entiscope-ko 0.1.0__tar.gz

entiscope_ko-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.

entiscope_ko-0.1.0/PKG-INFO

@@ -0,0 +1,126 @@
+Metadata-Version: 2.4
+Name: entiscope-ko
+Version: 0.1.0
+Summary: entiscope-ko — Korean PII detection & masking engine (ONNX, BIOES + Viterbi)
+Author: entiscope Core Team
+License: Apache-2.0
+Project-URL: Homepage, https://github.com/zafrem/entiscope-ko
+Project-URL: Documentation, https://github.com/zafrem/entiscope-ko/blob/main/README.md
+Keywords: pii,ner,redaction,privacy,korean,onnx
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+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
+
+# entiscope-ko
+
+Korean **PII detection & masking** engine — part of the
+[entiscope](https://github.com/zafrem) series. Detects and masks person names,
+phone numbers, national IDs, emails, addresses, financial info, private dates,
+and credentials in Korean text.
+
+> ⚠️ entiscope is a redaction **aid**, not an anonymization or compliance
+> guarantee. See [Limitations](#limitations).
+
+📖 **[한국어 README](README.ko.md)**
+
+## Install
+
+```bash
+pip install entiscope-ko
+```
+
+## 60-second quickstart
+
+**Python**
+
+```python
+from entiscope_ko import Entiscope
+
+engine = Entiscope.from_pretrained()                 # downloads ONNX weights on first run
+result = engine.redact("홍길동의 전화번호는 010-1234-5678")
+
+result.masked_text        # "<PER>의 전화번호는 <PHONE>"
+result.detected_spans     # [DetectedSpan(label="PER", start=0, end=3, ...), ...]
+result.summary            # {"span_count": 2, "by_label": {"PER": 1, "PHONE": 1}, ...}
+```
+
+**CLI**
+
+```bash
+entiscope redact "홍길동의 전화번호는 010-1234-5678"
+cat notes.txt | entiscope redact --operating-point high_recall
+```
+
+## Documentation
+
+Full guides live in [`docs/`](docs/) — organised by what you want to do:
+
+| I want to… | Guide |
+|---|---|
+| Run it from the terminal | [CLI Reference](docs/CLI.md) |
+| Call it from Python | [Python API Reference](docs/API.md) |
+| Understand the JSON output | [Output Schemas](docs/OUTPUT_SCHEMAS.md) |
+| Score it on my labelled data | [Evaluation & Output Modes](docs/EVAL_AND_OUTPUT_MODES.md) |
+| Trade precision vs recall | [Operating Points](docs/OPERATING_POINTS.md) |
+| Fine-tune on my own data | [Fine-tuning](docs/FINETUNING.md) |
+
+## Entities
+
+`PER` · `PHONE` · `ID_NUM` · `EMAIL` · `LOC` · `BANK` · `DATE` · `SECRET`.
+Regex patterns live in [`entiscope/regex_rules.yaml`](entiscope/regex_rules.yaml)
+(user-extensible, no code change); KO-specific extended entities in
+[`entiscope/entity_config.yaml`](entiscope/entity_config.yaml).
+
+## How it works
+
+A **two-stage hybrid pipeline** (SRS §3.4), results merged via Union:
+
+1. **Regex filter** — structurally obvious PII (phone, email, IDs, cards, secrets).
+2. **ONNX NER** — a BIOES token classifier with a constrained Viterbi decoder for
+   contextual PII (names, addresses, private dates).
+
+Inference is **ONNX Runtime only — no PyTorch at runtime**. Recall-first, with
+runtime [operating-point](docs/OPERATING_POINTS.md) tuning (no retraining).
+PyTorch is needed only to [fine-tune](docs/FINETUNING.md).
+
+## Model & performance
+
+- **Architecture** — `klue/roberta-base` encoder → BIOES token-classification
+  head → constrained Viterbi decoder.
+- **Runtime artifact** — INT8-quantized ONNX, **~105 MB** (well under the
+  ≤ 150 MB budget), max sequence length 256. Weights download from Hugging Face
+  Hub on first use, with a SHA-256 `checksum.txt` for integrity verification.
+- **Accuracy** — meets the entity-level **strict F1 ≥ 0.93** target on a
+  held-out validation set whose examples are disjoint from the training data, so
+  the score reflects generalization rather than memorization. See
+  [Evaluation & Output Modes](docs/EVAL_AND_OUTPUT_MODES.md) to score it on your
+  own labelled data.
+
+## Limitations
+
+- Not an anonymization/compliance guarantee; use as one layer of privacy-by-design.
+- Known failure modes: under-detection of uncommon/regional names; over-redaction
+  of public entities in ambiguous contexts; fragmented spans in heavily
+  mixed-format text; missed `SECRET` for novel credential formats.
+- Extra human review recommended for medical/legal/financial/government workflows.
+
+## License
+
+Apache-2.0. Weights are distributed on Hugging Face Hub under Apache-2.0 with a
+`checksum.txt` (SHA-256) for integrity verification. Contributions welcome — see
+[CONTRIBUTING.md](CONTRIBUTING.md).

