Marthee commited on
Commit
071c40f
·
verified ·
1 Parent(s): 1f2e03d

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +15 -61
app.py CHANGED
@@ -40,7 +40,6 @@ import Code_2_7
40
  import Counting_Columns_2_1
41
  # import Find_Hyperlinking_text
42
  import ezdxf
43
- import Azure_api
44
  from flask import Flask, render_template, session, redirect, url_for
45
  from flask_session import Session # Capital "S"
46
  app = Flask(__name__)
@@ -161,10 +160,6 @@ def get_javascript_data(jsdata):
161
  def searchDocument():
162
  return render_template('wordSearch.html')
163
 
164
- @app.route('/tableDetection',methods=["GET", "POST"])
165
- def TableDetection():
166
- return render_template('tableDetection.html')
167
-
168
  @app.route('/legends',methods=["GET", "POST"])
169
  def legendDirectory():
170
  return render_template('legendDirectory.html')
@@ -239,31 +234,7 @@ def getfromdropboxImg(jsdata):
239
  img = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)
240
  _, buffer = cv2.imencode('.png', img)
241
  return base64.b64encode(buffer).decode('utf-8')
242
-
243
-
244
- @app.route('/savedetectedtables/',methods=["POST"])
245
- def table():
246
- # 1. Get PDF bytes from Dropbox
247
- tt = eval(request.form.get('answers')) # consider json.loads instead of eval
248
- pdfpath, _ = tsadropboxretrieval.getPathtoPDF_File(nameofPDF=tt[0])
249
- dbx = tsadropboxretrieval.ADR_Access_DropboxTeam('user')
250
- _, res = dbx.files_download(path=pdfpath)
251
- pdf_bytes = res.content
252
-
253
- # 2. Generate in-memory Excel
254
- excel_io = Azure_api.detect_tables(pdf_bytes)
255
- print('type(excel_io) = ', type(excel_io))
256
- # 3. Send it as a downloadable .xlsx
257
- if excel_io is None:
258
- # No tables → return a JSON error (or another response of your choice)
259
- return ('', 204)
260
-
261
- return send_file(
262
- excel_io,
263
- as_attachment=True,
264
- download_name='detected_tables.xlsx',
265
- mimetype='application/vnd.openxmlformats-officedocument.spreadsheetml.sheet'
266
- )
267
 
268
  @app.route('/savebase64Img/',methods=["POST"])
269
  def stringToRGB():
@@ -295,35 +266,17 @@ def stringToRGB():
295
 
296
 
297
  if vv[5][2].startswith('2.8') or vv[5][2].startswith('2.6') or vv[5][2].startswith('2.1'):
298
- print(f"el mawgood fe vv[0]: {vv[0]}")
299
- arr_s = []
300
- dataDocs = []
301
- pls = []
302
- for v in vv[0]:
303
- pdfpath,pdflink=tsadropboxretrieval.getPathtoPDF_File(nameofPDF= str(v))
304
- dbxTeam= tsadropboxretrieval.ADR_Access_DropboxTeam('user')
305
- md, res =dbxTeam.files_download(path=pdfpath)
306
- dataDoc = res.content
307
- dataDocs.append(dataDoc)
308
- doc = fitz.open("pdf",dataDoc)
309
- page=doc[0]
310
- if page.rotation!=0:
311
- page.set_rotation(0)
312
- pix = page.get_pixmap(dpi=300) # render page to an image
313
- pl=Image.frombytes('RGB', [pix.width,pix.height],pix.samples)
314
- pls.append(pl)
315
- arr=measureproject(vv,dataDocs,pls)
316
- #pdfpath,pdflink=tsadropboxretrieval.getPathtoPDF_File(nameofPDF= str(vv[0]))
317
- #dbxTeam= tsadropboxretrieval.ADR_Access_DropboxTeam('user')
318
- #md, res =dbxTeam.files_download(path=pdfpath)
319
- #dataDoc = res.content
320
- #doc = fitz.open("pdf",dataDoc)
321
- #page=doc[0]
322
- #if page.rotation!=0:
323
- # page.set_rotation(0)
324
- #pix = page.get_pixmap(dpi=300) # render page to an image
325
- #pl=Image.frombytes('RGB', [pix.width,pix.height],pix.samples)
326
- #arr=measureproject(vv,dataDoc,pl)
327
  return jsonify(arr)
328
 
