From de19dcf81aad60d4f86e31d1e9ff46b071b93903 Mon Sep 17 00:00:00 2001
From: Idan Horowitz <idan.horowitz@gmail.com>
Date: Mon, 13 Sep 2021 00:59:12 +0300
Subject: [PATCH] LibWeb: Add URL::url_decode for decoding form url encoded
 parameters

---
 Userland/Libraries/LibWeb/URL/URL.cpp | 42 ++++++++++++++++++++++++++-
 Userland/Libraries/LibWeb/URL/URL.h   |  2 ++
 2 files changed, 43 insertions(+), 1 deletion(-)

diff --git a/Userland/Libraries/LibWeb/URL/URL.cpp b/Userland/Libraries/LibWeb/URL/URL.cpp
index 4bb41d92f1..f201b8f979 100644
--- a/Userland/Libraries/LibWeb/URL/URL.cpp
+++ b/Userland/Libraries/LibWeb/URL/URL.cpp
@@ -6,7 +6,6 @@
  */
 
 #include <AK/StringBuilder.h>
-#include <AK/URL.h>
 #include <LibWeb/URL/URL.h>
 
 namespace Web::URL {
@@ -24,4 +23,45 @@ String url_encode(const Vector<QueryParam>& pairs, AK::URL::PercentEncodeSet per
     return builder.to_string();
 }
 
+Vector<QueryParam> url_decode(StringView const& input)
+{
+    // 1. Let sequences be the result of splitting input on 0x26 (&).
+    auto sequences = input.split_view('&');
+
+    // 2. Let output be an initially empty list of name-value tuples where both name and value hold a string.
+    Vector<QueryParam> output;
+
+    // 3. For each byte sequence bytes in sequences:
+    for (auto bytes : sequences) {
+        // 1. If bytes is the empty byte sequence, then continue.
+        if (bytes.is_empty())
+            continue;
+
+        StringView name;
+        StringView value;
+
+        // 2. If bytes contains a 0x3D (=), then let name be the bytes from the start of bytes up to but excluding its first 0x3D (=), and let value be the bytes, if any, after the first 0x3D (=) up to the end of bytes. If 0x3D (=) is the first byte, then name will be the empty byte sequence. If it is the last, then value will be the empty byte sequence.
+        if (auto index = bytes.find('='); index.has_value()) {
+            name = bytes.substring_view(0, *index);
+            value = bytes.substring_view(*index + 1);
+        }
+        // 3. Otherwise, let name have the value of bytes and let value be the empty byte sequence.
+        else {
+            name = bytes;
+            value = ""sv;
+        }
+
+        // 4. Replace any 0x2B (+) in name and value with 0x20 (SP).
+        auto space_decoded_name = name.replace("+"sv, " "sv, true);
+
+        // 5. Let nameString and valueString be the result of running UTF-8 decode without BOM on the percent-decoding of name and value, respectively.
+        auto name_string = AK::URL::percent_decode(space_decoded_name);
+        auto value_string = AK::URL::percent_decode(value);
+
+        output.empend(move(name_string), move(value_string));
+    }
+
+    return output;
+}
+
 }
diff --git a/Userland/Libraries/LibWeb/URL/URL.h b/Userland/Libraries/LibWeb/URL/URL.h
index a8c65aa5c2..2ea27fe772 100644
--- a/Userland/Libraries/LibWeb/URL/URL.h
+++ b/Userland/Libraries/LibWeb/URL/URL.h
@@ -8,6 +8,7 @@
 #pragma once
 
 #include <AK/String.h>
+#include <AK/URL.h>
 #include <AK/Vector.h>
 
 namespace Web::URL {
@@ -17,5 +18,6 @@ struct QueryParam {
     String value;
 };
 String url_encode(const Vector<QueryParam>&, AK::URL::PercentEncodeSet);
+Vector<QueryParam> url_decode(StringView const&);
 
 }