Update app.py

app.py

@@ -1,19 +1,18 @@
 from __future__ import print_function
 from flask import Flask, render_template,request,flash , json, url_for,g , redirect , jsonify , send_file ,make_response
-import os
 import json
 import fitz
 from PIL import Image
 import cv2
 import numpy as np
 import pilecaps_adr
-import base64 
+import base64
 from db import dropbox_connect
-import db
 import cv2
 import pandas as pd
 import time
 from io import BytesIO, StringIO
+import urllib
 import tempfile
 from flask import Flask, Response
 from werkzeug.wsgi import wrap_file
@@ -21,7 +20,6 @@ import tameem3_2
 import pypdfium2 as pdfium
 import pixelconversion
 import tameem2_1
-import base64
 import io
 from urllib.parse import unquote
 import API
@@ -30,14 +28,16 @@ import tsadropboxretrieval
 import doc_search
 import google_sheet_Legend
 import dxf__omar3_2
+import requests
 import google_sheet_to_xml
 from threading import Thread
 import mainDBAlaa
 import datetime
 import doors_fasterrcnn
 import deploying_3_3
+import Code_2_7
 import Counting_Columns_2_1
-
+import Find_Hyperlinking_text
 import ezdxf
 app = Flask(__name__)
 
@@ -53,13 +53,11 @@ global pdflink
 def getInfotoMeasure():
     API.AppendtablestoSheets()
     return render_template("proposed-GUI.html")
-
 @app.route("/WordSearch",methods=["GET", "POST"])
 def getInfo2toMeasure():
     API.AppendtablestoSheets()
     return render_template("wordSearch.html")
 
-    
 @app.route('/getprojectnames/',methods=['GET'])
 def getprjnamesfromTestAPI():
     prjnames,prjids=API.getPrjNames()
@@ -85,9 +83,9 @@ def get_javascript_data(jsdata):
     #get project from the first dropdown
     # jsdata=eval(jsdata)
     print('tsa')
-    documnetsToMeasure,RelevantDocuments=tsadropboxretrieval.retrieveProjects(jsdata)
+    documnetsToMeasure,RelevantDocuments,extracted_path=tsadropboxretrieval.retrieveProjects(jsdata)
     if RelevantDocuments:
-        return jsonify ([documnetsToMeasure, RelevantDocuments])
+        return jsonify ([documnetsToMeasure, RelevantDocuments,extracted_path])
     else: 
         return ['No projects found']
 #---------------------------------------------------------------
@@ -175,7 +173,7 @@ def getfromdropboxImg(jsdata):
 def stringToRGB():
     vv = eval(request.form.get('answers'))
     print(vv)
-    if ( vv[5][2].startswith('3.2') or vv[5][2].startswith('3.3') ) :
+    if ( vv[5][2].startswith('3.2') or vv[5][2].startswith('3.3') or vv[5][2].startswith('2.7')) :
         print('3.2 section')
         pdfpath,pdflink=tsadropboxretrieval.getPathtoPDF_File(nameofPDF=vv[0])
         dbxTeam= tsadropboxretrieval.ADR_Access_DropboxTeam('user')
@@ -189,6 +187,8 @@ def stringToRGB():
             arr=measureproject(vv,dataDoc,0,file)
             return jsonify(arr)
         
+    
+        
     if vv[5][2].startswith('1.0'):
         opencv_img,dataDoc = plan2img( str(vv[0]) )
         if vv[1]==220:
@@ -273,6 +273,29 @@ def measureproject(result,dataDoc=0,img=0,dxffile=0):
                 # 
                 pdflink= tsadropboxretrieval.uploadanyFile(doc=doc,path=dbPath,pdfname=result[0]) #doc=doc,pdfname=path,pdfpath=pdfpath+'Measured Plan/'
 
