privyscope 0.1.0__tar.gz

privyscope-0.1.0/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 [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.

privyscope-0.1.0/PKG-INFO

@@ -0,0 +1,123 @@
+Metadata-Version: 2.4
+Name: privyscope
+Version: 0.1.0
+Summary: privyscope — multilingual PII detection & masking engine (ONNX, BIOES + Viterbi). Install a language pack, e.g. privyscope-ko.
+Author: privyscope Core Team
+License: Apache-2.0
+Project-URL: Homepage, https://github.com/zafrem/privyscope
+Project-URL: Documentation, https://github.com/zafrem/privyscope/blob/main/README.md
+Keywords: pii,ner,redaction,privacy,onnx,multilingual
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Text Processing :: Linguistic
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy>=1.22
+Requires-Dist: PyYAML>=6.0
+Requires-Dist: onnxruntime>=1.17
+Requires-Dist: transformers>=4.38
+Requires-Dist: huggingface_hub>=0.20
+Provides-Extra: train
+Requires-Dist: torch>=2.0; extra == "train"
+Requires-Dist: datasets>=2.16; extra == "train"
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.0; extra == "dev"
+Dynamic: license-file
+
+# privyscope
+
+**Multilingual PII detection & masking engine** — the language-neutral core of the
+[privyscope](https://github.com/zafrem) project.
+
+This package contains the engine (a two-stage hybrid pipeline: a regex filter plus
+an optional ONNX BIOES/Viterbi NER stage), the `privyscope` console command, and the
+plugin machinery that discovers installed **language packs**. It ships **no language
+data** on its own — install at least one language pack to do real work:
+
+```bash
+pip install privyscope-ko      # Korean   (pulls in this core automatically)
+pip install privyscope-en      # English
+```
+
+Installing a language pack pulls in this core as a dependency, so you normally never
+`pip install privyscope` directly.
+
+## Why privyscope?
+
+Compared to traditional NER systems from 3-4 years ago, `privyscope` delivers significantly higher precision and robustness by employing several modern architectural advancements:
+
+1. **BIOES Tagging:** Unlike the traditional BIO scheme, we use the BIOES (Begin, Inside, Outside, End, Single) scheme. This allows the model to explicitly learn span boundaries and single-token entities, which is critical for CJK languages where particles often follow PII entities without spaces.
+2. **Constrained Viterbi Decoding:** Instead of making independent per-token decisions, we use a Viterbi decoder with learned transition biases. This ensures that the output sequence is always grammatically valid (e.g., an "Inside" tag can never follow an "Outside" tag), preventing fragmented or "broken" masking results.
+3. **Domain-Adaptive MLM:** Before fine-tuning on PII extraction, we perform additional Masked Language Modeling (MLM) on a large-scale synthetic PII corpus. This "domain adaptation" phase allows the model to internalize the structural characteristics of PII (like API keys, ID numbers, and complex addresses) that are rarely seen in general-purpose datasets like Wikipedia.
+4. **LLM-Augmented Synthesis:** We leverage LLMs and Faker to generate hundreds of thousands of high-fidelity synthetic PII sentences across various registers (formal, conversational, etc.). This massive increase in training variety ensures the model remains robust against novel contexts and diverse writing styles.
+
+## One command, any combination of languages
+
+The `privyscope` command lives **only** here in the core, so co-installed language
+packs never collide over it (each pack only adds its own `privyscope_<lang>` data
+package).
+
+```bash
+# one language installed → it's used automatically
+privyscope redact "홍길동 010-1234-5678"
+
+# several installed → auto-detected per text, or forced with --lang
+privyscope redact "John Smith 555-123-4567"          # → English
+privyscope redact --lang ko "Call 010-1234-5678"     # force Korean
+privyscope --version                                  # lists installed languages
+```
+
+## Python API
+
+```python
+from privyscope import Privyscope
+
+# one language (explicit, or the sole one installed)
+engine = Privyscope.from_pretrained(lang="ko")
+engine.redact("홍길동의 전화번호는 010-1234-5678").masked_text   # "<PER>의 전화번호는 <PHONE>"
+
+# multiple languages → route each text automatically
+auto = Privyscope.auto()
+auto.redact("John Smith 555-123-4567")    # English engine
+auto.redact("홍길동 010-1234-5678")        # Korean engine
+```
+
+See [`docs/`](../docs) (in the repo) for the CLI reference, offline usage, the
+output schema, fine-tuning, and the **multilingual use-case guide**.
+
+## Writing a language pack
+
+A language pack is tiny: a package that ships two YAML files
+(`regex_rules.yaml`, `entity_config.yaml`) and registers a `LanguagePlugin` under
+the `privyscope.languages` entry-point group.
+
+```python
+# privyscope_xx/__init__.py
+from privyscope import Privyscope, LanguagePlugin, __version__
+
+LANG = LanguagePlugin(
+    code="xx", display_name="Example", default_repo="org/privyscope-xx",
+    package="privyscope_xx", scripts=("Latin",), default_base_model="roberta-base",
+)
+```
+
+```toml
+# pyproject.toml
+[project]
+dependencies = ["privyscope>=0.1.0"]
+
+[project.entry-points."privyscope.languages"]
+xx = "privyscope_xx:LANG"
+```
+
+## License
+
+Apache-2.0. See [LICENSE](LICENSE).

