cleanmonkey 0.1.0__tar.gz

cleanmonkey-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 RexBytes
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

cleanmonkey-0.1.0/PKG-INFO

@@ -0,0 +1,152 @@
+Metadata-Version: 2.4
+Name: cleanmonkey
+Version: 0.1.0
+Summary: One-call text cleanup: invisible characters, smart quotes, whitespace normalization.
+Author-email: RexBytes <pythonic@rexbytes.com>
+License: MIT
+Project-URL: Homepage, https://github.com/RexBytes/cleanmonkey
+Project-URL: Repository, https://github.com/RexBytes/cleanmonkey
+Project-URL: Issues, https://github.com/RexBytes/cleanmonkey/issues
+Keywords: text,cleanup,whitespace,unicode,normalize
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+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
+Classifier: Topic :: Text Processing :: Filters
+Classifier: Typing :: Typed
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: license-file
+
+# cleanmonkey
+
+One-call text cleanup for invisible characters, smart quotes, and whitespace normalization.
+
+## Install
+
+```bash
+pip install cleanmonkey
+```
+
+## Quick Start
+
+```python
+from cleanmonkey import clean
+
+# Sensible defaults handle the common garbage
+clean("hello\u00a0world\u2019s \u2014 test")
+# → "hello world's - test"
+
+# Idempotent — safe to call twice
+clean(clean(text)) == clean(text)
+```
+
+## What It Cleans (by default)
+
+| Category | Examples | Result |
+|---|---|---|
+| Non-breaking spaces | `\u00a0`, `\u2007`, `\u202f` | Regular space |
+| Zero-width chars | `\u200b`, `\u200c`, `\u200d`, `\ufeff` | Removed |
+| Smart quotes | `\u2018` `\u2019` `\u201c` `\u201d` | `'` and `"` |
+| Dashes | `\u2013` (en), `\u2014` (em) | `-` |
+| Ellipsis | `\u2026` | `...` |
+| Control chars | null, form feed, vertical tab | Removed |
+| Line endings | `\r\n`, `\r` | `\n` |
+| Multiple spaces | `"hello   world"` | `"hello world"` |
+| Leading/trailing | `"  hello  "` | `"hello"` |
+
+## Granular Control
+
+Override any default:
+
+```python
+clean(text, smart_quotes=False)       # keep curly quotes
+clean(text, dashes=False)             # keep em/en dashes
+clean(text, fullwidth=True)           # also normalize fullwidth digits/letters
+clean(text, collapse_spaces=False)    # keep multiple spaces
+clean(text, strip=False)              # keep leading/trailing whitespace
+```
+
+## Profiles
+
+```python
+clean(text, profile="default")     # all normalizations (the default)
+clean(text, profile="csv")         # default + fullwidth normalization
+clean(text, profile="sql")         # default + fullwidth normalization
+clean(text, profile="display")     # keep smart quotes & dashes; still clean invisible, control, whitespace, line endings
+clean(text, profile="minimal")     # invisible chars only, no collapsing or stripping
+clean(text, profile="aggressive")  # everything including fullwidth
+```
+
+## Batch Helpers
+
+```python
+from cleanmonkey import clean_column, clean_dict
+
+# Clean a list (non-strings pass through)
+clean_column(["hello\u00a0world", 42, None])
+# → ["hello world", 42, None]
+
+# Recursively clean dict values
+clean_dict({"name": "John\u00a0Doe", "nested": {"val": "test\u200b"}})
+# → {"name": "John Doe", "nested": {"val": "test"}}
+
+# Also clean keys
+clean_dict({"key\u00a0name": "val"}, keys=True)
+# → {"key name": "val"}
+```
+
+## Inspect
+
+Find out what's lurking in your text:
+
+```python
+from cleanmonkey import inspect
+
+for info in inspect("hello\u00a0world\u200b"):
+    print(f"{info.codepoint} {info.name} count={info.count} at {info.positions}")
+# U+00A0 NO-BREAK SPACE count=1 at [5]
+# U+200B ZERO WIDTH SPACE count=1 at [11]
+```
+
+## CLI
+
+```bash
+# Clean a file
+cleanmonkey input.txt -o output.txt
+
+# Pipe through stdin
+cat dirty.csv | cleanmonkey > clean.csv
+
+# Use a profile
+cleanmonkey --profile csv input.txt
+
+# Inspect mode — report what's in a file
+cleanmonkey --inspect input.txt
+
+# Machine-readable JSON inspect output
+cleanmonkey --json input.txt
+
+# Selective overrides
+cleanmonkey --no-smart-quotes --fullwidth input.txt
+
+# Preserve whitespace structure
+cleanmonkey --no-strip --no-collapse-spaces input.txt
+
+# Preserve line endings (CR/CRLF)
+cleanmonkey --no-line-endings input.txt
+```
+
+## Built for LLMs
+
+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.
+
+## License
+
+MIT

