First product

This commit is contained in:
Justin Visser 2026-02-17 14:51:25 +01:00
parent 778da9e2fc
commit 4433d7d2c4
157 changed files with 23975 additions and 0 deletions

66
alembic/env.py Normal file
View file

@ -0,0 +1,66 @@
from logging.config import fileConfig
import os
from alembic import context
from sqlalchemy import pool
from sqlalchemy.engine import Connection
from sqlalchemy.ext.asyncio import async_engine_from_config
from app.db.base import metadata
from app.db import models # noqa: F401
config = context.config
if config.config_file_name is not None:
fileConfig(config.config_file_name)
database_url = os.getenv("DATABASE_URL")
if database_url:
config.set_main_option("sqlalchemy.url", database_url)
target_metadata = metadata
def run_migrations_offline() -> None:
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 do_run_migrations(connection: Connection) -> None:
context.configure(connection=connection, target_metadata=target_metadata)
with context.begin_transaction():
context.run_migrations()
async def run_async_migrations() -> None:
connectable = async_engine_from_config(
config.get_section(config.config_ini_section, {}),
prefix="sqlalchemy.",
poolclass=pool.NullPool,
)
async with connectable.connect() as connection:
await connection.run_sync(do_run_migrations)
await connectable.dispose()
def run_migrations_online() -> None:
import asyncio
asyncio.run(run_async_migrations())
if context.is_offline_mode():
run_migrations_offline()
else:
run_migrations_online()

27
alembic/script.py.mako Normal file
View file

@ -0,0 +1,27 @@
"""${message}
Revision ID: ${up_revision}
Revises: ${down_revision | comma,n}
Create Date: ${create_date}
"""
from collections.abc import Sequence
from alembic import op
import sqlalchemy as sa
${imports if imports else ""}
# revision identifiers, used by Alembic.
revision: str = ${repr(up_revision)}
down_revision: str | Sequence[str] | None = ${repr(down_revision)}
branch_labels: str | Sequence[str] | None = ${repr(branch_labels)}
depends_on: str | Sequence[str] | None = ${repr(depends_on)}
def upgrade() -> None:
${upgrades if upgrades else "pass"}
def downgrade() -> None:
${downgrades if downgrades else "pass"}

