Main brez modelov

swagger_server/.env.template

@@ -0,0 +1,5 @@
+MDB_DATABASE=
+MDB_HOST=
+MDB_PORT=
+MDB_USER=
+MDB_PASSWORD=

swagger_server/__main__.py

@@ -4,7 +4,6 @@ import connexion
 
 from swagger_server import encoder
 
-
 def main():
     app = connexion.App(__name__, specification_dir='./swagger/')
     app.app.json_encoder = encoder.JSONEncoder

swagger_server/controllers/doc2text_controller.py

@@ -1,30 +0,0 @@
-import connexion
-import six
-
-from swagger_server import util
-
-
-def datoteka_v_besedilo_post(file=None):  # noqa: E501
-    """Pretvori datoteko formata pdf, doc, docx, ppt, xls,... v besedilo
-
-     # noqa: E501
-
-    :param file: 
-    :type file: strstr
-
-    :rtype: str
-    """
-    return 'do some magic!'
-
-
-def get_text_ocr(file=None):  # noqa: E501
-    """Pretvori datoteko formata pdf, doc, docx, ppt, xls,... v besedilo s pomočjo ocr razpoznavanja
-
-     # noqa: E501
-
-    :param file: 
-    :type file: strstr
-
-    :rtype: str
-    """
-    return 'do some magic!'

swagger_server/controllers/extract_controller.py

@@ -1,21 +1,88 @@
+import codecs
+import os
+
 import connexion
-import six
+import json
+from pathlib import Path
+from swagger_server.models.izlusci_async_body import IzlusciAsyncBody  # noqa: E501
+from swagger_server.models.izlusci_sync_body import IzlusciSyncBody  # noqa: E501
+from swagger_server.requets_db.models.vrsta import JobManager
+from swagger_server.utils import cl_utils
+from swagger_server.util import get_random_filename, create_random_file_in_tmp_folder
+import requests
+from werkzeug.utils import secure_filename
 
-from swagger_server.models.izlusci_body import IzlusciBody  # noqa: E501
-from swagger_server.models.terminoloski_kandidat import TerminoloskiKandidat  # noqa: E501
-from swagger_server import util
+ATEapi_endpoint = "http://ate-api:5000/predict"
+
+# endpoint below to be used only for development purposes (don't need to run docker)
+# ATEapi_endpoint = "http://localhost:5000/predict"
 
 
-def get_candidates(body):  # noqa: E501
-    """Izlusci terminološke kandidate iz seznama besedil v conllu obliki
+def do_izlusci(conllus, prepovedane_besede):
+    tmp_file_path = ""
+    try:
+        big_conllu = cl_utils.multipla_conllus_to_one_from_conllus_arr(conllus)
+        tmp_file_path = create_random_file_in_tmp_folder(big_conllu, ".conllu")
+        fp = open(tmp_file_path, 'rb')
+        try:
+            files = [
+                ('file', ('temp_1.conllu', fp, 'application/octet-stream'))
+            ]
+            res = requests.post(ATEapi_endpoint, files=files)
+            data = json.loads(res.text)
+        finally:
+            fp.close()
+            os.remove(tmp_file_path)
+
+        ret = {'terminoloski_kandidati': [
+            {
+                'POSoznake': tk['msd'],
+                'kandidat': tk['terms'],  # more to bit lemma al terms?
+                'kanonicnaoblika': tk['canonical'],
+                'ranking': tk['ranking'],
+                'podporneutezi': [
+                    0.0,  # ????????
+                    0.0  # ??????
+                ],
+                'pogostostpojavljanja': [0, 0]  # ???????
+            }
+            for tk in data if tk['terms'] not in prepovedane_besede
+        ]}
+        return ret, 200
+    except Exception as e:
+        return str(e), 500
+
+
+def get_candidates_async(body):  # noqa: E501
+    """Izlusci terminološke kandidate iz seznama besedil v conllu obliki [asinhrono, ustvari novi job]
 
      # noqa: E501
 
-    :param body: 
+    :param body:
+    :type body: dict | bytes
+
+    :rtype: str
+    """
+    if connexion.request.is_json:
+        body = IzlusciAsyncBody.from_dict(connexion.request.get_json())  # noqa: E501
+    job, is_old_job = JobManager.create_job(4, json.dumps(body.to_dict()))
+    if job is None:
+        return "Something went wrong", 500
+    ret = {'check_job_url': f'{connexion.request.url_root}/job/{job.id}'}
+    return ret, 200
+
+
+def get_candidates_sync(body):  # noqa: E501
+    """Izlusci terminološke kandidate iz seznama besedil v conllu obliki [sihrono, rezultat v sami zahtevi]
+
+     # noqa: E501
+
+    :param body:
     :type body: dict | bytes
 
     :rtype: List[TerminoloskiKandidat]
     """
     if connexion.request.is_json:
-        body = IzlusciBody.from_dict(connexion.request.get_json())  # noqa: E501
-    return 'do some magic!'
+        body = IzlusciSyncBody.from_dict(connexion.request.get_json())  # noqa: E501
+
+    return do_izlusci(body.conllus, body.prepovedane_besede)

swagger_server/controllers/jobs_controller.py

@@ -0,0 +1,233 @@
+import datetime
+import json
+import os.path
+import traceback
+
+import peewee
+import asyncio
+import concurrent.futures as cf
+
+from swagger_server.controllers.extract_controller import do_izlusci
+from swagger_server.models.job_response import JobResponse  # noqa: E501
+from swagger_server.requets_db.models.vrsta import (Job)
+from threading import Thread
+from swagger_server.utils import cl_utils
+from swagger_server.utils import txt_utils
+from werkzeug.datastructures import FileStorage
+import threading
+import time
+
+CLASSLA_CONCURANCE_LIMIT = 3
+DOC2TEXT_CONCURANCE_LIMIT = 3
+ATEAPI_CONCURANCE_LIMIT = 2
+
+classla_sem = threading.Semaphore(CLASSLA_CONCURANCE_LIMIT)
+doc2text_sem = threading.Semaphore(DOC2TEXT_CONCURANCE_LIMIT)
+ateapi_sem = threading.Semaphore(ATEAPI_CONCURANCE_LIMIT)
+
+
+def delete_job(job_id):  # noqa: E501
+    """Izbriše job
+
+     # noqa: E501
+
+    :param job_id:
+    :type job_id: int
+
+    :rtype: str
+    """
+    return 'Endpoint currently disabled'
+
+
+def get_job_status(job_id):  # noqa: E501
+    """Vrne status
+
+     # noqa: E501
+
+    :param job_id:
+    :type job_id: int
+
+    :rtype: JobResponse
+    """
+    try:
+        job = Job.get_by_id(job_id)
+        if job.started_on is None:
+            return JobResponse(job_status="waiting in que", created_on=job.created_on), 200
+        if job.started_on is not None and job.finished_on is None:
+            return JobResponse(job_status="currently processing", created_on=job.created_on,
+                               started_on=job.started_on), 200
+        if job.started_on is not None and job.finished_on is not None:
+            return JobResponse(job_status="finished processing", created_on=job.created_on, started_on=job.started_on,
+                               finished_on=job.finished_on, job_result=job.job_output), 200
+    except peewee.DoesNotExist:
+        return "Job with this ID does not exist", 404
+
+
+def clear_up_unfinished_jobs():
+    """
+    In case server crashed while jobs were in queue...
+    """
+    Job.update(started_on=None).where(Job.started_on.is_null(False), Job.finished_on.is_null()).execute()
+    if os.path.exists('tmp'):
+        for tmp_file in os.listdir('tmp'):
+            if not Job.select().where(Job.input_file == tmp_file).exists():
+                os.remove(f'tmp/{tmp_file}')
+
+
+async def try_do_jobs():
+    with cf.ThreadPoolExecutor(max_workers=3) as ex:
+        ex.submit(try_do_jobs_classla)
+        ex.submit(try_do_jobs_doc2text)
+        ex.submit(try_do_jobs_ateapi)
+
+
+### Job looping
+def try_do_jobs_ateapi():
+    while True:
+        try:
+            if ateapi_sem._value > 0:
+                unfinished_jobs = Job.select() \
+                    .where(Job.finished_on.is_null(), Job.started_on.is_null(), Job.job_type == 4) \
+                    .limit(ateapi_sem._value)
+                with cf.ThreadPoolExecutor(max_workers=ATEAPI_CONCURANCE_LIMIT) as ex:
+                    [ex.submit(execute_ateapi_job, job) for job in unfinished_jobs]
+        except Exception as e:
+            print(f"Exception in try_do_jobs_ateapi")
+            traceback.print_exc()
+        finally:
+            time.sleep(3)
+
+
+### Job looping
+def try_do_jobs_classla():
+    time.sleep(15)  # wait for tokenizers to load for classla ...
+    while True:
+        try:
+            if cl_utils.nlp_loaded:
+                if classla_sem._value > 0:
+                    unfinished_jobs_txt = Job.select() \
+                        .where(Job.finished_on.is_null(), Job.job_type == 2,
+                               Job.input_file.is_null(False)) \
+                        .limit(classla_sem._value)
+
+                    unfinished_jobs_no_txt = Job.select() \
+                        .where(Job.finished_on.is_null(), Job.started_on.is_null(), Job.job_type == 2,
+                               Job.input_file.is_null()) \
+                        .limit(classla_sem._value)
+
+                    unfinished_jobs = [j for j in unfinished_jobs_txt] + [j for j in unfinished_jobs_no_txt]
+                    unfinished_jobs = unfinished_jobs[:classla_sem._value]
+                    with cf.ThreadPoolExecutor(max_workers=CLASSLA_CONCURANCE_LIMIT) as ex:
+                        [ex.submit(execute_classla_job, job) for job in unfinished_jobs]
+
+        except Exception as e:
+            print(f"Exception in try_do_jobs_classla")
+            traceback.print_exc()
+        finally:
+            time.sleep(3)
+
+
+### Job looping
+def try_do_jobs_doc2text():
+    while True:
+        try:
+            if doc2text_sem._value > 0:
+                unfinished_jobs = Job.select() \
+                    .where(Job.finished_on.is_null(), Job.started_on.is_null(), Job.job_type << [1, 12, 3, 32]) \
+                    .limit(doc2text_sem._value)
+                with cf.ThreadPoolExecutor(max_workers=DOC2TEXT_CONCURANCE_LIMIT) as ex:
+                    [ex.submit(execute_doc2text_job, job) for job in unfinished_jobs]
+        except Exception as e:
+            print(f"Exception in try_do_jobs_doc2text")
+            traceback.print_exc()
+        finally:
+            time.sleep(3)
+
+
+async def prep_jobs(tasks):
+    await asyncio.gather(*tasks)
+
+
+def execute_doc2text_job(job: Job):
+    try:
+        doc2text_sem.acquire()
+        del_file = False
+        job.started_on = datetime.datetime.utcnow()
+        job.save()
+
+        tmp_file_path = job.input_file
+        if not os.path.exists(tmp_file_path):
+            job.finished_on = datetime.datetime.utcnow()
+            job.job_output = "ERROR - Temporary file went missing, couldn't properly finish job"
+            job.save()
+            return
+
+        with open(tmp_file_path, 'rb+') as f:
+            file = FileStorage(f)
+            jtype = job.job_type
+            text = ""
+            if jtype in [1, 12]:
+                text, _ = txt_utils.extract_text_prepResp(file)
+            elif jtype in [3, 32]:
+                text, _ = txt_utils.ocr_text_prepResp(file)
+
+            if jtype in [1, 3]:
+                job.job_output = text
+                job.finished_on = datetime.datetime.utcnow()
+            elif jtype in [12, 32]:
+                job.job_input = text
+                job.job_type = 2
+                job.input_size = len(text)
+                del_file = True
+            job.save()
+        if del_file:
+            try:
+                os.remove(tmp_file_path)
+            except:
+                pass
+
+    except:
+        job.started_on = None
+        job.save()
+    finally:
+        doc2text_sem.release()
+
+
+def execute_classla_job(job: Job):
+    try:
+        classla_sem.acquire()
+        job.started_on = datetime.datetime.utcnow()
+        job.save()
+        conllu, _ = cl_utils.raw_text_to_conllu(job.job_input)
+        job.job_output = conllu
+        job.finished_on = datetime.datetime.utcnow()
+        job.save()
+    finally:
+        classla_sem.release()
+
+
+def execute_ateapi_job(job: Job):
+    try:
+        ateapi_sem.acquire()
+        job.started_on = datetime.datetime.utcnow()
+        job.save()
+        info = json.loads(job.job_input)
+        ret_json, _ = do_izlusci(info['conllus'], info['prepovedane_besede'])
+        job.job_output = ret_json
+        job.finished_on = datetime.datetime.utcnow()
+        job.save()
+    finally:
+        ateapi_sem.release()
+
+
+clear_up_unfinished_jobs()
+loop = asyncio.get_event_loop()
+
+
+def loop_in_thread(loop):
+    asyncio.set_event_loop(loop)
+    loop.run_until_complete(try_do_jobs())
+
+
+t = Thread(target=loop_in_thread, args=(loop,))
+t.start()

