First Commit

12S4055 - STBI Project.ipynb

+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Kelompok 3 | Search Engine with Inverted Index Simulator Based on Billboard Songs Collection\n",
+    "    - 12S16003 Maria H. Siallagan\n",
+    "    - 12S16026 Yolanda Nainggolan\n",
+    "    - 12S16036 Prima Hutapea\n",
+    "    - 12S16049 Rosa Delima Mendrofa"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import string\n",
+    "import re\n",
+    "from sklearn.feature_extraction.text import CountVectorizer\n",
+    "import xml.dom.minidom as minidom\n",
+    "dcmnt_xml = minidom.parse(\"dataset_STBI.xml\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "all_doc_no = dcmnt_xml.getElementsByTagName('DOCNO')\n",
+    "all_profile = dcmnt_xml.getElementsByTagName('SONG')\n",
+    "all_date = dcmnt_xml.getElementsByTagName('ARTIST')\n",
+    "all_text = dcmnt_xml.getElementsByTagName('LYRICS')\n",
+    "all_pub = dcmnt_xml.getElementsByTagName('PUB')\n",
+    "all_page = dcmnt_xml.getElementsByTagName('PAGE')\n",
+    "\n",
+    "N_DOC_sample = len(all_doc_no)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "all_sentence_doc_sample = []\n",
+    "for i in range(N_DOC_sample):\n",
+    "    sentence_doc_sample = ' '+ all_text[i].firstChild.data\n",
+    "    all_sentence_doc_sample.append(sentence_doc_sample)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Preprocessing "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tokens_doc = []"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def remove_punc_tokenize(sentence):\n",
+    "    tokens = []\n",
+    "    for punctuation in string.punctuation:\n",
+    "        sentence = sentence.replace(punctuation,\" \")\n",
+    "    \n",
+    "    sentence = re.sub(r'^https?:\\/\\/.*[\\r\\n]*', '', sentence, flags=re.MULTILINE)\n",
+    "    for w in CountVectorizer().build_tokenizer()(sentence):\n",
+    "        tokens.append(w)\n",
+    "    return tokens"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for i in range(N_DOC):\n",
+    "    tokens_doc.append(remove_punc_tokenize(all_sentence_doc_sample[i]))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from nltk.corpus import stopwords\n",
+    "stop_words = set(stopwords.words('english'))\n",
+    "def stop_word_token(tokens):\n",
+    "    tokens = [w for w in tokens if not w in stop_words]\n",
+    "    return tokens\n",
+    "\n",
+    "for i in range(N_DOC):\n",
+    "    tokens_doc[i] = stop_word_token(tokens_doc[i])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for i in range(N_DOC):\n",
+    "    tokens_doc[i] = ([w for w in tokens_doc[i] if not any(j.isdigit() for j in w)])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from nltk.stem import PorterStemmer\n",
+    "stemmer = PorterStemmer()\n",
+    "def stemming(tokens):\n",
+    "    for i in range(0, len(tokens)):\n",
+    "        if (tokens[i] != stemmer.stem(tokens[i])):\n",
+    "            tokens[i] = stemmer.stem(tokens[i])\n",
+    "    return tokens\n",
+    "\n",
+    "\n",
+    "for i in range(N_DOC):\n",
+    "    tokens_doc[i] = stemming(tokens_doc[i])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "all_tokens = []\n",
+    "for i in range(N_DOC):\n",
+    "    for w in tokens_doc[i]:\n",
+    "        all_tokens.append(w)\n",
+    "\n",
+    "new_sentence = ' '.join([w for w in all_tokens])\n",
+    "\n",
+    "for w in CountVectorizer().build_tokenizer()(new_sentence):\n",
+    "    all_tokens.append(w)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "all_tokens = set(all_tokens)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from itertools import count\n",
+    "try: \n",
+    "    from itertools import izip as zip\n",
+    "except ImportError:\n",
+    "    pass\n",
+    "proximity_index = {}\n",
+    "for token in all_tokens:\n",
+    "    dict_doc_position = {}\n",
+    "    for n in range(N_DOC):\n",
+    "        if(token in tokens_doc[n]):\n",
+    "            dict_doc_position[all_doc_no[n].firstChild.data] = [i+1 for i, j in zip(count(), tokens_doc[n]) if j == token]\n",
+    "    proximity_index[token] = dict_doc_position"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import collections\n",
+    "proximity_index = collections.OrderedDict(sorted(proximity_index.items()))\n",
+    "for key, value in proximity_index.items():\n",
+    "    print (key, value)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

SearchEngine/InvertedIndexSimulator/admin.py

+from django.contrib import admin
+
+# Register your models here.

