structly-whois 1.0.0__tar.gz

structly_whois-1.0.0/.gitignore

@@ -0,0 +1,208 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# 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/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+.ruff.log
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/

structly_whois-1.0.0/CHANGELOG.md

@@ -0,0 +1,47 @@
+# Changelog
+
+All notable changes to this project will be documented here. This project adheres to
+[Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [1.0.0] - 2025-02-14
+
+### Added
+
+- Fallback guard for `.info` domains so callers who pass the domain explicitly always get it back even when registries return `INFO` as the payload's domain label.
+- Targeted unit tests for CLI defaults, domain inference helpers, normalization edge cases, and `.info` parsing paths, plus docs describing the Kafka benchmark batching strategy.
+
+### Changed
+
+- Reorganized the test suite into `tests/unit`, `tests/integration`, and `tests/common` with helper scripts under `tests/scripts`, making it clearer which suites hit fixtures vs. fast-running modules.
+- Updated README/docs examples to reference the new helper module path (`tests.common.helpers`) and use the improved benchmark documentation.
+
+### Fixed
+
+- Addressed Ruff's SIM102 warning in the domain inference registry and ensured `.info` expected fixtures behave consistently across sample-driven tests.
+
+## [0.2.4] - 2025-12-10
+
+### Added
+
+- Ship `tests/report_coverage.py` so maintainers can generate the per-TLD field coverage numbers that back `coverage_report.txt`, making it easier to decide which registries deserve new fixtures next.
+- Expand the WHOIS fixture corpus (Belgium, EU, Sweden, Ukraine, etc.) and expected outputs so regressions in tricky registries are caught by CI instead of surfacing in production.
+
+### Changed
+
+- Domain inference now refreshes itself from every `domain_name` pattern defined in the Structly base fields and overrides, so newly registered TLD configs immediately influence CLI/domain auto-detection without extra plumbing.
+
+### Fixed
+
+- Harden the `.be` override to drop stray single-token statuses (no more `["NOT", "NOT AVAILABLE"]`) and capture registrar/registrant metadata that DNS Belgium hides behind multi-line blocks.
+
+## [0.2.0] - 2024-06-01
+
+- Rename the package from `structly_whois_parser` to `structly_whois` (distribution: `structly-whois`) and expose `__version__` from `__about__.py`.
+- Introduce optional `date_parser: Callable[[str], datetime]` hooks across `WhoisParser` and `build_whois_record`.
+- Add pytest suite (fixtures + Hypothesis), CLI entry point, Ruff tooling, Makefile, and GitHub Actions pipeline (lint → test → build → publish).
+- Provide benchmark harness + marketing-grade docs/README demonstrating throughput vs `whois-parser` and `python-whois`.
+- Document SemVer/tagging strategy and include `py.typed` for downstream type checking.
+
+## [0.1.0] - 2023-xx-xx
+
+- Initial `structly_whois_parser` release (legacy name).

structly_whois-1.0.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Nikola Stankovic
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

