CTAN sync 202002270301

1 files changed, 174 insertions, 91 deletions

diff --git a/macros/luatex/optex/verbatim.opm b/macros/luatex/optex/verbatim.opm
index acc7922a8d..121ec0698e 100644
--- a/macros/luatex/optex/verbatim.opm
+++ b/macros/luatex/optex/verbatim.opm
@@ -2,21 +2,31 @@
 
 \_codedecl \begtt {Verbatim <2020-02-14>}
 
-\_newdimen\_ttindent \_ttindent=\_parindent
-   % indentation in \begtt...\endtt and \verbinput
-\_def\_ttskip{\medskip}       % space above and below \begtt, \verbinput
-\_mathchardef\_ttpenalty=100  % penalty between lines in \begtt, \verbinput
+%> parameters
+
+\_newdimen\_ttindent \_ttindent=\_parindent % indentation in \begtt...\endtt and \verbinput
+\_def\_ttskip{\_medskip}           % space above and below \begtt, \verbinput
+\_mathchardef\_ttpenalty=100       % penalty between lines in \begtt, \verbinput
+
+\_newcount\_ttline    \_ttline=-1  % last line number in \begtt...\endtt
+\_newcount\_viline                 % last line number in \verbinput
+\_newread\_vifile                  % file fgiven by \verinput
+\_newtoks\_tthook                  % tokens procesed in \begtt...\endtt
+\_newtoks\_intthook                % toens procesed in \code or in `...`
+
+\_public \ttline \tthook \intthook ;
+
+%> \code
 
 \_def\_code#1{\_unexpanded\_ea{\_csname _code \_endcsname{#1}}}
-\_protected\_sdef{_code }#1{{\_escapechar=-1 \_ea}%
-   \_ea\_printinverbatim\_ea{\_detokenize{#1}}}
-\_def\_printinverbatim#1{\_leavevmode\_hbox{\_tt \_the\_intthook\_relax #1}}
+\_protected\_sdef{_code }#1{{\_escapechar=-1 \_tt \_the\_intthook \_relax 
+   \_ea\_printinverbatim\_ea{\_detokenize{#1}}}}
+\_def\_printinverbatim#1{\_leavevmode\_hbox{#1}}
 
+\_toksapp \_pdfstringout{\_let\code=\_detokenize \_let\_code=\_detokenize}
 \_public \code ;
 
-\_newcount\_ttline    \_ttline=-1
-\_newcount\_viline
-\_newread\_vifile
+%> \_setverb
 
 \_newcatcodetable \_verbatimcatcodes
 \_def\_setverb{\_begingroup
@@ -28,45 +38,49 @@
 \_setverb
 \_def\_setverb{\_catcodetable\_verbatimcatcodes }%
 
-% \begtt ... \endtt
-
-\_eoldef \_begtt #1{%
-   \_par \_vskip\_parskip \_ttskip \_bgroup \_wipeepar
-   \_setverb \_adef{ }{\ }%
-   \_parindent=\_ttindent \_parskip=0pt
-   \_the\_tthook #1%
-   \_ifnum\_ttline<0 \_else
-     \_tenrm \_thefontscale[700]\_ea\_let\_ea\_sevenrm\_the\_font
-     \_toksapp\_everypar{\_global\_advance\_ttline by1 \_printttline}\_fi
-     \_def\par##1{\_endgraf\_ifx##1\_egroup\_else\_penalty\_ttpenalty\_leavevmode\_fi ##1}%
-   \_obeylines \_startverb}
-
-\_catcode`\|=0 \_catcode`\\=12
-  |_def|_startverb#1\endtt{|_tt|_the|_ptthook#1|_endtt}
-|_normalcatcodes
-
-\def\_endtt{\_egroup\_par\_ttskip\_testparA}
-\_def\_testparA{\_ea\_testparB\_romannumeral-`\.}
-\_def\_testparB{\_futurelet\_tmpa\_testparC}
-\_def\_testparC{\_ifx\_tmpa\_par\_else\afternoindent\_fi}
-
-\_def\_printttline{\_llap{\_sevenrm\_the\_ttline\_kern.9em}}
-
-\_newtoks\_tthook
-\_newtoks\_ptthook
-\_newtoks\_intthook
+%> \activettchar
 