SearchEngine/InvertedIndexSimulator/apps.py

+from django.apps import AppConfig
+
+
+class InvertedindexsimulatorConfig(AppConfig):
+    name = 'InvertedIndexSimulator'

SearchEngine/InvertedIndexSimulator/inverted/main.py

+resource_package = __name__
+
+import string
+import re
+from sklearn.feature_extraction.text import CountVectorizer
+import string
+import re
+from sklearn.feature_extraction.text import CountVectorizer
+from nltk.corpus import stopwords
+from nltk.tokenize import sent_tokenize, word_tokenize
+from Sastrawi.Stemmer.StemmerFactory import StemmerFactory
+from itertools import count
+import collections
+import math
+from xml.etree.ElementTree import ElementTree
+
+
+##############Remove Punctuation, URL and Tokenize###################
+def remove_punc_tokenize(sentence):
+    tokens = []
+    for punctuation in string.punctuation:
+        sentence = sentence.replace(punctuation," ")
+    
+    sentence = re.sub(r'^https?:\/\/.*[\r\n]*', '', sentence, flags=re.MULTILINE)
+    for w in CountVectorizer().build_tokenizer()(sentence):
+        tokens.append(w)
+    return tokens
+
+
+##############Case Folding########################
+def to_lower(tokens):
+    tokens = [x.lower() for x in tokens]
+    return tokens
+
+def generate_ngrams(data, n):
+    ngram=[]
+    result = []
+    
+    #menampilkan hasil n-gram per dokumen
+    for i in range(len(data)):
+        sequences = [data[i][j:] for j in range(n)]
+        temp = zip(*sequences)
+        lst = list(temp)
+        result.append([" ".join(lst) for lst in lst])
+    
+    #menggabungkan n-gram semua dokumen dalam bentuk array
+    for i in range(len(result)):
+        for j in range(len(result[i])):
+            ngram.append(result[i][j])
+            
+    return ngram, result
+
+def main(query):
+
+    tree = ElementTree()
+    tree.parse("InvertedIndexSimulator/data/dataset_STBI.xml")
+
+    all_doc_no = []
+    all_headline = []
+    all_text = []
+
+    for node in tree.iter("DOCNO"):
+        all_doc_no.append(node.text)
+        
+    for node in tree.iter("SONG"):
+        all_headline.append(node.text)
+        
+    for node in tree.iter("LYRICS"):
+        all_text.append(node.text)
+
+    N_DOC = len(all_text)
+
+    all_sentence_doc = []
+    for i in range(N_DOC):
+        all_sentence_doc.append(all_headline[i] + all_text[i])
+    tokens_doc = []
+    for i in range(N_DOC):
+        tokens_doc.append(remove_punc_tokenize(all_sentence_doc[i]))
+
+    for i in range(N_DOC):
+        tokens_doc[i] = to_lower(tokens_doc[i])
+
+    stop_words = set(stopwords.words('indonesian'))
+
+    stopping = []
+    for i in range(N_DOC):
+        temp = []
+        for j in tokens_doc[i]:
+            if j not in stop_words:
+                temp.append(j)
+        stopping.append(temp)
+
+    for i in range(N_DOC):
+        tokens_doc[i] = ([w for w in stopping[i] if not any(j.isdigit() for j in w)])
+
+    factory = StemmerFactory()
+    stemmer = factory.create_stemmer()
+
+    stemming = []
+    for i in range(N_DOC):
+        temp=[]
+        for j in tokens_doc[i]:
+    #         print(j)
+            temp.append(stemmer.stem(j))
+        stemming.append(temp)
+
+    all_tokens = []
+    for i in range(N_DOC):
+        for w in stemming[i]:
+            all_tokens.append(w)
+
+    new_sentence = ' '.join([w for w in all_tokens])
+
+    for w in CountVectorizer().build_tokenizer()(new_sentence):
+        all_tokens.append(w)
+
+    all_tokens = set(all_tokens)
+    alls = []
+    for i in all_tokens:
+        alls.append(i)
+
+
+    queri=[]
+    spl = query.split()
+    for i in range(len(spl)):
+        if not spl[i].isdigit():
+            queri.append(spl[i])
+
+    punc = []
+    for i in range(len(queri)):
+        no_punc = ""
+        for j in range(len(queri[i])):
+            if queri[i][j] not in string.punctuation:            
+                no_punc = no_punc + queri[i][j]        
+        punc.append(no_punc)
+    
+    lower=[]
+    for i in range(len(punc)):
+        lower.append(punc[i].lower())
+
+    stop = []
+    for i in range(len(lower)):
+        if lower[i] not in stop_words:
+            stop.append(lower[i])
+
+    stem = []
+    for i in range(len(stop)):
+        stem.append(stemmer.stem(stop[i]))
+        
+    join_word = ' '.join([w for w in stem])
+
+    ngram, ngram_doc = generate_ngrams(stemming, len(stem))
+
+    n_gram_index = {}
+    for ngram_token in ngram:
+        doc_no = []
+        for i in range(N_DOC):
+            if(ngram_token in ngram_doc[i]):
+                doc_no.append(all_doc_no[i])
+        n_gram_index[ngram_token] = doc_no
+
+    df = []
+
+    for i in range(N_DOC):
+        count = 0
+        for j in range(len(ngram_doc[i])):
+            if join_word == ngram_doc[i][j]:
+                count+=1
+        df.append(count)
+
+    idf = []
+    for i in range(len(df)):
+        try:
+            idf.append(math.log10(N_DOC/df[i]))
+        except ZeroDivisionError:
+            idf.append(str(0))
+
+    #w(t, d)
+    #t = term
+    #d = document
+    wtd = []
+    l = []
+    for i in range(N_DOC):
+        dic = {}
+        tf = ngram_doc[i].count(join_word) # menghitung nilai tf
+        if tf != 0:
+            score = math.log10(tf) #log10(tf(t,d))
+            score+=1 # 1 + log(tf(t,d))
+            score*=idf[i] #tf * idf
+            
+            idx = all_doc_no[i]
+            judul = all_headline[i]
+            
+            dic['docno'] = idx
+            dic['judul'] = judul
+            dic['score'] = score
+            
+            l.append(dic)
+    wtd.append(l) # [i+1] = defenisi nomor dokumen; score = wtd
+    #         print(score)
+
+    hasil = []
+    hasil.append(sorted(wtd[0], key = lambda x : x['score'], reverse = True))
+
+    return hasil
+
+def detail(nomor):
+    tree = ElementTree()
+    tree.parse("apps/data/BukuNyanyianHKBP.xml")
+
+    all_doc_no = []
+    all_headline = []
+    all_text = []
+
+    for node in tree.iter("DOCNO"):
+        all_doc_no.append(node.text)
+        
+    for node in tree.iter("SONG"):
+        # all_headline.append(node.text.replace("\n"," "))
+        all_headline.append(node.text)
+        head = all_headline
+        
+    for node in tree.iter("TEXT"):
+        # all_text.append(node.text.replace("\n"," "))
+        all_text.append(node.text)
+
+    N_DOC = len(all_text)
+    text = []
+    judul=[]
+    hasil = []
+    id = str(nomor)
+    for i in range(N_DOC):
+        check = all_doc_no[i]
+        if check == id:
+            text = all_text[i]
+            judul = all_headline[i]
+            return text,judul
\ No newline at end of file

