Merge branch 'IT17100908' into 'QA_RELEASE'

It17100908

See merge request !46

FirstApp/templates/FirstApp/template.html

@@ -118,7 +118,7 @@
                 <div id="collapseThree" class="collapse" aria-labelledby="headingThree" data-parent="#accordionSidebar">
                     <div class="bg-white py-2 collapse-inner rounded">
                         <h6 class="collapse-header">Components:</h6>
-                        <a class="collapse-item" href="/summary/record">Record Lecture</a>
+<!--                        <a class="collapse-item" href="/summary/record">Record Lecture</a>-->
                         <a class="collapse-item" href="/summary/lecture">Summarization</a>
                     </div>
                 </div>

LectureSummarizingApp/ExtractKeySentences.py

 import nltk
-read_lines = [line.rstrip('\n') for line in open("audioToText01.txt", "r")]
-sentences_list = []
-sentence_list = nltk.sent_tokenize(read_lines)
-word_search = "important"
-sentences_with_word = []
-for sentence in sentences_list:
-    if sentence.count(word_search)>0:
-        sentences_with_word.append(sentence)
-
-words_search = ["exam", "assignment"]
-word_sentence_dictionary = {"exam":[],"assignment":[]}
-
-for word in words_search:
+import os
+from fpdf import FPDF
+
+def LectureNotice(notice_name):
+
+    BASE_DIR = os.path.dirname(os.path.abspath(__file__))
+    FILE_PATH = os.path.join(BASE_DIR, "speechToText\\{}".format(notice_name))
+    DESTINATION_DIR = os.path.dirname(os.path.join(BASE_DIR, "LectureSummarizingApp\\Notices\\sample.txt"))
+    print('destination directory: ', DESTINATION_DIR)
+
+    read_lines = [line.rstrip('\n') for line in open("audioToText01.txt", "r")]
+    sentences_list = []
+    sentence_list = nltk.sent_tokenize(read_lines)
+    word_search = "important"
     sentences_with_word = []
-    for sentence in sentences_list:
-        if sentence.count(word)>0:
+    for sentence in sentence_list:
+        if sentence.count(word_search)>0:
             sentences_with_word.append(sentence)
-            word_sentence_dictionary[word] = sentences_with_word
\ No newline at end of file
+
+    words_search = ["exam", "assignment"]
+    word_sentence_dictionary = {"exam":[],"assignment":[]}
+
+    for word in words_search:
+        sentences_with_word = []
+        for sentence in sentences_list:
+            if sentence.count(word)>0:
+                sentences_with_word.append(sentence)
+                word_sentence_dictionary[word] = sentences_with_word
+
+
+def SaveNotices():
+    pdf = FPDF()
+    # Add a page
+    pdf.add_page()
+    # set style and size of font
+    # that you want in the pdf
+    pdf.set_font("Arial", size=15)
+
+    # open the text file in read mode
+    f = open("Summary01.txt", "r")
+
+    # insert the texts in pdf
+    for x in f:
+        pdf.cell(200, 10, txt=x, ln=1, align='C')
+
+    # save the pdf with name .pdf
+    pdf.output("summary01.pdf")
\ No newline at end of file

LectureSummarizingApp/Summary.py

 from spacy.lang.pt.stop_words import STOP_WORDS
 from sklearn.feature_extraction.text import CountVectorizer
 import pt_core_news_sm
+import os
+from fpdf import FPDF
 
+def LectureSummary(summary_name):
+
+    # BASE_DIR = os.path.dirname(os.path.abspath(__file__))
+    # FILE_PATH = os.path.join(BASE_DIR, "speechToText\\{}".format(summary_name))
+    # DESTINATION_DIR = os.path.dirname(os.path.join(BASE_DIR, "LectureSummarizingApp\\summary\\sample.txt"))
+    # print('destination directory: ', DESTINATION_DIR)
 
 # Reading the file
-nlp = pt_core_news_sm.load()
-with open("audioToText01.txt", "r", encoding="utf-8") as f:
-    text = " ".join(f.readlines())
+    nlp = pt_core_news_sm.load()
+    with open("audioToText.txt", "r", encoding="utf-8") as f:
+        text = " ".join(f.readlines())
 
-doc = nlp(text)
+    doc = nlp(text)
 
