shopdb-flask/scripts/site_imports/wjf/harness.py

"""Import harness for the WJ classic-ASP -> flask reference loader.

This is SITE-SPECIFIC reference glue, NOT product code. It maps West Jefferson's
classic schema onto the maintained, schema-agnostic import contract in
the IMPORT-API wiki page. Other sites copy this pattern against their own source DB;
they do not run this loader.

The harness builds the flask app against the current DATABASE_URL (point it at a
throwaway import database), mints an unscoped admin PAT in-process, and drives
the REAL import endpoints through the app test client with the X-Import-Mode
header - so it exercises the same routes/authz/validation an HTTP client would,
without needing a running server. Legacy-id -> new-id maps persist to JSON so a
crashed run resumes and later stages resolve foreign keys.
"""

import json
import uuid
import os
import pymysql

from shopdb import create_app
from shopdb.extensions import db


def _source_password():
    """Root password for the scratch source DBs: reuse the dev DATABASE_URL in
    .env unless SOURCE_DB_PASSWORD overrides."""
    if os.environ.get('SOURCE_DB_PASSWORD'):
        return os.environ['SOURCE_DB_PASSWORD']
    env = os.path.join(os.path.dirname(__file__), '..', '..', '..', '.env')
    with open(os.path.abspath(env)) as handle:
        for line in handle:
            if line.startswith('DATABASE_URL='):
                # Not every server runs as root, and 'root:' then simply is not
                # there: split()[1] raised IndexError, which read as a crash
                # rather than the clear message two lines down.
                if 'root:' not in line:
                    continue
                after = line.split('root:', 1)[1]
                return after.split('@', 1)[0]
    raise RuntimeError('could not resolve source DB password')


class Source:
    """Read-only access to the three source databases.

    The stage functions name a source by its LOGICAL name - 'shopdb_src',
    'cmmc_usb_src', 'wjf_employees_src' - and this class resolves each to a
    real database. That indirection is the point: the names were hardcoded at
    29 call sites, so pointing the loader at a differently-named copy (the
    prodscratch restore, or a site's own dump) meant editing run.py, which is
    not something anybody should do to aim a loader. The logical names stay in
    the stages where they read as documentation; the mapping lives here.

    Everything is environment-overridable, defaulting to the scratch layout:

        SOURCE_DB_MAIN        default shopdb_src
        SOURCE_DB_USB         default cmmc_usb_src
        SOURCE_DB_EMPLOYEES   default wjf_employees_src
        SOURCE_DB_HOST/PORT/USER/PASSWORD
    """

    # logical name -> (env var, default real name)
    ALIASES = {
        'shopdb_src': ('SOURCE_DB_MAIN', 'shopdb_src'),
        'cmmc_usb_src': ('SOURCE_DB_USB', 'cmmc_usb_src'),
        'wjf_employees_src': ('SOURCE_DB_EMPLOYEES', 'wjf_employees_src'),
    }

    def __init__(self, host=None, port=None, user=None, password=None):
        self.password = password or _source_password()
        self.host = host or os.environ.get('SOURCE_DB_HOST', '127.0.0.1')
        self.port = int(port or os.environ.get('SOURCE_DB_PORT', 3306))
        self.user = user or os.environ.get('SOURCE_DB_USER', 'root')
        self._conns = {}

    @classmethod
    def resolve(cls, name):
        """The real database behind a logical source name."""
        env, default = cls.ALIASES.get(name, (None, name))
        return os.environ.get(env, default) if env else name

    def db(self, name):
        real = self.resolve(name)
        if real not in self._conns:
            self._conns[real] = pymysql.connect(
                host=self.host, port=self.port, user=self.user,
                password=self.password, database=real, charset='utf8mb4',
                cursorclass=pymysql.cursors.DictCursor)
        return self._conns[real]

    def rows(self, dbname, sql, args=None):
        with self.db(dbname).cursor() as cur:
            cur.execute(sql, args or ())
            return cur.fetchall()


class StaleIdMapError(RuntimeError):
    """The crosswalk on disk was built against a different target database."""


class IdMap:
    """Persisted legacy-id -> new-id crosswalks, one namespace per entity.

