db

alembic.ini

@@ -0,0 +1,118 @@
+# A generic, single database configuration.
+
+[dotenv]
+dotenv_path = .env
+
+[alembic]
+# path to migration scripts
+script_location = migrations
+
+# template used to generate migration file names; The default value is %%(rev)s_%%(slug)s
+# Uncomment the line below if you want the files to be prepended with date and time
+# see https://alembic.sqlalchemy.org/en/latest/tutorial.html#editing-the-ini-file
+# for all available tokens
+# file_template = %%(year)d_%%(month).2d_%%(day).2d_%%(hour).2d%%(minute).2d-%%(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.
+# If specified, requires the python>=3.9 or backports.zoneinfo library.
+# Any required deps can installed by adding `alembic[tz]` to the pip requirements
+# string value is passed to ZoneInfo()
+# 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 migrations/versions.  When using multiple version
+# directories, initial revisions must be specified with --version-path.
+# The path separator used here should be the separator specified by "version_path_separator" below.
+# version_locations = %(here)s/bar:%(here)s/bat:migrations/versions
+
+# version path separator; As mentioned above, this is the character used to split
+# version_locations. The default within new alembic.ini files is "os", which uses os.pathsep.
+# If this key is omitted entirely, it falls back to the legacy behavior of splitting on spaces and/or commas.
+# Valid values for version_path_separator are:
+#
+# version_path_separator = :
+# version_path_separator = ;
+# version_path_separator = space
+version_path_separator = os  # Use os.pathsep. Default configuration used for new projects.
+
+# set to 'true' to search source files recursively
+# in each "version_locations" directory
+# new in Alembic version 1.10
+# recursive_version_locations = false
+
+# 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 REVISION_SCRIPT_FILENAME
+
+# lint with attempts to fix using "ruff" - use the exec runner, execute a binary
+# hooks = ruff
+# ruff.type = exec
+# ruff.executable = %(here)s/.venv/bin/ruff
+# ruff.options = --fix REVISION_SCRIPT_FILENAME
+
+# 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

db/__init__.py

@@ -0,0 +1,4 @@
+from db.base import Base
+
+from db.attachment import Attachment
+from db.meme import Meme

db/attachment.py

@@ -0,0 +1,15 @@
+from sqlalchemy import create_engine, Column, Integer, String, JSON, Uuid
+
+from db.base import Base
+
+# Define a model with a JSON column
+class Attachment(Base):
+    __tablename__ = 'attachments'
+
+    id = Column(Uuid, primary_key=True)
+    msg_id = Column(Integer, nullable=False, index=True)
+    attributes = Column(JSON, nullable=False)
+    vision = Column(JSON, nullable=False)
+    message = Column(JSON, nullable=False)
+    guild = Column(JSON, nullable=False)
+    channel = Column(JSON, nullable=False)

db/base.py

@@ -0,0 +1,3 @@
+from sqlalchemy.ext.declarative import declarative_base
+
+Base = declarative_base()

db/meme.py

@@ -0,0 +1,12 @@
+from sqlalchemy import Column, Integer, String, JSON, Uuid
+
+from db.base import Base
+
+# Define a model with a JSON column
+class Meme(Base):
+    __tablename__ = 'memes'
+
+    id = Column(Uuid, primary_key=True)
+    url = Column(String, nullable=False)
+    text = Column(String, nullable=False)
+    tags = Column(JSON, nullable=False)

db/migrate.py

@@ -0,0 +1,16 @@
+from sqlalchemy import create_engine, Column, Integer, String, Engine
+from alembic.config import Config
+from alembic import command
+from dotenv import dotenv_values
+
+# Function to perform the database migration
+def migrate_db(engine: Engine, db_url):
+    # Configure Alembic
+    alembic_cfg = Config()
+    alembic_cfg.set_main_option("script_location", "migrations")
+    alembic_cfg.set_main_option("sqlalchemy.url", db_url)
+
+    # Run migrations using Alembic
+    command.upgrade(alembic_cfg, "head")
+
+    print('db up to date')

image.py

@@ -1,26 +0,0 @@
-from google.cloud import vision
-from google.cloud.vision_v1 import types
-
-from dotenv import load_dotenv
-
-load_dotenv()
-
-crows = 'https://cdn.discordapp.com/attachments/367936426962190336/1222335573855834214/AjPuqci.png?ex=6615d7b6&is=660362b6&hm=e364398ce7401334298eb82bddedab56d944f5833508fde4b07363b329a95c6f&'
-
-# Authenticate the client
-client = vision.ImageAnnotatorClient()
-
-# Perform text detection
-features = [types.Feature(type=types.Feature.Type.TEXT_DETECTION)]
-request = {
-    'image': {
-        'source': { 'image_uri': crows }
-    },
-    'features': features
-}
-
-response: types.AnnotateImageResponse = client.annotate_image(request=request)
-texts = response.text_annotations[0].description
-
-print(texts)
-

main.py

@@ -19,11 +19,11 @@ from dotenv import dotenv_values, load_dotenv
 from google.cloud import vision as google_vision
 from google.protobuf.json_format import MessageToDict, MessageToJson
 from google.cloud.vision_v1 import types
-from minio import Minio
 import meilisearch
 from urllib3.util import Url, url
 
