Merge branch 'master' into UpdateZli

code/AssetLib/ASE/ASEParser.cpp

@@ -479,6 +479,11 @@ void Parser::ParseLV1MaterialListBlock() {
             if (TokenMatch(filePtr, "MATERIAL_COUNT", 14)) {
                 ParseLV4MeshLong(iMaterialCount);
 
+                if (UINT_MAX - iOldMaterialCount < iMaterialCount) {
+                    LogWarning("Out of range: material index is too large");
+                    return;
+                }
+
                 // now allocate enough storage to hold all materials
                 m_vMaterials.resize(iOldMaterialCount + iMaterialCount, Material("INVALID"));
                 continue;

code/AssetLib/LWS/LWSLoader.cpp

@@ -632,18 +632,17 @@ void LWSImporter::InternReadFile(const std::string &pFile, aiScene *pScene, IOSy
                     nodes.push_back(d);
                 }
                 ASSIMP_LOG_ERROR("LWS: Unexpected keyword: \'Channel\'");
-            }
-
-            // important: index of channel
-            nodes.back().channels.emplace_back();
-            LWO::Envelope &env = nodes.back().channels.back();
-
-            env.index = strtoul10(c);
+            } else {
+                // important: index of channel
+                nodes.back().channels.emplace_back();
+                LWO::Envelope &env = nodes.back().channels.back();
 
-            // currently we can just interpret the standard channels 0...9
-            // (hack) assume that index-i yields the binary channel type from LWO
-            env.type = (LWO::EnvelopeType)(env.index + 1);
+                env.index = strtoul10(c);
 
+                // currently we can just interpret the standard channels 0...9
+                // (hack) assume that index-i yields the binary channel type from LWO
+                env.type = (LWO::EnvelopeType)(env.index + 1);
+            }
         }
         // 'Envelope': a single animation channel
         else if ((*it).tokens[0] == "Envelope") {

code/AssetLib/MD5/MD5Parser.cpp

@@ -138,18 +138,31 @@ bool MD5Parser::ParseSection(Section &out) {
     char *sz = buffer;
     while (!IsSpaceOrNewLine(*buffer)) {
         ++buffer;
+        if (buffer == bufferEnd)
+            return false;
     }
     out.mName = std::string(sz, (uintptr_t)(buffer - sz));
-    SkipSpaces();
+    while (IsSpace(*buffer)) {
+        ++buffer;
+        if (buffer == bufferEnd)
+            return false;
+    }
 
     bool running = true;
     while (running) {
         if ('{' == *buffer) {
             // it is a normal section so read all lines
             ++buffer;
+            if (buffer == bufferEnd)
+                return false;
             bool run = true;
             while (run) {
-                if (!SkipSpacesAndLineEnd()) {
+                while (IsSpaceOrNewLine(*buffer)) {
+                    ++buffer;
+                    if (buffer == bufferEnd)
+                        return false;
+                }
+                if ('\0' == *buffer) {
                     return false; // seems this was the last section
                 }
                 if ('}' == *buffer) {
@@ -164,25 +177,39 @@ bool MD5Parser::ParseSection(Section &out) {
                 elem.szStart = buffer;
 
                 // terminate the line with zero
-                while (!IsLineEnd(*buffer))
+                while (!IsLineEnd(*buffer)) {
                     ++buffer;
+                    if (buffer == bufferEnd)
+                        return false;
+                }
                 if (*buffer) {
                     ++lineNumber;
                     *buffer++ = '\0';
+                    if (buffer == bufferEnd)
+                        return false;
                 }
             }
             break;
         } else if (!IsSpaceOrNewLine(*buffer)) {
             // it is an element at global scope. Parse its value and go on
             sz = buffer;
-            while (!IsSpaceOrNewLine(*buffer++))
-                ;
+            while (!IsSpaceOrNewLine(*buffer++)) {
+                if (buffer == bufferEnd)
+                    return false;
+            }
             out.mGlobalValue = std::string(sz, (uintptr_t)(buffer - sz));
             continue;
         }
         break;
     }
-    return SkipSpacesAndLineEnd();
+    if (buffer == bufferEnd)
+        return false;
+    while (IsSpaceOrNewLine(*buffer)) {
+        ++buffer;
+        if (buffer == bufferEnd)
+            return false;
+    }
+    return '\0' != *buffer;
 }
 
 // ------------------------------------------------------------------------------------------------

code/AssetLib/MDL/MDLMaterialLoader.cpp

@@ -481,6 +481,8 @@ void MDLImporter::ParseSkinLump_3DGS_MDL7(
         pcNew->achFormatHint[2] = 's';
         pcNew->achFormatHint[3] = '\0';
 
+        SizeCheck(szCurrent + pcNew->mWidth);
+
         pcNew->pcData = (aiTexel *)new unsigned char[pcNew->mWidth];
         memcpy(pcNew->pcData, szCurrent, pcNew->mWidth);
         szCurrent += iWidth;
@@ -493,12 +495,12 @@ void MDLImporter::ParseSkinLump_3DGS_MDL7(
 
         aiString szFile;
         const size_t iLen = strlen((const char *)szCurrent);
-        size_t iLen2 = iLen + 1;
-        iLen2 = iLen2 > MAXLEN ? MAXLEN : iLen2;
+        size_t iLen2 = iLen > (MAXLEN - 1) ? (MAXLEN - 1) : iLen;
         memcpy(szFile.data, (const char *)szCurrent, iLen2);
+        szFile.data[iLen2] = '\0';
         szFile.length = static_cast<ai_uint32>(iLen2);
 
-        szCurrent += iLen2;
+        szCurrent += iLen2 + 1;
 
         // place this as diffuse texture
         pcMatOut->AddProperty(&szFile, AI_MATKEY_TEXTURE_DIFFUSE(0));

code/AssetLib/Obj/ObjFileData.h

@@ -239,8 +239,6 @@ struct Mesh {
     unsigned int m_uiMaterialIndex;
     /// True, if normals are stored.
     bool m_hasNormals;
-    /// True, if vertex colors are stored.
-    bool m_hasVertexColors;
 
     /// Constructor
     explicit Mesh(const std::string &name) :

code/AssetLib/Obj/ObjFileMtlImporter.cpp

@@ -252,9 +252,9 @@ void ObjFileMtlImporter::load() {
             case 'a': // Anisotropy
             {
                 ++m_DataIt;
-                getFloatValue(m_pModel->mCurrentMaterial->anisotropy);
                 if (m_pModel->mCurrentMaterial != nullptr)
-                    m_DataIt = skipLine<DataArrayIt>(m_DataIt, m_DataItEnd, m_uiLine);
+                    getFloatValue(m_pModel->mCurrentMaterial->anisotropy);
+                m_DataIt = skipLine<DataArrayIt>(m_DataIt, m_DataItEnd, m_uiLine);
             } break;
 
             default: {
@@ -371,6 +371,7 @@ void ObjFileMtlImporter::getTexture() {
     if (m_pModel->mCurrentMaterial == nullptr) {
         m_pModel->mCurrentMaterial = new ObjFile::Material();
         m_pModel->mCurrentMaterial->MaterialName.Set("Empty_Material");
+        m_pModel->mMaterialMap["Empty_Material"] = m_pModel->mCurrentMaterial;
     }
 
     const char *pPtr(&(*m_DataIt));

code/AssetLib/Obj/ObjFileParser.cpp

@@ -156,9 +156,17 @@ void ObjFileParser::parseFile(IOStreamBuffer<char> &streamBuffer) {
                     // read in vertex definition (homogeneous coords)
                     getHomogeneousVector3(m_pModel->mVertices);
                 } else if (numComponents == 6) {
+                    // fill previous omitted vertex-colors by default
+                    if (m_pModel->mVertexColors.size() < m_pModel->mVertices.size()) {
+                        m_pModel->mVertexColors.resize(m_pModel->mVertices.size(), aiVector3D(0, 0, 0));
+                    }
                     // read vertex and vertex-color
                     getTwoVectors3(m_pModel->mVertices, m_pModel->mVertexColors);
                 }
+                // append omitted vertex-colors as default for the end if any vertex-color exists
+                if (!m_pModel->mVertexColors.empty() && m_pModel->mVertexColors.size() < m_pModel->mVertices.size()) {
+                    m_pModel->mVertexColors.resize(m_pModel->mVertices.size(), aiVector3D(0, 0, 0));
+                }
             } else if (*m_DataIt == 't') {
                 // read in texture coordinate ( 2D or 3D )
                 ++m_DataIt;
@@ -456,8 +464,19 @@ void ObjFileParser::getFace(aiPrimitiveType type) {
             iPos = 0;
         } else {
             //OBJ USES 1 Base ARRAYS!!!!
-            const char *token = &(*m_DataIt);
-            const int iVal = ::atoi(token);
+            int iVal;
+            auto end = m_DataIt;
+            // find either the buffer end or the '\0'
+            while (end < m_DataItEnd && *end != '\0')
+                ++end;
+            // avoid temporary string allocation if there is a zero
+            if (end != m_DataItEnd) {
+                iVal = ::atoi(&(*m_DataIt));
+            } else {
+                // otherwise make a zero terminated copy, which is safe to pass to atoi
+                std::string number(&(*m_DataIt), m_DataItEnd - m_DataIt);
+                iVal = ::atoi(number.c_str());
+            }
 
             // increment iStep position based off of the sign and # of digits
             int tmp = iVal;

code/Common/FileSystemFilter.h

@@ -297,7 +297,7 @@ private:
         }
 
         const char separator = getOsSeparator();
-        for (it = in.begin(); it != in.end(); ++it) {
+        for (it = in.begin(); it < in.end(); ++it) {
             const size_t remaining = std::distance(in.end(), it);
             // Exclude :// and \\, which remain untouched.
             // https://sourceforge.net/tracker/?func=detail&aid=3031725&group_id=226462&atid=1067632

code/Material/MaterialSystem.cpp

@@ -51,6 +51,7 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 #include <assimp/material.h>
 #include <assimp/types.h>
 #include <assimp/DefaultLogger.hpp>
+#include <memory>
 
 using namespace Assimp;
 
@@ -473,7 +474,7 @@ aiReturn aiMaterial::AddBinaryProperty(const void *pInput,
     }
 
     // Allocate a new material property
-    aiMaterialProperty *pcNew = new aiMaterialProperty();
+    std::unique_ptr<aiMaterialProperty> pcNew(new aiMaterialProperty());
 
     // .. and fill it
     pcNew->mType = pType;
@@ -489,7 +490,7 @@ aiReturn aiMaterial::AddBinaryProperty(const void *pInput,
     strcpy(pcNew->mKey.data, pKey);
 
     if (UINT_MAX != iOutIndex) {
-        mProperties[iOutIndex] = pcNew;
+        mProperties[iOutIndex] = pcNew.release();
         return AI_SUCCESS;
     }
 
@@ -502,7 +503,6 @@ aiReturn aiMaterial::AddBinaryProperty(const void *pInput,
         try {
             ppTemp = new aiMaterialProperty *[mNumAllocated];
         } catch (std::bad_alloc &) {
-            delete pcNew;
             return AI_OUTOFMEMORY;
         }
 
@@ -513,7 +513,7 @@ aiReturn aiMaterial::AddBinaryProperty(const void *pInput,
         mProperties = ppTemp;
     }
     // push back ...
-    mProperties[mNumProperties++] = pcNew;
+    mProperties[mNumProperties++] = pcNew.release();
 
     return AI_SUCCESS;
 }

code/PostProcessing/FindInvalidDataProcess.cpp

@@ -82,6 +82,9 @@ void UpdateMeshReferences(aiNode *node, const std::vector<unsigned int> &meshMap
         for (unsigned int a = 0; a < node->mNumMeshes; ++a) {
 
             unsigned int ref = node->mMeshes[a];
+            if (ref >= meshMapping.size())
+                throw DeadlyImportError("Invalid mesh ref");
+
             if (UINT_MAX != (ref = meshMapping[ref])) {
                 node->mMeshes[out++] = ref;
             }
@@ -143,7 +146,13 @@ void FindInvalidDataProcess::Execute(aiScene *pScene) {
             // we need to remove some meshes.
             // therefore we'll also need to remove all references
             // to them from the scenegraph
-            UpdateMeshReferences(pScene->mRootNode, meshMapping);
+            try {
+                UpdateMeshReferences(pScene->mRootNode, meshMapping);
+            } catch (const std::exception&) {
+                // fix the real number of meshes otherwise we'll get double free in the scene destructor
+                pScene->mNumMeshes = real;
+                throw;
+            }
             pScene->mNumMeshes = real;
         }
 

contrib/unzip/ioapi.c

@@ -231,8 +231,7 @@ static int ZCALLBACK ferror_file_func (voidpf opaque, voidpf stream)
     return ret;
 }
 
-void fill_fopen_filefunc (pzlib_filefunc_def)
-  zlib_filefunc_def* pzlib_filefunc_def;
+void fill_fopen_filefunc (zlib_filefunc_def* pzlib_filefunc_def)
 {
     pzlib_filefunc_def->zopen_file = fopen_file_func;
     pzlib_filefunc_def->zread_file = fread_file_func;

contrib/unzip/unzip.c

@@ -1038,7 +1038,7 @@ local int unz64local_GetCurrentFileInfoInternal (unzFile file,
             /* ZIP64 extra fields */
             if (headerId == 0x0001)
             {
-                                                        uLong uL;
+                                                        uLong uL1;
 
                                                                 if(file_info.uncompressed_size == MAXU32)
                                                                 {
@@ -1062,7 +1062,7 @@ local int unz64local_GetCurrentFileInfoInternal (unzFile file,
                                                                 if(file_info.disk_num_start == MAXU32)
                                                                 {
                                                                         /* Disk Start Number */
-                                                                        if (unz64local_getLong(&s->z_filefunc, s->filestream,&uL) != UNZ_OK)
+                                                                        if (unz64local_getLong(&s->z_filefunc, s->filestream,&uL1) != UNZ_OK)
                                                                                 err=UNZ_ERRNO;
                                                                 }
 

contrib/utf8cpp/doc/LICENSE

@@ -0,0 +1,23 @@
+Boost Software License - Version 1.0 - August 17th, 2003
+
+Permission is hereby granted, free of charge, to any person or organization
+obtaining a copy of the software and accompanying documentation covered by
+this license (the "Software") to use, reproduce, display, distribute,
+execute, and transmit the Software, and to prepare derivative works of the
+Software, and to permit third-parties to whom the Software is furnished to
+do so, all subject to the following:
+
+The copyright notices in the Software and this entire statement, including
+the above license grant, this restriction and the following disclaimer,
+must be included in all copies of the Software, in whole or in part, and
+all derivative works of the Software, unless such copies or derivative
+works are solely in the form of machine-executable object code generated by
+a source language processor.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT
+SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE
+FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE,
+ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+DEALINGS IN THE SOFTWARE.

