Fixing librarian result (#6)

* Formatting and additional logging for bugfix

* Formatting and additional logging for bugfix

* Change of log location

* fixing_librarian_result

* Hopefully final fix that will be needed

* Temporary

* Glebokie gardlo

* Fix in scrape_bot

* Fix that was needed.

* Scraper settings

* Small fix in scraping

* FIxing bad  naming convention

* Log message fix

* Test of deep search

* Fix in deep search

* Refactoring

* WHat and idiot coded that....
Ooops. That was me. A month ago.

* Refactoring continued

* Bugfix

* FIx

* Not needed after fix

.gitignore

@@ -197,3 +197,7 @@ node_modules/prettier/esm/parser-postcss.mjs
 node_modules/prettier/esm/parser-typescript.mjs
 node_modules/prettier/esm/parser-yaml.mjs
 node_modules/prettier/esm/standalone.mjs
+cr_results.json
+not_in_db.json
+rr_results.json
+s_results.json

.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_librarian/conjurer_librarian.py

@@ -1,190 +1,502 @@
-import re
+"""
+This module contains the implementation of the Librarian class and
+related functions for searching and refining queries.
+
+Classes:
+-   Librarian: Represents a librarian object that performs search and
+    refinement operations on queries
+
+Functions:
+-   flask_debug: Starts a Flask application in debug mode without using the reloader.
+-   waitress_run: Serves the Flask application using the Waitress WSGI server.
+-   BackgroundTaskSearch: Represents a background task for running the
+    Librarian object asynchronously
+"""
+
+import asyncio
+import json
 import logging
+import netrc
 import threading
 import time
-from flask import Flask, jsonify, request
-import netrc
-import json
 from json.decoder import JSONDecodeError
-from platform import uname
-from sys import platform
-from urllib.request import urlopen
+from logging import handlers
+from queue import Queue
+
+import requests
+import scrape_bot
+import search_bot
+from flask import Flask, jsonify, request
 from habanero import Crossref
 from waitress import serve
 
-if platform in ("linux", "linux2"):
-    SEPARATOR_FILE_PATH = "/"
-    if "microsoft-standard" in uname().release:
-        NETRC_FILE = "/home/mtuszowski/.netrc"
-    else:
-        NETRC_FILE = "/home/pi/.netrc"
-elif platform == "win32":
-    NETRC_FILE = "C:\\Users\\mtusz\\.netrc"
-
-#HOST_ADDRESS = "192.168.1.191"
-HOST_ADDRESS = "0.0.0.0"
+# Constants
+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 = 7000
 
+ENCODING = "utf-8"
+
+app = Flask(__name__)
+
+librarian_queue = Queue()
+librarian_list = []
+
+
+# trunk-ignore(pylint/R0902)
 class Librarian(object):
+    """
+    Represents a librarian object that performs search and refinement operations on queries.
+    """
 
-    def __init__(self) -> None:
+    def __init__(self, _app, query, uuid, _deep_search) -> None:
+        """
+        Initializes a Librarian object.
+
+        Args:
+        - _app: The Flask application object.
+        - query: The query to be searched.
+        - uuid: The unique identifier for the search.
+
+        Attributes:
+        - cr: The Crossref object for performing the search.
+        - query: The query to be searched.
+        - uuid: The unique identifier for the search.
+        - limit: The maximum number of search results to fetch.
+        - fetched: The number of search results fetched so far.
+        - hit: The number of search results that match the refinement criteria.
+        - total: The total number of search results.
+        - app: The Flask application object.
+        - live_results: A list to store live search results.
+        - final_result: A list to store the final refined search results.
+        - not_in_db: A list to store search results that are not in the local database.
+        - search_result_from_cr: A dictionary to store the search results from Crossref.
+        - done: A flag indicating if the search is done.
+        """
         netrc_mod = netrc.netrc(NETRC_FILE)
-        authTokens = netrc_mod.authenticators("crossref")
-        self.cr = Crossref(mailto=authTokens[0])
-        self.limit = 1000
+        auth_tokens = netrc_mod.authenticators("crossref")
+        self.cr = Crossref(
+            mailto=auth_tokens[0],
+            ua_string=f"Conjurer project. mailto:{auth_tokens[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.live_results = []
+        self.final_result = {}
+        self.not_in_db = {}
+        self.search_result_from_cr = {}
+        self.done = False
+        self.deep_search = _deep_search
 
