privaci 0.1.0b4__tar.gz

privaci-0.1.0b4/LICENSE

@@ -0,0 +1,99 @@
+# Copyright 2026 BoundaryLogic. All rights reserved.
+#
+# The PrivaCI source code is licensed under the Elastic License 2.0.
+# See https://www.elastic.co/licensing/elastic-license
+
+
+Elastic License 2.0
+
+URL: https://www.elastic.co/licensing/elastic-license
+
+## Acceptance
+
+By using the software, you agree to all of the terms and conditions below.
+
+## Copyright License
+
+The licensor grants you a non-exclusive, royalty-free, worldwide,
+non-sublicensable, non-transferable license to use, copy, distribute, make
+available, and prepare derivative works of the software, in each case subject to
+the limitations and conditions below.
+
+## Limitations
+
+You may not provide the software to third parties as a hosted or managed
+service, where the service provides users with access to any substantial set of
+the features or functionality of the software.
+
+You may not move, change, disable, or circumvent the license key functionality
+in the software, and you may not remove or obscure any functionality in the
+software that is protected by the license key.
+
+You may not alter, remove, or obscure any licensing, copyright, or other notices
+of the licensor in the software. Any use of the licensor’s trademarks is subject
+to applicable law.
+
+## Patents
+
+The licensor grants you a license, under any patent claims the licensor can
+license, or becomes able to license, to make, have made, use, sell, offer for
+sale, import and have imported the software, in each case subject to the
+limitations and conditions in this license. This license does not cover any
+patent claims that you cause to be infringed by modifications or additions to
+the software. If you or your company make any written claim that the software
+infringes or contributes to infringement of any patent, your patent license for
+the software granted under these terms ends immediately. If your company makes
+such a claim, your patent license ends immediately for work on behalf of your
+company.
+
+## Notices
+
+You must ensure that anyone who gets a copy of any part of the software from you
+also gets a copy of these terms.
+
+If you modify the software, you must include in any modified copies of the
+software prominent notices stating that you have modified the software.
+
+## No Other Rights
+
+These terms do not imply any licenses other than those expressly granted in
+these terms.
+
+## Termination
+
+If you use the software in violation of these terms, such use is not licensed,
+and your licenses will automatically terminate. If the licensor provides you
+with a notice of your violation, and you cease all violation of this license no
+later than 30 days after you receive that notice, your licenses will be
+reinstated retroactively. However, if you violate these terms after such
+reinstatement, any additional violation of these terms will cause your licenses
+to terminate automatically and permanently.
+
+## No Liability
+
+*As far as the law allows, the software comes as is, without any warranty or
+condition, and the licensor will not be liable to you for any damages arising
+out of these terms or the use or nature of the software, under any kind of
+legal claim.*
+
+## Definitions
+
+The **licensor** is the entity offering these terms, and the **software** is the
+software the licensor makes available under these terms, including any portion
+of it.
+
+**you** refers to the individual or entity agreeing to these terms.
+
+**your company** is any legal entity, sole proprietorship, or other kind of
+organization that you work for, plus all organizations that have control over,
+are under the control of, or are under common control with that
+organization. **control** means ownership of substantially all the assets of an
+entity, or the power to direct its management and policies by vote, contract, or
+otherwise. Control can be direct or indirect.
+
+**your licenses** are all the licenses granted to you for the software under
+these terms.
+
+**use** means anything you do with the software requiring one of your licenses.
+
+**trademark** means trademarks, service marks, and similar rights.