+                _, buffer = cv2.imencode('.png', outputimg)
+                arr=[ base64.b64encode(buffer).decode('utf-8'),SimilarAreaDictionary.to_dict(), spreadsheet_url,spreadsheetId,[],list1.to_dict(),pdflink,hatched_areas,namepathArr]#,hatched_areas,namepathArr]# , spreadsheetId, spreadsheet_url , list1.to_dict()]
+    #################################  2.7- #################################
+    elif result[5][2].startswith('2.7') : #section value - 2.7 floor finishes
+            print('code of 2.7')
+            dxfpath=dxffile.read()
+            with tempfile.NamedTemporaryFile(suffix='.dxf', delete=False) as temp_file:
+                temp_file.write(dxfpath)
+                temp_filename = temp_file.name
+                print(temp_filename)
+
+                SearchArray=result[6]
+                print(result)
+                print("SearchArray = ",SearchArray)
+
+                doc,outputimg, SimilarAreaDictionary ,spreadsheetId, spreadsheet_url , namepathArr , list1,hatched_areas=Code_2_7.mainFunctionDrawImgPdf(dataDoc,temp_filename,result[4],SearchArray, pdfpath,result[0])
+                # global colorsused
+                colorsused=list(SimilarAreaDictionary['Color'])
+                dbPath='/TSA JOBS/ADR Test'+pdfpath+'Measured Plan/'
+                print(dbPath,result[0]) 
+                # 
+                pdflink= tsadropboxretrieval.uploadanyFile(doc=doc,path=dbPath,pdfname=result[0]) #doc=doc,pdfname=path,pdfpath=pdfpath+'Measured Plan/'
+
                 _, buffer = cv2.imencode('.png', outputimg)
                 arr=[ base64.b64encode(buffer).decode('utf-8'),SimilarAreaDictionary.to_dict(), spreadsheet_url,spreadsheetId,[],list1.to_dict(),pdflink,hatched_areas,namepathArr]#,hatched_areas,namepathArr]# , spreadsheetId, spreadsheet_url , list1.to_dict()]
     #################################  -2.8- #################################
@@ -283,7 +306,7 @@ def measureproject(result,dataDoc=0,img=0,dxffile=0):
         legendLinks=[]
         listofmarkups=[]
 
-        annotatedimg,pdf_document,spreadsheet_url, list1 , df_doors=doors_fasterrcnn.main_run(img,dataDoc,'separated_classes.pth','separated_classes_all.pth',result[0],pdfpath, result[4]) #single_double.pth
+        annotatedimg,pdf_document,spreadsheet_url, list1 , df_doors=doors_fasterrcnn.main_run(img,dataDoc,'separated_classes_all.pth',result[0],pdfpath, result[4]) #single_double.pth
         
         dbPath='/TSA JOBS/ADR Test'+pdfpath+'Measured Plan/' 
         pdflink= tsadropboxretrieval.uploadanyFile(doc=pdf_document,path=dbPath,pdfname=result[0]) #doc=doc,pdfname=path,pdfpath=pdfpath+'Measured Plan/
@@ -297,12 +320,12 @@ def measureproject(result,dataDoc=0,img=0,dxffile=0):
         dpxlinks=[]
         legendLinks=[]
         listofmarkups=[]
-        print('wasalt::',dataDoc)
+
         annotatedimg,pdf_document,spreadsheet_url, list1 , df_doors=Counting_Columns_2_1.mainfun(dataDoc,pdfpath,result[0]) 
         
-        dbPath='/TSA JOBS/ADR Test'+pdfpath+'Measured Plan/' 
-        pdflink= tsadropboxretrieval.uploadanyFile(doc=pdf_document,path=dbPath,pdfname=result[0]) #doc=doc,pdfname=path,pdfpath=pdfpath+'Measured Plan/
-        _, buffer = cv2.imencode('.png', annotatedimg)
+        # dbPath='/TSA JOBS/ADR Test'+pdfpath+'Measured Plan/' 
+        # pdflink= tsadropboxretrieval.uploadanyFile(doc=pdf_document,path=dbPath,pdfname=result[0]) #doc=doc,pdfname=path,pdfpath=pdfpath+'Measured Plan/
+        # _, buffer = cv2.imencode('.png', annotatedimg)
         arr=[base64.b64encode(buffer).decode('utf-8') ,pdflink,spreadsheet_url,list1.to_dict(), df_doors.to_dict()]# , spreadsheetId, spreadsheet_url , list1.to_dict()]
 