-    def search_crossref(self, query, uuid):
-        search_result_from_cr = self.cr.works(query = query, limit = self.limit)
-        self.total = search_result_from_cr['message']['total-results']
-        self.fetched = len(search_result_from_cr['message']['items'])
-        #add to sql with UUID
-        #sql row - title, doi, author, uuid, last retrieved, is_available
-        with open("results.json", "r+", encoding="UTF-8") as data_file:
+    async def search_crossref(self, query, deep_search=False):
+        """
+        Performs a search on Crossref for the given query.
+
+        Args:
+        - query: The query to be searched.
+
+        Returns:
+        - result: The search result from Crossref.
+
+        Raises:
+        - None.
+        """
+
+        self.app.logger.info("STARTED SEARCH")
+        
+        if not deep_search:
+            cr_result = self.cr.works(query=query, limit=1000)
+            self.search_result_from_cr.update(cr_result)
+            self.total = cr_result["message"]["total-results"]
+            self.fetched += len(cr_result["message"]["items"])
+            self.app.logger.info(self.total)
+            self.app.logger.info(self.fetched)
+            while self.total > self.fetched and self.limit > self.fetched:
+                tmp_result = self.cr.works(query=query, limit=1000, offset=self.fetched)
+                cr_result["message"]["items"].extend(tmp_result["message"]["items"])
+                self.total = tmp_result["message"]["total-results"]
+                self.fetched = len(cr_result["message"]["items"])
+                self.app.logger.info(self.total)
+                self.app.logger.info(self.fetched)
+                time.sleep(0.1)
+
+        else:
+            cr_result = self.cr.works(query=query, cursor_max=10000, cursor='*', progress_bar = True)
+            result = cr_result[0]
+            for item in cr_result[1:]:
+                result["message"]["items"].extend(item["message"]["items"])
+                self.total = item["message"]["total-results"]
+                self.fetched = len(result["message"]["items"])
+                self.app.logger.info(self.total)
+                self.app.logger.info(self.fetched)
+            cr_result = result
+            self.app.logger.info("Total, fetched:")
+            self.app.logger.info(self.total)
+            self.app.logger.info(self.fetched)
+            self.search_result_from_cr.update(cr_result)
+            self.total = cr_result["message"]["total-results"]
+            self.app.logger.info("CROSSREF DONE")
+
+            self.app.logger.info("CROSSREF DONE")
+        with open("cr_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 = []
-            # Join new_data with file_data inside emp_details
-            summarized_results = []
-            for item in search_result_from_cr['message']['items']:
-                container = "NO"
-                if "container-title" in item:
-                    container = "YES"
-                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 = {"UUID": uuid, "total_results": search_result_from_cr['message']['total-results'], "on_page" : 1, "summary":summarized_results, "results":search_result_from_cr['message']['items'],  }
-            file_data.append(result)
-            print("Saving")
+                file_data = {}
+            data_file.truncate(0)
             data_file.seek(0)
-            # convert back to json.
+            tmp = {self.uuid : self.search_result_from_cr}
+            if file_data:
+                file_data.update(tmp)
+            else:
+                file_data = tmp
             json.dump(file_data, data_file, indent=4)
-            return result
+        return cr_result
 
 
-    def check_if_exists(self,page_url):
-        #TODO: Spowolnic
-        #TODO: Sprawdzac po mirrorach
-        #TODO: sprawdzac w tym jebanym pliku
-        in_scihub_db = True
-        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 None
-        if in_scihub_db:
-            return text
-        return None
+    async def refine_search(self, unrefined_result):
+        """
+        Refines the search query based on the unrefined search result.
 
-    def download(self, page_url):
-        if response := self.check_if_exists(page_url):
-            for line in response.splitlines():
-                if m := re.match(r".*<embed type=\"application.pdf\"\s*src=\"(.*\.pdf)",line):
-                    return "https:" + str(m.group(1))
-        return None
+        Args:
+        - unrefined_result: The unrefined search result.
 
-    def provide_sci_hub_link(self, page_url):
-        if self.check_if_exists(page_url):
-            return page_url
-        return None
+        Returns:
+        - refined_result: The refined search result.
 
-    def refine_query(self, unrefined_reqult):
-        print("Refine result")
-        refined_result = []
-        for item in unrefined_reqult["summary"]:
-            if item["container"] == "NO" and item["title"]:
-                item_link = "https://sci-hub.se/" + str(item['DOI'])
-                if self.check_if_exists(item_link):
-                    refined_result.append(item)
-                    print ("HIT")
-                    print(item["title"])
-                time.sleep(0.01)
-        print("Existing hits")
-        self.hit = len(refined_result)
+        Raises:
+        - None.
+        """
+        summarized_results = []
+        self.app.logger.info("REFINE: Removing all derived works from the list")
+        for item in unrefined_result["message"]["items"]:
+            summarized_results.append(
+                {
+                    "DOI": item["DOI"],
+                    "title": item["title"] if "title" in item else None,
+                    "type": item["type"] if "type" in item else None,
+                }
+            )
+
+        partial_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"],
+            }
+        }
+        self.app.logger.info("REFINE: Dumping to file")
+        temp = []
+        refined_result = {}
+        for key in partial_result:
+            self.app.logger.info("KEY:")
+            self.app.logger.info(key)
+
+        for item in partial_result[self.uuid]["summary"]:
+            if item["title"]:
+                temp.append(item)
+
+        for item in temp:
+            refined_result[item["DOI"]]=  item
+        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 = {}
+            data_file.truncate(0)
+            data_file.seek(0)
+            tmp = {self.uuid: refined_result}
+            if file_data:
+                file_data.update(tmp)
+            else:
+                file_data = tmp
+            json.dump(file_data, data_file, indent=4)
         return refined_result
 
