bool wxURI::ParseIPvFuture(const wxChar*& uri)
{
// IPvFuture = "v" 1*HEXDIG "." 1*( unreserved / sub-delims / ":" )
if (*++uri != wxT('v') || !IsHex(*++uri))
return false;
while (IsHex(*++uri)) {}
if (*uri != wxT('.') || !(IsUnreserved(*++uri) || IsSubDelim(*uri) || *uri == wxT(':')))
return false;
while(IsUnreserved(*++uri) || IsSubDelim(*uri) || *uri == wxT(':')) {}
return true;
}
const char* wxURI::ParseUserInfo(const char* uri)
{
const char * const start = uri;
// userinfo = *( unreserved / pct-encoded / sub-delims / ":" )
while ( *uri && *uri != '@' && *uri != '/' && *uri != '#' && *uri != '?' )
{
if ( IsUnreserved(*uri) || IsSubDelim(*uri) || *uri == ':' )
m_userinfo += *uri++;
else
AppendNextEscaped(m_userinfo, uri);
}
if ( *uri++ == '@' )
{
// valid userinfo
m_fields |= wxURI_USERINFO;
}
else
{
uri = start; // rewind
m_userinfo.clear();
}
return uri;
}
const wxChar* wxURI::ParseFragment(const wxChar* uri)
{
wxASSERT(uri != NULL);
// fragment = *( pchar / "/" / "?" )
if (*uri == wxT('#'))
{
++uri;
while(*uri)
{
if (IsUnreserved(*uri) || IsSubDelim(*uri) ||
*uri == wxT(':') || *uri == wxT('@') || *uri == wxT('/') || *uri == wxT('?'))
m_fragment += *uri++;
else if (IsEscape(uri))
{
m_fragment += *uri++;
m_fragment += *uri++;
m_fragment += *uri++;
}
else
Escape(m_fragment, *uri++);
}
//mark the server as valid
m_fields |= wxURI_FRAGMENT;
}
return uri;
}
const wxChar* wxURI::ParseQuery(const wxChar* uri)
{
wxASSERT(uri != NULL);
// query = *( pchar / "/" / "?" )
if (*uri == wxT('?'))
{
++uri;
while(*uri && *uri != wxT('#'))
{
if (IsUnreserved(*uri) || IsSubDelim(*uri) ||
*uri == wxT(':') || *uri == wxT('@') || *uri == wxT('/') || *uri == wxT('?'))
m_query += *uri++;
else if (IsEscape(uri))
{
m_query += *uri++;
m_query += *uri++;
m_query += *uri++;
}
else
Escape(m_query, *uri++);
}
//mark the server as valid
m_fields |= wxURI_QUERY;
}
return uri;
}
const char* wxURI::ParseFragment(const char* uri)
{
// fragment = *( pchar / "/" / "?" )
if ( *uri == '#' )
{
++uri;
while ( *uri )
{
if ( IsUnreserved(*uri) || IsSubDelim(*uri) ||
*uri == ':' || *uri == '@' || *uri == '/' || *uri == '?')
m_fragment += *uri++;
else
AppendNextEscaped(m_fragment, uri);
}
m_fields |= wxURI_FRAGMENT;
}
return uri;
}
const char* wxURI::ParseQuery(const char* uri)
{
// query = *( pchar / "/" / "?" )
if ( *uri == '?' )
{
++uri;
while ( *uri && *uri != '#' )
{
if ( IsUnreserved(*uri) || IsSubDelim(*uri) ||
*uri == ':' || *uri == '@' || *uri == '/' || *uri == '?' )
m_query += *uri++;
else
AppendNextEscaped(m_query, uri);
}
m_fields |= wxURI_QUERY;
}
return uri;
}
const wxChar* wxURI::ParseUserInfo(const wxChar* uri)
{
wxASSERT(uri != NULL);
//copy of the uri - used for figuring out
//length of each component
const wxChar* uricopy = uri;
// userinfo = *( unreserved / pct-encoded / sub-delims / ":" )
while(*uri && *uri != wxT('@') && *uri != wxT('/') && *uri != wxT('#') && *uri != wxT('?'))
