entiscope-en 0.1.0__tar.gz

entiscope_en-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_en-0.1.0/PKG-INFO

@@ -0,0 +1,126 @@
+Metadata-Version: 2.4
+Name: entiscope-en
+Version: 0.1.0
+Summary: entiscope-en — English language pack for the entiscope PII engine
+Author: entiscope Core Team
+License: Apache-2.0
+Project-URL: Homepage, https://github.com/zafrem/entiscope-en
+Project-URL: Documentation, https://github.com/zafrem/entiscope-en/blob/main/README.md
+Keywords: pii,ner,redaction,privacy,english,onnx
+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: entiscope>=0.1.0
+Provides-Extra: train
+Requires-Dist: entiscope[train]>=0.1.0; extra == "train"
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.0; extra == "dev"
+Dynamic: license-file
+
+# entiscope-en
+
+English **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 English text.
+
+> ⚠️ entiscope is a redaction **aid**, not an anonymization or compliance
+> guarantee. See [Limitations](#limitations).
+
+## Install
+
+```bash
+pip install entiscope-en
+```
+
+## 60-second quickstart
+
+**Python**
+
+```python
+from entiscope_en import Entiscope
+
+engine = Entiscope.from_pretrained()                 # downloads ONNX weights on first run
+result = engine.redact("John Smith's number is 555-123-4567")
+
+result.masked_text        # "<PER>'s number is <PHONE>"
+result.detected_spans     # [DetectedSpan(label="PER", start=0, end=10, ...), ...]
+result.summary            # {"span_count": 2, "by_label": {"PER": 1, "PHONE": 1}, ...}
+```
+
+**CLI**
+
+```bash
+entiscope redact "John Smith's number is 555-123-4567"
+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) |
+| Run it offline / air-gapped | [Offline Usage](docs/OFFLINE.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); EN-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** — `roberta-base` encoder → BIOES token-classification head →
+  constrained Viterbi decoder.
+- **Runtime artifact** — INT8-quantized ONNX, **~120 MB** (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_en-0.1.0/README.md

@@ -0,0 +1,97 @@
+# entiscope-en
+
+English **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 English text.
+
+> ⚠️ entiscope is a redaction **aid**, not an anonymization or compliance
+> guarantee. See [Limitations](#limitations).
+
+## Install
+
+```bash
+pip install entiscope-en
+```
+
+## 60-second quickstart
+
+**Python**
+
+```python
+from entiscope_en import Entiscope
+
+engine = Entiscope.from_pretrained()                 # downloads ONNX weights on first run
+result = engine.redact("John Smith's number is 555-123-4567")
+
+result.masked_text        # "<PER>'s number is <PHONE>"
+result.detected_spans     # [DetectedSpan(label="PER", start=0, end=10, ...), ...]
+result.summary            # {"span_count": 2, "by_label": {"PER": 1, "PHONE": 1}, ...}
+```
+
+**CLI**
+
+```bash
+entiscope redact "John Smith's number is 555-123-4567"
+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) |
+| Run it offline / air-gapped | [Offline Usage](docs/OFFLINE.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); EN-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** — `roberta-base` encoder → BIOES token-classification head →
+  constrained Viterbi decoder.
+- **Runtime artifact** — INT8-quantized ONNX, **~120 MB** (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_en-0.1.0/entiscope_en/__init__.py

@@ -0,0 +1,25 @@
+"""entiscope-en — English language pack for the ``entiscope`` engine (Apache-2.0).
+
+This is a thin **plugin**: it ships only English data (``regex_rules.yaml``,
+``entity_config.yaml``) and registers itself with the core via the
+``entiscope.languages`` entry point. All engine code lives in the ``entiscope``
+core package, which is pulled in as a dependency.
+
+    from entiscope_en import Entiscope          # re-exported from the core
+    engine = Entiscope.from_pretrained(lang="en")
+    engine.redact("John Smith's number is 555-123-4567").masked_text
+    # "<PER>'s number is <PHONE>"
+"""
+from entiscope import Entiscope, RedactionResult, DetectedSpan, LanguagePlugin, __version__
+
+#: Registered under the ``entiscope.languages`` entry-point group (see pyproject).
+LANG = LanguagePlugin(
+    code="en",
+    display_name="English",
+    default_repo="zafrem/entiscope-en",
+    package="entiscope_en",
+    scripts=("Latin",),
+    default_base_model="roberta-base",
+)
+
+__all__ = ["Entiscope", "RedactionResult", "DetectedSpan", "LANG", "__version__"]

