Maintain header order in merge_csv

Previously, if the --header property was not specified then merge_csv
would use a header constructed by sorting all the fields in the input
files. That required that any use of merge_csv which did not already
have headers in the required order would have to explicitly specify the
headers. That made it harder to use merge_csv as a generic tool as each
invocation needed to be aware of what headers were exported in the
output.

This change causes merge_csv to simply use the headers in the order in
which they are encountered in the input files. That removes the need to
specify the --header option when generating the index files.

Bug: 179354495
Test: m out/soong/hiddenapi/hiddenapi-index.csv out/soong/hiddenapi/hiddenapi-unsupported.csv
      - make sure that they are not changed by this change.
Change-Id: I420b7d07aea85af6372cd7580a8be5e2cc82a513

1 files changed, 4 insertions, 3 deletions

diff --git a/scripts/hiddenapi/merge_csv.py b/scripts/hiddenapi/merge_csv.py
index b047aab71..a65326c51 100755
--- a/scripts/hiddenapi/merge_csv.py
+++ b/scripts/hiddenapi/merge_csv.py
@@ -55,14 +55,15 @@ else:
                 if entry.endswith('.uau'):
                     csv_readers.append(dict_reader(io.TextIOWrapper(zip.open(entry, 'r'))))
 
-headers = set()
 if args.header:
     fieldnames = args.header.split(',')
 else:
+    headers = {}
     # Build union of all columns from source files:
     for reader in csv_readers:
-        headers = headers.union(reader.fieldnames)
-    fieldnames = sorted(headers)
+        for fieldname in reader.fieldnames:
+            headers[fieldname] = ""
+    fieldnames = list(headers.keys())
 
 # By default chain the csv readers together so that the resulting output is
 # the concatenation of the rows from each of them: