feat: added initial setup of project with working databasepdf

.gitignore

@@ -0,0 +1,15 @@
+# Dependency directories
+node_modules/
+venv/
+
+# Environment variables
+.env
+
+# Build output
+build/
+dist/
+
+# Misc
+.DS_Store
+__pycache__/
+*.pyc

backend/app.py

@@ -0,0 +1,65 @@
+from flask import Flask, request, jsonify
+from flask_cors import CORS
+from flask_sqlalchemy import SQLAlchemy
+from flask_migrate import Migrate
+from PyPDF2 import PdfReader
+import re
+from dotenv import load_dotenv
+load_dotenv()
+
+app = Flask(__name__)
+CORS(app)
+app.config['SQLALCHEMY_DATABASE_URI'] = 'postgresql://postgres:heslo@localhost/hackathon'
+
+db = SQLAlchemy(app)
+migrate = Migrate(app, db)
+
+class PdfText(db.Model):
+    id = db.Column(db.Integer, primary_key=True)
+    text = db.Column(db.Text)
+    filename = db.Column(db.String(255))
+
+    def __init__(self, text, filename):
+        self.text = text
+        self.filename = filename
+
+@app.route('/upload_pdf', methods=['POST'])
+def upload_pdf():
+    uploaded_file = request.files.get('file')
+    if uploaded_file and uploaded_file.filename.endswith('.pdf'):
+        pdf_reader = PdfReader(uploaded_file.stream)
+        text = ''
+        for page in pdf_reader.pages:
+            text += page.extract_text() or ''
+
+        text = re.sub(r'\s+', ' ', text).strip()
+        new_pdf_text = PdfText(text, uploaded_file.filename)
+        db.session.add(new_pdf_text)
+        db.session.commit()
+
+        return jsonify({"message": "PDF uploaded and text extracted."}), 201
+    else:
+        return jsonify({"error": "Invalid file format."}), 400
+
+@app.route('/pdf_texts', methods=['GET'])
+def get_pdf_texts():
+    pdf_texts = PdfText.query.all()
+    output = [{'id': text.id, 'text': text.text, 'filename': text.filename} for text in pdf_texts]
+    return jsonify(output)
+
+@app.route('/delete_pdf_text/<int:pdf_text_id>', methods=['DELETE'])
+def delete_pdf_text(pdf_text_id):
+    pdf_text = PdfText.query.get(pdf_text_id)
+    if pdf_text:
+        db.session.delete(pdf_text)
+        db.session.commit()
+        return jsonify({"message": "PDF Text deleted."}), 200
+    else:
+        return jsonify({"message": "PDF Text not found"}), 404
+
+def init_db():
+    db.create_all()
+
+if __name__ == '__main__':
+    init_db()
+    app.run(debug=True)

backend/migrations/README

@@ -0,0 +1 @@
+Single-database configuration for Flask.

backend/migrations/alembic.ini

@@ -0,0 +1,50 @@
+# A generic, single database configuration.
+
+[alembic]
+# template used to generate migration files
+# file_template = %%(rev)s_%%(slug)s
+
+# set to 'true' to run the environment during
+# the 'revision' command, regardless of autogenerate
+# revision_environment = false
+
+
+# Logging configuration
+[loggers]
+keys = root,sqlalchemy,alembic,flask_migrate
+
+[handlers]
+keys = console
+
+[formatters]
+keys = generic
+
+[logger_root]
+level = WARN
+handlers = console
+qualname =
+
+[logger_sqlalchemy]
+level = WARN
+handlers =
+qualname = sqlalchemy.engine
+
+[logger_alembic]
+level = INFO
+handlers =
+qualname = alembic
+
+[logger_flask_migrate]
+level = INFO
+handlers =
+qualname = flask_migrate
+
+[handler_console]
+class = StreamHandler
+args = (sys.stderr,)
+level = NOTSET
+formatter = generic
+
+[formatter_generic]
+format = %(levelname)-5.5s [%(name)s] %(message)s
+datefmt = %H:%M:%S

