cleanmonkey 0.1.0__tar.gz → 0.2.0__tar.gz

{cleanmonkey-0.1.0/src/cleanmonkey.egg-info → cleanmonkey-0.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cleanmonkey
-Version: 0.1.0
+Version: 0.2.0
 Summary: One-call text cleanup: invisible characters, smart quotes, whitespace normalization.
 Author-email: RexBytes <pythonic@rexbytes.com>
 License: MIT
@@ -22,6 +22,12 @@ Classifier: Typing :: Typed
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
+Provides-Extra: dev
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: pytest-cov; extra == "dev"
+Requires-Dist: hypothesis; extra == "dev"
+Requires-Dist: ruff; extra == "dev"
+Requires-Dist: mypy; extra == "dev"
 Dynamic: license-file
 
 # cleanmonkey
@@ -147,6 +153,28 @@ cleanmonkey --no-line-endings input.txt
 
 cleanmonkey is designed to work well as a tool for large language models. Invisible character cleanup is a constant source of silent bugs in LLM-driven data pipelines — non-breaking spaces break splits, zero-width characters corrupt comparisons, and smart quotes fail exact matches. Without cleanmonkey, LLMs end up generating repetitive `.replace()` chains that miss edge cases and waste tokens. A single `clean()` call handles all of it with a structured, idempotent result — no multi-step prompting or character-by-character debugging required. Fewer tokens in, clean data out.
 
+## A note on whitespace
+
+By default `clean()` strips each line and collapses runs of spaces, which is
+correct for prose but **destroys indentation** in structured text (YAML, Python,
+Markdown). Use `clean(text, strip=False, collapse_spaces=False)` or
+`profile="minimal"` for those. See [`LIMITATIONS.md`](LIMITATIONS.md) for this
+and other deliberate design tradeoffs.
+
+## Quality & review
+
+cleanmonkey is hardened with a competitive multi-model review methodology and a
+measurable release gate:
+
+- [`CONTRIBUTING.md`](CONTRIBUTING.md) — testing philosophy and the review-panel
+  process.
+- [`LIMITATIONS.md`](LIMITATIONS.md) — intentional tradeoffs reviewers should not
+  re-litigate.
+- [`RELEASE_READINESS.md`](RELEASE_READINESS.md) + `release_readiness.json` +
+  `scripts/readiness.py` — the release rubric and convergence metric
+  (`python scripts/readiness.py`).
+- [`REVIEW_HISTORY.md`](REVIEW_HISTORY.md) — how the library was hardened.
+
 ## License
 
 MIT

{cleanmonkey-0.1.0 → cleanmonkey-0.2.0}/README.md

@@ -121,6 +121,28 @@ cleanmonkey --no-line-endings input.txt
 
 cleanmonkey is designed to work well as a tool for large language models. Invisible character cleanup is a constant source of silent bugs in LLM-driven data pipelines — non-breaking spaces break splits, zero-width characters corrupt comparisons, and smart quotes fail exact matches. Without cleanmonkey, LLMs end up generating repetitive `.replace()` chains that miss edge cases and waste tokens. A single `clean()` call handles all of it with a structured, idempotent result — no multi-step prompting or character-by-character debugging required. Fewer tokens in, clean data out.
 
+## A note on whitespace
+
+By default `clean()` strips each line and collapses runs of spaces, which is
+correct for prose but **destroys indentation** in structured text (YAML, Python,
+Markdown). Use `clean(text, strip=False, collapse_spaces=False)` or
+`profile="minimal"` for those. See [`LIMITATIONS.md`](LIMITATIONS.md) for this
+and other deliberate design tradeoffs.
+
+## Quality & review
+
+cleanmonkey is hardened with a competitive multi-model review methodology and a
+measurable release gate:
+
+- [`CONTRIBUTING.md`](CONTRIBUTING.md) — testing philosophy and the review-panel
+  process.
+- [`LIMITATIONS.md`](LIMITATIONS.md) — intentional tradeoffs reviewers should not
+  re-litigate.
+- [`RELEASE_READINESS.md`](RELEASE_READINESS.md) + `release_readiness.json` +
+  `scripts/readiness.py` — the release rubric and convergence metric
+  (`python scripts/readiness.py`).
+- [`REVIEW_HISTORY.md`](REVIEW_HISTORY.md) — how the library was hardened.
+
 ## License
 
 MIT

{cleanmonkey-0.1.0 → cleanmonkey-0.2.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "cleanmonkey"
-version = "0.1.0"
+version = "0.2.0"
 description = "One-call text cleanup: invisible characters, smart quotes, whitespace normalization."
 readme = "README.md"
 license = {text = "MIT"}
@@ -27,6 +27,9 @@ classifiers = [
     "Typing :: Typed",
 ]
 
+[project.optional-dependencies]
+dev = ["pytest", "pytest-cov", "hypothesis", "ruff", "mypy"]
+
 [project.scripts]
 cleanmonkey = "cleanmonkey.cli:_main_with_broken_pipe_handling"
 
