legalsuffix 0.0.1a2__tar.gz

legalsuffix-0.0.1a2/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Slava Nazimkov
+
+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.

legalsuffix-0.0.1a2/PKG-INFO

@@ -0,0 +1,108 @@
+Metadata-Version: 2.4
+Name: legalsuffix
+Version: 0.0.1a2
+Summary: Detect, normalize, and strip legal entity suffixes.
+Requires-Python: >=3.12
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: license-file
+
+![LegalSuffix logo](assets/logo.png)
+
+# legalsuffix
+
+![Coverage](https://img.shields.io/badge/coverage-100%25-brightgreen)
+[![Python](https://img.shields.io/badge/python-3.12%2B-blue)](https://www.python.org/)
+[![License: MIT](https://img.shields.io/badge/license-MIT-green)](LICENSE)
+
+Detect, normalize, and strip legal entity suffixes (LLC, LTD, GmbH, OOO, 株式会社…) in 20+ languages. Parse company names safely.
+
+# Operations
+
+The package exposes these operations from `legalsuffix`. Country and language
+filters are optional; country codes use ISO 3166-1 alpha-2 and language codes use
+ISO 639-1 two-letter codes.
+
+```python
+from legalsuffix import (
+    get_suffixes,
+    match_legal_suffix,
+    normalize_legal_suffix,
+    parse_company_name,
+    strip_legal_suffix,
+)
+```
+
+### Get suffix records
+
+`get_suffixes` returns `LegalSuffix` records. Filters are optional.
+
+```python
+suffixes = get_suffixes(country_code="DE", language_code="de")
+for suffix in suffixes[:5]:
+    print(suffix.elf_code, suffix.entity_legal_form_name_local_name)
+```
+
+### Match a suffix
+
+`match_legal_suffix` finds a legal form in the company name. Some registry names
+place the legal form before additional descriptive text. It returns `None` if
+there is no match. The end offset is exclusive.
+
+```python
+company = "Musterfirma GmbH"
+match = match_legal_suffix(company, country_code="DE")
+if match is not None:
+    print(match.suffix)  # "GmbH"
+    print(match.start_pos, match.end_pos)  # 12 16
+    print(match.records[0].elf_code)  # ELF code for this legal form
+```
+
+### Normalize a suffix
+
+Normalization trims surrounding whitespace, ignores punctuation and accents,
+and lowercases the suffix.
+
+```python
+normalize_legal_suffix(" GmbH. ")  # "gmbh"
+```
+
+### Parse a company name
+
+`parse_company_name` returns the company name with the matched legal form
+removed, along with the optional suffix match. Text after the form is preserved.
+
+```python
+parsed = parse_company_name("Musterfirma GmbH", country_code="DE")
+print(parsed.name)  # "Musterfirma"
+if parsed.suffix is not None:
+    print(parsed.suffix.suffix)  # "GmbH"
+```
+
+### Strip a suffix
+
+`strip_legal_suffix` removes the recognized legal form and preserves any text
+that follows it.
+
+```python
+strip_legal_suffix("Musterfirma GmbH", country_code="DE")  # "Musterfirma"
+```
+
+Country codes use ISO 3166-1 alpha-2, and language codes use ISO 639-1 two-letter
+codes.
+
+# Development hooks
+
+Install the pre-commit hook to run the unit tests and refresh the coverage
+badge before a commit that changes a Python file under `src/`:
+
+```shell
+uv run pre-commit install
+```
+
+If the badge changes, stage `README.md` and retry the commit so the updated
+coverage is included.
+
+# Data Source
+
+ISO 20275: Entity Legal Forms Code List: [Entity Legal Forms Code List (Version 1.6 )](https://www.gleif.org/lei-data/code-lists/iso-20275-entity-legal-forms-code-list/2026-02-19-elf-code-list-v1.6.xlsx)