     #################################  -2.2- #################################
@@ -566,13 +589,121 @@ def dltmarkupslegend():
 #get pdf dropbox url after measurement is done
 @app.route('/getdropboxurl/<jsdata>',methods=["GET", "POST"])
 def calldropboxurl(jsdata):
-    print(jsdata)
+    print('jsdata',jsdata)
     pdfurl=tsadropboxretrieval.getPathtoPDF_File(nameofPDF=jsdata)[1]
-    print(pdfurl)
-    return jsonify(pdfurl)
+    print('urll',pdfurl)
+    if pdfurl and ('http' in pdfurl or 'dropbox' in pdfurl):
+        if 'dl=0' in pdfurl:
+            pdfurl = pdfurl.replace('dl=0', 'dl=1')
+    print('urll1',pdfurl)
+    # Download the PDF content from the shareable link
+    response = requests.get(pdfurl)
+    pdf_content = BytesIO(response.content)  # Store the content in memory
+    if pdf_content is None:
+        raise ValueError("No valid PDF content found.")
+
+    # Open the PDF using PyMuPDF
+    pdf_document = fitz.open(stream=pdf_content, filetype="pdf")
+    pdf_bytes = BytesIO()
+    pdf_document.save(pdf_bytes)
+    return Response(pdf_bytes.getvalue(), content_type='application/pdf')
 
 #_________________________________________________________________________________________________________________________
 #_________________________________________________________________________________________________________________________
+
+pdf_content = None
+pageNumTextFound = 0
+BASE_URL = "https://marthee-nbslink.hf.space"  # Hugging Face Spaces base URL
+
+@app.route("/", methods=["GET", "POST"])
+def thismain():
+    print('ayhaga')
+    return render_template("gui.html")
+
+@app.route('/view-pdf', methods=['GET'])
+def download_pdf():
+
+    # Manually parse the query parameters
+    full_query_string = request.query_string.decode()  # Get raw query string
+    parsed_params = urllib.parse.parse_qs(full_query_string)  # Parse it
+
+    # Extract pdfLink and keyword manually
+    pdf_link = parsed_params.get('pdfLink', [None])[0]
+    keyword = parsed_params.get('keyword', [None])[0]
+
+    if not pdf_link or not keyword:
+        return "Missing required parameters.", 400
+
+    # Decode the extracted values
+    pdf_link = urllib.parse.unquote(pdf_link)
+    keyword = urllib.parse.unquote(keyword)
+
+    # If the keyword is a JSON string, convert it back to a list
+    try:
+        keyword = json.loads(keyword)
+    except json.JSONDecodeError:
+        keyword = [keyword]  # Treat it as a single keyword if not JSON
+
+    print("Extracted PDF Link:", pdf_link)
+    print("Extracted Keywords:", keyword)
+    createDF=False
+    pdf_content = Find_Hyperlinking_text.annotate_text_from_pdf([pdf_link], keyword)[0]
+    if pdf_content is None:
+        return "PDF content not found.", 404
+
+    pdf_bytes = BytesIO(pdf_content)
+    return send_file(
+        pdf_bytes,
+        mimetype='application/pdf',
+        as_attachment=False,
+        download_name=f"annotated_page_{pageNumTextFound}.pdf"
+    )
+
+@app.route('/api/process-data', methods=['POST'])
+def receive_pdf_data():
+    global pdf_content, pageNumTextFound
+
+    # Get PDF link and keyword from finddata()
+    pdfLink, keyword = finddata()
+
+    if not pdfLink or not keyword:
+        return jsonify({"error": "Both 'pdfLink' and 'keyword' must be provided."}), 400
+
+    try:
+        print(pdfLink, keyword)
+
+
+        pdfbytes, pdf_document , df ,tablepdfoutput= Find_Hyperlinking_text.annotate_text_from_pdf([pdfLink], keyword)
+        dbxTeam= tsadropboxretrieval.ADR_Access_DropboxTeam('user')
+
+        # Get metadata using the shared link
+        metadata = dbxTeam.sharing_get_shared_link_metadata(pdfLink)
+        dbPath='/TSA JOBS/ADR Test/FIND/'
+        pdflink= tsadropboxretrieval.uploadanyFile(doc=pdf_document,path=dbPath,pdfname=metadata.name) #doc=doc,pdfname=path,pdfpath=pdfpath+'Measured Plan/
+        print('LINKS0',pdflink)
+     
+        dbPath='/TSA JOBS/ADR Test/FIND/'
+        tablepdfLink=tsadropboxretrieval.uploadanyFile(doc=tablepdfoutput,path=dbPath,pdfname=metadata.name.rsplit(".pdf", 1)[0] +' Markup Summary'+'.pdf')
+        print(f"PDF successfully uploaded to Dropbox at")
+        print('LINKS1',tablepdfLink)
+        return jsonify({
+            "message": "PDF processed successfully.",
+            "PDF_MarkedUp": pdflink,
+            'Table_PDF_Markup_Summary': tablepdfLink
+        })
+
+    except Exception as e:
+        return jsonify({"error": str(e)}), 500
+
+def finddata():
+    pdfLink = 'https://www.dropbox.com/scl/fi/hnp4mqigb51a5kp89kgfa/00801-ARC-20-ZZ-S-A-0002.pdf?rlkey=45abeoebzqw4qwnslnei6dkd6&st=m4yrcjm2&dl=1'
+    keyword = ['115 INTEGRATED MRI ROOM LININGS', '310 ACCURACY']
+    return pdfLink, keyword
+
+
+#_________________________________________________________________________________________________________________________
+#_________________________________________________________________________________________________________________________
+
 #Google sheet links
 @app.route('/getdrivelinks/<jsdata>',methods=["GET", "POST"])
 def getlinkscreated(jsdata):
@@ -703,7 +834,7 @@ def checktables():
 @app.route('/refreshDropbox',methods=["GET", "POST"])
 def checkdropbox():
     print('checkingggdf')
-    dfFromDropbox=tsadropboxretrieval.DropboxItemstoDF( "/TSA JOBS")[0]
+    dfFromDropbox=tsadropboxretrieval.DropboxItemstoDF("/TSA JOBS")[0]
     dfParquet=tsadropboxretrieval.GetParquetDF()
 