@@ -41,3 +44,11 @@ where = ["src"]
 [tool.pytest.ini_options]
 testpaths = ["tests"]
 pythonpath = ["src"]
+
+[tool.ruff]
+target-version = "py310"
+src = ["src", "tests"]
+
+[tool.mypy]
+files = ["src"]
+python_version = "3.10"

{cleanmonkey-0.1.0 → cleanmonkey-0.2.0}/src/cleanmonkey/__init__.py

@@ -3,5 +3,5 @@
 from cleanmonkey.core import MAX_DEPTH, clean, clean_column, clean_dict, inspect
 from cleanmonkey.profiles import PROFILES, Profile
 
-__version__ = "0.1.0"
+__version__ = "0.2.0"
 __all__ = ["MAX_DEPTH", "clean", "clean_column", "clean_dict", "inspect", "Profile", "PROFILES"]

{cleanmonkey-0.1.0 → cleanmonkey-0.2.0}/src/cleanmonkey/core.py

@@ -4,7 +4,18 @@ from __future__ import annotations
 
 import re
 from dataclasses import dataclass, replace
-from typing import Any
+from typing import Any, cast
+
+from cleanmonkey.maps import (
+    CONTROL,
+    DASHES,
+    ELLIPSIS,
+    FULLWIDTH,
+    INVISIBLE,
+    SMART_QUOTES,
+    WHITESPACE,
+)
+from cleanmonkey.profiles import PROFILES, Profile
 
 _BOOL_OVERRIDE_NAMES_CLEAN = (
     "smart_quotes", "dashes", "ellipsis", "invisible", "whitespace",
@@ -27,18 +38,6 @@ def _validate_bool_overrides(overrides: dict[str, Any], allowed: tuple[str, ...]
                 f"{func_name}() override {name!r} must be bool or None, got {type(val).__name__}"
             )
 
-from cleanmonkey.maps import (
-    CONTROL,
-    DASHES,
-    ELLIPSIS,
-    FULLWIDTH,
-    INVISIBLE,
-    SMART_QUOTES,
-    WHITESPACE,
-)
-from cleanmonkey.profiles import PROFILES, Profile
-
-
 def _validate_profile_kwarg(kwargs: dict[str, Any], func_name: str) -> None:
     """Validate the 'profile' kwarg type and name if present, matching clean()'s contract."""
     if "profile" in kwargs:
@@ -63,7 +62,7 @@ MAX_DEPTH: int = 200
 
 def _build_table(profile: Profile) -> dict[int, str | int | None]:
     """Build a str.translate table from a profile."""
-    merged: dict[str, str] = {}
+    merged: dict[str, str | int | None] = {}
     if profile.invisible:
         merged.update(INVISIBLE)
     if profile.whitespace:
@@ -78,7 +77,7 @@ def _build_table(profile: Profile) -> dict[int, str | int | None]:
         merged.update(ELLIPSIS)
     if profile.fullwidth:
         merged.update(FULLWIDTH)
-    return str.maketrans({k: v for k, v in merged.items()})
+    return str.maketrans(merged)
 
 
 # Cache tables for default profiles
@@ -228,7 +227,13 @@ def _clean_value(
                 _clean_value(item, keys=keys, _seen=_seen, _depth=_depth + 1, **kwargs)
                 for item in v
             ]
-            result = type(v)(cleaned_items)
+            if isinstance(v, tuple) and hasattr(v, "_fields"):
+                # namedtuple: its constructor takes positional fields, not a
+                # single iterable, so type(v)(cleaned_items) would fail. Rebuild
+                # via the _make classmethod, which constructs from an iterable.
+                result = cast(Any, type(v))._make(cleaned_items)
+            else:
+                result = type(v)(cleaned_items)
             if isinstance(v, (set, frozenset)) and len(result) != len(v):
                 raise ValueError(
                     "Set member collision: cleaning produced duplicate members"

{cleanmonkey-0.1.0 → cleanmonkey-0.2.0/src/cleanmonkey.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cleanmonkey
-Version: 0.1.0
+Version: 0.2.0
 Summary: One-call text cleanup: invisible characters, smart quotes, whitespace normalization.
 Author-email: RexBytes <pythonic@rexbytes.com>
 License: MIT
@@ -22,6 +22,12 @@ Classifier: Typing :: Typed
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
+Provides-Extra: dev
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: pytest-cov; extra == "dev"
+Requires-Dist: hypothesis; extra == "dev"
+Requires-Dist: ruff; extra == "dev"
+Requires-Dist: mypy; extra == "dev"
 Dynamic: license-file
 
 # cleanmonkey
@@ -147,6 +153,28 @@ cleanmonkey --no-line-endings input.txt
 
 cleanmonkey is designed to work well as a tool for large language models. Invisible character cleanup is a constant source of silent bugs in LLM-driven data pipelines — non-breaking spaces break splits, zero-width characters corrupt comparisons, and smart quotes fail exact matches. Without cleanmonkey, LLMs end up generating repetitive `.replace()` chains that miss edge cases and waste tokens. A single `clean()` call handles all of it with a structured, idempotent result — no multi-step prompting or character-by-character debugging required. Fewer tokens in, clean data out.
 