contrib/utf8cpp/doc/README.md

@@ -0,0 +1,1503 @@
+# UTF8-CPP: UTF-8 with C++ in a Portable Way
+
+
+## Introduction
+
+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.
+
+In order to easily handle UTF-8 encoded Unicode strings, I came up with a small, C++98 compatible 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](./LICENSE). The library has been used a lot in the past ten years both in commercial and open-source projects and is considered feature-complete now. If you run into bugs or performance issues, please let me know and I'll do my best to address them.
+
+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 [Unicode Home Page](http://www.unicode.org/) 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.
+
+## Examples of use
+
+### Introductionary Sample
+
+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:
+
+```cpp
+#include <fstream>
+#include <iostream>
+#include <string>
+#include <vector>
+#include "utf8.h"
+using namespace std;
+int main(int argc, char** argv)
+{
+    if (argc != 2) {
+        cout << "\nUsage: docsample filename\n";
+        return 0;
+    }
+    const char* test_file_path = argv[1];
+    // Open the test file (must be UTF-8 encoded)
+    ifstream fs8(test_file_path);
+    if (!fs8.is_open()) {
+        cout << "Could not open " << test_file_path << endl;
+        return 0;
+    }
+
+    unsigned line_count = 1;
+    string line;
+    // Play with all the lines in the file
+    while (getline(fs8, line)) {
+        // check for invalid utf-8 (for a simple yes/no check, there is also utf8::is_valid function)
+#if __cplusplus >= 201103L // C++ 11 or later
+        auto end_it = utf8::find_invalid(line.begin(), line.end());
+#else
+        string::iterator end_it = utf8::find_invalid(line.begin(), line.end());
+#endif // C++ 11
+        if (end_it != line.end()) {
+            cout << "Invalid UTF-8 encoding detected at line " << line_count << "\n";
+            cout << "This part is fine: " << string(line.begin(), end_it) << "\n";
+        }
+        // Get the line length (at least for the valid part)
+        int length = utf8::distance(line.begin(), end_it);
+        cout << "Length of line " << line_count << " is " << length <<  "\n";
+
+        // Convert it to utf-16
+#if __cplusplus >= 201103L // C++ 11 or later
+        u16string utf16line = utf8::utf8to16(line);
+#else
+        vector<unsigned short> utf16line;
+        utf8::utf8to16(line.begin(), end_it, back_inserter(utf16line));
+#endif // C++ 11
+        // And back to utf-8;
+#if __cplusplus >= 201103L // C++ 11 or later
+        string utf8line = utf8::utf16to8(utf16line);
+#else
+        string utf8line; 
+        utf8::utf16to8(utf16line.begin(), utf16line.end(), back_inserter(utf8line));
+#endif // C++ 11
+        // Confirm that the conversion went OK:
+        if (utf8line != string(line.begin(), end_it))
+            cout << "Error in UTF-16 conversion at line: " << line_count << "\n";        
+
+        line_count++;
+    } 
+
+    return 0;
+}
+```
+
+In the previous code sample, for each line we performed a detection of invalid UTF-8 sequences with `find_invalid`; 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 `utf8::distance`; finally, we have converted each line to UTF-16 encoding with `utf8to16` and back to UTF-8 with `utf16to8`.
+
+Note a different pattern of usage for old compilers. For instance, this is how we convert
+a UTF-8 encoded string to a UTF-16 encoded one with a pre - C++11 compiler:
+```cpp
+    vector<unsigned short> utf16line;
+    utf8::utf8to16(line.begin(), end_it, back_inserter(utf16line));
+```
+
+With a more modern compiler, the same operation would look like:
+```cpp
+    u16string utf16line = utf8::utf8to16(line);
+```
+If `__cplusplus` macro points to a C++ 11 or later, the library exposes API that takes into 
+account C++ standard Unicode strings and move semantics. With an older compiler, it is still
+possible to use the same functionality, just in a little less convenient way
+
+In case you do not trust the `__cplusplus` macro or, for instance, do not want to include
+the C++ 11 helper functions even with a modern compiler, define `UTF_CPP_CPLUSPLUS` macro
+before including `utf8.h` and assign it a value for the standard you want to use - the values are the same as for the `__cplusplus` macro. This can be also useful with compilers that are conservative in setting the `__cplusplus` macro even if they have a good support for a recent standard edition - Microsoft's Visual C++ is one example.
+
+### Checking if a file contains valid UTF-8 text
+
+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:
+
+```cpp
+bool valid_utf8_file(const char* file_name)
+{
+    ifstream ifs(file_name);
+    if (!ifs)
+        return false; // even better, throw here
+
+    istreambuf_iterator<char> it(ifs.rdbuf());
+    istreambuf_iterator<char> eos;
+
+    return utf8::is_valid(it, eos);
+}
+```
+
+Because the function `utf8::is_valid()` works with input iterators, we were able to pass an `istreambuf_iterator` to `it` and read the content of the file directly without loading it to the memory first.
+
+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:
+
+```cpp
+    utf8::utf8to16(it, eos, back_inserter(u16string));
+```
+
+### Ensure that a string contains valid UTF-8 text
+
+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:
+
+```cpp
+void fix_utf8_string(std::string& str)
+{
+    std::string temp;
+    utf8::replace_invalid(str.begin(), str.end(), back_inserter(temp));
+    str = temp;
+}
+```
+
+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.
+
+
+## Points of interest
+
+#### Design goals and decisions
+
+The library was designed to be:
+
+1.  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.
+2.  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. Support for post C++03 language features is included for modern compilers at API level only, so the library should work even with pretty old compilers.
+3.  Lightweight: follow the "pay only for what you use" guideline.
+4.  Unintrusive: avoid forcing any particular design or even programming style on the user. This is a library, not a framework.
+
+#### Alternatives
+
+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:
+
+1.  [ICU Library](http://icu.sourceforge.net/). 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.
+2.  C++11 language and library features. Still far from complete, and not easy to use.
+3.  [Glib::ustring](http://www.gtkmm.org/gtkmm2/docs/tutorial/html/ch03s04.html). A class specifically made to work with UTF-8 strings, and also feel like `std::string`. 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.
+4.  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.
+
+
+## Reference
+
+### Functions From utf8 Namespace
+
+#### utf8::append
+
+Available in version 3.0 and later. Requires a C++ 11 compliant compiler.
+
+Encodes a 32 bit code point as a UTF-8 sequence of octets and appends the sequence to a UTF-8 string.
+
+```cpp
+void append(char32_t cp, std::string& s);
+```
+
+`cp`: a code point to append to the string.  
+`s`: a utf-8 encoded string to append the code point to.  
+
+Example of use:
+
+```cpp
+std::string u;
+append(0x0448, u);
+assert (u[0] == char(0xd1) && u[1] == char(0x88) && u.length() == 2);
+```
+
+In case of an invalid code point, a `utf8::invalid_code_point` exception is thrown.
+
+
+#### utf8::append
+
+Available in version 1.0 and later.
+
+Encodes a 32 bit code point as a UTF-8 sequence of octets and appends the sequence to a UTF-8 string.
+
+```cpp
+template <typename octet_iterator>
+octet_iterator append(uint32_t cp, octet_iterator result);
+```
+
+`octet_iterator`: an output iterator.  
+`cp`: a 32 bit integer representing a code point to append to the sequence.  
+`result`: an output iterator to the place in the sequence where to append the code point.  
+Return value: an iterator pointing to the place after the newly appended sequence.
+
+Example of use:
+
+```cpp
+unsigned char u[5] = {0,0,0,0,0};
+unsigned char* end = append(0x0448, u);
+assert (u[0] == 0xd1 && u[1] == 0x88 && u[2] == 0 && u[3] == 0 && u[4] == 0);
+```
+
+Note that `append` 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, `append` can add anywhere between 1 and 4 octets to the sequence. In practice, you would most often want to use `std::back_inserter` to ensure that the necessary memory is allocated.
+
+In case of an invalid code point, a `utf8::invalid_code_point` exception is thrown.
+
+#### utf8::next
+
+Available in version 1.0 and later.
+
+Given the iterator to the beginning of the UTF-8 sequence, it returns the code point and moves the iterator to the next position.
+
+```cpp
+template <typename octet_iterator> 
+uint32_t next(octet_iterator& it, octet_iterator end);
+```
+
+`octet_iterator`: an input iterator.  
+`it`: 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.  
+`end`: end of the UTF-8 sequence to be processed. If `it` gets equal to `end` during the extraction of a code point, an `utf8::not_enough_room` exception is thrown.  
+Return value: the 32 bit representation of the processed UTF-8 code point.
+
+Example of use:
+
+```cpp
+char* twochars = "\xe6\x97\xa5\xd1\x88";
+char* w = twochars;
+int cp = next(w, twochars + 6);
+assert (cp == 0x65e5);
+assert (w == twochars + 3);
+```
+
+This function is typically used to iterate through a UTF-8 encoded string.
+
+In case of an invalid UTF-8 seqence, a `utf8::invalid_utf8` exception is thrown.
+
+#### utf8::peek_next
+
+Available in version 2.1 and later.
+
+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.
+
+```cpp
+template <typename octet_iterator> 
+uint32_t peek_next(octet_iterator it, octet_iterator end);
+```
+
+
+`octet_iterator`: an input iterator.  
+`it`: an iterator pointing to the beginning of an UTF-8 encoded code point.  
+`end`: end of the UTF-8 sequence to be processed. If `it` gets equal to `end` during the extraction of a code point, an `utf8::not_enough_room` exception is thrown.  
+Return value: the 32 bit representation of the processed UTF-8 code point.
+
+Example of use:
+
+```cpp
+char* twochars = "\xe6\x97\xa5\xd1\x88";
+char* w = twochars;
+int cp = peek_next(w, twochars + 6);
+assert (cp == 0x65e5);
+assert (w == twochars);
+```
+
+In case of an invalid UTF-8 seqence, a `utf8::invalid_utf8` exception is thrown.
+
+#### utf8::prior
+
+Available in version 1.02 and later.
+
+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.
+
+```cpp
+template <typename octet_iterator> 
+uint32_t prior(octet_iterator& it, octet_iterator start);
+```
+
+`octet_iterator`: a bidirectional iterator.  
+`it`: 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.  
+`start`: 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.  
+ Return value: the 32 bit representation of the previous code point.
+
+Example of use:
+
+```cpp
+char* twochars = "\xe6\x97\xa5\xd1\x88";
+unsigned char* w = twochars + 3;
+int cp = prior (w, twochars);
+assert (cp == 0x65e5);
+assert (w == twochars);
+```
+
+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 `utf8::next` 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 `utf8::prior` may not detect an invalid UTF-8 sequence in some scenarios: for instance if there are superfluous trail octets, it will just skip them.
+
+`it` will typically point to the beginning of a code point, and `start` will point to the beginning of the string to ensure we don't go backwards too far. `it` 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.
+
+In case `start` is reached before a UTF-8 lead octet is hit, or if an invalid UTF-8 sequence is started by the lead octet, an `invalid_utf8` exception is thrown.
+
+In case `start` equals `it`, a `not_enough_room` exception is thrown.
+
+#### utf8::advance
+Available in version 1.0 and later.
+
+Advances an iterator by the specified number of code points within an UTF-8 sequence.
+
+```cpp
+template <typename octet_iterator, typename distance_type> 
+void advance (octet_iterator& it, distance_type n, octet_iterator end);
+```
+
+`octet_iterator`: an input iterator.  
+`distance_type`: an integral type convertible to `octet_iterator`'s difference type.  
+`it`: 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.  
+`n`: number of code points `it` should be advanced. A negative value means decrement.  
+`end`: limit of the UTF-8 sequence to be processed. If `n` is positive and `it` gets equal to `end` during the extraction of a code point, an `utf8::not_enough_room` exception is thrown. If `n` is negative and `it` reaches `end` while `it` points t a trail byte of a UTF-8 sequence, a `utf8::invalid_code_point` exception is thrown.
+
+Example of use:
+
+```cpp
