glitchlings 0.2.1__tar.gz → 0.2.3__tar.gz

glitchlings-0.2.3/MANIFEST.in

@@ -0,0 +1,4 @@
+recursive-include rust *.rs *.toml *.lock *.tsv
+recursive-include src/glitchlings/zoo *.tsv
+prune rust/target
+prune rust/zoo/target

{glitchlings-0.2.1/src/glitchlings.egg-info → glitchlings-0.2.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: glitchlings
-Version: 0.2.1
+Version: 0.2.3
 Summary: Monsters for your language games.
 Author: osoleve
 License:                                  Apache License
@@ -215,6 +215,8 @@ Classifier: Intended Audience :: Developers
 Classifier: License :: OSI Approved :: Apache Software License
 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 :: Rust
 Classifier: Operating System :: MacOS :: MacOS X
@@ -223,7 +225,7 @@ Classifier: Operating System :: POSIX :: Linux
 Classifier: Operating System :: OS Independent
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Classifier: Topic :: Software Development :: Testing
-Requires-Python: >=3.12
+Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: confusable-homoglyphs>=3.3.1
@@ -232,11 +234,14 @@ 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: prime
 Requires-Dist: verifiers>=0.1.3.post0; 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
 
 #
@@ -277,14 +282,16 @@ After all, what good is general intelligence if it can't handle a little chaos?
 pip install -U glitchlings
 ```
 
+> Glitchlings requires Python 3.10 or newer.
+
 ```python
 from glitchlings import Gaggle, SAMPLE_TEXT, Typogre, Mim1c, Reduple, Rushmore
 
 gaggle = Gaggle([
-    Typogre(max_change_rate=0.03),
-    Mim1c(replacement_rate=0.02),
+    Typogre(rate=0.03),
+    Mim1c(rate=0.02),
     Reduple(seed=404),
-    Rushmore(max_deletion_rate=0.02),
+    Rushmore(rate=0.02),
 ])
 
 print(gaggle(SAMPLE_TEXT))
@@ -292,52 +299,9 @@ print(gaggle(SAMPLE_TEXT))
 
 > Onҽ m‎ھ‎rning, wһen Gregor Samƽa woke from trouble𝐝 𝑑reams, he found himself transformed in his bed into a horrible vermin‎٠‎ He l   lay on his armour-like back, and if he lifted his head a little he could see his brown belly, slightlh domed and divided by arches ino stiff sections. The bedding was adly able to cover it and and seemed ready to slide off any  moment. His many legxs, pitifully thin compared with the size of the the rest of him, waved about helplessly ashe looked looked.
 
-## Usage
-
-Glitchlings slot into evaluation pipelines just as easily as they corrupt stray strings.
-
-- **Direct invocation** – Instantiate a glitchling (or `Gaggle`) and call it on strings, iterables, or datasets. Keep the seed stable to make every run deterministic.
-- **Dataset corruption** – After ``import glitchlings.dlc.huggingface``, call ``Dataset.glitch(...)`` (or a `Gaggle`'s `.corrupt_dataset`) to perturb a Hugging Face `datasets.Dataset` and return a corrupted copy for training or evaluation.
-
-### Rust pipeline acceleration (opt-in)
-
-The refactored Rust pipeline can execute multiple glitchlings without
-bouncing back through Python, but it is gated behind a feature flag so
-teams can roll it out gradually. After compiling the Rust extension
-(`python -m cibuildwheel --output-dir dist`) set
-`GLITCHLINGS_RUST_PIPELINE=1` (or `true`, `yes`, `on`) before importing
-`glitchlings`. When the flag is set and the extension is available,
-`Gaggle` automatically batches compatible glitchlings into the Rust
-pipeline; otherwise it transparently falls back to the legacy Python
-loop.
-
-### Prime Intellect environments
-
-After `pip install -e .[prime]`, the `glitchlings.dlc.prime.load_environment` helper mirrors `verifiers.load_environment` for Prime Intellect scenarios while optionally applying glitchlings before returning the environment:
-
-```python
-from glitchlings import Mim1c, Typogre
-from glitchlings.dlc.prime import echo_chamber, load_environment
-
-env = load_environment(
-    "osoleve/syllabify-en",
-    glitchlings=[Mim1c(replacement_rate=0.01), Typogre(max_change_rate=0.02)],
-    seed=404,
-)
-
-# Spin up an echo chamber that corrupts a dataset column and
-# rewards models for perfectly restoring it
-practice_env = echo_chamber(
-    "osoleve/clean-room",
-    column="text",
-    glitchlings=["Typogre", "Mim1c"],
-    reward_function=lambda prompt, completion, answer: float(completion == answer),
-)
-```
-
-Skip the `glitchlings` argument to receive an untouched verifier dataset, and
-override `reward_function` when you want to evaluate completions with a custom
-scoring routine.
+Consult the [Glitchlings Usage Guide](docs/index.md)
+for end-to-end instructions spanning the Python API, CLI, HuggingFace and Prime Intellect
+integrations, and the feature-flagged Rust pipeline.
 
