Changeset 33018 for main/trunk/model-sites-dev

Timestamp:

2019-04-19T20:34:03+12:00 (5 years ago)

Author:

davidb

Message:

Script upgraded to work with full set of PDFs provided by Heritage NZ

File:

• main/trunk/model-sites-dev/heritage-nz/collect/reports-2019/prepare/xls-to-csv.py (modified) (2 diffs)

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

@@ -25 +25 @@
         value = xlrd.error_text_from_code[value]
     return value
+
+
+letter_to_folder = {
+  'a': "A - B",
+  'b': "A - B",
+  'c': "C - D",
+  'd': "C - D",
+  'e': "E - F",
+  'f': "E - F",
+  'g': "G - H",
+  'h': "G - H",
+  'i': "I - J",
+  'j': "I - J",
+  'k': "K - L",
+  'l': "K - L",
+  'm': "M - N",
+  'n': "M - N",
+  'o': "O - P",
+  'p': "O - P",
+  'q': "Q - R",
+  'r': "Q - R",
+  's': "S - T",
+  't': "S - T",
+  'u': "U - V",
+  'v': "U - V",
+  'w': "W - Z",
+  'x': "W - Z",
+  'y': "W - Z",
+  'z': "W - Z"
+}
+
+def id_to_relative_pdf_file(id):
+    first_char = id[0:1]
+    first_char_lower = first_char.lower()
+
+    file_tail = letter_to_folder[first_char_lower]
+    file_root = "Reports " + file_tail
+
+    pdf_file = os.path.join("Digital-Library-PDFs",file_root,id+".pdf")
+
+    return pdf_file
 
 
@@ -103 +144 @@
                 if col_j == 0:
                     # Check to see if companion PDF file present
-                    pdf_filename = os.path.join(excel_dirname,"pdfs",formatted_cell+".pdf")
+                    # pdf_filename = os.path.join(excel_dirname,"pdfs",formatted_cell+".pdf")
+                    id = formatted_cell.replace(" ","")
+
+                    pdf_file = id_to_relative_pdf_file(id)
+                    pdf_file_root, pdf_ext = os.path.splitext(pdf_file)
+                    PDF_file = pdf_file_root + ".PDF"
+
+                    pdf_filename = os.path.join(excel_dirname,pdf_file)
+                    PDF_filename = os.path.join(excel_dirname,PDF_file)
+
                     if os.path.exists(pdf_filename):
                         found_pdf = True
-                        pdf_file = os.path.join("pdfs",formatted_cell+".pdf")
                         formatted_utf8_row.insert(0, pdf_file)
-                                 
+                    elif os.path.exists(PDF_filename):
+                        found_pdf = True
+                        formatted_utf8_row.insert(0, PDF_file)
+                    else:
+                        print "Unbound id: '" + id + "'"
+
+                if isinstance(formatted_cell, basestring):
+                    # Remove any trailing whitespace.  
+                    # Newline at end particular harmful for a entry in the CSV file
+                    formatted_cell = formatted_cell.rstrip();
+
                 formatted_cell_utf8 = unicode(formatted_cell).encode("utf-8")
                 formatted_utf8_row.append(formatted_cell_utf8)