[index] Add UTF-8, UTF-16, UTF-32 to the index

Author: jensmaurer

source/basic.tex

@@ -2989,6 +2989,7 @@
 This information is given for the convenience of users of this document and
 does not constitute an endorsement by ISO or IEC of this product.
 \end{footnote}
+\indextext{UTF-8}%
 UTF-8 encoding form
 and is composed of a contiguous sequence of
 bits,

source/compatibility.tex

@@ -177,6 +177,7 @@
 Required for new features.
 \begin{itemize}
 \item
+\indextext{UTF-8}%
 The \keyword{char8_t} keyword is added to differentiate
 the types of ordinary and UTF-8 literals\iref{lex.string}.
 \item
@@ -225,6 +226,7 @@
 \end{codeblock}
 
 \diffref{lex.literal}
+\indextext{UTF-8}%
 \change
 Type of UTF-8 string and character literals.
 \rationale
@@ -681,6 +683,7 @@
 \end{codeblock}
 
 \diffref{ostream.inserters.character}
+\indextext{UTF-8}%
 \change
 Overload resolution for ostream inserters used with UTF-8 literals.
 \rationale
@@ -1961,12 +1964,15 @@
 The type of a \grammarterm{string-literal} is changed
 from ``array of \tcode{char}''
 to ``array of \tcode{const char}''.
+\indextext{UTF-8}%
 The type of a UTF-8 string literal is changed
 from ``array of \tcode{char}''
 to ``array of \tcode{const char8_t}''.
+\indextext{UTF-16}%
 The type of a UTF-16 string literal is changed
 from ``array of \textit{some-integer-type}''
 to ``array of \tcode{const char16_t}''.
+\indextext{UTF-32}%
 The type of a UTF-32 string literal is changed
 from ``array of \textit{some-integer-type}''
 to ``array of \tcode{const char32_t}''.

source/declarations.tex

@@ -5352,6 +5352,9 @@
 \indextext{initialization!character array}
 
 \pnum
+\indextext{UTF-8}%
+\indextext{UTF-16}%
+\indextext{UTF-32}%
 An array of ordinary character type\iref{basic.fundamental},
 \keyword{char8_t} array,
 \keyword{char16_t} array,

source/future.tex

@@ -1961,6 +1961,9 @@
 \end{itemize}
 
 \pnum
+\indextext{UTF-8}%
+\indextext{UCS-2}%
+\indextext{UTF-32}%
 For the facet \tcode{codecvt_utf8}\indexlibraryglobal{codecvt_utf8}:
 \begin{itemize}
 \item
@@ -1974,6 +1977,9 @@
 \end{itemize}
 
 \pnum
+\indextext{UTF-16}%
+\indextext{UCS-2}%
+\indextext{UTF-32}%
 For the facet \tcode{codecvt_utf16}\indexlibraryglobal{codecvt_utf16}:
 \begin{itemize}
 \item
@@ -1989,6 +1995,8 @@
 \end{itemize}
 
 \pnum
+\indextext{UTF-8}%
+\indextext{UTF-16}%
 For the facet \tcode{codecvt_utf8_utf16}\indexlibraryglobal{codecvt_utf8_utf16}:
 \begin{itemize}
 \item
@@ -2456,8 +2464,11 @@
 \pnum
 The following class template specializations are required
 in addition to those specified in~\ref{locale.codecvt}.
+\indextext{UTF-8}%
+\indextext{UTF-16}%
 The specialization \tcode{codecvt<char16_t, char, mbstate_t>}
 converts between the UTF-16 and UTF-8 encoding forms, and
+\indextext{UTF-32}%
 the specialization \tcode{codecvt<char32_t, char, mbstate_t>}
 converts between the UTF-32 and UTF-8 encoding forms.
 

source/iostreams.tex

@@ -13228,11 +13228,17 @@
 so no conversion from \keyword{wchar_t} value type arguments or to \tcode{wchar_t}
 value type return values is performed.
 \end{note}
-\item \keyword{char8_t}: The encoding is UTF-8. The method of conversion
+\item
+\indextext{UTF-8}%
+\keyword{char8_t}: The encoding is UTF-8. The method of conversion
 is unspecified.
-\item \keyword{char16_t}: The encoding is UTF-16. The method of conversion
+\item
+\indextext{UTF-16}%
+\keyword{char16_t}: The encoding is UTF-16. The method of conversion
 is unspecified.
-\item \keyword{char32_t}: The encoding is UTF-32. The method of conversion
+\item
+\indextext{UTF-32}%
+\keyword{char32_t}: The encoding is UTF-32. The method of conversion
 is unspecified.
 \end{itemize}
 

source/lex.tex

@@ -364,6 +364,9 @@
 shall be one greater than the value of the previous.
 The ordinary and wide literal encodings are otherwise
 \impldef{ordinary and wide literal encodings}.
+\indextext{UTF-8}%
+\indextext{UTF-16}%
+\indextext{UTF-32}%
 For a UTF-8, UTF-16, or UTF-32 literal,
 the UCS scalar value
 corresponding to each character of the translation character set

source/locales.tex

@@ -1650,6 +1650,9 @@
 convert the implementation-defined native character set.
 \tcode{codecvt<char, char, mbstate_t>} implements a degenerate conversion;
 it does not convert at all.
+\indextext{UTF-8}%
+\indextext{UTF-16}%
+\indextext{UTF-32}%
 The specialization \tcode{codecvt<char16_t, char8_t, mbstate_t>}
 converts between the UTF-16 and UTF-8 encoding forms, and
 the specialization \tcode{codecvt} \tcode{<char32_t, char8_t, mbstate_t>}

source/strings.tex

@@ -363,6 +363,7 @@
 the built-in operators \tcode{=}, \tcode{==}, and \tcode{<} respectively.
 
 \pnum
+\indextext{UTF-8}%
 The member \tcode{eof()} returns an
 \impldef{return value of \tcode{char_traits<char8_t>::eof}} constant
 that cannot appear as a valid UTF-8 code unit.
@@ -5763,6 +5764,7 @@
 the next multibyte character (including any shift sequences).
 If the function determines
 that the next multibyte character is complete and valid,
+\indextext{UTF-8}%
 it determines the values of the corresponding UTF-8 code units and then,
 if \tcode{pc8} is not a null pointer,
 stores the value of the first (or only) such code unit
@@ -5810,6 +5812,7 @@
 If \tcode{s} is a null pointer, equivalent to
 \tcode{c8rtomb(buf, u8'$\backslash$0', ps)}
 where \tcode{buf} is an internal buffer.
+\indextext{UTF-8}%
 Otherwise, if \tcode{c8} completes a sequence of valid UTF-8 code units,
 determines the number of bytes needed
 to represent the multibyte character (including any shift sequences),