From 13d140e9e928cfa4d751d005c7aaf31609855c67 Mon Sep 17 00:00:00 2001
From: bcomsugi <bcomsugi@yahoo.com>
Date: Wed, 8 Nov 2023 17:23:36 +0700
Subject: [PATCH] accomodate empty column in reading excel

---
 pdfexcel4DNwithxlrd.py | 48 ++++++++++++++++++++++++++++++------------
 1 file changed, 35 insertions(+), 13 deletions(-)

diff --git a/pdfexcel4DNwithxlrd.py b/pdfexcel4DNwithxlrd.py
index 8cb35a3..13c66af 100644
--- a/pdfexcel4DNwithxlrd.py
+++ b/pdfexcel4DNwithxlrd.py
@@ -158,10 +158,28 @@ def read_DN_excel(filename):
 		for colidx, col in enumerate(x):	### change the empty cell into None
 			if col == "":
 				data[idx][colidx]=None
-	
-	# for idx, x in enumerate(data):
-	# 	print(idx, x)
-	
+	coly=0
+	xylist=[]
+	for idx, x in enumerate(data):
+		print(idx, x)
+		xylist=[]
+		if len(x)>5 and (idx % 2)==1 :
+			print(idx,x)
+			for idy, y in enumerate(x):
+				if y == None:
+					coly=idy
+				else:
+					xylist.append(y)
+			if len(xylist)==5:
+				data[idx]=xylist
+		elif coly  !=0:
+			for idy, y in enumerate(x):
+				if idy!=coly:
+					xylist.append(y)
+			data[idx]=xylist
+			coly=0
+		print(idx, data[idx])
+
 	print(f'len data={len(data)}')
 
 
@@ -189,11 +207,11 @@ def read_DN_excel(filename):
 				dt.append(uom)
 				dt[2]=int(dt[2].split(".")[0])
 				templist=dt
-				# print(templist)
+				print(templist)
 
-	# for idx, x in enumerate(newdata):
-	#     print(idx, x)
-	# print(f'len newdata={len(newdata)}')
+	for idx, x in enumerate(newdata):
+	    print(idx, x)
+	print(f'len newdata={len(newdata)}')
 
 
 	df=pd.DataFrame(newdata, columns=['Item No', 'Description', 'Quantity', 'No.SO/Ext.Doc.No.', 'LPN No.', 'UOM', 'Ext.Doc.No.'])#, columns=data[0]+"UOM")
@@ -204,15 +222,16 @@ def read_DN_excel(filename):
 	# print(df)
 	# df['FullName'] = inteminvdf.loc[df['Item No'],'FullName']
 	df=df.merge(inteminvdf, how="left")
-	
+	print(df['FullName'].isnull())
+	print(df['FullName'])
 	# print(df)
 	if df['FullName'].isnull().sum() > 0:
 
 		print("Cannot Find Item FullName")
 		listitemNoFullName = df.loc[df['FullName'].isnull()].values.tolist()
 		df=df.reindex(columns=['Ext.Doc.No.', 'No.SO/Ext.Doc.No.', 'Item No', 'FullName', 'Quantity', 'UOM'])
-		print(df)
-		print(listitemNoFullName)
+		# print(df)
+		# print(listitemNoFullName)
 		# print(listitemNoFullName)
 		return False, listitemNoFullName
 	else:
@@ -232,5 +251,8 @@ if __name__=="__main__":
 	# read_DN_excel(filename)
 	# filename = "DN_Excel_files\TCO-DNPR-2305-00305.xls"
 	# read_DN_excel(filename)
-	filename = "DN_Excel_files\TCO-DNPG-2307-01407.xls"
-	read_DN_excel(filename)
\ No newline at end of file
+	# filename = "DN_Excel_files\TCO-DNPG-2307-01407.xls"
+    filename = "DN_Excel_files\TCO-DNPG-2310-00337.xls"
+    status, retdict = read_DN_excel(filename)
+    print(status)
+    print(retdict)
\ No newline at end of file