SearchEngine/InvertedIndexSimulator/models.py

+from django.db import models
+
+# Create your models here.

SearchEngine/InvertedIndexSimulator/templates/apps/home.html

+<!DOCTYPE html>
+<html lang="en">
+
+<head>
+
+  <meta charset="utf-8">
+  <meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no">
+  <meta name="description" content="">
+  <meta name="author" content="">
+
+  <title>Inverted Index</title>
+
+  <!-- Bootstrap core CSS -->
+  <link href="../../static/assets/vendor/bootstrap/css/bootstrap.min.css" rel="stylesheet">
+
+  <!-- Custom fonts for this template -->
+  <link href="../../static/assets/vendor/fontawesome-free/css/all.min.css" rel="stylesheet">
+  <link href="../../static/assets/vendor/simple-line-icons/css/simple-line-icons.css" rel="stylesheet" type="text/css">
+  <link href="https://fonts.googleapis.com/css?family=Lato:300,400,700,300italic,400italic,700italic" rel="stylesheet" type="text/css">
+
+  <!-- Custom styles for this template -->
+  <link href="../../static/assets/css/landing-page.min.css" rel="stylesheet">
+
+</head>
+
+<body>
+
+  <header class="masthead text-white text-center">
+    <div class="overlay"></div>
+    <div class="container">
+      <div class="row">
+        <div class="col-xl-9 mx-auto">
+          <h1 class="mb-5">Pilih Kategori Billboard Music</h1>
+                <div class="row">
+                  <div class="col-12 col-md-4">
+                    <a href="/index" class="btn btn-block btn-lg btn-primary">Mancanegara</a>
+                  </div>
+                  <div class="col-12 col-md-4">
+                    <a href="/index2" class="btn btn-block btn-lg btn-primary">Indonesia</a>
+                  </div>
+                  <div class="col-12 col-md-4">
+                    <a href="/index3" class="btn btn-block btn-lg btn-primary">Top Hits</a>
+                  </div>
+                      
+              
+        </div>
+        </div>
+      </div>
+    </div>
+  </header>
+
+ <section class="features-icons bg-light text-center">
+    <div class="container">
+      <div class="row">
+        <div class="col-lg-4">
+          <div class="features-icons-item mx-auto mb-5 mb-lg-0 mb-lg-3">
+            <div class="features-icons-icon d-flex">
+              <i class="icon-screen-desktop m-auto text-primary"></i>
+            </div>
+            <h3>Fully Responsive</h3>
+            <p class="lead mb-0">This theme will look great on any device, no matter the size!</p>
+          </div>
+        </div>
+        <div class="col-lg-4">
+          <div class="features-icons-item mx-auto mb-5 mb-lg-0 mb-lg-3">
+            <div class="features-icons-icon d-flex">
+              <i class="icon-layers m-auto text-primary"></i>
+            </div>
+            <h3>Bootstrap 4 Ready</h3>
+            <p class="lead mb-0">Featuring the latest build of the new Bootstrap 4 framework!</p>
+          </div>
+        </div>
+        <div class="col-lg-4">
+          <div class="features-icons-item mx-auto mb-0 mb-lg-3">
+            <div class="features-icons-icon d-flex">
+              <i class="icon-check m-auto text-primary"></i>
+            </div>
+            <h3>Easy to Use</h3>
+            <p class="lead mb-0">Ready to use with your own content, or customize the source files!</p>
+          </div>
+        </div>
+      </div>
+    </div>
+  </section>
+
+<section class="showcase">
+    <div class="container-fluid p-0">
+      <div class="row no-gutters">
+
+        <div class="col-lg-6 order-lg-2 text-white showcase-img" style="background-image: url('img/bg-showcase-1.jpg');"></div>
+        <div class="col-lg-6 order-lg-1 my-auto showcase-text">
+          <h2>Fully Responsive Design</h2>
+          <p class="lead mb-0">When you use a theme created by Start Bootstrap, you know that the theme will look great on any device, whether it's a phone, tablet, or desktop the page will behave responsively!</p>
+        </div>
+      </div>
+      <div class="row no-gutters">
+        <div class="col-lg-6 text-white showcase-img" style="background-image: url('img/bg-showcase-2.jpg');"></div>
+        <div class="col-lg-6 my-auto showcase-text">
+          <h2>Updated For Bootstrap 4</h2>
+          <p class="lead mb-0">Newly improved, and full of great utility classes, Bootstrap 4 is leading the way in mobile responsive web development! All of the themes on Start Bootstrap are now using Bootstrap 4!</p>
+        </div>
+      </div>
+      <div class="row no-gutters">