privyscope-0.1.0/README.md

@@ -0,0 +1,89 @@
+# privyscope
+
+**Multilingual PII detection & masking engine** — the language-neutral core of the
+[privyscope](https://github.com/zafrem) project.
+
+This package contains the engine (a two-stage hybrid pipeline: a regex filter plus
+an optional ONNX BIOES/Viterbi NER stage), the `privyscope` console command, and the
+plugin machinery that discovers installed **language packs**. It ships **no language
+data** on its own — install at least one language pack to do real work:
+
+```bash
+pip install privyscope-ko      # Korean   (pulls in this core automatically)
+pip install privyscope-en      # English
+```
+
+Installing a language pack pulls in this core as a dependency, so you normally never
+`pip install privyscope` directly.
+
+## Why privyscope?
+
+Compared to traditional NER systems from 3-4 years ago, `privyscope` delivers significantly higher precision and robustness by employing several modern architectural advancements:
+
+1. **BIOES Tagging:** Unlike the traditional BIO scheme, we use the BIOES (Begin, Inside, Outside, End, Single) scheme. This allows the model to explicitly learn span boundaries and single-token entities, which is critical for CJK languages where particles often follow PII entities without spaces.
+2. **Constrained Viterbi Decoding:** Instead of making independent per-token decisions, we use a Viterbi decoder with learned transition biases. This ensures that the output sequence is always grammatically valid (e.g., an "Inside" tag can never follow an "Outside" tag), preventing fragmented or "broken" masking results.
+3. **Domain-Adaptive MLM:** Before fine-tuning on PII extraction, we perform additional Masked Language Modeling (MLM) on a large-scale synthetic PII corpus. This "domain adaptation" phase allows the model to internalize the structural characteristics of PII (like API keys, ID numbers, and complex addresses) that are rarely seen in general-purpose datasets like Wikipedia.
+4. **LLM-Augmented Synthesis:** We leverage LLMs and Faker to generate hundreds of thousands of high-fidelity synthetic PII sentences across various registers (formal, conversational, etc.). This massive increase in training variety ensures the model remains robust against novel contexts and diverse writing styles.
+
+## One command, any combination of languages
+
+The `privyscope` command lives **only** here in the core, so co-installed language
+packs never collide over it (each pack only adds its own `privyscope_<lang>` data
+package).
+
+```bash
+# one language installed → it's used automatically
+privyscope redact "홍길동 010-1234-5678"
+
+# several installed → auto-detected per text, or forced with --lang
+privyscope redact "John Smith 555-123-4567"          # → English
+privyscope redact --lang ko "Call 010-1234-5678"     # force Korean
+privyscope --version                                  # lists installed languages
+```
+
+## Python API
+
+```python
+from privyscope import Privyscope
+
+# one language (explicit, or the sole one installed)
+engine = Privyscope.from_pretrained(lang="ko")
+engine.redact("홍길동의 전화번호는 010-1234-5678").masked_text   # "<PER>의 전화번호는 <PHONE>"
+
+# multiple languages → route each text automatically
+auto = Privyscope.auto()
+auto.redact("John Smith 555-123-4567")    # English engine
+auto.redact("홍길동 010-1234-5678")        # Korean engine
+```
+
+See [`docs/`](../docs) (in the repo) for the CLI reference, offline usage, the
+output schema, fine-tuning, and the **multilingual use-case guide**.
+
+## Writing a language pack
+
+A language pack is tiny: a package that ships two YAML files
+(`regex_rules.yaml`, `entity_config.yaml`) and registers a `LanguagePlugin` under
+the `privyscope.languages` entry-point group.
+
+```python
+# privyscope_xx/__init__.py
+from privyscope import Privyscope, LanguagePlugin, __version__
+
+LANG = LanguagePlugin(
+    code="xx", display_name="Example", default_repo="org/privyscope-xx",
+    package="privyscope_xx", scripts=("Latin",), default_base_model="roberta-base",
+)
+```
+
+```toml
+# pyproject.toml
+[project]
+dependencies = ["privyscope>=0.1.0"]
+
+[project.entry-points."privyscope.languages"]
+xx = "privyscope_xx:LANG"
+```
+
+## License
+
+Apache-2.0. See [LICENSE](LICENSE).