privaci-0.1.0b4/PKG-INFO

@@ -0,0 +1,108 @@
+Metadata-Version: 2.4
+Name: privaci
+Version: 0.1.0b4
+Summary: In-VPC PostgreSQL masking and anonymization engine
+Author-email: BoundaryLogic <hello@boundarylogic.io>
+License: Elastic License 2.0
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: Other/Proprietary License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Database
+Classifier: Topic :: Security
+Requires-Python: >=3.12
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: asyncpg==0.30.0
+Requires-Dist: click<8.5,>=8.1.7
+Requires-Dist: cryptography==48.0.1
+Requires-Dist: pydantic==2.10.6
+Requires-Dist: pyyaml==6.0.2
+Requires-Dist: typer==0.16.0
+Provides-Extra: nlp
+Requires-Dist: spacy==3.8.7; extra == "nlp"
+Provides-Extra: dev
+Requires-Dist: black==26.3.1; extra == "dev"
+Requires-Dist: cosmic-ray==8.4.6; extra == "dev"
+Requires-Dist: hypothesis==6.127.6; extra == "dev"
+Requires-Dist: isort==6.0.1; extra == "dev"
+Requires-Dist: mkdocs-material==9.6.11; extra == "dev"
+Requires-Dist: mkdocs==1.6.1; extra == "dev"
+Requires-Dist: mypy==1.15.0; extra == "dev"
+Requires-Dist: pip-audit==2.7.3; extra == "dev"
+Requires-Dist: pip-tools==7.4.1; extra == "dev"
+Requires-Dist: pre-commit==4.1.0; extra == "dev"
+Requires-Dist: pytest-asyncio==1.4.0; extra == "dev"
+Requires-Dist: pytest-cov==6.0.0; extra == "dev"
+Requires-Dist: pytest-mock==3.14.0; extra == "dev"
+Requires-Dist: pytest==9.0.3; extra == "dev"
+Requires-Dist: ruff==0.9.6; extra == "dev"
+Requires-Dist: types-PyYAML==6.0.12.20241230; extra == "dev"
+Dynamic: license-file
+
+# PrivaCI
+
+**One command. Sanitized staging data. No data leaves your VPC.**
+
+PrivaCI is a stateless batch engine that reads from a PostgreSQL source
+(typically a production replica), masks PII with a three-tier pipeline, and
+writes realistic synthetic data to a staging database with referential
+integrity preserved.
+
+## Prerequisites
+
+- Python **3.12+**, or the official container image
+  (`ghcr.io/boundarylogic/privaci`)
+- A PostgreSQL **source** (typically a production replica) and an empty
+  **target** database
+
+## Quickstart
+
+**Fastest path** — self-contained evaluation stack (~60 s):
+
+```bash
+export ANONYMIZATION_SALT="$(openssl rand -hex 32)"
+make eval-up
+```
+
+See [`docs/quickstart.md`](docs/quickstart.md) for the full walkthrough.
+
+**Your own databases:**
+
+```bash
+pip install -e .
+privaci gen-salt > .privaci-salt && chmod 600 .privaci-salt
+export ANONYMIZATION_SALT=$(cat .privaci-salt)
+export SOURCE_DB_URL=postgresql://user:pass@source-host:5432/app
+export TARGET_DB_URL=postgresql://user:pass@target-host:5432/staging
+
+privaci validate && privaci dry-run && privaci run && privaci verify
+```
+
+Browse the docs site locally: `pip install -e ".[dev]" && make docs-serve`
+
+## Documentation
+
+Start with the [documentation index](docs/README.md) or [quickstart](docs/quickstart.md).
+Key pages:
+
+**Using PrivaCI**
+
+- [CLI reference](docs/cli-reference.md) — every command, its options, and examples
+- [Configuration reference](docs/configuration.md) — the `mask-rules.yaml` format
+- [Error codes](docs/error-codes.md) — exit codes and message format
+- [State & audit schema](docs/state-schema.md) — what runs write to `_privaci`
+- [Extending PrivaCI](docs/extending-privaci.md) — the plugin contract model
+
+**Developing PrivaCI**
+
+- [Local development & testing](docs/local-development.md)
+- [Test fixtures — MedicalHelpDesk Corp](docs/test-fixtures.md)
+- [Architecture decision records](docs/adr/README.md)
+
+## License
+
+The engine is licensed under the [Elastic License 2.0](LICENSE). Optional
+paid features ship as a separate plugin layer via the
+[plugin contracts](docs/extending-privaci.md).

