whytofly
/
qt6-bb10
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
qt6-bb10/src/corelib/io/qurl.cpp

3583 lines
118 KiB
C++
Raw Blame History

/****************************************************************************
**
** Copyright (C) 2012 Nokia Corporation and/or its subsidiary(-ies).
** Copyright (C) 2012 Intel Corporation.
** Contact: http://www.qt-project.org/
**
** This file is part of the QtCore module of the Qt Toolkit.
**
** $QT_BEGIN_LICENSE:LGPL$
** GNU Lesser General Public License Usage
** This file may be used under the terms of the GNU Lesser General Public
** License version 2.1 as published by the Free Software Foundation and
** appearing in the file LICENSE.LGPL included in the packaging of this
** file. Please review the following information to ensure the GNU Lesser
** General Public License version 2.1 requirements will be met:
** http://www.gnu.org/licenses/old-licenses/lgpl-2.1.html.
**
** In addition, as a special exception, Nokia gives you certain additional
** rights. These rights are described in the Nokia Qt LGPL Exception
** version 1.1, included in the file LGPL_EXCEPTION.txt in this package.
**
** GNU General Public License Usage
** Alternatively, this file may be used under the terms of the GNU General
** Public License version 3.0 as published by the Free Software Foundation
** and appearing in the file LICENSE.GPL included in the packaging of this
** file. Please review the following information to ensure the GNU General
** Public License version 3.0 requirements will be met:
** http://www.gnu.org/copyleft/gpl.html.
**
** Other Usage
** Alternatively, this file may be used in accordance with the terms and
** conditions contained in a signed written agreement between you and Nokia.
**
**
**
**
**
**
** $QT_END_LICENSE$
**
****************************************************************************/
/*!
\class QUrl
\inmodule QtCore
\brief The QUrl class provides a convenient interface for working
with URLs.
\reentrant
\ingroup io
\ingroup network
\ingroup shared
It can parse and construct URLs in both encoded and unencoded
form. QUrl also has support for internationalized domain names
(IDNs).
The most common way to use QUrl is to initialize it via the
constructor by passing a QString. Otherwise, setUrl() can also
be used.
URLs can be represented in two forms: encoded or unencoded. The
unencoded representation is suitable for showing to users, but
the encoded representation is typically what you would send to
a web server. For example, the unencoded URL
"http://b\\uuml\c{}hler.example.com" would be sent to the server as
"http://xn--bhler-kva.example.com/List%20of%20applicants.xml".
A URL can also be constructed piece by piece by calling
setScheme(), setUserName(), setPassword(), setHost(), setPort(),
setPath(), setQuery() and setFragment(). Some convenience
functions are also available: setAuthority() sets the user name,
password, host and port. setUserInfo() sets the user name and
password at once.
Call isValid() to check if the URL is valid. This can be done at
any point during the constructing of a URL.
Constructing a query is particularly convenient through the use
of setQueryItems(), addQueryItem() and removeQueryItem(). Use
setQueryDelimiters() to customize the delimiters used for
generating the query string.
For the convenience of generating encoded URL strings or query
strings, there are two static functions called
fromPercentEncoding() and toPercentEncoding() which deal with
percent encoding and decoding of QStrings.
Calling isRelative() will tell whether or not the URL is
relative. A relative URL can be resolved by passing it as argument
to resolved(), which returns an absolute URL. isParentOf() is used
for determining whether one URL is a parent of another.
fromLocalFile() constructs a QUrl by parsing a local
file path. toLocalFile() converts a URL to a local file path.
The human readable representation of the URL is fetched with
toString(). This representation is appropriate for displaying a
URL to a user in unencoded form. The encoded form however, as
returned by toEncoded(), is for internal use, passing to web
servers, mail clients and so on.
QUrl conforms to the URI specification from
\l{RFC 3986} (Uniform Resource Identifier: Generic Syntax), and includes
scheme extensions from \l{RFC 1738} (Uniform Resource Locators). Case
folding rules in QUrl conform to \l{RFC 3491} (Nameprep: A Stringprep
Profile for Internationalized Domain Names (IDN)).
\section2 Character Conversions
Follow these rules to avoid erroneous character conversion when
dealing with URLs and strings:
\list
\li When creating an QString to contain a URL from a QByteArray or a
char*, always use QString::fromUtf8().
\endlist
*/
/*!
\enum QUrl::ParsingMode
The parsing mode controls the way QUrl parses strings.
\value TolerantMode QUrl will try to correct some common errors in URLs.
This mode is useful for parsing URLs coming from sources
not known to be strictly standards-conforming.
\value StrictMode Only valid URLs are accepted. This mode is useful for
general URL validation.
\value DecodedMode QUrl will interpret the URL component in the fully-decoded form,
where percent characters stand for themselves, not as the beginning
of a percent-encoded sequence. This mode is only valid for the
setters setting components of a URL; it is not permitted in
the QUrl constructor, in fromEncoded() or in setUrl().
In TolerantMode, the parser has the following behaviour:
\list
\li Spaces and "%20": unencoded space characters will be accepted and will
be treated as equivalent to "%20".
\li Single "%" characters: Any occurrences of a percent character "%" not
followed by exactly two hexadecimal characters (e.g., "13% coverage.html")
will be replaced by "%25". Note that one lone "%" character will trigger
the correction mode for all percent characters.
\li Reserved and unreserved characters: An encoded URL should only
contain a few characters as literals; all other characters should
be percent-encoded. In TolerantMode, these characters will be
automatically percent-encoded where they are not allowed:
space / double-quote / "<" / ">" / "\" /
"^" / "`" / "{" / "|" / "}"
Those same characters can be decoded again by passing QUrl::DecodeReserved
to toString() or toEncoded().
\endlist
When in StrictMode, if a parsing error is found, isValid() will return \c
false and errorString() will return a simple message describing the error.
If more than one error is detected, it is undefined which error gets
reported.
Note that TolerantMode is not usually enough for parsing user input, which
often contains more errors and expectations than the parser can deal with.
When dealing with data coming directly from the user -- as opposed to data
coming from data-transfer sources, such as other programs -- it is
recommended to use fromUserInput().
\sa fromUserInput(), setUrl(), toString(), toEncoded(), QUrl::FormattingOptions
*/
/*!
\enum QUrl::UrlFormattingOption
The formatting options define how the URL is formatted when written out
as text.
\value None The format of the URL is unchanged.
\value RemoveScheme The scheme is removed from the URL.
\value RemovePassword Any password in the URL is removed.
\value RemoveUserInfo Any user information in the URL is removed.
\value RemovePort Any specified port is removed from the URL.
\value RemoveAuthority
\value RemovePath The URL's path is removed, leaving only the scheme,
host address, and port (if present).
\value RemoveQuery The query part of the URL (following a '?' character)
is removed.
\value RemoveFragment
\value PreferLocalFile If the URL is a local file according to isLocalFile()
and contains no query or fragment, a local file path is returned.
\value StripTrailingSlash The trailing slash is removed if one is present.
Note that the case folding rules in \l{RFC 3491}{Nameprep}, which QUrl
conforms to, require host names to always be converted to lower case,
regardless of the Qt::FormattingOptions used.
The options from QUrl::ComponentFormattingOptions are also possible.
\sa QUrl::ComponentFormattingOptions
*/
/*!
\enum QUrl::ComponentFormattingOption
\since 5.0
The component formatting options define how the components of an URL will
be formatted when written out as text. They can be combined with the
options from QUrl::FormattingOptions when used in toString() and
toEncoded().
\value PrettyDecoded The component is returned in a "pretty form", with
most percent-encoded characters decoded. The exact
behavior of PrettyDecoded varies from component to
component and may also change from Qt release to Qt
release. This is the default.
\value EncodeSpaces Leave space characters in their encoded form ("%20").
\value EncodeUnicode Leave non-US-ASCII characters encoded in their UTF-8
percent-encoded form (e.g., "%C3%A9" for the U+00E9
codepoint, LATIN SMALL LETTER E WITH ACUTE).
\value EncodeDelimiters Leave certain delimiters in their encoded form, as
would appear in the URL when the full URL is
represented as text. The delimiters are affected
by this option change from component to component.
\value EncodeReserved Leave the US-ASCII reserved characters in their encoded
forms.
\value DecodeReserved Decode the US-ASCII reserved characters.
\value FullyEncoded Leave all characters in their properly-encoded form,
as this component would appear as part of a URL. When
used with toString(), this produces a fully-compliant
URL in QString form, exactly equal to the result of
toEncoded()
\value FullyDecoded Attempt to decode as much as possible. For individual
components of the URL, this decodes every percent
encoding sequence, including control characters (U+0000
to U+001F) and UTF-8 sequences found in percent-encoded form.
Note: if the component contains non-US-ASCII sequences
that aren't valid UTF-8 sequences, the behaviour is
undefined since QString cannot represent those values
(data will be lost!)
This mode is should not be used in functions where more
than one URL component is returned (userInfo() and authority())
and it is not allowed in url() and toString().
The values of EncodeReserved and DecodeReserved should not be used together
in one call. The behaviour is undefined if that happens. They are provided
as separate values because the behaviour of the "pretty mode" with regards
to reserved characters is different on certain components and specially on
the full URL.
The FullyDecoded mode is similar to the behaviour of the functions
returning QString in Qt 4.x, including the fact that they will most likely
cause data loss if the component in question contains a non-UTF-8
percent-encoded sequence. Fortunately, those cases aren't common, so this
mode should be used when the component in question is used in a non-URL
context. For example, in an FTP client application, the path to the remote
file could be stored in a QUrl object, and the string to be transmitted to
the FTP server should be obtained using this flag.
\sa QUrl::FormattingOptions
*/
#include "qurl.h"
#include "qurl_p.h"
#include "qplatformdefs.h"
#include "qstring.h"
#include "qstringlist.h"
#include "qdebug.h"
#include "qhash.h"
#include "qdir.h" // for QDir::fromNativeSeparators
#include "qtldurl_p.h"
#include "private/qipaddress_p.h"
#include "qurlquery.h"
#if defined(Q_OS_WINCE_WM)
#pragma optimize("g", off)
#endif
QT_BEGIN_NAMESPACE
inline static bool isHex(char c)
{
c |= 0x20;
return (c >= '0' && c <= '9') || (c >= 'a' && c <= 'f');
}
static inline QString ftpScheme()
{
return QStringLiteral("ftp");
}
static inline QString httpScheme()
{
return QStringLiteral("http");
}
static inline QString fileScheme()
{
return QStringLiteral("file");
}
QUrlPrivate::QUrlPrivate()
: ref(1), port(-1),
errorCode(NoError), errorSupplement(0),
sectionIsPresent(0), sectionHasError(0)
{
}
QUrlPrivate::QUrlPrivate(const QUrlPrivate &copy)
: ref(1), port(copy.port),
scheme(copy.scheme),
userName(copy.userName),
password(copy.password),
host(copy.host),
path(copy.path),
query(copy.query),
fragment(copy.fragment),
errorCode(copy.errorCode),
errorSupplement(copy.errorSupplement),
sectionIsPresent(copy.sectionIsPresent),
sectionHasError(copy.sectionHasError)
{
}
// From RFC 3896, Appendix A Collected ABNF for URI
// URI = scheme ":" hier-part [ "?" query ] [ "#" fragment ]
//[...]
// scheme = ALPHA *( ALPHA / DIGIT / "+" / "-" / "." )
//
// authority = [ userinfo "@" ] host [ ":" port ]
// userinfo = *( unreserved / pct-encoded / sub-delims / ":" )
// host = IP-literal / IPv4address / reg-name
// port = *DIGIT
//[...]
// reg-name = *( unreserved / pct-encoded / sub-delims )
//[..]
// pchar = unreserved / pct-encoded / sub-delims / ":" / "@"
//
// query = *( pchar / "/" / "?" )
//
// fragment = *( pchar / "/" / "?" )
//
// pct-encoded = "%" HEXDIG HEXDIG
//
// unreserved = ALPHA / DIGIT / "-" / "." / "_" / "~"
// reserved = gen-delims / sub-delims
// gen-delims = ":" / "/" / "?" / "#" / "[" / "]" / "@"
// sub-delims = "!" / "$" / "&" / "'" / "(" / ")"
// / "*" / "+" / "," / ";" / "="
// the path component has a complex ABNF that basically boils down to
// slash-separated segments of "pchar"
// The above is the strict definition of the URL components and it is what we
// return encoded as FullyEncoded. However, we store the equivalent to
// PrettyDecoded internally, as that is the default formatting mode and most
// likely to be used. PrettyDecoded decodes spaces, unicode sequences and
// unambiguous delimiters.
//
// An ambiguous delimiter is a delimiter that, if appeared decoded, would be
// interpreted as the beginning of a new component. The exact delimiters that
// match that definition change according to the use. When each field is
// considered in isolation from the rest, there are no ambiguities. In other
// words, we always store the most decoded form (except for the query, see
// below).
//
// The ambiguities arise when components are put together. From last to first
// component of a full URL, the ambiguities are:
// - fragment: none, since it's the last.
// - query: the "#" character is ambiguous, as it starts the fragment. In
// addition, the "+" character is treated specially, as should be both
// intra-query delimiters. Since we don't know which ones they are, we
// keep all reserved characters untouched.
// - path: the "#" and "?" characters are ambigous. In addition to them,
// the slash itself is considered special.
// - host: completely special but never ambiguous, see setHost() below.
// - password: the "#", "?", "/", "[", "]" and "@" characters are ambiguous
// - username: the "#", "?", "/", "[", "]", "@", and ":" characters are ambiguous
// - scheme: doesn't accept any delimiter, see setScheme() below.
