Merge PR #1624: Hebrew file names: draw them with an installed Hebrew face when the build has none

crates/ui-egui/src/system_fonts.rs

@@ -3,10 +3,10 @@
 //! 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
-//! 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).
+//! few more installed faces, [`devanagari_fallback`], [`telugu_fallback`], [`sinhala_fallback`],
+//! [`tamil_fallback`] and [`hebrew_fallback`], draw Hindi, Telugu, Sinhala, Tamil and Hebrew 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).
 
 use std::path::{Path, PathBuf};
 use std::sync::{Arc, OnceLock};
@@ -32,6 +32,8 @@ const TELUGU_PROBE: char = '\u{0C15}';
 const SINHALA_PROBE: char = '\u{0D9A}';
 /// Tamil letter ka (க): the face must have it to cover Tamil.
 const TAMIL_PROBE: char = '\u{0B95}';
+/// Hebrew letter alef: the face must have it to cover Hebrew.
+const HEBREW_PROBE: char = '\u{05D0}';
 /// 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.
@@ -103,6 +105,13 @@ pub fn tamil_fallback() -> Option<Arc<FontData>> {
     CACHE.get_or_init(|| script_fallback(&tamil_candidates(), TAMIL_PROBE)).clone()
 }
 
+/// The installed fallback face for Hebrew, read once. `None` when it is turned off or no
+/// candidate is installed; the interface then draws what the embedded faces can.
+pub fn hebrew_fallback() -> Option<Arc<FontData>> {
+    static CACHE: OnceLock<Option<Arc<FontData>>> = OnceLock::new();
+    CACHE.get_or_init(|| script_fallback(&hebrew_candidates(), HEBREW_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;
@@ -227,6 +236,30 @@ fn tamil_candidates() -> Vec<PathBuf> {
     }
 }
 
+/// Well-known locations of Hebrew faces, best first. The general fallback does not cover it:
+/// SF Arabic, Geeza Pro and Noto Sans Arabic have no Hebrew.
+fn hebrew_candidates() -> Vec<PathBuf> {
+    if cfg!(windows) {
+        ["segoeui.ttf", "arial.ttf", "tahoma.ttf", "david.ttf"].iter().map(|f| windows_fonts().join(f)).collect()
+    } else if cfg!(target_os = "macos") {
+        ["/System/Library/Fonts/SFHebrew.ttf", "/System/Library/Fonts/ArialHB.ttc", "/Library/Fonts/Arial Unicode.ttf"]
+            .iter()
+            .map(PathBuf::from)
+            .collect()
+    } else {
+        unix_fonts(&[
+            "google-noto/NotoSansHebrew-Regular.ttf",
+            "google-noto-vf/NotoSansHebrew[wght].ttf",
+            "truetype/noto/NotoSansHebrew-Regular.ttf",
+            "noto/NotoSansHebrew-Regular.ttf",
+            "truetype/dejavu/DejaVuSans.ttf",
+            "TTF/DejaVuSans.ttf",
+            "dejavu/DejaVuSans.ttf",
+            "dejavu-sans-fonts/DejaVuSans.ttf",
+        ])
+    }
+}
+
 /// Well-known locations of faces with broad script coverage, best first.
 fn candidates(need: Need) -> Vec<PathBuf> {
     match need {
@@ -407,11 +440,12 @@ mod tests {
         assert!(script_fallback(&candidates, DEVANAGARI_PROBE).is_none());
         assert!(script_fallback(&candidates, SINHALA_PROBE).is_none());
         assert!(script_fallback(&candidates, TAMIL_PROBE).is_none());
+        assert!(script_fallback(&candidates, HEBREW_PROBE).is_none());
     }
 
     #[test]
     fn script_candidates_are_absolute_font_files() {
-        for list in [devanagari_candidates(), telugu_candidates(), sinhala_candidates(), tamil_candidates()] {
+        for list in [devanagari_candidates(), telugu_candidates(), sinhala_candidates(), tamil_candidates(), hebrew_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

@@ -224,6 +224,8 @@ pub const SYSTEM_TELUGU_FALLBACK: &str = "system-telugu-fallback";
 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";
+/// The name of the installed Hebrew face [`installed_font_definitions`] may add.
+pub const SYSTEM_HEBREW_FALLBACK: &str = "system-hebrew-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.
@@ -236,9 +238,9 @@ pub const SYSTEM_TAMIL_FALLBACK: &str = "system-tamil-fallback";
 /// - Otherwise it is the last fallback of every family (an Arabic file name in a build without
 ///   craft-fonts).
 ///
-/// 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.
+/// Installed Devanagari, Telugu, Sinhala, Tamil and Hebrew 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, and Hebrew file names (#586) draw in a build without such faces.
 ///
 /// `PDFCRAFT_SYSTEM_FONTS=0` leaves them out.
 pub fn installed_font_definitions(cjk: CjkPreference) -> FontDefinitions {
@@ -253,6 +255,7 @@ pub fn installed_font_definitions(cjk: CjkPreference) -> FontDefinitions {
             (SYSTEM_TELUGU_FALLBACK, crate::system_fonts::telugu_fallback()),
             (SYSTEM_SINHALA_FALLBACK, crate::system_fonts::sinhala_fallback()),
             (SYSTEM_TAMIL_FALLBACK, crate::system_fonts::tamil_fallback()),
+            (SYSTEM_HEBREW_FALLBACK, crate::system_fonts::hebrew_fallback()),
         ] {
             let Some(data) = data else { continue };
             fonts.font_data.insert(name.to_owned(), data);

crates/ui-egui/tests/fonts.rs

@@ -8,6 +8,7 @@ const JAPANESE: &str = "日本語の文字";
 const CHINESE: &str = "简体中文欢迎";
 const ARABIC: &str = "واحد اثنين";
 const TELUGU: &str = "తెలుగు ఫైల్";
+const HEBREW: &str = "ייפוי כח.pdf";
 
 fn families() -> Vec<FontId> {
     vec![FontId::proportional(13.0), FontId::monospace(13.0), theme::medium(13.0), theme::semibold(17.0)]
@@ -219,6 +220,29 @@ fn system_fallback_covers_sinhala_and_tamil() {
     }
 }
 
+/// On a machine with an installed Hebrew font, the installed definitions include it and a
+/// Hebrew file name has glyphs in the document tab and the recent files (#586). macOS always
+/// ships Arial Hebrew and SF Hebrew, so there the test never skips.
+#[test]
+fn system_fallback_covers_hebrew() {
+    assert!(!theme::font_definitions().font_data.contains_key(theme::SYSTEM_HEBREW_FALLBACK));
+    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(theme::SYSTEM_HEBREW_FALLBACK) && (off || !cfg!(target_os = "macos")) {
+        eprintln!("skipping system_fallback_covers_hebrew: no installed Hebrew fallback font (or PDFCRAFT_SYSTEM_FONTS=0)");
+        assert!(defs.families.values().all(|stack| !stack.iter().any(|n| n == theme::SYSTEM_HEBREW_FALLBACK)));
+        return;
+    }
+    for (family, stack) in &defs.families {
+        assert_eq!(stack.iter().filter(|n| *n == theme::SYSTEM_HEBREW_FALLBACK).count(), 1, "{family:?}: {stack:?}");
+    }
+    let mut fonts = Fonts::new(TextOptions::default(), defs);
+    for id in families() {
+        assert!(fonts.has_glyphs(&id, HEBREW), "{id:?} lacks {HEBREW}");
+    }
+    assert!(layout_widths(&mut fonts, HEBREW).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