chonkie-core 0.9.1__cp314-cp314-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

chonkie_core/__init__.py

@@ -0,0 +1,73 @@
+"""chonkie-core - The fastest semantic text chunking library."""
+
+from chonkie_core._chunk import (
+    Chunker,
+    MergeResult,
+    PatternSplitter,
+    chunk_offsets,
+    find_merge_indices,
+    merge_splits,
+    split_offsets,
+    split_pattern_offsets,
+    # Savitzky-Golay filter functions
+    savgol_filter,
+    find_local_minima_interpolated,
+    windowed_cross_similarity,
+    filter_split_indices,
+    DEFAULT_TARGET_SIZE,
+    DEFAULT_DELIMITERS,
+)
+
+__all__ = [
+    "chunk",
+    "Chunker",
+    "MergeResult",
+    "PatternSplitter",
+    "chunk_offsets",
+    "find_merge_indices",
+    "merge_splits",
+    "split_offsets",
+    "split_pattern_offsets",
+    # Savitzky-Golay filter functions
+    "savgol_filter",
+    "find_local_minima_interpolated",
+    "windowed_cross_similarity",
+    "filter_split_indices",
+    "DEFAULT_TARGET_SIZE",
+    "DEFAULT_DELIMITERS",
+]
+__version__ = "0.9.1"
+
+
+def chunk(text, *, size=DEFAULT_TARGET_SIZE, delimiters=None):
+    """
+    Split text into chunks at delimiter boundaries.
+    Returns an iterator of zero-copy memoryview slices.
+
+    Args:
+        text: bytes or str to chunk
+        size: Target chunk size in bytes (default: 4096)
+        delimiters: bytes or str of delimiter characters (default: "\\n.?")
+
+    Yields:
+        memoryview slices of the original text
+
+    Example:
+        >>> text = b"Hello. World. Test."
+        >>> for chunk in chunk(text, size=10, delimiters=b"."):
+        ...     print(bytes(chunk))
+        b'Hello.'
+        b' World.'
+        b' Test.'
+    """
+    # Convert str to bytes if needed
+    if isinstance(text, str):
+        text = text.encode("utf-8")
+
+    # Get offsets from Rust (single FFI call)
+    offsets = chunk_offsets(text, size, delimiters)
+
+    # Return memoryview slices (zero-copy)
+    mv = memoryview(text)
+    for start, end in offsets:
+        yield mv[start:end]