swagger_server/controllers/marktext_async_controller.py

@@ -0,0 +1,96 @@
+import connexion
+
+from swagger_server.models.oznaci_besedilo_async_body import OznaciBesediloAsyncBody  # noqa: E501
+from swagger_server.requets_db.models.vrsta import (JobManager)
+
+
+def get_text(body):  # noqa: E501
+    """Označi besedilo s classlo/stanzo z uporabo slovenskih modelov ter vrne conll-u format
+
+     # noqa: E501
+
+    :param body:
+    :type body: dict | bytes
+
+    :rtype: str
+    """
+    if connexion.request.is_json:
+        body = OznaciBesediloAsyncBody.from_dict(connexion.request.get_json())  # noqa: E501
+    else:
+        return "Request in wrong format", 400
+    # conllu = cl_utils.raw_text_to_conllu(body.besedilo)
+    # return conllu
+    job, is_old_job = JobManager.create_job(2, body.besedilo)
+    if job is None:
+        return "Something went wrong", 500
+    ret = {'check_job_url': f'{connexion.request.url_root}/job/{job.id}'}
+
+    return ret, 200  # Todo: Update swagger to the newest response template later
+
+
+def get_conllu_from_file_async(file=None):  # noqa: E501
+    """Pretvori datoteko v besedilo in označi s classlo/stanzo z uporabo slovenskih modelov ter vrne conll-u format
+
+     # noqa: E501
+
+    :param file:
+    :type file: strstr
+
+    :rtype: str
+    """
+    job, is_old_job = JobManager.create_job(12, file)
+    if job is None:
+        return "Something went wrong", 500
+    ret = {'check_job_url': f'{connexion.request.url_root}/job/{job.id}'}
+    return ret, 200
+
+
+def get_conllu_from_file_ocr_async(file=None):  # noqa: E501
+    """Pretvori datoteko v besedilo in označi s classlo/stanzo z uporabo slovenskih modelov ter vrne conll-u format
+
+     # noqa: E501
+
+    :param file:
+    :type file: strstr
+
+    :rtype: str
+    """
+    job, is_old_job = JobManager.create_job(32, file)
+    if job is None:
+        return "Something went wrong", 500
+    ret = {'check_job_url': f'{connexion.request.url_root}/job/{job.id}'}
+    return ret, 200
+
+
+def get_text_from_doc_async(file=None):  # noqa: E501
+    """Pretvori datoteko v besedilo, vrača tekst
+
+     # noqa: E501
+
+    :param file:
+    :type file: strstr
+
+    :rtype: str
+    """
+    job, is_old_job = JobManager.create_job(1, file)
+    if job is None:
+        return "Something went wrong", 500
+    ret = {'check_job_url': f'{connexion.request.url_root}/job/{job.id}'}
+    return ret, 200
+
+
+def get_text_from_file_ocr_async(file=None):  # noqa: E501
+    """Pretvori datoteko v besedilo s pomočjo ocr razpoznavanja, vrača tekst
+
+     # noqa: E501
+
+    :param file:
+    :type file: strstr
+
+    :rtype: str
+    """
+    job, is_old_job = JobManager.create_job(3, file)
+    if job is None:
+        return "Something went wrong", 500
+    ret = {'check_job_url': f'{connexion.request.url_root}/job/{job.id}'}
+    return ret, 200

swagger_server/controllers/marktext_controller.py

@@ -1,19 +0,0 @@
-import connexion
-import six
-
-from swagger_server import util
-
-
-def get_text(body):  # noqa: E501
-    """Označi besedilo s classlo/stanzo z uporabo slovenskih modelov ter vrne conll-u format
-
-     # noqa: E501
-
-    :param body: 
-    :type body: dict | bytes
-
-    :rtype: str
-    """
-    if connexion.request.is_json:
-        body = str.from_dict(connexion.request.get_json())  # noqa: E501
-    return 'do some magic!'

swagger_server/controllers/marktext_sync_controller.py

@@ -0,0 +1,81 @@
+from swagger_server.utils import cl_utils
+from swagger_server.utils import txt_utils
+
+
+def datoteka_v_besedilo_in_classla(file=None):  # noqa: E501
+    """Pretvori datoteko formata pdf, doc, docx, ppt, xls,... vrača conllu
+
+     # noqa: E501
+
+    :param file:
+    :type file: strstr
+
+    :rtype: str
+    """
+    if not cl_utils.nlp_loaded:
+        return "NLP Models still loading up since server restart, please try again later.", 500
+    if file is None:
+        return "No file provided", 400
+    try:
+        txt, _ = txt_utils.extract_text_prepResp(file)
+        return cl_utils.raw_text_to_conllu(txt)
+    except Exception as e:
+        return str(e), 500
+
+
+def datoteka_v_besedilo_sync_post(file=None):  # noqa: E501
+    """Pretvori datoteko formata pdf, doc, docx, ppt, xls,... vrača besedilo
+
+     # noqa: E501
+
+    :param file:
+    :type file: strstr
+
+    :rtype: str
+    """
+    if file is None:
+        return "No file provided", 400
+    try:
+        return txt_utils.extract_text_prepResp(file)
+    except Exception as e:
+        print(e)
+        return str(e), 500
+
+
+def get_conllu_ocr(file=None):  # noqa: E501
+    """Pretvori datoteko formata pdf, doc, docx, ppt, xls,... v conllu s pomočjo ocr razpoznavanja
+
+     # noqa: E501
+
+    :param file:
+    :type file: strstr
+
+    :rtype: str
+    """
+    if not cl_utils.nlp_loaded:
+        return "NLP Models still loading up since server restart, please try again later.", 500
+    if file is None:
+        return "No file provided", 400
+    try:
+        txt, _ = txt_utils.ocr_text_prepResp(file)
+        return cl_utils.raw_text_to_conllu(txt)
+    except Exception as e:
+        return str(e), 500
+
+
+def get_text_ocr(file=None):  # noqa: E501
+    """Pretvori datoteko formata pdf, doc, docx, ppt, xls,... v besedilo s pomočjo ocr razpoznavanja
+
+     # noqa: E501
+
+    :param file:
+    :type file: strstr
+
+    :rtype: str
+    """
+    if file is None:
+        return "No file provided", 400
+    try:
+        return txt_utils.ocr_text_prepResp(file)
+    except Exception as e:
+        return str(e), 500

swagger_server/controllers/oss_controller.py

@@ -1,21 +1,6 @@
-import connexion
-import six
-
-from swagger_server.models.terminoloski_kandidat import TerminoloskiKandidat  # noqa: E501
+from swagger_server.utils import db_utils
 from swagger_server import util
-
-
-def get_conllu(id):  # noqa: E501
-    """Vrne CoNNL-U po id-ju datoteke
-
-     # noqa: E501
-
-    :param id: 
-    :type id: int
-
-    :rtype: str
-    """
-    return 'do some magic!'
+from flask import send_file
 
 
 def get_conllus(leta, vrste, kljucnebesede, cerifpodrocja):  # noqa: E501
@@ -34,10 +19,16 @@ def get_conllus(leta, vrste, kljucnebesede, cerifpodrocja):  # noqa: E501
 
     :rtype: List[str]
     """
-    return 'do some magic!'
+    if not kljucnebesede:
+        return "Manjkajo kljucne besede", 400
+    #zaenkrat ne potrebujemo te storitve
+    files = db_utils.get_files_by_udc(kljucnebesede)
+    if not files:
+        return 'Nobena datoteka ne ustreza iskalnemu pogoju', 404
+    return ' '.join(files), 200
 
 
-def get_extracted_words(leta, vrste, kljucnebesede, cerifpodrocja):  # noqa: E501
+def get_extracted_words(leta=None, vrste=None, kljucnebesede=None, udk=None):  # noqa: E501
     """Vrne terminloške kandidate glede na 
 
      # noqa: E501
@@ -53,21 +44,10 @@ def get_extracted_words(leta, vrste, kljucnebesede, cerifpodrocja):  # noqa: E50
 
     :rtype: List[TerminoloskiKandidat]
     """
-    return 'do some magic!'
+    files = db_utils.vrni_oss_terminoloske_kandidate(leta, vrste, kljucnebesede, udk)
+    return files, 200
 
 
-def get_file(id):  # noqa: E501
-    """Vrne binarni zapis v originalnem formatu po id-ju datoteke
-
-     # noqa: E501
-
-    :param id: 
-    :type id: int
-
-    :rtype: List[bytearray]
-    """
-    return 'do some magic!'
-
 
 def get_files(leta, vrste, kljucnebesede, cerifpodrocja):  # noqa: E501
     """Vrne seznam binarnih zapisov v originalnem formatu glede na iskalne pogoje
@@ -85,10 +65,16 @@ def get_files(leta, vrste, kljucnebesede, cerifpodrocja):  # noqa: E501
 
     :rtype: List[List[bytearray]]
     """
-    return 'do some magic!'
+    if not kljucnebesede:
+        return "Manjkajo kljucne besede", 400
+    #zaenkrat ne potrebujemo te storitve
+    files = db_utils.get_files_by_udc(kljucnebesede)
+    if not files:
+        return 'Nobena datoteka ne ustreza iskalnemu pogoju', 404
+    return ' '.join(files), 200
 
 
-def get_number_texts(leta, vrste, kljucnebesede, cerifpodrocja):  # noqa: E501
+def get_number_texts(leta=None, vrste=None, kljucnebesede=None, udk=None):  # noqa: E501
     """Vrne število besedil glede na iskalne pogoje
 
      # noqa: E501
@@ -100,11 +86,15 @@ def get_number_texts(leta, vrste, kljucnebesede, cerifpodrocja):  # noqa: E501
     :param kljucnebesede: 
     :type kljucnebesede: List[str]
     :param cerifpodrocja: 
-    :type cerifpodrocja: List[int]
+    :type udc: List[int]
 
     :rtype: int
     """
-    return 'do some magic!'
+    #if not kljucnebesede:
+    #    return "Manjkajo kljucne besede", 400
+
+    files = db_utils.vrni_oss_dokumente(leta, vrste, kljucnebesede, udk)
+    return len(files), 200
 
 
 def get_texts(leta, vrste, kljucnebesede, cerifpodrocja):  # noqa: E501
@@ -123,17 +113,60 @@ def get_texts(leta, vrste, kljucnebesede, cerifpodrocja):  # noqa: E501
 
     :rtype: List[str]
     """
-    return 'do some magic!'
+    if not kljucnebesede:
+        return "Manjkajo kljucne besede", 400
+    #zaenkrat ne potrebujemo te storitve
+    files = db_utils.get_files_by_udc(kljucnebesede)
+    if not files:
+        return 'Nobena datoteka ne ustreza iskalnemu pogoju', 404
+    return ' '.join(files), 200
 
 
-def oss_besedilo_po_id_get(id):  # noqa: E501
+def get_conllu(file_id):  # noqa: E501
+    """Vrne CoNNL-U po id-ju datoteke
+
+     # noqa: E501
+
+    :param file_id:
+    :type file_id: int
+
+    :rtype: str
+    """
+    try:
+        return send_file(util.get_conllu_file_path_by_id(file_id), download_name=f'{file_id}.conllu')
+    except FileNotFoundError as e:
+        return "The conllu with this ID doesn't exist.", 404
+
+
+def get_file(file_id):  # noqa: E501
+    """Vrne binarni zapis v originalnem formatu po id-ju datoteke
+
+     # noqa: E501
+
+    :param file_id:
+    :type file_id: int
+
+    :rtype: List[bytearray]
+    """
+    try:
+        return send_file(util.get_original_file_path_by_id(file_id), download_name=f'{file_id}.xml')
+    except FileNotFoundError as e:
+        return "The file with this ID doesn't exist.", 404
+
+
+def oss_besedilo_po_id_get(file_id):  # noqa: E501
     """Vrne besedilo po id-ju datoteke
 
