  ('POST', BaseUri.Zoo + '/api/v1/notifications/send-sms'),
+  ('DELETE', BaseUri.Zoo + '/api/v1/place/available_services')
+]
+
+class APICoverageTracker(metaclass=SingletonMeta):
+  def __init__(self):
+    self.called_endpoints = {}
+    self.api_info = self.request_api_info(api_info_urls)
+    self.build_called_endpoints()
+
+  def request_api_info(self, urls):
+    api_info = {}
+
+    for url in urls:
+      res = requests.get(url + swagger_api_json_endpoint)
+      api_info[url] = res.json()
+
+    return api_info
+
+  def build_called_endpoints(self):
+    for url, info in self.api_info.items():
+      try:
+        paths = info.get('paths')
+        if not url in self.called_endpoints:
+          self.called_endpoints[url] = {}
+        for path, methods in paths.items():
+          endpoint = url + path
+          self.called_endpoints[url][path] = {}
+          for method, method_info in methods.items():
+            if (method.upper(), endpoint) in excluded_endpoints:
+              continue
+            self.called_endpoints[url][path][method] = 0
+      except Exception as e:
+        logger.error('Error happened while getting api info:', e)
+
+  def endpoint_is_called(self, called_endpoint, method):
+    if not Settings.EnableCoverageStatistics:
+      return
+
+    for url, paths in self.called_endpoints.items():
+      for path, methods in paths.items():
+        endpoint = url + path
+        pattern = re.sub(r'{.+?}', r'[^/]+', endpoint) + '$'
+        if re.match(pattern, called_endpoint) and method.lower() in methods:
+          self.called_endpoints[url][path][method.lower()] += 1
+          return
+
+  def print_coverage(self):
+    def calculate_coverage_statistics(total_urls, covered_urls):
+      if total_urls == 0:
+        return 0
+      coverage_percentage = int(covered_urls / total_urls * 100)
+
+      if coverage_percentage < 50:
+        color = bcolors.FAIL
+      elif coverage_percentage < 75:
+        color = bcolors.WARNING
+      else:
+        color = bcolors.OKGREEN
+
+      statistics = f'{coverage_percentage}% ({covered_urls} / {total_urls})'
+      return f'{color}{statistics}{bcolors.ENDC}'
+
+    def count_urls(gateway_url):
+      urls_num = 0
+      covered_urls_num = 0
+
+      for url, paths in self.called_endpoints.items():
+        for path, methods in paths.items():
+          endpoint = url + path
+          if gateway_url in endpoint:
+            for method, num_of_calls in methods.items():
+              urls_num += 1
+              if num_of_calls > 0:
+                covered_urls_num += 1
+              else:
+                logger.warn(f'{method.upper()} {endpoint} is not covered')
+
+      return urls_num, covered_urls_num
+
+    if not Settings.EnableCoverageStatistics:
+      return
+
+    urls_num_sum = 0
+    covered_urls_num_sum = 0
+
+    urls_info = \
+      [(gateway_name, count_urls(gateway_url)) \
+        for gateway_url, gateway_name in api_info_urls.items()]
+
+    logger.info('Coverage statistics:')
+    logger.info()
+
+    for gateway_name, (urls_num, covered_urls_num) in urls_info:
+      coverage_statistics = calculate_coverage_statistics(urls_num, covered_urls_num)
+      message = f'    {gateway_name}: {coverage_statistics}'
+      logger.info(message)
+
+      urls_num_sum += urls_num
+      covered_urls_num_sum += covered_urls_num
+
+    coverage_statistics = \
+      calculate_coverage_statistics(urls_num_sum, covered_urls_num_sum)
+    logger.info()
+    logger.info(f'    Total: {coverage_statistics}\n')
+
+class Response(requests.Response):
+  def __init__(self, status_code=HTTPStatus.OK):
+    super().__init__()
+    self.status_code = status_code
+
+def log_req(method, url, params=None, data=None, json=None, headers=None):
+  logger.verbose(f'============================================================')
+  logger.verbose(f'[REQUEST] {method} {url}')
+  if params:
+    logger.verbose(f'params: {params}')
+  if data:
+    data = JSON.dumps(data, sort_keys=True, indent=4)
+    logger.verbose(f'data: {data}')
+  if json:
+    json = JSON.dumps(json, sort_keys=True, indent=4)
+    logger.verbose(f'json: {json}')
+  if headers:
+    headers = JSON.dumps(headers, sort_keys=True, indent=4)
+    logger.verbose(f'headers: {headers}')
+
+def log_res(res: requests.Response):
+  req = res.request
+  logger.verbose(f'[RESPONSE] {req.method} {req.url} {res.status_code}')
+  try:
+    json = JSON.dumps(res.json(), sort_keys=True, indent=4).replace('\\"', '"')
+    lines_num = json.count('\n')
+    max_lines_num = Settings.LoggingResponseMaxLinesNum
+    if lines_num <= max_lines_num:
+      logger.verbose(f'json: {json}')
+    else:
+      stats = f'{lines_num}/{max_lines_num}'
+      logger.verbose(f'Maximum number of lines for response exceeded:', stats)
+  except ValueError:
+    logger.verbose('response:', res.content)
+  except Exception as e:
+    logger.verbose(e)
+
+def request(method, url, headers=None, **kwargs):
+  APICoverageTracker().endpoint_is_called(url, method)
+  log_req(method, url, params=kwargs.get('params'), \
+    data=kwargs.get('data'), json=kwargs.get('json'), headers=headers)
+  res = requests.request(method, url, **kwargs)
+  log_res(res)
+  return res
+
+def get(url, params=None, headers=None, **kwargs):
+  method = 'GET'
+  APICoverageTracker().endpoint_is_called(url, method)
+  log_req(method, url, params=params, \
+    data=kwargs.get('data'), json=kwargs.get('json'), headers=headers)
+  res = requests.get(url, params=params, headers=headers, **kwargs)
+  log_res(res)
+  return res
+
+def options(url, headers=None, **kwargs):
+  method = 'OPTIONS'
+  APICoverageTracker().endpoint_is_called(url, method)
+  log_req(method, url, params=kwargs.get('params'), \
+    data=kwargs.get('data'), json=kwargs.get('json'), headers=headers)
+  res = requests.options(url, headers=headers, **kwargs)
+  log_res(res)
+  return res
+
+def head(url, headers=None, **kwargs):
+  method = 'HEAD'
+  APICoverageTracker().endpoint_is_called(url, method)
+  log_req(method, url, params=kwargs.get('params'), \
+    data=kwargs.get('data'), json=kwargs.get('json'), headers=headers)
+  res = requests.head(url, headers=headers, **kwargs)
+  log_res(res)
+  return res
+
+def post(url, data=None, json=None, headers=None, **kwargs):
+  method = 'POST'
+  APICoverageTracker().endpoint_is_called(url, method)
+  log_req(method, url, params=kwargs.get('params'), \
+    data=data, json=json, headers=headers)
+  res = requests.post(url, data=data, json=json, headers=headers, **kwargs)
+  log_res(res)
+  return res
+
+def put(url, data=None, headers=None, **kwargs):
+  method = 'PUT'
+  APICoverageTracker().endpoint_is_called(url, method)
+  log_req(method, url, params=kwargs.get('params'), \
+    data=data, json=kwargs.get('json'), headers=headers),
+  res = requests.put(url, data=data, headers=headers, **kwargs)
+  log_res(res)
+  return res
+
+def patch(url, data=None, headers=None, **kwargs):
+  method = 'PATCH'
+  APICoverageTracker().endpoint_is_called(url, method)
+  log_req(method, url, params=kwargs.get('params'), \
+    data=data, json=kwargs.get('json'), headers=headers)
+  res = requests.patch(url, data=data, headers=headers, **kwargs)
+  log_res(res)
+  return res
+
+def delete(url, headers=None, **kwargs):
+  method = 'DELETE'
+  APICoverageTracker().endpoint_is_called(url, method)
+  log_req(method, url, params=kwargs.get('params'), \
+    data=kwargs.get('data'), json=kwargs.get('json'), headers=headers)
+  res = requests.delete(url, headers=headers, **kwargs)
+  log_res(res)
+  return res
\ No newline at end of file
diff --git a/downloader/utils/logger.py b/downloader/utils/logger.py
new file mode 100644
index 0000000..3f4c473
--- /dev/null
+++ b/downloader/utils/logger.py
@@ -0,0 +1,69 @@
+import inspect
