graflo 1.1.0__tar.gz

graflo-1.1.0/.gitignore

@@ -0,0 +1,79 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+*.pyc
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.idea
+.Python
+env/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*,cover
+.hypothesis/
+
+# Translations
+*.mo
+*.pot
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+#Ipython Notebook
+.ipynb_checkpoints
+
+#Latex
+*.aux
+*.fdb_latexmk
+*.fls
+*.log
+*.synctex.gz
+
+# cache
+.pytest_cache
+
+.mypy_cache
+
+*.log.*
+#*/**/*png
+*/**/*pdf
+
+site/

graflo-1.1.0/LICENSE

@@ -0,0 +1,126 @@
+Business Source License 1.1
+
+Parameters
+
+Licensor:             Growgraph SAS
+Licensed Work:        GraFlo
+                      The Licensed Work is (c) 2025 GraFlo
+                      Formerly GraphCast
+
+Additional Use Grant:
+    The Licensor hereby grants you the right to make production use of the Licensed Work
+    if any of the following conditions are met:
+
+    - Your organization's annual revenue does not exceed USD 100,000
+    - You are not offering a commercially available product or service that
+        competes with the Licensor's products or services
+
+Definitions:
+    "Production Use" means any use of the Licensed Work in a production environment,
+        including but not limited to:
+
+    - Deploying the Licensed Work to serve production traffic
+    - Using the Licensed Work to process real customer data
+    - Incorporating the Licensed Work into a commercial product or service
+    - Using the Licensed Work to generate revenue directly or indirectly
+
+"Competing Product or Service" means any product or service that:
+
+    - Provides substantially similar functionality to the Licensed Work
+    - Offers the Licensed Work as a hosted or managed service
+    - Incorporates the Licensed Work into a broader product or service that competes
+        with the Licensor's current or reasonably anticipated products or services
+
+"Non-Production Use" means:
+
+    - Development and testing in isolated environments
+    - Academic research and educational purposes
+    - Evaluation of the Licensed Work for potential purchase of a commercial license
+    - Personal, non-commercial projects where the Licensed Work is not used to generate revenue
+
+Change Date:          2029-05-01
+
+Change License:       Apache License, Version 2.0
+
+For information about alternative licensing arrangements for the Software,
+please contact: <team@growgraph.dev>
+
+Notice
+
+The Business Source License (this document, or the “License”) is not an Open
+Source license. However, the Licensed Work will eventually be made available
+under an Open Source License, as stated in this License.
+
+License text copyright (c) 2017 MariaDB Corporation Ab, All Rights Reserved.
+“Business Source License” is a trademark of MariaDB Corporation Ab.
+
+-----------------------------------------------------------------------------
+
+Business Source License 1.1
+
+Terms
+
+The Licensor hereby grants you the right to copy, modify, create derivative
+works, redistribute, and make non-production use of the Licensed Work. The
+Licensor may make an Additional Use Grant, above, permitting limited
+production use.
+
+Effective on the Change Date, or the fourth anniversary of the first publicly
+available distribution of a specific version of the Licensed Work under this
+License, whichever comes first, the Licensor hereby grants you rights under
+the terms of the Change License, and the rights granted in the paragraph
+above terminate.
+
+If your use of the Licensed Work does not comply with the requirements
+currently in effect as described in this License, you must purchase a
+commercial license from the Licensor, its affiliated entities, or authorized
+resellers, or you must refrain from using the Licensed Work.
+
+All copies of the original and modified Licensed Work, and derivative works
+of the Licensed Work, are subject to this License. This License applies
+separately for each version of the Licensed Work and the Change Date may vary
+for each version of the Licensed Work released by Licensor.
+
+You must conspicuously display this License on each original or modified copy
+of the Licensed Work. If you receive the Licensed Work in original or
+modified form from a third party, the terms and conditions set forth in this
+License apply to your use of that work.
+
+Any use of the Licensed Work in violation of this License will automatically
+terminate your rights under this License for the current and all other
+versions of the Licensed Work.
+
+This License does not grant you any right in any trademark or logo of
+Licensor or its affiliates (provided that you may use a trademark or logo of
+Licensor as expressly required by this License).
+
+TO THE EXTENT PERMITTED BY APPLICABLE LAW, THE LICENSED WORK IS PROVIDED ON
+AN “AS IS” BASIS. LICENSOR HEREBY DISCLAIMS ALL WARRANTIES AND CONDITIONS,
+EXPRESS OR IMPLIED, INCLUDING (WITHOUT LIMITATION) WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, NON-INFRINGEMENT, AND
+TITLE.
+
+MariaDB hereby grants you permission to use this License’s text to license
+your works, and to refer to it using the trademark “Business Source License”,
+as long as you comply with the Covenants of Licensor below.
+
+Covenants of Licensor
+
+In consideration of the right to use this License’s text and the “Business
+Source License” name and trademark, Licensor covenants to MariaDB, and to all
+other recipients of the licensed work to be provided by Licensor:
+
+1. To specify as the Change License the GPL Version 2.0 or any later version,
+   or a license that is compatible with GPL Version 2.0 or a later version,
+   where “compatible” means that software provided under the Change License can
+   be included in a program with software provided under GPL Version 2.0 or a
+   later version. Licensor may specify additional Change Licenses without
+   limitation.
+
+2. To either: (a) specify an additional grant of rights to use that does not
+   impose any additional restriction on the right granted in this License, as
+   the Additional Use Grant; or (b) insert the text “None”.
+
+3. To specify a Change Date.
+
+4. Not to modify this License in any other way.

