credgate 0.1.0__tar.gz

credgate-0.1.0/.gitignore

@@ -0,0 +1,8 @@
+.Rproj.user/
+.Rhistory
+.RData
+*.Rcheck/
+credgate_*.tar.gz
+result
+result-*
+.DS_Store

credgate-0.1.0/AUTHORS

@@ -0,0 +1,6 @@
+# The CredGate Authors: people who hold copyright in CredGate.
+# Contributors are added here with their first contribution.
+# Format: Name <email> (GitHub handle)
+
+Bharat Sikka <bharat8sikka@gmail.com> (@bharatsikka)
+Aishwarya Bais <aishwarya.bais00@gmail.com> (@aishwaryabais)

credgate-0.1.0/LICENSE

@@ -0,0 +1,202 @@
+
+                                 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 [yyyy] [name of copyright owner]
+
+   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.

credgate-0.1.0/NOTICE

@@ -0,0 +1,5 @@
+CredGate
+Copyright 2026 The CredGate Authors
+
+This product is licensed under the Apache License, Version 2.0 (see
+LICENSE). The CredGate Authors are listed in the AUTHORS file.

credgate-0.1.0/PKG-INFO

@@ -0,0 +1,110 @@
+Metadata-Version: 2.5
+Name: credgate
+Version: 0.1.0
+Summary: Governance layer for LLM requests with Indian PII detection
+Project-URL: Homepage, https://github.com/dwarpal/credgate
+Project-URL: Issues, https://github.com/dwarpal/credgate/issues
+Author-email: Bharat Sikka <bharat8sikka@gmail.com>, Aishwarya Bais <aishwarya.bais00@gmail.com>
+Maintainer-email: Bharat Sikka <bharat8sikka@gmail.com>, Aishwarya Bais <aishwarya.bais00@gmail.com>
+License-Expression: Apache-2.0
+License-File: AUTHORS
+License-File: LICENSE
+License-File: NOTICE
+Keywords: aadhaar,compliance,dpdp,india,llm,pii,privacy
+Classifier: Development Status :: 2 - Pre-Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Security
+Classifier: Topic :: Text Processing
+Requires-Python: >=3.11
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: regex>=2023.0
+Provides-Extra: test
+Requires-Dist: pytest>=7; extra == 'test'
+Description-Content-Type: text/markdown
+
+# credgate
+
+Detects personal data before it leaves the machine, with Indian identifiers
+built in: Aadhaar (with Verhoeff checksum), Aadhaar Virtual ID, PAN, GSTIN,
+voter ID, passport, driving licence, UPI IDs, IFSC, bank accounts, payment
+cards, +91 mobile numbers, ABHA, and names and addresses in Latin and Indic
+scripts.
+
+The detection rules live in a shared, language-neutral spec, so this package
+and the R package `credgate` find exactly the same matches. Part of the
+[CredGate](https://github.com/dwarpal/credgate) project; early development.
+
+## Installation
+
+Python 3.11 or later; depends only on `regex` and `PyYAML`.
+
+```sh
+pip install "git+https://github.com/dwarpal/credgate#subdirectory=pkg/python"
+```
+
+With Nix: `nix build github:dwarpal/credgate#credgate`.
+
+## Usage
+
+```python
+import credgate
+
+spans = credgate.detect_pii("Name: Priya Nair; PAN: ABCPN1234K; UPI: priya.n@oksbi")
+for s in spans:
+    print(s)
+# Span(doc=0, start=6, end=16, type='person_name', value='XXXXX Nair', confidence=0.8)
+# Span(doc=0, start=23, end=33, type='pan', value='XXXXXX234K', confidence=0.97)
+# Span(doc=0, start=40, end=53, type='upi_id', value='XXXXX.X@Xksbi', confidence=0.99)
+
+spans[1].value    # 'ABCPN1234K' - printing masks values, the attribute does not
+spans[1].reasons  # "matched PAN pattern; context 'PAN'; holder type: individual"
+```
+
+`detect_pii()` takes a string or a list of strings and returns `Span`
+objects with the document index, 0-based end-exclusive positions, type, data
+class, value, canonical form, confidence and reasons. `span.to_dict()` gives
+a JSON-ready dict with the value masked (`reveal=True` to include it).
+
+Context makes generic patterns trustworthy; pass a column name or similar:
+
+```python
+credgate.detect_pii("ABC1234567")                      # [] - could be anything
+credgate.detect_pii("ABC1234567", context="voter_id")  # voter ID, confidence 0.97
+```
+
+Checksums, synthetic test data and your own detectors:
+
+```python
+credgate.verhoeff_valid("542229371182")
+credgate.synth_indian_pii(5, seed=1)   # synthetic records; never use as anonymised data
+
+credgate.register_detector(credgate.Detector(
+    id="employee_id", data_class="internal", label="Employee ID",
+    patterns=credgate.bounded("EMP[0-9]{6}"),
+))
+```
+
+## Command line
+
+```sh
+credgate detect notes.txt                      # masked report
+credgate detect --lines --json customers.csv   # one JSON object per match
+git diff --cached | credgate detect --fail     # non-zero exit if PII is found
+credgate detectors                             # list detectors
+```
+
+Values are masked unless you pass `--reveal`.
+
+## Limits
+
+Names and addresses are found only next to a cue: an honorific (Shri, Smt,
+श्रीमती), a relation (S/o, D/o), a field label (`Name:`, `पता:`) or a
+house/village keyword followed by a PIN code. A bare 12-digit number may pass
+the Aadhaar checksum by chance and is reported with lower confidence.
+
+## Licence
+
+Apache License 2.0.

