summaryrefslogtreecommitdiff
path: root/thirdparty
diff options
context:
space:
mode:
Diffstat (limited to 'thirdparty')
-rw-r--r--thirdparty/assimp/assimp/config.h7
-rw-r--r--thirdparty/assimp/code/Common/BaseImporter.cpp27
-rw-r--r--thirdparty/assimp/code/FBX/FBXConverter.cpp96
-rw-r--r--thirdparty/assimp/code/FBX/FBXConverter.h7
-rw-r--r--thirdparty/assimp/code/FBX/FBXDocument.cpp8
-rw-r--r--thirdparty/assimp/code/FBX/FBXExporter.cpp43
-rw-r--r--thirdparty/assimp/code/FBX/FBXImporter.cpp10
-rw-r--r--thirdparty/assimp/code/FBX/FBXMeshGeometry.cpp7
-rw-r--r--thirdparty/assimp/code/PostProcessing/CalcTangentsProcess.cpp6
-rw-r--r--thirdparty/assimp/code/PostProcessing/ScaleProcess.cpp125
-rw-r--r--thirdparty/assimp/code/PostProcessing/ScaleProcess.h13
-rw-r--r--thirdparty/assimp/contrib/utf8cpp/doc/ReleaseNotes12
-rw-r--r--thirdparty/assimp/contrib/utf8cpp/doc/utf8cpp.html1789
-rw-r--r--thirdparty/assimp/include/assimp/.editorconfig8
-rw-r--r--thirdparty/assimp/include/assimp/BaseImporter.h61
-rw-r--r--thirdparty/assimp/include/assimp/config.h.in9
-rw-r--r--thirdparty/assimp/include/assimp/irrXMLWrapper.h144
-rw-r--r--thirdparty/assimp/include/assimp/scene.h2
18 files changed, 2077 insertions, 297 deletions
diff --git a/thirdparty/assimp/assimp/config.h b/thirdparty/assimp/assimp/config.h
index 382a698268..d0e4817349 100644
--- a/thirdparty/assimp/assimp/config.h
+++ b/thirdparty/assimp/assimp/config.h
@@ -983,6 +983,13 @@ enum aiComponent {
#define AI_CONFIG_GLOBAL_SCALE_FACTOR_DEFAULT 1.0f
#endif // !! AI_DEBONE_THRESHOLD
+#define AI_CONFIG_APP_SCALE_KEY "APP_SCALE_FACTOR"
+
+#if (!defined AI_CONFIG_APP_SCALE_KEY)
+# define AI_CONFIG_APP_SCALE_KEY 1.0
+#endif // AI_CONFIG_APP_SCALE_KEY
+
+
// ---------- All the Build/Compile-time defines ------------
/** @brief Specifies if double precision is supported inside assimp
diff --git a/thirdparty/assimp/code/Common/BaseImporter.cpp b/thirdparty/assimp/code/Common/BaseImporter.cpp
index 0a5694aa0e..de5018a250 100644
--- a/thirdparty/assimp/code/Common/BaseImporter.cpp
+++ b/thirdparty/assimp/code/Common/BaseImporter.cpp
@@ -76,9 +76,25 @@ BaseImporter::~BaseImporter() {
// nothing to do here
}
+void BaseImporter::UpdateImporterScale( Importer* pImp )
+{
+ ai_assert(pImp != nullptr);
+ ai_assert(importerScale != 0.0);
+ ai_assert(fileScale != 0.0);
+
+ double activeScale = importerScale * fileScale;
+
+ // Set active scaling
+ pImp->SetPropertyFloat( AI_CONFIG_APP_SCALE_KEY, activeScale);
+
+ ASSIMP_LOG_DEBUG_F("UpdateImporterScale scale set: %f", activeScale );
+}
+
// ------------------------------------------------------------------------------------------------
// Imports the given file and returns the imported data.
-aiScene* BaseImporter::ReadFile(const Importer* pImp, const std::string& pFile, IOSystem* pIOHandler) {
+aiScene* BaseImporter::ReadFile(Importer* pImp, const std::string& pFile, IOSystem* pIOHandler) {
+
+
m_progress = pImp->GetProgressHandler();
if (nullptr == m_progress) {
return nullptr;
@@ -100,6 +116,11 @@ aiScene* BaseImporter::ReadFile(const Importer* pImp, const std::string& pFile,
{
InternReadFile( pFile, sc.get(), &filter);
+ // Calculate import scale hook - required because pImp not available anywhere else
+ // passes scale into ScaleProcess
+ UpdateImporterScale(pImp);
+
+
} catch( const std::exception& err ) {
// extract error description
m_ErrorText = err.what();
@@ -112,7 +133,7 @@ aiScene* BaseImporter::ReadFile(const Importer* pImp, const std::string& pFile,
}
// ------------------------------------------------------------------------------------------------
-void BaseImporter::SetupProperties(const Importer* /*pImp*/)
+void BaseImporter::SetupProperties(const Importer* pImp)
{
// the default implementation does nothing
}
@@ -588,6 +609,8 @@ aiScene* BatchLoader::GetImport( unsigned int which )
return nullptr;
}
+
+
// ------------------------------------------------------------------------------------------------
void BatchLoader::LoadAll()
{
diff --git a/thirdparty/assimp/code/FBX/FBXConverter.cpp b/thirdparty/assimp/code/FBX/FBXConverter.cpp
index 9f940d3226..9bd970098e 100644
--- a/thirdparty/assimp/code/FBX/FBXConverter.cpp
+++ b/thirdparty/assimp/code/FBX/FBXConverter.cpp
@@ -66,6 +66,7 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
#include <vector>
#include <sstream>
#include <iomanip>
+#include <cstdint>
namespace Assimp {
@@ -90,7 +91,6 @@ namespace Assimp {
, anim_fps()
, out(out)
, doc(doc)
- , mRemoveEmptyBones( removeEmptyBones )
, mCurrentUnit(FbxUnit::cm) {
// animations need to be converted first since this will
// populate the node_anim_chain_bits map, which is needed
@@ -119,7 +119,6 @@ namespace Assimp {
ConvertGlobalSettings();
TransferDataToScene();
- ConvertToUnitScale(unit);
// if we didn't read any meshes set the AI_SCENE_FLAGS_INCOMPLETE
// to make sure the scene passes assimp's validation. FBX files
@@ -685,30 +684,37 @@ namespace Assimp {
bool ok;
aiMatrix4x4 chain[TransformationComp_MAXIMUM];
+
+ ai_assert(TransformationComp_MAXIMUM < 32);
+ std::uint32_t chainBits = 0;
+ // A node won't need a node chain if it only has these.
+ const std::uint32_t chainMaskSimple = (1 << TransformationComp_Translation) + (1 << TransformationComp_Scaling) + (1 << TransformationComp_Rotation);
+ // A node will need a node chain if it has any of these.
+ const std::uint32_t chainMaskComplex = ((1 << (TransformationComp_MAXIMUM)) - 1) - chainMaskSimple;
+
std::fill_n(chain, static_cast<unsigned int>(TransformationComp_MAXIMUM), aiMatrix4x4());
// generate transformation matrices for all the different transformation components
const float zero_epsilon = 1e-6f;
const aiVector3D all_ones(1.0f, 1.0f, 1.0f);
- bool is_complex = false;
const aiVector3D& PreRotation = PropertyGet<aiVector3D>(props, "PreRotation", ok);
if (ok && PreRotation.SquareLength() > zero_epsilon) {
- is_complex = true;
+ chainBits = chainBits | (1 << TransformationComp_PreRotation);
GetRotationMatrix(Model::RotOrder::RotOrder_EulerXYZ, PreRotation, chain[TransformationComp_PreRotation]);
}
const aiVector3D& PostRotation = PropertyGet<aiVector3D>(props, "PostRotation", ok);
if (ok && PostRotation.SquareLength() > zero_epsilon) {
- is_complex = true;
+ chainBits = chainBits | (1 << TransformationComp_PostRotation);
GetRotationMatrix(Model::RotOrder::RotOrder_EulerXYZ, PostRotation, chain[TransformationComp_PostRotation]);
}
const aiVector3D& RotationPivot = PropertyGet<aiVector3D>(props, "RotationPivot", ok);
if (ok && RotationPivot.SquareLength() > zero_epsilon) {
- is_complex = true;
+ chainBits = chainBits | (1 << TransformationComp_RotationPivot) | (1 << TransformationComp_RotationPivotInverse);
aiMatrix4x4::Translation(RotationPivot, chain[TransformationComp_RotationPivot]);
aiMatrix4x4::Translation(-RotationPivot, chain[TransformationComp_RotationPivotInverse]);
@@ -716,21 +722,21 @@ namespace Assimp {
const aiVector3D& RotationOffset = PropertyGet<aiVector3D>(props, "RotationOffset", ok);
if (ok && RotationOffset.SquareLength() > zero_epsilon) {
- is_complex = true;
+ chainBits = chainBits | (1 << TransformationComp_RotationOffset);
aiMatrix4x4::Translation(RotationOffset, chain[TransformationComp_RotationOffset]);
}
const aiVector3D& ScalingOffset = PropertyGet<aiVector3D>(props, "ScalingOffset", ok);
if (ok && ScalingOffset.SquareLength() > zero_epsilon) {
- is_complex = true;
+ chainBits = chainBits | (1 << TransformationComp_ScalingOffset);
aiMatrix4x4::Translation(ScalingOffset, chain[TransformationComp_ScalingOffset]);
}
const aiVector3D& ScalingPivot = PropertyGet<aiVector3D>(props, "ScalingPivot", ok);
if (ok && ScalingPivot.SquareLength() > zero_epsilon) {
- is_complex = true;
+ chainBits = chainBits | (1 << TransformationComp_ScalingPivot) | (1 << TransformationComp_ScalingPivotInverse);
aiMatrix4x4::Translation(ScalingPivot, chain[TransformationComp_ScalingPivot]);
aiMatrix4x4::Translation(-ScalingPivot, chain[TransformationComp_ScalingPivotInverse]);
@@ -738,22 +744,28 @@ namespace Assimp {
const aiVector3D& Translation = PropertyGet<aiVector3D>(props, "Lcl Translation", ok);
if (ok && Translation.SquareLength() > zero_epsilon) {
+ chainBits = chainBits | (1 << TransformationComp_Translation);
+
aiMatrix4x4::Translation(Translation, chain[TransformationComp_Translation]);
}
const aiVector3D& Scaling = PropertyGet<aiVector3D>(props, "Lcl Scaling", ok);
if (ok && (Scaling - all_ones).SquareLength() > zero_epsilon) {
+ chainBits = chainBits | (1 << TransformationComp_Scaling);
+
aiMatrix4x4::Scaling(Scaling, chain[TransformationComp_Scaling]);
}
const aiVector3D& Rotation = PropertyGet<aiVector3D>(props, "Lcl Rotation", ok);
if (ok && Rotation.SquareLength() > zero_epsilon) {
+ chainBits = chainBits | (1 << TransformationComp_Rotation);
+
GetRotationMatrix(rot, Rotation, chain[TransformationComp_Rotation]);
}
const aiVector3D& GeometricScaling = PropertyGet<aiVector3D>(props, "GeometricScaling", ok);
if (ok && (GeometricScaling - all_ones).SquareLength() > zero_epsilon) {
- is_complex = true;
+ chainBits = chainBits | (1 << TransformationComp_GeometricScaling);
aiMatrix4x4::Scaling(GeometricScaling, chain[TransformationComp_GeometricScaling]);
aiVector3D GeometricScalingInverse = GeometricScaling;
bool canscale = true;
@@ -768,13 +780,14 @@ namespace Assimp {
}
}
if (canscale) {
+ chainBits = chainBits | (1 << TransformationComp_GeometricScalingInverse);
aiMatrix4x4::Scaling(GeometricScalingInverse, chain[TransformationComp_GeometricScalingInverse]);
}
}
const aiVector3D& GeometricRotation = PropertyGet<aiVector3D>(props, "GeometricRotation", ok);
if (ok && GeometricRotation.SquareLength() > zero_epsilon) {
- is_complex = true;
+ chainBits = chainBits | (1 << TransformationComp_GeometricRotation) | (1 << TransformationComp_GeometricRotationInverse);
GetRotationMatrix(rot, GeometricRotation, chain[TransformationComp_GeometricRotation]);
GetRotationMatrix(rot, GeometricRotation, chain[TransformationComp_GeometricRotationInverse]);
chain[TransformationComp_GeometricRotationInverse].Inverse();
@@ -782,7 +795,7 @@ namespace Assimp {
const aiVector3D& GeometricTranslation = PropertyGet<aiVector3D>(props, "GeometricTranslation", ok);
if (ok && GeometricTranslation.SquareLength() > zero_epsilon) {
- is_complex = true;
+ chainBits = chainBits | (1 << TransformationComp_GeometricTranslation) | (1 << TransformationComp_GeometricTranslationInverse);
aiMatrix4x4::Translation(GeometricTranslation, chain[TransformationComp_GeometricTranslation]);
aiMatrix4x4::Translation(-GeometricTranslation, chain[TransformationComp_GeometricTranslationInverse]);
}
@@ -790,12 +803,12 @@ namespace Assimp {
// is_complex needs to be consistent with NeedsComplexTransformationChain()
// or the interplay between this code and the animation converter would
// not be guaranteed.
- ai_assert(NeedsComplexTransformationChain(model) == is_complex);
+ ai_assert(NeedsComplexTransformationChain(model) == ((chainBits & chainMaskComplex) != 0));
// now, if we have more than just Translation, Scaling and Rotation,
// we need to generate a full node chain to accommodate for assimp's
// lack to express pivots and offsets.