 ## Motivation
 
@@ -353,8 +317,8 @@ Glitchlings are standard Python classes, so you can instantiate them with whatev
 ```python
 from glitchlings import Gaggle, Typogre, Mim1c
 
-custom_typogre = Typogre(max_change_rate=0.1)
-selective_mimic = Mim1c(replacement_rate=0.05, classes=["LATIN", "GREEK"])
+custom_typogre = Typogre(rate=0.1)
+selective_mimic = Mim1c(rate=0.05, classes=["LATIN", "GREEK"])
 
 gaggle = Gaggle([custom_typogre, selective_mimic], seed=99)
 print(gaggle("Summoned heroes do not fear the glitch."))
@@ -384,11 +348,14 @@ glitchlings --list
 # 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
 ```
 
-Use `--help` for a complete breakdown of available options.
+Use `--help` for a complete breakdown of available options, including support for parameterised glitchlings via `-g "Name(arg=value, ...)"` to mirror the Python API.
 
 ## Development
 
@@ -406,7 +373,7 @@ _What a nice word, would be a shame if something happened to it._
 >
 > Args
 >
-> - `max_change_rate (float)`: The maximum number of edits to make as a percentage of the length (default: 0.02, 2%).
+> - `rate (float)`: The maximum number of edits to make as a percentage of the length (default: 0.02, 2%).
 > - `keyboard (str)`: Keyboard layout key-neighbor map to use (default: "CURATOR_QWERTY"; also accepts "QWERTY", "DVORAK", "COLEMAK", and "AZERTY").
 > - `seed (int)`: The random seed for reproducibility (default: 151).
 
@@ -418,7 +385,7 @@ _Wait, was that...?_
 >
 > Args
 >
-> - `replacement_rate (float)`: The maximum proportion of characters to replace (default: 0.02, 2%).
+> - `rate (float)`: The maximum proportion of characters to replace (default: 0.02, 2%).
 > - `classes (list[str] | "all")`: Restrict replacements to these Unicode script classes (default: ["LATIN", "GREEK", "CYRILLIC"]).
 > - `banned_characters (Collection[str])`: Characters that must never appear as replacements (default: none).
 > - `seed (int)`: The random seed for reproducibility (default: 151).
@@ -431,7 +398,7 @@ _How can a computer need reading glasses?_
 >
 > Args
 >
-> - `error_rate (float)`: The maximum proportion of eligible confusion spans to replace (default: 0.02, 2%).
+> - `rate (float)`: The maximum proportion of eligible confusion spans to replace (default: 0.02, 2%).
 > - `seed (int)`: The random seed for reproducibility (default: 151).
 
