feat(dev): heavily improve post to portal;

- Added DB model for portal sync tracking.
- Heaving improved copy-datasets and PortalUpdater code to catch all exceptions and log them.
- Added logic actions and views to show all the new stuff.

ckanext/canada/auth.py

@@ -1,5 +1,6 @@
 from ckan.plugins.toolkit import chained_auth_function, config
 from ckan.authz import has_user_permission_for_group_or_org, is_sysadmin
+from ckan.plugins import plugin_loaded
 
 
 def _is_reporting_user(context):
@@ -10,19 +11,19 @@ def _is_reporting_user(context):
 # block datastore-modifying APIs on the portal
 @chained_auth_function
 def datastore_create(up_func, context, data_dict):
-    if 'canada_internal' not in config.get('ckan.plugins'):
+    if not plugin_loaded('canada_internal'):
         return {'success': False}
     return up_func(context, data_dict)
 
 @chained_auth_function
 def datastore_delete(up_func, context, data_dict):
-    if 'canada_internal' not in config.get('ckan.plugins'):
+    if not plugin_loaded('canada_internal'):
         return {'success': False}
     return up_func(context, data_dict)
 
 @chained_auth_function
 def datastore_upsert(up_func, context, data_dict):
-    if 'canada_internal' not in config.get('ckan.plugins'):
+    if not plugin_loaded('canada_internal'):
         return {'success': False}
     return up_func(context, data_dict)
 
@@ -51,3 +52,21 @@ def organization_list(context, data_dict):
 
 def organization_show(context, data_dict):
     return {'success': bool(context.get('user'))}
+
+
+def portal_sync_info(context, data_dict):
+    """
+    Registry users have to be logged in.
+
+    Anyone on public Portal can access.
+    """
+    if plugin_loaded('canada_internal'):
+        return {'success': bool(context.get('user'))}
+    return {'success': True}
+
+
+def list_out_of_sync_packages(context, data_dict):
+    """
+    Only sysadmins can list the out of sync packages.
+    """
+    return {'success': False}

ckanext/canada/logic.py

@@ -37,6 +37,9 @@
 from ckanext.scheming.helpers import scheming_get_preset
 
 from ckanext.datastore.backend import DatastoreBackend
+from ckanext.canada import model as canada_model
+
+from ckanapi import RemoteCKAN
 
 MIMETYPES_AS_DOMAINS = [
     'application/x-msdos-program',  # .com
@@ -529,3 +532,56 @@ def canada_datastore_run_triggers(up_func, context, data_dict):
         context['connection'] = backend._get_write_engine().connect()
     with datastore_create_temp_user_table(context, drop_on_commit=False):
         return up_func(context, data_dict)
+
+
+@side_effect_free
+def portal_sync_info(context, data_dict):
+    """
+    Returns PackageSync object for a given package_id if it exists.
+    """
+    package_id = get_or_bust(data_dict, 'id')
+
+    check_access('portal_sync_info', context, data_dict)
+
+    sync_info = canada_model.PackageSync.get(package_id=package_id)
+
+    if not sync_info:
+        raise ObjectNotFound(_('No Portal Sync information found for package %s') % package_id)
+
+    # NOTE: never show sync_info.error as it contains stack traces and system information
+    return {
+        'package_id': sync_info.package_id,
+        'created': sync_info.created,
+        'last_successful_sync': sync_info.last_successful_sync,
+        'error_on': sync_info.error_on,
+    }
+
+
+@side_effect_free
+def list_out_of_sync_packages(context, data_dict):
+    """
+    Returns a list of out of sync packages on the Portal.
+
+    Based on PackageSync model.
+    """
+    check_access('portal_sync_info', context, data_dict)
+
+    limit = data_dict.get('limit', 25)
+
+    sync_infos = model.Session.query(canada_model.PackageSync).filter(canada_model.PackageSync.error_on != None).limit(limit)
+
+    if not sync_infos:
+        return []
+
+    out_of_sync_packages = []
+
+    for sync_info in sync_infos:
+        try:
+            pkg_dict = get_action('package_show')({'user': context.get('user')}, {'id': sync_info.package_id})
+        except (ObjectNotFound, NotAuthorized):
+            continue
+        # NOTE: never show sync_info.error as it contains stack traces and system information
+        out_of_sync_packages.append({'pkg_dict': pkg_dict, 'last_successful_sync': sync_info.last_successful_sync,
+                                     'error_on': sync_info.error_on})
+
+    return out_of_sync_packages

ckanext/canada/migration/canada_public/README

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

ckanext/canada/migration/canada_public/alembic.ini

@@ -0,0 +1,74 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts
+script_location = %(here)s
+
+# template used to generate migration files
+# file_template = %%(rev)s_%%(slug)s
+
+# 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 /srv/app/ckan/registry/src/ckanext-canada/ckanext/canada/migration/canada_public/versions.  When using multiple version
+# directories, initial revisions must be specified with --version-path
+# version_locations = %(here)s/bar %(here)s/bat /srv/app/ckan/registry/src/ckanext-canada/ckanext/canada/migration/canada_public/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
+
+
+# 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

ckanext/canada/migration/canada_public/env.py

@@ -0,0 +1,81 @@
+# -*- coding: utf-8 -*-
+
+from __future__ import with_statement
+from alembic import context
+from sqlalchemy import engine_from_config, pool
+from logging.config import fileConfig
+
+import os
+
+# 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
+
+# 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.
+
+name = os.path.basename(os.path.dirname(__file__))
+
+
+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 = config.get_main_option(u"sqlalchemy.url")
+    context.configure(
+        url=url, target_metadata=target_metadata, literal_binds=True,
+        version_table=u'{}_alembic_version'.format(name)
+    )
+
+    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.
+
+    """
+    connectable = engine_from_config(
+        config.get_section(config.config_ini_section),
+        prefix=u'sqlalchemy.',
+        poolclass=pool.NullPool)
+
+    with connectable.connect() as connection:
+        context.configure(
+            connection=connection,
+            target_metadata=target_metadata,
+            version_table=u'{}_alembic_version'.format(name)
+        )
+
+        with context.begin_transaction():
+            context.run_migrations()
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

ckanext/canada/migration/canada_public/script.py.mako

@@ -0,0 +1,24 @@
+"""${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"}

ckanext/canada/migration/canada_public/versions/0ef791477ff0_.py

@@ -0,0 +1,36 @@
+"""empty message
+
+Revision ID: 0ef791477ff0
+Revises:
+Create Date: 2024-10-18 18:20:50.040861
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = '0ef791477ff0'
+down_revision = None
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    from ckanext.canada.model import PackageSync
+    if PackageSync.__table__.exists():
+        print('%s database table already exists' % PackageSync.__tablename__)
+        return
+    PackageSync.__table__.create()
+    print('%s database table created' % PackageSync.__tablename__)
+    pass
+
+
+def downgrade():
+    from ckanext.canada.model import PackageSync
+    if not PackageSync.__table__.exists():
+        print('%s database table not present' % PackageSync.__tablename__)
+        return
+    PackageSync.__table__.drop()
+    print('%s database table deleted' % PackageSync.__tablename__)
+    pass