graflo-1.1.0/PKG-INFO

@@ -0,0 +1,157 @@
+Metadata-Version: 2.4
+Name: graflo
+Version: 1.1.0
+Summary: (!) Deprecated: this package has been renamed to GraFlo. A framework for transforming tabular (CSV, SQL) and hierarchical data (JSON, XML) into property graphs and ingesting them into graph databases (ArangoDB, Neo4j)
+Author-email: Alexander Belikov <alexander@growgraph.dev>
+License-File: LICENSE
+Requires-Python: ~=3.11.0
+Requires-Dist: click<9,>=8.2.0
+Requires-Dist: ijson<4,>=3.2.3
+Requires-Dist: neo4j<6,>=5.22.0
+Requires-Dist: networkx~=3.3
+Requires-Dist: pandas-stubs==2.3.0.250703
+Requires-Dist: pandas<3,>=2.0.3
+Requires-Dist: python-arango<9,>=8.1.2
+Requires-Dist: suthing<0.5,>=0.4.1
+Requires-Dist: xmltodict<0.15,>=0.14.2
+Description-Content-Type: text/markdown
+
+# GraFlo <img src="https://raw.githubusercontent.com/growgraph/graflo/main/docs/assets/favicon.ico" alt="graflo logo" style="height: 32px; width:32px;"/>
+
+A framework for transforming **tabular** (CSV, SQL) and **hierarchical** data (JSON, XML) into property graphs and ingesting them into graph databases (ArangoDB, Neo4j).
+
+> **⚠️ Package Renamed**: This package was formerly known as `graphcast`.
+
+[Rest of your existing README content...]
+
+![Python](https://img.shields.io/badge/python-3.11-blue.svg) 
+[![PyPI version](https://badge.fury.io/py/graflo.svg)](https://badge.fury.io/py/graflo)
+[![PyPI Downloads](https://static.pepy.tech/badge/graflo)](https://pepy.tech/projects/graflo)
+[![License: BSL](https://img.shields.io/badge/license-BSL--1.1-green)](https://github.com/growgraph/graflo/blob/main/LICENSE)
+[![pre-commit](https://github.com/growgraph/graflo/actions/workflows/pre-commit.yml/badge.svg)](https://github.com/growgraph/graflo/actions/workflows/pre-commit.yml)
+[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.15446131.svg)]( https://doi.org/10.5281/zenodo.15446131)
+
+## Core Concepts
+
+### Property Graphs
+graflo works with property graphs, which consist of:
+
+- **Vertices**: Nodes with properties and optional unique identifiers
+- **Edges**: Relationships between vertices with their own properties
+- **Properties**: Both vertices and edges may have properties
+
+### Schema
+The Schema defines how your data should be transformed into a graph and contains:
+
+- **Vertex Definitions**: Specify vertex types, their properties, and unique identifiers
+- **Edge Definitions**: Define relationships between vertices and their properties
+- **Resource Mapping**: describe how data sources map to vertices and edges
+- **Transforms**: Modify data during the casting process
+
+### Resources
+Resources are your data sources that can be:
+
+- **Table-like**: CSV files, database tables
+- **JSON-like**: JSON files, nested data structures
+
+## Features
+
+- **Graph Transformation Meta-language**: A powerful declarative language to describe how your data becomes a property graph:
+    - Define vertex and edge structures
+    - Set compound indexes for vertices and edges
+    - Use blank vertices for complex relationships
+    - Specify edge constraints and properties
+    - Apply advanced filtering and transformations
+- **Parallel processing**: Use as many cores as you have
+- **Database support**: Ingest into ArangoDB and Neo4j using the same API (database agnostic)
+
+## Documentation
+Full documentation is available at: [growgraph.github.io/graflo](https://growgraph.github.io/graflo)
+
+## Installation
+
+```bash
+pip install graflo
+```
+
+## Usage Examples
+
+### Simple ingest
+
+```python
+from suthing import ConfigFactory, FileHandle
+
+from graflo import Schema, Caster, Patterns
+
+
+schema = Schema.from_dict(FileHandle.load("schema.yaml"))
+
+conn_conf = ConfigFactory.create_config({
+        "protocol": "http",
+        "hostname": "localhost",
+        "port": 8535,
+        "username": "root",
+        "password": "123",
+        "database": "_system",
+}
+)
+
+patterns = Patterns.from_dict(
+    {
+        "patterns": {
+            "work": {"regex": "\Sjson$"},
+        }
+    }
+)
+
+schema.fetch_resource()
+
+caster = Caster(
+    schema,
+)
+
+caster.ingest_files(
+    path="./data",
+    conn_conf=conn_conf,
+    patterns=patterns,
+)
+```
+
+## Development
+
+To install requirements
+
+```shell
+git clone git@github.com:growgraph/graflo.git && cd graflo
+uv sync --dev
+```
+
+### Tests
+
+#### Test databases
+Spin up Arango from [arango docker folder](./docker/arango) by
+
+```shell
+docker-compose --env-file .env up arango
+```
+
+and Neo4j from [neo4j docker folder](./docker/arango) by
+
+```shell
+docker-compose --env-file .env up neo4j
+```
+
+To run unit tests
+
+```shell
+pytest test
+```
+
+## Requirements
+
+- Python 3.11+
+- python-arango
+
+## Contributing
+
+Contributions are welcome! Please feel free to submit a Pull Request.