cleanmonkey-0.1.0/README.md

@@ -0,0 +1,126 @@
+# cleanmonkey
+
+One-call text cleanup for invisible characters, smart quotes, and whitespace normalization.
+
+## Install
+
+```bash
+pip install cleanmonkey
+```
+
+## Quick Start
+
+```python
+from cleanmonkey import clean
+
+# Sensible defaults handle the common garbage
+clean("hello\u00a0world\u2019s \u2014 test")
+# → "hello world's - test"
+
+# Idempotent — safe to call twice
+clean(clean(text)) == clean(text)
+```
+
+## What It Cleans (by default)
+
+| Category | Examples | Result |
+|---|---|---|
+| Non-breaking spaces | `\u00a0`, `\u2007`, `\u202f` | Regular space |
+| Zero-width chars | `\u200b`, `\u200c`, `\u200d`, `\ufeff` | Removed |
+| Smart quotes | `\u2018` `\u2019` `\u201c` `\u201d` | `'` and `"` |
+| Dashes | `\u2013` (en), `\u2014` (em) | `-` |
+| Ellipsis | `\u2026` | `...` |
+| Control chars | null, form feed, vertical tab | Removed |
+| Line endings | `\r\n`, `\r` | `\n` |
+| Multiple spaces | `"hello   world"` | `"hello world"` |
+| Leading/trailing | `"  hello  "` | `"hello"` |
+
+## Granular Control
+
+Override any default:
+
+```python
+clean(text, smart_quotes=False)       # keep curly quotes
+clean(text, dashes=False)             # keep em/en dashes
+clean(text, fullwidth=True)           # also normalize fullwidth digits/letters
+clean(text, collapse_spaces=False)    # keep multiple spaces
+clean(text, strip=False)              # keep leading/trailing whitespace
+```
+
+## Profiles
+
+```python
+clean(text, profile="default")     # all normalizations (the default)
+clean(text, profile="csv")         # default + fullwidth normalization
+clean(text, profile="sql")         # default + fullwidth normalization
+clean(text, profile="display")     # keep smart quotes & dashes; still clean invisible, control, whitespace, line endings
+clean(text, profile="minimal")     # invisible chars only, no collapsing or stripping
+clean(text, profile="aggressive")  # everything including fullwidth
+```
+
+## Batch Helpers
+
+```python
+from cleanmonkey import clean_column, clean_dict
+
+# Clean a list (non-strings pass through)
+clean_column(["hello\u00a0world", 42, None])
+# → ["hello world", 42, None]
+
+# Recursively clean dict values
+clean_dict({"name": "John\u00a0Doe", "nested": {"val": "test\u200b"}})
+# → {"name": "John Doe", "nested": {"val": "test"}}
+
+# Also clean keys
+clean_dict({"key\u00a0name": "val"}, keys=True)
+# → {"key name": "val"}
+```
+
+## Inspect
+
+Find out what's lurking in your text:
+
+```python
+from cleanmonkey import inspect
+
+for info in inspect("hello\u00a0world\u200b"):
+    print(f"{info.codepoint} {info.name} count={info.count} at {info.positions}")
+# U+00A0 NO-BREAK SPACE count=1 at [5]
+# U+200B ZERO WIDTH SPACE count=1 at [11]
+```
+
+## CLI
+
+```bash
+# Clean a file
+cleanmonkey input.txt -o output.txt
+
+# Pipe through stdin
+cat dirty.csv | cleanmonkey > clean.csv
+
+# Use a profile
+cleanmonkey --profile csv input.txt
+
+# Inspect mode — report what's in a file
+cleanmonkey --inspect input.txt
+
+# Machine-readable JSON inspect output
+cleanmonkey --json input.txt
+
+# Selective overrides
+cleanmonkey --no-smart-quotes --fullwidth input.txt
+
+# Preserve whitespace structure
+cleanmonkey --no-strip --no-collapse-spaces input.txt
+
+# Preserve line endings (CR/CRLF)
+cleanmonkey --no-line-endings input.txt
+```
+
+## Built for LLMs
+
+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.
+
+## License
+
+MIT

cleanmonkey-0.1.0/pyproject.toml

@@ -0,0 +1,43 @@
+[build-system]
+requires = ["setuptools>=68.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "cleanmonkey"
+version = "0.1.0"
+description = "One-call text cleanup: invisible characters, smart quotes, whitespace normalization."
+readme = "README.md"
+license = {text = "MIT"}
+requires-python = ">=3.10"
+authors = [
+    {name = "RexBytes", email = "pythonic@rexbytes.com"},
+]
+keywords = ["text", "cleanup", "whitespace", "unicode", "normalize"]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Topic :: Text Processing",
+    "Topic :: Text Processing :: Filters",
+    "Typing :: Typed",
+]
+
+[project.scripts]
+cleanmonkey = "cleanmonkey.cli:_main_with_broken_pipe_handling"
+
+[project.urls]
+Homepage = "https://github.com/RexBytes/cleanmonkey"
+Repository = "https://github.com/RexBytes/cleanmonkey"
+Issues = "https://github.com/RexBytes/cleanmonkey/issues"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+pythonpath = ["src"]

cleanmonkey-0.1.0/setup.cfg

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

cleanmonkey-0.1.0/src/cleanmonkey/__init__.py

@@ -0,0 +1,7 @@
+"""cleanmonkey — one-call text cleanup for invisible characters, smart quotes, and whitespace."""
+
+from cleanmonkey.core import MAX_DEPTH, clean, clean_column, clean_dict, inspect
+from cleanmonkey.profiles import PROFILES, Profile
+
+__version__ = "0.1.0"
+__all__ = ["MAX_DEPTH", "clean", "clean_column", "clean_dict", "inspect", "Profile", "PROFILES"]

cleanmonkey-0.1.0/src/cleanmonkey/__main__.py

@@ -0,0 +1,5 @@
+"""Allow running cleanmonkey as ``python -m cleanmonkey``."""
+
+from cleanmonkey.cli import _main_with_broken_pipe_handling
+
+_main_with_broken_pipe_handling()