    BOUND TO ONE TARGET DATABASE. The crosswalk holds this site's legacy ids
    mapped to assetids in a specific database, and those assetids mean nothing
    anywhere else. Two ways that used to go wrong, both silent:

      - Delete idmap.json and re-run: every create 409s, nothing resolves into
        the crosswalk, and warranties, installs, relationships and printer
        assignments all quietly import as ~0 rows.
      - Keep idmap.json across a drop-and-rebuild of the target: the legacy ids
        now point at assetids belonging to the OLD database, so warranties and
        printer assignments attach to whatever asset happens to hold that id
        now. Wrong data, no error, and the runbook's two "drop and rebuild"
        steps never said to delete the file.

    The bind is a marker row in the target's own settings table, so it dies
    with the data: a rebuild produces a new marker, and the mismatch is caught
    before a single row is written. The database NAME is not enough on its own,
    because a rebuild keeps it.
    """

    MARKER_KEY = 'siteimport_targetinstance'

    def __init__(self, path, target=None):
        self.path = path
        self.target = target
        self._data = {}
        if os.path.exists(path):
            with open(path) as handle:
                self._data = json.load(handle)
            self._check_target()

    def _check_target(self):
        if not self.target:
            return
        seen = self._data.get('_target')
        if seen is None:
            # Written before this check existed. Adopt it rather than refuse:
            # refusing would strand a crosswalk that is probably fine, and the
            # next run is bound properly.
            self._data['_target'] = self.target
            self.save()
            return
        if seen != self.target:
            raise StaleIdMapError(
                '%s was built against target %s, but this run targets %s.\n'
                'Those assetids belong to a different database and using them '
                'would attach imported rows to the wrong assets.\n'
                'Delete the file to start a fresh crosswalk, or point '
                '--idmap at the one for this target.'
                % (self.path, seen, self.target))

    def put(self, namespace, legacy, new):
        self._data.setdefault(namespace, {})[str(legacy)] = new
        self.save()

    def get(self, namespace, legacy, default=None):
        return self._data.get(namespace, {}).get(str(legacy), default)

    def has(self, namespace, legacy):
        return str(legacy) in self._data.get(namespace, {})

    def count(self, namespace):
        entry = self._data.get(namespace, {})
        return len(entry) if isinstance(entry, dict) else 0

    def save(self):
        with open(self.path, 'w') as handle:
            json.dump(self._data, handle, indent=1)


class Harness:
    """App + admin PAT + import-mode test client + id maps."""

    def __init__(self, idmap_path=None):
        self.app = create_app()
        self.appcontext = self.app.app_context()
        self.appcontext.push()
        self._silence_sql_logging()
        self.client = self.app.test_client()
        self._ensure_asset_types()
        self.secret = self._mint_admin_pat()
        default = os.path.join(os.path.dirname(__file__), 'idmap.json')
        self.ids = IdMap(idmap_path or default, target=self._target_instance())
        self.source = Source()
        self.errors = []
        self._defaultlevelid = None

    def _target_instance(self):
        """A stable id for THIS target database, created once and stored in it.

        Kept in the target's own settings table so it dies when the data does.
        A drop-and-rebuild yields a new id, which is what lets IdMap catch a
        crosswalk carried over from the previous database - the failure that
        silently attaches imported rows to whatever asset now holds that id.