+        <div class="col-lg-6 order-lg-2 text-white showcase-img" style="background-image: url('img/bg-showcase-3.jpg');"></div>
+        <div class="col-lg-6 order-lg-1 my-auto showcase-text">
+          <h2>Easy to Use &amp; Customize</h2>
+          <p class="lead mb-0">Landing Page is just HTML and CSS with a splash of SCSS for users who demand some deeper customization options. Out of the box, just add your content and images, and your new landing page will be ready to go!</p>
+        </div>
+      </div>
+    </div>
+  </section> --> 
+
+<section class="testimonials text-center bg-light">
+    <div class="container">
+      <h2 class="mb-5">What people are saying...</h2>
+      <div class="row">
+        <div class="col-lg-4">
+          <div class="testimonial-item mx-auto mb-5 mb-lg-0">
+            <img class="img-fluid rounded-circle mb-3" src="img/testimonials-1.jpg" alt="">
+            <h5>Margaret E.</h5>
+            <p class="font-weight-light mb-0">"This is fantastic! Thanks so much guys!"</p>
+          </div>
+        </div>
+        <div class="col-lg-4">
+          <div class="testimonial-item mx-auto mb-5 mb-lg-0">
+            <img class="img-fluid rounded-circle mb-3" src="img/testimonials-2.jpg" alt="">
+            <h5>Fred S.</h5>
+            <p class="font-weight-light mb-0">"Bootstrap is amazing. I've been using it to create lots of super nice landing pages."</p>
+          </div>
+        </div>
+        <div class="col-lg-4">
+          <div class="testimonial-item mx-auto mb-5 mb-lg-0">
+            <img class="img-fluid rounded-circle mb-3" src="img/testimonials-3.jpg" alt="">
+            <h5>Sarah W.</h5>
+            <p class="font-weight-light mb-0">"Thanks so much for making these free resources available to us!"</p>
+          </div>
+        </div>
+      </div>
+    </div>
+  </section> -->
+
+ <section class="call-to-action text-white text-center">
+    <div class="overlay"></div>
+    <div class="container">
+      <div class="row">
+        <div class="col-xl-9 mx-auto">
+          <h2 class="mb-4">Ready to get started? Sign up now!</h2>
+        </div>
+        <div class="col-md-10 col-lg-8 col-xl-7 mx-auto">
+          <form>
+            <div class="form-row">
+              <div class="col-12 col-md-9 mb-2 mb-md-0">
+                <input type="email" class="form-control form-control-lg" placeholder="Enter your email...">
+              </div>
+              <div class="col-12 col-md-3">
+                <button type="submit" class="btn btn-block btn-lg btn-primary">Sign up!</button>
+              </div>
+            </div>
+          </form>
+        </div>
+      </div>
+    </div>
+  </section> -->
+
+   <footer class="footer bg-light">
+    <div class="container">
+      <div class="row">
+        <div class="col-lg-6 h-100 text-center text-lg-left my-auto">
+          <ul class="list-inline mb-2">
+            <li class="list-inline-item">
+              <a href="#">About</a>
+            </li>
+            <li class="list-inline-item">&sdot;</li>
+            <li class="list-inline-item">
+              <a href="#">Contact</a>
+            </li>
+            <li class="list-inline-item">&sdot;</li>
+            <li class="list-inline-item">
+              <a href="#">Terms of Use</a>
+            </li>
+            <li class="list-inline-item">&sdot;</li>
+            <li class="list-inline-item">
+              <a href="#">Privacy Policy</a>
+            </li>
+          </ul>
+          <p class="text-muted small mb-4 mb-lg-0">&copy; Your Website 2019. All Rights Reserved.</p>
+        </div>
+        <div class="col-lg-6 h-100 text-center text-lg-right my-auto">
+          <ul class="list-inline mb-0">
+            <li class="list-inline-item mr-3">
+              <a href="#">
+                <i class="fab fa-facebook fa-2x fa-fw"></i>
+              </a>
+            </li>
+            <li class="list-inline-item mr-3">
+              <a href="#">
+                <i class="fab fa-twitter-square fa-2x fa-fw"></i>
+              </a>
+            </li>
+            <li class="list-inline-item">
+              <a href="#">
+                <i class="fab fa-instagram fa-2x fa-fw"></i>
+              </a>
+            </li>
+          </ul>
+        </div>
+      </div>
+    </div>
+  </footer> -->
+
+  <!-- Bootstrap core JavaScript -->
+  <script src="../../static/assets/vendor/jquery/jquery.min.js"></script>
+  <script src="../../static/assets/vendor/bootstrap/js/bootstrap.bundle.min.js"></script>
+
+</body>
+
+</html>