+import traceback
+from utils.utils import trace_origin
+
+class bcolors:
+  HEADER = '\033[95m'
+  OKBLUE = '\033[94m'
+  OKCYAN = '\033[96m'
+  OKGREEN = '\033[92m'
+  WARNING = '\033[93m'
+  FAIL = '\033[91m'
+  ENDC = '\033[0m'
+  BOLD = '\033[1m'
+  UNDERLINE = '\033[4m'
+
+class logger:
+  def debug(*args, **kwargs):
+    from infra.config import Settings
+    if not Settings.EnableDebugMessages:
+      return
+    print(bcolors.HEADER, end='[DEBUG]   ')
+    print(*args, **kwargs)
+    print(bcolors.ENDC, end='')
+
+  def error(*args, **kwargs):
+    print(bcolors.FAIL, end='[ERROR]   ')
+    print(*args, **kwargs)
+    print(bcolors.ENDC, end='')
+
+  def warn(*args, trace_origin_flag=False, stacklevel=0, \
+    print_stack=False, **kwargs):
+
+    print(bcolors.WARNING, end='[WARNING] ')
+    if trace_origin_flag:
+      trace_origin(inspect.currentframe(), stacklevel)
+    if print_stack:
+      print(traceback.format_exc())
+    print(*args, **kwargs)
+    print(bcolors.ENDC, end='')
+
+  def verbose(*args, trace_origin_flag=False, stacklevel=0, **kwargs):
+    from infra.config import Settings
+    if not Settings.EnableVerboseMessages:
+      return
+    if trace_origin_flag:
+      trace_origin(inspect.currentframe(), stacklevel)
+    print(bcolors.OKCYAN, end='[VERBOSE] ')
+    print(*args, **kwargs)
+    print(bcolors.ENDC, end='')
+
+  def log(*args, **kwargs):
+    print(bcolors.OKGREEN, end='[LOG]     ')
+    print(*args, **kwargs)
+    print(bcolors.ENDC, end='')
+
+  def info(*args, **kwargs):
+    print(bcolors.OKBLUE, end='[INFO]    ')
+    print(*args, **kwargs)
+    print(bcolors.ENDC, end='')
+
+  class DisableVerbose(object):
+    def __enter__(self):
+      from infra.config import Settings
+      self.verbose_flag = Settings.EnableVerboseMessages
+      Settings.EnableVerboseMessages = False
+
+    def __exit__(self, exc_type, exc_value, traceback):
+      from infra.config import Settings
+      Settings.EnableVerboseMessages = self.verbose_flag
\ No newline at end of file
diff --git a/downloader/utils/utils.py b/downloader/utils/utils.py
new file mode 100644
index 0000000..fdbc64c
--- /dev/null
+++ b/downloader/utils/utils.py
@@ -0,0 +1,19 @@
+def str_to_bool(val: str):
+  if not val:
+    return False
+  val = val.lower()
+  if val in ('y', 'yes', 't', 'true', 'on', '1'):
+    return True
+  elif val in ('', 'n', 'no', 'f', 'false', 'off', '0'):
+    return False
+  else:
+    raise ValueError('invalid truth value %r' % (val,))
+
+def trace_origin(initial_frame, stacklevel=0):
+  frame = initial_frame.f_back
+  for _ in range(stacklevel + 1):
+    frame = frame.f_back
+  file_name = frame.f_code.co_filename
+  line_number = frame.f_lineno
+  func_name = frame.f_code.co_name
+  print(file_name, ":", line_number, ": ", func_name, ": ")
diff --git a/mongo/docker-compose.yml b/mongo/docker-compose.yml
new file mode 100644
index 0000000..8359359
--- /dev/null
+++ b/mongo/docker-compose.yml
@@ -0,0 +1,20 @@
+version: '3.6'
+services:
+  mongodb:
+    image: mongo:4.2.8
+    container_name: mongo
+    ports:
+      - 27017:27017
+    environment:
+      - MONGO_INITDB_DATABASE=test
+      - MONGO_INITDB_ROOT_USERNAME=admin
+      - MONGO_INITDB_ROOT_PASSWORD=admin
+    volumes:
+      - ./docker-entrypoint-initdb.d:/docker-entrypoint-initdb.d:ro
+      - mongodb:/data/db
+      - mongoconfig:/data/configdb
+    
+volumes:
+  mongodb:
+  mongoconfig:
+
diff --git a/mongo/docker-entrypoint-initdb.d/mongo-init.js b/mongo/docker-entrypoint-initdb.d/mongo-init.js
new file mode 100644
index 0000000..39e866c
--- /dev/null
+++ b/mongo/docker-entrypoint-initdb.d/mongo-init.js
@@ -0,0 +1,13 @@
+db.createUser(
+    {
+        user: "git_downloader",
+        pwd: "password",
+        roles: [
+            {
+                role: "readWrite",
+                db: "git"
+            }
+        ]
+    }
+);
+db.createCollection("repos");