Adicionando PDFs via LFS

.dockerignore

@@ -0,0 +1,12 @@
+.editorconfig
+.gitattributes
+.github
+.gitignore
+.gitlab-ci.yml
+.idea
+.pre-commit-config.yaml
+.readthedocs.yml
+.travis.yml
+venv
+.git
+.envs/

.editorconfig

@@ -0,0 +1,27 @@
+# http://editorconfig.org
+
+root = true
+
+[*]
+charset = utf-8
+end_of_line = lf
+insert_final_newline = true
+trim_trailing_whitespace = true
+
+[*.{py,rst,ini}]
+indent_style = space
+indent_size = 4
+
+[*.{html,css,scss,json,yml,xml,toml}]
+indent_style = space
+indent_size = 2
+
+[*.md]
+trim_trailing_whitespace = false
+
+[Makefile]
+indent_style = tab
+
+[default.conf]
+indent_style = space
+indent_size = 2

.envs/.local/.django

@@ -0,0 +1,9 @@
+# General
+# ------------------------------------------------------------------------------
+USE_DOCKER=yes
+IPYTHONDIR=/app/.ipython
+ELASTICSEARCH_USER=elastic
+ELASTICSEARCH_PASSWORD=RwtC6t+BLWkLj44=cp-*
+DJANGO_SECRET_KEY=tYdYl0MP5zgpMlMmjBuYHvH4Dp3JDN5q3sxWBdFejemZSr0qpI9IrvrvTm17F0aW
+DJANGO_ADMIN_URL=manage-panel/
+DJANGO_ALLOWED_HOSTS=192.168.235.234,localhost,127.0.0.1,django

.envs/.local/.postgres

@@ -0,0 +1,7 @@
+# PostgreSQL
+# ------------------------------------------------------------------------------
+POSTGRES_HOST=postgres
+POSTGRES_PORT=5432
+POSTGRES_DB=diários_oficiais_alems
+POSTGRES_USER=debug
+POSTGRES_PASSWORD=debug

.gitattributes

@@ -0,0 +1,2 @@
+* text=auto
+*.pdf filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,277 @@
+### Python template
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+staticfiles/
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+
+
+# Environments
+.venv
+venv/
+ENV/
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+
+
+### Node template
+# Logs
+logs
+*.log
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+
+# Runtime data
+pids
+*.pid
+*.seed
+*.pid.lock
+
+# Directory for instrumented libs generated by jscoverage/JSCover
+lib-cov
+
+# Coverage directory used by tools like istanbul
+coverage
+
+# nyc test coverage
+.nyc_output
+
+# Bower dependency directory (https://bower.io/)
+bower_components
+
+# node-waf configuration
+.lock-wscript
+
+# Compiled binary addons (http://nodejs.org/api/addons.html)
+build/Release
+
+# Dependency directories
+node_modules/
+jspm_packages/
+
+# Typescript v1 declaration files
+typings/
+
+# Optional npm cache directory
+.npm
+
+# Optional eslint cache
+.eslintcache
+
+# Optional REPL history
+.node_repl_history
+
+# Output of 'npm pack'
+*.tgz
+
+# Yarn Integrity file
+.yarn-integrity
+
+
+### Linux template
+*~
+
+# temporary files which can be created if a process still has a handle open of a deleted file
+.fuse_hidden*
+
+# KDE directory preferences
+.directory
+
+# Linux trash folder which might appear on any partition or disk
+.Trash-*
+
+# .nfs files are created when an open file is removed but is still being accessed
+.nfs*
+
+
+### VisualStudioCode template
+.vscode/*
+!.vscode/settings.json
+!.vscode/tasks.json
+!.vscode/launch.json
+!.vscode/extensions.json
+*.code-workspace
+
+# Local History for devcontainer
+.devcontainer/bash_history
+
+
+
+
+### Windows template
+# Windows thumbnail cache files
+Thumbs.db
+ehthumbs.db
+ehthumbs_vista.db
+
+# Dump file
+*.stackdump
+
+# Folder config file
+Desktop.ini
+
+# Recycle Bin used on file shares
+$RECYCLE.BIN/
+
+# Windows Installer files
+*.cab
+*.msi
+*.msm
+*.msp
+
+# Windows shortcuts
+*.lnk
+
+
+### macOS template
+# General
+*.DS_Store
+.AppleDouble
+.LSOverride
+
+# Icon must end with two \r
+Icon
+
+# Thumbnails
+._*
+
+# Files that might appear in the root of a volume
+.DocumentRevisions-V100
+.fseventsd
+.Spotlight-V100
+.TemporaryItems
+.Trashes
+.VolumeIcon.icns
+.com.apple.timemachine.donotpresent
+
+# Directories potentially created on remote AFP share
+.AppleDB
+.AppleDesktop
+Network Trash Folder
+Temporary Items
+.apdisk
+
+
+### SublimeText template
+# Cache files for Sublime Text
+*.tmlanguage.cache
+*.tmPreferences.cache
+*.stTheme.cache
+
+# Workspace files are user-specific
+*.sublime-workspace
+
+# Project files should be checked into the repository, unless a significant
+# proportion of contributors will probably not be using Sublime Text
+# *.sublime-project
+
+# SFTP configuration file
+sftp-config.json
+
+# Package control specific files
+Package Control.last-run
+Package Control.ca-list
+Package Control.ca-bundle
+Package Control.system-ca-bundle
+Package Control.cache/
+Package Control.ca-certs/
+Package Control.merged-ca-bundle
+Package Control.user-ca-bundle
+oscrypto-ca-bundle.crt
+bh_unicode_properties.cache
+
+# Sublime-github package stores a github token in this file
+# https://packagecontrol.io/packages/sublime-github
+GitHub.sublime-settings
+
+
+### Vim template
+# Swap
+[._]*.s[a-v][a-z]
+[._]*.sw[a-p]
+[._]s[a-v][a-z]
+[._]sw[a-p]
+
+# Session
+Session.vim
+
+# Temporary
+.netrwhist
+
+# Auto-generated tag files
+tags
+
+# Redis dump file
+dump.rdb
+
+### Project template
+diarios_oficiais_alems/media/
+
+.pytest_cache/
+.ipython/
+.env
+.envs/*
+!.envs/.local/

.python-version

@@ -0,0 +1 @@
+3.12

README.md

@@ -1,2 +1,52 @@
-# Di-rios-Oficiais-Alems
+# Diários Oficiais ALEMS
+
 Indexação dos Diários Oficiais da ALEMS
+
+[![Built with Cookiecutter Django](https://img.shields.io/badge/built%20with-Cookiecutter%20Django-ff69b4.svg?logo=cookiecutter)](https://github.com/cookiecutter/cookiecutter-django/)
+[![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)
+
+## Configurações
+
+Consulte [settings](https://cookiecutter-django.readthedocs.io/en/latest/1-getting-started/settings.html).
+
+## Comandos Básicos
+
+### Configuração de Usuários
+
+- Para criar uma **conta de usuário normal**, vá para Cadastrar e preencha o formulário. Após enviar, você verá uma página "Verifique Seu Endereço de E-mail". Verifique no console a mensagem simulada de verificação de e-mail. Copie o link no seu navegador. Agora o e-mail do usuário estará verificado e pronto para uso.
+
+- Para criar uma **conta de superusuário**, use o comando:
+
+      $ python manage.py createsuperuser
+
+Para conveniência, você pode manter seu usuário normal logado no Chrome e seu superusuário logado no Firefox (ou similar), para ver como o site se comporta para ambos os tipos de usuários.
+
+### Verificação de Tipos
+
+Executando verificação de tipos com mypy:
+
+    $ mypy diários_oficiais_alems
+
+### Cobertura de Testes
+
+Para executar os testes, verificar a cobertura e gerar um relatório HTML de cobertura:
+
+    $ coverage run -m pytest
+    $ coverage html
+    $ open htmlcov/index.html
+
+#### Executando testes com pytest
+
+    $ pytest
+
+### Recarregamento automático e compilação Sass CSS
+
+Consulte [Live reloading and SASS compilation](https://cookiecutter-django.readthedocs.io/en/latest/2-local-development/developing-locally.html#using-webpack-or-gulp).
+
+## Deploy
+
+A seguir estão os detalhes para fazer o deploy desta aplicação.
+
+### Docker
+
+Consulte a [documentação Docker do cookiecutter-django](https://cookiecutter-django.readthedocs.io/en/latest/3-deployment/deployment-with-docker.html).

compose/local/django/Dockerfile

@@ -0,0 +1,77 @@
+
+FROM docker.io/python:3.12.9-slim-bookworm AS python-build-stage
+
+ARG BUILD_ENVIRONMENT=local
+
+# Instalar apenas dependências para construir pacotes Python
+RUN apt-get update && apt-get install --no-install-recommends -y \
+    build-essential \
+    libpq-dev \
+    # libtesseract-dev pode ser necessário aqui se alguma lib Python compila contra ele
+    libtesseract-dev \
+ && rm -rf /var/lib/apt/lists/*
+
+# Requirements são instalados aqui para garantir que serão cacheados.
+COPY ./requirements .
+
+# Criar Wheels das dependências Python.
+RUN pip wheel --wheel-dir /usr/src/app/wheels  \
+    -r ${BUILD_ENVIRONMENT}.txt
+
+
+# Python 'run' stage - ESTA É A IMAGEM FINAL
+FROM docker.io/python:3.12.9-slim-bookworm AS python-run-stage
+
+ARG BUILD_ENVIRONMENT=local
+ARG APP_HOME=/app
+
+ENV PYTHONUNBUFFERED=1
+ENV PYTHONDONTWRITEBYTECODE=1
+ENV BUILD_ENV=${BUILD_ENVIRONMENT}
+
+WORKDIR ${APP_HOME}
+
+# Instalar TODAS as dependências de sistema necessárias em TEMPO DE EXECUÇÃO
+RUN apt-get update && apt-get install --no-install-recommends -y \
+    # Dependências do psycopg e outras utilidades
+    libpq-dev \
+    wait-for-it \
+    gettext \
+    poppler-utils \
+    unpaper \
+    tesseract-ocr \
+    tesseract-ocr-por \
+    ghostscript \
+    openjdk-17-jdk \
+    # libtesseract-dev \
+    # Utilitários do devcontainer e outros
+    sudo git bash-completion vim ssh curl \
+ # Limpeza
+ && apt-get purge -y --auto-remove -o APT::AutoRemove::RecommendsImportant=false \
+ && rm -rf /var/lib/apt/lists/*
+
+# Criar usuário devcontainer (manter como está)
+RUN groupadd --gid 1000 dev-user \
+    && useradd --uid 1000 --gid dev-user --shell /bin/bash --create-home dev-user \
+    && echo dev-user ALL=\(root\) NOPASSWD:ALL > /etc/sudoers.d/dev-user \
+    && chmod 0440 /etc/sudoers.d/dev-user
+
+# Instalar dependências Python a partir dos wheels (manter como está)
+COPY --from=python-build-stage /usr/src/app/wheels  /wheels/
+RUN pip install --no-cache-dir --no-index --find-links=/wheels/ /wheels/* \
+    && rm -rf /wheels/
+
+# Copiar scripts e código (manter como está)
+COPY ./compose/production/django/entrypoint /entrypoint
+RUN sed -i 's/\r$//g' /entrypoint
+RUN chmod +x /entrypoint
+COPY ./compose/local/django/start /start
+RUN sed -i 's/\r$//g' /start
+RUN chmod +x /start
+COPY . ${APP_HOME}
+
+# REMOVER esta linha, poppler-utils já foi instalado acima
+# RUN apt-get update && apt-get install -y poppler-utils
+
+ENTRYPOINT ["/entrypoint"]
+

compose/local/django/start

@@ -0,0 +1,20 @@
+#!/bin/bash
+
+set -o errexit
+set -o pipefail
+set -o nounset
+
+# Aplica migrações antes de iniciar o servidor
+python manage.py migrate
+
+# Coleta arquivos estáticos
+python manage.py collectstatic --noinput
+
+python manage.py compress --force
+
+# Inicia o servidor com Gunicorn
+exec gunicorn config.wsgi:application \
+    --bind 0.0.0.0:8005 \
+    --workers 4 \
+    --timeout 120
+# python manage.py runserver_plus 0.0.0.0:8005

compose/local/docs/Dockerfile

@@ -0,0 +1,62 @@
+# define an alias for the specific python version used in this file.
+FROM docker.io/python:3.12.9-slim-bookworm AS python
+
+
+# Python build stage
+FROM python AS python-build-stage
+
+ENV PYTHONDONTWRITEBYTECODE=1
+
+RUN apt-get update && apt-get install --no-install-recommends -y \
+  # dependencies for building Python packages
+  build-essential \
+  # psycopg dependencies
+  libpq-dev \
+  # cleaning up unused files
+  && apt-get purge -y --auto-remove -o APT::AutoRemove::RecommendsImportant=false \
+  && rm -rf /var/lib/apt/lists/*
+
+# Requirements are installed here to ensure they will be cached.
+COPY ./requirements /requirements
+
+# create python dependency wheels
+RUN pip wheel --no-cache-dir --wheel-dir /usr/src/app/wheels  \
+  -r /requirements/local.txt -r /requirements/production.txt \
+  && rm -rf /requirements
+
+
+# Python 'run' stage
+FROM python AS python-run-stage
+
+ARG BUILD_ENVIRONMENT
+ENV PYTHONUNBUFFERED=1
+ENV PYTHONDONTWRITEBYTECODE=1
+
+RUN apt-get update && apt-get install --no-install-recommends -y \
+  # To run the Makefile
+  make \
+  # psycopg dependencies
+  libpq-dev \
+  # Translations dependencies
+  gettext \
+  # Uncomment below lines to enable Sphinx output to latex and pdf
+  # texlive-latex-recommended \
+  # texlive-fonts-recommended \
+  # texlive-latex-extra \
+  # latexmk \
+  # cleaning up unused files
+  && apt-get purge -y --auto-remove -o APT::AutoRemove::RecommendsImportant=false \
+  && rm -rf /var/lib/apt/lists/*
+
+# copy python dependency wheels from python-build-stage
+COPY --from=python-build-stage /usr/src/app/wheels /wheels
+
+# use wheels to install python dependencies
+RUN pip install --no-cache /wheels/* \
+  && rm -rf /wheels
+
+COPY ./compose/local/docs/start /start-docs
+RUN sed -i 's/\r$//g' /start-docs
+RUN chmod +x /start-docs
+
+WORKDIR /docs

compose/local/docs/start

@@ -0,0 +1,7 @@
+#!/bin/bash
+
+set -o errexit
+set -o pipefail
+set -o nounset
+
+exec make livehtml

compose/local/nginx/nginx.conf

@@ -0,0 +1,44 @@
+upstream django {
+    server django:8005;
+}
+
+server {
+    listen 80;
+    server_name 192.168.235.234 localhost;
+
+    client_max_body_size 10M;
+
+    location / {
+        proxy_pass http://django;
+        proxy_set_header Host $host;
+        proxy_set_header X-Real-IP $remote_addr;
+        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+        proxy_set_header X-Forwarded-Proto $scheme;
+        proxy_redirect off;
+        
+        # Timeouts
+        proxy_connect_timeout 75s;
+        proxy_read_timeout 300s;
+    }
+
+    location /static/ {
+        alias /app/staticfiles/;
+        expires 30d;
+        access_log off;
+        add_header Cache-Control "public, no-transform";
+    }
+
+    location /media/ {
+        alias /app/media/;
+        expires 30d;
+        access_log off;
+        add_header Cache-Control "public, no-transform";
+    }
+
+    # Bloqueia acesso a arquivos ocultos
+    location ~ /\. {
+        deny all;
+        access_log off;
+        log_not_found off;
+    }
+}

compose/production/django/Dockerfile

@@ -0,0 +1,73 @@
+# define an alias for the specific python version used in this file.
+FROM docker.io/python:3.12.9-slim-bookworm AS python
+
+# Python build stage
+FROM python AS python-build-stage
+
+ARG BUILD_ENVIRONMENT=production
+
+# Install apt packages
+RUN apt-get update && apt-get install --no-install-recommends -y \
+  build-essential \
+  libpq-dev \
+  wait-for-it \
+  && rm -rf /var/lib/apt/lists/*
+
+# Requirements are installed here to ensure they will be cached.
+COPY ./requirements .
+
+# Create Python Dependency and Sub-Dependency Wheels.
+RUN pip wheel --wheel-dir /usr/src/app/wheels \
+  -r ${BUILD_ENVIRONMENT}.txt
+
+# Python 'run' stage
+FROM python AS python-run-stage
+
+ARG BUILD_ENVIRONMENT=production
+ARG APP_HOME=/app
+
+ENV PYTHONUNBUFFERED=1 \
+    PYTHONDONTWRITEBYTECODE=1 \
+    BUILD_ENV=${BUILD_ENVIRONMENT} \
+    PATH="/home/django/.local/bin:${PATH}"
+
+WORKDIR ${APP_HOME}
+
+# Create system user
+RUN addgroup --system django && \
+    adduser --system --ingroup django django
+
+# Install required system dependencies
+RUN apt-get update && apt-get install --no-install-recommends -y \
+  libpq-dev \
+  gettext \
+  && apt-get purge -y --auto-remove -o APT::AutoRemove::RecommendsImportant=false \
+  && rm -rf /var/lib/apt/lists/*
+
+# Copy python dependency wheels
+COPY --from=python-build-stage /usr/src/app/wheels /wheels/
+
+# Install python dependencies
+RUN pip install --no-cache-dir --no-index --find-links=/wheels/ /wheels/* \
+  && rm -rf /wheels/
+
+# Copy entrypoint and start scripts
+COPY --chown=django:django ./compose/production/django/entrypoint /entrypoint
+RUN sed -i 's/\r$//g' /entrypoint && \
+    chmod +x /entrypoint
+
+COPY --chown=django:django ./compose/production/django/start /start
+RUN sed -i 's/\r$//g' /start && \
+    chmod +x /start
+
+# Copy application code
+COPY --chown=django:django . ${APP_HOME}
+
+# Fix permissions
+RUN chown -R django:django ${APP_HOME} && \
+    find ${APP_HOME} -type d -exec chmod 755 {} \; && \
+    find ${APP_HOME} -type f -exec chmod 644 {} \;
+
+USER django
+
+ENTRYPOINT ["/entrypoint"]

compose/production/django/entrypoint

@@ -0,0 +1,17 @@
+#!/bin/bash
+
+set -o errexit
+set -o pipefail
+set -o nounset
+
+if [ -z "${POSTGRES_USER}" ]; then
+    base_postgres_image_default_user='postgres'
+    export POSTGRES_USER="${base_postgres_image_default_user}"
+fi
+export DATABASE_URL="postgres://${POSTGRES_USER}:${POSTGRES_PASSWORD}@${POSTGRES_HOST}:${POSTGRES_PORT}/${POSTGRES_DB}"
+
+wait-for-it "${POSTGRES_HOST}:${POSTGRES_PORT}" -t 30
+
+>&2 echo 'PostgreSQL is available'
+
+exec "$@"

