glitchlings 0.2.5__cp312-cp312-win_amd64.whl → 0.9.3__cp312-cp312-win_amd64.whl

glitchlings-0.9.3.dist-info/METADATA

@@ -0,0 +1,334 @@
+Metadata-Version: 2.4
+Name: glitchlings
+Version: 0.9.3
+Summary: Monsters for your language games.
+Author: osoleve
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/osoleve/glitchlings
+Project-URL: Repository, https://github.com/osoleve/glitchlings.git
+Project-URL: Issues, https://github.com/osoleve/glitchlings/issues
+Project-URL: Changelog, https://github.com/osoleve/glitchlings/releases
+Keywords: nlp,adversarial augmentation,text augmentation,data augmentation,domain randomization
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python
+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: Programming Language :: Rust
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Software Development :: Testing
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: tomli>=2.0.1; python_version < "3.11"
+Requires-Dist: importlib-resources>=5.0.0; python_version < "3.11"
+Requires-Dist: packaging>=23.0
+Requires-Dist: pyyaml>=6.0.0
+Provides-Extra: all
+Requires-Dist: hypothesis>=6.140.0; extra == "all"
+Requires-Dist: interrogate>=1.5.0; extra == "all"
+Requires-Dist: jellyfish==1.2.0; extra == "all"
+Requires-Dist: isort>=5.13.0; extra == "all"
+Requires-Dist: mkdocs>=1.6.0; extra == "all"
+Requires-Dist: mkdocs-material>=9.5.0; extra == "all"
+Requires-Dist: mkdocstrings[python]>=0.24.0; extra == "all"
+Requires-Dist: mkdocstrings-python>=1.10.0; extra == "all"
+Requires-Dist: mypy>=1.8.0; extra == "all"
+Requires-Dist: numpy<3.0,>=1.24; extra == "all"
+Requires-Dist: pre-commit>=3.8.0; extra == "all"
+Requires-Dist: py-gutenberg==1.0.0; extra == "all"
+Requires-Dist: pytest>=8.0.0; extra == "all"
+Requires-Dist: pytest-cov>=4.1.0; extra == "all"
+Requires-Dist: ruff>=0.6.0; extra == "all"
+Requires-Dist: types-PyYAML>=6.0.0; extra == "all"
+Requires-Dist: verifiers>=0.1.8; extra == "all"
+Requires-Dist: tiktoken>=0.3.0; extra == "all"
+Requires-Dist: tokenizers>=0.13.0; extra == "all"
+Provides-Extra: attack
+Requires-Dist: tiktoken>=0.3.0; extra == "attack"
+Requires-Dist: tokenizers>=0.13.0; extra == "attack"
+Provides-Extra: gutenberg
+Requires-Dist: py-gutenberg==1.0.0; extra == "gutenberg"
+Provides-Extra: hf
+Requires-Dist: datasets>=4.0.0; extra == "hf"
+Provides-Extra: lightning
+Requires-Dist: pytorch_lightning>=2.0.0; extra == "lightning"
+Provides-Extra: prime
+Requires-Dist: verifiers>=0.1.8; extra == "prime"
+Requires-Dist: jellyfish==1.2.0; extra == "prime"
+Provides-Extra: torch
+Requires-Dist: torch>=2.0.0; extra == "torch"
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.1.0; extra == "dev"
+Requires-Dist: hypothesis>=6.140.0; extra == "dev"
+Requires-Dist: numpy<3.0,>=1.24; extra == "dev"
+Requires-Dist: mkdocs>=1.6.0; extra == "dev"
+Requires-Dist: mkdocstrings[python]>=0.24.0; extra == "dev"
+Requires-Dist: mkdocs-material>=9.5.0; extra == "dev"
+Requires-Dist: mkdocstrings-python>=1.10.0; extra == "dev"
+Requires-Dist: interrogate>=1.5.0; extra == "dev"
+Requires-Dist: isort>=5.13.0; extra == "dev"
+Requires-Dist: ruff>=0.6.0; extra == "dev"
+Requires-Dist: mypy>=1.8.0; extra == "dev"
+Requires-Dist: pre-commit>=3.8.0; extra == "dev"
+Requires-Dist: types-PyYAML>=6.0.0; extra == "dev"
+Dynamic: license-file
+
+#
+
+```plaintext
+     .─') _                                       .─') _                  
+    (  OO) )                                     ( OO ) )            
+  ░██████  ░██ ░██   ░██               ░██        ░██ ░██                                 
+ ░██   ░██ ░██       ░██                ░██        ░██                                     
+░██        ░██ ░██░████████  ░███████   ░████████  ░██ ░██░████████   ░████████ ░███████  
+░██  █████ ░██ ░██   ░██    ░██('─.░██ ░██    ░██ ░██ ░██░██    ░██ ░██.─')░██ ░██        
+░██     ██ ░██ ░██   ░██    ░██( OO ) ╱░██    ░██ ░██ ░██░██    ░██ ░██(OO)░██ ░███████  
+  ░██  ░███ ░██ ░██   ░██    ░██    ░██ ░██    ░██ ░██ ░██░██    ░██ ░██ o ░███      ░██ 
+  ░█████░█ ░██ ░██   ░████   ░███████  ░██    ░██ ░██ ░██░██    ░██  ░█████░██ ░███████  
+                                                                          ░██            
+                                                                  ░███████             
+
+                        Every language game breeds monsters.
