Main brez modelov
This commit is contained in:
Marko Ferme
@@ -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!'
|
||||
@@ -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)
|
||||
|
||||
@@ -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()
|
||||
@@ -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
|
||||
@@ -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!'
|
||||
@@ -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
|
||||
@@ -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
|
||||
|
||||
Reference in New Issue
Block a user