avrokit 0.0.1__tar.gz

avrokit-0.0.1/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2026 Greg Brandt
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

avrokit-0.0.1/PKG-INFO

@@ -0,0 +1,485 @@
+Metadata-Version: 2.4
+Name: avrokit
+Version: 0.0.1
+Summary: Python utilities for working with Avro data files
+License: Apache-2.0
+License-File: LICENSE
+Keywords: avro,data,serialization,gcs,s3,parquet
+Author: Greg Brandt
+Author-email: brandt.greg@gmail.com
+Requires-Python: >=3.12,<4.0
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Typing :: Typed
+Provides-Extra: all
+Provides-Extra: aws
+Provides-Extra: gcp
+Requires-Dist: avro (>=1.12.1,<2.0.0)
+Requires-Dist: boto3 (>=1.38.7,<2.0.0) ; extra == "aws" or extra == "all"
+Requires-Dist: boto3-stubs[s3] (>=1.38.8,<2.0.0)
+Requires-Dist: datetime-truncate (>=1.1.1,<2.0.0)
+Requires-Dist: filelock (>=3.18.0,<4.0.0)
+Requires-Dist: google-cloud-storage (>=3.6.0,<4.0.0) ; extra == "gcp" or extra == "all"
+Requires-Dist: google-crc32c (>=1.7.1,<2.0.0) ; extra == "gcp" or extra == "all"
+Requires-Dist: pyarrow (>=22.0.0,<23.0.0)
+Requires-Dist: requests (>=2.32.3,<3.0.0)
+Requires-Dist: types-requests (>=2.32.0.20250328,<3.0.0.0)
+Project-URL: Homepage, https://github.com/brandtg/avrokit
+Project-URL: Repository, https://github.com/brandtg/avrokit
+Description-Content-Type: text/markdown
+
+<!--
+SPDX-FileCopyrightText: 2026 Greg Brandt <brandt.greg@gmail.com>
+
+SPDX-License-Identifier: Apache-2.0
+-->
+
+# avrokit
+
+Python utilities for working with Avro data files with support for local files, GCS, S3, and HTTP/HTTPS URLs.
+
+## Features
+
+- **Unified URL Interface**: Read and write Avro files transparently across local filesystem, GCS, S3, and HTTP/HTTPS
+- **CLI Tools**: Comprehensive command-line tools for common Avro operations
+- **Python API**: Rich programmatic interface for reading, writing, and transforming Avro data
+- **Partitioned I/O**: Support for reading and writing partitioned/multi-file datasets
+- **Async Support**: Non-blocking I/O primitives for high-throughput applications
+- **Parquet Conversion**: Bidirectional conversion between Avro and Parquet formats
+- **Schema Operations**: Schema extraction, validation, and evolution checking
+
+## Installation
+
+### Basic Installation
+
+```bash
+pip install avrokit
+```
+
+### With Cloud Storage Support
+
+```bash
+# AWS S3 support
+pip install avrokit[aws]
+
+# Google Cloud Storage support
+pip install avrokit[gcp]
+
+# All extras (S3 + GCS)
+pip install avrokit[all]
+```
+
+### Development Installation
+
+```bash
+git clone https://github.com/brandtg/avrokit.git
+cd avrokit
+poetry env use python3.12
+make install
+```
+
+## Quick Start
+
+### CLI Usage
+
+```bash
+# View statistics for an Avro file
+avrokit stats gs://bucket/data.avro
+
+# Convert Avro to JSON
+avrokit tojson s3://bucket/data.avro > output.json
+
+# Extract sample records
+avrokit cat file:///path/to/data.avro --limit 10
+
+# Get schema
+avrokit getschema data.avro
+
+# Convert to Parquet
+avrokit toparquet data.avro output.parquet
+
+# Concatenate multiple files
+avrokit concat file1.avro file2.avro s3://bucket/file3.avro output.avro
+```
+
+### Python API
+
+```python
+from avrokit import avro_reader, avro_records, avro_writer, avro_schema, parse_url
+
+# Read records from any URL
+url = parse_url('gs://bucket/data.avro', mode='rb')
+for record in avro_records(url):
+    print(record)
+
+# Write Avro data
+schema = avro_schema({
+    'type': 'record',
+    'name': 'User',
+    'fields': [
+        {'name': 'name', 'type': 'string'},
+        {'name': 'age', 'type': 'int'}
+    ]
+})
+
+url = parse_url('output.avro', mode='wb')
+with avro_writer(url, schema) as writer:
+    writer.append({'name': 'Alice', 'age': 30})
+    writer.append({'name': 'Bob', 'age': 25})
+```
+
+## Architecture
+
+avrokit is organized into four main layers:
+
+### 1. URL Layer (`avrokit.url`)
+
+Provides a unified abstraction over different storage backends. All URL types implement the `URL` protocol with common operations:
+
+- **`URL`** (base protocol): Abstract interface for all URL types
+- **`FileURL`**: Local filesystem access with glob pattern support
+- **`GCSURL`**: Google Cloud Storage via `google-cloud-storage`
+- **`S3URL`**: Amazon S3 via `boto3`
+- **`HTTPURL`**: HTTP/HTTPS with range request support for streaming
+
+The `parse_url()` factory function automatically instantiates the correct URL class based on the scheme:
+
+```python
+from avrokit.url import parse_url
+
+# All of these return the appropriate URL subclass
+url1 = parse_url('file:///path/to/data.avro')      # FileURL