+## A note on whitespace
+
+By default `clean()` strips each line and collapses runs of spaces, which is
+correct for prose but **destroys indentation** in structured text (YAML, Python,
+Markdown). Use `clean(text, strip=False, collapse_spaces=False)` or
+`profile="minimal"` for those. See [`LIMITATIONS.md`](LIMITATIONS.md) for this
+and other deliberate design tradeoffs.
+
+## Quality & review
+
+cleanmonkey is hardened with a competitive multi-model review methodology and a
+measurable release gate:
+
+- [`CONTRIBUTING.md`](CONTRIBUTING.md) — testing philosophy and the review-panel
+  process.
+- [`LIMITATIONS.md`](LIMITATIONS.md) — intentional tradeoffs reviewers should not
+  re-litigate.
+- [`RELEASE_READINESS.md`](RELEASE_READINESS.md) + `release_readiness.json` +
+  `scripts/readiness.py` — the release rubric and convergence metric
+  (`python scripts/readiness.py`).
+- [`REVIEW_HISTORY.md`](REVIEW_HISTORY.md) — how the library was hardened.
+
 ## License
 
 MIT

{cleanmonkey-0.1.0 → cleanmonkey-0.2.0}/src/cleanmonkey.egg-info/SOURCES.txt

@@ -12,6 +12,7 @@ src/cleanmonkey.egg-info/PKG-INFO
 src/cleanmonkey.egg-info/SOURCES.txt
 src/cleanmonkey.egg-info/dependency_links.txt
 src/cleanmonkey.egg-info/entry_points.txt
+src/cleanmonkey.egg-info/requires.txt
 src/cleanmonkey.egg-info/top_level.txt
 tests/test_cli.py
 tests/test_core.py

cleanmonkey-0.2.0/src/cleanmonkey.egg-info/requires.txt

@@ -0,0 +1,7 @@
+
+[dev]
+pytest
+pytest-cov
+hypothesis
+ruff
+mypy

{cleanmonkey-0.1.0 → cleanmonkey-0.2.0}/tests/test_cli.py

@@ -6,7 +6,6 @@ import os
 import stat
 import subprocess
 import sys
-import tempfile
 from unittest import mock
 
 import pytest

{cleanmonkey-0.1.0 → cleanmonkey-0.2.0}/tests/test_core.py

@@ -279,6 +279,46 @@ class TestTupleRecursion:
         assert isinstance(result["data"], tuple)
         assert result["data"] == (1, "ab", None)
 
+    def test_namedtuple_in_list_preserves_type(self):
+        """namedtuples (tuple subclass, positional ctor) must clean and keep type."""
+        from collections import namedtuple
+
+        Row = namedtuple("Row", ["name", "city"])
+        result = clean_column([Row("Alice\u200b", "NYC"), Row("Bob", "LA")])
+        assert result == [Row("Alice", "NYC"), Row("Bob", "LA")]
+        assert isinstance(result[0], Row)
+        # cleaned values are accessible by field name (not collapsed to a plain tuple)
+        assert result[0].name == "Alice"
+
+    def test_namedtuple_as_dict_value_preserves_type(self):
+        """namedtuple dict values must clean and remain the same namedtuple type."""
+        from collections import namedtuple
+
+        Row = namedtuple("Row", ["name", "city"])
+        result = clean_dict({"r": Row("x\u200b", "y\u00a0z")})
+        assert isinstance(result["r"], Row)
+        assert result["r"] == Row("x", "y z")
+
+    def test_dict_list_subclasses_normalize_to_base_type(self):
+        """Documented contract (LIMITATIONS.md): dict/list subclasses clean their
+        values but are returned as the base type, not the subclass."""
+        from collections import Counter, OrderedDict, defaultdict
+
+        od = clean_dict(OrderedDict([("a\u200b", "v\u200b")]), keys=True)
+        assert type(od) is dict and od == {"a": "v"}
+
+        dd = clean_dict(defaultdict(int, {"a\u200b": "v\u200b"}), keys=True)
+        assert type(dd) is dict and dd == {"a": "v"}
+
+        class MyList(list):
+            pass
+
+        ml = clean_column(MyList(["a\u200b", "b"]))
+        assert type(ml) is list and ml == ["a", "b"]
+
+        cnt = clean_column([Counter({"a\u200b": 2})], keys=True)
+        assert type(cnt[0]) is dict and cnt[0] == {"a": 2}
+
 
 class TestCycleDetection:
     """Cyclic structures must raise ValueError, not RecursionError."""