Main bot (#4)

* Work on communication

Testing only

FIx

test

* Communication work progress

FX

aa

Maybe wrong

Another step forward.

STOP!

* Fixin comms

* View att 1

Fix

33

fx

Final fix

fix

Test

* View - beta version

aa

aa

aaa

aa

Chyba fix

aa

aa

aa

tst

test

FX

Maybe this ?

Fix

last fix ?

dix

* Client beta version search deploy

* Late fix

* Deploy!

* Safeguard against commands being used in dms

* Fixes

* Radiostation control

* Fix bug

* Bugfix

* fx

.trunk/.gitignore

@@ -6,8 +6,4 @@
 plugins
 user_trunk.yaml
 user.yaml
-<<<<<<< HEAD
 tmp
-=======
-tools
->>>>>>> c7dc465 (Parametryzacja "muzyki mojego ludu")

.trunk/trunk.yaml

@@ -2,7 +2,6 @@
 # To learn more about the format of this file, see https://docs.trunk.io/reference/trunk-yaml
 version: 0.1
 cli:
-<<<<<<< HEAD
   version: 1.20.1
 # Trunk provides extensibility via plugins. (https://docs.trunk.io/plugins)
 plugins:
@@ -11,44 +10,10 @@ plugins:
       ref: v1.4.5
       uri: https://github.com/trunk-io/plugins
 # Many linters and tools depend on runtimes - configure them here. (https://docs.trunk.io/runtimes)
-=======
-  version: 1.12.1
-plugins:
-  sources:
-    - id: trunk
-      ref: v0.0.22
-      uri: https://github.com/trunk-io/plugins
-lint:
-  enabled:
-    - actionlint@1.6.25
-    - markdownlint@0.35.0
-    - trivy@0.43.1
-    - trufflehog@3.44.0
-    - pylint
-    - codespell
-    - cspell
-    - git-diff-check
-    - eslint
-    - prettier
-    - semgrep
-    - autopep8
-    - bandit
-    - black
-    - flake8
-    - isort
-    - mypy
-    - pylint
-    - ruff
-    - semgrep
-    - yapf
-    - gitleaks
-
->>>>>>> c7dc465 (Parametryzacja "muzyki mojego ludu")
 runtimes:
   enabled:
     - node@18.12.1
     - python@3.10.8
-<<<<<<< HEAD
 # This is the section where you manage your linters. (https://docs.trunk.io/check/configuration)
 lint:
   enabled:
@@ -66,8 +31,6 @@ lint:
     - trivy@0.50.1
     - trufflehog@3.71.0
     - yamllint@1.35.1
-=======
->>>>>>> c7dc465 (Parametryzacja "muzyki mojego ludu")
 actions:
   disabled:
     - trunk-announce

communication_subroutine.py

@@ -0,0 +1,122 @@
+import logging
+import threading
+import json
+import time
+from queue import Queue, Empty
+from flask import Flask, jsonify, request
+from waitress import serve
+
+HOST_ADDRESS = "192.168.1.191"
+PORT_ADDRESS = 5000
+OUT_COMM_Q = Queue()
+IN_COMM_Q = Queue()
+awaiting_q = []
+incoming_q = Queue()
+app = Flask(__name__)
+
+@app.route("/conjurer", methods=["POST"])
+def answer_external_command():
+    """
+    The function `answer_external_command` logs the request data, loads the data as JSON, logs the
+    record, and then puts the record into an incoming queue before returning a success message.
+    :return: The function `answer_external_command()` is returning a JSON response with the message
+    "SUCCESS".
+    """
+    app.logger.info(request)
+    record = json.loads(request.data)
+    app.logger.info(record)
+    app.logger.info("DATA RECEIVED")
+    incoming_q.put(record)
+    return jsonify("SUCCESS")
+
+@app.route("/conjurer", methods=["GET"])
+def check_alive():
+    """
+    The function "check_alive" returns a JSON response with the message "ALIVE" when the "/conjurer"
+    route is accessed via a GET request.
+    :return: The code snippet is a Flask route that listens for GET requests to the "/conjurer"
+    endpoint. When a GET request is made to this endpoint, the function check_alive() is called, which
+    returns a JSON response with the message "ALIVE".
+    """
+    return jsonify("ALIVE")
+
+def flask_debug(_logger):
+    """
+    The `flask_debug` function starts a Flask application in debug mode without using the reloader.
+    Do not use for production for fucks sake.
+    """
+    _logger.info("Attempt debug")
+    # trunk-ignore(bandit/B201)
+    app.run(debug=True, use_reloader=False, host=HOST_ADDRESS, port=PORT_ADDRESS)
+
+
+def waitress_run(_logger):
+    """
+    The `waitress_run` function serves the `app` on host "0.0.0.0"
+    and port 5000 using the Waitress WSGI server.
+    """
+    _logger.info("Attempt waitress")
+    serve(app, host=HOST_ADDRESS, port=PORT_ADDRESS)
+
+def scan_queue(_logger):
+    """
+    The function `scan_queue` reads data from a queue, logs it, and appends it to another queue.
+
+    :param _logger: The `_logger` parameter is typically an instance of a logging object that is used to
+    record and store log messages. It is commonly used to track the flow of the program, record errors,
+    and provide information for debugging purposes. In this code snippet, the `_logger` object is used
+    to log the
+    """
+    while True:
+        data = OUT_COMM_Q.get()
+        _logger.info(data)
+        awaiting_q.append(data)
+
+def scan_incoming(_logger):
+    """
+    The `scan_incoming` function continuously checks for incoming data, processes it, and logs when data
+    is found.
+
+    :param _logger: The `_logger` parameter in the `scan_incoming` function is a logger object that is
+    used to log messages or information during the execution of the function. It is typically used for
+    debugging, monitoring, or tracking the flow of the program. In this case, the `_logger` is being
+    used
+    """
+    while True:
+        try:
+            answer = incoming_q.get(block=False)
+            _logger.info("DATA FOUND")
+            for record in awaiting_q:
+                if record.uuid in answer.keys():
+                    record.stop = True
+                    record.entries = answer[record.uuid]
+                    IN_COMM_Q.put(record)
+        except Empty:
+            time.sleep(1)
+
+
+def comm_subroutine(logger):
+    """
+    The `comm_subroutine` function starts multiple threads to run different tasks concurrently.
+
+    :param logger: The `logger` parameter in the `comm_subroutine` function is an instance of a logger
+    object that is used for logging messages at various levels (e.g., debug, info, warning, error). In
+    the provided code snippet, the logger is used to log messages at the "info" level
+    """
+    #logger.setLevel(logging.DEBUG)
+    logger.info("Started")
+    threads = []
+    #threads.append(threading.Thread(target=flask_debug, args=(logger,)))
+    threads.append(threading.Thread(target=waitress_run, args=(logger,)))
+    threads.append(threading.Thread(target=scan_queue,args=(logger,)))
+    threads.append(threading.Thread(target=scan_incoming,args=(logger,)))
+
+
+    for worker in threads:
+        worker.start()
+    for worker in threads:
+        worker.join()
+
+if __name__ == "__main__":
+    logging_client = logging.getLogger(__name__)
+    comm_subroutine(logging_client)

