Merge 43ae9da into 0c91cbc

documentation/c07-settings.sil

@@ -189,6 +189,11 @@ Note that non-breaking spaces (U+00A0), following the guidelines of Unicode Anne
 
 If you want to disable this behavior, the \autodoc:setting{languages.fixedNbsp} setting may be set to \code{true} to enforce fixed-width non-breaking spaces.
 
+Some typography conventions use an em-dash at the start of a paragraph line to denote a speaker change in a dialogue.
+This is the case in particular in French and Turkish typography.
+By default, all spaces following an em-dash at the beginning of a paragraph in your input are replaced by a single \em{fixed} inter-word space, so that subsequent dialogue lines all start identically, while other inter-word spaces may still be variable for justification purposes.
+To cancel this behavior, the \autodoc:setting{typesetter.fixedSpacingAfterInitialEmdash} setting may be set to \code{false}.
+
 \subsection{Letter spacing settings}
 
 You can also put spaces in between \em{letters} with the \autodoc:setting{document.letterspaceglue} setting.

tests/feat-emdash-dialogue.expected

@@ -0,0 +1,70 @@
+Set paper size 	209.7637818	297.6377985
+Begin page
+Mx 	10.4882
+My 	31.5323
+Set font 	Gentium Plus;22;400;;normal;;;LTR
+T	179 w=16.8545	(—)
+Mx 	33.1564
+T	47 82 85 72 80 w=58.0830	(Lorem)
+Mx 	102.5788
+T	76 83 86 88 80 w=55.4404	(ipsum)
+Mx 	169.3586
+T	71 82 w=22.5049	(do)
+Mx 	191.8635
+T	16 w=7.4121	(-)
+Mx 	10.4882
+My 	57.9323
+T	79 82 85 w=25.7383	(lor)
+Mx 	49.1531
+T	86 76 87 w=22.0322	(sit)
+Mx 	71.1853
+T	17 w=5.0381	(.)
+Mx 	89.1500
+T	179 w=16.8545	(—)
+Mx 	118.9310
+T	54 72 71 w=32.0762	(Sed)
+Mx 	163.9338
+T	81 82 81 w=35.3418	(non)
+Mx 	10.4882
+My 	84.3323
+T	85 76 86 88 86 w=43.3232	(risus)
+Mx 	53.8114
+T	17 w=5.0381	(.)
+Mx 	10.4882
+My 	110.7323
+T	179 w=16.8545	(—)
+Mx 	33.1564
+T	49 82 81 w=37.4795	(Non)
+Mx 	70.6358
+T	17 w=5.0381	(.)
+Mx 	10.4882
+My 	137.1323
+T	179 w=16.8545	(—)
+Mx 	36.8402
+T	47 82 85 72 80 w=58.0830	(Lorem)
+Mx 	104.4207
+T	76 83 86 88 80 w=55.4404	(ipsum)
+Mx 	169.3586
+T	71 82 w=22.5049	(do)
+Mx 	191.8635
+T	16 w=7.4121	(-)
+Mx 	10.4882
+My 	163.5323
+T	79 82 85 w=25.7383	(lor)
+Mx 	49.1531
+T	86 76 87 w=22.0322	(sit)
+Mx 	71.1853
+T	17 w=5.0381	(.)
+Mx 	89.1500
+T	179 w=16.8545	(—)
+Mx 	118.9310
+T	54 72 71 w=32.0762	(Sed)
+Mx 	163.9338
+T	81 82 81 w=35.3418	(non)
+Mx 	10.4882
+My 	189.9323
+T	85 76 86 88 86 w=43.3232	(risus)
+Mx 	53.8114
+T	17 w=5.0381	(.)
+End page
+Finish

tests/feat-emdash-dialogue.sil

@@ -0,0 +1,16 @@
+\begin[papersize=a7]{document}
+\nofolios
+\neverindent
+\font[size=22pt]
+\set[parameter=linebreak.emergencyStretch, value=50pt]
+
+% Affect paragraph-leading em-dash but not later...
+— Lorem ipsum dolor sit. — Sed non risus.
+
+— Non.
+
+\set[parameter=typesetter.fixedSpacingAfterInitialEmdash, value=false]
+
+— Lorem ipsum dolor sit. — Sed non risus.
+
+\end{document}

typesetters/base.lua

@@ -145,6 +145,13 @@ function typesetter.declareSettings(_)
     default = false,
     help = "When true, a warning is issued when a soft hyphen is encountered"
   })
+
+  SILE.settings:declare({
+    parameter = "typesetter.fixedSpacingAfterInitialEmdash",
+    type = "boolean",
+    default = true,
+    help = "When true, em-dash starting a paragraph is considered as a speaker change in a dialogue"
+  })
 end
 
 function typesetter:initState ()
@@ -330,6 +337,31 @@ function typesetter:endline ()
   SILE.documentState.documentClass.endPar(self)
 end
 
+-- Just compute once, to avoid unicode characters in source code.
+local speakerChangePattern = "^"
+   .. luautf8.char(0x2014) -- emdash
+   .. "[ " .. luautf8.char(0x00A0) .. luautf8.char(0x202F) -- regular space or NBSP or NNBSP
+   .. "]+"
+local speakerChangeReplacement = luautf8.char(0x2014) .. " "
+
+-- Special unshaped node subclass to handle space after a speaker change in dialogues
+-- introduced by an em-dash.
+local speakerChangeNode = pl.class(SILE.nodefactory.unshaped)
+function speakerChangeNode:shape()
+  local node = self._base.shape(self)
+  local spc = node[2]
+  if spc and spc.is_glue then
+    -- Switch the variable space glue to a fixed kern
+    node[2] = SILE.nodefactory.kern({ width = spc.width.length })
+    node[2].parent = self.parent
+  else
+    -- Should not occur:
+    -- How could it possibly be shaped differently?
+    SU.warn("Speaker change logic met an unexpected case, this might be a bug.")
+  end
+  return node
+end
+
 -- Takes string, writes onto self.state.nodes
 function typesetter:setpar (text)
   text = text:gsub("\r?\n", " "):gsub("\t", " ")
@@ -338,6 +370,19 @@ function typesetter:setpar (text)
       text = text:gsub("^%s+", "")
     end
     self:initline()
+
+    if SILE.settings:get("typesetter.fixedSpacingAfterInitialEmdash") and not SILE.settings:get("typesetter.obeyspaces") then
+      local speakerChange = false
+      local dialogue = luautf8.gsub(text, speakerChangePattern, function ()
+        speakerChange = true
+        return speakerChangeReplacement
+      end)
+      if speakerChange then
+        local node = speakerChangeNode({ text = dialogue, options = SILE.font.loadDefaults({})})
+        self:pushHorizontal(node)
+        return -- done here: speaker change space handling is done after nnode shaping
+      end
+    end
   end
   if #text >0 then
     self:pushUnshaped({ text = text, options= SILE.font.loadDefaults({})})