Ucalgary_Baja/BajaCloud
4
0
Fork 0
mirror of https://github.com/UofCBaja/BajaCloud.git synced 2025-06-15 13:14:17 -06:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'ReadDB' into Packagers

Browse Source
This commit is contained in:
darkicewolf50 2024-11-30 14:57:44 -07:00
commit 838e53905a
1 changed files with 60 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

85
ReadDB.py
View File

@ -1,42 +1,75 @@
import pandas as pd import pandas as pd
import json import json
from filelock import FileLock, Timeout
import time
# Define the path to the Excel file and the lock file
excel_file_path = "./interview_database.xlsx"
lock_file_path = "./interview_database.xlsx.lock"
def ReadDatabase(): def ReadDatabase():
""" """
Reads the Database Reads the Database
``REQUIRES``: None ``REQUIRES``: None
``PROMISES``: JSON (Interview Avaiable Slots) ``PROMISES``: JSON (Interview Available Slots)
``Develop in part by``: Ahmad ``Developed in part by``: Ahmad
``Contact``: ahmad.ahmad1@ucalgary.ca ``Contact``: ahmad.ahmad1@ucalgary.ca
""" """
# Load the updated Excel file into a pandas DataFrame # Retry parameters
excel_file_path = "./interview_database.xlsx" max_retries = 60 # Maximum number of retries if the file is locked
df = pd.read_excel(excel_file_path) retry_interval = 0.5 # Wait time (in seconds) between retries
# Initialize the dictionary to store the structured data retries = 0
interview_data = {} while retries < max_retries:
try:
# Attempt to acquire a shared read (non-blocking) access
with FileLock(lock_file_path, timeout=0): # Non-blocking, checks if the lock exists
# Load the Excel file into a pandas DataFrame
df = pd.read_excel(excel_file_path)
# Group the DataFrame by Date, Start Time, and Slot for organization # Initialize the dictionary to store the structured data
for _, row in df.iterrows(): interview_data = {}
date = str(row['Date'])
start_time = str(row['Start Time'])
slot = int(row['Slot']) if not pd.isna(row['Slot']) else 0
#Returns amount of interviewees in the slot and if it's empty it will return 0
interviewee_amount = len(str(row['Interviewee Name']).split()) if str(row['Interviewee Name']) != "nan" else 0
# Check if the slot is available for an interviewee to attend # Group the DataFrame by Date, Start Time, and Slot for organization
avaliable_slots = interviewee_amount != slot for _, row in df.iterrows():
if avaliable_slots: date = str(row['Date'])
# Initialize nested structure if not present start_time = str(row['Start Time'])
if date not in interview_data: slot = int(row['Slot']) if not pd.isna(row['Slot']) else 0
interview_data[date] = {}
#Adds the start time and duration if not present # Returns the number of interviewees in the slot; returns 0 if empty
if start_time not in interview_data[date]: interviewee_amount = len(str(row['Interviewee Name']).split()) if str(row['Interviewee Name']) != "nan" else 0
interview_data[date][start_time] = {
'Meeting Duration': row['Meeting Duration'], # Check if the slot is available for an interviewee to attend
} available_slots = interviewee_amount != slot
return interview_data if available_slots:
# Initialize nested structure if not present
if date not in interview_data:
interview_data[date] = {}
# Add the start time and duration if not present
if start_time not in interview_data[date]:
interview_data[date][start_time] = {
'Meeting Duration': row['Meeting Duration'],
}
return interview_data # Successfully read the database
except Timeout:
# File is locked; wait and retry
retries += 1
print(f"File is locked, retrying ({retries}/{max_retries})...")
time.sleep(retry_interval)
# If max retries are exceeded, raise an error
raise RuntimeError("Unable to access the database after multiple attempts due to a file lock.")
# Example usage of the ReadDatabase function
if __name__ == "__main__":
try:
data = ReadDatabase()
print(json.dumps(data, indent=4))
except RuntimeError as e:
print(e)