arnio 0.1.0__tar.gz

arnio-0.1.0/.gitignore

@@ -0,0 +1,218 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#   Usually these files are written by a python script from a template
+#   before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+# Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+# uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+# poetry.lock
+# poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+# pdm.lock
+# pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+# pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#   JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#   be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#   and can be added to the global gitignore or merged into this file.  For a more nuclear
+#   option (not recommended) you can uncomment the following to ignore the entire idea folder.
+# .idea/
+
+# Abstra
+#   Abstra is an AI-powered process automation framework.
+#   Ignore directories containing user credentials, local state, and settings.
+#   Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#   that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#   and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#   you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+# Temporary file for partial code execution
+tempCodeRunnerFile.py
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml

arnio-0.1.0/CMakeLists.txt

@@ -0,0 +1,20 @@
+cmake_minimum_required(VERSION 3.15)
+project(arnio LANGUAGES CXX)
+
+set(CMAKE_CXX_STANDARD 17)
+set(CMAKE_CXX_STANDARD_REQUIRED ON)
+set(CMAKE_POSITION_INDEPENDENT_CODE ON)
+
+find_package(Python3 REQUIRED COMPONENTS Interpreter Development)
+
+# Fetch pybind11
+include(FetchContent)
+FetchContent_Declare(
+    pybind11
+    GIT_REPOSITORY https://github.com/pybind/pybind11.git
+    GIT_TAG        v2.12.0
+)
+FetchContent_MakeAvailable(pybind11)
+
+add_subdirectory(cpp)
+add_subdirectory(bindings)

arnio-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Anish Raj
+
+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.

