Changeset 32820

Timestamp:

2019-02-26T11:35:55+13:00 (5 years ago)

Author:

davidb

Message:

Tidy up

File:

• main/trunk/model-sites-dev/heritage-nz/collect/reports-2019/prepare/xls-to-csv.py (modified) (4 diffs)

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

@@ -49 +49 @@
     unbound_wr  = csv.writer(csv_unbound_ofile, quoting=csv.QUOTE_ALL)
 
-    # 1. Skip lines until "Report Identifier" encountered
-    # 2. Remove "Report Identifier" line entries to turn 
-    #     into Greenstone friendly metadata names
+    # 1. Skip lines until Header encountered (as defined by encountering "Report Identifier")
+    # 2. Write out Header line as Greenstone friendly Metadata terms 
+    #      => remove sp spaces, change "Report Identifier" to hnz.Identifier
     # 3. Process the rest of the file, checking if accompanying 
     #     PDF file present or not
@@ -57 +57 @@
     num_rows = worksheet.nrows
 
+    # 1, Skip lines until Header encountered
     row_i = 0
     found_header = False
@@ -67 +68 @@
         row_i = row_i + 1
 
+    # 2. Process Header into Greenstone friendly metadata terms     
     if found_header:
         entry_utf8_row = []
@@ -87 +89 @@
         while row_i<num_rows:
             num_cols = worksheet.row_len(row_i)
-            entry_utf8_row = []
+            formatted_utf8_row = []
 
             found_pdf = False
 
-#            for entry in worksheet.row_values(row_i):
             for col_j in range(num_cols):
                 cell = worksheet.cell(row_i,col_j)
-#                xf = workbook.xf_list[cell.xf_index]
-#                format = workbook.format_map[xf.format_key]
-#                format_str = format.format_str
-
-#                print 'rowx=%d colx=%d ctype=%d xfx=%d s_value=%s fmt=%s' \
-#                    % (row_i, col_j, cell.ctype, cell.xf_index, str(cell.value), format_str)
 
                 cell_type  = worksheet.cell_type(row_i,col_j)
                 cell_value = worksheet.cell_value(row_i,col_j)
 
-                format_cell = format_excelval(workbook,cell_type,cell_value,False)
-                #print "**** format cell str = " +str(format_cell)
-
-                # entry = worksheet.cell_value(row_i,col_j)
-                entry = format_cell
+                formatted_cell = format_excelval(workbook,cell_type,cell_value,False)
 
                 if col_j == 0:
                     # Check to see if companion PDF file present
-                    pdf_filename = os.path.join(excel_dirname,"pdfs",entry+".pdf")
+                    pdf_filename = os.path.join(excel_dirname,"pdfs",formatted_cell+".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)
+                        pdf_file = os.path.join("pdfs",formatted_cell+".pdf")
+                        formatted_utf8_row.insert(0, pdf_file)
                                  
-                entry_utf8 = unicode(entry).encode("utf-8")
-                entry_utf8_row.append(entry_utf8)
+                formatted_cell_utf8 = unicode(formatted_cell).encode("utf-8")
+                formatted_utf8_row.append(formatted_cell_utf8)
             if found_pdf:
-                pdfbound_wr.writerow(entry_utf8_row)
+                pdfbound_wr.writerow(formatted_utf8_row)
             else:
-                unbound_wr.writerow(entry_utf8_row)
+                unbound_wr.writerow(formatted_utf8_row)
 
             row_i = row_i + 1