summaryrefslogtreecommitdiff
path: root/src/mesh/assimp-master/contrib/utf8cpp
diff options
context:
space:
mode:
Diffstat (limited to 'src/mesh/assimp-master/contrib/utf8cpp')
-rw-r--r--src/mesh/assimp-master/contrib/utf8cpp/doc/ReleaseNotes12
-rw-r--r--src/mesh/assimp-master/contrib/utf8cpp/doc/utf8cpp.html1789
-rw-r--r--src/mesh/assimp-master/contrib/utf8cpp/source/utf8.h34
-rw-r--r--src/mesh/assimp-master/contrib/utf8cpp/source/utf8/checked.h333
-rw-r--r--src/mesh/assimp-master/contrib/utf8cpp/source/utf8/core.h338
-rw-r--r--src/mesh/assimp-master/contrib/utf8cpp/source/utf8/cpp11.h103
-rw-r--r--src/mesh/assimp-master/contrib/utf8cpp/source/utf8/unchecked.h274
7 files changed, 2883 insertions, 0 deletions
diff --git a/src/mesh/assimp-master/contrib/utf8cpp/doc/ReleaseNotes b/src/mesh/assimp-master/contrib/utf8cpp/doc/ReleaseNotes
new file mode 100644
index 0000000..364411a
--- /dev/null
+++ b/src/mesh/assimp-master/contrib/utf8cpp/doc/ReleaseNotes
@@ -0,0 +1,12 @@
+utf8 cpp library
+Release 2.3.4
+
+A minor bug fix release. Thanks to all who reported bugs.
+
+Note: Version 2.3.3 contained a regression, and therefore was removed.
+
+Changes from version 2.3.2
+- Bug fix [39]: checked.h Line 273 and unchecked.h Line 182 have an extra ';'
+- Bug fix [36]: replace_invalid() only works with back_inserter
+
+Files included in the release: utf8.h, core.h, checked.h, unchecked.h, utf8cpp.html, ReleaseNotes
diff --git a/src/mesh/assimp-master/contrib/utf8cpp/doc/utf8cpp.html b/src/mesh/assimp-master/contrib/utf8cpp/doc/utf8cpp.html
new file mode 100644
index 0000000..6f2aacb
--- /dev/null
+++ b/src/mesh/assimp-master/contrib/utf8cpp/doc/utf8cpp.html
@@ -0,0 +1,1789 @@
+<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
+<html>
+ <head>
+ <meta name="generator" content=
+ "HTML Tidy for Linux/x86 (vers 1st November 2002), see www.w3.org">
+ <meta name="description" content=
+ "A simple, portable and lightweigt C++ library for easy handling of UTF-8 encoded strings">
+ <meta name="keywords" content="UTF-8 C++ portable utf8 unicode generic templates">
+ <meta name="author" content="Nemanja Trifunovic">
+ <title>
+ UTF8-CPP: UTF-8 with C++ in a Portable Way
+ </title>
+ <style type="text/css">
+ <!--
+ span.return_value {
+ color: brown;
+ }
+ span.keyword {
+ color: blue;
+ }
+ span.preprocessor {
+ color: navy;
+ }
+ span.literal {
+ color: olive;
+ }
+ span.comment {
+ color: green;
+ }
+ code {
+ font-weight: bold;
+ }
+ ul.toc {
+ list-style-type: none;
+ }
+ p.version {
+ font-size: small;
+ font-style: italic;
+ }
+ -->
+ </style>
+ </head>
+ <body>
+ <h1>
+ UTF8-CPP: UTF-8 with C++ in a Portable Way
+ </h1>
+ <p>
+ <a href="https://sourceforge.net/projects/utfcpp">The Sourceforge project page</a>
+ </p>
+ <div id="toc">
+ <h2>
+ Table of Contents
+ </h2>
+ <ul class="toc">
+ <li>
+ <a href="#introduction">Introduction</a>
+ </li>
+ <li>
+ <a href="#examples">Examples of Use</a>
+ <ul class="toc">
+ <li>
+ <a href=#introsample>Introductionary Sample </a>
+ </li>
+ <li>
+ <a href=#validfile>Checking if a file contains valid UTF-8 text</a>
+ </li>
+ <li>
+ <a href=#fixinvalid>Ensure that a string contains valid UTF-8 text</a>
+ </li>
+ </ul>
+ <li>
+ <a href="#reference">Reference</a>
+ <ul class="toc">
+ <li>
+ <a href="#funutf8">Functions From utf8 Namespace </a>
+ </li>
+ <li>
+ <a href="#typesutf8">Types From utf8 Namespace </a>
+ </li>
+ <li>
+ <a href="#fununchecked">Functions From utf8::unchecked Namespace </a>
+ </li>
+ <li>
+ <a href="#typesunchecked">Types From utf8::unchecked Namespace </a>
+ </li>
+ </ul>
+ </li>
+ <li>
+ <a href="#points">Points of Interest</a>
+ </li>
+ <li>
+ <a href="#links">Links</a>
+ </li>
+ </ul>
+ </div>
+ <h2 id="introduction">
+ Introduction
+ </h2>
+ <p>
+ Many C++ developers miss an easy and portable way of handling Unicode encoded
+ strings. The original C++ Standard (known as C++98 or C++03) is Unicode agnostic.
+ C++11 provides some support for Unicode on core language and library level:
+ u8, u, and U character and string literals, char16_t and char32_t character types,
+ u16string and u32string library classes, and codecvt support for conversions
+ between Unicode encoding forms.
+ In the meantime, developers use third party libraries like ICU, OS specific capabilities, or simply
+ roll out their own solutions.
+ </p>
+ <p>
+ In order to easily handle UTF-8 encoded Unicode strings, I came up with a small
+ generic library. For anybody used to work with STL algorithms and iterators, it should be
+ easy and natural to use. The code is freely available for any purpose - check out
+ the license at the beginning of the utf8.h file. If you run into
+ bugs or performance issues, please let me know and I'll do my best to address them.
+ </p>
+ <p>
+ The purpose of this article is not to offer an introduction to Unicode in general,
+ and UTF-8 in particular. If you are not familiar with Unicode, be sure to check out
+ <a href="http://www.unicode.org/">Unicode Home Page</a> or some other source of
+ information for Unicode. Also, it is not my aim to advocate the use of UTF-8
+ encoded strings in C++ programs; if you want to handle UTF-8 encoded strings from
+ C++, I am sure you have good reasons for it.
+ </p>
+ <h2 id="examples">
+ Examples of use
+ </h2>
+ <h3 id="introsample">
+ Introductionary Sample
+ </h3>
+ <p>
+ To illustrate the use of the library, let's start with a small but complete program
+ that opens a file containing UTF-8 encoded text, reads it line by line, checks each line
+ for invalid UTF-8 byte sequences, and converts it to UTF-16 encoding and back to UTF-8:
+ </p>
+<pre>
+<span class="preprocessor">#include &lt;fstream&gt;</span>
+<span class="preprocessor">#include &lt;iostream&gt;</span>
+<span class="preprocessor">#include &lt;string&gt;</span>
+<span class="preprocessor">#include &lt;vector&gt;</span>
+<span class="preprocessor">#include "utf8.h"</span>
+<span class="keyword">using namespace</span> std;
+<span class="keyword">int</span> main(<span class="keyword">int</span> argc, <span class="keyword">char</span>** argv)
+{
+ <span class="keyword">if</span> (argc != <span class="literal">2</span>) {
+ cout &lt;&lt; <span class="literal">"\nUsage: docsample filename\n"</span>;
+ <span class="keyword">return</span> <span class="literal">0</span>;
+ }
+
+ <span class="keyword">const char</span>* test_file_path = argv[1];
+ <span class="comment">// Open the test file (contains UTF-8 encoded text)</span>
+ ifstream fs8(test_file_path);
+ <span class="keyword">if</span> (!fs8.is_open()) {
+ cout &lt;&lt; <span class=
+"literal">"Could not open "</span> &lt;&lt; test_file_path &lt;&lt; endl;
+ <span class="keyword">return</span> <span class="literal">0</span>;
+ }
+
+ <span class="keyword">unsigned</span> line_count = <span class="literal">1</span>;
+ string line;
+ <span class="comment">// Play with all the lines in the file</span>
+ <span class="keyword">while</span> (getline(fs8, line)) {
+ <span class="comment">// check for invalid utf-8 (for a simple yes/no check, there is also utf8::is_valid function)</span>
+ string::iterator end_it = utf8::find_invalid(line.begin(), line.end());
+ <span class="keyword">if</span> (end_it != line.end()) {
+ cout &lt;&lt; <span class=
+"literal">"Invalid UTF-8 encoding detected at line "</span> &lt;&lt; line_count &lt;&lt; <span
+ class="literal">"\n"</span>;
+ cout &lt;&lt; <span class=
+"literal">"This part is fine: "</span> &lt;&lt; string(line.begin(), end_it) &lt;&lt; <span
+ class="literal">"\n"</span>;
+ }
+
+ <span class="comment">// Get the line length (at least for the valid part)</span>
+ <span class="keyword">int</span> length = utf8::distance(line.begin(), end_it);
+ cout &lt;&lt; <span class=
+"literal">"Length of line "</span> &lt;&lt; line_count &lt;&lt; <span class=
+"literal">" is "</span> &lt;&lt; length &lt;&lt; <span class="literal">"\n"</span>;
+
+ <span class="comment">// Convert it to utf-16</span>
+ vector&lt;unsigned short&gt; utf16line;
+ utf8::utf8to16(line.begin(), end_it, back_inserter(utf16line));
+
+ <span class="comment">// And back to utf-8</span>
+ string utf8line;
+ utf8::utf16to8(utf16line.begin(), utf16line.end(), back_inserter(utf8line));
+
+ <span class="comment">// Confirm that the conversion went OK:</span>
+ <span class="keyword">if</span> (utf8line != string(line.begin(), end_it))
+ cout &lt;&lt; <span class=
+"literal">"Error in UTF-16 conversion at line: "</span> &lt;&lt; line_count &lt;&lt; <span
+ class="literal">"\n"</span>;
+
+ line_count++;
+ }
+ <span class="keyword">return</span> <span class="literal">0</span>;
+}
+</pre>
+ <p>
+ In the previous code sample, for each line we performed
+ a detection of invalid UTF-8 sequences with <code>find_invalid</code>; the number
+ of characters (more precisely - the number of Unicode code points, including the end
+ of line and even BOM if there is one) in each line was
+ determined with a use of <code>utf8::distance</code>; finally, we have converted
+ each line to UTF-16 encoding with <code>utf8to16</code> and back to UTF-8 with
+ <code>utf16to8</code>.
+ </p>
+ <h3 id="validfile">Checking if a file contains valid UTF-8 text</h3>
+<p>
+Here is a function that checks whether the content of a file is valid UTF-8 encoded text without
+reading the content into the memory:
+</p>
+<pre>
+<span class="keyword">bool</span> valid_utf8_file(i<span class="keyword">const char</span>* file_name)
+{
+ ifstream ifs(file_name);
+ <span class="keyword">if</span> (!ifs)
+ <span class="keyword">return false</span>; <span class="comment">// even better, throw here</span>
+
+ istreambuf_iterator&lt;<span class="keyword">char</span>&gt; it(ifs.rdbuf());
+ istreambuf_iterator&lt;<span class="keyword">char</span>&gt; eos;
+
+ <span class="keyword">return</span> utf8::is_valid(it, eos);
+}
+</pre>
+<p>
+Because the function <code>utf8::is_valid()</code> works with input iterators, we were able
+to pass an <code>istreambuf_iterator</code> to it and read the content of the file directly
+without loading it to the memory first.</p>
+<p>
+Note that other functions that take input iterator arguments can be used in a similar way. For
+instance, to read the content of a UTF-8 encoded text file and convert the text to UTF-16, just
+do something like:
+</p>
+<pre>
+ utf8::utf8to16(it, eos, back_inserter(u16string));
+</pre>
+ <h3 id="fixinvalid">Ensure that a string contains valid UTF-8 text</h3>
+<p>
+If we have some text that "probably" contains UTF-8 encoded text and we want to
+replace any invalid UTF-8 sequence with a replacement character, something like
+the following function may be used:
+</p>
+<pre>
+<span class="keyword">void</span> fix_utf8_string(std::string&amp; str)
+{
+ std::string temp;
+ utf8::replace_invalid(str.begin(), str.end(), back_inserter(temp));
+ str = temp;
+}
+</pre>
+<p>The function will replace any invalid UTF-8 sequence with a Unicode replacement character.