 ### Jargoyle
@@ -442,7 +409,7 @@ _Uh oh. The worst person you know just bought a thesaurus._
 >
 > Args
 >
-> - `replacement_rate (float)`: The maximum proportion of words to replace (default: 0.1, 10%).
+> - `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.
 > - `seed (int)`: The random seed for reproducibility (default: 151).
 
@@ -454,7 +421,7 @@ _Did you say that or did I?_
 >
 > Args
 >
-> - `reduplication_rate (float)`: The maximum proportion of words to reduplicate (default: 0.05, 5%).
+> - `rate (float)`: The maximum proportion of words to reduplicate (default: 0.05, 5%).
 > - `seed (int)`: The random seed for reproducibility (default: 151).
 
 ### Rushmore
@@ -465,7 +432,7 @@ _I accidentally an entire word._
 >
 > Args
 >
-> - `max_deletion_rate (float)`: The maximum proportion of words to delete (default: 0.01, 1%).
+> - `rate (float)`: The maximum proportion of words to delete (default: 0.01, 1%).
 > - `seed (int)`: The random seed for reproducibility (default: 151).
 
 ### Redactyl
@@ -477,7 +444,7 @@ _Oops, that was my black highlighter._
 > ### Args
 >
 > - `replacement_char (str)`: The character to use for redaction (default: █).
-> - `redaction_rate (float)`: The maximum proportion of words to redact (default: 0.05, 5%).
+> - `rate (float)`: The maximum proportion of words to redact (default: 0.05, 5%).
 > - `merge_adjacent (bool)`: Whether to redact the space between adjacent redacted words (default: False).
 > - `seed (int)`: The random seed for reproducibility (default: 151).
 

{glitchlings-0.2.1 → glitchlings-0.2.3}/README.md

@@ -36,14 +36,16 @@ After all, what good is general intelligence if it can't handle a little chaos?
 pip install -U glitchlings
 ```
 
+> Glitchlings requires Python 3.10 or newer.
+
 ```python
 from glitchlings import Gaggle, SAMPLE_TEXT, Typogre, Mim1c, Reduple, Rushmore
 
 gaggle = Gaggle([
-    Typogre(max_change_rate=0.03),
-    Mim1c(replacement_rate=0.02),
+    Typogre(rate=0.03),
+    Mim1c(rate=0.02),
     Reduple(seed=404),
-    Rushmore(max_deletion_rate=0.02),
+    Rushmore(rate=0.02),
 ])
 
 print(gaggle(SAMPLE_TEXT))
@@ -51,52 +53,9 @@ print(gaggle(SAMPLE_TEXT))
 
 > Onҽ m‎ھ‎rning, wһen Gregor Samƽa woke from trouble𝐝 𝑑reams, he found himself transformed in his bed into a horrible vermin‎٠‎ He l   lay on his armour-like back, and if he lifted his head a little he could see his brown belly, slightlh domed and divided by arches ino stiff sections. The bedding was adly able to cover it and and seemed ready to slide off any  moment. His many legxs, pitifully thin compared with the size of the the rest of him, waved about helplessly ashe looked looked.
 