entiscope_ko-0.1.0/README.md

@@ -0,0 +1,98 @@
+# entiscope-ko
+
+Korean **PII detection & masking** engine — part of the
+[entiscope](https://github.com/zafrem) series. Detects and masks person names,
+phone numbers, national IDs, emails, addresses, financial info, private dates,
+and credentials in Korean text.
+
+> ⚠️ entiscope is a redaction **aid**, not an anonymization or compliance
+> guarantee. See [Limitations](#limitations).
+
+📖 **[한국어 README](README.ko.md)**
+
+## Install
+
+```bash
+pip install entiscope-ko
+```
+
+## 60-second quickstart
+
+**Python**
+
+```python
+from entiscope_ko import Entiscope
+
+engine = Entiscope.from_pretrained()                 # downloads ONNX weights on first run
+result = engine.redact("홍길동의 전화번호는 010-1234-5678")
+
+result.masked_text        # "<PER>의 전화번호는 <PHONE>"
+result.detected_spans     # [DetectedSpan(label="PER", start=0, end=3, ...), ...]
+result.summary            # {"span_count": 2, "by_label": {"PER": 1, "PHONE": 1}, ...}
+```
+
+**CLI**
+
+```bash
+entiscope redact "홍길동의 전화번호는 010-1234-5678"
+cat notes.txt | entiscope redact --operating-point high_recall
+```
+
+## Documentation
+
+Full guides live in [`docs/`](docs/) — organised by what you want to do:
+
+| I want to… | Guide |
+|---|---|
+| Run it from the terminal | [CLI Reference](docs/CLI.md) |
+| Call it from Python | [Python API Reference](docs/API.md) |
+| Understand the JSON output | [Output Schemas](docs/OUTPUT_SCHEMAS.md) |
+| Score it on my labelled data | [Evaluation & Output Modes](docs/EVAL_AND_OUTPUT_MODES.md) |
+| Trade precision vs recall | [Operating Points](docs/OPERATING_POINTS.md) |
+| Fine-tune on my own data | [Fine-tuning](docs/FINETUNING.md) |
+
+## Entities
+
+`PER` · `PHONE` · `ID_NUM` · `EMAIL` · `LOC` · `BANK` · `DATE` · `SECRET`.
+Regex patterns live in [`entiscope/regex_rules.yaml`](entiscope/regex_rules.yaml)
+(user-extensible, no code change); KO-specific extended entities in
+[`entiscope/entity_config.yaml`](entiscope/entity_config.yaml).
+
+## How it works
+
+A **two-stage hybrid pipeline** (SRS §3.4), results merged via Union:
+
+1. **Regex filter** — structurally obvious PII (phone, email, IDs, cards, secrets).
+2. **ONNX NER** — a BIOES token classifier with a constrained Viterbi decoder for
+   contextual PII (names, addresses, private dates).
+
+Inference is **ONNX Runtime only — no PyTorch at runtime**. Recall-first, with
+runtime [operating-point](docs/OPERATING_POINTS.md) tuning (no retraining).
+PyTorch is needed only to [fine-tune](docs/FINETUNING.md).
+
+## Model & performance
+
+- **Architecture** — `klue/roberta-base` encoder → BIOES token-classification
+  head → constrained Viterbi decoder.
+- **Runtime artifact** — INT8-quantized ONNX, **~105 MB** (well under the
+  ≤ 150 MB budget), max sequence length 256. Weights download from Hugging Face
+  Hub on first use, with a SHA-256 `checksum.txt` for integrity verification.
+- **Accuracy** — meets the entity-level **strict F1 ≥ 0.93** target on a
+  held-out validation set whose examples are disjoint from the training data, so
+  the score reflects generalization rather than memorization. See
+  [Evaluation & Output Modes](docs/EVAL_AND_OUTPUT_MODES.md) to score it on your
+  own labelled data.
+
+## Limitations
+
+- Not an anonymization/compliance guarantee; use as one layer of privacy-by-design.
+- Known failure modes: under-detection of uncommon/regional names; over-redaction
+  of public entities in ambiguous contexts; fragmented spans in heavily
+  mixed-format text; missed `SECRET` for novel credential formats.
+- Extra human review recommended for medical/legal/financial/government workflows.
+
+## License
+
+Apache-2.0. Weights are distributed on Hugging Face Hub under Apache-2.0 with a
+`checksum.txt` (SHA-256) for integrity verification. Contributions welcome — see
+[CONTRIBUTING.md](CONTRIBUTING.md).