+There is an overloaded function that enables the caller to supply their own replacement character.
+</p>
+ <h2 id="reference">
+ Reference
+ </h2>
+ <h3 id="funutf8">
+ Functions From utf8 Namespace
+ </h3>
+ <h4>
+ utf8::append
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Encodes a 32 bit code point as a UTF-8 sequence of octets and appends the sequence
+ to a UTF-8 string.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator&gt;
+octet_iterator append(uint32_t cp, octet_iterator result);
+
+</pre>
+ <p>
+ <code>octet_iterator</code>: an output iterator.<br>
+ <code>cp</code>: a 32 bit integer representing a code point to append to the
+ sequence.<br>
+ <code>result</code>: an output iterator to the place in the sequence where to
+ append the code point.<br>
+ <span class="return_value">Return value</span>: an iterator pointing to the place
+ after the newly appended sequence.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">unsigned char</span> u[<span class="literal">5</span>] = {<span
+class="literal">0</span>,<span class="literal">0</span>,<span class=
+"literal">0</span>,<span class="literal">0</span>,<span class="literal">0</span>};
+<span class="keyword">unsigned char</span>* end = append(<span class=
+"literal">0x0448</span>, u);
+assert (u[<span class="literal">0</span>] == <span class=
+"literal">0xd1</span> &amp;&amp; u[<span class="literal">1</span>] == <span class=
+"literal">0x88</span> &amp;&amp; u[<span class="literal">2</span>] == <span class=
+"literal">0</span> &amp;&amp; u[<span class="literal">3</span>] == <span class=
+"literal">0</span> &amp;&amp; u[<span class="literal">4</span>] == <span class=
+"literal">0</span>);
+</pre>
+ <p>
+ Note that <code>append</code> does not allocate any memory - it is the burden of
+ the caller to make sure there is enough memory allocated for the operation. To make
+ things more interesting, <code>append</code> can add anywhere between 1 and 4
+ octets to the sequence. In practice, you would most often want to use
+ <code>std::back_inserter</code> to ensure that the necessary memory is allocated.
+ </p>
+ <p>
+ In case of an invalid code point, a <code>utf8::invalid_code_point</code> exception
+ is thrown.
+ </p>
+ <h4>
+ utf8::next
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Given the iterator to the beginning of the UTF-8 sequence, it returns the code
+ point and moves the iterator to the next position.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator&gt;
+uint32_t next(octet_iterator&amp; it, octet_iterator end);
+
+</pre>
+ <p>
+ <code>octet_iterator</code>: an input iterator.<br>
+ <code>it</code>: a reference to an iterator pointing to the beginning of an UTF-8
+ encoded code point. After the function returns, it is incremented to point to the
+ beginning of the next code point.<br>
+ <code>end</code>: end of the UTF-8 sequence to be processed. If <code>it</code>
+ gets equal to <code>end</code> during the extraction of a code point, an
+ <code>utf8::not_enough_room</code> exception is thrown.<br>
+ <span class="return_value">Return value</span>: the 32 bit representation of the
+ processed UTF-8 code point.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">char</span>* twochars = <span class=
+"literal">"\xe6\x97\xa5\xd1\x88"</span>;
+<span class="keyword">char</span>* w = twochars;
+<span class="keyword">int</span> cp = next(w, twochars + <span class="literal">6</span>);
+assert (cp == <span class="literal">0x65e5</span>);
+assert (w == twochars + <span class="literal">3</span>);
+</pre>
+ <p>
+ This function is typically used to iterate through a UTF-8 encoded string.
+ </p>
+ <p>
+ In case of an invalid UTF-8 seqence, a <code>utf8::invalid_utf8</code> exception is
+ thrown.
+ </p>
+ <h4>
+ utf8::peek_next
+ </h4>
+ <p class="version">
+ Available in version 2.1 and later.
+ </p>
+ <p>
+ Given the iterator to the beginning of the UTF-8 sequence, it returns the code
+ point for the following sequence without changing the value of the iterator.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator&gt;
+uint32_t peek_next(octet_iterator it, octet_iterator end);
+
+</pre>
+ <p>
+ <code>octet_iterator</code>: an input iterator.<br>
+ <code>it</code>: an iterator pointing to the beginning of an UTF-8
+ encoded code point.<br>
+ <code>end</code>: end of the UTF-8 sequence to be processed. If <code>it</code>
+ gets equal to <code>end</code> during the extraction of a code point, an
+ <code>utf8::not_enough_room</code> exception is thrown.<br>
+ <span class="return_value">Return value</span>: the 32 bit representation of the
+ processed UTF-8 code point.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">char</span>* twochars = <span class=
+"literal">"\xe6\x97\xa5\xd1\x88"</span>;
+<span class="keyword">char</span>* w = twochars;
+<span class="keyword">int</span> cp = peek_next(w, twochars + <span class="literal">6</span>);
+assert (cp == <span class="literal">0x65e5</span>);
+assert (w == twochars);
+</pre>
+ <p>
+ In case of an invalid UTF-8 seqence, a <code>utf8::invalid_utf8</code> exception is
+ thrown.
+ </p>
+ <h4>
+ utf8::prior
+ </h4>
+ <p class="version">
+ Available in version 1.02 and later.
+ </p>
+ <p>
+ Given a reference to an iterator pointing to an octet in a UTF-8 sequence, it
+ decreases the iterator until it hits the beginning of the previous UTF-8 encoded
+ code point and returns the 32 bits representation of the code point.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator&gt;
+uint32_t prior(octet_iterator&amp; it, octet_iterator start);
+
+</pre>
+ <p>
+ <code>octet_iterator</code>: a bidirectional iterator.<br>
+ <code>it</code>: a reference pointing to an octet within a UTF-8 encoded string.
+ After the function returns, it is decremented to point to the beginning of the
+ previous code point.<br>
+ <code>start</code>: an iterator to the beginning of the sequence where the search
+ for the beginning of a code point is performed. It is a
+ safety measure to prevent passing the beginning of the string in the search for a
+ UTF-8 lead octet.<br>
+ <span class="return_value">Return value</span>: the 32 bit representation of the
+ previous code point.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">char</span>* twochars = <span class=
+"literal">"\xe6\x97\xa5\xd1\x88"</span>;
+<span class="keyword">unsigned char</span>* w = twochars + <span class=
+"literal">3</span>;
+<span class="keyword">int</span> cp = prior (w, twochars);
+assert (cp == <span class="literal">0x65e5</span>);
+assert (w == twochars);
+</pre>
+ <p>
+ This function has two purposes: one is two iterate backwards through a UTF-8
+ encoded string. Note that it is usually a better idea to iterate forward instead,
+ since <code>utf8::next</code> is faster. The second purpose is to find a beginning
+ of a UTF-8 sequence if we have a random position within a string. Note that in that
+ case <code>utf8::prior</code> may not detect an invalid UTF-8 sequence in some scenarios:
+ for instance if there are superfluous trail octets, it will just skip them.
+ </p>
+ <p>
+ <code>it</code> will typically point to the beginning of
+ a code point, and <code>start</code> will point to the
+ beginning of the string to ensure we don't go backwards too far. <code>it</code> is
+ decreased until it points to a lead UTF-8 octet, and then the UTF-8 sequence
+ beginning with that octet is decoded to a 32 bit representation and returned.
+ </p>
+ <p>
+ In case <code>start</code> is reached before a UTF-8 lead octet is hit, or if an
+ invalid UTF-8 sequence is started by the lead octet, an <code>invalid_utf8</code>
+ exception is thrown.
+ </p>
+ <p>In case <code>start</code> equals <code>it</code>, a <code>not_enough_room</code>
+ exception is thrown.
+ <h4>
+ utf8::previous
+ </h4>
+ <p class="version">
+ Deprecated in version 1.02 and later.
+ </p>
+ <p>
+ Given a reference to an iterator pointing to an octet in a UTF-8 seqence, it
+ decreases the iterator until it hits the beginning of the previous UTF-8 encoded
+ code point and returns the 32 bits representation of the code point.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator&gt;
+uint32_t previous(octet_iterator&amp; it, octet_iterator pass_start);
+
+</pre>
+ <p>
+ <code>octet_iterator</code>: a random access iterator.<br>
+ <code>it</code>: a reference pointing to an octet within a UTF-8 encoded string.
+ After the function returns, it is decremented to point to the beginning of the
+ previous code point.<br>
+ <code>pass_start</code>: an iterator to the point in the sequence where the search
+ for the beginning of a code point is aborted if no result was reached. It is a
+ safety measure to prevent passing the beginning of the string in the search for a
+ UTF-8 lead octet.<br>
+ <span class="return_value">Return value</span>: the 32 bit representation of the
+ previous code point.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">char</span>* twochars = <span class=
+"literal">"\xe6\x97\xa5\xd1\x88"</span>;
+<span class="keyword">unsigned char</span>* w = twochars + <span class=
+"literal">3</span>;
+<span class="keyword">int</span> cp = previous (w, twochars - <span class=
+"literal">1</span>);
+assert (cp == <span class="literal">0x65e5</span>);
+assert (w == twochars);
+</pre>
+ <p>
+ <code>utf8::previous</code> is deprecated, and <code>utf8::prior</code> should
+ be used instead, although the existing code can continue using this function.
+ The problem is the parameter <code>pass_start</code> that points to the position
+ just before the beginning of the sequence. Standard containers don't have the
+ concept of "pass start" and the function can not be used with their iterators.
+ </p>
+ <p>
+ <code>it</code> will typically point to the beginning of
+ a code point, and <code>pass_start</code> will point to the octet just before the
+ beginning of the string to ensure we don't go backwards too far. <code>it</code> is
+ decreased until it points to a lead UTF-8 octet, and then the UTF-8 sequence
+ beginning with that octet is decoded to a 32 bit representation and returned.
+ </p>
+ <p>
+ In case <code>pass_start</code> is reached before a UTF-8 lead octet is hit, or if an
+ invalid UTF-8 sequence is started by the lead octet, an <code>invalid_utf8</code>
+ exception is thrown
+ </p>
+ <h4>
+ utf8::advance
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Advances an iterator by the specified number of code points within an UTF-8
+ sequence.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator, typename distance_type&gt;
+<span class=
+"keyword">void</span> advance (octet_iterator&amp; it, distance_type n, octet_iterator end);
+
+</pre>
+ <p>
+ <code>octet_iterator</code>: an input iterator.<br>
+ <code>distance_type</code>: an integral type convertible to <code>octet_iterator</code>'s difference type.<br>
+ <code>it</code>: a reference to an iterator pointing to the beginning of an UTF-8
+ encoded code point. After the function returns, it is incremented to point to the
+ nth following code point.<br>
+ <code>n</code>: a positive integer that shows how many code points we want to
+ advance.<br>
+ <code>end</code>: end of the UTF-8 sequence to be processed. If <code>it</code>
+ gets equal to <code>end</code> during the extraction of a code point, an
+ <code>utf8::not_enough_room</code> exception is thrown.<br>
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">char</span>* twochars = <span class=
+"literal">"\xe6\x97\xa5\xd1\x88"</span>;
+<span class="keyword">unsigned char</span>* w = twochars;
+advance (w, <span class="literal">2</span>, twochars + <span class="literal">6</span>);
+assert (w == twochars + <span class="literal">5</span>);
+</pre>
+ <p>
+ This function works only "forward". In case of a negative <code>n</code>, there is
+ no effect.
+ </p>
+ <p>
+ In case of an invalid code point, a <code>utf8::invalid_code_point</code> exception
+ is thrown.