+url2 = parse_url('gs://bucket/data.avro')           # GCSURL
+url3 = parse_url('s3://bucket/data.avro')           # S3URL
+url4 = parse_url('https://example.com/data.avro')   # HTTPURL
+```
+
+### 2. I/O Layer (`avrokit.io`)
+
+High-level Avro reading and writing primitives built on the URL layer:
+
+**Reading:**
+
+- `avro_reader(url)`: Context manager for `DataFileReader`
+- `avro_records(url)`: Generator yielding records as dictionaries
+- `PartitionedAvroReader`: Reads from multiple files or glob patterns as a single stream
+
+**Writing:**
+
+- `avro_writer(url, schema)`: Context manager for `DataFileWriter`
+- `PartitionedAvroWriter`: Writes to multiple files with configurable size limits
+- `TimePartitionedAvroWriter`: Time-based partitioning (e.g., hourly/daily files)
+
+**Schema Operations:**
+
+- `avro_schema(dict)`: Create schema from dictionary
+- `read_avro_schema(url)`: Extract schema from file
+- `validate_avro_schema_evolution()`: Check backward/forward compatibility
+- `add_avro_schema_fields()`: Schema augmentation utilities
+
+**Utilities:**
+
+- `compact_avro_data()`: Remove deleted/updated records by key
+
+### 3. Async I/O Layer (`avrokit.asyncio`)
+
+Non-blocking primitives for async applications:
+
+- `DeferredAvroWriter`: Async writer that batches records and flushes in background
+- `BlockingQueueAvroReader`: Queue-based async reader for producer/consumer patterns
+
+### 4. Tools Layer (`avrokit.tools`)
+
+CLI commands implemented as classes following the `Tool` protocol:
+
+| Tool              | Command       | Description                                          |
+| ----------------- | ------------- | ---------------------------------------------------- |
+| `CatTool`         | `cat`         | Extract sample records with optional random sampling |
+| `ConcatTool`      | `concat`      | Concatenate multiple Avro files into one             |
+| `CountTool`       | `count`       | Count records in files                               |
+| `FileSortTool`    | `filesort`    | Sort records by key across multiple files            |
+| `FromParquetTool` | `fromparquet` | Convert Parquet to Avro                              |
+| `GetMetaTool`     | `getmeta`     | Extract file metadata (schema, compression, etc.)    |
+| `GetSchemaTool`   | `getschema`   | Extract and print schema                             |
+| `HttpServerTool`  | `httpserver`  | Serve Avro files over HTTP with filtering/sampling   |
+| `PartitionTool`   | `partition`   | Split files into multiple partitions                 |
+| `RepairTool`      | `repair`      | Fix corrupted Avro files                             |
+| `StatsTool`       | `stats`       | Compute statistics (count, nulls, sizes)             |
+| `ToJsonTool`      | `tojson`      | Convert to newline-delimited JSON                    |
+| `ToParquetTool`   | `toparquet`   | Convert to Parquet format                            |
+
+## CLI Reference
+
+### Global Options
+
+```
+avrokit --debug <command>    # Enable debug logging
+```
+
+### Available Commands
+
+#### cat - Extract Sample Records
+
+```bash
+avrokit cat FILE [OPTIONS]
+  --limit N          Maximum records to output (default: 10)
+  --sample-rate F    Random sampling rate (0.0-1.0)
+```
+
+#### concat - Concatenate Files
+
+```bash
+avrokit concat INPUT1 [INPUT2 ...] OUTPUT
+  INPUT can be local files, GCS, S3, or HTTP URLs
+  OUTPUT schema must be compatible with all inputs
+```
+
+#### count - Count Records
+
+```bash
+avrokit count FILE [FILE ...]
+  Returns total record count across all files
+```
+
+#### filesort - Sort Records
+
+```bash
+avrokit filesort INPUT OUTPUT --keys KEY1 [KEY2 ...]
+  Sorts records by specified keys using external merge sort
+```
+
+#### fromparquet - Parquet to Avro
+
+```bash
+avrokit fromparquet INPUT.parquet OUTPUT.avro
+```
+
+#### getmeta - File Metadata
+
+```bash
+avrokit getmeta FILE
+  Outputs: schema, codec, sync marker, block count, etc.
+```
+
+#### getschema - Extract Schema
+
+```bash
+avrokit getschema FILE
+  Outputs Avro schema as JSON
+```
+
+#### httpserver - HTTP Server
+
+```bash
+avrokit httpserver --port 8080 --files "*.avro"
+  Serves Avro files with filtering and sampling support
+```
+
+#### partition - Partition Files
+
+```bash
+avrokit partition INPUT OUTPUT --count N
+  Splits INPUT into N approximately equal partitions
+```
+
+#### repair - Fix Corrupted Files
+
+```bash
+avrokit repair INPUT OUTPUT
+  Attempts to recover readable records from damaged files
+```
+
+#### stats - Compute Statistics
+
+```bash
+avrokit stats FILE [FILE ...]