+```
+
+![Python Versions](https://img.shields.io/pypi/pyversions/glitchlings.svg)
+[![PyPI version](https://img.shields.io/pypi/v/glitchlings.svg)](https://pypi.org/project/glitchlings/)
+![Wheel](https://img.shields.io/pypi/wheel/glitchlings.svg)
+![Linting and Typing](https://github.com/osoleve/glitchlings/actions/workflows/ci.yml/badge.svg)  
+![Entropy Budget](https://img.shields.io/badge/entropy-lifegiving-magenta.svg)
+![Chaos](https://img.shields.io/badge/chaos-friend--shaped-chartreuse.svg)
+![Charm](https://img.shields.io/badge/jouissance-indefatigable-cyan.svg)  
+![Lore Compliance](https://img.shields.io/badge/ISO--474--▓▓-Z--Compliant-blue.svg)
+
+`Glitchlings` are **utilities for corrupting the text inputs to your language models in deterministic, _linguistically principled_** ways.  
+Each embodies a different way that documents can be compromised in the wild.
+
+If reinforcement learning environments are games, then `Glitchling`s are enemies to breathe new life into old challenges.
+
+They do this by breaking surface patterns in the input while keeping the target output intact.
+
+Some `Glitchling`s are petty nuisances. Some `Glitchling`s are eldritch horrors.  
+Together, they create truly nightmarish scenarios for your language models.
+
+After all, what good is general intelligence if it can't handle a little chaos?
+
+-_The Curator_
+
+## Motivation
+
+If your model performs well on a particular task, but not when `Glitchling`s are present, it's a sign that it hasn't actually generalized to the problem.
+
+Conversely, training a model to perform well in the presence of the types of perturbations introduced by `Glitchling`s should help it generalize better.
+
+## Quickstart
+
+```python
+pip install -U glitchlings
+```
+
+The fastest way to get started is to ask my assistant, `Auggie`, to prepare a custom mix of glitchlings for you:
+
+```python
+from glitchlings import Auggie, SAMPLE_TEXT
+
+auggie = (
+    Auggie(seed=404)
+    .typo(rate=0.015)
+    .confusable(rate=0.01)
+    .homophone(rate=0.02)
+)
+
+print(auggie(SAMPLE_TEXT))
+```
+
+> One morning, when Gregor Samsa woke from troubld dreams, he found himself transformed in his bed into a horible vermin. He layed on his armour-like back, and if he lifted his head a little he could see his brown belly, slightly domed and divided by arches into stiff sections. The bedding was hardly able to cover it and seemed ready to slide off any moment. His many legs, pitifully thin compared with the size of the rest of him, waved about helplessly as he looked.
+
+**You're more than welcome to summon them directly, if you're feeling brave:**
+
+```python
+from glitchlings import Gaggle, SAMPLE_TEXT, Typogre, Mim1c, Ekkokin
+
+gaggle = Gaggle(
+    [
+        Typogre(rate=0.015),
+        Mim1c(rate=0.01),
+        Ekkokin(rate=0.02),
+    ],
+    seed=404
+)
+```
+
+Consult the [Glitchlings Usage Guide](docs/index.md)
+for end-to-end instructions spanning the Python API, CLI, and third-party integrations.
+
+## Your First Battle
+
+Summon your chosen `Glitchling` (_or a few, if ya nasty_) and call it on your text or slot it into `Dataset.map(...)`, supplying a seed if desired.
+Glitchlings are standard Python classes:
+
+```python
+from glitchlings import Gaggle, Typogre, Mim1c
+
+custom_typogre = Typogre(rate=0.1)
+selective_mimic = Mim1c(rate=0.05, classes=["LATIN", "GREEK"])
+
+gaggle = Gaggle([custom_typogre, selective_mimic], seed=99)
+corrupted = gaggle("We Await Silent Tristero's Empire.")
