Merge branch 'feat/postgresql-storage' into 'dev'

✨ added database storage and broker

See merge request paulo/paulo-backend!1

.env.sample

@@ -3,3 +3,8 @@ SERVER_HOST=http://localhost
 BACKEND_CORS_ORIGINS='["http://localhost"]'
 
 PROJECT_NAME=PAULO
+
+POSTGRES_SERVER=localhost
+POSTGRES_USER=paulo
+POSTGRES_PASSWORD=paulo
+POSTGRES_DB=paulo

.gitignore

@@ -3,7 +3,6 @@ venv/
 __pycache__/
 .vscode/
 
-data.json
-data/
+data*.json
 
 .env

Dockerfile

+FROM python:3.9
+
+WORKDIR /backend
+
+COPY . /backend
+
+RUN pip3 install poetry
+
+RUN poetry config virtualenvs.create false
+
+RUN poetry install --no-dev
+
+RUN pip install uvicorn
+
+CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0"]

alembic.ini

+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts
+script_location = alembic
+
+# template used to generate migration files
+# file_template = %%(rev)s_%%(slug)s
+
+# sys.path path, will be prepended to sys.path if present.
+# defaults to the current working directory.
+prepend_sys_path = .
+
+# timezone to use when rendering the date
+# within the migration file as well as the filename.
+# string value is passed to dateutil.tz.gettz()
+# leave blank for localtime
+# timezone =
+
+# max length of characters to apply to the
+# "slug" field
+# truncate_slug_length = 40
+
+# set to 'true' to run the environment during
+# the 'revision' command, regardless of autogenerate
+# revision_environment = false
+
+# set to 'true' to allow .pyc and .pyo files without
+# a source .py file to be detected as revisions in the
+# versions/ directory
+# sourceless = false
+
+# version location specification; this defaults
+# to alembic/versions.  When using multiple version
+# directories, initial revisions must be specified with --version-path
+# version_locations = %(here)s/bar %(here)s/bat alembic/versions
+
+# the output encoding used when revision files
+# are written from script.py.mako
+# output_encoding = utf-8
+
+sqlalchemy.url = driver://user:pass@localhost/dbname
+
+
+[post_write_hooks]
+# post_write_hooks defines scripts or Python functions that are run
+# on newly generated revision scripts.  See the documentation for further
+# detail and examples
+
+# format using "black" - use the console_scripts runner, against the "black" entrypoint
+# hooks=black
+# black.type=console_scripts
+# black.entrypoint=black
+# black.options=-l 79
+
+# Logging configuration
+[loggers]
+keys = root,sqlalchemy,alembic
+
+[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
+
+[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

alembic/README

+Generic single-database configuration.
\ No newline at end of file

alembic/env.py

+import os
+
+from alembic import context
+from sqlalchemy import engine_from_config, pool
+from logging.config import fileConfig
+from dotenv import load_dotenv
+
+load_dotenv()
+
+# 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)
+
+# add your model's MetaData object here
+# for 'autogenerate' support
+# from myapp import mymodel
+# target_metadata = mymodel.Base.metadata
+# target_metadata = None
+
+from app.database import Base
+from app.data.storage import models
+
+target_metadata = Base.metadata
+
+
+# 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_url():
+    user = os.getenv("POSTGRES_USER", "postgres")
+    password = os.getenv("POSTGRES_PASSWORD", "")
+    server = os.getenv("POSTGRES_SERVER", "db")
+    db = os.getenv("POSTGRES_DB", "app")
+    return f"postgresql://{user}:{password}@{server}/{db}"
+
+
+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 = get_url()
+    context.configure(
+        url=url, target_metadata=target_metadata, literal_binds=True, compare_type=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.
+    """
+    configuration = config.get_section(config.config_ini_section)
+    configuration["sqlalchemy.url"] = get_url()
+    connectable = engine_from_config(
+        configuration, prefix="sqlalchemy.", poolclass=pool.NullPool,
+    )
+
+    with connectable.connect() as connection:
+        context.configure(
+            connection=connection, target_metadata=target_metadata, compare_type=True
+        )
+
+        with context.begin_transaction():
+            context.run_migrations()
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

