glitchlings 0.3.0__cp311-cp311-macosx_11_0_universal2.whl → 0.4.0__cp311-cp311-macosx_11_0_universal2.whl

glitchlings/zoo/rushmore.py

@@ -4,11 +4,7 @@ import re
 from typing import Any
 
 from ._rate import resolve_rate
-from ._text_utils import (
-    split_preserving_whitespace,
-    split_token_edges,
-    token_core_length,
-)
+from ._text_utils import WordToken, collect_word_tokens, split_preserving_whitespace
 from .core import AttackWave, Glitchling
 
 try:
@@ -31,30 +27,28 @@ def _python_delete_random_words(
         return text
 
     tokens = split_preserving_whitespace(text)
+    word_tokens = collect_word_tokens(tokens, skip_first_word=True)
 
-    candidate_data: list[tuple[int, float]] = []
-    for i in range(2, len(tokens), 2):
-        word = tokens[i]
-        if not word or word.isspace():
-            continue
-
-        length = token_core_length(word)
-        weight = 1.0 if unweighted else 1.0 / length
-        candidate_data.append((i, weight))
+    weighted_tokens: list[tuple[int, float, WordToken]] = []
+    for token in word_tokens:
+        weight = 1.0 if unweighted else 1.0 / float(token.core_length)
+        weighted_tokens.append((token.index, weight, token))
 
-    if not candidate_data:
+    if not weighted_tokens:
         return text
 
     allowed_deletions = min(
-        len(candidate_data), math.floor(len(candidate_data) * effective_rate)
+        len(weighted_tokens), math.floor(len(weighted_tokens) * effective_rate)
     )
     if allowed_deletions <= 0:
         return text
 
-    mean_weight = sum(weight for _, weight in candidate_data) / len(candidate_data)
+    mean_weight = sum(weight for _, weight, _ in weighted_tokens) / len(
+        weighted_tokens
+    )
 
     deletions = 0
-    for index, weight in candidate_data:
+    for index, weight, token in weighted_tokens:
         if deletions >= allowed_deletions:
             break
 
@@ -68,9 +62,9 @@ def _python_delete_random_words(
         if rng.random() >= probability:
             continue
 
-        word = tokens[index]
-        prefix, _, suffix = split_token_edges(word)
-        tokens[index] = f"{prefix.strip()}{suffix.strip()}"
+        prefix = token.prefix.strip()
+        suffix = token.suffix.strip()
+        tokens[index] = f"{prefix}{suffix}"
 
         deletions += 1
 

glitchlings/zoo/typogre.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 
 import math
 import random
-from typing import Optional
+from typing import Any, Optional
 
 from .core import Glitchling, AttackWave, AttackOrder
 from ._rate import resolve_rate
@@ -204,6 +204,27 @@ class Typogre(Glitchling):
             keyboard=keyboard,
         )
 
+    def pipeline_operation(self) -> dict[str, Any] | None:
+        rate = self.kwargs.get("rate")
+        if rate is None:
+            rate = self.kwargs.get("max_change_rate")
+        if rate is None:
+            return None
+
+        keyboard = self.kwargs.get("keyboard", "CURATOR_QWERTY")
+        layout = getattr(KEYNEIGHBORS, str(keyboard), None)
+        if layout is None:
+            return None
+
+        serialized_layout = {key: list(value) for key, value in layout.items()}
+
+        return {
+            "type": "typo",
+            "rate": float(rate),
+            "keyboard": str(keyboard),
+            "layout": serialized_layout,
+        }
+
 
 typogre = Typogre()
 