-## Usage
-
-Glitchlings slot into evaluation pipelines just as easily as they corrupt stray strings.
-
-- **Direct invocation** – Instantiate a glitchling (or `Gaggle`) and call it on strings, iterables, or datasets. Keep the seed stable to make every run deterministic.
-- **Dataset corruption** – After ``import glitchlings.dlc.huggingface``, call ``Dataset.glitch(...)`` (or a `Gaggle`'s `.corrupt_dataset`) to perturb a Hugging Face `datasets.Dataset` and return a corrupted copy for training or evaluation.
-
-### Rust pipeline acceleration (opt-in)
-
-The refactored Rust pipeline can execute multiple glitchlings without
-bouncing back through Python, but it is gated behind a feature flag so
-teams can roll it out gradually. After compiling the Rust extension
-(`python -m cibuildwheel --output-dir dist`) set
-`GLITCHLINGS_RUST_PIPELINE=1` (or `true`, `yes`, `on`) before importing
-`glitchlings`. When the flag is set and the extension is available,
-`Gaggle` automatically batches compatible glitchlings into the Rust
-pipeline; otherwise it transparently falls back to the legacy Python
-loop.
-
-### Prime Intellect environments
-
-After `pip install -e .[prime]`, the `glitchlings.dlc.prime.load_environment` helper mirrors `verifiers.load_environment` for Prime Intellect scenarios while optionally applying glitchlings before returning the environment:
-
-```python
-from glitchlings import Mim1c, Typogre
-from glitchlings.dlc.prime import echo_chamber, load_environment
-
-env = load_environment(
-    "osoleve/syllabify-en",
-    glitchlings=[Mim1c(replacement_rate=0.01), Typogre(max_change_rate=0.02)],
-    seed=404,
-)
-
-# Spin up an echo chamber that corrupts a dataset column and
-# rewards models for perfectly restoring it
-practice_env = echo_chamber(
-    "osoleve/clean-room",
-    column="text",
-    glitchlings=["Typogre", "Mim1c"],
-    reward_function=lambda prompt, completion, answer: float(completion == answer),
-)
-```
-
-Skip the `glitchlings` argument to receive an untouched verifier dataset, and
-override `reward_function` when you want to evaluate completions with a custom
-scoring routine.
+Consult the [Glitchlings Usage Guide](docs/index.md)
+for end-to-end instructions spanning the Python API, CLI, HuggingFace and Prime Intellect
+integrations, and the feature-flagged Rust pipeline.
 
 ## Motivation
 
@@ -112,8 +71,8 @@ Glitchlings are standard Python classes, so you can instantiate them with whatev
 ```python
 from glitchlings import Gaggle, Typogre, Mim1c
 
-custom_typogre = Typogre(max_change_rate=0.1)
-selective_mimic = Mim1c(replacement_rate=0.05, classes=["LATIN", "GREEK"])
+custom_typogre = Typogre(rate=0.1)
+selective_mimic = Mim1c(rate=0.05, classes=["LATIN", "GREEK"])
 
 gaggle = Gaggle([custom_typogre, selective_mimic], seed=99)
 print(gaggle("Summoned heroes do not fear the glitch."))
@@ -143,11 +102,14 @@ glitchlings --list
 # 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
 ```
 
-Use `--help` for a complete breakdown of available options.
+Use `--help` for a complete breakdown of available options, including support for parameterised glitchlings via `-g "Name(arg=value, ...)"` to mirror the Python API.
 
 ## Development
 
@@ -165,7 +127,7 @@ _What a nice word, would be a shame if something happened to it._
 >
 > Args
 >
-> - `max_change_rate (float)`: The maximum number of edits to make as a percentage of the length (default: 0.02, 2%).
+> - `rate (float)`: The maximum number of edits to make as a percentage of the length (default: 0.02, 2%).
 > - `keyboard (str)`: Keyboard layout key-neighbor map to use (default: "CURATOR_QWERTY"; also accepts "QWERTY", "DVORAK", "COLEMAK", and "AZERTY").
 > - `seed (int)`: The random seed for reproducibility (default: 151).
 
@@ -177,7 +139,7 @@ _Wait, was that...?_
 >
 > Args
 >
-> - `replacement_rate (float)`: The maximum proportion of characters to replace (default: 0.02, 2%).
+> - `rate (float)`: The maximum proportion of characters to replace (default: 0.02, 2%).
 > - `classes (list[str] | "all")`: Restrict replacements to these Unicode script classes (default: ["LATIN", "GREEK", "CYRILLIC"]).
 > - `banned_characters (Collection[str])`: Characters that must never appear as replacements (default: none).
 > - `seed (int)`: The random seed for reproducibility (default: 151).
@@ -190,7 +152,7 @@ _How can a computer need reading glasses?_
 >
 > Args
 >
-> - `error_rate (float)`: The maximum proportion of eligible confusion spans to replace (default: 0.02, 2%).
+> - `rate (float)`: The maximum proportion of eligible confusion spans to replace (default: 0.02, 2%).
 > - `seed (int)`: The random seed for reproducibility (default: 151).
 
