From 1cf43e501784731678d52655b2bb9fa67734cb12 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?S=C3=B8ren=20Kr=C3=B6ger?= <soren@kroger.dk>
Date: Fri, 23 Aug 2019 23:48:16 +0200
Subject: [PATCH] Handle multiple Content-Type headers correctly (#31238)

* Handle multiple Content-Type headers correctly

Avoids situations where mulitple Content-Type headers including charset information can result in errors like
```
LookupError: unknown encoding: UTF-8, text/html
```

* Account for multiple conflicting values for content-type and charset

* Add changelog fragment
---
 .../31238-uri-multi-content-type.yaml         |  3 +++
 lib/ansible/modules/net_tools/basics/uri.py   | 27 ++++++++++++++++---
 2 files changed, 27 insertions(+), 3 deletions(-)
 create mode 100644 changelogs/fragments/31238-uri-multi-content-type.yaml

diff --git a/changelogs/fragments/31238-uri-multi-content-type.yaml b/changelogs/fragments/31238-uri-multi-content-type.yaml
new file mode 100644
index 00000000000..2aa6ff71001
--- /dev/null
+++ b/changelogs/fragments/31238-uri-multi-content-type.yaml
@@ -0,0 +1,3 @@
+bugfixes:
+- uri - Handle multiple Content-Type headers correctly
+  (https://github.com/ansible/ansible/pull/31238)
diff --git a/lib/ansible/modules/net_tools/basics/uri.py b/lib/ansible/modules/net_tools/basics/uri.py
index eea77d8a858..7cf1e63341c 100644
--- a/lib/ansible/modules/net_tools/basics/uri.py
+++ b/lib/ansible/modules/net_tools/basics/uri.py
@@ -654,9 +654,30 @@ def main():
     # Default content_encoding to try
     content_encoding = 'utf-8'
     if 'content_type' in uresp:
-        content_type, params = cgi.parse_header(uresp['content_type'])
-        if 'charset' in params:
-            content_encoding = params['charset']
+        # Handle multiple Content-Type headers
+        charsets = []
+        content_types = []
+        for value in uresp['content_type'].split(','):
+            ct, params = cgi.parse_header(value)
+            if ct not in content_types:
+                content_types.append(ct)
+            if 'charset' in params:
+                if params['charset'] not in charsets:
+                    charsets.append(params['charset'])
+
+        if content_types:
+            content_type = content_types[0]
+            if len(content_types) > 1:
+                module.warn(
+                    'Received multiple conflicting Content-Type values (%s), using %s' % (', '.join(content_types), content_type)
+                )
+        if charsets:
+            content_encoding = charsets[0]
+            if len(charsets) > 1:
+                module.warn(
+                    'Received multiple conflicting charset values (%s), using %s' % (', '.join(charsets), content_encoding)
+                )
+
         u_content = to_text(content, encoding=content_encoding)
         if any(candidate in content_type for candidate in JSON_CANDIDATES):
             try: