added model

Backend/Python/controllers/api.py

+from flask import Flask, request, url_for, redirect, render_template
+from flask_cors import CORS
+import werkzeug
+import summerise.summary as summarizeed
+import json
+import textract
+from pptx import Presentation
+import os
+
+app = Flask(__name__)
+CORS(app)
+
+
+@app.route('/summerize', methods=['GET', 'POST'])
+def summerize():
+    file = request.files['file']
+    ratio = float(request.form['ratio'])
+    filename = werkzeug.utils.secure_filename(file.filename)
+    print("\nReceived image File name : " + file.filename)
+    file.save('upload/' + filename)
+
+    f, file_extension = os.path.splitext('upload/' + filename)
+    print(file_extension)
+
+    if file_extension == '.docx':
+        text = textract.process('upload/' + filename)
+        arr = str(text).replace("\\n", "")
+        arr = arr.replace("\\t", "")
+        arr = arr.replace("\\", "")
+
+        prs = Presentation()
+
+        lyt = prs.slide_layouts[0]  # choosing a slide layout
+
+        for x in range(0, 3):
+
+            if x == 2:
+                slide = prs.slides.add_slide(lyt)  # adding a slide
+                title = slide.shapes.title  # assigning a title
+                subtitle = slide.placeholders[1]  # placeholder for subtitle
+                subtitle.text = arr
+            else:
+                slide = prs.slides.add_slide(lyt)  # adding a slide
+                title = slide.shapes.title  # assigning a title
+                subtitle = slide.placeholders[1]  # placeholder for subtitle
+                title.text = "ignore"  # title
+                subtitle.text = "ignore"  # subtitle
+        prs.save("upload/slide3.pptx")  # saving file
+        print('file saved')
+        res = summarizeed.create_sumall('upload/slide3.pptx', ratio)
+    else:
+        res = summarizeed.create_sumall('upload/' + filename, ratio)
+
+    rr = []
+    for r in res[0]:
+        rr.append(r[0].replace('"', ''))
+
+    return_str = '{ "result" : ['
+
+    for i in range(len(rr)):
+        if i == len(rr) - 1:
+            return_str += '"' + rr[i] + '"'
+        else:
+            return_str += '"' + rr[i] + '"' + ','
+    return_str += ']}'
+
+    print(return_str)
+
+    return json.loads(return_str)
+
+
+if __name__ == '__main__':
+    app.run(host="0.0.0.0", port=5005, debug=True)

Backend/Python/modules/summary.py

+import glob
+from pptx import Presentation
+import math
+import nltk
+from nltk.corpus import stopwords
+from nltk.tokenize import word_tokenize, sent_tokenize
+import textract
+import os.path
+
+import nltk
+nltk.download('stopwords')
+nltk.download('punkt')
+
+
+def create_sumall(abc, ratio):
+    if abc:
+        filename = abc
+        stop_word = ['is', 'a', 'and', 'the']
+
+        # Function to create Text summarization
+        def create_summ(text):
+            stopWords = set(stopwords.words("english"))
+            words = word_tokenize(text)
+            freqTable = dict()
+            for word in words:
+                word = word.lower()
+                if word in stopWords:
+                    continue
+                if word in freqTable:
+                    freqTable[word] += 1
+                else:
+                    freqTable[word] = 1
+
+            sentences = sent_tokenize(text)
+            sentenceValue = dict()
+
+            for sentence in sentences:
+                for word, freq in freqTable.items():
+                    if word in sentence.lower():
+                        if sentence in sentenceValue:
+                            sentenceValue[sentence] += freq
+                        else:
+                            sentenceValue[sentence] = freq
+
+            sumValues = 0
+            for sentence in sentenceValue:
+                sumValues += sentenceValue[sentence]
+
+            lensenvalu = len(sentenceValue)
+            if lensenvalu == 0:
+                lensenvalu = 1
+                average = int(sumValues / lensenvalu)
+            else:
+                average = int(sumValues / lensenvalu)
+
+            summary = ''
+            for sentence in sentences:
+                if (sentence in sentenceValue) and (sentenceValue[sentence] > (
+                        ratio * average)):
+                    summary += " " + sentence
+
+            return summary
+
+        def read_full_pptxe(filename):
+            sentences = []
+            b = []
+            a = 0
+            for eachfile in glob.glob(filename):
+                prs = Presentation(eachfile)
+                for slide in prs.slides:
+                    a = a + 1
+                    for shape in slide.shapes:
+                        if hasattr(shape, "text"):
+                            s = create_summ(shape.text.replace("\n", " "))
+                            s = str(s)
+                            if (len(s)) >= 1:
+                                f = ["Slide " + str(a) + "-" + s]
+                                sentences.append(f)
+            return sentences
+
+        def read_full_docx(filename):
+            sentences = []
+            text = textract.process(filename)
+            temp = text.split(".")
+            for t in temp:
+                sentences.append(t.replace("\n", " "))
+            return sentences
+
+        extension = os.path.splitext(filename)[1]
+
+        if extension == 'docx':
+            read_full_docx(filename)
+        else:
+            read_full_pptxe(filename)
+
+        def Convert(string):
+            li = list(string.split(" "))
+            return li
+
+        def Convert2(string):
+            li = list(string.split("\n"))
+            return li
+
+        def read_slide3(filename):
+            a = 1
+            for eachfile in glob.glob(filename):
+                prs = Presentation(eachfile)
+                for slide in prs.slides:
+                    a = a + 1
+                    for shape in slide.shapes:
+                        if hasattr(shape, "text"):
+                            if a == 4 and shape.shape_id == 3:
+                                s3 = str(shape.text)
+                                return s3
+
+        def read_full_pptx(filename, sss):
+            numberslide = []
+            numberslide.append(sss)
+            a = 0
+            for eachfile in glob.glob(filename):
+                prs = Presentation(eachfile)
+                for slide in prs.slides:
+                    a = a + 1
+                    for shape in slide.shapes:
+                        if hasattr(shape, "text"):
+                            if shape.shape_id != 2:
+                                s = shape.text.replace("\n", " ")
+                                s = str(s)
+                                if (len(s)) >= 20 and a != 3 and a != 1 and a != 2:
+                                    lo_1 = [a for a in new_l1 if a in s.lower()]
+                                    f_lo_l = round((len(lo_1) / len_of_l1) * 100)
+                                    if f_lo_l >= 50:
+                                        f = "Slide " + str(a)
+                                        numberslide.append(f)
+
+            return numberslide
+
+        loooo = Convert2(read_slide3(filename))
+
+        abc = []
+        for i in loooo:
+            l1 = Convert(i.lower())
+            new_l1 = [w for w in l1 if w not in stop_word]
+            len_of_l1 = len(new_l1)
+            read_full_pptx(filename, i)
+            abc.append(read_full_pptx(filename, i))
+
+        return (read_full_pptxe(filename), abc)
+    else:
+        print('error')