conjurer.service

@@ -0,0 +1,11 @@
+[Unit]
+Description=Conjurer
+After=multi-user.target
+
+[Service]
+Type=simple
+ExecStart=/home/pi/Conjurer/env/bin/python3 /home/pi/Conjurer/bot.py
+Restart=on-abort
+
+[Install]
+WantedBy=multi-user.target

conjurer_librarian/conjurer_librarian.py

@@ -0,0 +1,335 @@
+import re
+import logging
+import threading
+import time
+from flask import Flask, jsonify, request
+import netrc
+import json
+import asyncio
+from json.decoder import JSONDecodeError
+from urllib.request import urlopen
+from habanero import Crossref
+from waitress import serve
+from queue import Queue
+import search_bot
+import scrape_bot
+import requests
+NETRC_FILE = r"C:\Users\Activcom.pl\.netrc"
+
+HOST_ADDRESS = "192.168.1.192"
+PORT_ADDRESS = 5001
+MAIN_BOT_ADDRESS = "http://192.168.1.191:5000"
+SEND_RESULTS = "/conjurer"
+BDSM_UUID_TEST = '96b7f85a-1142-4908-8986-62a2ea25a147'
+MAX_CR_RESULTS = 150000
+ENCODING = "utf-8"
+app = Flask(__name__)
+
+librarian_queue = Queue()
+librarian_list = []
+
+class Librarian(object):
+
+    def __init__(self, app, query, uuid) -> None:
+        netrc_mod = netrc.netrc(NETRC_FILE)
+        authTokens = netrc_mod.authenticators("crossref")
+        self.cr = Crossref(mailto=authTokens[0])
+        self.query = query
+        self.uuid = str(uuid)
+        self.limit = MAX_CR_RESULTS
+        self.fetched = 0
+        self.hit = 0
+        self.total = 0
+        self.app = app
+        self.logger = app.logger
+        self.live_results = []
+        self.final_result = []
+        self.not_in_db = []
+        self.search_result_from_cr = {}
+        self.done = False
+
+    async def search_crossref(self, query):
+        self.app.logger.info("STARTED SEARCH")
+        result = self.cr.works(query = query, limit = 1000)
+        self.search_result_from_cr.update(result)
+        self.total = result['message']['total-results']
+        self.fetched += len(result['message']['items'])
+        self.logger.info (self.total)
+        self.logger.info(self.fetched)
+        while self.total > self.fetched and self.limit > self.fetched:
+            result = self.cr.works(query = query, limit = 1000)
+            self.search_result_from_cr.update(result)
+            self.total = result['message']['total-results']
+            self.fetched += len(result['message']['items'])
+            self.logger.info (self.total)
+            self.logger.info(self.fetched)
+            time.sleep(0.1)
+        self.app.logger.info("CROSSREF DONE")
+        #TODO: add to sql with UUID
+        #sql row - title, doi, author, uuid, last retrieved, is_available
+        
+        with open("rr_results.json", "r+", encoding="utf-8") as data_file:
+            # First we load existing data into a dict.
+            try:
+                file_data = json.load(data_file)
+            except JSONDecodeError:
+                file_data = {}
+            summarized_results = []
+            self.app.logger.info("REFINE: Removing all derived works from the list")
+            for item in self.search_result_from_cr['message']['items']:
+                container = "NO"
+                if "container-title" in item:
+                    container = "YES"
+                else:
+                    summarized_results.append({"DOI" : item['DOI'], "title": item['title'] if 'title' in item else None,"type": item['type'] if 'type' in item else None, "container": container})
+            result = {self.uuid : {"total_results": self.search_result_from_cr['message']['total-results'], "on_page" : 1, "summary":summarized_results, "results":self.search_result_from_cr['message']['items']}}
+            if file_data:
+                file_data.update(result)
+            else:
+                file_data = result
+            
+            self.app.logger.info("REFINE: Dumping to file")
+            data_file.truncate(0)
+            data_file.seek(0)
+            json.dump(file_data, data_file, indent=4)
+            return result
+
+    async def check_dois_in_local_db(self, doi):
+        self.app.logger.info("REFINE: Running search in the backend app")
+        coro = asyncio.to_thread(search_bot.search_for_doi, doi, self.live_results, self.app.logger)
+        result = await coro
+        return result
+
+    async def check_if_exists_brute_force(self, page_url):
+        self.app.logger.error("REFINE: Brute force search!")
+        if not page_url.startswith(("http:", "https:")):
+            raise ValueError("URL must start with 'http:' or 'https:'")
+        # trunk-ignore(bandit/B310)
+        with urlopen(page_url) as response:
+            data = response.read()
+            text = data.decode("utf-8")
+            for line in text.splitlines():
+                if re.match(r".*Unfortunately, Sci-Hub doesn't have the requested document.*", line):
+                    return False
+                if m := re.match(r".*<embed type=\"application.pdf\"\s*src=\"(.*\.pdf)",line):
+                    direct_download_link = "https:" + str(m.group(1))
+                    self.app.logger.info (direct_download_link)
+                    return True
+        return False
+
+    async def check_if_exists(self, doi, brute_force = False):
+        result = {}
+        result = await self.check_dois_in_local_db(doi)
+        if brute_force and not result:
+            for item in doi:
+                item_link = "https://sci-hub.se/" + item[0]
+                tmp = {"DOI" : item["DOI"], "exists" : await self.check_if_exists_brute_force(item_link), "data": item}
+                result.update(tmp)
+        return result
+
+    async def refine_query(self, unrefined_reqult, brute_force = False):
+        temp = []
+        refined_result = []
+        for key in unrefined_reqult:
+            self.logger.info("KEY:")
+            self.logger.info(key)
+
+        for item in unrefined_reqult[self.uuid]["summary"]:
+            if item["container"] == "NO" and item["title"]:                
+                refined_result.append(item)
+
+        for item in refined_result:
+            temp.append([item["DOI"], item])
+
+        refined_result = await self.check_if_exists(temp)
+
+        for item in refined_result:
+            if item["exists"]:
+                self.final_result.append(item["data"])
+            else:
+                self.not_in_db.append(item["data"])
+        self.hit = len(self.final_result)
+        return self.final_result
+    #TODO: DOłożyć sprawdzenie czy w rafinowanym pliku już nie mamy częściowego wyniku
+    async def answer_query(self):
+        #TODO: DOłożyć sprawdzenie czy w rafinowanym pliku już nie mamy częściowego wyniku tutaj bo zanim w ogóle otworzymy nierafinowany
+        #Search sql for UUID
+        #SQL SELECT * FROM RESULTS WHERE UUID = uuid
+        self.logger.info(f"Search started {self.uuid}")
+        database = None
+        query = self.query