+char* twochars = "\xe6\x97\xa5\xd1\x88";
+unsigned char* w = twochars;
+advance (w, 2, twochars + 6);
+assert (w == twochars + 5);
+advance (w, -2, twochars);
+assert (w == twochars);
+```
+
+In case of an invalid code point, a `utf8::invalid_code_point` exception is thrown.
+
+#### utf8::distance
+
+Available in version 1.0 and later.
+
+Given the iterators to two UTF-8 encoded code points in a seqence, returns the number of code points between them.
+
+```cpp
+template <typename octet_iterator> 
+typename std::iterator_traits<octet_iterator>::difference_type distance (octet_iterator first, octet_iterator last);
+```
+
+`octet_iterator`: an input iterator.  
+`first`: an iterator to a beginning of a UTF-8 encoded code point.  
+`last`: 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.  
+ Return value the distance between the iterators, in code points.
+
+Example of use:
+
+```cpp
+char* twochars = "\xe6\x97\xa5\xd1\x88";
+size_t dist = utf8::distance(twochars, twochars + 5);
+assert (dist == 2);
+```
+
+This function is used to find the length (in code points) of a UTF-8 encoded string. The reason it is called _distance_, rather than, say, _length_ is mainly because developers are used that _length_ 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 `std::distance` algorithm.
+
+In case of an invalid UTF-8 seqence, a `utf8::invalid_utf8` exception is thrown. If `last` does not point to the past-of-end of a UTF-8 seqence, a `utf8::not_enough_room` exception is thrown.
+
+#### utf8::utf16to8
+
+Available in version 3.0 and later. Requires a C++ 11 compliant compiler.
+
+Converts a UTF-16 encoded string to UTF-8.
+
+```cpp
+std::string utf16to8(const std::u16string& s);
+```
+
+`s`: a UTF-16 encoded string.
+Return value: A UTF-8 encoded string.
+
+Example of use:
+
+```cpp
+    u16string utf16string = {0x41, 0x0448, 0x65e5, 0xd834, 0xdd1e};
+    string u = utf16to8(utf16string);
+    assert (u.size() == 10);
+```
+
+In case of invalid UTF-16 sequence, a `utf8::invalid_utf16` exception is thrown.
+
+#### utf8::utf16to8
+
+Available in version 3.2 and later. Requires a C++ 17 compliant compiler.
+
+Converts a UTF-16 encoded string to UTF-8.
+
+```cpp
+std::string utf16to8(std::u16string_view s);
+```
+
+`s`: a UTF-16 encoded string.
+Return value: A UTF-8 encoded string.
+
+Example of use:
+
+```cpp
+    u16string utf16string = {0x41, 0x0448, 0x65e5, 0xd834, 0xdd1e};
+    u16string_view utf16stringview(u16string);
+    string u = utf16to8(utf16string);
+    assert (u.size() == 10);
+```
+
+In case of invalid UTF-16 sequence, a `utf8::invalid_utf16` exception is thrown.
+
+
+#### utf8::utf16to8
+
+Available in version 1.0 and later.
+
+Converts a UTF-16 encoded string to UTF-8.
+
+```cpp
+template <typename u16bit_iterator, typename octet_iterator>
+octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result);
+```
+
+`u16bit_iterator`: an input iterator.  
+`octet_iterator`: an output iterator.  
+`start`: an iterator pointing to the beginning of the UTF-16 encoded string to convert.  
+`end`: an iterator pointing to pass-the-end of the UTF-16 encoded string to convert.  
+`result`: an output iterator to the place in the UTF-8 string where to append the result of conversion.  
+Return value: An iterator pointing to the place after the appended UTF-8 string.
+
+Example of use:
+
+```cpp
+unsigned short utf16string[] = {0x41, 0x0448, 0x65e5, 0xd834, 0xdd1e};
+vector<unsigned char> utf8result;
+utf16to8(utf16string, utf16string + 5, back_inserter(utf8result));
+assert (utf8result.size() == 10);    
+```
+
+In case of invalid UTF-16 sequence, a `utf8::invalid_utf16` exception is thrown.
+
+#### utf8::utf8to16
+
+Available in version 3.0 and later. Requires a C++ 11 compliant compiler.
+
+Converts an UTF-8 encoded string to UTF-16.
+
+```cpp
+std::u16string utf8to16(const std::string& s);
+```
+
+`s`: an UTF-8 encoded string to convert.  
+Return value: A UTF-16 encoded string
+
+Example of use:
+
+```cpp
+string utf8_with_surrogates = "\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e";
+u16string utf16result = utf8to16(utf8_with_surrogates);
+assert (utf16result.length() == 4);
+assert (utf16result[2] == 0xd834);
+assert (utf16result[3] == 0xdd1e);
+```
+
+In case of an invalid UTF-8 seqence, a `utf8::invalid_utf8` exception is thrown.
+
+#### utf8::utf8to16
+
+Available in version 3.2 and later. Requires a C++ 17 compliant compiler.
+
+Converts an UTF-8 encoded string to UTF-16.
+
+```cpp
+std::u16string utf8to16(std::string_view s);
+```
+
+`s`: an UTF-8 encoded string to convert.  
+Return value: A UTF-16 encoded string
+
+Example of use:
+
+```cpp
+string_view utf8_with_surrogates = "\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e";
+u16string utf16result = utf8to16(utf8_with_surrogates);
+assert (utf16result.length() == 4);
+assert (utf16result[2] == 0xd834);
+assert (utf16result[3] == 0xdd1e);
+```
+
+In case of an invalid UTF-8 seqence, a `utf8::invalid_utf8` exception is thrown.
+
+
+#### utf8::utf8to16
+
+Available in version 1.0 and later.
+
+Converts an UTF-8 encoded string to UTF-16
+
+```cpp
+template <typename u16bit_iterator, typename octet_iterator>
+u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result);
+```
+
+`octet_iterator`: an input iterator.  
+`u16bit_iterator`: an output iterator.  
+`start`: an iterator pointing to the beginning of the UTF-8 encoded string to convert. < br /> `end`: an iterator pointing to pass-the-end of the UTF-8 encoded string to convert.  
+`result`: an output iterator to the place in the UTF-16 string where to append the result of conversion.  
+Return value: An iterator pointing to the place after the appended UTF-16 string.
+
+Example of use:
+
+```cpp
+char utf8_with_surrogates[] = "\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e";
+vector <unsigned short> utf16result;
+utf8to16(utf8_with_surrogates, utf8_with_surrogates + 9, back_inserter(utf16result));
+assert (utf16result.size() == 4);
+assert (utf16result[2] == 0xd834);
+assert (utf16result[3] == 0xdd1e);
+```
+
+In case of an invalid UTF-8 seqence, a `utf8::invalid_utf8` exception is thrown. If `end` does not point to the past-of-end of a UTF-8 seqence, a `utf8::not_enough_room` exception is thrown.
+
+#### utf8::utf32to8
+
+Available in version 3.0 and later. Requires a C++ 11 compliant compiler.
+
+Converts a UTF-32 encoded string to UTF-8.
+
+```cpp
+std::string utf32to8(const std::u32string& s);
+```
+
+`s`: a UTF-32 encoded string.  
+Return value: a UTF-8 encoded string.
+
+Example of use:
+
+```cpp
+u32string utf32string = {0x448, 0x65E5, 0x10346};
+string utf8result = utf32to8(utf32string);
+assert (utf8result.size() == 9);
+```
+
+In case of invalid UTF-32 string, a `utf8::invalid_code_point` exception is thrown.
+
+#### utf8::utf32to8
+
+Available in version 3.2 and later. Requires a C++ 17 compliant compiler.
+
+Converts a UTF-32 encoded string to UTF-8.
+
+```cpp
+std::string utf32to8(std::u32string_view s);
+```
+
+`s`: a UTF-32 encoded string.  
+Return value: a UTF-8 encoded string.
+
+Example of use:
+
+```cpp
+u32string utf32string = {0x448, 0x65E5, 0x10346};
+u32string_view utf32stringview(utf32string);
+string utf8result = utf32to8(utf32stringview);
+assert (utf8result.size() == 9);
+```
+
+In case of invalid UTF-32 string, a `utf8::invalid_code_point` exception is thrown.
+
+
+#### utf8::utf32to8
+
+Available in version 1.0 and later.
+
+Converts a UTF-32 encoded string to UTF-8.
+
+```cpp
+template <typename octet_iterator, typename u32bit_iterator>
+octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result);
+```
+
+`octet_iterator`: an output iterator.  
+`u32bit_iterator`: an input iterator.  
+`start`: an iterator pointing to the beginning of the UTF-32 encoded string to convert.  
+`end`: an iterator pointing to pass-the-end of the UTF-32 encoded string to convert.  
+`result`: an output iterator to the place in the UTF-8 string where to append the result of conversion.  
+Return value: An iterator pointing to the place after the appended UTF-8 string.
+
+Example of use:
+
+```cpp
+int utf32string[] = {0x448, 0x65E5, 0x10346, 0};
+vector<unsigned char> utf8result;
+utf32to8(utf32string, utf32string + 3, back_inserter(utf8result));
+assert (utf8result.size() == 9);
+```
+
+In case of invalid UTF-32 string, a `utf8::invalid_code_point` exception is thrown.
+
+#### utf8::utf8to32
+
+Available in version 3.0 and later. Requires a C++ 11 compliant compiler.
+
+Converts a UTF-8 encoded string to UTF-32.
+
+```cpp
+std::u32string utf8to32(const std::string& s);
+```
+
+`s`: a UTF-8 encoded string.
+Return value: a UTF-32 encoded string.
+
+Example of use:
+
+```cpp
+const char* twochars = "\xe6\x97\xa5\xd1\x88";
+u32string utf32result = utf8to32(twochars);
+assert (utf32result.size() == 2);
+```
+
+In case of an invalid UTF-8 seqence, a `utf8::invalid_utf8` exception is thrown.
+
+#### utf8::utf8to32
+
+Available in version 3.2 and later. Requires a C++ 17 compliant compiler.
+
+Converts a UTF-8 encoded string to UTF-32.
+
+```cpp
+std::u32string utf8to32(std::string_view s);
+```
+
+`s`: a UTF-8 encoded string.
+Return value: a UTF-32 encoded string.
+
+Example of use:
+
+```cpp
+string_view twochars = "\xe6\x97\xa5\xd1\x88";
+u32string utf32result = utf8to32(twochars);
+assert (utf32result.size() == 2);
+```
+
+In case of an invalid UTF-8 seqence, a `utf8::invalid_utf8` exception is thrown.
+
+
+#### utf8::utf8to32
+
+Available in version 1.0 and later.
+
+Converts a UTF-8 encoded string to UTF-32.
+
+```cpp
+template <typename octet_iterator, typename u32bit_iterator>
+u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result);
+```
+
+`octet_iterator`: an input iterator.  
+`u32bit_iterator`: an output iterator.  
+`start`: an iterator pointing to the beginning of the UTF-8 encoded string to convert.  
+`end`: an iterator pointing to pass-the-end of the UTF-8 encoded string to convert.  
+`result`: an output iterator to the place in the UTF-32 string where to append the result of conversion.  
+Return value: An iterator pointing to the place after the appended UTF-32 string.
+
+Example of use:
+
+```cpp
+char* twochars = "\xe6\x97\xa5\xd1\x88";
+vector<int> utf32result;
+utf8to32(twochars, twochars + 5, back_inserter(utf32result));
+assert (utf32result.size() == 2);
+```
+
+In case of an invalid UTF-8 seqence, a `utf8::invalid_utf8` exception is thrown. If `end` does not point to the past-of-end of a UTF-8 seqence, a `utf8::not_enough_room` exception is thrown.
+
+#### utf8::find_invalid
+
+Available in version 3.0 and later. Requires a C++ 11 compliant compiler.
+
+Detects an invalid sequence within a UTF-8 string.
+
+```cpp
+std::size_t find_invalid(const std::string& s);
+```
+
+`s`: a UTF-8 encoded string.
+Return value: the index of the first invalid octet in the UTF-8 string. In case none were found, equals `std::string::npos`.
+
+Example of use:
+
+```cpp
+string utf_invalid = "\xe6\x97\xa5\xd1\x88\xfa";
+auto invalid = find_invalid(utf_invalid);
+assert (invalid == 5);
+```
+
+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 _unchecked_ operations on it.
+
+#### utf8::find_invalid
+
+Available in version 3.2 and later. Requires a C++ 17 compliant compiler.
+
+Detects an invalid sequence within a UTF-8 string.
+
+```cpp
+std::size_t find_invalid(std::string_view s);
+```
+
+`s`: a UTF-8 encoded string.
+Return value: the index of the first invalid octet in the UTF-8 string. In case none were found, equals `std::string_view::npos`.
+
+Example of use:
+
+```cpp
+string_view utf_invalid = "\xe6\x97\xa5\xd1\x88\xfa";
+auto invalid = find_invalid(utf_invalid);
+assert (invalid == 5);
+```
+
+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 _unchecked_ operations on it.
+
+
+#### utf8::find_invalid
+
+Available in version 1.0 and later.
+
+Detects an invalid sequence within a UTF-8 string.
+
+```cpp
+template <typename octet_iterator> 
+octet_iterator find_invalid(octet_iterator start, octet_iterator end);
+```
+
+`octet_iterator`: an input iterator.  
+`start`: an iterator pointing to the beginning of the UTF-8 string to test for validity.  
+`end`: an iterator pointing to pass-the-end of the UTF-8 string to test for validity.  
+Return value: an iterator pointing to the first invalid octet in the UTF-8 string. In case none were found, equals `end`.
+
+Example of use:
+
+```cpp
+char utf_invalid[] = "\xe6\x97\xa5\xd1\x88\xfa";
+char* invalid = find_invalid(utf_invalid, utf_invalid + 6);
+assert (invalid == utf_invalid + 5);
+```
+
+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 _unchecked_ operations on it.
+
+#### utf8::is_valid
+
+Available in version 3.0 and later. Requires a C++ 11 compliant compiler.
