Sinhala and Tamil interface: draw with an installed font (part of #1688) (#1706)

Sinhala and Tamil file names showed as boxes on the home screen, in Recent
and in document tabs: no embedded face covers either script, and the
installed-font fallback did not look for one.

Add sinhala_fallback() and tamil_fallback(), each probing for its script's
letter ka, and end every interface family with them:
- macOS: Sinhala Sangam MN / Sinhala MN, Tamil Sangam MN / Tamil MN
- Windows: Nirmala UI, then Iskoola Pota (Sinhala) or Latha (Tamil)
- Linux: Noto Sans Sinhala / Noto Sans Tamil, Lohit Tamil

The faces are read at runtime, never embedded or shipped, and
PDFCRAFT_SYSTEM_FONTS=0 still turns them off.

Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

crates/ui-egui/src/system_fonts.rs

@@ -3,8 +3,8 @@
 //! The embedded faces (Inter, egui's defaults, craft-fonts) come first in every family; this one
 //! only draws characters none of them has, such as an Arabic file name in a build without
 //! craft-fonts, or the Simplified Chinese interface in a build without a `Hans` face (#826). A
-//! second and a third installed face, [`devanagari_fallback`] and [`telugu_fallback`], draw Hindi
-//! and Telugu when one is installed. It is
+//! few more installed faces, [`devanagari_fallback`], [`telugu_fallback`], [`sinhala_fallback`]
+//! and [`tamil_fallback`], draw Hindi, Telugu, Sinhala and Tamil when one is installed. It is
 //! read at runtime and never embedded or shipped (AGENTS.md §1.4), and `PDFCRAFT_SYSTEM_FONTS=0`
 //! turns it off (published screenshots do).
 
@@ -25,6 +25,10 @@ const PROBE: char = '\u{0627}';
 const DEVANAGARI_PROBE: char = '\u{0915}';
 /// Telugu letter ka: the face must have it to cover Telugu.
 const TELUGU_PROBE: char = '\u{0C15}';
+/// Sinhala letter ka (ක): the face must have it to cover Sinhala.
+const SINHALA_PROBE: char = '\u{0D9A}';
+/// Tamil letter ka (க): the face must have it to cover Tamil.
+const TAMIL_PROBE: char = '\u{0B95}';
 /// 欢 (U+6B22): Simplified only, absent from the Japanese craft-fonts faces.
 const HANS_PROBE: char = '\u{6B22}';
 /// 說 (U+8AAA): Traditional only, absent from the Japanese craft-fonts faces.
@@ -82,6 +86,20 @@ pub fn telugu_fallback() -> Option<Arc<FontData>> {
     CACHE.get_or_init(|| script_fallback(&telugu_candidates(), TELUGU_PROBE)).clone()
 }
 
+/// The installed fallback face for Sinhala, read once. `None` when it is turned off or no
+/// candidate is installed; the interface then draws what the embedded faces can.
+pub fn sinhala_fallback() -> Option<Arc<FontData>> {
+    static CACHE: OnceLock<Option<Arc<FontData>>> = OnceLock::new();
+    CACHE.get_or_init(|| script_fallback(&sinhala_candidates(), SINHALA_PROBE)).clone()
+}
+
+/// The installed fallback face for Tamil, read once. `None` when it is turned off or no
+/// candidate is installed; the interface then draws what the embedded faces can.
+pub fn tamil_fallback() -> Option<Arc<FontData>> {
+    static CACHE: OnceLock<Option<Arc<FontData>>> = OnceLock::new();
+    CACHE.get_or_init(|| script_fallback(&tamil_candidates(), TAMIL_PROBE)).clone()
+}
+
 fn script_fallback(candidates: &[PathBuf], probe: char) -> Option<Arc<FontData>> {
     if std::env::var_os("PDFCRAFT_SYSTEM_FONTS").is_some_and(|v| v == "0") {
         return None;
@@ -155,6 +173,57 @@ fn telugu_candidates() -> Vec<PathBuf> {
     }
 }
 