privaci-0.1.0b4/README.md

@@ -0,0 +1,65 @@
+# PrivaCI
+
+**One command. Sanitized staging data. No data leaves your VPC.**
+
+PrivaCI is a stateless batch engine that reads from a PostgreSQL source
+(typically a production replica), masks PII with a three-tier pipeline, and
+writes realistic synthetic data to a staging database with referential
+integrity preserved.
+
+## Prerequisites
+
+- Python **3.12+**, or the official container image
+  (`ghcr.io/boundarylogic/privaci`)
+- A PostgreSQL **source** (typically a production replica) and an empty
+  **target** database
+
+## Quickstart
+
+**Fastest path** — self-contained evaluation stack (~60 s):
+
+```bash
+export ANONYMIZATION_SALT="$(openssl rand -hex 32)"
+make eval-up
+```
+
+See [`docs/quickstart.md`](docs/quickstart.md) for the full walkthrough.
+
+**Your own databases:**
+
+```bash
+pip install -e .
+privaci gen-salt > .privaci-salt && chmod 600 .privaci-salt
+export ANONYMIZATION_SALT=$(cat .privaci-salt)
+export SOURCE_DB_URL=postgresql://user:pass@source-host:5432/app
+export TARGET_DB_URL=postgresql://user:pass@target-host:5432/staging
+
+privaci validate && privaci dry-run && privaci run && privaci verify
+```
+
+Browse the docs site locally: `pip install -e ".[dev]" && make docs-serve`
+
+## Documentation
+
+Start with the [documentation index](docs/README.md) or [quickstart](docs/quickstart.md).
+Key pages:
+
+**Using PrivaCI**
+
+- [CLI reference](docs/cli-reference.md) — every command, its options, and examples
+- [Configuration reference](docs/configuration.md) — the `mask-rules.yaml` format
+- [Error codes](docs/error-codes.md) — exit codes and message format
+- [State & audit schema](docs/state-schema.md) — what runs write to `_privaci`
+- [Extending PrivaCI](docs/extending-privaci.md) — the plugin contract model
+
+**Developing PrivaCI**
+
+- [Local development & testing](docs/local-development.md)
+- [Test fixtures — MedicalHelpDesk Corp](docs/test-fixtures.md)
+- [Architecture decision records](docs/adr/README.md)
+
+## License
+
+The engine is licensed under the [Elastic License 2.0](LICENSE). Optional
+paid features ship as a separate plugin layer via the
+[plugin contracts](docs/extending-privaci.md).