arnio-0.1.0/PKG-INFO

@@ -0,0 +1,189 @@
+Metadata-Version: 2.2
+Name: arnio
+Version: 0.1.0
+Summary: Fast CSV processing and data cleaning companion for pandas
+Author: Anish Raj
+License: MIT
+Requires-Python: >=3.9
+Requires-Dist: pandas>=1.5
+Requires-Dist: numpy>=1.23
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.0; extra == "dev"
+Description-Content-Type: text/markdown
+
+# arnio
+
+**Fast CSV processing and data cleaning for Python — powered by C++.**
+
+---
+
+arnio is a lightweight, C++-backed Python library designed to make CSV ingestion and data cleaning faster, simpler, and more memory-efficient. It sits comfortably alongside your existing pandas workflows, handling the heavy lifting before your data ever hits a DataFrame.
+
+If you've ever waited too long for a large CSV to load, or spent more time wrangling messy columns than actually analyzing data — arnio is built for you.
+
+```python
+import arnio as ar
+
+df = ar.read_csv("sales_data.csv")
+clean = ar.clean(df, drop_nulls=True, strip_whitespace=True)
+```
+
+---
+
+## Why arnio?
+
+Python's data ecosystem is excellent — but reading and cleaning raw CSV files at scale has always been a rough edge. `pandas.read_csv` is versatile and reliable, but it isn't optimized for raw speed or low memory pressure. Preprocessing logic ends up scattered across notebooks, inconsistent between projects, and slow on large files.
+
+arnio addresses this directly:
+
+- **Reads large CSVs faster** using a C++ parsing core with minimal Python overhead
+- **Provides a clean, composable cleaning API** so preprocessing logic is explicit, readable, and repeatable
+- **Works with pandas** — arnio outputs standard DataFrames; it's a faster on-ramp, not a replacement
+- **Keeps memory usage low** by parsing efficiently before data is materialized in Python
+
+---
+
+## Key Features
+
+| Feature | Description |
+|---|---|
+| ⚡ C++ CSV parser | Reads large files with significantly lower overhead than pure-Python parsers |
+| 🧹 Cleaning primitives | Drop nulls, strip whitespace, fix dtypes, normalize column names, and more |
+| 🐼 pandas-compatible output | Returns standard `pd.DataFrame` objects — drop arnio into any existing workflow |
+| 🧠 Memory-conscious | Designed to avoid unnecessary copies during ingestion and cleaning |
+| 🔗 Composable API | Chain cleaning operations in a clear, readable style |
+| 📦 Simple import | `import arnio as ar` — that's it |
+
+---
+
+## Installation
+
+```bash
+pip install arnio
+```
+
+> **Note:** arnio requires Python 3.9+ and a platform with a compatible C++ build (wheels are provided for Linux, macOS, and Windows on PyPI). For source builds, a C++17-compatible compiler is required.
+
+---
+
+## Quick Start
+
+### Reading a CSV
+
+```python
+import arnio as ar
+
+# Fast CSV ingestion — returns a pandas DataFrame
+df = ar.read_csv("data/transactions.csv")
+```
+
+### Cleaning Data
+
+```python
+import arnio as ar
+
+df = ar.read_csv("data/customers.csv")
+
+clean = ar.clean(
+    df,
+    drop_nulls=True,          # Remove rows with missing values
+    strip_whitespace=True,    # Trim leading/trailing whitespace in string columns
+    normalize_columns=True,   # Lowercase, underscore-separated column names
+)
+```
+
+### Chaining Operations
+
+```python
+import arnio as ar
+
+result = (
+    ar.read_csv("data/orders.csv")
+      .pipe(ar.drop_nulls)
+      .pipe(ar.normalize_columns)
+      .pipe(ar.strip_whitespace)
+)
+```
+
+arnio operations return standard DataFrames, so you can pass results directly into any pandas, scikit-learn, or plotting workflow without modification.
+
+---
+
+## arnio + pandas: Better Together
+
+arnio is not a pandas replacement. It is the step that happens *before* pandas — and occasionally alongside it.
+
+Think of it this way:
+
+```
+Raw CSV on disk
+      │
+      ▼
+  ar.read_csv()        ← Fast C++ parsing, low memory
+      │
+      ▼
+  ar.clean()           ← Consistent preprocessing
+      │
+      ▼
+  pd.DataFrame         ← Your normal pandas workflow continues here
+      │
+      ▼
+  Analysis, modeling, visualization — business as usual
+```
+
+Once your data is clean and in a DataFrame, pandas takes over completely. arnio simply makes the path from raw file to clean DataFrame faster and more predictable.
+
+> **Philosophy:** arnio doesn't compete with the pandas ecosystem — it strengthens it. The goal is to reduce the friction between raw data and productive analysis.
+
+---
+
+## Roadmap
+
+arnio is actively in development. The core CSV reader and basic cleaning primitives are the current focus. Planned work includes:
+
+- [x] C++ CSV parser core
+- [x] Basic cleaning API (`drop_nulls`, `strip_whitespace`, `normalize_columns`)
+- [x] pandas DataFrame output
+- [ ] Streaming / chunked reads for very large files
+- [ ] Type inference and automatic dtype casting
+- [ ] Encoding detection and normalization
+- [ ] Schema validation and column contracts
+- [ ] Parallel parsing across CPU cores
+- [ ] CLI tool (`arnio clean data.csv --output clean.csv`)
+- [ ] Async-friendly API for use in async pipelines
+
+Feedback on priorities is welcome — open a [GitHub Discussion](https://github.com/yourusername/arnio/discussions) to share what matters most to you.
+
+---
+
+## Contributing
+
+Contributions are welcome and genuinely appreciated. arnio is early-stage, which means there's real space to shape how it grows.
+
+**To get started:**
+
+```bash
+git clone https://github.com/yourusername/arnio.git
+cd arnio
+pip install -e ".[dev]"
+```
+
+Before submitting a pull request:
+
+- Run the test suite: `pytest tests/`
+- Follow the existing code style (enforced via `ruff`)
+- Keep PRs focused — one concern per pull request
+- Open an issue first for significant changes so the direction can be discussed
+
+There's a [CONTRIBUTING.md](CONTRIBUTING.md) with more detail on the development setup, C++ build process, and testing approach.
+
+---
+
+## License
+
+arnio is released under the [MIT License](LICENSE).
+
+---
+
+*Built to make Python data work feel faster and cleaner — one CSV at a time.*