        The database name alone would not do: a rebuild keeps the name.
        """
        from shopdb.core.models import Setting
        existing = Setting.query.filter_by(key=IdMap.MARKER_KEY).first()
        if existing and existing.value:
            return existing.value
        marker = uuid.uuid4().hex
        if existing:
            existing.value = marker
        else:
            db.session.add(Setting(
                key=IdMap.MARKER_KEY, value=marker, valuetype='string',
                category='import',
                description='Identifies this database to the site-import '
                            'crosswalk. Created by the loader; do not copy it '
                            'between databases.'))
        db.session.commit()
        return marker

    @property
    def defaultlevelid(self):
        """The level imported map positions belong to (ADR-017).

        The legacy schema predates levels: it has ONE floor plan, so every
        mapleft/maptop it carries is a coordinate on this site's default level.
        Importing them without a level produces markers the map refuses to draw
        - it will not guess a drawing for coordinates that do not name one.
        """
        if self._defaultlevelid is None:
            from shopdb.core.models import MapLevel
            level = MapLevel.default_level()
            self._defaultlevelid = level.levelid if level else None
        return self._defaultlevelid

    def _silence_sql_logging(self):
        import logging
        logging.getLogger('sqlalchemy.engine').setLevel(logging.WARNING)

    def _ensure_asset_types(self):
        """Register each plugin's AssetType + seeded subtypes. on_install (which
        does this) is skipped when a DB is built with `flask plugin upgrade-all`
        rather than a fresh `install`, so run it idempotently here - the create
        routes 500 without the AssetType row."""
        manager = self.app.extensions.get('plugin_manager')
        if not manager:
            return
        for _name, plugin in manager.get_all_plugins().items():
            try:
                plugin.on_install(self.app)
            except Exception:
                pass
        # A full import IS the setup, so mark it complete - otherwise the admin
        # is bounced to the first-run wizard on every fresh import DB.
        from shopdb.core.models import Setting
        Setting.set('setup_complete', 'true', valuetype='boolean', category='site')
        db.session.commit()

    def _mint_admin_pat(self):
        """Create (or reuse) an admin user and an unscoped admin PAT. Unscoped
        because import mode + role gates require full owner authority
        (the IMPORT-API wiki page). Returns the clear secret."""
        from werkzeug.security import generate_password_hash
        from shopdb.core.models import User, Role, ApiToken
        admin = User.query.join(User.roles).filter(Role.rolename == 'admin').first()
        if not admin:
            role = Role.query.filter_by(rolename='admin').first() \
                or Role(rolename='admin', description='Administrator')
            db.session.add(role)
            admin = User(username='importer', email='importer@localhost',
                         passwordhash=generate_password_hash('x'), isactive=True)
            admin.roles.append(role)
            db.session.add(admin)
            db.session.commit()
        secret = ApiToken.generate_secret()
        token = ApiToken(userid=admin.userid, name='wjf legacy import',
                         tokenprefix=ApiToken.prefix_of(secret),
                         tokenhash=ApiToken.hash_secret(secret), scopes=None)
        db.session.add(token)
        db.session.commit()
        return secret

    def _headers(self, import_mode):
        # A PAT authenticates as Authorization: Bearer shopdb_pat_... (the
        # before_request shim resolves it into a JWT identity). X-API-Key is for
        # collector/service tokens, not personal tokens.
        headers = {'Authorization': f'Bearer {self.secret}'}
        if import_mode:
            headers['X-Import-Mode'] = 'true'
        return headers

    def post(self, path, payload, import_mode=True):
        """POST to an import endpoint. Returns (status, data). 409s are returned
        (idempotency handled by the caller), other 4xx/5xx are recorded."""
        resp = self.client.post(path, json=payload, headers=self._headers(import_mode))
        body = resp.get_json() or {}
        data = body.get('data', body)
        if resp.status_code >= 400 and resp.status_code != 409:
            self.errors.append((path, resp.status_code, payload, data))
        return resp.status_code, data

    def get(self, path):
        resp = self.client.get(path, headers=self._headers(False))
        body = resp.get_json() or {}
        return resp.status_code, body.get('data', body)

    def close(self):
        self.ids.save()
        self.appcontext.pop()