alembic/script.py.mako

+"""${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"}

alembic/versions/1ce4e17617c1_init.py

+"""init
+
+Revision ID: 1ce4e17617c1
+Revises: 
+Create Date: 2022-01-11 00:31:35.355535
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = '1ce4e17617c1'
+down_revision = None
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.create_table('appointment',
+    sa.Column('id', sa.Integer(), autoincrement=True, nullable=False),
+    sa.Column('start_time', sa.DateTime(), nullable=False),
+    sa.Column('end_time', sa.DateTime(), nullable=False),
+    sa.Column('room', sa.VARCHAR(length=64), nullable=False),
+    sa.Column('instructors', sa.VARCHAR(length=128), nullable=False),
+    sa.PrimaryKeyConstraint('id')
+    )
+    op.create_table('semester',
+    sa.Column('id', sa.Integer(), autoincrement=True, nullable=False),
+    sa.Column('name', sa.VARCHAR(length=32), nullable=False),
+    sa.PrimaryKeyConstraint('id')
+    )
+    op.create_table('course',
+    sa.Column('id', sa.Integer(), autoincrement=True, nullable=False),
+    sa.Column('cid', sa.VARCHAR(length=32), nullable=False),
+    sa.Column('name', sa.VARCHAR(length=64), nullable=False),
+    sa.Column('description', sa.VARCHAR(length=255), nullable=True),
+    sa.Column('semester_id', sa.Integer(), nullable=True),
+    sa.ForeignKeyConstraint(['semester_id'], ['semester.id'], ),
+    sa.PrimaryKeyConstraint('id')
+    )
+    op.create_table('course_appointment',
+    sa.Column('course_id', sa.Integer(), nullable=False),
+    sa.Column('appointment_id', sa.Integer(), nullable=False),
+    sa.ForeignKeyConstraint(['appointment_id'], ['appointment.id'], ),
+    sa.ForeignKeyConstraint(['course_id'], ['course.id'], ),
+    sa.PrimaryKeyConstraint('course_id', 'appointment_id')
+    )
+    op.create_table('small_group',
+    sa.Column('id', sa.Integer(), autoincrement=True, nullable=False),
+    sa.Column('name', sa.VARCHAR(length=64), nullable=False),
+    sa.Column('course_id', sa.Integer(), nullable=True),
+    sa.ForeignKeyConstraint(['course_id'], ['course.id'], ),
+    sa.PrimaryKeyConstraint('id')
+    )
+    op.create_table('small_group_appointment',
+    sa.Column('small_group_id', sa.Integer(), nullable=False),
+    sa.Column('appointment_id', sa.Integer(), nullable=False),
+    sa.ForeignKeyConstraint(['appointment_id'], ['appointment.id'], ),
+    sa.ForeignKeyConstraint(['small_group_id'], ['small_group.id'], ),
+    sa.PrimaryKeyConstraint('small_group_id', 'appointment_id')
+    )
+    # ### end Alembic commands ###
+
+
+def downgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_table('small_group_appointment')
+    op.drop_table('small_group')
+    op.drop_table('course_appointment')
+    op.drop_table('course')
+    op.drop_table('semester')
+    op.drop_table('appointment')
+    # ### end Alembic commands ###

alembic/versions/278aca658ba6_search_index.py

+"""search index
+
+Revision ID: 278aca658ba6
+Revises: 1ce4e17617c1
+Create Date: 2022-01-12 10:41:34.182181
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = '278aca658ba6'
+down_revision = '1ce4e17617c1'
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    pass
+    # ### end Alembic commands ###
+
+
+def downgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    pass
+    # ### end Alembic commands ###

alembic/versions/bed1aefe514f_overflow_fix.py

+"""overflow fix
+
+Revision ID: bed1aefe514f
+Revises: 278aca658ba6
+Create Date: 2022-01-26 11:52:48.248018
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = 'bed1aefe514f'
+down_revision = '278aca658ba6'
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.alter_column('appointment', 'room',
+               existing_type=sa.VARCHAR(length=64),
+               type_=sa.VARCHAR(length=128),
+               existing_nullable=False)
+    op.alter_column('appointment', 'instructors',
+               existing_type=sa.VARCHAR(length=128),
+               type_=sa.VARCHAR(length=256),
+               existing_nullable=False)
+    op.alter_column('course', 'name',
+               existing_type=sa.VARCHAR(length=64),
+               type_=sa.VARCHAR(length=256),
+               existing_nullable=False)
+    op.alter_column('small_group', 'name',
+               existing_type=sa.VARCHAR(length=64),
+               type_=sa.VARCHAR(length=128),
+               existing_nullable=False)
+    # ### end Alembic commands ###
+
+
+def downgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.alter_column('small_group', 'name',
+               existing_type=sa.VARCHAR(length=128),
+               type_=sa.VARCHAR(length=64),
+               existing_nullable=False)
+    op.alter_column('course', 'name',
+               existing_type=sa.VARCHAR(length=256),
+               type_=sa.VARCHAR(length=64),
+               existing_nullable=False)
+    op.alter_column('appointment', 'instructors',
+               existing_type=sa.VARCHAR(length=256),
+               type_=sa.VARCHAR(length=128),
+               existing_nullable=False)
+    op.alter_column('appointment', 'room',
+               existing_type=sa.VARCHAR(length=128),
+               type_=sa.VARCHAR(length=64),
+               existing_nullable=False)
+    # ### end Alembic commands ###

app/cli.py

@@ -8,6 +8,7 @@ app = typer.Typer()
 
 app.add_typer(cli.scraper_command, name="scraper")
 app.add_typer(cli.courses_command, name="courses")
+app.add_typer(cli.db_command, name="db")
 
 if __name__ == "__main__":
     app()

app/cli/__init__.py

 from .scraper import scraper_command
 from .courses import courses_command
+from .db import db_command

app/cli/courses.py

-import asyncio
-
 import typer
-from app import scraper
+
 from app.data.brokers import ListBroker
 from app.data.storage import PlainJSONStorage
 
