From 8a3b5fe36fca8b7450a4b7a2545436201eba83be Mon Sep 17 00:00:00 2001
From: Robert Alessi <alessi@robertalessi.net>
Date: Fri, 28 May 2021 12:38:48 +0200
Subject: use lpeg to relocate anchors. adapted frontier pattern to handle
 dots, hyphens and underscores in xml:ids

---
 ekdosis.dtx | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/ekdosis.dtx b/ekdosis.dtx
index b51cf53..7e24140 100644
--- a/ekdosis.dtx
+++ b/ekdosis.dtx
@@ -61,7 +61,7 @@ along with this program.  If not, see
 %<package>\NeedsTeXFormat{LaTeX2e}[1999/12/01]
 %<package>\ProvidesPackage{ekdosis}
 %<*package>
-    [2021/05/27 v1.3-dev Typesetting TEI xml-compliant critical editions]
+    [2021/05/28 v1.3-dev Typesetting TEI xml-compliant critical editions]
 %</package>
 %<*driver>
 \begin{filecontents}[noheader,overwrite]{bibdata.xml}
@@ -7507,7 +7507,7 @@ Sample text with a \textcolor{red}{word} in red.
 %    \end{macrocode}
 % \end{macro}
 % \begin{macro}{\teidirect}
-% \changes{v1.3}{2021/05/27}{direct insertion of elements in the
+% \changes{v1.3}{2021/05/28}{direct insertion of elements in the
 % \texttt{TEI xml} file}
 % \cs{teidirect}\oarg{xml attributes}\marg{xml element}\marg{code}
 % does nothing in \LaTeX. Its only use is to insert elements in the
@@ -7866,7 +7866,7 @@ Sample text with a \textcolor{red}{word} in red.
 %    \end{macrocode}
 % \end{macro}
 % \begin{macro}{\SetApparatusNoteLanguage}
-% \changes{v1.3}{2021/05/27}{defines an alternate language to be
+% \changes{v1.3}{2021/05/28}{defines an alternate language to be
 % applied in note apparatus entries}
 % \cs{SetApparatusNoteLang}\marg{languagename} can be used when
 % it is needed to apply in entries introduced by the \cs{note} command
@@ -9397,6 +9397,8 @@ local app = lpeg.Cs("app")
 local lemrdg = lpeg.Cs(lpeg.Cs("lem") + lpeg.Cs("rdg"))
 local note = lpeg.Cs("note")
 local inlem = lpeg.Cs{ "<lem" * ((1 - (lpeg.P"<lem" + lpeg.P"</lem>")) + lpeg.V(1))^0 * "</lem>" }
+local inanchor = lpeg.Cs{ "<anchor" * ((1 - (lpeg.P"<" + lpeg.P">")) + lpeg.V(1))^0 * ">" }
+local inopeningnote = lpeg.Cs{ "<note" * ((1 - (lpeg.P"<" + lpeg.P">")) + lpeg.V(1))^0 * ">" }
 local lnbrk = lpeg.Cs("\\\\")
 local poemline = lpeg.Cs(lnbrk * spcenc^-1 * lpeg.S("*!")^-1 * bsqbrackets^-1 * spcenc^-1)
 local poemlinebreak = lpeg.Cs(lnbrk * spcenc^-1 * lpeg.P("&gt;") * bsqbrackets^-1 * spcenc^-1)
@@ -9708,7 +9710,7 @@ function ekdosis.getsiglum(str, opt)
 	 str = string.gsub(str, shorthands[i].a, shorthands[i].c)
       end
       for i = 1,#idsRend do
-	 str  = string.gsub(str, "(%f[%w])"..idsRend[i].xmlid.."(%,)",
+	 str  = string.gsub(str, "(%f[%w%.%-%_])"..idsRend[i].xmlid.."(%,)",
 			    "%1#"..idsRend[i].xmlid.."%2")
 	 ctrl = string.gsub(ctrl, idsRend[i].xmlid.."%,", "")
       end
@@ -9747,7 +9749,7 @@ local cmdtotags = {
    {a="textsf", b="hi", c=" rend=\"sf\""},
    {a="arbup", b="hi", c=" rend=\"sup\""},
    {a="txarb", b="s", c=" xml:lang=\"arb\""},
-   {a="arb", b="foreign",
+   {a="arb", b="span",
     c=" xml:lang=\"ar-Latn\" type=\"transliterated\" subtype=\"arabtex\""}
 }
 
@@ -9920,7 +9922,7 @@ local function note_totei(str)
 end
 
 local function remove_extra_anchors(str)
-   str = string.gsub(str, "(</note>)(<anchor.->)(<note.->)", function(enote, anchor, bnote)
+   str = gsub(str, lpeg.Cs("</note>") * inanchor * inopeningnote, function(enote, anchor, bnote)
    			local id_one = string.gsub(anchor, "(%<anchor )(.-)(/%>)", "%2")
    			id_one = string.sub(get_attr_value(id_one, "xml:id"), 2, -2)
    			local id_two = string.match(bnote, "target%=.-right%((.-)%)")
-- 
cgit v1.2.3