- if (is_complex && doc.Settings().preservePivots) {
+ if ((chainBits & chainMaskComplex) && doc.Settings().preservePivots) {
FBXImporter::LogInfo("generating full transformation chain for node: " + name);
// query the anim_chain_bits dictionary to find out which chain elements
@@ -808,7 +821,7 @@ namespace Assimp {
for (size_t i = 0; i < TransformationComp_MAXIMUM; ++i, bit <<= 1) {
const TransformationComp comp = static_cast<TransformationComp>(i);
- if (chain[i].IsIdentity() && (anim_chain_bitmask & bit) == 0) {
+ if ((chainBits & bit) == 0 && (anim_chain_bitmask & bit) == 0) {
continue;
}
@@ -1462,14 +1475,8 @@ namespace Assimp {
const WeightIndexArray& indices = cluster->GetIndices();
- if (indices.empty() && mRemoveEmptyBones ) {
- continue;
- }
-
const MatIndexArray& mats = geo.GetMaterialIndices();
- bool ok = false;
-
const size_t no_index_sentinel = std::numeric_limits<size_t>::max();
count_out_indices.clear();
@@ -1509,8 +1516,7 @@ namespace Assimp {
out_indices.push_back(std::distance(outputVertStartIndices->begin(), it));
}
- ++count_out_indices.back();
- ok = true;
+ ++count_out_indices.back();
}
}
}
@@ -1518,10 +1524,8 @@ namespace Assimp {
// if we found at least one, generate the output bones
// XXX this could be heavily simplified by collecting the bone
// data in a single step.
- if (ok && mRemoveEmptyBones) {
- ConvertCluster(bones, model, *cluster, out_indices, index_out_indices,
+ ConvertCluster(bones, model, *cluster, out_indices, index_out_indices,
count_out_indices, node_global_transform);
- }
}
}
catch (std::exception&) {
@@ -3532,46 +3536,6 @@ void FBXConverter::SetShadingPropertiesRaw(aiMaterial* out_mat, const PropertyTa
out->mMetaData->Set(14, "CustomFrameRate", doc.GlobalSettings().CustomFrameRate());
}
- void FBXConverter::ConvertToUnitScale( FbxUnit unit ) {
- if (mCurrentUnit == unit) {
- return;
- }
-
- ai_real scale = 1.0;
- if (mCurrentUnit == FbxUnit::cm) {
- if (unit == FbxUnit::m) {
- scale = (ai_real)0.01;
- } else if (unit == FbxUnit::km) {
- scale = (ai_real)0.00001;
- }
- } else if (mCurrentUnit == FbxUnit::m) {
- if (unit == FbxUnit::cm) {
- scale = (ai_real)100.0;
- } else if (unit == FbxUnit::km) {
- scale = (ai_real)0.001;
- }
- } else if (mCurrentUnit == FbxUnit::km) {
- if (unit == FbxUnit::cm) {
- scale = (ai_real)100000.0;
- } else if (unit == FbxUnit::m) {
- scale = (ai_real)1000.0;
- }
- }
-
- for (auto mesh : meshes) {
- if (nullptr == mesh) {
- continue;
- }
-
- if (mesh->HasPositions()) {
- for (unsigned int i = 0; i < mesh->mNumVertices; ++i) {
- aiVector3D &pos = mesh->mVertices[i];
- pos *= scale;
- }
- }
- }
- }
-
void FBXConverter::TransferDataToScene()
{
ai_assert(!out->mMeshes);
diff --git a/thirdparty/assimp/code/FBX/FBXConverter.h b/thirdparty/assimp/code/FBX/FBXConverter.h
index 17a7bc56b7..b458627392 100644
--- a/thirdparty/assimp/code/FBX/FBXConverter.h
+++ b/thirdparty/assimp/code/FBX/FBXConverter.h
@@ -431,10 +431,6 @@ private:
void ConvertGlobalSettings();
// ------------------------------------------------------------------------------------------------
- // Will perform the conversion from a given unit to the requested unit.
- void ConvertToUnitScale(FbxUnit unit);
-
- // ------------------------------------------------------------------------------------------------
// copy generated meshes, animations, lights, cameras and textures to the output scene
void TransferDataToScene();
@@ -470,9 +466,6 @@ private:
aiScene* const out;
const FBX::Document& doc;
-
- bool mRemoveEmptyBones;
-
FbxUnit mCurrentUnit;
};
diff --git a/thirdparty/assimp/code/FBX/FBXDocument.cpp b/thirdparty/assimp/code/FBX/FBXDocument.cpp
index 1af08fe6d8..506fd978dd 100644
--- a/thirdparty/assimp/code/FBX/FBXDocument.cpp
+++ b/thirdparty/assimp/code/FBX/FBXDocument.cpp
@@ -90,14 +90,6 @@ const Object* LazyObject::Get(bool dieOnError)
return object.get();
}
- // if this is the root object, we return a dummy since there
- // is no root object int he fbx file - it is just referenced
- // with id 0.
- if(id == 0L) {
- object.reset(new Object(id, element, "Model::RootNode"));
- return object.get();
- }
-
const Token& key = element.KeyToken();
const TokenList& tokens = element.Tokens();
diff --git a/thirdparty/assimp/code/FBX/FBXExporter.cpp b/thirdparty/assimp/code/FBX/FBXExporter.cpp
index 153e676506..8ebc8555a2 100644
--- a/thirdparty/assimp/code/FBX/FBXExporter.cpp
+++ b/thirdparty/assimp/code/FBX/FBXExporter.cpp
@@ -1706,8 +1706,7 @@ void FBXExporter::WriteObjects ()
}
if (end) { break; }
}
- limbnodes.insert(parent);
- skeleton.insert(parent);
+
// if it was the skeleton root we can finish here
if (end) { break; }
}
@@ -1848,44 +1847,10 @@ void FBXExporter::WriteObjects ()
inverse_bone_xform.Inverse();
aiMatrix4x4 tr = inverse_bone_xform * mesh_xform;
- // this should be the same as the bone's mOffsetMatrix.
- // if it's not the same, the skeleton isn't in the bind pose.
- float epsilon = 1e-4f; // some error is to be expected
- float epsilon_custom = mProperties->GetPropertyFloat("BINDPOSE_EPSILON", -1);
- if(epsilon_custom > 0)
- epsilon = epsilon_custom;
- bool bone_xform_okay = true;
- if (b && ! tr.Equal(b->mOffsetMatrix, epsilon)) {
- not_in_bind_pose.insert(b);
- bone_xform_okay = false;
- }
+ sdnode.AddChild("Transform", tr);
- // if we have a bone we should use the mOffsetMatrix,
- // otherwise try to just use the calculated transform.
- if (b) {
- sdnode.AddChild("Transform", b->mOffsetMatrix);
- } else {
- sdnode.AddChild("Transform", tr);
- }
- // note: it doesn't matter if we mix these,
- // because if they disagree we'll throw an exception later.
- // it could be that the skeleton is not in the bone pose
- // but all bones are still defined,
- // in which case this would use the mOffsetMatrix for everything
- // and a correct skeleton would still be output.
-
- // transformlink should be the position of the bone in world space.
- // if the bone is in the bind pose (or nonexistent),
- // we can just use the matrix we already calculated
- if (bone_xform_okay) {
- sdnode.AddChild("TransformLink", bone_xform);
- // otherwise we can only work it out using the mesh position.
- } else {
- aiMatrix4x4 trl = b->mOffsetMatrix;
- trl.Inverse();
- trl *= mesh_xform;
- sdnode.AddChild("TransformLink", trl);
- }
+
+ sdnode.AddChild("TransformLink", bone_xform);
// note: this means we ALWAYS rely on the mesh node transform
// being unchanged from the time the skeleton was bound.
// there's not really any way around this at the moment.
diff --git a/thirdparty/assimp/code/FBX/FBXImporter.cpp b/thirdparty/assimp/code/FBX/FBXImporter.cpp
index ec8bbd2b47..bd359dbf29 100644
--- a/thirdparty/assimp/code/FBX/FBXImporter.cpp
+++ b/thirdparty/assimp/code/FBX/FBXImporter.cpp
@@ -189,8 +189,16 @@ void FBXImporter::InternReadFile( const std::string& pFile, aiScene* pScene, IOS
if (settings.convertToMeters) {
unit = FbxUnit::m;
}
+
// convert the FBX DOM to aiScene
- ConvertToAssimpScene(pScene,doc, settings.removeEmptyBones, unit);
+ ConvertToAssimpScene(pScene, doc, settings.removeEmptyBones, unit);
+
+ // size relative to cm
+ float size_relative_to_cm = doc.GlobalSettings().UnitScaleFactor();
+
+ // Set FBX file scale is relative to CM must be converted to M for
+ // assimp universal format (M)
+ SetFileScale( size_relative_to_cm * 0.01f);
std::for_each(tokens.begin(),tokens.end(),Util::delete_fun<Token>());
}
diff --git a/thirdparty/assimp/code/FBX/FBXMeshGeometry.cpp b/thirdparty/assimp/code/FBX/FBXMeshGeometry.cpp
index 44a0264ca0..5c9a0e309d 100644
--- a/thirdparty/assimp/code/FBX/FBXMeshGeometry.cpp
+++ b/thirdparty/assimp/code/FBX/FBXMeshGeometry.cpp
@@ -115,7 +115,6 @@ MeshGeometry::MeshGeometry(uint64_t id, const Element& element, const std::strin
if(tempVerts.empty()) {
FBXImporter::LogWarn("encountered mesh with no vertices");
- return;
}
std::vector<int> tempFaces;
@@ -123,7 +122,6 @@ MeshGeometry::MeshGeometry(uint64_t id, const Element& element, const std::strin
if(tempFaces.empty()) {
FBXImporter::LogWarn("encountered mesh with no faces");
- return;
}
m_vertices.reserve(tempFaces.size());
@@ -612,7 +610,10 @@ void MeshGeometry::ReadVertexDataMaterials(std::vector<int>& materials_out, cons
const std::string& ReferenceInformationType)
{
const size_t face_count = m_faces.size();
- ai_assert(face_count);
+ if(face_count <= 0)
+ {
+ return;
+ }
// materials are handled separately. First of all, they are assigned per-face
// and not per polyvert. Secondly, ReferenceInformationType=IndexToDirect
diff --git a/thirdparty/assimp/code/PostProcessing/CalcTangentsProcess.cpp b/thirdparty/assimp/code/PostProcessing/CalcTangentsProcess.cpp
index b30f39c274..a3f7dd2557 100644
--- a/thirdparty/assimp/code/PostProcessing/CalcTangentsProcess.cpp
+++ b/thirdparty/assimp/code/PostProcessing/CalcTangentsProcess.cpp
@@ -212,7 +212,7 @@ bool CalcTangentsProcess::ProcessMesh( aiMesh* pMesh, unsigned int meshIndex)
// project tangent and bitangent into the plane formed by the vertex' normal
aiVector3D localTangent = tangent - meshNorm[p] * (tangent * meshNorm[p]);
aiVector3D localBitangent = bitangent - meshNorm[p] * (bitangent * meshNorm[p]);
- localTangent.Normalize(); localBitangent.Normalize();
+ localTangent.NormalizeSafe(); localBitangent.NormalizeSafe();
// reconstruct tangent/bitangent according to normal and bitangent/tangent when it's infinite or NaN.
bool invalid_tangent = is_special_float(localTangent.x) || is_special_float(localTangent.y) || is_special_float(localTangent.z);
@@ -220,10 +220,10 @@ bool CalcTangentsProcess::ProcessMesh( aiMesh* pMesh, unsigned int meshIndex)
if (invalid_tangent != invalid_bitangent) {
if (invalid_tangent) {
localTangent = meshNorm[p] ^ localBitangent;
- localTangent.Normalize();
+ localTangent.NormalizeSafe();
} else {
localBitangent = localTangent ^ meshNorm[p];
- localBitangent.Normalize();
+ localBitangent.NormalizeSafe();
}
}
diff --git a/thirdparty/assimp/code/PostProcessing/ScaleProcess.cpp b/thirdparty/assimp/code/PostProcessing/ScaleProcess.cpp
index 6d458c4b11..ac770c41f2 100644
--- a/thirdparty/assimp/code/PostProcessing/ScaleProcess.cpp
+++ b/thirdparty/assimp/code/PostProcessing/ScaleProcess.cpp
@@ -39,19 +39,17 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
----------------------------------------------------------------------
*/
-#ifndef ASSIMP_BUILD_NO_GLOBALSCALE_PROCESS
-
#include "ScaleProcess.h"
#include <assimp/scene.h>
#include <assimp/postprocess.h>
+#include <assimp/BaseImporter.h>
namespace Assimp {
ScaleProcess::ScaleProcess()
: BaseProcess()
, mScale( AI_CONFIG_GLOBAL_SCALE_FACTOR_DEFAULT ) {
- // empty
}
ScaleProcess::~ScaleProcess() {
@@ -71,10 +69,26 @@ bool ScaleProcess::IsActive( unsigned int pFlags ) const {
}
void ScaleProcess::SetupProperties( const Importer* pImp ) {
- mScale = pImp->GetPropertyFloat( AI_CONFIG_GLOBAL_SCALE_FACTOR_KEY, 0 );
+ // User scaling
+ mScale = pImp->GetPropertyFloat( AI_CONFIG_GLOBAL_SCALE_FACTOR_KEY, 1.0f );
+
+ // File scaling * Application Scaling
+ float importerScale = pImp->GetPropertyFloat( AI_CONFIG_APP_SCALE_KEY, 1.0f );
+
+ // apply scale to the scale
+ // helps prevent bugs with backward compatibility for anyone using normal scaling.
