glitchlings 0.4.2__tar.gz → 0.4.3__tar.gz

{glitchlings-0.4.2 → glitchlings-0.4.3}/MANIFEST.in

@@ -1,5 +1,5 @@
 recursive-include rust *.rs *.toml *.lock *.tsv
-recursive-include src/glitchlings/zoo *.tsv
+recursive-include src/glitchlings/zoo *.tsv *.json
 recursive-include src/glitchlings/lexicon/data *.json
 include src/glitchlings/config.toml
 prune rust/target

{glitchlings-0.4.2 → glitchlings-0.4.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: glitchlings
-Version: 0.4.2
+Version: 0.4.3
 Summary: Monsters for your language games.
 Author: osoleve
 License:                                  Apache License
@@ -226,15 +226,37 @@ 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: all
+Requires-Dist: black>=24.4.0; 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<=2.0,>=1.24; extra == "all"
+Requires-Dist: pre-commit>=3.8.0; extra == "all"
+Requires-Dist: pytest>=8.0.0; extra == "all"
+Requires-Dist: ruff>=0.6.0; extra == "all"
+Requires-Dist: verifiers>=0.1.3.post0; extra == "all"
 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: 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: st
+Requires-Dist: sentence-transformers>=3.0.0; extra == "st"
 Provides-Extra: prime
 Requires-Dist: verifiers>=0.1.3.post0; 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: hypothesis>=6.140.0; extra == "dev"
@@ -307,7 +329,7 @@ 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.
 
 Consult the [Glitchlings Usage Guide](docs/index.md)
-for end-to-end instructions spanning the Python API, CLI, HuggingFace and Prime Intellect
+for end-to-end instructions spanning the Python API, CLI, HuggingFace, PyTorch, and Prime Intellect
 integrations, and the autodetected Rust pipeline (enabled whenever the extension is present).
 
 ## Motivation
@@ -356,6 +378,7 @@ glitchlings --list
 
 ```text
    Typogre — scope: Character, order: early
+Apostrofae — scope: Character, order: normal
      Mim1c — scope: Character, order: last
   Jargoyle — scope: Word, order: normal
      Adjax — scope: Word, order: normal
@@ -458,6 +481,16 @@ _What a nice word, would be a shame if something happened to it._
 > - `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).
 
+### Apostrofae
+
+_It looks like you're trying to paste some text. Can I help?_
+
+> _**Paperclip Manager.**_ Apostrofae scans for balanced runs of straight quotes, apostrophes, and backticks before replacing them with randomly sampled smart-quote pairs from a curated lookup table. The swap happens in-place so contractions and unpaired glyphs remain untouched.
+>
+> Args
+>
+> - `seed (int)`: Optional seed controlling the deterministic smart-quote sampling (default: 151).
+
 ### Mim1c
 
 _Wait, was that...?_

{glitchlings-0.4.2 → glitchlings-0.4.3}/README.md

@@ -54,7 +54,7 @@ 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.
 
 Consult the [Glitchlings Usage Guide](docs/index.md)
-for end-to-end instructions spanning the Python API, CLI, HuggingFace and Prime Intellect
+for end-to-end instructions spanning the Python API, CLI, HuggingFace, PyTorch, and Prime Intellect
 integrations, and the autodetected Rust pipeline (enabled whenever the extension is present).
 
 ## Motivation
@@ -103,6 +103,7 @@ glitchlings --list
 
 ```text
    Typogre — scope: Character, order: early
+Apostrofae — scope: Character, order: normal
      Mim1c — scope: Character, order: last
   Jargoyle — scope: Word, order: normal
      Adjax — scope: Word, order: normal
@@ -205,6 +206,16 @@ _What a nice word, would be a shame if something happened to it._
 > - `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).
 