privyscope-0.1.0/privyscope/__init__.py

@@ -0,0 +1,30 @@
+"""privyscope — multilingual PII detection & masking engine (Apache-2.0).
+
+This is the language-neutral **core**: the two-stage hybrid engine (regex filter
++ ONNX BIOES/Viterbi NER), the ``privyscope`` console command, and the plugin
+machinery that discovers installed language packs (``privyscope-ko``,
+``privyscope-en``, …). Install at least one language plugin to do real work::
+
+    pip install privyscope-ko            # pulls in this core automatically
+
+Public surface::
+
+    from privyscope import Privyscope
+    engine = Privyscope.from_pretrained(lang="ko")   # one language
+    auto   = Privyscope.auto()                        # route per text
+"""
+from ._api import Privyscope
+from ._core.schema import RedactionResult, DetectedSpan, SCHEMA_VERSION
+from ._core.plugins import LanguagePlugin, installed_languages
+
+__version__ = "0.1.0"
+
+__all__ = [
+    "Privyscope",
+    "RedactionResult",
+    "DetectedSpan",
+    "SCHEMA_VERSION",
+    "LanguagePlugin",
+    "installed_languages",
+    "__version__",
+]

privyscope-0.1.0/privyscope/__main__.py

@@ -0,0 +1,130 @@
+"""Unified CLI entrypoint: ``privyscope redact | eval | train`` (SRS FR-2.1)."""
+from __future__ import annotations
+
+import sys
+from typing import List, Optional, Sequence
+
+from ._api import AutoPrivyscope, Privyscope
+from ._cli.args import build_parser
+from ._cli.render import print_result, supports_color
+from ._core.plugins import installed_languages, resolve_plugin
+
+_PROVIDERS = {
+    "cpu": ["CPUExecutionProvider"],
+    "cuda": ["CUDAExecutionProvider", "CPUExecutionProvider"],
+    "coreml": ["CoreMLExecutionProvider", "CPUExecutionProvider"],
+}
+
+
+def _parse_operating_point(value: str):
+    """A preset name, or comma-separated raw transition biases (FR-2.5)."""
+    if value and "," in value:
+        return [float(x) for x in value.split(",")]
+    return value
+
+
+def _read_input(args) -> Optional[str]:
+    """Resolve redact input from arg / file / stdin; None triggers interactive mode."""
+    if args.text is not None:
+        return args.text
+    if args.file:
+        with open(args.file, "r", encoding="utf-8") as fh:
+            return fh.read().rstrip("\n")
+    if not sys.stdin.isatty():
+        data = sys.stdin.read()
+        return data.rstrip("\n") if data else None
+    return None
+
+
+def _build_engine(args):
+    """Build the inference engine for redact/eval.
+
+    ``--lang X`` → that language. No ``--lang`` with one plugin installed → that
+    plugin. No ``--lang`` with several installed → an auto-routing dispatcher.
+    Returns an ``Privyscope`` or an ``AutoPrivyscope`` (same redact surface).
+    """
+    operating_point = _parse_operating_point(getattr(args, "operating_point", "balanced"))
+    cache_dir = getattr(args, "cache_dir", None)
+    regex_only = getattr(args, "regex_only", False)
+    providers = _PROVIDERS.get(getattr(args, "device", "cpu"), None)
+    lang = getattr(args, "lang", None)
+
+    if lang is None and len(installed_languages()) > 1:
+        return AutoPrivyscope(
+            operating_point=operating_point,
+            cache_dir=cache_dir,
+            providers=providers,
+            regex_only=regex_only,
+        )
+    return Privyscope.from_pretrained(
+        operating_point=operating_point,
+        lang=lang,
+        cache_dir=cache_dir,
+        revision=getattr(args, "revision", None),
+        regex_only=regex_only,
+        providers=providers,
+    )
+
+
+def _cmd_redact(args) -> int:
+    engine = _build_engine(args)
+    entity_types = args.entity_types.split(",") if args.entity_types else None
+    text = _read_input(args)
+    as_json = args.json or not supports_color()
+
+    if text is None:  # interactive mode (FR-2.1)
+        print("privyscope interactive redact — enter text (Ctrl-D to exit)", file=sys.stderr)
+        for line in sys.stdin:
+            line = line.rstrip("\n")
+            if not line:
+                continue
+            print_result(engine.redact(line, entity_types, args.output_mode), as_json)
+        return 0
+
+    print_result(engine.redact(text, entity_types, args.output_mode), as_json)
+    return 0
+
+
+def _cmd_eval(args) -> int:
+    from ._eval.runner import run_eval
+
+    engine = _build_engine(args)
+    report = run_eval(engine, args.dataset, eval_mode=args.eval_mode, limit=args.limit)
+    import json
+
+    print(json.dumps(report, ensure_ascii=False, indent=2))
+    return 0
+
+
+def _cmd_train(args) -> int:
+    try:
+        from ._train.runner import run_train
+    except ImportError as exc:
+        print(
+            f"training requires the optional extra: pip install 'privyscope[train]' ({exc})",
+            file=sys.stderr,
+        )
+        return 2
+    # Default the base checkpoint from the selected language plugin (FR-2.6).
+    if not getattr(args, "base_model", None):
+        plugin = resolve_plugin(getattr(args, "lang", None))
+        if plugin.default_base_model:
+            args.base_model = plugin.default_base_model
+    summary = run_train(args)
+    import json
+
+    print(json.dumps(summary, ensure_ascii=False, indent=2))
+    return 0
+
+
+def main(argv: Optional[Sequence[str]] = None) -> int:
+    args = build_parser().parse_args(argv)
+    return {
+        "redact": _cmd_redact,
+        "eval": _cmd_eval,
+        "train": _cmd_train,
+    }[args.command](args)
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())