From 5851aca9a0da81c82ba26cd66f8d5b2b00dfd391 Mon Sep 17 00:00:00 2001
From: Irene Knapp <ireneista@irenes.space>
Date: Tue, 8 Sep 2026 17:22:45 -0700
Subject: hex-transform comment output now goes through a lexer

this will be used to substitute substrings, but that's not wired up yet

Force-Push: yes
Change-Id: I957ac153599b02ca8cdc46c7cb2ec487aa2af31c
---
 transform.e | 58 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 56 insertions(+), 2 deletions(-)

diff --git a/transform.e b/transform.e
index ea93ec3..b9b6cd8 100644
--- a/transform.e
+++ b/transform.e
@@ -3158,6 +3158,55 @@ allocate-transformation-state s" transformation-state" variable
     } while drop
   } while ;
 
+~ (string pointer --)
+: hex-emit-template-string
+  { unpack8 dup } {
+    dup is-space {
+      ~   Output space characters as we reach them, there's no need to do
+      ~ anything fancy.
+      value@ emitstring drop
+    } {
+      ~ (input point, first word character)
+      ~   We use the outer log's scratch space to accumulate each word in.
+      swap-transform-variables here @ swap-transform-variables
+      swap
+      pack8
+      swap
+      ~ (scratch output point, input point)
+
+      ~   Scan forward and find a space-separated word.
+      { unpack8 dup dup is-space not && } {
+        ~ (scratch output point, adjusted input point, next character)
+        3roll swap pack8 swap
+        ~ (adjusted scratch output point, adjusted input point)
+      } while
+      ~ (scratch output point, input point, first non-word character or 0)
+      3roll 0 pack8 drop
+      ~ (input point, first non-word character or 0)
+
+      swap-transform-variables here @ swap-transform-variables
+      ~ (input point, first non-word character or 0, word pointer)
+
+      dup s" #" stringcmp 0 = {
+        ." zazen" drop
+      } {
+        emitstring
+      } if-else
+      ~ (input point, first non-word character or 0)
+
+      dup {
+        ~   If the character is non-zero, it's a space, so it can't be part of
+        ~ a word, so we can output it.
+        value@ emitstring drop
+      } {
+        ~   If this is the end of the string, we can discard the 0, but then
+        ~ we need to nudge the input point back so the loop will terminate.
+        drop 1-
+      } if-else
+      ~ (input point)
+    } if-else
+  } while drop drop ;
+
 ~   This "replacement" is a little different from an alternate: When the code
 ~ under transformation attempts to compile its own version of sys-write, it
 ~ gets a stub that calls this word instead. It's swapped out by
@@ -3188,7 +3237,9 @@ allocate-transformation-state s" transformation-state" variable
           fresh-line
           indentation-depth@ dup indent advance-current-column
 
-          dup hex-output-metadata-entry-string @ ." ~ " emitstring newline
+          ." ~ "
+          dup hex-output-metadata-entry-string @ hex-emit-template-string
+          newline
 
           1 is-fresh-line!
           0 current-column!
@@ -3197,7 +3248,10 @@ allocate-transformation-state s" transformation-state" variable
         dup hex-output-metadata-entry-type @
         hex-output-metadata-entry-type-suffix-comment = {
           40 current-column@ - 1 max indent
-          dup hex-output-metadata-entry-string @ ." ~ " emitstring newline
+
+          ." ~ "
+          dup hex-output-metadata-entry-string @ hex-emit-template-string
+          newline
 
           1 is-fresh-line!
           0 current-column!
-- 
cgit 1.4.1