Ticket #1429: bumpy2.diff

source/graphics/Material.h

@@ -38 +38 @@
 
     void SetDiffuseTexture(const CTexturePtr& texture);
     const CTexturePtr& GetDiffuseTexture() const { return m_DiffuseTexture; }
+    
+    void SetNormalTexture(const CTexturePtr& texture);
+    const CTexturePtr& GetNormalTexture() const { return m_NormalTexture; }
+    
+    void SetSpecularTexture(const CTexturePtr& texture);
+    const CTexturePtr& GetSpecularTexture() const { return m_SpecularTexture; }
 
     void SetShaderEffect(const CStr& effect);
     CStrIntern GetShaderEffect() const { return m_ShaderEffect; }
@@ -50 +56 @@
 
 private:
     CTexturePtr m_DiffuseTexture;
+    CTexturePtr m_NormalTexture;
+    CTexturePtr m_SpecularTexture;
     CStrIntern m_ShaderEffect;
     CShaderDefines m_ShaderDefines;
     CShaderUniforms m_StaticUniforms;

source/graphics/ObjectEntry.h

@@ -47 +47 @@
     CObjectBase* m_Base;
 
     VfsPath m_TextureName;
+    VfsPath m_NormalName;
+    VfsPath m_SpecularName;
     // model name
     VfsPath m_ModelName;
     // colour (used when doing alpha-channel colouring, but not doing player-colour)

source/graphics/mikktspace.h

@@ +1 @@
+/** \file mikktspace/mikktspace.h
+ *  \ingroup mikktspace
+ */
+/**
+ *  Copyright (C) 2011 by Morten S. Mikkelsen
+ *
+ *  This software is provided 'as-is', without any express or implied
+ *  warranty.  In no event will the authors be held liable for any damages
+ *  arising from the use of this software.
+ *
+ *  Permission is granted to anyone to use this software for any purpose,
+ *  including commercial applications, and to alter it and redistribute it
+ *  freely, subject to the following restrictions:
+ *
+ *  1. The origin of this software must not be misrepresented; you must not
+ *     claim that you wrote the original software. If you use this software
+ *     in a product, an acknowledgment in the product documentation would be
+ *     appreciated but is not required.
+ *  2. Altered source versions must be plainly marked as such, and must not be
+ *     misrepresented as being the original software.
+ *  3. This notice may not be removed or altered from any source distribution.
+ */
+
+#ifndef __MIKKTSPACE_H__
+#define __MIKKTSPACE_H__
+
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* Author: Morten S. Mikkelsen
+ * Version: 1.0
+ *
+ * The files mikktspace.h and mikktspace.c are designed to be
+ * stand-alone files and it is important that they are kept this way.
+ * Not having dependencies on structures/classes/libraries specific
+ * to the program, in which they are used, allows them to be copied
+ * and used as is into any tool, program or plugin.
+ * The code is designed to consistently generate the same
+ * tangent spaces, for a given mesh, in any tool in which it is used.
+ * This is done by performing an internal welding step and subsequently an order-independent evaluation
+ * of tangent space for meshes consisting of triangles and quads.
+ * This means faces can be received in any order and the same is true for
+ * the order of vertices of each face. The generated result will not be affected
+ * by such reordering. Additionally, whether degenerate (vertices or texture coordinates)
+ * primitives are present or not will not affect the generated results either.
+ * Once tangent space calculation is done the vertices of degenerate primitives will simply
+ * inherit tangent space from neighboring non degenerate primitives.
+ * The analysis behind this implementation can be found in my master's thesis
+ * which is available for download --> http://image.diku.dk/projects/media/morten.mikkelsen.08.pdf
+ * Note that though the tangent spaces at the vertices are generated in an order-independent way,
+ * by this implementation, the interpolated tangent space is still affected by which diagonal is
+ * chosen to split each quad. A sensible solution is to have your tools pipeline always
+ * split quads by the shortest diagonal. This choice is order-independent and works with mirroring.
+ * If these have the same length then compare the diagonals defined by the texture coordinates.
+ * XNormal which is a tool for baking normal maps allows you to write your own tangent space plugin
+ * and also quad triangulator plugin.
+ */
+
+
+typedef int tbool;
+typedef struct SMikkTSpaceContext SMikkTSpaceContext;
+
+typedef struct
+{
+    // Returns the number of faces (triangles/quads) on the mesh to be processed.
+    int (*m_getNumFaces)(const SMikkTSpaceContext * pContext);
+
+    // Returns the number of vertices on face number iFace
+    // iFace is a number in the range {0, 1, ..., getNumFaces()-1}
+    int (*m_getNumVerticesOfFace)(const SMikkTSpaceContext * pContext, const int iFace);
+
+    // returns the position/normal/texcoord of the referenced face of vertex number iVert.
+    // iVert is in the range {0,1,2} for triangles and {0,1,2,3} for quads.
+    void (*m_getPosition)(const SMikkTSpaceContext * pContext, float fvPosOut[], const int iFace, const int iVert);
+    void (*m_getNormal)(const SMikkTSpaceContext * pContext, float fvNormOut[], const int iFace, const int iVert);
+    void (*m_getTexCoord)(const SMikkTSpaceContext * pContext, float fvTexcOut[], const int iFace, const int iVert);
+
+    // either (or both) of the two setTSpace callbacks can be set.
+    // The call-back m_setTSpaceBasic() is sufficient for basic normal mapping.
+
+    // This function is used to return the tangent and fSign to the application.
+    // fvTangent is a unit length vector.
+    // For normal maps it is sufficient to use the following simplified version of the bitangent which is generated at pixel/vertex level.
+    // bitangent = fSign * cross(vN, tangent);
+    // Note that the results are returned unindexed. It is possible to generate a new index list
+    // But averaging/overwriting tangent spaces by using an already existing index list WILL produce INCRORRECT results.
+    // DO NOT! use an already existing index list.
+    void (*m_setTSpaceBasic)(const SMikkTSpaceContext * pContext, const float fvTangent[], const float fSign, const int iFace, const int iVert);
+
+    // This function is used to return tangent space results to the application.
+    // fvTangent and fvBiTangent are unit length vectors and fMagS and fMagT are their
+    // true magnitudes which can be used for relief mapping effects.
+    // fvBiTangent is the "real" bitangent and thus may not be perpendicular to fvTangent.
+    // However, both are perpendicular to the vertex normal.
+    // For normal maps it is sufficient to use the following simplified version of the bitangent which is generated at pixel/vertex level.
+    // fSign = bIsOrientationPreserving ? 1.0f : (-1.0f);
+    // bitangent = fSign * cross(vN, tangent);
+    // Note that the results are returned unindexed. It is possible to generate a new index list
+    // But averaging/overwriting tangent spaces by using an already existing index list WILL produce INCRORRECT results.
+    // DO NOT! use an already existing index list.
+    void (*m_setTSpace)(const SMikkTSpaceContext * pContext, const float fvTangent[], const float fvBiTangent[], const float fMagS, const float fMagT,
+                        const tbool bIsOrientationPreserving, const int iFace, const int iVert);
+} SMikkTSpaceInterface;
+
+struct SMikkTSpaceContext
+{
+    SMikkTSpaceInterface * m_pInterface;    // initialized with callback functions
+    void * m_pUserData;                     // pointer to client side mesh data etc. (passed as the first parameter with every interface call)
+};
+
+// these are both thread safe!
+tbool genTangSpaceDefault(const SMikkTSpaceContext * pContext); // Default (recommended) fAngularThreshold is 180 degrees (which means threshold disabled)
+tbool genTangSpace(const SMikkTSpaceContext * pContext, const float fAngularThreshold);
+
+
+// To avoid visual errors (distortions/unwanted hard edges in lighting), when using sampled normal maps, the
+// normal map sampler must use the exact inverse of the pixel shader transformation.
+// The most efficient transformation we can possibly do in the pixel shader is
+// achieved by using, directly, the "unnormalized" interpolated tangent, bitangent and vertex normal: vT, vB and vN.
+// pixel shader (fast transform out)
+// vNout = normalize( vNt.x * vT + vNt.y * vB + vNt.z * vN );
+// where vNt is the tangent space normal. The normal map sampler must likewise use the
+// interpolated and "unnormalized" tangent, bitangent and vertex normal to be compliant with the pixel shader.
+// sampler does (exact inverse of pixel shader):
+// float3 row0 = cross(vB, vN);
+// float3 row1 = cross(vN, vT);
+// float3 row2 = cross(vT, vB);
+// float fSign = dot(vT, row0)<0 ? -1 : 1;
+// vNt = normalize( fSign * float3(dot(vNout,row0), dot(vNout,row1), dot(vNout,row2)) );
+// where vNout is the sampled normal in some chosen 3D space.
+//
+// Should you choose to reconstruct the bitangent in the pixel shader instead
+// of the vertex shader, as explained earlier, then be sure to do this in the normal map sampler also.
+// Finally, beware of quad triangulations. If the normal map sampler doesn't use the same triangulation of
+// quads as your renderer then problems will occur since the interpolated tangent spaces will differ
+// eventhough the vertex level tangent spaces match. This can be solved either by triangulating before
+// sampling/exporting or by using the order-independent choice of diagonal for splitting quads suggested earlier.
+// However, this must be used both by the sampler and your tools/rendering pipeline.
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif

source/graphics/weldmesh.cpp

@@ +1 @@
+/**
+ *  Copyright (C) 2011 by Morten S. Mikkelsen
+ *
+ *  This software is provided 'as-is', without any express or implied
+ *  warranty.  In no event will the authors be held liable for any damages
+ *  arising from the use of this software.
+ *
+ *  Permission is granted to anyone to use this software for any purpose,
+ *  including commercial applications, and to alter it and redistribute it
+ *  freely, subject to the following restrictions:
+ *
+ *  1. The origin of this software must not be misrepresented; you must not
+ *     claim that you wrote the original software. If you use this software
+ *     in a product, an acknowledgment in the product documentation would be
+ *     appreciated but is not required.
+ *  2. Altered source versions must be plainly marked as such, and must not be
+ *     misrepresented as being the original software.
+ *  3. This notice may not be removed or altered from any source distribution.
+ */
+
+
+#include "weldmesh.h"
+#include <string.h>
+#include <assert.h>
+
+#ifdef __APPLE__
+#include <stdlib.h>  /* OSX gets its malloc stuff through here */
+#else
+#include <malloc.h> 
+#endif
+
+static void MergeVertsFast(int * piCurNrUniqueVertices, int * piRemapTable, float * pfVertexDataOut, int * piVertexIDs,
+              const float pfVertexDataIn[], const int iNrVerticesIn, const int iFloatsPerVert,
+              const int iL_in, const int iR_in, const int iChannelNum);
+
+int WeldMesh(int * piRemapTable, float * pfVertexDataOut,
+              const float pfVertexDataIn[], const int iNrVerticesIn, const int iFloatsPerVert)
+{
+    int iUniqueVertices = 0, i=0;
+    int * piVertexIDs = NULL;
+    if(iNrVerticesIn<=0) return 0;
+
+
+    iUniqueVertices = 0;
+    piVertexIDs = (int *) malloc(sizeof(int)*iNrVerticesIn);
+    if(piVertexIDs!=NULL)
+    {
+        for(i=0; i<iNrVerticesIn; i++)
+        {
+            piRemapTable[i] = -1;
+            piVertexIDs[i] = i;
+        }
+
+        MergeVertsFast(&iUniqueVertices, piRemapTable, pfVertexDataOut, piVertexIDs,
+                                         pfVertexDataIn, iNrVerticesIn, iFloatsPerVert, 0, iNrVerticesIn-1, 0);
+
+        free(piVertexIDs);
+
+        // debug check
+        for(i=0; i<iUniqueVertices; i++)
+            assert(piRemapTable[i]>=0);
+    }
+
+    return iUniqueVertices;
+}
+
+
+
+
+
+static void MergeVertsFast(int * piCurNrUniqueVertices, int * piRemapTable, float * pfVertexDataOut, int * piVertexIDs,
+              const float pfVertexDataIn[], const int iNrVerticesIn, const int iFloatsPerVert,
+              const int iL_in, const int iR_in, const int iChannelNum)
+{
+    const int iCount = iR_in-iL_in+1;
+    int l=0;
+    float fMin, fMax, fAvg;
+    assert(iCount>0);
+    // make bbox
+    fMin = pfVertexDataIn[ piVertexIDs[iL_in]*iFloatsPerVert + iChannelNum]; fMax = fMin;
+    for(l=(iL_in+1); l<=iR_in; l++)
+    {
+        const int index = piVertexIDs[l]*iFloatsPerVert + iChannelNum;
+        const float fVal = pfVertexDataIn[index];
+        if(fMin>fVal) fMin=fVal;
+        else if(fMax<fVal) fMax=fVal;
+    }
+
+    // terminate recursion when the separation/average value
+    // is no longer strictly between fMin and fMax values.
+    fAvg = 0.5f*(fMax + fMin);
+    if(fAvg<=fMin || fAvg>=fMax || iCount==1)
+    {
+        if((iChannelNum+1) == iFloatsPerVert || iCount==1)  // we are done, weld by hand
+        {
+            int iUniqueNewVertices = 0;
+            float * pfNewUniVertsOut = &pfVertexDataOut[ piCurNrUniqueVertices[0]*iFloatsPerVert ];
+
+            for(l=iL_in; l<=iR_in; l++)
+            {
+                const int index = piVertexIDs[l]*iFloatsPerVert;
+
+                int iFound = 0; // didn't find copy yet.
+                int l2=0;
+                while(l2<iUniqueNewVertices && iFound==0)
+                {
+                    const int index2 = l2*iFloatsPerVert;
+
+                    int iAllSame = 1;
+                    int c=0;
+                    while(iAllSame!=0 && c<iFloatsPerVert)
+                    {
+                        iAllSame &= (pfVertexDataIn[index+c] == pfNewUniVertsOut[index2+c] ? 1 : 0);
+                        ++c;
+                    }
+
+                    iFound = iAllSame;
+                    if(iFound==0) ++l2;
+                }
+                
+                // generate new entry
+                if(iFound==0)
+                {
+                    memcpy(pfNewUniVertsOut+iUniqueNewVertices*iFloatsPerVert, pfVertexDataIn+index, sizeof(float)*iFloatsPerVert);
+                    ++iUniqueNewVertices;
+                }
+
+                assert(piRemapTable[piVertexIDs[l]] == -1); // has not yet been assigned
+                piRemapTable[piVertexIDs[l]] = piCurNrUniqueVertices[0] + l2;
+            }
+
+            piCurNrUniqueVertices[0] += iUniqueNewVertices;
+        }
+        else
+        {
+            MergeVertsFast(piCurNrUniqueVertices, piRemapTable, pfVertexDataOut, piVertexIDs,
+                           pfVertexDataIn, iNrVerticesIn, iFloatsPerVert,
+                            iL_in, iR_in, iChannelNum+1);
+        }
+    }
+    else
+    {
+        int iL=iL_in, iR=iR_in, index;
+
+        // seperate (by fSep) all points between iL_in and iR_in in pTmpVert[]
+        while(iL < iR)
+        {
+            int iReadyLeftSwap = 0;
+            int iReadyRightSwap = 0;
+            while(iReadyLeftSwap==0 && iL<iR)
+            {
+                assert(iL>=iL_in && iL<=iR_in);
+                index = piVertexIDs[iL]*iFloatsPerVert+iChannelNum;
+                iReadyLeftSwap = !(pfVertexDataIn[index]<fAvg) ? 1 : 0;
+                if(iReadyLeftSwap==0) ++iL;
+            }
+            while(iReadyRightSwap==0 && iL<iR)
+            {
+                assert(iR>=iL_in && iR<=iR_in);
+                index = piVertexIDs[iR]*iFloatsPerVert+iChannelNum;
+                iReadyRightSwap = pfVertexDataIn[index]<fAvg ? 1 : 0;
+                if(iReadyRightSwap==0) --iR;
+            }
+            assert( (iL<iR) || (iReadyLeftSwap==0 || iReadyRightSwap==0));
+
+            if(iReadyLeftSwap!=0 && iReadyRightSwap!=0)
+            {
+                int iID=0;
+                assert(iL<iR);
+                iID = piVertexIDs[iL];
+                piVertexIDs[iL] = piVertexIDs[iR];
+                piVertexIDs[iR] = iID;
+                ++iL; --iR;
+            }
+        }
+
+        assert(iL==(iR+1) || (iL==iR));
+        if(iL==iR)
+        {
+            const int index = piVertexIDs[iR]*iFloatsPerVert+iChannelNum;
+            const int iReadyRightSwap = pfVertexDataIn[index]<fAvg ? 1 : 0;
+            if(iReadyRightSwap!=0) ++iL;
+            else --iR;
+        }
+
+        // recurse
+        if(iL_in <= iR)
+            MergeVertsFast(piCurNrUniqueVertices, piRemapTable, pfVertexDataOut, piVertexIDs,
+                           pfVertexDataIn, iNrVerticesIn, iFloatsPerVert, iL_in, iR, iChannelNum);  // weld all left of fSep
+        if(iL <= iR_in)
+            MergeVertsFast(piCurNrUniqueVertices, piRemapTable, pfVertexDataOut, piVertexIDs,
+                           pfVertexDataIn, iNrVerticesIn, iFloatsPerVert, iL, iR_in, iChannelNum);  // weld all right of (or equal to) fSep
+    }
+}
+ No newline at end of file