+ </p>
+ <h4>
+ utf8::distance
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Given the iterators to two UTF-8 encoded code points in a seqence, returns the
+ number of code points between them.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator&gt;
+<span class=
+"keyword">typename</span> std::iterator_traits&lt;octet_iterator&gt;::difference_type distance (octet_iterator first, octet_iterator last);
+
+</pre>
+ <p>
+ <code>octet_iterator</code>: an input iterator.<br>
+ <code>first</code>: an iterator to a beginning of a UTF-8 encoded code point.<br>
+ <code>last</code>: an iterator to a "post-end" of the last UTF-8 encoded code
+ point in the sequence we are trying to determine the length. It can be the
+ beginning of a new code point, or not.<br>
+ <span class="return_value">Return value</span> the distance between the iterators,
+ in code points.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">char</span>* twochars = <span class=
+"literal">"\xe6\x97\xa5\xd1\x88"</span>;
+size_t dist = utf8::distance(twochars, twochars + <span class="literal">5</span>);
+assert (dist == <span class="literal">2</span>);
+</pre>
+ <p>
+ This function is used to find the length (in code points) of a UTF-8 encoded
+ string. The reason it is called <em>distance</em>, rather than, say,
+ <em>length</em> is mainly because developers are used that <em>length</em> is an
+ O(1) function. Computing the length of an UTF-8 string is a linear operation, and
+ it looked better to model it after <code>std::distance</code> algorithm.
+ </p>
+ <p>
+ In case of an invalid UTF-8 seqence, a <code>utf8::invalid_utf8</code> exception is
+ thrown. If <code>last</code> does not point to the past-of-end of a UTF-8 seqence,
+ a <code>utf8::not_enough_room</code> exception is thrown.
+ </p>
+ <h4>
+ utf8::utf16to8
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Converts a UTF-16 encoded string to UTF-8.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> u16bit_iterator, <span class=
+"keyword">typename</span> octet_iterator&gt;
+octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result);
+
+</pre>
+ <p>
+ <code>u16bit_iterator</code>: an input iterator.<br>
+ <code>octet_iterator</code>: an output iterator.<br>
+ <code>start</code>: an iterator pointing to the beginning of the UTF-16 encoded
+ string to convert.<br>
+ <code>end</code>: an iterator pointing to pass-the-end of the UTF-16 encoded
+ string to convert.<br>
+ <code>result</code>: an output iterator to the place in the UTF-8 string where to
+ append the result of conversion.<br>
+ <span class="return_value">Return value</span>: An iterator pointing to the place
+ after the appended UTF-8 string.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">unsigned short</span> utf16string[] = {<span class=
+"literal">0x41</span>, <span class="literal">0x0448</span>, <span class=
+"literal">0x65e5</span>, <span class="literal">0xd834</span>, <span class=
+"literal">0xdd1e</span>};
+vector&lt;<span class="keyword">unsigned char</span>&gt; utf8result;
+utf16to8(utf16string, utf16string + <span class=
+"literal">5</span>, back_inserter(utf8result));
+assert (utf8result.size() == <span class="literal">10</span>);
+</pre>
+ <p>
+ In case of invalid UTF-16 sequence, a <code>utf8::invalid_utf16</code> exception is
+ thrown.
+ </p>
+ <h4>
+ utf8::utf8to16
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Converts an UTF-8 encoded string to UTF-16
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> u16bit_iterator, typename octet_iterator&gt;
+u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result);
+
+</pre>
+ <p>
+ <code>octet_iterator</code>: an input iterator.<br>
+ <code>u16bit_iterator</code>: an output iterator.<br>
+ <code>start</code>: an iterator pointing to the beginning of the UTF-8 encoded
+ string to convert. &lt; br /&gt; <code>end</code>: an iterator pointing to
+ pass-the-end of the UTF-8 encoded string to convert.<br>
+ <code>result</code>: an output iterator to the place in the UTF-16 string where to
+ append the result of conversion.<br>
+ <span class="return_value">Return value</span>: An iterator pointing to the place
+ after the appended UTF-16 string.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">char</span> utf8_with_surrogates[] = <span class=
+"literal">"\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e"</span>;
+vector &lt;<span class="keyword">unsigned short</span>&gt; utf16result;
+utf8to16(utf8_with_surrogates, utf8_with_surrogates + <span class=
+"literal">9</span>, back_inserter(utf16result));
+assert (utf16result.size() == <span class="literal">4</span>);
+assert (utf16result[<span class="literal">2</span>] == <span class=
+"literal">0xd834</span>);
+assert (utf16result[<span class="literal">3</span>] == <span class=
+"literal">0xdd1e</span>);
+</pre>
+ <p>
+ In case of an invalid UTF-8 seqence, a <code>utf8::invalid_utf8</code> exception is
+ thrown. If <code>end</code> does not point to the past-of-end of a UTF-8 seqence, a
+ <code>utf8::not_enough_room</code> exception is thrown.
+ </p>
+ <h4>
+ utf8::utf32to8
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Converts a UTF-32 encoded string to UTF-8.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator, typename u32bit_iterator&gt;
+octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result);
+
+</pre>
+ <p>
+ <code>octet_iterator</code>: an output iterator.<br>
+ <code>u32bit_iterator</code>: an input iterator.<br>
+ <code>start</code>: an iterator pointing to the beginning of the UTF-32 encoded
+ string to convert.<br>
+ <code>end</code>: an iterator pointing to pass-the-end of the UTF-32 encoded
+ string to convert.<br>
+ <code>result</code>: an output iterator to the place in the UTF-8 string where to
+ append the result of conversion.<br>
+ <span class="return_value">Return value</span>: An iterator pointing to the place
+ after the appended UTF-8 string.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">int</span> utf32string[] = {<span class=
+"literal">0x448</span>, <span class="literal">0x65E5</span>, <span class=
+"literal">0x10346</span>, <span class="literal">0</span>};
+vector&lt;<span class="keyword">unsigned char</span>&gt; utf8result;
+utf32to8(utf32string, utf32string + <span class=
+"literal">3</span>, back_inserter(utf8result));
+assert (utf8result.size() == <span class="literal">9</span>);
+</pre>
+ <p>
+ In case of invalid UTF-32 string, a <code>utf8::invalid_code_point</code> exception
+ is thrown.
+ </p>
+ <h4>
+ utf8::utf8to32
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Converts a UTF-8 encoded string to UTF-32.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator, <span class=
+"keyword">typename</span> u32bit_iterator&gt;
+u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result);
+
+</pre>
+ <p>
+ <code>octet_iterator</code>: an input iterator.<br>
+ <code>u32bit_iterator</code>: an output iterator.<br>
+ <code>start</code>: an iterator pointing to the beginning of the UTF-8 encoded
+ string to convert.<br>
+ <code>end</code>: an iterator pointing to pass-the-end of the UTF-8 encoded string
+ to convert.<br>
+ <code>result</code>: an output iterator to the place in the UTF-32 string where to
+ append the result of conversion.<br>
+ <span class="return_value">Return value</span>: An iterator pointing to the place
+ after the appended UTF-32 string.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">char</span>* twochars = <span class=
+"literal">"\xe6\x97\xa5\xd1\x88"</span>;
+vector&lt;<span class="keyword">int</span>&gt; utf32result;
+utf8to32(twochars, twochars + <span class=
+"literal">5</span>, back_inserter(utf32result));
+assert (utf32result.size() == <span class="literal">2</span>);
+</pre>
+ <p>
+ In case of an invalid UTF-8 seqence, a <code>utf8::invalid_utf8</code> exception is
+ thrown. If <code>end</code> does not point to the past-of-end of a UTF-8 seqence, a
+ <code>utf8::not_enough_room</code> exception is thrown.
+ </p>
+ <h4>
+ utf8::find_invalid
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Detects an invalid sequence within a UTF-8 string.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator&gt;
+octet_iterator find_invalid(octet_iterator start, octet_iterator end);
+</pre>
+ <p>
+ <code>octet_iterator</code>: an input iterator.<br>
+ <code>start</code>: an iterator pointing to the beginning of the UTF-8 string to
+ test for validity.<br>
+ <code>end</code>: an iterator pointing to pass-the-end of the UTF-8 string to test
+ for validity.<br>
+ <span class="return_value">Return value</span>: an iterator pointing to the first
+ invalid octet in the UTF-8 string. In case none were found, equals
+ <code>end</code>.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">char</span> utf_invalid[] = <span class=
+"literal">"\xe6\x97\xa5\xd1\x88\xfa"</span>;
+<span class=
+"keyword">char</span>* invalid = find_invalid(utf_invalid, utf_invalid + <span class=
+"literal">6</span>);
+assert (invalid == utf_invalid + <span class="literal">5</span>);
+</pre>
+ <p>
+ This function is typically used to make sure a UTF-8 string is valid before
+ processing it with other functions. It is especially important to call it if before
+ doing any of the <em>unchecked</em> operations on it.
+ </p>
+ <h4>
+ utf8::is_valid
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Checks whether a sequence of octets is a valid UTF-8 string.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator&gt;
+<span class="keyword">bool</span> is_valid(octet_iterator start, octet_iterator end);
+
+</pre>
+ <p>
+ <code>octet_iterator</code>: an input iterator.<br>
+ <code>start</code>: an iterator pointing to the beginning of the UTF-8 string to
+ test for validity.<br>
+ <code>end</code>: an iterator pointing to pass-the-end of the UTF-8 string to test
+ for validity.<br>
+ <span class="return_value">Return value</span>: <code>true</code> if the sequence
+ is a valid UTF-8 string; <code>false</code> if not.
+ </p>
+ Example of use:
+<pre>
+<span class="keyword">char</span> utf_invalid[] = <span class=
+"literal">"\xe6\x97\xa5\xd1\x88\xfa"</span>;
+<span class="keyword">bool</span> bvalid = is_valid(utf_invalid, utf_invalid + <span
+class="literal">6</span>);
+assert (bvalid == false);
+</pre>
+ <p>
+ <code>is_valid</code> is a shorthand for <code>find_invalid(start, end) ==
+ end;</code>. You may want to use it to make sure that a byte seqence is a valid
+ UTF-8 string without the need to know where it fails if it is not valid.
+ </p>
+ <h4>
+ utf8::replace_invalid
+ </h4>
+ <p class="version">
+ Available in version 2.0 and later.
+ </p>
+ <p>
+ Replaces all invalid UTF-8 sequences within a string with a replacement marker.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator, <span class=
+"keyword">typename</span> output_iterator&gt;
+output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out, uint32_t replacement);
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator, <span class=
+"keyword">typename</span> output_iterator&gt;
+output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out);
+
+</pre>
+ <p>
+ <code>octet_iterator</code>: an input iterator.<br>
+ <code>output_iterator</code>: an output iterator.<br>
+ <code>start</code>: an iterator pointing to the beginning of the UTF-8 string to
+ look for invalid UTF-8 sequences.<br>
+ <code>end</code>: an iterator pointing to pass-the-end of the UTF-8 string to look
+ for invalid UTF-8 sequences.<br>
+ <code>out</code>: An output iterator to the range where the result of replacement
+ is stored.<br>
+ <code>replacement</code>: A Unicode code point for the replacement marker. The
+ version without this parameter assumes the value <code>0xfffd</code><br>
+ <span class="return_value">Return value</span>: An iterator pointing to the place
+ after the UTF-8 string with replaced invalid sequences.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">char</span> invalid_sequence[] = <span class=
+"literal">"a\x80\xe0\xa0\xc0\xaf\xed\xa0\x80z"</span>;
+vector&lt;<span class="keyword">char</span>&gt; replace_invalid_result;
+replace_invalid (invalid_sequence, invalid_sequence + sizeof(invalid_sequence), back_inserter(replace_invalid_result), <span
+ class="literal">'?'</span>);
+bvalid = is_valid(replace_invalid_result.begin(), replace_invalid_result.end());
+assert (bvalid);
+<span class="keyword">char</span>* fixed_invalid_sequence = <span class=
+"literal">"a????z"</span>;
+assert (std::equal(replace_invalid_result.begin(), replace_invalid_result.end(), fixed_invalid_sequence));
+</pre>
+ <p>
+ <code>replace_invalid</code> does not perform in-place replacement of invalid
+ sequences. Rather, it produces a copy of the original string with the invalid
+ sequences replaced with a replacement marker. Therefore, <code>out</code> must not
+ be in the <code>[start, end]</code> range.
+ </p>
+ <p>
+ If <code>end</code> does not point to the past-of-end of a UTF-8 sequence, a
+ <code>utf8::not_enough_room</code> exception is thrown.