+### Apostrofae
+
+_It looks like you're trying to paste some text. Can I help?_
+
+> _**Paperclip Manager.**_ Apostrofae scans for balanced runs of straight quotes, apostrophes, and backticks before replacing them with randomly sampled smart-quote pairs from a curated lookup table. The swap happens in-place so contractions and unpaired glyphs remain untouched.
+>
+> Args
+>
+> - `seed (int)`: Optional seed controlling the deterministic smart-quote sampling (default: 151).
+
 ### Mim1c
 
 _Wait, was that...?_

{glitchlings-0.4.2 → glitchlings-0.4.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "glitchlings"
-version = "0.4.2"
+version = "0.4.3"
 description = "Monsters for your language games."
 readme = "README.md"
 requires-python = ">=3.10"
@@ -49,9 +49,29 @@ Changelog = "https://github.com/osoleve/glitchlings/releases"
 glitchlings = "glitchlings.main:main"
 
 [project.optional-dependencies]
+all = [
+    "black>=24.4.0",
+    "hypothesis>=6.140.0",
+    "interrogate>=1.5.0",
+    "jellyfish>=1.2.0",
+    "isort>=5.13.0",
+    "mkdocs>=1.6.0",
+    "mkdocs-material>=9.5.0",
+    "mkdocstrings[python]>=0.24.0",
+    "mkdocstrings-python>=1.10.0",
+    "mypy>=1.8.0",
+    "numpy>=1.24,<=2.0",
+    "pre-commit>=3.8.0",
+    "pytest>=8.0.0",
+    "ruff>=0.6.0",
+    "verifiers>=0.1.3.post0",
+]
 hf = ["datasets>=4.0.0"]
+lightning = ["pytorch_lightning>=2.0.0"]
 vectors = ["numpy>=1.24,<=2.0", "spacy>=3.7.2", "gensim>=4.3.2"]
+st = ["sentence-transformers>=3.0.0"]
 prime = ["verifiers>=0.1.3.post0", "jellyfish>=1.2.0"]
+torch = ["torch>=2.0.0"]
 dev = [
     "pytest>=8.0.0",
     "hypothesis>=6.140.0",
@@ -80,6 +100,7 @@ include-package-data = true
 "glitchlings" = ["config.toml"]
 "glitchlings.lexicon" = ["data/*.json"]
 "glitchlings.zoo" = ["ocr_confusions.tsv"]
+"glitchlings.zoo.assets" = ["apostrofae_pairs.json"]
 
 [tool.setuptools.packages.find]
 where = ["src"]
@@ -151,10 +172,15 @@ module = [
     "glitchlings.config",
     "glitchlings.lexicon",
     "glitchlings.lexicon.*",
-    "glitchlings.zoo",
-    "glitchlings.zoo.*",
+]
+strict = true
+
+[[tool.mypy.overrides]]
+module = [
     "glitchlings.main",
     "glitchlings.__main__",
     "glitchlings.__init__",
+    "glitchlings.zoo",
+    "glitchlings.zoo.*",
 ]
-ignore_errors = true
+strict = true

{glitchlings-0.4.2 → glitchlings-0.4.3}/rust/Cargo.lock

@@ -90,6 +90,12 @@ version = "2.0.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f4c7245a08504955605670dbf141fceab975f15ca21570696aebe9d2e71576bd"
 
+[[package]]
+name = "itoa"
+version = "1.0.15"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4a5f13b858c8d314ee3e8f639011f7ccefe71f97f96e50151fb991f267928e2c"
+
 [[package]]
 name = "libc"
 version = "0.2.176"
@@ -275,12 +281,60 @@ version = "0.8.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "caf4aa5b0f434c91fe5c7f1ecb6a5ece2130b02ad2a590589dda5146df959001"
 
+[[package]]
+name = "ryu"
+version = "1.0.20"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "28d3b2b1366ec20994f1fd18c3c594f05c5dd4bc44d8bb0c1c632c8d6829481f"
+
 [[package]]
 name = "scopeguard"
 version = "1.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "94143f37725109f92c262ed2cf5e59bce7498c01bcc1502d7b9afe439a4e9f49"
 