graflo-1.1.0/README.md

@@ -0,0 +1,139 @@
+# GraFlo <img src="https://raw.githubusercontent.com/growgraph/graflo/main/docs/assets/favicon.ico" alt="graflo logo" style="height: 32px; width:32px;"/>
+
+A framework for transforming **tabular** (CSV, SQL) and **hierarchical** data (JSON, XML) into property graphs and ingesting them into graph databases (ArangoDB, Neo4j).
+
+> **⚠️ Package Renamed**: This package was formerly known as `graphcast`.
+
+[Rest of your existing README content...]
+
+![Python](https://img.shields.io/badge/python-3.11-blue.svg) 
+[![PyPI version](https://badge.fury.io/py/graflo.svg)](https://badge.fury.io/py/graflo)
+[![PyPI Downloads](https://static.pepy.tech/badge/graflo)](https://pepy.tech/projects/graflo)
+[![License: BSL](https://img.shields.io/badge/license-BSL--1.1-green)](https://github.com/growgraph/graflo/blob/main/LICENSE)
+[![pre-commit](https://github.com/growgraph/graflo/actions/workflows/pre-commit.yml/badge.svg)](https://github.com/growgraph/graflo/actions/workflows/pre-commit.yml)
+[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.15446131.svg)]( https://doi.org/10.5281/zenodo.15446131)
+
+## Core Concepts
+
+### Property Graphs
+graflo works with property graphs, which consist of:
+
+- **Vertices**: Nodes with properties and optional unique identifiers
+- **Edges**: Relationships between vertices with their own properties
+- **Properties**: Both vertices and edges may have properties
+
+### Schema
+The Schema defines how your data should be transformed into a graph and contains:
+
+- **Vertex Definitions**: Specify vertex types, their properties, and unique identifiers
+- **Edge Definitions**: Define relationships between vertices and their properties
+- **Resource Mapping**: describe how data sources map to vertices and edges
+- **Transforms**: Modify data during the casting process
+
+### Resources
+Resources are your data sources that can be:
+
+- **Table-like**: CSV files, database tables
+- **JSON-like**: JSON files, nested data structures
+
+## Features
+
+- **Graph Transformation Meta-language**: A powerful declarative language to describe how your data becomes a property graph:
+    - Define vertex and edge structures
+    - Set compound indexes for vertices and edges
+    - Use blank vertices for complex relationships
+    - Specify edge constraints and properties
+    - Apply advanced filtering and transformations
+- **Parallel processing**: Use as many cores as you have
+- **Database support**: Ingest into ArangoDB and Neo4j using the same API (database agnostic)
+
+## Documentation
+Full documentation is available at: [growgraph.github.io/graflo](https://growgraph.github.io/graflo)
+
+## Installation
+
+```bash
+pip install graflo
+```
+
+## Usage Examples
+
+### Simple ingest
+
+```python
+from suthing import ConfigFactory, FileHandle
+
+from graflo import Schema, Caster, Patterns
+
+
+schema = Schema.from_dict(FileHandle.load("schema.yaml"))
+
+conn_conf = ConfigFactory.create_config({
+        "protocol": "http",
+        "hostname": "localhost",
+        "port": 8535,
+        "username": "root",
+        "password": "123",
+        "database": "_system",
+}
+)
+
+patterns = Patterns.from_dict(
+    {
+        "patterns": {
+            "work": {"regex": "\Sjson$"},
+        }
+    }
+)
+
+schema.fetch_resource()
+
+caster = Caster(
+    schema,
+)
+
+caster.ingest_files(
+    path="./data",
+    conn_conf=conn_conf,
+    patterns=patterns,
+)
+```
+
+## Development
+
+To install requirements
+
+```shell
+git clone git@github.com:growgraph/graflo.git && cd graflo
+uv sync --dev
+```
+
+### Tests
+
+#### Test databases
+Spin up Arango from [arango docker folder](./docker/arango) by
+
+```shell
+docker-compose --env-file .env up arango
+```
+
+and Neo4j from [neo4j docker folder](./docker/arango) by
+
+```shell
+docker-compose --env-file .env up neo4j
+```
+
+To run unit tests
+
+```shell
+pytest test
+```
+
+## Requirements
+
+- Python 3.11+
+- python-arango
+
+## Contributing
+
+Contributions are welcome! Please feel free to submit a Pull Request.

