added xlsx parse, ip lookup

config/settings/local.py

@@ -11,9 +11,15 @@
     default="LnQa85vE4W235BIYizBVnsOPJOfrBxjpdrgWtmDNaUMEIbDCxwySRuyp4hpmJMZ2",
 )
 # https://docs.djangoproject.com/en/dev/ref/settings/#allowed-hosts
-ALLOWED_HOSTS = ["localhost", "0.0.0.0", "127.0.0.1", "192.168.107.4"]
+ALLOWED_HOSTS = [
+    "localhost",
+    "0.0.0.0",
+    "127.0.0.1",
+    "192.168.103.224",
+    "192.168.107.4",
+]
 CORS_ORIGIN_ALLOW_ALL = True
-CSRF_TRUSTED_ORIGINS = ["http://192.168.107.4"]
+CSRF_TRUSTED_ORIGINS = ["http://192.168.103.224", "http://192.168.107.4"]
 
 # WhiteNoise
 # ------------------------------------------------------------------------------

poetry.lock

@@ -1070,6 +1070,18 @@ files = [
     {file = "ebcdic-1.1.1-py2.py3-none-any.whl", hash = "sha256:33b4cb729bc2d0bf46cc1847b0e5946897cb8d3f53520c5b9aa5fa98d7e735f1"},
 ]
 
+[[package]]
+name = "et-xmlfile"
+version = "1.1.0"
+description = "An implementation of lxml.xmlfile for the standard library"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "et_xmlfile-1.1.0-py3-none-any.whl", hash = "sha256:a2ba85d1d6a74ef63837eed693bcb89c3f752169b0e3e7ae5b16ca5e1b3deada"},
+    {file = "et_xmlfile-1.1.0.tar.gz", hash = "sha256:8eb9e2bc2f8c97e37a2dc85a09ecdcdec9d8a396530a6d5a33b30b9a92da0c5c"},
+]
+
 [[package]]
 name = "executing"
 version = "1.2.0"
@@ -1786,6 +1798,21 @@ files = [
     {file = "olefile-0.46.zip", hash = "sha256:133b031eaf8fd2c9399b78b8bc5b8fcbe4c31e85295749bb17a87cba8f3c3964"},
 ]
 
+[[package]]
+name = "openpyxl"
+version = "3.1.2"
+description = "A Python library to read/write Excel 2010 xlsx/xlsm files"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "openpyxl-3.1.2-py2.py3-none-any.whl", hash = "sha256:f91456ead12ab3c6c2e9491cf33ba6d08357d802192379bb482f1033ade496f5"},
+    {file = "openpyxl-3.1.2.tar.gz", hash = "sha256:a6f5977418eff3b2d5500d54d9db50c8277a368436f4e4f8ddb1be3422870184"},
+]
+
+[package.dependencies]
+et-xmlfile = "*"
+
 [[package]]
 name = "packaging"
 version = "23.1"
@@ -2280,6 +2307,22 @@ files = [
 [package.dependencies]
 pylint = ">=1.7"
 
+[[package]]
+name = "pytesseract"
+version = "0.3.10"
+description = "Python-tesseract is a python wrapper for Google's Tesseract-OCR"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "pytesseract-0.3.10-py3-none-any.whl", hash = "sha256:8f22cc98f765bf13517ead0c70effedb46c153540d25783e04014f28b55a5fc6"},
+    {file = "pytesseract-0.3.10.tar.gz", hash = "sha256:f1c3a8b0f07fd01a1085d451f5b8315be6eec1d5577a6796d46dc7a62bd4120f"},
+]
+
+[package.dependencies]
+packaging = ">=21.3"
+Pillow = ">=8.0.0"
+
 [[package]]
 name = "pytest"
 version = "7.4.2"
@@ -3310,4 +3353,4 @@ files = [
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.11"
-content-hash = "5bcd52daf4504209b9936143d506ff50fae1f094bae17686a71ddd01efb9c49f"
+content-hash = "fa7686c29a2d587dbafb35cec00bf4da4424047410560854cec79f904dc9de97"

press_release_nl/processor/api/serializers.py

@@ -1,4 +1,5 @@
 from django.core.files.uploadedfile import InMemoryUploadedFile, TemporaryUploadedFile
+from drf_spectacular.utils import extend_schema_field
 from rest_framework import serializers
 
 from press_release_nl.processor.models import Entry, Text
@@ -65,14 +66,22 @@ def create(self, validated_data):
 class ProcessedTextSerializer(serializers.ModelSerializer):
     class Meta:
         model = Text
-        fields = ["text", "score"]
+        fields = ["id", "summery", "text", "score"]
 
 
 class EntrySerializer(serializers.ModelSerializer):
-    texts = ProcessedTextSerializer(many=True)
+    texts = serializers.SerializerMethodField(method_name="get_texts")
-    done = serializers.IntegerField(source="texts_done_count")
+    current = serializers.IntegerField(source="texts_done_count")
-    count = serializers.IntegerField(source="texts_count")
+    total = serializers.IntegerField(source="texts_count")
+
+    @extend_schema_field(ProcessedTextSerializer(many=True))
+    def get_texts(self, obj: Entry):
+        id = self.context["request"].query_params.get("id")
+        q = obj.texts.all()
+        if id:
+            q = q.filter(id=id)
+        return ProcessedTextSerializer(many=True).to_representation(q)
 
     class Meta:
         model = Entry
-        fields = ["texts", "done", "count", "created"]
+        fields = ["texts", "current", "total", "created"]

press_release_nl/processor/api/views.py

@@ -1,3 +1,4 @@
+from drf_spectacular.utils import OpenApiParameter, extend_schema, extend_schema_view
 from rest_framework import generics, parsers, permissions, status
 from rest_framework.response import Response
 