source/graphics/mikktspace.cpp

@@ +1 @@
+/** \file mikktspace/mikktspace.c
+ *  \ingroup mikktspace
+ */
+/**
+ *  Copyright (C) 2011 by Morten S. Mikkelsen
+ *
+ *  This software is provided 'as-is', without any express or implied
+ *  warranty.  In no event will the authors be held liable for any damages
+ *  arising from the use of this software.
+ *
+ *  Permission is granted to anyone to use this software for any purpose,
+ *  including commercial applications, and to alter it and redistribute it
+ *  freely, subject to the following restrictions:
+ *
+ *  1. The origin of this software must not be misrepresented; you must not
+ *     claim that you wrote the original software. If you use this software
+ *     in a product, an acknowledgment in the product documentation would be
+ *     appreciated but is not required.
+ *  2. Altered source versions must be plainly marked as such, and must not be
+ *     misrepresented as being the original software.
+ *  3. This notice may not be removed or altered from any source distribution.
+ */
+
+#include <assert.h>
+#include <stdio.h>
+#include <math.h>
+#include <string.h>
+#include <float.h>
+#include <stdlib.h>
+
+#include "mikktspace.h"
+
+#define TFALSE      0
+#define TTRUE       1
+
+#ifndef M_PI
+#define M_PI    3.1415926535897932384626433832795
+#endif
+
+#define INTERNAL_RND_SORT_SEED      39871946
+
+// internal structure
+typedef struct
+{
+    float x, y, z;
+} SVec3;
+
+static tbool            veq( const SVec3 v1, const SVec3 v2 )
+{
+    return (v1.x == v2.x) && (v1.y == v2.y) && (v1.z == v2.z);
+}
+
+static SVec3        vadd( const SVec3 v1, const SVec3 v2 )
+{
+    SVec3 vRes;
+
+    vRes.x = v1.x + v2.x;
+    vRes.y = v1.y + v2.y;
+    vRes.z = v1.z + v2.z;
+
+    return vRes;
+}
+
+
+static SVec3        vsub( const SVec3 v1, const SVec3 v2 )
+{
+    SVec3 vRes;
+
+    vRes.x = v1.x - v2.x;
+    vRes.y = v1.y - v2.y;
+    vRes.z = v1.z - v2.z;
+
+    return vRes;
+}
+
+static SVec3        vscale(const float fS, const SVec3 v)
+{
+    SVec3 vRes;
+
+    vRes.x = fS * v.x;
+    vRes.y = fS * v.y;
+    vRes.z = fS * v.z;
+
+    return vRes;
+}
+
+static float            LengthSquared( const SVec3 v )
+{
+    return v.x*v.x + v.y*v.y + v.z*v.z;
+}
+
+static float            Length( const SVec3 v )
+{
+    return sqrtf(LengthSquared(v));
+}
+
+static SVec3        Normalize( const SVec3 v )
+{
+    return vscale(1 / Length(v), v);
+}
+
+static float        vdot( const SVec3 v1, const SVec3 v2)
+{
+    return v1.x*v2.x + v1.y*v2.y + v1.z*v2.z;
+}
+
+
+static tbool NotZero(const float fX)
+{
+    // could possibly use FLT_EPSILON instead
+    return fabsf(fX) > FLT_MIN;
+}
+
+static tbool VNotZero(const SVec3 v)
+{
+    // might change this to an epsilon based test
+    return NotZero(v.x) || NotZero(v.y) || NotZero(v.z);
+}
+
+
+
+typedef struct
+{
+    int iNrFaces;
+    int * pTriMembers;
+} SSubGroup;
+
+typedef struct
+{
+    int iNrFaces;
+    int * pFaceIndices;
+    int iVertexRepresentitive;
+    tbool bOrientPreservering;
+} SGroup;
+
+// 
+#define MARK_DEGENERATE             1
+#define QUAD_ONE_DEGEN_TRI          2
+#define GROUP_WITH_ANY              4
+#define ORIENT_PRESERVING           8
+
+
+
+typedef struct
+{
+    int FaceNeighbors[3];
+    SGroup * AssignedGroup[3];
+    
+    // normalized first order face derivatives
+    SVec3 vOs, vOt;
+    float fMagS, fMagT; // original magnitudes
+
+    // determines if the current and the next triangle are a quad.
+    int iOrgFaceNumber;
+    int iFlag, iTSpacesOffs;
+    unsigned char vert_num[4];
+} STriInfo;
+
+typedef struct
+{
+    SVec3 vOs;
+    float fMagS;
+    SVec3 vOt;
+    float fMagT;
+    int iCounter;   // this is to average back into quads.
+    tbool bOrient;
+} STSpace;
+
+static int GenerateInitialVerticesIndexList(STriInfo pTriInfos[], int piTriList_out[], const SMikkTSpaceContext * pContext, const int iNrTrianglesIn);
+static void GenerateSharedVerticesIndexList(int piTriList_in_and_out[], const SMikkTSpaceContext * pContext, const int iNrTrianglesIn);
+static void InitTriInfo(STriInfo pTriInfos[], const int piTriListIn[], const SMikkTSpaceContext * pContext, const int iNrTrianglesIn);
+static int Build4RuleGroups(STriInfo pTriInfos[], SGroup pGroups[], int piGroupTrianglesBuffer[], const int piTriListIn[], const int iNrTrianglesIn);
+static tbool GenerateTSpaces(STSpace psTspace[], const STriInfo pTriInfos[], const SGroup pGroups[],
+                             const int iNrActiveGroups, const int piTriListIn[], const float fThresCos,
+                             const SMikkTSpaceContext * pContext);
+
+static int MakeIndex(const int iFace, const int iVert)
+{
+    assert(iVert>=0 && iVert<4 && iFace>=0);
+    return (iFace<<2) | (iVert&0x3);
+}
+
+static void IndexToData(int * piFace, int * piVert, const int iIndexIn)
+{
+    piVert[0] = iIndexIn&0x3;
+    piFace[0] = iIndexIn>>2;
+}
+
+static STSpace AvgTSpace(const STSpace * pTS0, const STSpace * pTS1)
+{
+    STSpace ts_res;
+
+    // this if is important. Due to floating point precision
+    // averaging when ts0==ts1 will cause a slight difference
+    // which results in tangent space splits later on
+    if (pTS0->fMagS==pTS1->fMagS && pTS0->fMagT==pTS1->fMagT &&
+       veq(pTS0->vOs,pTS1->vOs) && veq(pTS0->vOt, pTS1->vOt))
+    {
+        ts_res.fMagS = pTS0->fMagS;
+        ts_res.fMagT = pTS0->fMagT;
+        ts_res.vOs = pTS0->vOs;
+        ts_res.vOt = pTS0->vOt;
+    }
+    else
+    {
+        ts_res.fMagS = 0.5f*(pTS0->fMagS+pTS1->fMagS);
+        ts_res.fMagT = 0.5f*(pTS0->fMagT+pTS1->fMagT);
+        ts_res.vOs = vadd(pTS0->vOs,pTS1->vOs);
+        ts_res.vOt = vadd(pTS0->vOt,pTS1->vOt);
+        if ( VNotZero(ts_res.vOs) ) ts_res.vOs = Normalize(ts_res.vOs);
+        if ( VNotZero(ts_res.vOt) ) ts_res.vOt = Normalize(ts_res.vOt);
+    }
+
+    return ts_res;
+}
+
+
+
+static SVec3 GetPosition(const SMikkTSpaceContext * pContext, const int index);
+static SVec3 GetNormal(const SMikkTSpaceContext * pContext, const int index);
+static SVec3 GetTexCoord(const SMikkTSpaceContext * pContext, const int index);
+
+
+// degen triangles
+static void DegenPrologue(STriInfo pTriInfos[], int piTriList_out[], const int iNrTrianglesIn, const int iTotTris);
+static void DegenEpilogue(STSpace psTspace[], STriInfo pTriInfos[], int piTriListIn[], const SMikkTSpaceContext * pContext, const int iNrTrianglesIn, const int iTotTris);
+
+
+tbool genTangSpaceDefault(const SMikkTSpaceContext * pContext)
+{
+    return genTangSpace(pContext, 180.0f);
+}
+
+tbool genTangSpace(const SMikkTSpaceContext * pContext, const float fAngularThreshold)
+{
+    // count nr_triangles
+    int * piTriListIn = NULL, * piGroupTrianglesBuffer = NULL;
+    STriInfo * pTriInfos = NULL;
+    SGroup * pGroups = NULL;
+    STSpace * psTspace = NULL;
+    int iNrTrianglesIn = 0, f=0, t=0, i=0;
+    int iNrTSPaces = 0, iTotTris = 0, iDegenTriangles = 0, iNrMaxGroups = 0;
+    int iNrActiveGroups = 0, index = 0;
+    const int iNrFaces = pContext->m_pInterface->m_getNumFaces(pContext);
+    tbool bRes = TFALSE;
+    const float fThresCos = (float) cos((fAngularThreshold*(float)M_PI)/180.0f);
+
+    // verify all call-backs have been set
+    if ( pContext->m_pInterface->m_getNumFaces==NULL ||
+        pContext->m_pInterface->m_getNumVerticesOfFace==NULL ||
+        pContext->m_pInterface->m_getPosition==NULL ||
+        pContext->m_pInterface->m_getNormal==NULL ||
+        pContext->m_pInterface->m_getTexCoord==NULL )
+        return TFALSE;
+
+    // count triangles on supported faces
+    for (f=0; f<iNrFaces; f++)
+    {
+        const int verts = pContext->m_pInterface->m_getNumVerticesOfFace(pContext, f);
+        if (verts==3) ++iNrTrianglesIn;
+        else if(verts==4) iNrTrianglesIn += 2;
+    }
+    if (iNrTrianglesIn<=0) return TFALSE;
+
+    // allocate memory for an index list
+    piTriListIn = (int *) malloc(sizeof(int)*3*iNrTrianglesIn);
+    pTriInfos = (STriInfo *) malloc(sizeof(STriInfo)*iNrTrianglesIn);
+    if (piTriListIn==NULL || pTriInfos==NULL)
+    {
+        if (piTriListIn!=NULL) free(piTriListIn);
+        if (pTriInfos!=NULL) free(pTriInfos);
+        return TFALSE;
+    }
+
+    // make an initial triangle --> face index list
+    iNrTSPaces = GenerateInitialVerticesIndexList(pTriInfos, piTriListIn, pContext, iNrTrianglesIn);
+
+    // make a welded index list of identical positions and attributes (pos, norm, texc)
+    //printf("gen welded index list begin\n");
+    GenerateSharedVerticesIndexList(piTriListIn, pContext, iNrTrianglesIn);
+    //printf("gen welded index list end\n");
+
+    // Mark all degenerate triangles
+    iTotTris = iNrTrianglesIn;
+    iDegenTriangles = 0;
+    for (t=0; t<iTotTris; t++)
+    {
+        const int i0 = piTriListIn[t*3+0];
+        const int i1 = piTriListIn[t*3+1];
+        const int i2 = piTriListIn[t*3+2];
+        const SVec3 p0 = GetPosition(pContext, i0);
+        const SVec3 p1 = GetPosition(pContext, i1);
+        const SVec3 p2 = GetPosition(pContext, i2);
+        if (veq(p0,p1) || veq(p0,p2) || veq(p1,p2)) // degenerate
+        {
+            pTriInfos[t].iFlag |= MARK_DEGENERATE;
+            ++iDegenTriangles;
+        }
+    }
+    iNrTrianglesIn = iTotTris - iDegenTriangles;
+
+    // mark all triangle pairs that belong to a quad with only one
+    // good triangle. These need special treatment in DegenEpilogue().
+    // Additionally, move all good triangles to the start of
+    // pTriInfos[] and piTriListIn[] without changing order and
+    // put the degenerate triangles last.
+    DegenPrologue(pTriInfos, piTriListIn, iNrTrianglesIn, iTotTris);
+
+    
+    // evaluate triangle level attributes and neighbor list
+    //printf("gen neighbors list begin\n");
+    InitTriInfo(pTriInfos, piTriListIn, pContext, iNrTrianglesIn);
+    //printf("gen neighbors list end\n");
+
+    
+    // based on the 4 rules, identify groups based on connectivity
+    iNrMaxGroups = iNrTrianglesIn*3;
+    pGroups = (SGroup *) malloc(sizeof(SGroup)*iNrMaxGroups);
+    piGroupTrianglesBuffer = (int *) malloc(sizeof(int)*iNrTrianglesIn*3);
+    if (pGroups==NULL || piGroupTrianglesBuffer==NULL)
+    {
+        if (pGroups!=NULL) free(pGroups);
+        if (piGroupTrianglesBuffer!=NULL) free(piGroupTrianglesBuffer);
+        free(piTriListIn);
+        free(pTriInfos);
+        return TFALSE;
+    }
+    //printf("gen 4rule groups begin\n");
+    iNrActiveGroups =
+        Build4RuleGroups(pTriInfos, pGroups, piGroupTrianglesBuffer, piTriListIn, iNrTrianglesIn);
+    //printf("gen 4rule groups end\n");
+
+    //
+
+    psTspace = (STSpace *) malloc(sizeof(STSpace)*iNrTSPaces);
+    if (psTspace==NULL)
+    {
+        free(piTriListIn);
+        free(pTriInfos);
+        free(pGroups);
+        free(piGroupTrianglesBuffer);
+        return TFALSE;
+    }
+    memset(psTspace, 0, sizeof(STSpace)*iNrTSPaces);
+    for (t=0; t<iNrTSPaces; t++)
+    {
+        psTspace[t].vOs.x=1.0f; psTspace[t].vOs.y=0.0f; psTspace[t].vOs.z=0.0f; psTspace[t].fMagS = 1.0f;
+        psTspace[t].vOt.x=0.0f; psTspace[t].vOt.y=1.0f; psTspace[t].vOt.z=0.0f; psTspace[t].fMagT = 1.0f;
+    }
+
+    // make tspaces, each group is split up into subgroups if necessary
+    // based on fAngularThreshold. Finally a tangent space is made for
+    // every resulting subgroup
+    //printf("gen tspaces begin\n");
+    bRes = GenerateTSpaces(psTspace, pTriInfos, pGroups, iNrActiveGroups, piTriListIn, fThresCos, pContext);
+    //printf("gen tspaces end\n");
+    
+    // clean up
+    free(pGroups);
+    free(piGroupTrianglesBuffer);
+
+    if (!bRes)  // if an allocation in GenerateTSpaces() failed
+    {
+        // clean up and return false
+        free(pTriInfos); free(piTriListIn); free(psTspace);
+        return TFALSE;
+    }
+
+
+    // degenerate quads with one good triangle will be fixed by copying a space from
+    // the good triangle to the coinciding vertex.
+    // all other degenerate triangles will just copy a space from any good triangle
+    // with the same welded index in piTriListIn[].
+    DegenEpilogue(psTspace, pTriInfos, piTriListIn, pContext, iNrTrianglesIn, iTotTris);
+
+    free(pTriInfos); free(piTriListIn);
+
+    index = 0;
+    for (f=0; f<iNrFaces; f++)
+    {
+        const int verts = pContext->m_pInterface->m_getNumVerticesOfFace(pContext, f);
+        if (verts!=3 && verts!=4) continue;
+        
+
+        // I've decided to let degenerate triangles and group-with-anythings
+        // vary between left/right hand coordinate systems at the vertices.
+        // All healthy triangles on the other hand are built to always be either or.
+
+        /*// force the coordinate system orientation to be uniform for every face.
+        // (this is already the case for good triangles but not for
+        // degenerate ones and those with bGroupWithAnything==true)
+        bool bOrient = psTspace[index].bOrient;
+        if (psTspace[index].iCounter == 0)  // tspace was not derived from a group
+        {
+            // look for a space created in GenerateTSpaces() by iCounter>0
+            bool bNotFound = true;
+            int i=1;
+            while (i<verts && bNotFound)
+            {
+                if (psTspace[index+i].iCounter > 0) bNotFound=false;
+                else ++i;
+            }
+            if (!bNotFound) bOrient = psTspace[index+i].bOrient;
+        }*/
+
+        // set data
+        for (i=0; i<verts; i++)
+        {
+            const STSpace * pTSpace = &psTspace[index];
+            float tang[] = {pTSpace->vOs.x, pTSpace->vOs.y, pTSpace->vOs.z};
+            float bitang[] = {pTSpace->vOt.x, pTSpace->vOt.y, pTSpace->vOt.z};
+            if (pContext->m_pInterface->m_setTSpace!=NULL)
+                pContext->m_pInterface->m_setTSpace(pContext, tang, bitang, pTSpace->fMagS, pTSpace->fMagT, pTSpace->bOrient, f, i);
+            if (pContext->m_pInterface->m_setTSpaceBasic!=NULL)
+                pContext->m_pInterface->m_setTSpaceBasic(pContext, tang, pTSpace->bOrient==TTRUE ? 1.0f : (-1.0f), f, i);
+
+            ++index;
+        }
+    }
+
+    free(psTspace);
+
+    
+    return TTRUE;
+}
+
+///////////////////////////////////////////////////////////////////////////////////////////////////////////////////
+
+typedef struct
+{
+    float vert[3];
+    int index;
+} STmpVert;
+
+const int g_iCells = 2048;
+
+#ifdef _MSC_VER
+    #define NOINLINE __declspec(noinline)
+#else
+    #define NOINLINE __attribute__ ((noinline))
+#endif
+
+// it is IMPORTANT that this function is called to evaluate the hash since
+// inlining could potentially reorder instructions and generate different
+// results for the same effective input value fVal.
+NOINLINE int FindGridCell(const float fMin, const float fMax, const float fVal)
+{
+    const float fIndex = g_iCells * ((fVal-fMin)/(fMax-fMin));
+    const int iIndex = fIndex<0?0:((int)fIndex);
+    return iIndex<g_iCells?iIndex:(g_iCells-1);
+}
+
+static void MergeVertsFast(int piTriList_in_and_out[], STmpVert pTmpVert[], const SMikkTSpaceContext * pContext, const int iL_in, const int iR_in);
+static void MergeVertsSlow(int piTriList_in_and_out[], const SMikkTSpaceContext * pContext, const int pTable[], const int iEntries);
+static void GenerateSharedVerticesIndexListSlow(int piTriList_in_and_out[], const SMikkTSpaceContext * pContext, const int iNrTrianglesIn);
+
+static void GenerateSharedVerticesIndexList(int piTriList_in_and_out[], const SMikkTSpaceContext * pContext, const int iNrTrianglesIn)
+{
+
+    // Generate bounding box
+    int * piHashTable=NULL, * piHashCount=NULL, * piHashOffsets=NULL, * piHashCount2=NULL;
+    STmpVert * pTmpVert = NULL;
+    int i=0, iChannel=0, k=0, e=0;
+    int iMaxCount=0;
+    SVec3 vMin = GetPosition(pContext, 0), vMax = vMin, vDim;
+    float fMin, fMax;
+    for (i=1; i<(iNrTrianglesIn*3); i++)
+    {
+        const int index = piTriList_in_and_out[i];
+
+        const SVec3 vP = GetPosition(pContext, index);
+        if (vMin.x > vP.x) vMin.x = vP.x;
+        else if(vMax.x < vP.x) vMax.x = vP.x;
+        if (vMin.y > vP.y) vMin.y = vP.y;
+        else if(vMax.y < vP.y) vMax.y = vP.y;
+        if (vMin.z > vP.z) vMin.z = vP.z;
+        else if(vMax.z < vP.z) vMax.z = vP.z;
+    }
+
+    vDim = vsub(vMax,vMin);
+    iChannel = 0;
+    fMin = vMin.x; fMax=vMax.x;
+    if (vDim.y>vDim.x && vDim.y>vDim.z)
+    {
+        iChannel=1;
+        fMin = vMin.y, fMax=vMax.y;
+    }
+    else if(vDim.z>vDim.x)
+    {
+        iChannel=2;
+        fMin = vMin.z, fMax=vMax.z;
+    }
+
+    // make allocations
+    piHashTable = (int *) malloc(sizeof(int)*iNrTrianglesIn*3);
+    piHashCount = (int *) malloc(sizeof(int)*g_iCells);
+    piHashOffsets = (int *) malloc(sizeof(int)*g_iCells);
+    piHashCount2 = (int *) malloc(sizeof(int)*g_iCells);
+
+    if (piHashTable==NULL || piHashCount==NULL || piHashOffsets==NULL || piHashCount2==NULL)
+    {
+        if (piHashTable!=NULL) free(piHashTable);
+        if (piHashCount!=NULL) free(piHashCount);
+        if (piHashOffsets!=NULL) free(piHashOffsets);
+        if (piHashCount2!=NULL) free(piHashCount2);
+        GenerateSharedVerticesIndexListSlow(piTriList_in_and_out, pContext, iNrTrianglesIn);
+        return;
+    }
+    memset(piHashCount, 0, sizeof(int)*g_iCells);
+    memset(piHashCount2, 0, sizeof(int)*g_iCells);
+
+    // count amount of elements in each cell unit
