l10n: embedded english strings + test the whole thing in github

Cargo.toml

@@ -378,6 +378,7 @@ digest = "0.10.7"
 
 # Fluent dependencies
 fluent = "0.17.0"
+fluent-bundle = "0.16.0"
 unic-langid = "0.9.6"
 fluent-syntax = "0.12.0"
 

GNUmakefile

@@ -418,25 +418,29 @@ endif
 
 ifeq ($(LOCALES),y)
 locales:
-	$(foreach prog, $(INSTALLEES), \
-		if [ -d "$(BASEDIR)/src/uu/$(prog)/locales" ]; then \
-			mkdir -p "$(BUILDDIR)/locales/$(prog)"; \
-			for locale_file in "$(BASEDIR)"/src/uu/$(prog)/locales/*.ftl; do \
-				$(INSTALL) -v "$$locale_file" "$(BUILDDIR)/locales/$(prog)/"; \
+	@for prog in $(INSTALLEES); do \
+		if [ -d "$(BASEDIR)/src/uu/$$prog/locales" ]; then \
+			mkdir -p "$(BUILDDIR)/locales/$$prog"; \
+			for locale_file in "$(BASEDIR)"/src/uu/$$prog/locales/*.ftl; do \
+				if [ "$$(basename "$$locale_file")" != "en-US.ftl" ]; then \
+					$(INSTALL) -v "$$locale_file" "$(BUILDDIR)/locales/$$prog/"; \
+				fi; \
 			done; \
-		fi $(newline) \
-	)
+		fi; \
+	done
 
 
 install-locales:
-	$(foreach prog, $(INSTALLEES), \
-		if [ -d "$(BASEDIR)/src/uu/$(prog)/locales" ]; then \
-			mkdir -p "$(DESTDIR)$(DATAROOTDIR)/locales/$(prog)"; \
-			for locale_file in "$(BASEDIR)"/src/uu/$(prog)/locales/*.ftl; do \
-				$(INSTALL) -v "$$locale_file" "$(DESTDIR)$(DATAROOTDIR)/locales/$(prog)/"; \
+	@for prog in $(INSTALLEES); do \
+		if [ -d "$(BASEDIR)/src/uu/$$prog/locales" ]; then \
+			mkdir -p "$(DESTDIR)$(DATAROOTDIR)/locales/$$prog"; \
+			for locale_file in "$(BASEDIR)"/src/uu/$$prog/locales/*.ftl; do \
+				if [ "$$(basename "$$locale_file")" != "en-US.ftl" ]; then \
+					$(INSTALL) -v "$$locale_file" "$(DESTDIR)$(DATAROOTDIR)/locales/$$prog/"; \
+				fi; \
 			done; \
-		fi $(newline) \
-	)
+		fi; \
+	done
 else
 install-locales:
 endif

docs/src/l10n.md

@@ -2,6 +2,15 @@
 
 This guide explains how localization (L10n) is implemented in the **Rust-based coreutils project**, detailing the use of [Fluent](https://projectfluent.org/) files, runtime behavior, and developer integration.
 
+## 🏗️ Architecture Overview
+
+**English (US) locale files (`en-US.ftl`) are embedded directly in the binary**, ensuring that English always works regardless of how the software is installed. Other language locale files are loaded from the filesystem at runtime.
+
+### Source Repository Structure
+
+- **Main repository**: Contains English (`en-US.ftl`) locale files embedded in binaries
+- **Translation repository**: [uutils/coreutils-l10n](https://github.com/uutils/coreutils-l10n) contains all other language translations
+
 ---
 
 ## 📁 Fluent File Layout
@@ -15,8 +24,8 @@ Each utility has its own set of translation files under:
 Examples:
 
 ```
-    src/uu/ls/locales/en-US.ftl
-    src/uu/ls/locales/fr-FR.ftl
+    src/uu/ls/locales/en-US.ftl    # Embedded in binary
+    src/uu/ls/locales/fr-FR.ftl    # Loaded from filesystem
 ```
 
 These files follow Fluent syntax and contain localized message patterns.
@@ -31,12 +40,11 @@ Localization must be explicitly initialized at runtime using:
     setup_localization(path)
 ```
 
-
 This is typically done:
 - In `src/bin/coreutils.rs` for **multi-call binaries**
 - In `src/uucore/src/lib.rs` for **single-call utilities**
 
-The string parameter determines the lookup path for Fluent files.
+The string parameter determines the lookup path for Fluent files. **English always works** because it's embedded, but other languages need their `.ftl` files to be available at runtime.
 
 ---
 
@@ -155,9 +163,13 @@ In release mode, **paths are resolved relative to the executable**:
 