 #calculating the word frequency
-corpus = [sent.text.lower() for sent in doc.sents ]
-cv = CountVectorizer(stop_words=list(STOP_WORDS))
-cv_fit=cv.fit_transform(corpus)
-word_list = cv.get_feature_names()
-count_list = cv_fit.toarray().sum(axis=0)
-word_frequency = dict(zip(word_list,count_list))
-
-
-val=sorted(word_frequency.values())
-higher_word_frequencies = [word for word,freq in word_frequency.items() if freq in val[-3:]]
-print("\nWords with higher frequencies: ", higher_word_frequencies)
-# gets relative frequency of words
-higher_frequency = val[-1]
-for word in word_frequency.keys():
-    word_frequency[word] = (word_frequency[word]/higher_frequency)
+    corpus = [sent.text.lower() for sent in doc.sents ]
+    cv = CountVectorizer(stop_words=list(STOP_WORDS))
+    cv_fit=cv.fit_transform(corpus)
+    word_list = cv.get_feature_names()
+    count_list = cv_fit.toarray().sum(axis=0)
+    word_frequency = dict(zip(word_list,count_list))
+
+
+    val=sorted(word_frequency.values())
+    higher_word_frequencies = [word for word,freq in word_frequency.items() if freq in val[-3:]]
+    print("\nWords with higher frequencies: ", higher_word_frequencies)
+    # gets relative frequency of words
+    higher_frequency = val[-1]
+    for word in word_frequency.keys():
+        word_frequency[word] = (word_frequency[word]/higher_frequency)
 
 #calculating sentence rank and taking top ranked sentences for the summary
-sentence_rank={}
-for sent in doc.sents:
-    for word in sent :
-        if word.text.lower() in word_frequency.keys():
-            if sent in sentence_rank.keys():
-                sentence_rank[sent]+=word_frequency[word.text.lower()]
-            else:
-                sentence_rank[sent]=word_frequency[word.text.lower()]
-top_sentences=(sorted(sentence_rank.values())[::-1])
-top_sent=top_sentences[:3]
-
-
-
-summary=[]
-for sent,strength in sentence_rank.items():
-    if strength in top_sent:
-        summary.append(sent)
-    else:
-        continue
-for i in summary:
-    file = open('Summary01.txt', 'w')
-    file.write(str(i))
-    file.close()
\ No newline at end of file
+    sentence_rank={}
+    for sent in doc.sents:
+        for word in sent :
+            if word.text.lower() in word_frequency.keys():
+                if sent in sentence_rank.keys():
+                    sentence_rank[sent]+=word_frequency[word.text.lower()]
+                else:
+                    sentence_rank[sent]=word_frequency[word.text.lower()]
+    top_sentences=(sorted(sentence_rank.values())[::-1])
+    top_sent=top_sentences[:3]
+
+    summary=[]
+    for sent,strength in sentence_rank.items():
+        if strength in top_sent:
+            summary.append(sent)
+        else:
+            continue
+    for i in summary:
+        file = open('Summary01.txt', 'w')
+        file.write(str(i))
+        file.close()
+
+
+def SaveSummary():
+    pdf = FPDF()
+    # Add a page
+    pdf.add_page()
+    # set style and size of font
+    # that you want in the pdf
+    pdf.set_font("Arial", size=15)
+
+    # open the text file in read mode
+    f = open("Summary01.txt", "r")
+
+    # insert the texts in pdf
+    for x in f:
+        pdf.cell(200, 10, txt=x, ln=1, align='C')
+
+    # save the pdf with name .pdf
+    pdf.output("summary01.pdf")
\ No newline at end of file

LectureSummarizingApp/api.py

@@ -15,6 +15,7 @@ import datetime
 
 # APIs used in Lecture Summarizing Component
 from .noise import noise_removal
+from .speech_to_text import speech_to_text
 
 
 class LectureAudioAPI(APIView):
@@ -73,35 +74,36 @@ class audioNoiseRemovedList(APIView):
 class audioToTextList(APIView):
 
     def get(self, request):
-        lecture_speech_to_text_id = LectureSpeechToText.objects.all()
-        serializer = LectureSpeechToTextSerializer(lecture_speech_to_text_id, many=True)
+        #lecture_speech_to_text_id = LectureSpeechToText.objects.all()
+        #serializer = LectureSpeechToTextSerializer(lecture_speech_to_text_id, many=True)
+        audio_to_text_list = LectureSpeechToText.objects.order_by('lecture_speech_to_text_id').last()
         # return Response(serializer.data)
 