entiscope_ko-0.1.0/entiscope/__init__.py

@@ -0,0 +1,12 @@
+"""entiscope-ko — Korean PII detection & masking engine (Apache-2.0).
+
+Public surface:
+    from entiscope import Entiscope          # or: from entiscope_ko import Entiscope
+"""
+from ._api import Entiscope
+from ._core.schema import RedactionResult, DetectedSpan, SCHEMA_VERSION
+
+__version__ = "0.1.0"
+__language__ = "ko"
+
+__all__ = ["Entiscope", "RedactionResult", "DetectedSpan", "SCHEMA_VERSION", "__version__"]

entiscope_ko-0.1.0/entiscope/__main__.py

@@ -0,0 +1,104 @@
+"""Unified CLI entrypoint: ``entiscope redact | eval | train`` (SRS FR-2.1)."""
+from __future__ import annotations
+
+import sys
+from typing import List, Optional, Sequence
+
+from ._api import Entiscope
+from ._cli.args import build_parser
+from ._cli.render import print_result, supports_color
+
+_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) -> Entiscope:
+    return Entiscope.from_pretrained(
+        operating_point=_parse_operating_point(getattr(args, "operating_point", "balanced")),
+        cache_dir=getattr(args, "cache_dir", None),
+        revision=getattr(args, "revision", None),
+        regex_only=getattr(args, "regex_only", False),
+        providers=_PROVIDERS.get(getattr(args, "device", "cpu"), None),
+    )
+
+
+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("entiscope 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 'entiscope-ko[train]' ({exc})",
+            file=sys.stderr,
+        )
+        return 2
+    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())