SearchEngine/InvertedIndexSimulator/templates/apps/index.html

+<!DOCTYPE html>
+<html lang="en">
+
+<head>
+
+  <meta charset="utf-8">
+  <meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no">
+  <meta name="description" content="">
+  <meta name="author" content="">
+  
+  <title>Inverted Index</title>
+
+  <!-- Bootstrap core CSS -->
+  <link href="../../static/assets/vendor/bootstrap/css/bootstrap.min.css" rel="stylesheet">
+
+  <!-- Custom fonts for this template -->
+  <link href="../../static/assets/vendor/fontawesome-free/css/all.min.css" rel="stylesheet">
+  <link href="../../static/assets/vendor/simple-line-icons/css/simple-line-icons.css" rel="stylesheet" type="text/css">
+  <link href="https://fonts.googleapis.com/css?family=Lato:300,400,700,300italic,400italic,700italic" rel="stylesheet" type="text/css">
+
+  <!-- Custom styles for this template -->
+  <link href="../../static/assets/css/landing-page.min.css" rel="stylesheet">
+
+</head>
+
+<body>
+
+  <!-- Navigation -->
+  <nav class="navbar navbar-light bg-light static-top">
+    <div class="container">
+      <a class="navbar-brand" href="/">CariLagu</a>
+      <!-- <a class="btn btn-primary" href="#">Pilih Buku</a>
+         -->
+    </div>
+  </nav>
+
+  <!-- Masthead -->
+  <header class="masthead text-white text-center">
+    <div class="overlay"></div>
+    <div class="container">
+      <div class="row">
+        <div class="col-xl-9 mx-auto">
+          <h1 class="mb-5">Silahkan masukkan lirik dari lagu yang ingin Anda temukan</h1>
+        </div>
+        <div class="col-md-10 col-lg-8 col-xl-7 mx-auto">
+          <form method="POST" action="/result/">
+            {% csrf_token %}
+            <div class="form-row">
+              <div class="col-12 col-md-9 mb-2 mb-md-0">
+                <input type="text" class="form-control form-control-lg" name="querysearch" placeholder="Masukkan Query Anda...">
+              </div>
+              <div class="col-12 col-md-3">
+                <button type="submit" class="btn btn-block btn-lg btn-primary">Cari!</button>
+              </div>
+            </div>
+          </form>
+        </div>
+      </div>
+    </div>
+  </header>
+  
+  <!-- Bootstrap core JavaScript -->
+  <script src="../../static/assets/vendor/jquery/jquery.min.js"></script>
+  <script src="../../static/assets/vendor/bootstrap/js/bootstrap.bundle.min.js"></script>
+
+</body>
+
+</html>

