From 8682c2612ff35062f1b2e20ec1b008db49b252a3 Mon Sep 17 00:00:00 2001
From: Ander Juaristi <ajuaristi@gmx.es>
Date: Mon, 20 Apr 2015 23:16:18 +0200
Subject: [PATCH] Make sure Wget does not unescape reserved chars.

* testenv/Test-reserved-chars.py: New file.

* testenv/Makefile.am: Added new test Test-reserved-chars.py.

When following redirections, Wget should not unescape the reserved
characters that might appear in target URLs.
---
 testenv/Makefile.am            |  3 +-
 testenv/Test-reserved-chars.py | 59 ++++++++++++++++++++++++++++++++++
 2 files changed, 61 insertions(+), 1 deletion(-)
 create mode 100755 testenv/Test-reserved-chars.py

diff --git a/testenv/Makefile.am b/testenv/Makefile.am
index a4e03522..9acf0f34 100644
--- a/testenv/Makefile.am
+++ b/testenv/Makefile.am
@@ -53,7 +53,8 @@ if HAVE_PYTHON3
     Test-Post.py                                    \
     Test-504.py                                     \
     Test--spider-r.py                               \
-    Test-redirect-crash.py
+    Test-redirect-crash.py                          \
+    Test-reserved-chars.py
 
   # added test cases expected to fail here and under TESTS
   XFAIL_TESTS =
diff --git a/testenv/Test-reserved-chars.py b/testenv/Test-reserved-chars.py
new file mode 100755
index 00000000..e5d33d07
--- /dev/null
+++ b/testenv/Test-reserved-chars.py
@@ -0,0 +1,59 @@
+#!/usr/bin/env python3
+from sys import exit
+from os import environ # to set LC_ALL
+from test.http_test import HTTPTest
+from misc.wget_file import WgetFile
+
+"""
+This test ensures that Wget keeps reserved characters in URLs in non-UTF-8 charsets.
+"""
+# This bug only happened with ASCII charset,
+# so we need to set LC_ALL="C" in order to reproduce it.
+environ["LC_ALL"] = "C"
+
+TEST_NAME = "URLs with reserved characters"
+######### File Definitions #########
+RequestList = [
+    [
+        "HEAD /base.html",
+        "GET /base.html",
+        "GET /robots.txt",
+        "HEAD /a%2Bb.html",
+        "GET /a%2Bb.html"
+    ]
+]
+A_File_Name = "base.html"
+B_File_Name = "a%2Bb.html"
+A_File = WgetFile (A_File_Name, "<a href=\"a%2Bb.html\">")
+B_File = WgetFile (B_File_Name, "this is file B")
+
+WGET_OPTIONS = " --spider -r"
+WGET_URLS = [[A_File_Name]]
+
+Files = [[A_File, B_File]]
+
+ExpectedReturnCode = 0
+ExpectedDownloadedFiles = []
+
+######### Pre and Post Test Hooks #########
+pre_test = {
+    "ServerFiles"   : Files
+}
+test_options = {
+    "WgetCommands"      : WGET_OPTIONS,
+    "Urls"              : WGET_URLS
+}
+post_test = {
+    "ExpectedFiles"     : ExpectedDownloadedFiles,
+    "ExpectedRetcode"   : ExpectedReturnCode,
+    "FilesCrawled"      : RequestList
+}
+
+err = HTTPTest (
+                name=TEST_NAME,
+                pre_hook=pre_test,
+                test_params=test_options,
+                post_hook=post_test
+).begin ()
+
+exit (err)