Feat finalize page

alembic.ini

@@ -0,0 +1,44 @@
+# A generic, single database configuration.
+
+[alembic]
+
+# database URL.  This is consumed by the user-maintained env.py script only.
+# other means of configuring database URLs may be customized within the env.py
+# file.
+sqlalchemy.url = driver://user:pass@localhost/dbname
+
+
+# Logging configuration
+[loggers]
+keys = root,sqlalchemy,alembic
+
+[handlers]
+keys = console
+
+[formatters]
+keys = generic
+
+[logger_root]
+level = WARNING
+handlers = console
+qualname =
+
+[logger_sqlalchemy]
+level = WARNING
+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

@@ -0,0 +1 @@
+pyproject configuration, based on the generic configuration.

alembic/env.py

@@ -0,0 +1,83 @@
+from logging.config import fileConfig
+
+from sqlalchemy import engine_from_config, pool
+
+from alembic import context
+from pir_pipeline.config import DB_CONFIG, DB_NAME
+from pir_pipeline.models.pir_sql_models import sql_metadata
+from pir_pipeline.utils.SQLAlchemyUtils import SQLAlchemyUtils
+
+# 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.
+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 = sql_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.
+sql_utils = SQLAlchemyUtils(**DB_CONFIG, database=DB_NAME)
+config.set_main_option(
+    "sqlalchemy.url",
+    sql_utils._engine.url.__to_string__(hide_password=False).replace("%", "%%"),
+)
+
+
+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()

alembic/script.py.mako

@@ -0,0 +1,28 @@
+"""${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, Sequence[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:
+    """Upgrade schema."""
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    ${downgrades if downgrades else "pass"}

code/serve_qa_dashboard.sh

@@ -1,4 +1,5 @@
 cd ~/repos/ACF-pir-data/
 source .venv/bin/activate
+export LOADING_DASHBOARD="True"
 google-chrome http://localhost:8080 &>/dev/null &
 waitress-serve --host 127.0.0.1 --call "pir_pipeline.dashboard:create_app"

code/uqid_bug_correction.py

@@ -2,14 +2,14 @@
 from typing import MutableSequence
 
 from pandas import DataFrame
-from sqlalchemy import func, or_, select, text, Select, bindparam
+from sqlalchemy import bindparam, func, or_, select, text
 
 os.environ["RDS_CREDENTIALS"] = "True"
 
 from pir_pipeline.config import DB_CONFIG
 from pir_pipeline.linking.PIRLinker import PIRLinker
-from pir_pipeline.utils.SQLAlchemyUtils import SQLAlchemyUtils
 from pir_pipeline.utils.dashboard_utils import QuestionLinker
+from pir_pipeline.utils.SQLAlchemyUtils import SQLAlchemyUtils
 
 SQL_UTILS = SQLAlchemyUtils(**DB_CONFIG, database="pir_data")
 QUESTION = SQL_UTILS.tables["question"]

pyproject.toml

@@ -16,7 +16,7 @@ dependencies = [
     "mysql-connector-python", "sphinx", "pandas", "python-dotenv",
     "fuzzywuzzy", "python-Levenshtein", "pytest", "openpyxl", "xlrd",
     "pydantic", "Flask", "SQLAlchemy", "sqlalchemy-utils", "psycopg[binary]",
-    "requests", "selenium", "coverage", "boto3", "waitress"
+    "requests", "selenium", "coverage", "boto3", "waitress", "alembic"
 ]
 
 [build-system]
@@ -27,4 +27,89 @@ build-backend = "setuptools.build_meta"
 Homepage = "https://github.com/HHS/ACF-pir-data"
 
 [tool.pytest.ini_options]
-testpaths = ["tests"]
+testpaths = ["tests"]
+
+[tool.alembic]
+
+# path to migration scripts.
+# this is typically a path given in POSIX (e.g. forward slashes)
+# format, relative to the token %(here)s which refers to the location of this
+# ini file
+script_location = "%(here)s/alembic"
+
+# 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"
+# Or organize into date-based subdirectories (requires recursive_version_locations = true)
+# file_template = "%%(year)d/%%(month).2d/%%(day).2d_%%(hour).2d%%(minute).2d_%%(second).2d_%%(rev)s_%%(slug)s"
+
+# additional paths to be prepended to sys.path. 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 tzdata library which can be 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 <script_location>/versions.  When using multiple version
+# directories, initial revisions must be specified with --version-path.
+# version_locations = [
+#    "%(here)s/alembic/versions",
+#    "%(here)s/foo/bar"
+# ]
+
+
+# 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"
+
+# This section defines scripts or Python functions that are run
+# on newly generated revision scripts.  See the documentation for further
+# detail and examples
+# [[tool.alembic.post_write_hooks]]
+# format using "black" - use the console_scripts runner,
+# against the "black" entrypoint
+# name = "black"
+# type = "console_scripts"
+# entrypoint = "black"
+# options = "-l 79 REVISION_SCRIPT_FILENAME"
+#
+# [[tool.alembic.post_write_hooks]]
+# lint with attempts to fix using "ruff" - use the module runner, against the "ruff" module
+# name = "ruff"
+# type = "module"
+# module = "ruff"
+# options = "check --fix REVISION_SCRIPT_FILENAME"
+#
+# [[tool.alembic.post_write_hooks]]
+# Alternatively, use the exec runner to execute a binary found on your PATH
+# name = "ruff"
+# type = "exec"
+# executable = "ruff"
+# options = "check --fix REVISION_SCRIPT_FILENAME"
+

requirements.txt

@@ -29,7 +29,7 @@ openpyxl==3.1.5
 outcome==1.3.0.post0
 packaging==25.0
 pandas==2.2.3
--e git+https://github.com/HHS/ACF-pir-data.git@0104f01060b03cdcbef74e0f8008782c8059cd32#egg=pir_pipeline
+-e git+https://github.com/HHS/ACF-pir-data.git@d1bbee31e9490b6b089a91ffaed915bd9eff2364#egg=pir_pipeline
 pluggy==1.5.0
 psycopg==3.2.7
 psycopg-binary==3.2.7

src/pir_pipeline/dashboard/__init__.py

@@ -48,12 +48,13 @@ def create_app(test_config: dict = None, **kwargs) -> Flask:
 
     db.init_app(app)
 
-    from pir_pipeline.dashboard import index, review, search
+    from pir_pipeline.dashboard import finalize, index, review, search
 
     app.register_blueprint(index.bp)
     app.add_url_rule("/", endpoint="index")
 
     app.register_blueprint(search.bp)
     app.register_blueprint(review.bp)
+    app.register_blueprint(finalize.bp)
 
     return app