 ### Jargoyle
@@ -201,7 +163,7 @@ _Uh oh. The worst person you know just bought a thesaurus._
 >
 > Args
 >
-> - `replacement_rate (float)`: The maximum proportion of words to replace (default: 0.1, 10%).
+> - `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.
 > - `seed (int)`: The random seed for reproducibility (default: 151).
 
@@ -213,7 +175,7 @@ _Did you say that or did I?_
 >
 > Args
 >
-> - `reduplication_rate (float)`: The maximum proportion of words to reduplicate (default: 0.05, 5%).
+> - `rate (float)`: The maximum proportion of words to reduplicate (default: 0.05, 5%).
 > - `seed (int)`: The random seed for reproducibility (default: 151).
 
 ### Rushmore
@@ -224,7 +186,7 @@ _I accidentally an entire word._
 >
 > Args
 >
-> - `max_deletion_rate (float)`: The maximum proportion of words to delete (default: 0.01, 1%).
+> - `rate (float)`: The maximum proportion of words to delete (default: 0.01, 1%).
 > - `seed (int)`: The random seed for reproducibility (default: 151).
 
 ### Redactyl
@@ -236,7 +198,7 @@ _Oops, that was my black highlighter._
 > ### Args
 >
 > - `replacement_char (str)`: The character to use for redaction (default: █).
-> - `redaction_rate (float)`: The maximum proportion of words to redact (default: 0.05, 5%).
+> - `rate (float)`: The maximum proportion of words to redact (default: 0.05, 5%).
 > - `merge_adjacent (bool)`: Whether to redact the space between adjacent redacted words (default: False).
 > - `seed (int)`: The random seed for reproducibility (default: 151).
 

{glitchlings-0.2.1 → glitchlings-0.2.3}/pyproject.toml

@@ -1,9 +1,9 @@
 [project]
 name = "glitchlings"
-version = "0.2.1"
+version = "0.2.3"
 description = "Monsters for your language games."
 readme = "README.md"
-requires-python = ">=3.12"
+requires-python = ">=3.10"
 
 dependencies = [
     "confusable-homoglyphs>=3.3.1",
@@ -22,6 +22,8 @@ classifiers = [
     "License :: OSI Approved :: Apache Software License",
     "Programming Language :: Python",
     "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
     "Programming Language :: Python :: 3.12",
     "Programming Language :: Rust",
     "Operating System :: MacOS :: MacOS X",
@@ -46,11 +48,13 @@ glitchlings = "glitchlings.main:main"
 
 [project.optional-dependencies]
 hf = ["datasets>=4.0.0"]
-wordnet = ["nltk>=3.9.1"]
+wordnet = ["nltk>=3.9.1", "numpy>=1.24,<=2.0"]
 prime = ["verifiers>=0.1.3.post0"]
 dev = [
     "pytest>=8.0.0",
     "hypothesis>=6.140.0",
+    "nltk>=3.9.1",
+    "numpy>=1.24,<=2.0",
 ]
 
 [build-system]
@@ -59,6 +63,10 @@ build-backend = "setuptools.build_meta"
 
 [tool.setuptools]
 package-dir = {"" = "src"}
+include-package-data = true
+
+[tool.setuptools.package-data]
+"glitchlings.zoo" = ["ocr_confusions.tsv"]
 
 [tool.setuptools.packages.find]
 where = ["src"]
@@ -69,11 +77,6 @@ path = "rust/zoo/Cargo.toml"
 binding = "PyO3"
 debug = false
 
-[[tool.setuptools-rust.ext-modules]]
-target = "glitchlings._typogre_rust"
-path = "rust/typogre/Cargo.toml"
-binding = "PyO3"
-debug = false
 