+
+Checks whether a string object contains valid UTF-8 encoded text.
+
+```cpp
+bool is_valid(const std::string& s);
+```
+
+`s`: a UTF-8 encoded string.  
+Return value: `true` if the string contains valid UTF-8 encoded text; `false` if not.
+
+Example of use:
+
+```cpp
+char utf_invalid[] = "\xe6\x97\xa5\xd1\x88\xfa";
+bool bvalid = is_valid(utf_invalid);
+assert (bvalid == false);
+```
+
+You may want to use `is_valid` to make sure that a string contains valid UTF-8 text without the need to know where it fails if it is not valid.
+
+#### utf8::is_valid
+
+Available in version 3.2 and later. Requires a C++ 17 compliant compiler.
+
+Checks whether a string object contains valid UTF-8 encoded text.
+
+```cpp
+bool is_valid(std::string_view s);
+```
+
+`s`: a UTF-8 encoded string.  
+Return value: `true` if the string contains valid UTF-8 encoded text; `false` if not.
+
+Example of use:
+
+```cpp
+string_view utf_invalid = "\xe6\x97\xa5\xd1\x88\xfa";
+bool bvalid = is_valid(utf_invalid);
+assert (bvalid == false);
+```
+
+You may want to use `is_valid` to make sure that a string contains valid UTF-8 text without the need to know where it fails if it is not valid.
+
+
+#### utf8::is_valid
+
+Available in version 1.0 and later.
+
+Checks whether a sequence of octets is a valid UTF-8 string.
+
+```cpp
+template <typename octet_iterator> 
+bool is_valid(octet_iterator start, octet_iterator end);
+```
+
+`octet_iterator`: an input iterator.  
+`start`: an iterator pointing to the beginning of the UTF-8 string to test for validity.  
+`end`: an iterator pointing to pass-the-end of the UTF-8 string to test for validity.  
+Return value: `true` if the sequence is a valid UTF-8 string; `false` if not.
+
+Example of use:
+
+```cpp
+char utf_invalid[] = "\xe6\x97\xa5\xd1\x88\xfa";
+bool bvalid = is_valid(utf_invalid, utf_invalid + 6);
+assert (bvalid == false);
+```
+
+`is_valid` is a shorthand for `find_invalid(start, end) == end;`. 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.
+
+#### utf8::replace_invalid
+
+Available in version 3.0 and later. Requires a C++ 11 compliant compiler.
+
+Replaces all invalid UTF-8 sequences within a string with a replacement marker.
+
+```cpp
+std::string replace_invalid(const std::string& s, char32_t replacement);
+std::string replace_invalid(const std::string& s);
+```
+
+`s`: a UTF-8 encoded string.  
+`replacement`: A Unicode code point for the replacement marker. The version without this parameter assumes the value `0xfffd`  
+Return value: A UTF-8 encoded string with replaced invalid sequences.
+
+Example of use:
+
+```cpp
+string invalid_sequence = "a\x80\xe0\xa0\xc0\xaf\xed\xa0\x80z";
+string replace_invalid_result = replace_invalid(invalid_sequence, '?');
+bvalid = is_valid(replace_invalid_result);
+assert (bvalid);
+const string fixed_invalid_sequence = "a????z";
+assert (fixed_invalid_sequence == replace_invalid_result);
+```
+
+#### utf8::replace_invalid
+
+Available in version 3.2 and later. Requires a C++ 17 compliant compiler.
+
+Replaces all invalid UTF-8 sequences within a string with a replacement marker.
+
+```cpp
+std::string replace_invalid(std::string_view s, char32_t replacement);
+std::string replace_invalid(std::string_view s);
+```
+
+`s`: a UTF-8 encoded string.  
+`replacement`: A Unicode code point for the replacement marker. The version without this parameter assumes the value `0xfffd`  
+Return value: A UTF-8 encoded string with replaced invalid sequences.
+
+Example of use:
+
+```cpp
+string_view invalid_sequence = "a\x80\xe0\xa0\xc0\xaf\xed\xa0\x80z";
+string replace_invalid_result = replace_invalid(invalid_sequence, '?');
+bool bvalid = is_valid(replace_invalid_result);
+assert (bvalid);
+const string fixed_invalid_sequence = "a????z";
+assert(fixed_invalid_sequence, replace_invalid_result);
+```
+
+
+#### utf8::replace_invalid
+
+Available in version 2.0 and later.
+
+Replaces all invalid UTF-8 sequences within a string with a replacement marker.
+
+```cpp
+template <typename octet_iterator, typename output_iterator>
+output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out, uint32_t replacement);
+template <typename octet_iterator, typename output_iterator>
+output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out);
+```
+
+`octet_iterator`: an input iterator.  
+`output_iterator`: an output iterator.  
+`start`: an iterator pointing to the beginning of the UTF-8 string to look for invalid UTF-8 sequences.  
+`end`: an iterator pointing to pass-the-end of the UTF-8 string to look for invalid UTF-8 sequences.  
+`out`: An output iterator to the range where the result of replacement is stored.  
+`replacement`: A Unicode code point for the replacement marker. The version without this parameter assumes the value `0xfffd`  
+Return value: An iterator pointing to the place after the UTF-8 string with replaced invalid sequences.
+
+Example of use:
+
+```cpp
+char invalid_sequence[] = "a\x80\xe0\xa0\xc0\xaf\xed\xa0\x80z";
+vector<char> replace_invalid_result;
+replace_invalid (invalid_sequence, invalid_sequence + sizeof(invalid_sequence), back_inserter(replace_invalid_result), '?');
+bvalid = is_valid(replace_invalid_result.begin(), replace_invalid_result.end());
+assert (bvalid);
+char* fixed_invalid_sequence = "a????z";
+assert (std::equal(replace_invalid_result.begin(), replace_invalid_result.end(), fixed_invalid_sequence));
+```
+
+`replace_invalid` 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, `out` must not be in the `[start, end]` range.
+
+#### utf8::starts_with_bom
+
+Available in version 3.0 and later. Requires a C++ 11 compliant compiler.
+
+Checks whether a string starts with a UTF-8 byte order mark (BOM)
+
+```cpp
+bool starts_with_bom(const std::string& s);
+```
+
+`s`: a UTF-8 encoded string.
+Return value: `true` if the string starts with a UTF-8 byte order mark; `false` if not.
+
+Example of use:
+
+```cpp
+string byte_order_mark = {char(0xef), char(0xbb), char(0xbf)};
+bool bbom = starts_with_bom(byte_order_mark);
+assert (bbom == true);
+string threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88";
+bool no_bbom = starts_with_bom(threechars);
+assert (no_bbom == false);
+ ```
+
+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.
+
+
+#### utf8::starts_with_bom
+
+Available in version 3.2 and later. Requires a C++ 17 compliant compiler.
+
+Checks whether a string starts with a UTF-8 byte order mark (BOM)
+
+```cpp
+bool starts_with_bom(std::string_view s);
+```
+
+`s`: a UTF-8 encoded string.
+Return value: `true` if the string starts with a UTF-8 byte order mark; `false` if not.
+
+Example of use:
+
+```cpp
+string byte_order_mark = {char(0xef), char(0xbb), char(0xbf)};
+string_view byte_order_mark_view(byte_order_mark);
+bool bbom = starts_with_bom(byte_order_mark_view);
+assert (bbom);
+string_view threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88";
+bool no_bbom = starts_with_bom(threechars);
+assert (!no_bbom);
+ ```
+
+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.
+
+
+#### utf8::starts_with_bom
+
+Available in version 2.3 and later.
+
+Checks whether an octet sequence starts with a UTF-8 byte order mark (BOM)
+
+```cpp
+template <typename octet_iterator> 
+bool starts_with_bom (octet_iterator it, octet_iterator end);
+```
+
+`octet_iterator`: an input iterator.  
+`it`: beginning of the octet sequence to check  
+`end`: pass-end of the sequence to check  
+Return value: `true` if the sequence starts with a UTF-8 byte order mark; `false` if not.
+
+Example of use:
+
+```cpp
+unsigned char byte_order_mark[] = {0xef, 0xbb, 0xbf};
+bool bbom = starts_with_bom(byte_order_mark, byte_order_mark + sizeof(byte_order_mark));
+assert (bbom == true);
+```
+
+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.
+
+### Types From utf8 Namespace
+
+#### utf8::exception
+
+Available in version 2.3 and later.
+
+Base class for the exceptions thrown by UTF CPP library functions.
+
+```cpp
+class exception : public std::exception {};
+```
+
+Example of use:
+
+```cpp
+try {
+  code_that_uses_utf_cpp_library();
+}
+catch(const utf8::exception& utfcpp_ex) {
+  cerr << utfcpp_ex.what();
+}
+```
+
+#### utf8::invalid_code_point
+
+Available in version 1.0 and later.
+
+Thrown by UTF8 CPP functions such as `advance` and `next` if an UTF-8 sequence represents and invalid code point.
+
+```cpp
+class invalid_code_point : public exception {
+public: 
+    uint32_t code_point() const;
+};
+```
+
+Member function `code_point()` can be used to determine the invalid code point that caused the exception to be thrown.
+
+#### utf8::invalid_utf8
+
+Available in version 1.0 and later.
+
+Thrown by UTF8 CPP functions such as `next` and `prior` if an invalid UTF-8 sequence is detected during decoding.
+
+```cpp
+class invalid_utf8 : public exception {
+public: 
+    uint8_t utf8_octet() const;
+};
+```
+
+Member function `utf8_octet()` can be used to determine the beginning of the byte sequence that caused the exception to be thrown.
+
+#### utf8::invalid_utf16
+
+Available in version 1.0 and later.
+
+Thrown by UTF8 CPP function `utf16to8` if an invalid UTF-16 sequence is detected during decoding.
+
+```cpp
+class invalid_utf16 : public exception {
+public: 
+    uint16_t utf16_word() const;
+};
+```
+
+Member function `utf16_word()` can be used to determine the UTF-16 code unit that caused the exception to be thrown.
+
+#### utf8::not_enough_room
+
+Available in version 1.0 and later.
+
+Thrown by UTF8 CPP functions such as `next` if the end of the decoded UTF-8 sequence was reached before the code point was decoded.
+
+```cpp
+class not_enough_room : public exception {};
+```
+
+#### utf8::iterator
+
+Available in version 2.0 and later.
+
+Adapts the underlying octet iterator to iterate over the sequence of code points, rather than raw octets.
+
+```cpp
+template <typename octet_iterator>
+class iterator;
+```
+
+##### Member functions
+
+`iterator();` the deafult constructor; the underlying octet_iterator is constructed with its default constructor.
+
+`explicit iterator (const octet_iterator& octet_it, const octet_iterator& range_start, const octet_iterator& range_end);` a constructor that initializes the underlying octet_iterator with octet_it and sets the range in which the iterator is considered valid.
+
+`octet_iterator base () const;` returns the underlying octet_iterator.
+
+`uint32_t operator * () const;` decodes the utf-8 sequence the underlying octet_iterator is pointing to and returns the code point.
+
+`bool operator == (const iterator& rhs) const;` returns `true` if the two underlaying iterators are equal.
+
+`bool operator != (const iterator& rhs) const;` returns `true` if the two underlaying iterators are not equal.
+
+`iterator& operator ++ ();` the prefix increment - moves the iterator to the next UTF-8 encoded code point.
+
+`iterator operator ++ (int);` the postfix increment - moves the iterator to the next UTF-8 encoded code point and returns the current one.
+
+`iterator& operator -- ();` the prefix decrement - moves the iterator to the previous UTF-8 encoded code point.
+
+`iterator operator -- (int);` the postfix decrement - moves the iterator to the previous UTF-8 encoded code point and returns the current one.
+
+Example of use:
+
+```cpp
+char* threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88";
+utf8::iterator<char*> it(threechars, threechars, threechars + 9);
+utf8::iterator<char*> it2 = it;
+assert (it2 == it);
+assert (*it == 0x10346);
+assert (*(++it) == 0x65e5);
+assert ((*it++) == 0x65e5);
+assert (*it == 0x0448);
+assert (it != it2);
+utf8::iterator<char*> endit (threechars + 9, threechars, threechars + 9);  
+assert (++it == endit);
+assert (*(--it) == 0x0448);
+assert ((*it--) == 0x0448);
+assert (*it == 0x65e5);
+assert (--it == utf8::iterator<char*>(threechars, threechars, threechars + 9));
+assert (*it == 0x10346);
+```
+
+The purpose of `utf8::iterator` 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 `utf8::next()` and `utf8::prior()` functions.
+
+Note that `utf8::iterator` 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 `begin` and `end`, i.e.:
+
+```cpp
+std::string s = "example";
+utf8::iterator i (s.begin(), s.begin(), s.end());
+```
+
+### Functions From utf8::unchecked Namespace
+
+#### utf8::unchecked::append
+
+Available in version 1.0 and later.
+
+Encodes a 32 bit code point as a UTF-8 sequence of octets and appends the sequence to a UTF-8 string.
+
+```cpp
+template <typename octet_iterator>
+octet_iterator append(uint32_t cp, octet_iterator result);
+```
+
+`cp`: A 32 bit integer representing a code point to append to the sequence.  
+`result`: An output iterator to the place in the sequence where to append the code point.  
