Rename \char_to_utfviii_bytes:n to \codepoint_to_bytes:n

This fits a more general pattern of moving functions: several commits will address this. There is still the question of byte order here: do we want to change and 'fill from the bottom'.
latex3 · Oct 9, 2022 · 31a1124 · 31a1124
1 parent d4f3d9b
commit 31a1124
Show file tree

Hide file tree

Showing 25 changed files with 244 additions and 277 deletions.
diff --git a/l3kernel/CHANGELOG.md b/l3kernel/CHANGELOG.md
@@ -8,6 +8,7 @@ this project uses date-based 'snapshot' version identifiers.
 ## [Unreleased]
 
 ### Added
+- `\codepoint_to_bytes:n`
 - `\codepoint_str_generate:n`
 
 ### Changed
@@ -19,6 +20,9 @@ this project uses date-based 'snapshot' version identifiers.
   tokens (issue [\#1110](https://github.com/latex3/latex3/issues/1110)), and an
   esoteric case (issue [\#1113](https://github.com/latex3/latex3/issues/1113))
 
+### Deprecated
+- `\char_to_utfviii_bytes:n`
+
 ## [2022-09-28]
 
 ### Added

diff --git a/l3kernel/doc/l3obsolete.txt b/l3kernel/doc/l3obsolete.txt
@@ -22,6 +22,7 @@ Function                            Date deprecated
 \char_str_lower_case:N                   2020-01-03
 \char_str_mixed_case:N                   2020-01-03
 \char_str_upper_case:N                   2020-01-03
+\char_to_utfviii_bytes:n                 2022-10-09
 \cs_argument_spec:N                      2022-06-24
 \l_keys_key_tl                           2020-02-08
 \l_keys_path_tl                          2020-02-08

diff --git a/l3kernel/l3candidates.dtx b/l3kernel/l3candidates.dtx
@@ -626,18 +626,6 @@
 %   (\enquote{active}), and character code $32$ (space).
 % \end{variable}
 %
-% \begin{function}[added = 2020-01-09, EXP]{\char_to_utfviii_bytes:n}
-%   \begin{syntax}
-%     \cs{char_to_utfviii_bytes:n} \Arg{codepoint}
-%   \end{syntax}
-%   Converts the (Unicode) \meta{codepoint} to UTF-8 bytes. The expansion
-%   of this function comprises four brace groups, each of which will contain
-%   a hexadecimal value: the appropriate byte. As UTF-8 is a variable-length,
-%   one or more of the groups may be empty: the bytes read in the logical order,
-%   such that a two-byte codepoint will have groups |#1| and |#2| filled
-%   and |#3| and |#4| empty.
-% \end{function}
-%
 % \begin{function}[added = 2020-01-02, rEXP]{\char_to_nfd:N}
 %   \begin{syntax}
 %     \cs{char_to_nfd:N} \meta{char}

diff --git a/l3kernel/l3deprecation.dtx b/l3kernel/l3deprecation.dtx
@@ -549,6 +549,13 @@
 %
 % \subsection{Deprecated \pkg{l3token} functions}
 %
+% \begin{macro}[EXP]{\char_to_utfviii_bytes:n}
+%    \begin{macrocode}
+\__kernel_patch_deprecation:nnNNpn { 2022-10-09 } { \codepoint_to_bytes:n }
+\cs_gset:Npn \char_to_utfviii_bytes:n { \codepoint_to_bytes:n }
+%    \end{macrocode}
+% \end{macro}
+%
 % \begin{macro}[EXP]
 %   {
 %     \char_lower_case:N, \char_upper_case:N,

diff --git a/l3kernel/l3str-convert.dtx b/l3kernel/l3str-convert.dtx
@@ -2635,7 +2635,7 @@
     \cs_new:Npn \@@_convert_pdfname_bytes:n #1
       {
         \exp_args:Ne \@@_convert_pdfname_bytes_aux:n
-          { \char_to_utfviii_bytes:n {`#1} }
+          { \codepoint_to_bytes:n {`#1} }
       }
     \cs_new:Npn \@@_convert_pdfname_bytes_aux:n #1
       { \@@_convert_pdfname_bytes_aux:nnnn #1 }

diff --git a/l3kernel/l3str.dtx b/l3kernel/l3str.dtx
@@ -2056,7 +2056,7 @@
       \use:e
         {
           \exp_not:N \@@_change_case_generate:nnnn
-            \char_to_utfviii_bytes:n {#1}
+            \codepoint_to_bytes:n {#1}
         }
     }
   \cs_new:Npn \@@_change_case_generate:nnnn #1#2#3#4