compose/production/django/start

@@ -0,0 +1,51 @@
+#!/bin/bash
+#!/bin/bash
+
+set -o errexit
+set -o pipefail
+set -o nounset
+
+# Configurações ajustáveis via variáveis de ambiente
+PORT=${GUNICORN_PORT:-8005}
+WORKERS=${GUNICORN_WORKERS:-$(( $(nproc) * 2 + 1 ))}
+TIMEOUT=${GUNICORN_TIMEOUT:-120}
+MAX_REQUESTS=${GUNICORN_MAX_REQUESTS:-1000}
+
+# Aplica migrações do banco de dados (com tratamento de erro)
+python /app/manage.py migrate --noinput || {
+    echo "⚠️ Falha nas migrações do banco de dados!";
+    exit 1;
+}
+
+# Coleta arquivos estáticos
+python /app/manage.py collectstatic --noinput
+
+# Verifica e comprime arquivos (se compressor ativado)
+compress_enabled() {
+    python << END
+import sys
+from environ import Env
+
+env = Env(COMPRESS_ENABLED=(bool, True))
+sys.exit(0 if env('COMPRESS_ENABLED') else 1)
+END
+}
+
+if compress_enabled; then
+    python /app/manage.py compress --verbosity=0 || {
+        echo "⚠️ Falha ao comprimir arquivos (django-compressor pode estar desativado)";
+    }
+fi
+
+# Inicia o Gunicorn com configurações otimizadas
+exec /usr/local/bin/gunicorn config.wsgi:application \
+    --bind 0.0.0.0:${PORT} \
+    --workers ${WORKERS} \
+    --timeout ${TIMEOUT} \
+    --max-requests ${MAX_REQUESTS} \
+    --worker-class sync \
+    --name diarios_oficiais_alems \
+    --access-logfile - \
+    --error-logfile - \
+    --chdir=/app
+

compose/production/nginx/Dockerfile

@@ -0,0 +1,2 @@
+FROM docker.io/nginx:1.17.8-alpine
+COPY ./compose/production/nginx/default.conf /etc/nginx/conf.d/default.conf

compose/production/nginx/default.conf

@@ -0,0 +1,7 @@
+server {
+  listen       80;
+  server_name  localhost;
+  location /media/ {
+    alias /usr/share/nginx/media/;
+  }
+}

compose/production/nginx/nginx.conf

@@ -0,0 +1,39 @@
+worker_processes auto;
+
+events {
+    worker_connections 1024;
+}
+
+http {
+    include mime.types;
+    default_type application/octet-stream;
+
+    sendfile on;
+    keepalive_timeout 180;
+    gzip on;
+
+    server {
+        listen 80;
+        server_name _;
+
+        location / {
+            proxy_pass http://django:8005;
+            proxy_set_header Host $host;
+            proxy_set_header X-Real-IP $remote_addr;
+            proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+            proxy_set_header X-Forwarded-Proto $scheme;
+        }
+
+        location /static/ {
+            alias /usr/share/nginx/static/;
+            expires 30d;
+            access_log off;
+        }
+
+        location /media/ {
+            alias /usr/share/nginx/media/;
+            expires 30d;
+            access_log off;
+        }
+    }
+}

compose/production/postgres/Dockerfile

@@ -0,0 +1,6 @@
+FROM docker.io/postgres:16
+
+COPY ./compose/production/postgres/maintenance /usr/local/bin/maintenance
+RUN chmod +x /usr/local/bin/maintenance/*
+RUN mv /usr/local/bin/maintenance/* /usr/local/bin \
+    && rmdir /usr/local/bin/maintenance

compose/production/postgres/maintenance/_sourced/constants.sh

@@ -0,0 +1,5 @@
+#!/usr/bin/env bash
+
+
+BACKUP_DIR_PATH='/backups'
+BACKUP_FILE_PREFIX='backup'

compose/production/postgres/maintenance/_sourced/countdown.sh

@@ -0,0 +1,12 @@
+#!/usr/bin/env bash
+
+
+countdown() {
+    declare desc="A simple countdown. Source: https://superuser.com/a/611582"
+    local seconds="${1}"
+    local d=$(($(date +%s) + "${seconds}"))
+    while [ "$d" -ge `date +%s` ]; do
+        echo -ne "$(date -u --date @$(($d - `date +%s`)) +%H:%M:%S)\r";
+        sleep 0.1
+    done
+}

compose/production/postgres/maintenance/_sourced/messages.sh

@@ -0,0 +1,41 @@
+#!/usr/bin/env bash
+
+
+message_newline() {
+    echo
+}
+
+message_debug()
+{
+    echo -e "DEBUG: ${@}"
+}
+
+message_welcome()
+{
+    echo -e "\e[1m${@}\e[0m"
+}
+
+message_warning()
+{
+    echo -e "\e[33mWARNING\e[0m: ${@}"
+}
+
+message_error()
+{
+    echo -e "\e[31mERROR\e[0m: ${@}"
+}
+
+message_info()
+{
+    echo -e "\e[37mINFO\e[0m: ${@}"
+}
+
+message_suggestion()
+{
+    echo -e "\e[33mSUGGESTION\e[0m: ${@}"
+}
+
+message_success()
+{
+    echo -e "\e[32mSUCCESS\e[0m: ${@}"
+}

compose/production/postgres/maintenance/_sourced/yes_no.sh

@@ -0,0 +1,16 @@
+#!/usr/bin/env bash
+
+
+yes_no() {
+    declare desc="Prompt for confirmation. \$\"\{1\}\": confirmation message."
+    local arg1="${1}"
+
+    local response=
+    read -r -p "${arg1} (y/[n])? " response
+    if [[ "${response}" =~ ^[Yy]$ ]]
+    then
+        exit 0
+    else
+        exit 1
+    fi
+}

compose/production/postgres/maintenance/backup

@@ -0,0 +1,38 @@
+#!/usr/bin/env bash
+
+
+### Create a database backup.
+###
+### Usage:
+###     $ docker compose -f <environment>.yml (exec |run --rm) postgres backup
+
+
+set -o errexit
+set -o pipefail
+set -o nounset
+
+
+working_dir="$(dirname ${0})"
+source "${working_dir}/_sourced/constants.sh"
+source "${working_dir}/_sourced/messages.sh"
+
+
+message_welcome "Backing up the '${POSTGRES_DB}' database..."
+
+
+if [[ "${POSTGRES_USER}" == "postgres" ]]; then
+    message_error "Backing up as 'postgres' user is not supported. Assign 'POSTGRES_USER' env with another one and try again."
+    exit 1
+fi
+
+export PGHOST="${POSTGRES_HOST}"
+export PGPORT="${POSTGRES_PORT}"
+export PGUSER="${POSTGRES_USER}"
+export PGPASSWORD="${POSTGRES_PASSWORD}"
+export PGDATABASE="${POSTGRES_DB}"
+
+backup_filename="${BACKUP_FILE_PREFIX}_$(date +'%Y_%m_%dT%H_%M_%S').sql.gz"
+pg_dump | gzip > "${BACKUP_DIR_PATH}/${backup_filename}"
+
+
+message_success "'${POSTGRES_DB}' database backup '${backup_filename}' has been created and placed in '${BACKUP_DIR_PATH}'."

compose/production/postgres/maintenance/backups

@@ -0,0 +1,22 @@
+#!/usr/bin/env bash
+
+
+### View backups.
+###
+### Usage:
+###     $ docker compose -f <environment>.yml (exec |run --rm) postgres backups
+
+
+set -o errexit
+set -o pipefail
+set -o nounset
+
+
+working_dir="$(dirname ${0})"
+source "${working_dir}/_sourced/constants.sh"
+source "${working_dir}/_sourced/messages.sh"
+
+
+message_welcome "These are the backups you have got:"
+
+ls -lht "${BACKUP_DIR_PATH}"

compose/production/postgres/maintenance/restore

@@ -0,0 +1,55 @@
+#!/usr/bin/env bash
+
+
+### Restore database from a backup.
+###
+### Parameters:
+###     <1> filename of an existing backup.
+###
+### Usage:
+###     $ docker compose -f <environment>.yml (exec |run --rm) postgres restore <1>
+
+
+set -o errexit
+set -o pipefail
+set -o nounset
+
+
+working_dir="$(dirname ${0})"
+source "${working_dir}/_sourced/constants.sh"
+source "${working_dir}/_sourced/messages.sh"
+
+
+if [[ -z ${1+x} ]]; then
+    message_error "Backup filename is not specified yet it is a required parameter. Make sure you provide one and try again."
+    exit 1
+fi
+backup_filename="${BACKUP_DIR_PATH}/${1}"
+if [[ ! -f "${backup_filename}" ]]; then
+    message_error "No backup with the specified filename found. Check out the 'backups' maintenance script output to see if there is one and try again."
+    exit 1
+fi
+
+message_welcome "Restoring the '${POSTGRES_DB}' database from the '${backup_filename}' backup..."
+
+if [[ "${POSTGRES_USER}" == "postgres" ]]; then
+    message_error "Restoring as 'postgres' user is not supported. Assign 'POSTGRES_USER' env with another one and try again."
+    exit 1
+fi
+
+export PGHOST="${POSTGRES_HOST}"
+export PGPORT="${POSTGRES_PORT}"
+export PGUSER="${POSTGRES_USER}"
+export PGPASSWORD="${POSTGRES_PASSWORD}"
+export PGDATABASE="${POSTGRES_DB}"
+
+message_info "Dropping the database..."
+dropdb "${PGDATABASE}"
+
+message_info "Creating a new database..."
+createdb --owner="${POSTGRES_USER}"
+
+message_info "Applying the backup to the new database..."
+gunzip -c "${backup_filename}" | psql "${POSTGRES_DB}"
+
+message_success "The '${POSTGRES_DB}' database has been restored from the '${backup_filename}' backup."

compose/production/postgres/maintenance/rmbackup

@@ -0,0 +1,36 @@
+#!/usr/bin/env bash
+
+### Remove a database backup.
+###
+### Parameters:
+###     <1> filename of a backup to remove.
+###
+### Usage:
+###     $ docker-compose -f <environment>.yml (exec |run --rm) postgres rmbackup <1>
+
+
+set -o errexit
+set -o pipefail
+set -o nounset
+
+
+working_dir="$(dirname ${0})"
+source "${working_dir}/_sourced/constants.sh"
+source "${working_dir}/_sourced/messages.sh"
+
+
+if [[ -z ${1+x} ]]; then
+    message_error "Backup filename is not specified yet it is a required parameter. Make sure you provide one and try again."
+    exit 1
+fi
+backup_filename="${BACKUP_DIR_PATH}/${1}"
+if [[ ! -f "${backup_filename}" ]]; then
+    message_error "No backup with the specified filename found. Check out the 'backups' maintenance script output to see if there is one and try again."
+    exit 1
+fi
+
+message_welcome "Removing the '${backup_filename}' backup file..."
+
+rm -r "${backup_filename}"
+
+message_success "The '${backup_filename}' database backup has been removed."

compose/production/traefik/Dockerfile

@@ -0,0 +1,5 @@
+FROM docker.io/traefik:3.3.4
+RUN mkdir -p /etc/traefik/acme \
+  && touch /etc/traefik/acme/acme.json \
+  && chmod 600 /etc/traefik/acme/acme.json
+COPY ./compose/production/traefik/traefik.yml /etc/traefik

compose/production/traefik/traefik.yml

@@ -0,0 +1,73 @@
+log:
+  level: INFO
+
+entryPoints:
+  web:
+    # http
+    address: ':80'
+    http:
+      # https://doc.traefik.io/traefik/routing/entrypoints/#entrypoint
+      redirections:
+        entryPoint:
+          to: web-secure
+
+  web-secure:
+    # https
+    address: ':443'
+
+certificatesResolvers:
+  letsencrypt:
+    # https://doc.traefik.io/traefik/https/acme/#lets-encrypt
+    acme:
+      email: 'antonio-roberto@example.com'
+      storage: /etc/traefik/acme/acme.json
+      # https://doc.traefik.io/traefik/https/acme/#httpchallenge
+      httpChallenge:
+        entryPoint: web
+
+http:
+  routers:
+    web-secure-router:
+      rule: 'Host(`example.com`) || Host(`www.example.com`)'
+      entryPoints:
+        - web-secure
+      middlewares:
+        - csrf
+      service: django
+      tls:
+        # https://doc.traefik.io/traefik/routing/routers/#certresolver
+        certResolver: letsencrypt
+
+    web-media-router:
+      rule: '(Host(`example.com`) || Host(`www.example.com`)) && PathPrefix(`/media/`)'
+      entryPoints:
+        - web-secure
+      middlewares:
+        - csrf
+      service: django-media
+      tls:
+        certResolver: letsencrypt
+
+  middlewares:
+    csrf:
+      # https://doc.traefik.io/traefik/master/middlewares/http/headers/#hostsproxyheaders
+      # https://docs.djangoproject.com/en/dev/ref/csrf/#ajax
+      headers:
+        hostsProxyHeaders: ['X-CSRFToken']
+
+  services:
+    django:
+      loadBalancer:
+        servers:
+          - url: http://django:5000
+
+    django-media:
+      loadBalancer:
+        servers:
+          - url: http://nginx:80
+
+providers:
+  # https://doc.traefik.io/traefik/master/providers/file/
+  file:
+    filename: /etc/traefik/traefik.yml
+    watch: true

config/api.py

@@ -0,0 +1,11 @@
+from ninja import NinjaAPI
+from diarios.views import router as diarios_router
+
+
+api = NinjaAPI(
+    title="API de Diários Oficiais",
+    version="1.0.0",
+    description="API para busca em diários oficiais",
+)
+
+api.add_router("/diarios/", diarios_router)

config/asgi.py

@@ -0,0 +1,13 @@
+import os
+from pathlib import Path
+import sys
+
+from django.core.asgi import get_asgi_application
+
+BASE_DIR = Path(__file__).resolve(strict=True).parent.parent
+sys.path.append(str(BASE_DIR / "diarios_oficiais_alems"))
+
+os.environ.setdefault("DJANGO_SETTINGS_MODULE", "config.settings.production")
+
+application = get_asgi_application()
+