{
if(IsUnreserved(*uri) ||
IsSubDelim(*uri) || *uri == wxT(':'))
m_userinfo += *uri++;
else if (IsEscape(uri))
{
m_userinfo += *uri++;
m_userinfo += *uri++;
m_userinfo += *uri++;
}
else
Escape(m_userinfo, *uri++);
}
if(*uri == wxT('@'))
{
//valid userinfo
m_fields |= wxURI_USERINFO;
uricopy = ++uri;
}
else
m_userinfo = wxEmptyString;
return uricopy;
}
const char* wxURI::ParsePath(const char* uri)
{
/// hier-part = "//" authority path-abempty
/// / path-absolute
/// / path-rootless
/// / path-empty
///
/// relative-part = "//" authority path-abempty
/// / path-absolute
/// / path-noscheme
/// / path-empty
///
/// path-abempty = *( "/" segment )
/// path-absolute = "/" [ segment-nz *( "/" segment ) ]
/// path-noscheme = segment-nz-nc *( "/" segment )
/// path-rootless = segment-nz *( "/" segment )
/// path-empty = 0<pchar>
///
/// segment = *pchar
/// segment-nz = 1*pchar
/// segment-nz-nc = 1*( unreserved / pct-encoded / sub-delims / "@" )
/// ; non-zero-length segment without any colon ":"
///
/// pchar = unreserved / pct-encoded / sub-delims / ":" / "@"
if ( IsEndPath(*uri) )
return uri;
const bool isAbs = *uri == '/';
if ( isAbs )
m_path += *uri++;
wxArrayString segments;
wxString segment;
for ( ;; )
{
const bool endPath = IsEndPath(*uri);
if ( endPath || *uri == '/' )
{
// end of a segment, look at what we got
if ( segment == ".." )
{
if ( !segments.empty() && *segments.rbegin() != ".." )
segments.pop_back();
else if ( !isAbs )
segments.push_back("..");
}
else if ( segment == "." )
{
// normally we ignore "." but the last one should be taken into
// account as "path/." is the same as "path/" and not just "path"
if ( endPath )
segments.push_back("");
}
else // normal segment
{
segments.push_back(segment);
}
if ( endPath )
break;
segment.clear();
++uri;
continue;
}
if ( IsUnreserved(*uri) || IsSubDelim(*uri) || *uri == ':' || *uri == '@' )
segment += *uri++;
else
AppendNextEscaped(segment, uri);
}
m_path += wxJoin(segments, '/', '\0');
m_fields |= wxURI_PATH;
return uri;
}
const char* wxURI::ParseServer(const char* uri)
{
const char * const start = uri;
// host = IP-literal / IPv4address / reg-name
// IP-literal = "[" ( IPv6address / IPvFuture ) "]"
if (*uri == '[')
{
++uri;
if (ParseIPv6address(uri) && *uri == ']')
{
m_hostType = wxURI_IPV6ADDRESS;
m_server.assign(start + 1, uri - start - 1);
++uri;
}
else
{
uri = start + 1; // skip the leading '[' again
if (ParseIPvFuture(uri) && *uri == ']')
{
m_hostType = wxURI_IPVFUTURE;
m_server.assign(start + 1, uri - start - 1);
++uri;
}
else // unrecognized IP literal
{
uri = start;
}
}
}
else // IPv4 or a reg-name
{
if (ParseIPv4address(uri))
{
m_hostType = wxURI_IPV4ADDRESS;
m_server.assign(start, uri - start);
}
else
{
uri = start;
}
}
if ( m_hostType == wxURI_REGNAME )
{
uri = start;
// reg-name = *( unreserved / pct-encoded / sub-delims )
while ( *uri && *uri != '/' && *uri != ':' && *uri != '#' && *uri != '?' )
{
if ( IsUnreserved(*uri) || IsSubDelim(*uri) )
m_server += *uri++;
else
AppendNextEscaped(m_server, uri);
}
}
m_fields |= wxURI_SERVER;
return uri;
}
const wxChar* wxURI::ParsePath(const wxChar* uri, bool bReference, bool bNormalize)
{
wxASSERT(uri != NULL);
//copy of the uri - used for figuring out
//length of each component
const wxChar* uricopy = uri;
/// hier-part = "//" authority path-abempty
/// / path-absolute
/// / path-rootless
/// / path-empty
///
/// relative-part = "//" authority path-abempty
/// / path-absolute
/// / path-noscheme
/// / path-empty
///
/// path-abempty = *( "/" segment )
/// path-absolute = "/" [ segment-nz *( "/" segment ) ]
/// path-noscheme = segment-nz-nc *( "/" segment )
/// path-rootless = segment-nz *( "/" segment )
/// path-empty = 0<pchar>
///
/// segment = *pchar
/// segment-nz = 1*pchar
/// segment-nz-nc = 1*( unreserved / pct-encoded / sub-delims / "@" )
/// ; non-zero-length segment without any colon ":"
///
/// pchar = unreserved / pct-encoded / sub-delims / ":" / "@"
if (*uri == wxT('/'))
{
m_path += *uri++;
while(*uri && *uri != wxT('#') && *uri != wxT('?'))