@@ -9,14 +7,14 @@ courses_command = typer.Typer()
 
 
 @courses_command.command()
-def find(name: str):
+def find(semester: str, name: str):
     pjs = PlainJSONStorage()
     pjs.init_data()
     broker = ListBroker(pjs)
-    courses = broker.find_courses_by_name(name)
+    courses = broker.find_courses_by_name(semester, name)
 
     for c in courses:
         print("--------------")
         print("name:", c.name)
-        print("id:", c.id)
+        print("id:", c.cid)
     print("--------------")

app/cli/db.py

+import asyncio
+
+import typer
+
+from app import scraper, schemas
+from app.database import get_session
+from app.processing import mapper
+
+db_command = typer.Typer()
+
+
+@db_command.command()
+def scrapesite(semester: str, site_path: str):
+    session = next(get_session())
+
+    courses = asyncio.run(scraper.find_and_parse_courses(site_path))
+    s = schemas.Semester(name=semester, courses=courses)
+    db_s = mapper.map_semester(s)
+
+    session.add(db_s)
+    session.commit()
+
+    print("Success!")

app/cli/scraper.py

 import asyncio
 
 import typer
+
+import schemas
 from app import scraper
 from app.data.storage import PlainJSONStorage
 
@@ -25,11 +27,14 @@ def catalogue(
 def courses(url: str = None, interactive: bool = typer.Option(True, "--no-interactive"),
             verbose: bool = typer.Option(False, "--verbose", "-v")):
     if not url:
-        site_path = list(scraper.parse_semesters("https://paul.uni-paderborn.de/scripts"
+        scrape_result = scraper.parse_semesters("https://paul.uni-paderborn.de/scripts"
                                                  "/mgrqispi.dll?APPNAME=CampusNet&PRGNAME=EXTERNALPAGES"
-                                                 "&ARGUMENTS=-N000000000000001,-N000442,-Avvz").values())[0]
+                                                 "&ARGUMENTS=-N000000000000001,-N000442,-Avvz")
+        semester_name = list(scrape_result.keys())[0]
+        site_path = scrape_result[semester_name]
     else:
         site_path = url.replace("https://paul.uni-paderborn.de", "")
+        semester_name = "Custom"
 
     course_list = scraper.parse_courses_on_site(site_path)
     if interactive:
@@ -56,5 +61,5 @@ def courses(url: str = None, interactive: bool = typer.Option(True, "--no-intera
     if verbose:
         print(data)
 
-    PlainJSONStorage.save_data(data)
+    PlainJSONStorage.save_data([schemas.Semester(name=semester_name, courses=data)])
     print("Saved to plain JSON storage.")

app/config/__init__.py

 from .api import api_settings
+from .database import get_database_settings

app/config/api.py

@@ -21,6 +21,8 @@ class APISettings(BaseSettings):
     
     PROJECT_NAME: str = 'PAULO'
 
+    BROKER: str = 'database'
+    
     class Config:
         case_sensitive = True
         env_file = '.env'

app/config/database.py

+from typing import Optional, Dict, Any
+
+from pydantic import BaseSettings, validator, PostgresDsn
+from pydantic.tools import lru_cache
+
+
+class DatabaseSettings(BaseSettings):
+    POSTGRES_SERVER: str
+    POSTGRES_USER: str
+    POSTGRES_PASSWORD: str
+    POSTGRES_DB: str
+    SQLALCHEMY_DATABASE_URI: Optional[str] = None
+
+    @validator("SQLALCHEMY_DATABASE_URI", pre=True)
+    def assemble_db_connection(cls, v: Optional[str], values: Dict[str, Any]) -> Any:
+        if isinstance(v, str):
+            return v
+        return PostgresDsn.build(
+            scheme="postgresql",
+            user=values.get("POSTGRES_USER"),
+            password=values.get("POSTGRES_PASSWORD"),
+            host=values.get("POSTGRES_SERVER"),
+            path=f"/{values.get('POSTGRES_DB') or ''}",
+        )
+
+    class Config:
+        env_file = ".env"
+        env_file_encoding = 'utf-8'
+
+
+@lru_cache
+def get_database_settings() -> DatabaseSettings:
+    return DatabaseSettings()

app/data/brokers/__init__.py

-from .broker import Broker
 from .list import ListBroker
+from .database import DatabaseBroker
+from .broker import Broker