config/settings/base.py

@@ -0,0 +1,375 @@
+# ruff: noqa: ERA001, E501
+"""Base settings to build other settings files upon."""
+
+
+from pathlib import Path
+
+import environ
+
+BASE_DIR = Path(__file__).resolve(strict=True).parent.parent.parent
+# diarios_oficiais_alems/
+APPS_DIR = BASE_DIR / "diarios_oficiais_alems"
+env = environ.Env()
+
+READ_DOT_ENV_FILE = env.bool("DJANGO_READ_DOT_ENV_FILE", default=True)
+if READ_DOT_ENV_FILE:
+    # OS environment variables take precedence over variables from .env
+    env.read_env(str(BASE_DIR / ".env"))
+
+# GENERAL
+# ------------------------------------------------------------------------------
+# https://docs.djangoproject.com/en/dev/ref/settings/#debug
+DEBUG = env.bool("DJANGO_DEBUG", True)
+# Local time zone. Choices are
+# http://en.wikipedia.org/wiki/List_of_tz_zones_by_name
+# though not all of them may be available with every OS.
+# In Windows, this must be set to your system time zone.
+TIME_ZONE = "UTC"
+# https://docs.djangoproject.com/en/dev/ref/settings/#language-code
+LANGUAGE_CODE = "en-us"
+# https://docs.djangoproject.com/en/dev/ref/settings/#languages
+# from django.utils.translation import gettext_lazy as _
+# LANGUAGES = [
+#     ('en', _('English')),
+#     ('fr-fr', _('French')),
+#     ('pt-br', _('Portuguese')),
+# ]
+# https://docs.djangoproject.com/en/dev/ref/settings/#site-id
+SITE_ID = 1
+# https://docs.djangoproject.com/en/dev/ref/settings/#use-i18n
+USE_I18N = True
+# https://docs.djangoproject.com/en/dev/ref/settings/#use-tz
+USE_TZ = True
+# https://docs.djangoproject.com/en/dev/ref/settings/#locale-paths
+LOCALE_PATHS = [str(BASE_DIR / "locale")]
+
+# DATABASES
+# ------------------------------------------------------------------------------
+# https://docs.djangoproject.com/en/dev/ref/settings/#databases
+DATABASES = {"default": env.db("DATABASE_URL")}
+DATABASES["default"]["ATOMIC_REQUESTS"] = False
+# https://docs.djangoproject.com/en/stable/ref/settings/#std:setting-DEFAULT_AUTO_FIELD
+DEFAULT_AUTO_FIELD = "django.db.models.BigAutoField"
+
+# URLS
+# ------------------------------------------------------------------------------
+# https://docs.djangoproject.com/en/dev/ref/settings/#root-urlconf
+ROOT_URLCONF = "config.urls"
+# https://docs.djangoproject.com/en/dev/ref/settings/#wsgi-application
+WSGI_APPLICATION = "config.wsgi.application"
+
+# APPS
+# ------------------------------------------------------------------------------
+DJANGO_APPS = [
+    "django.contrib.auth",
+    "django.contrib.contenttypes",
+    "django.contrib.sessions",
+    "django.contrib.sites",
+    "django.contrib.messages",
+    "django.contrib.staticfiles",
+    "django.contrib.humanize",
+    "django.contrib.admin",
+    "django.forms",
+]
+THIRD_PARTY_APPS = [
+    "crispy_forms",
+    "crispy_bootstrap5",
+    "allauth",
+    "allauth.account",
+    "allauth.mfa",
+    "allauth.socialaccount",
+]
+
+LOCAL_APPS = [
+    "diarios_oficiais_alems.users",
+    "diarios",
+    "django_elasticsearch_dsl",
+    "corsheaders",
+]
+# https://docs.djangoproject.com/en/dev/ref/settings/#installed-apps
+INSTALLED_APPS = DJANGO_APPS + THIRD_PARTY_APPS + LOCAL_APPS
+
+# MIGRATIONS
+# ------------------------------------------------------------------------------
+# https://docs.djangoproject.com/en/dev/ref/settings/#migration-modules
+MIGRATION_MODULES = {"sites": "diarios_oficiais_alems.contrib.sites.migrations"}
+
+# AUTHENTICATION
+# ------------------------------------------------------------------------------
+# https://docs.djangoproject.com/en/dev/ref/settings/#authentication-backends
+AUTHENTICATION_BACKENDS = [
+    "django.contrib.auth.backends.ModelBackend",
+    "allauth.account.auth_backends.AuthenticationBackend",
+]
+# https://docs.djangoproject.com/en/dev/ref/settings/#auth-user-model
+AUTH_USER_MODEL = "users.User"
+# https://docs.djangoproject.com/en/dev/ref/settings/#login-redirect-url
+LOGIN_REDIRECT_URL = "users:redirect"
+# https://docs.djangoproject.com/en/dev/ref/settings/#login-url
+LOGIN_URL = "account_login"
+
+# PASSWORDS
+# ------------------------------------------------------------------------------
+# https://docs.djangoproject.com/en/dev/ref/settings/#password-hashers
+PASSWORD_HASHERS = [
+    # https://docs.djangoproject.com/en/dev/topics/auth/passwords/#using-argon2-with-django
+    "django.contrib.auth.hashers.Argon2PasswordHasher",
+    "django.contrib.auth.hashers.PBKDF2PasswordHasher",
+    "django.contrib.auth.hashers.PBKDF2SHA1PasswordHasher",
+    "django.contrib.auth.hashers.BCryptSHA256PasswordHasher",
+]
+# https://docs.djangoproject.com/en/dev/ref/settings/#auth-password-validators
+AUTH_PASSWORD_VALIDATORS = [
+    {
+        "NAME": "django.contrib.auth.password_validation.UserAttributeSimilarityValidator",
+    },
+    {"NAME": "django.contrib.auth.password_validation.MinimumLengthValidator"},
+    {"NAME": "django.contrib.auth.password_validation.CommonPasswordValidator"},
+    {"NAME": "django.contrib.auth.password_validation.NumericPasswordValidator"},
+]
+
+# MIDDLEWARE
+# ------------------------------------------------------------------------------
+# https://docs.djangoproject.com/en/dev/ref/settings/#middleware
+MIDDLEWARE = [
+    "django.middleware.security.SecurityMiddleware",
+    "whitenoise.middleware.WhiteNoiseMiddleware",
+    "django.contrib.sessions.middleware.SessionMiddleware",
+    "django.middleware.locale.LocaleMiddleware",
+    "django.middleware.common.CommonMiddleware",
+    "corsheaders.middleware.CorsMiddleware",
+    "django.middleware.csrf.CsrfViewMiddleware",
+    "django.contrib.auth.middleware.AuthenticationMiddleware",
+    "django.contrib.messages.middleware.MessageMiddleware",
+    "django.middleware.clickjacking.XFrameOptionsMiddleware",
+    "allauth.account.middleware.AccountMiddleware",
+]
+
+# STATIC
+# ------------------------------------------------------------------------------
+# https://docs.djangoproject.com/en/dev/ref/settings/#static-root
+STATIC_ROOT = str(BASE_DIR / "staticfiles")
+# https://docs.djangoproject.com/en/dev/ref/settings/#static-url
+STATIC_URL = "/static/"
+# https://docs.djangoproject.com/en/dev/ref/contrib/staticfiles/#std:setting-STATICFILES_DIRS
+STATICFILES_DIRS = [str(APPS_DIR / "static")]
+# https://docs.djangoproject.com/en/dev/ref/contrib/staticfiles/#staticfiles-finders
+STATICFILES_FINDERS = [
+    "django.contrib.staticfiles.finders.FileSystemFinder",
+    "django.contrib.staticfiles.finders.AppDirectoriesFinder",
+]
+
+# MEDIA
+# ------------------------------------------------------------------------------
+# https://docs.djangoproject.com/en/dev/ref/settings/#media-root
+MEDIA_ROOT = str(APPS_DIR / "media")
+# https://docs.djangoproject.com/en/dev/ref/settings/#media-url
+MEDIA_URL = "/media/"
+
+# TEMPLATES
+# ------------------------------------------------------------------------------
+# https://docs.djangoproject.com/en/dev/ref/settings/#templates
+TEMPLATES = [
+    {
+        # https://docs.djangoproject.com/en/dev/ref/settings/#std:setting-TEMPLATES-BACKEND
+        "BACKEND": "django.template.backends.django.DjangoTemplates",
+        # https://docs.djangoproject.com/en/dev/ref/settings/#dirs
+        "DIRS": [str(APPS_DIR / "templates")],
+        # https://docs.djangoproject.com/en/dev/ref/settings/#app-dirs
+        "APP_DIRS": True,
+        "OPTIONS": {
+            # https://docs.djangoproject.com/en/dev/ref/settings/#template-context-processors
+            "context_processors": [
+                "django.template.context_processors.debug",
+                "django.template.context_processors.request",
+                "django.contrib.auth.context_processors.auth",
+                "django.template.context_processors.i18n",
+                "django.template.context_processors.media",
+                "django.template.context_processors.static",
+                "django.template.context_processors.tz",
+                "django.contrib.messages.context_processors.messages",
+                "diarios_oficiais_alems.users.context_processors.allauth_settings",
+            ],
+        },
+    },
+]
+
+# https://docs.djangoproject.com/en/dev/ref/settings/#form-renderer
+FORM_RENDERER = "django.forms.renderers.TemplatesSetting"
+
+# http://django-crispy-forms.readthedocs.io/en/latest/install.html#template-packs
+CRISPY_TEMPLATE_PACK = "bootstrap5"
+CRISPY_ALLOWED_TEMPLATE_PACKS = "bootstrap5"
+
+# FIXTURES
+# ------------------------------------------------------------------------------
+# https://docs.djangoproject.com/en/dev/ref/settings/#fixture-dirs
+FIXTURE_DIRS = (str(APPS_DIR / "fixtures"),)
+
+# SECURITY
+# ------------------------------------------------------------------------------
+# https://docs.djangoproject.com/en/dev/ref/settings/#session-cookie-httponly
+# https://docs.djangoproject.com/en/dev/ref/settings/#csrf-cookie-httponly
+CSRF_COOKIE_SECURE = False
+CSRF_COOKIE_HTTPONLY = False
+CSRF_COOKIE_SAMESITE = "Lax"
+SESSION_COOKIE_SECURE = False
+SESSION_COOKIE_SAMESITE = "Lax"
+CSRF_TRUSTED_ORIGINS = [
+    'http://192.168.235.234:8005',
+    'http://192.168.235.234:80',
+    'http://192.168.235.234',
+    'http://localhost:8005',
+    'http://localhost:80',
+    'http://localhost',
+    'http://127.0.0.1:8005',
+    'http://127.0.0.1:80',
+    'http://127.0.0.1',
+]
+
+# https://docs.djangoproject.com/en/dev/ref/settings/#x-frame-options
+X_FRAME_OPTIONS = "DENY"
+USE_X_FORWARDED_HOST = True
+SECURE_PROXY_SSL_HEADER = ('HTTP_X_FORWARDED_PROTO', 'http')
+
+# EMAIL
+# ------------------------------------------------------------------------------
+# https://docs.djangoproject.com/en/dev/ref/settings/#email-backend
+EMAIL_BACKEND = env(
+    "DJANGO_EMAIL_BACKEND",
+    default="django.core.mail.backends.smtp.EmailBackend",
+)
+# https://docs.djangoproject.com/en/dev/ref/settings/#email-timeout
+EMAIL_TIMEOUT = 5
+
+# ADMIN
+# ------------------------------------------------------------------------------
+# Django Admin URL.
+ADMIN_URL = "manage-panel/"
+# https://docs.djangoproject.com/en/dev/ref/settings/#admins
+ADMINS = [("""Antonio Roberto""", "antonio-roberto@example.com")]
+# https://docs.djangoproject.com/en/dev/ref/settings/#managers
+MANAGERS = ADMINS
+# https://cookiecutter-django.readthedocs.io/en/latest/settings.html#other-environment-settings
+# Force the `admin` sign in process to go through the `django-allauth` workflow
+DJANGO_ADMIN_FORCE_ALLAUTH = env.bool("DJANGO_ADMIN_FORCE_ALLAUTH", default=False)
+
+# LOGGING
+# ------------------------------------------------------------------------------
+# https://docs.djangoproject.com/en/dev/ref/settings/#logging
+# See https://docs.djangoproject.com/en/dev/topics/logging for
+# more details on how to customize your logging configuration.
+LOGGING = {
+    "version": 1,
+    "disable_existing_loggers": False,
+    "formatters": {
+        "verbose": {
+            "format": "%(levelname)s %(asctime)s %(module)s %(process)d %(thread)d %(message)s",
+        },
+    },
+    "handlers": {
+        "console": {
+            "level": "DEBUG",
+            "class": "logging.StreamHandler",
+            "formatter": "verbose",
+        },
+    },
+    "root": {"level": "INFO", "handlers": ["console"]},
+}
+
+REDIS_URL = env("REDIS_URL", default="redis://redis:6379/0")
+REDIS_SSL = REDIS_URL.startswith("rediss://")
+
+
+# django-allauth
+# ------------------------------------------------------------------------------
+ACCOUNT_ALLOW_REGISTRATION = False
+# https://docs.allauth.org/en/latest/account/configuration.html
+ACCOUNT_LOGIN_METHODS = {"username"}
+# https://docs.allauth.org/en/latest/account/configuration.html
+ACCOUNT_EMAIL_REQUIRED = True
+# https://docs.allauth.org/en/latest/account/configuration.html
+ACCOUNT_EMAIL_VERIFICATION = "mandatory"
+# https://docs.allauth.org/en/latest/account/configuration.html
+ACCOUNT_ADAPTER = "diarios_oficiais_alems.users.adapters.AccountAdapter"
+# https://docs.allauth.org/en/latest/account/forms.html
+ACCOUNT_FORMS = {"signup": "diarios_oficiais_alems.users.forms.UserSignupForm"}
+# https://docs.allauth.org/en/latest/socialaccount/configuration.html
+SOCIALACCOUNT_ADAPTER = "diarios_oficiais_alems.users.adapters.SocialAccountAdapter"
+# https://docs.allauth.org/en/latest/socialaccount/configuration.html
+SOCIALACCOUNT_FORMS = {
+    "signup": "diarios_oficiais_alems.users.forms.UserSocialSignupForm"
+}
+# django-compressor
+# ------------------------------------------------------------------------------
+# https://django-compressor.readthedocs.io/en/latest/quickstart/#installation
+INSTALLED_APPS += ["compressor"]
+STATICFILES_FINDERS += ["compressor.finders.CompressorFinder"]
+
+# Elastic Search
+# ------------------------------------------------------------------------------
+ELASTICSEARCH_USER = env.str("ELASTICSEARCH_USER")
+ELASTICSEARCH_PASSWORD = env.str("ELASTICSEARCH_PASSWORD")
+
+ELASTICSEARCH_DSL = {
+    "default": {
+        "hosts": "http://elasticsearch:9200",
+        "timeout": 60,
+        "http_auth": (
+            ELASTICSEARCH_USER,
+            ELASTICSEARCH_PASSWORD,
+        ),
+    },
+}
+ELASTICSEARCH_HOSTS = "http://elasticsearch:9200"
+
+ELASTICSEARCH_INDEX_SETTINGS = {
+    # Define o número de shards (partições) para o índice.
+    "number_of_shards": 1,
+    # Define o número de réplicas de cada shard.
+    "number_of_replicas": 0,
+    # Configurações de análise do Elasticsearch para processamento do texto
+    "analysis": {
+        # Definição de filtros de análise
+        "filter": {
+            # Filtro de remoção de stopwords (palavras comuns que não agregam significado)
+            "portuguese_stop": {"type": "stop", "stopwords": "_portuguese_"},
+            # Filtro de stemming para reduzir palavras à sua raiz (ex: "correndo" -> "correr")
+            "portuguese_stemmer": {"type": "stemmer", "language": "portuguese"},
+            # Filtro de sinônimos, carregando um arquivo externo com a lista de sinônimos
+            "synonym_filter": {
+                "type": "synonym",
+                "synonyms_path": "analysis/sinonimos.txt",  # Caminho para o arquivo de sinônimos
+            },
+        },
+        # Definição de analisadores (combinações de tokenizer e filtros)
+        "analyzer": {
+            # Criando um analisador chamado "pt_analyzer" para português
+            "pt_analyzer": {
+                # Define o tokenizer como "standard", que quebra o texto em palavras básicas
+                "tokenizer": "standard",
+                # Lista de filtros a serem aplicados ao texto após a tokenização
+                "filter": [
+                    # Converte todas as palavras para minúsculas
+                    "lowercase",
+                    # Aplica o filtro de remoção de stopwords em português
+                    "portuguese_stop",
+                    # Aplica o filtro de stemming para reduzir palavras à sua raiz
+                    "portuguese_stemmer",
+                    # Aplica o filtro de sinônimos, substituindo palavras por seus sinônimos conforme o arquivo
+                    "synonym_filter",
+                ],
+            }
+        },
+    },
+}
+
+CORS_ALLOWED_ORIGINS = [
+    "http://192.168.235.234",
+    "http://109.199.98.226:8006",
+    "http://109.199.98.226:8005",
+    "http://localhost:8006",
+    "http://localhost:8005",
+    "http://127.0.0.1:8006",
+    "http://127.0.0.1:8005",
+]

config/settings/local.py

@@ -0,0 +1,80 @@
+# ruff: noqa: E501
+from .base import *  # noqa: F403
+from .base import INSTALLED_APPS
+from .base import MIDDLEWARE
+from .base import env
+
+# GENERAL
+# ------------------------------------------------------------------------------
+# https://docs.djangoproject.com/en/dev/ref/settings/#debug
+DEBUG = True
+# https://docs.djangoproject.com/en/dev/ref/settings/#secret-key
+SECRET_KEY = env(
+    "DJANGO_SECRET_KEY",
+    default="tYdYl0MP5zgpMlMmjBuYHvH4Dp3JDN5q3sxWBdFejemZSr0qpI9IrvrvTm17F0aW",
+)
+# https://docs.djangoproject.com/en/dev/ref/settings/#allowed-hosts
+ALLOWED_HOSTS = ["localhost", "0.0.0.0", "127.0.0.1", "192.168.235.234"]  # noqa: S104
+
+# CACHES
+# ------------------------------------------------------------------------------
+# https://docs.djangoproject.com/en/dev/ref/settings/#caches
+CACHES = {
+    "default": {
+        "BACKEND": "django.core.cache.backends.locmem.LocMemCache",
+        "LOCATION": "",
+    },
+}
+
+# EMAIL
+# ------------------------------------------------------------------------------
+# https://docs.djangoproject.com/en/dev/ref/settings/#email-backend
+EMAIL_BACKEND = env(
+    "DJANGO_EMAIL_BACKEND",
+    default="django.core.mail.backends.console.EmailBackend",
+)
+
+# WhiteNoise
+# ------------------------------------------------------------------------------
+# http://whitenoise.evans.io/en/latest/django.html#using-whitenoise-in-development
+INSTALLED_APPS = ["whitenoise.runserver_nostatic", *INSTALLED_APPS]
+
+
+# django-debug-toolbar
+# ------------------------------------------------------------------------------
+# https://django-debug-toolbar.readthedocs.io/en/latest/installation.html#prerequisites
+INSTALLED_APPS += ["debug_toolbar"]
+# https://django-debug-toolbar.readthedocs.io/en/latest/installation.html#middleware
+MIDDLEWARE += ["debug_toolbar.middleware.DebugToolbarMiddleware"]
+# https://django-debug-toolbar.readthedocs.io/en/latest/configuration.html#debug-toolbar-config
+DEBUG_TOOLBAR_CONFIG = {
+    "DISABLE_PANELS": [
+        "debug_toolbar.panels.redirects.RedirectsPanel",
+        # Disable profiling panel due to an issue with Python 3.12:
+        # https://github.com/jazzband/django-debug-toolbar/issues/1875
+        "debug_toolbar.panels.profiling.ProfilingPanel",
+    ],
+    "SHOW_TEMPLATE_CONTEXT": True,
+}
+# https://django-debug-toolbar.readthedocs.io/en/latest/installation.html#internal-ips
+INTERNAL_IPS = ["127.0.0.1", "10.0.2.2"]
+if env("USE_DOCKER") == "yes":
+    import socket
+
+    hostname, _, ips = socket.gethostbyname_ex(socket.gethostname())
+    INTERNAL_IPS += [".".join(ip.split(".")[:-1] + ["1"]) for ip in ips]
+    # RunServerPlus
+    # ------------------------------------------------------------------------------
+    # This is a custom setting for RunServerPlus to fix reloader issue in Windows docker environment
+    # Werkzeug reloader type [auto, watchdog, or stat]
+    RUNSERVERPLUS_POLLER_RELOADER_TYPE = "stat"
+    # If you have CPU and IO load issues, you can increase this poller interval e.g) 5
+    RUNSERVERPLUS_POLLER_RELOADER_INTERVAL = 1
+
+# django-extensions
+# ------------------------------------------------------------------------------
+# https://django-extensions.readthedocs.io/en/latest/installation_instructions.html#configuration
+INSTALLED_APPS += ["django_extensions"]
+
+# Your stuff...
+# ------------------------------------------------------------------------------

config/settings/production.py

@@ -0,0 +1,172 @@
+# ruff: noqa: E501
+from .base import *  # noqa: F403
+from .base import DATABASES
+from .base import INSTALLED_APPS
+from .base import REDIS_URL
+from .base import env
+
+# GENERAL
+# ------------------------------------------------------------------------------
+# https://docs.djangoproject.com/en/dev/ref/settings/#secret-key
+SECRET_KEY = env("DJANGO_SECRET_KEY")
+# https://docs.djangoproject.com/en/dev/ref/settings/#allowed-hosts
+ALLOWED_HOSTS = env.list("DJANGO_ALLOWED_HOSTS", default=[])
+
+# DATABASES
+# ------------------------------------------------------------------------------
+DATABASES["default"]["CONN_MAX_AGE"] = env.int("CONN_MAX_AGE", default=60)
+
+# CACHES
+# ------------------------------------------------------------------------------
+CACHES = {
+    "default": {
+        "BACKEND": "django_redis.cache.RedisCache",
+        "LOCATION": REDIS_URL,
+        "OPTIONS": {
+            "CLIENT_CLASS": "django_redis.client.DefaultClient",
+            # Mimicking memcache behavior.
+            # https://github.com/jazzband/django-redis#memcached-exceptions-behavior
+            "IGNORE_EXCEPTIONS": True,
+        },
+    },
+}
+
+# SECURITY
+# ------------------------------------------------------------------------------
+# https://docs.djangoproject.com/en/dev/ref/settings/#secure-proxy-ssl-header
+SECURE_PROXY_SSL_HEADER = ("HTTP_X_FORWARDED_PROTO", "https")
+# https://docs.djangoproject.com/en/dev/ref/settings/#secure-ssl-redirect
+SECURE_SSL_REDIRECT = env.bool("DJANGO_SECURE_SSL_REDIRECT", default=False)
+# https://docs.djangoproject.com/en/dev/ref/settings/#session-cookie-secure
+SESSION_COOKIE_SECURE = True
+# https://docs.djangoproject.com/en/dev/ref/settings/#session-cookie-name
+SESSION_COOKIE_NAME = "__Secure-sessionid"
+# https://docs.djangoproject.com/en/dev/ref/settings/#csrf-cookie-secure
+CSRF_COOKIE_SECURE = True
+# https://docs.djangoproject.com/en/dev/ref/settings/#csrf-cookie-name
+CSRF_COOKIE_NAME = "__Secure-csrftoken"
+# https://docs.djangoproject.com/en/dev/topics/security/#ssl-https
+# https://docs.djangoproject.com/en/dev/ref/settings/#secure-hsts-seconds
+# TODO: set this to 60 seconds first and then to 518400 once you prove the former works
+SECURE_HSTS_SECONDS = 60
+# https://docs.djangoproject.com/en/dev/ref/settings/#secure-hsts-include-subdomains
+SECURE_HSTS_INCLUDE_SUBDOMAINS = env.bool(
+    "DJANGO_SECURE_HSTS_INCLUDE_SUBDOMAINS",
+    default=True,
+)
+# https://docs.djangoproject.com/en/dev/ref/settings/#secure-hsts-preload
+SECURE_HSTS_PRELOAD = env.bool("DJANGO_SECURE_HSTS_PRELOAD", default=True)
+# https://docs.djangoproject.com/en/dev/ref/middleware/#x-content-type-options-nosniff
+SECURE_CONTENT_TYPE_NOSNIFF = env.bool(
+    "DJANGO_SECURE_CONTENT_TYPE_NOSNIFF",
+    default=True,
+)
+
+# STATIC & MEDIA
+# ------------------------
+STORAGES = {
+    "default": {
+        "BACKEND": "django.core.files.storage.FileSystemStorage",
+    },
+    "staticfiles": {
+        "BACKEND": "whitenoise.storage.CompressedManifestStaticFilesStorage",
+    },
+}
+
+# EMAIL
+# ------------------------------------------------------------------------------
+# https://docs.djangoproject.com/en/dev/ref/settings/#default-from-email
+DEFAULT_FROM_EMAIL = env(
+    "DJANGO_DEFAULT_FROM_EMAIL",
+    default="Diários Oficiais ALEMS <noreply@example.com>",
+)
+# https://docs.djangoproject.com/en/dev/ref/settings/#server-email
+SERVER_EMAIL = env("DJANGO_SERVER_EMAIL", default=DEFAULT_FROM_EMAIL)
+# https://docs.djangoproject.com/en/dev/ref/settings/#email-subject-prefix
+EMAIL_SUBJECT_PREFIX = env(
+    "DJANGO_EMAIL_SUBJECT_PREFIX",
+    default="[Diários Oficiais ALEMS] ",
+)
+ACCOUNT_EMAIL_SUBJECT_PREFIX = EMAIL_SUBJECT_PREFIX
+
+# ADMIN
+# ------------------------------------------------------------------------------
+# Django Admin URL regex.
+ADMIN_URL = env("DJANGO_ADMIN_URL")
+
+# Anymail
+# ------------------------------------------------------------------------------
+# https://anymail.readthedocs.io/en/stable/installation/#installing-anymail
+INSTALLED_APPS += ["anymail"]
+# https://docs.djangoproject.com/en/dev/ref/settings/#email-backend
+# https://anymail.readthedocs.io/en/stable/installation/#anymail-settings-reference
+# https://anymail.readthedocs.io/en/stable/esps
+EMAIL_BACKEND = "django.core.mail.backends.smtp.EmailBackend"
+ANYMAIL = {}
+
+# django-compressor
+# ------------------------------------------------------------------------------
+# https://django-compressor.readthedocs.io/en/latest/settings/#django.conf.settings.COMPRESS_ENABLED
+COMPRESS_ENABLED = env.bool("COMPRESS_ENABLED", default=True)
+# https://django-compressor.readthedocs.io/en/latest/settings/#django.conf.settings.COMPRESS_STORAGE
+COMPRESS_STORAGE = "compressor.storage.GzipCompressorFileStorage"
+# https://django-compressor.readthedocs.io/en/latest/settings/#django.conf.settings.COMPRESS_URL
+COMPRESS_URL = STATIC_URL  # noqa: F405
+# https://django-compressor.readthedocs.io/en/latest/settings/#django.conf.settings.COMPRESS_OFFLINE
+COMPRESS_OFFLINE = True  # Offline compression is required when using Whitenoise
+# https://django-compressor.readthedocs.io/en/latest/settings/#django.conf.settings.COMPRESS_FILTERS
+COMPRESS_FILTERS = {
+    "css": [
+        "compressor.filters.css_default.CssAbsoluteFilter",
+        "compressor.filters.cssmin.rCSSMinFilter",
+    ],
+    "js": ["compressor.filters.jsmin.JSMinFilter"],
+}
+
+# LOGGING
+# ------------------------------------------------------------------------------
+# https://docs.djangoproject.com/en/dev/ref/settings/#logging
+# See https://docs.djangoproject.com/en/dev/topics/logging for
+# more details on how to customize your logging configuration.
+# A sample logging configuration. The only tangible logging
+# performed by this configuration is to send an email to
+# the site admins on every HTTP 500 error when DEBUG=False.
+LOGGING = {
+    "version": 1,
+    "disable_existing_loggers": False,
+    "filters": {"require_debug_false": {"()": "django.utils.log.RequireDebugFalse"}},
+    "formatters": {
+        "verbose": {
+            "format": "%(levelname)s %(asctime)s %(module)s %(process)d %(thread)d %(message)s",
+        },
+    },
+    "handlers": {
+        "mail_admins": {
+            "level": "ERROR",
+            "filters": ["require_debug_false"],
+            "class": "django.utils.log.AdminEmailHandler",
+        },
+        "console": {
+            "level": "DEBUG",
+            "class": "logging.StreamHandler",
+            "formatter": "verbose",
+        },
+    },
+    "root": {"level": "INFO", "handlers": ["console"]},
+    "loggers": {
+        "django.request": {
+            "handlers": ["mail_admins"],
+            "level": "ERROR",
+            "propagate": True,
+        },
+        "django.security.DisallowedHost": {
+            "level": "ERROR",
+            "handlers": ["console", "mail_admins"],
+            "propagate": True,
+        },
+    },
+}
+
+
+# Your stuff...
+# ------------------------------------------------------------------------------