+Return value: An iterator pointing to the place after the newly appended sequence.
+
+Example of use:
+
+```cpp
+unsigned char u[5] = {0,0,0,0,0};
+unsigned char* end = unchecked::append(0x0448, u);
+assert (u[0] == 0xd1 && u[1] == 0x88 && u[2] == 0 && u[3] == 0 && u[4] == 0);
+```
+
+This is a faster but less safe version of `utf8::append`. It does not check for validity of the supplied code point, and may produce an invalid UTF-8 sequence.
+
+#### utf8::unchecked::next
+
+Available in version 1.0 and later.
+
+Given the iterator to the beginning of a UTF-8 sequence, it returns the code point and moves the iterator to the next position.
+
+```cpp
+template <typename octet_iterator>
+uint32_t next(octet_iterator& it);
+```
+
+`it`: 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.  
+ Return value: the 32 bit representation of the processed UTF-8 code point.
+
+Example of use:
+
+```cpp
+char* twochars = "\xe6\x97\xa5\xd1\x88";
+char* w = twochars;
+int cp = unchecked::next(w);
+assert (cp == 0x65e5);
+assert (w == twochars + 3);
+```
+
+This is a faster but less safe version of `utf8::next`. It does not check for validity of the supplied UTF-8 sequence.
+
+#### utf8::unchecked::peek_next
+
+Available in version 2.1 and later.
+
+Given the iterator to the beginning of a UTF-8 sequence, it returns the code point.
+
+```cpp
+template <typename octet_iterator>
+uint32_t peek_next(octet_iterator it);
+```
+
+`it`: an iterator pointing to the beginning of an UTF-8 encoded code point.  
+Return value: the 32 bit representation of the processed UTF-8 code point.
+
+Example of use:
+
+```cpp
+char* twochars = "\xe6\x97\xa5\xd1\x88";
+char* w = twochars;
+int cp = unchecked::peek_next(w);
+assert (cp == 0x65e5);
+assert (w == twochars);
+```
+
+This is a faster but less safe version of `utf8::peek_next`. It does not check for validity of the supplied UTF-8 sequence.
+
+#### utf8::unchecked::prior
+
+Available in version 1.02 and later.
+
+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.
+
+```cpp
+template <typename octet_iterator>
+uint32_t prior(octet_iterator& it);
+```
+
+`it`: 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.  
+ Return value: the 32 bit representation of the previous code point.
+
+Example of use:
+
+```cpp
+char* twochars = "\xe6\x97\xa5\xd1\x88";
+char* w = twochars + 3;
+int cp = unchecked::prior (w);
+assert (cp == 0x65e5);
+assert (w == twochars);
+```
+
+This is a faster but less safe version of `utf8::prior`. It does not check for validity of the supplied UTF-8 sequence and offers no boundary checking.
+
+#### utf8::unchecked::advance
+
+Available in version 1.0 and later.
+
+Advances an iterator by the specified number of code points within an UTF-8 sequence.
+
+```cpp
+template <typename octet_iterator, typename distance_type>
+void advance (octet_iterator& it, distance_type n);
+```
+
+`it`: 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.
+`n`: number of code points `it` should be advanced. A negative value means decrement.
+
+Example of use:
+
+```cpp
+char* twochars = "\xe6\x97\xa5\xd1\x88";
+char* w = twochars;
+unchecked::advance (w, 2);
+assert (w == twochars + 5);
+```
+
+This is a faster but less safe version of `utf8::advance`. It does not check for validity of the supplied UTF-8 sequence and offers no boundary checking.
+
+#### utf8::unchecked::distance
+
+Available in version 1.0 and later.
+
+Given the iterators to two UTF-8 encoded code points in a seqence, returns the number of code points between them.
+
+```cpp
+template <typename octet_iterator>
+typename std::iterator_traits<octet_iterator>::difference_type distance (octet_iterator first, octet_iterator last);
+```
+
+`first`: an iterator to a beginning of a UTF-8 encoded code point.  
+`last`: 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.  
+Return value: the distance between the iterators, in code points.
+
+Example of use:
+
+```cpp
+char* twochars = "\xe6\x97\xa5\xd1\x88";
+size_t dist = utf8::unchecked::distance(twochars, twochars + 5);
+assert (dist == 2);
+```
+
+This is a faster but less safe version of `utf8::distance`. It does not check for validity of the supplied UTF-8 sequence.
+
+#### utf8::unchecked::utf16to8
+
+Available in version 1.0 and later.
+
+Converts a UTF-16 encoded string to UTF-8.
+
+```cpp
+template <typename u16bit_iterator, typename octet_iterator>
+octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result);
+```
+
+`start`: an iterator pointing to the beginning of the UTF-16 encoded string to convert.  
+`end`: an iterator pointing to pass-the-end of the UTF-16 encoded string to convert.  
+`result`: an output iterator to the place in the UTF-8 string where to append the result of conversion.  
+Return value: An iterator pointing to the place after the appended UTF-8 string.
+
+Example of use:
+
+```cpp
+unsigned short utf16string[] = {0x41, 0x0448, 0x65e5, 0xd834, 0xdd1e};
+vector<unsigned char> utf8result;
+unchecked::utf16to8(utf16string, utf16string + 5, back_inserter(utf8result));
+assert (utf8result.size() == 10);    
+```
+
+This is a faster but less safe version of `utf8::utf16to8`. It does not check for validity of the supplied UTF-16 sequence.
+
+#### utf8::unchecked::utf8to16
+
+Available in version 1.0 and later.
+
+Converts an UTF-8 encoded string to UTF-16
+
+```cpp
+template <typename u16bit_iterator, typename octet_iterator>
+u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result);
+```
+
+`start`: an iterator pointing to the beginning of the UTF-8 encoded string to convert. < br /> `end`: an iterator pointing to pass-the-end of the UTF-8 encoded string to convert.  
+`result`: an output iterator to the place in the UTF-16 string where to append the result of conversion.  
+Return value: An iterator pointing to the place after the appended UTF-16 string.
+
+Example of use:
+
+```cpp
+char utf8_with_surrogates[] = "\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e";
+vector <unsigned short> utf16result;
+unchecked::utf8to16(utf8_with_surrogates, utf8_with_surrogates + 9, back_inserter(utf16result));
+assert (utf16result.size() == 4);
+assert (utf16result[2] == 0xd834);
+assert (utf16result[3] == 0xdd1e);
+```
+
+This is a faster but less safe version of `utf8::utf8to16`. It does not check for validity of the supplied UTF-8 sequence.
+
+#### utf8::unchecked::utf32to8
+
+Available in version 1.0 and later.
+
+Converts a UTF-32 encoded string to UTF-8.
+
+```cpp
+template <typename octet_iterator, typename u32bit_iterator>
+octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result);
+```
+
+`start`: an iterator pointing to the beginning of the UTF-32 encoded string to convert.  
+`end`: an iterator pointing to pass-the-end of the UTF-32 encoded string to convert.  
+`result`: an output iterator to the place in the UTF-8 string where to append the result of conversion.  
+Return value: An iterator pointing to the place after the appended UTF-8 string.
+
+Example of use:
+
+```cpp
+int utf32string[] = {0x448, 0x65e5, 0x10346, 0};
+vector<unsigned char> utf8result;
+utf32to8(utf32string, utf32string + 3, back_inserter(utf8result));
+assert (utf8result.size() == 9);
+```
+
+This is a faster but less safe version of `utf8::utf32to8`. It does not check for validity of the supplied UTF-32 sequence.
+
+#### utf8::unchecked::utf8to32
+
+Available in version 1.0 and later.
+
+Converts a UTF-8 encoded string to UTF-32.
+
+```cpp
+template <typename octet_iterator, typename u32bit_iterator>
+u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result);
+```
+
+`start`: an iterator pointing to the beginning of the UTF-8 encoded string to convert.  
+`end`: an iterator pointing to pass-the-end of the UTF-8 encoded string to convert.  
+`result`: an output iterator to the place in the UTF-32 string where to append the result of conversion.  
+Return value: An iterator pointing to the place after the appended UTF-32 string.
+
+Example of use:
+
+```cpp
+char* twochars = "\xe6\x97\xa5\xd1\x88";
+vector<int> utf32result;
+unchecked::utf8to32(twochars, twochars + 5, back_inserter(utf32result));
+assert (utf32result.size() == 2);
+```
+
+This is a faster but less safe version of `utf8::utf8to32`. It does not check for validity of the supplied UTF-8 sequence.
+
+#### utf8::unchecked::replace_invalid
+
+Available in version 3.1 and later.
+
+Replaces all invalid UTF-8 sequences within a string with a replacement marker.
+
+```cpp
+template <typename octet_iterator, typename output_iterator>
+output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out, uint32_t replacement);
+template <typename octet_iterator, typename output_iterator>
+output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out);
+```
+
+`octet_iterator`: an input iterator.  
+`output_iterator`: an output iterator.  
+`start`: an iterator pointing to the beginning of the UTF-8 string to look for invalid UTF-8 sequences.  
+`end`: an iterator pointing to pass-the-end of the UTF-8 string to look for invalid UTF-8 sequences.  
+`out`: An output iterator to the range where the result of replacement is stored.  
+`replacement`: A Unicode code point for the replacement marker. The version without this parameter assumes the value `0xfffd`  
+Return value: An iterator pointing to the place after the UTF-8 string with replaced invalid sequences.
+
+Example of use:
+
+```cpp
+char invalid_sequence[] = "a\x80\xe0\xa0\xc0\xaf\xed\xa0\x80z";
+vector<char> replace_invalid_result;
+unchecked::replace_invalid (invalid_sequence, invalid_sequence + sizeof(invalid_sequence), back_inserter(replace_invalid_result), '?');
+bvalid = utf8::is_valid(replace_invalid_result.begin(), replace_invalid_result.end());
+assert (bvalid);
+char* fixed_invalid_sequence = "a????z";
+assert (std::equal(replace_invalid_result.begin(), replace_invalid_result.end(), fixed_invalid_sequence));
+```
+
+`replace_invalid` 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, `out` must not be in the `[start, end]` range.
+
+Unlike `utf8::replace_invalid`, this function does not verify validity of the replacement marker.
+
+### Types From utf8::unchecked Namespace
+
+#### utf8::iterator
+
+Available in version 2.0 and later.
+
+Adapts the underlying octet iterator to iterate over the sequence of code points, rather than raw octets.
+
+```cpp
+template <typename octet_iterator>
+class iterator;
+```
+
+##### Member functions
+
+`iterator();` the deafult constructor; the underlying octet_iterator is constructed with its default constructor.
+
+`explicit iterator (const octet_iterator& octet_it);` a constructor that initializes the underlying octet_iterator with `octet_it`.
+
+`octet_iterator base () const;` returns the underlying octet_iterator.
+
+`uint32_t operator * () const;` decodes the utf-8 sequence the underlying octet_iterator is pointing to and returns the code point.
+
+`bool operator == (const iterator& rhs) const;` returns `true` if the two underlaying iterators are equal.
+
+`bool operator != (const iterator& rhs) const;` returns `true` if the two underlaying iterators are not equal.
+
+`iterator& operator ++ ();` the prefix increment - moves the iterator to the next UTF-8 encoded code point.
+
+`iterator operator ++ (int);` the postfix increment - moves the iterator to the next UTF-8 encoded code point and returns the current one.
+
+`iterator& operator -- ();` the prefix decrement - moves the iterator to the previous UTF-8 encoded code point.
+
+`iterator operator -- (int);` the postfix decrement - moves the iterator to the previous UTF-8 encoded code point and returns the current one.
+
+Example of use:
+
+```cpp
+char* threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88";
+utf8::unchecked::iterator<char*> un_it(threechars);
+utf8::unchecked::iterator<char*> un_it2 = un_it;
+assert (un_it2 == un_it);
+assert (*un_it == 0x10346);
+assert (*(++un_it) == 0x65e5);
+assert ((*un_it++) == 0x65e5);
+assert (*un_it == 0x0448);
+assert (un_it != un_it2);
+utf8::::unchecked::iterator<char*> un_endit (threechars + 9);  
+assert (++un_it == un_endit);
+assert (*(--un_it) == 0x0448);
+assert ((*un_it--) == 0x0448);
+assert (*un_it == 0x65e5);
+assert (--un_it == utf8::unchecked::iterator<char*>(threechars));
+assert (*un_it == 0x10346);
+```
+
+This is an unchecked version of `utf8::iterator`. It is faster in many cases, but offers no validity or range checks.
+
+## Links
+
+1.  [The Unicode Consortium](http://www.unicode.org/).
+2.  [ICU Library](http://icu.sourceforge.net/).
+3.  [UTF-8 at Wikipedia](http://en.wikipedia.org/wiki/UTF-8)
+4.  [UTF-8 and Unicode FAQ for Unix/Linux](http://www.cl.cam.ac.uk/~mgk25/unicode.html)