+    for (i=0; i<(iNrTrianglesIn*3); i++)
+    {
+        const int index = piTriList_in_and_out[i];
+        const SVec3 vP = GetPosition(pContext, index);
+        const float fVal = iChannel==0 ? vP.x : (iChannel==1 ? vP.y : vP.z);
+        const int iCell = FindGridCell(fMin, fMax, fVal);
+        ++piHashCount[iCell];
+    }
+
+    // evaluate start index of each cell.
+    piHashOffsets[0]=0;
+    for (k=1; k<g_iCells; k++)
+        piHashOffsets[k]=piHashOffsets[k-1]+piHashCount[k-1];
+
+    // insert vertices
+    for (i=0; i<(iNrTrianglesIn*3); i++)
+    {
+        const int index = piTriList_in_and_out[i];
+        const SVec3 vP = GetPosition(pContext, index);
+        const float fVal = iChannel==0 ? vP.x : (iChannel==1 ? vP.y : vP.z);
+        const int iCell = FindGridCell(fMin, fMax, fVal);
+        int * pTable = NULL;
+
+        assert(piHashCount2[iCell]<piHashCount[iCell]);
+        pTable = &piHashTable[piHashOffsets[iCell]];
+        pTable[piHashCount2[iCell]] = i;    // vertex i has been inserted.
+        ++piHashCount2[iCell];
+    }
+    for (k=0; k<g_iCells; k++)
+        assert(piHashCount2[k] == piHashCount[k]);  // verify the count
+    free(piHashCount2);
+
+    // find maximum amount of entries in any hash entry
+    iMaxCount = piHashCount[0];
+    for (k=1; k<g_iCells; k++)
+        if (iMaxCount<piHashCount[k])
+            iMaxCount=piHashCount[k];
+    pTmpVert = (STmpVert *) malloc(sizeof(STmpVert)*iMaxCount);
+    
+
+    // complete the merge
+    for (k=0; k<g_iCells; k++)
+    {
+        // extract table of cell k and amount of entries in it
+        int * pTable = &piHashTable[piHashOffsets[k]];
+        const int iEntries = piHashCount[k];
+        if (iEntries < 2) continue;
+
+        if (pTmpVert!=NULL)
+        {
+            for (e=0; e<iEntries; e++)
+            {
+                int i = pTable[e];
+                const SVec3 vP = GetPosition(pContext, piTriList_in_and_out[i]);
+                pTmpVert[e].vert[0] = vP.x; pTmpVert[e].vert[1] = vP.y;
+                pTmpVert[e].vert[2] = vP.z; pTmpVert[e].index = i;
+            }
+            MergeVertsFast(piTriList_in_and_out, pTmpVert, pContext, 0, iEntries-1);
+        }
+        else
+            MergeVertsSlow(piTriList_in_and_out, pContext, pTable, iEntries);
+    }
+
+    if (pTmpVert!=NULL) { free(pTmpVert); }
+    free(piHashTable);
+    free(piHashCount);
+    free(piHashOffsets);
+}
+
+static void MergeVertsFast(int piTriList_in_and_out[], STmpVert pTmpVert[], const SMikkTSpaceContext * pContext, const int iL_in, const int iR_in)
+{
+    // make bbox
+    int c=0, l=0, channel=0;
+    float fvMin[3], fvMax[3];
+    float dx=0, dy=0, dz=0, fSep=0;
+    for (c=0; c<3; c++)
+    {   fvMin[c]=pTmpVert[iL_in].vert[c]; fvMax[c]=fvMin[c];    }
+    for (l=(iL_in+1); l<=iR_in; l++)
+        for (c=0; c<3; c++)
+            if (fvMin[c]>pTmpVert[l].vert[c]) fvMin[c]=pTmpVert[l].vert[c];
+            else if(fvMax[c]<pTmpVert[l].vert[c]) fvMax[c]=pTmpVert[l].vert[c];
+
+    dx = fvMax[0]-fvMin[0];
+    dy = fvMax[1]-fvMin[1];
+    dz = fvMax[2]-fvMin[2];
+
+    channel = 0;
+    if (dy>dx && dy>dz) channel=1;
+    else if(dz>dx) channel=2;
+
+    fSep = 0.5f*(fvMax[channel]+fvMin[channel]);
+
+    // terminate recursion when the separation/average value
+    // is no longer strictly between fMin and fMax values.
+    if (fSep>=fvMax[channel] || fSep<=fvMin[channel])
+    {
+        // complete the weld
+        for (l=iL_in; l<=iR_in; l++)
+        {
+            int i = pTmpVert[l].index;
+            const int index = piTriList_in_and_out[i];
+            const SVec3 vP = GetPosition(pContext, index);
+            const SVec3 vN = GetNormal(pContext, index);
+            const SVec3 vT = GetTexCoord(pContext, index);
+
+            tbool bNotFound = TTRUE;
+            int l2=iL_in, i2rec=-1;
+            while (l2<l && bNotFound)
+            {
+                const int i2 = pTmpVert[l2].index;
+                const int index2 = piTriList_in_and_out[i2];
+                const SVec3 vP2 = GetPosition(pContext, index2);
+                const SVec3 vN2 = GetNormal(pContext, index2);
+                const SVec3 vT2 = GetTexCoord(pContext, index2);
+                i2rec=i2;
+
+                //if(vP==vP2 && vN==vN2 && vT==vT2)
+                if (vP.x==vP2.x && vP.y==vP2.y && vP.z==vP2.z &&
+                    vN.x==vN2.x && vN.y==vN2.y && vN.z==vN2.z &&
+                    vT.x==vT2.x && vT.y==vT2.y && vT.z==vT2.z)
+                    bNotFound = TFALSE;
+                else
+                    ++l2;
+            }
+            
+            // merge if previously found
+            if (!bNotFound)
+                piTriList_in_and_out[i] = piTriList_in_and_out[i2rec];
+        }
+    }
+    else
+    {
+        int iL=iL_in, iR=iR_in;
+        assert((iR_in-iL_in)>0);    // at least 2 entries
+
+        // separate (by fSep) all points between iL_in and iR_in in pTmpVert[]
+        while (iL < iR)
+        {
+            tbool bReadyLeftSwap = TFALSE, bReadyRightSwap = TFALSE;
+            while ((!bReadyLeftSwap) && iL<iR)
+            {
+                assert(iL>=iL_in && iL<=iR_in);
+                bReadyLeftSwap = !(pTmpVert[iL].vert[channel]<fSep);
+                if (!bReadyLeftSwap) ++iL;
+            }
+            while ((!bReadyRightSwap) && iL<iR)
+            {
+                assert(iR>=iL_in && iR<=iR_in);
+                bReadyRightSwap = pTmpVert[iR].vert[channel]<fSep;
+                if (!bReadyRightSwap) --iR;
+            }
+            assert( (iL<iR) || !(bReadyLeftSwap && bReadyRightSwap) );
+
+            if (bReadyLeftSwap && bReadyRightSwap)
+            {
+                const STmpVert sTmp = pTmpVert[iL];
+                assert(iL<iR);
+                pTmpVert[iL] = pTmpVert[iR];
+                pTmpVert[iR] = sTmp;
+                ++iL; --iR;
+            }
+        }
+
+        assert(iL==(iR+1) || (iL==iR));
+        if (iL==iR)
+        {
+            const tbool bReadyRightSwap = pTmpVert[iR].vert[channel]<fSep;
+            if (bReadyRightSwap) ++iL;
+            else --iR;
+        }
+
+        // only need to weld when there is more than 1 instance of the (x,y,z)
+        if (iL_in < iR)
+            MergeVertsFast(piTriList_in_and_out, pTmpVert, pContext, iL_in, iR);    // weld all left of fSep
+        if (iL < iR_in)
+            MergeVertsFast(piTriList_in_and_out, pTmpVert, pContext, iL, iR_in);    // weld all right of (or equal to) fSep
+    }
+}
+
+static void MergeVertsSlow(int piTriList_in_and_out[], const SMikkTSpaceContext * pContext, const int pTable[], const int iEntries)
+{
+    // this can be optimized further using a tree structure or more hashing.
+    int e=0;
+    for (e=0; e<iEntries; e++)
+    {
+        int i = pTable[e];
+        const int index = piTriList_in_and_out[i];
+        const SVec3 vP = GetPosition(pContext, index);
+        const SVec3 vN = GetNormal(pContext, index);
+        const SVec3 vT = GetTexCoord(pContext, index);
+
+        tbool bNotFound = TTRUE;
+        int e2=0, i2rec=-1;
+        while (e2<e && bNotFound)
+        {
+            const int i2 = pTable[e2];
+            const int index2 = piTriList_in_and_out[i2];
+            const SVec3 vP2 = GetPosition(pContext, index2);
+            const SVec3 vN2 = GetNormal(pContext, index2);
+            const SVec3 vT2 = GetTexCoord(pContext, index2);
+            i2rec = i2;
+
+            if (veq(vP,vP2) && veq(vN,vN2) && veq(vT,vT2))
+                bNotFound = TFALSE;
+            else
+                ++e2;
+        }
+        
+        // merge if previously found
+        if (!bNotFound)
+            piTriList_in_and_out[i] = piTriList_in_and_out[i2rec];
+    }
+}
+
+static void GenerateSharedVerticesIndexListSlow(int piTriList_in_and_out[], const SMikkTSpaceContext * pContext, const int iNrTrianglesIn)
+{
+    int iNumUniqueVerts = 0, t=0, i=0;
+    for (t=0; t<iNrTrianglesIn; t++)
+    {
+        for (i=0; i<3; i++)
+        {
+            const int offs = t*3 + i;
+            const int index = piTriList_in_and_out[offs];
+
+            const SVec3 vP = GetPosition(pContext, index);
+            const SVec3 vN = GetNormal(pContext, index);
+            const SVec3 vT = GetTexCoord(pContext, index);
+
+            tbool bFound = TFALSE;
+            int t2=0, index2rec=-1;
+            while (!bFound && t2<=t)
+            {
+                int j=0;
+                while (!bFound && j<3)
+                {
+                    const int index2 = piTriList_in_and_out[t2*3 + j];
+                    const SVec3 vP2 = GetPosition(pContext, index2);
+                    const SVec3 vN2 = GetNormal(pContext, index2);
+                    const SVec3 vT2 = GetTexCoord(pContext, index2);
+                    
+                    if (veq(vP,vP2) && veq(vN,vN2) && veq(vT,vT2))
+                        bFound = TTRUE;
+                    else
+                        ++j;
+                }
+                if (!bFound) ++t2;
+            }
+
+            assert(bFound);
+            // if we found our own
+            if (index2rec == index) { ++iNumUniqueVerts; }
+
+            piTriList_in_and_out[offs] = index2rec;
+        }
+    }
+}
+
+static int GenerateInitialVerticesIndexList(STriInfo pTriInfos[], int piTriList_out[], const SMikkTSpaceContext * pContext, const int iNrTrianglesIn)
+{
+    int iTSpacesOffs = 0, f=0, t=0;
+    int iDstTriIndex = 0;
+    for (f=0; f<pContext->m_pInterface->m_getNumFaces(pContext); f++)
+    {
+        const int verts = pContext->m_pInterface->m_getNumVerticesOfFace(pContext, f);
+        if (verts!=3 && verts!=4) continue;
+
+        pTriInfos[iDstTriIndex].iOrgFaceNumber = f;
+        pTriInfos[iDstTriIndex].iTSpacesOffs = iTSpacesOffs;
+
+        if (verts==3)
+        {
+            unsigned char * pVerts = pTriInfos[iDstTriIndex].vert_num;
+            pVerts[0]=0; pVerts[1]=1; pVerts[2]=2;
+            piTriList_out[iDstTriIndex*3+0] = MakeIndex(f, 0);
+            piTriList_out[iDstTriIndex*3+1] = MakeIndex(f, 1);
+            piTriList_out[iDstTriIndex*3+2] = MakeIndex(f, 2);
+            ++iDstTriIndex; // next
+        }
+        else
+        {
+            {
+                pTriInfos[iDstTriIndex+1].iOrgFaceNumber = f;
+                pTriInfos[iDstTriIndex+1].iTSpacesOffs = iTSpacesOffs;
+            }
+
+            {
+                // need an order independent way to evaluate
+                // tspace on quads. This is done by splitting
+                // along the shortest diagonal.
+                const int i0 = MakeIndex(f, 0);
+                const int i1 = MakeIndex(f, 1);
+                const int i2 = MakeIndex(f, 2);
+                const int i3 = MakeIndex(f, 3);
+                const SVec3 T0 = GetTexCoord(pContext, i0);
+                const SVec3 T1 = GetTexCoord(pContext, i1);
+                const SVec3 T2 = GetTexCoord(pContext, i2);
+                const SVec3 T3 = GetTexCoord(pContext, i3);
+                const float distSQ_02 = LengthSquared(vsub(T2,T0));
+                const float distSQ_13 = LengthSquared(vsub(T3,T1));
+                tbool bQuadDiagIs_02;
+                if (distSQ_02<distSQ_13)
+                    bQuadDiagIs_02 = TTRUE;
+                else if(distSQ_13<distSQ_02)
+                    bQuadDiagIs_02 = TFALSE;
+                else
+                {
+                    const SVec3 P0 = GetPosition(pContext, i0);
+                    const SVec3 P1 = GetPosition(pContext, i1);
+                    const SVec3 P2 = GetPosition(pContext, i2);
+                    const SVec3 P3 = GetPosition(pContext, i3);
+                    const float distSQ_02 = LengthSquared(vsub(P2,P0));
+                    const float distSQ_13 = LengthSquared(vsub(P3,P1));
+
+                    bQuadDiagIs_02 = distSQ_13<distSQ_02 ? TFALSE : TTRUE;
+                }
+
+                if (bQuadDiagIs_02)
+                {
+                    {
+                        unsigned char * pVerts_A = pTriInfos[iDstTriIndex].vert_num;
+                        pVerts_A[0]=0; pVerts_A[1]=1; pVerts_A[2]=2;
+                    }
+                    piTriList_out[iDstTriIndex*3+0] = i0;
+                    piTriList_out[iDstTriIndex*3+1] = i1;
+                    piTriList_out[iDstTriIndex*3+2] = i2;
+                    ++iDstTriIndex; // next
+                    {
+                        unsigned char * pVerts_B = pTriInfos[iDstTriIndex].vert_num;
+                        pVerts_B[0]=0; pVerts_B[1]=2; pVerts_B[2]=3;
+                    }
+                    piTriList_out[iDstTriIndex*3+0] = i0;
+                    piTriList_out[iDstTriIndex*3+1] = i2;
+                    piTriList_out[iDstTriIndex*3+2] = i3;
+                    ++iDstTriIndex; // next
+                }
+                else
+                {
+                    {
+                        unsigned char * pVerts_A = pTriInfos[iDstTriIndex].vert_num;
+                        pVerts_A[0]=0; pVerts_A[1]=1; pVerts_A[2]=3;
+                    }
+                    piTriList_out[iDstTriIndex*3+0] = i0;
+                    piTriList_out[iDstTriIndex*3+1] = i1;
+                    piTriList_out[iDstTriIndex*3+2] = i3;
+                    ++iDstTriIndex; // next
+                    {
+                        unsigned char * pVerts_B = pTriInfos[iDstTriIndex].vert_num;
+                        pVerts_B[0]=1; pVerts_B[1]=2; pVerts_B[2]=3;
+                    }
+                    piTriList_out[iDstTriIndex*3+0] = i1;
+                    piTriList_out[iDstTriIndex*3+1] = i2;
+                    piTriList_out[iDstTriIndex*3+2] = i3;
+                    ++iDstTriIndex; // next
+                }
+            }
+        }
+
+        iTSpacesOffs += verts;
+        assert(iDstTriIndex<=iNrTrianglesIn);
+    }
+
+    for (t=0; t<iNrTrianglesIn; t++)
+        pTriInfos[t].iFlag = 0;
+
+    // return total amount of tspaces
+    return iTSpacesOffs;
+}
+
+static SVec3 GetPosition(const SMikkTSpaceContext * pContext, const int index)
+{
+    int iF, iI;
+    SVec3 res; float pos[3];
+    IndexToData(&iF, &iI, index);
+    pContext->m_pInterface->m_getPosition(pContext, pos, iF, iI);
+    res.x=pos[0]; res.y=pos[1]; res.z=pos[2];
+    return res;
+}
+
+static SVec3 GetNormal(const SMikkTSpaceContext * pContext, const int index)
+{
+    int iF, iI;
+    SVec3 res; float norm[3];
+    IndexToData(&iF, &iI, index);
+    pContext->m_pInterface->m_getNormal(pContext, norm, iF, iI);
+    res.x=norm[0]; res.y=norm[1]; res.z=norm[2];
+    return res;
+}
+
+static SVec3 GetTexCoord(const SMikkTSpaceContext * pContext, const int index)
+{
+    int iF, iI;
+    SVec3 res; float texc[2];
+    IndexToData(&iF, &iI, index);
+    pContext->m_pInterface->m_getTexCoord(pContext, texc, iF, iI);
+    res.x=texc[0]; res.y=texc[1]; res.z=1.0f;
+    return res;
+}
+
+/////////////////////////////////////////////////////////////////////////////////////////////////////
+/////////////////////////////////////////////////////////////////////////////////////////////////////
+
+typedef union
+{
+    struct
+    {
+        int i0, i1, f;
+    };
+    int array[3];
+} SEdge;
+
+static void BuildNeighborsFast(STriInfo pTriInfos[], SEdge * pEdges, const int piTriListIn[], const int iNrTrianglesIn);
+static void BuildNeighborsSlow(STriInfo pTriInfos[], const int piTriListIn[], const int iNrTrianglesIn);
+
+// returns the texture area times 2
+static float CalcTexArea(const SMikkTSpaceContext * pContext, const int indices[])
+{
+    const SVec3 t1 = GetTexCoord(pContext, indices[0]);
+    const SVec3 t2 = GetTexCoord(pContext, indices[1]);
+    const SVec3 t3 = GetTexCoord(pContext, indices[2]);
+
+    const float t21x = t2.x-t1.x;
+    const float t21y = t2.y-t1.y;
+    const float t31x = t3.x-t1.x;
+    const float t31y = t3.y-t1.y;
+
+    const float fSignedAreaSTx2 = t21x*t31y - t21y*t31x;
+
+    return fSignedAreaSTx2<0 ? (-fSignedAreaSTx2) : fSignedAreaSTx2;
+}
+
+static void InitTriInfo(STriInfo pTriInfos[], const int piTriListIn[], const SMikkTSpaceContext * pContext, const int iNrTrianglesIn)
+{
+    int f=0, i=0, t=0;
+    // pTriInfos[f].iFlag is cleared in GenerateInitialVerticesIndexList() which is called before this function.
+
+    // generate neighbor info list
+    for (f=0; f<iNrTrianglesIn; f++)
+        for (i=0; i<3; i++)
+        {
+            pTriInfos[f].FaceNeighbors[i] = -1;
+            pTriInfos[f].AssignedGroup[i] = NULL;
+
+            pTriInfos[f].vOs.x=0.0f; pTriInfos[f].vOs.y=0.0f; pTriInfos[f].vOs.z=0.0f;
+            pTriInfos[f].vOt.x=0.0f; pTriInfos[f].vOt.y=0.0f; pTriInfos[f].vOt.z=0.0f;
+            pTriInfos[f].fMagS = 0;
+            pTriInfos[f].fMagT = 0;
+
+            // assumed bad
+            pTriInfos[f].iFlag |= GROUP_WITH_ANY;
+        }
+
+    // evaluate first order derivatives
+    for (f=0; f<iNrTrianglesIn; f++)
+    {
+        // initial values
+        const SVec3 v1 = GetPosition(pContext, piTriListIn[f*3+0]);
+        const SVec3 v2 = GetPosition(pContext, piTriListIn[f*3+1]);
+        const SVec3 v3 = GetPosition(pContext, piTriListIn[f*3+2]);
+        const SVec3 t1 = GetTexCoord(pContext, piTriListIn[f*3+0]);
+        const SVec3 t2 = GetTexCoord(pContext, piTriListIn[f*3+1]);
+        const SVec3 t3 = GetTexCoord(pContext, piTriListIn[f*3+2]);
+
+        const float t21x = t2.x-t1.x;