config/settings/test.py

@@ -0,0 +1,38 @@
+"""
+With these settings, tests run faster.
+"""
+
+from .base import *  # noqa: F403
+from .base import TEMPLATES
+from .base import env
+
+# GENERAL
+# ------------------------------------------------------------------------------
+# https://docs.djangoproject.com/en/dev/ref/settings/#secret-key
+SECRET_KEY = env(
+    "DJANGO_SECRET_KEY",
+    default="zxqr3Ze2WN38ZLJaQLVByrC5TQ0sQHejMO3yiAv5tClsfNjkb9VjrgjNGvA6U002",
+)
+# https://docs.djangoproject.com/en/dev/ref/settings/#test-runner
+TEST_RUNNER = "django.test.runner.DiscoverRunner"
+
+# PASSWORDS
+# ------------------------------------------------------------------------------
+# https://docs.djangoproject.com/en/dev/ref/settings/#password-hashers
+PASSWORD_HASHERS = ["django.contrib.auth.hashers.MD5PasswordHasher"]
+
+# EMAIL
+# ------------------------------------------------------------------------------
+# https://docs.djangoproject.com/en/dev/ref/settings/#email-backend
+EMAIL_BACKEND = "django.core.mail.backends.locmem.EmailBackend"
+
+# DEBUGGING FOR TEMPLATES
+# ------------------------------------------------------------------------------
+TEMPLATES[0]["OPTIONS"]["debug"] = True  # type: ignore[index]
+
+# MEDIA
+# ------------------------------------------------------------------------------
+# https://docs.djangoproject.com/en/dev/ref/settings/#media-url
+MEDIA_URL = "http://media.testserver/"
+# Your stuff...
+# ------------------------------------------------------------------------------

config/urls.py

@@ -0,0 +1,55 @@
+# ruff: noqa
+from django.conf import settings
+from django.conf.urls.static import static
+from django.contrib import admin
+from django.urls import include
+from django.urls import path
+from django.views import defaults as default_views
+from django.views.generic import TemplateView
+from .api import api
+
+
+urlpatterns = [
+    # path("", TemplateView.as_view(template_name="pages/home.html"), name="home"),
+    path("", include('diarios.urls')),
+    path(
+        "about/",
+        TemplateView.as_view(template_name="pages/about.html"),
+        name="about",
+    ),
+    path("api/v1/", api.urls),
+    # Django Admin, use {% url 'admin:index' %}
+    path(settings.ADMIN_URL, admin.site.urls),
+    # User management
+    path("users/", include("diarios_oficiais_alems.users.urls", namespace="users")),
+    # path("accounts/", include("allauth.urls")),
+    # Media files
+    *static(settings.MEDIA_URL, document_root=settings.MEDIA_ROOT),
+]
+
+
+if settings.DEBUG:
+    # This allows the error pages to be debugged during development, just visit
+    # these url in browser to see how these error pages look like.
+    urlpatterns += [
+        path(
+            "400/",
+            default_views.bad_request,
+            kwargs={"exception": Exception("Bad Request!")},
+        ),
+        path(
+            "403/",
+            default_views.permission_denied,
+            kwargs={"exception": Exception("Permission Denied")},
+        ),
+        path(
+            "404/",
+            default_views.page_not_found,
+            kwargs={"exception": Exception("Page not Found")},
+        ),
+        path("500/", default_views.server_error),
+    ]
+    if "debug_toolbar" in settings.INSTALLED_APPS:
+        import debug_toolbar
+
+        urlpatterns = [path("__debug__/", include(debug_toolbar.urls))] + urlpatterns

config/wsgi.py

@@ -0,0 +1,40 @@
+# ruff: noqa
+"""
+WSGI config for Diários Oficiais ALEMS project.
+
+This module contains the WSGI application used by Django's development server
+and any production WSGI deployments. It should expose a module-level variable
+named ``application``. Django's ``runserver`` and ``runfcgi`` commands discover
+this application via the ``WSGI_APPLICATION`` setting.
+
+Usually you will have the standard Django WSGI application here, but it also
+might make sense to replace the whole Django WSGI application with a custom one
+that later delegates to the Django one. For example, you could introduce WSGI
+middleware here, or combine a Django application with an application of another
+framework.
+
+"""
+
+import os
+import sys
+from pathlib import Path
+
+from django.core.wsgi import get_wsgi_application
+
+# This allows easy placement of apps within the interior
+# diarios_oficiais_alems directory.
+BASE_DIR = Path(__file__).resolve(strict=True).parent.parent
+sys.path.append(str(BASE_DIR / "diarios_oficiais_alems"))
+# We defer to a DJANGO_SETTINGS_MODULE already in the environment. This breaks
+# if running multiple sites in the same mod_wsgi process. To fix this, use
+# mod_wsgi daemon mode with each site in its own daemon process, or use
+# os.environ["DJANGO_SETTINGS_MODULE"] = "config.settings.production"
+os.environ.setdefault("DJANGO_SETTINGS_MODULE", "config.settings.production")
+
+# This application object is used by any WSGI server configured to use this
+# file. This includes Django's development server, if the WSGI_APPLICATION
+# setting points here.
+application = get_wsgi_application()
+# Apply WSGI middleware here.
+# from helloworld.wsgi import HelloWorldApplication
+# application = HelloWorldApplication(application)

diarios/admin.py

@@ -0,0 +1,150 @@
+from django.contrib import admin
+from django.utils.html import format_html
+from django.urls import reverse
+from django.utils.safestring import mark_safe
+from .models import TipoDiarioOficial, DiarioOficial, PageDiarioOficial
+from .forms import PageDiarioOficialInlineForm
+
+
+@admin.register(TipoDiarioOficial)
+class TipoDiarioOficialAdmin(admin.ModelAdmin):
+    list_display = ("nome", "quantidade_diarios")
+    search_fields = ("nome",)
+    ordering = ("nome",)
+
+    def quantidade_diarios(self, obj):
+        return obj.diarios.count()
+
+    quantidade_diarios.short_description = "Nº de Diários"
+
+
+class PageDiarioOficialInline(admin.TabularInline):
+    form = PageDiarioOficialInlineForm
+    model = PageDiarioOficial
+    extra = 0
+    fields = ("id", "numero", "conteudo")
+    can_delete = False
+
+    def numero_link(self, instance):
+        if instance.id:
+            url = reverse("admin:diarios_pagediariooficial_change", args=[instance.id])
+            return mark_safe(f'<a href="{url}">{instance.numero}</a>')
+        return instance.numero
+
+    def conteudo_resumido(self, instance):
+        return (
+            (instance.conteudo[:100] + "...")
+            if len(instance.conteudo) > 100
+            else instance.conteudo
+        )
+
+    conteudo_resumido.short_description = "Conteúdo (resumo)"
+
+
+@admin.register(DiarioOficial)
+class DiarioOficialAdmin(admin.ModelAdmin):
+    list_display = (
+        "numero",
+        "tipo_nome",
+        "data_formatada_admin",
+        "arquivo_link",
+        "link_externo",
+        "paginas_count",
+    )
+    list_filter = ("tipo", "data")
+    search_fields = ("numero", "tipo__nome", "data")
+    date_hierarchy = "data"
+    ordering = ("-data", "-numero")
+    readonly_fields = (
+        "data_formatada_admin",
+        "arquivo_preview",
+        "paginas_count",
+        "link_externo",
+    )
+    fieldsets = (
+        (
+            "Informações Básicas",
+            {"fields": ("numero", "tipo", "data", "data_formatada_admin")},
+        ),
+        (
+            "Arquivos e Links",
+            {"fields": ("arquivo", "arquivo_preview", "link", "link_externo")},
+        ),
+        ("Estatísticas", {"fields": ("paginas_count",), "classes": ("collapse",)}),
+    )
+    # inlines = (PageDiarioOficialInline,)
+
+    def tipo_nome(self, obj):
+        return obj.tipo.nome if obj.tipo else "-"
+
+    tipo_nome.short_description = "Tipo"
+    tipo_nome.admin_order_field = "tipo__nome"
+
+    def data_formatada_admin(self, obj):
+        return obj.data_formatada
+
+    data_formatada_admin.short_description = "Data"
+
+    def arquivo_link(self, obj):
+        if obj.arquivo:
+            return mark_safe(
+                f'<a href="{obj.arquivo.url}" target="_blank">Download PDF</a>'
+            )
+        return "-"
+
+    arquivo_link.short_description = "Arquivo"
+    arquivo_link.allow_tags = True
+
+    def link_externo(self, obj):
+        if obj.link:
+            return mark_safe(f'<a href="{obj.link}" target="_blank">Acessar Online</a>')
+        return "-"
+
+    link_externo.short_description = "Link Externo"
+    link_externo.allow_tags = True
+
+    def arquivo_preview(self, obj):
+        if obj.arquivo:
+            return mark_safe(
+                f'<a href="{obj.arquivo.url}" target="_blank">Visualizar PDF</a>'
+            )
+        return "-"
+
+    arquivo_preview.short_description = "Pré-visualização"
+    arquivo_preview.allow_tags = True
+
+    def paginas_count(self, obj):
+        return obj.paginas.count()
+
+    paginas_count.short_description = "Nº de Páginas"
+
+    def get_queryset(self, request):
+        return super().get_queryset(request).prefetch_related("paginas")
+
+
+@admin.register(PageDiarioOficial)
+class PageDiarioOficialAdmin(admin.ModelAdmin):
+    autocomplete_fields = ("diario",)
+    list_display = ("id", "diario_link", "numero", "conteudo_resumido")
+    list_display_links = ('id', 'numero')
+    list_filter = ("diario__tipo", "diario__data", "layout_duas_colunas")
+    search_fields = ("diario__numero",)
+    readonly_fields = (
+        "diario_link",
+    )
+
+
+    def diario_link(self, obj):
+        url = reverse("admin:diarios_diariooficial_change", args=[obj.diario.id])
+        return mark_safe(f'<a href="{url}">{obj.diario}</a>')
+
+    diario_link.short_description = "Diário Oficial"
+    diario_link.allow_tags = True
+
+    def conteudo_resumido(self, obj):
+        return (obj.conteudo[:100] + "...") if len(obj.conteudo) > 100 else obj.conteudo
+
+    conteudo_resumido.short_description = "Conteúdo"
+
+    def get_queryset(self, request):
+        return super().get_queryset(request).select_related("diario")

diarios/api.py

@@ -0,0 +1,5 @@
+from ninja import NinjaAPI
+
+
+api = NinjaAPI()
+api.add_router("/diarios/", route)

diarios/apps.py

@@ -0,0 +1,10 @@
+from django.apps import AppConfig
+
+
+class DiariosConfig(AppConfig):
+    default_auto_field = "django.db.models.BigAutoField"
+    name = "diarios"
+
+    def ready(self):
+        import diarios.documents
+

diarios/crud_service.py

@@ -0,0 +1,179 @@
+from typing import Optional, List
+from datetime import date
+from diarios.models import DiarioOficial, TipoDiarioOficial
+from django.core.exceptions import ObjectDoesNotExist
+from ninja.errors import HttpError
+
+
+class DiarioOficialService:
+    @staticmethod
+    def criar_diario(
+        data: date,
+        numero: str,
+        tipo_id: Optional[int] = None,
+        arquivo=None,
+        link: Optional[str] = None
+    ) -> DiarioOficial:
+        """
+        Cria um novo diário oficial
+        
+        Args:
+            data: Data do diário
+            numero: Número do diário
+            tipo_id: ID do tipo de diário
+            arquivo: Arquivo PDF (opcional)
+            link: URL do PDF (opcional)
+            
+        Returns:
+            DiarioOficial: O diário criado
+            
+        Raises:
+            HttpError: Se ocorrer algum erro na criação
+        """
+        try:
+            tipo = TipoDiarioOficial.objects.get(pk=tipo_id) if tipo_id else None
+            
+            diario = DiarioOficial(
+                data=data,
+                numero=numero,
+                tipo=tipo,
+                link=link
+            )
+            
+            if arquivo:
+                diario.arquivo = arquivo
+                
+            diario.full_clean()
+            diario.save()
+            return diario
+            
+        except ObjectDoesNotExist:
+            raise HttpError(404, "Tipo de diário não encontrado")
+        except Exception as e:
+            raise HttpError(400, f"Erro ao criar diário: {str(e)}")
+
+    @staticmethod
+    def obter_diario_por_id(id: int) -> DiarioOficial:
+        """
+        Obtém um diário pelo ID
+        
+        Args:
+            id: ID do diário
+            
+        Returns:
+            DiarioOficial: O diário encontrado
+            
+        Raises:
+            HttpError: Se o diário não for encontrado
+        """
+        try:
+            return DiarioOficial.objects.get(pk=id)
+        except ObjectDoesNotExist:
+            raise HttpError(404, "Diário não encontrado")
+
+    @staticmethod
+    def listar_diarios(
+        tipo_id: Optional[int] = None,
+        data_inicio: Optional[date] = None,
+        data_fim: Optional[date] = None,
+        numero: Optional[str] = None
+    ) -> List[DiarioOficial]:
+        """
+        Lista diários com filtros opcionais
+        
+        Args:
+            tipo_id: ID do tipo de diário para filtrar
+            data_inicio: Data inicial para filtrar
+            data_fim: Data final para filtrar
+            numero: Número do diário para filtrar
+            
+        Returns:
+            List[DiarioOficial]: Lista de diários filtrados
+        """
+        queryset = DiarioOficial.objects.all().order_by('-data')
+        
+        if tipo_id:
+            queryset = queryset.filter(tipo_id=tipo_id)
+            
+        if data_inicio and data_fim:
+            queryset = queryset.filter(data__range=[data_inicio, data_fim])
+        elif data_inicio:
+            queryset = queryset.filter(data__gte=data_inicio)
+        elif data_fim:
+            queryset = queryset.filter(data__lte=data_fim)
+            
+        if numero:
+            queryset = queryset.filter(numero__icontains=numero)
+            
+        return list(queryset)
+
+    @staticmethod
+    def atualizar_diario(
+        id: int,
+        data: Optional[date] = None,
+        numero: Optional[str] = None,
+        tipo_id: Optional[int] = None,
+        arquivo=None,
+        link: Optional[str] = None
+    ) -> DiarioOficial:
+        """
+        Atualiza um diário existente
+        
+        Args:
+            id: ID do diário a ser atualizado
+            data: Nova data (opcional)
+            numero: Novo número (opcional)
+            tipo_id: Novo tipo (opcional)
+            arquivo: Novo arquivo (opcional)
+            link: Novo link (opcional)
+            
+        Returns:
+            DiarioOficial: O diário atualizado
+            
+        Raises:
+            HttpError: Se ocorrer algum erro na atualização
+        """
+        try:
+            diario = DiarioOficial.objects.get(pk=id)
+            
+            if data is not None:
+                diario.data = data
+                
+            if numero is not None:
+                diario.numero = numero
+                
+            if tipo_id is not None:
+                tipo = TipoDiarioOficial.objects.get(pk=tipo_id) if tipo_id else None
+                diario.tipo = tipo
+                
+            if arquivo is not None:
+                diario.arquivo = arquivo
+                
+            if link is not None:
+                diario.link = link
+                
+            diario.full_clean()
+            diario.save()
+            return diario
+            
+        except ObjectDoesNotExist:
+            raise HttpError(404, "Diário ou tipo não encontrado")
+        except Exception as e:
+            raise HttpError(400, f"Erro ao atualizar diário: {str(e)}")
+
+    @staticmethod
+    def deletar_diario(id: int) -> None:
+        """
+        Remove um diário
+        
+        Args:
+            id: ID do diário a ser removido
+            
+        Raises:
+            HttpError: Se o diário não for encontrado
+        """
+        try:
+            diario = DiarioOficial.objects.get(pk=id)
+            diario.delete()
+        except ObjectDoesNotExist:
+            raise HttpError(404, "Diário não encontrado")