+[[package]]
+name = "serde"
+version = "1.0.228"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9a8e94ea7f378bd32cbbd37198a4a91436180c5bb472411e48b5ec2e2124ae9e"
+dependencies = [
+ "serde_core",
+]
+
+[[package]]
+name = "serde_core"
+version = "1.0.228"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "41d385c7d4ca58e59fc732af25c3983b67ac852c1a25000afe1175de458b67ad"
+dependencies = [
+ "serde_derive",
+]
+
+[[package]]
+name = "serde_derive"
+version = "1.0.228"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d540f220d3187173da220f885ab66608367b6574e925011a9353e4badda91d79"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "serde_json"
+version = "1.0.145"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "402a6f66d8c709116cf22f558eab210f5a50187f702eb4d7e5ef38d9a7f1c79c"
+dependencies = [
+ "itoa",
+ "memchr",
+ "ryu",
+ "serde",
+ "serde_core",
+]
+
 [[package]]
 name = "smallvec"
 version = "1.15.1"
@@ -407,5 +461,6 @@ dependencies = [
  "pyo3",
  "pyo3-build-config",
  "regex",
+ "serde_json",
  "smallvec",
 ]

{glitchlings-0.4.2 → glitchlings-0.4.3}/rust/zoo/Cargo.toml

@@ -14,6 +14,7 @@ regex = { workspace = true }
 once_cell = { workspace = true }
 blake2 = { workspace = true }
 smallvec = "1"
+serde_json = "1"
 
 [package.metadata.maturin]
 module-name = "glitchlings._zoo_rust"

{glitchlings-0.4.2 → glitchlings-0.4.3}/rust/zoo/build.rs

@@ -6,7 +6,9 @@ use std::path::PathBuf;
 use std::process::Command;
 
 fn main() {
-    prepare_confusion_table().expect("failed to stage OCR confusion table for compilation");
+    stage_asset("ocr_confusions.tsv").expect("failed to stage OCR confusion table for compilation");
+    stage_asset("apostrofae_pairs.json")
+        .expect("failed to stage Apostrofae replacement table for compilation");
     pyo3_build_config::add_extension_module_link_args();
 
     // Only perform custom Python linking on non-Linux platforms.
@@ -97,46 +99,60 @@ fn query_python(python: &OsStr, command: &str) -> Option<String> {
     Some(value)
 }
 
-fn prepare_confusion_table() -> io::Result<()> {
+fn stage_asset(asset_name: &str) -> 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");
+    let repo_candidates = [
+        manifest_dir
+            .join("../../src/glitchlings/zoo/assets")
+            .join(asset_name),
+        manifest_dir
+            .join("../../src/glitchlings/zoo")
+            .join(asset_name),
+    ];
+    let packaged_path = manifest_dir.join("assets").join(asset_name);
     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()
-                    ),
-                ));
+    let mut source_path: Option<PathBuf> = None;
+    for candidate in &repo_candidates {
+        if candidate.exists() {
+            println!("cargo:rerun-if-changed={}", candidate.display());
+            if packaged_path.exists() {
+                let repo_bytes = fs::read(candidate)?;
+                let packaged_bytes = fs::read(&packaged_path)?;
+                if repo_bytes != packaged_bytes {
+                    return Err(io::Error::new(
+                        ErrorKind::Other,
+                        format!(
+                            "asset {} is out of sync with {}",
+                            packaged_path.display(),
+                            candidate.display()
+                        ),
+                    ));
+                }
             }
+            source_path = Some(candidate.clone());
+            break;
         }
-        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()
-                ),
-            ));
-        }
+    }
+
+    let source_path = if let Some(path) = source_path {
+        path
+    } else if packaged_path.exists() {
         packaged_path
+    } else {
+        return Err(io::Error::new(
+            ErrorKind::NotFound,
+            format!(
+                "missing asset {asset_name}; looked for {} and {}",
+                repo_candidates[0].display(),
+                packaged_path.display()
+            ),
+        ));
     };
 
     fs::create_dir_all(&out_dir)?;
-    fs::copy(&source_path, out_dir.join("ocr_confusions.tsv"))?;
+    fs::copy(&source_path, out_dir.join(asset_name))?;
     Ok(())
 }

