ose-core 0.2.5__tar.gz

ose_core-0.2.5/PKG-INFO

@@ -0,0 +1,21 @@
+Metadata-Version: 2.4
+Name: ose-core
+Version: 0.2.5
+Summary: Core library for OntoSpreadEd - Ontology spreadsheet editor
+Requires-Python: >=3.12
+Requires-Dist: pandas
+Requires-Dist: openpyxl
+Requires-Dist: jsonschema
+Requires-Dist: daff
+Requires-Dist: whoosh
+Requires-Dist: networkx
+Requires-Dist: pydot
+Requires-Dist: py-horned-owl
+Requires-Dist: ontoutils
+Requires-Dist: pyyaml
+Requires-Dist: dacite
+Requires-Dist: aiohttp
+Requires-Dist: async-lru
+Provides-Extra: dev
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: ruff; extra == "dev"

ose_core-0.2.5/README.md

@@ -0,0 +1,36 @@
+# OSE Core
+
+Core library for OntoSpreadEd - Ontology Spreadsheet Editor.
+
+## Description
+
+This package contains the business logic, data models, and services for the OntoSpreadEd ontology spreadsheet editor. It provides:
+
+- Data models for ontology entities (classes, properties, individuals)
+- Database schema and migrations (using Alembic)
+- Full-text search index (using Whoosh)
+- Ontology processing and validation
+- Release pipeline framework
+- Plugin system infrastructure
+
+## Installation
+
+```bash
+pip install ose-core
+```
+
+## Requirements
+
+- Python 3.12+
+
+## Dependencies
+
+Key dependencies include:
+- `py-horned-owl` - OWL ontology processing
+- `pandas` / `openpyxl` - Excel file handling
+- `whoosh` - Full-text search
+- `SQLAlchemy` - Database ORM
+
+## License
+
+LGPL-3.0-or-later

ose_core-0.2.5/pyproject.toml

@@ -0,0 +1,38 @@
+[build-system]
+requires = ["setuptools >= 61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "ose-core"
+description = "Core library for OntoSpreadEd - Ontology spreadsheet editor"
+requires-python = ">= 3.12"
+version = "0.2.5"
+
+dependencies = [
+    "pandas",
+    "openpyxl",
+    "jsonschema",
+    "daff",
+    "whoosh",
+    "networkx",
+    "pydot",
+    "py-horned-owl",
+    "ontoutils",
+    "pyyaml",
+    "dacite",
+    "aiohttp",
+    "async-lru",
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest",
+    "ruff",
+]
+
+[tool.setuptools.packages.find]
+where = ["src"]
+include = ["ose", "ose.*"]
+
+[tool.setuptools.package-data]
+"ose.database.migrations" = ["alembic.ini", "script.py.mako", "README"]

ose_core-0.2.5/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

ose_core-0.2.5/src/ose/__init__.py

@@ -0,0 +1,9 @@
+"""
+OSE Core - Core library for OntoSpreadEd
+
+This package contains the business logic, models, and services
+for the OntoSpreadEd ontology spreadsheet editor.
+"""
+
+# Re-export commonly used classes
+from .model import *  # noqa: F401, F403