glitchlings/zoo/zeedub.py

@@ -101,7 +101,26 @@ def insert_zero_widths(
         return text
 
     if _inject_zero_widths_rust is not None:
-        return _inject_zero_widths_rust(text, clamped_rate, list(cleaned_palette), rng)
+        state = None
+        python_state = None
+        if hasattr(rng, "getstate") and hasattr(rng, "setstate"):
+            state = rng.getstate()
+        python_result = _python_insert_zero_widths(
+            text,
+            rate=clamped_rate,
+            rng=rng,
+            characters=cleaned_palette,
+        )
+        if state is not None:
+            if hasattr(rng, "getstate"):
+                python_state = rng.getstate()
+            rng.setstate(state)
+        rust_result = _inject_zero_widths_rust(text, clamped_rate, list(cleaned_palette), rng)
+        if rust_result == python_result:
+            return rust_result
+        if python_state is not None and hasattr(rng, "setstate"):
+            rng.setstate(python_state)
+        return python_result
 
     return _python_insert_zero_widths(
         text,
@@ -137,6 +156,26 @@ class Zeedub(Glitchling):
             characters=tuple(characters) if characters is not None else None,
         )
 
+    def pipeline_operation(self) -> dict[str, Any] | None:
+        rate = self.kwargs.get("rate")
+        if rate is None:
+            return None
+
+        raw_characters = self.kwargs.get("characters")
+        if raw_characters is None:
+            palette = tuple(_DEFAULT_ZERO_WIDTH_CHARACTERS)
+        else:
+            palette = tuple(str(char) for char in raw_characters if char)
+
+        if not palette:
+            return None
+
+        return {
+            "type": "zwj",
+            "rate": float(rate),
+            "characters": list(palette),
+        }
+
 
 zeedub = Zeedub()
 

{glitchlings-0.3.0.dist-info → glitchlings-0.4.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: glitchlings
-Version: 0.3.0
+Version: 0.4.0
 Summary: Monsters for your language games.
 Author: osoleve
 License:                                  Apache License
@@ -209,7 +209,7 @@ 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,text,adversarial augmentation,text augmentation,large language models,llms,data augmentation,rlvr
+Keywords: nlp,adversarial augmentation,text augmentation,data augmentation,domain randomization
 Classifier: Development Status :: 3 - Alpha
 Classifier: Intended Audience :: Developers
 Classifier: Programming Language :: Python
@@ -224,18 +224,20 @@ Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: confusable-homoglyphs>=3.3.1
+Requires-Dist: tomli>=2.0.1; python_version < "3.11"
+Requires-Dist: pyyaml>=6.0.0
 Provides-Extra: hf
 Requires-Dist: datasets>=4.0.0; extra == "hf"
-Provides-Extra: wordnet
-Requires-Dist: nltk>=3.9.1; extra == "wordnet"
-Requires-Dist: numpy<=2.0,>=1.24; extra == "wordnet"
+Provides-Extra: vectors
+Requires-Dist: numpy<=2.0,>=1.24; extra == "vectors"
+Requires-Dist: spacy>=3.7.2; extra == "vectors"
+Requires-Dist: gensim>=4.3.2; extra == "vectors"
 Provides-Extra: prime
 Requires-Dist: verifiers>=0.1.3.post0; extra == "prime"
 Requires-Dist: jellyfish>=1.2.0; extra == "prime"
 Provides-Extra: dev
 Requires-Dist: pytest>=8.0.0; extra == "dev"
 Requires-Dist: hypothesis>=6.140.0; extra == "dev"
-Requires-Dist: nltk>=3.9.1; extra == "dev"
 Requires-Dist: numpy<=2.0,>=1.24; extra == "dev"
 Dynamic: license-file
 