contrib/utf8cpp/doc/ReleaseNotes

@@ -1,12 +0,0 @@
-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

contrib/utf8cpp/doc/utf8cpp.html

@@ -1,1789 +0,0 @@
-<!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>

contrib/utf8cpp/source/utf8/checked.h

@@ -42,7 +42,7 @@ namespace utf8
         uint32_t cp;
     public:
         invalid_code_point(uint32_t codepoint) : cp(codepoint) {}
-        virtual const char* what() const NOEXCEPT OVERRIDE { return "Invalid code point"; }
+        virtual const char* what() const UTF_CPP_NOEXCEPT UTF_CPP_OVERRIDE { return "Invalid code point"; }
         uint32_t code_point() const {return cp;}
     };
 
@@ -50,7 +50,8 @@ namespace utf8
         uint8_t u8;
     public:
         invalid_utf8 (uint8_t u) : u8(u) {}
-        virtual const char* what() const NOEXCEPT OVERRIDE { return "Invalid UTF-8"; }
+        invalid_utf8 (char c) : u8(static_cast<uint8_t>(c)) {}
+        virtual const char* what() const UTF_CPP_NOEXCEPT UTF_CPP_OVERRIDE { return "Invalid UTF-8"; }
         uint8_t utf8_octet() const {return u8;}
     };
 
@@ -58,13 +59,13 @@ namespace utf8
         uint16_t u16;
     public:
         invalid_utf16 (uint16_t u) : u16(u) {}
-        virtual const char* what() const NOEXCEPT OVERRIDE { return "Invalid UTF-16"; }
+        virtual const char* what() const UTF_CPP_NOEXCEPT UTF_CPP_OVERRIDE { return "Invalid UTF-16"; }
         uint16_t utf16_word() const {return u16;}
     };
 
     class not_enough_room : public exception {
     public:
-        virtual const char* what() const NOEXCEPT OVERRIDE { return "Not enough space"; }
+        virtual const char* what() const UTF_CPP_NOEXCEPT UTF_CPP_OVERRIDE { return "Not enough space"; }
     };
 
     /// The library API - functions intended to be called by the users
@@ -75,24 +76,7 @@ namespace utf8
         if (!utf8::internal::is_code_point_valid(cp))
             throw invalid_code_point(cp);
 
-        if (cp < 0x80)                        // one octet
-            *(result++) = static_cast<uint8_t>(cp);
-        else if (cp < 0x800) {                // two octets
-            *(result++) = static_cast<uint8_t>((cp >> 6)            | 0xc0);
-            *(result++) = static_cast<uint8_t>((cp & 0x3f)          | 0x80);
-        }
-        else if (cp < 0x10000) {              // three octets
-            *(result++) = static_cast<uint8_t>((cp >> 12)           | 0xe0);
-            *(result++) = static_cast<uint8_t>(((cp >> 6) & 0x3f)   | 0x80);
-            *(result++) = static_cast<uint8_t>((cp & 0x3f)          | 0x80);
-        }
-        else {                                // four octets
-            *(result++) = static_cast<uint8_t>((cp >> 18)           | 0xf0);
-            *(result++) = static_cast<uint8_t>(((cp >> 12) & 0x3f)  | 0x80);
-            *(result++) = static_cast<uint8_t>(((cp >> 6) & 0x3f)   | 0x80);
-            *(result++) = static_cast<uint8_t>((cp & 0x3f)          | 0x80);
-        }
-        return result;
+        return internal::append(cp, result);
     }
 
     template <typename octet_iterator, typename output_iterator>
@@ -148,7 +132,7 @@ namespace utf8
             case internal::INVALID_LEAD :
             case internal::INCOMPLETE_SEQUENCE :
             case internal::OVERLONG_SEQUENCE :
-                throw invalid_utf8(*it);
+                throw invalid_utf8(static_cast<uint8_t>(*it));
             case internal::INVALID_CODE_POINT :
                 throw invalid_code_point(cp);
         }
@@ -325,7 +309,9 @@ namespace utf8
 
 } // namespace utf8
 
-#if UTF_CPP_CPLUSPLUS >= 201103L // C++ 11 or later
+#if UTF_CPP_CPLUSPLUS >= 201703L // C++ 17 or later
+#include "cpp17.h"
+#elif UTF_CPP_CPLUSPLUS >= 201103L // C++ 11 or later
 #include "cpp11.h"
 #endif // C++ 11 or later
 

contrib/utf8cpp/source/utf8/core.h

@@ -39,11 +39,11 @@ DEALINGS IN THE SOFTWARE.
 #endif
 
 #if UTF_CPP_CPLUSPLUS >= 201103L // C++ 11 or later
-    #define OVERRIDE override
-    #define NOEXCEPT noexcept
+    #define UTF_CPP_OVERRIDE override
+    #define UTF_CPP_NOEXCEPT noexcept
 #else // C++ 98/03
-    #define OVERRIDE
-    #define NOEXCEPT throw()
+    #define UTF_CPP_OVERRIDE
+    #define UTF_CPP_NOEXCEPT throw()
 #endif // C++ 11 or later
 
 
@@ -297,6 +297,55 @@ namespace internal
         return utf8::internal::validate_next(it, end, ignored);
     }
 
+    // Internal implementation of both checked and unchecked append() function
+    // This function will be invoked by the overloads below, as they will know
+    // the octet_type.
+    template <typename octet_iterator, typename octet_type>
+    octet_iterator append(uint32_t cp, octet_iterator result) {
+        if (cp < 0x80)                        // one octet
+            *(result++) = static_cast<octet_type>(cp);
+        else if (cp < 0x800) {                // two octets
+            *(result++) = static_cast<octet_type>((cp >> 6)          | 0xc0);
+            *(result++) = static_cast<octet_type>((cp & 0x3f)        | 0x80);
+        }
+        else if (cp < 0x10000) {              // three octets
+            *(result++) = static_cast<octet_type>((cp >> 12)         | 0xe0);
+            *(result++) = static_cast<octet_type>(((cp >> 6) & 0x3f) | 0x80);
+            *(result++) = static_cast<octet_type>((cp & 0x3f)        | 0x80);
+        }
+        else {                                // four octets
+            *(result++) = static_cast<octet_type>((cp >> 18)         | 0xf0);
+            *(result++) = static_cast<octet_type>(((cp >> 12) & 0x3f)| 0x80);
+            *(result++) = static_cast<octet_type>(((cp >> 6) & 0x3f) | 0x80);
+            *(result++) = static_cast<octet_type>((cp & 0x3f)        | 0x80);
+        }
+        return result;
+    }
+    
+    // One of the following overloads will be invoked from the API calls
+
+    // A simple (but dangerous) case: the caller appends byte(s) to a char array
+    inline char* append(uint32_t cp, char* result) {
+        return append<char*, char>(cp, result);
+    }
+
+    // Hopefully, most common case: the caller uses back_inserter
+    // i.e. append(cp, std::back_inserter(str));
+    template<typename container_type>
+    std::back_insert_iterator<container_type> append
+            (uint32_t cp, std::back_insert_iterator<container_type> result) {
+        return append<std::back_insert_iterator<container_type>,
+            typename container_type::value_type>(cp, result);
+    }
+
+    // The caller uses some other kind of output operator - not covered above
+    // Note that in this case we are not able to determine octet_type
+    // so we assume it's uint_8; that can cause a conversion warning if we are wrong.
+    template <typename octet_iterator>
+    octet_iterator append(uint32_t cp, octet_iterator result) {
+        return append<octet_iterator, uint8_t>(cp, result);
+    }
+
 } // namespace internal
 