structly_whois-1.0.0/PKG-INFO

@@ -0,0 +1,264 @@
+Metadata-Version: 2.4
+Name: structly-whois
+Version: 1.0.0
+Summary: Fast WHOIS parsing core with a Pythonic surface area.
+Project-URL: Homepage, https://gitlab.com/example/structly-whois
+Project-URL: Repository, https://gitlab.com/example/structly-whois
+Project-URL: Issues, https://gitlab.com/example/structly-whois/-/issues
+Author-email: Nikola Stankovic <nstankovic.bg@proton.me>
+License: MIT License
+        
+        Copyright (c) 2025 Nikola Stankovic
+        
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to deal
+        in the Software without restriction, including without limitation the rights
+        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+        copies of the Software, and to permit persons to whom the Software is
+        furnished to do so, subject to the following conditions:
+        
+        The above copyright notice and this permission notice shall be included in all
+        copies or substantial portions of the Software.
+        
+        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+        SOFTWARE.
+License-File: LICENSE
+Keywords: domain,parser,structly,whois
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Internet :: Name Service (DNS)
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.9
+Requires-Dist: msgspec>=0.18
+Requires-Dist: structly>=1.0.1
+Provides-Extra: benchmarks
+Requires-Dist: confluent-kafka>=2.3; extra == 'benchmarks'
+Requires-Dist: orjson>=3.9; extra == 'benchmarks'
+Requires-Dist: python-snappy>=0.6; extra == 'benchmarks'
+Provides-Extra: dev
+Requires-Dist: build>=1.2; extra == 'dev'
+Requires-Dist: confluent-kafka>=2.3; extra == 'dev'
+Requires-Dist: hypothesis>=6.100; extra == 'dev'
+Requires-Dist: maturin>=1.5.1; extra == 'dev'
+Requires-Dist: orjson>=3.9; extra == 'dev'
+Requires-Dist: psutil>=5.9; extra == 'dev'
+Requires-Dist: pytest-cov>=5.0; extra == 'dev'
+Requires-Dist: pytest>=8.2; extra == 'dev'
+Requires-Dist: python-snappy>=0.6; extra == 'dev'
+Requires-Dist: python-whois>=0.9; extra == 'dev'
+Requires-Dist: ruff>=0.5; extra == 'dev'
+Requires-Dist: tabulate>=0.9; extra == 'dev'
+Requires-Dist: whois-parser; extra == 'dev'
+Description-Content-Type: text/markdown
+
+<p align="center">
+  <picture>
+    <source media="(prefers-color-scheme: dark)" srcset="docs/structly_whois.svg">
+    <img src="https://github.com/bytevader/structly-whois-parser/raw/main/docs/structly_whois.svg" alt="structly_whois" width="320">
+  </picture>
+</p>
+<p align="center">
+    <em>Structly-powered WHOIS parsing.</em>
+</p>
+<p align="center">
+<a href="https://github.com/bytevader/structly-whois-parser/actions/workflows/ci.yml?query=branch%3Amain" target="_blank">
+    <img src="https://github.com/bytevader/structly-whois-parser/actions/workflows/ci.yml/badge.svg?branch=main" alt="Main CI">
+</a>
+<a href="https://coverage-badge.samuelcolvin.workers.dev/bytevader/structly-whois-parser.svg?branch=main" target="_blank">
+    <img src="https://coverage-badge.samuelcolvin.workers.dev/bytevader/structly-whois-parser.svg?branch=main" alt="Coverage">
+</a>
+<a href="https://pypi.org/project/structly-whois" target="_blank">
+    <img src="https://img.shields.io/pypi/v/structly-whois?color=%2334D058&label=pypi%20package" alt="PyPI">
+</a>
+</p>
+
+> Fast WHOIS parser powered by [structly](https://pypi.org/project/structly/) and [msgspec](https://pypi.org/project/structly/).
+
+**structly_whois** wraps Structly's compiled parsers with a modern Python API so you can normalize noisy WHOIS payloads, auto-detect TLD-specific overrides, and emit JSON-ready records without hauling heavy regex DSLs or dateparser into your hot path.
+
+## Highlights
+
+- **Structly speed** – Per-TLD configurations are compiled by Structly, keeping parsing under a millisecond/record even on commodity hardware.
+- **Typed surface** – msgspec-based `WhoisRecord` structs, `py.typed` wheels, and a CLI entrypoint (`structly-whois`) for quick inspection.
+- **Configurable** – Inject your own Structly configs, register TLD overrides at runtime, or extend the base field definitions without forking.
+- **Lean dependencies** – No `dateparser` or required by default. Plug in a `date_parser` callable only when locale-aware coercion is truly needed.
+- **Batched & streaming friendly** – `parse_many` and `parse_chunks` let you process millions of payloads from queues, tarballs, or S3 archives without buffering everything in memory.
+
+## Installation
+
+```bash
+pip install structly-whois               # end users
+pip install -e '.[dev]'                  # contributors (installs Ruff, pytest, etc.)
+```
+
+Python 3.9+ is supported. Wheels ship `py.typed` markers for static analyzers.
+
+## Quickstart
+
+```python
+from structly_whois import WhoisParser
+
+parser = WhoisParser()
+payload = """\
+Domain Name: example.com
+Registrar: Example Registrar LLC
+Creation Date: 2020-01-01T12:00:00Z
+Registry Expiry Date: 2030-01-01T12:00:00Z
+Name Server: NS1.EXAMPLE.COM
+Name Server: NS2.EXAMPLE.COM
+Status: clientTransferProhibited https://icann.org/epp#clientTransferProhibited
+Registrant Name: Example DNS
+"""
+
+record = parser.parse_record(payload, domain="example.com")
+print(record.domain)