 \_def\_activettchar#1{%
    \_ifx\_savedttchar\_undefined\_else \_catcode\_savedttchar=\_savedttcharc \_fi
-   \_chardef\_savedttchar=`#1%
-   \_chardef\_savedttcharc=\_catcode`#1%
-   \_adef{#1}{{\_setverb\_adef{ }{\ }\_catcode`#1=13 \_ea}\_readverb}%
-   \_bgroup\_lccode`\~=`#1\_lowercase{\_egroup\_def\_readverb ##1~}{\_printinverbatim{##1}}%
-   \_catcode`#1=13
+   \_chardef\_savedttchar=`#1
+   \_chardef\_savedttcharc=\_catcode`#1
+   \_adef{#1}{\_begingroup \_setverb \_adef{ }{\ }\_tt \_the\_intthook\_relax \_readverb}%
+   \_def\_readverb ##1#1{\_printinverbatim{##1}\_endgroup}%
 }
+\_public \activettchar ;
 
-\_newcount\_viline
-\_newread\_vifile
+%> \begtt ... \endtt
+
+\_eoldef \begtt#1{\_par \_wipeepar 
+   \_begingroup
+   \_vskip\_parskip \_ttskip
+   \_setverb 
+   \_ifnum\_ttline<0 \_let\_printverblinenum=\_relax \_else \_initverblinenum \_fi
+   \_adef{ }{\ }\_parindent=\_ttindent \_parskip=0pt
+   \_the\_tthook #1\_relax \_tt
+   \_endlinechar=`^^J
+   \_startverb
+}
+\_ea\_def\_ea\_startverb \_ea#\ea1\_csstring\\endtt#2^^J{%
+   \_prepareverbdata\_tmpb{#1^^J}%
+   \_ea\_printverb \_tmpb\_end
+   \_par\_ttskip
+   \_endgroup
+   \_noindent \_setbox0=\_lastbox
+}
+\_def\_printverb #1^^J#2{\_ifx\_end#2
+      \_bgroup \_adef{ }{}\_if\_relax#1\_relax\_egroup \_else\_egroup \_printverbline{#1}\_fi
+   \_else
+      \_printverbline{#1}%
+      \_ea \_printverb \_ea #2%
+   \_fi
+}
+\_def\_prepareverbdata#1#2{\_def#1{#2}}
+\_def\_printverbline#1{\_penalty \_ttpenalty \_indent \_printverblinenum #1 \par}
+\_def\_initverblinenum{\_tenrm \_thefontscale[700]\_ea\_let\_ea\_sevenrm\_the\_font}
+\_def\_printverblinenum{\_global\_advance\_ttline by1 \_llap{\_sevenrm \_the\_ttline\_kern.9em}}
+
+%> \verbinput
 
