Update app.py

app.py

@@ -40,6 +40,7 @@ import Code_2_7
 import Counting_Columns_2_1
 # import Find_Hyperlinking_text
 import ezdxf
+import Azure_api
 from flask import Flask, render_template, session, redirect, url_for
 from flask_session import Session  # Capital "S"
 app = Flask(__name__)
@@ -160,6 +161,10 @@ def get_javascript_data(jsdata):
 def searchDocument():
     return render_template('wordSearch.html')
 
+@app.route('/tableDetection',methods=["GET", "POST"])
+def TableDetection():
+    return render_template('tableDetection.html')
+
 @app.route('/legends',methods=["GET", "POST"])
 def legendDirectory():
     return render_template('legendDirectory.html')
@@ -234,7 +239,31 @@ def getfromdropboxImg(jsdata):
     img = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)
     _, buffer = cv2.imencode('.png', img)
     return base64.b64encode(buffer).decode('utf-8')
-    
+
+
+@app.route('/savedetectedtables/',methods=["POST"])
+def table():
+    # 1. Get PDF bytes from Dropbox
+    tt = eval(request.form.get('answers'))              # consider json.loads instead of eval
+    pdfpath, _ = tsadropboxretrieval.getPathtoPDF_File(nameofPDF=tt[0])
+    dbx = tsadropboxretrieval.ADR_Access_DropboxTeam('user')
+    _, res = dbx.files_download(path=pdfpath)
+    pdf_bytes = res.content
+
+    # 2. Generate in-memory Excel
+    excel_io = Azure_api.detect_tables(pdf_bytes)
+    print('type(excel_io) = ', type(excel_io))
+    # 3. Send it as a downloadable .xlsx
+    if excel_io is None:
+        # No tables → return a JSON error (or another response of your choice)
+        return ('', 204)
+        
+    return send_file(
+        excel_io,
+        as_attachment=True,
+        download_name='detected_tables.xlsx',
+        mimetype='application/vnd.openxmlformats-officedocument.spreadsheetml.sheet'
+    )
 
 @app.route('/savebase64Img/',methods=["POST"])
 def stringToRGB():
@@ -266,17 +295,35 @@ def stringToRGB():
        
 
     if vv[5][2].startswith('2.8') or vv[5][2].startswith('2.6')  or vv[5][2].startswith('2.1'):
-        pdfpath,pdflink=tsadropboxretrieval.getPathtoPDF_File(nameofPDF= str(vv[0]))
-        dbxTeam= tsadropboxretrieval.ADR_Access_DropboxTeam('user')
-        md, res =dbxTeam.files_download(path=pdfpath)
-        dataDoc = res.content
-        doc = fitz.open("pdf",dataDoc)
-        page=doc[0]
-        if page.rotation!=0:
-            page.set_rotation(0)
-        pix = page.get_pixmap(dpi=300)  # render page to an image
-        pl=Image.frombytes('RGB', [pix.width,pix.height],pix.samples)
-        arr=measureproject(vv,dataDoc,pl)
+        print(f"el mawgood fe vv[0]: {vv[0]}")
+        arr_s = []
+        dataDocs = []
+        pls = []
+        for v in vv[0]:
+            pdfpath,pdflink=tsadropboxretrieval.getPathtoPDF_File(nameofPDF= str(v))
+            dbxTeam= tsadropboxretrieval.ADR_Access_DropboxTeam('user')
+            md, res =dbxTeam.files_download(path=pdfpath)
+            dataDoc = res.content
+            dataDocs.append(dataDoc)
+            doc = fitz.open("pdf",dataDoc)
+            page=doc[0]
+            if page.rotation!=0:
+                page.set_rotation(0)
+            pix = page.get_pixmap(dpi=300)  # render page to an image
+            pl=Image.frombytes('RGB', [pix.width,pix.height],pix.samples)
+            pls.append(pl)
+        arr=measureproject(vv,dataDocs,pls)
+        #pdfpath,pdflink=tsadropboxretrieval.getPathtoPDF_File(nameofPDF= str(vv[0]))
+        #dbxTeam= tsadropboxretrieval.ADR_Access_DropboxTeam('user')
+        #md, res =dbxTeam.files_download(path=pdfpath)
+        #dataDoc = res.content
+        #doc = fitz.open("pdf",dataDoc)
+        #page=doc[0]
+        #if page.rotation!=0:
+         #   page.set_rotation(0)
+        #pix = page.get_pixmap(dpi=300)  # render page to an image
+        #pl=Image.frombytes('RGB', [pix.width,pix.height],pix.samples)
+        #arr=measureproject(vv,dataDoc,pl)
     return jsonify(arr)
 
 @app.route('/2.1Trial/',methods=["POST"])
@@ -385,7 +432,7 @@ def measureproject(result,dataDoc=0,img=0,dxffile=0):
         # 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
         annotatedimg, pdf_document , list1, repeated_labels , not_found =Doors_Schedule.mainRun(dataDocDoorsSchedule, dataDoc, SearchArray)
         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/
+        pdflink= tsadropboxretrieval.uploadanyFile(doc=pdf_document,path=dbPath,pdfname="combined_output.pdf") #doc=doc,pdfname=path,pdfpath=pdfpath+'Measured Plan/
         _, buffer = cv2.imencode('.png', annotatedimg)
         repeatedLabelsReturn=''
         NotFoundReturn=''
@@ -787,7 +834,7 @@ def receive_pdf_data():
 
         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/'