+        const float t21y = t2.y-t1.y;
+        const float t31x = t3.x-t1.x;
+        const float t31y = t3.y-t1.y;
+        const SVec3 d1 = vsub(v2,v1);
+        const SVec3 d2 = vsub(v3,v1);
+
+        const float fSignedAreaSTx2 = t21x*t31y - t21y*t31x;
+        //assert(fSignedAreaSTx2!=0);
+        SVec3 vOs = vsub(vscale(t31y,d1), vscale(t21y,d2)); // eq 18
+        SVec3 vOt = vadd(vscale(-t31x,d1), vscale(t21x,d2)); // eq 19
+
+        pTriInfos[f].iFlag |= (fSignedAreaSTx2>0 ? ORIENT_PRESERVING : 0);
+
+        if ( NotZero(fSignedAreaSTx2) )
+        {
+            const float fAbsArea = fabsf(fSignedAreaSTx2);
+            const float fLenOs = Length(vOs);
+            const float fLenOt = Length(vOt);
+            const float fS = (pTriInfos[f].iFlag&ORIENT_PRESERVING)==0 ? (-1.0f) : 1.0f;
+            if ( NotZero(fLenOs) ) pTriInfos[f].vOs = vscale(fS/fLenOs, vOs);
+            if ( NotZero(fLenOt) ) pTriInfos[f].vOt = vscale(fS/fLenOt, vOt);
+
+            // evaluate magnitudes prior to normalization of vOs and vOt
+            pTriInfos[f].fMagS = fLenOs / fAbsArea;
+            pTriInfos[f].fMagT = fLenOt / fAbsArea;
+
+            // if this is a good triangle
+            if ( NotZero(pTriInfos[f].fMagS) && NotZero(pTriInfos[f].fMagT))
+                pTriInfos[f].iFlag &= (~GROUP_WITH_ANY);
+        }
+    }
+
+    // force otherwise healthy quads to a fixed orientation
+    while (t<(iNrTrianglesIn-1))
+    {
+        const int iFO_a = pTriInfos[t].iOrgFaceNumber;
+        const int iFO_b = pTriInfos[t+1].iOrgFaceNumber;
+        if (iFO_a==iFO_b)   // this is a quad
+        {
+            const tbool bIsDeg_a = (pTriInfos[t].iFlag&MARK_DEGENERATE)!=0 ? TTRUE : TFALSE;
+            const tbool bIsDeg_b = (pTriInfos[t+1].iFlag&MARK_DEGENERATE)!=0 ? TTRUE : TFALSE;
+            
+            // bad triangles should already have been removed by
+            // DegenPrologue(), but just in case check bIsDeg_a and bIsDeg_a are false
+            if ((bIsDeg_a||bIsDeg_b)==TFALSE)
+            {
+                const tbool bOrientA = (pTriInfos[t].iFlag&ORIENT_PRESERVING)!=0 ? TTRUE : TFALSE;
+                const tbool bOrientB = (pTriInfos[t+1].iFlag&ORIENT_PRESERVING)!=0 ? TTRUE : TFALSE;
+                // if this happens the quad has extremely bad mapping!!
+                if (bOrientA!=bOrientB)
+                {
+                    //printf("found quad with bad mapping\n");
+                    tbool bChooseOrientFirstTri = TFALSE;
+                    if ((pTriInfos[t+1].iFlag&GROUP_WITH_ANY)!=0) bChooseOrientFirstTri = TTRUE;
+                    else if( CalcTexArea(pContext, &piTriListIn[t*3+0]) >= CalcTexArea(pContext, &piTriListIn[(t+1)*3+0]) )
+                        bChooseOrientFirstTri = TTRUE;
+
+                    // force match
+                    {
+                        const int t0 = bChooseOrientFirstTri ? t : (t+1);
+                        const int t1 = bChooseOrientFirstTri ? (t+1) : t;
+                        pTriInfos[t1].iFlag &= (~ORIENT_PRESERVING);    // clear first
+                        pTriInfos[t1].iFlag |= (pTriInfos[t0].iFlag&ORIENT_PRESERVING); // copy bit
+                    }
+                }
+            }
+            t += 2;
+        }
+        else
+            ++t;
+    }
+    
+    // match up edge pairs
+    {
+        SEdge * pEdges = (SEdge *) malloc(sizeof(SEdge)*iNrTrianglesIn*3);
+        if (pEdges==NULL)
+            BuildNeighborsSlow(pTriInfos, piTriListIn, iNrTrianglesIn);
+        else
+        {
+            BuildNeighborsFast(pTriInfos, pEdges, piTriListIn, iNrTrianglesIn);
+    
+            free(pEdges);
+        }
+    }
+}
+
+/////////////////////////////////////////////////////////////////////////////////////////////////////
+/////////////////////////////////////////////////////////////////////////////////////////////////////
+
+static tbool AssignRecur(const int piTriListIn[], STriInfo psTriInfos[], const int iMyTriIndex, SGroup * pGroup);
+static void AddTriToGroup(SGroup * pGroup, const int iTriIndex);
+
+static int Build4RuleGroups(STriInfo pTriInfos[], SGroup pGroups[], int piGroupTrianglesBuffer[], const int piTriListIn[], const int iNrTrianglesIn)
+{
+    const int iNrMaxGroups = iNrTrianglesIn*3;
+    int iNrActiveGroups = 0;
+    int iOffset = 0, f=0, i=0;
+    for (f=0; f<iNrTrianglesIn; f++)
+    {
+        for (i=0; i<3; i++)
+        {
+            // if not assigned to a group
+            if ((pTriInfos[f].iFlag&GROUP_WITH_ANY)==0 && pTriInfos[f].AssignedGroup[i]==NULL)
+            {
+                tbool bOrPre;
+                int neigh_indexL, neigh_indexR;
+                const int vert_index = piTriListIn[f*3+i];
+                assert(iNrActiveGroups<iNrMaxGroups);
+                pTriInfos[f].AssignedGroup[i] = &pGroups[iNrActiveGroups];
+                pTriInfos[f].AssignedGroup[i]->iVertexRepresentitive = vert_index;
+                pTriInfos[f].AssignedGroup[i]->bOrientPreservering = (pTriInfos[f].iFlag&ORIENT_PRESERVING)!=0;
+                pTriInfos[f].AssignedGroup[i]->iNrFaces = 0;
+                pTriInfos[f].AssignedGroup[i]->pFaceIndices = &piGroupTrianglesBuffer[iOffset];
+                ++iNrActiveGroups;
+
+                AddTriToGroup(pTriInfos[f].AssignedGroup[i], f);
+                bOrPre = (pTriInfos[f].iFlag&ORIENT_PRESERVING)!=0 ? TTRUE : TFALSE;
+                neigh_indexL = pTriInfos[f].FaceNeighbors[i];
+                neigh_indexR = pTriInfos[f].FaceNeighbors[i>0?(i-1):2];
+                if (neigh_indexL>=0) // neighbor
+                {
+                    const tbool bAnswer =
+                        AssignRecur(piTriListIn, pTriInfos, neigh_indexL,
+                                    pTriInfos[f].AssignedGroup[i] );
+                    
+                    const tbool bOrPre2 = (pTriInfos[neigh_indexL].iFlag&ORIENT_PRESERVING)!=0 ? TTRUE : TFALSE;
+                    const tbool bDiff = bOrPre!=bOrPre2 ? TTRUE : TFALSE;
+                    assert(bAnswer || bDiff);
+                }
+                if (neigh_indexR>=0) // neighbor
+                {
+                    const tbool bAnswer =
+                        AssignRecur(piTriListIn, pTriInfos, neigh_indexR,
+                                    pTriInfos[f].AssignedGroup[i] );
+
+                    const tbool bOrPre2 = (pTriInfos[neigh_indexR].iFlag&ORIENT_PRESERVING)!=0 ? TTRUE : TFALSE;
+                    const tbool bDiff = bOrPre!=bOrPre2 ? TTRUE : TFALSE;
+                    assert(bAnswer || bDiff);
+                }
+
+                // update offset
+                iOffset += pTriInfos[f].AssignedGroup[i]->iNrFaces;
+                // since the groups are disjoint a triangle can never
+                // belong to more than 3 groups. Subsequently something
+                // is completely screwed if this assertion ever hits.
+                assert(iOffset <= iNrMaxGroups);
+            }
+        }
+    }
+
+    return iNrActiveGroups;
+}
+
+static void AddTriToGroup(SGroup * pGroup, const int iTriIndex)
+{
+    pGroup->pFaceIndices[pGroup->iNrFaces] = iTriIndex;
+    ++pGroup->iNrFaces;
+}
+
+static tbool AssignRecur(const int piTriListIn[], STriInfo psTriInfos[],
+                 const int iMyTriIndex, SGroup * pGroup)
+{
+    STriInfo * pMyTriInfo = &psTriInfos[iMyTriIndex];
+
+    // track down vertex
+    const int iVertRep = pGroup->iVertexRepresentitive;
+    const int * pVerts = &piTriListIn[3*iMyTriIndex+0];
+    int i=-1;
+    if (pVerts[0]==iVertRep) i=0;
+    else if(pVerts[1]==iVertRep) i=1;
+    else if(pVerts[2]==iVertRep) i=2;
+    assert(i>=0 && i<3);
+
+    // early out
+    if (pMyTriInfo->AssignedGroup[i] == pGroup) return TTRUE;
+    else if(pMyTriInfo->AssignedGroup[i]!=NULL) return TFALSE;
+    if ((pMyTriInfo->iFlag&GROUP_WITH_ANY)!=0)
+    {
+        // first to group with a group-with-anything triangle
+        // determines it's orientation.
+        // This is the only existing order dependency in the code!!
+        if ( pMyTriInfo->AssignedGroup[0] == NULL &&
+            pMyTriInfo->AssignedGroup[1] == NULL &&
+            pMyTriInfo->AssignedGroup[2] == NULL )
+        {
+            pMyTriInfo->iFlag &= (~ORIENT_PRESERVING);
+            pMyTriInfo->iFlag |= (pGroup->bOrientPreservering ? ORIENT_PRESERVING : 0);
+        }
+    }
+    {
+        const tbool bOrient = (pMyTriInfo->iFlag&ORIENT_PRESERVING)!=0 ? TTRUE : TFALSE;
+        if (bOrient != pGroup->bOrientPreservering) return TFALSE;
+    }
+
+    AddTriToGroup(pGroup, iMyTriIndex);
+    pMyTriInfo->AssignedGroup[i] = pGroup;
+
+    {
+        const int neigh_indexL = pMyTriInfo->FaceNeighbors[i];
+        const int neigh_indexR = pMyTriInfo->FaceNeighbors[i>0?(i-1):2];
+        if (neigh_indexL>=0)
+            AssignRecur(piTriListIn, psTriInfos, neigh_indexL, pGroup);
+        if (neigh_indexR>=0)
+            AssignRecur(piTriListIn, psTriInfos, neigh_indexR, pGroup);
+    }
+
+
+
+    return TTRUE;
+}
+
+/////////////////////////////////////////////////////////////////////////////////////////////////////
+/////////////////////////////////////////////////////////////////////////////////////////////////////
+
+static tbool CompareSubGroups(const SSubGroup * pg1, const SSubGroup * pg2);
+static void QuickSort(int* pSortBuffer, int iLeft, int iRight, unsigned int uSeed);
+static STSpace EvalTspace(int face_indices[], const int iFaces, const int piTriListIn[], const STriInfo pTriInfos[], const SMikkTSpaceContext * pContext, const int iVertexRepresentitive);
+
+static tbool GenerateTSpaces(STSpace psTspace[], const STriInfo pTriInfos[], const SGroup pGroups[],
+                             const int iNrActiveGroups, const int piTriListIn[], const float fThresCos,
+                             const SMikkTSpaceContext * pContext)
+{
+    STSpace * pSubGroupTspace = NULL;
+    SSubGroup * pUniSubGroups = NULL;
+    int * pTmpMembers = NULL;
+    int iMaxNrFaces=0, iUniqueTspaces=0, g=0, i=0;
+    for (g=0; g<iNrActiveGroups; g++)
+        if (iMaxNrFaces < pGroups[g].iNrFaces)
+            iMaxNrFaces = pGroups[g].iNrFaces;
+
+    if (iMaxNrFaces == 0) return TTRUE;
+
+    // make initial allocations
+    pSubGroupTspace = (STSpace *) malloc(sizeof(STSpace)*iMaxNrFaces);
+    pUniSubGroups = (SSubGroup *) malloc(sizeof(SSubGroup)*iMaxNrFaces);
+    pTmpMembers = (int *) malloc(sizeof(int)*iMaxNrFaces);
+    if (pSubGroupTspace==NULL || pUniSubGroups==NULL || pTmpMembers==NULL)
+    {
+        if (pSubGroupTspace!=NULL) free(pSubGroupTspace);
+        if (pUniSubGroups!=NULL) free(pUniSubGroups);
+        if (pTmpMembers!=NULL) free(pTmpMembers);
+        return TFALSE;
+    }
+
+
+    iUniqueTspaces = 0;
+    for (g=0; g<iNrActiveGroups; g++)
+    {
+        const SGroup * pGroup = &pGroups[g];
+        int iUniqueSubGroups = 0, s=0;
+
+        for (i=0; i<pGroup->iNrFaces; i++)  // triangles
+        {
+            const int f = pGroup->pFaceIndices[i];  // triangle number
+            int index=-1, iVertIndex=-1, iOF_1=-1, iMembers=0, j=0, l=0;
+            SSubGroup tmp_group;
+            tbool bFound;
+            SVec3 n, vOs, vOt;
+            if (pTriInfos[f].AssignedGroup[0]==pGroup) index=0;
+            else if(pTriInfos[f].AssignedGroup[1]==pGroup) index=1;
+            else if(pTriInfos[f].AssignedGroup[2]==pGroup) index=2;
+            assert(index>=0 && index<3);
+
+            iVertIndex = piTriListIn[f*3+index];
+            assert(iVertIndex==pGroup->iVertexRepresentitive);
+
+            // is normalized already
+            n = GetNormal(pContext, iVertIndex);
+            
+            // project
+            vOs = vsub(pTriInfos[f].vOs, vscale(vdot(n,pTriInfos[f].vOs), n));
+            vOt = vsub(pTriInfos[f].vOt, vscale(vdot(n,pTriInfos[f].vOt), n));
+            if ( VNotZero(vOs) ) vOs = Normalize(vOs);
+            if ( VNotZero(vOt) ) vOt = Normalize(vOt);
+
+            // original face number
+            iOF_1 = pTriInfos[f].iOrgFaceNumber;
+            
+            iMembers = 0;
+            for (j=0; j<pGroup->iNrFaces; j++)
+            {
+                const int t = pGroup->pFaceIndices[j];  // triangle number
+                const int iOF_2 = pTriInfos[t].iOrgFaceNumber;
+
+                // project
+                SVec3 vOs2 = vsub(pTriInfos[t].vOs, vscale(vdot(n,pTriInfos[t].vOs), n));
+                SVec3 vOt2 = vsub(pTriInfos[t].vOt, vscale(vdot(n,pTriInfos[t].vOt), n));
+                if ( VNotZero(vOs2) ) vOs2 = Normalize(vOs2);
+                if ( VNotZero(vOt2) ) vOt2 = Normalize(vOt2);
+
+                {
+                    const tbool bAny = ( (pTriInfos[f].iFlag | pTriInfos[t].iFlag) & GROUP_WITH_ANY )!=0 ? TTRUE : TFALSE;
+                    // make sure triangles which belong to the same quad are joined.
+                    const tbool bSameOrgFace = iOF_1==iOF_2 ? TTRUE : TFALSE;
+
+                    const float fCosS = vdot(vOs,vOs2);
+                    const float fCosT = vdot(vOt,vOt2);
+
+                    assert(f!=t || bSameOrgFace);   // sanity check
+                    if (bAny || bSameOrgFace || (fCosS>fThresCos && fCosT>fThresCos))
+                        pTmpMembers[iMembers++] = t;
+                }
+            }
+
+            // sort pTmpMembers
+            tmp_group.iNrFaces = iMembers;
+            tmp_group.pTriMembers = pTmpMembers;
+            if (iMembers>1)
+            {
+                unsigned int uSeed = INTERNAL_RND_SORT_SEED;    // could replace with a random seed?
+                QuickSort(pTmpMembers, 0, iMembers-1, uSeed);
+            }
+
+            // look for an existing match
+            bFound = TFALSE;
+            l=0;
+            while (l<iUniqueSubGroups && !bFound)
+            {
+                bFound = CompareSubGroups(&tmp_group, &pUniSubGroups[l]);
+                if (!bFound) ++l;
+            }
+            
+            // assign tangent space index
+            assert(bFound || l==iUniqueSubGroups);
+            //piTempTangIndices[f*3+index] = iUniqueTspaces+l;
+
+            // if no match was found we allocate a new subgroup
+            if (!bFound)
+            {
+                // insert new subgroup
+                int * pIndices = (int *) malloc(sizeof(int)*iMembers);
+                if (pIndices==NULL)
+                {
+                    // clean up and return false
+                    int s=0;
+                    for (s=0; s<iUniqueSubGroups; s++)
+                        free(pUniSubGroups[s].pTriMembers);
+                    free(pUniSubGroups);
+                    free(pTmpMembers);
+                    free(pSubGroupTspace);
+                    return TFALSE;
+                }
+                pUniSubGroups[iUniqueSubGroups].iNrFaces = iMembers;
+                pUniSubGroups[iUniqueSubGroups].pTriMembers = pIndices;
+                memcpy(pIndices, tmp_group.pTriMembers, iMembers*sizeof(int));
+                pSubGroupTspace[iUniqueSubGroups] =
+                    EvalTspace(tmp_group.pTriMembers, iMembers, piTriListIn, pTriInfos, pContext, pGroup->iVertexRepresentitive);
+                ++iUniqueSubGroups;
+            }
+
+            // output tspace
+            {
+                const int iOffs = pTriInfos[f].iTSpacesOffs;
+                const int iVert = pTriInfos[f].vert_num[index];
+                STSpace * pTS_out = &psTspace[iOffs+iVert];
+                assert(pTS_out->iCounter<2);
+                assert(((pTriInfos[f].iFlag&ORIENT_PRESERVING)!=0) == pGroup->bOrientPreservering);
+                if (pTS_out->iCounter==1)
+                {
+                    *pTS_out = AvgTSpace(pTS_out, &pSubGroupTspace[l]);
+                    pTS_out->iCounter = 2;  // update counter
+                    pTS_out->bOrient = pGroup->bOrientPreservering;
+                }
+                else
+                {
+                    assert(pTS_out->iCounter==0);
+                    *pTS_out = pSubGroupTspace[l];
+                    pTS_out->iCounter = 1;  // update counter
+                    pTS_out->bOrient = pGroup->bOrientPreservering;
+                }
+            }
+        }
+
+        // clean up and offset iUniqueTspaces
+        for (s=0; s<iUniqueSubGroups; s++)
+            free(pUniSubGroups[s].pTriMembers);
+        iUniqueTspaces += iUniqueSubGroups;
+    }
+
+    // clean up
+    free(pUniSubGroups);
+    free(pTmpMembers);
+    free(pSubGroupTspace);
+
+    return TTRUE;
+}
+
+static STSpace EvalTspace(int face_indices[], const int iFaces, const int piTriListIn[], const STriInfo pTriInfos[],
+                          const SMikkTSpaceContext * pContext, const int iVertexRepresentitive)
+{
+    STSpace res;
+    float fAngleSum = 0;
+    int face=0;
+    res.vOs.x=0.0f; res.vOs.y=0.0f; res.vOs.z=0.0f;
+    res.vOt.x=0.0f; res.vOt.y=0.0f; res.vOt.z=0.0f;
+    res.fMagS = 0; res.fMagT = 0;
+
+    for (face=0; face<iFaces; face++)
+    {
+        const int f = face_indices[face];
+
+        // only valid triangles get to add their contribution
+        if ( (pTriInfos[f].iFlag&GROUP_WITH_ANY)==0 )
+        {
+            SVec3 n, vOs, vOt, p0, p1, p2, v1, v2;
+            float fCos, fAngle, fMagS, fMagT;
+            int i=-1, index=-1, i0=-1, i1=-1, i2=-1;
+            if (piTriListIn[3*f+0]==iVertexRepresentitive) i=0;
+            else if(piTriListIn[3*f+1]==iVertexRepresentitive) i=1;
