From 5b84305d8e0223f163c1f5ec606d6e96c3b5fc77 Mon Sep 17 00:00:00 2001
From: Mike Gerwitz <mtg@gnu.org>
Date: Sat, 27 Jul 2019 14:27:35 -0400
Subject: [PATCH] src/post2html (prefmt): Ties and newline stripping

I hate Markdown as a format for disciplined writing, especially when I want
macros (mostly semantic), indexes, and such.  I was originally going to use
LaTeX with Pandoc, but it lacks support for inline HTML and such, and I do
not want to distract too much from the work that I want to be doing.
---
 src/post2html | 33 ++++++++++++++++++++++++++++++++-
 1 file changed, 32 insertions(+), 1 deletion(-)

diff --git a/src/post2html b/src/post2html
index 803fef7..8fd821f 100755
--- a/src/post2html
+++ b/src/post2html
@@ -83,6 +83,37 @@ hgroup-wrap()
 }
 
 
+# Pre-format Markdown files before they get to Pandoc
+#
+# These may be able to be implemented as Pandoc filters, but I haven't had
+# the time to research that yet.  This is actually a fitting real-world
+# demonstration of incremental development / MVP that I'm writing about at
+# the time that this comment was written (MyCustomBB Part I)!
+prefmt()
+{
+  awk '
+    triml {
+      gsub( /^ +/, "" )
+      triml = 0
+    }
+
+    # ties
+    { $0 = gensub( /([^\\])~/, "\\1 ", "g" ) }
+    { $0 = gensub( /\\~/, "~", "g" ) }
+
+    # TeX-style newline removal
+    /%$/ {
+      gsub( /%$/, "" )
+      printf "%s", $0
+      triml = 1
+      next
+    }
+
+    { print }
+  '
+}
+
+
 # Generate HTML from post.  Note that `pagetitle' is set just to suppress
 # Pandoc warnings about it missing; it is unused.
 main()
@@ -97,7 +128,7 @@ main()
          --base-header-level=1 \
          -B <( src/mkheader post @__PAGE_TITLE__@ ) \
          -A src/footer.tpl.htm \
-         < "$file" \
+         < <( prefmt < "$file" ) \
     | src/h12title @__PAGE_TITLE__@ \
     | hgroup-wrap "$date" "$file"
 }