-        # video_name = request.query_params.get("video_name")
-        #
-        # print('video name: ', video_name)
-        #
-        # # nr.noise_removalll(video_name)
-        # noise_removal(video_name)
+        speech_to_text_name = request.query_params.get("speech_to_text_name")
 
-        # stt.speech_to_text(video_name)
+        print('file name: ', speech_to_text_name)
+        id = int(request.query_params.get("id"))
+
+        # generate new id for speech to text file
+        new_speech_to_text_id = generate_new_id(audio_to_text_list.new_speech_to_text_id)
+
+        speech_to_text(speech_to_text_name)
+
+        LectureSpeechToText(
+            lecture_speech_to_text_id=new_speech_to_text_id,
+            lecture_audio_id=id,
+            audio_original_text=speech_to_text_name
+        ).save()
 
         return Response({
-            "response": "successful"
+            "response": Response.status_code
         })
 
     def post(self, request):
-
-        # video_name = request.data["video_name"]
-        #
-        # print('video name: ', video_name)
-        #
-        # stt.speech_to_text(video_name)
-
         LectureSpeechToText(
             lecture_speech_to_text_id=request.data["lecture_speech_to_text_id"],
             lecture_audio_id=request.data["lecture_audio_id"],
-            audio_original_text=request.data["audio_original_text"]
+            audio_original_text=request.data["audio_original_text"],
         ).save()
         return Response({"response": request.data})
 
@@ -110,13 +112,29 @@ class lectureSummaryList(APIView):
 
     def get(self, request):
         lecture_audio_summary_id = LectureAudioSummary.objects.all()
-        serializer = LectureAudioSummarySerializer(lecture_audio_summary_id, many=True)
-        return Response(serializer.data)
+        # serializer = LectureAudioSummarySerializer(lecture_audio_summary_id, many=True)
+        # return Response(serializer.data)
 
-    def post(self, request):
+        lecture_summary_list = LectureAudioSummary.objects.order_by('lecture_summary_list').last()
+
+        lecture_summary_name = request.query_params.get("lecture_summary_name")
+        id = int(request.query_params.get("id"))
+        current_date = datetime.datetime.now().date()
+
+        # generate new id for summary
+        lecture_summary_id = generate_new_id(lecture_summary_list.lecture_summary_id)
 
+        LectureAudioSummary(lecture_summary_name)
 
+        LectureAudioSummary(
+            lecture_speech_to_text_id=id,
+            lecture_audio_id=lecture_summary_id,
+            audio_original_text=current_date,
+            audio_summary=lecture_summary_name
+        ).save()
+        return Response({"response": request.data})
 
+    def post(self, request):
         LectureAudioSummary(
             lecture_speech_to_text_id=request.data["lecture_speech_to_text_id"],
             lecture_audio_id=request.data["lecture_audio_id"],
@@ -131,8 +149,27 @@ class lectureNoticeList(APIView):
 
     def get(self, request):
         lecture_notice_id = LectureNotices.objects.all()
-        serializer = LectureNoticesSerializer(lecture_notice_id, many=True)
-        return Response(serializer.data)
+        # serializer = LectureNoticesSerializer(lecture_notice_id, many=True)
+        # return Response(serializer.data)
+
+        lecture_notice_list = LectureNotices.objects.order_by('lecture_notice_list').last()
+
+        lecture_notice_name = request.query_params.get("lecture_notice_name")
+        id = int(request.query_params.get("id"))
+
+        # generate new id for notices
+        lecture_notice_id = generate_new_id(lecture_notice_list.lecture_notice_id)
+
+        LectureNotices(lecture_notice_name)
+
+        LectureNotices(
+            lecture_notice_id=id,
+            lecture_audio_id=lecture_notice_id,
+            notice_text=lecture_notice_name
+        ).save()
+        return Response({"response": request.data})
+
+
 
     def post(self, request):
         LectureNotices(

LectureSummarizingApp/noise.py

@@ -78,27 +78,3 @@ def output_file(destination ,filename, a, sr, ext=""):
     destination = destination + filename[:-4] + ext + '.wav'
     librosa.output.write_wav(destination, a, sr)
 
