Upload ChatIPC.cpp

ChatIPC.cpp

@@ -147,42 +147,85 @@ static bool is_punctuation_only_token(const std::string &s){
     return true;
 }
 
-static bool is_common_determiner(const std::string &s){
-    return s == "a" || s == "an" || s == "the" || s == "this" || s == "that" ||
-           s == "these" || s == "those" || s == "my" || s == "your" || s == "his" ||
-           s == "her" || s == "its" || s == "our" || s == "their";
+static std::string to_lower_ascii(std::string s) {
+    std::transform(s.begin(), s.end(), s.begin(),
+                   [](unsigned char c) { return static_cast<char>(std::tolower(c)); });
+    return s;
+}
+
+static bool is_common_determiner(const std::string &s) {
+    static const std::unordered_set<std::string> words = {
+        "a", "an", "the", "this", "that", "these", "those",
+        "my", "your", "his", "her", "its", "our", "their",
+        "all", "some", "any", "each", "every", "either", "neither",
+        "no", "many", "much", "more", "most", "few", "fewer", "less",
+        "little", "several", "both", "another", "other", "such",
+        "own", "same", "certain", "what", "which", "whose",
+        "whatever", "whichever", "enough", "various", "particular"
+    };
+
+    return words.find(to_lower_ascii(s)) != words.end();
 }
 
-static bool is_common_preposition(const std::string &s){
-    return s == "of" || s == "in" || s == "on" || s == "at" || s == "by" ||
-           s == "for" || s == "from" || s == "with" || s == "into" || s == "onto" ||
-           s == "about" || s == "over" || s == "under" || s == "after" || s == "before" ||
-           s == "between" || s == "through" || s == "during" || s == "without" || s == "within" ||
-           s == "under" || s == "across" || s == "against" || s == "among" || s == "around";
+static bool is_common_preposition(const std::string &s) {
+    static const std::unordered_set<std::string> words = {
+        "of", "in", "on", "at", "by", "for", "from", "with",
+        "into", "onto", "about", "over", "under", "after", "before",
+        "between", "through", "during", "without", "within", "across",
+        "against", "among", "around", "as", "like", "per", "via",
+        "toward", "towards", "upon", "beneath", "beside", "besides",
+        "beyond", "inside", "outside", "near", "past", "since",
+        "until", "till", "up", "down", "off", "out", "underneath",
+        "amid", "amidst", "despite", "except", "regarding", "concerning",
+        "throughout", "amongst", "opposite", "along", "behind", "ahead",
+        "above", "below", "plus", "minus"
+    };
+
+    return words.find(to_lower_ascii(s)) != words.end();
 }
 
-static bool is_common_aux_or_modal(const std::string &s){
-    return s == "to" || s == "be" || s == "am" || s == "is" || s == "are" || s == "was" ||
-           s == "were" || s == "been" || s == "being" || s == "have" || s == "has" ||
-           s == "had" || s == "do" || s == "does" || s == "did" || s == "can" ||
-           s == "could" || s == "may" || s == "might" || s == "must" || s == "shall" ||
-           s == "should" || s == "will" || s == "would";
+static bool is_common_aux_or_modal(const std::string &s) {
+    static const std::unordered_set<std::string> words = {
+        "to", "be", "am", "is", "are", "was", "were", "been", "being",
+        "have", "has", "had", "do", "does", "did",
+        "can", "could", "may", "might", "must", "shall", "should", "will",
+        "would", "ought", "need", "dare", "used",
+        "cannot", "can't", "won't", "wouldn't", "shouldn't", "couldn't",
+        "mustn't", "mayn't", "mightn't", "shan't"
+    };
+
+    return words.find(to_lower_ascii(s)) != words.end();
 }
 
 static bool begins_with_vowel_sound(const std::string &s){
     if (s.empty()) return false;
 
-    if (s.rfind("hour", 0) == 0 || s.rfind("honest", 0) == 0 || s.rfind("honor", 0) == 0 ||
-        s.rfind("heir", 0) == 0 || s.rfind("herb", 0) == 0) {
-        return true;
+    const std::string t = to_lower_ascii(s);
+
+    static const std::unordered_set<std::string> vowel_sound_exceptions = {
+        "hour", "hours", "honest", "honesty", "honor", "honour", "honorable", "honourable",
+        "heir", "heiress", "herb", "herbal", "herbalist", "homage", "hono(u)rary"
+    };
+
+    static const std::unordered_set<std::string> consonant_sound_prefixes = {
+        "uni", "univ", "unit", "use", "user", "euro", "eu", "one", "once", "ouija",
+        "ufo", "ut", "uk", "ubiq", "ewe", "eul", "eup", "x", "y"
+    };
+
+    for (const auto &w : vowel_sound_exceptions) {
+        if (t.rfind(w, 0) == 0) {
+            return true;
+        }
     }
 
-    if (s.rfind("uni", 0) == 0 || s.rfind("use", 0) == 0 || s.rfind("user", 0) == 0 ||
-        s.rfind("one", 0) == 0 || s.rfind("once", 0) == 0 || s.rfind("euro", 0) == 0) {
-        return false;
+    for (const auto &p : consonant_sound_prefixes) {
+        if (t.rfind(p, 0) == 0) {
+            return false;
+        }
     }
 
-    char c = s[0];
+    if (t.empty()) return false;
+    char c = t[0];
     return c == 'a' || c == 'e' || c == 'i' || c == 'o' || c == 'u';
 }