graflo-1.1.0/graflo/README.md

@@ -0,0 +1,18 @@
+### Table Config  
+
+Table part of the config specifies how input sources will be transformed and mapped to vertex collections.
+
+```yaml
+table:
+-   tabletype: ibes
+    encoding: ISO-8859-1
+    transforms:
+    -   foo: parse_date_ibes
+        module: graflo.util.transform
+        input:
+        -   ANNDATS
+        -   ANNTIMS
+        output:
+        -   datetime_announce
+```
+

graflo-1.1.0/graflo/__init__.py

@@ -0,0 +1,39 @@
+"""graflo: A flexible graph database abstraction layer.
+
+graflo provides a unified interface for working with different graph databases
+(ArangoDB, Neo4j) through a common API. It handles graph operations, data
+transformations, and query generation while abstracting away database-specific
+details.
+
+Key Features:
+    - Database-agnostic graph operations
+    - Flexible schema management
+    - Query generation and execution
+    - Data transformation utilities
+    - Filter expression system
+
+Example:
+    >>> from graflo.db.manager import ConnectionManager
+    >>> with ConnectionManager(config) as conn:
+    ...     conn.init_db(schema, clean_start=True)
+    ...     conn.upsert_docs_batch(docs, "users")
+"""
+
+from .architecture import Index, Schema
+from .caster import Caster
+from .db import ConnectionManager, ConnectionType
+from .filter.onto import ComparisonOperator, LogicalOperator
+from .onto import AggregationType
+from .util.onto import Patterns
+
+__all__ = [
+    "Caster",
+    "ConnectionManager",
+    "ConnectionType",
+    "ComparisonOperator",
+    "LogicalOperator",
+    "Index",
+    "Schema",
+    "Patterns",
+    "AggregationType",
+]

graflo-1.1.0/graflo/architecture/__init__.py

@@ -0,0 +1,37 @@
+"""Graph database architecture components.
+
+This package defines the core architecture components for graph database operations,
+including schema management, resource handling, and data transformations.
+
+Key Components:
+    - Schema: Graph database schema definition and management
+    - Resource: Data resource management and processing
+    - Transform: Data transformation and standardization
+    - Vertex: Vertex collection configuration
+    - Edge: Edge collection configuration
+
+Example:
+    >>> from graflo.architecture import Schema, Resource
+    >>> schema = Schema(
+    ...     general={"name": "my_graph", "version": "1.0"},
+    ...     vertex_config=vertex_config,
+    ...     edge_config=edge_config
+    ... )
+    >>> resource = Resource(name="users", data=user_data)
+"""
+
+from .edge import Edge, EdgeConfig
+from .onto import Index
+from .resource import Resource
+from .schema import Schema
+from .vertex import Vertex, VertexConfig
+
+__all__ = [
+    "Edge",
+    "EdgeConfig",
+    "Index",
+    "Resource",
+    "Schema",
+    "Vertex",
+    "VertexConfig",
+]