+print(corrupted)
+```
+
+Calling a `Glitchling` on a `str` transparently calls `.corrupt(str, ...) -> str`.
+This means that as long as your glitchlings get along logically, they play nicely with one another.
+
+When summoned as or gathered into a `Gaggle`, the `Glitchling`s will automatically order themselves into attack waves, based on the scope of the change they make:
+
+1. Document
+2. Paragraph
+3. Sentence
+4. Word
+5. Character
+
+They're horrible little gremlins, but they're not _unreasonable_.
+
+## Command-Line Interface (CLI)
+
+Keyboard warriors can challenge them directly via the `glitchlings` command (see the generated CLI reference in `docs/cli.md` for the full contract):
+
+```bash
+# Discover which glitchlings are currently on the loose.
+glitchlings --list
+ 
+# Review the full CLI contract.
+glitchlings --help
+ 
+# Run Typogre against the contents of a file and inspect the diff.
+glitchlings -g typogre --file documents/report.txt --diff
+
+# Configure glitchlings inline by passing keyword arguments.
+glitchlings -g "Typogre(rate=0.05)" "Ghouls just wanna have fun"
+
+# Pipe text straight into the CLI for an on-the-fly corruption.
+echo "Beware LLM-written flavor-text" | glitchlings -g mim1c
+
+# Emit a structured Attack report with tokens, token IDs, and metrics.
+glitchlings --report json --sample
+```
+
+## Configuration Files
+
+Configurations live in plain YAML files so you can version-control experiments without touching code:
+
+```bash
+# Load a roster from a YAML attack configuration.
+glitchlings --config experiments/chaos.yaml "Let slips the glitchlings of war"
+```
+
+```yaml
+# experiments/chaos.yaml
+seed: 31337
+glitchlings:
+  - name: Typogre
+    rate: 0.04
+  - "Rushmore(rate=0.12, unweighted=True)"
+  - name: Zeedub
+    parameters:
+      rate: 0.02
+      characters: ["\u200b", "\u2060"]
+```
+
+## Attack on Token
+
+Looking to compare before/after corruption with metrics and stable seeds? Reach for the [`Attack` helper](docs/attack.md), which bundles tokenization, metrics, and transcript batching into a single utility. It accepts plain `list[str]` batches, renders quick `summary()` reports, and can compare multiple tokenizers via `Attack.compare(...)` when you need a metrics matrix.
+
+## Development
+
+Follow the [development setup guide](docs/development.md) for editable installs, automated tests, and tips on enabling the Rust pipeline while you hack on new glitchlings.
+
+## Starter 'lings
+
+For maintainability reasons, all `Glitchling` have consented to be given nicknames once they're in your care. See the [Monster Manual](MONSTER_MANUAL.md) for a complete bestiary.
+
+### Typogre
+
+_What a nice word, would be a shame if something happened to it._
+
+> _**Fatfinger.**_ Typogre introduces character-level errors (duplicating, dropping, adding, or swapping) based on the layout of a keyboard (QWERTY by default, with Dvorak and Colemak variants built-in).
+
+### Mim1c
+
+_Wait, was that...?_
+
+> _**Confusion.**_ Mim1c replaces non-space characters with Unicode Confusables, characters that are distinct but would not usually confuse a human reader.
+
+### Hokey
+
+_She's soooooo coooool!_
+
+> _**Passionista.**_ Hokey gets a little excited and streeeeetches words for emphasis.
+>
+> _Apocryphal Glitchling contributed by Chloé Nunes_
+
+### Scannequin
+
+_How can a computer need reading glasses?_
+
+> _**OCArtifacts.**_ Scannequin mimics optical character recognition errors by swapping visually similar character sequences (like rn↔m, cl↔d, O↔0, l/I/1).
+
+### Zeedub
+
+_Watch your step around here._
+
+> _**Invisible Ink.**_ Zeedub slips zero-width codepoints between non-space character pairs, forcing models to reason about text whose visible form masks hidden glyphs.
+
+### Ekkokin
+
+_Did you hear what I heard?_
+
+> _**Echo Chamber.**_ Ekkokin swaps words with curated homophones so the text still sounds right while the spelling drifts. Groups are normalised to prevent duplicates and casing is preserved when substitutions fire.
+
+### Jargoyle
+
+_Uh oh. The worst person you know just bought a thesaurus._
+
+> _**Sesquipedalianism.**_ Jargoyle insufferably replaces words with synonyms at random, without regard for connotational or denotational differences.