credgate-0.1.0/README.md

@@ -0,0 +1,83 @@
+# credgate
+
+Detects personal data before it leaves the machine, with Indian identifiers
+built in: Aadhaar (with Verhoeff checksum), Aadhaar Virtual ID, PAN, GSTIN,
+voter ID, passport, driving licence, UPI IDs, IFSC, bank accounts, payment
+cards, +91 mobile numbers, ABHA, and names and addresses in Latin and Indic
+scripts.
+
+The detection rules live in a shared, language-neutral spec, so this package
+and the R package `credgate` find exactly the same matches. Part of the
+[CredGate](https://github.com/dwarpal/credgate) project; early development.
+
+## Installation
+
+Python 3.11 or later; depends only on `regex` and `PyYAML`.
+
+```sh
+pip install "git+https://github.com/dwarpal/credgate#subdirectory=pkg/python"
+```
+
+With Nix: `nix build github:dwarpal/credgate#credgate`.
+
+## Usage
+
+```python
+import credgate
+
+spans = credgate.detect_pii("Name: Priya Nair; PAN: ABCPN1234K; UPI: priya.n@oksbi")
+for s in spans:
+    print(s)
+# Span(doc=0, start=6, end=16, type='person_name', value='XXXXX Nair', confidence=0.8)
+# Span(doc=0, start=23, end=33, type='pan', value='XXXXXX234K', confidence=0.97)
+# Span(doc=0, start=40, end=53, type='upi_id', value='XXXXX.X@Xksbi', confidence=0.99)
+
+spans[1].value    # 'ABCPN1234K' - printing masks values, the attribute does not
+spans[1].reasons  # "matched PAN pattern; context 'PAN'; holder type: individual"
+```
+
+`detect_pii()` takes a string or a list of strings and returns `Span`
+objects with the document index, 0-based end-exclusive positions, type, data
+class, value, canonical form, confidence and reasons. `span.to_dict()` gives
+a JSON-ready dict with the value masked (`reveal=True` to include it).
+
+Context makes generic patterns trustworthy; pass a column name or similar:
+
+```python
+credgate.detect_pii("ABC1234567")                      # [] - could be anything
+credgate.detect_pii("ABC1234567", context="voter_id")  # voter ID, confidence 0.97
+```
+
+Checksums, synthetic test data and your own detectors:
+
+```python
+credgate.verhoeff_valid("542229371182")
+credgate.synth_indian_pii(5, seed=1)   # synthetic records; never use as anonymised data
+
+credgate.register_detector(credgate.Detector(
+    id="employee_id", data_class="internal", label="Employee ID",
+    patterns=credgate.bounded("EMP[0-9]{6}"),
+))
+```
+
+## Command line
+
+```sh
+credgate detect notes.txt                      # masked report
+credgate detect --lines --json customers.csv   # one JSON object per match
+git diff --cached | credgate detect --fail     # non-zero exit if PII is found
+credgate detectors                             # list detectors
+```
+
+Values are masked unless you pass `--reveal`.
+
+## Limits
+
+Names and addresses are found only next to a cue: an honorific (Shri, Smt,
+श्रीमती), a relation (S/o, D/o), a field label (`Name:`, `पता:`) or a
+house/village keyword followed by a PIN code. A bare 12-digit number may pass
+the Aadhaar checksum by chance and is reported with lower confidence.
+
+## Licence
+
+Apache License 2.0.

