Merge lp:~robru/cupstream2distro/stop-hardcoding-spreadsheet-column-numbers into lp:cupstream2distro

[Robert Bruce Park]

Stop hard-coding spreadsheet column numbers, adapt flexibly to spreadsheet modifications.

=== modified file 'citrain/prepare-silo-using-spreadsheet-info'
--- citrain/prepare-silo-using-spreadsheet-info	2014-04-04 07:35:59 +0000
+++ citrain/prepare-silo-using-spreadsheet-info	2014-07-28 16:53:19 +0000
@@ -27,10 +27,14 @@
 import sys
 import tempfile
 
-from cupstream2distro.settings import SPREADSHEET_CSV_URL, LANDERS_COL_NUM, SPREADSHEET_ID_COL_NUM, SPREADSHEET_SILONAME_COL_NUM, SPREADSHEET_MPS_COL_NUM, SPREADSHEET_SOURCES_COL_NUM
+from cupstream2distro.settings import SPREADSHEET_CSV_URL
 from cupstream2distro.tools import parse_and_clean_entry
 
 
+class COL:
+    pass
+
+
 if __name__ == '__main__':
 
     logging.basicConfig(level=logging.INFO)
@@ -82,23 +86,32 @@
     unique_silo_name = True
     with open(filename, 'rb') as f:
         content = csv.reader(f)
+
+        # First two rows are misc header data that don't conform to the columns
+        content.next() and content.next()
+
+        # Map column header names to column numbers
+        for i, heading in enumerate(content.next()):
+            setattr(COL, re.split('\W', heading.lower())[0], i)
+
+        # Now iterate over the remaining rows, which are just the actual data
         for row in content:
             if args.reconfigure_for_silo:
-                if row[SPREADSHEET_SILONAME_COL_NUM] == args.reconfigure_for_silo:
+                if row[COL.assigned] == args.reconfigure_for_silo:
                     # second matching
                     if request_found:
                         logging.error("{} is available more than once in the spreadsheet. Please request to fix some wrong metadata due to a bad automated sync.".format(args.reconfigure_for_silo))
                         unique_silo_name = False
-                    args.request_id = row[SPREADSHEET_ID_COL_NUM]
-                    raw_mps = row[SPREADSHEET_MPS_COL_NUM]
-                    raw_sources = row[SPREADSHEET_SOURCES_COL_NUM]
-                    raw_landers = row[LANDERS_COL_NUM]
+                    args.request_id = row[COL.request]
+                    raw_mps = row[COL.merge]
+                    raw_sources = row[COL.additional]
+                    raw_landers = row[COL.lander]
                     request_found = True
             else:
-                if row[SPREADSHEET_ID_COL_NUM] == args.request_id:
-                    raw_mps = row[SPREADSHEET_MPS_COL_NUM]
-                    raw_sources = row[SPREADSHEET_SOURCES_COL_NUM]
-                    raw_landers = row[LANDERS_COL_NUM]
+                if row[COL.request] == args.request_id:
+                    raw_mps = row[COL.merge]
+                    raw_sources = row[COL.additional]
+                    raw_landers = row[COL.lander]
                     request_found = True
                     break
     os.remove(filename)
 
=== modified file 'cupstream2distro/settings.py'
--- cupstream2distro/settings.py	2014-07-22 14:17:37 +0000
+++ cupstream2distro/settings.py	2014-07-28 16:53:19 +0000
@@ -20,11 +20,6 @@
 import os
 
 SPREADSHEET_CSV_URL = "https://docs.google.com/a/canonical.com/spreadsheet/ccc?key=0AuDk72Lpx8U5dFVHQ3FuMDJGLUZCamJfSjYzbWh3Wnc&output=csv"
-LANDERS_COL_NUM = 1
-SPREADSHEET_ID_COL_NUM = 10
-SPREADSHEET_SILONAME_COL_NUM = 11
-SPREADSHEET_MPS_COL_NUM = 5
-SPREADSHEET_SOURCES_COL_NUM = 6
 
 REV_STRING_FORMAT = "Automatic snapshot from revision"
 NEW_CHANGELOG_PATTERN = "^{} \(.*\) (?!UNRELEASED)"