+
+### Rushmore
+
+_I accidentally an entire word._
+
+> _**Tactical Scrambler.**_ Rushmore randomly drops, duplicates, or swaps words in the text to simulate hasty writing, editing mistakes, or transmission errors.
+
+### Redactyl
+
+_Oops, that was my black highlighter._
+
+> _**FOIA Reply.**_ Redactyl obscures random words in your document like an NSA analyst with a bad sense of humor.
+
+## Apocrypha
+
+Cave paintings and oral tradition contain many depictions of strange, otherworldly `Glitchling`s.  
+These _Apocryphal `Glitchling`_ are said to possess unique abilities or behaviors.  
+If you encounter one of these elusive beings, please document your findings and share them with _The Curator_.
+
+### Ensuring Reproducible Corruption
+
+Every `Glitchling` should own its own independent `random.Random` instance. That means:
+
+- No `random.seed(...)` calls touch Python's global RNG.
+- Supplying a `seed` when you construct a `Glitchling` (or when you `summon(...)`) makes its behavior reproducible.
+- Re-running a `Gaggle` with the same master seed and the same input text (_and same external data!_) yields identical corruption output.
+- Corruption functions are written to accept an `rng` parameter internally so that all randomness is centralized and testable.
+
+#### At Wits' End?
+
+If you're trying to add a new glitchling and can't seem to make it deterministic, here are some places to look for determinism-breaking code:
+
+1. Search for any direct calls to `random.choice`, `random.shuffle`, or `set(...)` ordering without going through the provided `rng`.
+2. Ensure you sort collections before shuffling or sampling.
+3. Make sure indices are chosen from a stable reference (e.g., original text) when applying length‑changing edits.
+4. Make sure there are enough sort keys to maintain stability.

glitchlings-0.9.3.dist-info/RECORD

@@ -0,0 +1,80 @@
+glitchlings/__init__.py,sha256=YuzCOa41eGE9HfQ4SAGup5Kpp9P4B7x6LBhDdfG-t1s,1123
+glitchlings/__main__.py,sha256=nB7btO_T4wBFOcyawfWpjEindVrUfTqqV5hdeeS1HT8,128
+glitchlings/_zoo_rust.cp312-win_amd64.pyd,sha256=_TxMtxPzPDKDDJRXEswD1OPiy5lsZAFS7yVMGVB41lE,3484672
+glitchlings/auggie.py,sha256=ShLFd-Ic6D_yScXa7XLNcpyFV2uJcrYInQe22JctuvU,9051
+glitchlings/config.toml,sha256=051Rri2m5ebSekQ4Z8kGWUaXsuH7b7QcVl8zFMpQUak,105
+glitchlings/constants.py,sha256=OeijOqSpbT03spKqoAYSJ-B9pfQ6-h5s-K8s0OI-Wzo,1674
+glitchlings/main.py,sha256=1Z_2Nja1KJyhxrWIDLS1YDOAmaIRzXKSDRzOu2Tsju0,9301
+glitchlings/runtime_config.py,sha256=Lt6e2p-Ykmt0jkFZlTJl31T_7Mtx9AmkQr1QA7UVBE4,450
+glitchlings/_zoo_rust/__init__.py,sha256=bApb6gCn5zGYGluVn7LIaB96BTfNnIhhw_TRXF6QrxE,285
+glitchlings/assets/__init__.py,sha256=DE2nT3P8guxbeqoi807hwJDaTQGIhAbCADVfAg4iLJE,5982
+glitchlings/assets/apostrofae_pairs.json,sha256=lPLFLndzn_f7_5wZizxsLMnwBY4O63zsCvDjyJ56MLA,553
+glitchlings/assets/ekkokin_homophones.json,sha256=SWp7jFWehrshTwC76W8MA248C87yP1xQrp8iKTxM1vE,19258