      # noqa: E501
 
-    :param id: 
-    :type id: int
+    :param file_id:
+    :type file_id: int
 
     :rtype: str
     """
-    return 'do some magic!'
+    try:
+        f = util.get_original_file_path_by_id(file_id)
+        print(f) # for debugging purposes on the server, delete this later
+        return send_file(util.get_original_file_path_by_id(file_id), download_name=f'{file_id}.xml')
+    except FileNotFoundError as e:
+        return "The file with this ID doesn't exist.", 404

swagger_server/models/__init__.py

@@ -3,7 +3,16 @@
 # flake8: noqa
 from __future__ import absolute_import
 # import models into model package
-from swagger_server.models.datoteka_v_besedilo_body import DatotekaVBesediloBody
-from swagger_server.models.datoteka_v_besedilo_ocr_body import DatotekaVBesediloOcrBody
-from swagger_server.models.izlusci_body import IzlusciBody
+from swagger_server.models.datoteka_v_besedilo_async_body import DatotekaVBesediloAsyncBody
+from swagger_server.models.datoteka_v_besedilo_async_ocr_body import DatotekaVBesediloAsyncOcrBody
+from swagger_server.models.datoteka_v_besedilo_sync_body import DatotekaVBesediloSyncBody
+from swagger_server.models.datoteka_v_besedilo_sync_ocr_body import DatotekaVBesediloSyncOcrBody
+from swagger_server.models.datoteka_v_conllu_async_body import DatotekaVConlluAsyncBody
+from swagger_server.models.datoteka_v_conllu_async_ocr_body import DatotekaVConlluAsyncOcrBody
+from swagger_server.models.datoteka_v_conllu_sync_body import DatotekaVConlluSyncBody
+from swagger_server.models.datoteka_v_conllu_sync_ocr_body import DatotekaVConlluSyncOcrBody
+from swagger_server.models.job_response import JobResponse
+from swagger_server.models.oznaci_besedilo_async_body import OznaciBesediloAsyncBody
 from swagger_server.models.terminoloski_kandidat import TerminoloskiKandidat
+from swagger_server.models.izlusci_async_body import IzlusciAsyncBody
+from swagger_server.models.izlusci_sync_body import IzlusciSyncBody

swagger_server/models/datoteka_v_besedilo_async_body.py

@@ -0,0 +1,64 @@
+# coding: utf-8
+
+from __future__ import absolute_import
+from datetime import date, datetime  # noqa: F401
+
+from typing import List, Dict  # noqa: F401
+
+from swagger_server.models.base_model_ import Model
+from swagger_server import util
+
+
+class DatotekaVBesediloAsyncBody(Model):
+    """NOTE: This class is auto generated by the swagger code generator program.
+
+    Do not edit the class manually.
+    """
+    def __init__(self, file: str=None):  # noqa: E501
+        """DatotekaVBesediloAsyncBody - a model defined in Swagger
+
+        :param file: The file of this DatotekaVBesediloAsyncBody.  # noqa: E501
+        :type file: str
+        """
+        self.swagger_types = {
+            'file': str
+        }
+
+        self.attribute_map = {
+            'file': 'file'
+        }
+        self._file = file
+
+    @classmethod
+    def from_dict(cls, dikt) -> 'DatotekaVBesediloAsyncBody':
+        """Returns the dict as a model
+
+        :param dikt: A dict.
+        :type: dict
+        :return: The datotekaVBesediloAsync_body of this DatotekaVBesediloAsyncBody.  # noqa: E501
+        :rtype: DatotekaVBesediloAsyncBody
+        """
+        return util.deserialize_model(dikt, cls)
+
+    @property
+    def file(self) -> str:
+        """Gets the file of this DatotekaVBesediloAsyncBody.
+
+
+        :return: The file of this DatotekaVBesediloAsyncBody.
+        :rtype: str
+        """
+        return self._file
+
+    @file.setter
+    def file(self, file: str):
+        """Sets the file of this DatotekaVBesediloAsyncBody.
+
+
+        :param file: The file of this DatotekaVBesediloAsyncBody.
+        :type file: str
+        """
+        if file is None:
+            raise ValueError("Invalid value for `file`, must not be `None`")  # noqa: E501
+
+        self._file = file

swagger_server/models/datoteka_v_besedilo_async_ocr_body.py

@@ -0,0 +1,64 @@
+# coding: utf-8
+
+from __future__ import absolute_import
+from datetime import date, datetime  # noqa: F401
+
+from typing import List, Dict  # noqa: F401
+
+from swagger_server.models.base_model_ import Model
+from swagger_server import util
+
+
+class DatotekaVBesediloAsyncOcrBody(Model):
+    """NOTE: This class is auto generated by the swagger code generator program.
+
+    Do not edit the class manually.
+    """
+    def __init__(self, file: str=None):  # noqa: E501
+        """DatotekaVBesediloAsyncOcrBody - a model defined in Swagger
+
+        :param file: The file of this DatotekaVBesediloAsyncOcrBody.  # noqa: E501
+        :type file: str
+        """
+        self.swagger_types = {
+            'file': str
+        }
+
+        self.attribute_map = {
+            'file': 'file'
+        }
+        self._file = file
+
+    @classmethod
+    def from_dict(cls, dikt) -> 'DatotekaVBesediloAsyncOcrBody':
+        """Returns the dict as a model
+
+        :param dikt: A dict.
+        :type: dict
+        :return: The datotekaVBesediloAsync_ocr_body of this DatotekaVBesediloAsyncOcrBody.  # noqa: E501
+        :rtype: DatotekaVBesediloAsyncOcrBody
+        """
+        return util.deserialize_model(dikt, cls)
+
+    @property
+    def file(self) -> str:
+        """Gets the file of this DatotekaVBesediloAsyncOcrBody.
+
+
+        :return: The file of this DatotekaVBesediloAsyncOcrBody.
+        :rtype: str
+        """
+        return self._file
+
+    @file.setter
+    def file(self, file: str):
+        """Sets the file of this DatotekaVBesediloAsyncOcrBody.
+
+
+        :param file: The file of this DatotekaVBesediloAsyncOcrBody.
+        :type file: str
+        """
+        if file is None:
+            raise ValueError("Invalid value for `file`, must not be `None`")  # noqa: E501
+
+        self._file = file

swagger_server/models/datoteka_v_besedilo_sync_body.py

@@ -0,0 +1,64 @@
+# coding: utf-8
+
+from __future__ import absolute_import
+from datetime import date, datetime  # noqa: F401
+
+from typing import List, Dict  # noqa: F401
+
+from swagger_server.models.base_model_ import Model
+from swagger_server import util
+
+
+class DatotekaVBesediloSyncBody(Model):
+    """NOTE: This class is auto generated by the swagger code generator program.
+
+    Do not edit the class manually.
+    """
+    def __init__(self, file: str=None):  # noqa: E501
+        """DatotekaVBesediloSyncBody - a model defined in Swagger
+
+        :param file: The file of this DatotekaVBesediloSyncBody.  # noqa: E501
+        :type file: str
+        """
+        self.swagger_types = {
+            'file': str
+        }
+
+        self.attribute_map = {
+            'file': 'file'
+        }
+        self._file = file
+
+    @classmethod
+    def from_dict(cls, dikt) -> 'DatotekaVBesediloSyncBody':
+        """Returns the dict as a model
+
+        :param dikt: A dict.
+        :type: dict
+        :return: The datotekaVBesediloSync_body of this DatotekaVBesediloSyncBody.  # noqa: E501
+        :rtype: DatotekaVBesediloSyncBody
+        """
+        return util.deserialize_model(dikt, cls)
+
+    @property
+    def file(self) -> str:
+        """Gets the file of this DatotekaVBesediloSyncBody.
+
+
+        :return: The file of this DatotekaVBesediloSyncBody.
+        :rtype: str
+        """
+        return self._file
+
+    @file.setter
+    def file(self, file: str):
+        """Sets the file of this DatotekaVBesediloSyncBody.
+
+
+        :param file: The file of this DatotekaVBesediloSyncBody.
+        :type file: str
+        """
+        if file is None:
+            raise ValueError("Invalid value for `file`, must not be `None`")  # noqa: E501
+
+        self._file = file

swagger_server/models/datoteka_v_besedilo_sync_ocr_body.py

@@ -0,0 +1,64 @@
+# coding: utf-8
+
+from __future__ import absolute_import
+from datetime import date, datetime  # noqa: F401
+
+from typing import List, Dict  # noqa: F401
+
+from swagger_server.models.base_model_ import Model
+from swagger_server import util
+
+
+class DatotekaVBesediloSyncOcrBody(Model):
+    """NOTE: This class is auto generated by the swagger code generator program.
+
+    Do not edit the class manually.
+    """
+    def __init__(self, file: str=None):  # noqa: E501
+        """DatotekaVBesediloSyncOcrBody - a model defined in Swagger
+
+        :param file: The file of this DatotekaVBesediloSyncOcrBody.  # noqa: E501
+        :type file: str
+        """
+        self.swagger_types = {
+            'file': str
+        }
+
+        self.attribute_map = {
+            'file': 'file'
+        }
+        self._file = file
+
+    @classmethod
+    def from_dict(cls, dikt) -> 'DatotekaVBesediloSyncOcrBody':
+        """Returns the dict as a model
+
+        :param dikt: A dict.
+        :type: dict
+        :return: The datotekaVBesediloSync_ocr_body of this DatotekaVBesediloSyncOcrBody.  # noqa: E501
+        :rtype: DatotekaVBesediloSyncOcrBody
+        """
+        return util.deserialize_model(dikt, cls)
+
+    @property
+    def file(self) -> str:
+        """Gets the file of this DatotekaVBesediloSyncOcrBody.
+
+
+        :return: The file of this DatotekaVBesediloSyncOcrBody.
+        :rtype: str
+        """
+        return self._file
+
+    @file.setter
+    def file(self, file: str):
+        """Sets the file of this DatotekaVBesediloSyncOcrBody.
+
+
+        :param file: The file of this DatotekaVBesediloSyncOcrBody.
+        :type file: str
+        """
+        if file is None:
+            raise ValueError("Invalid value for `file`, must not be `None`")  # noqa: E501
+
+        self._file = file

swagger_server/models/datoteka_v_conllu_async_body.py

@@ -9,15 +9,15 @@ from swagger_server.models.base_model_ import Model
 from swagger_server import util
 
 
-class DatotekaVBesediloOcrBody(Model):
+class DatotekaVConlluAsyncBody(Model):
     """NOTE: This class is auto generated by the swagger code generator program.
 
     Do not edit the class manually.
     """
     def __init__(self, file: str=None):  # noqa: E501
-        """DatotekaVBesediloOcrBody - a model defined in Swagger
+        """DatotekaVConlluAsyncBody - a model defined in Swagger
 
-        :param file: The file of this DatotekaVBesediloOcrBody.  # noqa: E501
+        :param file: The file of this DatotekaVConlluAsyncBody.  # noqa: E501
         :type file: str
         """
         self.swagger_types = {
@@ -30,32 +30,32 @@ class DatotekaVBesediloOcrBody(Model):
         self._file = file
 
     @classmethod
-    def from_dict(cls, dikt) -> 'DatotekaVBesediloOcrBody':
+    def from_dict(cls, dikt) -> 'DatotekaVConlluAsyncBody':
         """Returns the dict as a model
 
         :param dikt: A dict.
         :type: dict
-        :return: The datotekaVBesedilo_ocr_body of this DatotekaVBesediloOcrBody.  # noqa: E501
-        :rtype: DatotekaVBesediloOcrBody
+        :return: The datotekaVConlluAsync_body of this DatotekaVConlluAsyncBody.  # noqa: E501
+        :rtype: DatotekaVConlluAsyncBody
         """
         return util.deserialize_model(dikt, cls)
 
     @property
     def file(self) -> str:
-        """Gets the file of this DatotekaVBesediloOcrBody.
+        """Gets the file of this DatotekaVConlluAsyncBody.
 
 
-        :return: The file of this DatotekaVBesediloOcrBody.
+        :return: The file of this DatotekaVConlluAsyncBody.
         :rtype: str
         """
         return self._file
 
     @file.setter
     def file(self, file: str):
-        """Sets the file of this DatotekaVBesediloOcrBody.
+        """Sets the file of this DatotekaVConlluAsyncBody.
 
 
-        :param file: The file of this DatotekaVBesediloOcrBody.
+        :param file: The file of this DatotekaVConlluAsyncBody.
         :type file: str
         """
         if file is None:

swagger_server/models/datoteka_v_conllu_async_ocr_body.py

@@ -0,0 +1,64 @@
+# coding: utf-8
+
+from __future__ import absolute_import
+from datetime import date, datetime  # noqa: F401
+
+from typing import List, Dict  # noqa: F401
+
+from swagger_server.models.base_model_ import Model
+from swagger_server import util
+
+
+class DatotekaVConlluAsyncOcrBody(Model):
+    """NOTE: This class is auto generated by the swagger code generator program.
+
+    Do not edit the class manually.
+    """
+    def __init__(self, file: str=None):  # noqa: E501
+        """DatotekaVConlluAsyncOcrBody - a model defined in Swagger
+
+        :param file: The file of this DatotekaVConlluAsyncOcrBody.  # noqa: E501
+        :type file: str
+        """
+        self.swagger_types = {
+            'file': str
+        }
+
+        self.attribute_map = {
+            'file': 'file'
+        }
+        self._file = file
+
+    @classmethod
+    def from_dict(cls, dikt) -> 'DatotekaVConlluAsyncOcrBody':
+        """Returns the dict as a model
+
+        :param dikt: A dict.
+        :type: dict
+        :return: The datotekaVConlluAsync_ocr_body of this DatotekaVConlluAsyncOcrBody.  # noqa: E501
+        :rtype: DatotekaVConlluAsyncOcrBody
+        """
+        return util.deserialize_model(dikt, cls)
+
+    @property
+    def file(self) -> str:
+        """Gets the file of this DatotekaVConlluAsyncOcrBody.
+
+
+        :return: The file of this DatotekaVConlluAsyncOcrBody.
+        :rtype: str
+        """
+        return self._file
+
+    @file.setter
+    def file(self, file: str):
+        """Sets the file of this DatotekaVConlluAsyncOcrBody.
+
+
+        :param file: The file of this DatotekaVConlluAsyncOcrBody.
+        :type file: str
+        """
+        if file is None:
+            raise ValueError("Invalid value for `file`, must not be `None`")  # noqa: E501
+
+        self._file = file

swagger_server/models/datoteka_v_conllu_sync_body.py

@@ -9,15 +9,15 @@ from swagger_server.models.base_model_ import Model
 from swagger_server import util
 
 
-class DatotekaVBesediloBody(Model):
+class DatotekaVConlluSyncBody(Model):
     """NOTE: This class is auto generated by the swagger code generator program.
 
