Module 10: Search the Library, Fast

a.c

@@ -1,6 +1,7 @@
 #include <iostream> // library for printing
 #include <string>   // support for strings
 #include <vector>   // support for vectors
+#include <unordered_map>  // support for hash-tables
 #include <assert.h>
 #include <fstream> // support for reading files
 using namespace std;
@@ -8,172 +9,120 @@ using namespace std;
 // For compiling C++ code
 // g++ a.c -o a
 
-string ToUpper(string s)
-{
+string ToUpper(string s) {
   string s2;
-  for (char c : s)
-  {
+  for (char c : s) {
     s2.push_back(toupper(c));
   }
   return s2;
 }
 
-struct Word
-{
-  Word(string s)
-  {
-    word = s;
-  }
+struct Word {
+  Word() {}  // default empty constructor
+  Word(string s) : word(s) {}  // standard way of initialization
   string word;
 };
 typedef vector<Word> Words;
+typedef unordered_map<string, Word> WordMap;  // hash-table from stl
 
-const int num_buckets = 1001;
-
-// hash function
-int bucket(string s)
-{
-  assert(!s.empty());
-  int i = 0;
-  for (char c : s)
-  {
-    i = (i * 217) + c;
-  }
-  i = abs(i);
-  int b = i % num_buckets;
-  assert(b >= 0 && b < num_buckets);
-  return b;
-}
-
-class Library
-{
+class Library {
 public:
-  Library()
-  {
-    shelves.resize(num_buckets);
-  }
-  bool IsWord(string s) const
-  {
-    for (Word w : shelves[bucket(s)])
-    {
-      if (s == w.word)
-      {
-        return true;
-      }
+  Library() {}  // hash-tables are automatically initialized
+  bool IsWord(string s) const {
+    auto it = word_map_.find(s);  // use iterator
+    if (it == word_map_.end()) {
+      return false;  // if word is not found on hast-table
+    } else {
+      return true;
     }
-    return false;
+    //return word_map_.count(s) > 0;  // True if word exists
   }
-  void ComputeStats()
-  {
-    assert(counts.empty());
-    counts.resize(18);
-    for (Word w : words)
-    {
+  void ComputeStats() {
+    assert(counts_.empty());
+    counts_.resize(18);
+    for (Word w : words_) {
       int len = w.word.length();
-      if (len < 18)
-      {
-        counts[len]++;
+      if (len < 18) {
+        counts_[len]++;
       }
     }
   }
-  void PrintStats() const
-  {
+  void PrintStats() const {
     cout << "Here are the counts of each word length:\n";
-    for (int i = 1; i < counts.size(); i++)
-    {
-      cout << "[" << i << "] " << counts[i] << "\n";
+    for (int i = 1; i < counts_.size(); i++) {
+      cout << "[" << i << "] " << counts_[i] << "\n";
     }
   }
-  string GetWord(int i) const
-  {
-    assert(i >= 0 && i < words.size());
-    return words[i].word;
+  string GetWord(int i) const {
+    assert(i >= 0 && i < words_.size());
+    return words_[i].word;
   }
-  void ReadFromFile(string filename)
-  {
+  void ReadFromFile(string filename) {
     ifstream f;
     f.open(filename);
-    while (!f.eof())
-    {
+    while (!f.eof()) {
       string line;
       getline(f, line);
       // cout << line << "\n";
-      if (!line.empty())
-      {
+      if (!line.empty()) {
         line = ToUpper(line);
         int len = line.length();
-        if (line[len - 1] == '\r')
-        {
+        if (line[len - 1] == '\r') {
           line = line.substr(0, len - 1);
         }
-        words.push_back(Word(line));
-        shelves[bucket(line)].push_back(Word(line));
+        words_.push_back(Word(line));
+        word_map_[line] = Word(line);  // create entry for the hash-table
       }
     }
-    cout << "Read " << words.size() << " words from file '"
+    cout << "Read " << words_.size() << " words from file '"
          << filename << "'\n";
   }
-  void DebugBuckets() const
-  {
-    for (int i = 0; i < shelves.size(); i++)
-    {
-      cout << "[" << i << "] " << shelves[i].size() << "\n";
+  void DebugBuckets() const {
+    for (int i = 0; i < word_map_.bucket_count(); i++) {
+      cout << "[" << i << "] " << word_map_.bucket_size(i) << "\n";
     }
   }
 
-private:
-  Words words;
-  vector<Words> shelves;
-  vector<int> counts;
+private:  // _ is used to indicate privacy
+  Words words_;
+  WordMap word_map_;
+  vector<int> counts_;
 };
 
-struct Grid
-{
-  Grid(string n)
-  {
+struct Grid {
+  Grid(string n) {
     name = n;
   }
   int rows() const { return lines.size(); }
-  int cols() const
-  {
-    if (lines.empty())
-    {
+  int cols() const {
+    if (lines.empty()) {
       return 0;
-    }
-    else
-    {
+    } else {
       return lines[0].size();
     }
   }
-  void LoadFromFile(string filename)
-  {
+  void LoadFromFile(string filename) {
     ifstream f;
     f.open("test");
-    while (!f.eof())
-    {
+    while (!f.eof()) {
       string line;
       getline(f, line);
       // cout << line << "\n";
-      if (!line.empty() && line[0] != '#')
-      {
+      if (!line.empty() && line[0] != '#') {
         lines.push_back(line);
       }
     }
   }
-  void Check() const
-  {
-    for (string s : lines)
-    {
+  void Check() const {
+    for (string s : lines) {
       assert(s.size() == cols());
     }
   }
-  void Print() const
-  {
+  void Print() const {
     cout << "Grid: " << name
          << " (rows=" << rows()
          << ", cols=" << cols() << ")\n";
-    for (string s : lines)
-    {
+    for (string s : lines) {
       cout << "  " << s << "\n";
     }
   }
@@ -181,8 +130,7 @@ struct Grid
   vector<string> lines;
 };
 
-int main()
-{
+int main() {
   Library lib;
   lib.ReadFromFile("top_12000.txt");
   //lib.ComputeStats();
@@ -191,6 +139,7 @@ int main()
   cout << lib.IsWord("DOG") << "\n";
   cout << lib.IsWord("CAT") << "\n";
   cout << lib.IsWord("THANKS") << "\n";
+  cout << lib.IsWord("TFAFAS") << "\n";
   lib.DebugBuckets();
 
   //Grid grid("MY GRID");