+ mScale *= importerScale;
}
void ScaleProcess::Execute( aiScene* pScene ) {
+ if(mScale == 1.0f) {
+ return; // nothing to scale
+ }
+
+ ai_assert( mScale != 0 );
+ ai_assert( nullptr != pScene );
+ ai_assert( nullptr != pScene->mRootNode );
+
if ( nullptr == pScene ) {
return;
}
@@ -82,22 +96,113 @@ void ScaleProcess::Execute( aiScene* pScene ) {
if ( nullptr == pScene->mRootNode ) {
return;
}
+
+ // Process animations and update position transform to new unit system
+ for( unsigned int animationID = 0; animationID < pScene->mNumAnimations; animationID++ )
+ {
+ aiAnimation* animation = pScene->mAnimations[animationID];
+
+ for( unsigned int animationChannel = 0; animationChannel < animation->mNumChannels; animationChannel++)
+ {
+ aiNodeAnim* anim = animation->mChannels[animationChannel];
+
+ for( unsigned int posKey = 0; posKey < anim->mNumPositionKeys; posKey++)
+ {
+ aiVectorKey& vectorKey = anim->mPositionKeys[posKey];
+ vectorKey.mValue *= mScale;
+ }
+ }
+ }
+
+ for( unsigned int meshID = 0; meshID < pScene->mNumMeshes; meshID++)
+ {
+ aiMesh *mesh = pScene->mMeshes[meshID];
+
+ // Reconstruct mesh vertexes to the new unit system
+ for( unsigned int vertexID = 0; vertexID < mesh->mNumVertices; vertexID++)
+ {
+ aiVector3D& vertex = mesh->mVertices[vertexID];
+ vertex *= mScale;
+ }
+
+
+ // bone placement / scaling
+ for( unsigned int boneID = 0; boneID < mesh->mNumBones; boneID++)
+ {
+ // Reconstruct matrix by transform rather than by scale
+ // This prevent scale values being changed which can
+ // be meaningful in some cases
+ // like when you want the modeller to see 1:1 compatibility.
+ aiBone* bone = mesh->mBones[boneID];
+
+ aiVector3D pos, scale;
+ aiQuaternion rotation;
+
+ bone->mOffsetMatrix.Decompose( scale, rotation, pos);
+
+ aiMatrix4x4 translation;
+ aiMatrix4x4::Translation( pos * mScale, translation );
+
+ aiMatrix4x4 scaling;
+ aiMatrix4x4::Scaling( aiVector3D(scale), scaling );
+
+ aiMatrix4x4 RotMatrix = aiMatrix4x4 (rotation.GetMatrix());
+
+ bone->mOffsetMatrix = translation * RotMatrix * scaling;
+ }
+
+
+ // animation mesh processing
+ // convert by position rather than scale.
+ for( unsigned int animMeshID = 0; animMeshID < mesh->mNumAnimMeshes; animMeshID++)
+ {
+ aiAnimMesh * animMesh = mesh->mAnimMeshes[animMeshID];
+
+ for( unsigned int vertexID = 0; vertexID < animMesh->mNumVertices; vertexID++)
+ {
+ aiVector3D& vertex = animMesh->mVertices[vertexID];
+ vertex *= mScale;
+ }
+ }
+ }
traverseNodes( pScene->mRootNode );
}
-void ScaleProcess::traverseNodes( aiNode *node ) {
+void ScaleProcess::traverseNodes( aiNode *node, unsigned int nested_node_id ) {
applyScaling( node );
+
+ for( size_t i = 0; i < node->mNumChildren; i++)
+ {
+ // recurse into the tree until we are done!
+ traverseNodes( node->mChildren[i], nested_node_id+1 );
+ }
}
void ScaleProcess::applyScaling( aiNode *currentNode ) {
if ( nullptr != currentNode ) {
- currentNode->mTransformation.a1 = currentNode->mTransformation.a1 * mScale;
- currentNode->mTransformation.b2 = currentNode->mTransformation.b2 * mScale;
- currentNode->mTransformation.c3 = currentNode->mTransformation.c3 * mScale;
+ // Reconstruct matrix by transform rather than by scale
+ // This prevent scale values being changed which can
+ // be meaningful in some cases
+ // like when you want the modeller to
+ // see 1:1 compatibility.
+
+ aiVector3D pos, scale;
+ aiQuaternion rotation;
+ currentNode->mTransformation.Decompose( scale, rotation, pos);
+
+ aiMatrix4x4 translation;
+ aiMatrix4x4::Translation( pos * mScale, translation );
+
+ aiMatrix4x4 scaling;
+
+ // note: we do not use mScale here, this is on purpose.
+ aiMatrix4x4::Scaling( scale, scaling );
+
+ aiMatrix4x4 RotMatrix = aiMatrix4x4 (rotation.GetMatrix());
+
+ currentNode->mTransformation = translation * RotMatrix * scaling;
}
}
} // Namespace Assimp
-
-#endif // !! ASSIMP_BUILD_NO_GLOBALSCALE_PROCESS
diff --git a/thirdparty/assimp/code/PostProcessing/ScaleProcess.h b/thirdparty/assimp/code/PostProcessing/ScaleProcess.h
index 2567378759..468a216736 100644
--- a/thirdparty/assimp/code/PostProcessing/ScaleProcess.h
+++ b/thirdparty/assimp/code/PostProcessing/ScaleProcess.h
@@ -39,7 +39,8 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
----------------------------------------------------------------------
*/
-#pragma once
+#ifndef SCALE_PROCESS_H_
+#define SCALE_PROCESS_H_
#include "Common/BaseProcess.h"
@@ -53,6 +54,11 @@ namespace Assimp {
// ---------------------------------------------------------------------------
/** ScaleProcess: Class to rescale the whole model.
+ * Now rescales animations, bones, and blend shapes properly.
+ * Please note this will not write to 'scale' transform it will rewrite mesh
+ * and matrixes so that your scale values
+ * from your model package are preserved, so this is completely intentional
+ * bugs should be reported as soon as they are found.
*/
class ASSIMP_API ScaleProcess : public BaseProcess {
public:
@@ -78,7 +84,7 @@ public:
virtual void Execute( aiScene* pScene );
private:
- void traverseNodes( aiNode *currentNode );
+ void traverseNodes( aiNode *currentNode, unsigned int nested_node_id = 0 );
void applyScaling( aiNode *currentNode );
private:
@@ -86,3 +92,6 @@ private:
};
} // Namespace Assimp
+
+
+#endif // SCALE_PROCESS_H_ \ No newline at end of file
diff --git a/thirdparty/assimp/contrib/utf8cpp/doc/ReleaseNotes b/thirdparty/assimp/contrib/utf8cpp/doc/ReleaseNotes
new file mode 100644
index 0000000000..364411a23d
--- /dev/null
+++ b/thirdparty/assimp/contrib/utf8cpp/doc/ReleaseNotes
@@ -0,0 +1,12 @@
+utf8 cpp library
+Release 2.3.4
+
+A minor bug fix release. Thanks to all who reported bugs.
+
+Note: Version 2.3.3 contained a regression, and therefore was removed.
+
+Changes from version 2.3.2
+- Bug fix [39]: checked.h Line 273 and unchecked.h Line 182 have an extra ';'
+- Bug fix [36]: replace_invalid() only works with back_inserter
+
+Files included in the release: utf8.h, core.h, checked.h, unchecked.h, utf8cpp.html, ReleaseNotes
diff --git a/thirdparty/assimp/contrib/utf8cpp/doc/utf8cpp.html b/thirdparty/assimp/contrib/utf8cpp/doc/utf8cpp.html
new file mode 100644
index 0000000000..6f2aacbe7b
--- /dev/null
+++ b/thirdparty/assimp/contrib/utf8cpp/doc/utf8cpp.html
@@ -0,0 +1,1789 @@
+<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
+<html>
+ <head>
+ <meta name="generator" content=
+ "HTML Tidy for Linux/x86 (vers 1st November 2002), see www.w3.org">
+ <meta name="description" content=
+ "A simple, portable and lightweigt C++ library for easy handling of UTF-8 encoded strings">
+ <meta name="keywords" content="UTF-8 C++ portable utf8 unicode generic templates">
+ <meta name="author" content="Nemanja Trifunovic">
+ <title>
+ UTF8-CPP: UTF-8 with C++ in a Portable Way
+ </title>
+ <style type="text/css">
+ <!--
+ span.return_value {
+ color: brown;
+ }
+ span.keyword {
+ color: blue;
+ }
+ span.preprocessor {
+ color: navy;
+ }
+ span.literal {
+ color: olive;
+ }
+ span.comment {
+ color: green;
+ }
+ code {
+ font-weight: bold;
+ }
+ ul.toc {
+ list-style-type: none;
+ }
+ p.version {
+ font-size: small;
+ font-style: italic;
+ }
+ -->
+ </style>
+ </head>
+ <body>
+ <h1>
+ UTF8-CPP: UTF-8 with C++ in a Portable Way
+ </h1>
+ <p>
+ <a href="https://sourceforge.net/projects/utfcpp">The Sourceforge project page</a>
+ </p>
+ <div id="toc">
+ <h2>
+ Table of Contents
+ </h2>
+ <ul class="toc">
+ <li>
+ <a href="#introduction">Introduction</a>
+ </li>
+ <li>
+ <a href="#examples">Examples of Use</a>
+ <ul class="toc">
+ <li>
+ <a href=#introsample>Introductionary Sample </a>
+ </li>
+ <li>
+ <a href=#validfile>Checking if a file contains valid UTF-8 text</a>
+ </li>
+ <li>
+ <a href=#fixinvalid>Ensure that a string contains valid UTF-8 text</a>
+ </li>
+ </ul>
+ <li>
+ <a href="#reference">Reference</a>
+ <ul class="toc">
+ <li>
+ <a href="#funutf8">Functions From utf8 Namespace </a>
+ </li>
+ <li>
+ <a href="#typesutf8">Types From utf8 Namespace </a>
+ </li>
+ <li>
+ <a href="#fununchecked">Functions From utf8::unchecked Namespace </a>
+ </li>
+ <li>
+ <a href="#typesunchecked">Types From utf8::unchecked Namespace </a>
+ </li>
+ </ul>
+ </li>
+ <li>
+ <a href="#points">Points of Interest</a>
+ </li>
+ <li>
+ <a href="#links">Links</a>
+ </li>
+ </ul>
+ </div>
+ <h2 id="introduction">
+ Introduction
+ </h2>
+ <p>
+ Many C++ developers miss an easy and portable way of handling Unicode encoded
+ strings. The original C++ Standard (known as C++98 or C++03) is Unicode agnostic.
+ C++11 provides some support for Unicode on core language and library level:
+ u8, u, and U character and string literals, char16_t and char32_t character types,
+ u16string and u32string library classes, and codecvt support for conversions
+ between Unicode encoding forms.
+ In the meantime, developers use third party libraries like ICU, OS specific capabilities, or simply
+ roll out their own solutions.
+ </p>
+ <p>
+ In order to easily handle UTF-8 encoded Unicode strings, I came up with a small
+ generic library. For anybody used to work with STL algorithms and iterators, it should be
+ easy and natural to use. The code is freely available for any purpose - check out
+ the license at the beginning of the utf8.h file. If you run into
+ bugs or performance issues, please let me know and I'll do my best to address them.
+ </p>
+ <p>
+ The purpose of this article is not to offer an introduction to Unicode in general,
+ and UTF-8 in particular. If you are not familiar with Unicode, be sure to check out
+ <a href="http://www.unicode.org/">Unicode Home Page</a> or some other source of
+ information for Unicode. Also, it is not my aim to advocate the use of UTF-8
+ encoded strings in C++ programs; if you want to handle UTF-8 encoded strings from
+ C++, I am sure you have good reasons for it.
+ </p>
+ <h2 id="examples">
+ Examples of use
+ </h2>
+ <h3 id="introsample">
+ Introductionary Sample
+ </h3>
+ <p>
+ To illustrate the use of the library, let's start with a small but complete program
+ that opens a file containing UTF-8 encoded text, reads it line by line, checks each line
+ for invalid UTF-8 byte sequences, and converts it to UTF-16 encoding and back to UTF-8:
+ </p>
+<pre>
+<span class="preprocessor">#include &lt;fstream&gt;</span>
+<span class="preprocessor">#include &lt;iostream&gt;</span>
+<span class="preprocessor">#include &lt;string&gt;</span>
+<span class="preprocessor">#include &lt;vector&gt;</span>
+<span class="preprocessor">#include "utf8.h"</span>
+<span class="keyword">using namespace</span> std;
+<span class="keyword">int</span> main(<span class="keyword">int</span> argc, <span class="keyword">char</span>** argv)
+{
+ <span class="keyword">if</span> (argc != <span class="literal">2</span>) {
+ cout &lt;&lt; <span class="literal">"\nUsage: docsample filename\n"</span>;
+ <span class="keyword">return</span> <span class="literal">0</span>;
+ }
+
+ <span class="keyword">const char</span>* test_file_path = argv[1];
+ <span class="comment">// Open the test file (contains UTF-8 encoded text)</span>
+ ifstream fs8(test_file_path);
+ <span class="keyword">if</span> (!fs8.is_open()) {
+ cout &lt;&lt; <span class=
+"literal">"Could not open "</span> &lt;&lt; test_file_path &lt;&lt; endl;
+ <span class="keyword">return</span> <span class="literal">0</span>;
+ }
+
+ <span class="keyword">unsigned</span> line_count = <span class="literal">1</span>;
+ string line;
+ <span class="comment">// Play with all the lines in the file</span>
+ <span class="keyword">while</span> (getline(fs8, line)) {
+ <span class="comment">// check for invalid utf-8 (for a simple yes/no check, there is also utf8::is_valid function)</span>
+ string::iterator end_it = utf8::find_invalid(line.begin(), line.end());
+ <span class="keyword">if</span> (end_it != line.end()) {
+ cout &lt;&lt; <span class=
+"literal">"Invalid UTF-8 encoding detected at line "</span> &lt;&lt; line_count &lt;&lt; <span
+ class="literal">"\n"</span>;
+ cout &lt;&lt; <span class=
+"literal">"This part is fine: "</span> &lt;&lt; string(line.begin(), end_it) &lt;&lt; <span
+ class="literal">"\n"</span>;
+ }
+
+ <span class="comment">// Get the line length (at least for the valid part)</span>
+ <span class="keyword">int</span> length = utf8::distance(line.begin(), end_it);
+ cout &lt;&lt; <span class=
+"literal">"Length of line "</span> &lt;&lt; line_count &lt;&lt; <span class=
+"literal">" is "</span> &lt;&lt; length &lt;&lt; <span class="literal">"\n"</span>;
+
+ <span class="comment">// Convert it to utf-16</span>
+ vector&lt;unsigned short&gt; utf16line;
+ utf8::utf8to16(line.begin(), end_it, back_inserter(utf16line));
+
+ <span class="comment">// And back to utf-8</span>
+ string utf8line;
+ utf8::utf16to8(utf16line.begin(), utf16line.end(), back_inserter(utf8line));
+
+ <span class="comment">// Confirm that the conversion went OK:</span>
+ <span class="keyword">if</span> (utf8line != string(line.begin(), end_it))
+ cout &lt;&lt; <span class=
+"literal">"Error in UTF-16 conversion at line: "</span> &lt;&lt; line_count &lt;&lt; <span
+ class="literal">"\n"</span>;
+
+ line_count++;
+ }
+ <span class="keyword">return</span> <span class="literal">0</span>;
+}
+</pre>
+ <p>
+ In the previous code sample, for each line we performed
+ a detection of invalid UTF-8 sequences with <code>find_invalid</code>; the number
+ of characters (more precisely - the number of Unicode code points, including the end
+ of line and even BOM if there is one) in each line was
+ determined with a use of <code>utf8::distance</code>; finally, we have converted
+ each line to UTF-16 encoding with <code>utf8to16</code> and back to UTF-8 with
+ <code>utf16to8</code>.