//
// When the authority component is considered in isolation, the ambiguities of
// its components are:
// - host: special, never ambiguous
// - password: "[", "]", "@" are ambiguous
// - username: "[", "]", "@", ":" are ambiguous
//
// Finally, when the userinfo is considered in isolation, the ambiguities of its
// components are:
// - password: none, since it's the last
// - username: ":" is ambiguous
// list the recoding table modifications to be used with the recodeFromUser and
// appendToUser functions, according to the rules above.
// the encodedXXX tables are run with the delimiters set to "leave" by default;
// the decodedXXX tables are run with the delimiters set to "decode" by default
// (except for the query, which doesn't use these functions)
#define decode(x) ushort(x)
#define leave(x) ushort(0x100 | (x))
#define encode(x) ushort(0x200 | (x))
static const ushort encodedUserNameActions[] = {
// first field, everything must be encoded, including the ":"
// userinfo = *( unreserved / pct-encoded / sub-delims / ":" )
encode('/'), // 0
encode('?'), // 1
encode('#'), // 2
encode('['), // 3
encode(']'), // 4
encode('@'), // 5
encode(':'), // 6
0
};
static const ushort * const decodedUserNameInAuthorityActions = encodedUserNameActions + 3;
static const ushort * const decodedUserNameInUserInfoActions = encodedUserNameActions + 6;
static const ushort * const decodedUserNameInUrlActions = encodedUserNameActions;
static const ushort * const decodedUserNameInIsolationActions = 0;
static const ushort encodedPasswordActions[] = {
// same as encodedUserNameActions, but decode ":"
// userinfo = *( unreserved / pct-encoded / sub-delims / ":" )
encode('/'), // 0
encode('?'), // 1
encode('#'), // 2
encode('['), // 3
encode(']'), // 4
encode('@'), // 5
0
};
static const ushort * const decodedPasswordInAuthorityActions = encodedPasswordActions + 3;
static const ushort * const decodedPasswordInUserInfoActions = 0;
static const ushort * const decodedPasswordInUrlActions = encodedPasswordActions;
static const ushort * const decodedPasswordInIsolationActions = 0;
static const ushort encodedPathActions[] = {
// pchar = unreserved / pct-encoded / sub-delims / ":" / "@"
encode('['), // 0
encode(']'), // 1
encode('?'), // 2
encode('#'), // 3
leave('/'), // 4
0
};
static const ushort decodedPathInUrlActions[] = {
decode('{'), // 0
decode('}'), // 1
encode('?'), // 2
encode('#'), // 3
leave('/'), // 4
0
};
static const ushort * const decodedPathInIsolationActions = encodedPathActions + 4; // leave('/')
static const ushort encodedFragmentActions[] = {
// fragment = *( pchar / "/" / "?" )
// gen-delims permitted: ":" / "@" / "/" / "?"
// -> must encode: "[" / "]" / "#"
// HOWEVER: we allow "#" to remain decoded
decode('#'), // 0
decode(':'), // 1
decode('@'), // 2
decode('/'), // 3
decode('?'), // 4
encode('['), // 5
encode(']'), // 6
0
};
static const ushort * const decodedFragmentInUrlActions = 0;
static const ushort * const decodedFragmentInIsolationActions = 0;
// the query is handled specially: the decodedQueryXXX tables are run with
// the delimiters set to "leave" by default and the others set to "encode"
static const ushort encodedQueryActions[] = {
// query = *( pchar / "/" / "?" )
// gen-delims permitted: ":" / "@" / "/" / "?"
// HOWEVER: we leave alone them alone, plus "[" and "]"
// -> must encode: "#"
encode('#'), // 0
0
};
static const ushort decodedQueryInIsolationActions[] = {
decode('"'), // 0
decode('<'), // 1
decode('>'), // 2
decode('^'), // 3
decode('\\'),// 4
decode('|'), // 5
decode('{'), // 6
decode('}'), // 7
decode('#'), // 8
0
};
static const ushort decodedQueryInUrlActions[] = {
decode('{'), // 6
decode('}'), // 7
encode('#'), // 8
0
};
static inline void parseDecodedComponent(QString &data)
{
data.replace(QLatin1Char('%'), QStringLiteral("%25"));
}
static inline QString
recodeFromUser(const QString &input, const ushort *actions, int from, int to)
{
QString output;
const QChar *begin = input.constData() + from;
const QChar *end = input.constData() + to;
if (qt_urlRecode(output, begin, end,
QUrl::DecodeReserved, actions))
return output;
return input.mid(from, to - from);
}
// appendXXXX functions:
// the internal value is stored in its most decoded form, so that case is easy.
// DecodeUnicode and DecodeSpaces are handled by qt_urlRecode.
// That leaves these functions to handle two cases related to delimiters:
// 1) encoded encodedXXXX tables
// 2) decoded decodedXXXX tables
static inline void appendToUser(QString &appendTo, const QString &value, QUrl::FormattingOptions options,
const ushort *encodedActions, const ushort *decodedActions)
{
if (options == QUrl::PrettyDecoded) {
appendTo += value;
return;
}
const ushort *actions = 0;
if (options & QUrl::EncodeDelimiters)
actions = encodedActions;
else
actions = decodedActions;
if (!qt_urlRecode(appendTo, value.constData(), value.constEnd(), options, actions))
appendTo += value;
}
inline void QUrlPrivate::appendAuthority(QString &appendTo, QUrl::FormattingOptions options, Section appendingTo) const
{
if ((options & QUrl::RemoveUserInfo) != QUrl::RemoveUserInfo) {
appendUserInfo(appendTo, options, appendingTo);
// add '@' only if we added anything
if (hasUserName() || (hasPassword() && (options & QUrl::RemovePassword) == 0))
appendTo += QLatin1Char('@');
}
appendHost(appendTo, options);
if (!(options & QUrl::RemovePort) && port != -1)
appendTo += QLatin1Char(':') + QString::number(port);
}
inline void QUrlPrivate::appendUserInfo(QString &appendTo, QUrl::FormattingOptions options, Section appendingTo) const
{
if (Q_LIKELY(!hasUserInfo()))
return;
const ushort *userNameActions;
const ushort *passwordActions;
if (options & QUrl::EncodeDelimiters) {
userNameActions = encodedUserNameActions;
passwordActions = encodedPasswordActions;
} else {
switch (appendingTo) {
case UserInfo:
userNameActions = decodedUserNameInUserInfoActions;
passwordActions = decodedPasswordInUserInfoActions;
break;
case Authority:
userNameActions = decodedUserNameInAuthorityActions;
passwordActions = decodedPasswordInAuthorityActions;
break;
case FullUrl:
default:
userNameActions = decodedUserNameInUrlActions;
passwordActions = decodedPasswordInUrlActions;
break;
}
}
if ((options & QUrl::EncodeReserved) == 0)
options |= QUrl::DecodeReserved;
if (!qt_urlRecode(appendTo, userName.constData(), userName.constEnd(), options, userNameActions))
appendTo += userName;
if (options & QUrl::RemovePassword || !hasPassword()) {
return;
} else {
appendTo += QLatin1Char(':');
if (!qt_urlRecode(appendTo, password.constData(), password.constEnd(), options, passwordActions))
appendTo += password;
}
}
inline void QUrlPrivate::appendUserName(QString &appendTo, QUrl::FormattingOptions options) const
{
appendToUser(appendTo, userName, options, encodedUserNameActions, decodedUserNameInIsolationActions);
}
inline void QUrlPrivate::appendPassword(QString &appendTo, QUrl::FormattingOptions options) const
{
appendToUser(appendTo, password, options, encodedPasswordActions, decodedPasswordInIsolationActions);
}
inline void QUrlPrivate::appendPath(QString &appendTo, QUrl::FormattingOptions options, Section appendingTo) const
{
if (appendingTo != Path && !(options & QUrl::EncodeDelimiters)) {
if (!qt_urlRecode(appendTo, path.constData(), path.constEnd(), options, decodedPathInUrlActions))
appendTo += path;
} else {
appendToUser(appendTo, path, options, encodedPathActions, decodedPathInIsolationActions);
}
}
inline void QUrlPrivate::appendFragment(QString &appendTo, QUrl::FormattingOptions options) const
{
appendToUser(appendTo, fragment, options, encodedFragmentActions, decodedFragmentInIsolationActions);
}
inline void QUrlPrivate::appendQuery(QString &appendTo, QUrl::FormattingOptions options, Section appendingTo) const
{
// almost the same code as the previous functions
// except we prefer not to touch the delimiters
if (options == QUrl::PrettyDecoded && appendingTo == Query) {
appendTo += query;
return;
}
const ushort *actions = 0;
if (options & QUrl::EncodeDelimiters) {
actions = encodedQueryActions;
} else {
// reset to default qt_urlRecode behaviour (leave delimiters alone)
options |= QUrl::EncodeDelimiters;
actions = appendingTo == Query ? decodedQueryInIsolationActions : decodedQueryInUrlActions;
}
if (!qt_urlRecode(appendTo, query.constData(), query.constData() + query.length(),
options, actions))
appendTo += query;
}
// setXXX functions
bool QUrlPrivate::setScheme(const QString &value, int len)
{
// schemes are strictly RFC-compliant:
// scheme = ALPHA *( ALPHA / DIGIT / "+" / "-" / "." )
// but we need to decode any percent-encoding sequences that fall on
// those characters
// we also lowercase the scheme
scheme.clear();
sectionIsPresent |= Scheme;
sectionHasError |= Scheme; // assume it has errors, we'll clear before returning true
errorCode = SchemeEmptyError;
if (len == 0)
return false;
// validate it:
errorCode = InvalidSchemeError;
int needsLowercasing = -1;
const ushort *p = reinterpret_cast<const ushort *>(value.constData());
for (int i = 0; i < len; ++i) {
if (p[i] >= 'a' && p[i] <= 'z')
continue;
if (p[i] >= 'A' && p[i] <= 'Z') {
needsLowercasing = i;
continue;
}
if (p[i] >= '0' && p[i] <= '9' && i > 0)
continue;
if (p[i] == '+' || p[i] == '-' || p[i] == '.')
continue;
// found something else
errorSupplement = p[i];
return false;
}
scheme = value.left(len);
sectionHasError &= ~Scheme;
errorCode = NoError;
if (needsLowercasing != -1) {
// schemes are ASCII only, so we don't need the full Unicode toLower
QChar *schemeData = scheme.data(); // force detaching here
for (int i = needsLowercasing; i >= 0; --i) {
register ushort c = schemeData[i].unicode();
if (c >= 'A' && c <= 'Z')
schemeData[i] = c + 0x20;
}
}
return true;
}
bool QUrlPrivate::setAuthority(const QString &auth, int from, int end, QUrl::ParsingMode mode)
{
sectionHasError &= ~Authority;
sectionIsPresent &= ~Authority;
sectionIsPresent |= Host;
if (from == end) {
userName.clear();
password.clear();
host.clear();
port = -1;
return true;
}
int userInfoIndex = auth.indexOf(QLatin1Char('@'), from);
if (uint(userInfoIndex) < uint(end)) {
setUserInfo(auth, from, userInfoIndex);
from = userInfoIndex + 1;
}
int colonIndex = auth.lastIndexOf(QLatin1Char(':'), end - 1);
if (colonIndex < from)
colonIndex = -1;
if (uint(colonIndex) < uint(end)) {
if (auth.at(from).unicode() == '[') {
// check if colonIndex isn't inside the "[...]" part
int closingBracket = auth.indexOf(QLatin1Char(']'), from);
if (uint(closingBracket) > uint(colonIndex))
colonIndex = -1;
}
}
if (colonIndex == end - 1) {
// found a colon but no digits after it
sectionHasError |= Port;
errorCode = PortEmptyError;
} else if (uint(colonIndex) < uint(end)) {
unsigned long x = 0;
for (int i = colonIndex + 1; i < end; ++i) {
ushort c = auth.at(i).unicode();
if (c >= '0' && c <= '9') {
x *= 10;
x += c - '0';
} else {
sectionHasError |= Port;
errorCode = InvalidPortError;
x = ulong(-1); // x != ushort(x)
break;
}
}
if (x == ushort(x)) {
port = ushort(x);
} else {
sectionHasError |= Port;
errorCode = InvalidPortError;
}
} else {
port = -1;
}
return setHost(auth, from, qMin<uint>(end, colonIndex), mode) && !(sectionHasError & Port);
}
void QUrlPrivate::setUserInfo(const QString &userInfo, int from, int end)
{
int delimIndex = userInfo.indexOf(QLatin1Char(':'), from);
setUserName(userInfo, from, qMin<uint>(delimIndex, end));
if (uint(delimIndex) >= uint(end)) {
password.clear();
sectionIsPresent &= ~Password;
sectionHasError &= ~Password;
} else {
setPassword(userInfo, delimIndex + 1, end);
}
}
inline void QUrlPrivate::setUserName(const QString &value, int from, int end)
{
sectionIsPresent |= UserName;
sectionHasError &= ~UserName;
userName = recodeFromUser(value, decodedUserNameInIsolationActions, from, end);
}
inline void QUrlPrivate::setPassword(const QString &value, int from, int end)
{
sectionIsPresent |= Password;
sectionHasError &= ~Password;
password = recodeFromUser(value, decodedPasswordInIsolationActions, from, end);
}
inline void QUrlPrivate::setPath(const QString &value, int from, int end)
{
// sectionIsPresent |= Path; // not used, save some cycles
sectionHasError &= ~Path;
path = recodeFromUser(value, decodedPathInIsolationActions, from, end);
// ### FIXME?