+        with open("cr_results.json", "r+", encoding="utf-8") as cr_file:
+            #tu logika komunikacji z SQL i cała logika związana z wyszukaniem
+            #ale tymczasowo plik
+            try:
+                database =  json.load(cr_file)
+            except JSONDecodeError:
+                pass
+            #TODO: Zwracać i final_result i not_in_db. Not in db_do pliku - i do ręcznego przeglądania potem.
+            if database:
+                for item in database.keys():
+                    if item in self.uuid:
+                        self.result = await self.refine_query(database)
+                        temp = {}
+                        for item in self.result:
+                            temp[item['DOI']] = {"Title" : item['title'], "type": item['type']}
+                        self.result = temp
+                        temp2 = {}
+                        for item in self.not_in_db:
+                            temp2[item['DOI']] = {"Title" : item['title'], "type": item['type']}
+                        self.not_in_db = temp2
+                        return self.result
+                answer = await self.search_crossref(query=query)
+                database.update(answer)
+                cr_file.truncate(0)
+                cr_file.seek(0)
+                json.dump(database,cr_file)
+                self.result = await self.refine_query(answer)
+            else:
+                answer = await self.search_crossref(query=query)
+                database = answer
+                cr_file.truncate(0)
+                cr_file.seek(0)
+                json.dump(database,cr_file)
+                self.result = await self.refine_query(answer)
+                self.app.logger.info("Refined")
+                self.done = True
+            temp = {}
+            for item in self.result:
+                temp[item['DOI']] = {"Title" : item['title'], "type": item['type']}
+            self.result = temp
+            temp2 = {}
+            for item in self.not_in_db:
+                temp2[item['DOI']] = {"Title" : item['title'], "type": item['type']}
+                self.not_in_db = temp2
+            return self.result
+
+#============================= FLASK INTERNALS===============================
+def flask_debug():
+    """
+    The `flask_debug` function starts a Flask application in debug mode without using the reloader.
+    Do not use for production for fucks sake.
+    """
+    # trunk-ignore(bandit/B201)
+    app.run(debug=True, use_reloader=False, host=HOST_ADDRESS, port=PORT_ADDRESS)
+
+def waitress_run():
+    """
+    The `waitress_run` function serves the `app` on host "0.0.0.0"
+    and port 5000 using the Waitress WSGI server.
+    """
+    serve(app, host=HOST_ADDRESS, port=PORT_ADDRESS)
+
+class BackgroundTaskSearch(threading.Thread):
+    def run(self):
+        loop = asyncio.new_event_loop()  # loop = asyncio.get_event_loop()
+        loop.run_until_complete(self._run())
+        loop.close()
+
+    async def _run(self):
+        while True:
+            database = None
+            ndb_database = None
+            librarian = librarian_queue.get()
+            self.app.logger.info("STARTED")
+            result = await librarian.answer_query()
+            result = {librarian.uuid: result}
+            self.app.logger.info("Saving to file")
+            with open("not_in_db.json", "r+", encoding="utf-8") as ndb_file:
+                try:
+                    ndb_database =  json.load(ndb_file)
+                except JSONDecodeError:
+                    pass
+                if ndb_database:
+                    ndb_database.update(librarian.not_in_db)
+                else:
+                    ndb_database = librarian.not_in_db
+                ndb_file.truncate(0)
+                ndb_file.seek(0)
+                json.dump(ndb_database, ndb_file)
+
+            with open("s_results.json", "r+", encoding="utf-8") as s_file:
+                try:
+                    database =  json.load(s_file)
+                except JSONDecodeError:
+                    pass
+                if database:
+                    self.app.logger.info(database)
+                    self.app.logger.info(result)
+                    database.update(result)
+                else:
+                    database = result
+                self.app.logger.info("DUMPING DATA")
+                s_file.truncate(0)
+                s_file.seek(0)
+                json.dump(database, s_file)
+            self.app.logger.info("FINISHED")
+
+            self.app.logger.info(result)
+            coroutine = asyncio.to_thread(
+            requests.post,
+            f"{MAIN_BOT_ADDRESS}{SEND_RESULTS}",
+            json=result,
+            timeout=360,
+    )       
+            self.app.logger.info("SENT")
+            result = await coroutine
+            self.app.logger.info(result.status_code)
+            self.app.logger.info("SEND CONFIRMED")
+            time.sleep(1)
+            
+#==================================SERVER ROUTES==========================================
+@app.route("/query", methods=["POST"])
+async def query_database():
+    record = json.loads(request.data)
+    app.logger.info(record)
+    app.logger.info(record["query"])
+    app.logger.info(record["UUID"])
+    uuid = record["UUID"]
+    cl = Librarian(app, record["query"], uuid)
+    librarian_queue.put(cl)
+    librarian_list.append(cl)
+    answer_data = (record["query"], record["UUID"], librarian_queue.qsize())
+    return_data = (
+        jsonify(isError=False, message="Success", statusCode=200, data=answer_data),
+        200,
+    )
+    return return_data
+
+@app.route("/get_partial_result", methods=["POST"])
+async def get_partial():
+    record = json.loads(request.data)
+    app.logger.info(record)
+    app.logger.info(record["UUID"])
+    for lib in librarian_list:
+        if lib.uuid == record["UUID"]:
+            answer_data = lib.live_results
+            break
+    return_data = (
+        jsonify(isError=False, message="Success", statusCode=200, data=answer_data),
+        200,
+    )
+    return return_data
+
+#=======================================MAIN===================================================
+if __name__ == "__main__":
+    logger = app.logger
+    logger.setLevel(logging.DEBUG)
+    threads = []
+    threads.append(threading.Thread(target=waitress_run))
+    #threads.append(threading.Thread(target=flask_debug))
+    bgtask = BackgroundTaskSearch()
+    bgtask.app = app
+    threads.append(bgtask)
+    threads.append(threading.Thread(target = scrape_bot.scraper, args=(logger,)))
+    i = 0
+    for worker in threads:
+        try:
+            logger.info(f"App number: {i}")
+            i+=1
+            worker.start()
+        except RuntimeError as e:
+            logger.error("Exploded")
+            print(str(e))
+    for worker in threads:
+        worker.join()