+ </p>
+ <h3 id="validfile">Checking if a file contains valid UTF-8 text</h3>
+<p>
+Here is a function that checks whether the content of a file is valid UTF-8 encoded text without
+reading the content into the memory:
+</p>
+<pre>
+<span class="keyword">bool</span> valid_utf8_file(i<span class="keyword">const char</span>* file_name)
+{
+ ifstream ifs(file_name);
+ <span class="keyword">if</span> (!ifs)
+ <span class="keyword">return false</span>; <span class="comment">// even better, throw here</span>
+
+ istreambuf_iterator&lt;<span class="keyword">char</span>&gt; it(ifs.rdbuf());
+ istreambuf_iterator&lt;<span class="keyword">char</span>&gt; eos;
+
+ <span class="keyword">return</span> utf8::is_valid(it, eos);
+}
+</pre>
+<p>
+Because the function <code>utf8::is_valid()</code> works with input iterators, we were able
+to pass an <code>istreambuf_iterator</code> to it and read the content of the file directly
+without loading it to the memory first.</p>
+<p>
+Note that other functions that take input iterator arguments can be used in a similar way. For
+instance, to read the content of a UTF-8 encoded text file and convert the text to UTF-16, just
+do something like:
+</p>
+<pre>
+ utf8::utf8to16(it, eos, back_inserter(u16string));
+</pre>
+ <h3 id="fixinvalid">Ensure that a string contains valid UTF-8 text</h3>
+<p>
+If we have some text that "probably" contains UTF-8 encoded text and we want to
+replace any invalid UTF-8 sequence with a replacement character, something like
+the following function may be used:
+</p>
+<pre>
+<span class="keyword">void</span> fix_utf8_string(std::string&amp; str)
+{
+ std::string temp;
+ utf8::replace_invalid(str.begin(), str.end(), back_inserter(temp));
+ str = temp;
+}
+</pre>
+<p>The function will replace any invalid UTF-8 sequence with a Unicode replacement character.
+There is an overloaded function that enables the caller to supply their own replacement character.
+</p>
+ <h2 id="reference">
+ Reference
+ </h2>
+ <h3 id="funutf8">
+ Functions From utf8 Namespace
+ </h3>
+ <h4>
+ utf8::append
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Encodes a 32 bit code point as a UTF-8 sequence of octets and appends the sequence
+ to a UTF-8 string.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator&gt;
+octet_iterator append(uint32_t cp, octet_iterator result);
+
+</pre>
+ <p>
+ <code>octet_iterator</code>: an output iterator.<br>
+ <code>cp</code>: a 32 bit integer representing a code point to append to the
+ sequence.<br>
+ <code>result</code>: an output iterator to the place in the sequence where to
+ append the code point.<br>
+ <span class="return_value">Return value</span>: an iterator pointing to the place
+ after the newly appended sequence.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">unsigned char</span> u[<span class="literal">5</span>] = {<span
+class="literal">0</span>,<span class="literal">0</span>,<span class=
+"literal">0</span>,<span class="literal">0</span>,<span class="literal">0</span>};
+<span class="keyword">unsigned char</span>* end = append(<span class=
+"literal">0x0448</span>, u);
+assert (u[<span class="literal">0</span>] == <span class=
+"literal">0xd1</span> &amp;&amp; u[<span class="literal">1</span>] == <span class=
+"literal">0x88</span> &amp;&amp; u[<span class="literal">2</span>] == <span class=
+"literal">0</span> &amp;&amp; u[<span class="literal">3</span>] == <span class=
+"literal">0</span> &amp;&amp; u[<span class="literal">4</span>] == <span class=
+"literal">0</span>);
+</pre>
+ <p>
+ Note that <code>append</code> does not allocate any memory - it is the burden of
+ the caller to make sure there is enough memory allocated for the operation. To make
+ things more interesting, <code>append</code> can add anywhere between 1 and 4
+ octets to the sequence. In practice, you would most often want to use
+ <code>std::back_inserter</code> to ensure that the necessary memory is allocated.
+ </p>
+ <p>
+ In case of an invalid code point, a <code>utf8::invalid_code_point</code> exception
+ is thrown.
+ </p>
+ <h4>
+ utf8::next
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Given the iterator to the beginning of the UTF-8 sequence, it returns the code
+ point and moves the iterator to the next position.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator&gt;
+uint32_t next(octet_iterator&amp; it, octet_iterator end);
+
+</pre>
+ <p>
+ <code>octet_iterator</code>: an input iterator.<br>
+ <code>it</code>: a reference to an iterator pointing to the beginning of an UTF-8
+ encoded code point. After the function returns, it is incremented to point to the
+ beginning of the next code point.<br>
+ <code>end</code>: end of the UTF-8 sequence to be processed. If <code>it</code>
+ gets equal to <code>end</code> during the extraction of a code point, an
+ <code>utf8::not_enough_room</code> exception is thrown.<br>
+ <span class="return_value">Return value</span>: the 32 bit representation of the
+ processed UTF-8 code point.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">char</span>* twochars = <span class=
+"literal">"\xe6\x97\xa5\xd1\x88"</span>;
+<span class="keyword">char</span>* w = twochars;
+<span class="keyword">int</span> cp = next(w, twochars + <span class="literal">6</span>);
+assert (cp == <span class="literal">0x65e5</span>);
+assert (w == twochars + <span class="literal">3</span>);
+</pre>
+ <p>
+ This function is typically used to iterate through a UTF-8 encoded string.
+ </p>
+ <p>
+ In case of an invalid UTF-8 seqence, a <code>utf8::invalid_utf8</code> exception is
+ thrown.
+ </p>
+ <h4>
+ utf8::peek_next
+ </h4>
+ <p class="version">
+ Available in version 2.1 and later.
+ </p>
+ <p>
+ Given the iterator to the beginning of the UTF-8 sequence, it returns the code
+ point for the following sequence without changing the value of the iterator.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator&gt;
+uint32_t peek_next(octet_iterator it, octet_iterator end);
+
+</pre>
+ <p>
+ <code>octet_iterator</code>: an input iterator.<br>
+ <code>it</code>: an iterator pointing to the beginning of an UTF-8
+ encoded code point.<br>
+ <code>end</code>: end of the UTF-8 sequence to be processed. If <code>it</code>
+ gets equal to <code>end</code> during the extraction of a code point, an
+ <code>utf8::not_enough_room</code> exception is thrown.<br>
+ <span class="return_value">Return value</span>: the 32 bit representation of the
+ processed UTF-8 code point.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">char</span>* twochars = <span class=
+"literal">"\xe6\x97\xa5\xd1\x88"</span>;
+<span class="keyword">char</span>* w = twochars;
+<span class="keyword">int</span> cp = peek_next(w, twochars + <span class="literal">6</span>);
+assert (cp == <span class="literal">0x65e5</span>);
+assert (w == twochars);
+</pre>
+ <p>
+ In case of an invalid UTF-8 seqence, a <code>utf8::invalid_utf8</code> exception is
+ thrown.
+ </p>
+ <h4>
+ utf8::prior
+ </h4>
+ <p class="version">
+ Available in version 1.02 and later.
+ </p>
+ <p>
+ Given a reference to an iterator pointing to an octet in a UTF-8 sequence, it
+ decreases the iterator until it hits the beginning of the previous UTF-8 encoded
+ code point and returns the 32 bits representation of the code point.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator&gt;
+uint32_t prior(octet_iterator&amp; it, octet_iterator start);
+
+</pre>
+ <p>
+ <code>octet_iterator</code>: a bidirectional iterator.<br>
+ <code>it</code>: a reference pointing to an octet within a UTF-8 encoded string.
+ After the function returns, it is decremented to point to the beginning of the
+ previous code point.<br>
+ <code>start</code>: an iterator to the beginning of the sequence where the search
+ for the beginning of a code point is performed. It is a
+ safety measure to prevent passing the beginning of the string in the search for a
+ UTF-8 lead octet.<br>
+ <span class="return_value">Return value</span>: the 32 bit representation of the
+ previous code point.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">char</span>* twochars = <span class=
+"literal">"\xe6\x97\xa5\xd1\x88"</span>;
+<span class="keyword">unsigned char</span>* w = twochars + <span class=
+"literal">3</span>;
+<span class="keyword">int</span> cp = prior (w, twochars);
+assert (cp == <span class="literal">0x65e5</span>);
+assert (w == twochars);
+</pre>
+ <p>
+ This function has two purposes: one is two iterate backwards through a UTF-8
+ encoded string. Note that it is usually a better idea to iterate forward instead,
+ since <code>utf8::next</code> is faster. The second purpose is to find a beginning
+ of a UTF-8 sequence if we have a random position within a string. Note that in that
+ case <code>utf8::prior</code> may not detect an invalid UTF-8 sequence in some scenarios:
+ for instance if there are superfluous trail octets, it will just skip them.
+ </p>
+ <p>
+ <code>it</code> will typically point to the beginning of
+ a code point, and <code>start</code> will point to the
+ beginning of the string to ensure we don't go backwards too far. <code>it</code> is
+ decreased until it points to a lead UTF-8 octet, and then the UTF-8 sequence
+ beginning with that octet is decoded to a 32 bit representation and returned.
+ </p>
+ <p>
+ In case <code>start</code> is reached before a UTF-8 lead octet is hit, or if an
+ invalid UTF-8 sequence is started by the lead octet, an <code>invalid_utf8</code>
+ exception is thrown.
+ </p>
+ <p>In case <code>start</code> equals <code>it</code>, a <code>not_enough_room</code>
+ exception is thrown.
+ <h4>
+ utf8::previous
+ </h4>
+ <p class="version">
+ Deprecated in version 1.02 and later.
+ </p>
+ <p>
+ Given a reference to an iterator pointing to an octet in a UTF-8 seqence, it
+ decreases the iterator until it hits the beginning of the previous UTF-8 encoded
+ code point and returns the 32 bits representation of the code point.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator&gt;
+uint32_t previous(octet_iterator&amp; it, octet_iterator pass_start);
+
+</pre>
+ <p>
+ <code>octet_iterator</code>: a random access iterator.<br>
+ <code>it</code>: a reference pointing to an octet within a UTF-8 encoded string.
+ After the function returns, it is decremented to point to the beginning of the
+ previous code point.<br>
+ <code>pass_start</code>: an iterator to the point in the sequence where the search
+ for the beginning of a code point is aborted if no result was reached. It is a
+ safety measure to prevent passing the beginning of the string in the search for a
+ UTF-8 lead octet.<br>
+ <span class="return_value">Return value</span>: the 32 bit representation of the
+ previous code point.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">char</span>* twochars = <span class=
+"literal">"\xe6\x97\xa5\xd1\x88"</span>;
+<span class="keyword">unsigned char</span>* w = twochars + <span class=
+"literal">3</span>;
+<span class="keyword">int</span> cp = previous (w, twochars - <span class=
+"literal">1</span>);
+assert (cp == <span class="literal">0x65e5</span>);
+assert (w == twochars);
+</pre>
+ <p>
+ <code>utf8::previous</code> is deprecated, and <code>utf8::prior</code> should
+ be used instead, although the existing code can continue using this function.
+ The problem is the parameter <code>pass_start</code> that points to the position
+ just before the beginning of the sequence. Standard containers don't have the
+ concept of "pass start" and the function can not be used with their iterators.
+ </p>
+ <p>
+ <code>it</code> will typically point to the beginning of
+ a code point, and <code>pass_start</code> will point to the octet just before the
+ beginning of the string to ensure we don't go backwards too far. <code>it</code> is
+ decreased until it points to a lead UTF-8 octet, and then the UTF-8 sequence
+ beginning with that octet is decoded to a 32 bit representation and returned.