 \_def\_verbinput (#1) #2 {\_par \_def\_tmpa{#2}%
    \_ifx\_vifilename\_tmpa \_else
@@ -114,76 +128,145 @@
    \_else
       \_edef\_vinolines{\_the\_tmpnum}%
    \_fi
-   \_vskip\_parskip \_ttskip \_bgroup \_wipeepar
-   \_setverb \_adef{ }{\ }%
-   \_ifx\_savedttchar\_undefined \_else \_catcode\_savedttchar=12 \_fi
-   \_parindent=\_ttindent \_parskip=0pt
-   \_the\_tthook\_relax
-   \_ifnum\_ttline<-1 \_else
-     \_tenrm \_thefontscale[700]\_ea\_let\_ea\_sevenrm\_the\_font
-     \_everypar\_ea{\_the\_everypar \_glob\_advance\_ttline by1 \_printttline}\_fi
-   \_def\par##1{\_endgraf\_ifx##1\_egroup\_else\_penalty\_ttpenalty\_leavevmode\_fi ##1}%
-   \_obeylines \_tmpnum=0 \_lccode`\~=`\^^M \_lowercase{\_def\_tmpb{~}}%
+   \_vskip\_parskip \_ttskip \_wipeepar
+   \_begingroup
+   \_ifnum\_ttline<-1 \_let\_printverblinenum=\_relax \_else \_initverblinenum \_fi
+   \_setverb \_adef{ }{\ }\_parindent=\_ttindent \_parskip=0pt
+   \_the\_tthook\_relax \_tt
+   \_endlinechar=`^^J \_tmpnum=0
    \_loop \_ifeof\_vifile \_tmpnum=\_vinolines\_space \_fi
          \_ifnum\_tmpnum<\_vinolines\_space
-         \_vireadline \_advance\_tmpnum by1 \_repeat      %% skip line
-   \_ifnum\_ttline=-1 \_ttline=\_viline \_let\_glob=\_relax \_else\_let\_glob=\_global \_fi
-   \_tmpnum=0 \_ifnum\_vidolines=0 \_tmpnum=-1 \_fi
+         \_vireadline \_advance\_tmpnum by1 \_repeat      %% skip lines
+   \_edef\_ttlinesave{\_ttline=\_the\_ttline}%
+   \_ifnum\_ttline=-1 \_ttline=\_viline \_fi
+   \_tmpnum=0 \_def\_tmpb{}%
+   \_ifnum\_vidolines=0 \_tmpnum=-1 \_fi
    \_ifeof\_vifile \_tmpnum=\_vidolines\_space \_fi
    \_loop \_ifnum\_tmpnum<\_vidolines\_space
             \_vireadline 
-            \_ifeof\_vifile \_tmpnum=\_vidolines\_space \_else \_viprintline \_fi %% print line
-            \_ifnum\_vidolines=0 \_else\_advance\_tmpnum by1 \_fi 
+            \_ifnum\_vidolines=0 \_else\_advance\_tmpnum by1 \_fi
+            \_ifeof\_vifile \_tmpnum=\_vidolines\_space \_else \_visaveline \_fi %% save line
             \_repeat
-   \_tt\_ea\_the\_ea\_ptthook\_tmpb\_egroup\_par\_ttskip\_testparA
+   \_ea\_prepareverbdata \_ea \_tmpb\_ea{\_tmpb^^J}%
+   \_ea\_printverb \_tmpb\_end
+   \_global\_ttlinesave
+   \_par\_ttskip
+   \_endgroup
+   \_noindent \_setbox0=\_lastbox
 }
 \_def\_vireadline{\_read\_vifile to \_tmp \_global\_advance\_viline by1 }
-\_def\_viprintline{\_ea\_addto\_ea\_tmpb\_ea{\_tmp}}
+\_def\_visaveline{\_ea\_addto\_ea\_tmpb\_ea{\_tmp}}
 
 \_public 
-   \begtt \activettchar \tthook \ptthook \intthook \verbinput ;
-
+   \verbinput ;
 
 
 \_endcode %---------------------------------------
 
-`\code{text}` is a macro which writes verbatim-like inline text and it is
-robust to use it in parameters of macros or section names etc. User have to
-escape the following characters: percent, hash mark, escape, space (if there
-are more than one consecutive spaces) and  `{`, `}` (if these braces are
-unbalanced in the `\code` parameter). For example
+\secc Implementation notes
 
-\begtt
-   \code{\\text, \%\#}  ... \text, %#
-   \code{@{..}*&^$ $}   ... prints the same without escaping, but you can
-                            escape these characters too, if you want.
-   \code{a \ b}         ... two spaces between a b, the second one must be escaped
-   \code{xy\{z}         ... unbalanced brace must be escaped
-\endtt
+\%> parameters
 
-If you set a character as `\activettchar` then it can be used as boundary
-character of inline code. The text betweent these boundary characters are
-printed without any change. For example
-\code{\`}`\print %  whatever #&`\code{\`} does `\print %  whatever #&`
-if `\activettchar`\code{\`} was declared.
+The parameters for verbatim macros are set. `\ttline` is set to $-1$ by
+default, so `\begtt...\endtt` are not numbered but `\verbinput` are with
+numbers. 
 
-But this in/line verbatim text cannot be used inside parameters of
-macros, for example inside section names. Use `\code` in such situation. 
+\%> \code
 
+`\code{<text>}` expands to `\detokenize{<text>}` when `\escapechar=-1`. In
+order to do it more robust when it is used in `\write` then it expands as
+noexpanded `\code<space>` (followed by space in its csname). This macro doew
+really the work.
 