+ </p>
+ <h4>
+ utf8::starts_with_bom
+ </h4>
+ <p class="version">
+ Available in version 2.3 and later. Relaces deprecated <code>is_bom()</code> function.
+ </p>
+ <p>
+ Checks whether an octet sequence starts with a UTF-8 byte order mark (BOM)
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator&gt;
+<span class="keyword">bool</span> starts_with_bom (octet_iterator it, octet_iterator end);
+</pre>
+ <p>
+ <code>octet_iterator</code>: an input iterator.<br>
+ <code>it</code>: beginning of the octet sequence to check<br>
+ <code>end</code>: pass-end of the sequence to check<br>
+ <span class="return_value">Return value</span>: <code>true</code> if the sequence
+ starts with a UTF-8 byte order mark; <code>false</code> if not.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">unsigned char</span> byte_order_mark[] = {<span class=
+"literal">0xef</span>, <span class="literal">0xbb</span>, <span class=
+"literal">0xbf</span>};
+<span class="keyword">bool</span> bbom = starts_with_bom(byte_order_mark, byte_order_mark + <span class="keyword">sizeof</span>(byte_order_mark));
+assert (bbom == <span class="literal">true</span>);
+</pre>
+ <p>
+ The typical use of this function is to check the first three bytes of a file. If
+ they form the UTF-8 BOM, we want to skip them before processing the actual UTF-8
+ encoded text.
+ </p>
+ <h4>
+ utf8::is_bom
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later. Deprecated in version 2.3. <code>starts_with_bom()</code> should be used
+ instead.
+ </p>
+ <p>
+ Checks whether a sequence of three octets is a UTF-8 byte order mark (BOM)
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator&gt;
+<span class="keyword">bool</span> is_bom (octet_iterator it); <span class="comment"> // Deprecated</span>
+</pre>
+ <p>
+ <code>octet_iterator</code>: an input iterator.<br>
+ <code>it</code>: beginning of the 3-octet sequence to check<br>
+ <span class="return_value">Return value</span>: <code>true</code> if the sequence
+ is UTF-8 byte order mark; <code>false</code> if not.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">unsigned char</span> byte_order_mark[] = {<span class=
+"literal">0xef</span>, <span class="literal">0xbb</span>, <span class=
+"literal">0xbf</span>};
+<span class="keyword">bool</span> bbom = is_bom(byte_order_mark);
+assert (bbom == <span class="literal">true</span>);
+</pre>
+ <p>
+ The typical use of this function is to check the first three bytes of a file. If
+ they form the UTF-8 BOM, we want to skip them before processing the actual UTF-8
+ encoded text.
+ </p>
+ <p>
+ If a sequence is
+ shorter than three bytes, an invalid iterator will be dereferenced. Therefore, this function is deprecated
+ in favor of <code>starts_with_bom()</code>that takes the end of sequence as an argument.
+ </p>
+ <h3 id="typesutf8">
+ Types From utf8 Namespace
+ </h3>
+ <h4>utf8::exception
+ </h4>
+ <p class="version">
+ Available in version 2.3 and later.
+ </p>
+ <p>
+ Base class for the exceptions thrown by UTF CPP library functions.
+ </p>
+<pre>
+<span class="keyword">class</span> exception : <span class="keyword">public</span> std::exception {};
+</pre>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">try</span> {
+ code_that_uses_utf_cpp_library();
+}
+<span class="keyword">catch</span>(<span class="keyword">const</span> utf8::exception&amp; utfcpp_ex) {
+ cerr &lt;&lt; utfcpp_ex.what();
+}
+</pre>
+
+ <h4>utf8::invalid_code_point
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Thrown by UTF8 CPP functions such as <code>advance</code> and <code>next</code> if an UTF-8 sequence represents and invalid code point.
+ </p>
+
+<pre>
+<span class="keyword">class</span> invalid_code_point : <span class="keyword">public</span> exception {
+<span class="keyword">public</span>:
+ uint32_t code_point() <span class="keyword">const</span>;
+};
+
+</pre>
+ <p>
+ Member function <code>code_point()</code> can be used to determine the invalid code point that
+ caused the exception to be thrown.
+ </p>
+ <h4>utf8::invalid_utf8
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Thrown by UTF8 CPP functions such as <code>next</code> and <code>prior</code> if an invalid UTF-8 sequence
+ is detected during decoding.
+ </p>
+
+<pre>
+<span class="keyword">class</span> invalid_utf8 : <span class="keyword">public</span> exception {
+<span class="keyword">public</span>:
+ uint8_t utf8_octet() <span class="keyword">const</span>;
+};
+</pre>
+
+ <p>
+ Member function <code>utf8_octet()</code> can be used to determine the beginning of the byte
+ sequence that caused the exception to be thrown.
+ </p>
+</pre>
+ <h4>utf8::invalid_utf16
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Thrown by UTF8 CPP function <code>utf16to8</code> if an invalid UTF-16 sequence
+ is detected during decoding.
+ </p>
+
+<pre>
+<span class="keyword">class</span> invalid_utf16 : <span class="keyword">public</span> exception {
+<span class="keyword">public</span>:
+ uint16_t utf16_word() <span class="keyword">const</span>;
+};
+</pre>
+
+ <p>
+ Member function <code>utf16_word()</code> can be used to determine the UTF-16 code unit
+ that caused the exception to be thrown.
+ </p>
+ <h4>utf8::not_enough_room
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Thrown by UTF8 CPP functions such as <code>next</code> if the end of the decoded UTF-8 sequence
+ was reached before the code point was decoded.
+ </p>
+
+<pre>
+<span class="keyword">class</span> not_enough_room : <span class="keyword">public</span> exception {};
+</pre>
+ <h4>
+ utf8::iterator
+ </h4>
+ <p class="version">
+ Available in version 2.0 and later.
+ </p>
+ <p>
+ Adapts the underlying octet iterator to iterate over the sequence of code points,
+ rather than raw octets.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class="keyword">typename</span> octet_iterator&gt;
+<span class="keyword">class</span> iterator;
+</pre>
+
+ <h5>Member functions</h5>
+ <dl>
+ <dt><code>iterator();</code> <dd> the deafult constructor; the underlying <code>octet_iterator</code> is
+ constructed with its default constructor.
+ <dt><code><span class="keyword">explicit</span> iterator (const octet_iterator&amp; octet_it,
+ const octet_iterator&amp; range_start,
+ const octet_iterator&amp; range_end);</code> <dd> a constructor
+ that initializes the underlying <code>octet_iterator</code> with <code>octet_it</code>
+ and sets the range in which the iterator is considered valid.
+ <dt><code>octet_iterator base () <span class="keyword">const</span>;</code> <dd> returns the
+ underlying <code>octet_iterator</code>.
+ <dt><code>uint32_t operator * () <span class="keyword">const</span>;</code> <dd> decodes the utf-8 sequence
+ the underlying <code>octet_iterator</code> is pointing to and returns the code point.
+ <dt><code><span class="keyword">bool operator</span> == (const iterator&amp; rhs)
+ <span class="keyword">const</span>;</code> <dd> returns <span class="keyword">true</span>
+ if the two underlaying iterators are equal.
+ <dt><code><span class="keyword">bool operator</span> != (const iterator&amp; rhs)
+ <span class="keyword">const</span>;</code> <dd> returns <span class="keyword">true</span>
+ if the two underlaying iterators are not equal.
+ <dt><code>iterator&amp; <span class="keyword">operator</span> ++ (); </code> <dd> the prefix increment - moves
+ the iterator to the next UTF-8 encoded code point.
+ <dt><code>iterator <span class="keyword">operator</span> ++ (<span class="keyword">int</span>); </code> <dd>
+ the postfix increment - moves the iterator to the next UTF-8 encoded code point and returns the current one.
+ <dt><code>iterator&amp; <span class="keyword">operator</span> -- (); </code> <dd> the prefix decrement - moves
+ the iterator to the previous UTF-8 encoded code point.
+ <dt><code>iterator <span class="keyword">operator</span> -- (<span class="keyword">int</span>); </code> <dd>
+ the postfix decrement - moves the iterator to the previous UTF-8 encoded code point and returns the current one.
+ </dl>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">char</span>* threechars = <span class="literal">"\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88"</span>;
+utf8::iterator&lt;<span class="keyword">char</span>*&gt; it(threechars, threechars, threechars + <span class="literal">9</span>);
+utf8::iterator&lt;<span class="keyword">char</span>*&gt; it2 = it;
+assert (it2 == it);
+assert (*it == <span class="literal">0x10346</span>);
+assert (*(++it) == <span class="literal">0x65e5</span>);
+assert ((*it++) == <span class="literal">0x65e5</span>);
+assert (*it == <span class="literal">0x0448</span>);
+assert (it != it2);
+utf8::iterator&lt;<span class="keyword">char</span>*&gt; endit (threechars + <span class="literal">9</span>, threechars, threechars + <span class="literal">9</span>);
+assert (++it == endit);
+assert (*(--it) == <span class="literal">0x0448</span>);
+assert ((*it--) == <span class="literal">0x0448</span>);
+assert (*it == <span class="literal">0x65e5</span>);
+assert (--it == utf8::iterator&lt;<span class="keyword">char</span>*&gt;(threechars, threechars, threechars + <span class="literal">9</span>));
+assert (*it == <span class="literal">0x10346</span>);
+</pre>
+ <p>
+ The purpose of <code>utf8::iterator</code> adapter is to enable easy iteration as well as the use of STL
+ algorithms with UTF-8 encoded strings. Increment and decrement operators are implemented in terms of
+ <code>utf8::next()</code> and <code>utf8::prior()</code> functions.
+ </p>
+ <p>
+ Note that <code>utf8::iterator</code> adapter is a checked iterator. It operates on the range specified in
+ the constructor; any attempt to go out of that range will result in an exception. Even the comparison operators
+ require both iterator object to be constructed against the same range - otherwise an exception is thrown. Typically,
+ the range will be determined by sequence container functions <code>begin</code> and <code>end</code>, i.e.:
+ </p>
+<pre>
+std::string s = <span class="literal">"example"</span>;
+utf8::iterator i (s.begin(), s.begin(), s.end());
+</pre>
+ <h3 id="fununchecked">
+ Functions From utf8::unchecked Namespace
+ </h3>
+ <h4>
+ utf8::unchecked::append
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Encodes a 32 bit code point as a UTF-8 sequence of octets and appends the sequence
+ to a UTF-8 string.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator&gt;
+octet_iterator append(uint32_t cp, octet_iterator result);
+
+</pre>
+ <p>
+ <code>cp</code>: A 32 bit integer representing a code point to append to the
+ sequence.<br>
+ <code>result</code>: An output iterator to the place in the sequence where to
+ append the code point.<br>
+ <span class="return_value">Return value</span>: An iterator pointing to the place
+ after the newly appended sequence.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">unsigned char</span> u[<span class="literal">5</span>] = {<span
+class="literal">0</span>,<span class="literal">0</span>,<span class=
+"literal">0</span>,<span class="literal">0</span>,<span class="literal">0</span>};
+<span class="keyword">unsigned char</span>* end = unchecked::append(<span class=
+"literal">0x0448</span>, u);
+assert (u[<span class="literal">0</span>] == <span class=
+"literal">0xd1</span> &amp;&amp; u[<span class="literal">1</span>] == <span class=
+"literal">0x88</span> &amp;&amp; u[<span class="literal">2</span>] == <span class=
+"literal">0</span> &amp;&amp; u[<span class="literal">3</span>] == <span class=
+"literal">0</span> &amp;&amp; u[<span class="literal">4</span>] == <span class=
+"literal">0</span>);
+</pre>
+ <p>
+ This is a faster but less safe version of <code>utf8::append</code>. It does not
+ check for validity of the supplied code point, and may produce an invalid UTF-8
+ sequence.
+ </p>
+ <h4>
+ utf8::unchecked::next
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Given the iterator to the beginning of a UTF-8 sequence, it returns the code point
+ and moves the iterator to the next position.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator&gt;
+uint32_t next(octet_iterator&amp; it);
+
+</pre>
+ <p>
+ <code>it</code>: a reference to an iterator pointing to the beginning of an UTF-8
+ encoded code point. After the function returns, it is incremented to point to the
+ beginning of the next code point.<br>
+ <span class="return_value">Return value</span>: the 32 bit representation of the
+ processed UTF-8 code point.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">char</span>* twochars = <span class=
+"literal">"\xe6\x97\xa5\xd1\x88"</span>;
+<span class="keyword">char</span>* w = twochars;
+<span class="keyword">int</span> cp = unchecked::next(w);
+assert (cp == <span class="literal">0x65e5</span>);
+assert (w == twochars + <span class="literal">3</span>);
+</pre>
+ <p>
+ This is a faster but less safe version of <code>utf8::next</code>. It does not
+ check for validity of the supplied UTF-8 sequence.