 ```
     <executable_dir>/locales/<utility>/
+    <prefix>/share/locales/<utility>/
+    ~/.local/share/coreutils/locales/<utility>/
+    ~/.cargo/share/coreutils/locales/<utility>/
+    /usr/share/coreutils/locales/<utility>/
 ```
 
-If both fallback paths fail, an error is returned during `setup_localization()`.
+If external locale files aren't found, the system falls back to embedded English locales.
 
 ---
 
@@ -184,3 +196,15 @@ Fluent default (disabled here):
 ```
     "\u{2068}Alice\u{2069}"
 ```
+
+---
+
+## 🔧 Embedded English Locales
+
+English locale files are always embedded directly in the binary during the build process. This ensures that:
+
+- **English always works** regardless of installation method (e.g., `cargo install`)
+- **No runtime dependency** on external `.ftl` files for English
+- **Fallback behavior** when other language files are missing
+
+The embedded English locales are generated at build time and included in the binary, providing a reliable fallback while still supporting full localization for other languages when their `.ftl` files are available.

src/uucore/Cargo.toml

@@ -71,10 +71,11 @@ icu_decimal = { workspace = true, optional = true, features = [
 icu_locale = { workspace = true, optional = true, features = ["compiled_data"] }
 icu_provider = { workspace = true, optional = true }
 
-# Fluent dependencies
+# Fluent dependencies (always available for localization)
 fluent = { workspace = true }
 fluent-syntax = { workspace = true }
 unic-langid = { workspace = true }
+fluent-bundle = { workspace = true }
 thiserror = { workspace = true }
 [target.'cfg(unix)'.dependencies]
 walkdir = { workspace = true, optional = true }

src/uucore/build.rs

@@ -0,0 +1,204 @@
+// This file is part of the uutils coreutils package.
+//
+// For the full copyright and license information, please view the LICENSE
+// file that was distributed with this source code.
+
+use std::env;
+use std::fs::File;
+use std::io::Write;
+use std::path::Path;
+
+pub fn main() -> Result<(), Box<dyn std::error::Error>> {
+    let out_dir = env::var("OUT_DIR")?;
+
+    let mut embedded_file = File::create(Path::new(&out_dir).join("embedded_locales.rs"))?;
+
+    writeln!(embedded_file, "// Generated at compile time - do not edit")?;
+    writeln!(
+        embedded_file,
+        "// This file contains embedded English locale files"
+    )?;
+    writeln!(embedded_file)?;
+    writeln!(embedded_file, "use std::collections::HashMap;")?;
+    writeln!(embedded_file)?;
+
+    // Start the function that returns embedded locales
+    writeln!(
+        embedded_file,
+        "pub fn get_embedded_locales() -> HashMap<&'static str, &'static str> {{"
+    )?;
+    writeln!(embedded_file, "    let mut locales = HashMap::new();")?;
+    writeln!(embedded_file)?;
+
+    // Try to detect if we're building for a specific utility by checking build configuration
+    // This attempts to identify individual utility builds vs multicall binary builds
+    let target_utility = detect_target_utility();
+
+    match target_utility {
+        Some(util_name) => {
+            // Embed only the specific utility's locale (cat.ftl for cat for example)
+            embed_single_utility_locale(&mut embedded_file, &project_root()?, &util_name)?;
+        }
+        None => {
+            // Embed all utilities locales (multicall binary or fallback)
+            embed_all_utilities_locales(&mut embedded_file, &project_root()?)?;
+        }
+    }
+
+    writeln!(embedded_file)?;
+    writeln!(embedded_file, "    locales")?;
+    writeln!(embedded_file, "}}")?;
+
+    embedded_file.flush()?;
+    Ok(())
+}
+
+/// Get the project root directory
+fn project_root() -> Result<std::path::PathBuf, Box<dyn std::error::Error>> {
+    let manifest_dir = env::var("CARGO_MANIFEST_DIR")?;
+    let uucore_path = std::path::Path::new(&manifest_dir);
+
+    // Navigate from src/uucore to project root
+    let project_root = uucore_path
+        .parent() // src/
+        .and_then(|p| p.parent()) // project root
+        .ok_or("Could not determine project root")?;
+
+    Ok(project_root.to_path_buf())
+}
+
+/// Attempt to detect which specific utility is being built
+fn detect_target_utility() -> Option<String> {
+    use std::fs;
+
+    // First check if an explicit environment variable was set
+    if let Ok(target_util) = env::var("UUCORE_TARGET_UTIL") {
+        if !target_util.is_empty() {
+            return Some(target_util);
+        }
+    }
+
+    // Check for a build configuration file in the target directory
+    if let Ok(target_dir) = env::var("CARGO_TARGET_DIR") {
+        let config_path = std::path::Path::new(&target_dir).join("uucore_target_util.txt");