// check for the "path-noscheme" case
// if the path contains a ":" before the first "/", it could be misinterpreted
// as a scheme
}
inline void QUrlPrivate::setFragment(const QString &value, int from, int end)
{
sectionIsPresent |= Fragment;
sectionHasError &= ~Fragment;
fragment = recodeFromUser(value, decodedFragmentInIsolationActions, from, end);
}
inline void QUrlPrivate::setQuery(const QString &value, int from, int iend)
{
sectionIsPresent |= Query;
sectionHasError &= ~Query;
// use the default actions for the query (don't set QUrl::DecodeAllDelimiters)
QString output;
const QChar *begin = value.constData() + from;
const QChar *end = value.constData() + iend;
// leave delimiters alone but decode the rest
if (qt_urlRecode(output, begin, end, QUrl::EncodeDelimiters,
decodedQueryInIsolationActions))
query = output;
else
query = value.mid(from, iend - from);
}
// Host handling
// The RFC says the host is:
// host = IP-literal / IPv4address / reg-name
// IP-literal = "[" ( IPv6address / IPvFuture ) "]"
// IPvFuture = "v" 1*HEXDIG "." 1*( unreserved / sub-delims / ":" )
// [a strict definition of IPv6Address and IPv4Address]
// reg-name = *( unreserved / pct-encoded / sub-delims )
//
// We deviate from the standard in all but IPvFuture. For IPvFuture we accept
// and store only exactly what the RFC says we should. No percent-encoding is
// permitted in this field, so Unicode characters and space aren't either.
//
// For IPv4 addresses, we accept broken addresses like inet_aton does (that is,
// less than three dots). However, we correct the address to the proper form
// and store the corrected address. After correction, we comply to the RFC and
// it's exclusively composed of unreserved characters.
//
// For IPv6 addresses, we accept addresses including trailing (embedded) IPv4
// addresses, the so-called v4-compat and v4-mapped addresses. We also store
// those addresses like that in the hostname field, which violates the spec.
// IPv6 hosts are stored with the square brackets in the QString. It also
// requires no transformation in any way.
//
// As for registered names, it's the other way around: we accept only valid
// hostnames as specified by STD 3 and IDNA. That means everything we accept is
// valid in the RFC definition above, but there are many valid reg-names
// according to the RFC that we do not accept in the name of security. Since we
// do accept IDNA, reg-names are subject to ACE encoding and decoding, which is
// specified by the DecodeUnicode flag. The hostname is stored in its Unicode form.
inline void QUrlPrivate::appendHost(QString &appendTo, QUrl::FormattingOptions options) const
{
// this is the only flag that matters
options &= QUrl::EncodeUnicode;
if (host.isEmpty())
return;
if (host.at(0).unicode() == '[') {
// IPv6Address and IPvFuture address never require any transformation
appendTo += host;
} else {
// this is either an IPv4Address or a reg-name
// if it is a reg-name, it is already stored in Unicode form
if (options == QUrl::EncodeUnicode)
appendTo += qt_ACE_do(host, ToAceOnly);
else
appendTo += host;
}
}
// the whole IPvFuture is passed and parsed here, including brackets
static int parseIpFuture(QString &host, const QChar *begin, const QChar *end)
{
// IPvFuture = "v" 1*HEXDIG "." 1*( unreserved / sub-delims / ":" )
static const char acceptable[] =
"!$&'()*+,;=" // sub-delims
":" // ":"
"-._~"; // unreserved
// the brackets and the "v" have been checked
if (begin[3].unicode() != '.')
return begin[3].unicode();
if ((begin[2].unicode() >= 'A' && begin[2].unicode() >= 'F') ||
(begin[2].unicode() >= 'a' && begin[2].unicode() <= 'f') ||
(begin[2].unicode() >= '0' && begin[2].unicode() <= '9')) {
// this is so unlikely that we'll just go down the slow path
// decode the whole string, skipping the "[vH." and "]" which we already know to be there
host += QString::fromRawData(begin, 4);
begin += 4;
--end;
QString decoded;
if (qt_urlRecode(decoded, begin, end, QUrl::FullyEncoded, 0)) {
begin = decoded.constBegin();
end = decoded.constEnd();
}
for ( ; begin != end; ++begin) {
if (begin->unicode() >= 'A' && begin->unicode() <= 'Z')
host += *begin;
else if (begin->unicode() >= 'a' && begin->unicode() <= 'z')
host += *begin;
else if (begin->unicode() >= '0' && begin->unicode() <= '9')
host += *begin;
else if (begin->unicode() < 0x80 && strchr(acceptable, begin->unicode()) != 0)
host += *begin;
else
return begin->unicode();
}
host += QLatin1Char(']');
return -1;
}
return begin[2].unicode();
}
// ONLY the IPv6 address is parsed here, WITHOUT the brackets
static bool parseIp6(QString &host, const QChar *begin, const QChar *end)
{
QIPAddressUtils::IPv6Address address;
if (!QIPAddressUtils::parseIp6(address, begin, end)) {
// IPv6 failed parsing, check if it was a percent-encoded character in
// the middle and try again
QString decoded;
if (!qt_urlRecode(decoded, begin, end, QUrl::FullyEncoded, 0)) {
// no transformation, nothing to re-parse
return false;
}
// recurse
// if the parsing fails again, the qt_urlRecode above will return 0
return parseIp6(host, decoded.constBegin(), decoded.constEnd());
}
host.reserve(host.size() + (end - begin));
host += QLatin1Char('[');
QIPAddressUtils::toString(host, address);
host += QLatin1Char(']');
return true;
}
bool QUrlPrivate::setHost(const QString &value, int from, int iend, QUrl::ParsingMode mode)
{
const QChar *begin = value.constData() + from;
const QChar *end = value.constData() + iend;
const int len = end - begin;
host.clear();
sectionIsPresent |= Host;
sectionHasError &= ~Host;
if (len == 0)
return true;
if (begin[0].unicode() == '[') {
// IPv6Address or IPvFuture
// smallest IPv6 address is "[::]" (len = 4)
// smallest IPvFuture address is "[v7.X]" (len = 6)
if (end[-1].unicode() != ']') {
sectionHasError |= Host;
errorCode = HostMissingEndBracket;
return false;
}
if (len > 5 && begin[1].unicode() == 'v') {
int c = parseIpFuture(host, begin, end);
if (c != -1) {
sectionHasError |= Host;
errorCode = InvalidIPvFutureError;
errorSupplement = short(c);
}
return c == -1;
}
if (parseIp6(host, begin + 1, end - 1))
return true;
sectionHasError |= Host;
errorCode = begin[1].unicode() == 'v' ?
InvalidIPvFutureError : InvalidIPv6AddressError;
return false;
}
// check if it's an IPv4 address
QIPAddressUtils::IPv4Address ip4;
if (QIPAddressUtils::parseIp4(ip4, begin, end)) {
// yes, it was
QIPAddressUtils::toString(host, ip4);
sectionHasError &= ~Host;
return true;
}
// This is probably a reg-name.
// But it can also be an encoded string that, when decoded becomes one
// of the types above.
//
// Two types of encoding are possible:
// percent encoding (e.g., "%31%30%2E%30%2E%30%2E%31" -> "10.0.0.1")
// Unicode encoding (some non-ASCII characters case-fold to digits
// when nameprepping is done)
//
// The qt_ACE_do function below applies nameprepping and the STD3 check.
// That means a Unicode string may become an IPv4 address, but it cannot
// produce a '[' or a '%'.
// check for percent-encoding first
QString s;
if (mode == QUrl::TolerantMode && qt_urlRecode(s, begin, end, QUrl::DecodeReserved, 0)) {
// something was decoded
// anything encoded left?
if (s.contains(QChar(0x25))) { // '%'
sectionHasError |= Host;
errorCode = InvalidRegNameError;
return false;
}
// recurse
return setHost(s, 0, s.length(), QUrl::StrictMode);
}
s = qt_ACE_do(QString::fromRawData(begin, len), NormalizeAce);
if (s.isEmpty()) {
sectionHasError |= Host;
errorCode = InvalidRegNameError;
return false;
}
// check IPv4 again
if (QIPAddressUtils::parseIp4(ip4, s.constBegin(), s.constEnd())) {
QIPAddressUtils::toString(host, ip4);
} else {
host = s;
}
return true;
}
void QUrlPrivate::parse(const QString &url, QUrl::ParsingMode parsingMode)
{
// URI-reference = URI / relative-ref
// URI = scheme ":" hier-part [ "?" query ] [ "#" fragment ]
// relative-ref = relative-part [ "?" query ] [ "#" fragment ]
// hier-part = "//" authority path-abempty
// / other path types
// relative-part = "//" authority path-abempty
// / other path types here
sectionIsPresent = 0;
sectionHasError = 0;
// find the important delimiters
int colon = -1;
int question = -1;
int hash = -1;
const int len = url.length();
const QChar *const begin = url.constData();
const ushort *const data = reinterpret_cast<const ushort *>(begin);
for (int i = 0; i < len; ++i) {
register uint uc = data[i];
if (uc == '#' && hash == -1) {
hash = i;
// nothing more to be found
break;
}
if (question == -1) {
if (uc == ':' && colon == -1)
colon = i;
else if (uc == '?')
question = i;
}
}
// check if we have a scheme
int hierStart;
if (colon != -1 && setScheme(url, colon)) {
hierStart = colon + 1;
} else {
// recover from a failed scheme: it might not have been a scheme at all
scheme.clear();
sectionHasError = 0;
sectionIsPresent = 0;
hierStart = 0;
}
int pathStart;
int hierEnd = qMin<uint>(qMin<uint>(question, hash), len);
if (hierEnd - hierStart >= 2 && data[hierStart] == '/' && data[hierStart + 1] == '/') {
// we have an authority, it ends at the first slash after these
int authorityEnd = hierEnd;
for (int i = hierStart + 2; i < authorityEnd ; ++i) {
if (data[i] == '/') {
authorityEnd = i;
break;
}
}
setAuthority(url, hierStart + 2, authorityEnd, parsingMode);
// even if we failed to set the authority properly, let's try to recover
pathStart = authorityEnd;
setPath(url, pathStart, hierEnd);
} else {
userName.clear();
password.clear();
host.clear();
port = -1;
pathStart = hierStart;
if (hierStart < hierEnd)
setPath(url, hierStart, hierEnd);
else
path.clear();
}
if (uint(question) < uint(hash))
setQuery(url, question + 1, qMin<uint>(hash, len));
if (hash != -1)
setFragment(url, hash + 1, len);
if (sectionHasError || parsingMode == QUrl::TolerantMode)
return;
// The parsing so far was tolerant of errors, so the StrictMode
// parsing is actually implemented here, as an extra post-check.
// We only execute it if we haven't found any errors so far.
// What we need to look out for, that the regular parser tolerates:
// - percent signs not followed by two hex digits
// - forbidden characters, which should always appear encoded
// '"' / '<' / '>' / '\' / '^' / '`' / '{' / '|' / '}' / BKSP
// control characters
// - delimiters not allowed in certain positions
// . scheme: parser is already strict
// . user info: gen-delims (except for ':') disallowed
// . host: parser is stricter than the standard
// . port: parser is stricter than the standard
// . path: all delimiters allowed
// . fragment: all delimiters allowed
// . query: all delimiters allowed
// We would only need to check the user-info. However, the presence
// of the disallowed gen-delims changes the parsing, so we don't
// actually need to do anything
static const char forbidden[] = "\"<>\\^`{|}\x7F";
for (uint i = 0; i < uint(len); ++i) {
register uint uc = data[i];
if (uc >= 0x80)
continue;
if ((uc == '%' && (uint(len) < i + 2 || !isHex(data[i + 1]) || !isHex(data[i + 2])))
|| uc <= 0x20 || strchr(forbidden, uc)) {
// found an error
errorSupplement = uc;
// where are we?
if (i > uint(hash)) {
errorCode = InvalidFragmentError;
sectionHasError |= Fragment;
} else if (i > uint(question)) {
errorCode = InvalidQueryError;
sectionHasError |= Query;
} else if (i > uint(pathStart)) {
// pathStart is never -1
errorCode = InvalidPathError;
sectionHasError |= Path;
} else {
// It must be in the authority, since the scheme is strict.
// Since the port and hostname parsers are also strict,
// the error can only have happened in the user info.
int pos = url.indexOf(QLatin1Char(':'), hierStart);
if (i > uint(pos)) {
errorCode = InvalidPasswordError;
sectionHasError |= Password;
} else {
errorCode = InvalidUserNameError;
sectionHasError |= UserName;
}
}
}
}
}
/*
From http://www.ietf.org/rfc/rfc3986.txt, 5.2.3: Merge paths
Returns a merge of the current path with the relative path passed
as argument.
Note: \a relativePath is relative (does not start with '/').
*/
QString QUrlPrivate::mergePaths(const QString &relativePath) const
{
// If the base URI has a defined authority component and an empty
// path, then return a string consisting of "/" concatenated with
// the reference's path; otherwise,
if (!host.isEmpty() && path.isEmpty())
return QLatin1Char('/') + relativePath;
// Return a string consisting of the reference's path component
// appended to all but the last segment of the base URI's path
// (i.e., excluding any characters after the right-most "/" in the
// base URI path, or excluding the entire base URI path if it does
// not contain any "/" characters).