ose_core-0.2.5/src/ose/commands/CLICommandContext.py

@@ -0,0 +1,49 @@
+import logging
+import os.path
+import shutil
+from tempfile import TemporaryDirectory
+from typing import Optional
+
+from ose.commands.CommandContext import CommandContext
+
+
+class CLICommandContext(CommandContext):
+    _logger = logging.getLogger(__name__)
+
+    _working_dir: str
+    _tempdir: Optional[TemporaryDirectory] = None
+
+    def __init__(self, working_dir: Optional[str] = None):
+        if working_dir is None:
+            self._tempdir = TemporaryDirectory("ose-cli-context")
+            self._working_dir = self._tempdir.name
+        else:
+            self._working_dir = os.path.abspath(working_dir)
+
+    def canceled(self) -> bool:
+        return False
+
+    def local_name(self, remote_name, file_ending=None) -> str:
+        file_name = os.path.join(self._working_dir, remote_name)
+
+        if file_ending is not None:
+            file_name = file_name[:file_name.rfind(".")] + file_ending
+
+        self._logger.debug(f"Local name of '{remote_name}' is '{file_name}' (ending: {file_ending})")
+
+        return file_name
+
+    def save_file(self, file: str, temporary: Optional[bool] = None, **kwargs):
+        target_path = os.path.abspath(os.path.join(self._working_dir, file))
+
+        if os.path.abspath(target_path) != os.path.abspath(file):
+            self._logger.debug(f"Saving file '{file}' to '{target_path}'")
+            shutil.copy2(file, target_path)
+        else:
+            self._logger.debug(f"Saving file '{file}' to '{target_path}' (Already existing)")
+
+    def cleanup(self) -> None:
+        super().cleanup()
+
+        if self._tempdir is not None:
+            self._tempdir.cleanup()

ose_core-0.2.5/src/ose/commands/Command.py

@@ -0,0 +1,29 @@
+import abc
+from typing import Tuple
+
+from .CommandContext import CommandContext
+from ..model.Result import Result
+
+
+class CommandCanceledException(Exception):
+    pass
+
+
+class Command(abc.ABC):
+    _context: CommandContext
+
+    def __init__(self, context: CommandContext):
+        self._context = context
+
+    def run(self, **kwargs) -> Tuple[Result, bool]:
+        ...
+
+    def _raise_if_canceled(self):
+        if self._context.canceled():
+            raise CommandCanceledException("Release has been canceled!")
+
+    def _local_name(self, remote_name, file_ending=None) -> str:
+        return self._context.local_name(remote_name, file_ending)
+
+    def cleanup(self):
+        pass

ose_core-0.2.5/src/ose/commands/CommandContext.py

@@ -0,0 +1,25 @@
+import abc
+from typing import Optional
+
+
+class CommandContext(abc.ABC):
+    @abc.abstractmethod
+    def canceled(self) -> bool:
+        ...
+
+    @abc.abstractmethod
+    def local_name(self, remote_name, file_ending=None) -> str:
+        ...
+
+    @abc.abstractmethod
+    def save_file(self, file: str, temporary: Optional[bool] = None, **kwargs):
+        ...
+
+    def cleanup(self) -> None:
+        pass
+
+    def __enter__(self):
+        return self
+
+    def __exit__(self, exc_type, exc_val, exc_tb):
+        self.cleanup()