+print(record.statuses)
+print(record.registered_at)
+print(record.to_dict())
+```
+
+If you omit `domain`, structly_whois inspects the payload to infer the domain/TLD and automatically picks the right Structly configuration.
+
+## CLI usage
+
+```bash
+structly-whois tests/samples/whois/google.com.txt \
+  --domain google.com \
+  --record --json \
+  --date-parser tests.common.helpers:iso_to_datetime
+```
+
+The CLI mirrors the Python API: pass `--record` to emit a structured `WhoisRecord`, `--lowercase` to normalize strings, and `--date-parser module:callable` when you want custom date coercion.
+
+## Advanced usage
+
+### Batched parsing
+
+```python
+parser = WhoisParser()
+payloads: list[str] = fetch_from_queue()
+records = parser.parse_many(payloads, to_records=True, lowercase=True)
+for record in records:
+    ingest(record)  # bulk insert, emit to Kafka, etc.
+```
+
+### Optional date parser hook
+
+`structly_whois` intentionally avoids bundling `dateparser`. If you need locale-specific conversions, pass a callable either when constructing the parser or per method:
+
+```python
+from datetime import datetime
+
+def date_hook(value: str) -> datetime:
+    return datetime.fromisoformat(value.replace("Z", "+00:00"))
+
+parser = WhoisParser(date_parser=date_hook)
+record = parser.parse_record(raw_whois, domain="example.dev", date_parser=date_hook)
+```
+
+For multilingual registries, the simplest plug-in is [`dateparser.parse`](https://pypi.org/project/dateparser/). 
+
+NOTE: It can cut throughput by more than half.
+
+### Streaming from S3
+
+```python
+import boto3
+import gzip
+import tarfile
+from structly_whois import WhoisParser
+
+def iter_whois_payloads(bucket: str, key: str):
+    """Stream WHOIS samples from an S3-hosted tar.gz without touching disk."""
+    s3 = boto3.client("s3")
+    obj = s3.get_object(Bucket=bucket, Key=key)
+    with gzip.GzipFile(fileobj=obj["Body"]) as gz:
+        with tarfile.open(fileobj=gz, mode="r:") as tar:
+            for member in tar:
+                if not member.isfile():
+                    continue
+                raw = tar.extractfile(member).read().decode("utf-8", errors="ignore")
+                yield raw
+
+parser = WhoisParser()
+payloads = iter_whois_payloads("whois-dumps", "2024-12.tar.gz")
+
+for chunk in parser.parse_chunks(payloads, chunk_size=512):
+    process(chunk)  # bulk insert, publish, etc.
+```
+
+### Custom Structly Config overrides
+
+`structly_whois` is built for easy extensibility—you can extend the bundled Structly configs or replace
+  them entirely, so parser behavior stays configurable without forking.
+
+```python
+from structly import FieldPattern
+from structly_whois import StructlyConfigFactory, WhoisParser
+
+factory = StructlyConfigFactory(
+    base_field_definitions={
+        "domain_name": {"patterns": [FieldPattern.regex(r"^dn:\s*(?P<val>[a-z0-9.-]+)$")]},
+    },
+    tld_overrides={},
+)
+parser = WhoisParser(preload_tlds=("dev",), config_factory=factory)
+parser.register_tld(
+    "app",
+    {
+        "domain_name": {
+            "extend_patterns": [FieldPattern.starts_with("App Domain:")],
+        }
+    },
+)
+```
+
+## API overview
+
+| Component | Description |
+| --------- | ----------- |
+| `structly_whois.WhoisParser` | High-level parser with batching, record conversion, and optional CLI integration. |
+| `structly_whois.StructlyConfigFactory` | Factory that builds Structly configs with base fields + TLD overrides. |
+| `structly_whois.records.WhoisRecord` | Typed msgspec struct with `to_dict()` for JSON serialization. |
+| `structly_whois.normalize_raw_text` | Fast trimming of noise, privacy banners, and multiline headers. |
+| `structly_whois.cli` | Argparse-powered CLI that mirrors the Python API. |
+
+## Benchmarks
+
+`make bench` runs `benchmarks/run_benchmarks.py`, comparing structly_whois against `whois-parser` and `python-whois`. 
+Default settings parse all 105 fixtures ×100 iterations on a MacBook Pro (M4, Python 3.14):
+
+| backend                   | records | records/s | avg latency (ms) |
+| ------------------------- | ------- | --------- | ---------------- |
+| structly-whois            | 10,500  | 7,779     | 0.129            |
+| structly-whois + dateutil | 10,500  | 3,236     | 0.309            |
+| structly-whois + dateparser | 10,500 | 996      | 1.004            |
+| python-whois              | 10,500  | 196       | 5.096            |
+| whois-parser              | 10,500  | 17        | 58.229           |
+
+“dateutil” uses `date_parser=dateutil.parser.parse`; “dateparser” uses `date_parser=dateparser.parse`. Both illustrate how heavier date coercion affects throughput.
+
+## Development
+
+```bash
+make lint     # Ruff (E/F/W/I/UP/B/SIM)
+make fmt      # Ruff formatter across src/tests/benchmarks
+make test     # pytest + coverage (Hypothesis fixtures)
+make cov      # coverage xml/report (≥90%)
+make bench    # compare structly_whois vs whois-parser/python-whois
+```
+
+See [CONTRIBUTING.md](CONTRIBUTING.md) for versioning, release, and pull-request guidelines. 
+CI (GitHub Actions) runs lint/test/build on every push; pushes to `dev` publish wheels to TestPyPI and tags `vX.Y.Z` publish to PyPI.
+
+## License
+
+MIT © Nikola Stankovic.