credgate-0.1.0/pyproject.toml

@@ -0,0 +1,64 @@
+[build-system]
+requires = ["hatchling>=1.27"]
+build-backend = "hatchling.build"
+
+[project]
+name = "credgate"
+version = "0.1.0"
+description = "Governance layer for LLM requests with Indian PII detection"
+readme = "README.md"
+license = "Apache-2.0"
+license-files = ["LICENSE", "NOTICE", "AUTHORS"]
+requires-python = ">=3.11"
+authors = [
+  { name = "Bharat Sikka", email = "bharat8sikka@gmail.com" },
+  { name = "Aishwarya Bais", email = "aishwarya.bais00@gmail.com" },
+]
+maintainers = [
+  { name = "Bharat Sikka", email = "bharat8sikka@gmail.com" },
+  { name = "Aishwarya Bais", email = "aishwarya.bais00@gmail.com" },
+]
+keywords = ["pii", "privacy", "llm", "aadhaar", "dpdp", "compliance", "india"]
+classifiers = [
+  "Development Status :: 2 - Pre-Alpha",
+  "Intended Audience :: Developers",
+  "Intended Audience :: Science/Research",
+  "Operating System :: OS Independent",
+  "Programming Language :: Python :: 3",
+  "Topic :: Security",
+  "Topic :: Text Processing",
+]
+dependencies = ["regex>=2023.0", "PyYAML>=6.0"]
+
+[project.urls]
+Homepage = "https://github.com/dwarpal/credgate"
+Issues = "https://github.com/dwarpal/credgate/issues"
+
+[project.optional-dependencies]
+test = ["pytest>=7"]
+
+[project.scripts]
+credgate = "credgate.cli:main"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/credgate"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+
+[tool.ruff]
+line-length = 100
+target-version = "py311"
+
+[tool.ruff.lint]
+select = [
+  "E", "W",   # pycodestyle
+  "F",        # pyflakes
+  "I",        # isort
+  "B",        # bugbear
+  "UP",       # pyupgrade
+  "SIM",      # simplify
+  "C4",       # comprehensions
+  "PT",       # pytest style
+  "RUF",      # ruff-specific
+]

credgate-0.1.0/src/credgate/__init__.py

@@ -0,0 +1,47 @@
+"""CredGate: governance layer for LLM requests with Indian PII detection.
+
+Detection rules come from the shared spec (see :func:`spec_path`), so this
+package and the R package find exactly the same matches.
+"""
+
+from importlib.metadata import PackageNotFoundError, version
+
+try:
+    __version__ = version("credgate")
+except PackageNotFoundError:  # running from a source checkout
+    __version__ = "0.1.0"
+
+from ._spec import spec_path
+from .checksums import (
+    gstin_check_char,
+    gstin_valid,
+    luhn_check_digit,
+    luhn_valid,
+    verhoeff_check_digit,
+    verhoeff_valid,
+)
+from .detect import Span, detect_pii, mask_value
+from .detectors import Detector, bounded, detectors, register_detector, reset_detectors
+from .normalise import Normalised, normalise
+from .synth import synth_indian_pii
+
+__all__ = [
+    "Detector",
+    "Normalised",
+    "Span",
+    "bounded",
+    "detect_pii",
+    "detectors",
+    "gstin_check_char",
+    "gstin_valid",
+    "luhn_check_digit",
+    "luhn_valid",
+    "mask_value",
+    "normalise",
+    "register_detector",
+    "reset_detectors",
+    "spec_path",
+    "synth_indian_pii",
+    "verhoeff_check_digit",
+    "verhoeff_valid",
+]

credgate-0.1.0/src/credgate/_spec.py

@@ -0,0 +1,64 @@
+"""Reading the shared detection spec shipped inside the package.
+
+The spec (``spec/`` in the repository, copied here by ``tools/sync-spec.sh``)
+is shared with the R package; see its README.md for the schema.
+"""
+
+from __future__ import annotations
+
+import functools
+from importlib import resources
+from pathlib import Path
+from typing import Any
+
+import regex
+import yaml
+
+SPEC_VERSION_SUPPORTED = 1
+
+
+def spec_path() -> Path:
+    """Path of the ``spec`` directory shipped with the package."""
+    return Path(str(resources.files("credgate") / "spec"))
+
+
+def read_spec_file(name: str, directory: Path | None = None) -> dict[str, Any]:
+    path = (directory or spec_path()) / name
+    with open(path, encoding="utf-8") as f:
+        data = yaml.safe_load(f)
+    if data.get("spec_version") != SPEC_VERSION_SUPPORTED:
+        raise ValueError(
+            f"Unsupported spec_version {data.get('spec_version')} in {name} "
+            f"(this credgate supports {SPEC_VERSION_SUPPORTED})."
+        )
+    return data
+
+
+def _code_points(values: list[str]) -> frozenset[int]:
+    return frozenset(int(v.removeprefix("U+"), 16) for v in values)
+
+
+@functools.cache
+def engine() -> dict[str, Any]:
+    """Engine parameters from engine.yaml, with code points parsed."""
+    spec = read_spec_file("engine.yaml")
+    norm = spec["normalisation"]
+    return {
+        "digit_zeros": sorted(_code_points(norm["digit_zeros"])),
+        "remove": _code_points(norm["remove"]),
+        "dash": _code_points(norm["dash"]),
+        "boundary": spec["boundary"],
+        "separators": regex.compile(spec["separators"]),
+        "scoring": spec["scoring"],
+    }
+
+
+@functools.cache
+def detector_spec() -> dict[str, Any]:
+    """The parsed detectors.yaml."""
+    spec = read_spec_file("detectors.yaml")
+    spec["lists"] = {k: [str(x) for x in v] for k, v in spec.get("lists", {}).items()}
+    spec["tables"] = {
+        k: {str(key): str(val) for key, val in v.items()} for k, v in spec.get("tables", {}).items()
+    }
+    return spec