-import uploader
+from sqlalchemy import create_engine
+from db.migrate import migrate_db
 
 # need to change the env for the google api calls
 load_dotenv()
@@ -55,42 +55,16 @@ class MemeDocument:
     text: str
     tags: List[str]
 
-@dataclass
+def detect_text(url, vision):
-class DiscordAttachmentMessage:
+    request = {
-    id: UUID
+        'image': { 'source': { 'image_uri': url } },
-    msg_id: int
+        'features': [types.Feature(type=types.Feature.Type.TEXT_DETECTION)],
-    url: str
+    }
-    upload_url: str
-    guild_name: str
-    channel_name: str
-    vision_json: str | None
-    message_json: Dict[str, Any]
-    guild_json: Dict[str, Any]
-    channel_json: Dict[str, Any]
 
-    def document_dir(self):
+    response: types.AnnotateImageResponse = vision.annotate_image(request=request)
-        return f'{DATA_DIR}/guilds/{self.guild_name}/{self.channel_name}'
+    vision_json = json.loads(types.AnnotateImageResponse.to_json(response))
 
-    def file_dir(self):
+    return request
-        return f"{DATA_DIR}/imgs/"
-
-    def detect_text(self, vision):
-        request = {
-            'image': { 'source': { 'image_uri': self.url } },
-            'features': [types.Feature(type=types.Feature.Type.TEXT_DETECTION)],
-        }
-
-        response: types.AnnotateImageResponse = vision.annotate_image(request=request)
-        self.vision_json = json.loads(types.AnnotateImageResponse.to_json(response))
-
-        if len(response.text_annotations) > 0:
-            self.text = response.text_annotations[0].description
-
-        return request
-
-    def persist(self):
-        with open(f'{self.document_dir()}/{self.id}.json', 'w') as f:
-            json.dump(vars(self), f, indent=4)
 
 def filter_message_img_urls(messages):
     url_lists = map(
@@ -203,38 +177,39 @@ async def check_bucket_exists(storage, bucket_name):
             raise  # Reraise other exceptions
 
 async def main():
-    assert config['MINIO_URL']
+    assert config['STORAGE_URL']
+    assert config['POSTGRES_URL']
 
     vision = google_vision.ImageAnnotatorClient()
 
-    # storage = Minio(config['MINIO_URL'],
+    # db setup
-    #     access_key=config['MINIO_ACCESS_KEY'],
+    db_url = config['POSTGRES_URL']
-    #     secret_key=config['MINIO_SECRET_KEY'],
+    db_engine = create_engine(db_url)
-    # )
+    migrate_db(db_engine, db_url)
 
-    aioboto = aiobotocore_get_session()
+    # aioboto = aiobotocore_get_session()
-    async with aioboto.create_client(
+    # async with aioboto.create_client(
-        's3',
+    #     's3',
-        endpoint_url=config['STORAGE_URL'],
+    #     endpoint_url=config['STORAGE_URL'],
-        aws_access_key_id=config['STORAGE_ACCESS_KEY'],
+    #     aws_access_key_id=config['STORAGE_ACCESS_KEY'],
-        aws_secret_access_key=config['STORAGE_SECRET_KEY'],
+    #     aws_secret_access_key=config['STORAGE_SECRET_KEY'],
-    ) as storage:
+    # ) as storage:
-        storage: S3Client
+    #     storage: S3Client
 
-        storage_bucket = config['UPLOAD_BUCKET']
+    #     storage_bucket = config['UPLOAD_BUCKET']
-        assert storage_bucket
+    #     assert storage_bucket
 
-        # Make the bucket if it doesn't exist.
+    #     # Make the bucket if it doesn't exist.
-        exists = await check_bucket_exists(storage, storage_bucket)
+    #     exists = await check_bucket_exists(storage, storage_bucket)
-        if not exists:
+    #     if not exists:
-            await storage.create_bucket(Bucket=storage_bucket)
+    #         await storage.create_bucket(Bucket=storage_bucket)
-            print("Created bucket", storage_bucket)
+    #         print("Created bucket", storage_bucket)
-        else:
+    #     else:
-            print("Bucket", storage_bucket, "already exists")
+    #         print("Bucket", storage_bucket, "already exists")
 
-        async with aiohttp.ClientSession() as session:
+    #     async with aiohttp.ClientSession() as session:
-            channels = [download_channel_attachments(session, storage, vision, channel_id) for channel_id in CHANNEL_IDS]
+    #         channels = [download_channel_attachments(session, storage, vision, channel_id) for channel_id in CHANNEL_IDS]
-            memes = await asyncio.gather(*channels)
+    #         memes = await asyncio.gather(*channels)
 
 
 asyncio.run(main())

migrations/README

@@ -0,0 +1 @@
+Generic single-database configuration.