+glitchlings/assets/hokey_assets.json,sha256=1GaSEzXwtT1nvf0B9mFyLzHOcqzKbPreibsC6iBWAHA,3083
+glitchlings/assets/mim1c_homoglyphs.json.gz.b64,sha256=SIKCmFw7Tm5NkoNf-CqntytqqQJfYpRmWXdlDt92s6U,82968
+glitchlings/assets/ocr_confusions.tsv,sha256=S-IJEYCIXYKT1Uu7Id8Lnvg5pw528yNigTtWUdnMv9k,213
+glitchlings/assets/pipeline_assets.json,sha256=CHj25Z1l6BTe6Y-c1hGMx_8fXgAaiJE5OKY0Q0ZGna0,532
+glitchlings/assets/lexemes/academic.json,sha256=qgwocuJCuyYZHXSp4fqch4kH4n94Q-EvAefwvVzxVH0,16879
+glitchlings/assets/lexemes/colors.json,sha256=rdanKP6cZwXY56cur3yKN_D15xHrtZwE7JwNckdRUpE,17986
+glitchlings/assets/lexemes/corporate.json,sha256=1t7LEzZoCdsvMCihtR7R1ACLherW1B4i7S_C5LQewvQ,11880
+glitchlings/assets/lexemes/cyberpunk.json,sha256=ZLa-sV3Bpl2k2NW1WJauA21EbEGBqNZOghLN86bFS8A,1360
+glitchlings/assets/lexemes/lovecraftian.json,sha256=XPONzHTD3ZoIowwyGvFp8oqZ9VJ5corQI_ls5bE0CD8,1599
+glitchlings/assets/lexemes/synonyms.json,sha256=JQPySTgfcUNEk9ZU7W4RCNZPbQvQ0aafEHdDST2-pz4,47878
+glitchlings/attack/__init__.py,sha256=tst8ueSJe6NYYj9sxCa0u_8epLj-vqMwD-RmgmHt4a4,1454
+glitchlings/attack/compose.py,sha256=lahyb2f125WOVrggPOUcb6N1xmbjwrvKFOEIdShzTes,9984
+glitchlings/attack/core.py,sha256=CB2tt4225Tk7QctmuW6bCQ52rdcA-5deTquCa8f7OKE,18461
+glitchlings/attack/encode.py,sha256=yUOtV1P9iAlEjDycReOaKAkBBtAa4aSqXzN2xUypAcY,3352
+glitchlings/attack/metrics.py,sha256=XYN8l9zFQZ6yhgfaI5BleR6aXBNKRhiz6ARCDsv5vrg,3088
+glitchlings/attack/metrics_dispatch.py,sha256=U4cvRPD3nzteBeTqX1WCAFQSGpCjkl3_PzcP0ZQRCmQ,2137
+glitchlings/attack/tokenization.py,sha256=i3iCdDsW4Sg-jPcvxFZH4eO27aitQ-U5apBVZAk_aOU,5437
+glitchlings/compat/__init__.py,sha256=vHd79zAxelHzcDyzY9dEBzKoGJtwGi7Lu_RdcL1BL78,317
+glitchlings/compat/loaders.py,sha256=ONJaVdKq6uLjIg2i9EQpP4cZeEbE4rTjoi8Qa7fisGI,12119
+glitchlings/compat/types.py,sha256=DVFS0s0D_K-iVaSR5LJHTVpMm3TzG8CXMZvZrsc3mqI,975
+glitchlings/conf/__init__.py,sha256=_eZwO3y53_UahbgW_LMUTFXrkTiH2daK0cpvIVJiNTY,1052
+glitchlings/conf/loaders.py,sha256=Xh3LXDBpP9NT4mc4paQeQcZFjDN-AiCFVaUSK88CdAE,10804
+glitchlings/conf/schema.py,sha256=kCeGT_XCNLC0yS0Qd2MbygPOayos2gHiMcxrVjG2oNg,5358
+glitchlings/conf/types.py,sha256=w52gt46VTF0Q04TEygMkHvHj-MyjZeJU_8PuqtDTTwM,1905
+glitchlings/dev/__init__.py,sha256=z-7rcrkV0wexkZMVH7jZRML5juQkFv3EFOTmVgW8EX0,94
+glitchlings/dev/docs.py,sha256=2cYLDVmBsigdNb4l897vFz-61J2qWVBw2UafOno8c9o,1128
+glitchlings/dlc/__init__.py,sha256=F7Ba_OXz4tv_hjKMyJEjU8j1weDzl4GvsCGwnBlmySk,799
+glitchlings/dlc/_shared.py,sha256=kQhIFQSAaWRcfqcS2cJCN3mAlL9nn4p1iKXEqfhUnnw,10557
+glitchlings/dlc/gutenberg.py,sha256=WL37NpsOV8TQchHXa4sksSCs1GA0gsRGcFDM4F5IcJQ,13976
+glitchlings/dlc/huggingface.py,sha256=nMRkLVWyY9oLO_DUT_vjHWRUpLp4hLWchQKTi9D7mic,2275
+glitchlings/dlc/prime.py,sha256=BT7ta1P7NWyItNteU4XgEY-xswa0nIgRhqXbzfi13yg,7743
+glitchlings/dlc/pytorch.py,sha256=FMAgR4qVg432bOalvkGtpKh_uZYbdMLgLh5o-eO0vGo,3533