-\secc Implementation notes
+The `\_printinverbatim{<text>}` macro is used for `\code{<text>}` printing and for
+\code{`}<text>\code{`} printing. It is defined as `\_hbox`, so the in-verbatim <text> 
+will be never broken. But you can re-define this macro.
+
+When `\code` occurs in PDF outlines then it does the same as `\detokenize`.
+The macro for preparing outlines sets `\escapechar` to $-1$ and uses
+\_pdftringout` token list before `\edef`.
+
+The `\code` is not `\_proteced` because we want that it expands to
+`\_unexpanded{\code<space>{<text>}` in `\write` parameters. This protect the 
+expansions of the `\code` parameter (like `\\`, `\^` etc.).
+
+\%> \_setverb
+
+The `\_setverb` macro sets all catcodes to \"verbatim mode". It should be used only 
+in a group, so we prepare a new catcode table with \"verbatim" catcodes and we define
+it as `\_catcodetable\_verbatimcatcodes`. After the group is finished then
+original catcode table is restored.
+
+\%> \activettchar
 
-If the code is used in non-detokenized `\write` parameter, we must to
-`detokenize` its parameter and write `\code` as prefix again. The second
-(internal) `\code` is a macro with the name followed by a space. So
+This macro saves original catcode of previously declared `\catcodettchar` (if
+such character was decalred) from `\_savedttchar` and `\_savedttcharc`
+values. Then new such values are stored. The declared charater is activated
+by `\_adef` as a macro (active character) which opens a group, 
+does `\_setverb` and other settings and reads its parameter until second the same 
+character. This is done by `\_readverb` macro. Finally it prints scanned
+<text> by `\_printinverbatim` and closes group. Suppose that `\activettchar"` is
+used. Then the following work is schematically done:
 
 \begtt
-   \code{\\aha\%}  ... writes: \code  {\\aha\%} into workong file.
+\_def "{\_begingroup \_setverb ... \_readverb}
+\_def \_readverb #1"{\_printinverbatim{#1}\_endgroup}
 \endtt
+%
+Note that the second occurence of `"` is not active because `\_setverb`
+deactivates it.
+
+\%> \begtt ... \endtt
+
+`\begtt` id defined only as public. We don't need private `\_begtt` variant.
+This macro os defined by `\eoldef`, sot user can put an parameter at the
+same line where `\begtt` is. This `#1` parameter is used after globap
+parameters settings, so user can change it locally.
+
+The `\begtt` macro opens group, does `\_setverb` and another preprocessing, sets
+`\endlinechar` to `^^J` and reads the following text in verbatim mode 
+until `\endtt` occurs. This scanning is done by `\_startverb` macro which is
+edfined as:
+
+\begtt
+\_def\_startverb #1\endtt #2^^J{...}
+\endtt
+%
+We must to ensure that the backslash in `\endtt` has category 12 (this is a
+reason of the `\ea` chain in real code).
+The `#2` is something between `\endtt` and end of line and it is simply
+ignored.
+
+The `\startverb` puts the scanned data to `\_prepareverbdata`. It sets the data
+to `\_tmpb` without changes by default, but you should re-define it in order
+to does s special changes (for example colorization of the code), if you
+want. The scanned data have `^^J` at each end of line and all spaces are
+active characters. Other characters have nomal category 11 or 12.  
+
+When `\prepareverbdata` finishes then `\startverb` runs `\_printverb` loop
+over aech line of the data and does a final work: last skip plus `\noindent`
+without first indentation box. This trick keeps horizontal mode without
+indentation when the empty line after `\endtt` does not exists. But it stops
+horizontal mode without any new box in outer vertical mode if `\par` is
+processed immediately after `\endtt`.
+
+The `\_printverb` macro calls `\_printverbline{<line>}` to each scanned line of
+verbatim text. This macro expect that it strarts in vertical mode ant it must
+do `\par` in order to return the vertical mode. The `\_printverblinenum`
+is used here: it does nothing when `\_ttline<0` else it prints the line
+number using `\_llap`.
 
-This can be read again without any chnge of meaning of the parameter (the
-second space after `\code` sequence will be ingnored).
+\%> \verbinput
 
-If the `\code` is used in normal horizontal mode, then escape characters are
-ignored using `\ecsapechar=-1 \detokenize`.
+Macro `\verbinput` uses a file read perviously or opens the given file. Then
+it runss the parameter scanning by `\_viscanparameter` and `\_viscanminus`.
+Finally the `\_doverbinput` is run. At begining of `\_doverbinput` we have
+`\_viline`= number of lines already read using previous `\verbinput`,
+`\_vinolines`= the number of lines we need to skip and `\_vidolnes`= the
+number of lines we need to print.
+After group is opened then similar preparation is done as in `\begtt`. Then
+we skip `\_nolines` lines in a loop a and we read `\_dolines` lines. The
+read data is accumulated into `\_tmpb` macro. The next steps are equal to
+the steps done in `\_startverb` macro: data are processed via
+`\_prepareverbdata` and printed via `\_printverb` loop.