From d6eab32bb6b0669b96be77976481d04902e19b6a Mon Sep 17 00:00:00 2001
From: Lucidiot <lucidiot@protonmail.com>
Date: Sun, 15 Dec 2019 13:17:56 +0100
Subject: [PATCH] Support XML namespaces in json2xml for thumbnails in danish
 feeds

---
 bin/json2xml  | 58 +++++++++++++++++++++++++++++++++++++++++++++++++--
 feedgen.sh    |  6 +++---
 jq/denmark.jq |  3 +--
 3 files changed, 60 insertions(+), 7 deletions(-)

diff --git a/bin/json2xml b/bin/json2xml
index fa18f4d..8fc123d 100755
--- a/bin/json2xml
+++ b/bin/json2xml
@@ -1,6 +1,60 @@
 #!/usr/bin/env python3
-import fileinput
+import argparse
 import json
 import xmltodict
+import sys
 
-print(xmltodict.unparse(json.loads('\n'.join(fileinput.input()))))
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        'infile',
+        type=argparse.FileType('r'),
+        nargs='?',
+        default=sys.stdin,
+    )
+    parser.add_argument(
+        'outfile',
+        type=argparse.FileType('w'),
+        nargs='?',
+        default=sys.stdout,
+    )
+    parser.add_argument(
+        '-s',
+        '--short-empty',
+        help='Shorten empty elements to <a/> instead of <a></a>',
+        action='store_true',
+        default=False,
+    )
+    parser.add_argument(
+        '-p',
+        '--pretty',
+        help='Indent XML with tabs and newlines.',
+        action='store_true',
+        default=False,
+    )
+    parser.add_argument(
+        '-ns',
+        '--namespace',
+        help='Add a namespace abbreviation.\n'
+             'Use the empty string as a name to set a default namespace.\n'
+             'xmltodict will expect the URL in your JSON objects:\n'
+             '{"http://my/ns:tag": "something"}',
+        action='append',
+        nargs=2,
+        default=[],
+        metavar=('URL', 'NAME'),
+    )
+
+    args = parser.parse_args()
+
+    args.outfile.write(xmltodict.unparse(
+        json.load(args.infile),
+        pretty=args.pretty,
+        namespaces=dict(args.namespace),
+        short_empty_elements=args.short_empty,
+    ))
+
+
+if __name__ == '__main__':
+    main()
diff --git a/feedgen.sh b/feedgen.sh
index 915195b..9159a5b 100755
--- a/feedgen.sh
+++ b/feedgen.sh
@@ -74,7 +74,7 @@ curl -s 'https://en.havarikommissionen.dk/aviation-archive/' \
 		--arg title 'AIBD Aviation' \
 		--arg description 'Accident Investigation Board Denmark aviation accident reports' \
 		--arg link 'https://en.havarikommissionen.dk/aviation-archive/' \
-	| json2xml > $DIR/feeds/aibd/aviation.xml.new \
+	| json2xml -s -ns 'http://search.yahoo.com/mrss/' media > $DIR/feeds/aibd/aviation.xml.new \
 	&& mv $DIR/feeds/aibd/aviation.xml.new $DIR/feeds/aibd/aviation.xml
 
 echo Building AIBD Rail feed to $DIR/feeds/aibd/rail.xml
@@ -84,7 +84,7 @@ curl -s 'https://en.havarikommissionen.dk/railway-archive/' \
 		--arg title 'AIBD Rail' \
 		--arg description 'Accident Investigation Board Denmark railroad accident reports' \
 		--arg link 'https://en.havarikommissionen.dk/railway-archive/' \
-	| json2xml > $DIR/feeds/aibd/rail.xml.new \
+	| json2xml -s -ns 'http://search.yahoo.com/mrss/' media > $DIR/feeds/aibd/rail.xml.new \
 	&& mv $DIR/feeds/aibd/rail.xml.new $DIR/feeds/aibd/rail.xml
 
 echo Building DMAIB feed to $DIR/feeds/dmaib.xml
@@ -94,5 +94,5 @@ curl -s 'https://dmaib.com/reports/?categorizations=9510' \
 		--arg title 'DMAIB' \
 		--arg description 'Danish Maritime Accident Investigation Board accident reports' \
 		--arg link 'https://dmaib.com/reports/?categorizations=9510' \
-	| json2xml > $DIR/feeds/dmaib.xml.new \
+	| json2xml -s -ns 'http://search.yahoo.com/mrss/' media > $DIR/feeds/dmaib.xml.new \
 	&& mv $DIR/feeds/dmaib.xml.new $DIR/feeds/dmaib.xml
diff --git a/jq/denmark.jq b/jq/denmark.jq
index cba075b..f775e84 100644
--- a/jq/denmark.jq
+++ b/jq/denmark.jq
@@ -12,7 +12,6 @@
 {
     "rss": {
         "@version": "2.0",
-        "@xmlns:media": "http://search.yahoo.com/mrss/",
         "channel": {
             "title": $title,
             "description": $description,
@@ -28,7 +27,7 @@
                 "link": .["data-url"],
                 "pubDate": (first(.children[-1].children[] | select(.class == "date")).text[-10:] | strptime("%d-%m-%Y") | mktime | strftime("%a, %d %b %Y %T %z")),
                 "category": [.children[-1].children[] | select(.class == "labels") | .children[].text],
-                "media:thumbnail": (
+                "http://search.yahoo.com/mrss/:thumbnail": (
                     if .children[0].class == "media-left" then {
                         "@url": .children[0].children[0].src
                     } else empty end