ose_core-0.2.5/src/ose/commands/ImportExternalCommand.py

@@ -0,0 +1,87 @@
+import csv
+from typing import List, Tuple, Literal
+
+from .Command import Command
+from ..model.ExcelOntology import ExcelOntology
+from ..model.ReleaseScript import ReleaseScript, ReleaseScriptFile
+from ..model.Result import Result
+from ..services.RobotOntologyBuildService import RobotOntologyBuildService
+
+
+class ReleaseCommand(Command):
+    def _store_target_artifact(self, file: ReleaseScriptFile,
+                               kind: Literal["source", "intermediate", "final"] = "final",
+                               downloadable: bool = True):
+        return self._context.save_file(self._local_name(file.target.file), target_file=file.target.file, kind=kind,
+                                       downloadable=downloadable)
+
+
+class ImportExternalCommand(ReleaseCommand):
+    def run(self, release_script: ReleaseScript, working_dir: str) -> Tuple[Result, bool]:
+        builder = RobotOntologyBuildService()
+
+        result = Result(())
+
+        file = release_script.external
+        ontology = ExcelOntology(file.target.iri)
+        for s in file.sources:
+            xlsx = self._local_name(s.file)
+            result += ontology.add_imported_terms(s.file, xlsx)
+
+            self._raise_if_canceled()
+
+        new_parents: List[Tuple[str, str, Literal["class", "object property", "data_property"]]] = []
+        if file.addParentsFile:
+            with open(self._local_name(file.addParentsFile)) as f:
+                rows = csv.DictReader(f, skipinitialspace=True)
+                for row in rows:
+                    # Skip potential ROBOT header
+                    if row.get("ID") == "ID":
+                        continue
+
+                    id = row.get("ID")
+                    new_parent = row.get("NEW PARENT ID")
+                    type = row.get("TYPE", "class").lower()
+                    if type not in ["class", "object property", "data property"]:
+                        result.warning(type='unknown-owl-type',
+                                       file=file.renameTermFile,
+                                       msg=f"Unknown OWL type '{type}' in column 'TYPE'")
+
+                    new_parents.append((id, new_parent, type))
+
+        renamings: List[Tuple[str, str, Literal["class", "object property", "data_property"]]] = []
+        if file.renameTermFile is not None:
+            with open(self._local_name(file.renameTermFile)) as f:
+                rows = csv.DictReader(f, skipinitialspace=True)
+                for row in rows:
+                    # Skip potential ROBOT header
+                    if row.get("ID") == "ID":
+                        continue
+
+                    id = row.get("ID")
+                    new_label = row.get("NEW LABEL")
+                    type = row.get("TYPE", "class").lower()
+                    if type not in ["class", "object property", "data property"]:
+                        result.warning(type='unknown-owl-type',
+                                       file=file.renameTermFile,
+                                       msg=f"Unknown OWL type '{type}' in column 'TYPE'")
+                        type = "class"
+
+                    renamings.append((id, new_label, type))
+
+        result += builder.merge_imports(
+            ontology.imports(),
+            self._local_name(file.target.file),
+            file.target.iri,
+            release_script.short_repository_name,
+            working_dir,
+            renamings,
+            new_parents
+        )
+
+        self._raise_if_canceled()
+
+        self._store_target_artifact(file, downloadable=False)
+
+        # self._set_release_result(result)
+        return result, result.ok()

ose_core-0.2.5/src/ose/commands/ReleaseCommandContext.py

@@ -0,0 +1,60 @@
+from typing import Optional, Literal
+
+from flask_github import GitHub
+from flask_sqlalchemy import SQLAlchemy
+from sqlalchemy.orm import Query
+
+from .CommandContext import CommandContext
+from ..database.Release import Release, ReleaseArtifact
+from ..model.ReleaseScript import ReleaseScript, ReleaseScriptFile
+from ..release.common import add_artifact, local_name
+from ..services.ConfigurationService import ConfigurationService
+
+
+class ReleaseCommandContext(CommandContext):
+    _config: ConfigurationService
+    _working_dir: str
+    _release_id: int
+    _release_script: ReleaseScript
+    _gh: GitHub
+    _db: SQLAlchemy
+    _q: Query[Release]
+
+    _total_items: Optional[int] = None
+    _current_item: int = 1
+
+    def __init__(self, db: SQLAlchemy, gh: GitHub, release_script: ReleaseScript, release_id: int, tmp: str,
+                 config: ConfigurationService) -> None:
+        self._config = config
+        self._db = db
+        self._gh = gh
+        self._release_script = release_script
+        self._release_id = release_id
+        self._q = db.session.query(Release)
+        self._a = db.session.query(ReleaseArtifact)
+        self._working_dir = tmp
+
+    def canceled(self) -> bool:
+        r: Release = self._q.get(self._release_id)
+        return r.state == "canceled"
+
+    def local_name(self, remote_name, file_ending=None) -> str:
+        return local_name(self._working_dir, remote_name, file_ending)
+
+    def store_artifact(self, local_path: str, target_path: Optional[str] = None,
+                       kind: Optional[Literal["source", "intermediate", "final"]] = None,
+                       downloadable: bool = True) -> None:
+        kind = kind if kind is not None else ("intermediate" if target_path is None else "final")
+
+        artifact = ReleaseArtifact(release_id=self._release_id, local_path=local_path, target_path=target_path,
+                                   kind=kind, downloadable=downloadable)
+
+        add_artifact(self._db, artifact)
+
+    def store_target_artifact(self, file: ReleaseScriptFile,
+                              kind: Literal["source", "intermediate", "final"] = "final",
+                              downloadable: bool = True):
+        return self.store_artifact(self._local_name(file.target.file), file.target.file, kind, downloadable)
+
+    def save_file(self, file: str, temporary: Optional[bool] = None, **kwargs):
+        return self.store_artifact(file, kind="intermediate" if temporary else "final", **kwargs)

ose_core-0.2.5/src/ose/constants.py

@@ -0,0 +1,3 @@
+"""Core constants for OSE"""
+
+RDFS_LABEL = "http://www.w3.org/2000/01/rdf-schema#label"

ose_core-0.2.5/src/ose/database/Base.py

@@ -0,0 +1,5 @@
+from sqlalchemy.orm import DeclarativeBase
+
+
+class Base(DeclarativeBase):
+    pass

ose_core-0.2.5/src/ose/database/NextId.py

@@ -0,0 +1,10 @@
+from sqlalchemy import Column, Integer, String
+
+from .Base import Base
+
+
+class NextId(Base):
+    __tablename__ = 'nextids'
+    id = Column(Integer, primary_key=True)
+    repo_name = Column(String(50))
+    next_id = Column(Integer)

ose_core-0.2.5/src/ose/database/Release.py

@@ -0,0 +1,44 @@
+from sqlalchemy import Integer, String, JSON, DateTime, Boolean, ForeignKey, CheckConstraint
+from sqlalchemy.orm import relationship, mapped_column
+
+from .Base import Base
+
+
+class ReleaseArtifact(Base):
+    __tablename__ = 'release_artifacts'
+
+    id = mapped_column(Integer(), primary_key=True)
+    release_id = mapped_column(Integer(), ForeignKey('releases.id'))
+
+    local_path = mapped_column(String())
+    target_path = mapped_column(String(), nullable=True)
+    downloadable = mapped_column(Boolean(), default=True)
+    kind = mapped_column(String(), CheckConstraint(
+        "kind in ('source', 'intermediate', 'final') and (kind <> 'final' or target_path is not null)"), )
+
+    def as_dict(self):
+        return {c.name: getattr(self, c.name) for c in self.__table__.columns}
+
+
+class Release(Base):
+    __tablename__ = 'releases'
+
+    id = mapped_column(Integer, primary_key=True)
+    state = mapped_column(String(20))
+    running = mapped_column(Boolean(), default=True)
+    step = mapped_column(Integer)
+    details = mapped_column(JSON(none_as_null=True))  # Dict from step nr to step info
+    start = mapped_column(DateTime)
+    started_by = mapped_column(String())
+    end = mapped_column(DateTime)
+    repo = mapped_column(String(20))
+    release_script = mapped_column(JSON(none_as_null=True))
+    worker_id = mapped_column(String(20))
+    local_dir = mapped_column(String())
+
+    artifacts = relationship("ReleaseArtifact", lazy="joined")
+
+    def as_dict(self):
+        val = {c.name: getattr(self, c.name) for c in self.__table__.columns}
+        val["artifacts"] = [a.as_dict() for a in self.artifacts]
+        return val

ose_core-0.2.5/src/ose/database/User.py

@@ -0,0 +1,18 @@
+from typing import Any
+
+from sqlalchemy import Column, Integer, String
+
+from .Base import Base
+
+
+class User(Base):
+    __tablename__ = 'users'
+
+    id = Column(Integer, primary_key=True)
+    github_access_token = Column(String(255))
+    github_id = Column(Integer)
+    github_login = Column(String(255))
+
+    def __init__(self, github_access_token, **kw: Any):
+        super().__init__(**kw)
+        self.github_access_token = github_access_token