diarios/documents.py

@@ -0,0 +1,67 @@
+from django_elasticsearch_dsl import Document, fields
+from django_elasticsearch_dsl.registries import registry
+from .models import DiarioOficial
+
+
+@registry.register_document
+class DiarioOficialDocument(Document):
+    numero = fields.KeywordField()
+    data = fields.DateField()
+    link = fields.KeywordField()
+    tipo = fields.ObjectField(properties={"nome": fields.KeywordField()})
+
+    # Campo para páginas
+    paginas = fields.NestedField(
+        properties={
+            "id": fields.IntegerField(),
+            "numero": fields.IntegerField(),
+            "conteudo": fields.TextField(
+                analyzer="custom_portuguese",
+                fields={
+                    "keyword": fields.KeywordField(),
+                    "search": fields.TextField(analyzer="custom_portuguese"),
+                },
+            ),
+        }
+    )
+
+    class Index:
+        name = "diario_oficial"
+        settings = {
+            "number_of_shards": 1,
+            "number_of_replicas": 0,
+            "analysis": {
+                "analyzer": {
+                    "custom_portuguese": {
+                        "type": "custom",
+                        "tokenizer": "standard",
+                        "filter": [
+                            "lowercase",
+                            "asciifolding",
+                            "portuguese_stop",
+                        ],
+                    }
+                },
+                "filter": {
+                    "portuguese_stop": {"type": "stop", "stopwords": "_portuguese_"},
+                },
+            },
+        }
+
+    class Django:
+        model = DiarioOficial
+        fields = ["id"]
+
+    def prepare_tipo(self, instance):
+        return {"nome": instance.tipo.nome if instance.tipo else "Sem Tipo"}
+
+    def prepare_link(self, instance):
+        return instance.link or ""
+
+    def prepare_paginas(self, instance):
+        # Preparar páginas ordenadas
+        paginas = instance.paginas.all().order_by("numero")
+        return [
+            {"id": pagina.id, "numero": pagina.numero, "conteudo": pagina.conteudo}
+            for pagina in paginas
+        ]

diarios/forms.py

@@ -0,0 +1,21 @@
+from django import forms
+from .models import PageDiarioOficial
+
+
+class PageDiarioOficialInlineForm(forms.ModelForm):
+    class Meta:
+        model = PageDiarioOficial
+        fields = "__all__"
+
+    def clean(self):
+        cleaned_data = super().clean()
+        if "numero" in cleaned_data and self.instance.diario:
+            if (
+                PageDiarioOficial.objects.filter(
+                    diario=self.instance.diario, numero=cleaned_data["numero"]
+                )
+                .exclude(pk=self.instance.pk)
+                .exists()
+            ):
+                self.add_error("numero", "Já existe uma página com este número")
+        return cleaned_data

diarios/management/commands/importar_diarios_com_ocr.py

@@ -0,0 +1,105 @@
+import os
+import time
+from django.core.files import File
+from django.core.management.base import BaseCommand
+from diarios.models import DiarioOficial
+from diarios.signals import update_document, delete_document
+from django.db.models.signals import post_save, post_delete
+
+
+class Command(BaseCommand):
+    help = "Importa arquivos PDF de diários oficiais e associa aos objetos existentes no banco."
+
+    def add_arguments(self, parser):
+        parser.add_argument(
+            "pasta",
+            type=str,
+            help="Caminho para a pasta contendo os arquivos PDF (nomes devem conter o número do diário)",
+        )
+
+    def handle(self, *args, **options):
+        post_save.disconnect(update_document, sender=DiarioOficial)
+        post_delete.disconnect(delete_document, sender=DiarioOficial)
+
+        pasta = options["pasta"]
+        if not os.path.isdir(pasta):
+            self.stderr.write(
+                self.style.ERROR(f"A pasta fornecida não existe: {pasta}")
+            )
+            return
+
+        arquivos_pdf = [
+            f
+            for f in os.listdir(pasta)
+            if f.lower().endswith(".pdf") and "Diário_Oficial_Eletrônico_nº_" in f
+        ]
+
+        if not arquivos_pdf:
+            self.stdout.write(
+                self.style.WARNING("Nenhum arquivo PDF válido encontrado na pasta.")
+            )
+            return
+
+        total = len(arquivos_pdf)
+        erros = []
+        atualizados = []
+        start_time = time.time()
+
+        # Mapeia os números aos nomes de arquivos
+        numero_para_arquivo = {
+            f.replace("Diário_Oficial_Eletrônico_nº_", "")
+            .replace(".pdf", "")
+            .strip("_-"): f
+            for f in arquivos_pdf
+        }
+
+        # Busca todos os objetos de uma vez
+        diarios_existentes = DiarioOficial.objects.in_bulk(
+            numero_para_arquivo.keys(), field_name="numero"
+        )
+
+        for idx, (numero, nome_arquivo) in enumerate(
+            numero_para_arquivo.items(), start=1
+        ):
+            try:
+                diario = diarios_existentes.get(numero)
+                if not diario:
+                    raise DiarioOficial.DoesNotExist()
+
+                caminho_pdf = os.path.join(pasta, nome_arquivo)
+                with open(caminho_pdf, "rb") as f:
+                    diario.arquivo.save(nome_arquivo, File(f), save=True)
+
+                atualizados.append(diario.pk)
+                elapsed = time.time() - start_time
+                remaining = (elapsed / idx) * (total - idx)
+                self.stdout.write(
+                    f"[{idx}/{total}] Atualizado: {nome_arquivo} | Estimativa restante: {remaining:.1f}s"
+                )
+
+            except DiarioOficial.DoesNotExist:
+                msg = f"Não encontrado no banco: {nome_arquivo}"
+                erros.append(msg)
+                self.stderr.write(self.style.WARNING(msg))
+
+            except Exception as e:
+                msg = f"Erro ao processar {nome_arquivo}: {str(e)}"
+                erros.append(msg)
+                self.stderr.write(self.style.ERROR(msg))
+
+        self.stdout.write(
+            self.style.SUCCESS(f"{len(atualizados)} arquivos importados com sucesso.")
+        )
+        self.stdout.write(self.style.WARNING(f"{len(erros)} arquivos com erro."))
+
+        if erros:
+            caminho_log = os.path.join(pasta, "erros_importacao.txt")
+            with open(caminho_log, "w", encoding="utf-8") as erro_file:
+                for linha in erros:
+                    erro_file.write(f"{linha}\n")
+            self.stdout.write(
+                self.style.WARNING(f"Erros registrados em: {caminho_log}")
+            )
+
+        post_save.connect(update_document, sender=DiarioOficial)
+        post_delete.connect(delete_document, sender=DiarioOficial)

diarios/migrations/0001_initial.py

@@ -0,0 +1,31 @@
+# Generated by Django 5.0.12 on 2025-03-06 16:00
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    initial = True
+
+    dependencies = []
+
+    operations = [
+        migrations.CreateModel(
+            name="PDFDocument",
+            fields=[
+                (
+                    "id",
+                    models.BigAutoField(
+                        auto_created=True,
+                        primary_key=True,
+                        serialize=False,
+                        verbose_name="ID",
+                    ),
+                ),
+                ("title", models.CharField(max_length=255)),
+                ("file", models.FileField(upload_to="pdfs/")),
+                ("content", models.TextField(blank=True)),
+                ("uploaded_at", models.DateTimeField(auto_now_add=True)),
+            ],
+        ),
+    ]

diarios/migrations/0002_pdfdocument_page_content.py

@@ -0,0 +1,18 @@
+# Generated by Django 5.0.12 on 2025-03-07 13:47
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("diarios", "0001_initial"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="pdfdocument",
+            name="page_content",
+            field=models.TextField(blank=True),
+        ),
+    ]

diarios/migrations/0003_tipodiariooficial_diariooficial_and_more.py

@@ -0,0 +1,75 @@
+# Generated by Django 5.0.12 on 2025-03-07 14:58
+
+import django.db.models.deletion
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("diarios", "0002_pdfdocument_page_content"),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name="TipoDiarioOficial",
+            fields=[
+                (
+                    "id",
+                    models.BigAutoField(
+                        auto_created=True,
+                        primary_key=True,
+                        serialize=False,
+                        verbose_name="ID",
+                    ),
+                ),
+                ("nome", models.CharField(max_length=100, unique=True)),
+            ],
+            options={
+                "verbose_name_plural": "Tipos de Diários Oficiais",
+            },
+        ),
+        migrations.CreateModel(
+            name="DiarioOficial",
+            fields=[
+                (
+                    "id",
+                    models.BigAutoField(
+                        auto_created=True,
+                        primary_key=True,
+                        serialize=False,
+                        verbose_name="ID",
+                    ),
+                ),
+                ("data", models.DateField()),
+                (
+                    "arquivo",
+                    models.FileField(
+                        blank=True, null=True, upload_to="diarios_oficiais/"
+                    ),
+                ),
+                ("numero", models.CharField(max_length=20, unique=True)),
+                ("link", models.URLField(blank=True, null=True, unique=True)),
+                ("finalizado", models.BooleanField(default=False)),
+                (
+                    "tipo",
+                    models.ForeignKey(
+                        blank=True,
+                        null=True,
+                        on_delete=django.db.models.deletion.CASCADE,
+                        related_name="diarios",
+                        to="diarios.tipodiariooficial",
+                    ),
+                ),
+            ],
+            options={
+                "verbose_name_plural": "Diários Oficiais",
+            },
+        ),
+        migrations.AddConstraint(
+            model_name="diariooficial",
+            constraint=models.UniqueConstraint(
+                fields=("numero",), name="unique_numero"
+            ),
+        ),
+    ]

diarios/migrations/0004_remove_diariooficial_finalizado_and_more.py

@@ -0,0 +1,39 @@
+# Generated by Django 5.0.12 on 2025-03-07 15:25
+
+import django.core.serializers.json
+import django.db.models.deletion
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("diarios", "0003_tipodiariooficial_diariooficial_and_more"),
+    ]
+
+    operations = [
+        migrations.RemoveField(
+            model_name="diariooficial",
+            name="finalizado",
+        ),
+        migrations.AddField(
+            model_name="diariooficial",
+            name="page_content",
+            field=models.JSONField(
+                blank=True,
+                encoder=django.core.serializers.json.DjangoJSONEncoder,
+                null=True,
+            ),
+        ),
+        migrations.AlterField(
+            model_name="diariooficial",
+            name="tipo",
+            field=models.ForeignKey(
+                blank=True,
+                null=True,
+                on_delete=django.db.models.deletion.SET_NULL,
+                related_name="diarios",
+                to="diarios.tipodiariooficial",
+            ),
+        ),
+    ]

diarios/migrations/0005_delete_pdfdocument.py

@@ -0,0 +1,16 @@
+# Generated by Django 5.0.12 on 2025-03-15 15:51
+
+from django.db import migrations
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("diarios", "0004_remove_diariooficial_finalizado_and_more"),
+    ]
+
+    operations = [
+        migrations.DeleteModel(
+            name="PDFDocument",
+        ),
+    ]

diarios/migrations/0006_remove_diariooficial_page_content_pagediariooficial.py

@@ -0,0 +1,47 @@
+# Generated by Django 5.0.12 on 2025-03-27 12:30
+
+import django.db.models.deletion
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("diarios", "0005_delete_pdfdocument"),
+    ]
+
+    operations = [
+        migrations.RemoveField(
+            model_name="diariooficial",
+            name="page_content",
+        ),
+        migrations.CreateModel(
+            name="PageDiarioOficial",
+            fields=[
+                (
+                    "id",
+                    models.BigAutoField(
+                        auto_created=True,
+                        primary_key=True,
+                        serialize=False,
+                        verbose_name="ID",
+                    ),
+                ),
+                ("numero", models.PositiveIntegerField()),
+                ("conteudo", models.TextField()),
+                (
+                    "diario",
+                    models.ForeignKey(
+                        on_delete=django.db.models.deletion.CASCADE,
+                        related_name="paginas",
+                        to="diarios.diariooficial",
+                    ),
+                ),
+            ],
+            options={
+                "verbose_name": "Página de Diário Oficial",
+                "verbose_name_plural": "Páginas de Diários Oficiais",
+                "unique_together": {("diario", "numero")},
+            },
+        ),
+    ]

diarios/migrations/0007_diariooficial_layout_duas_colunas.py

@@ -0,0 +1,18 @@
+# Generated by Django 5.0.12 on 2025-04-28 13:35
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("diarios", "0006_remove_diariooficial_page_content_pagediariooficial"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="diariooficial",
+            name="layout_duas_colunas",
+            field=models.BooleanField(default=False),
+        ),
+    ]

diarios/migrations/0008_remove_diariooficial_layout_duas_colunas_and_more.py

@@ -0,0 +1,22 @@
+# Generated by Django 5.0.12 on 2025-04-28 13:43
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("diarios", "0007_diariooficial_layout_duas_colunas"),
+    ]
+
+    operations = [
+        migrations.RemoveField(
+            model_name="diariooficial",
+            name="layout_duas_colunas",
+        ),
+        migrations.AddField(
+            model_name="pagediariooficial",
+            name="layout_duas_colunas",
+            field=models.BooleanField(default=False),
+        ),
+    ]

diarios/models.py

@@ -0,0 +1,167 @@
+import os
+from urllib.parse import urlparse
+import requests
+from babel.dates import format_date
+from django.core.files.base import ContentFile
+from django.db import models, transaction
+from django.core.exceptions import ValidationError
+import fitz  # PyMuPDF
+from asgiref.sync import async_to_sync
+
+
+class TipoDiarioOficial(models.Model):
+    nome = models.CharField(max_length=100, unique=True)
+
+    def __str__(self):
+        return self.nome
+
+    class Meta:
+        verbose_name_plural = "Tipos de Diários Oficiais"
+
+
+class DiarioOficial(models.Model):
+    data = models.DateField()
+    arquivo = models.FileField(upload_to="diarios_oficiais/", blank=True, null=True)
+    tipo = models.ForeignKey(
+        TipoDiarioOficial,
+        blank=True,
+        null=True,
+        on_delete=models.SET_NULL,
+        related_name="diarios",
+    )
+    numero = models.CharField(max_length=20, unique=True)
+    link = models.URLField(blank=True, null=True, unique=True)
+
+    def save(self, *args, **kwargs):
+        updated = False
+        super().save(*args, **kwargs)
+
+        if self.link and not self.arquivo:
+            self._download_pdf_from_link()
+            updated = True
+
+        if self.arquivo and not self.paginas.exists():
+            self._extract_pdf_pages()
+            updated = True
+
+        if updated:
+            super().save(*args, **kwargs)
+
+    def clean(self):
+        super().clean()
+        if not self.arquivo and not self.link:
+            raise ValidationError("Informe um arquivo ou um link para o Diário.")
+
+    def _validar_link(self):
+        if not self.link.lower().endswith(".pdf"):
+            raise ValidationError("O link deve apontar para um arquivo PDF.")
+
+    def _download_pdf_from_link(self):
+        try:
+            response = requests.get(self.link)
+            response.raise_for_status()
+
+            parsed_url = urlparse(self.link)
+            file_name = os.path.basename(parsed_url.path) or f"diario_{self.numero}.pdf"
+
+            self.arquivo.save(file_name, ContentFile(response.content), save=True)
+        except requests.RequestException as e:
+            raise ValidationError(f"Não foi possível baixar o PDF: {e}")
+
+    def _extract_pdf_pages(self):
+        try:
+            # Salvar temporariamente o PDF para abrir com o PyMuPDF
+            with self.arquivo.open("rb") as pdf_file:
+                temp_pdf_path = f"/tmp/diario_{self.id}.pdf"
+                with open(temp_pdf_path, "wb") as temp_file:
+                    temp_file.write(pdf_file.read())
+
+            # Abrir e processar com fitz
+            doc = fitz.open(temp_pdf_path)
+            self._process_pdf_pages(doc)
+            doc.close()
+
+            # Remover arquivo temporário
+            os.remove(temp_pdf_path)
+
+        except Exception as pdf_error:
+            raise ValidationError(f"Não foi possível processar o PDF: {pdf_error}")
+
+    def _process_pdf_pages(self, doc):
+        with transaction.atomic():
+            self.paginas.all().delete()
+
+            for i, page in enumerate(doc):
+                try:
+                    blocks = page.get_text("blocks")
+                    # Ordenar os blocos por coordenadas (y, x) para manter a ordem de leitura
+                    blocks.sort(key=lambda b: (b[1], b[0]))
+                    page_text = ""
+                    for block in blocks:
+                        text = block[4].strip()
+                        if text:
+                            page_text += text + "\n"
+
+                    # Crucial: Remove NULL bytes from the extracted text
+                    # PostgreSQL text fields cannot contain NUL (0x00) bytes
+                    cleaned_text = page_text.strip().replace('\x00', '')
+
+                    if cleaned_text:
+                        PageDiarioOficial.objects.create(
+                            diario=self,
+                            numero=i + 1,
+                            conteudo=cleaned_text,
+                        )
+                    else:
+                        PageDiarioOficial.objects.create(
+                            diario=self,
+                            numero=i + 1,
+                            conteudo="[Conteúdo não extraído ou vazio]",
+                        )
+
+                except Exception as page_error:
+                    PageDiarioOficial.objects.create(
+                        diario=self,
+                        numero=i + 1,
+                        conteudo=f"[Erro na extração do texto: {str(page_error)}]",
+                    )
+                    print(f"Erro ao processar a página {i+1} no Diario ID {self.id}: {page_error}")
+
+    @property
+    def data_formatada(self):
+        return format_date(self.data, format="long", locale="pt_BR")
+
+    @property
+    def is_online(self):
+        return bool(self.link)
+
+    def __str__(self):
+        tipo_nome = self.tipo.nome if self.tipo else "Sem Tipo"
+        return f"Diário {tipo_nome} nº {self.numero}, {self.data_formatada}"
+
+    class Meta:
+        constraints = [models.UniqueConstraint(fields=["numero"], name="unique_numero")]
+        verbose_name_plural = "Diários Oficiais"
+
+
+class PageDiarioOficial(models.Model):
+    diario = models.ForeignKey(
+        DiarioOficial, on_delete=models.CASCADE, related_name="paginas"
+    )
+    layout_duas_colunas = models.BooleanField(default=False)
+    numero = models.PositiveIntegerField()
+    conteudo = models.TextField()
+
+    class Meta:
+        unique_together = ("diario", "numero")
+        verbose_name = "Página de Diário Oficial"
+        verbose_name_plural = "Páginas de Diários Oficiais"
+
+    def save(self, *args, **kwargs):
+        super().save(*args, **kwargs)
+        if self.diario:
+            self.diario.save()
+
+    def __str__(self):
+        return f"Página {self.numero} do Diário {self.diario.numero}"
+