+ </p>
+ <p>
+ In case <code>pass_start</code> is reached before a UTF-8 lead octet is hit, or if an
+ invalid UTF-8 sequence is started by the lead octet, an <code>invalid_utf8</code>
+ exception is thrown
+ </p>
+ <h4>
+ utf8::advance
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Advances an iterator by the specified number of code points within an UTF-8
+ sequence.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator, typename distance_type&gt;
+<span class=
+"keyword">void</span> advance (octet_iterator&amp; it, distance_type n, octet_iterator end);
+
+</pre>
+ <p>
+ <code>octet_iterator</code>: an input iterator.<br>
+ <code>distance_type</code>: an integral type convertible to <code>octet_iterator</code>'s difference type.<br>
+ <code>it</code>: a reference to an iterator pointing to the beginning of an UTF-8
+ encoded code point. After the function returns, it is incremented to point to the
+ nth following code point.<br>
+ <code>n</code>: a positive integer that shows how many code points we want to
+ advance.<br>
+ <code>end</code>: end of the UTF-8 sequence to be processed. If <code>it</code>
+ gets equal to <code>end</code> during the extraction of a code point, an
+ <code>utf8::not_enough_room</code> exception is thrown.<br>
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">char</span>* twochars = <span class=
+"literal">"\xe6\x97\xa5\xd1\x88"</span>;
+<span class="keyword">unsigned char</span>* w = twochars;
+advance (w, <span class="literal">2</span>, twochars + <span class="literal">6</span>);
+assert (w == twochars + <span class="literal">5</span>);
+</pre>
+ <p>
+ This function works only "forward". In case of a negative <code>n</code>, there is
+ no effect.
+ </p>
+ <p>
+ In case of an invalid code point, a <code>utf8::invalid_code_point</code> exception
+ is thrown.
+ </p>
+ <h4>
+ utf8::distance
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Given the iterators to two UTF-8 encoded code points in a seqence, returns the
+ number of code points between them.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator&gt;
+<span class=
+"keyword">typename</span> std::iterator_traits&lt;octet_iterator&gt;::difference_type distance (octet_iterator first, octet_iterator last);
+
+</pre>
+ <p>
+ <code>octet_iterator</code>: an input iterator.<br>
+ <code>first</code>: an iterator to a beginning of a UTF-8 encoded code point.<br>
+ <code>last</code>: an iterator to a "post-end" of the last UTF-8 encoded code
+ point in the sequence we are trying to determine the length. It can be the
+ beginning of a new code point, or not.<br>
+ <span class="return_value">Return value</span> the distance between the iterators,
+ in code points.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">char</span>* twochars = <span class=
+"literal">"\xe6\x97\xa5\xd1\x88"</span>;
+size_t dist = utf8::distance(twochars, twochars + <span class="literal">5</span>);
+assert (dist == <span class="literal">2</span>);
+</pre>
+ <p>
+ This function is used to find the length (in code points) of a UTF-8 encoded
+ string. The reason it is called <em>distance</em>, rather than, say,
+ <em>length</em> is mainly because developers are used that <em>length</em> is an
+ O(1) function. Computing the length of an UTF-8 string is a linear operation, and
+ it looked better to model it after <code>std::distance</code> algorithm.
+ </p>
+ <p>
+ In case of an invalid UTF-8 seqence, a <code>utf8::invalid_utf8</code> exception is
+ thrown. If <code>last</code> does not point to the past-of-end of a UTF-8 seqence,
+ a <code>utf8::not_enough_room</code> exception is thrown.
+ </p>
+ <h4>
+ utf8::utf16to8
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Converts a UTF-16 encoded string to UTF-8.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> u16bit_iterator, <span class=
+"keyword">typename</span> octet_iterator&gt;
+octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result);
+
+</pre>
+ <p>
+ <code>u16bit_iterator</code>: an input iterator.<br>
+ <code>octet_iterator</code>: an output iterator.<br>
+ <code>start</code>: an iterator pointing to the beginning of the UTF-16 encoded
+ string to convert.<br>
+ <code>end</code>: an iterator pointing to pass-the-end of the UTF-16 encoded
+ string to convert.<br>
+ <code>result</code>: an output iterator to the place in the UTF-8 string where to
+ append the result of conversion.<br>
+ <span class="return_value">Return value</span>: An iterator pointing to the place
+ after the appended UTF-8 string.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">unsigned short</span> utf16string[] = {<span class=
+"literal">0x41</span>, <span class="literal">0x0448</span>, <span class=
+"literal">0x65e5</span>, <span class="literal">0xd834</span>, <span class=
+"literal">0xdd1e</span>};
+vector&lt;<span class="keyword">unsigned char</span>&gt; utf8result;
+utf16to8(utf16string, utf16string + <span class=
+"literal">5</span>, back_inserter(utf8result));
+assert (utf8result.size() == <span class="literal">10</span>);
+</pre>
+ <p>
+ In case of invalid UTF-16 sequence, a <code>utf8::invalid_utf16</code> exception is
+ thrown.
+ </p>
+ <h4>
+ utf8::utf8to16
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Converts an UTF-8 encoded string to UTF-16
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> u16bit_iterator, typename octet_iterator&gt;
+u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result);
+
+</pre>
+ <p>
+ <code>octet_iterator</code>: an input iterator.<br>
+ <code>u16bit_iterator</code>: an output iterator.<br>
+ <code>start</code>: an iterator pointing to the beginning of the UTF-8 encoded
+ string to convert. &lt; br /&gt; <code>end</code>: an iterator pointing to
+ pass-the-end of the UTF-8 encoded string to convert.<br>
+ <code>result</code>: an output iterator to the place in the UTF-16 string where to
+ append the result of conversion.<br>
+ <span class="return_value">Return value</span>: An iterator pointing to the place
+ after the appended UTF-16 string.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">char</span> utf8_with_surrogates[] = <span class=
+"literal">"\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e"</span>;
+vector &lt;<span class="keyword">unsigned short</span>&gt; utf16result;
+utf8to16(utf8_with_surrogates, utf8_with_surrogates + <span class=
+"literal">9</span>, back_inserter(utf16result));
+assert (utf16result.size() == <span class="literal">4</span>);
+assert (utf16result[<span class="literal">2</span>] == <span class=
+"literal">0xd834</span>);
+assert (utf16result[<span class="literal">3</span>] == <span class=
+"literal">0xdd1e</span>);
+</pre>
+ <p>
+ In case of an invalid UTF-8 seqence, a <code>utf8::invalid_utf8</code> exception is
+ thrown. If <code>end</code> does not point to the past-of-end of a UTF-8 seqence, a
+ <code>utf8::not_enough_room</code> exception is thrown.
+ </p>
+ <h4>
+ utf8::utf32to8
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Converts a UTF-32 encoded string to UTF-8.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator, typename u32bit_iterator&gt;
+octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result);
+
+</pre>
+ <p>
+ <code>octet_iterator</code>: an output iterator.<br>
+ <code>u32bit_iterator</code>: an input iterator.<br>
+ <code>start</code>: an iterator pointing to the beginning of the UTF-32 encoded
+ string to convert.<br>
+ <code>end</code>: an iterator pointing to pass-the-end of the UTF-32 encoded
+ string to convert.<br>
+ <code>result</code>: an output iterator to the place in the UTF-8 string where to
+ append the result of conversion.<br>
+ <span class="return_value">Return value</span>: An iterator pointing to the place
+ after the appended UTF-8 string.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">int</span> utf32string[] = {<span class=
+"literal">0x448</span>, <span class="literal">0x65E5</span>, <span class=
+"literal">0x10346</span>, <span class="literal">0</span>};
+vector&lt;<span class="keyword">unsigned char</span>&gt; utf8result;
+utf32to8(utf32string, utf32string + <span class=
+"literal">3</span>, back_inserter(utf8result));
+assert (utf8result.size() == <span class="literal">9</span>);
+</pre>
+ <p>
+ In case of invalid UTF-32 string, a <code>utf8::invalid_code_point</code> exception
+ is thrown.
+ </p>
+ <h4>
+ utf8::utf8to32
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Converts a UTF-8 encoded string to UTF-32.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator, <span class=
+"keyword">typename</span> u32bit_iterator&gt;
+u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result);
+
+</pre>
+ <p>
+ <code>octet_iterator</code>: an input iterator.<br>
+ <code>u32bit_iterator</code>: an output iterator.<br>
+ <code>start</code>: an iterator pointing to the beginning of the UTF-8 encoded
+ string to convert.<br>
+ <code>end</code>: an iterator pointing to pass-the-end of the UTF-8 encoded string
+ to convert.<br>
+ <code>result</code>: an output iterator to the place in the UTF-32 string where to
+ append the result of conversion.<br>
+ <span class="return_value">Return value</span>: An iterator pointing to the place
+ after the appended UTF-32 string.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">char</span>* twochars = <span class=
+"literal">"\xe6\x97\xa5\xd1\x88"</span>;
+vector&lt;<span class="keyword">int</span>&gt; utf32result;
+utf8to32(twochars, twochars + <span class=
+"literal">5</span>, back_inserter(utf32result));
+assert (utf32result.size() == <span class="literal">2</span>);
+</pre>
+ <p>
+ In case of an invalid UTF-8 seqence, a <code>utf8::invalid_utf8</code> exception is
+ thrown. If <code>end</code> does not point to the past-of-end of a UTF-8 seqence, a
+ <code>utf8::not_enough_room</code> exception is thrown.
+ </p>
+ <h4>
+ utf8::find_invalid
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Detects an invalid sequence within a UTF-8 string.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator&gt;
+octet_iterator find_invalid(octet_iterator start, octet_iterator end);
+</pre>
+ <p>
+ <code>octet_iterator</code>: an input iterator.<br>
+ <code>start</code>: an iterator pointing to the beginning of the UTF-8 string to
+ test for validity.<br>
+ <code>end</code>: an iterator pointing to pass-the-end of the UTF-8 string to test
+ for validity.<br>
+ <span class="return_value">Return value</span>: an iterator pointing to the first
+ invalid octet in the UTF-8 string. In case none were found, equals
+ <code>end</code>.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">char</span> utf_invalid[] = <span class=
+"literal">"\xe6\x97\xa5\xd1\x88\xfa"</span>;
+<span class=
+"keyword">char</span>* invalid = find_invalid(utf_invalid, utf_invalid + <span class=
+"literal">6</span>);
+assert (invalid == utf_invalid + <span class="literal">5</span>);
+</pre>
+ <p>
+ This function is typically used to make sure a UTF-8 string is valid before
+ processing it with other functions. It is especially important to call it if before
+ doing any of the <em>unchecked</em> operations on it.
+ </p>
+ <h4>
+ utf8::is_valid
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Checks whether a sequence of octets is a valid UTF-8 string.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator&gt;
+<span class="keyword">bool</span> is_valid(octet_iterator start, octet_iterator end);
+
+</pre>
+ <p>
+ <code>octet_iterator</code>: an input iterator.<br>
+ <code>start</code>: an iterator pointing to the beginning of the UTF-8 string to
+ test for validity.<br>
+ <code>end</code>: an iterator pointing to pass-the-end of the UTF-8 string to test
+ for validity.<br>
+ <span class="return_value">Return value</span>: <code>true</code> if the sequence
+ is a valid UTF-8 string; <code>false</code> if not.
+ </p>
+ Example of use:
+<pre>
+<span class="keyword">char</span> utf_invalid[] = <span class=
+"literal">"\xe6\x97\xa5\xd1\x88\xfa"</span>;
+<span class="keyword">bool</span> bvalid = is_valid(utf_invalid, utf_invalid + <span
+class="literal">6</span>);
+assert (bvalid == false);
+</pre>
+ <p>
+ <code>is_valid</code> is a shorthand for <code>find_invalid(start, end) ==
+ end;</code>. You may want to use it to make sure that a byte seqence is a valid
+ UTF-8 string without the need to know where it fails if it is not valid.
+ </p>
+ <h4>
+ utf8::replace_invalid
+ </h4>
+ <p class="version">
+ Available in version 2.0 and later.
+ </p>
+ <p>
+ Replaces all invalid UTF-8 sequences within a string with a replacement marker.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator, <span class=
+"keyword">typename</span> output_iterator&gt;
+output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out, uint32_t replacement);
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator, <span class=
+"keyword">typename</span> output_iterator&gt;
+output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out);
+
+</pre>
+ <p>
+ <code>octet_iterator</code>: an input iterator.<br>
+ <code>output_iterator</code>: an output iterator.<br>
+ <code>start</code>: an iterator pointing to the beginning of the UTF-8 string to
+ look for invalid UTF-8 sequences.<br>
+ <code>end</code>: an iterator pointing to pass-the-end of the UTF-8 string to look
+ for invalid UTF-8 sequences.<br>
+ <code>out</code>: An output iterator to the range where the result of replacement
+ is stored.<br>
+ <code>replacement</code>: A Unicode code point for the replacement marker. The
+ version without this parameter assumes the value <code>0xfffd</code><br>
+ <span class="return_value">Return value</span>: An iterator pointing to the place
+ after the UTF-8 string with replaced invalid sequences.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">char</span> invalid_sequence[] = <span class=
+"literal">"a\x80\xe0\xa0\xc0\xaf\xed\xa0\x80z"</span>;
+vector&lt;<span class="keyword">char</span>&gt; replace_invalid_result;
+replace_invalid (invalid_sequence, invalid_sequence + sizeof(invalid_sequence), back_inserter(replace_invalid_result), <span
+ class="literal">'?'</span>);
+bvalid = is_valid(replace_invalid_result.begin(), replace_invalid_result.end());
+assert (bvalid);
+<span class="keyword">char</span>* fixed_invalid_sequence = <span class=
+"literal">"a????z"</span>;
+assert (std::equal(replace_invalid_result.begin(), replace_invalid_result.end(), fixed_invalid_sequence));
+</pre>
+ <p>
+ <code>replace_invalid</code> does not perform in-place replacement of invalid
+ sequences. Rather, it produces a copy of the original string with the invalid
+ sequences replaced with a replacement marker. Therefore, <code>out</code> must not
+ be in the <code>[start, end]</code> range.