-    def answer_query(self, query, uuid):
-        #Search sql for UUID
-        #SQL SELECT * FROM RESULTS WHERE UUID = uuid
-        print("Answer result")
-        uuid_found = False
-        database = None
-        with open("results.json", "r", encoding="UTF-8") as new_file:
-            #tu logika komunikacji z SQL i cała logika związana z wyszukaniem
-            #ale tymczasowo plik
-            try:
-                database =  json.load(new_file)
-            except JSONDecodeError:
-                pass
-        if database:
-            for item in database:
-                if item["UUID"] == uuid:
-                    print (item["UUID"])
-                    uuid_found = True
-                    return self.refine_query(item)
+    async def check_if_exists(self, refined_result):
+        """
+        Checks if the given DOI exists.
 
-        if not uuid_found:
-            answer = self.search_crossref(query=query, uuid=uuid)
-            return self.refine_query(answer)
+        Args:
+        - doi: The DOI to be checked.
+        - brute_force: A flag indicating if brute force method should be used.
+
+        Returns:
+        - result: The search result.
+
+        Raises:
+        - None.
+        """
+        result = {}
+        self.app.logger.info("REFINE: Running search in the backend app")
+        dois = []
+        for item, value in refined_result.items():
+            dois.append([item, value])
+        coro = asyncio.to_thread(
+            search_bot.search_for_doi, dois, self.live_results, self.app.logger
+        )
+        result = await coro
+        result_list = []
+        result_no_db = []
+        for item in result:
+            if item["exists"]:
+                result_list.append(item)
+            else:
+                result_no_db.append(item)
+        self.hit = len(result)
+        return result_list, result_no_db
+
+
+    async def answer_query(self, deep_search=False):
+        """
+        Answers the search query.
+
+        Args:
+        - None.
+
+        Returns:
+        - result: The search result.
+
+        Raises:
+        - None.
+        """
+        self.app.logger.info(f"Search started {self.uuid}")
+        cr_result = await self.search_crossref(query=self.query, deep_search=deep_search)
+        refined_result = await self.refine_search(cr_result)
+        answer, negative_answer = await self.check_if_exists(refined_result)
+
+        self.app.logger.info("Returning result")
+        self.app.logger.info(answer)
+        self.app.logger.info(negative_answer)
+
+        for item in answer:
+            self.final_result[item["DOI"]] = {"Title": item["data"]["title"], "type": item["data"]["type"]}
+        for item in negative_answer:
+            self.not_in_db[item["DOI"]] = {"Title": item["data"]["title"], "type": item["data"]["type"]}
+        self.app.logger.info("Returning result case2")
+        self.app.logger.info(self.final_result)
+        return self.final_result
+
+# ============================= FLASK INTERNALS===============================
 
-#example not exists
-#sample_non_existing_page_url = "https://sci-hub.se/10.4324/9781003006237"
-#sample usage to download
-#sample_existing_page_url = "https://sci-hub.se/10.1057/9781137435026"
-#print(cl.download(sample_existing_page_url))
-#cl.search_crossref("BDSM")
 
-app = Flask(__name__)
 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.
+    Starts a Flask application in debug mode without using the reloader.
+
+    Args:
+    - None.
+
+    Returns:
+    - None.
+
+    Raises:
+    - None.
     """
     # 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.
+    Serves the Flask application using the Waitress WSGI server.
+
+    Args:
+    - None.
+
+    Returns:
+    - None.
+
+    Raises:
+    - None.
     """
     serve(app, host=HOST_ADDRESS, port=PORT_ADDRESS)
 