+ </p>
+ <h4>
+ utf8::unchecked::peek_next
+ </h4>
+ <p class="version">
+ Available in version 2.1 and later.
+ </p>
+ <p>
+ Given the iterator to the beginning of a UTF-8 sequence, it returns the code point.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator&gt;
+uint32_t peek_next(octet_iterator it);
+
+</pre>
+ <p>
+ <code>it</code>: an iterator pointing to the beginning of an UTF-8
+ encoded code point.<br>
+ <span class="return_value">Return value</span>: the 32 bit representation of the
+ processed UTF-8 code point.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">char</span>* twochars = <span class=
+"literal">"\xe6\x97\xa5\xd1\x88"</span>;
+<span class="keyword">char</span>* w = twochars;
+<span class="keyword">int</span> cp = unchecked::peek_next(w);
+assert (cp == <span class="literal">0x65e5</span>);
+assert (w == twochars);
+</pre>
+ <p>
+ This is a faster but less safe version of <code>utf8::peek_next</code>. It does not
+ check for validity of the supplied UTF-8 sequence.
+ </p>
+ <h4>
+ utf8::unchecked::prior
+ </h4>
+ <p class="version">
+ Available in version 1.02 and later.
+ </p>
+ <p>
+ Given a reference to an iterator pointing to an octet in a UTF-8 seqence, it
+ decreases the iterator until it hits the beginning of the previous UTF-8 encoded
+ code point and returns the 32 bits representation of the code point.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator&gt;
+uint32_t prior(octet_iterator&amp; it);
+
+</pre>
+ <p>
+ <code>it</code>: a reference pointing to an octet within a UTF-8 encoded string.
+ After the function returns, it is decremented to point to the beginning of the
+ previous code point.<br>
+ <span class="return_value">Return value</span>: the 32 bit representation of the
+ previous code point.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">char</span>* twochars = <span class=
+"literal">"\xe6\x97\xa5\xd1\x88"</span>;
+<span class="keyword">char</span>* w = twochars + <span class="literal">3</span>;
+<span class="keyword">int</span> cp = unchecked::prior (w);
+assert (cp == <span class="literal">0x65e5</span>);
+assert (w == twochars);
+</pre>
+ <p>
+ This is a faster but less safe version of <code>utf8::prior</code>. It does not
+ check for validity of the supplied UTF-8 sequence and offers no boundary checking.
+ </p>
+ <h4>
+ utf8::unchecked::previous (deprecated, see utf8::unchecked::prior)
+ </h4>
+ <p class="version">
+ Deprecated in version 1.02 and later.
+ </p>
+ <p>
+ Given a reference to an iterator pointing to an octet in a UTF-8 seqence, it
+ decreases the iterator until it hits the beginning of the previous UTF-8 encoded
+ code point and returns the 32 bits representation of the code point.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator&gt;
+uint32_t previous(octet_iterator&amp; it);
+
+</pre>
+ <p>
+ <code>it</code>: a reference pointing to an octet within a UTF-8 encoded string.
+ After the function returns, it is decremented to point to the beginning of the
+ previous code point.<br>
+ <span class="return_value">Return value</span>: the 32 bit representation of the
+ previous code point.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">char</span>* twochars = <span class=
+"literal">"\xe6\x97\xa5\xd1\x88"</span>;
+<span class="keyword">char</span>* w = twochars + <span class="literal">3</span>;
+<span class="keyword">int</span> cp = unchecked::previous (w);
+assert (cp == <span class="literal">0x65e5</span>);
+assert (w == twochars);
+</pre>
+ <p>
+ The reason this function is deprecated is just the consistency with the "checked"
+ versions, where <code>prior</code> should be used instead of <code>previous</code>.
+ In fact, <code>unchecked::previous</code> behaves exactly the same as <code>
+ unchecked::prior</code>
+ </p>
+ <p>
+ This is a faster but less safe version of <code>utf8::previous</code>. It does not
+ check for validity of the supplied UTF-8 sequence and offers no boundary checking.
+ </p>
+ <h4>
+ utf8::unchecked::advance
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Advances an iterator by the specified number of code points within an UTF-8
+ sequence.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator, typename distance_type&gt;
+<span class="keyword">void</span> advance (octet_iterator&amp; it, distance_type n);
+
+</pre>
+ <p>
+ <code>it</code>: a reference to an iterator pointing to the beginning of an UTF-8
+ encoded code point. After the function returns, it is incremented to point to the
+ nth following code point.<br>
+ <code>n</code>: a positive integer that shows how many code points we want to
+ advance.<br>
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">char</span>* twochars = <span class=
+"literal">"\xe6\x97\xa5\xd1\x88"</span>;
+<span class="keyword">char</span>* w = twochars;
+unchecked::advance (w, <span class="literal">2</span>);
+assert (w == twochars + <span class="literal">5</span>);
+</pre>
+ <p>
+ This function works only "forward". In case of a negative <code>n</code>, there is
+ no effect.
+ </p>
+ <p>
+ This is a faster but less safe version of <code>utf8::advance</code>. It does not
+ check for validity of the supplied UTF-8 sequence and offers no boundary checking.
+ </p>
+ <h4>
+ utf8::unchecked::distance
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Given the iterators to two UTF-8 encoded code points in a seqence, returns the
+ number of code points between them.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator&gt;
+<span class=
+"keyword">typename</span> std::iterator_traits&lt;octet_iterator&gt;::difference_type distance (octet_iterator first, octet_iterator last);
+</pre>
+ <p>
+ <code>first</code>: an iterator to a beginning of a UTF-8 encoded code point.<br>
+ <code>last</code>: an iterator to a "post-end" of the last UTF-8 encoded code
+ point in the sequence we are trying to determine the length. It can be the
+ beginning of a new code point, or not.<br>
+ <span class="return_value">Return value</span> the distance between the iterators,
+ in code points.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">char</span>* twochars = <span class=
+"literal">"\xe6\x97\xa5\xd1\x88"</span>;
+size_t dist = utf8::unchecked::distance(twochars, twochars + <span class=
+"literal">5</span>);
+assert (dist == <span class="literal">2</span>);
+</pre>
+ <p>
+ This is a faster but less safe version of <code>utf8::distance</code>. It does not
+ check for validity of the supplied UTF-8 sequence.
+ </p>
+ <h4>
+ utf8::unchecked::utf16to8
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Converts a UTF-16 encoded string to UTF-8.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> u16bit_iterator, <span class=
+"keyword">typename</span> octet_iterator&gt;
+octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result);
+
+</pre>
+ <p>
+ <code>start</code>: an iterator pointing to the beginning of the UTF-16 encoded
+ string to convert.<br>
+ <code>end</code>: an iterator pointing to pass-the-end of the UTF-16 encoded
+ string to convert.<br>
+ <code>result</code>: an output iterator to the place in the UTF-8 string where to
+ append the result of conversion.<br>
+ <span class="return_value">Return value</span>: An iterator pointing to the place
+ after the appended UTF-8 string.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">unsigned short</span> utf16string[] = {<span class=
+"literal">0x41</span>, <span class="literal">0x0448</span>, <span class=
+"literal">0x65e5</span>, <span class="literal">0xd834</span>, <span class=
+"literal">0xdd1e</span>};
+vector&lt;<span class="keyword">unsigned char</span>&gt; utf8result;
+unchecked::utf16to8(utf16string, utf16string + <span class=
+"literal">5</span>, back_inserter(utf8result));
+assert (utf8result.size() == <span class="literal">10</span>);
+</pre>
+ <p>
+ This is a faster but less safe version of <code>utf8::utf16to8</code>. It does not
+ check for validity of the supplied UTF-16 sequence.
+ </p>
+ <h4>
+ utf8::unchecked::utf8to16
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Converts an UTF-8 encoded string to UTF-16
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> u16bit_iterator, typename octet_iterator&gt;
+u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result);
+
+</pre>
+ <p>
+ <code>start</code>: an iterator pointing to the beginning of the UTF-8 encoded
+ string to convert. &lt; br /&gt; <code>end</code>: an iterator pointing to
+ pass-the-end of the UTF-8 encoded string to convert.<br>
+ <code>result</code>: an output iterator to the place in the UTF-16 string where to
+ append the result of conversion.<br>
+ <span class="return_value">Return value</span>: An iterator pointing to the place
+ after the appended UTF-16 string.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">char</span> utf8_with_surrogates[] = <span class=
+"literal">"\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e"</span>;
+vector &lt;<span class="keyword">unsigned short</span>&gt; utf16result;
+unchecked::utf8to16(utf8_with_surrogates, utf8_with_surrogates + <span class=
+"literal">9</span>, back_inserter(utf16result));
+assert (utf16result.size() == <span class="literal">4</span>);
+assert (utf16result[<span class="literal">2</span>] == <span class=
+"literal">0xd834</span>);
+assert (utf16result[<span class="literal">3</span>] == <span class=
+"literal">0xdd1e</span>);
+</pre>
+ <p>
+ This is a faster but less safe version of <code>utf8::utf8to16</code>. It does not
+ check for validity of the supplied UTF-8 sequence.
+ </p>
+ <h4>
+ utf8::unchecked::utf32to8
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Converts a UTF-32 encoded string to UTF-8.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator, <span class=
+"keyword">typename</span> u32bit_iterator&gt;
+octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result);
+
+</pre>
+ <p>
+ <code>start</code>: an iterator pointing to the beginning of the UTF-32 encoded
+ string to convert.<br>
+ <code>end</code>: an iterator pointing to pass-the-end of the UTF-32 encoded
+ string to convert.<br>
+ <code>result</code>: an output iterator to the place in the UTF-8 string where to
+ append the result of conversion.<br>
+ <span class="return_value">Return value</span>: An iterator pointing to the place
+ after the appended UTF-8 string.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">int</span> utf32string[] = {<span class=
+"literal">0x448</span>, <span class="literal">0x65e5</span>, <span class=
+"literal">0x10346</span>, <span class="literal">0</span>};
+vector&lt;<span class="keyword">unsigned char</span>&gt; utf8result;
+utf32to8(utf32string, utf32string + <span class=
+"literal">3</span>, back_inserter(utf8result));
+assert (utf8result.size() == <span class="literal">9</span>);
+</pre>
+ <p>
+ This is a faster but less safe version of <code>utf8::utf32to8</code>. It does not
+ check for validity of the supplied UTF-32 sequence.
+ </p>
+ <h4>
+ utf8::unchecked::utf8to32
+ </h4>
+ <p class="version">
+ Available in version 1.0 and later.
+ </p>
+ <p>
+ Converts a UTF-8 encoded string to UTF-32.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class=
+"keyword">typename</span> octet_iterator, typename u32bit_iterator&gt;
+u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result);
+
+</pre>
+ <p>
+ <code>start</code>: an iterator pointing to the beginning of the UTF-8 encoded
+ string to convert.<br>
+ <code>end</code>: an iterator pointing to pass-the-end of the UTF-8 encoded string
+ to convert.<br>
+ <code>result</code>: an output iterator to the place in the UTF-32 string where to
+ append the result of conversion.<br>
+ <span class="return_value">Return value</span>: An iterator pointing to the place
+ after the appended UTF-32 string.
+ </p>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">char</span>* twochars = <span class=
+"literal">"\xe6\x97\xa5\xd1\x88"</span>;
+vector&lt;<span class="keyword">int</span>&gt; utf32result;
+unchecked::utf8to32(twochars, twochars + <span class=
+"literal">5</span>, back_inserter(utf32result));
+assert (utf32result.size() == <span class="literal">2</span>);
+</pre>
+ <p>
+ This is a faster but less safe version of <code>utf8::utf8to32</code>. It does not
+ check for validity of the supplied UTF-8 sequence.