@@ -348,10 +350,30 @@ 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
+
+# Load a roster from a YAML attack configuration.
+glitchlings --config experiments/chaos.yaml "Let slips the glitchlings of war"
 ```
 
 Use `--help` for a complete breakdown of available options, including support for parameterised glitchlings via `-g "Name(arg=value, ...)"` to mirror the Python API.
 
+Attack configurations live in plain YAML files so you can version-control experiments without touching code:
+
+```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"]
+```
+
+Pass the file to `glitchlings --config` or load it from Python with `glitchlings.load_attack_config` and `glitchlings.build_gaggle`.
+
 ## 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.
@@ -416,8 +438,8 @@ _Uh oh. The worst person you know just bought a thesaurus._
 >
 > Args
 >
-> - `rate (float)`: The maximum proportion of words to replace (default: 0.1, 10%).
-> - `part_of_speech`: The WordNet part(s) of speech to target (default: nouns). Accepts `wn.NOUN`, `wn.VERB`, `wn.ADJ`, `wn.ADV`, any iterable of those tags, or the string `"any"` to include them all.
+> - `rate (float)`: The maximum proportion of words to replace (default: 0.01, 1%).
+- `part_of_speech`: The WordNet-style part(s) of speech to target (default: nouns). Accepts `wn.NOUN`, `wn.VERB`, `wn.ADJ`, `wn.ADV`, any iterable of those tags, or the string `"any"` to include them all. Vector/graph backends ignore this filter while still honouring deterministic sampling.
 > - `seed (int)`: The random seed for reproducibility (default: 151).
 
 ### Reduple

glitchlings-0.4.0.dist-info/RECORD

@@ -0,0 +1,38 @@
+glitchlings/__init__.py,sha256=hEmQ1rl3G5uZBDbfJX_W4aIUNSsPAsy_Ai5DgQHasvk,813
+glitchlings/__main__.py,sha256=EOiBgay0x6B9VlSDzSQvMuoq6bHJdSvFSgcAVGGKkd4,121
+glitchlings/_zoo_rust.cpython-311-darwin.so,sha256=l05pofs9b3aNpJ9yj9RTt7_DGzFP_aQl3BiEkWDjFyA,2450000
+glitchlings/config.py,sha256=hwkcMkhEvUzK8FECgG6kbf_4MpMQcopskiSgXzK5B3o,7785
+glitchlings/config.toml,sha256=MWwgbx1-KIRAY3JZmMrCVbZNxFjHgRJXbtNAVuUNcxY,108
+glitchlings/main.py,sha256=Rw9pCgNrGxwzC1rZbbng7cHUP9xlL0WWWTdjW95XiSM,10084
+glitchlings/dlc/__init__.py,sha256=eTLEEWrVWPqniXHqee4W23H1rjElI1PQ_jcqWFe9D3g,141
+glitchlings/dlc/huggingface.py,sha256=I1QWanWVxO02awgSpHDtgQEVF-9AQRLtsta2RCitWhE,2933
+glitchlings/dlc/prime.py,sha256=wpRMNtgka1vNlEzifeCjGMp1q_-QclZn3NxXczGnNpM,9278
+glitchlings/lexicon/__init__.py,sha256=-w35jPtg7WCP_IfRxAUZBNFXeSnlIaVfbJiPDI3f3K4,5663