     Do not edit the class manually.
     """
     def __init__(self, file: str=None):  # noqa: E501
-        """DatotekaVBesediloBody - a model defined in Swagger
+        """DatotekaVConlluSyncBody - a model defined in Swagger
 
-        :param file: The file of this DatotekaVBesediloBody.  # noqa: E501
+        :param file: The file of this DatotekaVConlluSyncBody.  # noqa: E501
         :type file: str
         """
         self.swagger_types = {
@@ -30,32 +30,32 @@ class DatotekaVBesediloBody(Model):
         self._file = file
 
     @classmethod
-    def from_dict(cls, dikt) -> 'DatotekaVBesediloBody':
+    def from_dict(cls, dikt) -> 'DatotekaVConlluSyncBody':
         """Returns the dict as a model
 
         :param dikt: A dict.
         :type: dict
-        :return: The datotekaVBesedilo_body of this DatotekaVBesediloBody.  # noqa: E501
-        :rtype: DatotekaVBesediloBody
+        :return: The datotekaVConlluSync_body of this DatotekaVConlluSyncBody.  # noqa: E501
+        :rtype: DatotekaVConlluSyncBody
         """
         return util.deserialize_model(dikt, cls)
 
     @property
     def file(self) -> str:
-        """Gets the file of this DatotekaVBesediloBody.
+        """Gets the file of this DatotekaVConlluSyncBody.
 
 
-        :return: The file of this DatotekaVBesediloBody.
+        :return: The file of this DatotekaVConlluSyncBody.
         :rtype: str
         """
         return self._file
 
     @file.setter
     def file(self, file: str):
-        """Sets the file of this DatotekaVBesediloBody.
+        """Sets the file of this DatotekaVConlluSyncBody.
 
 
-        :param file: The file of this DatotekaVBesediloBody.
+        :param file: The file of this DatotekaVConlluSyncBody.
         :type file: str
         """
         if file is None:

swagger_server/models/datoteka_v_conllu_sync_ocr_body.py

@@ -0,0 +1,64 @@
+# coding: utf-8
+
+from __future__ import absolute_import
+from datetime import date, datetime  # noqa: F401
+
+from typing import List, Dict  # noqa: F401
+
+from swagger_server.models.base_model_ import Model
+from swagger_server import util
+
+
+class DatotekaVConlluSyncOcrBody(Model):
+    """NOTE: This class is auto generated by the swagger code generator program.
+
+    Do not edit the class manually.
+    """
+    def __init__(self, file: str=None):  # noqa: E501
+        """DatotekaVConlluSyncOcrBody - a model defined in Swagger
+
+        :param file: The file of this DatotekaVConlluSyncOcrBody.  # noqa: E501
+        :type file: str
+        """
+        self.swagger_types = {
+            'file': str
+        }
+
+        self.attribute_map = {
+            'file': 'file'
+        }
+        self._file = file
+
+    @classmethod
+    def from_dict(cls, dikt) -> 'DatotekaVConlluSyncOcrBody':
+        """Returns the dict as a model
+
+        :param dikt: A dict.
+        :type: dict
+        :return: The datotekaVConlluSync_ocr_body of this DatotekaVConlluSyncOcrBody.  # noqa: E501
+        :rtype: DatotekaVConlluSyncOcrBody
+        """
+        return util.deserialize_model(dikt, cls)
+
+    @property
+    def file(self) -> str:
+        """Gets the file of this DatotekaVConlluSyncOcrBody.
+
+
+        :return: The file of this DatotekaVConlluSyncOcrBody.
+        :rtype: str
+        """
+        return self._file
+
+    @file.setter
+    def file(self, file: str):
+        """Sets the file of this DatotekaVConlluSyncOcrBody.
+
+
+        :param file: The file of this DatotekaVConlluSyncOcrBody.
+        :type file: str
+        """
+        if file is None:
+            raise ValueError("Invalid value for `file`, must not be `None`")  # noqa: E501
+
+        self._file = file

swagger_server/models/izlusci_async_body.py

@@ -0,0 +1,88 @@
+# coding: utf-8
+
+from __future__ import absolute_import
+from datetime import date, datetime  # noqa: F401
+
+from typing import List, Dict  # noqa: F401
+
+from swagger_server.models.base_model_ import Model
+from swagger_server import util
+
+
+class IzlusciAsyncBody(Model):
+    """NOTE: This class is auto generated by the swagger code generator program.
+
+    Do not edit the class manually.
+    """
+    def __init__(self, conllus: List[str]=None, prepovedane_besede: List[str]=None):  # noqa: E501
+        """IzlusciAsyncBody - a model defined in Swagger
+
+        :param conllus: The conllus of this IzlusciAsyncBody.  # noqa: E501
+        :type conllus: List[str]
+        :param prepovedane_besede: The prepovedane_besede of this IzlusciAsyncBody.  # noqa: E501
+        :type prepovedane_besede: List[str]
+        """
+        self.swagger_types = {
+            'conllus': List[str],
+            'prepovedane_besede': List[str]
+        }
+
+        self.attribute_map = {
+            'conllus': 'conllus',
+            'prepovedane_besede': 'prepovedaneBesede'
+        }
+        self._conllus = conllus
+        self._prepovedane_besede = prepovedane_besede
+
+    @classmethod
+    def from_dict(cls, dikt) -> 'IzlusciAsyncBody':
+        """Returns the dict as a model
+
+        :param dikt: A dict.
+        :type: dict
+        :return: The izlusciAsync_body of this IzlusciAsyncBody.  # noqa: E501
+        :rtype: IzlusciAsyncBody
+        """
+        return util.deserialize_model(dikt, cls)
+
+    @property
+    def conllus(self) -> List[str]:
+        """Gets the conllus of this IzlusciAsyncBody.
+
+
+        :return: The conllus of this IzlusciAsyncBody.
+        :rtype: List[str]
+        """
+        return self._conllus
+
+    @conllus.setter
+    def conllus(self, conllus: List[str]):
+        """Sets the conllus of this IzlusciAsyncBody.
+
+
+        :param conllus: The conllus of this IzlusciAsyncBody.
+        :type conllus: List[str]
+        """
+
+        self._conllus = conllus
+
+    @property
+    def prepovedane_besede(self) -> List[str]:
+        """Gets the prepovedane_besede of this IzlusciAsyncBody.
+
+
+        :return: The prepovedane_besede of this IzlusciAsyncBody.
+        :rtype: List[str]
+        """
+        return self._prepovedane_besede
+
+    @prepovedane_besede.setter
+    def prepovedane_besede(self, prepovedane_besede: List[str]):
+        """Sets the prepovedane_besede of this IzlusciAsyncBody.
+
+
+        :param prepovedane_besede: The prepovedane_besede of this IzlusciAsyncBody.
+        :type prepovedane_besede: List[str]
+        """
+
+        self._prepovedane_besede = prepovedane_besede

swagger_server/models/izlusci_sync_body.py

@@ -9,17 +9,17 @@ from swagger_server.models.base_model_ import Model
 from swagger_server import util
 
 
-class IzlusciBody(Model):
+class IzlusciSyncBody(Model):
     """NOTE: This class is auto generated by the swagger code generator program.
 
     Do not edit the class manually.
     """
     def __init__(self, conllus: List[str]=None, prepovedane_besede: List[str]=None):  # noqa: E501
-        """IzlusciBody - a model defined in Swagger
+        """IzlusciSyncBody - a model defined in Swagger
 
-        :param conllus: The conllus of this IzlusciBody.  # noqa: E501
+        :param conllus: The conllus of this IzlusciSyncBody.  # noqa: E501
         :type conllus: List[str]
-        :param prepovedane_besede: The prepovedane_besede of this IzlusciBody.  # noqa: E501
+        :param prepovedane_besede: The prepovedane_besede of this IzlusciSyncBody.  # noqa: E501
         :type prepovedane_besede: List[str]
         """
         self.swagger_types = {
@@ -35,32 +35,32 @@ class IzlusciBody(Model):
         self._prepovedane_besede = prepovedane_besede
 
     @classmethod
-    def from_dict(cls, dikt) -> 'IzlusciBody':
+    def from_dict(cls, dikt) -> 'IzlusciSyncBody':
         """Returns the dict as a model
 
         :param dikt: A dict.
         :type: dict
-        :return: The izlusci_body of this IzlusciBody.  # noqa: E501
-        :rtype: IzlusciBody
+        :return: The izlusciSync_body of this IzlusciSyncBody.  # noqa: E501
+        :rtype: IzlusciSyncBody
         """
         return util.deserialize_model(dikt, cls)
 
     @property
     def conllus(self) -> List[str]:
-        """Gets the conllus of this IzlusciBody.
+        """Gets the conllus of this IzlusciSyncBody.
 
 
-        :return: The conllus of this IzlusciBody.
+        :return: The conllus of this IzlusciSyncBody.
         :rtype: List[str]
         """
         return self._conllus
 
     @conllus.setter
     def conllus(self, conllus: List[str]):
-        """Sets the conllus of this IzlusciBody.
+        """Sets the conllus of this IzlusciSyncBody.
 
 
-        :param conllus: The conllus of this IzlusciBody.
+        :param conllus: The conllus of this IzlusciSyncBody.
         :type conllus: List[str]
         """
 
@@ -68,20 +68,20 @@ class IzlusciBody(Model):
 
     @property
     def prepovedane_besede(self) -> List[str]:
-        """Gets the prepovedane_besede of this IzlusciBody.
+        """Gets the prepovedane_besede of this IzlusciSyncBody.
 
 
-        :return: The prepovedane_besede of this IzlusciBody.
+        :return: The prepovedane_besede of this IzlusciSyncBody.
         :rtype: List[str]
         """
         return self._prepovedane_besede
 
     @prepovedane_besede.setter
     def prepovedane_besede(self, prepovedane_besede: List[str]):
-        """Sets the prepovedane_besede of this IzlusciBody.
+        """Sets the prepovedane_besede of this IzlusciSyncBody.
 
 
-        :param prepovedane_besede: The prepovedane_besede of this IzlusciBody.
+        :param prepovedane_besede: The prepovedane_besede of this IzlusciSyncBody.
         :type prepovedane_besede: List[str]
         """
 