View file

@ -0,0 +1 @@

View file

@ -0,0 +1,353 @@
"""Create multi-user core schema
Revision ID: 20260216_0001
Revises:
Create Date: 2026-02-16 17:10:00.000000
"""
from collections.abc import Sequence
from alembic import op
import sqlalchemy as sa
from sqlalchemy.dialects import postgresql
# revision identifiers, used by Alembic.
revision: str = "20260216_0001"
down_revision: str | Sequence[str] | None = None
branch_labels: str | Sequence[str] | None = None
depends_on: str | Sequence[str] | None = None
run_status_enum = sa.Enum(
"running",
"success",
"partial_failure",
"failed",
name="run_status",
)
run_trigger_type_enum = sa.Enum(
"manual",
"scheduled",
name="run_trigger_type",
)
run_status_ref = postgresql.ENUM(
"running",
"success",
"partial_failure",
"failed",
name="run_status",
create_type=False,
)
run_trigger_type_ref = postgresql.ENUM(
"manual",
"scheduled",
name="run_trigger_type",
create_type=False,
)
def upgrade() -> None:
bind = op.get_bind()
run_status_enum.create(bind, checkfirst=True)
run_trigger_type_enum.create(bind, checkfirst=True)
op.create_table(
"users",
sa.Column("id", sa.Integer(), nullable=False),
sa.Column("email", sa.String(length=255), nullable=False),
sa.Column("password_hash", sa.String(length=255), nullable=False),
sa.Column(
"is_active",
sa.Boolean(),
nullable=False,
server_default=sa.text("true"),
),
sa.Column(
"created_at",
sa.DateTime(timezone=True),
nullable=False,
server_default=sa.func.now(),
),
sa.Column(
"updated_at",
sa.DateTime(timezone=True),
nullable=False,
server_default=sa.func.now(),
),
sa.PrimaryKeyConstraint("id", name="pk_users"),
sa.UniqueConstraint("email", name="uq_users_email"),
)
op.create_table(
"user_settings",
sa.Column("user_id", sa.Integer(), nullable=False),
sa.Column(
"auto_run_enabled",
sa.Boolean(),
nullable=False,
server_default=sa.text("false"),
),
sa.Column(
"run_interval_minutes",
sa.Integer(),
nullable=False,
server_default=sa.text("1440"),
),
sa.Column(
"request_delay_seconds",
sa.Integer(),
nullable=False,
server_default=sa.text("10"),
),
sa.Column(
"created_at",
sa.DateTime(timezone=True),
nullable=False,
server_default=sa.func.now(),
),
sa.Column(
"updated_at",
sa.DateTime(timezone=True),
nullable=False,
server_default=sa.func.now(),
),
sa.CheckConstraint(
"run_interval_minutes >= 15",
name="ck_user_settings_run_interval_minutes_min_15",
),
sa.CheckConstraint(
"request_delay_seconds >= 1",
name="ck_user_settings_request_delay_seconds_min_1",
),
sa.ForeignKeyConstraint(
["user_id"],
["users.id"],
name="fk_user_settings_user_id_users",
ondelete="CASCADE",
),
sa.PrimaryKeyConstraint("user_id", name="pk_user_settings"),
)
op.create_table(
"publications",
sa.Column("id", sa.Integer(), nullable=False),
sa.Column("cluster_id", sa.String(length=64), nullable=True),
sa.Column("fingerprint_sha256", sa.String(length=64), nullable=False),
sa.Column("title_raw", sa.Text(), nullable=False),
sa.Column("title_normalized", sa.Text(), nullable=False),
sa.Column("year", sa.Integer(), nullable=True),
sa.Column(
"citation_count",
sa.Integer(),
nullable=False,
server_default=sa.text("0"),
),
sa.Column("author_text", sa.Text(), nullable=True),
sa.Column("venue_text", sa.Text(), nullable=True),
sa.Column("pub_url", sa.Text(), nullable=True),
sa.Column("pdf_url", sa.Text(), nullable=True),
sa.Column(
"created_at",
sa.DateTime(timezone=True),
nullable=False,
server_default=sa.func.now(),
),
sa.Column(
"updated_at",
sa.DateTime(timezone=True),
nullable=False,
server_default=sa.func.now(),
),
sa.PrimaryKeyConstraint("id", name="pk_publications"),
sa.UniqueConstraint(
"fingerprint_sha256",
name="uq_publications_fingerprint",
),
)
op.create_index(
"uq_publications_cluster_id_not_null",
"publications",
["cluster_id"],
unique=True,
postgresql_where=sa.text("cluster_id IS NOT NULL"),
)
op.create_table(
"scholar_profiles",
sa.Column("id", sa.Integer(), nullable=False),
sa.Column("user_id", sa.Integer(), nullable=False),