privaci-0.1.0b4/pyproject.toml

@@ -0,0 +1,152 @@
+[build-system]
+requires = ["setuptools>=69", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "privaci"
+version = "0.1.0-beta.4"
+description = "In-VPC PostgreSQL masking and anonymization engine"
+readme = "README.md"
+license = { text = "Elastic License 2.0" }
+requires-python = ">=3.12"
+authors = [{ name = "BoundaryLogic", email = "hello@boundarylogic.io" }]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "License :: Other/Proprietary License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.12",
+    "Topic :: Database",
+    "Topic :: Security",
+]
+dependencies = [
+    "asyncpg==0.30.0",
+    # Pinned alongside typer: Click 8.4 broke Typer 0.15 (make_metavar(ctx)).
+    # Keep this range until a Typer release is validated against newer Click.
+    "click>=8.1.7,<8.5",
+    "cryptography==48.0.1",
+    "pydantic==2.10.6",
+    "pyyaml==6.0.2",
+    "typer==0.16.0",
+]
+
+[project.optional-dependencies]
+nlp = [
+    "spacy==3.8.7",
+]
+dev = [
+    "black==26.3.1",
+    "cosmic-ray==8.4.6",
+    "hypothesis==6.127.6",
+    "isort==6.0.1",
+    "mkdocs-material==9.6.11",
+    "mkdocs==1.6.1",
+    "mypy==1.15.0",
+    "pip-audit==2.7.3",
+    "pip-tools==7.4.1",
+    "pre-commit==4.1.0",
+    "pytest-asyncio==1.4.0",
+    "pytest-cov==6.0.0",
+    "pytest-mock==3.14.0",
+    "pytest==9.0.3",
+    "ruff==0.9.6",
+    "types-PyYAML==6.0.12.20241230",
+]
+
+[project.scripts]
+privaci = "privaci.cli.app:main"
+
+[project.entry-points."privaci.plugins"]
+# Commercial layer registers implementations here.
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.setuptools.package-data]
+# Ship the PEP 561 marker so downstream packages (e.g. privaci-commercial) get
+# the engine's types when they build against privaci.contracts.
+privaci = ["py.typed"]
+
+[tool.pytest.ini_options]
+asyncio_mode = "auto"
+asyncio_default_fixture_loop_scope = "function"
+testpaths = ["tests"]
+markers = [
+    "integration: tests that require a real PostgreSQL instance",
+    "slow: long-running tests",
+    "spike: Week-1 architecture validation (see docs/spikes/)",
+]
+addopts = "-m 'not integration'"
+
+[tool.coverage.run]
+source = ["src/privaci"]
+branch = true
+# Paths must match measured files under ``pytest --cov=src`` (``src/privaci/...``).
+omit = [
+    "*/__main__.py",
+    "*/mask/__init__.py",
+    "*/stream/__init__.py",
+    "*/schema/__init__.py",
+    "*/pipeline/__init__.py",
+    "*/autodetect/__init__.py",
+    "*/observability/__init__.py",
+    "*/preflight/__init__.py",
+    "*/verify/__init__.py",
+    "*/verify/runner.py",
+    "*/verify/structural.py",
+    "*/spikes/*",
+]
+
+[tool.coverage.report]
+fail_under = 85
+show_missing = true
+
+[tool.black]
+line-length = 88
+target-version = ["py312"]
+
+[tool.isort]
+profile = "black"
+line_length = 88
+src_paths = ["src", "tests"]
+
+[tool.mypy]
+python_version = "3.12"
+strict = true
+warn_unreachable = true
+packages = ["privaci", "tests"]
+mypy_path = "src"
+
+[[tool.mypy.overrides]]
+# Optional/untyped third-party libs (cloud SDKs are lazy-imported per scheme).
+module = [
+    "spacy",
+    "spacy.*",
+    "asyncpg",
+    "asyncpg.*",
+    "boto3",
+    "botocore",
+    "botocore.*",
+    "azure.*",
+    "hvac",
+    "hvac.*",
+    "prometheus_client",
+    "prometheus_client.*",
+]
+ignore_missing_imports = true
+
+[tool.ruff]
+line-length = 88
+target-version = "py312"
+src = ["src", "tests"]
+
+[tool.ruff.lint]
+select = ["E", "F", "W", "I", "N", "UP", "S", "B", "A"]
+
+[tool.ruff.lint.per-file-ignores]
+"tests/conftest.py" = ["E402"]
+"tests/**" = ["S101", "S105", "S108"]
+"src/privaci/secrets/**" = ["A005"]
+
+[tool.ruff.lint.isort]
+known-first-party = ["privaci", "tests"]

privaci-0.1.0b4/setup.cfg

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

privaci-0.1.0b4/src/privaci/__init__.py

@@ -0,0 +1,5 @@
+"""PrivaCI — in-VPC PostgreSQL masking and anonymization engine."""
+
+from __future__ import annotations
+
+__version__ = "0.1.0"

privaci-0.1.0b4/src/privaci/__main__.py

@@ -0,0 +1,8 @@
+"""Allow `python -m privaci` to invoke the CLI."""
+
+from __future__ import annotations
+
+from privaci.cli.app import main
+
+if __name__ == "__main__":
+    raise SystemExit(main())

privaci-0.1.0b4/src/privaci/autodetect/__init__.py

@@ -0,0 +1,27 @@
+"""PII column auto-detection."""
+
+from __future__ import annotations
+
+from privaci.autodetect.models import (
+    DetectionConfidence,
+    DetectionFinding,
+    DetectionResult,
+)
+from privaci.autodetect.report import write_detection_report
+from privaci.autodetect.resolve import (
+    build_detection,
+    resolve_effective_table_config,
+    uncovered_strict_columns,
+)
+from privaci.autodetect.scanner import scan_catalog
+
+__all__ = [
+    "DetectionConfidence",
+    "DetectionFinding",
+    "DetectionResult",
+    "build_detection",
+    "resolve_effective_table_config",
+    "scan_catalog",
+    "uncovered_strict_columns",
+    "write_detection_report",
+]