swagger_server/models/job_response.py

@@ -0,0 +1,172 @@
+# coding: utf-8
+
+from __future__ import absolute_import
+from datetime import date, datetime  # noqa: F401
+
+from typing import List, Dict  # noqa: F401
+
+from swagger_server.models.base_model_ import Model
+from swagger_server import util
+
+
+class JobResponse(Model):
+    """NOTE: This class is auto generated by the swagger code generator program.
+
+    Do not edit the class manually.
+    """
+    def __init__(self, job_status: str=None, finished_on: datetime=None, started_on: datetime=None, created_on: datetime=None, job_result: str=None):  # noqa: E501
+        """JobResponse - a model defined in Swagger
+
+        :param job_status: The job_status of this JobResponse.  # noqa: E501
+        :type job_status: str
+        :param finished_on: The finished_on of this JobResponse.  # noqa: E501
+        :type finished_on: datetime
+        :param started_on: The started_on of this JobResponse.  # noqa: E501
+        :type started_on: datetime
+        :param created_on: The created_on of this JobResponse.  # noqa: E501
+        :type created_on: datetime
+        :param job_result: The job_result of this JobResponse.  # noqa: E501
+        :type job_result: str
+        """
+        self.swagger_types = {
+            'job_status': str,
+            'finished_on': datetime,
+            'started_on': datetime,
+            'created_on': datetime,
+            'job_result': str
+        }
+
+        self.attribute_map = {
+            'job_status': 'job_status',
+            'finished_on': 'finished_on',
+            'started_on': 'started_on',
+            'created_on': 'created_on',
+            'job_result': 'job_result'
+        }
+        self._job_status = job_status
+        self._finished_on = finished_on
+        self._started_on = started_on
+        self._created_on = created_on
+        self._job_result = job_result
+
+    @classmethod
+    def from_dict(cls, dikt) -> 'JobResponse':
+        """Returns the dict as a model
+
+        :param dikt: A dict.
+        :type: dict
+        :return: The JobResponse of this JobResponse.  # noqa: E501
+        :rtype: JobResponse
+        """
+        return util.deserialize_model(dikt, cls)
+
+    @property
+    def job_status(self) -> str:
+        """Gets the job_status of this JobResponse.
+
+
+        :return: The job_status of this JobResponse.
+        :rtype: str
+        """
+        return self._job_status
+
+    @job_status.setter
+    def job_status(self, job_status: str):
+        """Sets the job_status of this JobResponse.
+
+
+        :param job_status: The job_status of this JobResponse.
+        :type job_status: str
+        """
+        allowed_values = ["waiting in que", "currently processing", "finished processing"]  # noqa: E501
+        if job_status not in allowed_values:
+            raise ValueError(
+                "Invalid value for `job_status` ({0}), must be one of {1}"
+                .format(job_status, allowed_values)
+            )
+
+        self._job_status = job_status
+
+    @property
+    def finished_on(self) -> datetime:
+        """Gets the finished_on of this JobResponse.
+
+
+        :return: The finished_on of this JobResponse.
+        :rtype: datetime
+        """
+        return self._finished_on
+
+    @finished_on.setter
+    def finished_on(self, finished_on: datetime):
+        """Sets the finished_on of this JobResponse.
+
+
+        :param finished_on: The finished_on of this JobResponse.
+        :type finished_on: datetime
+        """
+
+        self._finished_on = finished_on
+
+    @property
+    def started_on(self) -> datetime:
+        """Gets the started_on of this JobResponse.
+
+
+        :return: The started_on of this JobResponse.
+        :rtype: datetime
+        """
+        return self._started_on
+
+    @started_on.setter
+    def started_on(self, started_on: datetime):
+        """Sets the started_on of this JobResponse.
+
+
+        :param started_on: The started_on of this JobResponse.
+        :type started_on: datetime
+        """
+
+        self._started_on = started_on
+
+    @property
+    def created_on(self) -> datetime:
+        """Gets the created_on of this JobResponse.
+
+
+        :return: The created_on of this JobResponse.
+        :rtype: datetime
+        """
+        return self._created_on
+
+    @created_on.setter
+    def created_on(self, created_on: datetime):
+        """Sets the created_on of this JobResponse.
+
+
+        :param created_on: The created_on of this JobResponse.
+        :type created_on: datetime
+        """
+
+        self._created_on = created_on
+
+    @property
+    def job_result(self) -> str:
+        """Gets the job_result of this JobResponse.
+
+
+        :return: The job_result of this JobResponse.
+        :rtype: str
+        """
+        return self._job_result
+
+    @job_result.setter
+    def job_result(self, job_result: str):
+        """Sets the job_result of this JobResponse.
+
+
+        :param job_result: The job_result of this JobResponse.
+        :type job_result: str
+        """
+
+        self._job_result = job_result

swagger_server/models/oznaci_besedilo_async_body.py

@@ -0,0 +1,62 @@
+# coding: utf-8
+
+from __future__ import absolute_import
+from datetime import date, datetime  # noqa: F401
+
+from typing import List, Dict  # noqa: F401
+
+from swagger_server.models.base_model_ import Model
+from swagger_server import util
+
+
+class OznaciBesediloAsyncBody(Model):
+    """NOTE: This class is auto generated by the swagger code generator program.
+
+    Do not edit the class manually.
+    """
+    def __init__(self, besedilo: str=None):  # noqa: E501
+        """OznaciBesediloAsyncBody - a model defined in Swagger
+
+        :param besedilo: The besedilo of this OznaciBesediloAsyncBody.  # noqa: E501
+        :type besedilo: str
+        """
+        self.swagger_types = {
+            'besedilo': str
+        }
+
+        self.attribute_map = {
+            'besedilo': 'besedilo'
+        }
+        self._besedilo = besedilo
+
+    @classmethod
+    def from_dict(cls, dikt) -> 'OznaciBesediloAsyncBody':
+        """Returns the dict as a model
+
+        :param dikt: A dict.
+        :type: dict
+        :return: The oznaciBesediloAsync_body of this OznaciBesediloAsyncBody.  # noqa: E501
+        :rtype: OznaciBesediloAsyncBody
+        """
+        return util.deserialize_model(dikt, cls)
+
+    @property
+    def besedilo(self) -> str:
+        """Gets the besedilo of this OznaciBesediloAsyncBody.
+
+
+        :return: The besedilo of this OznaciBesediloAsyncBody.
+        :rtype: str
+        """
+        return self._besedilo
+
+    @besedilo.setter
+    def besedilo(self, besedilo: str):
+        """Sets the besedilo of this OznaciBesediloAsyncBody.
+
+
+        :param besedilo: The besedilo of this OznaciBesediloAsyncBody.
+        :type besedilo: str
+        """
+
+        self._besedilo = besedilo

swagger_server/requets_db/models/vrsta.py

@@ -0,0 +1,90 @@
+import pathlib
+
+import werkzeug.datastructures
+from peewee import *
+from datetime import datetime
+import os
+from swagger_server.util import get_random_filename
+from werkzeug.utils import secure_filename
+
+LOCAL_PATH = "requets_db/dbs"
+SERVER_PATH = "swagger_server/requets_db/dbs"
+
+if not os.path.exists(LOCAL_PATH):
+    if os.path.exists('requets_db'):
+        os.makedirs(LOCAL_PATH, exist_ok=True)
+    elif os.path.exists('swagger_server/requets_db'):
+        os.makedirs(SERVER_PATH, exist_ok=True)
+
+DB = f'{LOCAL_PATH}/jobs.db'
+if not os.path.exists(LOCAL_PATH):
+    DB = f'{SERVER_PATH}/jobs.db'
+db = SqliteDatabase(DB, pragmas={
+    # 'journal_mode': 'wal',
+    'cache_size': -1 * 128 * 1024,  # 128MB
+    'foreign_keys': 1
+})
+
+
+class BaseModel(Model):
+    class Meta:
+        database = db
+
+
+class Job(BaseModel):
+    id = AutoField(index=True)
+    job_type = IntegerField()
+    job_input = TextField(index=True, null=True)
+    job_output = TextField(null=True)
+    created_on = DateTimeField(default=datetime.utcnow)
+    finished_on = DateTimeField(null=True)
+    started_on = DateTimeField(null=True)
+    input_size = IntegerField()
+    input_file = TextField(index=True, null=True)
+
+
+db.drop_tables([Job])  # TODO: After pushing this, comment it and push again
+db.create_tables([Job])
+
+
+class JobManager:
+    @staticmethod
+    def create_job(job_type, job_input) -> Tuple(Job, bool):
+        """
+        :param: job_type
+        :possibilities:
+        # 1 = pretvori datoteko v besedilo, 2 = oznaci besedilo, 12 = oboje
+        # 3 = pretvori dat v besedilo OCR, 2 = oznaci besedilo, 32 = oboje
+        # 4 = izlusci async
+
+        :return: Job object, Did already exist boolean
+        """
+        try:
+            if job_type in [2, 4]:
+                job, is_new = Job.get_or_create(job_type=job_type, job_input=job_input, input_size=len(job_input))
+            elif job_type in [1, 3, 12, 32]:
+                tmp_file = ""
+                while True:
+                    # just in case a VERY rare chance of a same generate name happens
+                    tmp_file = "tmp/" + secure_filename(get_random_filename() + "_" + job_input.filename)
+                    if not os.path.exists(tmp_file):
+                        break
+                pathlib.Path('tmp').mkdir(exist_ok=True)
+                job_input: werkzeug.datastructures.FileStorage
+                job_input.save(tmp_file)
+                job, is_new = Job.get_or_create(job_type=job_type, input_file=tmp_file, input_size=-1)
+            return job, is_new
+
+        except Exception as e:
+            print(f'Exception at creating a job: {e}')
+            return None, False
+
+        # try:
+        #     job = Job.get_or_none(Job.job_input == job_input, Job.job_type == job_type)
+        #     if job:
+        #         return job, True
+        #     job = Job.create(job_type=job_type, job_input=job_input, input_size=len(job_input))
+        #     return job, False
+        # except Exception as e:
+        #     print(f'Exception at creating a job: {e}')
+        #     return None, False