+        if let Ok(content) = fs::read_to_string(&config_path) {
+            let util_name = content.trim();
+            if !util_name.is_empty() && util_name != "multicall" {
+                return Some(util_name.to_string());
+            }
+        }
+    }
+
+    // Fallback: Check the default target directory
+    if let Ok(project_root) = project_root() {
+        let config_path = project_root.join("target/uucore_target_util.txt");
+        if let Ok(content) = fs::read_to_string(&config_path) {
+            let util_name = content.trim();
+            if !util_name.is_empty() && util_name != "multicall" {
+                return Some(util_name.to_string());
+            }
+        }
+    }
+
+    // If no configuration found, assume multicall build
+    None
+}
+
+/// Embed locale for a single specific utility
+fn embed_single_utility_locale(
+    embedded_file: &mut std::fs::File,
+    project_root: &Path,
+    util_name: &str,
+) -> Result<(), Box<dyn std::error::Error>> {
+    use std::fs;
+
+    // Embed the specific utility's locale
+    let locale_path = project_root
+        .join("src/uu")
+        .join(util_name)
+        .join("locales/en-US.ftl");
+
+    if locale_path.exists() {
+        let content = fs::read_to_string(&locale_path)?;
+        writeln!(embedded_file, "    // Locale for {util_name}")?;
+        writeln!(
+            embedded_file,
+            "    locales.insert(\"{util_name}/en-US.ftl\", r###\"{content}\"###);"
+        )?;
+        writeln!(embedded_file)?;
+
+        // Tell Cargo to rerun if this file changes
+        println!("cargo:rerun-if-changed={}", locale_path.display());
+    }
+
+    // Always embed uucore locale file if it exists
+    let uucore_locale_path = project_root.join("src/uucore/locales/en-US.ftl");
+    if uucore_locale_path.exists() {
+        let content = fs::read_to_string(&uucore_locale_path)?;
+        writeln!(embedded_file, "    // Common uucore locale")?;
+        writeln!(
+            embedded_file,
+            "    locales.insert(\"uucore/en-US.ftl\", r###\"{content}\"###);"
+        )?;
+        println!("cargo:rerun-if-changed={}", uucore_locale_path.display());
+    }
+
+    Ok(())
+}
+
+/// Embed locale files for all utilities (multicall binary)
+fn embed_all_utilities_locales(
+    embedded_file: &mut std::fs::File,
+    project_root: &Path,
+) -> Result<(), Box<dyn std::error::Error>> {
+    use std::fs;
+
+    // Discover all uu_* directories
+    let src_uu_dir = project_root.join("src/uu");
+    if !src_uu_dir.exists() {
+        return Ok(());
+    }
+
+    let mut util_dirs = Vec::new();
+    for entry in fs::read_dir(&src_uu_dir)? {
+        let entry = entry?;
+        if entry.file_type()?.is_dir() {
+            if let Some(dir_name) = entry.file_name().to_str() {
+                util_dirs.push(dir_name.to_string());
+            }
+        }
+    }
+    util_dirs.sort();
+
+    // Embed locale files for each utility
+    for util_name in &util_dirs {
+        let locale_path = src_uu_dir.join(util_name).join("locales/en-US.ftl");
+        if locale_path.exists() {
+            let content = fs::read_to_string(&locale_path)?;
+            writeln!(embedded_file, "    // Locale for {util_name}")?;
+            writeln!(
+                embedded_file,
+                "    locales.insert(\"{util_name}/en-US.ftl\", r###\"{content}\"###);"
+            )?;
+            writeln!(embedded_file)?;
+
+            // Tell Cargo to rerun if this file changes
+            println!("cargo:rerun-if-changed={}", locale_path.display());
+        }
+    }
+
+    // Also embed uucore locale file if it exists
+    let uucore_locale_path = project_root.join("src/uucore/locales/en-US.ftl");
+    if uucore_locale_path.exists() {
+        let content = fs::read_to_string(&uucore_locale_path)?;
+        writeln!(embedded_file, "    // Common uucore locale")?;
+        writeln!(
+            embedded_file,
+            "    locales.insert(\"uucore/en-US.ftl\", r###\"{content}\"###);"
+        )?;
+        println!("cargo:rerun-if-changed={}", uucore_locale_path.display());
+    }
+
+    embedded_file.flush()?;
+    Ok(())
+}

src/uucore/src/lib/lib.rs

@@ -185,7 +185,7 @@ macro_rules! bin {
                         uucore::locale::LocalizationError::ParseResource {
                             error: err_msg,
                             snippet,
-                        } => eprintln!("Localization parse error at {snippet}: {err_msg}"),
+                        } => eprintln!("Localization parse error at {snippet}: {err_msg:?}"),
                         other => eprintln!("Could not init the localization system: {other}"),
                     }
                     std::process::exit(99)