SearchEngine/InvertedIndexSimulator/templates/apps/lyric.html

+<!DOCTYPE html>
+<html lang="en">
+
+<head>
+
+  <meta charset="utf-8">
+  <meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no">
+  <meta name="description" content="">
+  <meta name="author" content="">
+  
+  <title>Inverted Index</title>
+
+  <!-- Bootstrap core CSS -->
+  <link href="../../static/assets/vendor/bootstrap/css/bootstrap.min.css" rel="stylesheet">
+
+  <!-- Custom fonts for this template -->
+  <link href="../../static/assets/vendor/fontawesome-free/css/all.min.css" rel="stylesheet">
+  <link href="../../static/assets/vendor/simple-line-icons/css/simple-line-icons.css" rel="stylesheet" type="text/css">
+  <link href="https://fonts.googleapis.com/css?family=Lato:300,400,700,300italic,400italic,700italic" rel="stylesheet" type="text/css">
+
+  <!-- Custom styles for this template -->
+  <link href="../../static/assets/css/landing-page.min.css" rel="stylesheet">
+
+</head>
+
+<body>
+
+  <!-- Navigation -->
+  <nav class="navbar navbar-light bg-light static-top">
+    <div class="container">
+      <a class="navbar-brand" href="/">CariLagu</a>
+      <!-- <a class="btn btn-primary" href="#">Pilih Buku</a>
+         -->
+    </div>
+  </nav>
+
+  <!-- Masthead -->
+  <!-- <header class="masthead text-white text-center">
+    <div class="overlay"></div>
+    <div class="container">
+      <div class="row">
+        <div class="col-xl-9 mx-auto">
+          <h1 class="mb-5">Silahkan masukkan lirik dari lagu yang ingin Anda temukan</h1>
+        </div>
+        <div class="col-md-10 col-lg-8 col-xl-7 mx-auto">
+          <form method="POST" action="/search">
+            <div class="form-row">
+              <div class="col-12 col-md-9 mb-2 mb-md-0">
+                <input type="text" class="form-control form-control-lg" name="querysearch" placeholder="Masukkan Query Anda...">
+              </div>
+              <div class="col-12 col-md-3">
+                <button type="submit" class="btn btn-block btn-lg btn-primary">Cari!</button>
+              </div>
+            </div>
+          </form>
+        </div>
+      </div>
+    </div>
+  </header> -->
+
+
+  <!-- Testimonials -->
+  <section class="testimonials text-center bg-light">
+    <div class="container">
+      
+        <h2 class="mb-3">Buku Nyanyian HKBP</h2>
+        <h4 class="mb-3">No.{{no}} - {{judul}}  </h2>
+        <p>{{text}}</p>
+
+    </div>
+
+  </section>
+
+  
+  <!-- Bootstrap core JavaScript -->
+  <script src="../../static/assets/vendor/jquery/jquery.min.js"></script>
+  <script src="../../static/assets/vendor/bootstrap/js/bootstrap.bundle.min.js"></script>
+
+</body>
+
+</html>