swagger_server/swagger/swagger.yaml

@@ -6,18 +6,64 @@ servers:
 - url: http://localhost:8089
   description: Generated server url
 paths:
-  /oznaciBesedilo:
+  /job/{job_id}:
+    get:
+      tags:
+      - jobs
+      summary: Vrne status
+      operationId: get_job_status
+      parameters:
+      - name: job_id
+        in: path
+        required: true
+        style: simple
+        explode: false
+        schema:
+          type: integer
+          format: int64
+      responses:
+        "200":
+          description: OK
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/JobResponse'
+      x-openapi-router-controller: swagger_server.controllers.jobs_controller
+    delete:
+      tags:
+      - jobs
+      summary: Izbriše job
+      operationId: delete_job
+      parameters:
+      - name: job_id
+        in: path
+        required: true
+        style: simple
+        explode: false
+        schema:
+          type: integer
+          format: int64
+      responses:
+        "200":
+          description: OK
+          content:
+            '*/*':
+              schema:
+                type: string
+                x-content-type: '*/*'
+      x-openapi-router-controller: swagger_server.controllers.jobs_controller
+  /oznaciBesediloAsync:
     post:
       tags:
-      - marktext
-      summary: Označi besedilo s classlo/stanzo z uporabo slovenskih modelov ter vrne
-        conll-u format
+      - marktext-async
+      summary: Označi surovo (angl. raw) besedilo s classlo/stanzo z uporabo slovenskih
+        modelov ter vrne conll-u format
       operationId: get_text
       requestBody:
         content:
           application/json:
             schema:
-              type: string
+              $ref: '#/components/schemas/oznaciBesediloAsync_body'
         required: true
       responses:
         "200":
@@ -27,18 +73,101 @@ paths:
               schema:
                 type: string
                 x-content-type: '*/*'
-      x-openapi-router-controller: swagger_server.controllers.marktext_controller
-  /izlusci:
+      x-openapi-router-controller: swagger_server.controllers.marktext_async_controller
+  /datotekaVBesediloAsync:
+    post:
+      tags:
+      - marktext-async
+      summary: "Pretvori datoteko v besedilo, vrača tekst"
+      operationId: get_text_from_doc_async
+      requestBody:
+        content:
+          multipart/form-data:
+            schema:
+              $ref: '#/components/schemas/datotekaVBesediloAsync_body'
+      responses:
+        "200":
+          description: OK
+          content:
+            '*/*':
+              schema:
+                type: string
+                x-content-type: '*/*'
+      x-openapi-router-controller: swagger_server.controllers.marktext_async_controller
+  /datotekaVConlluAsync:
+    post:
+      tags:
+      - marktext-async
+      summary: Pretvori datoteko v besedilo in označi s classlo/stanzo z uporabo slovenskih
+        modelov ter vrne conll-u format
+      operationId: get_conllu_from_file_async
+      requestBody:
+        content:
+          multipart/form-data:
+            schema:
+              $ref: '#/components/schemas/datotekaVConlluAsync_body'
+      responses:
+        "200":
+          description: OK
+          content:
+            '*/*':
+              schema:
+                type: string
+                x-content-type: '*/*'
+      x-openapi-router-controller: swagger_server.controllers.marktext_async_controller
+  /datotekaVConlluAsync/ocr:
+    post:
+      tags:
+      - marktext-async
+      summary: Pretvori datoteko v besedilo in označi s classlo/stanzo z uporabo slovenskih
+        modelov ter vrne conll-u format
+      operationId: get_conllu_from_file_ocr_async
+      requestBody:
+        content:
+          multipart/form-data:
+            schema:
+              $ref: '#/components/schemas/datotekaVConlluAsync_ocr_body'
+      responses:
+        "200":
+          description: OK
+          content:
+            '*/*':
+              schema:
+                type: string
+                x-content-type: '*/*'
+      x-openapi-router-controller: swagger_server.controllers.marktext_async_controller
+  /datotekaVBesediloAsync/ocr:
+    post:
+      tags:
+      - marktext-async
+      summary: "Pretvori datoteko v besedilo s pomočjo ocr razpoznavanja, vrača tekst"
+      operationId: get_text_from_file_ocr_async
+      requestBody:
+        content:
+          multipart/form-data:
+            schema:
+              $ref: '#/components/schemas/datotekaVBesediloAsync_ocr_body'
+      responses:
+        "200":
+          description: OK
+          content:
+            '*/*':
+              schema:
+                type: string
+                x-content-type: '*/*'
+      x-openapi-router-controller: swagger_server.controllers.marktext_async_controller
+  /izlusciSync:
     post:
       tags:
       - extract
-      summary: Izlusci terminološke kandidate iz seznama besedil v conllu obliki
-      operationId: get_candidates
+      summary: "Izlusci terminološke kandidate iz seznama besedil v conllu obliki\
+        \ [sihrono, rezultat v sami zahtevi]"
+      operationId: get_candidates_sync
       requestBody:
         content:
           application/json:
             schema:
-              $ref: '#/components/schemas/izlusci_body'
+              $ref: '#/components/schemas/izlusciSync_body'
         required: true
       responses:
         "200":
@@ -51,10 +180,52 @@ paths:
                   $ref: '#/components/schemas/TerminoloskiKandidat'
                 x-content-type: '*/*'
       x-openapi-router-controller: swagger_server.controllers.extract_controller
-  /datotekaVBesedilo/ocr:
+  /izlusciAsync:
     post:
       tags:
-      - doc-2text
+      - extract
+      summary: "Izlusci terminološke kandidate iz seznama besedil v conllu obliki\
+        \ [asinhrono, ustvari novi job]"
+      operationId: get_candidates_async
+      requestBody:
+        content:
+          application/json:
+            schema:
+              $ref: '#/components/schemas/izlusciAsync_body'
+        required: true
+      responses:
+        "200":
+          description: OK
+          content:
+            '*/*':
+              schema:
+                type: string
+                x-content-type: '*/*'
+      x-openapi-router-controller: swagger_server.controllers.extract_controller
+  /datotekaVBesediloSync:
+    post:
+      tags:
+      - marktext-sync
+      summary: "Pretvori datoteko formata pdf, doc, docx, ppt, xls,... vrača besedilo"
+      operationId: datoteka_v_besedilo_sync_post
+      requestBody:
+        content:
+          multipart/form-data:
+            schema:
+              $ref: '#/components/schemas/datotekaVBesediloSync_body'
+      responses:
+        "200":
+          description: OK
+          content:
+            '*/*':
+              schema:
+                type: string
+                x-content-type: '*/*'
+      x-openapi-router-controller: swagger_server.controllers.marktext_sync_controller
+  /datotekaVBesediloSync/ocr:
+    post:
+      tags:
+      - marktext-sync
       summary: "Pretvori datoteko formata pdf, doc, docx, ppt, xls,... v besedilo\
         \ s pomočjo ocr razpoznavanja"
       operationId: get_text_ocr
@@ -62,7 +233,7 @@ paths:
         content:
           multipart/form-data:
             schema:
-              $ref: '#/components/schemas/datotekaVBesedilo_ocr_body'
+              $ref: '#/components/schemas/datotekaVBesediloSync_ocr_body'
       responses:
         "200":
           description: OK
@@ -71,18 +242,18 @@ paths:
               schema:
                 type: string
                 x-content-type: '*/*'
-      x-openapi-router-controller: swagger_server.controllers.doc2text_controller
-  /datotekaVBesedilo/:
+      x-openapi-router-controller: swagger_server.controllers.marktext_sync_controller
+  /datotekaVConlluSync:
     post:
       tags:
-      - doc-2text
-      summary: "Pretvori datoteko formata pdf, doc, docx, ppt, xls,... v besedilo"
-      operationId: datoteka_v_besedilo_post
+      - marktext-sync
+      summary: "Pretvori datoteko formata pdf, doc, docx, ppt, xls,... vrača conllu"
+      operationId: datoteka_v_besedilo_in_classla
       requestBody:
         content:
           multipart/form-data:
             schema:
-              $ref: '#/components/schemas/datotekaVBesedilo_body'
+              $ref: '#/components/schemas/datotekaVConlluSync_body'
       responses:
         "200":
           description: OK
@@ -91,7 +262,28 @@ paths:
               schema:
                 type: string
                 x-content-type: '*/*'
-      x-openapi-router-controller: swagger_server.controllers.doc2text_controller
+      x-openapi-router-controller: swagger_server.controllers.marktext_sync_controller
+  /datotekaVConlluSync/ocr:
+    post:
+      tags:
+      - marktext-sync
+      summary: "Pretvori datoteko formata pdf, doc, docx, ppt, xls,... v conllu s\
+        \ pomočjo ocr razpoznavanja"
+      operationId: get_conllu_ocr
+      requestBody:
+        content:
+          multipart/form-data:
+            schema:
+              $ref: '#/components/schemas/datotekaVConlluSync_ocr_body'
+      responses:
+        "200":
+          description: OK
+          content:
+            '*/*':
+              schema:
+                type: string
+                x-content-type: '*/*'
+      x-openapi-router-controller: swagger_server.controllers.marktext_sync_controller
   /oss/steviloBesedilPoIskanju:
     get:
       tags:
@@ -101,7 +293,7 @@ paths:
       parameters:
       - name: leta
         in: query
-        required: true
+        required: false
         style: form
         explode: true
         schema:
@@ -111,25 +303,7 @@ paths:
             format: int64
       - name: vrste
         in: query
-        required: true
-        style: form
-        explode: true
-        schema:
-          type: array
-          items:
-            type: string
-      - name: kljucnebesede
-        in: query
-        required: true
-        style: form
-        explode: true
-        schema:
-          type: array
-          items:
-            type: string
-      - name: cerifpodrocja
-        in: query
-        required: true
+        required: false
         style: form
         explode: true
         schema:
@@ -137,6 +311,24 @@ paths:
           items:
             type: integer
             format: int64
+      - name: kljucnebesede
+        in: query
+        required: false
+        style: form
+        explode: true
+        schema:
+          type: array
+          items:
+            type: string
+      - name: udk
+        in: query
+        required: false
+        style: form
+        explode: true
+        schema:
+          type: array
+          items:
+            type: string
       responses:
         "200":
           description: OK
@@ -156,7 +348,7 @@ paths:
       parameters:
       - name: leta
         in: query
-        required: true
+        required: false
         style: form
         explode: true
         schema:
@@ -166,25 +358,7 @@ paths:
             format: int64
       - name: vrste
         in: query
-        required: true
-        style: form
-        explode: true
-        schema:
-          type: array
-          items:
-            type: string
-      - name: kljucnebesede
-        in: query
-        required: true
-        style: form
-        explode: true
-        schema:
-          type: array
-          items:
-            type: string
-      - name: cerifpodrocja
-        in: query
-        required: true
+        required: false
         style: form
         explode: true
         schema:
@@ -192,6 +366,24 @@ paths:
           items:
             type: integer
             format: int64
+      - name: kljucnebesede
+        in: query
+        required: false
+        style: form
+        explode: true
+        schema:
+          type: array
+          items:
+            type: string
+      - name: udk
+        in: query
+        required: false
+        style: form
+        explode: true
+        schema:
+          type: array
+          items:
+            type: string
       responses:
         "200":
           description: OK
@@ -270,7 +462,7 @@ paths:
       summary: Vrne binarni zapis v originalnem formatu po id-ju datoteke
       operationId: get_file
       parameters:
-      - name: id
+      - name: file_id
         in: query
         required: true
         style: form
@@ -353,7 +545,7 @@ paths:
       summary: Vrne CoNNL-U po id-ju datoteke
       operationId: get_conllu
       parameters:
-      - name: id
+      - name: file_id
         in: query
         required: true
         style: form
@@ -377,7 +569,7 @@ paths:
       summary: Vrne besedilo po id-ju datoteke
       operationId: oss_besedilo_po_id_get
       parameters:
-      - name: id
+      - name: file_id
         in: query
         required: true
         style: form
@@ -485,7 +677,72 @@ components:
         kanonicnaoblika: kanonicnaoblika
         nosilnautez: 0.8008282
         kandidat: kandidat
-    izlusci_body:
+    JobResponse:
+      required:
+      - finished_job
+      type: object
+      properties:
+        job_status:
+          type: string
+          enum:
+          - waiting in que
+          - currently processing
+          - finished processing
+        finished_on:
+          type: string
+          format: date-time
+        started_on:
+          type: string
+          format: date-time
+        created_on:
+          type: string
+          format: date-time
+        job_result:
+          type: string
+      example:
+        job_status: waiting in que
+        started_on: 2000-01-23T04:56:07.000+00:00
+        created_on: 2000-01-23T04:56:07.000+00:00
+        finished_on: 2000-01-23T04:56:07.000+00:00
+        job_result: job_result
+    oznaciBesediloAsync_body:
+      type: object
+      properties:
+        besedilo:
+          type: string
+    datotekaVBesediloAsync_body:
+      required:
+      - file
+      type: object
+      properties:
+        file:
+          type: string
+          format: binary
+    datotekaVConlluAsync_body:
+      required:
+      - file
+      type: object
+      properties:
+        file:
+          type: string
+          format: binary
+    datotekaVConlluAsync_ocr_body:
+      required:
+      - file
+      type: object
+      properties:
+        file:
+          type: string
+          format: binary
+    datotekaVBesediloAsync_ocr_body:
+      required:
+      - file
+      type: object
+      properties:
+        file:
+          type: string
+          format: binary
+    izlusciSync_body:
       type: object
       properties:
         conllus:
@@ -496,7 +753,18 @@ components:
           type: array
           items:
             type: string
-    datotekaVBesedilo_ocr_body:
+    izlusciAsync_body:
+      type: object
+      properties:
+        conllus:
+          type: array
+          items:
+            type: string
+        prepovedaneBesede:
+          type: array
+          items:
+            type: string
+    datotekaVBesediloSync_body:
       required:
       - file
       type: object
@@ -504,7 +772,23 @@ components:
         file:
           type: string
           format: binary
-    datotekaVBesedilo_body:
+    datotekaVBesediloSync_ocr_body:
+      required:
+      - file
+      type: object
+      properties:
+        file:
+          type: string
+          format: binary
+    datotekaVConlluSync_body:
+      required:
+      - file
+      type: object
+      properties:
+        file:
+          type: string
+          format: binary
+    datotekaVConlluSync_ocr_body:
       required:
       - file
       type: object

swagger_server/test/__init__.py

@@ -1,16 +0,0 @@
-import logging
-
-import connexion
-from flask_testing import TestCase
-
-from swagger_server.encoder import JSONEncoder
-
-
-class BaseTestCase(TestCase):
-
-    def create_app(self):
-        logging.getLogger('connexion.operation').setLevel('ERROR')
-        app = connexion.App(__name__, specification_dir='../swagger/')
-        app.app.json_encoder = JSONEncoder
-        app.add_api('swagger.yaml')
-        return app.app

swagger_server/test/__main__.py

@@ -0,0 +1,16 @@
+#!/usr/bin/env python3
+
+import connexion
+
+from swagger_server import encoder
+
+
+def main():
+    app = connexion.App(__name__, specification_dir='./swagger/')
+    app.app.json_encoder = encoder.JSONEncoder
+    app.add_api('swagger.yaml', arguments={'title': 'OpenAPI definition'}, pythonic_params=True)
+    app.run(port=8080)
+
+
+if __name__ == '__main__':
+    main()

swagger_server/test/encoder.py

@@ -0,0 +1,20 @@
+from connexion.apps.flask_app import FlaskJSONEncoder
+import six
+
+from swagger_server.models.base_model_ import Model
+
+
+class JSONEncoder(FlaskJSONEncoder):
+    include_nulls = False
+
+    def default(self, o):
+        if isinstance(o, Model):
+            dikt = {}
+            for attr, _ in six.iteritems(o.swagger_types):
+                value = getattr(o, attr)
+                if value is None and not self.include_nulls:
+                    continue
+                attr = o.attribute_map[attr]
+                dikt[attr] = value
+            return dikt
+        return FlaskJSONEncoder.default(self, o)

swagger_server/test/test_doc2text_controller.py

@@ -1,45 +0,0 @@
-# coding: utf-8
-
-from __future__ import absolute_import
-
-from flask import json
-from six import BytesIO
-
-from swagger_server.test import BaseTestCase
-
-
-class TestDoc2textController(BaseTestCase):
-    """Doc2textController integration test stubs"""
-
-    def test_datoteka_v_besedilo_post(self):
-        """Test case for datoteka_v_besedilo_post
-
-        Pretvori datoteko formata pdf, doc, docx, ppt, xls,... v besedilo
-        """
-        data = dict(file='file_example')
-        response = self.client.open(
-            '/datotekaVBesedilo/',
-            method='POST',
-            data=data,
-            content_type='multipart/form-data')
-        self.assert200(response,
-                       'Response body is : ' + response.data.decode('utf-8'))
-
-    def test_get_text_ocr(self):
-        """Test case for get_text_ocr
-
-        Pretvori datoteko formata pdf, doc, docx, ppt, xls,... v besedilo s pomočjo ocr razpoznavanja
-        """
-        data = dict(file='file_example')
-        response = self.client.open(
-            '/datotekaVBesedilo/ocr',
-            method='POST',
-            data=data,
-            content_type='multipart/form-data')
-        self.assert200(response,
-                       'Response body is : ' + response.data.decode('utf-8'))
-
-
-if __name__ == '__main__':
-    import unittest
-    unittest.main()

swagger_server/test/test_extract_controller.py

@@ -1,33 +0,0 @@
-# coding: utf-8
-
-from __future__ import absolute_import
-
-from flask import json
-from six import BytesIO
-
-from swagger_server.models.izlusci_body import IzlusciBody  # noqa: E501
-from swagger_server.models.terminoloski_kandidat import TerminoloskiKandidat  # noqa: E501
-from swagger_server.test import BaseTestCase
-
-
-class TestExtractController(BaseTestCase):
-    """ExtractController integration test stubs"""
-
-    def test_get_candidates(self):
-        """Test case for get_candidates
-
-        Izlusci terminološke kandidate iz seznama besedil v conllu obliki
-        """
-        body = IzlusciBody()
-        response = self.client.open(
-            '/izlusci',
-            method='POST',
-            data=json.dumps(body),
-            content_type='application/json')
-        self.assert200(response,
-                       'Response body is : ' + response.data.decode('utf-8'))
-
-
-if __name__ == '__main__':
-    import unittest
-    unittest.main()