@@ -25,6 +26,9 @@ def create(self, request, *args, **kwargs):
         )
 
 
+@extend_schema_view(
+    get=extend_schema(parameters=[OpenApiParameter(name="id", type=int)])
+)
 class RetrieveEntryApiView(generics.RetrieveAPIView):
     queryset = Entry.objects.all()
     permission_classes = [permissions.AllowAny]

press_release_nl/processor/migrations/0002_text_summery_alter_text_file.py

@@ -0,0 +1,23 @@
+# Generated by Django 4.2.5 on 2023-09-08 18:42
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("processor", "0001_initial"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="text",
+            name="summery",
+            field=models.TextField(blank=True, max_length=2000, null=True),
+        ),
+        migrations.AlterField(
+            model_name="text",
+            name="file",
+            field=models.FileField(blank=True, null=True, upload_to="uploads/"),
+        ),
+    ]

press_release_nl/processor/models.py

@@ -12,7 +12,7 @@ def __str__(self):
 
     @property
     def texts_done_count(self):
-        return len(self.texts.filter(score__isnull=False))
+        return len(self.texts.filter(score__isnull=False, summery__isnull=False))
 
     @property
     def texts_count(self):
@@ -21,6 +21,7 @@ def texts_count(self):
 
 class Text(models.Model):
     entry = models.ForeignKey("Entry", related_name="texts", on_delete=models.CASCADE)
+    summery = models.TextField(max_length=2000, blank=True, null=True)
     file = models.FileField(blank=True, null=True, upload_to="uploads/")
     text = models.TextField(blank=True, null=True, max_length=25_000)
     score = models.JSONField(null=True)

press_release_nl/processor/signals.py

@@ -1,11 +1,25 @@
+import openpyxl
 from django.db.models.signals import post_save
 from django.dispatch import receiver
 
 from press_release_nl.processor.models import Text
-from press_release_nl.processor.tasks import load_text
+from press_release_nl.processor.tasks import load_text, load_text_sum
 
 
 @receiver(post_save, sender=Text)
 def run_text_process(sender, instance: Text, created, **kwargs):
     if created:
-        load_text.apply_async(kwargs={"pk": instance.pk}, countdown=1)
+        if instance.file and instance.file.path.endswith("xlsx"):
+            wb_obj = openpyxl.load_workbook(instance.file.path)
+            sheet = wb_obj.worksheets[0]
+            for column in sheet.iter_cols():
+                column_name = column[0].value
+                if column_name == "pr_txt":
+                    for text in column:
+                        text = text.value
+                        if text and text != "pr_txt":
+                            Text.objects.create(entry=instance.entry, text=text)
+                    instance.delete()
+                    return
+        load_text.apply_async(kwargs={"pk": instance.pk}, countdown=2)
+        load_text_sum.apply_async(kwargs={"pk": instance.pk}, countdown=4)

press_release_nl/processor/tasks.py

@@ -1,3 +1,5 @@
+from time import sleep
+
 import requests
 import textract
 from celery import shared_task
@@ -5,13 +7,16 @@
 from press_release_nl.processor.models import Text
 
 ML_HOST = "https://2b6a-176-59-106-6.ngrok-free.app/"
+ML_SUM_HOST = "https://dev.akarpov.ru/"
 
 
 @shared_task
 def load_text(pk: int):
     text = Text.objects.get(pk=pk)
     if not text.text:
-        text.text = textract.process(text.file.path, encoding="unicode_escape").decode()
+        text.text = textract.process(
+            text.file.path, encoding="unicode_escape", language="rus"
+        ).decode()
         text.save()
     re = requests.post(ML_HOST + "predict", json={"data": text.text})
     if re.status_code != 200:
@@ -19,3 +24,18 @@ def load_text(pk: int):
     text.score = re.json()
     text.save()
     return pk
+
+
+@shared_task
+def load_text_sum(pk: int):
+    text = Text.objects.get(pk=pk)
+    if not text.text:
+        sleep(3)
+    text.refresh_from_db()
+    re = requests.post(ML_SUM_HOST, json={"body": text.text})
+    if re.status_code != 200:
+        raise ValueError(re.text)
+    data = re.json()
+    text.summery = str(data)
+    text.save()
+    return pk

pyproject.toml

@@ -48,6 +48,8 @@ django-coverage-plugin = "^3.0.0"
 pytest-django = "^4.5.2"
 sentry-sdk = "^1.12.0"
 textract = "^1.6.5"
+pytesseract = "^0.3.10"
+openpyxl = "^3.1.2"
 
 
 [build-system]