conjurer_librarian/install_librarian_service.sh

@@ -0,0 +1,11 @@
+#!/bin/bash
+python3 -m venv /home/pi/Conjurer_librarian/env
+cp  /home/pi/conjurer/conjurer_librarian/conjurer_librarian.py ./Conjurer_librarian/
+cp  /home/pi/conjurer/conjurer_librarian/requirements_librarian.txt ./Conjurer_librarian/
+cd /home/pi/Conjurer_librarian
+source /home/pi/Conjurer_librarian/env/bin/activate
+./env/bin/python3 -m pip install --upgrade pip
+./env/bin/python3 -m pip install -r requirements_librarian.txt
+deactivate
+
+cp  /home/pi/conjurer/conjurer_librarian/conjurer_librarian.py ./Conjurer_librarian/

conjurer_librarian/requirements_librarian.txt

@@ -0,0 +1,3 @@
+habanero
+waitress
+flask

conjurer_librarian/run_server.bat

@@ -0,0 +1 @@
+c:\conjurer\env\Scripts\activate.bat && c:\conjurer\conjurer_librarian\conjurer_librarian.py

conjurer_librarian/scrape_bot.py

@@ -0,0 +1,93 @@
+import json
+from json.decoder import JSONDecodeError
+from urllib.request import urlopen
+from requests import Timeout,ConnectTimeout, ConnectionError
+from queue import Queue
+import re
+import time
+import random
+import logging
+from threading import Thread
+SCR_DATABASE_PATH = r'C:\\Database\\chunks\\'
+SCR_FILENAME = "40_chunk.txt"
+SCR_ENCODING = "utf-8"
+
+WORK_Q = Queue()
+random.seed()
+def load_ndb_to_q(logger):
+    logger.info("Loader started")
+    while True:    
+        with open("not_in_db.json", "r+", encoding="utf-8") as ndb_file:
+            try:
+                ndb_database =  json.load(ndb_file)
+                for item in ndb_database.keys():
+                    logger.info(item)
+                    url = f"https://sci-hub.se/{item}"
+                    WORK_Q.put([item, url, False])
+                ndb_file.truncate(0)
+            except JSONDecodeError:
+                time.sleep(60*60*2)
+                pass
+        time.sleep(180)
+
+def check_if_exists_brute_force(logger):
+    while True:
+        logger.info("Scraper tick")
+        item = WORK_Q.get()
+        page_url =item[1] 
+        logger.error("REFINE: Brute force search!")
+        if not page_url.startswith(("http:", "https:")):
+            raise ValueError("URL must start with 'http:' or 'https:'")
+        blocked = True
+        try:
+        # trunk-ignore(bandit/B310)
+            with urlopen(page_url) as response:
+                data = response.read()
+                text = data.decode("utf-8")
+                if item[2]:
+                    logger.info("Already found")
+                    time.sleep(180)
+                    blocked = False
+                else:
+                    for line in text.splitlines():
+                        if re.match(r".*Unfortunately, Sci-Hub doesn't have the requested document.*", line):
+                            blocked = False
+                            logger.info("Not found")
+                            item[2] = False
+                        if m := re.match(r".*<embed type=\"application.pdf\"\s*src=\"(.*\.pdf)",line):
+                            blocked = False
+                            direct_download_link = "https:" + str(m.group(1))
+                            logger.info (direct_download_link)
+                            with open(SCR_DATABASE_PATH + SCR_FILENAME, "a", encoding=SCR_ENCODING) as operated_file:
+                                operated_file.write("\n")
+                                operated_file.write(item[0])
+                                item[2] = True
+        except (Timeout,ConnectTimeout, ConnectionRefusedError, ConnectionError):
+            pass
+        if blocked:
+            logger.info(item)
+            logger.info(text)
+            logger.error("Got blocked. Fuck.")
+            time.sleep(60*60*72)
+        # trunk-ignore(bandit/B311)
+        rand = random.randint(1,100)
+        logger.info(f"Sleeping for {3*rand} minutes")
+        time.sleep(180*rand)
+
+def scraper(logger = None):
+    if not logger:
+        logger = logging.getLogger()
+        logger.setLevel("DEBUG")
+        h1 = logging.StreamHandler()
+        logger.addHandler(h1)
+        logger.info("No logger set. Test run")
+  
+    loader = Thread(target = load_ndb_to_q, args = (logger,))
+    scraper = Thread(target = check_if_exists_brute_force, args = (logger,))
+    loader.start()
+    scraper.start()
+    loader.join()
+    scraper.join()
+
+if __name__ == "__main__":
+    scraper()