{glitchlings-0.4.2 → glitchlings-0.4.3}/rust/zoo/src/glitch_ops.rs

@@ -6,8 +6,8 @@ use std::collections::HashMap;
 use std::sync::{Mutex, OnceLock};
 
 use crate::resources::{
-    affix_bounds, confusion_table, is_whitespace_only, split_affixes, MULTIPLE_WHITESPACE,
-    SPACE_BEFORE_PUNCTUATION,
+    affix_bounds, apostrofae_pairs, confusion_table, is_whitespace_only, split_affixes,
+    MULTIPLE_WHITESPACE, SPACE_BEFORE_PUNCTUATION,
 };
 use crate::rng::{PyRng, PyRngError};
 use crate::text_buffer::{SegmentKind, TextBuffer, TextBufferError};
@@ -988,6 +988,156 @@ impl GlitchOp for TypoOp {
     }
 }
 
+#[derive(Clone, Copy, Debug)]
+enum QuoteKind {
+    Double,
+    Single,
+    Backtick,
+}
+
+impl QuoteKind {
+    fn from_char(ch: char) -> Option<Self> {
+        match ch {
+            '"' => Some(Self::Double),
+            '\'' => Some(Self::Single),
+            '`' => Some(Self::Backtick),
+            _ => None,
+        }
+    }
+
+    fn as_char(self) -> char {
+        match self {
+            Self::Double => '"',
+            Self::Single => '\'',
+            Self::Backtick => '`',
+        }
+    }
+
+    fn index(self) -> usize {
+        match self {
+            Self::Double => 0,
+            Self::Single => 1,
+            Self::Backtick => 2,
+        }
+    }
+}
+
+#[derive(Debug, Clone, Copy)]
+struct QuotePair {
+    start: usize,
+    end: usize,
+    kind: QuoteKind,
+}
+
+#[derive(Debug)]
+struct Replacement {
+    start: usize,
+    end: usize,
+    value: String,
+}
+
+#[derive(Debug, Default, Clone, Copy)]
+pub struct QuotePairsOp;
+
+impl QuotePairsOp {
+    fn collect_pairs(text: &str) -> Vec<QuotePair> {
+        let mut pairs: Vec<QuotePair> = Vec::new();
+        let mut stack: [Option<usize>; 3] = [None, None, None];
+
+        for (idx, ch) in text.char_indices() {
+            if let Some(kind) = QuoteKind::from_char(ch) {
+                let slot = kind.index();
+                if let Some(start) = stack[slot] {
+                    pairs.push(QuotePair {
+                        start,
+                        end: idx,
+                        kind,
+                    });
+                    stack[slot] = None;
+                } else {
+                    stack[slot] = Some(idx);
+                }
+            }
+        }
+
+        pairs
+    }
+}
+
+impl GlitchOp for QuotePairsOp {
+    fn apply(&self, buffer: &mut TextBuffer, rng: &mut dyn GlitchRng) -> Result<(), GlitchOpError> {
+        let text = buffer.to_string();
+        if text.is_empty() {
+            return Ok(());
+        }
+
+        let pairs = Self::collect_pairs(&text);
+        if pairs.is_empty() {
+            return Ok(());
+        }
+
+        let table = apostrofae_pairs();
+        if table.is_empty() {
+            return Ok(());
+        }
+
+        let mut replacements: Vec<Replacement> = Vec::with_capacity(pairs.len() * 2);
+
+        for pair in pairs {
+            let key = pair.kind.as_char();
+            let Some(options) = table.get(&key) else {
+                continue;
+            };
+            if options.is_empty() {
+                continue;
+            }
+            let choice = rng.rand_index(options.len())?;
+            let (left, right) = &options[choice];
+            let glyph_len = pair.kind.as_char().len_utf8();
+            replacements.push(Replacement {
+                start: pair.start,
+                end: pair.start + glyph_len,
+                value: left.clone(),
+            });
+            replacements.push(Replacement {
+                start: pair.end,
+                end: pair.end + glyph_len,
+                value: right.clone(),
+            });
+        }
+
+        if replacements.is_empty() {
+            return Ok(());
+        }
+
+        replacements.sort_by_key(|replacement| replacement.start);
+        let mut extra_capacity = 0usize;
+        for replacement in &replacements {
+            let span = replacement.end - replacement.start;
+            if replacement.value.len() > span {
+                extra_capacity += replacement.value.len() - span;
+            }
+        }
+
+        let mut result = String::with_capacity(text.len() + extra_capacity);
+        let mut cursor = 0usize;
+
+        for replacement in replacements {
+            if cursor < replacement.start {
+                result.push_str(&text[cursor..replacement.start]);
+            }
+            result.push_str(&replacement.value);
+            cursor = replacement.end;
+        }
+        if cursor < text.len() {
+            result.push_str(&text[cursor..]);
+        }
+
+        *buffer = TextBuffer::from_owned(result);
+        Ok(())
+    }
+}
+
 /// Type-erased glitchling operation for pipeline sequencing.
 #[derive(Debug, Clone)]
 pub enum GlitchOperation {
@@ -998,6 +1148,7 @@ pub enum GlitchOperation {
     Ocr(OcrArtifactsOp),
     Typo(TypoOp),
     ZeroWidth(ZeroWidthOp),
+    QuotePairs(QuotePairsOp),
 }
 
