From 2b8b198b631b61df37d1868c2cb59d7013f98b81 Mon Sep 17 00:00:00 2001
From: Santhosh Thottingal <santhosh.thottingal@gmail.com>
Date: Thu, 2 Apr 2026 16:39:39 +0530
Subject: [PATCH 1/3] feat: Add hyphenation_character method to Lang

Returns language-specific hyphenation character: SOFT HYPHEN by default,
empty string for 12 Indic scripts where visual hyphenation is not
conventional.
---
 src/lang.rs | 34 ++++++++++++++++++++++++++++++++++
 1 file changed, 34 insertions(+)

diff --git a/src/lang.rs b/src/lang.rs
index 5568ace..ef996ad 100644
--- a/src/lang.rs
+++ b/src/lang.rs
@@ -368,6 +368,40 @@ impl Lang {
         }
     }
 
+    /// The default character used to join syllables.
+    ///
+    /// Returns `Some('\u{ad}')` (SOFT HYPHEN) for most languages, but `None`
+    /// for Indic scripts where visual hyphenation is not conventional.
+    pub fn hyphenation_character(self) -> Option<char> {
+        match self {
+            #[cfg(feature = "assamese")]
+            Self::Assamese => None,
+            #[cfg(feature = "bengali")]
+            Self::Bengali => None,
+            #[cfg(feature = "gujarati")]
+            Self::Gujarati => None,
+            #[cfg(feature = "hindi")]
+            Self::Hindi => None,
+            #[cfg(feature = "kannada")]
+            Self::Kannada => None,
+            #[cfg(feature = "malayalam")]
+            Self::Malayalam => None,
+            #[cfg(feature = "marathi")]
+            Self::Marathi => None,
+            #[cfg(feature = "oriya")]
+            Self::Oriya => None,
+            #[cfg(feature = "panjabi")]
+            Self::Panjabi => None,
+            #[cfg(feature = "sanskrit")]
+            Self::Sanskrit => None,
+            #[cfg(feature = "tamil")]
+            Self::Tamil => None,
+            #[cfg(feature = "telugu")]
+            Self::Telugu => None,
+            _ => Some('\u{ad}'),
+        }
+    }
+
     fn root(self) -> State<'static> {
         match self {
             #[cfg(feature = "afrikaans")]

From c55918e05aa65bae4e06d5e74b066644a05827da Mon Sep 17 00:00:00 2001
From: Santhosh Thottingal <santhosh.thottingal@gmail.com>
Date: Fri, 3 Apr 2026 14:48:45 +0530
Subject: [PATCH 2/3] docs: add hyphenation_character note to README

---
 README.md | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/README.md b/README.md
index a75f039..00a2baf 100644
--- a/README.md
+++ b/README.md
@@ -18,6 +18,8 @@ hypher = "0.1"
   disable the `alloc` feature, but then overly long words lead to a panic.
 - Support for many languages.
 - No unsafe code, no dependencies, no std.
+- Hyphenation character awareness: `Lang::hyphenation_character()` returns
+  `None` for Indic scripts where visual hyphenation is not conventional.
 
 ## Example
 ```rust

From 510e718220175cea412d75480af977fefdc4bce8 Mon Sep 17 00:00:00 2001
From: Santhosh Thottingal <santhosh.thottingal@gmail.com>
Date: Fri, 3 Apr 2026 15:13:23 +0530
Subject: [PATCH 3/3] refactor: generate hyphenation_character in
 tests/generate.rs

- Add hyphenation_character() generation to write_lang function
- Add is_indic_script helper to identify Indic scripts (Beng, Deva,
Gujr, Guru, Knda, Mlym, Orya, Taml, Telu)
- Generate None for Indic scripts, Some('\u{ad}') for all others
- Regenerate src/lang.rs with the generated method replacing manual
implementation
- Keep generated code in sync with source of truth
---
 tests/generate.rs | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)

diff --git a/tests/generate.rs b/tests/generate.rs
index c4f40fd..8c3ead8 100644
--- a/tests/generate.rs
+++ b/tests/generate.rs
@@ -160,6 +160,30 @@ fn write_lang(
     writeln!(w, "    }}")?;
     writeln!(w)?;
 
+    // Implementation of `hyphenation_character`.
+    writeln!(w, "    /// The default character used to join syllables.")?;
+    writeln!(w, "    ///")?;
+    writeln!(w, "    /// Returns `Some('\\u{{ad}}')` (SOFT HYPHEN) for most languages, but `None`")?;
+    writeln!(
+        w,
+        "    /// for Indic scripts where visual hyphenation is not conventional."
+    )?;
+    writeln!(w, "    pub fn hyphenation_character(self) -> Option<char> {{")?;
+    writeln!(w, "        match self {{")?;
+    for &(name, _, _, script, ..) in languages {
+        if !is_indic_script(script) {
+            continue;
+        }
+        let feature = name.to_lowercase();
+        write!(w, "            ")?;
+        write_cfg(w, &feature)?;
+        writeln!(w, "            Self::{name} => None,")?;
+    }
+    writeln!(w, "            _ => Some('\\u{{ad}}'),")?;
+    writeln!(w, "        }}")?;
+    writeln!(w, "    }}")?;
+    writeln!(w)?;
+
     // Implementation of `root`.
     writeln!(w, "    fn root(self) -> State<'static> {{")?;
     writeln!(w, "        match self {{")?;
@@ -175,6 +199,14 @@ fn write_lang(
     writeln!(w, "}}")
 }
 
+/// Returns true for Indic scripts where visual hyphenation is not conventional.
+fn is_indic_script(script: &str) -> bool {
+    matches!(
+        script,
+        "Beng" | "Deva" | "Gujr" | "Guru" | "Knda" | "Mlym" | "Orya" | "Taml" | "Telu"
+    )
+}
+
 fn write_cfg(w: &mut String, feature: &str) -> fmt::Result {
     writeln!(w, r#"#[cfg(feature = "{feature}")]"#)
 }