entiscope_en-0.1.0/entiscope_en/entity_config.yaml

@@ -0,0 +1,49 @@
+# entiscope-en — entity configuration (ENTITY_SPEC §8.3).
+# Base PII taxonomy (SRS §6) plus EN-specific extended entities. Extended
+# entities are detected by regex only unless added to the NER label space via a
+# custom fine-tune (FR-2.6).
+language: en
+
+base_entities:
+  - code: PER
+    detection: contextual
+    regex: null
+  - code: PHONE
+    detection: structural
+    regex: '\+?1?[-. ]?\(?\d{3}\)?[-. ]?\d{3}[-. ]?\d{4}'
+  - code: ID_NUM
+    detection: structural
+    regex: '\d{3}-\d{2}-\d{4}'
+  - code: EMAIL
+    detection: structural
+    regex: '[A-Za-z0-9._%+\-]+@[A-Za-z0-9.\-]+\.[A-Za-z]{2,}'
+  - code: LOC
+    detection: contextual
+    regex: null
+  - code: BANK
+    detection: structural
+    regex: '\d{4}[- ]\d{4}[- ]\d{4}[- ]\d{4}'
+  - code: DATE
+    detection: hybrid
+    regex: null
+  - code: SECRET
+    detection: hybrid
+    regex: 'sk-[A-Za-z0-9]{20,}'
+
+extended_entities:
+  # EN-specific identifiers not in the base label set (ENTITY_SPEC §3.3).
+  - code: EIN
+    detection: structural
+    regex: '\d{2}-\d{7}'
+    description: US Employer Identification Number
+  - code: PASSPORT
+    detection: structural
+    regex: '[A-Z]\d{8}'
+    description: US passport number
+
+# Partial-masking policy (ENTITY_SPEC §7.3); applied by downstream consumers.
+partial_masking:
+  ID_NUM: '***-**-1234'
+  PHONE: '555-***-4567'
+  BANK: '****-****-****-3456'
+  EMAIL: 'u***@domain.com'

entiscope_en-0.1.0/entiscope_en/regex_rules.yaml

@@ -0,0 +1,73 @@
+# entiscope-en — Stage 1 Regex Filter rules (SRS §3.4, ENTITY_SPEC §3).
+# Structurally obvious PII caught before the NER stage. Externally extensible:
+# add patterns here without touching engine code. Each rule is tried in order;
+# `priority` breaks ties when two rules overlap (higher wins).
+#
+# Fields:
+#   label    : entiscope entity code
+#   pattern  : Python `regex`/`re` pattern (anchored as written)
+#   priority : overlap-resolution weight (default 0)
+version: 1
+language: en
+rules:
+  # -- SECRET (high priority: very specific, must win over generic numbers) --
+  # These credential formats are language-neutral; shared with the KO ruleset.
+  - label: SECRET
+    pattern: 'sk-ant-api03-[A-Za-z0-9\-_]{20,}'
+    priority: 100
+  - label: SECRET
+    pattern: 'sk-[A-Za-z0-9]{20,}'
+    priority: 95
+  - label: SECRET
+    pattern: 'ghp_[A-Za-z0-9]{36}'
+    priority: 95
+  - label: SECRET
+    pattern: 'gho_[A-Za-z0-9]{36}'
+    priority: 95
+  - label: SECRET
+    pattern: 'AKIA[A-Z0-9]{16}'
+    priority: 95
+  - label: SECRET
+    pattern: 'AIza[A-Za-z0-9\-_]{35}'
+    priority: 95
+  - label: SECRET
+    pattern: 'eyJ[A-Za-z0-9\-_]+\.[A-Za-z0-9\-_]+\.[A-Za-z0-9\-_]+'
+    priority: 90
+  - label: SECRET
+    pattern: '[A-Z_]{2,}=\S{8,}'
+    priority: 40
+
+  # -- EMAIL ----------------------------------------------------------------
+  - label: EMAIL
+    pattern: '[A-Za-z0-9._%+\-]+@[A-Za-z0-9.\-]+\.[A-Za-z]{2,}'
+    priority: 80
+
+  # -- ID_NUM (US/intl) -----------------------------------------------------
+  - label: ID_NUM            # US Social Security Number (SSN)
+    pattern: '\d{3}-\d{2}-\d{4}'
+    priority: 70
+  - label: ID_NUM            # US Employer Identification Number (EIN)
+    pattern: '\d{2}-\d{7}'
+    priority: 60
+
+  # -- BANK (card numbers; before phone to avoid mis-capture) ---------------
+  - label: BANK
+    pattern: '\d{4}-\d{4}-\d{4}-\d{4}'
+    priority: 65
+  - label: BANK             # 16 digits, space-separated
+    pattern: '\d{4} \d{4} \d{4} \d{4}'
+    priority: 64
+
+  # -- PHONE (US/intl) ------------------------------------------------------
+  - label: PHONE            # +1 country code, e.g. +1-555-123-4567
+    pattern: '\+1[-. ]?\(?\d{3}\)?[-. ]?\d{3}[-. ]?\d{4}'
+    priority: 55
+  - label: PHONE            # (555) 123-4567
+    pattern: '\(\d{3}\)[-. ]?\d{3}[-. ]?\d{4}'
+    priority: 52
+  - label: PHONE            # 555-123-4567 / 555.123.4567 / 555 123 4567
+    pattern: '\b\d{3}[-. ]\d{3}[-. ]\d{4}\b'
+    priority: 50
+  - label: PHONE            # generic E.164, e.g. +442071838750
+    pattern: '\+\d{6,15}'
+    priority: 35