+glitchlings/dlc/pytorch_lightning.py,sha256=2L1cqzIdYbABrLV7LqBmZHAuXj1ncn3RYJMQHKhh1oE,7303
+glitchlings/internal/__init__.py,sha256=76MgFj19zewI0iyxKcrDQph4Kjd1pE8r9inxi7dSW1I,518
+glitchlings/internal/rust.py,sha256=_DuSpPa_C91OYqSNnHWC4AqBFcIrDkIjWry1XVbuVMM,4938
+glitchlings/internal/rust_ffi.py,sha256=FkdWIIFI9OZ-nAYFwxcYIt-vYlFEwsrFRq_H0VMQ6VI,12278
+glitchlings/util/__init__.py,sha256=q20xcxERkKrfMBVqF4Q6mg2UgyFngfbFF5zqCTooO9s,1022
+glitchlings/util/adapters.py,sha256=HnwwQN6g3Mit4h6VrmRfBXN4Lrh5FqnTZSGnIUqOLe4,2489
+glitchlings/util/keyboards.py,sha256=bxbLi_qq2icjz45JedAAeZZslcqwtiIQgjT7YPokWj8,6729
+glitchlings/util/transcripts.py,sha256=kHKny4gdnc9zixLmNJ9zv90TmEhk3ql1koyBm2-65GQ,3495
+glitchlings/zoo/__init__.py,sha256=u29QxRVJGRjg3wMYwAlm9avlX_fm9nIsQn3XqfF2T6o,4936
+glitchlings/zoo/core.py,sha256=pqK9cnj0efpIW7pZwN9BwteIWMqeO6whk2IDEvyH-fQ,21143
+glitchlings/zoo/core_execution.py,sha256=quiTLyTEchPMPx7bQsk4tdYrDZ7aSiiAs5F7WWsOmmQ,3123
+glitchlings/zoo/core_planning.py,sha256=49FtUrfzMje05PKQKkM81y-jDt2_Qbs7dgJaDUV5KBo,14940
+glitchlings/zoo/corrupt_dispatch.py,sha256=-XIxIb9AEcI3KV79o12sfupny99oCXzdvnBr52UBCSc,9262
+glitchlings/zoo/ekkokin.py,sha256=K_Png2lML6THcYa3AoWagHziRNaEHEvQtnSsKzRoU1Q,3425
+glitchlings/zoo/hokey.py,sha256=xdIwcMiOIXl7PmonjPZo4PLKsD_p6priZwoOpsLl6-g,4401
+glitchlings/zoo/jargoyle.py,sha256=mVDCkRSv09wZ4KyRG7P9WjexVyVZo0NKGNXci8Tcxnk,7885
+glitchlings/zoo/mim1c.py,sha256=s0eQpCvxlMLm6WMpD9GzrHpBK2wD5neU1KNkw2SmRcY,4752
+glitchlings/zoo/redactyl.py,sha256=mc8QeRgdGDH35LZnrncl-Q27mBGv7Q6VL-Zf2H--gG8,3060
+glitchlings/zoo/rng.py,sha256=Mb3UnHM7t3SGidAs-N61KiTVj85azB89JsiXGPkapQ8,8130
+glitchlings/zoo/rushmore.py,sha256=lfBdSTqt-GEQPFCLzYGtXHVqX8N1nE8BVAYYHrUsrSc,13061
+glitchlings/zoo/scannequin.py,sha256=-RtpfqYk1fAVyK_wLkCGopq2p0VsbO2tUthMYINuzX0,1852
+glitchlings/zoo/transforms.py,sha256=kLIriPIumQjL5uAhRwrGe6gbgq3bXx6kpGE7BgA_eBE,11651
+glitchlings/zoo/typogre.py,sha256=bUtLmIHupZuJz2cGFJ0qwpb4yOWaC58l0kTjVo6RJws,4568
+glitchlings/zoo/validation.py,sha256=ehOxf2jzJx8SBQHtvw5QtlbcCDwTg7bLfJ0UCHQf_fk,14523
+glitchlings/zoo/zeedub.py,sha256=XueKsAtcgml6DBo4eDKAQAjrXmlO8rHa8KHTrTD_5Yk,2719
+glitchlings/zoo/assets/__init__.py,sha256=2x6eIdZliPnbt9w3eVjhNbXxZ-Aj0Vt369LI_pfmyho,566
+glitchlings/zoo/pedant/__init__.py,sha256=w1wBJtk4wBqd8-zVqPskiYsJ6NQ0kUvPKKIltunLbLI,2918
+glitchlings/zoo/pedant/core.py,sha256=WGDmNRdnemGtCkcirli_8ClFV8gvhTcaHS7_-R4hFOc,3089
+glitchlings/zoo/pedant/forms.py,sha256=aYKdjN9E77v7D2ARvn7ordZ0T4eCdtlu1Qiob1on6kE,1685
+glitchlings/zoo/pedant/stones.py,sha256=atw4l1AdWDuxtUXRN9-jiqWoZHQv70YVCTyMbegETKU,2364
+glitchlings-0.9.3.dist-info/licenses/LICENSE,sha256=EFEP1evBfHaxsMTBjxm0sZVRp2wct8QLvHE1saII5FI,11538
+glitchlings-0.9.3.dist-info/METADATA,sha256=YQKwglA3KrpAZKr94TPfWRVkuSDoMbexHNC35lOZZj4,15016
+glitchlings-0.9.3.dist-info/WHEEL,sha256=8UP9x9puWI0P1V_d7K2oMTBqfeLNm21CTzZ_Ptr0NXU,101