diarios/schemas.py

@@ -0,0 +1,126 @@
+from ninja import Schema, ModelSchema, UploadedFile
+from typing import List, Optional
+from .models import TipoDiarioOficial
+from datetime import date
+
+
+class PaginaSchema(Schema):
+    """Schema que representa uma página de um Diário Oficial.
+
+    Attributes:
+        numero (int): Número ordinal da página no Diário (começa em 1).
+        conteudo (str): Texto extraído da página.
+    """
+
+    numero: int
+    conteudo: str
+
+
+class ResultadoSchema(Schema):
+    """Schema de resposta para um Diário Oficial em resultados de busca.
+
+    Attributes:
+        id (int): ID único do Diário no banco de dados.
+        numero (str): Número de identificação oficial do Diário (e.g., '123-A').
+        data (str): Data de publicação no formato ISO (YYYY-MM-DD).
+        link (str): URL para acessar o Diário Oficial online.
+        tipo (str): Nome do tipo de Diário (e.g., 'Municipal', 'Federal').
+        paginas (List[PaginaSchema]): Lista de páginas com conteúdo extraído.
+        score (Optional[float]): Relevância do resultado (0 a 1), se aplicável.
+    """
+
+    id: int
+    numero: str
+    data: str
+    link: str
+    tipo: str
+    paginas: List[PaginaSchema]
+    score: Optional[float] = None
+
+
+class BuscaDiariosResponseSchema(Schema):
+    """Schema de resposta para buscas paginadas em Diários Oficiais.
+
+    Attributes:
+        total (int): Total de resultados disponíveis (ignorando paginação).
+        resultados (List[ResultadoSchema]): Lista de Diários encontrados.
+        pagina (int): Número da página atual (começa em 1).
+        por_pagina (int): Quantidade de resultados por página.
+    """
+
+    total: int
+    resultados: List[ResultadoSchema]
+    pagina: int
+    por_pagina: int
+
+
+class SugestaoResponse(Schema):
+    """Schema para sugestões de correção de busca (e.g., 'Voc quis dizer...?').
+
+    Attributes:
+        sugestao (Optional[str]): Termo sugerido para refinar a busca.
+                          None se nenhuma sugestão for relevante.
+    """
+
+    sugestao: Optional[str]
+
+class TipoDiarioSchema(ModelSchema):
+    class Config:
+        model = TipoDiarioOficial
+        model_fields = ["id", "nome"]
+
+class DiarioOficialIn(Schema):
+    """Schema para criação de Diário Oficial"""
+    data: date
+    numero: str
+    tipo_id: Optional[int] = None
+    link: Optional[str] = None
+    arquivo: Optional[UploadedFile] = None  # Adicionando o campo de arquivo
+
+    class Config:
+        # Configuração adicional para o Swagger UI
+        json_schema_extra = {
+            "example": {
+                "data": "2023-12-01",
+                "numero": "1234/2023",
+            }
+        }
+
+class DiarioOficialOut(Schema):
+    """Schema para retorno de Diário Oficial (com detalhes completos)"""
+    id: int
+    data: str  # Será formatado como ISO (YYYY-MM-DD)
+    numero: str
+    link: Optional[str]
+    tipo: Optional[TipoDiarioSchema]
+    total_paginas: int
+    
+    @staticmethod
+    def resolve_data(obj):
+        return obj.data.isoformat()
+    
+    @staticmethod
+    def resolve_total_paginas(obj):
+        return obj.paginas.count()
+
+class DiarioOficialUpdate(Schema):
+    """Schema para atualização de Diário Oficial"""
+    data: Optional[date] = None
+    numero: Optional[str] = None
+    tipo_id: Optional[int] = None
+    link: Optional[str] = None
+
+class DiarioListagem(Schema):
+    """Schema simplificado para listagem de Diários"""
+    id: int
+    data: str
+    numero: str
+    tipo_nome: Optional[str]
+    
+    @staticmethod
+    def resolve_data(obj):
+        return obj.data.isoformat()
+    
+    @staticmethod
+    def resolve_tipo_nome(obj):
+        return obj.tipo.nome if obj.tipo else None

diarios/search_service.py

@@ -0,0 +1,848 @@
+import re
+from datetime import datetime
+from typing import Optional, Dict, Any, List
+from elasticsearch import Elasticsearch, AsyncElasticsearch
+from .schemas import BuscaDiariosResponseSchema, ResultadoSchema, PaginaSchema
+import unicodedata
+import asyncio
+from django.conf import settings
+
+
+async def is_fuzzy_appropriate(term: str) -> bool:
+    """
+    Determina se a fuzziness é apropriada para o termo de busca.
+
+    Args:
+        term: Termo de busca a ser avaliado
+
+    Returns:
+        bool: True se fuzziness é apropriada, False caso contrário
+    """
+    return not re.match(r"^\d+/\d+$", term.strip())
+
+
+async def parse_date(date_str: Optional[str]) -> Optional[str]:
+    """
+    Converte string de data para formato ISO para ElasticSearch.
+
+    Args:
+        date_str: String de data no formato YYYY-MM-DD
+
+    Returns:
+        Optional[str]: Data formatada ou None se inválida
+    """
+    if not date_str:
+        return None
+    try:
+        dt = datetime.strptime(date_str, "%Y-%m-%d")
+        return dt.strftime("%Y-%m-%d")
+    except ValueError:
+        print(f"Alerta: Formato de data inválido recebido: {date_str}")
+        return None
+
+
+async def buscar_diarios(
+    query: Optional[str] = None,
+    data_inicio: Optional[str] = None,
+    data_fim: Optional[str] = None,
+    tipo_diario: Optional[str] = None,
+    page: int = 1,
+    page_size: int = 10,
+) -> Dict[str, Any]:
+    """
+    Realiza busca nos diários oficiais com os parâmetros fornecidos.
+
+    Args:
+        query: Termo de busca
+        data_inicio: Data inicial no formato YYYY-MM-DD
+        data_fim: Data final no formato YYYY-MM-DD
+        tipo_diario: Tipo de diário a ser filtrado
+        page: Número da página de resultados
+        page_size: Quantidade de resultados por página
+
+    Returns:
+        Dict[str, Any]: Dicionário com resultados da busca
+    """
+    try:
+        es = AsyncElasticsearch(
+            "http://elasticsearch:9200",
+            request_timeout=30,
+            basic_auth=(
+                settings.ELASTICSEARCH_USER,
+                settings.ELASTICSEARCH_PASSWORD,
+            ),
+        )
+        if not await es.ping():
+            raise ConnectionError("Não foi possível conectar ao Elasticsearch")
+    except Exception as e:
+        print(f"Erro ao conectar com Elasticsearch: {e}")
+        return {"total": 0, "resultados": [], "pagina": page, "por_pagina": page_size}
+
+    es_body = {
+        "query": {"bool": {"must": [], "filter": []}},
+        "size": page_size,
+        "from": (page - 1) * page_size,
+        "_source": [
+            "numero",
+            "data",
+            "link",
+            "tipo",
+            "paginas.numero",
+            "paginas.conteudo",
+        ],
+    }
+
+    parsed_dt_inicio = await parse_date(data_inicio)
+    parsed_dt_fim = await parse_date(data_fim)
+    if parsed_dt_inicio or parsed_dt_fim:
+        date_range_filter = {}
+        if parsed_dt_inicio:
+            date_range_filter["gte"] = parsed_dt_inicio
+        if parsed_dt_fim:
+            date_range_filter["lte"] = parsed_dt_fim
+        es_body["query"]["bool"]["filter"].append(
+            {"range": {"data": date_range_filter}}
+        )
+
+    if tipo_diario:
+        es_body["query"]["bool"]["filter"].append({"term": {"tipo.nome": tipo_diario}})
+
+    if query:
+        aplicar_fuzziness = await is_fuzzy_appropriate(query)
+        text_query_bool = {
+            "bool": {
+                "should": [
+                    {
+                        "match_phrase": {
+                            "paginas.conteudo.search": {
+                                "query": query,
+                                "slop": 4,
+                                "boost": 5.0,
+                            }
+                        }
+                    },
+                    {
+                        "match": {
+                            "paginas.conteudo.search": {
+                                "query": query,
+                                "fuzziness": "AUTO",
+                                "operator": "and",
+                                "prefix_length": 3,
+                            }
+                        }
+                    },
+                ],
+                "minimum_should_match": "75%",
+            }
+        }
+
+        nested_query = {
+            "nested": {
+                "path": "paginas",
+                "query": text_query_bool,
+                "inner_hits": {
+                    "highlight": {
+                        "fields": {"paginas.conteudo.search": {}},
+                        "fragment_size": 500,
+                        "number_of_fragments": 1,
+                        "pre_tags": ["<mark>"],
+                        "post_tags": ["</mark>"],
+                    },
+                    "_source": ["paginas.numero"],
+                },
+            }
+        }
+
+        es_body["query"]["bool"]["must"].append(nested_query)
+    else:
+        es_body["query"]["bool"]["must"].append({"match_all": {}})
+
+    # Adicionar min_score
+    if query:
+        es_body["min_score"] = 2.5 * len(query.split())
+    try:
+        response = await es.search(index="diario_oficial", body=es_body)
+    except Exception as e:
+        print(f"Erro ao executar busca no Elasticsearch: {e}")
+        return {"total": 0, "resultados": [], "pagina": page, "por_pagina": page_size}
+    finally:
+        await es.close()
+
+    hits = response.get("hits", {})
+    total = hits.get("total", {}).get("value", 0)
+    resultados_formatados = []
+
+    for hit in hits.get("hits", []):
+        source = hit.get("_source", {})
+        resultado_data = {
+            "id": hit.get("_id"),
+            "numero": source.get("numero", ""),
+            "data": source.get("data"),
+            "link": source.get("link", ""),
+            "tipo": source.get("tipo", {}).get("nome", "Sem Tipo"),
+            "score": hit.get("_score"),
+            "paginas": [],
+        }
+
+        pagina_match = None
+        if query and "inner_hits" in hit and "paginas" in hit["inner_hits"]:
+            paginas_inner_hits = hit["inner_hits"]["paginas"]["hits"]["hits"]
+            if paginas_inner_hits:
+                inner_hit = paginas_inner_hits[0]
+                inner_source = inner_hit.get("_source", {})
+                page_num = inner_source.get("numero", "N/A")
+                highlights = inner_hit.get("highlight", {}).get(
+                    "paginas.conteudo.search", []
+                )
+                highlight_content = " ... ".join(highlights) if highlights else ""
+
+                if page_num != "N/A" and highlight_content:
+                    pagina_match = PaginaSchema(
+                        numero=page_num, conteudo=highlight_content
+                    )
+
+        if pagina_match:
+            resultado_data["paginas"].append(pagina_match)
+        elif not query and "paginas" in source and source["paginas"]:
+            primeira_pagina_source = source["paginas"][0]
+            conteudo_orig = primeira_pagina_source.get("conteudo", "")
+            resultado_data["paginas"].append(
+                PaginaSchema(
+                    numero=primeira_pagina_source.get("numero", 0),
+                    conteudo=conteudo_orig,
+                )
+            )
+
+        resultados_formatados.append(ResultadoSchema(**resultado_data))
+
+    return {
+        "total": total,
+        "resultados": resultados_formatados,
+        "pagina": page,
+        "por_pagina": page_size,
+    }
+
+
+async def remover_acentos(texto: str) -> str:
+    """
+    Remove acentos de uma string para comparações mais neutras.
+
+    Args:
+        texto: Texto a ser normalizado
+
+    Returns:
+        str: Texto sem acentos
+    """
+    return "".join(
+        c
+        for c in unicodedata.normalize("NFD", texto)
+        if unicodedata.category(c) != "Mn"
+    )
+
+
+async def processar_query(query: str) -> str:
+    """
+    Faz pré-processamento da query para separar termos como 'processonº404'.
+
+    Args:
+        query: Texto da consulta original
+
+    Returns:
+        str: Consulta processada
+    """
+    return re.sub(r"([a-zA-Z]+)(nº|n°|no)(\d+)", r"\1 \2 \3", query)
+
+
+async def montar_suggest_body(query_processada: str) -> dict:
+    """
+    Monta o corpo da sugestão para a requisição ao Elasticsearch.
+
+    Args:
+        query_processada: Query processada para sugestão
+
+    Returns:
+        dict: Corpo da requisição para suggest
+    """
+    return {
+        "suggest": {
+            "text": query_processada,
+            "correcao": {
+                "phrase": {
+                    "field": "paginas.conteudo.search",
+                    "size": 3,
+                    "gram_size": 2,
+                    "confidence": 0.8,
+                    "max_errors": 4,
+                    "highlight": {"pre_tag": "**", "post_tag": "**"},
+                    "collate": {
+                        "query": {
+                            "source": {
+                                "nested": {
+                                    "path": "paginas",
+                                    "query": {
+                                        "bool": {
+                                            "should": [
+                                                {
+                                                    "match_phrase": {
+                                                        "paginas.conteudo.search": {
+                                                            "query": "{{suggestion}}",
+                                                            "slop": 1,
+                                                        }
+                                                    }
+                                                }
+                                            ]
+                                        }
+                                    },
+                                }
+                            }
+                        },
+                        "params": {"field_name": "paginas.conteudo.search"},
+                        "prune": True,
+                    },
+                }
+            },
+        },
+        "size": 0,
+    }
+
+
+async def sugestao_termo(query: str) -> Optional[str]:
+    """
+    Oferece sugestões de correção para a query, verificando se a sugestão
+    realmente retorna resultados antes de apresentá-la ao usuário.
+
+    Args:
+        query: Texto da consulta original
+
+    Returns:
+        Optional[str]: Sugestão para a consulta ou None
+    """
+    es = await conectar_elasticsearch()
+    if not es:
+        return None
+
+    query_processada = await processar_query(query)
+    suggest_body = await montar_suggest_body(query_processada)
+
+    try:
+        response = await es.search(index="diario_oficial", body=suggest_body)
+        suggestions = response.get("suggest", {}).get("correcao", [])
+
+        for sug in suggestions:
+            for option in sug.get("options", []):
+                if option.get("collate_match", False):
+                    sugestao = option["text"]
+
+                    # Verifica se a sugestão é idêntica à query (ignorando acentos e case)
+                    if sugestao.lower() == query.lower():
+                        continue
+                    if await remover_acentos(sugestao.lower()) == await remover_acentos(
+                        query.lower()
+                    ):
+                        continue
+
+                    return sugestao
+
+        return None
+
+    except Exception as e:
+        print(f"Erro ao buscar sugestão: {e}")
+        return None
+    finally:
+        await es.close()
+
+
+async def conectar_elasticsearch() -> Optional[AsyncElasticsearch]:
+    """
+    Conecta ao Elasticsearch e retorna o cliente.
+
+    Returns:
+        Optional[AsyncElasticsearch]: Cliente Elasticsearch ou None se falhar
+    """
+    try:
+        es = AsyncElasticsearch(
+            "http://elasticsearch:9200",
+            request_timeout=30,
+            basic_auth=(
+                settings.ELASTICSEARCH_USER,
+                settings.ELASTICSEARCH_PASSWORD,
+            ),
+        )
+        if not await es.ping():
+            raise ConnectionError("Não foi possível conectar ao Elasticsearch")
+        return es
+    except Exception as e:
+        print(f"Erro ao conectar com Elasticsearch: {e}")
+        return None
+
+
+async def construir_ordenacao(ordenar_por: str) -> List[Dict[str, Any]]:
+    """
+    Constrói a cláusula de ordenação para a consulta.
+
+    Args:
+        ordenar_por: Critério de ordenação
+
+    Returns:
+        List[Dict[str, Any]]: Lista de ordenação para Elasticsearch
+    """
+    if ordenar_por == "data_asc":
+        return [{"data": {"order": "asc"}}]
+    elif ordenar_por == "data_desc":
+        return [{"data": {"order": "desc"}}]
+    else:  # relevancia
+        return ["_score"]
+
+
+async def preencher_numero_do_diario_com_zeros(numero_diario: str) -> str:
+    """
+    Preenche o número do diário com zeros à esquerda.
+
+    Args:
+        numero_diario: Número do diário
+
+    Returns:
+        str: Número formatado com zeros à esquerda
+    """
+    return numero_diario.zfill(4)
+
+
+async def construir_filtros(
+    data_inicio: Optional[str],
+    data_fim: Optional[str],
+    tipo_diario: Optional[str],
+    numero_diario: Optional[str],
+) -> List[Dict[str, Any]]:
+    """
+    Constrói os filtros de data, tipo e número do diário.
+
+    Args:
+        data_inicio: Data inicial no formato YYYY-MM-DD
+        data_fim: Data final no formato YYYY-MM-DD
+        tipo_diario: Tipo de diário a ser filtrado
+        numero_diario: Número do diário
+
+    Returns:
+        List[Dict[str, Any]]: Lista de filtros para Elasticsearch
+    """
+    filtros = []
+
+    parsed_dt_inicio = await parse_date(data_inicio)
+    parsed_dt_fim = await parse_date(data_fim)
+    if parsed_dt_inicio or parsed_dt_fim:
+        date_range = {}
+        if parsed_dt_inicio:
+            date_range["gte"] = parsed_dt_inicio
+        if parsed_dt_fim:
+            date_range["lte"] = parsed_dt_fim
+        filtros.append({"range": {"data": date_range}})
+
+    if tipo_diario:
+        filtros.append({"term": {"tipo.nome": tipo_diario}})
+
+    if numero_diario:
+        # numero_diario = await preencher_numero_do_diario_com_zeros(numero_diario)
+        filtros.append({"wildcard": {"numero": f"*{numero_diario}*"}})
+
+    return filtros
+
+
+async def construir_query_busca(
+    query: Optional[str], modo_busca: str
+) -> Dict[str, Any]:
+    """
+    Constrói a query de busca com base no termo e modo de busca.
+
+    Args:
+        query: Termo de busca
+        modo_busca: Modo de busca (exata ou qualquer)
+
+    Returns:
+        Dict[str, Any]: Query de busca para Elasticsearch
+    """
+    if not query:
+        return {
+            "nested": {
+                "path": "paginas",
+                "query": {"match_all": {}},
+                "inner_hits": {
+                    "_source": ["paginas.numero", "paginas.conteudo"],
+                    "size": 100,
+                },
+            }
+        }
+
+    should_queries = []
+
+    # Busca exata (boost maior)
+    should_queries.append(
+        {
+            "match_phrase": {
+                "paginas.conteudo.search": {"query": query, "slop": 3, "boost": 5.0}
+            }
+        }
+    )
+
+    # Busca mais leve (separando termos), se modo_busca permitir
+    if modo_busca == "qualquer":
+        should_queries.append(
+            {
+                "match": {
+                    "paginas.conteudo.search": {
+                        "query": query,
+                        "operator": "or",
+                        "fuzziness": "AUTO",
+                        "prefix_length": 3,
+                        "boost": 1.0,
+                    }
+                }
+            }
+        )
+
+    return {
+        "nested": {
+            "path": "paginas",
+            "query": {"bool": {"should": should_queries, "minimum_should_match": 1}},
+            "inner_hits": {
+                "highlight": {
+                    "fields": {"paginas.conteudo.search": {}},
+                    "fragment_size": 500,
+                    "number_of_fragments": 1,
+                    "pre_tags": ["<mark>"],
+                    "post_tags": ["</mark>"],
+                },
+                "_source": ["paginas.numero"],
+                "size": 100,  # Aumentar para retornar mais páginas correspondentes
+            },
+        }
+    }
+
+
+async def construir_request_body(
+    query: Optional[str],
+    modo_busca: str,
+    ordenar_por: str,
+    data_inicio: Optional[str],
+    data_fim: Optional[str],
+    tipo_diario: Optional[str],
+    numero_diario: Optional[str],
+    page: int,
+    page_size: int,
+) -> Dict[str, Any]:
+    """
+    Constrói o corpo da requisição para o Elasticsearch.
+
+    Args:
+        query: Termo de busca
+        modo_busca: Modo de busca (exata ou qualquer)
+        ordenar_por: Critério de ordenação
+        data_inicio: Data inicial
+        data_fim: Data final
+        tipo_diario: Tipo de diário
+        numero_diario: Número do diário
+        page: Número da página
+        page_size: Tamanho da página
+
+    Returns:
+        Dict[str, Any]: Corpo da requisição para Elasticsearch
+    """
+    es_body = {
+        "query": {"bool": {"must": [], "filter": []}},
+        "size": page_size,
+        "from": (page - 1) * page_size,
+        "_source": [
+            "numero",
+            "data",
+            "link",
+            "tipo",
+            "paginas.numero",
+            "paginas.conteudo",
+        ],
+    }
+
+    # Adicionar ordenação
+    es_body["sort"] = await construir_ordenacao(ordenar_por)
+
+    # Adicionar filtros
+    es_body["query"]["bool"]["filter"] = await construir_filtros(
+        data_inicio, data_fim, tipo_diario, numero_diario
+    )
+
+    # Adicionar query principal
+    query_principal = await construir_query_busca(query, modo_busca)
+    es_body["query"]["bool"]["must"].append(query_principal)
+
+    return es_body
+
+
+async def processar_paginas_encontradas(
+    hit: Dict[str, Any], query: Optional[str]
+) -> List[PaginaSchema]:
+    """
+    Processa as páginas encontradas em um hit, retornando todas as correspondências.
+
+    Args:
+        hit: Item de resultado do Elasticsearch
+        query: Termo de busca original
+
+    Returns:
+        List[PaginaSchema]: Lista de páginas encontradas
+    """
+    if not query:
+        return []
+
+    paginas = []
+    source = hit.get("_source", {})
+
+    #if not query and "paginas" in source:
+    #    for pagina in source["paginas"]:
+    #        paginas.append(
+    #            PaginaSchema(
+    #                numero=pagina.get("numero", 0), conteudo=pagina.get("conteudo", "")
+    #            )
+    #        )
+    # Se temos uma query e há inner_hits, processamos todas as páginas correspondentes
+    if query and "inner_hits" in hit and "paginas" in hit["inner_hits"]:
+        paginas_inner_hits = hit["inner_hits"]["paginas"]["hits"]["hits"]
+
+        # Processar todas as páginas encontradas, não apenas a primeira
+        for inner_hit in paginas_inner_hits:
+            inner_source = inner_hit.get("_source", {})
+            page_num = inner_source.get("numero", "N/A")
+            highlights = inner_hit.get("highlight", {}).get(
+                "paginas.conteudo.search", []
+            )
+            highlight_content = " ... ".join(highlights) if highlights else ""
+
+            if page_num != "N/A" and highlight_content:
+                paginas.append(
+                    PaginaSchema(numero=page_num, conteudo=highlight_content)
+                )
+
+    # Se não há query ou não encontramos páginas nos inner_hits, usamos a primeira página do documento
+    if not paginas and "paginas" in source and source["paginas"]:
+        primeira_pagina_source = source["paginas"][0]
+        conteudo_orig = primeira_pagina_source.get("conteudo", "")
+        paginas.append(
+            PaginaSchema(
+                numero=primeira_pagina_source.get("numero", 0),
+                conteudo=conteudo_orig,
+            )
+        )
+
+    return paginas
+
+
+async def processar_resultados(
+    response: Dict[str, Any], query: Optional[str], page: int, page_size: int
+) -> Dict[str, Any]:
+    """
+    Processa os resultados da busca no Elasticsearch.
+
+    Args:
+        response: Resposta do Elasticsearch
+        query: Termo de busca original
+        page: Número da página atual
+        page_size: Tamanho da página
+
+    Returns:
+        Dict[str, Any]: Resultados processados
+    """
+    hits = response.get("hits", {})
+    total = hits.get("total", {}).get("value", 0)
+    resultados_formatados = []
+
+    for hit in hits.get("hits", []):
+        source = hit.get("_source", {})
+        resultado_data = {
+            "id": hit.get("_id"),
+            "numero": source.get("numero", ""),
+            "data": source.get("data"),
+            "link": source.get("link", ""),
+            "tipo": source.get("tipo", {}).get("nome", "Sem Tipo"),
+            "score": hit.get("_score"),
+            "paginas": [],
+        }
+
+        # Processar todas as páginas encontradas
+        resultado_data["paginas"] = await processar_paginas_encontradas(hit, query)
+
+        resultados_formatados.append(ResultadoSchema(**resultado_data))
+
+    return {
+        "total": total,
+        "resultados": resultados_formatados,
+        "pagina": page,
+        "por_pagina": page_size,
+    }
+
+
+async def buscar_diarios_simples(
+    query: Optional[str] = None,
+    numero_diario: Optional[str] = None,
+    modo_busca: str = "exata",  # "exata" ou "qualquer"
+    ordenar_por: str = "data_asc",  # "relevancia" ou "data"
+    data_inicio: Optional[str] = None,
+    data_fim: Optional[str] = None,
+    tipo_diario: Optional[str] = None,
+    page: int = 1,
+    page_size: int = 10,
+) -> Dict[str, Any]:
+    """
+    Função principal para buscar diários oficiais.
+
+    Args:
+        query: Termo de busca
+        numero_diario: Número do diário oficial
+        modo_busca: Modo de busca (exata ou qualquer)
+        ordenar_por: Critério de ordenação
+        data_inicio: Data inicial
+        data_fim: Data final
+        tipo_diario: Tipo de diário
+        page: Número da página
+        page_size: Tamanho da página
+
+    Returns:
+        Dict[str, Any]: Dicionário com os resultados da busca
+    """
+    # Conectar ao Elasticsearch
+    es = await conectar_elasticsearch()
+    if not es:
+        return {"total": 0, "resultados": [], "pagina": page, "por_pagina": page_size}
+
+    # Construir o corpo da requisição
+    es_body = await construir_request_body(
+        query,
+        modo_busca,
+        ordenar_por,
+        data_inicio,
+        data_fim,
+        tipo_diario,
+        numero_diario,
+        page,
+        page_size,
+    )
+
+    # Executar a busca
+    try:
+        response = await es.search(index="diario_oficial", body=es_body)
+    except Exception as e:
+        print(f"Erro ao executar busca no Elasticsearch: {e}")
+        return {"total": 0, "resultados": [], "pagina": page, "por_pagina": page_size}
+    finally:
+        await es.close()
+
+    # Processar e retornar os resultados
+    return await processar_resultados(response, query, page, page_size)
+
+
+async def list_diarios(
+    es_client: AsyncElasticsearch,
+    page: int = 1,
+    page_size: int = 10,
+    data_inicio: Optional[str] = None,
+    data_fim: Optional[str] = None,
+    tipo_diario: Optional[str] = None,
+    numero_diario: Optional[str] = None,
+    ordenar_por: str = "data_desc"
+) -> Dict[str, any]:
+    """
+    Lista diários com paginação e filtros opcionais
+
+    Args:
+        es_client: Cliente do Elasticsearch
+        page: Número da página
+        page_size: Itens por página
+        data_inicio: Data inicial (YYYY-MM-DD)
+        data_fim: Data final (YYYY-MM-DD)
+        tipo_diario: Filtro por tipo de diário
+        numero_diario: Filtro por número do diário
+        ordenar_por: Campo para ordenação (data_desc, data_asc)
+
+    Returns:
+        Dict com total de itens e lista de diários
+    """
+    # Construir query de filtros
+    filters = []
+
+    # Filtro por data
+    if data_inicio or data_fim:
+        date_range = {}
+        if data_inicio:
+            try:
+                datetime.strptime(data_inicio, "%Y-%m-%d")
+                date_range["gte"] = data_inicio
+            except ValueError:
+                pass
+        if data_fim:
+            try:
+                datetime.strptime(data_fim, "%Y-%m-%d")
+                date_range["lte"] = data_fim
+            except ValueError:
+                pass
+        if date_range:
+            filters.append({"range": {"data": date_range}})
+
+    # Filtro por tipo
+    if tipo_diario:
+        filters.append({"term": {"tipo.nome": tipo_diario}})
+
+    # Filtro por número
+    if numero_diario:
+        filters.append({"wildcard": {"numero": f"*{numero_diario}*"}})
+
+    # Construir query completa
+    query = {
+        "bool": {
+            "must": [{"match_all": {}}],
+            "filter": filters
+        }
+    }
+
+    # Definir ordenação
+    sort = [{"data": {"order": "asc" if ordenar_por == "data_asc" else "desc"}}]
+
+    # Executar consulta
+    try:
+        response = await es_client.search(
+            index="diario_oficial",
+            body={
+                "query": query,
+                "sort": sort,
+                "from": (page - 1) * page_size,
+                "size": page_size,
+                "_source": ["numero", "data", "tipo", "link"]
+            }
+        )
+
+        hits = response["hits"]["hits"]
+        total = response["hits"]["total"]["value"]
+
+        # Processar resultados
+        diarios = []
+        for hit in hits:
+            source = hit["_source"]
+            diarios.append(BuscaDiariosResponseSchema(
+                id=hit["_id"],
+                numero=source.get("numero"),
+                data=source.get("data"),
+                tipo=source.get("tipo", {}).get("nome"),
+                link=source.get("link")
+            ))
+
+        return {
+            "total": total,
+            "page": page,
+            "page_size": page_size,
+            "results": diarios
+        }
+
+    except Exception as e:
+        print(f"Erro ao listar diários: {e}")
+        return {
+            "total": 0,
+            "page": page,
+            "page_size": page_size,
+            "results": []
+        }
+