+
+class BackgroundTaskSearch(threading.Thread):
+    """
+    A background task for searching and saving results to files.
+
+    This class extends the `threading.Thread` class and is responsible for running
+    the search task in the background. It retrieves queries from a queue, performs
+    the search, and saves the results to files.
+
+    Attributes:
+        app (App): The application instance.
+    """
+
+    def run(self):
+        """
+        Run the background task.
+
+        This method is called when the thread is started. It creates a new event loop,
+        runs the `_run` method, and closes the event loop.
+        """
+        loop = asyncio.new_event_loop()
+        loop.run_until_complete(self._run())
+        loop.close()
+
+    async def _run(self):
+        """
+        Perform the search task.
+
+        This method is an asynchronous coroutine that runs in a loop. It retrieves a
+        librarian from the queue, answers the query, and saves the results to files.
+        It also sends the results to a remote server.
+
+        The search task continues running indefinitely until the thread is stopped.
+        """
+        while True:
+            database = None
+            ndb_database = None
+            librarian = librarian_queue.get()
+            self.app.logger.info("STARTED")
+            result = await librarian.answer_query(librarian.deep_search)
+            result = {librarian.uuid: result}
+            self.app.logger.info("Saving to file")
+
+            # Save results to "not_in_db.json" 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)
+
+            # Save results to "s_results.json" 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"])
-def query_database():
+async def query_database():
+    """
+    Endpoint for querying the database.
+
+    This function receives a POST request containing a JSON payload with a query and a UUID.
+    It creates a Librarian object with the query and UUID,
+    and adds it to the librarian_queue and librarian_list.
+    Finally, it returns a JSON response indicating the success
+    of the operation, along with the query, UUID,
+    and the current size of the librarian_queue.
+
+    Returns:
+        tuple: A tuple containing a JSON response and a status code.
+    """
     record = json.loads(request.data)
     app.logger.info(record)
     app.logger.info(record["query"])
     app.logger.info(record["UUID"])
-    cl = Librarian()
-    answer_data = cl.answer_query(record["query"], record["UUID"])
-    app.logger.info(answer_data)
-    summary = (cl.hit,cl.fetched, cl.total, record["UUID"])
-    answer_data = (summary,answer_data)
+    uuid = record["UUID"]
+    deep_search = record["deep_search"]
+    cl = Librarian(app, record["query"], uuid, deep_search)
+    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
 
-if __name__ == "__main__":
-    logger = logging.getLogger('conjurer_musician')
-    logger.setLevel(logging.DEBUG)
-    threads = []
-    #threads.append(threading.Thread(target=waitress_run))
-    threads.append(threading.Thread(target=flask_debug))
 
+@app.route("/get_partial_result", methods=["POST"])
+async def get_partial():
+    """
+    Retrieves the partial result for a given UUID.
+
+    Returns:
+        A JSON response containing the partial result.
+    """
+    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__":
+    app.logger.setLevel(logging.DEBUG)
+    h1 = handlers.RotatingFileHandler(
+        filename="D:\\logs\\librarian.log",
+        encoding="utf-8",
+        mode="a",
+        maxBytes=6 * 1024 * 1024,
+        backupCount=6,
+    )
+
+    app.logger.addHandler(h1)
+    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=(app.logger,)))
+    i = 0
     for worker in threads:
-        worker.start()
+        try:
+            app.logger.info("App number: %s", i)
+            i += 1
+            worker.start()
+        except RuntimeError as e:
+            app.logger.error("Exploded")
+            print(str(e))
     for worker in threads:
         worker.join()
-
-#1. robi liste wyników i ją wyświetla - ale tylko tytuły niezależnych dzieł - jeśli jest coś w containerze to trza pogrupować
-#2. Tworzy przyciski pozwalające sprawdzić czy jest dostępne - i jeśli jest zwraca link
-#3. Jest też przycisk "more" - wyszukujemy po 100, wyświetlamy po 20. Po 100 jak jeszcze to dopiero odpytujemy crossref przyciski strzałek przesuwają po obecnej porcji danych

conjurer_librarian/install_librarian_service.sh

@@ -1,11 +1,33 @@
 #!/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
+# This script sets up a virtual environment for the Conjurer Librarian service and installs the required dependencies.
 
-cp  /home/pi/conjurer/conjurer_librarian/conjurer_librarian.py ./Conjurer_librarian/
+
+# Create a virtual environment at /home/pi/Conjurer_librarian/env
+python3 -m venv /home/pi/Conjurer_librarian/env
+
+# Copy the Conjurer Librarian Python script to the appropriate directory
+cp /home/pi/conjurer/conjurer_librarian/conjurer_librarian.py ./Conjurer_librarian/
+
+# Copy the requirements file to the appropriate directory
+cp /home/pi/conjurer/conjurer_librarian/requirements_librarian.txt ./Conjurer_librarian/
+
+# Change directory to /home/pi/Conjurer_librarian
+cd /home/pi/Conjurer_librarian
+
+touch /home/pi/Conjurer/rr_results.json
+touch /home/pi/Conjurer/cr_results.json
+touch /home/pi/Conjurer/s_results.json
+touch /home/pi/Conjurer/rr_results.json
+touch /home/pi/Conjurer/not_in_db.json
+
+# Activate the virtual environment
+source /home/pi/Conjurer_librarian/env/bin/activate
+
+# Upgrade pip
+./env/bin/python3 -m pip install --upgrade pip
+
+# Install the required dependencies
+./env/bin/python3 -m pip install -r requirements_librarian.txt
+
+# Deactivate the virtual environment
+deactivate