SearchEngine/InvertedIndexSimulator/templates/apps/result.html

+<!DOCTYPE html>
+<html lang="en">
+
+<head>
+
+  <meta charset="utf-8">
+  <meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no">
+  <meta name="description" content="">
+  <meta name="author" content="">
+  
+  <title>Inverted Index</title>
+
+  <!-- Bootstrap core CSS -->
+  <link href="../../static/assets/vendor/bootstrap/css/bootstrap.min.css" rel="stylesheet">
+
+  <!-- Custom fonts for this template -->
+  <link href="../../static/assets/vendor/fontawesome-free/css/all.min.css" rel="stylesheet">
+  <link href="../../static/assets/vendor/simple-line-icons/css/simple-line-icons.css" rel="stylesheet" type="text/css">
+  <link href="https://fonts.googleapis.com/css?family=Lato:300,400,700,300italic,400italic,700italic" rel="stylesheet" type="text/css">
+
+  <!-- Custom styles for this template -->
+  <link href="../../static/assets/css/landing-page.min.css" rel="stylesheet">
+
+</head>
+
+<body>
+
+  <!-- Navigation -->
+  <nav class="navbar navbar-light bg-light static-top">
+    <div class="container">
+      <a class="navbar-brand" href="/">CariLagu</a>
+      <!-- <a class="btn btn-primary" href="#">Pilih Buku</a>
+         -->
+    </div>
+  </nav>
+  <!-- Testimonials -->
+  <section class="testimonials text-center bg-light">
+    <div class="container">
+      <h2 class="mb-5">Lagu yang sesuai dengan "{{ query }}"</h2>
+      {% if hasil %}
+      <div class="row">
+        {% for i in hasil %}
+          {% for j in i %}  
+          
+            <div class="col-lg-4">
+              <div class="testimonial-item mx-auto mb-5 mb-lg-0">
+                <img class="img-fluid rounded-circle mb-3" src="../../static/img/hkbp.jpg" alt="">
+                <h5><a href="/lyric/{{j.docno}}">Lagu No:{{ j.docno }}</a></h5>
+                <h5>"{{ j.judul }}"</h5>
+                <p class="font-weight-light mb-0">score :{{ j.score }}</p>
+              </div>
+            </div>      
+          {% endfor %}
+        {% endfor %}
+      </div>
+
+      {% else %}
+      <h2 class="mb-5">Lagu dengan lirik: "{{ query }}" tidak ditemukan</h2>
+      {% endif %}
+    </div>
+    
+  </section>
+
+  
+  <!-- Bootstrap core JavaScript -->
+  <script src="../../static/assets/vendor/jquery/jquery.min.js"></script>
+  <script src="../../static/assets/vendor/bootstrap/js/bootstrap.bundle.min.js"></script>
+
+</body>
+
+</html>

SearchEngine/InvertedIndexSimulator/tests.py

+from django.test import TestCase
+
+# Create your tests here.

SearchEngine/InvertedIndexSimulator/urls.py

+from django.urls import path
+from apps import views
+from . import views
+
+app_name = 'InvertedIndexSimulator'
+
+
+
+urlpatterns = [
+    path('', views.home),
+    path('index/', views.index),
+    
+    path('result/', views.result),
+    
+    path('lyric/<int:id>', views.lyric, name='lyric'),
+    
+]
\ No newline at end of file

SearchEngine/InvertedIndexSimulator/views.py

+from django.shortcuts import render
+from django.http import HttpResponse
+from InvertedIndexSimulator.inverted import main
+# Create your views here.
+# def index(request):
+#     return HttpResponse("Hello, world. You're at the polls index.")
+
+def home(request):
+    return render(request, 'apps/home.html')
+
+def index(request):
+    return render(request, 'apps/index.html')
+
+
+def lyric(request,id):
+    
+    text, judul = main.detail(id)
+    content={
+        'no': id,
+        'judul':judul,
+        'text':text
+    }
+    return render(request, 'apps/lyric.html', content)
+
+def result(request):
+    #%%
+    # proximity_index = collections.OrderedDict(sorted(proximity_index.items()))
+    # for key, value in proximity_index.items():
+    #     # print (key, value)
+    if request.method == 'POST':
+        query = request.POST['querysearch']
+        hasil= main.main(query)
+
+        content={
+            'hasil':hasil,
+            'query':query
+        }
+        return render(request, 'apps/result.html',content)