diarios/tests/factories.py

@@ -0,0 +1,31 @@
+from factory.django import DjangoModelFactory
+from factory import Faker, SubFactory, LazyAttribute, Sequence
+import datetime
+from diarios.models import PageDiarioOficial, DiarioOficial, TipoDiarioOficial
+
+
+class TipoDiarioOficialFactory(DjangoModelFactory):
+    nome = Faker("word")
+
+    class Meta:
+        model = TipoDiarioOficial
+        django_get_or_create = ["nome"]
+
+class DiarioOficialFactory(DjangoModelFactory):
+    data = Faker("date_this_decade")
+    numero = Sequence(lambda n: f"{n:04d}-DO")  # ex: 0001-DO, 0002-DO
+    tipo = SubFactory(TipoDiarioOficialFactory)
+    link = None
+
+    class Meta:
+        model = DiarioOficial
+
+class PageDiarioOficialFactory(DjangoModelFactory):
+    diario = SubFactory(DiarioOficialFactory)
+    numero = Sequence(lambda n: n + 1)
+    layout_duas_colunas = False
+    conteudo = Faker("text", max_nb_chars=3000)
+
+    class Meta:
+        model = PageDiarioOficial
+        django_get_or_create = ["diario", "numero"]

diarios/tests/test_models.py

@@ -0,0 +1,34 @@
+from django.test import TestCase
+from diarios.models import TipoDiarioOficial, DiarioOficial, PageDiarioOficial
+from .factories import (
+    TipoDiarioOficialFactory,
+    DiarioOficialFactory,
+    PageDiarioOficialFactory,
+)
+
+
+class TipoDiarioOficialFactoryTest(TestCase):
+    def test_create_tipo_diario_oficial(self):
+        tipo = TipoDiarioOficialFactory()
+        self.assertIsInstance(tipo, TipoDiarioOficial)
+        self.assertIsNotNone(tipo.pk)
+        self.assertTrue(tipo.nome)
+
+
+class DiarioOficialFactoryTest(TestCase):
+    def test_create_diario_oficial(self):
+        diario = DiarioOficialFactory()
+        self.assertIsInstance(diario, DiarioOficial)
+        self.assertIsNotNone(diario.pk)
+        self.assertIsNotNone(diario.numero)
+        self.assertIsInstance(diario.tipo, TipoDiarioOficial)
+
+
+class PageDiarioOficialFactoryTest(TestCase):
+    def test_create_page_diario_oficial(self):
+        page = PageDiarioOficialFactory()
+        self.assertIsInstance(page, PageDiarioOficial)
+        self.assertIsNotNone(page.pk)
+        self.assertIsInstance(page.diario, DiarioOficial)
+        self.assertIsInstance(page.conteudo, str)
+        self.assertGreater(len(page.conteudo), 0)

diarios/urls.py

@@ -0,0 +1,6 @@
+from django.urls import path
+from . import views
+
+urlpatterns = [
+        path("", views.home, name='home')
+]

diarios/views.py

@@ -0,0 +1,113 @@
+from ninja import Router, File, Form
+from ninja.files import UploadedFile
+from typing import Optional
+from django.http import HttpRequest, HttpResponse
+from .search_service import (
+    buscar_diarios,
+    sugestao_termo,
+    buscar_diarios_simples,
+)
+from .schemas import BuscaDiariosResponseSchema, SugestaoResponse, DiarioOficialIn, DiarioOficialOut
+from django.shortcuts import render
+
+router = Router(tags=["Diários Oficiais"])
+
+async def home(request):
+    return render(request, 'diarios/index.html')
+
+@router.get(
+    "/sugestao",
+    response=SugestaoResponse,
+    summary="Sugestão de correção para termo de busca",
+)
+async def sugestao_busca(request: HttpRequest, q: str) -> SugestaoResponse:
+    """
+    Sugere correção para o termo buscado, se necessário.
+
+    Args:
+        request (HttpRequest): Requisição HTTP.
+        q (str): Termo original digitado pelo usuário.
+
+    Returns:
+        SugestaoResponse: Termo corrigido.
+    """
+    sugestao = await sugestao_termo(q)
+    return {"sugestao": sugestao}
+
+
+@router.get(
+    "/busca",
+    response=BuscaDiariosResponseSchema,
+    summary="Busca simplificada com modos e ordenação",
+)
+async def busca_diarios_oficiais_simples(
+    request: HttpRequest,
+    q: Optional[str] = None,
+    numero_diario: Optional[str] = None,
+    data_inicio: Optional[str] = None,
+    data_fim: Optional[str] = None,
+    tipo: Optional[str] = None,
+    ordenar_por: str = "relevancia",  # "relevancia", "data_asc", "data_desc"
+    modo_busca: str = "exata",  # "exata" ou "qualquer"
+    page: int = 1,
+    page_size: int = 10,
+) -> BuscaDiariosResponseSchema:
+    """
+    Busca com modo de correspondência, ordenação e número do diário.
+
+    Args:
+        request (HttpRequest): Requisição HTTP.
+        q (Optional[str]): Termo de busca.
+        numero_diario (Optional[str]): Número exato do diário (ex: 1234/2024).
+        data_inicio (Optional[str]): Data inicial (YYYY-MM-DD).
+        data_fim (Optional[str]): Data final (YYYY-MM-DD).
+        tipo (Optional[str]): Tipo exato do diário.
+        ordenar_por (str): "relevancia", "data_asc" ou "data_desc".
+        modo_busca (str): "exata" ou "qualquer".
+        page (int): Página atual (mínimo: 1).
+        page_size (int): Itens por página (mínimo: 1, máximo: 50).
+
+    Returns:
+        BuscaDiariosResponseSchema: Resultado paginado da busca.
+    """
+    page_size = min(max(page_size, 1), 50)
+    page = max(page, 1)
+
+    resultado = await buscar_diarios_simples(
+        query=q,
+        numero_diario=numero_diario,
+        data_inicio=data_inicio,
+        data_fim=data_fim,
+        tipo_diario=tipo,
+        ordenar_por=ordenar_por,
+        modo_busca=modo_busca,
+        page=page,
+        page_size=page_size,
+    )
+    return resultado
+
+@router.post("/", response=DiarioOficialOut, summary="Criar novo diário oficial")
+def criar_diario(
+    request: HttpRequest,
+    # Usamos Form para os dados normais e File para o upload
+    payload: DiarioOficialIn = Form(...),
+    arquivo: UploadedFile = File(None)
+):
+    """
+    Cria um novo diário oficial.
+    
+    Observações:
+    - Aceita tanto upload de arquivo PDF quanto link para o diário
+    - Se ambos (arquivo e link) forem fornecidos, o arquivo terá prioridade
+    - O arquivo deve ser um PDF válido
+    """
+    # Prioriza o arquivo se ambos existirem
+    arquivo_final = arquivo if arquivo else payload.arquivo
+    
+    return DiarioOficialService.criar_diario(
+        data=payload.data,
+        numero=payload.numero,
+        tipo_id=payload.tipo_id,
+        arquivo=arquivo_final,
+        link=payload.link
+    )

diarios_oficiais_alems/__init__.py

@@ -0,0 +1,5 @@
+__version__ = "0.1.0"
+__version_info__ = tuple(
+    int(num) if num.isdigit() else num
+    for num in __version__.replace("-", ".", 1).split(".")
+)

diarios_oficiais_alems/conftest.py

@@ -0,0 +1,14 @@
+import pytest
+
+from diarios_oficiais_alems.users.models import User
+from diarios_oficiais_alems.users.tests.factories import UserFactory
+
+
+@pytest.fixture(autouse=True)
+def _media_storage(settings, tmpdir) -> None:
+    settings.MEDIA_ROOT = tmpdir.strpath
+
+
+@pytest.fixture
+def user(db) -> User:
+    return UserFactory()

diarios_oficiais_alems/contrib/__init__.py

@@ -0,0 +1,5 @@
+"""
+To understand why this file is here, please read:
+
+https://cookiecutter-django.readthedocs.io/en/latest/5-help/faq.html#why-is-there-a-django-contrib-sites-directory-in-cookiecutter-django
+"""

diarios_oficiais_alems/contrib/sites/__init__.py

@@ -0,0 +1,5 @@
+"""
+To understand why this file is here, please read:
+
+https://cookiecutter-django.readthedocs.io/en/latest/5-help/faq.html#why-is-there-a-django-contrib-sites-directory-in-cookiecutter-django
+"""

diarios_oficiais_alems/contrib/sites/migrations/0001_initial.py

@@ -0,0 +1,43 @@
+import django.contrib.sites.models
+from django.contrib.sites.models import _simple_domain_name_validator
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = []
+
+    operations = [
+        migrations.CreateModel(
+            name="Site",
+            fields=[
+                (
+                    "id",
+                    models.AutoField(
+                        verbose_name="ID",
+                        serialize=False,
+                        auto_created=True,
+                        primary_key=True,
+                    ),
+                ),
+                (
+                    "domain",
+                    models.CharField(
+                        max_length=100,
+                        verbose_name="domain name",
+                        validators=[_simple_domain_name_validator],
+                    ),
+                ),
+                ("name", models.CharField(max_length=50, verbose_name="display name")),
+            ],
+            options={
+                "ordering": ("domain",),
+                "db_table": "django_site",
+                "verbose_name": "site",
+                "verbose_name_plural": "sites",
+            },
+            bases=(models.Model,),
+            managers=[("objects", django.contrib.sites.models.SiteManager())],
+        ),
+    ]

diarios_oficiais_alems/contrib/sites/migrations/0002_alter_domain_unique.py

@@ -0,0 +1,21 @@
+import django.contrib.sites.models
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [("sites", "0001_initial")]
+
+    operations = [
+        migrations.AlterField(
+            model_name="site",
+            name="domain",
+            field=models.CharField(
+                max_length=100,
+                unique=True,
+                validators=[django.contrib.sites.models._simple_domain_name_validator],
+                verbose_name="domain name",
+            ),
+        )
+    ]

diarios_oficiais_alems/contrib/sites/migrations/0003_set_site_domain_and_name.py

@@ -0,0 +1,64 @@
+"""
+To understand why this file is here, please read:
+
+https://cookiecutter-django.readthedocs.io/en/latest/5-help/faq.html#why-is-there-a-django-contrib-sites-directory-in-cookiecutter-django
+"""
+
+from django.conf import settings
+from django.db import migrations
+
+
+def _update_or_create_site_with_sequence(site_model, connection, domain, name):
+    """Update or create the site with default ID and keep the DB sequence in sync."""
+    site, created = site_model.objects.update_or_create(
+        id=settings.SITE_ID,
+        defaults={
+            "domain": domain,
+            "name": name,
+        },
+    )
+    if created:
+        # We provided the ID explicitly when creating the Site entry, therefore the DB
+        # sequence to auto-generate them wasn't used and is now out of sync. If we
+        # don't do anything, we'll get a unique constraint violation the next time a
+        # site is created.
+        # To avoid this, we need to manually update DB sequence and make sure it's
+        # greater than the maximum value.
+        max_id = site_model.objects.order_by("-id").first().id
+        with connection.cursor() as cursor:
+            cursor.execute("SELECT last_value from django_site_id_seq")
+            (current_id,) = cursor.fetchone()
+            if current_id <= max_id:
+                cursor.execute(
+                    "alter sequence django_site_id_seq restart with %s",
+                    [max_id + 1],
+                )
+
+
+def update_site_forward(apps, schema_editor):
+    """Set site domain and name."""
+    Site = apps.get_model("sites", "Site")
+    _update_or_create_site_with_sequence(
+        Site,
+        schema_editor.connection,
+        "example.com",
+        "Diários Oficiais ALEMS",
+    )
+
+
+def update_site_backward(apps, schema_editor):
+    """Revert site domain and name to default."""
+    Site = apps.get_model("sites", "Site")
+    _update_or_create_site_with_sequence(
+        Site,
+        schema_editor.connection,
+        "example.com",
+        "example.com",
+    )
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [("sites", "0002_alter_domain_unique")]
+
+    operations = [migrations.RunPython(update_site_forward, update_site_backward)]

diarios_oficiais_alems/contrib/sites/migrations/0004_alter_options_ordering_domain.py

