main compiled + tests passed

topmost.py

@@ -0,0 +1,32 @@
+import sys
+import wordfreq
+import urllib.request
+
+
+
+
+
+def main():
+    stop_word_file = sys.argv[1]
+    word_file = sys.argv[2]
+    amount_of_words = int(sys.argv[3])
+
+    if "https" in word_file:
+        response = urllib.request.urlopen(word_file)
+        lines = response.read().decode("utf8").splitlines()
+    else:
+        inp_file = open(word_file, encoding="utf-8")
+        lines = inp_file.readlines()
+        inp_file.close()
+    tokenized = wordfreq.tokenize(lines)
+
+    stop_word_lines = open(stop_word_file, encoding="utf-8")
+    stop_words = stop_word_lines.read().split("\n")
+    stop_word_lines.close()
+
+    counted_words = wordfreq.countWords(tokenized, stop_words)
+
+    wordfreq.printTopMost(counted_words, amount_of_words)
+
+
+main()

wordfreq.py

@@ -5,7 +5,7 @@ class CharType(Enum):
 	NONE = 0
 	DIGIT = 1
 	ALPHA = 2
-	SPACE = 3
+	WHITESPACE = 3
 	SYMBOL = 4
 
 
@@ -14,8 +14,8 @@ def char_type(char: str) -> CharType:
 		return CharType.DIGIT
 	elif char.isalpha():
 		return CharType.ALPHA
-	elif char == " ":
+	elif char == " " or char == "	":
-		return CharType.SPACE
+		return CharType.WHITESPACE
 	return CharType.SYMBOL
 
 
@@ -27,7 +27,7 @@ def tokenize(lines: list[str]) -> list[str]:
 		for i, char in enumerate(line.strip().lower()):
 			if len(current_word) == 0:
 				ct = char_type(char)
-				if ct == CharType.SPACE:
+				if ct == CharType.WHITESPACE:
 					continue
 				if ct == CharType.SYMBOL:
 					result.append(char)
@@ -38,3 +38,24 @@ def tokenize(lines: list[str]) -> list[str]:
 				result.append("".join(current_word))
 				current_word = []
 	return result
+
+
+def countWords(words, stopWords = []):
+	dict = {}
+	for word in words:
+		if word not in stopWords:
+			if word in dict.keys():
+				dict[word] += 1
+			else:
+				dict[word] = 1
+	return(dict)
+
+def printTopMost(frequencies,n):
+    list = []
+    
+    for word,freq in frequencies.items():
+        list.append((word,freq))
+    list = sorted(list, key=lambda x: -x[1])
+    for i in range (0, n):
+        if len(list)-1 >= i:
+	        print(list[i][0].ljust(19),str(list[i][1]).rjust(5))