QString newPath;
if (!path.contains(QLatin1Char('/')))
newPath = relativePath;
else
newPath = path.leftRef(path.lastIndexOf(QLatin1Char('/')) + 1) + relativePath;
return newPath;
}
/*
From http://www.ietf.org/rfc/rfc3986.txt, 5.2.4: Remove dot segments
Removes unnecessary ../ and ./ from the path. Used for normalizing
the URL.
*/
static void removeDotsFromPath(QString *path)
{
// The input buffer is initialized with the now-appended path
// components and the output buffer is initialized to the empty
// string.
QChar *out = path->data();
const QChar *in = out;
const QChar *end = out + path->size();
// If the input buffer consists only of
// "." or "..", then remove that from the input
// buffer;
if (path->size() == 1 && in[0].unicode() == '.')
++in;
else if (path->size() == 2 && in[0].unicode() == '.' && in[1].unicode() == '.')
in += 2;
// While the input buffer is not empty, loop:
while (in < end) {
// otherwise, if the input buffer begins with a prefix of "../" or "./",
// then remove that prefix from the input buffer;
if (path->size() >= 2 && in[0].unicode() == '.' && in[1].unicode() == '/')
in += 2;
else if (path->size() >= 3 && in[0].unicode() == '.'
&& in[1].unicode() == '.' && in[2].unicode() == '/')
in += 3;
// otherwise, if the input buffer begins with a prefix of
// "/./" or "/.", where "." is a complete path segment,
// then replace that prefix with "/" in the input buffer;
if (in <= end - 3 && in[0].unicode() == '/' && in[1].unicode() == '.'
&& in[2].unicode() == '/') {
in += 2;
continue;
} else if (in == end - 2 && in[0].unicode() == '/' && in[1].unicode() == '.') {
*out++ = QLatin1Char('/');
in += 2;
break;
}
// otherwise, if the input buffer begins with a prefix
// of "/../" or "/..", where ".." is a complete path
// segment, then replace that prefix with "/" in the
// input buffer and remove the last //segment and its
// preceding "/" (if any) from the output buffer;
if (in <= end - 4 && in[0].unicode() == '/' && in[1].unicode() == '.'
&& in[2].unicode() == '.' && in[3].unicode() == '/') {
while (out > path->constData() && (--out)->unicode() != '/')
;
if (out == path->constData() && out->unicode() != '/')
++in;
in += 3;
continue;
} else if (in == end - 3 && in[0].unicode() == '/' && in[1].unicode() == '.'
&& in[2].unicode() == '.') {
while (out > path->constData() && (--out)->unicode() != '/')
;
if (out->unicode() == '/')
++out;
in += 3;
break;
}
// otherwise move the first path segment in
// the input buffer to the end of the output
// buffer, including the initial "/" character
// (if any) and any subsequent characters up
// to, but not including, the next "/"
// character or the end of the input buffer.
*out++ = *in++;
while (in < end && in->unicode() != '/')
*out++ = *in++;
}
path->truncate(out - path->constData());
}
#if 0
void QUrlPrivate::validate() const
{
QUrlPrivate *that = (QUrlPrivate *)this;
that->encodedOriginal = that->toEncoded(); // may detach
parse(ParseOnly);
QURL_SETFLAG(that->stateFlags, Validated);
if (!isValid)
return;
QString auth = authority(); // causes the non-encoded forms to be valid
// authority() calls canonicalHost() which sets this
if (!isHostValid)
return;
if (scheme == QLatin1String("mailto")) {
if (!host.isEmpty() || port != -1 || !userName.isEmpty() || !password.isEmpty()) {
that->isValid = false;
that->errorInfo.setParams(0, QT_TRANSLATE_NOOP(QUrl, "expected empty host, username,"
"port and password"),
0, 0);
}
} else if (scheme == ftpScheme() || scheme == httpScheme()) {
if (host.isEmpty() && !(path.isEmpty() && encodedPath.isEmpty())) {
that->isValid = false;
that->errorInfo.setParams(0, QT_TRANSLATE_NOOP(QUrl, "the host is empty, but not the path"),
0, 0);
}
}
}
const QByteArray &QUrlPrivate::normalized() const
{
if (QURL_HASFLAG(stateFlags, QUrlPrivate::Normalized))
return encodedNormalized;
QUrlPrivate *that = const_cast<QUrlPrivate *>(this);
QURL_SETFLAG(that->stateFlags, QUrlPrivate::Normalized);
QUrlPrivate tmp = *this;
tmp.scheme = tmp.scheme.toLower();
tmp.host = tmp.canonicalHost();
// ensure the encoded and normalized parts of the URL
tmp.ensureEncodedParts();
if (tmp.encodedUserName.contains('%'))
q_normalizePercentEncoding(&tmp.encodedUserName, userNameExcludeChars);
if (tmp.encodedPassword.contains('%'))
q_normalizePercentEncoding(&tmp.encodedPassword, passwordExcludeChars);
if (tmp.encodedFragment.contains('%'))
q_normalizePercentEncoding(&tmp.encodedFragment, fragmentExcludeChars);
if (tmp.encodedPath.contains('%')) {
// the path is a bit special:
// the slashes shouldn't be encoded or decoded.
// They should remain exactly like they are right now
//
// treat the path as a slash-separated sequence of pchar
QByteArray result;
result.reserve(tmp.encodedPath.length());
if (tmp.encodedPath.startsWith('/'))
result.append('/');
const char *data = tmp.encodedPath.constData();
int lastSlash = 0;
int nextSlash;
do {
++lastSlash;
nextSlash = tmp.encodedPath.indexOf('/', lastSlash);
int len;
if (nextSlash == -1)
len = tmp.encodedPath.length() - lastSlash;
else
len = nextSlash - lastSlash;
if (memchr(data + lastSlash, '%', len)) {
// there's at least one percent before the next slash
QByteArray block = QByteArray(data + lastSlash, len);
q_normalizePercentEncoding(&block, pathExcludeChars);
result.append(block);
} else {
// no percents in this path segment, append wholesale
result.append(data + lastSlash, len);
}
// append the slash too, if it's there
if (nextSlash != -1)
result.append('/');
lastSlash = nextSlash;
} while (lastSlash != -1);
tmp.encodedPath = result;
}
if (!tmp.scheme.isEmpty()) // relative test
removeDotsFromPath(&tmp.encodedPath);
int qLen = tmp.query.length();
for (int i = 0; i < qLen; i++) {
if (qLen - i > 2 && tmp.query.at(i) == '%') {
++i;
tmp.query[i] = qToLower(tmp.query.at(i));
++i;
tmp.query[i] = qToLower(tmp.query.at(i));
}
}
encodedNormalized = tmp.toEncoded();
return encodedNormalized;
}
#endif
/*!
\macro QT_NO_URL_CAST_FROM_STRING
\relates QUrl
Disables automatic conversions from QString (or char *) to QUrl.
Compiling your code with this define is useful when you have a lot of
code that uses QString for file names and you wish to convert it to
use QUrl for network transparency. In any code that uses QUrl, it can
help avoid missing QUrl::resolved() calls, and other misuses of
QString to QUrl conversions.
\oldcode
url = filename; // probably not what you want
\newcode
url = QUrl::fromLocalFile(filename);
url = baseurl.resolved(QUrl(filename));
\endcode
\sa QT_NO_CAST_FROM_ASCII
*/
/*!
Constructs a URL by parsing \a url. QUrl will automatically percent encode
all characters that are not allowed in a URL and decode the percent-encoded
sequences that represent a character that is allowed in a URL.
Parses the \a url using the parser mode \a parsingMode. In TolerantMode
(the default), QUrl will correct certain mistakes, notably the presence of
a percent character ('%') not followed by two hexadecimal digits, and it
will accept any character in any position. In StrictMode, encoding mistakes
will not be tolerated and QUrl will also check that certain forbidden
characters are not present in unencoded form. If an error is detected in
StrictMode, isValid() will return false. The parsing mode DecodedMode is not
permitted in this context.
Example:
\snippet code/src_corelib_io_qurl.cpp 0
To construct a URL from an encoded string, you can also use fromEncoded():
\snippet code/src_corelib_io_qurl.cpp 1
Both functions are equivalent and, in Qt 5, both functions accept encoded
data. Usually, the choice of the QUrl constructor or setUrl() versus
fromEncoded() will depend on the source data: the constructor and setUrl()
take a QString, whereas fromEncoded takes a QByteArray.
\sa setUrl(), fromEncoded(), TolerantMode
*/
QUrl::QUrl(const QString &url, ParsingMode parsingMode) : d(0)
{
setUrl(url, parsingMode);
}
/*!
Constructs an empty QUrl object.
*/
QUrl::QUrl() : d(0)
{
}
/*!
Constructs a copy of \a other.
*/
QUrl::QUrl(const QUrl &other) : d(other.d)
{
if (d)
d->ref.ref();
}
/*!
Destructor; called immediately before the object is deleted.
*/
QUrl::~QUrl()
{
if (d && !d->ref.deref())
delete d;
}
/*!
Returns true if the URL is non-empty and valid; otherwise returns false.
The URL is run through a conformance test. Every part of the URL
must conform to the standard encoding rules of the URI standard
for the URL to be reported as valid.
\snippet code/src_corelib_io_qurl.cpp 2
*/
bool QUrl::isValid() const
{
if (isEmpty()) return false;
return d->sectionHasError == 0;
}
/*!
Returns true if the URL has no data; otherwise returns false.
\sa clear()
*/
bool QUrl::isEmpty() const
{
if (!d) return true;
return d->isEmpty();
}
/*!
Resets the content of the QUrl. After calling this function, the
QUrl is equal to one that has been constructed with the default
empty constructor.
\sa isEmpty()
*/
void QUrl::clear()
{
if (d && !d->ref.deref())
delete d;
d = 0;
}
/*!
Parses \a url and sets this object to that value. QUrl will automatically
percent encode all characters that are not allowed in a URL and decode the
percent-encoded sequences that represent a character that is allowed in a
URL.
Parses the \a url using the parser mode \a parsingMode. In TolerantMode
(the default), QUrl will correct certain mistakes, notably the presence of
a percent character ('%') not followed by two hexadecimal digits, and it
will accept any character in any position. In StrictMode, encoding mistakes
will not be tolerated and QUrl will also check that certain forbidden
characters are not present in unencoded form. If an error is detected in
StrictMode, isValid() will return false. The parsing mode DecodedMode is
not permitted in this context and will produce a run-time warning.
\sa url(), toString()
*/
void QUrl::setUrl(const QString &url, ParsingMode parsingMode)
{
if (parsingMode == DecodedMode) {
qWarning("QUrl: QUrl::DecodedMode is not permitted when parsing a full URL");
} else {
detach();
d->parse(url, parsingMode);
}
}
/*!
\fn void QUrl::setEncodedUrl(const QByteArray &encodedUrl, ParsingMode parsingMode)
\deprecated
Constructs a URL by parsing the contents of \a encodedUrl.
\a encodedUrl is assumed to be a URL string in percent encoded
form, containing only ASCII characters.
The parsing mode \a parsingMode is used for parsing \a encodedUrl.
\obsolete Use setUrl(QString::fromUtf8(encodedUrl), parsingMode)
\sa setUrl()
*/
/*!
Sets the scheme of the URL to \a scheme. As a scheme can only
contain ASCII characters, no conversion or decoding is done on the
input. It must also start with an ASCII letter.
The scheme describes the type (or protocol) of the URL. It's
represented by one or more ASCII characters at the start the URL,
and is followed by a ':'. The following example shows a URL where
the scheme is "ftp":
\image qurl-authority2.png
The scheme can also be empty, in which case the URL is interpreted
as relative.
\sa scheme(), isRelative()
*/
void QUrl::setScheme(const QString &scheme)
{
detach();
if (scheme.isEmpty()) {
// schemes are not allowed to be empty
d->sectionIsPresent &= ~QUrlPrivate::Scheme;
d->sectionHasError &= ~QUrlPrivate::Scheme;
d->scheme.clear();
} else {
d->setScheme(scheme, scheme.length());
}
}
/*!
Returns the scheme of the URL. If an empty string is returned,
this means the scheme is undefined and the URL is then relative.
The scheme can only contain US-ASCII letters or digits, which means it
cannot contain any character that would otherwise require encoding.
\sa setScheme(), isRelative()
*/
QString QUrl::scheme() const
{
if (!d) return QString();
return d->scheme;
}
/*!
Sets the authority of the URL to \a authority.
The authority of a URL is the combination of user info, a host
name and a port. All of these elements are optional; an empty
authority is therefore valid.
The user info and host are separated by a '@', and the host and
port are separated by a ':'. If the user info is empty, the '@'
must be omitted; although a stray ':' is permitted if the port is
empty.
The following example shows a valid authority string:
\image qurl-authority.png
The \a authority data is interpreted according to \a mode: in StrictMode,
any '%' characters must be followed by exactly two hexadecimal characters
and some characters (including space) are not allowed in undecoded form. In
TolerantMode (the default), all characters are accepted in undecoded form
and the tolerant parser will correct stray '%' not followed by two hex
characters. In DecodedMode, '%' stand for themselves and encoded characters
are not possible. Because of that, in DecodedMode, it is not possible to
use the delimiter characters as non-delimiters (e.g., a password containing
a '@').
\sa setUserInfo(), setHost(), setPort()
*/
void QUrl::setAuthority(const QString &authority, ParsingMode mode)
{
detach();
QString data = authority;
if (mode == DecodedMode) {
parseDecodedComponent(data);
mode = TolerantMode;
}
d->setAuthority(data, 0, data.length(), mode);
if (authority.isNull()) {
// QUrlPrivate::setAuthority cleared almost everything
// but it leaves the Host bit set
d->sectionIsPresent &= ~QUrlPrivate::Authority;
}
}
/*!