     dfParquet1 = dfParquet[['name', 'path_display', 'client_modified', 'server_modified']]
@@ -718,13 +849,45 @@ def checkdropbox():
         stringReturned= 'Updated Sucessfully.' 
     else:
         stringReturned= 'Nothing to update.' 
-    return stringReturned
+    return 'stringReturned'
+
+def refreshDropboxRetrievals(extractedPath):
+    dfFromDropbox = tsadropboxretrieval.DropboxItemstoDF(extractedPath)[0]
+    dfParquet = tsadropboxretrieval.GetParquetDF()
+
+    # print("Original Parquet size:", len(dfParquet))
+
+    # Keep only relevant columns
+    dfParquet = dfParquet[['name', 'path_display', 'client_modified', 'server_modified']]
+    dfFromDropbox = dfFromDropbox[['name', 'path_display', 'client_modified', 'server_modified']]
+
+    # **Drop rows that start with extractedPath**
+    dfParquetUpdated = dfParquet[~dfParquet['path_display'].str.startswith(extractedPath)]
+    
+    # **Append new data from Dropbox**
+    dfParquetUpdated = pd.concat([dfParquetUpdated, dfFromDropbox], ignore_index=True)
 
+    # print("Updated Parquet size:", len(dfParquetUpdated),dfParquetUpdated)
 
+    # **Save the updated Parquet file**
+    tsadropboxretrieval.dropbox_upload_file(dfParquetUpdated)
 
-@app.route('/postdropboxprojects',methods=["GET", "POST"])
-def postDropboxprojectsinConsole():
-    stringReturned=checkdropbox()
+    if len(dfFromDropbox) > 0:
+        print("Updated entries:", dfFromDropbox)
+        return 'Updated Successfully.'
+    else:
+        return 'Nothing to update.'
+
+
+
+
+
+@app.route('/postdropboxprojects/<path:encoded_path>')
+def handle_path(encoded_path):
+    decoded_path = urllib.parse.unquote(encoded_path)  # Decode URL encoding
+    extracted_path = json.loads(decoded_path)  # Convert back to Python object
+    print('path to refresh',extracted_path)
+    stringReturned=refreshDropboxRetrievals(extracted_path)
     print(stringReturned)
     return stringReturned
 
@@ -750,9 +913,6 @@ def cvtSummarytoXML(jsdata):
     # print(result[1])
     xmllink=google_sheet_to_xml.create_xml(documentname=result[1],dbPath=path)
     return jsonify(xmllink)
- 
- 
-
 #_________________________________________________________________________________________________________________________
 #_________________________________________________________________________________________________________________________