entiscope_en-0.1.0/entiscope_en.egg-info/PKG-INFO

@@ -0,0 +1,126 @@
+Metadata-Version: 2.4
+Name: entiscope-en
+Version: 0.1.0
+Summary: entiscope-en — English language pack for the entiscope PII engine
+Author: entiscope Core Team
+License: Apache-2.0
+Project-URL: Homepage, https://github.com/zafrem/entiscope-en
+Project-URL: Documentation, https://github.com/zafrem/entiscope-en/blob/main/README.md
+Keywords: pii,ner,redaction,privacy,english,onnx
+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: entiscope>=0.1.0
+Provides-Extra: train
+Requires-Dist: entiscope[train]>=0.1.0; extra == "train"
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.0; extra == "dev"
+Dynamic: license-file
+
+# entiscope-en
+
+English **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 English text.
+
+> ⚠️ entiscope is a redaction **aid**, not an anonymization or compliance
+> guarantee. See [Limitations](#limitations).
+
+## Install
+
+```bash
+pip install entiscope-en
+```
+
+## 60-second quickstart
+
+**Python**
+
+```python
+from entiscope_en import Entiscope
+
+engine = Entiscope.from_pretrained()                 # downloads ONNX weights on first run
+result = engine.redact("John Smith's number is 555-123-4567")
+
+result.masked_text        # "<PER>'s number is <PHONE>"
+result.detected_spans     # [DetectedSpan(label="PER", start=0, end=10, ...), ...]
+result.summary            # {"span_count": 2, "by_label": {"PER": 1, "PHONE": 1}, ...}
+```
+
+**CLI**
+
+```bash
+entiscope redact "John Smith's number is 555-123-4567"
+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) |
+| Run it offline / air-gapped | [Offline Usage](docs/OFFLINE.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); EN-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** — `roberta-base` encoder → BIOES token-classification head →
+  constrained Viterbi decoder.
+- **Runtime artifact** — INT8-quantized ONNX, **~120 MB** (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_en-0.1.0/entiscope_en.egg-info/SOURCES.txt

@@ -0,0 +1,14 @@
+LICENSE
+README.md
+pyproject.toml
+entiscope_en/__init__.py
+entiscope_en/entity_config.yaml
+entiscope_en/regex_rules.yaml
+entiscope_en.egg-info/PKG-INFO
+entiscope_en.egg-info/SOURCES.txt
+entiscope_en.egg-info/dependency_links.txt
+entiscope_en.egg-info/entry_points.txt
+entiscope_en.egg-info/requires.txt
+entiscope_en.egg-info/top_level.txt
+tests/test_en_regex.py
+tests/test_plugin_registered.py

entiscope_en-0.1.0/entiscope_en.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

entiscope_en-0.1.0/entiscope_en.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[entiscope.languages]
+en = entiscope_en:LANG