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 +1,134 @@
+"""
+This module contains the code for the scrape bot.
+"""
+
+import json
+import logging
+import random
+import re
+import time
+from json import JSONDecodeError
+from queue import Queue
+from threading import Thread
+from urllib.request import urlopen
+
+from requests import ConnectionError as RequestsConnectionError
+from requests import ConnectTimeout, Timeout
+
+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):
+    """
+    This function loads items from the not_in_db.json file into the work queue.
+    """
+    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 _ in range (1,10):
+                    key = next(iter(ndb_database))
+                    item = ndb_database.pop(key)
+                    logger.info(key)
+                    url = f"https://sci-hub.se/{key}"
+                    WORK_Q.put([item, url, False])
+
+                ndb_file.truncate(0)
+                ndb_file.seek(0)
+                json.dump(ndb_database, ndb_file, indent=4)
+            except JSONDecodeError:
+                time.sleep(60 * 60 * 3)
+        time.sleep(60*60*3)
+
+
+def check_if_exists_brute_force(logger):
+    """
+    This function checks if a document exists using brute force search.
+    """
+    # Function code here
+    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,
+            RequestsConnectionError,
+        ):
+            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, 60)
+        logger.info(f"Sleeping for {2*rand} minutes")
+        time.sleep(120 * rand)
+
+
+def scraper(logger=None):
+    """
+    This function is responsible for scraping data.
+    """
+    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 +1,165 @@
+"""
+This module contains functions for searching for DOI (Digital Object Identifier)
+in a list of live results.
+It includes a producer-consumer pattern implementation using threads and queues.
+
+Functions:
+- producer: Reads lines from a file and puts them into an output queue.
+- consumer: Consumes items from an input queue and checks if DOI exists in the live results list.
+- search_for_doi: Searches for DOI in live results using the producer-consumer pattern.
+
+Global Variables:
+- MAXTHREADS: Maximum number of worker threads.
+- DATABASE_PATH: Path to the database files.
+- ENCODING: Encoding of the database files.
+- CHUNK: File name pattern for the database files.
+- _sentinel: Sentinel object used to signal termination.
+- result_list: List to store the search results.
+- WORK_Q_SIZE: Maximum size of the work queue.
+"""
+
+# TODO: Wpiemdolić to wszystko w klasę z loggerem przysłanym z góry
+from queue import Empty, Queue
+from threading import Thread
+
+q = Queue()
+
+# DATA FOR TEST ONLY
+# MAXTHREADS = 5
+# DATABASE_PATH = r'C:\\Database\\chunks_1\\'
+
+# DEPLOYMENT DATA
+MAXTHREADS = 41
+DATABASE_PATH = r"C:\\Database\\chunks\\"
+
+ENCODING = "utf-8"
+CHUNK = "_chunk.txt"
+_sentinel = object()
+WORK_Q_SIZE = 15500000
+
+
+def producer(out_q, control_q, filename, _logger):
+    """
+    Produces items from the output queue and puts them into the control queue.
+
+    Args:
+        out_q (Queue): Output queue.
+        control_q (Queue): Control queue.
+        filename (str): Name of the file.
+        _logger: Logger object for logging.
+    """
+    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
+            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
+def consumer(in_q, control_q, doi, live_results, result_list, _logger, ):
+    """
+    Consumes items from an input queue and checks if DOI exists in the live results list.
+
+    Args:
+        in_q (Queue): Input queue.
+        control_q (Queue): Control queue.
+        doi (list): List of DOI to search for.
+        live_results (list): List to store the search results.
+        _logger: Logger object for logging.
+    """
+    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):
+    """
+    Search for DOI in live_results using _logger for logging.
+
+    Args:
+        doi (list): List of DOI to search for.
+        live_results (list): List to store the search results.
+        _logger: Logger object for logging.
+    """
+    result_list = []
+    threads = []
+    work_q = Queue(maxsize=WORK_Q_SIZE)
+    control_q = Queue()
+    t_cons = Thread(
+        target=consumer, args=(work_q, control_q, doi, live_results, result_list, _logger)
+    )
+    _logger.info("Consumer thread created")
+    threads.append(t_cons)
+    for i in range(0, MAXTHREADS):
+        # TEST DATA
+        # filename = "test" + str(i) + CHUNk
+        # 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)

