From a6e6f7405f48b6ec972fe8bc0d6250c1a507aa1d Mon Sep 17 00:00:00 2001
From: Ivryxia <spelaren06@gmail.com>
Date: Thu, 25 Sep 2025 14:54:05 +0200
Subject: [PATCH] main compiled + tests passed

---
 __pycache__/wordfreq.cpython-313.pyc | Bin 0 -> 3199 bytes
 topmost.py                           |  32 +++++++++++++++++++++++++++
 wordfreq.py                          |  29 ++++++++++++++++++++----
 3 files changed, 57 insertions(+), 4 deletions(-)
 create mode 100644 __pycache__/wordfreq.cpython-313.pyc
 create mode 100644 topmost.py

diff --git a/__pycache__/wordfreq.cpython-313.pyc b/__pycache__/wordfreq.cpython-313.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..4e7d123304f811d74459d823a94bebcb504db7e3
GIT binary patch
literal 3199
zcmai0-A`M|6`#3ZzSqV$e3&GJCeDV0cne9WNTmQtm4zt4g4yNb4J*95a?D+F6LW3m
zUYBN{OrtJXSrxA;w5<BjMBRtY+wR*|?H>{3B)GR!TB&{Er6PrwsxLifjLpZY*(2RE
zXXea3Gjl$EGdsbcp8)-$@8!J(nUH^Ar%KT0v~v%dRiYD}zDq_ZqY-j~yhU`OmFQxE
zUKK0Tn4n7uQI``!kEAQD<i5lt-ItIPA{v76Jqffb*D9Au57jl0Df8+6R>IWTK(uZP
z%|)pv-Li9Ysfz6ir+b~9iy*9$1YuMsuq<VwF2G_UlXZzHx(wzhQ+0)Dv%aY6sRQ?t
zZ1Q2&+>+o&CIH()TU%Vh?LQ;2sNYi!!%ohbhT-`QV=gn3OQT$881uPgdQTHFjE^nm
zxM|Ba?F^`;*m&%gCl3za9-j2%o1^ay-Sqr-hK46^>F?bfxaBGOhhy)Ik9uLlaNMM8
zrHrKOGV5;6H66oX=>8q}h&MFQn}|Cma}w4slg!S5Fqlc@=1kjl61OdPD0eq;n`Ls@
zuI{eU<lU}288*{3kjdGuWzQxSp!YE|=PzX+GW0iRcwFZcuun-@)$+|{&7TifSbZqp
zTJ{GXwXkq?wkM^)PoBa|H^=N$)!U#Z=qU8l&cA@Ik~o<-sD&}4tCfaebdZwA2${w|
zIZfbZj!-*V@*Nq3?vGeffA|Ml(rND$Au|d=SwQ*74tS~`{<r<$4(kr<u-8taV$7ov
zk7`k$=d+v{Yu0ir9){x)97?9M;I{_ou|{M~z@n5LhsHrSMOX`PPebn-E~Ftl4Sih9
z83&dpWl3EcT^wDCEygyrhLzKW)6a$DWyQagUQ939i}s<x<<z4G#mP1OchfMup|!1R
zZO?_aP4(DHs1SNikMnqXGUlgqD2C`Y9zzvkvPv!!o5o2K8Tt<)wlEFK3Qg1^RviJo
z2(zW>Dj<-!@TRCuX#0OwrD{a4?&S@v`zJzjuvYei=|FW>T&n6Tu}qFY1_f(crK+`k
zao>R**H>rkw><h_eGC>pG#7(*g!o(tTAWT`=#EglwrYfoCD58J#-$&d8JBgT3oIQt
zn^4_-?_VHGAtmDC{@JF^SLUOOYx5Rh9-iTg|F<_?oCqJ;E_C<3ShW<vXiH;%CL}=M
z6#uQXaSGWj#W)@^tU`}O1C`VcVNWvwfK8TkO;2_Jva*m>nFW)1V%oHM4)5o?rzEpk
z)1L99`x(oQs_YC}04Q;CY1fl58$As%iWh)am&!2)z-Hi(M=f3~o{(}K%+kmnRq94{
zGY?GL`ov_HK!>H|Yyg9@@z>>B{uXS^Pj1$?tjrbW^3ifbQ@(Svp>?h254~UZ{=R?X
zRM+~cuF|Q?uNtl_&gPSwiniQYQjV{6mz1_mt+Cki_)PwtvQPVLY9km~4@OG9$Y13k
zA6PL8M#<M!mIF&4Eq+w&c_E)b)v?C>a9Ip(h%M`4OVNEHwv`p%GF?o4rWczZe^^pl
z)}miM{HFOk`fcjllckQnm#uwe$-gwVI97b?i;mAb);dd#9WSJd<)-kjM|Vz=#_rcX
zQs1;4AzCQ^6JEZlgEfdL!RyuqVU=8gYUOo%8S8SYyALXgX9=L&)X(08%YE>F5^81Y
z+;!o)fM#{t1=Zz<j?e+Uv7h3|)HyD9@8yWlPM!%do*sB7KQJFUQOT1rZjPrpZYFz&
zi_(mhf<W_eM0yNiC4T-C-cfuO`#ES}72@;*g9xhrd^3+=S=L_4t$=weR>6Awpro7x
zP<%8}Ji9plo00Du8uNpXMqUTdO?5;I=G%VgrW(BUgF`sHft%js4uBwlXbwR=0BGpq
zBQ(|1Q!831o0Aon9E3rg!W&4qCIEoet}$JV)2n*{gf%81O!9OM65}<Cy3_?Bi_07i
zu*_jM`*1OJo(G7(ohE7!xW7SNt`_$+7AvQ{f24yTGJ*Hf5z=drR^2C@?t{wdW=Yf+
zJ9Ka0Q4kk*5N7f2*C{UWHr$Qu3JClO1Gzzeb?~-R`_sv}yEDlf-svo}Y<Dt~9m_cG
zrT%m#l}tM~K&a?@!Gwc1bDlhz|GMF+`_$yY1&bnN+devN;U>0l>8R$(mTS&A>;m*W
z#mO+&obhCqv}a9r9>-+9C;-;|oa1^Tz!#`djw)UN-$^;sPFbeoQ5(?-^ms#g5~^4y
zhz>j>coJ9BxbEOF7+g&JmEwE~0wi)Em>>K;9N7q8SPx%#6~0)|mZh><w-P7>ij&26
zU#XGTB58^KGtf|M|8jgi(3v0H3^o>T7UzGPSf-nS`epa=wc`7QzO}P21E)4M=oc1>
z^My|~LTA=PXPyY9(7CS$zLuW(zM;?je;nUvzqa0f?Ypz3_WoDe^?%ExzLk3|2ELIH
zw;ASh1<VIg!Y2nCLWU^H3y~j!N00xyhqnEdhwlwG3iI%`cHRfJEmBJVPQts2OzW22
zT>{PaF&{lq9M~q%tPSmAv)$ZCL&d?hrq74B35ZYHpEysWyC`nIP0pR)B`U4oX;$eC
HzU2P^23ca{

literal 0
HcmV?d00001

diff --git a/topmost.py b/topmost.py
new file mode 100644
index 0000000..e2efcb2
--- /dev/null
+++ b/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()
\ No newline at end of file
diff --git a/wordfreq.py b/wordfreq.py
index 5e19758..2ce24cb 100644
--- a/wordfreq.py
+++ b/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 == " ":
-		return CharType.SPACE
+	elif char == " " or char == "	":
+		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))
\ No newline at end of file