Returns the authority of the URL if it is defined; otherwise
an empty string is returned.
The \a options argument controls how to format the authority portion of the
URL. The value of QUrl::FullyDecoded should be avoided, since it may
produce an ambiguous return value (for example, if the username contains a
colon ':' or either the username or password contain an at-sign '@'). In
all other cases, this function returns an unambiguous value, which may
contain those characters still percent-encoded, plus some control
sequences not representable in decoded form in QString.
\sa setAuthority(), userInfo(), userName(), password(), host(), port()
*/
QString QUrl::authority(ComponentFormattingOptions options) const
{
if (!d) return QString();
QString result;
d->appendAuthority(result, options, QUrlPrivate::Authority);
return result;
}
/*!
Sets the user info of the URL to \a userInfo. The user info is an
optional part of the authority of the URL, as described in
setAuthority().
The user info consists of a user name and optionally a password,
separated by a ':'. If the password is empty, the colon must be
omitted. The following example shows a valid user info string:
\image qurl-authority3.png
The \a userInfo data is interpreted according to \a mode: in StrictMode,
any '%' characters must be followed by exactly two hexadecimal characters
and some characters (including space) are not allowed in undecoded form. In
TolerantMode (the default), all characters are accepted in undecoded form
and the tolerant parser will correct stray '%' not followed by two hex
characters. In DecodedMode, '%' stand for themselves and encoded characters
are not possible. Because of that, in DecodedMode, it is not possible to
use the ':' delimiter characters as non-delimiter in the user name.
\sa userInfo(), setUserName(), setPassword(), setAuthority()
*/
void QUrl::setUserInfo(const QString &userInfo, ParsingMode mode)
{
detach();
QString trimmed = userInfo.trimmed();
if (mode == DecodedMode) {
parseDecodedComponent(trimmed);
mode = TolerantMode;
}
d->setUserInfo(trimmed, 0, trimmed.length());
if (userInfo.isNull()) {
// QUrlPrivate::setUserInfo cleared almost everything
// but it leaves the UserName bit set
d->sectionIsPresent &= ~QUrlPrivate::UserInfo;
}
}
/*!
Returns the user info of the URL, or an empty string if the user
info is undefined.
The \a options argument controls how to format the user info component. The
value of QUrl::FullyDecoded should be avoided, since it may produce an
ambiguous return value (for example, if the username contains a colon ':').
In all other cases, this function returns an unambiguous value, which may
contain that characters still percent-encoded, plus some control sequences
not representable in decoded form in QString.
\sa setUserInfo(), userName(), password(), authority()
*/
QString QUrl::userInfo(ComponentFormattingOptions options) const
{
if (!d) return QString();
QString result;
d->appendUserInfo(result, options, QUrlPrivate::UserInfo);
return result;
}
/*!
Sets the URL's user name to \a userName. The \a userName is part
of the user info element in the authority of the URL, as described
in setUserInfo().
The \a userName data is interpreted according to \a mode: in StrictMode,
any '%' characters must be followed by exactly two hexadecimal characters
and some characters (including space) are not allowed in undecoded form. In
TolerantMode (the default), all characters are accepted in undecoded form
and the tolerant parser will correct stray '%' not followed by two hex
characters. In DecodedMode, '%' stand for themselves and encoded characters
are not possible.
QUrl::DecodedMode should be used when setting the user name from a data
source which is not a URL, such as a password dialog shown to the user or
with a user name obtained by calling userName() with the QUrl::FullyDecoded
formatting option.
\sa userName(), setUserInfo()
*/
void QUrl::setUserName(const QString &userName, ParsingMode mode)
{
detach();
QString data = userName;
if (mode == DecodedMode) {
parseDecodedComponent(data);
mode = TolerantMode;
}
d->setUserName(data, 0, data.length());
if (userName.isNull())
d->sectionIsPresent &= ~QUrlPrivate::UserName;
}
/*!
Returns the user name of the URL if it is defined; otherwise
an empty string is returned.
The \a options argument controls how to format the user name component. All
values produce an unambiguous result. With QUrl::FullyDecoded, all
percent-encoded sequences are decoded; otherwise, the returned value may
contain some percent-encoded sequences for some control sequences not
representable in decoded form in QString.
Note that QUrl::FullyDecoded may cause data loss if those non-representable
sequences are present. It is recommended to use that value when the result
will be used in a non-URL context, such as setting in QAuthenticator or
negotiating a login.
\sa setUserName(), userInfo()
*/
QString QUrl::userName(ComponentFormattingOptions options) const
{
if (!d) return QString();
QString result;
d->appendUserName(result, options);
return result;
}
/*!
\fn void QUrl::setEncodedUserName(const QByteArray &userName)
\deprecated
\since 4.4
Sets the URL's user name to the percent-encoded \a userName. The \a
userName is part of the user info element in the authority of the
URL, as described in setUserInfo().
\obsolete Use setUserName(QString::fromUtf8(userName))
\sa setUserName(), encodedUserName(), setUserInfo()
*/
/*!
\fn QByteArray QUrl::encodedUserName() const
\deprecated
\since 4.4
Returns the user name of the URL if it is defined; otherwise
an empty string is returned. The returned value will have its
non-ASCII and other control characters percent-encoded, as in
toEncoded().
\obsolete Use userName(QUrl::FullyEncoded).toLatin1()
\sa setEncodedUserName()
*/
/*!
Sets the URL's password to \a password. The \a password is part of
the user info element in the authority of the URL, as described in
setUserInfo().
The \a password data is interpreted according to \a mode: in StrictMode,
any '%' characters must be followed by exactly two hexadecimal characters
and some characters (including space) are not allowed in undecoded form. In
TolerantMode, all characters are accepted in undecoded form and the
tolerant parser will correct stray '%' not followed by two hex characters.
In DecodedMode, '%' stand for themselves and encoded characters are not
possible.
QUrl::DecodedMode should be used when setting the password from a data
source which is not a URL, such as a password dialog shown to the user or
with a password obtained by calling password() with the QUrl::FullyDecoded
formatting option.
\sa password(), setUserInfo()
*/
void QUrl::setPassword(const QString &password, ParsingMode mode)
{
detach();
QString data = password;
if (mode == DecodedMode) {
parseDecodedComponent(data);
mode = TolerantMode;
}
d->setPassword(data, 0, data.length());
if (password.isNull())
d->sectionIsPresent &= ~QUrlPrivate::Password;
}
/*!
Returns the password of the URL if it is defined; otherwise
an empty string is returned.
The \a options argument controls how to format the user name component. All
values produce an unambiguous result. With QUrl::FullyDecoded, all
percent-encoded sequences are decoded; otherwise, the returned value may
contain some percent-encoded sequences for some control sequences not
representable in decoded form in QString.
Note that QUrl::FullyDecoded may cause data loss if those non-representable
sequences are present. It is recommended to use that value when the result
will be used in a non-URL context, such as setting in QAuthenticator or
negotiating a login.
\sa setPassword()
*/
QString QUrl::password(ComponentFormattingOptions options) const
{
if (!d) return QString();
QString result;
d->appendPassword(result, options);
return result;
}
/*!
\fn void QUrl::setEncodedPassword(const QByteArray &password)
\deprecated
\since 4.4
Sets the URL's password to the percent-encoded \a password. The \a
password is part of the user info element in the authority of the
URL, as described in setUserInfo().
\obsolete Use setPassword(QString::fromUtf8(password));
\sa setPassword(), encodedPassword(), setUserInfo()
*/
/*!
\fn QByteArray QUrl::encodedPassword() const
\deprecated
\since 4.4
Returns the password of the URL if it is defined; otherwise an
empty string is returned. The returned value will have its
non-ASCII and other control characters percent-encoded, as in
toEncoded().
\obsolete Use password(QUrl::FullyEncoded).toLatin1()
\sa setEncodedPassword(), toEncoded()
*/
/*!
Sets the host of the URL to \a host. The host is part of the
authority.
The \a host data is interpreted according to \a mode: in StrictMode,
any '%' characters must be followed by exactly two hexadecimal characters
and some characters (including space) are not allowed in undecoded form. In
TolerantMode, all characters are accepted in undecoded form and the
tolerant parser will correct stray '%' not followed by two hex characters.
In DecodedMode, '%' stand for themselves and encoded characters are not
possible.
Note that, in all cases, the result of the parsing must be a valid hostname
according to STD 3 rules, as modified by the Internationalized Resource
Identifiers specification (RFC 3987). Invalid hostnames are not permitted
and will cause isValid() to become false.
\sa host(), setAuthority()
*/
void QUrl::setHost(const QString &host, ParsingMode mode)
{
detach();
QString data = host;
if (mode == DecodedMode) {
parseDecodedComponent(data);
mode = TolerantMode;
}
if (d->setHost(data, 0, data.length(), mode)) {
if (host.isNull())
d->sectionIsPresent &= ~QUrlPrivate::Host;
} else if (!data.startsWith(QLatin1Char('['))) {
// setHost failed, it might be IPv6 or IPvFuture in need of bracketing
ushort oldCode = d->errorCode;
ushort oldSupplement = d->errorSupplement;
data.prepend(QLatin1Char('['));
data.append(QLatin1Char(']'));
if (!d->setHost(data, 0, data.length(), mode)) {
// failed again: choose if this was an IPv6 error or not
if (!data.contains(QLatin1Char(':'))) {
d->errorCode = oldCode;
d->errorSupplement = oldSupplement;
}
}
}
}
/*!
Returns the host of the URL if it is defined; otherwise
an empty string is returned.
The \a options argument controls how the hostname will be formatted. The
QUrl::EncodeUnicode option will cause this function to return the hostname
in the ASCII-Compatible Encoding (ACE) form, which is suitable for use in
channels that are not 8-bit clean or that require the legacy hostname (such
as DNS requests or in HTTP request headers). If that flag is not present,
this function returns the International Domain Name (IDN) in Unicode form,
according to the list of permissible top-level domains (see
idnWhiteList()).
All other flags are ignored. Host names cannot contain control or percent
characters, so the returned value can be considered fully decoded.
\sa setHost(), idnWhitelist(), setIdnWhitelist(), authority()
*/
QString QUrl::host(ComponentFormattingOptions options) const
{
if (!d) return QString();
QString result;
d->appendHost(result, options);
if (result.startsWith(QLatin1Char('[')))
return result.mid(1, result.length() - 2);
return result;
}
/*!
\fn void QUrl::setEncodedHost(const QByteArray &host)
\deprecated
\since 4.4
Sets the URL's host to the ACE- or percent-encoded \a host. The \a
host is part of the user info element in the authority of the
URL, as described in setAuthority().
\obsolete Use setHost(QString::fromUtf8(host)).
\sa setHost(), encodedHost(), setAuthority(), fromAce()
*/
/*!
\fn QByteArray QUrl::encodedHost() const
\deprecated
\since 4.4
Returns the host part of the URL if it is defined; otherwise
an empty string is returned.
Note: encodedHost() does not return percent-encoded hostnames. Instead,
the ACE-encoded (bare ASCII in Punycode encoding) form will be
returned for any non-ASCII hostname.
This function is equivalent to calling QUrl::toAce() on the return
value of host().
\obsolete Use host(QUrl::FullyEncoded).toLatin1() or toAce(host()).
\sa setEncodedHost()
*/
/*!
Sets the port of the URL to \a port. The port is part of the
authority of the URL, as described in setAuthority().
\a port must be between 0 and 65535 inclusive. Setting the
port to -1 indicates that the port is unspecified.
*/
void QUrl::setPort(int port)
{
detach();
if (port < -1 || port > 65535) {
qWarning("QUrl::setPort: Out of range");
port = -1;
d->sectionHasError |= QUrlPrivate::Port;
d->errorCode = QUrlPrivate::InvalidPortError;
} else {
d->sectionHasError &= ~QUrlPrivate::Port;
}
d->port = port;
}
/*!
\since 4.1
Returns the port of the URL, or \a defaultPort if the port is
unspecified.
Example:
\snippet code/src_corelib_io_qurl.cpp 3
*/
int QUrl::port(int defaultPort) const
{
if (!d) return defaultPort;
return d->port == -1 ? defaultPort : d->port;
}
/*!
Sets the path of the URL to \a path. The path is the part of the
URL that comes after the authority but before the query string.
\image qurl-ftppath.png
For non-hierarchical schemes, the path will be everything
following the scheme declaration, as in the following example:
\image qurl-mailtopath.png
The \a path data is interpreted according to \a mode: in StrictMode,
any '%' characters must be followed by exactly two hexadecimal characters
and some characters (including space) are not allowed in undecoded form. In
TolerantMode (the default), all characters are accepted in undecoded form and the
tolerant parser will correct stray '%' not followed by two hex characters.
In DecodedMode, '%' stand for themselves and encoded characters are not
possible.
QUrl::DecodedMode should be used when setting the path from a data source
which is not a URL, such as a dialog shown to the user or with a path
obtained by calling path() with the QUrl::FullyDecoded formatting option.
\sa path()
*/
void QUrl::setPath(const QString &path, ParsingMode mode)
{
detach();
QString data = path;
if (mode == DecodedMode) {
parseDecodedComponent(data);
mode = TolerantMode;
}
d->setPath(data, 0, data.length());
// optimized out, since there is no path delimiter
// if (path.isNull())
// d->sectionIsPresent &= ~QUrlPrivate::Path;
}
/*!