+ </p>
+ <h3 id="typesunchecked">
+ Types From utf8::unchecked Namespace
+ </h3>
+ <h4>
+ utf8::iterator
+ </h4>
+ <p class="version">
+ Available in version 2.0 and later.
+ </p>
+ <p>
+ Adapts the underlying octet iterator to iterate over the sequence of code points,
+ rather than raw octets.
+ </p>
+<pre>
+<span class="keyword">template</span> &lt;<span class="keyword">typename</span> octet_iterator&gt;
+<span class="keyword">class</span> iterator;
+</pre>
+
+ <h5>Member functions</h5>
+ <dl>
+ <dt><code>iterator();</code> <dd> the deafult constructor; the underlying <code>octet_iterator</code> is
+ constructed with its default constructor.
+ <dt><code><span class="keyword">explicit</span> iterator (const octet_iterator&amp; octet_it);
+ </code> <dd> a constructor
+ that initializes the underlying <code>octet_iterator</code> with <code>octet_it</code>
+ <dt><code>octet_iterator base () <span class="keyword">const</span>;</code> <dd> returns the
+ underlying <code>octet_iterator</code>.
+ <dt><code>uint32_t operator * () <span class="keyword">const</span>;</code> <dd> decodes the utf-8 sequence
+ the underlying <code>octet_iterator</code> is pointing to and returns the code point.
+ <dt><code><span class="keyword">bool operator</span> == (const iterator&amp; rhs)
+ <span class="keyword">const</span>;</code> <dd> returns <span class="keyword">true</span>
+ if the two underlaying iterators are equal.
+ <dt><code><span class="keyword">bool operator</span> != (const iterator&amp; rhs)
+ <span class="keyword">const</span>;</code> <dd> returns <span class="keyword">true</span>
+ if the two underlaying iterators are not equal.
+ <dt><code>iterator&amp; <span class="keyword">operator</span> ++ (); </code> <dd> the prefix increment - moves
+ the iterator to the next UTF-8 encoded code point.
+ <dt><code>iterator <span class="keyword">operator</span> ++ (<span class="keyword">int</span>); </code> <dd>
+ the postfix increment - moves the iterator to the next UTF-8 encoded code point and returns the current one.
+ <dt><code>iterator&amp; <span class="keyword">operator</span> -- (); </code> <dd> the prefix decrement - moves
+ the iterator to the previous UTF-8 encoded code point.
+ <dt><code>iterator <span class="keyword">operator</span> -- (<span class="keyword">int</span>); </code> <dd>
+ the postfix decrement - moves the iterator to the previous UTF-8 encoded code point and returns the current one.
+ </dl>
+ <p>
+ Example of use:
+ </p>
+<pre>
+<span class="keyword">char</span>* threechars = <span class="literal">"\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88"</span>;
+utf8::unchecked::iterator&lt;<span class="keyword">char</span>*&gt; un_it(threechars);
+utf8::unchecked::iterator&lt;<span class="keyword">char</span>*&gt; un_it2 = un_it;
+assert (un_it2 == un_it);
+assert (*un_it == <span class="literal">0x10346</span>);
+assert (*(++un_it) == <span class="literal">0x65e5</span>);
+assert ((*un_it++) == <span class="literal">0x65e5</span>);
+assert (*un_it == <span class="literal">0x0448</span>);
+assert (un_it != un_it2);
+utf8::::unchecked::iterator&lt;<span class="keyword">char</span>*&gt; un_endit (threechars + <span class="literal">9</span>);
+assert (++un_it == un_endit);
+assert (*(--un_it) == <span class="literal">0x0448</span>);
+assert ((*un_it--) == <span class="literal">0x0448</span>);
+assert (*un_it == <span class="literal">0x65e5</span>);
+assert (--un_it == utf8::unchecked::iterator&lt;<span class="keyword">char</span>*&gt;(threechars));
+assert (*un_it == <span class="literal">0x10346</span>);
+</pre>
+ <p>
+ This is an unchecked version of <code>utf8::iterator</code>. It is faster in many cases, but offers
+ no validity or range checks.
+ </p>
+ <h2 id="points">
+ Points of interest
+ </h2>
+ <h4>
+ Design goals and decisions
+ </h4>
+ <p>
+ The library was designed to be:
+ </p>
+ <ol>
+ <li>
+ Generic: for better or worse, there are many C++ string classes out there, and
+ the library should work with as many of them as possible.
+ </li>
+ <li>
+ Portable: the library should be portable both accross different platforms and
+ compilers. The only non-portable code is a small section that declares unsigned
+ integers of different sizes: three typedefs. They can be changed by the users of
+ the library if they don't match their platform. The default setting should work
+ for Windows (both 32 and 64 bit), and most 32 bit and 64 bit Unix derivatives.
+ </li>
+ <li>
+ Lightweight: follow the "pay only for what you use" guideline.
+ </li>
+ <li>
+ Unintrusive: avoid forcing any particular design or even programming style on the
+ user. This is a library, not a framework.
+ </li>
+ </ol>
+ <h4>
+ Alternatives
+ </h4>
+ <p>
+ In case you want to look into other means of working with UTF-8 strings from C++,
+ here is the list of solutions I am aware of:
+ </p>
+ <ol>
+ <li>
+ <a href="http://icu.sourceforge.net/">ICU Library</a>. It is very powerful,
+ complete, feature-rich, mature, and widely used. Also big, intrusive,
+ non-generic, and doesn't play well with the Standard Library. I definitelly
+ recommend looking at ICU even if you don't plan to use it.
+ </li>
+ <li>
+ C++11 language and library features. Still far from complete, and not widely
+ supported by compiler vendors.
+ </li>
+ <li>
+ <a href=
+ "http://www.gtkmm.org/gtkmm2/docs/tutorial/html/ch03s04.html">Glib::ustring</a>.
+ A class specifically made to work with UTF-8 strings, and also feel like
+ <code>std::string</code>. If you prefer to have yet another string class in your
+ code, it may be worth a look. Be aware of the licensing issues, though.
+ </li>
+ <li>
+ Platform dependent solutions: Windows and POSIX have functions to convert strings
+ from one encoding to another. That is only a subset of what my library offers,
+ but if that is all you need it may be good enough.
+ </li>
+ </ol>
+ <h2 id="links">
+ Links
+ </h2>
+ <ol>
+ <li>
+ <a href="http://www.unicode.org/">The Unicode Consortium</a>.
+ </li>
+ <li>
+ <a href="http://icu.sourceforge.net/">ICU Library</a>.
+ </li>
+ <li>
+ <a href="http://en.wikipedia.org/wiki/UTF-8">UTF-8 at Wikipedia</a>
+ </li>
+ <li>
+ <a href="http://www.cl.cam.ac.uk/~mgk25/unicode.html">UTF-8 and Unicode FAQ for
+ Unix/Linux</a>
+ </li>
+ </ol>
+ </body>
+</html>
diff --git a/src/mesh/assimp-master/contrib/utf8cpp/source/utf8.h b/src/mesh/assimp-master/contrib/utf8cpp/source/utf8.h
new file mode 100644
index 0000000..82b13f5
--- /dev/null
+++ b/src/mesh/assimp-master/contrib/utf8cpp/source/utf8.h
@@ -0,0 +1,34 @@
+// Copyright 2006 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_2675DCD0_9480_4c0c_B92A_CC14C027B731
+#define UTF8_FOR_CPP_2675DCD0_9480_4c0c_B92A_CC14C027B731
+
+#include "utf8/checked.h"
+#include "utf8/unchecked.h"
+
+#endif // header guard
diff --git a/src/mesh/assimp-master/contrib/utf8cpp/source/utf8/checked.h b/src/mesh/assimp-master/contrib/utf8cpp/source/utf8/checked.h
new file mode 100644
index 0000000..648636e
--- /dev/null
+++ b/src/mesh/assimp-master/contrib/utf8cpp/source/utf8/checked.h
@@ -0,0 +1,333 @@
+// Copyright 2006-2016 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_CHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731
+#define UTF8_FOR_CPP_CHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731
+
+#include "core.h"
+#include <stdexcept>
+
+namespace utf8
+{
+ // Base for the exceptions that may be thrown from the library
+ class exception : public ::std::exception {
+ };
+
+ // Exceptions that may be thrown from the library functions.
+ class invalid_code_point : public exception {
+ uint32_t cp;
+ public:
+ invalid_code_point(uint32_t codepoint) : cp(codepoint) {}
+ virtual const char* what() const NOEXCEPT OVERRIDE { return "Invalid code point"; }
+ uint32_t code_point() const {return cp;}
+ };
+
+ class invalid_utf8 : public exception {
+ uint8_t u8;
+ public:
+ invalid_utf8 (uint8_t u) : u8(u) {}
+ virtual const char* what() const NOEXCEPT OVERRIDE { return "Invalid UTF-8"; }
+ uint8_t utf8_octet() const {return u8;}
+ };
+
+ class invalid_utf16 : public exception {
+ uint16_t u16;
+ public:
+ invalid_utf16 (uint16_t u) : u16(u) {}
+ virtual const char* what() const NOEXCEPT 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"; }
+ };
+
+ /// The library API - functions intended to be called by the users
+
+ template <typename octet_iterator>
+ octet_iterator append(uint32_t cp, octet_iterator result)
+ {
+ 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;
+ }
+
+ template <typename octet_iterator, typename output_iterator>
+ output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out, uint32_t replacement)
+ {
+ while (start != end) {
+ octet_iterator sequence_start = start;
+ internal::utf_error err_code = utf8::internal::validate_next(start, end);
+ switch (err_code) {
+ case internal::UTF8_OK :
+ for (octet_iterator it = sequence_start; it != start; ++it)
+ *out++ = *it;
+ break;
+ case internal::NOT_ENOUGH_ROOM:
+ out = utf8::append (replacement, out);
+ start = end;
+ break;
+ case internal::INVALID_LEAD:
+ out = utf8::append (replacement, out);
+ ++start;
+ break;
+ case internal::INCOMPLETE_SEQUENCE:
+ case internal::OVERLONG_SEQUENCE:
+ case internal::INVALID_CODE_POINT:
+ out = utf8::append (replacement, out);
+ ++start;
+ // just one replacement mark for the sequence
+ while (start != end && utf8::internal::is_trail(*start))
+ ++start;
+ break;
+ }
+ }
+ return out;
+ }
+
+ template <typename octet_iterator, typename output_iterator>
+ inline output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out)
+ {
+ static const uint32_t replacement_marker = utf8::internal::mask16(0xfffd);
+ return utf8::replace_invalid(start, end, out, replacement_marker);
+ }
+
+ template <typename octet_iterator>
+ uint32_t next(octet_iterator& it, octet_iterator end)
+ {
+ uint32_t cp = 0;
+ internal::utf_error err_code = utf8::internal::validate_next(it, end, cp);
+ switch (err_code) {
+ case internal::UTF8_OK :
+ break;
+ case internal::NOT_ENOUGH_ROOM :
+ throw not_enough_room();
+ case internal::INVALID_LEAD :
+ case internal::INCOMPLETE_SEQUENCE :
+ case internal::OVERLONG_SEQUENCE :
+ throw invalid_utf8(*it);
+ case internal::INVALID_CODE_POINT :
+ throw invalid_code_point(cp);
+ }
+ return cp;
+ }
+
+ template <typename octet_iterator>
+ uint32_t peek_next(octet_iterator it, octet_iterator end)
+ {
+ return utf8::next(it, end);
+ }
+
+ template <typename octet_iterator>
+ uint32_t prior(octet_iterator& it, octet_iterator start)
+ {
+ // can't do much if it == start
+ if (it == start)
+ throw not_enough_room();
+
+ octet_iterator end = it;
+ // Go back until we hit either a lead octet or start
+ while (utf8::internal::is_trail(*(--it)))
+ if (it == start)
+ throw invalid_utf8(*it); // error - no lead byte in the sequence
+ return utf8::peek_next(it, end);
+ }
+
+ template <typename octet_iterator, typename distance_type>
+ void advance (octet_iterator& it, distance_type n, octet_iterator end)
+ {
+ const distance_type zero(0);
+ if (n < zero) {
+ // backward
+ for (distance_type i = n; i < zero; ++i)