@@ -0,0 +1,21 @@
+# Generated by Django 3.1.7 on 2021-02-04 14:49
+
+from django.db import migrations
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("sites", "0003_set_site_domain_and_name"),
+    ]
+
+    operations = [
+        migrations.AlterModelOptions(
+            name="site",
+            options={
+                "ordering": ["domain"],
+                "verbose_name": "site",
+                "verbose_name_plural": "sites",
+            },
+        ),
+    ]

diarios_oficiais_alems/contrib/sites/migrations/__init__.py

@@ -0,0 +1,5 @@
+"""
+To understand why this file is here, please read:
+
+https://cookiecutter-django.readthedocs.io/en/latest/5-help/faq.html#why-is-there-a-django-contrib-sites-directory-in-cookiecutter-django
+"""

diarios_oficiais_alems/static/css/project.css

@@ -0,0 +1,13 @@
+/* These styles are generated from project.scss. */
+
+.alert-debug {
+  color: black;
+  background-color: white;
+  border-color: #d6e9c6;
+}
+
+.alert-error {
+  color: #b94a48;
+  background-color: #f2dede;
+  border-color: #eed3d7;
+}

diarios_oficiais_alems/static/css/style.css

@@ -0,0 +1,76 @@
+.bg-light-gradient {
+    background: linear-gradient(to right, #f8f9fa, #e9ecef);
+}
+.search-card {
+    border-radius: 15px;
+    box-shadow: 0 4px 20px rgba(0, 0, 0, 0.05);
+    border: none;
+}
+.result-card {
+    transition: transform 0.2s, box-shadow 0.2s;
+    border-radius: 10px;
+}
+.result-card:hover {
+    transform: translateY(-3px);
+    box-shadow: 0 6px 12px rgba(0, 0, 0, 0.1);
+}
+.page-item.active .page-link {
+    background-color: #0d6efd;
+    border-color: #0d6efd;
+}
+.date-picker {
+    background-color: #fff;
+    border: 1px solid #ced4da;
+    border-radius: 4px;
+    padding: 0.375rem 0.75rem;
+}
+.best-match {
+    border-left: 4px solid #0d6efd;
+    background-color: rgba(13, 110, 253, 0.05);
+}
+.page-content {
+    max-height: 400px;
+    overflow-y: auto;
+    font-size: 0.9rem;
+}
+.accordion-button:not(.collapsed) {
+    background-color: rgba(13, 110, 253, 0.1);
+    color: #0d6efd;
+}
+.accordion-button:focus {
+    box-shadow: none;
+}
+mark {
+    background-color: #fff3cd;
+    padding: 0.1em 0.2em;
+    border-radius: 2px;
+}
+.page-badge {
+    background-color: #6c757d;
+    color: white;
+    padding: 2px 8px;
+    border-radius: 4px;
+    font-size: 0.75rem;
+}
+.match-score {
+    color: #0d6efd;
+    font-size: 0.85rem;
+    font-weight: 500;
+}
+.btn-sort {
+    padding: 0.375rem 0.75rem;
+    font-size: 0.875rem;
+}
+.btn-sort.active {
+    background-color: #0d6efd;
+    color: white;
+}
+.search-options {
+    display: flex;
+    gap: 10px;
+}
+@media (max-width: 768px) {
+    .search-options {
+        flex-direction: column;
+    }
+}

diarios_oficiais_alems/static/js/config.js

@@ -0,0 +1 @@
+const API_BASE_URL = "http://109.199.98.226";

diarios_oficiais_alems/static/js/project.js

@@ -0,0 +1 @@
+/* Project specific Javascript goes here. */

diarios_oficiais_alems/static/js/script.js

@@ -0,0 +1,242 @@
+document.addEventListener('alpine:init', () => {
+    Alpine.data('searchApp', () => ({
+        searchParams: {
+            q: '',
+            numero_diario: '',
+            data_inicio: '',
+            data_fim: '',
+            modo_busca: 'exata',
+            ordenar_por: 'data_asc',
+            page: 1,
+            page_size: 10
+        },
+        searchResults: null,
+        isLoading: false,
+        hasSearched: false,
+        error: null,
+        showAdvanced: false,
+        expandedContents: {},
+        suggestion: null,
+        ultimoTermoBuscado: '',
+
+        get shouldShowSuggestion() {
+            if (!this.suggestion || !this.searchParams.q) return false;
+
+            // Função para remover acentos e converter para minúsculas
+            const normalize = (text) => {
+                return text.toLowerCase()
+                    .normalize('NFD')
+                    .replace("/", " ")
+                    .replace(/[^a-z0-9\s]/g, " ") // Substitui todos os outros símbolos por espaço
+                    .replace(/[\u0300-\u036f]/g, '');
+            };
+
+            const normalizedQuery = normalize(this.searchParams.q);
+            const normalizedSuggestion = normalize(this.suggestion);
+
+            // Só mostra a sugestão se for diferente do termo buscado (ignorando acentos e caixa)
+            return normalizedQuery !== normalizedSuggestion;
+        },
+
+        // Usa a sugestão como novo termo de busca
+        usesuggestion() {
+            this.searchParams.q = this.suggestion;
+            this.searchParams.page = 1;
+            this.performSearch();
+        },
+
+        // Verifica se um diário tem uma melhor correspondência
+        hasBestMatch(diario) {
+            return diario.paginas && diario.paginas.length > 0;
+        },
+
+        // Muda a ordenação e faz uma nova busca
+        changeOrder(order) {
+            if (this.searchParams.ordenar_por !== order) {
+                this.searchParams.ordenar_por = order;
+                this.searchParams.page = 1; // Volta para a primeira página
+                this.performSearch();
+            }
+        },
+
+        // Obter sugestão da API
+        async getSuggestion(query) {
+            if (!query) return null;
+
+            try {
+                const url = new URL('http://192.168.235.234/api/v1/diarios/sugestao');
+                url.searchParams.append('q', query);
+
+                const response = await fetch(url);
+
+                if (response.ok) {
+                    const data = await response.json();
+                    return data.sugestao;
+                }
+                return null;
+            } catch (error) {
+                console.error('Erro ao buscar sugestão:', error);
+                return null;
+            }
+        },
+
+        get totalPages() {
+            if (!this.searchResults) return 0;
+            return Math.ceil(this.searchResults.total / this.searchResults.por_pagina);
+        },
+
+        get paginationArray() {
+            const pages = [];
+            const currentPage = this.searchParams.page;
+            const totalPages = this.totalPages;
+
+            // Função auxiliar para adicionar páginas
+            const addPage = (page) => {
+                if (page >= 1 && page <= totalPages && !pages.includes(page)) {
+                    pages.push(page);
+                }
+            };
+
+            // Sempre mostrar primeira página, página atual, última página
+            // e 1-2 páginas adjacentes à página atual
+            addPage(1);
+            addPage(currentPage - 2);
+            addPage(currentPage - 1);
+            addPage(currentPage);
+            addPage(currentPage + 1);
+            addPage(currentPage + 2);
+            addPage(totalPages);
+
+            // Ordenar e adicionar separadores
+            const result = pages.sort((a, b) => a - b);
+
+            return result;
+        },
+
+        // Retorna a melhor página (maior score) de um diário
+        getBestPage(paginas) {
+            if (!paginas || paginas.length === 0) return null;
+
+            // Ordena as páginas por score (se disponível) ou pelo número da página se não houver score
+            const sortedPages = [...paginas].sort((a, b) => {
+                if (a.score === undefined || b.score === undefined) return 0;
+                if (a.score === undefined) return 1;
+                if (b.score === undefined) return -1;
+                return b.score - a.score;
+            });
+
+            return sortedPages[0];
+        },
+
+        // Retorna todas as páginas exceto a melhor
+        getOtherPages(paginas) {
+            if (!paginas || paginas.length <= 1) return [];
+
+            const bestPage = this.getBestPage(paginas);
+            if (!bestPage) return paginas;
+
+            return paginas.filter(p => p.numero !== bestPage.numero)
+                .sort((a, b) => a.numero - b.numero); // Ordena por número da página
+        },
+
+        // Controla a exibição do conteúdo completo de uma página
+        toggleFullContent(diarioIndex, paginaNumero) {
+            const key = `${diarioIndex}-${paginaNumero}`;
+            this.expandedContents[key] = !this.expandedContents[key];
+        },
+
+        // Verifica se um conteúdo está expandido
+        isFullContentVisible(diarioIndex, paginaNumero) {
+            const key = `${diarioIndex}-${paginaNumero}`;
+            return this.expandedContents[key] === true;
+        },
+
+        async performSearch() {
+            this.isLoading = true;
+            this.error = null;
+            this.hasSearched = true;
+            this.expandedContents = {}; // Resetar estados expandidos
+            this.suggestion = null; // Resetar a sugestão
+
+            try {
+                let suggestionPromise = null;
+                if (this.searchParams.q) {
+                    suggestionPromise = this.getSuggestion(this.searchParams.q);
+                }
+                if (this.searchParams.q !== this.ultimoTermoBuscado) {
+                    this.searchParams.page = 1;
+                }
+                this.ultimoTermoBuscado = this.searchParams.q;
+                // Usando agora o endpoint busca
+                const url = new URL('http://192.168.235.234/api/v1/diarios/busca');
+
+                // Adicionar parâmetros à URL
+                Object.entries(this.searchParams).forEach(([key, value]) => {
+                    if (value !== '' && value !== null) {
+                        url.searchParams.append(key, value);
+                    }
+                });
+
+                const response = await fetch(url);
+
+                if (!response.ok) {
+                    const errorData = await response.json().catch(() => null);
+                    throw new Error(errorData?.message || `Erro HTTP: ${response.status}`);
+                }
+
+                this.searchResults = await response.json();
+
+                // Processar os resultados para garantir que as páginas tenham score
+                if (this.searchResults && this.searchResults.resultados) {
+                    this.searchResults.resultados.forEach(diario => {
+                        if (diario.paginas) {
+                            // Atribuir scores padrão se não existirem
+                            diario.paginas.forEach((pagina, index) => {
+                                if (pagina.score === undefined || pagina.score === null) {
+                                    pagina.score = diario.paginas.length - index; // Score inversamente proporcional ao índice
+                                }
+                            });
+                        }
+                    });
+                }
+
+                if (suggestionPromise) {
+                    this.suggestion = await suggestionPromise;
+                }
+            } catch (error) {
+                console.error('Erro na busca:', error);
+                this.error = `Erro ao buscar diários: ${error.message}`;
+            } finally {
+                this.isLoading = false;
+            }
+        },
+
+        formatDate(dateString) {
+            const options = { day: '2-digit', month: '2-digit', year: 'numeric' };
+            return new Date(dateString + 'T00:00:00').toLocaleDateString('pt-BR', options);
+        },
+        goToPage(page) {
+            if (page < 1 || page > this.totalPages) return;
+            this.searchParams.page = page;
+            this.performSearch();
+            window.scrollTo({ top: 0, behavior: 'smooth' });
+        },
+
+        resetSearch() {
+            this.searchParams = {
+                q: '',
+                numero_diario: '',
+                data_inicio: '',
+                data_fim: '',
+                modo_busca: 'exata',
+                ordenar_por: 'relevancia',
+                page: 1,
+                page_size: 10
+            };
+            this.searchResults = null;
+            this.hasSearched = false;
+            this.error = null;
+            this.expandedContents = {};
+        }
+    }));
+});

diarios_oficiais_alems/templates/403.html

@@ -0,0 +1,13 @@
+{% extends "base.html" %}
+
+{% block title %}Forbidden (403){% endblock title %}
+{% block content %}
+  <h1>Forbidden (403)</h1>
+  <p>
+    {% if exception %}
+      {{ exception }}
+    {% else %}
+      You're not allowed to access this page.
+    {% endif %}
+  </p>
+{% endblock content %}

diarios_oficiais_alems/templates/403_csrf.html

@@ -0,0 +1,13 @@
+{% extends "base.html" %}
+
+{% block title %}Forbidden (403){% endblock title %}
+{% block content %}
+  <h1>Forbidden (403)</h1>
+  <p>
+    {% if exception %}
+      {{ exception }}
+    {% else %}
+      You're not allowed to access this page.
+    {% endif %}
+  </p>
+{% endblock content %}

diarios_oficiais_alems/templates/404.html

@@ -0,0 +1,13 @@
+{% extends "base.html" %}
+
+{% block title %}Page not found{% endblock title %}
+{% block content %}
+  <h1>Page not found</h1>
+  <p>
+    {% if exception %}
+      {{ exception }}
+    {% else %}
+      This is not the page you were looking for.
+    {% endif %}
+  </p>
+{% endblock content %}

diarios_oficiais_alems/templates/500.html

@@ -0,0 +1,10 @@
+{% extends "base.html" %}
+
+{% block title %}Server Error{% endblock title %}
+{% block content %}
+  <h1>Ooops!!! 500</h1>
+  <h3>Looks like something went wrong!</h3>
+  <p>
+    We track these errors automatically, but if the problem persists feel free to contact us. In the meantime, try refreshing.
+  </p>
+{% endblock content %}

diarios_oficiais_alems/templates/account/base_manage_password.html

@@ -0,0 +1,11 @@
+{% extends "account/base_manage.html" %}
+
+{% block main %}
+  <div class="card">
+    <div class="card-body">
+      {% block content %}
+      {% endblock content %}
+    </div>
+  </div>
+{% endblock main %}
+

diarios_oficiais_alems/templates/allauth/elements/alert.html

@@ -0,0 +1,7 @@
+{% load i18n %}
+{% load allauth %}
+
+<div class="alert alert-error">
+  {% slot message %}
+{% endslot %}
+</div>

diarios_oficiais_alems/templates/allauth/elements/badge.html

@@ -0,0 +1,6 @@
+{% load allauth %}
+
+<span class="badge {% if 'success' in attrs.tags %}bg-success{% endif %} {% if 'warning' in attrs.tags %}bg-warning{% endif %} {% if 'secondary' in attrs.tags %}bg-secondary{% endif %} {% if 'danger' in attrs.tags %}bg-danger{% endif %} {% if 'primary' in attrs.tags %}bg-primary{% endif %}">
+  {% slot %}
+{% endslot %}
+</span>

diarios_oficiais_alems/templates/allauth/elements/button.html

@@ -0,0 +1,20 @@
+{% load allauth %}
+
+{% comment %} djlint:off {% endcomment %}
+<{% if attrs.href %}a href="{{ attrs.href }}"{% else %}button{% endif %}
+                      {% if attrs.form %}form="{{ attrs.form }}"{% endif %}
+                      {% if attrs.id %}id="{{ attrs.id }}"{% endif %}
+                      {% if attrs.name %}name="{{ attrs.name }}"{% endif %}
+                      {% if attrs.type %}type="{{ attrs.type }}"{% endif %}
+                      class="btn
+{% if 'success' in attrs.tags %}btn-success
+{% elif 'warning' in attrs.tags %}btn-warning
+{% elif 'secondary' in attrs.tags %}btn-secondary
+{% elif 'danger' in attrs.tags %}btn-danger
+{% elif 'primary' in attrs.tags %}btn-primary
+{% else %}btn-primary
+{% endif %}"
+>
+  {% slot %}
+  {% endslot %}
+  </{% if attrs.href %}a{% else %}button{% endif %}>

diarios_oficiais_alems/templates/allauth/elements/field.html

@@ -0,0 +1,66 @@
+{% load allauth %}
+{% load crispy_forms_tags %}
+
+{% if attrs.type == "textarea" %}
+  <div class="row mb-3">
+    <div class="col-sm-10">
+      <label for="{{ attrs.id }}">
+        {% slot label %}
+      {% endslot %}
+    </label>
+  </div>
+  <textarea {% if attrs.required %}required{% endif %}
+            {% if attrs.rows %}rows="{{ attrs.rows }}"{% endif %}
+            {% if attrs.disabled %}disabled{% endif %}
+            {% if attrs.readonly %}readonly{% endif %}
+            {% if attrs.checked %}checked{% endif %}
+            {% if attrs.name %}name="{{ attrs.name }}"{% endif %}
+            {% if attrs.id %}id="{{ attrs.id }}"{% endif %}
+            {% if attrs.placeholder %}placeholder="{{ attrs.placeholder }}"{% endif %}
+            class="form-control">{% slot value %}{% endslot %}</textarea>
+</div>
+{% elif attrs.type == "radio" %}
+<div class="row mb-3">
+  <div class="col-sm-10">
+    <div class="form-check">
+      <input {% if attrs.required %}required{% endif %}
+             {% if attrs.disabled %}disabled{% endif %}
+             {% if attrs.readonly %}readonly{% endif %}
+             {% if attrs.checked %}checked{% endif %}
+             {% if attrs.name %}name="{{ attrs.name }}"{% endif %}
+             {% if attrs.id %}id="{{ attrs.id }}"{% endif %}
+             {% if attrs.placeholder %}placeholder="{{ attrs.placeholder }}"{% endif %}
+             {% if attrs.autocomplete %}autocomplete="{{ attrs.autocomplete }}"{% endif %}
+             value="{{ attrs.value|default_if_none:"" }}"
+             type="{{ attrs.type }}" />
+      <label class="form-check-label" for="{{ attrs.id }}">
+        {% slot label %}
+      {% endslot %}
+    </label>
+  </div>
+</div>
+</div>
+{% else %}
+<div class="col-sm-10">
+  <label for="{{ attrs.id }}">
+    {% slot label %}
+  {% endslot %}
+</label>
+</div>
+<div class="col-sm-10">
+  <input {% if attrs.required %}required{% endif %}
+         {% if attrs.disabled %}disabled{% endif %}
+         {% if attrs.readonly %}readonly{% endif %}
+         {% if attrs.checked %}checked{% endif %}
+         {% if attrs.name %}name="{{ attrs.name }}"{% endif %}
+         {% if attrs.id %}id="{{ attrs.id }}"{% endif %}
+         {% if attrs.placeholder %}placeholder="{{ attrs.placeholder }}"{% endif %}
+         {% if attrs.autocomplete %}autocomplete="{{ attrs.autocomplete }}"{% endif %}
+         value="{{ attrs.value|default_if_none:"" }}"
+         type="{{ attrs.type }}"
+         class="form-control" />
+</div>
+{% endif %}
+{% if slots.help_text %}
+  <div class="form-text">{% slot help_text %}{% endslot %}</div>
+{% endif %}