329
  @app.route('/2.1Trial/',methods=["POST"])
@@ -432,7 +385,7 @@ def measureproject(result,dataDoc=0,img=0,dxffile=0):
432
  # 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
433
  annotatedimg, pdf_document , list1, repeated_labels , not_found =Doors_Schedule.mainRun(dataDocDoorsSchedule, dataDoc, SearchArray)
434
  dbPath='/TSA JOBS/ADR Test'+pdfpath+'Measured Plan/'
435
- pdflink= tsadropboxretrieval.uploadanyFile(doc=pdf_document,path=dbPath,pdfname="combined_output.pdf") #doc=doc,pdfname=path,pdfpath=pdfpath+'Measured Plan/
436
  _, buffer = cv2.imencode('.png', annotatedimg)
437
  repeatedLabelsReturn=''
438
  NotFoundReturn=''
@@ -834,7 +787,7 @@ def receive_pdf_data():
834
 
835
  pdfbytes, pdf_document , df ,tablepdfoutput= Find_Hyperlinking_text.annotate_text_from_pdf([pdfLink], keyword)
836
  dbxTeam= tsadropboxretrieval.ADR_Access_DropboxTeam('user')
837
-
838
  # Get metadata using the shared link
839
  metadata = dbxTeam.sharing_get_shared_link_metadata(pdfLink)
840
  dbPath='/TSA JOBS/ADR Test/FIND/'
@@ -1048,6 +1001,7 @@ def cvtSummarytoXML(jsdata):
1048
  xmllink=google_sheet_to_xml.create_xml(documentname=result[1],dbPath=path)
1049
  return jsonify(xmllink)
1050
 
 
1051
  #_________________________________________________________________________________________________________________________
1052
  #_________________________________________________________________________________________________________________________
1053
 
 
40
  import Counting_Columns_2_1
41
  # import Find_Hyperlinking_text
42
  import ezdxf
 
43
  from flask import Flask, render_template, session, redirect, url_for
44
  from flask_session import Session # Capital "S"
45
  app = Flask(__name__)
 
160
  def searchDocument():
161
  return render_template('wordSearch.html')
162
 
 
 
 
 
163
  @app.route('/legends',methods=["GET", "POST"])
164
  def legendDirectory():
165
  return render_template('legendDirectory.html')
 
234
  img = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)
235
  _, buffer = cv2.imencode('.png', img)
236
  return base64.b64encode(buffer).decode('utf-8')
237
+
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
238
 
239
  @app.route('/savebase64Img/',methods=["POST"])
240
  def stringToRGB():
 
266
 
267
 
268
  if vv[5][2].startswith('2.8') or vv[5][2].startswith('2.6') or vv[5][2].startswith('2.1'):
269
+ pdfpath,pdflink=tsadropboxretrieval.getPathtoPDF_File(nameofPDF= str(vv[0]))
270
+ dbxTeam= tsadropboxretrieval.ADR_Access_DropboxTeam('user')
271
+ md, res =dbxTeam.files_download(path=pdfpath)
272
+ dataDoc = res.content
273
+ doc = fitz.open("pdf",dataDoc)
274
+ page=doc[0]
275
+ if page.rotation!=0:
276
+ page.set_rotation(0)
277
+ pix = page.get_pixmap(dpi=300) # render page to an image
278
+ pl=Image.frombytes('RGB', [pix.width,pix.height],pix.samples)
279
+ arr=measureproject(vv,dataDoc,pl)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
280
  return jsonify(arr)
281
 
282
  @app.route('/2.1Trial/',methods=["POST"])
 
385
  # 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
386
  annotatedimg, pdf_document , list1, repeated_labels , not_found =Doors_Schedule.mainRun(dataDocDoorsSchedule, dataDoc, SearchArray)
387
  dbPath='/TSA JOBS/ADR Test'+pdfpath+'Measured Plan/'
388
+ pdflink= tsadropboxretrieval.uploadanyFile(doc=pdf_document,path=dbPath,pdfname=result[0]) #doc=doc,pdfname=path,pdfpath=pdfpath+'Measured Plan/
389
  _, buffer = cv2.imencode('.png', annotatedimg)
390
  repeatedLabelsReturn=''
391
  NotFoundReturn=''
 
787
 
788
  pdfbytes, pdf_document , df ,tablepdfoutput= Find_Hyperlinking_text.annotate_text_from_pdf([pdfLink], keyword)
789
  dbxTeam= tsadropboxretrieval.ADR_Access_DropboxTeam('user')
790
+
791
  # Get metadata using the shared link
792
  metadata = dbxTeam.sharing_get_shared_link_metadata(pdfLink)
793
  dbPath='/TSA JOBS/ADR Test/FIND/'
 
1001
  xmllink=google_sheet_to_xml.create_xml(documentname=result[1],dbPath=path)
1002
  return jsonify(xmllink)
1003
 
1004
+
1005
  #_________________________________________________________________________________________________________________________
1006
  #_________________________________________________________________________________________________________________________
1007