+glitchlings-0.9.3.dist-info/entry_points.txt,sha256=0pVGF4NIGjlDEt5Q0i0QUSUNigl5h9rhazn6DWEfyXg,107
+glitchlings-0.9.3.dist-info/top_level.txt,sha256=VHFNBrLjtDwPCYXbGKi6o17Eueedi81eNbR3hBOoST0,12
+glitchlings-0.9.3.dist-info/RECORD,,

{glitchlings-0.2.5.dist-info → glitchlings-0.9.3.dist-info}/entry_points.txt

@@ -1,2 +1,3 @@
 [console_scripts]
 glitchlings = glitchlings.main:main
+glitchlings-refresh-docs = glitchlings.dev.docs:main

glitchlings/zoo/_ocr_confusions.py

@@ -1,34 +0,0 @@
-from __future__ import annotations
-
-from importlib import resources
-
-_CONFUSION_TABLE: list[tuple[str, list[str]]] | None = None
-
-
-def load_confusion_table() -> list[tuple[str, list[str]]]:
-    """Load the OCR confusion table shared by Python and Rust implementations."""
-    global _CONFUSION_TABLE
-    if _CONFUSION_TABLE is not None:
-        return _CONFUSION_TABLE
-
-    data = resources.files(__package__) / "ocr_confusions.tsv"
-    text = data.read_text(encoding="utf-8")
-    indexed_entries: list[tuple[int, tuple[str, list[str]]]] = []
-    for line_number, line in enumerate(text.splitlines()):
-        stripped = line.strip()
-        if not stripped or stripped.startswith("#"):
-            continue
-        parts = stripped.split()
-        if len(parts) < 2:
-            continue
-        source, *replacements = parts
-        indexed_entries.append((line_number, (source, replacements)))
-
-    # Sort longer patterns first to avoid overlapping matches, mirroring the
-    # behaviour of the Rust `confusion_table` helper.
-    indexed_entries.sort(
-        key=lambda item: (-len(item[1][0]), item[0])
-    )
-    entries = [entry for _, entry in indexed_entries]
-    _CONFUSION_TABLE = entries
-    return entries

glitchlings/zoo/_rate.py

@@ -1,21 +0,0 @@
-from __future__ import annotations
-
-
-def resolve_rate(
-    *,
-    rate: float | None,
-    legacy_value: float | None,
-    default: float,
-    legacy_name: str,
-) -> float:
-    """Return the effective rate while enforcing mutual exclusivity."""
-
-    if rate is not None and legacy_value is not None:
-        raise ValueError(
-            f"Specify either 'rate' or '{legacy_name}', not both."
-        )
-    if rate is not None:
-        return rate
-    if legacy_value is not None:
-        return legacy_value
-    return default

glitchlings/zoo/reduple.py

@@ -1,169 +0,0 @@
-import re
-import random
-from typing import Any
-
-from .core import Glitchling, AttackWave
-from ._rate import resolve_rate
-
-try:
-    from glitchlings._zoo_rust import reduplicate_words as _reduplicate_words_rust
-except ImportError:  # pragma: no cover - compiled extension not present
-    _reduplicate_words_rust = None
-
-
-def _python_reduplicate_words(
-    text: str,
-    *,
-    rate: float,
-    rng: random.Random,
-    unweighted: bool = False,
-) -> str:
-    """Randomly reduplicate words in the text.