sa.Column("scholar_id", sa.String(length=64), nullable=False),
sa.Column("display_name", sa.String(length=255), nullable=True),
sa.Column(
"is_enabled",
sa.Boolean(),
nullable=False,
server_default=sa.text("true"),
),
sa.Column(
"baseline_completed",
sa.Boolean(),
nullable=False,
server_default=sa.text("false"),
),
sa.Column("last_run_dt", sa.DateTime(timezone=True), nullable=True),
sa.Column("last_run_status", run_status_ref, nullable=True),
sa.Column(
"created_at",
sa.DateTime(timezone=True),
nullable=False,
server_default=sa.func.now(),
),
sa.Column(
"updated_at",
sa.DateTime(timezone=True),
nullable=False,
server_default=sa.func.now(),
),
sa.ForeignKeyConstraint(
["user_id"],
["users.id"],
name="fk_scholar_profiles_user_id_users",
ondelete="CASCADE",
),
sa.PrimaryKeyConstraint("id", name="pk_scholar_profiles"),
sa.UniqueConstraint(
"user_id",
"scholar_id",
name="uq_scholar_profiles_user_scholar",
),
)
op.create_index(
"ix_scholar_profiles_user_enabled",
"scholar_profiles",
["user_id", "is_enabled"],
unique=False,
)
op.create_table(
"crawl_runs",
sa.Column("id", sa.Integer(), nullable=False),
sa.Column("user_id", sa.Integer(), nullable=False),
sa.Column("trigger_type", run_trigger_type_ref, nullable=False),
sa.Column("status", run_status_ref, nullable=False),
sa.Column(
"start_dt",
sa.DateTime(timezone=True),
nullable=False,
server_default=sa.func.now(),
),
sa.Column("end_dt", sa.DateTime(timezone=True), nullable=True),
sa.Column(
"scholar_count",
sa.Integer(),
nullable=False,
server_default=sa.text("0"),
),
sa.Column(
"new_pub_count",
sa.Integer(),
nullable=False,
server_default=sa.text("0"),
),
sa.Column(
"error_log",
postgresql.JSONB(astext_type=sa.Text()),
nullable=False,
server_default=sa.text("'{}'::jsonb"),
),
sa.Column(
"created_at",
sa.DateTime(timezone=True),
nullable=False,
server_default=sa.func.now(),
),
sa.Column(
"updated_at",
sa.DateTime(timezone=True),
nullable=False,
server_default=sa.func.now(),
),
sa.ForeignKeyConstraint(
["user_id"],
["users.id"],
name="fk_crawl_runs_user_id_users",
ondelete="CASCADE",
),
sa.PrimaryKeyConstraint("id", name="pk_crawl_runs"),
)
op.create_index(
"ix_crawl_runs_user_start",
"crawl_runs",
["user_id", "start_dt"],
unique=False,
)
op.create_table(
"scholar_publications",
sa.Column("scholar_profile_id", sa.Integer(), nullable=False),
sa.Column("publication_id", sa.Integer(), nullable=False),
sa.Column(
"is_read",
sa.Boolean(),
nullable=False,
server_default=sa.text("false"),
),
sa.Column("first_seen_run_id", sa.Integer(), nullable=True),
sa.Column(
"created_at",
sa.DateTime(timezone=True),
nullable=False,
server_default=sa.func.now(),
),
sa.ForeignKeyConstraint(
["first_seen_run_id"],
["crawl_runs.id"],
name="fk_scholar_publications_first_seen_run_id_crawl_runs",
ondelete="SET NULL",
),
sa.ForeignKeyConstraint(
["publication_id"],
["publications.id"],
name="fk_scholar_publications_publication_id_publications",
ondelete="CASCADE",
),
sa.ForeignKeyConstraint(
["scholar_profile_id"],
["scholar_profiles.id"],
name="fk_scholar_publications_scholar_profile_id_scholar_profiles",
ondelete="CASCADE",
),
sa.PrimaryKeyConstraint(
"scholar_profile_id",
"publication_id",
name="pk_scholar_publications",
),
)
op.create_index(
"ix_scholar_publications_is_read",
"scholar_publications",
["is_read"],
unique=False,
)
def downgrade() -> None:
op.drop_index("ix_scholar_publications_is_read", table_name="scholar_publications")
op.drop_table("scholar_publications")
op.drop_index("ix_crawl_runs_user_start", table_name="crawl_runs")
op.drop_table("crawl_runs")
op.drop_index("ix_scholar_profiles_user_enabled", table_name="scholar_profiles")
op.drop_table("scholar_profiles")
op.drop_index("uq_publications_cluster_id_not_null", table_name="publications")
op.drop_table("publications")
op.drop_table("user_settings")
op.drop_table("users")
bind = op.get_bind()
run_trigger_type_enum.drop(bind, checkfirst=True)
run_status_enum.drop(bind, checkfirst=True)

