From: Lady <redacted>
Date: Sun, 27 Apr 2025 05:21:13 +0000 (-0400)
Subject: Drop langtags on offset text but support on paras
X-Git-Tag: 0.5.0~3
X-Git-Url: https://git.ladys.computer/LesML/commitdiff_plain/0c826f34b9a00337f05549fcc3b796470b83dc4056fd840c1ee7897820158ca7?hp=270379268b6fba8003f66a1d5646ec4cd077df1ed3f433f38145eccf760f52ef

Drop langtags on offset text but support on paras

Now that language attributes can be arbitrarily added to any inline,
  a special syntax for them doesn’t make much sense.
However, that syntax would be useful on block‐level elements.

There isn¦t a real technical reason for the explicit `$´ end of the
  language tag, since the following whitespace could have been used to
  end it also, but it makes the syntax a bit more obvious, matches the
  existing format with the shebangs, and is less likely to conflict
  with i·d syntaxes (which might include `@´ but probably won¦t also
  end in a `$´).

You can still make i·d¦s like `@es$´ if you need by explicitly
  language‐tagging: `¶@es$@en$´.

This commit also allows block sigils to not be followed by a space if
  they are immediately followed by a pilcrow.
---

diff --git a/README.markdown b/README.markdown
index 00d077b..84ea519 100644
--- a/README.markdown
+++ b/README.markdown
@@ -179,10 +179,12 @@ After this classification, each quoted or unquoted paragraph is further
 
 - Otherwise, it is an ordinary paragraph.
 
-Following this sigil (if any, including trailing white·space) there may
-  be a `¶` followed by zero or more non·white·space characters.
+Following this sigil (if any) there may be a `¶` followed by zero or
+  more non·white·space characters.
 The characters following the `¶` give the identifier for the paragraph,
   which is expected to be unique within a document.
+This may be suffixed with a language tag beginning with `@` and
+  terminated with `$`.
 
 The remaining characters in a paragraph form its contents.
 Markup within paragraphs is delimited with·out exception by pairs of
@@ -227,8 +229,6 @@ Markup within paragraphs is delimited with·out exception by pairs of
 - The characters `⸶` and `⸷` indicate names (`<html:u class="name">`).
 
 - The characters `⟨` and `⟩` indicate offset text (`<html:i>`).
-  This may be followed by a `@`, a language tag, and a `$` to provide
-    the language of the text.
 
