Changeset 32808

Timestamp:

2019-02-24T18:12:33+13:00 (5 years ago)

Author:

davidb

Message:

Splitting between unbound and pdf-bound added in

File:

• main/trunk/model-sites-dev/heritage-nz/collect/reports-2019/prepare/xls-to-csv.py (modified) (3 diffs)

main/trunk/model-sites-dev/heritage-nz/collect/reports-2019/prepare/xls-to-csv.py

@@ -17 +17 @@
     pdfbound_filename = os.path.join(excel_dirname,"PDF-BOUND "+excel_file_root+".csv")
     unbound_filename  = os.path.join(excel_dirname,"UNBOUND "+excel_file_root+".csv")
-
-    pdf_dirname = os.path.join(excel_dirname,"pdfs")
 
     # print "Worksheet: " + worksheet_name
@@ -39 +37 @@
     found_header = False
     while row_i<num_rows:
-        first_cell = worksheet.row_values(row_i)[0];
+        first_cell = worksheet.cell_value(row_i,0);
         if first_cell == "Report Identifier":
             found_header = True
@@ -55 +53 @@
         unbound_wr.writerow(entry_utf8_row)
 
+        # Add in 'Filename' as first column in pdfbound CSV file
+        entry_utf8_row.insert(0, "Filename")
+        pdfbound_wr.writerow(entry_utf8_row)
+
+
         row_i = row_i + 1
         while row_i<num_rows:
+            num_cols = worksheet.row_len(row_i)
             entry_utf8_row = []
-            for entry in worksheet.row_values(row_i):
+
+            found_pdf = False
+
+#            for entry in worksheet.row_values(row_i):
+            for col_j in range(num_cols):
+                entry = worksheet.cell_value(row_i,col_j)
+
+                if col_j == 0:
+                    # Check to see if companion PDF file present
+                    pdf_filename = os.path.join(excel_dirname,"pdfs",entry+".pdf")
+                    if os.path.exists(pdf_filename):
+                        found_pdf = True
+                        pdf_file = os.path.join("pdfs",entry+".pdf")
+                        entry_utf8_row.insert(0, pdf_file)
+                                 
                 entry_utf8 = unicode(entry).encode("utf-8")
                 entry_utf8_row.append(entry_utf8)
-            unbound_wr.writerow(entry_utf8_row)
+            if found_pdf:
+                pdfbound_wr.writerow(entry_utf8_row)
+            else:
+                unbound_wr.writerow(entry_utf8_row)
 
             row_i = row_i + 1