privaci-0.1.0b4/src/privaci/autodetect/actions.py

@@ -0,0 +1,70 @@
+"""Map pattern rules to config column actions, respecting column types."""
+
+from __future__ import annotations
+
+from privaci.autodetect.patterns import PatternRule
+from privaci.catalog.models import ColumnInfo
+from privaci.config.actions import (
+    ColumnAction,
+    FakeAction,
+    HashAction,
+    NerMaskAction,
+    StaticAction,
+)
+
+_TEXTLIKE = frozenset(
+    {"text", "character varying", "character", "varchar", "char", "citext", "name"}
+)
+
+# Column base types each fake provider can produce a valid value for. Providers
+# absent from this map are treated as text-only.
+_PROVIDER_TYPES: dict[str, frozenset[str]] = {
+    "dob": frozenset({"date"}) | _TEXTLIKE,
+    "ip_address": frozenset({"inet", "cidr"}) | _TEXTLIKE,
+    "uuid": frozenset({"uuid"}) | _TEXTLIKE,
+}
+
+
+def _base_type(data_type: str) -> str:
+    head, _, _ = data_type.strip().lower().partition("(")
+    return head.strip()
+
+
+def action_for_column(rule: PatternRule, column: ColumnInfo) -> ColumnAction | None:
+    """Build a type-compatible action for ``column``, or ``None`` to skip.
+
+    Returns ``None`` when the matched rule's action cannot produce a value
+    valid for the column's type (e.g. ``hash`` on a ``uuid`` column), so the
+    scanner can leave the column as passthrough rather than emit a broken mask.
+    """
+    base = _base_type(column.data_type)
+    if rule.action == "fake":
+        return _fake_action(rule, base)
+    if rule.action == "hash":
+        return _hash_action(base)
+    if rule.action == "static":
+        if base not in _TEXTLIKE:
+            return None
+        value = rule.static_value or "privaci-test-pw"
+        return StaticAction(action="static", value=value)
+    if base not in _TEXTLIKE:
+        return None
+    return NerMaskAction(action="ner_mask")
+
+
+def _fake_action(rule: PatternRule, base: str) -> ColumnAction | None:
+    if rule.provider is None:
+        msg = f"fake rule {rule.rule_id} missing provider"
+        raise ValueError(msg)
+    allowed = _PROVIDER_TYPES.get(rule.provider, _TEXTLIKE)
+    if base not in allowed:
+        return None
+    return FakeAction(action="fake", provider=rule.provider)
+
+
+def _hash_action(base: str) -> ColumnAction | None:
+    if base == "uuid":
+        return FakeAction(action="fake", provider="uuid")
+    if base in _TEXTLIKE:
+        return HashAction(action="hash")
+    return None