     /// The library API - functions intended to be called by the users

contrib/utf8cpp/source/utf8/cpp11.h

@@ -70,7 +70,7 @@ namespace utf8
     inline std::size_t find_invalid(const std::string& s)
     {
         std::string::const_iterator invalid = find_invalid(s.begin(), s.end());
-        return (invalid == s.end()) ? std::string::npos : (invalid - s.begin());
+        return (invalid == s.end()) ? std::string::npos : static_cast<std::size_t>(invalid - s.begin());
     }
 
     inline bool is_valid(const std::string& s)

contrib/utf8cpp/source/utf8/cpp17.h

@@ -0,0 +1,103 @@
+// Copyright 2018 Nemanja Trifunovic
+
+/*
+Permission is hereby granted, free of charge, to any person or organization
+obtaining a copy of the software and accompanying documentation covered by
+this license (the "Software") to use, reproduce, display, distribute,
+execute, and transmit the Software, and to prepare derivative works of the
+Software, and to permit third-parties to whom the Software is furnished to
+do so, all subject to the following:
+
+The copyright notices in the Software and this entire statement, including
+the above license grant, this restriction and the following disclaimer,
+must be included in all copies of the Software, in whole or in part, and
+all derivative works of the Software, unless such copies or derivative
+works are solely in the form of machine-executable object code generated by
+a source language processor.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT
+SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE
+FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE,
+ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+DEALINGS IN THE SOFTWARE.
+*/
+
+
+#ifndef UTF8_FOR_CPP_7e906c01_03a3_4daf_b420_ea7ea952b3c9
+#define UTF8_FOR_CPP_7e906c01_03a3_4daf_b420_ea7ea952b3c9
+
+#include "checked.h"
+#include <string>
+
+namespace utf8
+{
+
+    inline void append(char32_t cp, std::string& s)
+    {
+        append(uint32_t(cp), std::back_inserter(s));
+    }
+
+    inline std::string utf16to8(std::u16string_view s)
+    {
+        std::string result;
+        utf16to8(s.begin(), s.end(), std::back_inserter(result));
+        return result;
+    }
+
+    inline std::u16string utf8to16(std::string_view s)
+    {
+        std::u16string result;
+        utf8to16(s.begin(), s.end(), std::back_inserter(result));
+        return result;
+    }
+
+    inline std::string utf32to8(std::u32string_view s)
+    {
+        std::string result;
+        utf32to8(s.begin(), s.end(), std::back_inserter(result));
+        return result;
+    }
+
+    inline std::u32string utf8to32(std::string_view s)
+    {
+        std::u32string result;
+        utf8to32(s.begin(), s.end(), std::back_inserter(result));
+        return result;
+    }
+
+    inline std::size_t find_invalid(std::string_view s)
+    {
+        std::string_view::const_iterator invalid = find_invalid(s.begin(), s.end());
+        return (invalid == s.end()) ? std::string_view::npos : static_cast<std::size_t>(invalid - s.begin());
+    }
+
+    inline bool is_valid(std::string_view s)
+    {
+        return is_valid(s.begin(), s.end());
+    }
+
+    inline std::string replace_invalid(std::string_view s, char32_t replacement)
+    {
+        std::string result;
+        replace_invalid(s.begin(), s.end(), std::back_inserter(result), replacement);
+        return result;
+    }
+
+    inline std::string replace_invalid(std::string_view s)
+    {
+        std::string result;
+        replace_invalid(s.begin(), s.end(), std::back_inserter(result));
+        return result;
+    }
+
+    inline bool starts_with_bom(std::string_view s)
+    {
+        return starts_with_bom(s.begin(), s.end());
+    }
+ 
+} // namespace utf8
+
+#endif // header guard
+

contrib/utf8cpp/source/utf8/unchecked.h

@@ -37,24 +37,7 @@ namespace utf8
         template <typename octet_iterator>
         octet_iterator append(uint32_t cp, octet_iterator result)
         {
-            if (cp < 0x80)                        // one octet
-                *(result++) = static_cast<uint8_t>(cp);
-            else if (cp < 0x800) {                // two octets
-                *(result++) = static_cast<uint8_t>((cp >> 6)          | 0xc0);
-                *(result++) = static_cast<uint8_t>((cp & 0x3f)        | 0x80);
-            }
-            else if (cp < 0x10000) {              // three octets
-                *(result++) = static_cast<uint8_t>((cp >> 12)         | 0xe0);
-                *(result++) = static_cast<uint8_t>(((cp >> 6) & 0x3f) | 0x80);
-                *(result++) = static_cast<uint8_t>((cp & 0x3f)        | 0x80);
-            }
-            else {                                // four octets
-                *(result++) = static_cast<uint8_t>((cp >> 18)         | 0xf0);
-                *(result++) = static_cast<uint8_t>(((cp >> 12) & 0x3f)| 0x80);
-                *(result++) = static_cast<uint8_t>(((cp >> 6) & 0x3f) | 0x80);
-                *(result++) = static_cast<uint8_t>((cp & 0x3f)        | 0x80);
-            }
-            return result;
+            return internal::append(cp, result);
         }
 
         template <typename octet_iterator, typename output_iterator>

port/PyAssimp/setup.py

@@ -8,7 +8,7 @@ def readme():
         return f.read()
 
 setup(name='pyassimp',
-      version='4.1.4',
+      version='5.2.5',
       license='ISC',
       description='Python bindings for the Open Asset Import Library (ASSIMP)',
       long_description=readme(),

test/models/OBJ/only_a_part_of_vertexcolors.obj

@@ -0,0 +1,11 @@
+g cube
+
+v  0.0  0.0  0.0
+v  0.0  0.0  1.0  0.0  0.0  1.0
+v  0.0  1.0  0.0
+v  1.0  0.0  0.0  1.0  0.6  0.3
+v  1.0  1.0  0.0
+
+f 1 2 3
+f 1 4 3
+f 2 5 4

test/unit/utObjImportExport.cpp

@@ -286,6 +286,54 @@ TEST_F(utObjImportExport, issue1923_vertex_color_Test) {
     delete scene;
 }
 
+TEST_F(utObjImportExport, only_a_part_of_vertex_colors_Test) {
+    ::Assimp::Importer importer;
+    const aiScene *const scene = importer.ReadFile(ASSIMP_TEST_MODELS_DIR "/OBJ/only_a_part_of_vertexcolors.obj", aiProcess_ValidateDataStructure);
+    EXPECT_NE(nullptr, scene);
+
+    EXPECT_EQ(scene->mNumMeshes, 1U);
+    const aiMesh *const mesh = scene->mMeshes[0];
+    EXPECT_EQ(mesh->mNumVertices, 9U);
+    EXPECT_EQ(mesh->mNumFaces, 3U);
+    EXPECT_TRUE(mesh->HasVertexColors(0));
+
+    const aiVector3D *const vertices = mesh->mVertices;
+    const aiColor4D *const colors = mesh->mColors[0];
+    EXPECT_EQ(aiVector3D(0.0f, 0.0f, 0.0f), vertices[0]);
+    EXPECT_EQ(aiColor4D(0.0f, 0.0f, 0.0f, 1.0f), colors[0]);
+    EXPECT_EQ(aiVector3D(0.0f, 0.0f, 1.0f), vertices[1]);
+    EXPECT_EQ(aiColor4D(0.0f, 0.0f, 1.0f, 1.0f), colors[1]);
+    EXPECT_EQ(aiVector3D(0.0f, 1.0f, 0.0f), vertices[2]);
+    EXPECT_EQ(aiColor4D(0.0f, 0.0f, 0.0f, 1.0f), colors[2]);
+    EXPECT_EQ(aiVector3D(0.0f, 0.0f, 0.0f), vertices[3]);
+    EXPECT_EQ(aiColor4D(0.0f, 0.0f, 0.0f, 1.0f), colors[3]);
+    EXPECT_EQ(aiVector3D(1.0f, 0.0f, 0.0f), vertices[4]);
+    EXPECT_EQ(aiColor4D(1.0f, 0.6f, 0.3f, 1.0f), colors[4]);
+    EXPECT_EQ(aiVector3D(0.0f, 1.0f, 0.0f), vertices[5]);
+    EXPECT_EQ(aiColor4D(0.0f, 0.0f, 0.0f, 1.0f), colors[5]);
+    EXPECT_EQ(aiVector3D(0.0f, 0.0f, 1.0f), vertices[6]);
+    EXPECT_EQ(aiColor4D(0.0f, 0.0f, 1.0f, 1.0f), colors[6]);
+    EXPECT_EQ(aiVector3D(1.0f, 1.0f, 0.0f), vertices[7]);
+    EXPECT_EQ(aiColor4D(0.0f, 0.0f, 0.0f, 1.0f), colors[7]);
+    EXPECT_EQ(aiVector3D(1.0f, 0.0f, 0.0f), vertices[8]);
+    EXPECT_EQ(aiColor4D(1.0f, 0.6f, 0.3f, 1.0f), colors[8]);
+
+#ifndef ASSIMP_BUILD_NO_EXPORT
+    ::Assimp::Exporter exporter;
+    EXPECT_EQ(aiReturn_SUCCESS, exporter.Export(scene, "obj", ASSIMP_TEST_MODELS_DIR "/OBJ/test_out.obj"));
+#endif // ASSIMP_BUILD_NO_EXPORT
+}
+
+TEST_F(utObjImportExport, no_vertex_colors_Test) {
+    ::Assimp::Importer importer;
+    const aiScene *const scene = importer.ReadFile(ASSIMP_TEST_MODELS_DIR "/OBJ/box.obj", aiProcess_ValidateDataStructure);
+    EXPECT_NE(nullptr, scene);
+
+    EXPECT_EQ(scene->mNumMeshes, 1U);
+    const aiMesh *const mesh = scene->mMeshes[0];
+    EXPECT_FALSE(mesh->HasVertexColors(0));
+}
+
 TEST_F(utObjImportExport, issue1453_segfault) {
     static const char *curObjModel =
             "v  0.0  0.0  0.0\n"