swagger_server/test/test_marktext_controller.py

@@ -1,31 +0,0 @@
-# coding: utf-8
-
-from __future__ import absolute_import
-
-from flask import json
-from six import BytesIO
-
-from swagger_server.test import BaseTestCase
-
-
-class TestMarktextController(BaseTestCase):
-    """MarktextController integration test stubs"""
-
-    def test_get_text(self):
-        """Test case for get_text
-
-        Označi besedilo s classlo/stanzo z uporabo slovenskih modelov ter vrne conll-u format
-        """
-        body = 'body_example'
-        response = self.client.open(
-            '/oznaciBesedilo',
-            method='POST',
-            data=json.dumps(body),
-            content_type='application/json')
-        self.assert200(response,
-                       'Response body is : ' + response.data.decode('utf-8'))
-
-
-if __name__ == '__main__':
-    import unittest
-    unittest.main()

swagger_server/test/test_oss_controller.py

@@ -1,137 +0,0 @@
-# coding: utf-8
-
-from __future__ import absolute_import
-
-from flask import json
-from six import BytesIO
-
-from swagger_server.models.terminoloski_kandidat import TerminoloskiKandidat  # noqa: E501
-from swagger_server.test import BaseTestCase
-
-
-class TestOssController(BaseTestCase):
-    """OssController integration test stubs"""
-
-    def test_get_conllu(self):
-        """Test case for get_conllu
-
-        Vrne CoNNL-U po id-ju datoteke
-        """
-        query_string = [('id', 789)]
-        response = self.client.open(
-            '/oss/conlluPoId',
-            method='GET',
-            query_string=query_string)
-        self.assert200(response,
-                       'Response body is : ' + response.data.decode('utf-8'))
-
-    def test_get_conllus(self):
-        """Test case for get_conllus
-
-        Vrne seznam CoNNL-U-jev glede na iskalne pogoje
-        """
-        query_string = [('leta', 56),
-                        ('vrste', 'vrste_example'),
-                        ('kljucnebesede', 'kljucnebesede_example'),
-                        ('cerifpodrocja', 56)]
-        response = self.client.open(
-            '/oss/conlluPoIskanju',
-            method='GET',
-            query_string=query_string)
-        self.assert200(response,
-                       'Response body is : ' + response.data.decode('utf-8'))
-
-    def test_get_extracted_words(self):
-        """Test case for get_extracted_words
-
-        Vrne terminloške kandidate glede na 
-        """
-        query_string = [('leta', 56),
-                        ('vrste', 'vrste_example'),
-                        ('kljucnebesede', 'kljucnebesede_example'),
-                        ('cerifpodrocja', 56)]
-        response = self.client.open(
-            '/oss/izlusciPoIskanju',
-            method='GET',
-            query_string=query_string)
-        self.assert200(response,
-                       'Response body is : ' + response.data.decode('utf-8'))
-
-    def test_get_file(self):
-        """Test case for get_file
-
-        Vrne binarni zapis v originalnem formatu po id-ju datoteke
-        """
-        query_string = [('id', 789)]
-        response = self.client.open(
-            '/oss/datotekaPoId',
-            method='GET',
-            query_string=query_string)
-        self.assert200(response,
-                       'Response body is : ' + response.data.decode('utf-8'))
-
-    def test_get_files(self):
-        """Test case for get_files
-
-        Vrne seznam binarnih zapisov v originalnem formatu glede na iskalne pogoje
-        """
-        query_string = [('leta', 56),
-                        ('vrste', 'vrste_example'),
-                        ('kljucnebesede', 'kljucnebesede_example'),
-                        ('cerifpodrocja', 56)]
-        response = self.client.open(
-            '/oss/datotekePoIskanju',
-            method='GET',
-            query_string=query_string)
-        self.assert200(response,
-                       'Response body is : ' + response.data.decode('utf-8'))
-
-    def test_get_number_texts(self):
-        """Test case for get_number_texts
-
-        Vrne število besedil glede na iskalne pogoje
-        """
-        query_string = [('leta', 56),
-                        ('vrste', 'vrste_example'),
-                        ('kljucnebesede', 'kljucnebesede_example'),
-                        ('cerifpodrocja', 56)]
-        response = self.client.open(
-            '/oss/steviloBesedilPoIskanju',
-            method='GET',
-            query_string=query_string)
-        self.assert200(response,
-                       'Response body is : ' + response.data.decode('utf-8'))
-
-    def test_get_texts(self):
-        """Test case for get_texts
-
-        Vrne seznam besedil glede na iskalne pogoje
-        """
-        query_string = [('leta', 56),
-                        ('vrste', 'vrste_example'),
-                        ('kljucnebesede', 'kljucnebesede_example'),
-                        ('cerifpodrocja', 56)]
-        response = self.client.open(
-            '/oss/besedilaPoIskanju',
-            method='GET',
-            query_string=query_string)
-        self.assert200(response,
-                       'Response body is : ' + response.data.decode('utf-8'))
-
-    def test_oss_besedilo_po_id_get(self):
-        """Test case for oss_besedilo_po_id_get
-
-        Vrne besedilo po id-ju datoteke
-        """
-        query_string = [('id', 789)]
-        response = self.client.open(
-            '/oss/besediloPoId',
-            method='GET',
-            query_string=query_string)
-        self.assert200(response,
-                       'Response body is : ' + response.data.decode('utf-8'))
-
-
-if __name__ == '__main__':
-    import unittest
-    unittest.main()

swagger_server/test/type_util.py

@@ -0,0 +1,32 @@
+# coding: utf-8
+
+import sys
+
+if sys.version_info < (3, 7):
+    import typing
+
+    def is_generic(klass):
+        """ Determine whether klass is a generic class """
+        return type(klass) == typing.GenericMeta
+
+    def is_dict(klass):
+        """ Determine whether klass is a Dict """
+        return klass.__extra__ == dict
+
+    def is_list(klass):
+        """ Determine whether klass is a List """
+        return klass.__extra__ == list
+
+else:
+
+    def is_generic(klass):
+        """ Determine whether klass is a generic class """
+        return hasattr(klass, '__origin__')
+
+    def is_dict(klass):
+        """ Determine whether klass is a Dict """
+        return klass.__origin__ == dict
+
+    def is_list(klass):
+        """ Determine whether klass is a List """
+        return klass.__origin__ == list

swagger_server/test/util.py

@@ -0,0 +1,142 @@
+import datetime
+
+import six
+import typing
+from swagger_server import type_util
+
+
+def _deserialize(data, klass):
+    """Deserializes dict, list, str into an object.
+
+    :param data: dict, list or str.
+    :param klass: class literal, or string of class name.
+
+    :return: object.
+    """
+    if data is None:
+        return None
+
+    if klass in six.integer_types or klass in (float, str, bool, bytearray):
+        return _deserialize_primitive(data, klass)
+    elif klass == object:
+        return _deserialize_object(data)
+    elif klass == datetime.date:
+        return deserialize_date(data)
+    elif klass == datetime.datetime:
+        return deserialize_datetime(data)
+    elif type_util.is_generic(klass):
+        if type_util.is_list(klass):
+            return _deserialize_list(data, klass.__args__[0])
+        if type_util.is_dict(klass):
+            return _deserialize_dict(data, klass.__args__[1])
+    else:
+        return deserialize_model(data, klass)
+
+
+def _deserialize_primitive(data, klass):
+    """Deserializes to primitive type.
+
+    :param data: data to deserialize.
+    :param klass: class literal.
+
+    :return: int, long, float, str, bool.
+    :rtype: int | long | float | str | bool
+    """
+    try:
+        value = klass(data)
+    except UnicodeEncodeError:
+        value = six.u(data)
+    except TypeError:
+        value = data
+    return value
+
+
+def _deserialize_object(value):
+    """Return an original value.
+
+    :return: object.
+    """
+    return value
+
+
+def deserialize_date(string):
+    """Deserializes string to date.
+
+    :param string: str.
+    :type string: str
+    :return: date.
+    :rtype: date
+    """
+    try:
+        from dateutil.parser import parse
+        return parse(string).date()
+    except ImportError:
+        return string
+
+
+def deserialize_datetime(string):
+    """Deserializes string to datetime.
+
+    The string should be in iso8601 datetime format.
+
+    :param string: str.
+    :type string: str
+    :return: datetime.
+    :rtype: datetime
+    """
+    try:
+        from dateutil.parser import parse
+        return parse(string)
+    except ImportError:
+        return string
+
+
+def deserialize_model(data, klass):
+    """Deserializes list or dict to model.
+
+    :param data: dict, list.
+    :type data: dict | list
+    :param klass: class literal.
+    :return: model object.
+    """
+    instance = klass()
+
+    if not instance.swagger_types:
+        return data
+
+    for attr, attr_type in six.iteritems(instance.swagger_types):
+        if data is not None \
+                and instance.attribute_map[attr] in data \
+                and isinstance(data, (list, dict)):
+            value = data[instance.attribute_map[attr]]
+            setattr(instance, attr, _deserialize(value, attr_type))
+
+    return instance
+
+
+def _deserialize_list(data, boxed_type):
+    """Deserializes a list and its elements.
+
+    :param data: list to deserialize.
+    :type data: list
+    :param boxed_type: class literal.
+
+    :return: deserialized list.
+    :rtype: list
+    """
+    return [_deserialize(sub_data, boxed_type)
+            for sub_data in data]
+
+
+def _deserialize_dict(data, boxed_type):
+    """Deserializes a dict and its elements.
+
+    :param data: dict to deserialize.
+    :type data: dict
+    :param boxed_type: class literal.
+
+    :return: deserialized dict.
+    :rtype: dict
+    """
+    return {k: _deserialize(v, boxed_type)
+            for k, v in six.iteritems(data)}

swagger_server/util.py

@@ -1,8 +1,18 @@
+import codecs
 import datetime
+import os.path
+import pathlib
 
 import six
 import typing
+
+import werkzeug.datastructures
+from werkzeug.utils import secure_filename
+
 from swagger_server import type_util
+import pandas as pd
+import string
+import random
 
 
 def _deserialize(data, klass):
@@ -140,3 +150,66 @@ def _deserialize_dict(data, boxed_type):
     """
     return {k: _deserialize(v, boxed_type)
             for k, v in six.iteritems(data)}
+
+
+def is_docker() -> bool:
+    # todo: better way of checking if we're on docker or if we're in the develoment enviroment
+    return not os.path.exists('.env')
+
+
+def get_conllu_file_path_by_id(file_id):
+    r = f'classla_OS2022/conll/rsdo_doc-{file_id}.plainText.conllu'
+    if is_docker():
+        return f'/usr/src/app/{r}'
+    return f'../mnt/ssd/ds_ftp/{r}'
+
+
+def get_original_file_path_by_id(file_id):
+    r = f'classla_OS2022/besedila/rsdo_doc-{file_id}.xml'
+    if is_docker():
+        return f'/usr/src/app/{r}'
+    return f'../mnt/ssd/ds_ftp/{r}'
+
+
+def get_tei_file_path_by_id(file_id):
+    r = f'classla_OS2022/tei/rsdo_doc-{file_id}.plainText.tei.xml'
+    if is_docker():
+        return f'/usr/src/app/{r}'
+    return f'../mnt/ssd/ds_ftp/{r}'
+
+
+def get_files_by_keywords(kljucnebesede):
+    ret = []
+    kljucnebesede = [k.lower() for k in kljucnebesede]
+    # Temporary solution until connection with mariadb is fixed
+    ngrams_path = "classla_OS2022/ngrams/" if is_docker() else "../mnt/ssd/ds_ftp/classla_OS2022/ngrams/"
+    print("Looping trough ngrams")
+    for path, dirs, files, in os.walk(ngrams_path):
+        for i, _file in enumerate(files[:100]):
+            if i % 500 == 0: print(f"{i}/{len(files)}")
+            file = f'{ngrams_path}{_file}'
+            data = pd.read_csv(file, sep='\t')
+            amount = len(data[data['ngram_len'] == 1 & data['gram_text'].str.lower().isin(kljucnebesede)])
+            # this should be 1
+            if amount >= 1:
+                ret.append(_file[9:][:-12])
+    return ret
+
+
+def get_random_filename():
+    ts = str(int(datetime.datetime.now().timestamp()))
+    extra = ''.join(random.choices(string.ascii_letters + string.digits, k=8))
+    return f'{ts}_{extra}'
+
+
+def create_random_file_in_tmp_folder(fill_content, extension=""):
+    pathlib.Path('tmp').mkdir(exist_ok=True)
+    tmp_file = ""
+    while True:
+        # just in case a VERY rare chance of a same generate name happens
+        tmp_file = "tmp/" + secure_filename(get_random_filename() + extension)
+        if not os.path.exists(tmp_file):
+            break
+    with codecs.open(tmp_file, 'w', 'utf-8') as f:
+        f.write(fill_content)
+    return tmp_file