+ </p>
+ <p>
+ If <code>end</code> does not point to the past-of-end of a UTF-8 sequence, a
+ <code>utf8::not_enough_room</code> exception is thrown.
+ </p>
+ <h4>
+ utf8::starts_with_bom
+ </h4>
+ <p class="version">
+ Available in version 2.3 and later. Relaces deprecated <code>is_bom()</code> function.
+ </p>
+ <p>
+ Checks whether an octet sequence starts with a UTF-8 byte order mark (BOM)
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator&gt;
+<span class="keyword">bool</span> starts_with_bom (octet_iterator it, octet_iterator end);
+</pre>
+ <p>
+ <code>octet_iterator</code>: an input iterator.<br>
+ <code>it</code>: beginning of the octet sequence to check<br>
+ <code>end</code>: pass-end of the sequence to check<br>
+ <span class="return_value">Return value</span>: <code>true</code> if the sequence
+ starts with a UTF-8 byte order mark; <code>false</code> if not.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">unsigned char</span> byte_order_mark[] = {<span class=
+"literal">0xef</span>, <span class="literal">0xbb</span>, <span class=
+"literal">0xbf</span>};
+<span class="keyword">bool</span> bbom = starts_with_bom(byte_order_mark, byte_order_mark + <span class="keyword">sizeof</span>(byte_order_mark));
+assert (bbom == <span class="literal">true</span>);
+</pre>
+ <p>
+ The typical use of this function is to check the first three bytes of a file. If
+ they form the UTF-8 BOM, we want to skip them before processing the actual UTF-8
+ encoded text.
+ </p>
+ <h4>
+ utf8::is_bom
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later. Deprecated in version 2.3. <code>starts_with_bom()</code> should be used
+ instead.
+ </p>
+ <p>
+ Checks whether a sequence of three octets is a UTF-8 byte order mark (BOM)
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator&gt;
+<span class="keyword">bool</span> is_bom (octet_iterator it); <span class="comment"> // Deprecated</span>
+</pre>
+ <p>
+ <code>octet_iterator</code>: an input iterator.<br>
+ <code>it</code>: beginning of the 3-octet sequence to check<br>
+ <span class="return_value">Return value</span>: <code>true</code> if the sequence
+ is UTF-8 byte order mark; <code>false</code> if not.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">unsigned char</span> byte_order_mark[] = {<span class=
+"literal">0xef</span>, <span class="literal">0xbb</span>, <span class=
+"literal">0xbf</span>};
+<span class="keyword">bool</span> bbom = is_bom(byte_order_mark);
+assert (bbom == <span class="literal">true</span>);
+</pre>
+ <p>
+ The typical use of this function is to check the first three bytes of a file. If
+ they form the UTF-8 BOM, we want to skip them before processing the actual UTF-8
+ encoded text.
+ </p>
+ <p>
+ If a sequence is
+ shorter than three bytes, an invalid iterator will be dereferenced. Therefore, this function is deprecated
+ in favor of <code>starts_with_bom()</code>that takes the end of sequence as an argument.
+ </p>
+ <h3 id="typesutf8">
+ Types From utf8 Namespace
+ </h3>
+ <h4>utf8::exception
+ </h4>
+ <p class="version">
+ Available in version 2.3 and later.
+ </p>
+ <p>
+ Base class for the exceptions thrown by UTF CPP library functions.
+ </p>
+<pre>
+<span class="keyword">class</span> exception : <span class="keyword">public</span> std::exception {};
+</pre>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">try</span> {
+ code_that_uses_utf_cpp_library();
+}
+<span class="keyword">catch</span>(<span class="keyword">const</span> utf8::exception&amp; utfcpp_ex) {
+ cerr &lt;&lt; utfcpp_ex.what();
+}
+</pre>
+
+ <h4>utf8::invalid_code_point
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Thrown by UTF8 CPP functions such as <code>advance</code> and <code>next</code> if an UTF-8 sequence represents and invalid code point.
+ </p>
+
+<pre>
+<span class="keyword">class</span> invalid_code_point : <span class="keyword">public</span> exception {
+<span class="keyword">public</span>:
+ uint32_t code_point() <span class="keyword">const</span>;
+};
+
+</pre>
+ <p>
+ Member function <code>code_point()</code> can be used to determine the invalid code point that
+ caused the exception to be thrown.
+ </p>
+ <h4>utf8::invalid_utf8
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Thrown by UTF8 CPP functions such as <code>next</code> and <code>prior</code> if an invalid UTF-8 sequence
+ is detected during decoding.
+ </p>
+
+<pre>
+<span class="keyword">class</span> invalid_utf8 : <span class="keyword">public</span> exception {
+<span class="keyword">public</span>:
+ uint8_t utf8_octet() <span class="keyword">const</span>;
+};
+</pre>
+
+ <p>
+ Member function <code>utf8_octet()</code> can be used to determine the beginning of the byte
+ sequence that caused the exception to be thrown.
+ </p>
+</pre>
+ <h4>utf8::invalid_utf16
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Thrown by UTF8 CPP function <code>utf16to8</code> if an invalid UTF-16 sequence
+ is detected during decoding.
+ </p>
+
+<pre>
+<span class="keyword">class</span> invalid_utf16 : <span class="keyword">public</span> exception {
+<span class="keyword">public</span>:
+ uint16_t utf16_word() <span class="keyword">const</span>;
+};
+</pre>
+
+ <p>
+ Member function <code>utf16_word()</code> can be used to determine the UTF-16 code unit
+ that caused the exception to be thrown.
+ </p>
+ <h4>utf8::not_enough_room
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Thrown by UTF8 CPP functions such as <code>next</code> if the end of the decoded UTF-8 sequence
+ was reached before the code point was decoded.
+ </p>
+
+<pre>
+<span class="keyword">class</span> not_enough_room : <span class="keyword">public</span> exception {};
+</pre>
+ <h4>
+ utf8::iterator
+ </h4>
+ <p class="version">
+ Available in version 2.0 and later.
+ </p>
+ <p>
+ Adapts the underlying octet iterator to iterate over the sequence of code points,
+ rather than raw octets.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class="keyword">typename</span> octet_iterator&gt;
+<span class="keyword">class</span> iterator;
+</pre>
+
+ <h5>Member functions</h5>
+ <dl>
+ <dt><code>iterator();</code> <dd> the deafult constructor; the underlying <code>octet_iterator</code> is
+ constructed with its default constructor.
+ <dt><code><span class="keyword">explicit</span> iterator (const octet_iterator&amp; octet_it,
+ const octet_iterator&amp; range_start,
+ const octet_iterator&amp; range_end);</code> <dd> a constructor
+ that initializes the underlying <code>octet_iterator</code> with <code>octet_it</code>
+ and sets the range in which the iterator is considered valid.
+ <dt><code>octet_iterator base () <span class="keyword">const</span>;</code> <dd> returns the
+ underlying <code>octet_iterator</code>.
+ <dt><code>uint32_t operator * () <span class="keyword">const</span>;</code> <dd> decodes the utf-8 sequence
+ the underlying <code>octet_iterator</code> is pointing to and returns the code point.
+ <dt><code><span class="keyword">bool operator</span> == (const iterator&amp; rhs)
+ <span class="keyword">const</span>;</code> <dd> returns <span class="keyword">true</span>
+ if the two underlaying iterators are equal.
+ <dt><code><span class="keyword">bool operator</span> != (const iterator&amp; rhs)
+ <span class="keyword">const</span>;</code> <dd> returns <span class="keyword">true</span>
+ if the two underlaying iterators are not equal.
+ <dt><code>iterator&amp; <span class="keyword">operator</span> ++ (); </code> <dd> the prefix increment - moves
+ the iterator to the next UTF-8 encoded code point.
+ <dt><code>iterator <span class="keyword">operator</span> ++ (<span class="keyword">int</span>); </code> <dd>
+ the postfix increment - moves the iterator to the next UTF-8 encoded code point and returns the current one.
+ <dt><code>iterator&amp; <span class="keyword">operator</span> -- (); </code> <dd> the prefix decrement - moves
+ the iterator to the previous UTF-8 encoded code point.
+ <dt><code>iterator <span class="keyword">operator</span> -- (<span class="keyword">int</span>); </code> <dd>
+ the postfix decrement - moves the iterator to the previous UTF-8 encoded code point and returns the current one.
+ </dl>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">char</span>* threechars = <span class="literal">"\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88"</span>;
+utf8::iterator&lt;<span class="keyword">char</span>*&gt; it(threechars, threechars, threechars + <span class="literal">9</span>);
+utf8::iterator&lt;<span class="keyword">char</span>*&gt; it2 = it;
+assert (it2 == it);
+assert (*it == <span class="literal">0x10346</span>);
+assert (*(++it) == <span class="literal">0x65e5</span>);
+assert ((*it++) == <span class="literal">0x65e5</span>);
+assert (*it == <span class="literal">0x0448</span>);
+assert (it != it2);
+utf8::iterator&lt;<span class="keyword">char</span>*&gt; endit (threechars + <span class="literal">9</span>, threechars, threechars + <span class="literal">9</span>);
+assert (++it == endit);
+assert (*(--it) == <span class="literal">0x0448</span>);
+assert ((*it--) == <span class="literal">0x0448</span>);
+assert (*it == <span class="literal">0x65e5</span>);
+assert (--it == utf8::iterator&lt;<span class="keyword">char</span>*&gt;(threechars, threechars, threechars + <span class="literal">9</span>));
+assert (*it == <span class="literal">0x10346</span>);
+</pre>
+ <p>
+ The purpose of <code>utf8::iterator</code> adapter is to enable easy iteration as well as the use of STL
+ algorithms with UTF-8 encoded strings. Increment and decrement operators are implemented in terms of
+ <code>utf8::next()</code> and <code>utf8::prior()</code> functions.
+ </p>
+ <p>
+ Note that <code>utf8::iterator</code> adapter is a checked iterator. It operates on the range specified in
+ the constructor; any attempt to go out of that range will result in an exception. Even the comparison operators
+ require both iterator object to be constructed against the same range - otherwise an exception is thrown. Typically,
+ the range will be determined by sequence container functions <code>begin</code> and <code>end</code>, i.e.:
+ </p>
+<pre>
+std::string s = <span class="literal">"example"</span>;
+utf8::iterator i (s.begin(), s.begin(), s.end());
+</pre>
+ <h3 id="fununchecked">
+ Functions From utf8::unchecked Namespace
+ </h3>
+ <h4>
+ utf8::unchecked::append
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Encodes a 32 bit code point as a UTF-8 sequence of octets and appends the sequence
+ to a UTF-8 string.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator&gt;
+octet_iterator append(uint32_t cp, octet_iterator result);
+
+</pre>
+ <p>
+ <code>cp</code>: A 32 bit integer representing a code point to append to the
+ sequence.<br>
+ <code>result</code>: An output iterator to the place in the sequence where to
+ append the code point.<br>
+ <span class="return_value">Return value</span>: An iterator pointing to the place
+ after the newly appended sequence.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">unsigned char</span> u[<span class="literal">5</span>] = {<span
+class="literal">0</span>,<span class="literal">0</span>,<span class=
+"literal">0</span>,<span class="literal">0</span>,<span class="literal">0</span>};
+<span class="keyword">unsigned char</span>* end = unchecked::append(<span class=
+"literal">0x0448</span>, u);
+assert (u[<span class="literal">0</span>] == <span class=
+"literal">0xd1</span> &amp;&amp; u[<span class="literal">1</span>] == <span class=
+"literal">0x88</span> &amp;&amp; u[<span class="literal">2</span>] == <span class=
+"literal">0</span> &amp;&amp; u[<span class="literal">3</span>] == <span class=
+"literal">0</span> &amp;&amp; u[<span class="literal">4</span>] == <span class=
+"literal">0</span>);
+</pre>
+ <p>
+ This is a faster but less safe version of <code>utf8::append</code>. It does not
+ check for validity of the supplied code point, and may produce an invalid UTF-8
+ sequence.
+ </p>
+ <h4>
+ utf8::unchecked::next
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Given the iterator to the beginning of a UTF-8 sequence, it returns the code point
+ and moves the iterator to the next position.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator&gt;
+uint32_t next(octet_iterator&amp; it);
+
+</pre>
+ <p>
+ <code>it</code>: a reference to an iterator pointing to the beginning of an UTF-8
+ encoded code point. After the function returns, it is incremented to point to the
+ beginning of the next code point.<br>
+ <span class="return_value">Return value</span>: the 32 bit representation of the
+ processed UTF-8 code point.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">char</span>* twochars = <span class=
+"literal">"\xe6\x97\xa5\xd1\x88"</span>;
+<span class="keyword">char</span>* w = twochars;
+<span class="keyword">int</span> cp = unchecked::next(w);
+assert (cp == <span class="literal">0x65e5</span>);
+assert (w == twochars + <span class="literal">3</span>);
+</pre>
+ <p>
+ This is a faster but less safe version of <code>utf8::next</code>. It does not
+ check for validity of the supplied UTF-8 sequence.
+ </p>
+ <h4>
+ utf8::unchecked::peek_next
+ </h4>
+ <p class="version">
+ Available in version 2.1 and later.