Returns the path of the URL.
The \a options argument controls how to format the path component. All
values produce an unambiguous result. With QUrl::FullyDecoded, all
percent-encoded sequences are decoded; otherwise, the returned value may
contain some percent-encoded sequences for some control sequences not
representable in decoded form in QString.
Note that QUrl::FullyDecoded may cause data loss if those non-representable
sequences are present. It is recommended to use that value when the result
will be used in a non-URL context, such as sending to an FTP server.
\sa setPath()
*/
QString QUrl::path(ComponentFormattingOptions options) const
{
if (!d) return QString();
QString result;
d->appendPath(result, options, QUrlPrivate::Path);
return result;
}
/*!
\fn void QUrl::setEncodedPath(const QByteArray &path)
\deprecated
\since 4.4
Sets the URL's path to the percent-encoded \a path. The path is
the part of the URL that comes after the authority but before the
query string.
\image qurl-ftppath.png
For non-hierarchical schemes, the path will be everything
following the scheme declaration, as in the following example:
\image qurl-mailtopath.png
\obsolete Use setPath(QString::fromUtf8(path)).
\sa setPath(), encodedPath(), setUserInfo()
*/
/*!
\fn QByteArray QUrl::encodedPath() const
\deprecated
\since 4.4
Returns the path of the URL if it is defined; otherwise an
empty string is returned. The returned value will have its
non-ASCII and other control characters percent-encoded, as in
toEncoded().
\obsolete Use path(QUrl::FullyEncoded).toLatin1().
\sa setEncodedPath(), toEncoded()
*/
/*!
\since 4.2
Returns true if this URL contains a Query (i.e., if ? was seen on it).
\sa setQuery(), query(), hasFragment()
*/
bool QUrl::hasQuery() const
{
if (!d) return false;
return d->hasQuery();
}
/*!
Sets the query string of the URL to \a query.
This function is useful if you need to pass a query string that
does not fit into the key-value pattern, or that uses a different
scheme for encoding special characters than what is suggested by
QUrl.
Passing a value of QString() to \a query (a null QString) unsets
the query completely. However, passing a value of QString("")
will set the query to an empty value, as if the original URL
had a lone "?".
The \a query data is interpreted according to \a mode: in StrictMode,
any '%' characters must be followed by exactly two hexadecimal characters
and some characters (including space) are not allowed in undecoded form. In
TolerantMode, all characters are accepted in undecoded form and the
tolerant parser will correct stray '%' not followed by two hex characters.
In DecodedMode, '%' stand for themselves and encoded characters are not
possible.
Query strings often contain percent-encoded sequences, so use of
DecodedMode is discouraged. One special sequence to be aware of is that of
the plus character ('+'). QUrl does not convert spaces to plus characters,
even though HTML forms posted by web browsers do. In order to represent an
actual plus character in a query, the sequence "%2B" is usually used. This
function will leave "%2B" sequences untouched in TolerantMode or
StrictMode.
\sa query(), hasQuery()
*/
void QUrl::setQuery(const QString &query, ParsingMode mode)
{
detach();
QString data = query;
if (mode == DecodedMode) {
parseDecodedComponent(data);
mode = TolerantMode;
}
d->setQuery(data, 0, data.length());
if (query.isNull())
d->sectionIsPresent &= ~QUrlPrivate::Query;
}
/*!
\fn void QUrl::setEncodedQuery(const QByteArray &query)
\deprecated
Sets the query string of the URL to \a query. The string is
inserted as-is, and no further encoding is performed when calling
toEncoded().
This function is useful if you need to pass a query string that
does not fit into the key-value pattern, or that uses a different
scheme for encoding special characters than what is suggested by
QUrl.
Passing a value of QByteArray() to \a query (a null QByteArray) unsets
the query completely. However, passing a value of QByteArray("")
will set the query to an empty value, as if the original URL
had a lone "?".
\obsolete Use setQuery, which has the same null / empty behavior.
\sa encodedQuery(), hasQuery()
*/
/*!
\overload
\since 5.0
Sets the query string of the URL to \a query.
This function reconstructs the query string from the QUrlQuery object and
sets on this QUrl object. This function does not have parsing parameters
because the QUrlQuery contains data that is already parsed.
\sa query(), hasQuery()
*/
void QUrl::setQuery(const QUrlQuery &query)
{
detach();
// we know the data is in the right format
d->query = query.toString();
if (query.isEmpty())
d->sectionIsPresent &= ~QUrlPrivate::Query;
else
d->sectionIsPresent |= QUrlPrivate::Query;
}
/*!
\fn void QUrl::setQueryItems(const QList<QPair<QString, QString> > &query)
\deprecated
Sets the query string of the URL to an encoded version of \a
query. The contents of \a query are converted to a string
internally, each pair delimited by the character returned by
pairDelimiter(), and the key and value are delimited by
valueDelimiter().
\note This method does not encode spaces (ASCII 0x20) as plus (+) signs,
like HTML forms do. If you need that kind of encoding, you must encode
the value yourself and use QUrl::setEncodedQueryItems.
\obsolete Use QUrlQuery and setQuery().
\sa queryItems(), setEncodedQueryItems()
*/
/*!
\fn void QUrl::setEncodedQueryItems(const QList<QPair<QByteArray, QByteArray> > &query)
\deprecated
\since 4.4
Sets the query string of the URL to the encoded version of \a
query. The contents of \a query are converted to a string
internally, each pair delimited by the character returned by
pairDelimiter(), and the key and value are delimited by
valueDelimiter().
\obsolete Use QUrlQuery and setQuery().
\sa encodedQueryItems(), setQueryItems()
*/
/*!
\fn void QUrl::addQueryItem(const QString &key, const QString &value)
\deprecated
Inserts the pair \a key = \a value into the query string of the
URL.
The key/value pair is encoded before it is added to the query. The
pair is converted into separate strings internally. The \a key and
\a value is first encoded into UTF-8 and then delimited by the
character returned by valueDelimiter(). Each key/value pair is
delimited by the character returned by pairDelimiter().
\note This method does not encode spaces (ASCII 0x20) as plus (+) signs,
like HTML forms do. If you need that kind of encoding, you must encode
the value yourself and use QUrl::addEncodedQueryItem.
\obsolete Use QUrlQuery and setQuery().
\sa addEncodedQueryItem()
*/
/*!
\fn void QUrl::addEncodedQueryItem(const QByteArray &key, const QByteArray &value)
\deprecated
\since 4.4
Inserts the pair \a key = \a value into the query string of the
URL.
\obsolete Use QUrlQuery and setQuery().
\sa addQueryItem()
*/
/*!
\fn QList<QPair<QString, QString> > QUrl::queryItems() const
\deprecated
Returns the query string of the URL, as a map of keys and values.
\note This method does not decode spaces plus (+) signs as spaces (ASCII
0x20), like HTML forms do. If you need that kind of decoding, you must
use QUrl::encodedQueryItems and decode the data yourself.
\obsolete Use QUrlQuery.
\sa setQueryItems(), setEncodedQuery()
*/
/*!
\fn QList<QPair<QByteArray, QByteArray> > QUrl::encodedQueryItems() const
\deprecated
\since 4.4
Returns the query string of the URL, as a map of encoded keys and values.
\obsolete Use QUrlQuery.
\sa setEncodedQueryItems(), setQueryItems(), setEncodedQuery()
*/
/*!
\fn bool QUrl::hasQueryItem(const QString &key) const
\deprecated
Returns true if there is a query string pair whose key is equal
to \a key from the URL.
\obsolete Use QUrlQuery.
\sa hasEncodedQueryItem()
*/
/*!
\fn bool QUrl::hasEncodedQueryItem(const QByteArray &key) const
\deprecated
\since 4.4
Returns true if there is a query string pair whose key is equal
to \a key from the URL.
\obsolete Use QUrlQuery.
\sa hasQueryItem()
*/
/*!
\fn QString QUrl::queryItemValue(const QString &key) const
\deprecated
Returns the first query string value whose key is equal to \a key
from the URL.
\note This method does not decode spaces plus (+) signs as spaces (ASCII
0x20), like HTML forms do. If you need that kind of decoding, you must
use QUrl::encodedQueryItemValue and decode the data yourself.
\obsolete Use QUrlQuery.
\sa allQueryItemValues()
*/
/*!
\fn QByteArray QUrl::encodedQueryItemValue(const QByteArray &key) const
\deprecated
\since 4.4
Returns the first query string value whose key is equal to \a key
from the URL.
\obsolete Use QUrlQuery.
\sa queryItemValue(), allQueryItemValues()
*/
/*!
\fn QStringList QUrl::allQueryItemValues(const QString &key) const
\deprecated
Returns the a list of query string values whose key is equal to
\a key from the URL.
\note This method does not decode spaces plus (+) signs as spaces (ASCII
0x20), like HTML forms do. If you need that kind of decoding, you must
use QUrl::allEncodedQueryItemValues and decode the data yourself.
\obsolete Use QUrlQuery.
\sa queryItemValue()
*/
/*!
\fn QList<QByteArray> QUrl::allEncodedQueryItemValues(const QByteArray &key) const
\deprecated
\since 4.4
Returns the a list of query string values whose key is equal to
\a key from the URL.
\obsolete Use QUrlQuery.
\sa allQueryItemValues(), queryItemValue(), encodedQueryItemValue()
*/
/*!
\fn void QUrl::removeQueryItem(const QString &key)
\deprecated
Removes the first query string pair whose key is equal to \a key
from the URL.
\obsolete Use QUrlQuery.
\sa removeAllQueryItems()
*/
/*!
\fn void QUrl::removeEncodedQueryItem(const QByteArray &key)
\deprecated
\since 4.4
Removes the first query string pair whose key is equal to \a key
from the URL.
\obsolete Use QUrlQuery.
\sa removeQueryItem(), removeAllQueryItems()
*/
/*!
\fn void QUrl::removeAllQueryItems(const QString &key)
\deprecated
Removes all the query string pairs whose key is equal to \a key
from the URL.
\obsolete Use QUrlQuery.
\sa removeQueryItem()
*/
/*!
\fn void QUrl::removeAllEncodedQueryItems(const QByteArray &key)
\deprecated
\since 4.4
Removes all the query string pairs whose key is equal to \a key
from the URL.
\obsolete Use QUrlQuery.
\sa removeQueryItem()
*/
/*!
\fn QByteArray QUrl::encodedQuery() const
\deprecated
Returns the query string of the URL in percent encoded form.
\obsolete Use query(QUrl::FullyEncoded).toLatin1()
\sa setEncodedQuery(), query()
*/
/*!
Returns the query string of the URL if there's a query string, or an empty
result if not. To determine if the parsed URL contained a query string, use
hasQuery().
The \a options argument controls how to format the query component. All
values produce an unambiguous result. With QUrl::FullyDecoded, all
percent-encoded sequences are decoded; otherwise, the returned value may
contain some percent-encoded sequences for some control sequences not
representable in decoded form in QString.
Note that use of QUrl::FullyDecoded in queries is discouraged, as queries
often contain data that is supposed to remain percent-encoded, including
the use of the "%2B" sequence to represent a plus character ('+').
\sa setQuery(), hasQuery()
*/
QString QUrl::query(ComponentFormattingOptions options) const
{
if (!d) return QString();
QString result;
d->appendQuery(result, options, QUrlPrivate::Query);
if (d->hasQuery() && result.isNull())
result.detach();
return result;
}
/*!
Sets the fragment of the URL to \a fragment. The fragment is the
last part of the URL, represented by a '#' followed by a string of
characters. It is typically used in HTTP for referring to a
certain link or point on a page:
\image qurl-fragment.png
The fragment is sometimes also referred to as the URL "reference".
Passing an argument of QString() (a null QString) will unset the fragment.
Passing an argument of QString("") (an empty but not null QString)
will set the fragment to an empty string (as if the original URL
had a lone "#").
The \a fragment data is interpreted according to \a mode: in StrictMode,
any '%' characters must be followed by exactly two hexadecimal characters
and some characters (including space) are not allowed in undecoded form. In
TolerantMode, all characters are accepted in undecoded form and the
tolerant parser will correct stray '%' not followed by two hex characters.
In DecodedMode, '%' stand for themselves and encoded characters are not
possible.
QUrl::DecodedMode should be used when setting the fragment from a data
source which is not a URL or with a fragment obtained by calling
fragment() with the QUrl::FullyDecoded formatting option.
\sa fragment(), hasFragment()
*/
void QUrl::setFragment(const QString &fragment, ParsingMode mode)
{
detach();
QString data = fragment;
if (mode == DecodedMode) {
parseDecodedComponent(data);
mode = TolerantMode;
}
d->setFragment(data, 0, data.length());
if (fragment.isNull())
d->sectionIsPresent &= ~QUrlPrivate::Fragment;
}
/*!
Returns the fragment of the URL. To determine if the parsed URL contained a
fragment, use hasFragment().
The \a options argument controls how to format the fragment component. All
values produce an unambiguous result. With QUrl::FullyDecoded, all
percent-encoded sequences are decoded; otherwise, the returned value may
contain some percent-encoded sequences for some control sequences not
representable in decoded form in QString.
Note that QUrl::FullyDecoded may cause data loss if those non-representable
sequences are present. It is recommended to use that value when the result
will be used in a non-URL context.
\sa setFragment(), hasFragment()
*/
QString QUrl::fragment(ComponentFormattingOptions options) const
{
if (!d) return QString();
QString result;
d->appendFragment(result, options);
if (d->hasFragment() && result.isNull())
result.detach();
return result;
}
/*!