arnio-0.1.0/README.md

@@ -0,0 +1,175 @@
+# arnio
+
+**Fast CSV processing and data cleaning for Python — powered by C++.**
+
+---
+
+arnio is a lightweight, C++-backed Python library designed to make CSV ingestion and data cleaning faster, simpler, and more memory-efficient. It sits comfortably alongside your existing pandas workflows, handling the heavy lifting before your data ever hits a DataFrame.
+
+If you've ever waited too long for a large CSV to load, or spent more time wrangling messy columns than actually analyzing data — arnio is built for you.
+
+```python
+import arnio as ar
+
+df = ar.read_csv("sales_data.csv")
+clean = ar.clean(df, drop_nulls=True, strip_whitespace=True)
+```
+
+---
+
+## Why arnio?
+
+Python's data ecosystem is excellent — but reading and cleaning raw CSV files at scale has always been a rough edge. `pandas.read_csv` is versatile and reliable, but it isn't optimized for raw speed or low memory pressure. Preprocessing logic ends up scattered across notebooks, inconsistent between projects, and slow on large files.
+
+arnio addresses this directly:
+
+- **Reads large CSVs faster** using a C++ parsing core with minimal Python overhead
+- **Provides a clean, composable cleaning API** so preprocessing logic is explicit, readable, and repeatable
+- **Works with pandas** — arnio outputs standard DataFrames; it's a faster on-ramp, not a replacement
+- **Keeps memory usage low** by parsing efficiently before data is materialized in Python
+
+---
+
+## Key Features
+
+| Feature | Description |
+|---|---|
+| ⚡ C++ CSV parser | Reads large files with significantly lower overhead than pure-Python parsers |
+| 🧹 Cleaning primitives | Drop nulls, strip whitespace, fix dtypes, normalize column names, and more |
+| 🐼 pandas-compatible output | Returns standard `pd.DataFrame` objects — drop arnio into any existing workflow |
+| 🧠 Memory-conscious | Designed to avoid unnecessary copies during ingestion and cleaning |
+| 🔗 Composable API | Chain cleaning operations in a clear, readable style |
+| 📦 Simple import | `import arnio as ar` — that's it |
+
+---
+
+## Installation
+
+```bash
+pip install arnio
+```
+
+> **Note:** arnio requires Python 3.9+ and a platform with a compatible C++ build (wheels are provided for Linux, macOS, and Windows on PyPI). For source builds, a C++17-compatible compiler is required.
+
+---
+
+## Quick Start
+
+### Reading a CSV
+
+```python
+import arnio as ar
+
+# Fast CSV ingestion — returns a pandas DataFrame
+df = ar.read_csv("data/transactions.csv")
+```
+
+### Cleaning Data
+
+```python
+import arnio as ar
+
+df = ar.read_csv("data/customers.csv")
+
+clean = ar.clean(
+    df,
+    drop_nulls=True,          # Remove rows with missing values
+    strip_whitespace=True,    # Trim leading/trailing whitespace in string columns
+    normalize_columns=True,   # Lowercase, underscore-separated column names
+)
+```
+
+### Chaining Operations
+
+```python
+import arnio as ar
+
+result = (
+    ar.read_csv("data/orders.csv")
+      .pipe(ar.drop_nulls)
+      .pipe(ar.normalize_columns)
+      .pipe(ar.strip_whitespace)
+)
+```
+
+arnio operations return standard DataFrames, so you can pass results directly into any pandas, scikit-learn, or plotting workflow without modification.
+
+---
+
+## arnio + pandas: Better Together
+
+arnio is not a pandas replacement. It is the step that happens *before* pandas — and occasionally alongside it.
+
+Think of it this way:
+
+```
+Raw CSV on disk
+      │
+      ▼
+  ar.read_csv()        ← Fast C++ parsing, low memory
+      │
+      ▼
+  ar.clean()           ← Consistent preprocessing
+      │
+      ▼
+  pd.DataFrame         ← Your normal pandas workflow continues here
+      │
+      ▼
+  Analysis, modeling, visualization — business as usual
+```
+
+Once your data is clean and in a DataFrame, pandas takes over completely. arnio simply makes the path from raw file to clean DataFrame faster and more predictable.
+
+> **Philosophy:** arnio doesn't compete with the pandas ecosystem — it strengthens it. The goal is to reduce the friction between raw data and productive analysis.
+
+---
+
+## Roadmap
+
+arnio is actively in development. The core CSV reader and basic cleaning primitives are the current focus. Planned work includes:
+
+- [x] C++ CSV parser core
+- [x] Basic cleaning API (`drop_nulls`, `strip_whitespace`, `normalize_columns`)
+- [x] pandas DataFrame output
+- [ ] Streaming / chunked reads for very large files
+- [ ] Type inference and automatic dtype casting
+- [ ] Encoding detection and normalization
+- [ ] Schema validation and column contracts
+- [ ] Parallel parsing across CPU cores
+- [ ] CLI tool (`arnio clean data.csv --output clean.csv`)
+- [ ] Async-friendly API for use in async pipelines
+
+Feedback on priorities is welcome — open a [GitHub Discussion](https://github.com/yourusername/arnio/discussions) to share what matters most to you.
+
+---
+
+## Contributing
+
+Contributions are welcome and genuinely appreciated. arnio is early-stage, which means there's real space to shape how it grows.
+
+**To get started:**
+
+```bash
+git clone https://github.com/yourusername/arnio.git
+cd arnio
+pip install -e ".[dev]"
+```
+
+Before submitting a pull request:
+
+- Run the test suite: `pytest tests/`
+- Follow the existing code style (enforced via `ruff`)
+- Keep PRs focused — one concern per pull request
+- Open an issue first for significant changes so the direction can be discussed
+
+There's a [CONTRIBUTING.md](CONTRIBUTING.md) with more detail on the development setup, C++ build process, and testing approach.
+
+---
+
+## License
+
+arnio is released under the [MIT License](LICENSE).
+
+---
+
+*Built to make Python data work feel faster and cleaner — one CSV at a time.*