entiscope_en-0.1.0/entiscope_en.egg-info/requires.txt

@@ -0,0 +1,8 @@
+entiscope>=0.1.0
+
+[dev]
+pytest>=7.0
+pytest-cov>=4.0
+
+[train]
+entiscope[train]>=0.1.0

entiscope_en-0.1.0/entiscope_en.egg-info/top_level.txt

@@ -0,0 +1 @@
+entiscope_en

entiscope_en-0.1.0/pyproject.toml

@@ -0,0 +1,48 @@
+[build-system]
+requires = ["setuptools>=61.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "entiscope-en"
+version = "0.1.0"
+description = "entiscope-en — English language pack for the entiscope PII engine"
+readme = "README.md"
+requires-python = ">=3.9"
+license = { text = "Apache-2.0" }
+authors = [{ name = "entiscope Core Team" }]
+keywords = ["pii", "ner", "redaction", "privacy", "english", "onnx"]
+classifiers = [
+    "License :: OSI Approved :: Apache Software License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3 :: Only",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Topic :: Text Processing :: Linguistic",
+]
+# The engine lives in the core; this pack only adds English data + registration.
+dependencies = [
+    "entiscope>=0.1.0",
+]
+
+[project.optional-dependencies]
+train = ["entiscope[train]>=0.1.0"]
+dev = ["pytest>=7.0", "pytest-cov>=4.0"]
+
+# Register the English plugin so the core discovers it at runtime. No console
+# script here — the `entiscope` command is owned solely by the core.
+[project.entry-points."entiscope.languages"]
+en = "entiscope_en:LANG"
+
+[project.urls]
+Homepage = "https://github.com/zafrem/entiscope-en"
+Documentation = "https://github.com/zafrem/entiscope-en/blob/main/README.md"
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["entiscope_en*"]
+
+[tool.setuptools.package-data]
+entiscope_en = ["*.yaml"]

entiscope_en-0.1.0/setup.cfg

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

entiscope_en-0.1.0/tests/test_en_regex.py

@@ -0,0 +1,35 @@
+"""English Stage-1 regex rules (over the real en data) + engine wiring."""
+import pytest
+
+from entiscope import installed_languages
+from entiscope._core.regex_filter import RegexFilter
+
+from entiscope_en import LANG, Entiscope
+
+
+def _filter():
+    return RegexFilter.from_yaml(LANG.regex_rules_path())
+
+
+def test_en_phone_email_id():
+    rf = _filter()
+    text = "call 555-123-4567, email user@example.com, ssn 123-45-6789"
+    spans = {(s.label, text[s.start:s.end]) for s in rf.find(text)}
+    assert ("PHONE", "555-123-4567") in spans
+    assert ("EMAIL", "user@example.com") in spans
+    assert ("ID_NUM", "123-45-6789") in spans
+
+
+def test_en_card_is_bank_not_phone():
+    rf = _filter()
+    spans = {(s.label, s.start, s.end) for s in rf.find("card 1234-5678-9012-3456 charged")}
+    assert any(lab == "BANK" for lab, _s, _e in spans)
+    assert not any(lab == "PHONE" for lab, _s, _e in spans)
+
+
+def test_en_engine_regex_only():
+    if "en" not in installed_languages():
+        pytest.skip("entiscope-en not pip-installed; plugin not discoverable")
+    engine = Entiscope.regex_only(lang="en")
+    r = engine.redact("call 555-123-4567 email user@example.com")
+    assert r.redacted_text == "call <PHONE> email <EMAIL>"

entiscope_en-0.1.0/tests/test_plugin_registered.py

@@ -0,0 +1,21 @@
+"""Verify the English pack registers itself with the core (requires install)."""
+import pytest
+
+from entiscope import installed_languages
+from entiscope_en import LANG
+
+
+def test_lang_record_shape():
+    assert LANG.code == "en"
+    assert LANG.display_name == "English"
+    assert LANG.default_repo == "zafrem/entiscope-en"
+    assert LANG.scripts == ("Latin",)
+    assert LANG.regex_rules_path().exists()
+    assert LANG.entity_config_path().exists()
+
+
+def test_discovered_via_entry_point():
+    langs = installed_languages()
+    if "en" not in langs:
+        pytest.skip("entiscope-en not pip-installed; entry point not discoverable")
+    assert langs["en"].display_name == "English"