legalsuffix-0.0.1a2/README.md

@@ -0,0 +1,99 @@
+![LegalSuffix logo](assets/logo.png)
+
+# legalsuffix
+
+![Coverage](https://img.shields.io/badge/coverage-100%25-brightgreen)
+[![Python](https://img.shields.io/badge/python-3.12%2B-blue)](https://www.python.org/)
+[![License: MIT](https://img.shields.io/badge/license-MIT-green)](LICENSE)
+
+Detect, normalize, and strip legal entity suffixes (LLC, LTD, GmbH, OOO, 株式会社…) in 20+ languages. Parse company names safely.
+
+# Operations
+
+The package exposes these operations from `legalsuffix`. Country and language
+filters are optional; country codes use ISO 3166-1 alpha-2 and language codes use
+ISO 639-1 two-letter codes.
+
+```python
+from legalsuffix import (
+    get_suffixes,
+    match_legal_suffix,
+    normalize_legal_suffix,
+    parse_company_name,
+    strip_legal_suffix,
+)
+```
+
+### Get suffix records
+
+`get_suffixes` returns `LegalSuffix` records. Filters are optional.
+
+```python
+suffixes = get_suffixes(country_code="DE", language_code="de")
+for suffix in suffixes[:5]:
+    print(suffix.elf_code, suffix.entity_legal_form_name_local_name)
+```
+
+### Match a suffix
+
+`match_legal_suffix` finds a legal form in the company name. Some registry names
+place the legal form before additional descriptive text. It returns `None` if
+there is no match. The end offset is exclusive.
+
+```python
+company = "Musterfirma GmbH"
+match = match_legal_suffix(company, country_code="DE")
+if match is not None:
+    print(match.suffix)  # "GmbH"
+    print(match.start_pos, match.end_pos)  # 12 16
+    print(match.records[0].elf_code)  # ELF code for this legal form
+```
+
+### Normalize a suffix
+
+Normalization trims surrounding whitespace, ignores punctuation and accents,
+and lowercases the suffix.
+
+```python
+normalize_legal_suffix(" GmbH. ")  # "gmbh"
+```
+
+### Parse a company name
+
+`parse_company_name` returns the company name with the matched legal form
+removed, along with the optional suffix match. Text after the form is preserved.
+
+```python
+parsed = parse_company_name("Musterfirma GmbH", country_code="DE")
+print(parsed.name)  # "Musterfirma"
+if parsed.suffix is not None:
+    print(parsed.suffix.suffix)  # "GmbH"
+```
+
+### Strip a suffix
+
+`strip_legal_suffix` removes the recognized legal form and preserves any text
+that follows it.
+
+```python
+strip_legal_suffix("Musterfirma GmbH", country_code="DE")  # "Musterfirma"
+```
+
+Country codes use ISO 3166-1 alpha-2, and language codes use ISO 639-1 two-letter
+codes.
+
+# Development hooks
+
+Install the pre-commit hook to run the unit tests and refresh the coverage
+badge before a commit that changes a Python file under `src/`:
+
+```shell
+uv run pre-commit install
+```
+
+If the badge changes, stage `README.md` and retry the commit so the updated
+coverage is included.
+
+# Data Source
+
+ISO 20275: Entity Legal Forms Code List: [Entity Legal Forms Code List (Version 1.6 )](https://www.gleif.org/lei-data/code-lists/iso-20275-entity-legal-forms-code-list/2026-02-19-elf-code-list-v1.6.xlsx)

legalsuffix-0.0.1a2/pyproject.toml

@@ -0,0 +1,52 @@
+[project]
+name = "legalsuffix"
+version = "0.0.1a2"
+description = "Detect, normalize, and strip legal entity suffixes."
+readme = "README.md"
+requires-python = ">=3.12"
+dependencies = []
+
+[build-system]
+requires = ["setuptools>=68"]
+build-backend = "setuptools.build_meta"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.setuptools.package-data]
+legalsuffix = ["data/*.csv"]
+
+[dependency-groups]
+dev = [
+    "pre-commit>=4.2.0",
+    "ruff>=0.12.4",
+    "pyright>=1.1.403",
+    "coverage>=7.17.2",
+]
+
+
+[tool.pyright]
+venvPath = "."
+venv = ".venv"
+exclude = [
+    "**/__pycache__",
+    "**/.venv",
+    "**/htmlcov",
+    "**/.pytest_cache"
+]
+pythonVersion = "3.12"
+typeCheckingMode = "basic"
+
+
+[tool.ruff]
+line-length = 120
+
+[tool.ruff.lint]
+select = [
+    "E",    # pycodestyle errors
+    "F",    # pyflakes
+    "I",    # isort
+    "N",    # pep8-naming
+    "UP",   # pyupgrade
+    "B",    # flake8-bugbear
+]

legalsuffix-0.0.1a2/setup.cfg

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

legalsuffix-0.0.1a2/src/legalsuffix/__init__.py

@@ -0,0 +1,27 @@
+"""Public API for detecting and working with legal suffixes.
+
+Example:
+    >>> from legalsuffix import parse_company_name
+    >>> parsed = parse_company_name("Acme GmbH", country_code="DE")
+    >>> parsed.name
+    'Acme'
+    >>> parsed.suffix.suffix
+    'GmbH'
+"""
+
+from .loader import get_suffixes
+from .matching import match_legal_suffix, normalize_legal_suffix, parse_company_name, strip_legal_suffix
+from .models import LegalSuffix, LegalSuffixMatch, ParsedCompanyName
+
+__version__ = "0.0.1a2"
+
+__all__ = [
+    "LegalSuffix",
+    "LegalSuffixMatch",
+    "ParsedCompanyName",
+    "get_suffixes",
+    "match_legal_suffix",
+    "normalize_legal_suffix",
+    "parse_company_name",
+    "strip_legal_suffix",
+]

legalsuffix-0.0.1a2/src/legalsuffix/constants.py

@@ -0,0 +1,6 @@
+from pathlib import Path
+
+DATA_FILE = "suffixes.csv"
+DATA_FOLDER = Path(__file__).parent / "data"
+
+DATA_FILE_PATH = DATA_FOLDER / DATA_FILE