update Dockerfiles (base and main), requirements and some python-libs

Author: HadronCollider

Dockerfile

@@ -1,4 +1,4 @@
-FROM node:20-alpine as frontend_build
+FROM node:20-alpine AS frontend_build
 
 WORKDIR /app
 ADD package.json webpack.config.js ./
@@ -7,10 +7,11 @@ RUN npm install && npm install webpack
 ADD ./assets ./assets
 RUN npm run build
 
-FROM dvivanov/dis-base:v0.4
+FROM dvivanov/dis-base:v0.5
 
 LABEL project='dis'
-LABEL version='0.4'
+LABEL version='0.5'
+ENV PYTHONPATH="${PYTHONPATH}:/usr/src/project/app"
 
 WORKDIR /usr/src/project
 
@@ -19,6 +20,4 @@ ADD ./db_versioning ./db_versioning/
 ADD ./app ./app/
 COPY --from=frontend_build /app/src ./src/
 
-ENV PYTHONPATH "${PYTHONPATH}:/usr/src/project/app"
-
-CMD ./scripts/local_start.sh
+CMD ["./scripts/local_start.sh"]

Dockerfile_base

@@ -1,14 +1,13 @@
-FROM python:3.10-slim-bullseye
+FROM python:3.12-slim-bullseye
 
 LABEL project='dis'
-LABEL version='0.4-base'
+LABEL version='0.5-base'
 
-ENV LANG en_US.UTF-8
+ENV LANG=en_US.UTF-8
 ENV TZ=Europe/Moscow
 
 RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone
-
-RUN apt update && apt install -y libreoffice-writer libreoffice-impress default-jre
+RUN apt update && apt install -y g++ gcc libreoffice-writer libreoffice-impress default-jre
 
 ADD requirements.txt .
 RUN python3 -m pip install -r requirements.txt --no-cache-dir

app/main/checks/base_check.py

@@ -1,6 +1,6 @@
-import pymorphy2
+import pymorphy3
 
-morph = pymorphy2.MorphAnalyzer()
+morph = pymorphy3.MorphAnalyzer()
 
 
 def answer(mod, *args):

app/main/checks/presentation_checks/find_theme_in_pres.py

@@ -7,7 +7,7 @@
 import nltk
 from nltk.tokenize import word_tokenize, sent_tokenize
 from nltk.corpus import stopwords
-from pymorphy2 import MorphAnalyzer
+from pymorphy3 import MorphAnalyzer
 
 
 MORPH_ANALYZER = MorphAnalyzer()

app/main/checks/report_checks/find_theme_in_report.py

@@ -6,7 +6,7 @@
 import  string
 from nltk.tokenize import word_tokenize, sent_tokenize
 from nltk.corpus import stopwords
-from pymorphy2 import MorphAnalyzer
+from pymorphy3 import MorphAnalyzer
 
 
 MORPH_ANALYZER = MorphAnalyzer()

app/main/checks/report_checks/sw_keywords_check.py

@@ -3,7 +3,7 @@
 
 from nltk.tokenize import word_tokenize
 from nltk.corpus import stopwords
-from pymorphy2 import MorphAnalyzer
+from pymorphy3 import MorphAnalyzer
 from ..base_check import BaseReportCriterion, answer
 
 

app/main/reports/pdf_document/pdf_document_manager.py

@@ -1,6 +1,6 @@
 
 # import pdfplumber
-import fitz
+import pymupdf
 
 
 from app.utils import convert_to
@@ -9,10 +9,10 @@ class PdfDocumentManager:
     def __init__(self, path_to_file, pdf_filepath):
         if not pdf_filepath:
             # self.pdf_file = pdfplumber.open(convert_to(path_to_file, target_format='pdf'))
-            self.pdf_file = fitz.open(convert_to(path_to_file, target_format='pdf'))
+            self.pdf_file = pymupdf.open(convert_to(path_to_file, target_format='pdf'))
         else:
             # self.pdf_file = pdfplumber.open(pdf_filepath)
-            self.pdf_file = fitz.open(pdf_filepath)
+            self.pdf_file = pymupdf.open(pdf_filepath)
         self.pages = [self.pdf_file.load_page(page_num) for page_num in range(self.pdf_file.page_count)]
         self.page_count_all = self.pdf_file.page_count
         # self.page_count = len(self.pages)
@@ -34,7 +34,7 @@ def page_images(self, page_without_pril):
         total_height = 0
         for page_num in range(page_without_pril):
             page = self.pdf_file[page_num]
-            images = self.pdf_file.get_page_images(page)
+            images = self.pdf_file.get_page_images(page_num)
             for image in images:
                 image_coord = page.get_image_bbox(image[7], transform=0)    # might be [1.0, 1.0, -1.0, -1.0]
                 image_height = image_coord[3] - image_coord[1]

app/nlp/stemming.py

@@ -1,7 +1,7 @@
 import itertools
 from nltk.corpus import stopwords
 from nltk.tokenize import word_tokenize, sent_tokenize
-from pymorphy2 import MorphAnalyzer
+from pymorphy3 import MorphAnalyzer
 
 
 MORPH_ANALYZER = MorphAnalyzer()

requirements.txt

@@ -1,37 +1,37 @@
-werkzeug==2.0.0
+argparse~=1.4.0
+celery==5.5.3
+configparser~=5.3.0
+docx2python~=2.0.4
+filetype==1.2.0
 Flask==2.0.3
-jinja2==3.0.0
-requests~=2.31.0
-python-pptx==0.6.18
-odfpy==1.4.1
-pymongo==3.11.1
 flask-login==0.5.0
-numpy==1.22
-scipy~=1.10.1
-pymorphy2==0.9.1
-nltk==3.6.6
 flask-recaptcha==0.4.2
-lti==0.9.5
 flask-security==3.0.0
-celery==5.2.2
 flower==1.2.0
-redis==3.5.3
-pandas~=2.0.3
 fsspec==2022.2.0
-python-docx==0.8.11
-odfpy==1.4.1
-argparse~=1.4.0
-docx2python~=2.0.4
+jinja2==3.0.0
+language-tool-python==2.8.1
+lti==0.9.5
+lxml~=4.9.2
+markdown==3.4.4
+md2pdf==1.0.1
+nltk==3.6.6
+numpy==1.26.4
 oauthlib~=3.1.0
+odfpy==1.4.1
+odfpy==1.4.1
+pandas~=2.0.3
 pdfplumber==0.6.1
-pytest~=7.1.2
-PyMuPDF~=1.22.5
+PyMuPDF==1.26.6
 PyPDF2~=3.0.1
-configparser~=5.3.0
+pymongo==3.11.1
+pymorphy3==2.0.6
+pytest~=7.1.2
+python-docx==0.8.11
+python-pptx==0.6.18
 pytz~=2023.3
-lxml~=4.9.2
+redis==6.1.0
+requests~=2.31.0
+scipy~=1.11.1
 urllib3~=2.0.3
-filetype==1.2.0
-language-tool-python==2.8.1
-markdown==3.4.4
-md2pdf==1.0.1
+werkzeug==2.0.0