From 1ca791faf5b89c35b4b39d443d2118a882c3946b Mon Sep 17 00:00:00 2001
From: Thiago Macieira <thiago.macieira@intel.com>
Date: Mon, 21 May 2012 20:21:16 +0200
Subject: Add the QUrl::FullyDecoded flag to the component formatting

This allows the QUrl component getters to return fully decoded data,
like they did in Qt 4. This is necessary for some use-cases where the
component like the user name, password or path are used outside the
context of a URL. In those contexts, the percent-encoded data makes no
sense, and the loss of data of what could be represented in a URL is
acceptable.

Also take the opportunity to expand the documentation of those getter
methods, explaining what the options argument does.

Discussed-on: http://lists.qt-project.org/pipermail/development/2012-May/003811.html
Change-Id: I89f743cde78c02f169c88314bff0768714341419
Reviewed-by: Lars Knoll <lars.knoll@nokia.com>
Reviewed-by: David Faure <faure@kde.org>
Reviewed-by: Shane Kearns <shane.kearns@accenture.com>
---
 src/corelib/io/qurlrecode.cpp | 47 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 47 insertions(+)

(limited to 'src/corelib/io/qurlrecode.cpp')

diff --git a/src/corelib/io/qurlrecode.cpp b/src/corelib/io/qurlrecode.cpp
index 3d985dbdc0..12d23e9450 100644
--- a/src/corelib/io/qurlrecode.cpp
+++ b/src/corelib/io/qurlrecode.cpp
@@ -560,6 +560,43 @@ non_trivial:
     return 0;
 }
 
+static int decode(QString &appendTo, const ushort *begin, const ushort *end)
+{
+    const int origSize = appendTo.size();
+    const ushort *input = begin;
+    ushort *output = 0;
+    while (input != end) {
+        if (*input != '%') {
+            if (output)
+                *output++ = *input;
+            ++input;
+            continue;
+        }
+
+        if (Q_UNLIKELY(!output)) {
+            // detach
+            appendTo.resize(origSize + (end - begin));
+            output = reinterpret_cast<ushort *>(appendTo.begin()) + origSize;
+            memcpy(output, begin, (input - begin) * sizeof(ushort));
+            output += input - begin;
+        }
+
+        ++input;
+        Q_ASSERT(input <= end - 2); // we need two characters
+        Q_ASSERT(isHex(input[0]));
+        Q_ASSERT(isHex(input[1]));
+        *output++ = decodeNibble(input[0]) << 4 | decodeNibble(input[1]);
+        input += 2;
+    }
+
+    if (output) {
+        int len = output - reinterpret_cast<ushort *>(appendTo.begin());
+        appendTo.truncate(len);
+        return len - origSize;
+    }
+    return 0;
+}
+
 template <size_t N>
 static void maskTable(uchar (&table)[N], const uchar (&mask)[N])
 {
@@ -583,6 +620,12 @@ static void maskTable(uchar (&table)[N], const uchar (&mask)[N])
     \li QUrl::EncodeSpaces: if set, spaces will be encoded to "%20"; if unset, they will be " "
     \li QUrl::EncodeUnicode: if set, characters above U+0080 will be encoded to their UTF-8
                              percent-encoded form; if unset, they will be decoded to UTF-16
+    \li QUrl::FullyDecoded: if set, this function will decode all percent-encoded sequences,
+                            including that of the percent character. The resulting string
+                            will not be percent-encoded anymore. Use with caution!
+                            In this mode, the behaviour is undefined if the input string
+                            contains any percent-encoding sequences above %80.
+                            Also, the function will not correct bad % sequences.
     \endlist
 
     Other flags are ignored (including QUrl::EncodeReserved).
@@ -599,6 +642,10 @@ qt_urlRecode(QString &appendTo, const QChar *begin, const QChar *end,
              QUrl::ComponentFormattingOptions encoding, const ushort *tableModifications)
 {
     uchar actionTable[sizeof defaultActionTable];
+    if (encoding == QUrl::FullyDecoded) {
+        return decode(appendTo, reinterpret_cast<const ushort *>(begin), reinterpret_cast<const ushort *>(end));
+    }
+
     if (!(encoding & QUrl::EncodeDelimiters) && encoding & QUrl::DecodeReserved) {
         // reset the table
         memset(actionTable, DecodeCharacter, sizeof actionTable);
-- 
cgit v1.2.3