import importlib

# Check if xerparser is already installed
try:
    importlib.import_module('xerparser')
    print("xerparser is already installed.")
except ImportError:
    try:
        # Attempt installation
        %pip install xerparser
    except Exception as e:
        print("An error occurred while installing xerparser:", e)

import requests

url = "https://raw.githubusercontent.com/inigmat/exupery/main/files/schedule/MDL4D.xer"

try:
    response = requests.get(url)
    if response.status_code == 200:
        print("Request successful!")
    else:
        print(f"Failed to retrieve data. Status code: {response.status_code}")
except requests.exceptions.RequestException as e:
    print(f"An error occurred: {e}")

from xerparser import Xer, CorruptXerFile

try:
    xer = Xer(response.text)
except CorruptXerFile as e:
    for error in e.errors:
        print(error)

project = list(xer.projects.values())[0]

WBS_LVL = 2
houses = [obj.name for obj in project.wbs_nodes[WBS_LVL:]]
NbHouses= len(houses)
houses

workers = {}
for res in project.resources:
  if res.rsrc_type == "RT_Labor":
    workers[res.rsrc_id] = res.resource.name
NbWorkers = len(workers)

import pandas as pd

tasks_df = pd.DataFrame(columns=['TASK ID','Name','Type', 'WBS ID', 'Duration', 'Successors (ID, Link, Lag)'])

for task in project.tasks:
    task_sucs = []
    for pred_link in task.successors:
        task_suc = pred_link.task.uid
        task_link = pred_link.link
        task_lag = pred_link.lag
        task_sucs.append((task_suc, task_link, task_lag))

    tasks_df = pd.concat([tasks_df, pd.DataFrame(
        {'TASK ID': [task.uid],
         'Name': [task.name],
         'Type': [task.type],
         'WBS ID': [task.wbs_id],
         'Duration': [task.duration],
         'Successors (ID, Link, Lag)': [task_sucs],
         })], ignore_index=True)

tasks_df.head(15)

def get_task_dict_by_wbs_id(df, wbs_id):
    filtered_df = df[df['WBS ID'] == wbs_id]
    task_dict = dict(zip(filtered_df['TASK ID'], filtered_df['Name']))
    return task_dict

wbs_id = '26154' # wbs_id of activites on House 1 (taken from the dataframe above)
task_dict = get_task_dict_by_wbs_id(tasks_df, wbs_id)
TaskNames = tuple(task_dict.values())

durations = {task_id: tasks_df.loc[tasks_df['TASK ID'] == task_id, 'Duration'].values[0] for task_id in task_dict.keys()}
Duration =  list(durations.values())

prec = []
for task in project.tasks:
  if task.uid in task_dict:
    for pred_link in task.successors:
      suc_uid = pred_link.task.uid
      if suc_uid in task_dict:
        suc_name = pred_link.task.name
        prec.append((task.name,suc_name))
Precedences = prec

lags = {}
for rel in project.relationships:
    if str(rel.predecessor.type) == 'TaskType.TT_Mile':
      lags[rel.successor.wbs.name] = rel.lag
lags

ReleaseDate_dict = {key: lags.get(key) for key in sorted(lags)}
ReleaseDate = list(ReleaseDate_dict.values())

print("NbWorkers =", NbWorkers, "\n")
print("NbHouses =", NbHouses, "\n")
print("TaskNames =", TaskNames, "\n")
print("Duration =", Duration, "\n")
print("ReleaseDate =", ReleaseDate, "\n")
print("Precedences =", Precedences, "\n")