privaci-0.1.0b4/src/privaci/autodetect/freeform.py

@@ -0,0 +1,68 @@
+"""Freeform-text shape and confidence scoring."""
+
+from __future__ import annotations
+
+import re
+
+from privaci.autodetect.models import DetectionConfidence
+from privaci.autodetect.table_context import table_sensitivity
+from privaci.catalog.models import ColumnInfo
+
+_FREEFORM_MIN_AVG_WIDTH = 200
+_FREEFORM_UNCERTAIN_MIN_AVG_WIDTH = 100
+_TEXT_TYPES = frozenset({"text"})
+_VARCHAR_RE = re.compile(r"^character varying\((\d+)\)$", re.IGNORECASE)
+
+
+def is_freeform_eligible_type(column: ColumnInfo) -> bool:
+    """Return whether the column type can hold narrative freeform text."""
+    base = _base_type(column.data_type)
+    if base in _TEXT_TYPES:
+        return True
+    match = _VARCHAR_RE.match(column.data_type.strip())
+    if match is None:
+        return False
+    return int(match.group(1)) >= 500
+
+
+def score_freeform_confidence(
+    *,
+    table_name: str,
+    column: ColumnInfo,
+) -> tuple[DetectionConfidence, tuple[str, ...]]:
+    """Score a freeform name-match using type, stats, and table context."""
+    reasons: list[str] = []
+    if not is_freeform_eligible_type(column):
+        reasons.append(f"type {column.data_type!r} is not freeform-eligible")
+        return "low", tuple(reasons)
+
+    reasons.append("column type is freeform-eligible")
+    sensitivity = table_sensitivity(table_name)
+    avg_width = column.avg_width
+
+    if avg_width is None:
+        reasons.append("pg_stats.avg_width unavailable")
+        if sensitivity == "sensitive":
+            reasons.append("sensitive table context")
+            return "medium", tuple(reasons)
+        return "low", tuple(reasons)
+
+    reasons.append(f"pg_stats.avg_width={avg_width:.0f}")
+    if avg_width >= _FREEFORM_MIN_AVG_WIDTH:
+        if sensitivity == "low":
+            reasons.append("low-sensitivity table context downgrades confidence")
+            return "medium", tuple(reasons)
+        if sensitivity == "sensitive":
+            reasons.append("sensitive table context")
+        return "high", tuple(reasons)
+
+    if avg_width >= _FREEFORM_UNCERTAIN_MIN_AVG_WIDTH and sensitivity == "sensitive":
+        reasons.append("borderline avg_width on sensitive table")
+        return "medium", tuple(reasons)
+
+    reasons.append("avg_width below freeform threshold")
+    return "low", tuple(reasons)
+
+
+def _base_type(data_type: str) -> str:
+    return re.sub(r"\(.*\)$", "", data_type.strip().lower())

privaci-0.1.0b4/src/privaci/autodetect/matcher.py

@@ -0,0 +1,59 @@
+"""Column-name pattern matching for auto-detect."""
+
+from __future__ import annotations
+
+import re
+from typing import get_args
+
+from privaci.autodetect.patterns import (
+    BUILTIN_PATTERNS,
+    PatternKind,
+    PatternRule,
+    compile_patterns,
+)
+
+
+def match_column_name(column_name: str) -> PatternRule | None:
+    """Return the first pattern rule matching ``column_name``, if any.
+
+    Rules are evaluated in library order; earlier rules win.
+    """
+    lowered = column_name.lower()
+    compiled = compile_patterns()
+    for rule in BUILTIN_PATTERNS:
+        if _rule_matches(lowered, rule, compiled):
+            return rule
+    return None
+
+
+def _delimiter_bounded_substring(lowered: str, needle: str) -> bool:
+    """Match ``needle`` only at underscore boundaries or as the whole name."""
+    if lowered == needle:
+        return True
+    padded = f"_{lowered}_"
+    return f"_{needle}_" in padded
+
+
+def _rule_matches(
+    lowered: str,
+    rule: PatternRule,
+    compiled: dict[str, re.Pattern[str]],
+) -> bool:
+    kind = rule.kind
+    if kind == "substring":
+        return rule.pattern in lowered
+    elif kind == "bounded_substring":
+        return _delimiter_bounded_substring(lowered, rule.pattern)
+    elif kind == "suffix":
+        return lowered.endswith(rule.pattern)
+    elif kind in ("prefix", "wildcard_prefix"):
+        return lowered.startswith(rule.pattern)
+    elif kind == "regex":
+        pattern = compiled.get(rule.rule_id)
+        return pattern is not None and pattern.fullmatch(lowered) is not None
+    # CodeQL's mixed-return rule wants an explicit non-returning terminal rather
+    # than an implicit fall-through after the exhaustive ``kind`` chain above.
+    # Derive the valid kinds from PatternKind so the message can never drift.
+    expected = ", ".join(get_args(PatternKind))
+    msg = f"Unknown auto-detect pattern kind: {kind!r}. Expected one of: {expected}."
+    raise ValueError(msg)