+glitchlings/lexicon/graph.py,sha256=_2w5shu-fEieDN-egpqLvMu0rxG78RAQWqENU0r7PlM,10533
+glitchlings/lexicon/metrics.py,sha256=W8TCemZaCjBOUSX8G7JdgQAbMykXXfRTfodkDSkc3aQ,4599
+glitchlings/lexicon/vector.py,sha256=Qqspc8KR4hqJiTTiXnu8DCIp2ROYPgEKK4RM4kLkyGY,20284
+glitchlings/lexicon/wordnet.py,sha256=FwjTtVPOQEmWEXL0Sl4faM-C4PPNkDu_z7-FyINlh3c,5652
+glitchlings/lexicon/data/default_vector_cache.json,sha256=7obKHqmR3odbTfgJPWLSRFYFh4J_6uvv_CntCSe_EjI,725
+glitchlings/util/__init__.py,sha256=7KiZ0gKMjocfd34cajneZhTqYb7Hkwi_PpjltPqvkNI,4498
+glitchlings/zoo/__init__.py,sha256=eFYmaWeFDlSqfaiED51HWM-OqiTo_BOz0ASeyhOwOsw,4818
+glitchlings/zoo/_ocr_confusions.py,sha256=MkCbwk9T24SO2pD3JNPajYCfpMMlm2vQ5_sJty5GoXE,1218
+glitchlings/zoo/_rate.py,sha256=TMyfVFV7pLxSGVswPlOAtBvk25Bjtx5xXTtpb_utgik,527
+glitchlings/zoo/_sampling.py,sha256=VOSWDgYWXIiAuKxn2IckFJhpRgGotQP_KW28db8kTKI,1587
+glitchlings/zoo/_text_utils.py,sha256=nAfFT_VdXMXciCR7eQ5EAmym5wvzL6_Sdn9dvCx2s3Q,2758
+glitchlings/zoo/adjax.py,sha256=N3CzfM7m7mAYgFcQYLQkqK2VYLw_vFvEMBM2aNU--ZA,3530
+glitchlings/zoo/core.py,sha256=fhceCZKa9W1vVlhpR2zVKBXnzgJICB2-nmDywiqx4js,14207
+glitchlings/zoo/jargoyle.py,sha256=6-DJxUFz2AjT-iQDFlK2ZG9pVwq2boDtslEzCNyI_04,11481
+glitchlings/zoo/mim1c.py,sha256=yAt1ngR3j2KXLbzc8LhrQlIWRO_KT5dFK1EE8QivMAQ,3429
+glitchlings/zoo/ocr_confusions.tsv,sha256=KhtR7vJDTITpfTSGa-I7RHr6CK7LkGi2KjdhEWipI6o,183
+glitchlings/zoo/redactyl.py,sha256=H4PwAMBCIsDw1KBOBiTR3VUbRZwynqakwwfx3wHjVp8,5457
+glitchlings/zoo/reduple.py,sha256=Q9NRCdvUgaHvvJu8A0n6zW9v_L3pdmNZbWqaJ7uycw4,4216
+glitchlings/zoo/rushmore.py,sha256=J1wd4IB7WOAR2TdntkxCMZWseWR0Yii8UQZ7ucfpWCc,4335
+glitchlings/zoo/scannequin.py,sha256=Ps8nxysKjkJV408zaL1kjVjy4jliATDBpYcNHLWbNFg,4859
+glitchlings/zoo/typogre.py,sha256=0fYaxOEiTnxiCqmsiSN1r_wl1vC1Ueaiks2e94kks70,6668
+glitchlings/zoo/zeedub.py,sha256=l51swlo556-TXhDk4nayHOm1XgHwWmfUKzQ01YMuCpE,4801
+glitchlings-0.4.0.dist-info/licenses/LICENSE,sha256=YCvGip-LoaRyu6h0nPo71q6eHEkzUpsE11psDJOIRkw,11337
+glitchlings-0.4.0.dist-info/METADATA,sha256=Dldj4SIrrNF6TKAvvJghd_L4lVrzdViqb8DWMSvPWVE,28345
+glitchlings-0.4.0.dist-info/WHEEL,sha256=Tgp8Vc-mmQm0KX-V22BSUoymoX1p0w13bZbX85y8hSs,114
+glitchlings-0.4.0.dist-info/entry_points.txt,sha256=kGOwuAsjFDLtztLisaXtOouq9wFVMOJg5FzaAkg-Hto,54
+glitchlings-0.4.0.dist-info/top_level.txt,sha256=VHFNBrLjtDwPCYXbGKi6o17Eueedi81eNbR3hBOoST0,12
+glitchlings-0.4.0.dist-info/RECORD,,

glitchlings-0.3.0.dist-info/RECORD