diff --git a/l3kernel/l3text-case.dtx b/l3kernel/l3text-case.dtx
@@ -1868,7 +1868,7 @@
                   }
               }
             \use:x
-              { \@@_tmp:w \char_to_utfviii_bytes:n { "#2 } }  
+              { \@@_tmp:w \codepoint_to_bytes:n { "#2 } }  
           \group_end:
         }
       \@@_tmp:w \c_@@_dotless_i_tl      { 0131 }
@@ -1902,8 +1902,8 @@
           \use:x
             {
               \@@_tmp:w
-                \char_to_utfviii_bytes:n { "#1 }
-                \char_to_utfviii_bytes:n { "#2 }
+                \codepoint_to_bytes:n { "#1 }
+                \codepoint_to_bytes:n { "#2 }
             }
           \@@_loop:nn
         }
@@ -2183,8 +2183,8 @@
             \use:x
               {
                 \@@_tmp:w
-                  \char_to_utfviii_bytes:n { "#1 }
-                  \char_to_utfviii_bytes:n { "#2 }
+                  \codepoint_to_bytes:n { "#1 }
+                  \codepoint_to_bytes:n { "#2 }
               }
           \group_end:
         }
@@ -2238,7 +2238,7 @@
                     {#2}
               }
             \use:x
-              { \@@_tmp:w \char_to_utfviii_bytes:n { "#1 } }
+              { \@@_tmp:w \codepoint_to_bytes:n { "#1 } }
           \group_end:
         }
       \@@_tmp:w { 00DF } { SS } { upper }
@@ -2463,8 +2463,8 @@
             \use:x
               {
                 \@@_tmp:w
-                  \char_to_utfviii_bytes:n { "#1 }
-                  \char_to_utfviii_bytes:n { "#2 }
+                  \codepoint_to_bytes:n { "#1 }
+                  \codepoint_to_bytes:n { "#2 }
               }
           \group_end:
         }

diff --git a/l3kernel/l3text-purify.dtx b/l3kernel/l3text-purify.dtx
@@ -486,7 +486,7 @@
         \text_declare_purify_equivalent:Nx #1
           {
             \exp_args:Ne \@@_tmp:n
-              { \char_to_utfviii_bytes:n { "#2 } }
+              { \codepoint_to_bytes:n { "#2 } }
           }
         \@@_loop:Nn
       }
@@ -574,7 +574,7 @@
       \cs_set:Npn \@@_tmp:n #1
         {
           \exp_args:Ne \@@_tmp_aux:n
-            { \char_to_utfviii_bytes:n { "#1 } }
+            { \codepoint_to_bytes:n { "#1 } }
         }
       \cs_set:Npn \@@_tmp_aux:n #1 { \@@_tmp:nnnn #1 }
       \cs_set:Npn \@@_tmp:nnnn #1#2#3#4