 [tool.pytest.ini_options]
 pythonpath = [

{glitchlings-0.2.1 → glitchlings-0.2.3}/rust/Cargo.lock

@@ -316,13 +316,6 @@ version = "1.19.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "562d481066bde0658276a35467c4af00bdc6ee726305698a55b86e61d7ad82bb"
 
-[[package]]
-name = "typogre_rust"
-version = "0.1.0"
-dependencies = [
- "pyo3",
-]
-
 [[package]]
 name = "unicode-ident"
 version = "1.0.19"

{glitchlings-0.2.1 → glitchlings-0.2.3}/rust/Cargo.toml

@@ -1,6 +1,5 @@
 [workspace]
 members = [
-    "typogre",
     "zoo",
 ]
 resolver = "2"

glitchlings-0.2.3/rust/zoo/assets/ocr_confusions.tsv

@@ -0,0 +1,30 @@
+# Source  Replacements (space-separated)
+li h
+h li
+rn m
+m rn
+cl d
+d cl
+I l
+l I 1
+1 l I
+0 O
+O 0
+B 8
+8 B
+S 5
+5 S
+Z 2
+2 Z
+G 6
+6 G
+“ "
+” "
+‘ '
+’ '
+— -
+– -
+vv w
+w vv
+ri n
+n ri

glitchlings-0.2.3/rust/zoo/build.rs

@@ -0,0 +1,140 @@
+use std::env;
+use std::ffi::{OsStr, OsString};
+use std::fs;
+use std::io::{self, ErrorKind};
+use std::path::PathBuf;
+use std::process::Command;
+
+fn main() {
+    prepare_confusion_table().expect("failed to stage OCR confusion table for compilation");
+    pyo3_build_config::add_extension_module_link_args();
+
+    if let Some(python) = configured_python() {
+        link_python(&python);
+    } else if let Some(python) = detect_python() {
+        link_python(&python);
+    }
+}
+
+fn configured_python() -> Option<OsString> {
+    std::env::var_os("PYO3_PYTHON")
+        .or_else(|| std::env::var_os("PYTHON"))
+        .filter(|path| !path.is_empty())
+}
+
+fn detect_python() -> Option<OsString> {
+    const CANDIDATES: &[&str] = &[
+        "python3.12",
+        "python3.11",
+        "python3.10",
+        "python3",
+        "python",
+    ];
+
+    for candidate in CANDIDATES {
+        let status = Command::new(candidate)
+            .arg("-c")
+            .arg("import sys")
+            .output();
+
+        if let Ok(output) = status {
+            if output.status.success() {
+                return Some(OsString::from(candidate));
+            }
+        }
+    }
+
+    None
+}
+
+fn link_python(python: &OsStr) {
+    if let Some(path) = query_python(
+        python,
+        "import sysconfig; print(sysconfig.get_config_var('LIBDIR') or '')",
+    ) {
+        let trimmed = path.trim();
+        if !trimmed.is_empty() {
+            println!("cargo:rustc-link-search=native={trimmed}");
+        }
+    }
+
+    if let Some(path) = query_python(
+        python,
+        "import sysconfig; print(sysconfig.get_config_var('LIBPL') or '')",
+    ) {
+        let trimmed = path.trim();
+        if !trimmed.is_empty() {
+            println!("cargo:rustc-link-search=native={trimmed}");
+        }
+    }
+
+    if let Some(library) = query_python(
+        python,
+        "import sysconfig; print(sysconfig.get_config_var('LDLIBRARY') or '')",
+    ) {
+        let name = library.trim();
+        if let Some(stripped) = name.strip_prefix("lib") {
+            let stem = stripped
+                .strip_suffix(".so")
+                .or_else(|| stripped.strip_suffix(".a"))
+                .unwrap_or(stripped);
+            if !stem.is_empty() {
+                println!("cargo:rustc-link-lib={stem}");
+            }
+        }
+    }
+}
+
+fn query_python(python: &OsStr, command: &str) -> Option<String> {
+    let output = Command::new(python).arg("-c").arg(command).output().ok()?;
+    if !output.status.success() {
+        return None;
+    }
+    let value = String::from_utf8(output.stdout).ok()?;
+    Some(value)
+}
+
+fn prepare_confusion_table() -> io::Result<()> {
+    let manifest_dir = PathBuf::from(env::var("CARGO_MANIFEST_DIR").expect("missing manifest dir"));
+    let out_dir = PathBuf::from(env::var("OUT_DIR").expect("missing OUT_DIR"));
+
+    let repo_path = manifest_dir.join("../../src/glitchlings/zoo/ocr_confusions.tsv");
+    let packaged_path = manifest_dir.join("assets/ocr_confusions.tsv");
+    println!("cargo:rerun-if-changed={}", packaged_path.display());
+
+    let source_path = if repo_path.exists() {
+        println!("cargo:rerun-if-changed={}", repo_path.display());
+        if packaged_path.exists() {
+            let repo_bytes = fs::read(&repo_path)?;
+            let packaged_bytes = fs::read(&packaged_path)?;
+            if repo_bytes != packaged_bytes {
+                return Err(io::Error::new(
+                    ErrorKind::Other,
+                    format!(
+                        "OCR confusion table at {} is out of sync with {}",
+                        packaged_path.display(),
+                        repo_path.display()
+                    ),
+                ));
+            }
+        }
+        repo_path
+    } else {
+        if !packaged_path.exists() {
+            return Err(io::Error::new(
+                ErrorKind::NotFound,
+                format!(
+                    "missing OCR confusion table; looked for {} and {}",
+                    repo_path.display(),
+                    packaged_path.display()
+                ),
+            ));
+        }
+        packaged_path
+    };
+
+    fs::create_dir_all(&out_dir)?;
+    fs::copy(&source_path, out_dir.join("ocr_confusions.tsv"))?;
+    Ok(())
+}
+