chonkie_core-0.9.1.dist-info/METADATA

@@ -0,0 +1,115 @@
+Metadata-Version: 2.4
+Name: chonkie-core
+Version: 0.9.1
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Rust
+Classifier: Programming Language :: Python :: Implementation :: CPython
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+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: Topic :: Text Processing
+Requires-Dist: numpy>=1.20
+Summary: The fastest semantic text chunking library
+Keywords: chunking,text,simd,nlp,tokenization,rag,chonkie
+Author: Bhavnick Minhas
+License: MIT OR Apache-2.0
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown; charset=UTF-8; variant=GFM
+Project-URL: Homepage, https://github.com/chonkie-inc/chunk
+Project-URL: Repository, https://github.com/chonkie-inc/chunk
+
+<p align="center">
+  <img src="../../assets/memchunk_wide.png" alt="chonkie-core" width="500">
+</p>
+
+<h1 align="center">chonkie-core</h1>
+
+<p align="center">
+  <em>the fastest text chunking library — up to 1 TB/s throughput</em>
+</p>
+
+<p align="center">
+  <a href="https://crates.io/crates/chunk"><img src="https://img.shields.io/crates/v/chunk.svg?color=e74c3c" alt="crates.io"></a>
+  <a href="https://pypi.org/project/chonkie-core"><img src="https://img.shields.io/pypi/v/chonkie-core.svg?color=e67e22" alt="PyPI"></a>
+  <a href="https://www.npmjs.com/package/@chonkiejs/chunk"><img src="https://img.shields.io/npm/v/@chonkiejs/chunk.svg?color=2ecc71" alt="npm"></a>
+  <a href="https://github.com/chonkie-inc/chunk"><img src="https://img.shields.io/badge/github-chunk-3498db" alt="GitHub"></a>
+  <a href="LICENSE-MIT"><img src="https://img.shields.io/badge/license-MIT%2FApache--2.0-9b59b6.svg" alt="License"></a>
+</p>
+
+---
+
+you know how every chunking library claims to be fast? yeah, we actually meant it.
+
+**chonkie-core** splits text at semantic boundaries (periods, newlines, the usual suspects) and does it stupid fast. we're talking "chunk the entire english wikipedia in 120ms" fast.
+
+want to know how? [read the blog post](https://minha.sh/posts/so,-you-want-to-chunk-really-fast) where we nerd out about SIMD instructions and lookup tables.
+
+## 📦 installation
+
+```bash
+pip install chonkie-core
+```
+
+looking for [rust](https://github.com/chonkie-inc/chunk) or [javascript](https://github.com/chonkie-inc/chunk/tree/main/packages/wasm)?
+
+## 🚀 usage
+
+```python
+from chonkie_core import Chunker
+
+text = "Hello world. How are you? I'm fine.\nThanks for asking."
+
+# with defaults (4KB chunks, split at \n . ?)
+for chunk in Chunker(text):
+    print(bytes(chunk))
+
+# with custom size
+for chunk in Chunker(text, size=1024):
+    print(bytes(chunk))
+
+# with custom delimiters
+for chunk in Chunker(text, delimiters=".?!\n"):
+    print(bytes(chunk))
+
+# with multi-byte pattern (e.g., metaspace ▁ for SentencePiece tokenizers)
+for chunk in Chunker(text, pattern="▁", prefix=True):
+    print(bytes(chunk))
+
+# with consecutive pattern handling (split at START of runs, not middle)
+for chunk in Chunker("word   next", pattern=" ", consecutive=True):
+    print(bytes(chunk))
+
+# with forward fallback (search forward if no pattern in backward window)
+for chunk in Chunker(text, pattern=" ", forward_fallback=True):
+    print(bytes(chunk))
+
+# collect all chunks
+chunks = list(Chunker(text))
+```
+
+chunks are returned as `memoryview` objects (zero-copy slices of the original text).
+
+## 📝 citation
+
+if you use chonkie-core in your research, please cite it as follows:
+
+```bibtex
+@software{chunk2025,
+  author = {Minhas, Bhavnick},
+  title = {chunk: The fastest text chunking library},
+  year = {2025},
+  publisher = {GitHub},
+  howpublished = {\url{https://github.com/chonkie-inc/chunk}},
+}
+```
+
+## 📄 license
+
+licensed under either of [Apache License, Version 2.0](LICENSE-APACHE) or [MIT license](LICENSE-MIT) at your option.
+

chonkie_core-0.9.1.dist-info/RECORD

@@ -0,0 +1,6 @@
+chonkie_core/__init__.py,sha256=DNpYt5zYmK3a4VRAZmVp-F2Utgi3TYom7Nic63Veuxs,1865
+chonkie_core/_chunk.cpython-314-x86_64-linux-gnu.so,sha256=VtKuZziX_UhAfjAIm4h4VUXjiW8OMaoWqmrdkAYrENM,949992
+chonkie_core/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+chonkie_core-0.9.1.dist-info/METADATA,sha256=vGIgFz9F-xj_WwtJDfeT37t_sooUJJNDkWM4g2RPIRI,4146
+chonkie_core-0.9.1.dist-info/WHEEL,sha256=1GO8NDKTfrlRkgVXFQ5KJDUbdgIfejZHnbKJV8XeeSw,147
+chonkie_core-0.9.1.dist-info/RECORD,,

chonkie_core-0.9.1.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: maturin (1.11.5)
+Root-Is-Purelib: false
+Tag: cp314-cp314-manylinux_2_17_x86_64
+Tag: cp314-cp314-manylinux2014_x86_64