conjurer_musician/conjurer_musician.py

@@ -0,0 +1,470 @@
+# This Python file uses the following encoding: utf-8
+"""
+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 logging
+import re
+import threading
+import time
+from datetime import datetime
+from logging import handlers
+from pathlib import Path
+from platform import uname
+from sys import platform
+
+from flask import Flask, jsonify, redirect, request, send_from_directory
+from waitress import serve
+
+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/"
+        PRIORITY_FOLDER = "/home/pi/RetroPie/mp3/Magiczne i chuj/"
+
+
+music_file_list = []
+priority_list = []
+
+
+def create_playlist():
+    """
+    Reads a JSON file containing a playlist and writes the playlist items to a text file.
+
+    The JSON file path is '/home/pi/Conjurer/playlist.json',
+    and the text file path is '/home/pi/Conjurer/all_playlist.playlist'.
+
+    Raises:
+        JSONDecodeError: If the JSON file cannot be decoded.
+
+    """
+    with open("/home/pi/Conjurer/playlist.json", "r+", encoding="utf-8") as r_file:
+        with open(
+            "/home/pi/Conjurer/all_playlist.playlist", "w", encoding="utf-8"
+        ) as w_file:
+            try:
+                playlist = json.load(r_file)
+                for item in playlist:
+                    w_file.write(item)
+                    w_file.write("\n")
+            except json.JSONDecodeError:
+                pass
+
+    with open("/home/pi/Conjurer/prio_playlist.json", "r+", encoding="utf-8") as r_file:
+        with open("/home/pi/Conjurer/hit.playlist", "w", encoding="utf-8") as w_file:
+            try:
+                playlist = json.load(r_file)
+                for item in playlist:
+                    w_file.write(item)
+                    w_file.write("\n")
+            except json.JSONDecodeError:
+                pass
+
+
+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)
+
+    for mp3_item in Path.glob(Path(PRIORITY_FOLDER), "**/*.mp3"):
+        temp_music_file = mp3_item.as_posix()
+        if platform == "win32":
+            temp_music_file = temp_music_file.replace("/", "\\")
+        priority_list.append(temp_music_file)
+
+    with open("/home/pi/Conjurer/playlist.json", "r+", encoding="utf-8") as s_file:
+        database = music_file_list
+        # self.app.logger.info("DUMPING DATA")
+        s_file.truncate(0)
+        s_file.seek(0)
+        json.dump(database, s_file)
+    with open("/home/pi/Conjurer/prio_playlist.json", "r+", encoding="utf-8") as s_file:
+        # self.app.logger.info("DUMPING DATA")
+        s_file.truncate(0)
+        s_file.seek(0)
+        json.dump(priority_list, s_file)
+    create_playlist()
+
+
+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__)
+
+
+# TODO: Odpalić wyszukiwarki w wątkach i dopiero po wszystkim zsumować wyszukiwanie.
+def wyszukaj(word_list, how_many, _logger=None, return_to_bot=True):
+    """
+    Searches for music files based on a list of keywords and returns a list of matching files.
+
+    Args:
+        word_list (list): A list of keywords to search for.
+        how_many (int): The maximum number of matching files to return.
+
+    Returns:
+        list: A list of matching files, sorted by their search weight.
+
+    """
+    if _logger is None:
+        fun_logger = logging.getLogger()
+    else:
+        fun_logger = _logger
+    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)
+        fun_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
+            # TODO: To do wątków albo for asynchroniczny
+            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
+
+    fun_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 []
+    not_found = True
+    return_list = []
+    if int(how_many) <= 0:
+        fun_logger.info("Jeden plik do zagrania")
+        while not_found:
+            if search_weight[itr][0] == item_to_search:
+                return_list.append(search_weight[itr])
+                if not return_to_bot:
+                    with open(
+                        "/home/pi/Conjurer/priority_queue.playlist",
+                        "r+",
+                        encoding="utf-8",
+                    ) as s_file:
+                        s_file.write(search_weight[itr][1])
+                break
+            itr += 1
+    else:
+        fun_logger.info("Wiele plików do zagrania")
+        search_weight.sort(key=lambda x: x[0], reverse=True)
+        return_list.extend(search_weight[: int(how_many)])
+        if not return_to_bot:
+
+            with open(
+                "/home/pi/Conjurer/priority_queue.playlist", "a", encoding="utf-8"
+            ) as s_file:
+                for item in return_list:
+                    s_file.write(item[1] + "\n")
+    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"])
+def stream_music():
+    """
+    The function `stream_music` is a route handler for the "/stream" endpoint.
+    It returns a JSON response containing a key "music_file_list" with the value of the variable `music_file_list`.
+
+    :return: A JSON response containing a key "music_file_list" with the value of the variable `music_file_list`.
+    """
+    return send_from_directory("/tmp/hls", "stream.m3u8")
+
+
+@app.route("/<string:file_name>")
+def stream(file_name):
+    """
+    Stream the specified file from the video directory.
+
+    Args:
+        file_name (str): The name of the file to be streamed.
+
+    Returns:
+        Response: The response containing the streamed file.
+    """
+    video_dir = "/tmp/hls"
+    return send_from_directory(video_dir, file_name)
+
+
+@app.route("/stream_mp3", methods=["GET"])
+def stream_music_mp3():
+    """
+    The function `stream_music_mp3` is a route handler for the "/stream_mp3" endpoint.
+    It redirects the user to the URL "http://www.example.com" with a status code of 302.
+
+    :return: A redirect response to "http://www.example.com" with a status code of 302.
+    """
+    return redirect("http://www.example.com", code=302)
+
+
+@app.route("/clear_pr_pls", methods=["GET"])
+def clear_pr_pls():
+    """
+    The function `clear_pr_pls` clears the contents of the priority queue playlist file.
+
+    :return: A JSON response indicating the success of the operation.
+    """
+    with open(
+        "/home/pi/Conjurer/priority_queue.playlist", "w", encoding="utf-8"
+    ) as s_file:
+        s_file.truncate(0)
+    return_data = jsonify(isError=False, message="Success", statusCode=200, data=[])
+    return return_data, 200
+
+
+@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 `look_for_playlist` 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: 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"], app.logger, True
+    )
+
+    return_data = (
+        jsonify(isError=False, message="Success", statusCode=200, data=return_data),
+        200,
+    )
+    return return_data
+
+
+@app.route("/add_to_priority", methods=["POST"])
+def add_to_priority():
+    """
+    The function `add_to_priority` 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: 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"], app.logger, False
+    )
+
+    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 HOST_ADDRESS
+    and port 5000 using the Waitress WSGI server.
+
+    This function starts the Waitress server and listens for incoming requests
+    on the specified host and port. It uses the `serve` function from the Waitress
+    library to handle the serving process.
+
+    Parameters:
+        None
+
+    Returns:
+        None
+    """
+    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=flask_debug))
+    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()