View file

@ -0,0 +1,34 @@
"""Add admin flag to users
Revision ID: 20260216_0002
Revises: 20260216_0001
Create Date: 2026-02-16 17:40:00.000000
"""
from collections.abc import Sequence
from alembic import op
import sqlalchemy as sa
# revision identifiers, used by Alembic.
revision: str = "20260216_0002"
down_revision: str | Sequence[str] | None = "20260216_0001"
branch_labels: str | Sequence[str] | None = None
depends_on: str | Sequence[str] | None = None
def upgrade() -> None:
op.add_column(
"users",
sa.Column(
"is_admin",
sa.Boolean(),
nullable=False,
server_default=sa.text("false"),
),
)
def downgrade() -> None:
op.drop_column("users", "is_admin")

View file

@ -0,0 +1,94 @@
"""Add ingestion continuation queue table
Revision ID: 20260216_0003
Revises: 20260216_0002
Create Date: 2026-02-16 23:45:00.000000
"""
from collections.abc import Sequence
from alembic import op
import sqlalchemy as sa
# revision identifiers, used by Alembic.
revision: str = "20260216_0003"
down_revision: str | Sequence[str] | None = "20260216_0002"
branch_labels: str | Sequence[str] | None = None
depends_on: str | Sequence[str] | None = None
def upgrade() -> None:
op.create_table(
"ingestion_queue_items",
sa.Column("id", sa.Integer(), nullable=False),
sa.Column("user_id", sa.Integer(), nullable=False),
sa.Column("scholar_profile_id", sa.Integer(), nullable=False),
sa.Column(
"resume_cstart",
sa.Integer(),
nullable=False,
server_default=sa.text("0"),
),
sa.Column("reason", sa.String(length=64), nullable=False),
sa.Column(
"attempt_count",
sa.Integer(),
nullable=False,
server_default=sa.text("0"),
),
sa.Column(
"next_attempt_dt",
sa.DateTime(timezone=True),
nullable=False,
server_default=sa.func.now(),
),
sa.Column("last_run_id", sa.Integer(), nullable=True),
sa.Column("last_error", sa.Text(), nullable=True),
sa.Column(
"created_at",
sa.DateTime(timezone=True),
nullable=False,
server_default=sa.func.now(),
),
sa.Column(
"updated_at",
sa.DateTime(timezone=True),
nullable=False,
server_default=sa.func.now(),
),
sa.ForeignKeyConstraint(
["last_run_id"],
["crawl_runs.id"],
name="fk_ingestion_queue_items_last_run_id_crawl_runs",
ondelete="SET NULL",
),
sa.ForeignKeyConstraint(
["scholar_profile_id"],
["scholar_profiles.id"],
name="fk_ingestion_queue_items_scholar_profile_id_scholar_profiles",
ondelete="CASCADE",
),
sa.ForeignKeyConstraint(
["user_id"],
["users.id"],
name="fk_ingestion_queue_items_user_id_users",
ondelete="CASCADE",
),
sa.PrimaryKeyConstraint("id", name="pk_ingestion_queue_items"),
sa.UniqueConstraint(
"user_id",
"scholar_profile_id",
name="uq_ingestion_queue_user_scholar",
),
)
op.create_index(
"ix_ingestion_queue_next_attempt",
"ingestion_queue_items",
["next_attempt_dt"],
unique=False,
)
def downgrade() -> None:
op.drop_index("ix_ingestion_queue_next_attempt", table_name="ingestion_queue_items")
op.drop_table("ingestion_queue_items")

View file

@ -0,0 +1,96 @@
"""Add queue status and dropped diagnostics fields
Revision ID: 20260217_0004
Revises: 20260216_0003
Create Date: 2026-02-17 10:15:00.000000
"""
from collections.abc import Sequence
from alembic import op
import sqlalchemy as sa
# revision identifiers, used by Alembic.
revision: str = "20260217_0004"
down_revision: str | Sequence[str] | None = "20260216_0003"
branch_labels: str | Sequence[str] | None = None
depends_on: str | Sequence[str] | None = None
def upgrade() -> None:
bind = op.get_bind()
inspector = sa.inspect(bind)
columns = {column["name"] for column in inspector.get_columns("ingestion_queue_items")}
indexes = {index["name"] for index in inspector.get_indexes("ingestion_queue_items")}
checks = {
constraint["name"] for constraint in inspector.get_check_constraints("ingestion_queue_items")
}
if "status" not in columns:
op.add_column(
"ingestion_queue_items",
sa.Column(
"status",
sa.String(length=16),
nullable=False,
server_default=sa.text("'queued'"),
),
)
columns.add("status")
if "dropped_reason" not in columns:
op.add_column(
"ingestion_queue_items",
sa.Column("dropped_reason", sa.String(length=128), nullable=True),
)
if "dropped_at" not in columns:
op.add_column(
"ingestion_queue_items",
sa.Column("dropped_at", sa.DateTime(timezone=True), nullable=True),
)
if "status" in columns:
op.execute(
"""
UPDATE ingestion_queue_items
SET status = 'queued'
WHERE status IS NULL OR status = ''
"""
)
if "ingestion_queue_status_valid" not in checks:
op.create_check_constraint(
"ingestion_queue_status_valid",
"ingestion_queue_items",
"status IN ('queued', 'retrying', 'dropped')",
)
if "ix_ingestion_queue_status_next_attempt" not in indexes:
op.create_index(
"ix_ingestion_queue_status_next_attempt",
"ingestion_queue_items",
["status", "next_attempt_dt"],
unique=False,
)
def downgrade() -> None:
bind = op.get_bind()
inspector = sa.inspect(bind)
columns = {column["name"] for column in inspector.get_columns("ingestion_queue_items")}
indexes = {index["name"] for index in inspector.get_indexes("ingestion_queue_items")}
checks = {
constraint["name"] for constraint in inspector.get_check_constraints("ingestion_queue_items")
}
if "ix_ingestion_queue_status_next_attempt" in indexes:
op.drop_index("ix_ingestion_queue_status_next_attempt", table_name="ingestion_queue_items")
if "ingestion_queue_status_valid" in checks:
op.drop_constraint("ingestion_queue_status_valid", "ingestion_queue_items", type_="check")
if "dropped_at" in columns:
op.drop_column("ingestion_queue_items", "dropped_at")
if "dropped_reason" in columns:
op.drop_column("ingestion_queue_items", "dropped_reason")
if "status" in columns:
op.drop_column("ingestion_queue_items", "status")