{glitchlings-0.2.1 → glitchlings-0.2.3}/rust/zoo/src/glitch_ops.rs

@@ -500,6 +500,6 @@ mod tests {
         let mut rng = PyRng::new(1);
         let op = OcrArtifactsOp { error_rate: 1.0 };
         op.apply(&mut buffer, &mut rng).expect("ocr succeeds");
-        assert_eq!(buffer.to_string(), "Tlie rn m");
+        assert_eq!(buffer.to_string(), "Tlie rn rri");
     }
 }

{glitchlings-0.2.1 → glitchlings-0.2.3}/rust/zoo/src/lib.rs

@@ -3,6 +3,7 @@ mod pipeline;
 mod resources;
 mod rng;
 mod text_buffer;
+mod typogre;
 
 use glitch_ops::{GlitchOp, GlitchRng};
 use pyo3::prelude::*;
@@ -17,7 +18,6 @@ pub use glitch_ops::{
 pub use pipeline::{derive_seed, GlitchDescriptor, Pipeline, PipelineError};
 pub use rng::{PyRng, PyRngError};
 pub use text_buffer::{SegmentKind, TextBuffer, TextBufferError, TextSegment, TextSpan};
-
 struct PythonRngAdapter<'py> {
     rng: Bound<'py, PyAny>,
 }
@@ -279,5 +279,6 @@ fn _zoo_rust(_py: Python, m: &Bound<'_, PyModule>) -> PyResult<()> {
     m.add_function(wrap_pyfunction!(ocr_artifacts, m)?)?;
     m.add_function(wrap_pyfunction!(redact_words, m)?)?;
     m.add_function(wrap_pyfunction!(compose_glitchlings, m)?)?;
+    m.add_function(wrap_pyfunction!(typogre::fatfinger, m)?)?;
     Ok(())
 }