conjurer_librarian/search_bot.py

@@ -0,0 +1,106 @@
+#TODO: Wpiemdolić to wszystko w klasę z loggerem przysłanym z góry
+
+from queue import Queue, Empty
+from threading import Thread
+q = Queue()
+
+#TODO: DATA FOR TEST ONLY
+#MAXTHREADS = 5
+#DATABASE_PATH = r'C:\\Database\\chunks_1\\'
+
+#TODO: DEPLOYMENT DATA
+MAXTHREADS = 41
+DATABASE_PATH = r'C:\\Database\\chunks\\'
+
+ENCODING = "utf-8"
+CHUNk = "_chunk.txt"
+_sentinel = object()
+result_list = []
+WORK_Q_SIZE = 15500000
+
+def producer(out_q, control_q, filename, logger):
+    with open(DATABASE_PATH + filename, "r+", encoding=ENCODING) as operated_file:
+        logger.info(f"Worker {filename} ")
+        while True:
+            line = operated_file.readline()
+            if not line:
+                break
+            out_q.put(line)
+            try:
+                check = control_q.get(block=False)
+            except Empty:
+                check = False
+                pass
+            if check is _sentinel:
+                logger.info("TERM signal received")
+                control_q.put(check)
+                break
+        logger.info(f"Worker finished: {filename}")
+        out_q.put(_sentinel)
+ 
+#IMPORTANT!!! ONLY ONE CONSUMER THREAD AS WE ARE NOT PUTTING SENTINELS BACK
+#TODO: Change doi to tuple list and only put term when all doi are found => (doi, True)
+def consumer(in_q, control_q, doi, live_results, logger):
+    sentinels = 0
+    for item in doi:
+        result_list.append({"DOI" : item[0], "exists" : False, "data" : item[1]})
+    while True:
+        done_check = True
+        data = in_q.get()
+        if data is _sentinel:
+            logger.info("Worker finished")
+            sentinels += 1
+        else:
+            for item in result_list:
+                if item["DOI"] in data and not item["exists"]:
+                    logger.info(data)
+                    logger.info("HIT")
+                    item["exists"] = True
+                    live_results.append(item)
+                done_check = done_check and item["exists"]
+            if done_check:
+                control_q.put(_sentinel)
+        if sentinels >= MAXTHREADS:
+            logger.info("All workers finished")
+            break
+
+
+def search_for_doi(doi, live_results, logger):
+    threads = []
+    work_q = Queue(maxsize=WORK_Q_SIZE)
+    control_q = Queue()
+    t_cons = Thread(target = consumer, args = (work_q, control_q, doi, live_results, logger))
+    logger.info("Consumer thread created")
+    threads.append(t_cons)
+    for i in range(0,MAXTHREADS):
+        #TODO: TEST DATA
+        #filename = "test" + str(i) + CHUNk
+        #TODO: DEPLOYMENT DATA
+        filename = str(i) + CHUNk
+        logger.info(f"Creating worker thread no: {i}")
+        threads.append(Thread(target = producer, args = (work_q, control_q, filename,logger)))
+    for worker in threads:
+        worker.start()
+    for worker in threads:
+        worker.join()
+    return result_list
+
+if __name__ == "__main__":
+    import logging
+    logger = logging.getLogger()
+    logger.setLevel("DEBUG")
+    h1 = logging.StreamHandler()
+    logger.addHandler(h1)
+    logger.info("TEST RUN")
+    live_result = []
+    logger.info(search_for_doi([
+        ("10.1002/9781118786352.wbieg0998.pub2","DATA"),
+        ("10.1002/j.2050-0416.2002.tb00563.x","DATA"),
+        ("10.1111/j.1365-2958.1994.tb00448.x","DATA"),
+        ("10.2165/00128415-200309690-00017","DATA"),
+        ("10.5772/48313","DATA"),
+        ("10.15803/ijnc.7.2_419","DATA"),
+        ("10.1051/0004-6361/201321596e","DATA"),
+        ("10.2307/40835941","DATA"),
+        ], live_result, logger))
+    logger.info(live_result)

deploy.sh

@@ -0,0 +1,9 @@
+#!/bin/bash
+git pull
+cd ..
+cp ./conjurer/bot.py ./Conjurer/
+cp ./conjurer/settings.json ./Conjurer/
+cp ./conjurer/system_gpt_settings.json ./Conjurer/
+cp ./conjurer/install.sh ./Conjurer/
+cp ./conjurer/requirements.txt ./Conjurer/requirements.txt
+sudo systemctl restart conjurer.service