-
-# lectures = ['Lecture01.wav', 'Lecture02.wav']
-
-# for s in lectures:
-#     filename = s
-#     a, sr = noise_removal(filename)
-#
-#
-#     # a_reduced_centroid_s = reduce_noise_centroid_s(a, sr)
-#     # a_reduced_mfcc_lowshelf = mfcc_lowshelf(a, sr)
-#     a_reduced_mfcc_highshelf = mffc_highshelf(a, sr)
-#
-#
-#     # trimming silences
-#     # a_reduced_centroid_s, time_trimmed = trim_silence(a_reduced_centroid_s)
-#     # a_reduced_mfcc_up, time_trimmed = trim_silence(mfcc_lowshelf)
-#     a_reduced_mfcc_down, time_trimmed = trim_silence(mffc_highshelf)
-#
-#
-#
-#     # output_file('lectures_trimmed_noise_reduced/' ,filename, y_reduced_centroid_s, sr, '_ctr_s')
-#     #output_file('lectures_trimmed_noise_reduced/' ,filename, a_reduced_mfcc_up, sr, '_mfcc_up')
-#     output_file('lectures_trimmed_noise_reduced/' ,filename, a_reduced_mfcc_down, sr, '_mfcc_down')
-#     # output_file('lectures_trimmed_noise_reduced/' ,filename, a, sr, '_org')

LectureSummarizingApp/speech_to_text.py

@@ -2,15 +2,17 @@ import speech_recognition as sr
 import os
 
 
-def speech_to_text(video_name):
+def speech_to_text(speech_to_text_name):
 
 #calling the Recognizer()
     r = sr.Recognizer()
 
     BASE_DIR = os.path.dirname(os.path.abspath(__file__))
-    VIDEO_PATH = os.path.join(BASE_DIR, "lectures\\{}".format(video_name))
+    FILE_PATH = os.path.join(BASE_DIR, "noise_removed_lectures\\{}".format(speech_to_text_name))
+    DESTINATION_DIR = os.path.dirname(os.path.join(BASE_DIR, "LectureSummarizingApp\\speechToText\\sample.txt"))
+    print('destination directory: ', DESTINATION_DIR)
 
-    with sr.AudioFile(VIDEO_PATH) as source:
+    with sr.AudioFile(FILE_PATH) as source:
         audio = r.listen(source)
         file = open('audioToText01.txt', 'w') #open file
         try:

LectureSummarizingApp/templates/LectureSummarizingApp/summarization.html

@@ -34,33 +34,38 @@
 
     $(document).ready(function() {
 
-
 <!--        speech to text-->
         $('.audio_to_text_process').click(function() {
             alert('Processing');
+            let id = e.target.parentNode.parentNode.getAttribute('id');
+            let speech_to_text_name = e.target.parentNode.parentNode.getAttribute('data-noiseless-audio-name');
+            speech_to_text_name = speech_to_text_name + ".txt";
+            alert('id: ' + id);
+            alert('speech to text file name: ' + speech_to_text_name);
 
             //call the fetch API
-            fetch('http://127.0.0.1:8000/summary/lecture-audio-to-text/?video_name=Lecture01.wav')
+            fetch('http://127.0.0.1:8000/summary/lecture-audio-to-text/?speech_to_text_name=' + speech_to_text_name + '&id=' + id)
             .then((res) => res.json())
-            .then((out) => alert(out.response))
+            .then((out) => handleSpeechToText(out.response))
             .catch((err) => alert('error: ' + err))
 
         });
+          //this function will handle the success response for speech-to-text
+        function handleSpeechToText(response) {
+            if (response === 200) {
+                document.location.reload();
+            }
+        }
 
 <!--        background noise-->
         $('.audio_process').click(function(e) {
-
+            alert('Processing');
             let id = e.target.parentNode.parentNode.getAttribute('id');
             let audio_name = e.target.parentNode.parentNode.getAttribute('data-audio-name');
             audio_name = audio_name + ".wav";
             alert('id: ' + id);
             alert('audio name: ' + audio_name);
-
             //call the fetch API
-<!--            fetch('http://127.0.0.1:8000/summary/lecture-audio-to-text/?audio_name=')-->
-<!--            .then((res) => res.json())-->
-<!--            .then((out) => alert(out.response))-->
-<!--            .catch((err) => alert('error: ' + err))-->
 
             fetch('http://127.0.0.1:8000/summary/lecture-audio-noise-removed/?audio_name=' + audio_name + '&id=' + id)
             .then((res) => res.json())
@@ -68,8 +73,6 @@
             .catch((err) => alert('error: ' + err))
 