+ utf8::prior(it, end);
+ } else {
+ // forward
+ for (distance_type i = zero; i < n; ++i)
+ utf8::next(it, end);
+ }
+ }
+
+ template <typename octet_iterator>
+ typename std::iterator_traits<octet_iterator>::difference_type
+ distance (octet_iterator first, octet_iterator last)
+ {
+ typename std::iterator_traits<octet_iterator>::difference_type dist;
+ for (dist = 0; first < last; ++dist)
+ utf8::next(first, last);
+ return dist;
+ }
+
+ template <typename u16bit_iterator, typename octet_iterator>
+ octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result)
+ {
+ while (start != end) {
+ uint32_t cp = utf8::internal::mask16(*start++);
+ // Take care of surrogate pairs first
+ if (utf8::internal::is_lead_surrogate(cp)) {
+ if (start != end) {
+ uint32_t trail_surrogate = utf8::internal::mask16(*start++);
+ if (utf8::internal::is_trail_surrogate(trail_surrogate))
+ cp = (cp << 10) + trail_surrogate + internal::SURROGATE_OFFSET;
+ else
+ throw invalid_utf16(static_cast<uint16_t>(trail_surrogate));
+ }
+ else
+ throw invalid_utf16(static_cast<uint16_t>(cp));
+
+ }
+ // Lone trail surrogate
+ else if (utf8::internal::is_trail_surrogate(cp))
+ throw invalid_utf16(static_cast<uint16_t>(cp));
+
+ result = utf8::append(cp, result);
+ }
+ return result;
+ }
+
+ template <typename u16bit_iterator, typename octet_iterator>
+ u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result)
+ {
+ while (start < end) {
+ uint32_t cp = utf8::next(start, end);
+ if (cp > 0xffff) { //make a surrogate pair
+ *result++ = static_cast<uint16_t>((cp >> 10) + internal::LEAD_OFFSET);
+ *result++ = static_cast<uint16_t>((cp & 0x3ff) + internal::TRAIL_SURROGATE_MIN);
+ }
+ else
+ *result++ = static_cast<uint16_t>(cp);
+ }
+ return result;
+ }
+
+ template <typename octet_iterator, typename u32bit_iterator>
+ octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result)
+ {
+ while (start != end)
+ result = utf8::append(*(start++), result);
+
+ return result;
+ }
+
+ template <typename octet_iterator, typename u32bit_iterator>
+ u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result)
+ {
+ while (start < end)
+ (*result++) = utf8::next(start, end);
+
+ return result;
+ }
+
+ // The iterator class
+ template <typename octet_iterator>
+ class iterator {
+ octet_iterator it;
+ octet_iterator range_start;
+ octet_iterator range_end;
+ public:
+ typedef uint32_t value_type;
+ typedef uint32_t* pointer;
+ typedef uint32_t& reference;
+ typedef std::ptrdiff_t difference_type;
+ typedef std::bidirectional_iterator_tag iterator_category;
+ iterator () {}
+ explicit iterator (const octet_iterator& octet_it,
+ const octet_iterator& rangestart,
+ const octet_iterator& rangeend) :
+ it(octet_it), range_start(rangestart), range_end(rangeend)
+ {
+ if (it < range_start || it > range_end)
+ throw std::out_of_range("Invalid utf-8 iterator position");
+ }
+ // the default "big three" are OK
+ octet_iterator base () const { return it; }
+ uint32_t operator * () const
+ {
+ octet_iterator temp = it;
+ return utf8::next(temp, range_end);
+ }
+ bool operator == (const iterator& rhs) const
+ {
+ if (range_start != rhs.range_start || range_end != rhs.range_end)
+ throw std::logic_error("Comparing utf-8 iterators defined with different ranges");
+ return (it == rhs.it);
+ }
+ bool operator != (const iterator& rhs) const
+ {
+ return !(operator == (rhs));
+ }
+ iterator& operator ++ ()
+ {
+ utf8::next(it, range_end);
+ return *this;
+ }
+ iterator operator ++ (int)
+ {
+ iterator temp = *this;
+ utf8::next(it, range_end);
+ return temp;
+ }
+ iterator& operator -- ()
+ {
+ utf8::prior(it, range_start);
+ return *this;
+ }
+ iterator operator -- (int)
+ {
+ iterator temp = *this;
+ utf8::prior(it, range_start);
+ return temp;
+ }
+ }; // class iterator
+
+} // namespace utf8
+
+#if UTF_CPP_CPLUSPLUS >= 201103L // C++ 11 or later
+#include "cpp11.h"
+#endif // C++ 11 or later
+
+#endif //header guard
+
diff --git a/src/mesh/assimp-master/contrib/utf8cpp/source/utf8/core.h b/src/mesh/assimp-master/contrib/utf8cpp/source/utf8/core.h
new file mode 100644
index 0000000..244e892
--- /dev/null
+++ b/src/mesh/assimp-master/contrib/utf8cpp/source/utf8/core.h
@@ -0,0 +1,338 @@
+// Copyright 2006 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_CORE_H_2675DCD0_9480_4c0c_B92A_CC14C027B731
+#define UTF8_FOR_CPP_CORE_H_2675DCD0_9480_4c0c_B92A_CC14C027B731
+
+#include <iterator>
+
+// Determine the C++ standard version.
+// If the user defines UTF_CPP_CPLUSPLUS, use that.
+// Otherwise, trust the unreliable predefined macro __cplusplus
+
+#if !defined UTF_CPP_CPLUSPLUS
+ #define UTF_CPP_CPLUSPLUS __cplusplus
+#endif
+
+#if UTF_CPP_CPLUSPLUS >= 201103L // C++ 11 or later
+ #define OVERRIDE override
+ #define NOEXCEPT noexcept
+#else // C++ 98/03
+ #define OVERRIDE
+ #define NOEXCEPT throw()
+#endif // C++ 11 or later
+
+
+namespace utf8
+{
+ // The typedefs for 8-bit, 16-bit and 32-bit unsigned integers
+ // You may need to change them to match your system.
+ // These typedefs have the same names as ones from cstdint, or boost/cstdint
+ typedef unsigned char uint8_t;
+ typedef unsigned short uint16_t;
+ typedef unsigned int uint32_t;
+
+// Helper code - not intended to be directly called by the library users. May be changed at any time
+namespace internal
+{
+ // Unicode constants
+ // Leading (high) surrogates: 0xd800 - 0xdbff
+ // Trailing (low) surrogates: 0xdc00 - 0xdfff
+ const uint16_t LEAD_SURROGATE_MIN = 0xd800u;
+ const uint16_t LEAD_SURROGATE_MAX = 0xdbffu;
+ const uint16_t TRAIL_SURROGATE_MIN = 0xdc00u;
+ const uint16_t TRAIL_SURROGATE_MAX = 0xdfffu;
+ const uint16_t LEAD_OFFSET = 0xd7c0u; // LEAD_SURROGATE_MIN - (0x10000 >> 10)
+ const uint32_t SURROGATE_OFFSET = 0xfca02400u; // 0x10000u - (LEAD_SURROGATE_MIN << 10) - TRAIL_SURROGATE_MIN
+
+ // Maximum valid value for a Unicode code point
+ const uint32_t CODE_POINT_MAX = 0x0010ffffu;
+
+ template<typename octet_type>
+ inline uint8_t mask8(octet_type oc)
+ {
+ return static_cast<uint8_t>(0xff & oc);
+ }
+ template<typename u16_type>
+ inline uint16_t mask16(u16_type oc)
+ {
+ return static_cast<uint16_t>(0xffff & oc);
+ }
+ template<typename octet_type>
+ inline bool is_trail(octet_type oc)
+ {
+ return ((utf8::internal::mask8(oc) >> 6) == 0x2);
+ }
+
+ template <typename u16>
+ inline bool is_lead_surrogate(u16 cp)
+ {
+ return (cp >= LEAD_SURROGATE_MIN && cp <= LEAD_SURROGATE_MAX);
+ }
+
+ template <typename u16>
+ inline bool is_trail_surrogate(u16 cp)
+ {
+ return (cp >= TRAIL_SURROGATE_MIN && cp <= TRAIL_SURROGATE_MAX);
+ }
+
+ template <typename u16>
+ inline bool is_surrogate(u16 cp)
+ {
+ return (cp >= LEAD_SURROGATE_MIN && cp <= TRAIL_SURROGATE_MAX);
+ }
+
+ template <typename u32>
+ inline bool is_code_point_valid(u32 cp)
+ {
+ return (cp <= CODE_POINT_MAX && !utf8::internal::is_surrogate(cp));
+ }
+
+ template <typename octet_iterator>
+ inline typename std::iterator_traits<octet_iterator>::difference_type
+ sequence_length(octet_iterator lead_it)
+ {
+ uint8_t lead = utf8::internal::mask8(*lead_it);
+ if (lead < 0x80)
+ return 1;
+ else if ((lead >> 5) == 0x6)
+ return 2;
+ else if ((lead >> 4) == 0xe)
+ return 3;
+ else if ((lead >> 3) == 0x1e)
+ return 4;
+ else
+ return 0;
+ }
+
+ template <typename octet_difference_type>
+ inline bool is_overlong_sequence(uint32_t cp, octet_difference_type length)
+ {
+ if (cp < 0x80) {
+ if (length != 1)
+ return true;
+ }
+ else if (cp < 0x800) {
+ if (length != 2)
+ return true;
+ }
+ else if (cp < 0x10000) {
+ if (length != 3)
+ return true;
+ }
+
+ return false;
+ }
+
+ enum utf_error {UTF8_OK, NOT_ENOUGH_ROOM, INVALID_LEAD, INCOMPLETE_SEQUENCE, OVERLONG_SEQUENCE, INVALID_CODE_POINT};
+
+ /// Helper for get_sequence_x
+ template <typename octet_iterator>
+ utf_error increase_safely(octet_iterator& it, octet_iterator end)
+ {
+ if (++it == end)
+ return NOT_ENOUGH_ROOM;
+
+ if (!utf8::internal::is_trail(*it))
+ return INCOMPLETE_SEQUENCE;
+
+ return UTF8_OK;
+ }
+
+ #define UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(IT, END) {utf_error ret = increase_safely(IT, END); if (ret != UTF8_OK) return ret;}
+
+ /// get_sequence_x functions decode utf-8 sequences of the length x
+ template <typename octet_iterator>
+ utf_error get_sequence_1(octet_iterator& it, octet_iterator end, uint32_t& code_point)
+ {
+ if (it == end)
+ return NOT_ENOUGH_ROOM;
+
+ code_point = utf8::internal::mask8(*it);
+
+ return UTF8_OK;
+ }
+
+ template <typename octet_iterator>
+ utf_error get_sequence_2(octet_iterator& it, octet_iterator end, uint32_t& code_point)
+ {
+ if (it == end)
+ return NOT_ENOUGH_ROOM;
+
+ code_point = utf8::internal::mask8(*it);
+
+ UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
+
+ code_point = ((code_point << 6) & 0x7ff) + ((*it) & 0x3f);
+
+ return UTF8_OK;
+ }
+
+ template <typename octet_iterator>
+ utf_error get_sequence_3(octet_iterator& it, octet_iterator end, uint32_t& code_point)
+ {
+ if (it == end)
+ return NOT_ENOUGH_ROOM;
+
+ code_point = utf8::internal::mask8(*it);
+
+ UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
+
+ code_point = ((code_point << 12) & 0xffff) + ((utf8::internal::mask8(*it) << 6) & 0xfff);
+
+ UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
+
+ code_point += (*it) & 0x3f;
+
+ return UTF8_OK;
+ }
+
+ template <typename octet_iterator>
+ utf_error get_sequence_4(octet_iterator& it, octet_iterator end, uint32_t& code_point)
+ {
+ if (it == end)
+ return NOT_ENOUGH_ROOM;
+
+ code_point = utf8::internal::mask8(*it);
+
+ UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
+
+ code_point = ((code_point << 18) & 0x1fffff) + ((utf8::internal::mask8(*it) << 12) & 0x3ffff);
+
+ UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
+
+ code_point += (utf8::internal::mask8(*it) << 6) & 0xfff;
+
+ UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
+
+ code_point += (*it) & 0x3f;
+
+ return UTF8_OK;
+ }
+
+ #undef UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR
+
+ template <typename octet_iterator>
+ utf_error validate_next(octet_iterator& it, octet_iterator end, uint32_t& code_point)
+ {
+ if (it == end)
+ return NOT_ENOUGH_ROOM;
+
+ // Save the original value of it so we can go back in case of failure
+ // Of course, it does not make much sense with i.e. stream iterators
+ octet_iterator original_it = it;
+
+ uint32_t cp = 0;
+ // Determine the sequence length based on the lead octet
+ typedef typename std::iterator_traits<octet_iterator>::difference_type octet_difference_type;
+ const octet_difference_type length = utf8::internal::sequence_length(it);
+
+ // Get trail octets and calculate the code point
+ utf_error err = UTF8_OK;
+ switch (length) {
+ case 0:
+ return INVALID_LEAD;
+ case 1:
+ err = utf8::internal::get_sequence_1(it, end, cp);
+ break;
+ case 2:
+ err = utf8::internal::get_sequence_2(it, end, cp);
+ break;
+ case 3:
+ err = utf8::internal::get_sequence_3(it, end, cp);
+ break;
+ case 4:
+ err = utf8::internal::get_sequence_4(it, end, cp);
+ break;
+ }
+
+ if (err == UTF8_OK) {
+ // Decoding succeeded. Now, security checks...