\fn void QUrl::setEncodedFragment(const QByteArray &fragment)
\deprecated
\since 4.4
Sets the URL's fragment to the percent-encoded \a fragment. The fragment is the
last part of the URL, represented by a '#' followed by a string of
characters. It is typically used in HTTP for referring to a
certain link or point on a page:
\image qurl-fragment.png
The fragment is sometimes also referred to as the URL "reference".
Passing an argument of QByteArray() (a null QByteArray) will unset
the fragment. Passing an argument of QByteArray("") (an empty but
not null QByteArray) will set the fragment to an empty string (as
if the original URL had a lone "#").
\obsolete Use setFragment(), which has the same behavior of null / empty.
\sa setFragment(), encodedFragment()
*/
/*!
\fn QByteArray QUrl::encodedFragment() const
\deprecated
\since 4.4
Returns the fragment of the URL if it is defined; otherwise an
empty string is returned. The returned value will have its
non-ASCII and other control characters percent-encoded, as in
toEncoded().
\obsolete Use query(QUrl::FullyEncoded).toLatin1().
\sa setEncodedFragment(), toEncoded()
*/
/*!
\since 4.2
Returns true if this URL contains a fragment (i.e., if # was seen on it).
\sa fragment(), setFragment()
*/
bool QUrl::hasFragment() const
{
if (!d) return false;
return d->hasFragment();
}
/*!
\since 4.8
Returns the TLD (Top-Level Domain) of the URL, (e.g. .co.uk, .net).
Note that the return value is prefixed with a '.' unless the
URL does not contain a valid TLD, in which case the function returns
an empty string.
If \a options includes EncodeUnicode, the returned string will be in
ASCII Compatible Encoding.
*/
QString QUrl::topLevelDomain(ComponentFormattingOptions options) const
{
QString tld = qTopLevelDomain(host());
if (options & EncodeUnicode) {
return qt_ACE_do(tld, ToAceOnly);
}
return tld;
}
/*!
Returns the result of the merge of this URL with \a relative. This
URL is used as a base to convert \a relative to an absolute URL.
If \a relative is not a relative URL, this function will return \a
relative directly. Otherwise, the paths of the two URLs are
merged, and the new URL returned has the scheme and authority of
the base URL, but with the merged path, as in the following
example:
\snippet code/src_corelib_io_qurl.cpp 5
Calling resolved() with ".." returns a QUrl whose directory is
one level higher than the original. Similarly, calling resolved()
with "../.." removes two levels from the path. If \a relative is
"/", the path becomes "/".
\sa isRelative()
*/
QUrl QUrl::resolved(const QUrl &relative) const
{
if (!d) return relative;
if (!relative.d) return *this;
QUrl t;
// be non strict and allow scheme in relative url
if (!relative.d->scheme.isEmpty() && relative.d->scheme != d->scheme) {
t = relative;
t.detach();
} else {
if (relative.d->hasAuthority()) {
t = relative;
t.detach();
} else {
t.d = new QUrlPrivate;
// copy the authority
t.d->userName = d->userName;
t.d->password = d->password;
t.d->host = d->host;
t.d->port = d->port;
t.d->sectionIsPresent = d->sectionIsPresent & QUrlPrivate::Authority;
if (relative.d->path.isEmpty()) {
t.d->path = d->path;
if (relative.d->hasQuery()) {
t.d->query = relative.d->query;
t.d->sectionIsPresent |= QUrlPrivate::Query;
} else if (d->hasQuery()) {
t.d->query = d->query;
t.d->sectionIsPresent |= QUrlPrivate::Query;
}
} else {
t.d->path = relative.d->path.startsWith(QLatin1Char('/'))
? relative.d->path
: d->mergePaths(relative.d->path);
if (relative.d->hasQuery()) {
t.d->query = relative.d->query;
t.d->sectionIsPresent |= QUrlPrivate::Query;
}
}
}
t.d->scheme = d->scheme;
if (d->hasScheme())
t.d->sectionIsPresent |= QUrlPrivate::Scheme;
else
t.d->sectionIsPresent &= ~QUrlPrivate::Scheme;
}
t.d->fragment = relative.d->fragment;
if (relative.d->hasFragment())
t.d->sectionIsPresent |= QUrlPrivate::Fragment;
else
t.d->sectionIsPresent &= ~QUrlPrivate::Fragment;
removeDotsFromPath(&t.d->path);
#if defined(QURL_DEBUG)
qDebug("QUrl(\"%s\").resolved(\"%s\") = \"%s\"",
qPrintable(url()),
qPrintable(relative.url()),
qPrintable(t.url()));
#endif
return t;
}
/*!
Returns true if the URL is relative; otherwise returns false. A URL is
relative reference if its scheme is undefined; this function is therefore
equivalent to calling scheme().isEmpty().
Relative references are defined in RFC 3986 section 4.2.
*/
bool QUrl::isRelative() const
{
if (!d) return true;
return !d->hasScheme();
}
/*!
Returns a string representation of the URL. The output can be customized by
passing flags with \a options. The option QUrl::FullyDecoded is not
permitted in this function since it would generate ambiguous data.
The resulting QString can be passed back to a QUrl later on.
Synonym for toString(options).
\sa FormattingOptions, toEncoded(), toString()
*/
QString QUrl::url(FormattingOptions options) const
{
return toString(options);
}
/*!
Returns a string representation of the URL. The output can be customized by
passing flags with \a options. The option QUrl::FullyDecoded is not
permitted in this function since it would generate ambiguous data.
The default formatting option is \l{QUrl::FormattingOptions}{PrettyDecoded}.
\sa FormattingOptions, url(), setUrl()
*/
QString QUrl::toString(FormattingOptions options) const
{
if (!d) return QString();
if (options == QUrl::FullyDecoded) {
qWarning("QUrl: QUrl::FullyDecoded is not permitted when reconstructing the full URL");
options = QUrl::PrettyDecoded;
}
// return just the path if:
// - QUrl::PreferLocalFile is passed
// - QUrl::RemovePath isn't passed (rather stupid if the user did...)
// - there's no query or fragment to return
// that is, either they aren't present, or we're removing them
// - it's a local file
// (test done last since it's the most expensive)
if (options.testFlag(QUrl::PreferLocalFile) && !options.testFlag(QUrl::RemovePath)
&& (!d->hasQuery() || options.testFlag(QUrl::RemoveQuery))
&& (!d->hasFragment() || options.testFlag(QUrl::RemoveFragment))
&& isLocalFile()) {
return path(options);
}
QString url;
// for the full URL, we consider that the reserved characters are prettier if encoded
if (options & DecodeReserved)
options &= ~EncodeReserved;
else
options |= EncodeReserved;
if (!(options & QUrl::RemoveScheme) && d->hasScheme())
url += d->scheme + QLatin1Char(':');
bool pathIsAbsolute = d->path.startsWith(QLatin1Char('/'));
if (!((options & QUrl::RemoveAuthority) == QUrl::RemoveAuthority) && d->hasAuthority()) {
url += QLatin1String("//");
d->appendAuthority(url, options, QUrlPrivate::FullUrl);
} else if (isLocalFile() && pathIsAbsolute) {
url += QLatin1String("//");
}
if (!(options & QUrl::RemovePath)) {
// check if we need to insert a slash
if (!pathIsAbsolute && !d->path.isEmpty() && !url.isEmpty() && !url.endsWith(QLatin1Char(':')))
url += QLatin1Char('/');
d->appendPath(url, options, QUrlPrivate::FullUrl);
// check if we need to remove trailing slashes
if ((options & StripTrailingSlash) && !d->path.isEmpty() && d->path != QLatin1String("/") && url.endsWith(QLatin1Char('/')))
url.chop(1);
}
if (!(options & QUrl::RemoveQuery) && d->hasQuery()) {
url += QLatin1Char('?');
d->appendQuery(url, options, QUrlPrivate::FullUrl);
}
if (!(options & QUrl::RemoveFragment) && d->hasFragment()) {
url += QLatin1Char('#');
d->appendFragment(url, options);
}
return url;
}
/*!
\since 5.0
Returns a human-displayable string representation of the URL.
The output can be customized by passing flags with \a options.
The option RemovePassword is always enabled, since passwords
should never be shown back to users.
With the default options, the resulting QString can be passed back
to a QUrl later on, but any password that was present initially will
be lost.
\sa FormattingOptions, toEncoded(), toString()
*/
QString QUrl::toDisplayString(FormattingOptions options) const
{
return toString(options | RemovePassword);
}
/*!
Returns the encoded representation of the URL if it's valid;
otherwise an empty QByteArray is returned. The output can be
customized by passing flags with \a options.
The user info, path and fragment are all converted to UTF-8, and
all non-ASCII characters are then percent encoded. The host name
is encoded using Punycode.
*/
QByteArray QUrl::toEncoded(FormattingOptions options) const
{
options &= ~(FullyDecoded | FullyEncoded);
QString stringForm = toString(options | FullyEncoded);
return stringForm.toLatin1();
}
/*!
\fn QUrl QUrl::fromEncoded(const QByteArray &input, ParsingMode parsingMode)
Parses \a input and returns the corresponding QUrl. \a input is
assumed to be in encoded form, containing only ASCII characters.
Parses the URL using \a parsingMode. See setUrl() for more information on
this parameter. QUrl::DecodedMode is not permitted in this context.
\sa toEncoded(), setUrl()
*/
QUrl QUrl::fromEncoded(const QByteArray &input, ParsingMode mode)
{
return QUrl(QString::fromUtf8(input.constData(), input.size()), mode);
}
/*!
Returns a decoded copy of \a input. \a input is first decoded from
percent encoding, then converted from UTF-8 to unicode.
*/
QString QUrl::fromPercentEncoding(const QByteArray &input)
{
QByteArray ba = QByteArray::fromPercentEncoding(input);
return QString::fromUtf8(ba, ba.size());
}
/*!
Returns an encoded copy of \a input. \a input is first converted
to UTF-8, and all ASCII-characters that are not in the unreserved group
are percent encoded. To prevent characters from being percent encoded
pass them to \a exclude. To force characters to be percent encoded pass
them to \a include.
Unreserved is defined as:
ALPHA / DIGIT / "-" / "." / "_" / "~"
\snippet code/src_corelib_io_qurl.cpp 6
*/
QByteArray QUrl::toPercentEncoding(const QString &input, const QByteArray &exclude, const QByteArray &include)
{
return input.toUtf8().toPercentEncoding(exclude, include);
}
/*!
\internal
\since 5.0
Used in the setEncodedXXX compatibility functions. Converts \a ba to
QString form.
*/
QString QUrl::fromEncodedComponent_helper(const QByteArray &ba)
{
return qt_urlRecodeByteArray(ba);
}
/*!
\fn QByteArray QUrl::toPunycode(const QString &uc)
\obsolete
Returns a \a uc in Punycode encoding.
Punycode is a Unicode encoding used for internationalized domain
names, as defined in RFC3492. If you want to convert a domain name from
Unicode to its ASCII-compatible representation, use toAce().
*/
/*!
\fn QString QUrl::fromPunycode(const QByteArray &pc)
\obsolete
Returns the Punycode decoded representation of \a pc.
Punycode is a Unicode encoding used for internationalized domain
names, as defined in RFC3492. If you want to convert a domain from
its ASCII-compatible encoding to the Unicode representation, use
fromAce().
*/
/*!
\since 4.2
Returns the Unicode form of the given domain name
\a domain, which is encoded in the ASCII Compatible Encoding (ACE).
The result of this function is considered equivalent to \a domain.
If the value in \a domain cannot be encoded, it will be converted
to QString and returned.
The ASCII Compatible Encoding (ACE) is defined by RFC 3490, RFC 3491
and RFC 3492. It is part of the Internationalizing Domain Names in
Applications (IDNA) specification, which allows for domain names
(like \c "example.com") to be written using international
characters.
*/
QString QUrl::fromAce(const QByteArray &domain)
{
return qt_ACE_do(QString::fromLatin1(domain), NormalizeAce);
}
/*!
\since 4.2
Returns the ASCII Compatible Encoding of the given domain name \a domain.
The result of this function is considered equivalent to \a domain.
The ASCII-Compatible Encoding (ACE) is defined by RFC 3490, RFC 3491
and RFC 3492. It is part of the Internationalizing Domain Names in
Applications (IDNA) specification, which allows for domain names
(like \c "example.com") to be written using international
characters.
This function return an empty QByteArra if \a domain is not a valid
hostname. Note, in particular, that IPv6 literals are not valid domain
names.
*/
QByteArray QUrl::toAce(const QString &domain)
{
QString result = qt_ACE_do(domain, ToAceOnly);
return result.toLatin1();
}
/*!
\internal
Returns true if this URL is "less than" the given \a url. This
provides a means of ordering URLs.
*/
bool QUrl::operator <(const QUrl &url) const
{
if (!d || !url.d) {
bool thisIsEmpty = !d || d->isEmpty();
bool thatIsEmpty = !url.d || url.d->isEmpty();
// sort an empty URL first
return thisIsEmpty && !thatIsEmpty;
}
int cmp;
cmp = d->scheme.compare(url.d->scheme);
if (cmp != 0)
return cmp < 0;
cmp = d->userName.compare(url.d->userName);
if (cmp != 0)
return cmp < 0;
cmp = d->password.compare(url.d->password);
if (cmp != 0)
return cmp < 0;
cmp = d->host.compare(url.d->host);
if (cmp != 0)
return cmp < 0;
if (d->port != url.d->port)
return d->port < url.d->port;
cmp = d->path.compare(url.d->path);
if (cmp != 0)
return cmp < 0;
if (d->hasQuery() != url.d->hasQuery())
return url.d->hasQuery();
cmp = d->query.compare(url.d->query);
if (cmp != 0)
return cmp < 0;
if (d->hasFragment() != url.d->hasFragment())
return url.d->hasFragment();
cmp = d->fragment.compare(url.d->fragment);
return cmp < 0;
}
/*!