arnio-0.1.0/arnio/__init__.py

@@ -0,0 +1,42 @@
+"""
+arnio — Fast CSV processing and data cleaning companion for pandas.
+
+import arnio as ar
+"""
+
+__version__ = "0.1.0"
+
+from .frame import ArFrame
+from .io import read_csv, scan_csv
+from .cleaning import (
+    drop_nulls,
+    fill_nulls,
+    drop_duplicates,
+    strip_whitespace,
+    normalize_case,
+    rename_columns,
+    cast_types,
+)
+from .convert import to_pandas, from_pandas
+from .pipeline import pipeline
+
+__all__ = [
+    # Core class
+    "ArFrame",
+    # I/O
+    "read_csv",
+    "scan_csv",
+    # Cleaning
+    "drop_nulls",
+    "fill_nulls",
+    "drop_duplicates",
+    "strip_whitespace",
+    "normalize_case",
+    "rename_columns",
+    "cast_types",
+    # Conversion
+    "to_pandas",
+    "from_pandas",
+    # Pipeline
+    "pipeline",
+]

arnio-0.1.0/arnio/_core.py

@@ -0,0 +1,25 @@
+"""
+arnio._core
+Internal module that imports the C++ extension.
+"""
+
+try:
+    from ._arnio_cpp import (  # type: ignore[import-not-found]
+        Frame as _Frame,
+        Column as _Column,
+        CsvConfig as _CsvConfig,
+        CsvReader as _CsvReader,
+        DType as _DType,
+        drop_nulls as _drop_nulls,
+        fill_nulls as _fill_nulls,
+        drop_duplicates as _drop_duplicates,
+        strip_whitespace as _strip_whitespace,
+        normalize_case as _normalize_case,
+        rename_columns as _rename_columns,
+        cast_types as _cast_types,
+    )
+except ImportError as e:
+    raise ImportError(
+        "arnio C++ extension (_arnio_cpp) not found. "
+        "Please install arnio with: pip install ."
+    ) from e