+ if (utf8::internal::is_code_point_valid(cp)) {
+ if (!utf8::internal::is_overlong_sequence(cp, length)){
+ // Passed! Return here.
+ code_point = cp;
+ ++it;
+ return UTF8_OK;
+ }
+ else
+ err = OVERLONG_SEQUENCE;
+ }
+ else
+ err = INVALID_CODE_POINT;
+ }
+
+ // Failure branch - restore the original value of the iterator
+ it = original_it;
+ return err;
+ }
+
+ template <typename octet_iterator>
+ inline utf_error validate_next(octet_iterator& it, octet_iterator end) {
+ uint32_t ignored;
+ return utf8::internal::validate_next(it, end, ignored);
+ }
+
+} // namespace internal
+
+ /// The library API - functions intended to be called by the users
+
+ // Byte order mark
+ const uint8_t bom[] = {0xef, 0xbb, 0xbf};
+
+ template <typename octet_iterator>
+ octet_iterator find_invalid(octet_iterator start, octet_iterator end)
+ {
+ octet_iterator result = start;
+ while (result != end) {
+ utf8::internal::utf_error err_code = utf8::internal::validate_next(result, end);
+ if (err_code != internal::UTF8_OK)
+ return result;
+ }
+ return result;
+ }
+
+ template <typename octet_iterator>
+ inline bool is_valid(octet_iterator start, octet_iterator end)
+ {
+ return (utf8::find_invalid(start, end) == end);
+ }
+
+ template <typename octet_iterator>
+ inline bool starts_with_bom (octet_iterator it, octet_iterator end)
+ {
+ return (
+ ((it != end) && (utf8::internal::mask8(*it++)) == bom[0]) &&
+ ((it != end) && (utf8::internal::mask8(*it++)) == bom[1]) &&
+ ((it != end) && (utf8::internal::mask8(*it)) == bom[2])
+ );
+ }
+} // namespace utf8
+
+#endif // header guard
+
+
diff --git a/src/mesh/assimp-master/contrib/utf8cpp/source/utf8/cpp11.h b/src/mesh/assimp-master/contrib/utf8cpp/source/utf8/cpp11.h
new file mode 100644
index 0000000..d93961b
--- /dev/null
+++ b/src/mesh/assimp-master/contrib/utf8cpp/source/utf8/cpp11.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_a184c22c_d012_11e8_a8d5_f2801f1b9fd1
+#define UTF8_FOR_CPP_a184c22c_d012_11e8_a8d5_f2801f1b9fd1
+
+#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(const std::u16string& s)
+ {
+ std::string result;
+ utf16to8(s.begin(), s.end(), std::back_inserter(result));
+ return result;
+ }
+
+ inline std::u16string utf8to16(const std::string& s)
+ {
+ std::u16string result;
+ utf8to16(s.begin(), s.end(), std::back_inserter(result));
+ return result;
+ }
+
+ inline std::string utf32to8(const std::u32string& s)
+ {
+ std::string result;
+ utf32to8(s.begin(), s.end(), std::back_inserter(result));
+ return result;
+ }
+
+ inline std::u32string utf8to32(const std::string& s)
+ {
+ std::u32string result;
+ utf8to32(s.begin(), s.end(), std::back_inserter(result));
+ return result;
+ }
+
+ 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());
+ }
+
+ inline bool is_valid(const std::string& s)
+ {
+ return is_valid(s.begin(), s.end());
+ }
+
+ inline std::string replace_invalid(const std::string& 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(const std::string& s)
+ {
+ std::string result;
+ replace_invalid(s.begin(), s.end(), std::back_inserter(result));
+ return result;
+ }
+
+ inline bool starts_with_bom(const std::string& s)
+ {
+ return starts_with_bom(s.begin(), s.end());
+ }
+
+} // namespace utf8
+
+#endif // header guard
+
diff --git a/src/mesh/assimp-master/contrib/utf8cpp/source/utf8/unchecked.h b/src/mesh/assimp-master/contrib/utf8cpp/source/utf8/unchecked.h
new file mode 100644
index 0000000..0e1b51c
--- /dev/null
+++ b/src/mesh/assimp-master/contrib/utf8cpp/source/utf8/unchecked.h
@@ -0,0 +1,274 @@
+// Copyright 2006 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_UNCHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731
+#define UTF8_FOR_CPP_UNCHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731
+
+#include "core.h"
+
+namespace utf8
+{
+ namespace unchecked
+ {
+ 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;
+ }
+
+ template <typename octet_iterator, typename output_iterator>
+ output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out, uint32_t replacement)
+ {
+ while (start != end) {
+ octet_iterator sequence_start = start;
+ internal::utf_error err_code = utf8::internal::validate_next(start, end);
+ switch (err_code) {
+ case internal::UTF8_OK :
+ for (octet_iterator it = sequence_start; it != start; ++it)
+ *out++ = *it;
+ break;
+ case internal::NOT_ENOUGH_ROOM:
+ out = utf8::unchecked::append (replacement, out);
+ start = end;
+ break;
+ case internal::INVALID_LEAD:
+ out = utf8::unchecked::append (replacement, out);
+ ++start;
+ break;
+ case internal::INCOMPLETE_SEQUENCE:
+ case internal::OVERLONG_SEQUENCE:
+ case internal::INVALID_CODE_POINT:
+ out = utf8::unchecked::append (replacement, out);
+ ++start;
+ // just one replacement mark for the sequence
+ while (start != end && utf8::internal::is_trail(*start))
+ ++start;
+ break;
+ }
+ }
+ return out;
+ }
+
+ template <typename octet_iterator, typename output_iterator>
+ inline output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out)
+ {
+ static const uint32_t replacement_marker = utf8::internal::mask16(0xfffd);
+ return utf8::unchecked::replace_invalid(start, end, out, replacement_marker);
+ }
+
+ template <typename octet_iterator>
+ uint32_t next(octet_iterator& it)
+ {
+ uint32_t cp = utf8::internal::mask8(*it);
+ typename std::iterator_traits<octet_iterator>::difference_type length = utf8::internal::sequence_length(it);
+ switch (length) {
+ case 1:
+ break;
+ case 2:
+ it++;
+ cp = ((cp << 6) & 0x7ff) + ((*it) & 0x3f);
+ break;
+ case 3:
+ ++it;
+ cp = ((cp << 12) & 0xffff) + ((utf8::internal::mask8(*it) << 6) & 0xfff);
+ ++it;
+ cp += (*it) & 0x3f;
+ break;
+ case 4:
+ ++it;
+ cp = ((cp << 18) & 0x1fffff) + ((utf8::internal::mask8(*it) << 12) & 0x3ffff);
+ ++it;
+ cp += (utf8::internal::mask8(*it) << 6) & 0xfff;
+ ++it;
+ cp += (*it) & 0x3f;
+ break;
+ }
+ ++it;
+ return cp;
+ }
+
+ template <typename octet_iterator>
+ uint32_t peek_next(octet_iterator it)
+ {
+ return utf8::unchecked::next(it);
+ }
+
+ template <typename octet_iterator>
+ uint32_t prior(octet_iterator& it)
+ {
+ while (utf8::internal::is_trail(*(--it))) ;
+ octet_iterator temp = it;
+ return utf8::unchecked::next(temp);
+ }
+
+ template <typename octet_iterator, typename distance_type>
+ void advance (octet_iterator& it, distance_type n)
+ {
+ const distance_type zero(0);
+ if (n < zero) {
+ // backward
+ for (distance_type i = n; i < zero; ++i)
+ utf8::unchecked::prior(it);
+ } else {
+ // forward
+ for (distance_type i = zero; i < n; ++i)
+ utf8::unchecked::next(it);
+ }
+ }
+
+ template <typename octet_iterator>
+ typename std::iterator_traits<octet_iterator>::difference_type
+ distance (octet_iterator first, octet_iterator last)
+ {
+ typename std::iterator_traits<octet_iterator>::difference_type dist;
+ for (dist = 0; first < last; ++dist)
+ utf8::unchecked::next(first);
+ return dist;
+ }
+
+ template <typename u16bit_iterator, typename octet_iterator>
+ octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result)
+ {
+ while (start != end) {
+ uint32_t cp = utf8::internal::mask16(*start++);
+ // Take care of surrogate pairs first
+ if (utf8::internal::is_lead_surrogate(cp)) {
+ uint32_t trail_surrogate = utf8::internal::mask16(*start++);
+ cp = (cp << 10) + trail_surrogate + internal::SURROGATE_OFFSET;
+ }
+ result = utf8::unchecked::append(cp, result);
+ }
+ return result;
+ }
+
+ template <typename u16bit_iterator, typename octet_iterator>
+ u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result)
+ {
+ while (start < end) {
+ uint32_t cp = utf8::unchecked::next(start);
+ if (cp > 0xffff) { //make a surrogate pair
+ *result++ = static_cast<uint16_t>((cp >> 10) + internal::LEAD_OFFSET);
+ *result++ = static_cast<uint16_t>((cp & 0x3ff) + internal::TRAIL_SURROGATE_MIN);
+ }
+ else
+ *result++ = static_cast<uint16_t>(cp);
+ }
+ return result;
+ }
+
+ template <typename octet_iterator, typename u32bit_iterator>
+ octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result)
+ {
+ while (start != end)
+ result = utf8::unchecked::append(*(start++), result);
+
+ return result;
+ }
+
+ template <typename octet_iterator, typename u32bit_iterator>
+ u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result)
+ {
+ while (start < end)
+ (*result++) = utf8::unchecked::next(start);
+
+ return result;
+ }
+
+ // The iterator class
+ template <typename octet_iterator>
+ class iterator {
+ octet_iterator it;
+ public:
+ typedef uint32_t value_type;
+ typedef uint32_t* pointer;
+ typedef uint32_t& reference;
+ typedef std::ptrdiff_t difference_type;
+ typedef std::bidirectional_iterator_tag iterator_category;
+ iterator () {}
+ explicit iterator (const octet_iterator& octet_it): it(octet_it) {}
+ // the default "big three" are OK
+ octet_iterator base () const { return it; }
+ uint32_t operator * () const
+ {
+ octet_iterator temp = it;
+ return utf8::unchecked::next(temp);
+ }
+ bool operator == (const iterator& rhs) const
+ {
+ return (it == rhs.it);
+ }
+ bool operator != (const iterator& rhs) const
+ {
+ return !(operator == (rhs));
+ }
+ iterator& operator ++ ()
+ {
+ ::std::advance(it, utf8::internal::sequence_length(it));
+ return *this;
+ }
+ iterator operator ++ (int)
+ {
+ iterator temp = *this;
+ ::std::advance(it, utf8::internal::sequence_length(it));
+ return temp;
+ }
+ iterator& operator -- ()
+ {
+ utf8::unchecked::prior(it);
+ return *this;
+ }
+ iterator operator -- (int)
+ {
+ iterator temp = *this;
+ utf8::unchecked::prior(it);
+ return temp;
+ }
+ }; // class iterator
+
+ } // namespace utf8::unchecked
+} // namespace utf8
+
+
+#endif // header guard
+