entiscope_ko-0.1.0/entiscope/_api.py

@@ -0,0 +1,129 @@
+"""Public Python API (SRS FR-2.7).
+
+    from entiscope_ko import Entiscope
+    engine = Entiscope.from_pretrained()
+    result = engine.redact("홍길동의 전화번호는 010-1234-5678")
+    result.masked_text      # "<PER>의 전화번호는 <PHONE>"
+    result.detected_spans   # [{"label": "PER", ...}, ...]
+    result.summary          # {"span_count": 2, "by_label": {...}}
+
+The engine is a two-stage hybrid pipeline (SRS §3.4): a regex filter (always
+available) plus an optional ONNX NER stage. ``regex_only=True`` runs the engine
+with no model weights — useful offline and for structurally-obvious PII.
+"""
+from __future__ import annotations
+
+import os
+from pathlib import Path
+from typing import Iterable, List, Optional, Sequence, Union
+
+from ._core.bioes import Span
+from ._core.download import DEFAULT_REPO, resolve_weights
+from ._core.pipeline import assemble, merge_union
+from ._core.regex_filter import RegexFilter
+from ._core.schema import RedactionResult
+from ._core.transitions import CATEGORIES, resolve_operating_point
+
+OperatingPoint = Union[str, Sequence[float], dict, None]
+
+
+def _package_resource(name: str) -> Path:
+    """Locate a packaged resource (regex_rules.yaml / entity_config.yaml)."""
+    env = os.environ.get(f"ENTISCOPE_{name.split('.')[0].upper()}")
+    if env:
+        return Path(env)
+    try:
+        from importlib.resources import files
+
+        cand = Path(str(files("entiscope") / name))
+        if cand.exists():
+            return cand
+    except Exception:  # pragma: no cover - fallback for odd layouts
+        pass
+    return Path(__file__).resolve().parent / name
+
+
+class Entiscope:
+    """KO PII redaction engine."""
+
+    def __init__(
+        self,
+        regex_filter: RegexFilter,
+        runtime=None,
+        operating_point: OperatingPoint = "balanced",
+    ) -> None:
+        self._regex = regex_filter
+        self._runtime = runtime
+        self._operating_point = operating_point
+
+    # -- construction -------------------------------------------------------
+    @classmethod
+    def from_pretrained(
+        cls,
+        operating_point: OperatingPoint = "balanced",
+        *,
+        repo_id: str = DEFAULT_REPO,
+        revision: Optional[str] = None,
+        cache_dir: Optional[str] = None,
+        regex_rules: Optional[str] = None,
+        providers: Optional[Sequence[str]] = None,
+        regex_only: bool = False,
+    ) -> "Entiscope":
+        """Load the engine, downloading ONNX weights from HF Hub on first use.
+
+        Pass ``regex_only=True`` to skip the NER stage (no weights required).
+        ``cache_dir`` pointing at a local bundle enables fully-offline use.
+        """
+        rules_path = regex_rules or _package_resource("regex_rules.yaml")
+        regex = RegexFilter.from_yaml(rules_path)
+
+        runtime = None
+        if not regex_only:
+            from ._core.runtime import NerRuntime
+
+            bundle = resolve_weights(repo_id=repo_id, revision=revision, cache_dir=cache_dir)
+            runtime = NerRuntime(bundle, providers=providers)
+        return cls(regex, runtime, operating_point)
+
+    @classmethod
+    def regex_only(cls, regex_rules: Optional[str] = None) -> "Entiscope":
+        """Convenience constructor for a Stage-1-only engine (no weights)."""
+        return cls.from_pretrained(regex_only=True, regex_rules=regex_rules)
+
+    # -- inference ----------------------------------------------------------
+    def _effective_biases(self, operating_point: OperatingPoint) -> List[float]:
+        """Learned baseline biases shifted by the operating-point offset (FR-2.5)."""
+        offset = resolve_operating_point(
+            operating_point if operating_point is not None else self._operating_point
+        )
+        base = self._runtime.default_biases if self._runtime else [0.0] * len(CATEGORIES)
+        return [b + o for b, o in zip(base, offset)]
+
+    def redact(
+        self,
+        text: str,
+        entity_types: Optional[Iterable[str]] = None,
+        output_mode: str = "typed",
+        operating_point: OperatingPoint = None,
+    ) -> RedactionResult:
+        """Detect and mask PII in a single string (FR-2.2)."""
+        regex_spans: List[Span] = self._regex.find(text)
+        ner_spans: List[Span] = []
+        mismatch = False
+        if self._runtime is not None:
+            ner_spans, mismatch = self._runtime.predict(text, self._effective_biases(operating_point))
+        merged = merge_union(regex_spans, ner_spans)
+        return assemble(text, merged, output_mode, entity_types, mismatch)
+
+    def batch_redact(
+        self,
+        texts: Sequence[str],
+        entity_types: Optional[Iterable[str]] = None,
+        output_mode: str = "typed",
+        operating_point: OperatingPoint = None,
+    ) -> List[RedactionResult]:
+        return [self.redact(t, entity_types, output_mode, operating_point) for t in texts]
+
+    @property
+    def has_ner(self) -> bool:
+        return self._runtime is not None

entiscope_ko-0.1.0/entiscope/_cli/__init__.py

@@ -0,0 +1,4 @@
+"""CLI argument parsing and terminal rendering."""
+from .args import build_parser
+
+__all__ = ["build_parser"]