file_webservice/conjurer_musician.py

@@ -0,0 +1,296 @@
+"""
+The provided Python script sets up a Flask web server to manage a list of music files, with
+functions for rescanning the music folder, updating the music list, and serving the music list via
+API endpoints.
+"""
+import json
+import re
+from pathlib import Path
+from platform import uname
+import threading
+import time
+from datetime import datetime
+from sys import platform
+import logging
+from flask import Flask, jsonify, request
+from waitress import serve
+from logging import handlers
+
+
+HOST_ADDRESS = "192.168.1.15"
+PORT_ADDRESS = 5000
+if platform in ("linux", "linux2"):
+    SEPARATOR_FILE_PATH = "/"
+    if "microsoft-standard" in uname().release:
+        LOGFILE = "/home/mtuszowski/conjurer/discord_mus_service.log"
+        MUSIC_FOLDER = "/mnt/g/Muzyka/"
+        NETRC_FILE = "/home/mtuszowski/.netrc"
+        LOGSTORE = "/home/mtuszowski/conjurer/logs/"
+        ENCODING = "utf-8"
+
+
+    else:
+        LOGFILE = "/home/pi/Conjurer/discord_mus_service.log"
+        NETRC_FILE = "/home/pi/.netrc"
+        LOGSTORE = "/home/pi/RetroPie/logs/"
+        ENCODING = "utf-8"
+        MUSIC_FOLDER = "/home/pi/RetroPie/mp3/"
+
+
+
+music_file_list = []
+def rescan():
+    """
+    The `rescan` function logs a message, scans for mp3 files in a specified folder,
+    and adds them to a list of music files.
+    """
+    logging.info("Rescan triggered")
+    for mp3_item in Path.glob(Path(MUSIC_FOLDER), "**/*.mp3"):
+        temp_music_file = mp3_item.as_posix()
+        if platform == "win32":
+            temp_music_file = temp_music_file.replace("/", "\\")
+        music_file_list.append(temp_music_file)
+
+def thread_rescan():
+    """
+    The `thread_rescan` function periodically triggers a rescan operation after a specified time
+    interval.
+    """
+    logging.info("Starting filesystemupdater")
+    while True:
+        time.sleep(60*60*24)
+        logging.info("Rescan triggered")
+        rescan()
+
+app = Flask(__name__)
+
+def wyszukaj(word_list, how_many):
+    logger = logging.getLogger()
+    return_list = []
+    search_weight = []
+
+    for _ in range(len(music_file_list)):
+        search_weight.append((0, ""))
+
+    time_start = datetime.now()
+    if int(how_many) > 0:
+        skip_start = 2
+    else:
+        skip_start = 1
+    for word in word_list[skip_start:]:
+        token_weight = len(word)
+        logger.info("Słowo kluczowe: %s", word)
+        itr = 0
+        for file in music_file_list:
+            file = file.split(SEPARATOR_FILE_PATH)
+
+            char_remove = [
+                ".",
+                "^",
+                "$",
+                "*",
+                "+",
+                "?",
+                "{",
+                "}",
+                "[",
+                "]",
+                "\\",
+                "/",
+                "|",
+                "(",
+                ")",
+                "!",
+                ",",
+                "-",
+                ":",
+                "mp3",
+            ]
+            all_words = []
+            for f_iter in file:
+                for char in char_remove:
+                    f_iter = remove_characters(f_iter, char)
+                tmp = f_iter.split()
+                all_words.extend(tmp)
+            pingu = 1
+            pattern_len = len(all_words)
+            if platform == "win32":
+                skip = 2
+            else:
+                skip = 4
+            matched_times = 1
+            for itm in all_words[skip:]:
+                pingu += 1
+                pattern = ".*" + word + ".*"
+                if re.match(pattern, itm, re.IGNORECASE):
+                    temp_weight = (
+                        search_weight[itr][0]
+                        + (token_weight + (pingu**1.5) / pattern_len) / matched_times
+                    )
+                    search_weight[itr] = (
+                        temp_weight,
+                        music_file_list[itr],
+                    )
+                    matched_times += 1
+            itr += 1
+
+    logger.info("Stworzylem tablice wag zajęło mi to %s", datetime.now() - time_start)
+    time_start = datetime.now()
+    item_to_search = max_weight(search_weight)
+    itr = 0
+    if item_to_search == 0:
+        return None
+    not_found = True
+    return_list = []
+    if int(how_many) <= 0:
+        logger.info("Jeden plik do zagrania")
+        while not_found:
+            if search_weight[itr][0] == item_to_search:
+                return_list.append(search_weight[itr])
+                return return_list
+            itr += 1
+    else:
+        logger.info("Wiele plików do zagrania")
+        search_weight.sort(key=lambda x: x[0], reverse=True)
+        return_list.extend(search_weight[: int(how_many)])
+        return return_list
+
+def max_weight(lista):
+    """
+    Take a list of weights and return the maximum weight.
+
+    :param lista: It seems like the parameter `lista` is a list of items, possibly representing weights.
+    The function name `max_weight` suggests that the function is intended to find the maximum weight
+    from the list. However, without more context or information about the problem, it's difficult to say
+    for sure what the
+    """
+    maximum_weight = 0
+    for iterator in lista:
+        if iterator[0] > maximum_weight:
+            maximum_weight = iterator[0]
+    return maximum_weight
+
+
+def remove_characters(string, character):
+    """
+    The `remove_characters` function removes all occurrences of a specified character from a given
+    string.
+
+    :param string: The string parameter is the input string from which characters will be removed
+    :param character: The character parameter is the character that you want to remove from the string
+    :return: a new string where all occurrences of the specified character have been removed.
+    """
+    return string.replace(character, "")
+
+
+@app.route("/stream", methods=["GET"])
+async def stream_music():
+    """
+    The function `get_music_list` returns a JSON object containing a list of music files.
+    :return: A JSON response containing a key "music_file_list" with the value of the variable
+    `music_file_list`.
+    """
+    try:
+        m3u8 = Path("/tmp/hls/stream.m3u8")
+        r = Response(m3u8)
+        r.headers["Content-Type"] = "application/mpegURL"
+        return r, 200
+    except FileNotFoundError:
+        return jsonify({"error": "No stream available"}), 404
+
+
+@app.route("/mp3", methods=["GET"])
+def get_music_list():
+    """
+    The function `get_music_list` returns a JSON object containing a list of music files.
+    :return: A JSON response containing a key "music_file_list" with the value of the variable
+    `music_file_list`.
+    """
+    return jsonify({"music_file_list": music_file_list})
+
+
+@app.route("/update_mp3", methods=["POST"])
+def update_music_list():
+    """
+    The function `update_music_list` receives a POST request with a JSON payload, logs the received
+    item, adds it to a music file list, and returns a success message along with the updated record.
+    :return: The function `update_music_list` is returning a tuple containing a JSON response and a
+    status code. The JSON response includes keys `isError`, `message`, `statusCode`, and `data`,
+    with values indicating the success of the operation and the data that was
+    received and added to the `music_file_list`.
+    The status code returned is 200, indicating a successful response.
+    """
+    record = json.loads(request.data)
+    app.logger.info(record["item"])
+    music_file_list.append(record["item"])
+    return_data = (
+        jsonify(isError=False, message="Success", statusCode=200, data=record),
+        200,
+    )
+    return return_data
+
+@app.route("/get_music", methods=["POST"])
+def look_for_playlist():
+    """
+    The function `update_music_list` receives a POST request with a JSON payload, logs the received
+    item, adds it to a music file list, and returns a success message along with the updated record.
+    :return: The function `update_music_list` is returning a tuple containing a JSON response and a
+    status code. The JSON response includes keys `isError`, `message`, `statusCode`, and `data`,
+    with values indicating the success of the operation and the data that was
+    received and added to the `music_file_list`.
+    The status code returned is 200, indicating a successful response.
+    """
+    record = json.loads(request.data)
+    app.logger.info(record)
+    app.logger.info(record["lista_slow"])
+    app.logger.info(record["UUID"])
+    app.logger.info(record["dlugosc_plejlisty"])
+    return_data = wyszukaj(record["lista_slow"],record["dlugosc_plejlisty"])
+
+    return_data = (
+        jsonify(isError=False, message="Success", statusCode=200, data=return_data),
+        200,
+    )
+    return return_data
+
+
+def flask_debug():
+    """
+    The `flask_debug` function starts a Flask application in debug mode without using the reloader.
+    Do not use for production for fucks sake.
+    """
+    # trunk-ignore(bandit/B201)
+    app.run(debug=True, use_reloader=False, host=HOST_ADDRESS, port=PORT_ADDRESS)
+
+def waitress_run():
+    """
+    The `waitress_run` function serves the `app` on host "0.0.0.0"
+    and port 5000 using the Waitress WSGI server.
+    """
+    serve(app, host=HOST_ADDRESS, port=PORT_ADDRESS)
+
+if __name__ == "__main__":
+    logger = logging.getLogger('conjurer_musician')
+    logger.setLevel(logging.DEBUG)
+    formatter = logging.Formatter("%(asctime)s - %(name)s - %(levelname)s - %(message)s")
+    handler = handlers.RotatingFileHandler(
+    filename=LOGFILE,
+    encoding=ENCODING,
+    mode="a",
+    maxBytes=6 * 1024 * 1024,
+    backupCount=6,
+    )
+    handler.setFormatter(formatter)
+    logger.addHandler(handler)
+
+    rescan()
+    logger.info("Started")
+    threads = []
+    threads.append(threading.Thread(target=waitress_run))
+    threads.append(threading.Thread(target=thread_rescan))
+
+    for worker in threads:
+        worker.start()
+
+    for worker in threads:
+        worker.join()