{
if( IsUnreserved(*uri) || IsSubDelim(*uri) ||
*uri == wxT(':') || *uri == wxT('@') || *uri == wxT('/'))
m_path += *uri++;
else if (IsEscape(uri))
{
m_path += *uri++;
m_path += *uri++;
m_path += *uri++;
}
else
Escape(m_path, *uri++);
}
if (bNormalize)
{
wxStringBufferLength theBuffer(m_path, m_path.length() + 1);
#if wxUSE_STL
wxTmemcpy(theBuffer, m_path.c_str(), m_path.length()+1);
#endif
Normalize(theBuffer, true);
theBuffer.SetLength(wxStrlen(theBuffer));
}
//mark the path as valid
m_fields |= wxURI_PATH;
}
else if(*uri) //Relative path
{
if (bReference)
{
//no colon allowed
while(*uri && *uri != wxT('#') && *uri != wxT('?'))
{
if(IsUnreserved(*uri) || IsSubDelim(*uri) ||
*uri == wxT('@') || *uri == wxT('/'))
m_path += *uri++;
else if (IsEscape(uri))
{
m_path += *uri++;
m_path += *uri++;
m_path += *uri++;
}
else
Escape(m_path, *uri++);
}
}
else
{
while(*uri && *uri != wxT('#') && *uri != wxT('?'))
{
if(IsUnreserved(*uri) || IsSubDelim(*uri) ||
*uri == wxT(':') || *uri == wxT('@') || *uri == wxT('/'))
m_path += *uri++;
else if (IsEscape(uri))
{
m_path += *uri++;
m_path += *uri++;
m_path += *uri++;
}
else
Escape(m_path, *uri++);
}
}
if (uri != uricopy)
{
if (bNormalize)
{
wxStringBufferLength theBuffer(m_path, m_path.length() + 1);
#if wxUSE_STL
wxTmemcpy(theBuffer, m_path.c_str(), m_path.length()+1);
#endif
Normalize(theBuffer);
theBuffer.SetLength(wxStrlen(theBuffer));
}
//mark the path as valid
m_fields |= wxURI_PATH;
}
}
return uri;
}
const wxChar* wxURI::ParseServer(const wxChar* uri)
{
wxASSERT(uri != NULL);
//copy of the uri - used for figuring out
//length of each component
const wxChar* uricopy = uri;
// host = IP-literal / IPv4address / reg-name
// IP-literal = "[" ( IPv6address / IPvFuture ) "]"
if (*uri == wxT('['))
{
++uri; //some compilers don't support *&ing a ++*
if (ParseIPv6address(uri) && *uri == wxT(']'))
{
++uri;
m_hostType = wxURI_IPV6ADDRESS;
wxStringBufferLength theBuffer(m_server, uri - uricopy);
wxTmemcpy(theBuffer, uricopy, uri-uricopy);
theBuffer.SetLength(uri-uricopy);
}
else
{
uri = uricopy;
++uri; //some compilers don't support *&ing a ++*
if (ParseIPvFuture(uri) && *uri == wxT(']'))
{
++uri;
m_hostType = wxURI_IPVFUTURE;
wxStringBufferLength theBuffer(m_server, uri - uricopy);
wxTmemcpy(theBuffer, uricopy, uri-uricopy);
theBuffer.SetLength(uri-uricopy);
}
else
uri = uricopy;
}
}
else
{
if (ParseIPv4address(uri))
{
m_hostType = wxURI_IPV4ADDRESS;
wxStringBufferLength theBuffer(m_server, uri - uricopy);
wxTmemcpy(theBuffer, uricopy, uri-uricopy);
theBuffer.SetLength(uri-uricopy);
}
else
uri = uricopy;
}
if(m_hostType == wxURI_REGNAME)
{
uri = uricopy;
// reg-name = *( unreserved / pct-encoded / sub-delims )
while(*uri && *uri != wxT('/') && *uri != wxT(':') && *uri != wxT('#') && *uri != wxT('?'))
{
if(IsUnreserved(*uri) || IsSubDelim(*uri))
m_server += *uri++;
else if (IsEscape(uri))
{
m_server += *uri++;
m_server += *uri++;
m_server += *uri++;
}
else
Escape(m_server, *uri++);
}
}
//mark the server as valid
m_fields |= wxURI_SERVER;
return uri;
}