diff --git a/l3kernel/l3token.dtx b/l3kernel/l3token.dtx
@@ -1690,111 +1690,6 @@
 % \end{macro}
 % \end{macro}
 %
-% \begin{macro}[EXP]{\char_to_utfviii_bytes:n}
-% \begin{macro}[EXP]{\@@_to_utfviii_bytes_auxi:n}
-% \begin{macro}[EXP]{\@@_to_utfviii_bytes_auxii:Nnn}
-% \begin{macro}[EXP]{\@@_to_utfviii_bytes_auxiii:n}
-% \begin{macro}[EXP]
-%   {
-%     \@@_to_utfviii_bytes_outputi:nw   ,
-%     \@@_to_utfviii_bytes_outputii:nw  ,
-%     \@@_to_utfviii_bytes_outputiii:nw ,
-%     \@@_to_utfviii_bytes_outputiv:nw
-%   }
-% \begin{macro}[EXP]
-%   {\@@_to_utfviii_bytes_output:nnn, \@@_to_utfviii_bytes_output:fnn}
-% \begin{macro}[EXP]{\@@_to_utfviii_bytes_end:}
-%   This code converts a codepoint into the correct UTF-8 representation.
-%   In terms of the algorithm itself, see
-%   \url{https://en.wikipedia.org/wiki/UTF-8} for the octet pattern.
-%    \begin{macrocode}
-\cs_new:Npn \char_to_utfviii_bytes:n #1
-  {
-    \exp_args:Nf \@@_to_utfviii_bytes_auxi:n
-      { \int_eval:n {#1} }
-  }
-\cs_new:Npn \@@_to_utfviii_bytes_auxi:n #1
-  {
-    \if_int_compare:w #1 > "80 \exp_stop_f:
-      \if_int_compare:w #1 < "800 \exp_stop_f:
-        \@@_to_utfviii_bytes_outputi:nw
-          { \@@_to_utfviii_bytes_auxii:Nnn C {#1} { 64 } }
-        \@@_to_utfviii_bytes_outputii:nw
-          { \@@_to_utfviii_bytes_auxiii:n {#1} }
-      \else:
-        \if_int_compare:w #1 < "10000 \exp_stop_f:
-          \@@_to_utfviii_bytes_outputi:nw
-            { \@@_to_utfviii_bytes_auxii:Nnn E {#1} { 64 * 64 } }
-          \@@_to_utfviii_bytes_outputii:nw
-            {
-              \@@_to_utfviii_bytes_auxiii:n
-                { \int_div_truncate:nn {#1} { 64 } }
-            }
-          \@@_to_utfviii_bytes_outputiii:nw
-            { \@@_to_utfviii_bytes_auxiii:n {#1} }
-        \else:
-          \@@_to_utfviii_bytes_outputi:nw
-            {
-              \@@_to_utfviii_bytes_auxii:Nnn F
-                 {#1} { 64 * 64 * 64 }
-            }
-          \@@_to_utfviii_bytes_outputii:nw
-            {
-              \@@_to_utfviii_bytes_auxiii:n
-                { \int_div_truncate:nn {#1} { 64 * 64 } }
-            }
-          \@@_to_utfviii_bytes_outputiii:nw
-            {
-              \@@_to_utfviii_bytes_auxiii:n
-                { \int_div_truncate:nn {#1} { 64 } }
-            }
-          \@@_to_utfviii_bytes_outputiv:nw
-            { \@@_to_utfviii_bytes_auxiii:n {#1} }
-        \fi:
-      \fi:
-    \else:
-      \@@_to_utfviii_bytes_outputi:nw {#1}
-    \fi:
-    \@@_to_utfviii_bytes_end: { } { } { } { }
-  }
-\cs_new:Npn \@@_to_utfviii_bytes_auxii:Nnn #1#2#3
-  {  "#10 + \int_div_truncate:nn {#2} {#3} }
-\cs_new:Npn \@@_to_utfviii_bytes_auxiii:n #1
-  { \int_mod:nn {#1} { 64 } + 128 }
-\cs_new:Npn \@@_to_utfviii_bytes_outputi:nw
-  #1 #2 \@@_to_utfviii_bytes_end: #3
-  { \@@_to_utfviii_bytes_output:fnn { \int_eval:n {#1} } { } {#2} }
-\cs_new:Npn \@@_to_utfviii_bytes_outputii:nw
-  #1 #2 \@@_to_utfviii_bytes_end: #3#4
-  { \@@_to_utfviii_bytes_output:fnn { \int_eval:n {#1} } { {#3} } {#2} }
-\cs_new:Npn \@@_to_utfviii_bytes_outputiii:nw
-  #1 #2 \@@_to_utfviii_bytes_end: #3#4#5
-  {
-    \@@_to_utfviii_bytes_output:fnn
-      { \int_eval:n {#1} } { {#3} {#4} } {#2}
-  }
-\cs_new:Npn \@@_to_utfviii_bytes_outputiv:nw
-  #1 #2 \@@_to_utfviii_bytes_end: #3#4#5#6
-  {
-    \@@_to_utfviii_bytes_output:fnn
-      { \int_eval:n {#1} } { {#3} {#4} {#5} } {#2}
-  }
-\cs_new:Npn \@@_to_utfviii_bytes_output:nnn #1#2#3
-  {
-    #3
-    \@@_to_utfviii_bytes_end: #2 {#1}
-  }
-\cs_generate_variant:Nn \@@_to_utfviii_bytes_output:nnn { f }
-\cs_new:Npn \@@_to_utfviii_bytes_end: { }
-%    \end{macrocode}
-% \end{macro}
-% \end{macro}
-% \end{macro}
-% \end{macro}
-% \end{macro}
-% \end{macro}
-% \end{macro}
-%
 % \begin{macro}[EXP]{\char_to_nfd:N}
 % \begin{macro}[EXP]{\char_to_nfd:n}
 % \begin{macro}[EXP]{\@@_to_nfd:nn}