+  Outputs: record count, file sizes, null counts per field
+```
+
+#### tojson - Convert to JSON
+
+```bash
+avrokit tojson FILE [FILE ...]
+  One JSON record per line (newline-delimited JSON)
+```
+
+#### toparquet - Convert to Parquet
+
+```bash
+avrokit toparquet INPUT.avro OUTPUT.parquet
+  Type mapping: Avro types → Parquet types
+```
+
+## Development
+
+### Prerequisites
+
+- Python 3.12+
+- Poetry
+- Docker (for GCS/S3 integration tests)
+
+### Setup
+
+```bash
+# Set up Python environment
+poetry env use python3.12
+
+# Install dependencies
+make install
+
+# Pull fake-gcs-server for testing
+docker pull fsouza/fake-gcs-server
+```
+
+### Running Tests
+
+```bash
+# Run all tests
+make test
+
+# Run with coverage
+make test-coverage
+
+# Run tests in parallel (default)
+poetry run pytest -n auto
+```
+
+### Code Quality
+
+```bash
+# Format code
+make format
+
+# Lint code
+make lint
+
+# Type checking
+make typecheck
+
+# Add license headers
+make license
+```
+
+### Building
+
+```bash
+make build    # Build wheel and source distribution
+```
+
+### Releasing to PyPI
+
+Releases are automated via GitHub Actions using [Trusted Publishing](https://docs.pypi.org/trusted-publishers/) (OIDC) - no API tokens needed.
+
+**One-time PyPI setup:**
+1. Log into [PyPI](https://pypi.org)
+2. Go to your project → Publishing
+3. Add a new pending publisher:
+   - **Owner**: `brandtg`
+   - **Repository**: `avrokit`
+   - **Workflow name**: `release.yml`
+4. Save the configuration
+
+**To release a new version:**
+1. Update version in `pyproject.toml` (e.g., `0.1.1`)
+2. Commit and push the version bump
+3. Go to GitHub → Releases → [Draft a new release](https://github.com/brandtg/avrokit/releases/new)
+4. Create a new tag matching the version (e.g., `v0.1.1`)
+5. Click **Publish release**
+
+The GitHub Actions workflow will automatically build and publish to PyPI.
+
+## Python API Examples
+
+### Working with Partitioned Files
+
+```python
+from avrokit import PartitionedAvroReader, PartitionedAvroWriter, parse_url
+
+# Read from multiple files as single stream
+url = parse_url('data-*.avro', mode='rb')
+with PartitionedAvroReader(url) as reader:
+    for record in reader:
+        process(record)
+
+# Write to multiple files (roll every 10000 records)
+url = parse_url('output/', mode='wb')
+with PartitionedAvroWriter(url, schema, max_records=10000) as writer:
+    for record in records:
+        writer.append(record)
+        if should_roll():
+            writer.roll()  # Create new partition file
+```
+
+### Time-Based Partitioning
+
+```python
+from avrokit import TimePartitionedAvroWriter, parse_url
+from datetime import datetime
+
+# Creates hourly files: output/2024/01/15/10.avro
+url = parse_url('output/', mode='wb')
+with TimePartitionedAvroWriter(
+    url,
+    schema,
+    time_granularity='hour',
+    time_field='timestamp'
+) as writer:
+    for record in records:
+        writer.append(record, timestamp=record['timestamp'])
+```
+
+### Async Operations
+
+```python
+import asyncio
+from avrokit.asyncio import DeferredAvroWriter
+from avrokit import parse_url, avro_schema
+
+async def write_async():
+    url = parse_url('output.avro', mode='wb')
+    schema = avro_schema({...})
+
+    async with DeferredAvroWriter(url, schema) as writer:
+        for record in records:
+            await writer.append(record)
+        # Flushes happen automatically in background
+
+asyncio.run(write_async())
+```
+
+### Schema Evolution
+
+```python
+from avrokit import validate_avro_schema_evolution, read_avro_schema
+from avrokit.url import parse_url
+
+# Check if new schema is backward compatible
+reader_schema = read_avro_schema(parse_url('old.avro', 'rb'))
+writer_schema = read_avro_schema(parse_url('new.avro', 'rb'))
+
+is_valid = validate_avro_schema_evolution(
+    reader_schema,
+    writer_schema,
+    strategy='backward'  # or 'forward', 'full'
+)
+```
+
+## License
+
+Apache-2.0 - See [LICENSE](LICENSE) for details.
+
+## Contributing
+
+Contributions welcome! Please ensure:
+
+1. Code follows the existing style (enforced by `make format` and `make lint`)
+2. All tests pass (`make test`)
+3. Type checks pass (`make typecheck`)
+4. License headers are present (`make license`)
+