+ </p>
+ <p>
+ Given the iterator to the beginning of a UTF-8 sequence, it returns the code point.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator&gt;
+uint32_t peek_next(octet_iterator it);
+
+</pre>
+ <p>
+ <code>it</code>: an iterator pointing to the beginning of an UTF-8
+ encoded code point.<br>
+ <span class="return_value">Return value</span>: the 32 bit representation of the
+ processed UTF-8 code point.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">char</span>* twochars = <span class=
+"literal">"\xe6\x97\xa5\xd1\x88"</span>;
+<span class="keyword">char</span>* w = twochars;
+<span class="keyword">int</span> cp = unchecked::peek_next(w);
+assert (cp == <span class="literal">0x65e5</span>);
+assert (w == twochars);
+</pre>
+ <p>
+ This is a faster but less safe version of <code>utf8::peek_next</code>. It does not
+ check for validity of the supplied UTF-8 sequence.
+ </p>
+ <h4>
+ utf8::unchecked::prior
+ </h4>
+ <p class="version">
+ Available in version 1.02 and later.
+ </p>
+ <p>
+ Given a reference to an iterator pointing to an octet in a UTF-8 seqence, it
+ decreases the iterator until it hits the beginning of the previous UTF-8 encoded
+ code point and returns the 32 bits representation of the code point.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator&gt;
+uint32_t prior(octet_iterator&amp; it);
+
+</pre>
+ <p>
+ <code>it</code>: a reference pointing to an octet within a UTF-8 encoded string.
+ After the function returns, it is decremented to point to the beginning of the
+ previous code point.<br>
+ <span class="return_value">Return value</span>: the 32 bit representation of the
+ previous code point.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">char</span>* twochars = <span class=
+"literal">"\xe6\x97\xa5\xd1\x88"</span>;
+<span class="keyword">char</span>* w = twochars + <span class="literal">3</span>;
+<span class="keyword">int</span> cp = unchecked::prior (w);
+assert (cp == <span class="literal">0x65e5</span>);
+assert (w == twochars);
+</pre>
+ <p>
+ This is a faster but less safe version of <code>utf8::prior</code>. It does not
+ check for validity of the supplied UTF-8 sequence and offers no boundary checking.
+ </p>
+ <h4>
+ utf8::unchecked::previous (deprecated, see utf8::unchecked::prior)
+ </h4>
+ <p class="version">
+ Deprecated in version 1.02 and later.
+ </p>
+ <p>
+ Given a reference to an iterator pointing to an octet in a UTF-8 seqence, it
+ decreases the iterator until it hits the beginning of the previous UTF-8 encoded
+ code point and returns the 32 bits representation of the code point.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator&gt;
+uint32_t previous(octet_iterator&amp; it);
+
+</pre>
+ <p>
+ <code>it</code>: a reference pointing to an octet within a UTF-8 encoded string.
+ After the function returns, it is decremented to point to the beginning of the
+ previous code point.<br>
+ <span class="return_value">Return value</span>: the 32 bit representation of the
+ previous code point.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">char</span>* twochars = <span class=
+"literal">"\xe6\x97\xa5\xd1\x88"</span>;
+<span class="keyword">char</span>* w = twochars + <span class="literal">3</span>;
+<span class="keyword">int</span> cp = unchecked::previous (w);
+assert (cp == <span class="literal">0x65e5</span>);
+assert (w == twochars);
+</pre>
+ <p>
+ The reason this function is deprecated is just the consistency with the "checked"
+ versions, where <code>prior</code> should be used instead of <code>previous</code>.
+ In fact, <code>unchecked::previous</code> behaves exactly the same as <code>
+ unchecked::prior</code>
+ </p>
+ <p>
+ This is a faster but less safe version of <code>utf8::previous</code>. It does not
+ check for validity of the supplied UTF-8 sequence and offers no boundary checking.
+ </p>
+ <h4>
+ utf8::unchecked::advance
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Advances an iterator by the specified number of code points within an UTF-8
+ sequence.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator, typename distance_type&gt;
+<span class="keyword">void</span> advance (octet_iterator&amp; it, distance_type n);
+
+</pre>
+ <p>
+ <code>it</code>: a reference to an iterator pointing to the beginning of an UTF-8
+ encoded code point. After the function returns, it is incremented to point to the
+ nth following code point.<br>
+ <code>n</code>: a positive integer that shows how many code points we want to
+ advance.<br>
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">char</span>* twochars = <span class=
+"literal">"\xe6\x97\xa5\xd1\x88"</span>;
+<span class="keyword">char</span>* w = twochars;
+unchecked::advance (w, <span class="literal">2</span>);
+assert (w == twochars + <span class="literal">5</span>);
+</pre>
+ <p>
+ This function works only "forward". In case of a negative <code>n</code>, there is
+ no effect.
+ </p>
+ <p>
+ This is a faster but less safe version of <code>utf8::advance</code>. It does not
+ check for validity of the supplied UTF-8 sequence and offers no boundary checking.
+ </p>
+ <h4>
+ utf8::unchecked::distance
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Given the iterators to two UTF-8 encoded code points in a seqence, returns the
+ number of code points between them.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator&gt;
+<span class=
+"keyword">typename</span> std::iterator_traits&lt;octet_iterator&gt;::difference_type distance (octet_iterator first, octet_iterator last);
+</pre>
+ <p>
+ <code>first</code>: an iterator to a beginning of a UTF-8 encoded code point.<br>
+ <code>last</code>: an iterator to a "post-end" of the last UTF-8 encoded code
+ point in the sequence we are trying to determine the length. It can be the
+ beginning of a new code point, or not.<br>
+ <span class="return_value">Return value</span> the distance between the iterators,
+ in code points.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">char</span>* twochars = <span class=
+"literal">"\xe6\x97\xa5\xd1\x88"</span>;
+size_t dist = utf8::unchecked::distance(twochars, twochars + <span class=
+"literal">5</span>);
+assert (dist == <span class="literal">2</span>);
+</pre>
+ <p>
+ This is a faster but less safe version of <code>utf8::distance</code>. It does not
+ check for validity of the supplied UTF-8 sequence.
+ </p>
+ <h4>
+ utf8::unchecked::utf16to8
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Converts a UTF-16 encoded string to UTF-8.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> u16bit_iterator, <span class=
+"keyword">typename</span> octet_iterator&gt;
+octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result);
+
+</pre>
+ <p>
+ <code>start</code>: an iterator pointing to the beginning of the UTF-16 encoded
+ string to convert.<br>
+ <code>end</code>: an iterator pointing to pass-the-end of the UTF-16 encoded
+ string to convert.<br>
+ <code>result</code>: an output iterator to the place in the UTF-8 string where to
+ append the result of conversion.<br>
+ <span class="return_value">Return value</span>: An iterator pointing to the place
+ after the appended UTF-8 string.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">unsigned short</span> utf16string[] = {<span class=
+"literal">0x41</span>, <span class="literal">0x0448</span>, <span class=
+"literal">0x65e5</span>, <span class="literal">0xd834</span>, <span class=
+"literal">0xdd1e</span>};
+vector&lt;<span class="keyword">unsigned char</span>&gt; utf8result;
+unchecked::utf16to8(utf16string, utf16string + <span class=
+"literal">5</span>, back_inserter(utf8result));
+assert (utf8result.size() == <span class="literal">10</span>);
+</pre>
+ <p>
+ This is a faster but less safe version of <code>utf8::utf16to8</code>. It does not
+ check for validity of the supplied UTF-16 sequence.
+ </p>
+ <h4>
+ utf8::unchecked::utf8to16
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Converts an UTF-8 encoded string to UTF-16
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> u16bit_iterator, typename octet_iterator&gt;
+u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result);
+
+</pre>
+ <p>
+ <code>start</code>: an iterator pointing to the beginning of the UTF-8 encoded
+ string to convert. &lt; br /&gt; <code>end</code>: an iterator pointing to
+ pass-the-end of the UTF-8 encoded string to convert.<br>
+ <code>result</code>: an output iterator to the place in the UTF-16 string where to
+ append the result of conversion.<br>
+ <span class="return_value">Return value</span>: An iterator pointing to the place
+ after the appended UTF-16 string.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">char</span> utf8_with_surrogates[] = <span class=
+"literal">"\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e"</span>;
+vector &lt;<span class="keyword">unsigned short</span>&gt; utf16result;
+unchecked::utf8to16(utf8_with_surrogates, utf8_with_surrogates + <span class=
+"literal">9</span>, back_inserter(utf16result));
+assert (utf16result.size() == <span class="literal">4</span>);
+assert (utf16result[<span class="literal">2</span>] == <span class=
+"literal">0xd834</span>);
+assert (utf16result[<span class="literal">3</span>] == <span class=
+"literal">0xdd1e</span>);
+</pre>
+ <p>
+ This is a faster but less safe version of <code>utf8::utf8to16</code>. It does not
+ check for validity of the supplied UTF-8 sequence.
+ </p>
+ <h4>
+ utf8::unchecked::utf32to8
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Converts a UTF-32 encoded string to UTF-8.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator, <span class=
+"keyword">typename</span> u32bit_iterator&gt;
+octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result);
+
+</pre>
+ <p>
+ <code>start</code>: an iterator pointing to the beginning of the UTF-32 encoded
+ string to convert.<br>
+ <code>end</code>: an iterator pointing to pass-the-end of the UTF-32 encoded
+ string to convert.<br>
+ <code>result</code>: an output iterator to the place in the UTF-8 string where to
+ append the result of conversion.<br>
+ <span class="return_value">Return value</span>: An iterator pointing to the place
+ after the appended UTF-8 string.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">int</span> utf32string[] = {<span class=
+"literal">0x448</span>, <span class="literal">0x65e5</span>, <span class=
+"literal">0x10346</span>, <span class="literal">0</span>};
+vector&lt;<span class="keyword">unsigned char</span>&gt; utf8result;
+utf32to8(utf32string, utf32string + <span class=
+"literal">3</span>, back_inserter(utf8result));
+assert (utf8result.size() == <span class="literal">9</span>);
+</pre>
+ <p>
+ This is a faster but less safe version of <code>utf8::utf32to8</code>. It does not
+ check for validity of the supplied UTF-32 sequence.
+ </p>
+ <h4>
+ utf8::unchecked::utf8to32
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Converts a UTF-8 encoded string to UTF-32.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator, typename u32bit_iterator&gt;
+u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result);
+
+</pre>
+ <p>
+ <code>start</code>: an iterator pointing to the beginning of the UTF-8 encoded
+ string to convert.<br>
+ <code>end</code>: an iterator pointing to pass-the-end of the UTF-8 encoded string
+ to convert.<br>
+ <code>result</code>: an output iterator to the place in the UTF-32 string where to
+ append the result of conversion.<br>
+ <span class="return_value">Return value</span>: An iterator pointing to the place
+ after the appended UTF-32 string.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">char</span>* twochars = <span class=
+"literal">"\xe6\x97\xa5\xd1\x88"</span>;
+vector&lt;<span class="keyword">int</span>&gt; utf32result;
+unchecked::utf8to32(twochars, twochars + <span class=
+"literal">5</span>, back_inserter(utf32result));
+assert (utf32result.size() == <span class="literal">2</span>);
+</pre>
+ <p>
+ This is a faster but less safe version of <code>utf8::utf8to32</code>. It does not
+ check for validity of the supplied UTF-8 sequence.
+ </p>
+ <h3 id="typesunchecked">
+ Types From utf8::unchecked Namespace
+ </h3>
+ <h4>
+ utf8::iterator
+ </h4>
+ <p class="version">
+ Available in version 2.0 and later.
+ </p>
+ <p>
+ Adapts the underlying octet iterator to iterate over the sequence of code points,
+ rather than raw octets.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class="keyword">typename</span> octet_iterator&gt;
+<span class="keyword">class</span> iterator;
+</pre>
+
+ <h5>Member functions</h5>
+ <dl>
+ <dt><code>iterator();</code> <dd> the deafult constructor; the underlying <code>octet_iterator</code> is
+ constructed with its default constructor.
+ <dt><code><span class="keyword">explicit</span> iterator (const octet_iterator&amp; octet_it);
+ </code> <dd> a constructor
+ that initializes the underlying <code>octet_iterator</code> with <code>octet_it</code>
+ <dt><code>octet_iterator base () <span class="keyword">const</span>;</code> <dd> returns the
+ underlying <code>octet_iterator</code>.
+ <dt><code>uint32_t operator * () <span class="keyword">const</span>;</code> <dd> decodes the utf-8 sequence
+ the underlying <code>octet_iterator</code> is pointing to and returns the code point.
+ <dt><code><span class="keyword">bool operator</span> == (const iterator&amp; rhs)
+ <span class="keyword">const</span>;</code> <dd> returns <span class="keyword">true</span>
+ if the two underlaying iterators are equal.
+ <dt><code><span class="keyword">bool operator</span> != (const iterator&amp; rhs)
+ <span class="keyword">const</span>;</code> <dd> returns <span class="keyword">true</span>
+ if the two underlaying iterators are not equal.
+ <dt><code>iterator&amp; <span class="keyword">operator</span> ++ (); </code> <dd> the prefix increment - moves
+ the iterator to the next UTF-8 encoded code point.
+ <dt><code>iterator <span class="keyword">operator</span> ++ (<span class="keyword">int</span>); </code> <dd>
+ the postfix increment - moves the iterator to the next UTF-8 encoded code point and returns the current one.
+ <dt><code>iterator&amp; <span class="keyword">operator</span> -- (); </code> <dd> the prefix decrement - moves
+ the iterator to the previous UTF-8 encoded code point.
+ <dt><code>iterator <span class="keyword">operator</span> -- (<span class="keyword">int</span>); </code> <dd>
+ the postfix decrement - moves the iterator to the previous UTF-8 encoded code point and returns the current one.
