Fix text normalization bug (#16)

rust/README.md

@@ -4,6 +4,8 @@ This guide provides examples for running TTS inference using Rust.
 
 ## 📰 Update News
 
+**2025.11.23** - Enhanced text preprocessing with comprehensive normalization, emoji removal, symbol replacement, and punctuation handling for improved synthesis quality.
+
 **2025.11.19** - Added `--speed` parameter to control speech synthesis speed (default: 1.05, recommended range: 0.9-1.5).
 
 **2025.11.19** - Added automatic text chunking for long-form inference. Long texts are split into chunks and synthesized with natural pauses.

rust/src/helper.rs

@@ -113,7 +113,95 @@ impl UnicodeProcessor {
 }
 
 pub fn preprocess_text(text: &str) -> String {
-    text.nfkd().collect()
+    // TODO: Need advanced normalizer for better performance
+    let mut text: String = text.nfkd().collect();
+
+    // FIXME: this should be fixed for non-English languages
+
+    // Remove emojis (wide Unicode range)
+    let emoji_pattern = Regex::new(r"[\x{1F600}-\x{1F64F}\x{1F300}-\x{1F5FF}\x{1F680}-\x{1F6FF}\x{1F700}-\x{1F77F}\x{1F780}-\x{1F7FF}\x{1F800}-\x{1F8FF}\x{1F900}-\x{1F9FF}\x{1FA00}-\x{1FA6F}\x{1FA70}-\x{1FAFF}\x{2600}-\x{26FF}\x{2700}-\x{27BF}\x{1F1E6}-\x{1F1FF}]+").unwrap();
+    text = emoji_pattern.replace_all(&text, "").to_string();
+
+    // Replace various dashes and symbols
+    let replacements = [
+        ("–", "-"),      // en dash
+        ("‑", "-"),      // non-breaking hyphen
+        ("—", "-"),      // em dash
+        ("¯", " "),      // macron
+        ("_", " "),      // underscore
+        ("\u{201C}", "\""),     // left double quote
+        ("\u{201D}", "\""),     // right double quote
+        ("\u{2018}", "'"),      // left single quote
+        ("\u{2019}", "'"),      // right single quote
+        ("´", "'"),      // acute accent
+        ("`", "'"),      // grave accent
+        ("[", " "),      // left bracket
+        ("]", " "),      // right bracket
+        ("|", " "),      // vertical bar
+        ("/", " "),      // slash
+        ("#", " "),      // hash
+        ("→", " "),      // right arrow
+        ("←", " "),      // left arrow
+    ];
+
+    for (from, to) in &replacements {
+        text = text.replace(from, to);
+    }
+
+    // Remove combining diacritics // FIXME: this should be fixed for non-English languages
+    let diacritics_pattern = Regex::new(r"[\u{0302}\u{0303}\u{0304}\u{0305}\u{0306}\u{0307}\u{0308}\u{030A}\u{030B}\u{030C}\u{0327}\u{0328}\u{0329}\u{032A}\u{032B}\u{032C}\u{032D}\u{032E}\u{032F}]").unwrap();
+    text = diacritics_pattern.replace_all(&text, "").to_string();
+
+    // Remove special symbols
+    let special_symbols = ["♥", "☆", "♡", "©", "\\"];
+    for symbol in &special_symbols {
+        text = text.replace(symbol, "");
+    }
+
+    // Replace known expressions
+    let expr_replacements = [
+        ("@", " at "),
+        ("e.g.,", "for example, "),
+        ("i.e.,", "that is, "),
+    ];
+
+    for (from, to) in &expr_replacements {
+        text = text.replace(from, to);
+    }
+
+    // Fix spacing around punctuation
+    text = Regex::new(r" ,").unwrap().replace_all(&text, ",").to_string();
+    text = Regex::new(r" \.").unwrap().replace_all(&text, ".").to_string();
+    text = Regex::new(r" !").unwrap().replace_all(&text, "!").to_string();
+    text = Regex::new(r" \?").unwrap().replace_all(&text, "?").to_string();
+    text = Regex::new(r" ;").unwrap().replace_all(&text, ";").to_string();
+    text = Regex::new(r" :").unwrap().replace_all(&text, ":").to_string();
+    text = Regex::new(r" '").unwrap().replace_all(&text, "'").to_string();
+
+    // Remove duplicate quotes
+    while text.contains("\"\"") {
+        text = text.replace("\"\"", "\"");
+    }
+    while text.contains("''") {
+        text = text.replace("''", "'");
+    }
+    while text.contains("``") {
+        text = text.replace("``", "`");
+    }
+
+    // Remove extra spaces
+    text = Regex::new(r"\s+").unwrap().replace_all(&text, " ").to_string();
+    text = text.trim().to_string();
+
+    // If text doesn't end with punctuation, quotes, or closing brackets, add a period
+    if !text.is_empty() {
+        let ends_with_punct = Regex::new(r#"[.!?;:,'"\u{201C}\u{201D}\u{2018}\u{2019})\]}…。」』】〉》›»]$"#).unwrap();
+        if !ends_with_punct.is_match(&text) {
+            text.push('.');
+        }
+    }
+
+    text
 }
 
 pub fn text_to_unicode_values(text: &str) -> Vec<usize> {