Returns true if this URL and the given \a url are equal;
otherwise returns false.
*/
bool QUrl::operator ==(const QUrl &url) const
{
if (!d && !url.d)
return true;
if (!d)
return url.d->isEmpty();
if (!url.d)
return d->isEmpty();
// Compare which sections are present, but ignore Host
// which is set by parsing but not by construction, when empty.
const int mask = QUrlPrivate::FullUrl & ~QUrlPrivate::Host;
return (d->sectionIsPresent & mask) == (url.d->sectionIsPresent & mask) &&
d->scheme == url.d->scheme &&
d->userName == url.d->userName &&
d->password == url.d->password &&
d->host == url.d->host &&
d->port == url.d->port &&
d->path == url.d->path &&
d->query == url.d->query &&
d->fragment == url.d->fragment;
}
/*!
Returns true if this URL and the given \a url are not equal;
otherwise returns false.
*/
bool QUrl::operator !=(const QUrl &url) const
{
return !(*this == url);
}
/*!
Assigns the specified \a url to this object.
*/
QUrl &QUrl::operator =(const QUrl &url)
{
if (!d) {
if (url.d) {
url.d->ref.ref();
d = url.d;
}
} else {
if (url.d)
qAtomicAssign(d, url.d);
else
clear();
}
return *this;
}
/*!
Assigns the specified \a url to this object.
*/
QUrl &QUrl::operator =(const QString &url)
{
if (url.isEmpty()) {
clear();
} else {
detach();
d->parse(url, TolerantMode);
}
return *this;
}
/*!
\fn void QUrl::swap(QUrl &other)
\since 4.8
Swaps URL \a other with this URL. This operation is very
fast and never fails.
*/
/*!
\internal
Forces a detach.
*/
void QUrl::detach()
{
if (!d)
d = new QUrlPrivate;
else
qAtomicDetach(d);
}
/*!
\internal
*/
bool QUrl::isDetached() const
{
return !d || d->ref.load() == 1;
}
/*!
Returns a QUrl representation of \a localFile, interpreted as a local
file. This function accepts paths separated by slashes as well as the
native separator for this platform.
This function also accepts paths with a doubled leading slash (or
backslash) to indicate a remote file, as in
"//servername/path/to/file.txt". Note that only certain platforms can
actually open this file using QFile::open().
\sa toLocalFile(), isLocalFile(), QDir::toNativeSeparators()
*/
QUrl QUrl::fromLocalFile(const QString &localFile)
{
QUrl url;
url.setScheme(fileScheme());
QString deslashified = QDir::fromNativeSeparators(localFile);
// magic for drives on windows
if (deslashified.length() > 1 && deslashified.at(1) == QLatin1Char(':') && deslashified.at(0) != QLatin1Char('/')) {
deslashified.prepend(QLatin1Char('/'));
} else if (deslashified.startsWith(QLatin1String("//"))) {
// magic for shared drive on windows
int indexOfPath = deslashified.indexOf(QLatin1Char('/'), 2);
url.setHost(deslashified.mid(2, indexOfPath - 2));
if (indexOfPath > 2)
deslashified = deslashified.right(deslashified.length() - indexOfPath);
else
deslashified.clear();
}
url.setPath(deslashified, DecodedMode);
return url;
}
/*!
Returns the path of this URL formatted as a local file path. The path
returned will use forward slashes, even if it was originally created
from one with backslashes.
If this URL contains a non-empty hostname, it will be encoded in the
returned value in the form found on SMB networks (for example,
"//servername/path/to/file.txt").
Note: if the path component of this URL contains a non-UTF-8 binary
sequence (such as %80), the behaviour of this function is undefined.
\sa fromLocalFile(), isLocalFile()
*/
QString QUrl::toLocalFile() const
{
// the call to isLocalFile() also ensures that we're parsed
if (!isLocalFile())
return QString();
QString tmp;
QString ourPath = path(QUrl::FullyDecoded);
// magic for shared drive on windows
if (!d->host.isEmpty()) {
tmp = QStringLiteral("//") + host() + (ourPath.length() > 0 && ourPath.at(0) != QLatin1Char('/')
? QLatin1Char('/') + ourPath : ourPath);
} else {
tmp = ourPath;
#ifdef Q_OS_WIN
// magic for drives on windows
if (ourPath.length() > 2 && ourPath.at(0) == QLatin1Char('/') && ourPath.at(2) == QLatin1Char(':'))
tmp.remove(0, 1);
#endif
}
return tmp;
}
/*!
\since 4.8
Returns true if this URL is pointing to a local file path. A URL is a
local file path if the scheme is "file".
Note that this function considers URLs with hostnames to be local file
paths, even if the eventual file path cannot be opened with
QFile::open().
\sa fromLocalFile(), toLocalFile()
*/
bool QUrl::isLocalFile() const
{
if (!d) return false;
if (d->scheme != fileScheme())
return false; // not file
return true;
}
/*!
Returns true if this URL is a parent of \a childUrl. \a childUrl is a child
of this URL if the two URLs share the same scheme and authority,
and this URL's path is a parent of the path of \a childUrl.
*/
bool QUrl::isParentOf(const QUrl &childUrl) const
{
QString childPath = childUrl.path();
if (!d)
return ((childUrl.scheme().isEmpty())
&& (childUrl.authority().isEmpty())
&& childPath.length() > 0 && childPath.at(0) == QLatin1Char('/'));
QString ourPath = path();
return ((childUrl.scheme().isEmpty() || d->scheme == childUrl.scheme())
&& (childUrl.authority().isEmpty() || authority() == childUrl.authority())
&& childPath.startsWith(ourPath)
&& ((ourPath.endsWith(QLatin1Char('/')) && childPath.length() > ourPath.length())
|| (!ourPath.endsWith(QLatin1Char('/'))
&& childPath.length() > ourPath.length() && childPath.at(ourPath.length()) == QLatin1Char('/'))));
}
#ifndef QT_NO_DATASTREAM
/*! \relates QUrl
Writes url \a url to the stream \a out and returns a reference
to the stream.
\sa{Serializing Qt Data Types}{Format of the QDataStream operators}
*/
QDataStream &operator<<(QDataStream &out, const QUrl &url)
{
QByteArray u;
if (url.isValid())
u = url.toEncoded();
out << u;
return out;
}
/*! \relates QUrl
Reads a url into \a url from the stream \a in and returns a
reference to the stream.
\sa{Serializing Qt Data Types}{Format of the QDataStream operators}
*/
QDataStream &operator>>(QDataStream &in, QUrl &url)
{
QByteArray u;
in >> u;
url.setUrl(QString::fromLatin1(u));
return in;
}
#endif // QT_NO_DATASTREAM
#ifndef QT_NO_DEBUG_STREAM
QDebug operator<<(QDebug d, const QUrl &url)
{
d.maybeSpace() << "QUrl(" << url.toDisplayString() << ')';
return d.space();
}
#endif
/*!
\since 4.2
Returns a text string that explains why an URL is invalid in the case being;
otherwise returns an empty string.
*/
QString QUrl::errorString() const
{
if (!d)
return QString();
if (d->sectionHasError == 0)
return QString();
// check if the error code matches a section with error
if ((d->sectionHasError & (d->errorCode >> 8)) == 0)
return QString();
QChar c = d->errorSupplement;
switch (QUrlPrivate::ErrorCode(d->errorCode)) {
case QUrlPrivate::NoError:
return QString();
case QUrlPrivate::InvalidSchemeError: {
QString msg = QStringLiteral("Invalid scheme (character '%1' not permitted)");
return msg.arg(c);
}
case QUrlPrivate::SchemeEmptyError:
return QStringLiteral("Empty scheme");
case QUrlPrivate::InvalidUserNameError:
return QString(QStringLiteral("Invalid user name (character '%1' not permitted)"))
.arg(c);
case QUrlPrivate::InvalidPasswordError:
return QString(QStringLiteral("Invalid password (character '%1' not permitted)"))
.arg(c);
case QUrlPrivate::InvalidRegNameError:
if (d->errorSupplement)
return QString(QStringLiteral("Invalid hostname (character '%1' not permitted)"))
.arg(c);
else
return QStringLiteral("Hostname contains invalid characters");
case QUrlPrivate::InvalidIPv4AddressError:
return QString(); // doesn't happen yet
case QUrlPrivate::InvalidIPv6AddressError:
return QStringLiteral("Invalid IPv6 address");
case QUrlPrivate::InvalidIPvFutureError:
return QStringLiteral("Invalid IPvFuture address");
case QUrlPrivate::HostMissingEndBracket:
return QStringLiteral("Expected ']' to match '[' in hostname");
case QUrlPrivate::InvalidPortError:
case QUrlPrivate::PortEmptyError:
return QStringLiteral("Invalid port or port number out of range");
case QUrlPrivate::InvalidPathError:
return QString(QStringLiteral("Invalid path (character '%1' not permitted)"))
.arg(c);
case QUrlPrivate::PathContainsColonBeforeSlash:
return QStringLiteral("Path component contains ':' before any '/'");
case QUrlPrivate::InvalidQueryError:
return QString(QStringLiteral("Invalid query (character '%1' not permitted)"))
.arg(c);
case QUrlPrivate::InvalidFragmentError:
return QString(QStringLiteral("Invalid fragment (character '%1' not permitted)"))
.arg(c);
}
return QStringLiteral("<unknown error>");
}
/*!
\typedef QUrl::DataPtr
\internal
*/
/*!
\fn DataPtr &QUrl::data_ptr()
\internal
*/
/*!
Returns the hash value for the \a url. If specified, \a seed is used to
initialize the hash.
\relates QHash
\since 5.0
*/
uint qHash(const QUrl &url, uint seed) Q_DECL_NOTHROW
{
if (!url.d)
return qHash(-1, seed); // the hash of an unset port (-1)
return qHash(url.d->scheme) ^
qHash(url.d->userName) ^
qHash(url.d->password) ^
qHash(url.d->host) ^
qHash(url.d->port, seed) ^
qHash(url.d->path) ^
qHash(url.d->query) ^
qHash(url.d->fragment);
}
static QUrl adjustFtpPath(QUrl url)
{
if (url.scheme() == ftpScheme()) {
QString path = url.path();
if (path.startsWith(QLatin1String("//")))
url.setPath(QLatin1String("/%2F") + path.midRef(2));
}
return url;
}
// The following code has the following copyright:
/*
Copyright (C) Research In Motion Limited 2009. All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of Research In Motion Limited nor the
names of its contributors may be used to endorse or promote products
derived from this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY Research In Motion Limited ''AS IS'' AND ANY
EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
DISCLAIMED. IN NO EVENT SHALL Research In Motion Limited BE LIABLE FOR ANY
DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
/*!
Returns a valid URL from a user supplied \a userInput string if one can be
deducted. In the case that is not possible, an invalid QUrl() is returned.
\since 4.6
Most applications that can browse the web, allow the user to input a URL
in the form of a plain string. This string can be manually typed into
a location bar, obtained from the clipboard, or passed in via command
line arguments.
When the string is not already a valid URL, a best guess is performed,
making various web related assumptions.
In the case the string corresponds to a valid file path on the system,
a file:// URL is constructed, using QUrl::fromLocalFile().
If that is not the case, an attempt is made to turn the string into a
http:// or ftp:// URL. The latter in the case the string starts with
'ftp'. The result is then passed through QUrl's tolerant parser, and
in the case or success, a valid QUrl is returned, or else a QUrl().
\section1 Examples:
\list
\li qt.nokia.com becomes http://qt.nokia.com
\li ftp.qt.nokia.com becomes ftp://ftp.qt.nokia.com
\li hostname becomes http://hostname
\li /home/user/test.html becomes file:///home/user/test.html
\endlist
*/
QUrl QUrl::fromUserInput(const QString &userInput)
{
QString trimmedString = userInput.trimmed();
// Check first for files, since on Windows drive letters can be interpretted as schemes
if (QDir::isAbsolutePath(trimmedString))
return QUrl::fromLocalFile(trimmedString);
QUrl url = QUrl(trimmedString, QUrl::TolerantMode);
QUrl urlPrepended = QUrl(QStringLiteral("http://") + trimmedString, QUrl::TolerantMode);
// Check the most common case of a valid url with scheme and host
// We check if the port would be valid by adding the scheme to handle the case host:port
// where the host would be interpretted as the scheme
if (url.isValid()
&& !url.scheme().isEmpty()
&& (!url.host().isEmpty() || !url.path().isEmpty())
&& urlPrepended.port() == -1)
return adjustFtpPath(url);
// Else, try the prepended one and adjust the scheme from the host name
if (urlPrepended.isValid() && (!urlPrepended.host().isEmpty() || !urlPrepended.path().isEmpty()))
{
int dotIndex = trimmedString.indexOf(QLatin1Char('.'));
const QString hostscheme = trimmedString.left(dotIndex).toLower();
if (hostscheme == ftpScheme())
urlPrepended.setScheme(ftpScheme());
return adjustFtpPath(urlPrepended);
}
return QUrl();
}
// end of BSD code
QT_END_NAMESPACE
Reference in New Issue View Git Blame Copy Permalink