conjurer_musician/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

conjurer_musician/radio_conjurer.liq

@@ -0,0 +1,71 @@
+# FILEPATH: /home/mtuszowski/conjurer/conjurer_musician/radio_conjurer.liq
+
+# This script sets up a Liquidsoap radio stream with various features and configurations.
+
+# Load icecast credentials from a JSON file
+let json.parse credentials  = file.contents("/home/pi/Conjurer/icecast_credentials.json")
+
+# Enable replaygain metadata processing
+enable_replaygain_metadata()
+
+# Define playlists to be used in the stream
+s1 = replaygain(playlist(reload_mode="watch", "/home/pi/Conjurer/all_playlist.playlist"))
+s2 = replaygain(playlist(reload_mode="watch", "/home/pi/Conjurer/priority_queue.playlist"))
+s3 = replaygain(playlist(reload_mode="watch", "/home/pi/Conjurer/hit.playlist"))
+
+# Randomly select a playlist with weights
+s = random(id="randomizer", weights=[1, 3, 2], [s1, s2, s3])
+
+# Set up an interactive harbor for controlling the stream
+interactive.harbor(port = 9999)
+
+# Set up interactive controls for bass boost
+f = interactive.float("f", description="Frequency", min=0., max=1000., unit="Hz", 200.)
+g = interactive.float("g", description="Gain", min=0., max=20., unit="dB", 8.)
+b = bass_boost(frequency=f, gain=g, s)
+s = add([s, b])
+
+# Set up interactive control for main volume
+a = interactive.float("main_volume", min=0., max=20., 1.)
+s = compress.multiband.interactive(bands=3, s)
+
+# Apply audio processing effects
+s = nrj(normalize(s))
+s = crossfade(fade_out=3., fade_in=3., duration=5., s)
+s = amplify(a, s)
+
+# Skip blank sections in the stream
+s = blank.skip(max_blank=2., s)
+
+# Configure logging settings
+log_to_stdout = true
+log_to_file = true
+logpath = "/home/pi/Conjurer/radio_log.log"
+loglevel = 4
+set("log.stdout", log_to_stdout)
+set("log.level", loglevel)
+
+# Enable logging to file
+set("log.file", log_to_file)
+set("log.file.path", logpath)
+
+# Set up emergency fallback track
+emergency = single("/home/pi/RetroPie/mp3/Youtube/Dr. Peacock - Trip to Ireland [GvrvQTUbUcA].mp3")
+
+# Create a fallback stream with the main stream and emergency track
+radio = fallback(id="switcher", track_sensitive=false, [s, emergency])
+
+# Handle metadata events
+handle_metadata = fun (m) -> begin
+    log.info(m["title"])
+    log.info(m["artist"])
+    log.info(m["filename"])
+end
+radio.on_metadata(handle_metadata)
+
+# Enable persistent script parameters
+interactive.persistent("script.params")
+
+# Configure output formats and destinations
+output.file.hls("/tmp/hls", [("mp3-low", %mp3(bitrate=96)), ("mp3-hi", %mp3(bitrate=160))], radio)
+output.icecast(%mp3, host="retropie", port=8000, password=credentials.password, icy_metadata="true", mount="mp3-stream", radio)

conjurer_musician/radio_service.service

@@ -0,0 +1,14 @@
+[Unit]
+Description=radio_conjurer Liquidsoap daemon
+After=network.target
+Documentation=http://liquidsoap.fm/
+
+[Service]
+User=pi
+WorkingDirectory=/home/pi/Conjurer/
+ExecStart=/home/pi/.opam/4.13.0/bin/liquidsoap /home/pi/Conjurer/radio_conjurer.liq
+Restart=always
+
+[Install]
+WantedBy=multi-user.target
+Alias=radio_conjurer-liquidsoap.service