file_webservice/conjurer_musician.service

@@ -0,0 +1,11 @@
+[Unit]
+Description=Conjurer_musician
+After=multi-user.target
+
+[Service]
+Type=simple
+ExecStart=/home/pi/Conjurer/env/bin/python3 /home/pi/Conjurer/conjurer_musician.py
+Restart=on-abort
+
+[Install]
+WantedBy=multi-user.target

file_webservice/install_musician_service.sh

@@ -0,0 +1,11 @@
+#!/bin/bash
+python3 -m venv /home/pi/Conjurer-service/conjurer/file_webservice
+source ./bin/activate
+./bin/python3 -m pip install --upgrade pip
+./bin/python3 -m pip install -r requirements_musician.txt
+deactivate
+
+sudo cp ./conjurer_musician.service /etc/systemd/system/
+sudo systemctl daemon-reload
+sudo systemctl start conjurer_musician.service
+sudo systemctl enable conjurer_musician.service

file_webservice/requirements_musician.txt

@@ -0,0 +1,2 @@
+flask
+waitress

install_main_bot.sh

@@ -0,0 +1,12 @@
+#!/bin/bash
+python3 -m venv /home/pi/Conjurer/env
+source ./env/bin/activate
+./env/bin/python3 -m pip install --upgrade pip
+./env/bin/python3 -m pip install -r requirements_bot.txt
+sed -i -e 's/os.rename/shutil.copy/g' ./env/lib/python3.11/site-packages/spotify_dl/youtube.py
+sed -i '1i\import shutil' ./env/lib/python3.11/site-packages/spotify_dl/youtube.py
+deactivate
+sudo cp ./conjurer.service /etc/systemd/system/
+sudo systemctl daemon-reload
+sudo systemctl start conjurer_musician.service
+sudo systemctl enable conjurer_musician.service