+            else if(piTriListIn[3*f+2]==iVertexRepresentitive) i=2;
+            assert(i>=0 && i<3);
+
+            // project
+            index = piTriListIn[3*f+i];
+            n = GetNormal(pContext, index);
+            vOs = vsub(pTriInfos[f].vOs, vscale(vdot(n,pTriInfos[f].vOs), n));
+            vOt = vsub(pTriInfos[f].vOt, vscale(vdot(n,pTriInfos[f].vOt), n));
+            if ( VNotZero(vOs) ) vOs = Normalize(vOs);
+            if ( VNotZero(vOt) ) vOt = Normalize(vOt);
+
+            i2 = piTriListIn[3*f + (i<2?(i+1):0)];
+            i1 = piTriListIn[3*f + i];
+            i0 = piTriListIn[3*f + (i>0?(i-1):2)];
+
+            p0 = GetPosition(pContext, i0);
+            p1 = GetPosition(pContext, i1);
+            p2 = GetPosition(pContext, i2);
+            v1 = vsub(p0,p1);
+            v2 = vsub(p2,p1);
+
+            // project
+            v1 = vsub(v1, vscale(vdot(n,v1),n)); if( VNotZero(v1) ) v1 = Normalize(v1);
+            v2 = vsub(v2, vscale(vdot(n,v2),n)); if( VNotZero(v2) ) v2 = Normalize(v2);
+
+            // weight contribution by the angle
+            // between the two edge vectors
+            fCos = vdot(v1,v2); fCos=fCos>1?1:(fCos<(-1) ? (-1) : fCos);
+            fAngle = (float) acos(fCos);
+            fMagS = pTriInfos[f].fMagS;
+            fMagT = pTriInfos[f].fMagT;
+
+            res.vOs=vadd(res.vOs, vscale(fAngle,vOs));
+            res.vOt=vadd(res.vOt,vscale(fAngle,vOt));
+            res.fMagS+=(fAngle*fMagS);
+            res.fMagT+=(fAngle*fMagT);
+            fAngleSum += fAngle;
+        }
+    }
+
+    // normalize
+    if ( VNotZero(res.vOs) ) res.vOs = Normalize(res.vOs);
+    if ( VNotZero(res.vOt) ) res.vOt = Normalize(res.vOt);
+    if (fAngleSum>0)
+    {
+        res.fMagS /= fAngleSum;
+        res.fMagT /= fAngleSum;
+    }
+
+    return res;
+}
+
+static tbool CompareSubGroups(const SSubGroup * pg1, const SSubGroup * pg2)
+{
+    tbool bStillSame=TTRUE;
+    int i=0;
+    if (pg1->iNrFaces!=pg2->iNrFaces) return TFALSE;
+    while (i<pg1->iNrFaces && bStillSame)
+    {
+        bStillSame = pg1->pTriMembers[i]==pg2->pTriMembers[i] ? TTRUE : TFALSE;
+        if (bStillSame) ++i;
+    }
+    return bStillSame;
+}
+
+static void QuickSort(int* pSortBuffer, int iLeft, int iRight, unsigned int uSeed)
+{
+    int iL, iR, n, index, iMid, iTmp;
+
+    // Random
+    unsigned int t=uSeed&31;
+    t=(uSeed<<t)|(uSeed>>(32-t));
+    uSeed=uSeed+t+3;
+    // Random end
+
+    iL=iLeft; iR=iRight;
+    n = (iR-iL)+1;
+    assert(n>=0);
+    index = (int) (uSeed%n);
+
+    iMid=pSortBuffer[index + iL];
+
+
+    do
+    {
+        while (pSortBuffer[iL] < iMid)
+            ++iL;
+        while (pSortBuffer[iR] > iMid)
+            --iR;
+
+        if (iL <= iR)
+        {
+            iTmp = pSortBuffer[iL];
+            pSortBuffer[iL] = pSortBuffer[iR];
+            pSortBuffer[iR] = iTmp;
+            ++iL; --iR;
+        }
+    }
+    while (iL <= iR);
+
+    if (iLeft < iR)
+        QuickSort(pSortBuffer, iLeft, iR, uSeed);
+    if (iL < iRight)
+        QuickSort(pSortBuffer, iL, iRight, uSeed);
+}
+
+/////////////////////////////////////////////////////////////////////////////////////////////
+/////////////////////////////////////////////////////////////////////////////////////////////
+
+static void QuickSortEdges(SEdge * pSortBuffer, int iLeft, int iRight, const int channel, unsigned int uSeed);
+static void GetEdge(int * i0_out, int * i1_out, int * edgenum_out, const int indices[], const int i0_in, const int i1_in);
+
+static void BuildNeighborsFast(STriInfo pTriInfos[], SEdge * pEdges, const int piTriListIn[], const int iNrTrianglesIn)
+{
+    // build array of edges
+    unsigned int uSeed = INTERNAL_RND_SORT_SEED;                // could replace with a random seed?
+    int iEntries=0, iCurStartIndex=-1, f=0, i=0;
+    for (f=0; f<iNrTrianglesIn; f++)
+        for (i=0; i<3; i++)
+        {
+            const int i0 = piTriListIn[f*3+i];
+            const int i1 = piTriListIn[f*3+(i<2?(i+1):0)];
+            pEdges[f*3+i].i0 = i0 < i1 ? i0 : i1;           // put minimum index in i0
+            pEdges[f*3+i].i1 = !(i0 < i1) ? i0 : i1;        // put maximum index in i1
+            pEdges[f*3+i].f = f;                            // record face number
+        }
+
+    // sort over all edges by i0, this is the pricy one.
+    QuickSortEdges(pEdges, 0, iNrTrianglesIn*3-1, 0, uSeed);    // sort channel 0 which is i0
+
+    // sub sort over i1, should be fast.
+    // could replace this with a 64 bit int sort over (i0,i1)
+    // with i0 as msb in the quicksort call above.
+    iEntries = iNrTrianglesIn*3;
+    iCurStartIndex = 0;
+    for (i=1; i<iEntries; i++)
+    {
+        if (pEdges[iCurStartIndex].i0 != pEdges[i].i0)
+        {
+            const int iL = iCurStartIndex;
+            const int iR = i-1;
+            //const int iElems = i-iL;
+            iCurStartIndex = i;
+            QuickSortEdges(pEdges, iL, iR, 1, uSeed);   // sort channel 1 which is i1
+        }
+    }
+
+    // sub sort over f, which should be fast.
+    // this step is to remain compliant with BuildNeighborsSlow() when
+    // more than 2 triangles use the same edge (such as a butterfly topology).
+    iCurStartIndex = 0;
+    for (i=1; i<iEntries; i++)
+    {
+        if (pEdges[iCurStartIndex].i0 != pEdges[i].i0 || pEdges[iCurStartIndex].i1 != pEdges[i].i1)
+        {
+            const int iL = iCurStartIndex;
+            const int iR = i-1;
+            //const int iElems = i-iL;
+            iCurStartIndex = i;
+            QuickSortEdges(pEdges, iL, iR, 2, uSeed);   // sort channel 2 which is f
+        }
+    }
+
+    // pair up, adjacent triangles
+    for (i=0; i<iEntries; i++)
+    {
+        const int i0=pEdges[i].i0;
+        const int i1=pEdges[i].i1;
+        const int f = pEdges[i].f;
+        tbool bUnassigned_A;
+
+        int i0_A, i1_A;
+        int edgenum_A, edgenum_B=0; // 0,1 or 2
+        GetEdge(&i0_A, &i1_A, &edgenum_A, &piTriListIn[f*3], i0, i1);   // resolve index ordering and edge_num
+        bUnassigned_A = pTriInfos[f].FaceNeighbors[edgenum_A] == -1 ? TTRUE : TFALSE;
+
+        if (bUnassigned_A)
+        {
+            // get true index ordering
+            int j=i+1, t;
+            tbool bNotFound = TTRUE;
+            while (j<iEntries && i0==pEdges[j].i0 && i1==pEdges[j].i1 && bNotFound)
+            {
+                tbool bUnassigned_B;
+                int i0_B, i1_B;
+                t = pEdges[j].f;
+                // flip i0_B and i1_B
+                GetEdge(&i1_B, &i0_B, &edgenum_B, &piTriListIn[t*3], pEdges[j].i0, pEdges[j].i1);   // resolve index ordering and edge_num
+                //assert(!(i0_A==i1_B && i1_A==i0_B));
+                bUnassigned_B =  pTriInfos[t].FaceNeighbors[edgenum_B]==-1 ? TTRUE : TFALSE;
+                if (i0_A==i0_B && i1_A==i1_B && bUnassigned_B)
+                    bNotFound = TFALSE;
+                else
+                    ++j;
+            }
+
+            if (!bNotFound)
+            {
+                int t = pEdges[j].f;
+                pTriInfos[f].FaceNeighbors[edgenum_A] = t;
+                //assert(pTriInfos[t].FaceNeighbors[edgenum_B]==-1);
+                pTriInfos[t].FaceNeighbors[edgenum_B] = f;
+            }
+        }
+    }
+}
+
+static void BuildNeighborsSlow(STriInfo pTriInfos[], const int piTriListIn[], const int iNrTrianglesIn)
+{
+    int f=0, i=0;
+    for (f=0; f<iNrTrianglesIn; f++)
+    {
+        for (i=0; i<3; i++)
+        {
+            // if unassigned
+            if (pTriInfos[f].FaceNeighbors[i] == -1)
+            {
+                const int i0_A = piTriListIn[f*3+i];
+                const int i1_A = piTriListIn[f*3+(i<2?(i+1):0)];
+
+                // search for a neighbor
+                tbool bFound = TFALSE;
+                int t=0, j=0;
+                while (!bFound && t<iNrTrianglesIn)
+                {
+                    if (t!=f)
+                    {
+                        j=0;
+                        while (!bFound && j<3)
+                        {
+                            // in rev order
+                            const int i1_B = piTriListIn[t*3+j];
+                            const int i0_B = piTriListIn[t*3+(j<2?(j+1):0)];
+                            //assert(!(i0_A==i1_B && i1_A==i0_B));
+                            if (i0_A==i0_B && i1_A==i1_B)
+                                bFound = TTRUE;
+                            else
+                                ++j;
+                        }
+                    }
+                    
+                    if (!bFound) ++t;
+                }
+
+                // assign neighbors
+                if (bFound)
+                {
+                    pTriInfos[f].FaceNeighbors[i] = t;
+                    //assert(pTriInfos[t].FaceNeighbors[j]==-1);
+                    pTriInfos[t].FaceNeighbors[j] = f;
+                }
+            }
+        }
+    }
+}
+
+static void QuickSortEdges(SEdge * pSortBuffer, int iLeft, int iRight, const int channel, unsigned int uSeed)
+{
+    unsigned int t;
+    int iL, iR, n, index, iMid;
+
+    // early out
+    SEdge sTmp;
+    const int iElems = iRight-iLeft+1;
+    if (iElems<2) return;
+    else if(iElems==2)
+    {
+        if (pSortBuffer[iLeft].array[channel] > pSortBuffer[iRight].array[channel])
+        {
+            sTmp = pSortBuffer[iLeft];
+            pSortBuffer[iLeft] = pSortBuffer[iRight];
+            pSortBuffer[iRight] = sTmp;
+        }
+        return;
+    }
+
+    // Random
+    t=uSeed&31;
+    t=(uSeed<<t)|(uSeed>>(32-t));
+    uSeed=uSeed+t+3;
+    // Random end
+
+    iL=iLeft, iR=iRight;
+    n = (iR-iL)+1;
+    assert(n>=0);
+    index = (int) (uSeed%n);
+
+    iMid=pSortBuffer[index + iL].array[channel];
+
+    do
+    {
+        while (pSortBuffer[iL].array[channel] < iMid)
+            ++iL;
+        while (pSortBuffer[iR].array[channel] > iMid)
+            --iR;
+
+        if (iL <= iR)
+        {
+            sTmp = pSortBuffer[iL];
+            pSortBuffer[iL] = pSortBuffer[iR];
+            pSortBuffer[iR] = sTmp;
+            ++iL; --iR;
+        }
+    }
+    while (iL <= iR);
+
+    if (iLeft < iR)
+        QuickSortEdges(pSortBuffer, iLeft, iR, channel, uSeed);
+    if (iL < iRight)
+        QuickSortEdges(pSortBuffer, iL, iRight, channel, uSeed);
+}
+
+// resolve ordering and edge number
+static void GetEdge(int * i0_out, int * i1_out, int * edgenum_out, const int indices[], const int i0_in, const int i1_in)
+{
+    *edgenum_out = -1;
+    
+    // test if first index is on the edge
+    if (indices[0]==i0_in || indices[0]==i1_in)
+    {
+        // test if second index is on the edge
+        if (indices[1]==i0_in || indices[1]==i1_in)
+        {
+            edgenum_out[0]=0;   // first edge
+            i0_out[0]=indices[0];
+            i1_out[0]=indices[1];
+        }
+        else
+        {
+            edgenum_out[0]=2;   // third edge
+            i0_out[0]=indices[2];
+            i1_out[0]=indices[0];
+        }
+    }
+    else
+    {
+        // only second and third index is on the edge
+        edgenum_out[0]=1;   // second edge
+        i0_out[0]=indices[1];
+        i1_out[0]=indices[2];
+    }
+}
+
+
+/////////////////////////////////////////////////////////////////////////////////////////////
+/////////////////////////////////// Degenerate triangles ////////////////////////////////////
+
+static void DegenPrologue(STriInfo pTriInfos[], int piTriList_out[], const int iNrTrianglesIn, const int iTotTris)
+{
+    int iNextGoodTriangleSearchIndex=-1;
+    tbool bStillFindingGoodOnes;
+
+    // locate quads with only one good triangle
+    int t=0;
+    while (t<(iTotTris-1))
+    {
+        const int iFO_a = pTriInfos[t].iOrgFaceNumber;
+        const int iFO_b = pTriInfos[t+1].iOrgFaceNumber;
+        if (iFO_a==iFO_b)   // this is a quad
+        {
+            const tbool bIsDeg_a = (pTriInfos[t].iFlag&MARK_DEGENERATE)!=0 ? TTRUE : TFALSE;
+            const tbool bIsDeg_b = (pTriInfos[t+1].iFlag&MARK_DEGENERATE)!=0 ? TTRUE : TFALSE;
+            if ((bIsDeg_a^bIsDeg_b)!=0)
+            {
+                pTriInfos[t].iFlag |= QUAD_ONE_DEGEN_TRI;
+                pTriInfos[t+1].iFlag |= QUAD_ONE_DEGEN_TRI;
+            }
+            t += 2;
+        }
+        else
+            ++t;
+    }
+
+    // reorder list so all degen triangles are moved to the back
+    // without reordering the good triangles
+    iNextGoodTriangleSearchIndex = 1;
+    t=0;
+    bStillFindingGoodOnes = TTRUE;
+    while (t<iNrTrianglesIn && bStillFindingGoodOnes)
+    {
+        const tbool bIsGood = (pTriInfos[t].iFlag&MARK_DEGENERATE)==0 ? TTRUE : TFALSE;
+        if (bIsGood)
+        {
+            if (iNextGoodTriangleSearchIndex < (t+2))
+                iNextGoodTriangleSearchIndex = t+2;
+        }
+        else
+        {
+            int t0, t1;
+            // search for the first good triangle.
+            tbool bJustADegenerate = TTRUE;
+            while (bJustADegenerate && iNextGoodTriangleSearchIndex<iTotTris)
+            {
+                const tbool bIsGood = (pTriInfos[iNextGoodTriangleSearchIndex].iFlag&MARK_DEGENERATE)==0 ? TTRUE : TFALSE;
+                if (bIsGood) bJustADegenerate=TFALSE;
+                else ++iNextGoodTriangleSearchIndex;
+            }
+
+            t0 = t;
+            t1 = iNextGoodTriangleSearchIndex;
+            ++iNextGoodTriangleSearchIndex;
+            assert(iNextGoodTriangleSearchIndex > (t+1));
+
+            // swap triangle t0 and t1
+            if (!bJustADegenerate)
+            {
+                int i=0;
+                for (i=0; i<3; i++)
+                {
+                    const int index = piTriList_out[t0*3+i];
+                    piTriList_out[t0*3+i] = piTriList_out[t1*3+i];
+                    piTriList_out[t1*3+i] = index;
+                }
+                {
+                    const STriInfo tri_info = pTriInfos[t0];
+                    pTriInfos[t0] = pTriInfos[t1];
+                    pTriInfos[t1] = tri_info;
+                }
+            }
+            else
+                bStillFindingGoodOnes = TFALSE; // this is not supposed to happen
+        }
+
+        if (bStillFindingGoodOnes) ++t;
+    }
+
+    assert(bStillFindingGoodOnes);  // code will still work.
+    assert(iNrTrianglesIn == t);
+}
+
+static void DegenEpilogue(STSpace psTspace[], STriInfo pTriInfos[], int piTriListIn[], const SMikkTSpaceContext * pContext, const int iNrTrianglesIn, const int iTotTris)
+{
+    int t=0, i=0;
+    // deal with degenerate triangles
+    // punishment for degenerate triangles is O(N^2)
+    for (t=iNrTrianglesIn; t<iTotTris; t++)
+    {
+        // degenerate triangles on a quad with one good triangle are skipped
+        // here but processed in the next loop
+        const tbool bSkip = (pTriInfos[t].iFlag&QUAD_ONE_DEGEN_TRI)!=0 ? TTRUE : TFALSE;
+
+        if (!bSkip)
+        {
+            for (i=0; i<3; i++)
+            {
+                const int index1 = piTriListIn[t*3+i];
+                // search through the good triangles
+                tbool bNotFound = TTRUE;
+                int j=0;
+                while (bNotFound && j<(3*iNrTrianglesIn))
+                {
+                    const int index2 = piTriListIn[j];
+                    if (index1==index2) bNotFound=TFALSE;
+                    else ++j;
+                }
+
+                if (!bNotFound)
+                {
+                    const int iTri = j/3;
+                    const int iVert = j%3;
+                    const int iSrcVert=pTriInfos[iTri].vert_num[iVert];
+                    const int iSrcOffs=pTriInfos[iTri].iTSpacesOffs;
+                    const int iDstVert=pTriInfos[t].vert_num[i];
+                    const int iDstOffs=pTriInfos[t].iTSpacesOffs;
+                    
+                    // copy tspace
+                    psTspace[iDstOffs+iDstVert] = psTspace[iSrcOffs+iSrcVert];
+                }
+            }
+        }
+    }
+
+    // deal with degenerate quads with one good triangle
+    for (t=0; t<iNrTrianglesIn; t++)
+    {
+        // this triangle belongs to a quad where the
+        // other triangle is degenerate
+        if ( (pTriInfos[t].iFlag&QUAD_ONE_DEGEN_TRI)!=0 )
+        {
+            SVec3 vDstP;
+            int iOrgF=-1, i=0;
+            tbool bNotFound;
+            unsigned char * pV = pTriInfos[t].vert_num;
+            int iFlag = (1<<pV[0]) | (1<<pV[1]) | (1<<pV[2]);
+            int iMissingIndex = 0;
+            if ((iFlag&2)==0) iMissingIndex=1;
+            else if((iFlag&4)==0) iMissingIndex=2;
+            else if((iFlag&8)==0) iMissingIndex=3;
+
+            iOrgF = pTriInfos[t].iOrgFaceNumber;
+            vDstP = GetPosition(pContext, MakeIndex(iOrgF, iMissingIndex));
+            bNotFound = TTRUE;
+            i=0;
+            while (bNotFound && i<3)
+            {
+                const int iVert = pV[i];
+                const SVec3 vSrcP = GetPosition(pContext, MakeIndex(iOrgF, iVert));
+                if (veq(vSrcP, vDstP)==TTRUE)
+                {
+                    const int iOffs = pTriInfos[t].iTSpacesOffs;
+                    psTspace[iOffs+iMissingIndex] = psTspace[iOffs+iVert];
+                    bNotFound=TFALSE;
+                }
+                else
+                    ++i;
+            }
+            assert(!bNotFound);
+        }
+    }
+}