deploy_music.sh

@@ -0,0 +1,6 @@
+#!/bin/bash
+cd ./conjurer
+git pull
+cd ..
+cp ./conjurer/conjurer_musician/conjurer_musician.py ./Conjurer
+sudo systemctl restart conjurer_musician.service

deploy_radio.sh

@@ -0,0 +1,6 @@
+#!/bin/bash
+cd ./conjurer
+git pull
+cd ..
+cp ./conjurer/conjurer_musician/radio_conjurer.liq ./Conjurer
+sudo systemctl restart radio_service.service

file_webservice/conjurer_musician.py

@@ -1,134 +0,0 @@
-"""
-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
-from pathlib import Path
-from platform import uname
-import threading
-import time
-from sys import platform
-import logging
-from flask import Flask, jsonify, request
-from waitress import serve
-
-
-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"
-        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 = []
-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__)
-
-@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
-
-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)
-
-def waitress_run():
-    serve(app, host="0.0.0.0", port=5000)
-
-if __name__ == "__main__":
-    logger = logging.getLogger('conjurer_musician')
-    logger.setLevel(logging.DEBUG)
-    rescan()
-    threads = []
-    threads.append(threading.Thread(target=waitress_run))
-    threads.append(threading.Thread(target=thread_rescan))
-    #threads.append(threading.Thread(target=flask_debug))
-
-    for worker in threads:
-        worker.start()
-
-    for worker in threads:
-        worker.join()
-
-#TODO: wrzucić wyszukanie i robienie playlist
-#TODO: Inne pliki - sadox, dokumenty naukowe itp.

file_webservice/conjurer_musician.service

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

file_webservice/install_musician_service.sh

@@ -1,11 +0,0 @@
-#!/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

install_main_bot.sh

@@ -1,5 +1,9 @@
 #!/bin/bash
+cd /home/pi
+mdkir Conjurer
+cd Conjurer
 python3 -m venv /home/pi/Conjurer/env
+cp /home/pi/conjurer/requirements_bot.txt /home/pi/Conjurer/
 source ./env/bin/activate
 ./env/bin/python3 -m pip install --upgrade pip
 ./env/bin/python3 -m pip install -r requirements_bot.txt
@@ -8,5 +12,5 @@ sed -i '1i\import shutil' ./env/lib/python3.11/site-packages/spotify_dl/youtube.
 deactivate
 sudo cp ./conjurer.service /etc/systemd/system/
 sudo systemctl daemon-reload
-sudo systemctl start conjurer_musician.service
-sudo systemctl enable conjurer_musician.service
+sudo systemctl start conjurer.service
+sudo systemctl enable conjurer.service

install_music_bot.sh

@@ -0,0 +1,31 @@
+#!/bin/bash
+cd /home/pi
+mkdir Conjurer
+cd Conjurer
+python3 -m venv /home/pi/Conjurer/env
+source /home/pi/Conjurer/env/bin/activate
+cp /home/pi/conjurer/conjurer_musician/requirements_musician.txt /home/pi/Conjurer/
+cp /home/pi/conjurer/conjurer_musician/conjurer_musician.py /home/pi/Conjurer/
+cp /home/pi/conjurer/conjurer_musician/radio_conjurer.liq /home/pi/Conjurer/
+touch /home/pi/Conjurer/discord_mus_service.log
+
+touch /home/pi/Conjurer/playlist.json
+touch /home/pi/Conjurer/prio_playlist.json
+
+touch /home/pi/Conjurer/all_playlist.playlist
+touch /home/pi/Conjurer/priority_queue.playlist
+touch /home/pi/Conjurer/hit.playlist
+
+touch /home/pi/Conjurer/radio_log.log
+./env/bin/python3 -m pip install --upgrade pip
+./env/bin/python3 -m pip install -r requirements_musician.txt
+deactivate
+sudo cp /home/pi/conjurer/conjurer_musician/conjurer_musician.service /etc/systemd/system/
+sudo systemctl daemon-reload
+sudo systemctl start conjurer_musician.service
+sudo systemctl enable conjurer_musician.service
+
+sudo cp /home/pi/conjurer/conjurer_musician/radio_service.service /etc/systemd/system/
+sudo systemctl daemon-reload
+sudo systemctl start radio_service.service
+sudo systemctl enable radio_service.service

requirements_bot.txt

@@ -10,4 +10,6 @@ PyPDF2
 requests
 spotipy
 tiktoken
-PyNaCl
+PyNaCl
+flask
+waitress

utils/cut_large_file.py

@@ -15,10 +15,16 @@ the `smart_write` function returns the size of the encoded bytes of the input `l
 return any value.
 """
 
-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"
+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):
@@ -33,9 +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
 
@@ -59,8 +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
@@ -70,4 +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)