mp3_list.service.py

@@ -1,35 +0,0 @@
-from pathlib import Path, PurePath
-from platform import uname
-from sys import platform
-MUSIC_FOLDER = ""
-if platform in ("linux", "linux2"):
-    SEPARATOR_FILE_PATH = "/"
-    if "microsoft-standard" in uname().release:
-        LOGFILE = "/home/mtuszowski/conjurer/discord_mus_service.log"
-        MUSIC_FOLDER = "/mnt/g/Muzyka/"
-        NETRC_FILE = "/home/mtuszowski/.netrc"
-        LOGSTORE = "/home/mtuszowski/conjurer/logs/"
-        ENCODING = "utf-8"
-        GRAPHICS_PATH = "/home/mtuszowski/conjurer/Conjurer_graphics/"
-
-    else:
-        LOGFILE = "/home/pi/Conjurer/discord_mus_service.log"
-        MEMORY_FIVE_SIARA = "/home/pi/Conjurer/pamiec.json"
-        SYSTEM_GPT_SETTINGS = "/home/pi/Conjurer/system_gpt_settings.json"
-        MEMORY_FIVE_MUZYKA = "/home/pi/Conjurer/pamiec_muzyki.json"
-        MUSIC_FOLDER = "/home/pi/RetroPie/mp3/"
-        SETTINGS_FILE = "/home/pi/Conjurer/settings.json"
-        NETRC_FILE = "/home/pi/.netrc"
-        LOGSTORE = "/home/pi/RetroPie/logs/"
-        ACCIDENT_LOG = "/home/pi/Conjurer/accident_log.json"
-        ENCODING = "utf-8"
-        GRAPHICS_PATH = "/home/pi/RetroPie/Conjurer_graphics/"
-        DIR_PATH_SADOX = "/home/pi/RetroPie/Fansadox/"
-
-music_file_list = []
-for mp3_item in Path.glob(Path(MUSIC_FOLDER), "**/*.mp3"):
-    temp_music_file = mp3_item.as_posix()
-    if platform == "win32":
-        temp_music_file = temp_music_file.replace("/", "\\")
-    music_file_list.append(temp_music_file)
-

requirements_bot.txt

@@ -0,0 +1,15 @@
+discord
+yt_dlp
+spotify_dl
+spotipy
+openai
+eyed3
+numpy
+pdf2image
+PyPDF2
+requests
+spotipy
+tiktoken
+PyNaCl
+flask
+waitress

spotify_dl/youtube.py

@@ -97,8 +97,8 @@ def write_tracks(tracks_file, song_dict):
 def set_tags(temp, filename, kwargs):
     """
      sets song tags after they are downloaded
-    :param temp: contains index used to obtain more info about song being editted
-    :param filename: location of song whose tags are to be editted
+    :param temp: contains index used to obtain more info about song being edited
+    :param filename: location of song whose tags are to be edited
     :param kwargs: a dictionary of extra arguments to be used in tag editing
     """
     song = kwargs["track_db"][int(temp[-1])]

utils/cut_large_file.py

@@ -1,9 +1,30 @@
 # trunk-ignore-all(pylint/C0301)
+"""
+The function `cut_my_life_into_pieces` reads a source file, splits its content based on a file size
+limit, and writes the parts to separate output files in a specified folder.
 
-FILE_SIZE_LIMIT = 100000 * 1024
-SOURCE = "/mnt/n/scimag_2020-05-30.sql/scimag_2020-05-30.sql"
-OUTPUT_FOLDER = "/mnt/n/scimag_2020-05-30.sql/"
-OUTPUT_FILE_SCHEMA = "_scimag_chunk.sql"
+:param lines: The `lines` parameter in the `smart_write` function is a string that contains the text
+content that you want to write to a file. It represents the actual content that will be written to
+the file
+:param file: The code you provided defines two functions: `smart_write` and
+`cut_my_life_into_pieces`. The `smart_write` function encodes input lines to UTF-8, writes them to a
+file, and returns the size of the encoded bytes. The `cut_my_life_into_pieces` function reads
+:return: The functions provided in the code snippet do not explicitly return any values. However,
+the `smart_write` function returns the size of the encoded bytes of the input `lines` in bytes. The
+`cut_my_life_into_pieces` function does not have a return statement, so it does not explicitly
+return any value.
+"""
+
+FILE_SIZE_LIMIT = 50000 * 1024
+
+
+SOURCE = r"C:\Database\dois-2022-02-12\sci-hub-doi-2022-02-12.txt"
+OUTPUT_FOLDER = r"C:\Database\\chunks\\"
+OUTPUT_FILE_SCHEMA = r"_chunk.txt"
+
+#SOURCE = "/mnt/n/scimag_2020-05-30.sql/scimag_2020-05-30.sql"
+#OUTPUT_FOLDER = "/mnt/n/scimag_2020-05-30.sql/"
+#OUTPUT_FILE_SCHEMA = "_scimag_chunk.sql"
 
 
 def smart_write(lines, file):
@@ -18,9 +39,12 @@ def smart_write(lines, file):
     :return: The function `smart_write` returns the size of the encoded bytes of the input `lines` in
     bytes.
     """
-    encoded_bytes = lines.encode("utf-8")
-    size_in_bytes = len(encoded_bytes)
-    file.write(lines)
+    try:
+        encoded_bytes = lines.encode("utf-8")
+        size_in_bytes = len(encoded_bytes)
+        file.write(lines)
+    except:
+        return 0
 
     return size_in_bytes
 
@@ -44,8 +68,9 @@ def cut_my_life_into_pieces(source, output_folder, output_file):
     with open(source, encoding="utf-8") as infile:
         output_size = 0
         output_no = 0
-
+        lineno = 0
         for line in infile:
+            lineno += 1
             if output_size > FILE_SIZE_LIMIT:
                 output_no += 1
                 output_size = 0
@@ -55,4 +80,12 @@ def cut_my_life_into_pieces(source, output_folder, output_file):
                 "a",
                 encoding="utf-8",
             ) as op_file:
-                output_size += smart_write(line, op_file)
+                tmp =  smart_write(line, op_file)
+                if tmp > 0:
+                    output_size += smart_write(line, op_file)
+                else:
+                    print (f'Error at {lineno}')
+                    print(line)
+
+if __name__ == "__main__":
+    cut_my_life_into_pieces(SOURCE,OUTPUT_FOLDER,OUTPUT_FILE_SCHEMA)