 impl GlitchOp for GlitchOperation {
@@ -1010,6 +1161,7 @@ impl GlitchOp for GlitchOperation {
             GlitchOperation::Ocr(op) => op.apply(buffer, rng),
             GlitchOperation::Typo(op) => op.apply(buffer, rng),
             GlitchOperation::ZeroWidth(op) => op.apply(buffer, rng),
+            GlitchOperation::QuotePairs(op) => op.apply(buffer, rng),
         }
     }
 }

{glitchlings-0.4.2 → glitchlings-0.4.3}/rust/zoo/src/lib.rs

@@ -15,8 +15,8 @@ use std::collections::HashMap;
 use std::sync::{Arc, OnceLock, RwLock};
 
 pub use glitch_ops::{
-    DeleteRandomWordsOp, GlitchOpError, GlitchOperation, OcrArtifactsOp, RedactWordsOp,
-    ReduplicateWordsOp, SwapAdjacentWordsOp, TypoOp, ZeroWidthOp,
+    DeleteRandomWordsOp, GlitchOpError, GlitchOperation, OcrArtifactsOp, QuotePairsOp,
+    RedactWordsOp, ReduplicateWordsOp, SwapAdjacentWordsOp, TypoOp, ZeroWidthOp,
 };
 pub use pipeline::{derive_seed, GlitchDescriptor, Pipeline, PipelineError};
 pub use rng::{PyRng, PyRngError};
@@ -193,6 +193,7 @@ enum PyGlitchOperation {
         rate: f64,
         characters: Vec<String>,
     },
+    QuotePairs,
 }
 
 impl<'py> FromPyObject<'py> for PyGlitchOperation {
@@ -308,6 +309,7 @@ impl<'py> FromPyObject<'py> for PyGlitchOperation {
                     .unwrap_or_default();
                 Ok(PyGlitchOperation::ZeroWidth { rate, characters })
             }
+            "apostrofae" | "quote_pairs" => Ok(PyGlitchOperation::QuotePairs),
             other => Err(PyValueError::new_err(format!(
                 "unsupported operation type: {other}"
             ))),
@@ -363,6 +365,12 @@ fn swap_adjacent_words(text: &str, swap_rate: f64, rng: &Bound<'_, PyAny>) -> Py
     apply_operation(text, op, rng).map_err(glitch_ops::GlitchOpError::into_pyerr)
 }
 
+#[pyfunction]
+fn apostrofae(text: &str, rng: &Bound<'_, PyAny>) -> PyResult<String> {
+    let op = QuotePairsOp::default();
+    apply_operation(text, op, rng).map_err(glitch_ops::GlitchOpError::into_pyerr)
+}
+
 #[pyfunction]
 fn ocr_artifacts(text: &str, error_rate: f64, rng: &Bound<'_, PyAny>) -> PyResult<String> {
     let op = OcrArtifactsOp { error_rate };
@@ -463,6 +471,9 @@ fn compose_glitchlings(
                 PyGlitchOperation::ZeroWidth { rate, characters } => {
                     GlitchOperation::ZeroWidth(glitch_ops::ZeroWidthOp { rate, characters })
                 }
+                PyGlitchOperation::QuotePairs => {
+                    GlitchOperation::QuotePairs(glitch_ops::QuotePairsOp::default())
+                }
             };
             Ok(GlitchDescriptor {
                 name: descriptor.name,
@@ -481,6 +492,7 @@ fn _zoo_rust(_py: Python, m: &Bound<'_, PyModule>) -> PyResult<()> {
     m.add_function(wrap_pyfunction!(reduplicate_words, m)?)?;
     m.add_function(wrap_pyfunction!(delete_random_words, m)?)?;
     m.add_function(wrap_pyfunction!(swap_adjacent_words, m)?)?;
+    m.add_function(wrap_pyfunction!(apostrofae, m)?)?;
     m.add_function(wrap_pyfunction!(ocr_artifacts, m)?)?;
     m.add_function(wrap_pyfunction!(redact_words, m)?)?;
     m.add_function(wrap_pyfunction!(plan_glitchlings, m)?)?;