+/// Well-known locations of Sinhala faces, best first. Nirmala UI has Sinhala from Windows 10;
+/// Iskoola Pota is the older Windows Sinhala face.
+fn sinhala_candidates() -> Vec<PathBuf> {
+    if cfg!(windows) {
+        ["Nirmala.ttc", "Nirmala.ttf", "iskpota.ttf"].iter().map(|f| windows_fonts().join(f)).collect()
+    } else if cfg!(target_os = "macos") {
+        ["/System/Library/Fonts/Supplemental/Sinhala Sangam MN.ttc", "/System/Library/Fonts/Supplemental/Sinhala MN.ttc"]
+            .iter()
+            .map(PathBuf::from)
+            .collect()
+    } else {
+        unix_fonts(&[
+            "google-noto/NotoSansSinhalaUI-Regular.ttf",
+            "google-noto/NotoSansSinhala-Regular.ttf",
+            "google-noto-vf/NotoSansSinhala[wght].ttf",
+            "truetype/noto/NotoSansSinhala-Regular.ttf",
+            "truetype/noto/NotoSansSinhalaUI-Regular.ttf",
+            "noto/NotoSansSinhala-Regular.ttf",
+            "noto/NotoSansSinhalaUI-Regular.ttf",
+        ])
+    }
+}
+
+/// Well-known locations of Tamil faces, best first. Latha is the older Windows Tamil face.
+fn tamil_candidates() -> Vec<PathBuf> {
+    if cfg!(windows) {
+        ["Nirmala.ttc", "Nirmala.ttf", "latha.ttf"].iter().map(|f| windows_fonts().join(f)).collect()
+    } else if cfg!(target_os = "macos") {
+        [
+            "/System/Library/Fonts/Supplemental/Tamil Sangam MN.ttc",
+            "/System/Library/Fonts/Supplemental/Tamil MN.ttc",
+            "/Library/Fonts/Arial Unicode.ttf",
+        ]
+        .iter()
+        .map(PathBuf::from)
+        .collect()
+    } else {
+        unix_fonts(&[
+            "google-noto/NotoSansTamilUI-Regular.ttf",
+            "google-noto/NotoSansTamil-Regular.ttf",
+            "google-noto-vf/NotoSansTamil[wght].ttf",
+            "truetype/noto/NotoSansTamil-Regular.ttf",
+            "truetype/noto/NotoSansTamilUI-Regular.ttf",
+            "noto/NotoSansTamil-Regular.ttf",
+            "noto/NotoSansTamilUI-Regular.ttf",
+            "lohit-tamil-fonts/Lohit-Tamil.ttf",
+            "truetype/lohit-tamil/Lohit-Tamil.ttf",
+        ])
+    }
+}
+
 /// Well-known locations of faces with broad script coverage, best first.
 fn candidates(need: Need) -> Vec<PathBuf> {
     match need {
@@ -292,11 +361,13 @@ mod tests {
         assert!(script_fallback(&candidates, 'A').is_some());
         assert!(script_fallback(&candidates, TELUGU_PROBE).is_none());
         assert!(script_fallback(&candidates, DEVANAGARI_PROBE).is_none());
+        assert!(script_fallback(&candidates, SINHALA_PROBE).is_none());
+        assert!(script_fallback(&candidates, TAMIL_PROBE).is_none());
     }
 
     #[test]
     fn script_candidates_are_absolute_font_files() {
-        for list in [devanagari_candidates(), telugu_candidates()] {
+        for list in [devanagari_candidates(), telugu_candidates(), sinhala_candidates(), tamil_candidates()] {
             assert!(!list.is_empty());
             assert!(list.iter().all(|p| p.is_absolute() || cfg!(windows)), "{list:?}");
             assert!(list.iter().all(|p| p.extension().is_some_and(|e| e == "ttf" || e == "ttc")), "{list:?}");

crates/ui-egui/src/theme.rs

@@ -220,6 +220,10 @@ pub const SYSTEM_FALLBACK: &str = "system-fallback";
 pub const SYSTEM_DEVANAGARI_FALLBACK: &str = "system-devanagari-fallback";
 /// The name of the installed Telugu face [`installed_font_definitions`] may add.
 pub const SYSTEM_TELUGU_FALLBACK: &str = "system-telugu-fallback";
+/// The name of the installed Sinhala face [`installed_font_definitions`] may add.
+pub const SYSTEM_SINHALA_FALLBACK: &str = "system-sinhala-fallback";
+/// The name of the installed Tamil face [`installed_font_definitions`] may add.
+pub const SYSTEM_TAMIL_FALLBACK: &str = "system-tamil-fallback";
 