+ </dl>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">char</span>* threechars = <span class="literal">"\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88"</span>;
+utf8::unchecked::iterator&lt;<span class="keyword">char</span>*&gt; un_it(threechars);
+utf8::unchecked::iterator&lt;<span class="keyword">char</span>*&gt; un_it2 = un_it;
+assert (un_it2 == un_it);
+assert (*un_it == <span class="literal">0x10346</span>);
+assert (*(++un_it) == <span class="literal">0x65e5</span>);
+assert ((*un_it++) == <span class="literal">0x65e5</span>);
+assert (*un_it == <span class="literal">0x0448</span>);
+assert (un_it != un_it2);
+utf8::::unchecked::iterator&lt;<span class="keyword">char</span>*&gt; un_endit (threechars + <span class="literal">9</span>);
+assert (++un_it == un_endit);
+assert (*(--un_it) == <span class="literal">0x0448</span>);
+assert ((*un_it--) == <span class="literal">0x0448</span>);
+assert (*un_it == <span class="literal">0x65e5</span>);
+assert (--un_it == utf8::unchecked::iterator&lt;<span class="keyword">char</span>*&gt;(threechars));
+assert (*un_it == <span class="literal">0x10346</span>);
+</pre>
+ <p>
+ This is an unchecked version of <code>utf8::iterator</code>. It is faster in many cases, but offers
+ no validity or range checks.
+ </p>
+ <h2 id="points">
+ Points of interest
+ </h2>
+ <h4>
+ Design goals and decisions
+ </h4>
+ <p>
+ The library was designed to be:
+ </p>
+ <ol>
+ <li>
+ Generic: for better or worse, there are many C++ string classes out there, and
+ the library should work with as many of them as possible.
+ </li>
+ <li>
+ Portable: the library should be portable both accross different platforms and
+ compilers. The only non-portable code is a small section that declares unsigned
+ integers of different sizes: three typedefs. They can be changed by the users of
+ the library if they don't match their platform. The default setting should work
+ for Windows (both 32 and 64 bit), and most 32 bit and 64 bit Unix derivatives.
+ </li>
+ <li>
+ Lightweight: follow the "pay only for what you use" guideline.
+ </li>
+ <li>
+ Unintrusive: avoid forcing any particular design or even programming style on the
+ user. This is a library, not a framework.
+ </li>
+ </ol>
+ <h4>
+ Alternatives
+ </h4>
+ <p>
+ In case you want to look into other means of working with UTF-8 strings from C++,
+ here is the list of solutions I am aware of:
+ </p>
+ <ol>
+ <li>
+ <a href="http://icu.sourceforge.net/">ICU Library</a>. It is very powerful,
+ complete, feature-rich, mature, and widely used. Also big, intrusive,
+ non-generic, and doesn't play well with the Standard Library. I definitelly
+ recommend looking at ICU even if you don't plan to use it.
+ </li>
+ <li>
+ C++11 language and library features. Still far from complete, and not widely
+ supported by compiler vendors.
+ </li>
+ <li>
+ <a href=
+ "http://www.gtkmm.org/gtkmm2/docs/tutorial/html/ch03s04.html">Glib::ustring</a>.
+ A class specifically made to work with UTF-8 strings, and also feel like
+ <code>std::string</code>. If you prefer to have yet another string class in your
+ code, it may be worth a look. Be aware of the licensing issues, though.
+ </li>
+ <li>
+ Platform dependent solutions: Windows and POSIX have functions to convert strings
+ from one encoding to another. That is only a subset of what my library offers,
+ but if that is all you need it may be good enough.
+ </li>
+ </ol>
+ <h2 id="links">
+ Links
+ </h2>
+ <ol>
+ <li>
+ <a href="http://www.unicode.org/">The Unicode Consortium</a>.
+ </li>
+ <li>
+ <a href="http://icu.sourceforge.net/">ICU Library</a>.
+ </li>
+ <li>
+ <a href="http://en.wikipedia.org/wiki/UTF-8">UTF-8 at Wikipedia</a>
+ </li>
+ <li>
+ <a href="http://www.cl.cam.ac.uk/~mgk25/unicode.html">UTF-8 and Unicode FAQ for
+ Unix/Linux</a>
+ </li>
+ </ol>
+ </body>
+</html>
diff --git a/thirdparty/assimp/include/assimp/.editorconfig b/thirdparty/assimp/include/assimp/.editorconfig
deleted file mode 100644
index 9ea66423ad..0000000000
--- a/thirdparty/assimp/include/assimp/.editorconfig
+++ /dev/null
@@ -1,8 +0,0 @@
-# See <http://EditorConfig.org> for details
-
-[*.{h,hpp,inl}]
-end_of_line = lf
-insert_final_newline = true
-trim_trailing_whitespace = true
-indent_size = 4
-indent_style = space
diff --git a/thirdparty/assimp/include/assimp/BaseImporter.h b/thirdparty/assimp/include/assimp/BaseImporter.h
index 48dfc8ed8b..55f7fe3754 100644
--- a/thirdparty/assimp/include/assimp/BaseImporter.h
+++ b/thirdparty/assimp/include/assimp/BaseImporter.h
@@ -48,8 +48,10 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
#include <vector>
#include <set>
+#include <map>
#include <assimp/types.h>
#include <assimp/ProgressHandler.hpp>
+#include <assimp/ai_assert.h>
struct aiScene;
struct aiImporterDesc;
@@ -80,6 +82,10 @@ class IOStream;
class ASSIMP_API BaseImporter {
friend class Importer;
+private:
+ /* Pushes state into importer for the importer scale */
+ virtual void UpdateImporterScale( Importer* pImp );
+
public:
/** Constructor to be privately used by #Importer */
@@ -132,7 +138,7 @@ public:
* a suitable response to the caller.
*/
aiScene* ReadFile(
- const Importer* pImp,
+ Importer* pImp,
const std::string& pFile,
IOSystem* pIOHandler
);
@@ -161,14 +167,65 @@ public:
* some loader features. Importers must provide this information. */
virtual const aiImporterDesc* GetInfo() const = 0;
+ /**
+ * Will be called only by scale process when scaling is requested.
+ */
+ virtual void SetFileScale(double scale)
+ {
+ fileScale = scale;
+ }
+
+ virtual double GetFileScale() const
+ {
+ return fileScale;
+ }
+
+ enum ImporterUnits {
+ M,
+ MM,
+ CM,
+ INCHES,
+ FEET
+ };
+
+ /**
+ * Assimp Importer
+ * unit conversions available
+ * if you need another measurment unit add it below.
+ * it's currently defined in assimp that we prefer meters.
+ * */
+ std::map<ImporterUnits, double> importerUnits = {
+ {ImporterUnits::M, 1},
+ {ImporterUnits::CM, 0.01},
+ {ImporterUnits::MM, 0.001},
+ {ImporterUnits::INCHES, 0.0254},
+ {ImporterUnits::FEET, 0.3048}
+ };
+
+ virtual void SetApplicationUnits( const ImporterUnits& unit )
+ {
+ importerScale = importerUnits[unit];
+ applicationUnits = unit;
+ }
+
+ virtual const ImporterUnits& GetApplicationUnits()
+ {
+ return applicationUnits;
+ }
+
// -------------------------------------------------------------------
/** Called by #Importer::GetExtensionList for each loaded importer.
* Take the extension list contained in the structure returned by
* #GetInfo and insert all file extensions into the given set.
* @param extension set to collect file extensions in*/
void GetExtensionList(std::set<std::string>& extensions);
+
+protected:
+ ImporterUnits applicationUnits = ImporterUnits::M;
+ double importerScale = 1.0;
+ double fileScale = 1.0;
+
-protected:
// -------------------------------------------------------------------
/** Imports the given file into the given scene structure. The
diff --git a/thirdparty/assimp/include/assimp/config.h.in b/thirdparty/assimp/include/assimp/config.h.in
index d08b929a10..3a6379bf40 100644
--- a/thirdparty/assimp/include/assimp/config.h.in
+++ b/thirdparty/assimp/include/assimp/config.h.in
@@ -142,7 +142,7 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
/** @brief Specifies the maximum angle that may be between two vertex tangents
* that their tangents and bi-tangents are smoothed.
*
- * This applies to the CalcTangentSpace-Step. TFvhe angle is specified
+ * This applies to the CalcTangentSpace-Step. The angle is specified
* in degrees. The maximum value is 175.
* Property type: float. Default value: 45 degrees
*/
@@ -999,6 +999,13 @@ enum aiComponent
# define AI_CONFIG_GLOBAL_SCALE_FACTOR_DEFAULT 1.0f
#endif // !! AI_DEBONE_THRESHOLD
+#define AI_CONFIG_APP_SCALE_KEY "APP_SCALE_FACTOR"
+
+#if (!defined AI_CONFIG_APP_SCALE_KEY)
+# define AI_CONFIG_APP_SCALE_KEY 1.0
+#endif // AI_CONFIG_APP_SCALE_KEY
+
+
// ---------- All the Build/Compile-time defines ------------
/** @brief Specifies if double precision is supported inside assimp
diff --git a/thirdparty/assimp/include/assimp/irrXMLWrapper.h b/thirdparty/assimp/include/assimp/irrXMLWrapper.h
deleted file mode 100644
index ec8ee7c76e..0000000000
--- a/thirdparty/assimp/include/assimp/irrXMLWrapper.h
+++ /dev/null
@@ -1,144 +0,0 @@
-/*
-Open Asset Import Library (assimp)
-----------------------------------------------------------------------
-
-Copyright (c) 2006-2019, assimp team
-
-
-All rights reserved.
-
-Redistribution and use of this software in source and binary forms,
-with or without modification, are permitted provided that the
-following conditions are met:
-
-* Redistributions of source code must retain the above
-copyright notice, this list of conditions and the
-following disclaimer.
-
-* Redistributions in binary form must reproduce the above
-copyright notice, this list of conditions and the
-following disclaimer in the documentation and/or other
-materials provided with the distribution.
-
-* Neither the name of the assimp team, nor the names of its
-contributors may be used to endorse or promote products
-derived from this software without specific prior
-written permission of the assimp team.
-
-THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
-"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
-LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
-A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
-OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
-SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
-LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
-DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
-THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
-(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
-OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-
-----------------------------------------------------------------------
-*/
-
-#ifndef INCLUDED_AI_IRRXML_WRAPPER
-#define INCLUDED_AI_IRRXML_WRAPPER
-
-// some long includes ....
-#include <irrXML.h>
-#include "IOStream.hpp"
-#include "BaseImporter.h"
-#include <vector>
-
-namespace Assimp {
-
-// ---------------------------------------------------------------------------------
-/** @brief Utility class to make IrrXML work together with our custom IO system
- * See the IrrXML docs for more details.
- *
- * Construct IrrXML-Reader in BaseImporter::InternReadFile():
- * @code
- * // open the file
- * std::unique_ptr<IOStream> file( pIOHandler->Open( pFile));
- * if( file.get() == NULL) {
- * throw DeadlyImportError( "Failed to open file " + pFile + ".");
- * }
- *
- * // generate a XML reader for it
- * std::unique_ptr<CIrrXML_IOStreamReader> mIOWrapper( new CIrrXML_IOStreamReader( file.get()));
- * mReader = irr::io::createIrrXMLReader( mIOWrapper.get());
- * if( !mReader) {
- * ThrowException( "xxxx: Unable to open file.");
- * }
- * @endcode
- **/
-class CIrrXML_IOStreamReader : public irr::io::IFileReadCallBack {
-public:
-
- // ----------------------------------------------------------------------------------
- //! Construction from an existing IOStream
- explicit CIrrXML_IOStreamReader(IOStream* _stream)
- : stream (_stream)
- , t (0)
- {
-
- // Map the buffer into memory and convert it to UTF8. IrrXML provides its
- // own conversion, which is merely a cast from uintNN_t to uint8_t. Thus,
- // it is not suitable for our purposes and we have to do it BEFORE IrrXML
- // gets the buffer. Sadly, this forces us to map the whole file into
- // memory.
-
- data.resize(stream->FileSize());
- stream->Read(&data[0],data.size(),1);
-
- // Remove null characters from the input sequence otherwise the parsing will utterly fail
- unsigned int size = 0;
- unsigned int size_max = static_cast<unsigned int>(data.size());
- for(unsigned int i = 0; i < size_max; i++) {
- if(data[i] != '\0') {
- data[size++] = data[i];
- }
- }
- data.resize(size);
-
- BaseImporter::ConvertToUTF8(data);
- }
-
- // ----------------------------------------------------------------------------------
- //! Virtual destructor
- virtual ~CIrrXML_IOStreamReader() {}
-
- // ----------------------------------------------------------------------------------
- //! Reads an amount of bytes from the file.
- /** @param buffer: Pointer to output buffer.
- * @param sizeToRead: Amount of bytes to read
- * @return Returns how much bytes were read. */
- virtual int read(void* buffer, int sizeToRead) {
- if(sizeToRead<0) {
- return 0;
- }
- if(t+sizeToRead>data.size()) {
- sizeToRead = static_cast<int>(data.size()-t);
- }
-
- memcpy(buffer,&data.front()+t,sizeToRead);
-
- t += sizeToRead;
- return sizeToRead;
- }
-
- // ----------------------------------------------------------------------------------
- //! Returns size of file in bytes
- virtual int getSize() {
- return (int)data.size();
- }
-
-private:
- IOStream* stream;
- std::vector<char> data;
- size_t t;
-
-}; // ! class CIrrXML_IOStreamReader
-
-} // ! Assimp
-
-#endif // !! INCLUDED_AI_IRRXML_WRAPPER
diff --git a/thirdparty/assimp/include/assimp/scene.h b/thirdparty/assimp/include/assimp/scene.h
index df5d6f3b5e..2667db85b3 100644
--- a/thirdparty/assimp/include/assimp/scene.h
+++ b/thirdparty/assimp/include/assimp/scene.h
@@ -56,9 +56,9 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
#include "material.h"
#include "anim.h"
#include "metadata.h"
-#include <cstdlib>
#ifdef __cplusplus
+# include <cstdlib>
extern "C" {
#endif