swagger_server/utils/cl_utils.py

@@ -0,0 +1,47 @@
+import classla
+import time
+from swagger_server import util
+from pathlib import Path
+import re
+
+nlp_loaded = False
+nlpSlo = classla.Pipeline('sl', processors='tokenize,ner,pos,lemma,depparse')
+nlp_loaded = True
+
+sent_extractor = re.compile(r"# sent_id = \d+\.\d+(.*?)\n\n", re.MULTILINE | re.DOTALL)
+
+def raw_text_to_conllu(text):
+    try:
+        docall = nlpSlo(text)
+        docallconllu = docall.to_conll()
+
+        return docallconllu, 200
+    except Exception as e:
+        return e, 400
+
+
+def multipla_conllus_to_one_from_file_ids(list_file_ids):
+    sent_cnt = 1
+    ret = "# newpar id = 1\n"
+    files = [f'{util.get_conllu_file_path_by_id(i)}' for i in list_file_ids]
+    for file in files:
+        txt = Path(file).read_text('utf-8')
+        matches = sent_extractor.finditer(txt)
+        for match in matches:
+            ret += f'# sent_id = 1.{sent_cnt}{match.group(1)}\n\n'
+            sent_cnt += 1
+
+    return ret
+
+
+def multipla_conllus_to_one_from_conllus_arr(list_conllus):
+    sent_cnt = 1
+    ret = "# newpar id = 1\n"
+    for conllu in list_conllus:
+        conllu = conllu.replace('\r\n', '\n')
+        matches = sent_extractor.finditer(conllu)
+        for match in matches:
+            ret += f'# sent_id = 1.{sent_cnt}{match.group(1)}\n\n'
+            sent_cnt += 1
+
+    return ret

swagger_server/utils/db_utils.py

@@ -0,0 +1,225 @@
+import mariadb
+import os
+import sys
+import requests
+import json
+
+
+database_info = {
+    'database': os.getenv("MDB_DATABASE", "oss"),
+    'host': os.getenv("MDB_HOST", "localhost"),
+    'port': int(os.getenv("PORT", 3306)) ,
+    'user': os.getenv("MDB_USER", "root"),
+    'password': os.getenv("MDB_PASSWORD", "root"),
+}
+
+canonapi_endpoint = "http://canonizer:5000/rest_api/canonize"
+
+cur = None
+# Connect to MariaDB Platform
+
+def get_files_by_udc(udc):
+    ret = []
+
+    try:
+        print(database_info)
+        conn = mariadb.connect(**database_info)
+        cur = conn.cursor()
+        where_in = ','.join(['%s'] * len(udc))
+        print(where_in)
+        sql = "select distinct xml_id from metadata_udc where udk IN (%s)" % (where_in)
+        print(sql)
+        cur.execute(sql,udc)
+        #cur.execute(f'SELECT COUNT(*) FROM os2022_ngrams')
+        ret = list(cur)
+    except mariadb.Error as e:
+        print(f"Error connecting to MariaDB Platform: {e}")
+    
+
+    return ret
+
+def vrni_oss_dokumente(leta, vrste, kljucnebesede, udk):
+    ret = []
+  
+    try:
+        print(database_info)
+        conn = mariadb.connect(**database_info)
+        cur = conn.cursor()
+        
+        
+        
+        sql = "select distinct document_id from metadata"
+        where=""
+        params=[]
+        if (udk):
+            where_in_udk = ','.join(['%s'] * len(udk))
+            where=" udk IN (%s) " % (where_in_udk)
+            params=udk
+        
+        if (leta):
+
+            where_in_leta = ','.join(['%s'] * len(leta))
+            if (where):
+                where=where+ " AND "
+            where=where + " leto IN (%s) " % (where_in_leta)
+            params=params+leta
+        
+        if (vrste):
+            if (where):
+                where=where+ " AND "
+            where_in_vrste = ','.join(['%s'] * len(vrste))
+            where=where + " tipologija IN (%s) " % (where_in_vrste)
+            params=params+vrste
+
+        if (kljucnebesede):
+            if (where):
+                where=where+ " AND "
+            where_in_kb = ','.join(['%s'] * len(kljucnebesede))
+            where=where + " kljucnabeseda IN (%s) " % (where_in_kb)
+            params=params+kljucnebesede
+
+        if(where):
+            sql=sql+" where " + where + ";"
+        
+        print(sql)
+        print(params)
+
+
+        
+        cur.execute(sql,params)
+        
+        ret = list(cur)
+    except mariadb.Error as e:
+        print(f"Error connecting to MariaDB Platform: {e}")
+    
+
+    return ret
+
+
+def vrni_oss_terminoloske_kandidate(leta, vrste, kljucnebesede, udk):
+    ret = []
+  
+    try:
+        print(database_info)
+        conn = mariadb.connect(**database_info)
+        cur = conn.cursor()
+        
+        
+        
+        sql = "select distinct document_id from metadata"
+        where=""
+        params=[]
+        if (udk):
+            where_in_udk = ','.join(['%s'] * len(udk))
+            where=" udk IN (%s) " % (where_in_udk)
+            params=udk
+        
+        if (leta):
+
+            where_in_leta = ','.join(['%s'] * len(leta))
+            if (where):
+                where=where+ " AND "
+            where=where + " leto IN (%s) " % (where_in_leta)
+            params=params+leta
+        
+        if (vrste):
+            if (where):
+                where=where+ " AND "
+            where_in_vrste = ','.join(['%s'] * len(vrste))
+            where=where + " tipologija IN (%s) " % (where_in_vrste)
+            params=params+vrste
+
+        if (kljucnebesede):
+            if (where):
+                where=where+ " AND "
+            where_in_kb = ','.join(['%s'] * len(kljucnebesede))
+            where=where + " kljucnabeseda IN (%s) " % (where_in_kb)
+            params=params+kljucnebesede
+
+        if(where):
+            sql=sql+" where " + where
+        
+        print(sql)
+        print(params)
+
+        sqltk=f"""Select ngram,upos,avg(tfidf) as tfidf, sum(tf) as tf from (
+                    SELECT tf.ngram, tf.upos,(0.5+0.5*(tf.tf/d.maxtf))*log(152000/df.df)*(-1*log(1-((dff.df)/(1+df.df)))) as tfidf, tf.tf as tf
+                    FROM ngrams_upos_tf tf, documents d,
+                        (
+                        Select ngram, upos, count(*) as df from ngrams_upos_tf TF
+                        where document_id in
+                    ({sql})
+                    group by TF.ngram, TF.upos
+                    ) dff, ngrams_upos_df df
+                    where
+                    tf.document_id=d.document_id and
+                    df.ngram=tf.ngram AND df.upos=tf.upos and
+                    dff.ngram=tf.ngram AND dff.upos=tf.upos
+                    ) X
+                    group by ngram,upos
+                    order by tfidf desc
+                    limit 1000;"""
+                    #
+        print (sqltk)
+        
+        cur.execute(sqltk,params)
+        terms=cur.fetchall()
+        #ret = list(cur)
+        can = {'forms':[
+            ngram 
+            for ngram in terms
+            ]
+        }
+        res = requests.post(ATEapi_endpoint, json=can)
+        data = res.json().canonical_forms
+
+        ret = {'terminoloski_kandidati': [
+            {
+                'POSoznake': x.upos,
+                'kandidat': x.ngram,  # more to bit lemma al terms?
+                'kanonicnaoblika': d,
+                'ranking': x.tfidf,
+                'podporneutezi': [
+                    0.0,  # ????????
+                    0.0  # ??????
+                ],
+                'pogostostpojavljanja': [tf, 0]  # ???????
+            }
+            for d,x in zip(data,cur) 
+        ]}
+            
+    except mariadb.Error as e:
+        print(f"Error connecting to MariaDB Platform: {e}")
+    
+
+    return ret
+
+# class BaseModel(Model):
+#     class Meta:
+#         database = db
+#
+#
+# class os2022_ngrams(BaseModel):
+#     file_id = IntegerField()
+#     sent_id = FloatField()
+#     ngram_len = IntegerField()
+#     frequency_g_t = IntegerField()
+#     gram_text = TextField()
+#     lemma_text = TextField()
+#     xpos_text = TextField()
+#     upos_text = TextField()
+#
+# db.connect()
+
+
+#class Ngrams_Manager:
+    #@staticmethod
+    #def get_by_file_id(file_id):
+        #try:
+            # cur.execute(f'SELECT * from os2022_ngrams WHERE file_id = {file_id}')
+            # cur.execute(f'SELECT COUNT(*) FROM os2022_ngrams')
+            # return list(cur)
+         #   return 1
+        #except Exception as e:
+            #print(e, 'EXC')
+        #return 0

swagger_server/utils/txt_utils.py

@@ -0,0 +1,117 @@
+import os.path
+
+import pytesseract
+import requests
+import docx
+import xml.etree.ElementTree as ET
+from PyPDF2 import PdfReader
+from swagger_server.utils import cl_utils
+import cv2
+import numpy as np
+import magic
+import re
+#to še mora v env 
+tika_server = "http://tika2:9999/tika"
+
+# endpoint below to be used only for development purposes (don't need to run docker)
+# tika_server = "http://rsdo.lhrs.feri.um.si:9998/tika"
+
+
+def extract_text_prepResp(file, content_type=""):
+    content_type = file.content_type
+    if content_type is None:
+        content_type = magic.from_file(file.stream.name, mime=True)
+
+    content = ""
+    if tika_responding():
+        try:
+            response = requests.put(tika_server, data=file, headers={"Accept": "text/plain; charset=UTF-8"})
+            content = response.text
+            #preveri če je pretvorba uspešna
+            
+            # original string
+            res = re.findall(r'\w+', content)
+
+            #preveri, če imamo vsaj 10 besed in če je povprečna dolžina >3 in < 12
+            #če to drži, idi v ocr
+            reslen=map(lambda n:len(n),res)
+            print(f"Število besed je {len(res)}")
+
+            if len(res)>0 :
+                avglen=sum(reslen)/len(res)
+            else:
+                avglen=0
+            
+            print(f"Povprečna dolžina besede je {avglen}")
+            
+            if(len(res)<10 or avglen<4 or avglen>11):
+                print("Besedilo je sumljivo, gremo v OCR in damo file na začetek!")
+                file.seek(0)
+                response = requests.put(tika_server, data=file, headers={"X-Tika-PDFOcrStrategy": "ocr_only", "X-Tika-OCRLanguage": "slv+eng",
+                                             "Accept": "text/plain; charset=UTF-8"})
+                content = response.text
+
+            #odstranim še vse prelome vrstic, ker imamo s tem probleme
+            content=' '.join(content.splitlines())
+        except:
+            content = "ERROR - something went wrong when reading file with tika"
+
+    #if content == "":
+    #    if "openxmlformats-officedocument.wordprocessingml.document" in content_type:
+    #        content = '\n'.join([p.text for p in docx.Document(file).paragraphs])
+    #    elif "application/pdf" in content_type:
+    #        reader = PdfReader(file)
+    #        content = '\n'.join([p.extract_text() for p in reader.pages])
+    #       content = content
+    #    elif "text/xml" in content_type:
+    #        root = ET.parse(file).getroot()
+    #        plainText = root.findall('PlainText')
+    #        if len(plainText) == 0:
+    #            return "Didn't find anything in PlainText", 400
+    #        content = '\n'.join([pt.text for pt in plainText])
+    #   # elif "text/plain" in file.content_type:
+    #    else:
+    #       try:
+    #           content = file.read().decode('utf-8')
+    #       except:
+    #           content = "ERROR - something went wrong when reading file with not-tika method!"
+
+    return content, 200
+
+
+def ocr_text_prepResp(file):
+    content = ""
+    if tika_responding():
+        try:
+            response = requests.put(tika_server, data=file,
+                                    headers={"X-Tika-PDFOcrStrategy": "ocr_only", "X-Tika-OCRLanguage": "slv+eng",
+                                             "Accept": "text/plain; charset=UTF-8"})
+            content = response.text
+        except:
+            content = "ERROR - something went wrong when reading file with tika (OCR)"
+
+    if content == "":
+        try:
+            win_p = "C:/Program Files/Tesseract-OCR/tesseract.exe"
+            if os.path.exists(win_p):
+                pytesseract.pytesseract.tesseract_cmd = win_p
+
+            # convert string data to numpy array
+            file_bytes = np.fromstring(file.read(), np.uint8)
+            # convert numpy array to image
+            img = cv2.imdecode(file_bytes, cv2.IMREAD_COLOR)
+
+            conf = '-l eng+slv'
+            content = pytesseract.image_to_string(img, config=conf)
+        except:
+            content = "ERROR - something went wrong when reading file with not-tika method! (OCR)"
+
+    return content, 200
+
+
+def tika_responding():
+    try:
+        ret = requests.get(tika_server)
+        return ret.status_code == 200
+    except:
+        return False