source/graphics/ObjectBase.h

@@ -80 +80 @@
         int m_Frequency;
         VfsPath m_ModelFilename;
         VfsPath m_TextureFilename;
+        VfsPath m_NormalFilename;
+        VfsPath m_SpecularFilename;
         Decal m_Decal;
         VfsPath m_Particles;
         CStr m_Color;
@@ -91 +93 @@
     struct Variation
     {
         VfsPath texture;
+        VfsPath normal;
+        VfsPath specular;
         VfsPath model;
         Decal decal;
         VfsPath particles;

source/graphics/weldmesh.h

@@ +1 @@
+/**
+ *  Copyright (C) 2011 by Morten S. Mikkelsen
+ *
+ *  This software is provided 'as-is', without any express or implied
+ *  warranty.  In no event will the authors be held liable for any damages
+ *  arising from the use of this software.
+ *
+ *  Permission is granted to anyone to use this software for any purpose,
+ *  including commercial applications, and to alter it and redistribute it
+ *  freely, subject to the following restrictions:
+ *
+ *  1. The origin of this software must not be misrepresented; you must not
+ *     claim that you wrote the original software. If you use this software
+ *     in a product, an acknowledgment in the product documentation would be
+ *     appreciated but is not required.
+ *  2. Altered source versions must be plainly marked as such, and must not be
+ *     misrepresented as being the original software.
+ *  3. This notice may not be removed or altered from any source distribution.
+ */
+
+
+#ifndef __WELDMESH_H__
+#define __WELDMESH_H__
+
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+// piRemapTable must be initialized and point to an area in memory
+// with the byte size: iNrVerticesIn * sizeof(int).
+// pfVertexDataOut must be initialized and point to an area in memory
+// with the byte size: iNrVerticesIn * iFloatsPerVert * sizeof(float).
+// At the end of the WeldMesh() call the array pfVertexDataOut will contain
+// unique vertices only. Each entry in piRemapTable contains the index to
+// the new location of the vertex in pfVertexDataOut in units of iFloatsPerVert.
+// Note that this code is suitable for welding both unindexed meshes but also
+// indexed meshes which need to have duplicates removed. In the latter case
+// one simply uses the remap table to convert the old index list to the new vertex array.
+// Finally, the return value is the number of unique vertices found.
+int WeldMesh(int * piRemapTable, float * pfVertexDataOut,
+              const float pfVertexDataIn[], const int iNrVerticesIn, const int iFloatsPerVert);
+
+#ifdef __cplusplus
+}
+#endif
+
+
+#endif
+ No newline at end of file

source/graphics/Material.cpp

@@ -32 +32 @@
     m_DiffuseTexture = texture;
 }
 
+void CMaterial::SetNormalTexture(const CTexturePtr& texture)
+{
+    m_NormalTexture = texture;
+}
+
+void CMaterial::SetSpecularTexture(const CTexturePtr& texture)
+{
+    m_SpecularTexture = texture;
+}
+
 void CMaterial::SetShaderEffect(const CStr& effect)
 {
     m_ShaderEffect = CStrIntern(effect);

source/graphics/ObjectBase.cpp

@@ -62 +62 @@
     EL(prop);
     EL(mesh);
     EL(texture);
+    EL(normal);
+    EL(specular);
     EL(colour);
     EL(decal);
     EL(particles);
@@ -151 +153 @@
                     {
                         currentVariant->m_TextureFilename = VfsPath("art/textures/skins") / option.GetText().FromUTF8();
                     }
+                    else if (option_name == el_normal)
+                    {
+                        currentVariant->m_NormalFilename = VfsPath("art/textures/skins") / option.GetText().FromUTF8();
+                    }       
+                    else if (option_name == el_specular)
+                    {
+                        currentVariant->m_SpecularFilename = VfsPath("art/textures/skins") / option.GetText().FromUTF8();
+                    }                   
                     else if (option_name == el_decal)
                     {
                         XMBAttributeList attrs = option.GetAttributes();
@@ -399 +409 @@
         if (! var.m_TextureFilename.empty())
             variation.texture = var.m_TextureFilename;
 
+        if (! var.m_NormalFilename.empty())
+            variation.normal = var.m_NormalFilename;
+
+        if (! var.m_SpecularFilename.empty())
+            variation.specular = var.m_SpecularFilename;    
+
         if (! var.m_ModelFilename.empty())
             variation.model = var.m_ModelFilename;
 

source/graphics/ObjectEntry.cpp

@@ -61 +61 @@
     // Copy the chosen data onto this model:
 
     m_TextureName = variation.texture;
+    m_NormalName = variation.normal;
+    m_SpecularName = variation.specular;
     m_ModelName = variation.model;
 
     if (! variation.color.empty())
@@ -128 +130 @@
     texture->Prefetch(); // if we've loaded this model we're probably going to render it soon, so prefetch its texture
     model->GetMaterial().SetDiffuseTexture(texture);
 
+    CTextureProperties normalProps(m_NormalName);
+    normalProps.SetWrap(GL_CLAMP_TO_EDGE);
+    CTexturePtr normal = g_Renderer.GetTextureManager().CreateTexture(normalProps);
+    //normal->Prefetch(); // if we've loaded this model we're probably going to render it soon, so prefetch its texture
+    model->GetMaterial().SetNormalTexture(normal);
+
+    CTextureProperties specularProps(m_SpecularName);
+    specularProps.SetWrap(GL_CLAMP_TO_EDGE);
+    CTexturePtr specular = g_Renderer.GetTextureManager().CreateTexture(specularProps);
+    //specular->Prefetch(); // if we've loaded this model we're probably going to render it soon, so prefetch its texture
+    model->GetMaterial().SetSpecularTexture(specular);
+
     // calculate initial object space bounds, based on vertex positions
     model->CalcStaticObjectBounds();
 

source/renderer/RenderModifiers.h

@@ -73 +73 @@
      */
     virtual void PrepareTexture(const CShaderProgramPtr& shader, CTexture& texture) = 0;
 
+    virtual void PrepareNormal(const CShaderProgramPtr& shader, CTexture& normal) = 0;
+
+    virtual void PrepareSpecular(const CShaderProgramPtr& shader, CTexture& specular) = 0;
+
     /**
      * PrepareModel: Called before rendering the given model.
      *
@@ -134 +138 @@
     // Implementation
     void BeginPass(const CShaderProgramPtr& shader);
     void PrepareTexture(const CShaderProgramPtr& shader, CTexture& texture);
+    void PrepareNormal(const CShaderProgramPtr& shader, CTexture& normal);
+    void PrepareSpecular(const CShaderProgramPtr& shader, CTexture& specular);
     void PrepareModel(const CShaderProgramPtr& shader, CModel* model);
 
 private:
@@ -141 +147 @@
     CShaderProgram::Binding m_BindingShadingColor;
     CShaderProgram::Binding m_BindingPlayerColor;
     CShaderProgram::Binding m_BindingBaseTex;
+    CShaderProgram::Binding m_BindingNormTex;
+    CShaderProgram::Binding m_BindingSpecTex;
 };
 