SearchEngine/SearchEngine/settings.py

+"""
+Django settings for SearchEngine project.
+
+Generated by 'django-admin startproject' using Django 1.11.29.
+
+For more information on this file, see
+https://docs.djangoproject.com/en/1.11/topics/settings/
+
+For the full list of settings and their values, see
+https://docs.djangoproject.com/en/1.11/ref/settings/
+"""
+
+import os
+
+# Build paths inside the project like this: os.path.join(BASE_DIR, ...)
+BASE_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+
+
+# Quick-start development settings - unsuitable for production
+# See https://docs.djangoproject.com/en/1.11/howto/deployment/checklist/
+
+# SECURITY WARNING: keep the secret key used in production secret!
+SECRET_KEY = 'xd@mmg2jpyfctv%tfb1qtb2y7u8g&jy^dr^p_%_qlswh4j50^z'
+
+# SECURITY WARNING: don't run with debug turned on in production!
+DEBUG = True
+
+ALLOWED_HOSTS = []
+
+
+# Application definition
+
+INSTALLED_APPS = [
+    'django.contrib.admin',
+    'django.contrib.auth',
+    'django.contrib.contenttypes',
+    'django.contrib.sessions',
+    'django.contrib.messages',
+    'django.contrib.staticfiles',
+    'InvertedIndexSimulator',
+]
+
+MIDDLEWARE = [
+    'django.middleware.security.SecurityMiddleware',
+    'django.contrib.sessions.middleware.SessionMiddleware',
+    'django.middleware.common.CommonMiddleware',
+    'django.middleware.csrf.CsrfViewMiddleware',
+    'django.contrib.auth.middleware.AuthenticationMiddleware',
+    'django.contrib.messages.middleware.MessageMiddleware',
+    'django.middleware.clickjacking.XFrameOptionsMiddleware',
+]
+
+ROOT_URLCONF = 'SearchEngine.urls'
+
+TEMPLATES = [
+    {
+        'BACKEND': 'django.template.backends.django.DjangoTemplates',
+        'DIRS': [],
+        'APP_DIRS': True,
+        'OPTIONS': {
+            'context_processors': [
+                'django.template.context_processors.debug',
+                'django.template.context_processors.request',
+                'django.contrib.auth.context_processors.auth',
+                'django.contrib.messages.context_processors.messages',
+            ],
+        },
+    },
+]
+
+WSGI_APPLICATION = 'SearchEngine.wsgi.application'
+
+
+# Database
+# https://docs.djangoproject.com/en/1.11/ref/settings/#databases
+
+DATABASES = {
+    'default': {
+        'ENGINE': 'django.db.backends.sqlite3',
+        'NAME': os.path.join(BASE_DIR, 'db.sqlite3'),
+    }
+}
+
+
+# Password validation
+# https://docs.djangoproject.com/en/1.11/ref/settings/#auth-password-validators
+
+AUTH_PASSWORD_VALIDATORS = [
+    {
+        'NAME': 'django.contrib.auth.password_validation.UserAttributeSimilarityValidator',
+    },
+    {
+        'NAME': 'django.contrib.auth.password_validation.MinimumLengthValidator',
+    },
+    {
+        'NAME': 'django.contrib.auth.password_validation.CommonPasswordValidator',
+    },
+    {
+        'NAME': 'django.contrib.auth.password_validation.NumericPasswordValidator',
+    },
+]
+
+
+# Internationalization
+# https://docs.djangoproject.com/en/1.11/topics/i18n/
+
+LANGUAGE_CODE = 'en-us'
+
+TIME_ZONE = 'UTC'
+
+USE_I18N = True
+
+USE_L10N = True
+
+USE_TZ = True
+
+
+# Static files (CSS, JavaScript, Images)
+# https://docs.djangoproject.com/en/1.11/howto/static-files/
+
+STATIC_URL = '/static/'

SearchEngine/SearchEngine/urls.py

+"""SearchEngine URL Configuration
+
+The `urlpatterns` list routes URLs to views. For more information please see:
+    https://docs.djangoproject.com/en/1.11/topics/http/urls/
+Examples:
+Function views
+    1. Add an import:  from my_app import views
+    2. Add a URL to urlpatterns:  url(r'^$', views.home, name='home')
+Class-based views
+    1. Add an import:  from other_app.views import Home
+    2. Add a URL to urlpatterns:  url(r'^$', Home.as_view(), name='home')
+Including another URLconf
+    1. Import the include() function: from django.conf.urls import url, include
+    2. Add a URL to urlpatterns:  url(r'^blog/', include('blog.urls'))
+"""
+from django.conf.urls import url
+from django.contrib import admin
+from django.urls import include, path
+from InvertedIndexSimulator import views
+
+urlpatterns = [
+    path('', views.home),
+    path('index/', views.index),
+    
+    path('result/', views.result),
+    
+    path('lyric/<int:id>', views.lyric, name='lyric'),
+    
+]

SearchEngine/SearchEngine/wsgi.py

+"""
+WSGI config for SearchEngine project.
+
+It exposes the WSGI callable as a module-level variable named ``application``.
+
+For more information on this file, see
+https://docs.djangoproject.com/en/1.11/howto/deployment/wsgi/
+"""
+
+import os
+
+from django.core.wsgi import get_wsgi_application
+
+os.environ.setdefault("DJANGO_SETTINGS_MODULE", "SearchEngine.settings")
+
+application = get_wsgi_application()

SearchEngine/manage.py

+#!/usr/bin/env python
+import os
+import sys
+
+if __name__ == "__main__":
+    os.environ.setdefault("DJANGO_SETTINGS_MODULE", "SearchEngine.settings")
+    try:
+        from django.core.management import execute_from_command_line
+    except ImportError:
+        # The above import may fail for some other reason. Ensure that the
+        # issue is really that Django is missing to avoid masking other
+        # exceptions on Python 2.
+        try:
+            import django
+        except ImportError:
+            raise ImportError(
+                "Couldn't import Django. Are you sure it's installed and "
+                "available on your PYTHONPATH environment variable? Did you "
+                "forget to activate a virtual environment?"
+            )
+        raise
+    execute_from_command_line(sys.argv)