 - The characters `⦃` and `⦄` indicate keyword highlighting
     (`<html:b>`).
diff --git a/parser.xslt b/parser.xslt
index fbcfb15..014c15b 100644
--- a/parser.xslt
+++ b/parser.xslt
@@ -14,8 +14,8 @@ If a copy of the M·P·L was not distributed with this file, You can obtain one
 <!DOCTYPE transform [
 	<!ENTITY LesML "urn:fdc:ladys.computer:20240512:LesML">
 	<!ENTITY section-break "*-.=_~·․‥…⁂⋯─━┄┅┈┉╌╍═╴╶╸╺☙❧　・＊－．＝＿～">
-	<!ENTITY sigiled-text "(string-length($text)=1 or substring($text, 2, 1)=' ')">
-	<!ENTITY unsigiled-text "substring($text, 3, string-length($text)-2)">
+	<!ENTITY sigiled-text "(string-length($text)=1 or substring($text, 2, 1)=' ' or substring($text, 2, 1)='¶')">
+	<!ENTITY unsigiled-text "concat(translate(substring($text, 2, 1), ' ', ''), substring($text, 3, string-length($text)-2))">
 	<!ENTITY xhtml "http://www.w3.org/1999/xhtml">
 ]>
 <transform
@@ -123,29 +123,69 @@ If a copy of the M·P·L was not distributed with this file, You can obtain one
 	</template>
 	<template name="LesML:id-and-contents">
 		<param name="source"/>
-		<choose>
-			<when test="starts-with($source, '¶')">
+		<variable name="id-and-lang">
+			<if test="starts-with($source, '¶')">
 				<choose>
 					<when test="contains($source, ' ')">
-						<variable name="id" select="substring-before(substring-after($source, '¶'), ' ')"/>
-						<if test="$id!=''">
-							<attribute name="id">
-								<value-of select="$id"/>
-							</attribute>
-						</if>
-						<value-of select="substring-after($source, ' ')"/>
+						<value-of select="substring-before(substring-after($source, '¶'), ' ')"/>
 					</when>
 					<otherwise>
-						<attribute name="id">
-							<value-of select="substring-after($source, '¶')"/>
-						</attribute>
+						<value-of select="substring-after($source, '¶')"/>
 					</otherwise>
 				</choose>
-			</when>
-			<otherwise>
-				<value-of select="$source"/>
-			</otherwise>
-		</choose>
+			</if>
+		</variable>
+		<variable name="restoftext">
+			<choose>
+				<when test="starts-with($source, '¶') and contains($source, ' ')">
+					<value-of select="substring-after($source, ' ')"/>
+				</when>
+				<when test="starts-with($source, '¶')"/>
+				<otherwise>
+					<value-of select="$source"/>
+				</otherwise>
+			</choose>
+		</variable>
+		<variable name="maybe-langtag">
+			<if test="substring($id-and-lang, string-length($id-and-lang), 1)='$' and contains($id-and-lang, '@')">
+				<variable name="split-tag-fragment">
+					<call-template name="LesML:split">
+						<with-param name="source" select="substring($id-and-lang, 2, string-length($id-and-lang)-2)"/>
+						<with-param name="separator" select="'@'"/>
+					</call-template>
+				</variable>
+				<value-of select="exsl:node-set($split-tag-fragment)/*[last()]"/>
+			</if>
+		</variable>
+		<variable name="langtag">
+			<if test="translate($maybe-langtag, '0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz-', '')=''">
+				<value-of select="$maybe-langtag"/>
+			</if>
+		</variable>
+		<variable name="id">
+			<choose>
+				<when test="string($langtag)!=''">
+					<value-of select="substring($id-and-lang, 1, string-length($id-and-lang)-(string-length($langtag)+2))"/>
+				</when>
+				<otherwise>
+					<value-of select="$id-and-lang"/>
+				</otherwise>
+			</choose>
+		</variable>
+		<if test="string($id)!=''">
+			<attribute name="id">
+				<value-of select="$id"/>
+			</attribute>
+		</if>
+		<if test="string($langtag)!=''">
+			<attribute name="lang">
+				<value-of select="$langtag"/>
+			</attribute>
+			<attribute name="xml:lang">
+				<value-of select="$langtag"/>
+			</attribute>
+		</if>
+		<value-of select="$restoftext"/>
 	</template>
 	<template name="LesML:parse">
 		<param name="lines" select="/.."/>
@@ -875,7 +915,6 @@ If a copy of the M·P·L was not distributed with this file, You can obtain one
 		<param name="end-sigil"/>
 		<param name="class"/>
 		<param name="role"/>
-		<param name="langtag-supported" select="false()"/>
 		<choose>
 			<when test="self::*">
 				<variable name="end-node" select="text()[contains(., $end-sigil)][1]"/>
@@ -887,17 +926,6 @@ If a copy of the M·P·L was not distributed with this file, You can obtain one
 							<value-of select="substring-before($end-node, $end-sigil)"/>
 						</variable>
 						<variable name="start-node" select="exsl:node-set($preceding)/text()[contains(., $start-sigil)][last()]"/>
-						<variable name="restoftext" select="substring-after($end-node, $end-sigil)"/>
-						<variable name="maybe-langtag">
-							<if test="$langtag-supported and starts-with($restoftext, '@') and contains($restoftext, '$')">
-								<value-of select="substring-before(substring-after($restoftext, '@'), '$')"/>
-							</if>
-						</variable>
-						<variable name="langtag">
-							<if test="translate($maybe-langtag, '0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz-', '')=''">
-								<value-of select="$maybe-langtag"/>
-							</if>
-						</variable>
 						<variable name="start-tokens-fragment">
 							<call-template name="LesML:split">
 								<with-param name="source" select="string($start-node)"/>
@@ -926,27 +954,10 @@ If a copy of the M·P·L was not distributed with this file, You can obtain one
 											<value-of select="$class"/>
 										</attribute>
 									</if>
-									<if test="string($langtag)!=''">
-										<if test="$element-namespace='http://www.w3.org/1999/xhtml'">
-											<attribute name="lang">
-												<value-of select="$langtag"/>
-											</attribute>
-										</if>
-										<attribute name="xml:lang">
-											<value-of select="$langtag"/>
-										</attribute>
-									</if>
 									<value-of select="$start-tokens[last()]"/>
 									<copy-of select="$start-node/following-sibling::node()"/>
 								</element>
-								<choose>
-									<when test="string($langtag)!=''">
-										<value-of select="substring-after($restoftext, '$')"/>
-									</when>
-									<otherwise>
-										<value-of select="$restoftext"/>
-									</otherwise>
-								</choose>
+								<value-of select="substring-after($end-node, $end-sigil)"/>
 								<copy-of select="$end-node/following-sibling::node()"/>
 							</copy>
 						</variable>
@@ -956,7 +967,6 @@ If a copy of the M·P·L was not distributed with this file, You can obtain one
 							<with-param name="start-sigil" select="$start-sigil"/>
 							<with-param name="end-sigil" select="$end-sigil"/>
 							<with-param name="role" select="$role"/>
-							<with-param name="langtag-supported" select="$langtag-supported"/>
 						</apply-templates>
 					</when>
 					<otherwise>
@@ -968,7 +978,6 @@ If a copy of the M·P·L was not distributed with this file, You can obtain one
 								<with-param name="start-sigil" select="$start-sigil"/>
 								<with-param name="end-sigil" select="$end-sigil"/>
 								<with-param name="role" select="$role"/>
-								<with-param name="langtag-supported" select="$langtag-supported"/>
 							</apply-templates>
 						</copy>
 					</otherwise>
@@ -1330,7 +1339,6 @@ If a copy of the M·P·L was not distributed with this file, You can obtain one
 				<with-param name="element-namespace" select="'&xhtml;'"/>
 				<with-param name="start-sigil" select="'⟨'"/>
 				<with-param name="end-sigil" select="'⟩'"/>
-				<with-param name="langtag-supported" select="true()"/>
 			</apply-templates>
 		</variable>
 		<apply-templates select="exsl:node-set($result)/node()" mode="LesML:bolded"/>