 /// What [`install_fonts_for`] installs: [`font_definitions_for`], then, on desktop, one face
 /// already installed on this machine. It only draws characters no embedded face has.
@@ -232,8 +236,9 @@ pub const SYSTEM_TELUGU_FALLBACK: &str = "system-telugu-fallback";
 /// - Otherwise it is the last fallback of every family (an Arabic file name in a build without
 ///   craft-fonts).
 ///
-/// An installed Devanagari face and an installed Telugu face, when there are, end every family
-/// just before that one, so Hindi and Telugu text draw in a build without such faces (#1531).
+/// Installed Devanagari, Telugu, Sinhala and Tamil faces, when there are, end every family just
+/// before that one, so Hindi, Telugu (#1531), Sinhala and Tamil (#1688) text, such as a file
+/// name, draws in a build without such faces.
 ///
 /// `PDFCRAFT_SYSTEM_FONTS=0` leaves them out.
 pub fn installed_font_definitions(cjk: CjkPreference) -> FontDefinitions {
@@ -246,6 +251,8 @@ pub fn installed_font_definitions(cjk: CjkPreference) -> FontDefinitions {
         for (name, data) in [
             (SYSTEM_DEVANAGARI_FALLBACK, crate::system_fonts::devanagari_fallback()),
             (SYSTEM_TELUGU_FALLBACK, crate::system_fonts::telugu_fallback()),
+            (SYSTEM_SINHALA_FALLBACK, crate::system_fonts::sinhala_fallback()),
+            (SYSTEM_TAMIL_FALLBACK, crate::system_fonts::tamil_fallback()),
         ] {
             let Some(data) = data else { continue };
             fonts.font_data.insert(name.to_owned(), data);

crates/ui-egui/tests/fonts.rs

@@ -193,6 +193,32 @@ fn system_fallback_covers_telugu() {
     assert!(layout_widths(&mut fonts, TELUGU).iter().all(|w| w.is_finite() && *w > 0.0));
 }
 
+/// On a machine with installed Sinhala and Tamil fonts, the installed definitions include them
+/// and Sinhala and Tamil text, such as a file name, has glyphs instead of boxes (#1688). macOS
+/// always ships Sinhala Sangam MN and Tamil Sangam MN, so there the test never skips.
+#[test]
+fn system_fallback_covers_sinhala_and_tamil() {
+    for (name, text) in [(theme::SYSTEM_SINHALA_FALLBACK, "ශ්‍රී ලංකා ගොනුව"), (theme::SYSTEM_TAMIL_FALLBACK, "தமிழ் கோப்பு")]
+    {
+        assert!(!theme::font_definitions().font_data.contains_key(name));
+        let defs = theme::installed_font_definitions(theme::CjkPreference::Default);
+        let off = std::env::var_os("PDFCRAFT_SYSTEM_FONTS").is_some_and(|v| v == "0");
+        if !defs.font_data.contains_key(name) && (off || !cfg!(target_os = "macos")) {
+            eprintln!("skipping {name}: no installed fallback font (or PDFCRAFT_SYSTEM_FONTS=0)");
+            assert!(defs.families.values().all(|stack| !stack.iter().any(|n| n == name)));
+            continue;
+        }
+        for (family, stack) in &defs.families {
+            assert_eq!(stack.iter().filter(|n| *n == name).count(), 1, "{family:?}: {stack:?}");
+        }
+        let mut fonts = Fonts::new(TextOptions::default(), defs);
+        for id in families() {
+            assert!(fonts.has_glyphs(&id, text), "{id:?} lacks {text}");
+        }
+        assert!(layout_widths(&mut fonts, text).iter().all(|w| w.is_finite() && *w > 0.0));
+    }
+}
+
 /// The Han characters of a catalog's translations.
 fn catalog_han(catalog: &str) -> String {
     let mut han: Vec<char> = catalog