-
-    Parameters
-    - text: Input text.
-    - rate: Max proportion of words to reduplicate (default 0.05).
-    - rng: RNG used for sampling decisions.
-    - unweighted: When True, sample words uniformly instead of length-weighted.
-
-    Notes
-    - Preserves spacing and punctuation by tokenizing with separators.
-    - Deterministic when run with a fixed seed or via Gaggle.
-    """
-    # Preserve exact spacing and punctuation by using regex
-    tokens = re.split(r"(\s+)", text)  # Split but keep separators
-
-    candidate_weights: list[tuple[int, float]] = []
-    for i in range(0, len(tokens), 2):  # Every other token is a word
-        if i >= len(tokens):
-            break
-
-        word = tokens[i]
-        if not word or word.isspace():  # Skip empty or whitespace
-            continue
-
-        match = re.match(r"^(\W*)(.*?)(\W*)$", word)
-        core = match.group(2) if match else word
-        core_length = len(core) if core else len(word)
-        if core_length <= 0:
-            core_length = len(word.strip()) or len(word)
-        if core_length <= 0:
-            core_length = 1
-        weight = 1.0 if unweighted else 1.0 / core_length
-        candidate_weights.append((i, weight))
-
-    if not candidate_weights:
-        return "".join(tokens)
-
-    effective_rate = max(rate, 0.0)
-    if effective_rate <= 0.0:
-        return "".join(tokens)
-
-    mean_weight = sum(weight for _, weight in candidate_weights) / len(
-        candidate_weights
-    )
-
-    for index, weight in candidate_weights:
-        if effective_rate >= 1.0:
-            probability = 1.0
-        else:
-            if mean_weight <= 0.0:
-                probability = effective_rate
-            else:
-                probability = min(1.0, effective_rate * (weight / mean_weight))
-        if rng.random() >= probability:
-            continue
-
-        word = tokens[index]
-        match = re.match(r"^(\W*)(.*?)(\W*)$", word)
-        if match:
-            prefix, core, suffix = match.groups()
-            # Reduplicate with a space: "word" -> "word word"
-            tokens[index] = f"{prefix}{core} {core}{suffix}"
-        else:
-            tokens[index] = f"{word} {word}"
-    return "".join(tokens)
-
-
-def reduplicate_words(
-    text: str,
-    rate: float | None = None,
-    seed: int | None = None,
-    rng: random.Random | None = None,
-    *,
-    reduplication_rate: float | None = None,
-    unweighted: bool = False,
-) -> str:
-    """Randomly reduplicate words in the text.
-
-    Falls back to the Python implementation when the optional Rust
-    extension is unavailable.
-    """
-
-    effective_rate = resolve_rate(
-        rate=rate,
-        legacy_value=reduplication_rate,
-        default=0.01,
-        legacy_name="reduplication_rate",
-    )
-
-    if rng is None:
-        rng = random.Random(seed)
-
-    clamped_rate = max(0.0, effective_rate)
-    unweighted_flag = bool(unweighted)
-
-    if _reduplicate_words_rust is not None:
-        return _reduplicate_words_rust(text, clamped_rate, unweighted_flag, rng)
-
-    return _python_reduplicate_words(
-        text,
-        rate=clamped_rate,
-        rng=rng,
-        unweighted=unweighted_flag,
-    )
-
-
-class Reduple(Glitchling):
-    """Glitchling that repeats words to simulate stuttering speech."""
-
-    def __init__(
-        self,
-        *,
-        rate: float | None = None,
-        reduplication_rate: float | None = None,
-        seed: int | None = None,
-        unweighted: bool = False,
-    ) -> None:
-        self._param_aliases = {"reduplication_rate": "rate"}
-        effective_rate = resolve_rate(
-            rate=rate,
-            legacy_value=reduplication_rate,
-            default=0.01,
-            legacy_name="reduplication_rate",
-        )
-        super().__init__(
-            name="Reduple",
-            corruption_function=reduplicate_words,
-            scope=AttackWave.WORD,
-            seed=seed,
-            rate=effective_rate,
-            unweighted=unweighted,
-        )
-
-    def pipeline_operation(self) -> dict[str, Any] | None:
-        rate = self.kwargs.get("rate")
-        if rate is None:
-            return None
-        unweighted = bool(self.kwargs.get("unweighted", False))
-        return {
-            "type": "reduplicate",
-            "reduplication_rate": float(rate),
-            "unweighted": unweighted,
-        }
-
-
-reduple = Reduple()
-
-
-__all__ = ["Reduple", "reduple"]