 #endif // INCLUDED_RENDERMODIFIERS

source/renderer/ModelRenderer.cpp

@@ -35 +35 @@
 #include "renderer/ModelVertexRenderer.h"
 #include "renderer/Renderer.h"
 #include "renderer/RenderModifiers.h"
+#include "renderer/MikktspaceWrap.h"
 
 #include <boost/weak_ptr.hpp>
 
@@ -57 +58 @@
 #endif
 }
 
+void ModelRenderer::GenTangents(const CModelDefPtr& mdef, std::vector<float>& newVertices)
+{
+    MikkTSpace ms(mdef, newVertices);
+
+    ms.generate();
+}
+
 // Helper function to copy object-space position and normal vectors into arrays.
 void ModelRenderer::CopyPositionAndNormals(
         const CModelDefPtr& mdef,
@@ -557 +565 @@
                 m->vertexRenderer->BeginPass(streamflags);
 
                 CTexture* currentTex = NULL;
+                CTexture* currentNorm = NULL;
+                CTexture* currentSpec = NULL;
                 CModelDef* currentModeldef = NULL;
                 CShaderUniforms currentStaticUniforms;
                 // (Texture needs to be rebound after binding a new shader, so we
@@ -581 +591 @@
                             modifier->PrepareTexture(shader, *currentTex);
                         }
 
+                        CTexture* newNorm = model->GetMaterial().GetNormalTexture().get();
+                        if (newNorm != currentNorm)
+                        {
+                            currentNorm = newNorm;
+                            modifier->PrepareNormal(shader, *currentNorm);
+                        }   
+
+                        CTexture* newSpec = model->GetMaterial().GetSpecularTexture().get();
+                        if (newSpec != currentSpec)
+                        {
+                            currentSpec = newSpec;
+                            modifier->PrepareSpecular(shader, *currentSpec);
+                        }   
+
                         // Bind modeldef when it changes
                         CModelDef* newModeldef = model->GetModelDef().get();
                         if (newModeldef != currentModeldef)

source/renderer/MikktspaceWrap.h

@@ +1 @@
+#ifndef INCLUDED_MIKKWRAP
+#define INCLUDED_MIKKWRAP
+
+
+#include <graphics/mikktspace.h>
+
+class MikkTSpace
+{
+
+public:
+    
+    MikkTSpace(const CModelDefPtr& m, std::vector<float>& v);
+
+    void generate();
+    
+private:
+    
+    SMikkTSpaceInterface interface;
+    SMikkTSpaceContext context;
+
+    const CModelDefPtr& model;
+
+    std::vector<float>& newVertices;
+    
+
+    // Returns the number of faces (triangles/quads) on the mesh to be processed.
+    static int getNumFaces(const SMikkTSpaceContext *pContext);
+
+
+    // Returns the number of vertices on face number iFace
+    // iFace is a number in the range {0, 1, ..., getNumFaces()-1}
+    static int getNumVerticesOfFace(const SMikkTSpaceContext *pContext, const int iFace);
+
+
+    // returns the position/normal/texcoord of the referenced face of vertex number iVert.
+    // iVert is in the range {0,1,2} for triangles and {0,1,2,3} for quads.
+    static void getPosition(const SMikkTSpaceContext *pContext, 
+            float fvPosOut[], const int iFace, const int iVert);
+
+    static void getNormal(const SMikkTSpaceContext *pContext, 
+            float fvNormOut[], const int iFace, const int iVert);
+
+    static void getTexCoord(const SMikkTSpaceContext *pContext, 
+            float fvTexcOut[], const int iFace, const int iVert);
+
+
+    // either (or both) of the two setTSpace callbacks can be set.
+    // The call-back m_setTSpaceBasic() is sufficient for basic normal mapping.
+
+    // This function is used to return the tangent and fSign to the application.
+    // fvTangent is a unit length vector.
+    // For normal maps it is sufficient to use the following simplified version of the bitangent which is generated at pixel/vertex level.
+    // bitangent = fSign * cross(vN, tangent);
+    // Note that the results are returned unindexed. It is possible to generate a new index list
+    // But averaging/overwriting tangent spaces by using an already existing index list WILL produce INCRORRECT results.
+    // DO NOT! use an already existing index list.
+    //void setTSpaceBasic(const MikkTSpace *parent, const SMikkTSpaceContext *pContext, 
+    //      const float fvTangent[], const float fSign, const int iFace, const int iVert);
+
+
+    // This function is used to return tangent space results to the application.
+    // fvTangent and fvBiTangent are unit length vectors and fMagS and fMagT are their
+    // true magnitudes which can be used for relief mapping effects.
+    // fvBiTangent is the "real" bitangent and thus may not be perpendicular to fvTangent.
+    // However, both are perpendicular to the vertex normal.
+    // For normal maps it is sufficient to use the following simplified version of the bitangent which is generated at pixel/vertex level.
+    // fSign = bIsOrientationPreserving ? 1.0f : (-1.0f);
+    // bitangent = fSign * cross(vN, tangent);
+    // Note that the results are returned unindexed. It is possible to generate a new index list
+    // But averaging/overwriting tangent spaces by using an already existing index list WILL produce INCRORRECT results.
+    // DO NOT! use an already existing index list.
+    static void setTSpace(const SMikkTSpaceContext * pContext, const float fvTangent[], 
+            const float fvBiTangent[], const float fMagS, const float fMagT, 
+            const tbool bIsOrientationPreserving, const int iFace, const int iVert);
+
+
+};
+
+
+#endif // INCLUDED_MIKKWRAP
+ No newline at end of file

source/renderer/InstancingModelRenderer.cpp

@@ -31 +31 @@
 #include "graphics/LightEnv.h"
 #include "graphics/Model.h"
 #include "graphics/ModelDef.h"
+#include "graphics/weldmesh.h"
 
 #include "renderer/InstancingModelRenderer.h"
 #include "renderer/Renderer.h"
@@ -49 +50 @@
     /// Position, normals and UV are all static
     VertexArray::Attribute m_Position;
     VertexArray::Attribute m_Normal;
+    VertexArray::Attribute m_Tangent;
     VertexArray::Attribute m_UV;
     VertexArray::Attribute m_BlendJoints; // valid iff gpuSkinning == true
     VertexArray::Attribute m_BlendWeights; // valid iff gpuSkinning == true
@@ -76 +78 @@
     m_UV.type = GL_FLOAT;
     m_UV.elems = 2;
     m_Array.AddAttribute(&m_UV);
+    
+    m_Tangent.type = GL_FLOAT;
+    m_Tangent.elems = 4;
+    m_Array.AddAttribute(&m_Tangent);
 
     if (gpuSkinning)
     {
@@ -87 +93 @@
         m_BlendWeights.elems = 4;
         m_Array.AddAttribute(&m_BlendWeights);
     }
+    
 
-    m_Array.SetNumVertices(numVertices);
+    std::vector<float> newVertices;
+    
+    SModelVertex* vertices = mdef->GetVertices();
+    
+    ModelRenderer::GenTangents(mdef, newVertices);
+    
+    int numVertexAttrs = 3 + 3 + 2 + 4;
+    
+    int vert = newVertices.size() / numVertexAttrs;
+    
+    std::vector<int> remapTable(vert);
+    std::vector<float> vertexDataIn(vert * numVertexAttrs); 
+    std::vector<float> vertexDataOut(vert * numVertexAttrs);
+        
+    vertexDataIn = newVertices;
+
+    int numVertices2 = WeldMesh(&remapTable[0], &vertexDataOut[0],
+              &vertexDataIn[0], vert, numVertexAttrs);
+
+    m_Array.SetNumVertices(numVertices2);
     m_Array.Layout();
 
     VertexArrayIterator<CVector3D> Position = m_Position.GetIterator<CVector3D>();
     VertexArrayIterator<CVector3D> Normal = m_Normal.GetIterator<CVector3D>();
     VertexArrayIterator<float[2]> UVit = m_UV.GetIterator<float[2]>();
+    VertexArrayIterator<CVector4D> Tangent = m_Tangent.GetIterator<CVector4D>();
 
-    ModelRenderer::CopyPositionAndNormals(mdef, Position, Normal);
-    ModelRenderer::BuildUV(mdef, UVit);
+    for (int i = 0; i < numVertices2; i++)
+    {   
+        int p = remapTable[i];
+        
+        int q = numVertexAttrs * i;
+        
+        Position[i] = CVector3D(vertexDataOut[q + 0], vertexDataOut[q + 1], vertexDataOut[q + 2]);
+        
+        Normal[i] = CVector3D(vertexDataOut[q + 3], vertexDataOut[q + 4], vertexDataOut[q + 5]);
+        
+        UVit[i][0] = vertexDataOut[q + 6];
+        UVit[i][1] = vertexDataOut[q + 7];
+        
+        Tangent[i] = CVector4D(vertexDataOut[q + 8], vertexDataOut[q + 9], vertexDataOut[q + 10], 
+                       vertexDataOut[q + 11]);
+    }
 
     if (gpuSkinning)
     {
@@ -118 +159 @@
 
     m_IndexArray.SetNumVertices(mdef->GetNumFaces()*3);
     m_IndexArray.Layout();
-    ModelRenderer::BuildIndices(mdef, m_IndexArray.GetIterator());
+    
+    VertexArrayIterator<u16> Indices = m_IndexArray.GetIterator();
+    
+    size_t idxidx = 0;
+    SModelFace* faces = mdef->GetFaces();   
+
+    for (size_t j = 0; j < mdef->GetNumFaces(); ++j) {  
+        Indices[idxidx++]=remapTable[j * 3 + 0];
+        Indices[idxidx++]=remapTable[j * 3 + 1];
+        Indices[idxidx++]=remapTable[j * 3 + 2];
+    }
+    
+    
+    
     m_IndexArray.Upload();
     m_IndexArray.FreeBackingStore();
 }
@@ -211 +265 @@
     if (streamflags & STREAM_UV0)
         shader->TexCoordPointer(GL_TEXTURE0, 2, GL_FLOAT, stride, base + m->imodeldef->m_UV.offset);
 
+    shader->VertexAttribPointer("a_tangent", 4, GL_FLOAT, GL_TRUE, stride, base + m->imodeldef->m_Tangent.offset);
+
     // GPU skinning requires extra attributes to compute positions/normals
     if (m->gpuSkinning)
     {

source/renderer/RenderModifiers.cpp

@@ -104 +104 @@
     m_BindingShadingColor = shader->GetUniformBinding("shadingColor");
     m_BindingPlayerColor = shader->GetUniformBinding("playerColor");
     m_BindingBaseTex = shader->GetTextureBinding("baseTex");
+    m_BindingNormTex = shader->GetTextureBinding("normTex");
+    m_BindingSpecTex = shader->GetTextureBinding("specTex");
 }
 
 void ShaderRenderModifier::PrepareTexture(const CShaderProgramPtr& shader, CTexture& texture)
@@ -112 +114 @@
         shader->BindTexture(m_BindingBaseTex, texture.GetHandle());
 }
 
+void ShaderRenderModifier::PrepareNormal(const CShaderProgramPtr& shader, CTexture& normal)
+{
+    if (m_BindingNormTex.Active())
+        shader->BindTexture(m_BindingNormTex, normal.GetHandle());
+}
+
+void ShaderRenderModifier::PrepareSpecular(const CShaderProgramPtr& shader, CTexture& specular)
+{
+    if (m_BindingSpecTex.Active())
+        shader->BindTexture(m_BindingSpecTex, specular.GetHandle());
+}
+
 void ShaderRenderModifier::PrepareModel(const CShaderProgramPtr& shader, CModel* model)
 {
     if (m_BindingInstancingTransform.Active())

source/renderer/MikktspaceWrap.cpp

@@ +1 @@
+
+#include "precompiled.h"
+
+#include <boost/bind.hpp>
+
+#include "graphics/Color.h"
+#include "graphics/LightEnv.h"
+#include "graphics/Model.h"
+#include "graphics/ModelDef.h"
+#include "graphics/ShaderManager.h"
+#include "graphics/TextureManager.h"
+#include <graphics/mikktspace.h>
+
+#include <renderer/MikktspaceWrap.h>
+
+
+
+MikkTSpace::MikkTSpace(const CModelDefPtr& m, std::vector<float>& v) : model(m), newVertices(v)
+{   
+    interface.m_getNumFaces = getNumFaces;
+    interface.m_getNumVerticesOfFace = getNumVerticesOfFace;
+    interface.m_getPosition = getPosition;
+    interface.m_getNormal = getNormal;
+    interface.m_getTexCoord = getTexCoord;
+    interface.m_setTSpaceBasic = NULL;
+    interface.m_setTSpace = setTSpace;
+
+    context.m_pInterface = &interface;
+    context.m_pUserData = (void*)this;
+}
+
+void MikkTSpace::generate()
+{
+    genTangSpaceDefault(&context);
+}
+
+
+int MikkTSpace::getNumFaces(const SMikkTSpaceContext *pContext)
+{
+    return ((MikkTSpace*)pContext->m_pUserData)->model->GetNumFaces();
+}
+
+
+int MikkTSpace::getNumVerticesOfFace(const SMikkTSpaceContext *pContext, const int iFace)
+{
+    return 3;
+}
+
+
+void MikkTSpace::getPosition(const SMikkTSpaceContext *pContext, 
+        float fvPosOut[], const int iFace, const int iVert)
+{
+    SModelFace &face = ((MikkTSpace*)pContext->m_pUserData)->model->GetFaces()[iFace];
+    long i = face.m_Verts[iVert];
+    const CVector3D &p = ((MikkTSpace*)pContext->m_pUserData)->model->GetVertices()[i].m_Coords;
+
+    fvPosOut[0] = p.X;
+    fvPosOut[1] = p.Y;
+    fvPosOut[2] = p.Z;
+}
+
+
+void MikkTSpace::getNormal(const SMikkTSpaceContext *pContext, 
+        float fvNormOut[], const int iFace, const int iVert)
+{
+    SModelFace &face = ((MikkTSpace*)pContext->m_pUserData)->model->GetFaces()[iFace];
+    long i = face.m_Verts[iVert];
+    const CVector3D &n = ((MikkTSpace*)pContext->m_pUserData)->model->GetVertices()[i].m_Norm;
+
+    fvNormOut[0] = n.X;
+    fvNormOut[1] = n.Y;
+    fvNormOut[2] = n.Z;
+}
+
+
+void MikkTSpace::getTexCoord(const SMikkTSpaceContext *pContext, 
+        float fvTexcOut[], const int iFace, const int iVert)
+{
+    SModelFace &face = ((MikkTSpace*)pContext->m_pUserData)->model->GetFaces()[iFace];
+    long i = face.m_Verts[iVert];
+    SModelVertex &v = ((MikkTSpace*)pContext->m_pUserData)->model->GetVertices()[i];
+
+    fvTexcOut[0] = v.m_U;
+    fvTexcOut[1] = 1.0-v.m_V;       
+}
+
+
+void MikkTSpace::setTSpace(const SMikkTSpaceContext * pContext, const float fvTangent[], 
+        const float fvBiTangent[], const float fMagS, const float fMagT, 
+        const tbool bIsOrientationPreserving, const int iFace, const int iVert)
+{
+    SModelFace &face = ((MikkTSpace*)pContext->m_pUserData)->model->GetFaces()[iFace];
+    long i = face.m_Verts[iVert];
+    
+    const CVector3D &p = ((MikkTSpace*)pContext->m_pUserData)->model->GetVertices()[i].m_Coords;
+    const CVector3D &n = ((MikkTSpace*)pContext->m_pUserData)->model->GetVertices()[i].m_Norm;
+    const float u = ((MikkTSpace*)pContext->m_pUserData)->model->GetVertices()[i].m_U;
+    const float v = 1.0 - ((MikkTSpace*)pContext->m_pUserData)->model->GetVertices()[i].m_V;
+    
+    ((MikkTSpace*)pContext->m_pUserData)->newVertices.push_back(p.X);
+    ((MikkTSpace*)pContext->m_pUserData)->newVertices.push_back(p.Y);
+    ((MikkTSpace*)pContext->m_pUserData)->newVertices.push_back(p.Z);
+    
+    ((MikkTSpace*)pContext->m_pUserData)->newVertices.push_back(n.X);
+    ((MikkTSpace*)pContext->m_pUserData)->newVertices.push_back(n.Y);
+    ((MikkTSpace*)pContext->m_pUserData)->newVertices.push_back(n.Z);
+    
+    ((MikkTSpace*)pContext->m_pUserData)->newVertices.push_back(u);
+    ((MikkTSpace*)pContext->m_pUserData)->newVertices.push_back(v);
+    
+    ((MikkTSpace*)pContext->m_pUserData)->newVertices.push_back(fvTangent[0]);
+    ((MikkTSpace*)pContext->m_pUserData)->newVertices.push_back(fvTangent[1]);
+    ((MikkTSpace*)pContext->m_pUserData)->newVertices.push_back(fvTangent[2]);
+    ((MikkTSpace*)pContext->m_pUserData)->newVertices.push_back(bIsOrientationPreserving > 0.5 ? 1.0f : (-1.0f));
+}
+
+
+

source/renderer/ModelRenderer.h

@@ -253 +253 @@
     static void BuildIndices(
             const CModelDefPtr& mdef,
             const VertexArrayIterator<u16>& Indices);
+
+
+    static void GenTangents(const CModelDefPtr& mdef, std::vector<float>& newVertices);
 };
 
