def setUpClass(cls) -> None:
#Test database setup
cls.dbConnector = DatabaseConnector(
databaseFileName="testLanguageDB.db")
cls.dbConnector.createDatabase()
cls.dbConnector.openDatabaseConnection()
cls.dbConnector.executeSQL(
sql=
"CREATE TABLE Languages (ID INTEGER, Language TEXT, Bytes_of_Code INTEGER, PRIMARY KEY(ID))"
)
#Test data
cls.testData = {'testLang1': 7357, 'testLang2': 5}
cls.dataComparison = [(0, 'testLang1', 7357), (1, 'testLang2', 5)]
#Commit class setup
cls.lang = Languages(dbConnection=cls.dbConnector,
oauthToken="token",
repository="repo",
username="******",
url="url")
def core_before_request():
""" To run before each request"""
my = None
g.db = db
languages_object = Languages()
g.languages = languages_object.get_languages(0)
get_headers()
# Check that user has login
if 'user_id' in session:
# get user_id from session
user_id = session['user_id']
# get the user's personal data.
my = g.db.users.find_one({ '_id' : ObjectId(user_id) })
# If user_id not exist in the user list g.my is None
if my:
g.my = my
# get user language
g.lan = g.my['lan']
g.language = g.languages[g.lan]
get_hash_admin()
import re
from flask import Blueprint, request, session, g, render_template, url_for, redirect
from pymongo import ASCENDING, DESCENDING
from pymongo.objectid import ObjectId
from pymongo.errors import InvalidId, PyMongoError
# Imports inside bombolone
from decorators import check_authentication, check_admin, get_hash_pages
from languages import Languages
from validators import CheckValue
MODULE_DIR = 'modules/pages'
pages = Blueprint('pages', __name__)
check = CheckValue() # Check Value class
languages_object = Languages()
class Pages(object):
""" This class allows to :
- get_page
- reset
- new
- remove
"""
page = {}
type_label = {}
len_of_label = 0
message = None # Error or succcess message
def startDataCollection(self) -> None:
def _collectData(collector) -> int or bool:
data = collector.getData()
collector.insertData(dataset=data[0])
return collector.iterateNext(data[1])
def _scrapeData(collector) -> int or bool:
collector.insertData()
return 0
def _showProgression(collector, maxIterations: int) -> None:
for iteration in tqdm(range(0, abs(maxIterations) - 1), ):
_collectData(collector)
databaseConnection = self.checkForFile()
self.createFileTablesColumns(dbConnection=databaseConnection)
branchCollector = Branches(
dbConnection=self.dbConnector,
oauthToken=self.token,
repository=self.repository,
username=self.username,
url=
"https://api.github.com/repos/{}/{}/branches?per_page=100&page={}",
)
forksCollector = Forks(
dbConnection=self.dbConnector,
oauthToken=self.token,
repository=self.repository,
username=self.username,
url="https://api.github.com/repos/{}/{}/forks?per_page=100&page={}",
)
issuesCollector = Issues(
dbConnection=self.dbConnector,
oauthToken=self.token,
repository=self.repository,
username=self.username,
url=
"https://api.github.com/repos/{}/{}/issues?state=all&per_page=100&page={}",
)
languageCollector = Languages(
dbConnection=self.dbConnector,
oauthToken=self.token,
repository=self.repository,
username=self.username,
url=
"https://api.github.com/repos/{}/{}/languages?per_page=100&page={}",
)
repositoryCollector = Repository(
dbConnection=self.dbConnector,
oauthToken=self.token,
repository=self.repository,
username=self.username,
url="https://api.github.com/repos/{}/{}?per_page=100&page={}",
)
print("\nRepository Languages")
languagePages = _collectData(languageCollector) # One request only
_showProgression(languageCollector, languagePages)
print("\nRepository Information")
repositoryPages = _collectData(repositoryCollector) # One request only
_showProgression(repositoryCollector, repositoryPages)
print("\nRepository Branches")
branchPages = _collectData(branchCollector) # Estimated < 10 requests
_showProgression(branchCollector, branchPages)
print("\nRepository Forks")
forkPages = _collectData(forksCollector) # Estimated < 10 requests
_showProgression(forksCollector, forkPages)
print("\nRepository Issues")
issuePages = _collectData(issuesCollector) # Estimated < 20 requests
_showProgression(issuesCollector, issuePages)
commitsID = 0
branchList = self.dbConnector.selectColumn(table="Branches",
column="Name")
for branch in branchList:
print("\nRepository Commits from Branch {}".format(branch[0]))
commitsCollector = Commits(
dbConnection=self.dbConnector,
id=commitsID,
oauthToken=self.token,
repository=self.repository,
sha=branch[0],
username=self.username,
url=
"https://api.github.com/repos/{}/{}/commits?per_page=100&page={}&sha={}",
)
commitPages = _collectData(
commitsCollector) # Estimated to have the most requests
_showProgression(commitsCollector, commitPages)
commitsID = commitsCollector.exportID()
# TODO: Implement a loading bar for the Files module
# TODO: Reduce complexity where possible in the Files module
# Creates a combined list of every commit paired with its corresponding branch
branchList = self.dbConnector.selectColumn(table="Commits",
column="Branch")
commitSHAList = self.dbConnector.selectColumn(table="Commits",
column="Commit_SHA")
# https://www.geeksforgeeks.org/python-merge-two-lists-into-list-of-tuples/
mergedList = tuple(zip(branchList, commitSHAList))
filesID = 0
for pair in mergedList:
branch = pair[0][0]
commit = pair[1][0]
print("\nRepository Files from Branch {} from Commit {}".format(
branch, commit))
filesCollector = Files(
commitSHA=commit,
branch=branch,
dbConnection=self.dbConnector,
id=filesID,
repository=self.repository,
username=self.username,
url="https://github.com/{}/{}/commit/{}",
)
_scrapeData(filesCollector)
filesID = filesCollector.exportID()
