Add initial word-level support

MarkovGrams/NGrams.cs

@@ -15,6 +15,8 @@ namespace MarkovGrams
 	/// </summary>
 	public static class NGrams
 	{
+		public static bool Verbose { get; set; } = true;
+
 		/// <summary>
 		/// Generates a unique list of n-grams that the given list of words.
 		/// </summary>
@@ -38,7 +40,7 @@ namespace MarkovGrams
 		/// <param name="str">The string to n-gram-ise.</param>
 		/// <param name="order">The order of n-gram to generate.</param>
 		/// <returns>A unique list of n-grams found in the specified string.</returns>
-		public static IEnumerable<string> GenerateFlat(string str, int order, GenerationMode mode)
+		private static IEnumerable<string> GenerateFlat(string str, int order, GenerationMode mode)
 		{
 			List<string> results = new List<string>();
 			if (mode == GenerationMode.CharacterLevel) {
@@ -62,9 +64,15 @@ namespace MarkovGrams
 		/// <returns>The weighted dictionary of ngrams.</returns>
 		public static Dictionary<string, int> GenerateWeighted(IEnumerable<string> words, int order, GenerationMode mode)
 		{
+			List<string> wordList = new List<string>(words);
+			int wordCount = wordList.Count();
 			Dictionary<string, int> results = new Dictionary<string, int>();
-			foreach(string word in words)
-				GenerateWeighted(word, order, mode);
+			int i = 0;
+			foreach (string word in wordList) {
+				GenerateWeighted(word, order, mode, ref results);
+				i++;
+			}
+			Console.WriteLine(" - done");
 			return results;
 		}
 		/// <summary>
@@ -73,15 +81,24 @@ namespace MarkovGrams
 		/// <param name="str">The string to n-gram-ise.</param>
 		/// <param name="order">The order of n-grams to generate.</param>
 		/// <returns>The weighted dictionary of ngrams.</returns>
-		public static void GenerateWeighted(string str, int order, GenerationMode mode, Dictionary<string, int> results)
+		private static void GenerateWeighted(string str, int order, GenerationMode mode, ref Dictionary<string, int> results)
 		{
-			string[] parts = mode == GenerationMode.WordLevel ? str.Split(" ".ToCharArray()) : null;
-			for(int i = 0; i < str.Length - order; i++)
-			{
-				string ngram = mode == GenerationMode.CharacterLevel ? str.Substring(i, order) : string.Join(" ", parts.Skip(i).Take(order));
-				if(!results.ContainsKey(ngram))
-					results[ngram] = 0;
-				results[ngram]++;
+			if (mode == GenerationMode.CharacterLevel) {
+				for (int i = 0; i < str.Length - order; i++) {
+					string ngram = str.Substring(i, order);
+					if (!results.ContainsKey(ngram))
+						results[ngram] = 0;
+					results[ngram]++;
+				}
+			}
+			else {
+				string[] parts = str.Split(" ".ToCharArray());
+				for (int i = 0; i < parts.Length - order; i++) {
+					string ngram = string.Join(" ", parts.Skip(i).Take(order));
+					if (!results.ContainsKey(ngram))
+						results[ngram] = 0;
+					results[ngram]++;
+				}
 			}
 		}
 	}

MarkovGrams/Program.cs

@@ -65,6 +65,7 @@ namespace MarkovGrams
 						break;
 					case "words":
 						generationMode = GenerationMode.WordLevel;
+						splitOnWhitespace = false;
 						break;
 					case "help":
 						operationMode = Mode.Help;
@@ -141,9 +142,9 @@ namespace MarkovGrams
 					Console.WriteLine("    --help                  Show this message");
 					Console.WriteLine("    --wordlist {filename}   Read the wordlist from the specified filename instead of stdin");
 					Console.WriteLine("    --order {number}        Use the specified order when generating n-grams (default: 3)");
-					Console.WriteLine("    --length {number}       The target length of word to generate (Not available in ngrams mode)");
+					Console.WriteLine("    --length {number}       The target length of word to generate (Not available in ngrams mode; instead specifies the number of words to generate with --words)");
 					Console.WriteLine("    --count {number}        The number of words to generate (Not valid in ngrams mode)");
-					Console.WriteLine("    --words                 Generate ngrams on word-level instead of character-level (Applies to all modes)");
+					Console.WriteLine("    --words                 Generate ngrams on word-level instead of character-level (Applies to all modes; implies --no-split)");
 					Console.WriteLine("    --no-split              Don't split input words on whitespace - treat each line as a single word");
 					Console.WriteLine("    --lowercase             Convert the input to lowercase before processing");
 					Console.WriteLine("    --start-uppercase       Start the generating a word only with n-grams that start with a capital letter");

MarkovGrams/UnweightedMarkovChain.cs

@@ -69,7 +69,7 @@ namespace MarkovGrams
 		{
 			string result = RandomNgram();
 			string lastNgram = result;
-			while(result.Length < length)
+			while((Mode == GenerationMode.CharacterLevel ? result.Length : result.Split(' ').Length) < length)
 			{
 				// The substring that the next ngram in the chain needs to start with
 				string nextStartsWith = Mode == GenerationMode.CharacterLevel ? lastNgram.Substring(1) : lastNgram.Split(' ')[0];

MarkovGrams/WeightedMarkovChain.cs

@@ -83,7 +83,7 @@ namespace MarkovGrams
 		{
 			string result = RandomNgram();
 			string lastNgram = result;
-			while(result.Length < length)
+			while((Mode == GenerationMode.CharacterLevel ? result.Length : result.Split(' ').Length) < length)
 			{
 				wrandom.ClearContents();
 				// The substring that the next ngram in the chain needs to start with

wordlists/download.sh

@@ -17,4 +17,4 @@ sort Final-Fantasy-15-Items.txt -o Final-Fantasy-15-Items.txt
 curl "http://orcz.com/No_Man's_Sky:_Items_List" | xidel --data - --css "table td:first-child a, #mw-content-text > ul > li" | sed -e 's/\s*—.*$//g' | sort >No-Mans-Sky-Items.txt
 
 ### Recipes Wikia ###
-curl http://recipes.wikia.com/sitemap-newsitemapxml-index.xml | xidel --data - --css "loc" | grep -i NS_0 | xargs -n1 -I{} sh -c 'curl {} | xidel --data - --css "loc"' | sed -e 's/^.*\///g' -e 's/_/ /g' | sort >Dishes.txt
+curl http://recipes.wikia.com/sitemap-newsitemapxml-index.xml | xidel --data - --css "loc" | grep -i NS_0 | xargs -n1 -I{} sh -c 'curl {} | xidel --data - --css "loc"' | sed -e 's/^.*\///g' -e 's/_/ /g' | python -c "import urllib, sys; print urllib.unquote(sys.argv[1] if len(sys.argv) > 1 else sys.stdin.read()[0:-1])" | sort >Dishes.txt