 

binaries/data/mods/public/art/materials/player_trans_norm.xml

@@ +1 @@
+<?xml version="1.0" encoding="utf-8"?>
+<material>
+    <shader effect="model_norm"/>
+    <define name="USE_PLAYERCOLOR" value="1"/>
+</material>

binaries/data/mods/public/art/actors/structures/romans/civic_centre.xml

@@ -15 +15 @@
         <prop actor="props/units/weapons/arrow_front.xml" attachpoint="projectile"/>
       </props>
       <texture>structural/rome_struct.png</texture>
+      <normal>structural/rome_struct_norm.png</normal>
+      <specular>structural/rome_struct_spec.png</specular>
     </variant>
   </group>
   <group>
@@ -36 +38 @@
       </props>
     </variant>
   </group>
-  <material>player_trans.xml</material>
+  <material>player_trans_norm.xml</material>
 </actor>

binaries/data/mods/public/art/actors/structures/romans/triumphal_arch.xml

@@ -5 +5 @@
     <variant frequency="100" name="Roman Triumphal Arch">
       <mesh>structural/rome_arch.dae</mesh>
       <texture>structural/rome_struct_arch.dds</texture>
+      <normal>structural/rome_struct_arch_norm.png</normal>
+      <specular>structural/rome_struct_arch_spec.png</specular>
     </variant>
   </group>
   <group>
@@ -17 +19 @@
       </props>
     </variant>
   </group>
-  <material>player_trans.xml</material>
+  <material>player_trans_norm.xml</material>
 </actor>

binaries/data/mods/public/shaders/effects/model_norm.xml

@@ +1 @@
+<?xml version="1.0" encoding="utf-8"?>
+<effect>
+
+    <technique>
+        <require context="MODE_SHADOWCAST || MODE_SILHOUETTEOCCLUDER"/>
+        <require shaders="arb"/>
+        <pass shader="arb/model_solid"/>
+    </technique>
+
+    <technique>
+        <require context="MODE_SHADOWCAST || MODE_SILHOUETTEOCCLUDER"/>
+        <require shaders="glsl"/>
+        <pass shader="glsl/model_solid"/>
+    </technique>
+
+    <technique>
+        <require context="MODE_SHADOWCAST || MODE_SILHOUETTEOCCLUDER"/>
+        <require shaders="fixed"/>
+        <define name="USE_PLAYERCOLOR" value="0"/>
+        <define name="USE_OBJECTCOLOR" value="0"/>
+        <pass shader="fixed:model_solid"/>
+    </technique>
+
+
+    <technique>
+        <require context="MODE_SILHOUETTEDISPLAY || MODE_WIREFRAME"/>
+        <require shaders="arb"/>
+        <pass shader="arb/model_solid_player"/>
+    </technique>
+
+    <technique>
+        <require context="MODE_SILHOUETTEDISPLAY || MODE_WIREFRAME"/>
+        <require shaders="glsl"/>
+        <pass shader="glsl/model_solid_player"/>
+    </technique>
+
+    <technique>
+        <require context="MODE_SILHOUETTEDISPLAY || MODE_WIREFRAME"/>
+        <require shaders="fixed"/>
+        <define name="USE_PLAYERCOLOR" value="1"/>
+        <define name="USE_OBJECTCOLOR" value="0"/>
+        <pass shader="fixed:model_solid"/>
+    </technique>
+
+
+    <technique>
+        <require shaders="arb"/>
+        <pass shader="arb/model_common"/>
+    </technique>
+
+    <technique>
+        <require shaders="glsl"/>
+        <pass shader="glsl/model_common_norm"/>
+    </technique>
+
+    <technique>
+        <require context="USE_PLAYERCOLOR || USE_OBJECTCOLOR"/>
+        <require shaders="fixed"/>
+        <pass shader="fixed:model_color"/>
+    </technique>
+
+    <technique>
+        <require shaders="fixed"/>
+        <pass shader="fixed:model"/>
+    </technique>
+
+</effect>

binaries/data/mods/public/shaders/glsl/terrain_common.fs

@@ -40 +40 @@
         vec4 size = vec4(offset + 1.0, 2.0 - offset);
         vec4 weight = (vec4(2.0 - 1.0 / size.xy, 1.0 / size.zw - 1.0) + (v_shadow.xy - offset).xyxy) * shadowScale.zwzw;
         return (1.0/9.0)*dot(size.zxzx*size.wwyy,
-          vec4(shadow2D(shadowTex, vec3(weight.zw, v_shadow.z)).a,
-               shadow2D(shadowTex, vec3(weight.xw, v_shadow.z)).a,
-               shadow2D(shadowTex, vec3(weight.zy, v_shadow.z)).a,
-               shadow2D(shadowTex, vec3(weight.xy, v_shadow.z)).a));
+          vec4(shadow2D(shadowTex, vec3(weight.zw, v_shadow.z)).r,
+               shadow2D(shadowTex, vec3(weight.xw, v_shadow.z)).r,
+               shadow2D(shadowTex, vec3(weight.zy, v_shadow.z)).r,
+               shadow2D(shadowTex, vec3(weight.xy, v_shadow.z)).r));
       #else
-        return shadow2D(shadowTex, v_shadow.xyz).a;
+        return shadow2D(shadowTex, v_shadow.xyz).r;
       #endif
     #else
       if (v_shadow.z >= 1.0)

binaries/data/mods/public/shaders/glsl/model_common_norm.vs

@@ +1 @@
+#if USE_GPU_SKINNING
+// Skinning requires GLSL 1.30 for ivec4 vertex attributes
+#version 120
+#else
+#version 140
+#endif
+
+uniform mat4 transform;
+uniform vec3 cameraPos;
+uniform vec3 sunDir;
+uniform vec3 sunColor;
+uniform vec2 losTransform;
+uniform mat4 shadowTransform;
+uniform mat4 instancingTransform;
+uniform mat4 normalMatrix;
+uniform mat4 orientation;
+
+//varying vec3 v_lighting;
+varying vec2 v_tex;
+varying vec4 v_shadow;
+varying vec2 v_los;
+
+//#if USE_SPECULAR
+  varying vec3 v_half;
+//#endif
+
+attribute vec3 a_vertex;
+attribute vec3 a_normal;
+attribute vec2 a_uv0;
+
+attribute vec4 a_tangent;
+
+
+
+#if USE_GPU_SKINNING
+  const int MAX_INFLUENCES = 4;
+  const int MAX_BONES = 64;
+  uniform mat4 skinBlendMatrices[MAX_BONES];
+  attribute ivec4 a_skinJoints;
+  attribute vec4 a_skinWeights;
+#endif
+
+varying vec4 debugx;
+
+
+
+
+varying vec3 lightVec;
+varying vec3 eyeVec;
+
+varying vec3 v_normal;
+varying vec3 v_tangent;
+varying vec3 v_bitangent;
+
+
+varying float sign;
+
+
+void main()
+{
+  #if USE_GPU_SKINNING
+    vec3 p = vec3(0.0);
+    vec3 n = vec3(0.0);
+    for (int i = 0; i < MAX_INFLUENCES; ++i) {
+      int joint = a_skinJoints[i];
+      if (joint != 0xff) {
+        mat4 m = skinBlendMatrices[joint];
+        p += vec3(m * vec4(a_vertex, 1.0)) * a_skinWeights[i];
+        n += vec3(m * vec4(a_normal, 0.0)) * a_skinWeights[i];
+      }
+    }
+    vec4 position = instancingTransform * vec4(p, 1.0);
+    vec3 normal = mat3(instancingTransform) * normalize(n);
+  #else
+  #if USE_INSTANCING
+    vec4 position = instancingTransform * vec4(a_vertex, 1.0);
+    vec3 normal = mat3(instancingTransform) * a_normal;
+    vec4 tangent = vec4(mat3(instancingTransform) * a_tangent.xyz, a_tangent.w);
+  #else
+    vec4 position = vec4(a_vertex, 1.0);
+    vec3 normal = a_normal;
+    vec4 tangent = a_tangent;    
+  #endif
+  #endif
+
+  gl_Position = transform * position;
+
+
+
+
+    eyeVec = cameraPos.xyz - position.xyz;
+    lightVec = -sunDir;
+
+
+    
+ 
+    vec3 sunVec = -sunDir;
+    
+    v_half = normalize(sunVec + eyeVec);
+
+    
+    v_normal = normal;
+    v_tangent = tangent.xyz;
+    sign = tangent.w;
+    v_bitangent = cross(v_normal, v_tangent);
+    
+
+  //v_lighting = max(0.0, dot(normal, -sunDir)) * sunColor;
+  v_tex = a_uv0;
+  v_shadow = shadowTransform * position;
+  v_los = position.xz * losTransform.x + losTransform.y;
+}

binaries/data/mods/public/shaders/glsl/model_common_norm.xml

@@ +1 @@
+<?xml version="1.0" encoding="utf-8"?>
+<program type="glsl">
+
+    <vertex file="glsl/model_common_norm.vs">
+        <stream name="pos"/>
+        <stream name="normal"/>
+        <stream name="uv0"/>    
+        <attrib name="a_vertex" semantics="gl_Vertex"/>
+        <attrib name="a_normal" semantics="gl_Normal"/>
+        <attrib name="a_uv0" semantics="gl_MultiTexCoord0"/>    
+    <attrib name="a_tangent" semantics="CustomAttribute2"/>
+    </vertex>
+
+    <fragment file="glsl/model_common_norm.fs"/>
+
+</program>

binaries/data/mods/public/shaders/glsl/model_common.fs

@@ -47 +47 @@
         vec4 size = vec4(offset + 1.0, 2.0 - offset);
         vec4 weight = (vec4(2.0 - 1.0 / size.xy, 1.0 / size.zw - 1.0) + (v_shadow.xy - offset).xyxy) * shadowScale.zwzw;
         return (1.0/9.0)*dot(size.zxzx*size.wwyy,
-          vec4(shadow2D(shadowTex, vec3(weight.zw, v_shadow.z)).a,
-               shadow2D(shadowTex, vec3(weight.xw, v_shadow.z)).a,
-               shadow2D(shadowTex, vec3(weight.zy, v_shadow.z)).a,
-               shadow2D(shadowTex, vec3(weight.xy, v_shadow.z)).a));
+          vec4(shadow2D(shadowTex, vec3(weight.zw, v_shadow.z)).r,
+               shadow2D(shadowTex, vec3(weight.xw, v_shadow.z)).r,
+               shadow2D(shadowTex, vec3(weight.zy, v_shadow.z)).r,
+               shadow2D(shadowTex, vec3(weight.xy, v_shadow.z)).r));
       #else
-        return shadow2D(shadowTex, v_shadow.xyz).a;
+        return shadow2D(shadowTex, v_shadow.xyz).r;
       #endif
     #else
       if (v_shadow.z >= 1.0)

binaries/data/mods/public/shaders/glsl/model_common_norm.fs

@@ +1 @@
+#version 120
+
+uniform sampler2D baseTex;
+uniform sampler2D normTex;
+uniform sampler2D losTex;
+uniform sampler2D specTex;
+
+#if USE_SHADOW
+  #if USE_SHADOW_SAMPLER
+    uniform sampler2DShadow shadowTex;
+  #else
+    uniform sampler2D shadowTex;
+  #endif
+#endif
+
+#if USE_OBJECTCOLOR
+  uniform vec3 objectColor;
+#else
+#if USE_PLAYERCOLOR
+  uniform vec3 playerColor;
+#endif
+#endif
+
+uniform vec3 shadingColor;
+uniform vec3 ambient;
+uniform vec4 shadowOffsets1;
+uniform vec4 shadowOffsets2;
+
+//uniform mat4 normalMatrix;
+
+//varying vec3 v_lighting;
+varying vec2 v_tex;
+varying vec4 v_shadow;
+varying vec2 v_los;
+
+uniform vec3 sunDir;
+uniform vec3 sunColor;
+
+#if USE_SPECULAR
+  uniform float specularPower;
+  uniform vec3 specularColor;
+  varying vec3 v_normal;
+#endif
+
+varying vec3 v_half;
+
+varying vec3 lightVec;  
+varying vec3 eyeVec;
+varying vec3 v_normal;
+varying vec3 v_tangent;
+varying vec3 v_bitangent;
+
+
+varying float sign;
+
+
+float get_shadow()
+{
+  #if USE_SHADOW && !DISABLE_RECEIVE_SHADOWS
+    #if USE_SHADOW_SAMPLER
+      #if USE_SHADOW_PCF
+        return 0.25 * (
+          shadow2D(shadowTex, vec3(v_shadow.xy + shadowOffsets1.xy, v_shadow.z)).r +
+          shadow2D(shadowTex, vec3(v_shadow.xy + shadowOffsets1.zw, v_shadow.z)).r +
+          shadow2D(shadowTex, vec3(v_shadow.xy + shadowOffsets2.xy, v_shadow.z)).r +
+          shadow2D(shadowTex, vec3(v_shadow.xy + shadowOffsets2.zw, v_shadow.z)).r
+        );
+      #else
+        return shadow2D(shadowTex, v_shadow.xyz).r;
+      #endif
+    #else
+      if (v_shadow.z >= 1.0)
+        return 1.0;
+      #if USE_SHADOW_PCF
+        return (
+          (v_shadow.z <= texture2D(shadowTex, v_shadow.xy + shadowOffsets1.xy).x ? 0.25 : 0.0) +
+          (v_shadow.z <= texture2D(shadowTex, v_shadow.xy + shadowOffsets1.zw).x ? 0.25 : 0.0) +
+          (v_shadow.z <= texture2D(shadowTex, v_shadow.xy + shadowOffsets2.xy).x ? 0.25 : 0.0) +
+          (v_shadow.z <= texture2D(shadowTex, v_shadow.xy + shadowOffsets2.zw).x ? 0.25 : 0.0)
+        );
+      #else
+        return (v_shadow.z <= texture2D(shadowTex, v_shadow.xy).x ? 1.0 : 0.0);
+      #endif
+    #endif
+  #else
+    return 1.0;
+  #endif
+}
+
+
+#define USE_PARALLAX      1
+#define USE_NORMAL_MAP    1
+#define USE_SPECULAR_MAP  1
+#define USE_SELF_LIGHT    1
+
+void main()
+{
+
+
+    vec3 color;
+    mat3 tbn;
+    vec2 coord = v_tex;
+
+
+#if USE_PARALLAX
+    float h = texture2D(normTex, coord).a;
+
+    tbn = transpose(mat3(v_tangent, v_bitangent * sign, v_normal));
+
+    vec3 eyeDir = normalize( tbn * eyeVec );
+    float dist = length(eyeVec);
+
+    if (dist < 65 && h < 0.99)
+    {
+
+        float scale = 0.015;
+        float height = 0.5;
+        float iter;
+        
+        float s;
+        vec2 move;
+
+        iter = (40 - (dist - 25)) / 2 + 5;
+
+        if (dist < 25) iter = 25;
+        
+
+        vec3 tangEye = -eyeDir;
+
+        iter = mix(iter * 2, iter, tangEye.z);
+        
+        s = 1.0 / iter;
+        move = vec2(-eyeDir.x, eyeDir.y) * scale / (eyeDir.z * iter);
+
+        while (h < height) 
+        {
+            height -= s;
+            coord += move;
+            h = texture2D(normTex, coord).a;
+        }
+
+    }
+#endif
+    
+
+
+    tbn = transpose(mat3(v_tangent, v_bitangent * -sign, v_normal));
+    vec3 ntex = texture2D(normTex, coord).rgb * 2.0 - 1.0;
+    vec3 vNout = normalize(ntex * tbn);
+
+
+
+#if USE_NORMAL_MAP
+    float bump = max (dot (-sunDir, vNout), 0.0) ;
+#else
+    float bump = 1.0;
+#endif
+
+
+    vec3 specular;
+#if USE_SPECULAR_MAP
+    vec4 specColour = texture2D(specTex, coord);
+    specular = bump * specColour.xyz * sunColor * pow(max(0.0, dot(normalize(vNout), v_half)), 12);
+#else
+    // if enabled, do normal specular
+    specular = vec3(0.0);
+#endif
+    
+
+    vec4 diffuse = texture2D(baseTex, coord);
+
+#if USE_TRANSPARENT
+    gl_FragColor.a = diffuse.a;
+#else
+    gl_FragColor.a = 1.0;
+#endif
+
+    vec3 texdiffuse = diffuse.rgb;
+
+    // Apply-coloring based on texture alpha
+#if USE_OBJECTCOLOR
+    texdiffuse *= mix(objectColor, vec3(1.0, 1.0, 1.0), diffuse.a);
+#else
+#if USE_PLAYERCOLOR
+    texdiffuse *= mix(playerColor, vec3(1.0, 1.0, 1.0), diffuse.a);
+#endif
+#endif
+
+
+
+
+    color = texdiffuse * bump * sunColor * get_shadow() + texdiffuse * ambient + specular;
+
+#if USE_SELF_LIGHT
+    color = mix(texdiffuse, color, specColour.a);
+#endif
+
+    
+
+
+#if !IGNORE_LOS
+    float los = texture2D(losTex, v_los).a;
+    color *= los;
+#endif
+
+  
+    gl_FragColor.rgb = color;
+}

binaries/data/config/default.cfg

@@ -58 +58 @@
 renderpath = default
 
 ; Prefer GLSL shaders over ARB shaders (not recommended)
-preferglsl = false
+preferglsl = true
 
 ; Replace alpha-blending with alpha-testing, for performance experiments
 forcealphatest = false