ose_core-0.2.5/src/ose/database/__init__.py

@@ -0,0 +1,17 @@
+from os.path import join, dirname
+
+from flask_migrate import Migrate
+from flask_sqlalchemy import SQLAlchemy
+
+db = SQLAlchemy()
+migrate = Migrate()
+
+# Get the migrations directory path relative to this package
+_migrations_dir = join(dirname(__file__),  'migrations')
+
+
+def init_app(app):
+    db.init_app(app)
+    migrate.init_app(app, db, directory=_migrations_dir)
+
+    return db

ose_core-0.2.5/src/ose/database/migrations/README

@@ -0,0 +1 @@
+Single-database configuration for Flask.

ose_core-0.2.5/src/ose/database/migrations/alembic.ini

@@ -0,0 +1,50 @@
+# A generic, single database configuration.
+
+[alembic]
+# template used to generate migration files
+# file_template = %%(rev)s_%%(slug)s
+
+# set to 'true' to run the environment during
+# the 'revision' command, regardless of autogenerate
+# revision_environment = false
+
+
+# Logging configuration
+[loggers]
+keys = root,sqlalchemy,alembic,flask_migrate
+
+[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
+
+[logger_flask_migrate]
+level = INFO
+handlers =
+qualname = flask_migrate
+
+[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

ose_core-0.2.5/src/ose/database/migrations/env.py

@@ -0,0 +1,113 @@
+import logging
+from logging.config import fileConfig
+
+from flask import current_app
+
+from alembic import context
+
+# 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)
+logger = logging.getLogger('alembic.env')
+
+
+def get_engine():
+    try:
+        # this works with Flask-SQLAlchemy<3 and Alchemical
+        return current_app.extensions['migrate'].db.get_engine()
+    except (TypeError, AttributeError):
+        # this works with Flask-SQLAlchemy>=3
+        return current_app.extensions['migrate'].db.engine
+
+
+def get_engine_url():
+    try:
+        return get_engine().url.render_as_string(hide_password=False).replace(
+            '%', '%%')
+    except AttributeError:
+        return str(get_engine().url).replace('%', '%%')
+
+
+# add your model's MetaData object here
+# for 'autogenerate' support
+# from myapp import mymodel
+# target_metadata = mymodel.Base.metadata
+config.set_main_option('sqlalchemy.url', get_engine_url())
+target_db = current_app.extensions['migrate'].db
+
+# 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 get_metadata():
+    if hasattr(target_db, 'metadatas'):
+        return target_db.metadatas[None]
+    return target_db.metadata
+
+
+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("sqlalchemy.url")
+    context.configure(
+        url=url, target_metadata=get_metadata(), literal_binds=True
+    )
+
+    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.
+
+    """
+
+    # this callback is used to prevent an auto-migration from being generated
+    # when there are no changes to the schema
+    # reference: http://alembic.zzzcomputing.com/en/latest/cookbook.html
+    def process_revision_directives(context, revision, directives):
+        if getattr(config.cmd_opts, 'autogenerate', False):
+            script = directives[0]
+            if script.upgrade_ops.is_empty():
+                directives[:] = []
+                logger.info('No changes in schema detected.')
+
+    conf_args = current_app.extensions['migrate'].configure_args
+    if conf_args.get("process_revision_directives") is None:
+        conf_args["process_revision_directives"] = process_revision_directives
+
+    connectable = get_engine()
+
+    with connectable.connect() as connection:
+        context.configure(
+            connection=connection,
+            target_metadata=get_metadata(),
+            **conf_args
+        )
+
+        with context.begin_transaction():
+            context.run_migrations()
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

ose_core-0.2.5/src/ose/database/migrations/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"}