@@ -1,29 +0,0 @@
-glitchlings/__init__.py,sha256=BLwp5ncEEVTurUDEo6DZcYjYz7r12LzblLfOcVc4MEU,680
-glitchlings/__main__.py,sha256=EOiBgay0x6B9VlSDzSQvMuoq6bHJdSvFSgcAVGGKkd4,121
-glitchlings/_zoo_rust.cpython-311-darwin.so,sha256=K9GCUmlYT8zipQe_Ak5IgrUKJVI0AKbz7CbJEgoOaqo,2406592
-glitchlings/main.py,sha256=u6969Vl0n47e3S-ZlYZBj3HWVsjs-hvW6RpF9RYuXnc,5931
-glitchlings/dlc/__init__.py,sha256=eTLEEWrVWPqniXHqee4W23H1rjElI1PQ_jcqWFe9D3g,141
-glitchlings/dlc/huggingface.py,sha256=I1QWanWVxO02awgSpHDtgQEVF-9AQRLtsta2RCitWhE,2933
-glitchlings/dlc/prime.py,sha256=wpRMNtgka1vNlEzifeCjGMp1q_-QclZn3NxXczGnNpM,9278
-glitchlings/util/__init__.py,sha256=7KiZ0gKMjocfd34cajneZhTqYb7Hkwi_PpjltPqvkNI,4498
-glitchlings/zoo/__init__.py,sha256=sTmh-1u02kgjYlpRPz9lF9c1aXHamcShRXUOGK87J5Q,4378
-glitchlings/zoo/_ocr_confusions.py,sha256=MkCbwk9T24SO2pD3JNPajYCfpMMlm2vQ5_sJty5GoXE,1218
-glitchlings/zoo/_rate.py,sha256=TMyfVFV7pLxSGVswPlOAtBvk25Bjtx5xXTtpb_utgik,527
-glitchlings/zoo/_text_utils.py,sha256=ZXy5khgoMTZp7NHdekkkj4vQjeMWGK2bzXPwIECBIfo,1120
-glitchlings/zoo/adjax.py,sha256=N3CzfM7m7mAYgFcQYLQkqK2VYLw_vFvEMBM2aNU--ZA,3530
-glitchlings/zoo/core.py,sha256=fhceCZKa9W1vVlhpR2zVKBXnzgJICB2-nmDywiqx4js,14207
-glitchlings/zoo/jargoyle.py,sha256=T6vPWBxceIPE6gOQ7BaihaqALOJwzXuhfiZzvKa4S50,10666
-glitchlings/zoo/mim1c.py,sha256=yAt1ngR3j2KXLbzc8LhrQlIWRO_KT5dFK1EE8QivMAQ,3429
-glitchlings/zoo/ocr_confusions.tsv,sha256=KhtR7vJDTITpfTSGa-I7RHr6CK7LkGi2KjdhEWipI6o,183
-glitchlings/zoo/redactyl.py,sha256=8xsamnVt1RFy7ztvfgfJDwCadQIlN-9fDz-TLfBQ89k,6357
-glitchlings/zoo/reduple.py,sha256=IQM0WYinWJWjMIaBSuPPcpOXOynly9Tp2UtJEZxibGk,4313
-glitchlings/zoo/rushmore.py,sha256=Cw6qpk3jp8DjtxmFALd5zTIOnS6C0tIkoPFA7F-xlVk,4369
-glitchlings/zoo/scannequin.py,sha256=Ps8nxysKjkJV408zaL1kjVjy4jliATDBpYcNHLWbNFg,4859
-glitchlings/zoo/typogre.py,sha256=xD02ldcMIA07XsdSts2bUniOc-k_DqTf0PBMaXGjLZE,6009
-glitchlings/zoo/zeedub.py,sha256=D6rGk3O02OQ9jEIO9o0Ag-maVzNPN5O6qO3klG6Y62c,3552
-glitchlings-0.3.0.dist-info/licenses/LICENSE,sha256=YCvGip-LoaRyu6h0nPo71q6eHEkzUpsE11psDJOIRkw,11337
-glitchlings-0.3.0.dist-info/METADATA,sha256=iflxCI-vHtZP-omUePVGqx0QHLoFiJoHzcM7aSNvboQ,27579
-glitchlings-0.3.0.dist-info/WHEEL,sha256=Tgp8Vc-mmQm0KX-V22BSUoymoX1p0w13bZbX85y8hSs,114
-glitchlings-0.3.0.dist-info/entry_points.txt,sha256=kGOwuAsjFDLtztLisaXtOouq9wFVMOJg5FzaAkg-Hto,54
-glitchlings-0.3.0.dist-info/top_level.txt,sha256=VHFNBrLjtDwPCYXbGKi6o17Eueedi81eNbR3hBOoST0,12
-glitchlings-0.3.0.dist-info/RECORD,,