         });
-
-
         //this function will handle the success respopnse for noise removed
         function handleNoiseRemoved(response) {
 
@@ -78,18 +81,52 @@
             }
         }
 
-
         <!--        To summary-->
         $('.to_summary').click(function() {
             alert('Processing');
+            let id = e.target.parentNode.parentNode.getAttribute('id');
+            let lecture_summary_name = e.target.parentNode.parentNode.getAttribute('data-summary-name');
+            lecture_summary_name = lecture_summary_name + ".wav";
+            alert('id: ' + id);
+            alert('lecture_summary_name: ' + lecture_summary_name);
 
-            //call the fetch API
-            fetch('http://127.0.0.1:8000/summary/lecture-audio-to-text/?video_name=Lecture01.wav')
+        //call the fetch API
+
+            etch('http://127.0.0.1:8000/summary/lecture-summary/?lecture_summary_name=' + lecture_summary_name + '&id=' + id)
             .then((res) => res.json())
-            .then((out) => alert(out.response))
+            .then((out) => handleLectureRemoved(out.response))
             .catch((err) => alert('error: ' + err))
+        });
+         //this function will handle the success response for summary
+        function handleLectureRemoved(response) {
 
+            if (response === 200) {
+                document.location.reload();
+            }
+        }
+
+        <!--        To Notice-->
+        $('.get_notices').click(function() {
+            alert('Processing');
+            let id = e.target.parentNode.parentNode.getAttribute('id');
+            let lecture_notice_name = e.target.parentNode.parentNode.getAttribute('data-summary-name');
+            lecture_notice_name = lecture_notice_name + ".wav";
+            alert('id: ' + id);
+            alert('lecture_notice_name: ' + lecture_notice_name);
+
+        //call the fetch API
+
+            etch('http://127.0.0.1:8000/summary/lecture-notices/?lecture_notice_name=' + lecture_notice_name + '&id=' + id)
+            .then((res) => res.json())
+            .then((out) => handleNoticeRemoved(out.response))
+            .catch((err) => alert('error: ' + err))
         });
+         //this function will handle the success response for notices
+        function handleNoticeRemoved(response) {
+            if (response === 200) {
+                document.location.reload();
+            }
+        }
 
     });
 
@@ -127,6 +164,7 @@
                                     <span class="font-italic">No Recordings</span>
                                 </div>
                                 {% else %}
+                                #lecture list
                                 <div class="table-responsive">
                                     <table class="table table-bordered" id="datatable">
                                         <thead>
@@ -187,6 +225,7 @@
                                     <span class="font-italic">No Recordings</span>
                                 </div>
                                 {% else %}
+                                #noise removes list
                                 <div class="table-responsive">
                                     <table class="table table-bordered" id="datatable">
                                         <thead>
@@ -201,7 +240,7 @@
                                         <tbody>
 
                                         {% for noiseless_audio in noiseless_data %}
-                                        <tr class="recordings not_clicked" id="{{ noiseless_audio.lecture_audio_id }}">
+                                        <tr class="recordings not_clicked" id="{{ noiseless_audio.lecture_audio_id }}" data-noiseless-audio-name="{{ noiseless_audio.lecture_audio_name }}">
 <!--                                            <td>-->
 <!--                                                <div class="radio">-->
 <!--                                                    <label><input type="radio"-->
@@ -269,7 +308,7 @@
                                         <tbody>
 
                                         {% for lec_text in lecture_text_data %}
-                                        <tr class="recordings not_clicked" id="{{ lec_text.lecture_audio_id }}">
+                                        <tr class="recordings not_clicked" id="{{ lec_text.lecture_audio_id }}" data-summary-name="{{lec_text.lecture_audio_id.subject.name}}">
 <!--                                            <td>-->
 <!--                                                <div class="radio">-->
 <!--                                                    <label><input type="radio"-->
@@ -287,7 +326,7 @@
                                                 </button>
                                             </td>
                                             <td>
-                                                <button TYPE="button" class="btn btn-danger get_notices">Notices
+                                                <button TYPE="button" class="btn btn-success get_notices">Notices
                                                 </button>
                                             </td>
                                         </tr>