basic python binding

.gitignore

@@ -1,13 +1,64 @@
+# Archive
+**.7z
+**.bz2
+**.gz
+**.gzip
+**.jar
+**.lz4
+**.lzma
+**.pak
+**.rar
+**.tar
+**.tbz2
+**.tgz
+**.tlz
+**.txz
+**.xz
+**.zip
+**.zst
+
 # Artifacts
+**.buildlog/
+**.class
 **.dart_tool/
 **.flutter*
-**.ipynb_checkpoints/
+**.flutter-plugins
+**.flutter-plugins-dependencies
+**.history
+**.iml
+**.ipr
+**.iws
+**.lock
+**.o
+**.pub-cache/
+**.pub/
 **.pyc
-**__pycache__/
-**build/
+**.so
+**/.dSYM/
+**/.dart_tool/
+**/.idea/
+**/.ipynb_checkpoints/
+**/__pycache__/
+**/android/app/debug/
+**/android/app/profile/
+**/android/app/release/
+**/app.*.map.json
+**/app.*.symbols
+**/build/
+**/doc/api/
+**/ios/Flutter/.last_build_id
+**/migrate_working_dir/
+**/node_modules/
+**/package-lock.json
+**/target/
+**/venv/
+
+# Audio
+**.wav
 
 # Auxiliary files
 **.bak
+**.swp
 **.tmp
 
 # Databases
@@ -17,6 +68,7 @@
 # Documents
 **.csv
 **.doc*
+**.html
 **.pdf
 **.ppt*
 **.txt
@@ -72,20 +124,20 @@
 **.dvi
 **.fdb_latexmk
 **.fls
-**.gz
 **.lof
 **.log
 **.lot
 **.out
 **.pdf
+**.run.xml
 **.synctex.gz
 **.toc
 **.xcp
 **.xdv
-**.xml
 **blx.bib
 **comment.cut
 
-# Specific
-**.lock
-/target
+# Video
+**.mkv
+**.mov
+**.mp4

.python-version

@@ -0,0 +1 @@
+3.12.2

Cargo.toml

@@ -8,9 +8,16 @@ repository = "https://github.com/SichangHe/fmtt"
 
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 
+[lib]
+name = "fmtt"
+crate-type = ["cdylib", "lib"]
+
 [dependencies]
 anyhow = "1"
 clap = { version = "4", features = ["derive"] }
+pyo3 = { version = "0.21", features = [
+    "experimental-declarative-modules",
+], optional = true }
 regex = "1"
 tracing = { version = "0.1", default_features = false }
 tracing-subscriber = { version = "0.3", default_features = false, features = [
@@ -22,6 +29,10 @@ tracing-subscriber = { version = "0.3", default_features = false, features = [
 [dev-dependencies]
 insta = "1.39"
 
+[features]
+default = []
+py = ["dep:pyo3"]
+
 [profile.release]
 opt-level = "s"
 lto = true

pyproject.toml

@@ -0,0 +1,23 @@
+[project]
+name = "fmtt"
+version = "0.5.0"
+description = "Python binding for ForMaT Text (FMTT)"
+authors = [
+    { name = "Steven Hé (Sīchàng)", email = "[email protected]" },
+]
+dependencies = []
+readme = "README.md"
+requires-python = ">= 3.8"
+
+[build-system]
+requires = ["maturin>=1.2,<2.0"]
+build-backend = "maturin"
+
+[tool.rye]
+managed = true
+dev-dependencies = []
+
+[tool.maturin]
+python-source = "python"
+module-name = "fmtt._lowlevel"
+features = ["pyo3/extension-module", "py"]

python/fmtt/__init__.py

@@ -0,0 +1,3 @@
+from fmtt._lowlevel import format
+
+__all__ = ["format"]

src/lib.rs

@@ -27,5 +27,53 @@ pub fn format<'a>(
     result
 }
 
+#[cfg(feature = "py")]
+#[pyo3::pymodule]
+mod _lowlevel {
+    use pyo3::{exceptions::PyValueError, prelude::*};
+
+    use super::*;
+
+    /// Format text diff-friendly by breaking lines of sensible punctuations and
+    /// words.
+    ///
+    /// See <https://github.com/SichangHe/fmtt> for the options.
+    #[pyfunction]
+    #[pyo3(signature = (
+        text,
+        line_width=80,
+        allow_indented_paragraphs=false,
+        single_line_starts=vec![],
+        multi_line_starts=vec![],
+        ignore_line_starts=vec![],
+    ))]
+    fn format(
+        text: &str,
+        line_width: usize,
+        allow_indented_paragraphs: bool,
+        single_line_starts: Vec<String>,
+        multi_line_starts: Vec<String>,
+        ignore_line_starts: Vec<String>,
+    ) -> PyResult<String> {
+        let paragraph_starts = ParagraphStarts::try_from_str_slices(
+            &borrowed_str_slice(&single_line_starts),
+            &borrowed_str_slice(&multi_line_starts),
+            &borrowed_str_slice(&ignore_line_starts),
+        )
+        .map_err(|why| PyValueError::new_err(format!("{why}")))?;
+        let formatted_words = super::format(
+            text,
+            line_width,
+            allow_indented_paragraphs,
+            &paragraph_starts,
+        );
+        Ok(formatted_words.join(""))
+    }
+
+    fn borrowed_str_slice(slice: &[String]) -> Vec<&str> {
+        slice.iter().map(String::as_str).collect()
+    }
+}
+
 #[cfg(test)]
 mod tests;