backend/migrations/env.py

@@ -0,0 +1,113 @@
+import logging
+from logging.config import fileConfig
+
+from flask import current_app
+
+from alembic import context
+
+# this is the Alembic Config object, which provides
+# access to the values within the .ini file in use.
+config = context.config
+
+# Interpret the config file for Python logging.
+# This line sets up loggers basically.
+fileConfig(config.config_file_name)
+logger = logging.getLogger('alembic.env')
+
+
+def get_engine():
+    try:
+        # this works with Flask-SQLAlchemy<3 and Alchemical
+        return current_app.extensions['migrate'].db.get_engine()
+    except (TypeError, AttributeError):
+        # this works with Flask-SQLAlchemy>=3
+        return current_app.extensions['migrate'].db.engine
+
+
+def get_engine_url():
+    try:
+        return get_engine().url.render_as_string(hide_password=False).replace(
+            '%', '%%')
+    except AttributeError:
+        return str(get_engine().url).replace('%', '%%')
+
+
+# add your model's MetaData object here
+# for 'autogenerate' support
+# from myapp import mymodel
+# target_metadata = mymodel.Base.metadata
+config.set_main_option('sqlalchemy.url', get_engine_url())
+target_db = current_app.extensions['migrate'].db
+
+# other values from the config, defined by the needs of env.py,
+# can be acquired:
+# my_important_option = config.get_main_option("my_important_option")
+# ... etc.
+
+
+def get_metadata():
+    if hasattr(target_db, 'metadatas'):
+        return target_db.metadatas[None]
+    return target_db.metadata
+
+
+def run_migrations_offline():
+    """Run migrations in 'offline' mode.
+
+    This configures the context with just a URL
+    and not an Engine, though an Engine is acceptable
+    here as well.  By skipping the Engine creation
+    we don't even need a DBAPI to be available.
+
+    Calls to context.execute() here emit the given string to the
+    script output.
+
+    """
+    url = config.get_main_option("sqlalchemy.url")
+    context.configure(
+        url=url, target_metadata=get_metadata(), literal_binds=True
+    )
+
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+def run_migrations_online():
+    """Run migrations in 'online' mode.
+
+    In this scenario we need to create an Engine
+    and associate a connection with the context.
+
+    """
+
+    # this callback is used to prevent an auto-migration from being generated
+    # when there are no changes to the schema
+    # reference: http://alembic.zzzcomputing.com/en/latest/cookbook.html
+    def process_revision_directives(context, revision, directives):
+        if getattr(config.cmd_opts, 'autogenerate', False):
+            script = directives[0]
+            if script.upgrade_ops.is_empty():
+                directives[:] = []
+                logger.info('No changes in schema detected.')
+
+    conf_args = current_app.extensions['migrate'].configure_args
+    if conf_args.get("process_revision_directives") is None:
+        conf_args["process_revision_directives"] = process_revision_directives
+
+    connectable = get_engine()
+
+    with connectable.connect() as connection:
+        context.configure(
+            connection=connection,
+            target_metadata=get_metadata(),
+            **conf_args
+        )
+
+        with context.begin_transaction():
+            context.run_migrations()
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

backend/migrations/script.py.mako

@@ -0,0 +1,24 @@
+"""${message}
+
+Revision ID: ${up_revision}
+Revises: ${down_revision | comma,n}
+Create Date: ${create_date}
+
+"""
+from alembic import op
+import sqlalchemy as sa
+${imports if imports else ""}
+
+# revision identifiers, used by Alembic.
+revision = ${repr(up_revision)}
+down_revision = ${repr(down_revision)}
+branch_labels = ${repr(branch_labels)}
+depends_on = ${repr(depends_on)}
+
+
+def upgrade():
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade():
+    ${downgrades if downgrades else "pass"}

backend/migrations/versions/c4b843d1ef4c_initial_migration.py

@@ -0,0 +1,33 @@
+"""Initial migration
+
+Revision ID: c4b843d1ef4c
+Revises: 
+Create Date: 2023-11-25 13:45:06.008866
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = 'c4b843d1ef4c'
+down_revision = None
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.create_table('pdf_text',
+    sa.Column('id', sa.Integer(), nullable=False),
+    sa.Column('text', sa.Text(), nullable=True),
+    sa.Column('filename', sa.String(length=255), nullable=True),
+    sa.PrimaryKeyConstraint('id')
+    )
+    # ### end Alembic commands ###
+
+
+def downgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_table('pdf_text')
+    # ### end Alembic commands ###

backend/requirements.txt

@@ -0,0 +1,21 @@
+alembic==1.12.1
+blinker==1.7.0
+click==8.1.7
+Flask==3.0.0
+Flask-Cors==4.0.0
+Flask-Migrate==4.0.5
+Flask-SQLAlchemy==3.1.1
+greenlet==3.0.1
+itsdangerous==2.1.2
+Jinja2==3.1.2
+joblib==1.3.2
+Mako==1.3.0
+MarkupSafe==2.1.3
+nltk==3.8.1
+psycopg2-binary==2.9.9
+PyPDF2==3.0.1
+regex==2023.10.3
+SQLAlchemy==2.0.23
+tqdm==4.66.1
+typing_extensions==4.8.0
+Werkzeug==3.0.1