migrations/env.py

@@ -0,0 +1,86 @@
+from logging.config import fileConfig
+
+from sqlalchemy import engine_from_config
+from sqlalchemy import pool
+
+from alembic import context
+
+from dotenv import dotenv_values
+
+from db import Base
+
+# this is the Alembic Config object, which provides
+# access to the values within the .ini file in use.
+config = context.config
+
+env = dotenv_values(".env")
+assert env['POSTGRES_URL']
+config.set_main_option('sqlalchemy.url', env['POSTGRES_URL'])
+
+# Interpret the config file for Python logging.
+# This line sets up loggers basically.
+if config.config_file_name is not None:
+    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 = 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 run_migrations_offline() -> None:
+    """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=target_metadata,
+        literal_binds=True,
+        dialect_opts={"paramstyle": "named"},
+    )
+
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+def run_migrations_online() -> None:
+    """Run migrations in 'online' mode.
+
+    In this scenario we need to create an Engine
+    and associate a connection with the context.
+
+    """
+    connectable = engine_from_config(
+        config.get_section(config.config_ini_section, {}),
+        prefix="sqlalchemy.",
+        poolclass=pool.NullPool,
+    )
+
+    with connectable.connect() as connection:
+        context.configure(
+            connection=connection, target_metadata=target_metadata
+        )
+
+        with context.begin_transaction():
+            context.run_migrations()
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

migrations/script.py.mako

@@ -0,0 +1,26 @@
+"""${message}
+
+Revision ID: ${up_revision}
+Revises: ${down_revision | comma,n}
+Create Date: ${create_date}
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+${imports if imports else ""}
+
+# revision identifiers, used by Alembic.
+revision: str = ${repr(up_revision)}
+down_revision: Union[str, None] = ${repr(down_revision)}
+branch_labels: Union[str, Sequence[str], None] = ${repr(branch_labels)}
+depends_on: Union[str, Sequence[str], None] = ${repr(depends_on)}
+
+
+def upgrade() -> None:
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade() -> None:
+    ${downgrades if downgrades else "pass"}

migrations/versions/e04bee35feab_create_memes_and_attachments_table.py

@@ -0,0 +1,49 @@
+"""Create Memes and Attachments table
+
+Revision ID: e04bee35feab
+Revises: 
+Create Date: 2024-04-08 10:45:47.138438
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision: str = 'e04bee35feab'
+down_revision: Union[str, None] = None
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.create_table('attachments',
+    sa.Column('id', sa.Uuid(), nullable=False),
+    sa.Column('msg_id', sa.Integer(), nullable=False),
+    sa.Column('attributes', sa.JSON(), nullable=False),
+    sa.Column('vision', sa.JSON(), nullable=False),
+    sa.Column('message', sa.JSON(), nullable=False),
+    sa.Column('guild', sa.JSON(), nullable=False),
+    sa.Column('channel', sa.JSON(), nullable=False),
+    sa.PrimaryKeyConstraint('id')
+    )
+    op.create_index(op.f('ix_attachments_msg_id'), 'attachments', ['msg_id'], unique=False)
+    op.create_table('memes',
+    sa.Column('id', sa.Uuid(), nullable=False),
+    sa.Column('url', sa.String(), nullable=False),
+    sa.Column('text', sa.String(), nullable=False),
+    sa.Column('tags', sa.JSON(), nullable=False),
+    sa.PrimaryKeyConstraint('id')
+    )
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_table('memes')
+    op.drop_index(op.f('ix_attachments_msg_id'), table_name='attachments')
+    op.drop_table('attachments')
+    # ### end Alembic commands ###

requirements.txt

@@ -3,5 +3,7 @@ aiohttp
 google-cloud-vision
 meilisearch
 pillow
-minio
+aiobotocore
-aiobotocore
+sqlalchemy
+alembic
+psycopg2-binary

uploader.py

@@ -1,31 +0,0 @@
-from minio import Minio
-
-def upload(config, document, source_file):
-    assert config['MINIO_URL']
-
-    client = Minio(config['MINIO_URL'],
-        access_key=config['MINIO_ACCESS_KEY'],
-        secret_key=config['MINIO_SECRET_KEY'],
-    )
-
-    # The destination bucket and filename on the MinIO server
-    bucket_name = config['UPLOAD_BUCKET']
-    destination_file = document.url
-    
-    # Make the bucket if it doesn't exist.
-    found = client.bucket_exists(bucket_name)
-    if not found:
-        client.make_bucket(bucket_name)
-        print("Created bucket", bucket_name)
-    else:
-        print("Bucket", bucket_name, "already exists")
-
-    # Upload the file, renaming it in the process
-    client.fput_object(
-        bucket_name, destination_file, source_file,
-    )
-
-    print(
-        source_file, "successfully uploaded as object",
-        destination_file, "to bucket", bucket_name,
-    )