{glitchlings-0.4.2 → glitchlings-0.4.3}/rust/zoo/src/resources.rs

@@ -1,5 +1,8 @@
 use once_cell::sync::Lazy;
 use regex::Regex;
+use std::collections::HashMap;
+
+const RAW_APOSTROFAE_PAIRS: &str = include_str!(concat!(env!("OUT_DIR"), "/apostrofae_pairs.json"));
 
 const RAW_OCR_CONFUSIONS: &str = include_str!(concat!(env!("OUT_DIR"), "/ocr_confusions.tsv"));
 
@@ -11,6 +14,23 @@ pub static SPACE_BEFORE_PUNCTUATION: Lazy<Regex> =
 pub static MULTIPLE_WHITESPACE: Lazy<Regex> =
     Lazy::new(|| Regex::new(r"\s{2,}").expect("valid multi-whitespace regex"));
 
+/// Replacement pairs used by the Apostrofae glitchling.
+pub static APOSTROFAE_PAIR_TABLE: Lazy<HashMap<char, Vec<(String, String)>>> = Lazy::new(|| {
+    let raw: HashMap<String, Vec<[String; 2]>> = serde_json::from_str(RAW_APOSTROFAE_PAIRS)
+        .expect("apostrofae pair table should be valid JSON");
+    let mut table: HashMap<char, Vec<(String, String)>> = HashMap::new();
+    for (key, pairs) in raw {
+        if let Some(ch) = key.chars().next() {
+            let entries: Vec<(String, String)> = pairs
+                .into_iter()
+                .map(|pair| (pair[0].to_string(), pair[1].to_string()))
+                .collect();
+            table.insert(ch, entries);
+        }
+    }
+    table
+});
+
 /// Sorted confusion pairs reused by glitchling implementations.
 pub static OCR_CONFUSION_TABLE: Lazy<Vec<(&'static str, &'static [&'static str])>> =
     Lazy::new(|| {
@@ -50,6 +70,11 @@ pub fn confusion_table() -> &'static [(&'static str, &'static [&'static str])] {
     OCR_CONFUSION_TABLE.as_slice()
 }
 
+/// Returns the Apostrofae replacement pairs keyed by the straight glyph.
+pub fn apostrofae_pairs() -> &'static HashMap<char, Vec<(String, String)>> {
+    &APOSTROFAE_PAIR_TABLE
+}
+
 #[inline]
 pub fn is_whitespace_only(s: &str) -> bool {
     s.chars().all(char::is_whitespace)
@@ -126,7 +151,7 @@ pub fn split_affixes(word: &str) -> (String, String, String) {
 
 #[cfg(test)]
 mod tests {
-    use super::{confusion_table, split_affixes, split_with_separators};
+    use super::{apostrofae_pairs, confusion_table, split_affixes, split_with_separators};
 
     #[test]
     fn split_with_separators_matches_expected_boundaries() {
@@ -162,4 +187,13 @@ mod tests {
             a_src.len() >= b_src.len()
         }));
     }
+
+    #[test]
+    fn apostrofae_pairs_loaded_from_asset() {
+        let table = apostrofae_pairs();
+        assert!(table.contains_key(&'"'));
+        assert!(table.contains_key(&'\''));
+        assert!(table.contains_key(&'`'));
+        assert!(table.values().all(|entries| !entries.is_empty()));
+    }
 }