luwrap: replace Nim unicode maps with libunicode

Instead of using the built-in (and outdated, and buggy) tables, we now
use libunicode from QJS.  This shaves some bytes off the executable,
though far less than I had imagined it would.

Also, a surprising effect of this change: because libunicode's tables
aren't glitched out, kanji properly gets classified as alpha.  I found
this greatly annoying because `w' in Japanese text would now jump
through whole sentences.  As a band-aid solution I added an extra
Han category, but I wish we had a more robust solution that could
differentiate between *all* scripts.

TODO: I suspect that separately loading the tables for every rune in
breaksViWordCat is rather inefficient.  Using some context object (at
least per operation) would probably be beneficial.

2 files changed, 5 insertions, 2 deletions

diff --git a/src/local/container.nim b/src/local/container.nim
index e4901902..985e45ef 100644
--- a/src/local/container.nim
+++ b/src/local/container.nim
@@ -12,8 +12,8 @@ import io/promise
 import io/serversocket
 import io/socketstream
 import js/javascript
-import js/jstypes
 import js/jsregex
+import js/jstypes
 import layout/renderdocument
 import loader/headers
 import loader/loader
@@ -26,9 +26,11 @@ import types/cookie
 import types/referrer
 import types/url
 import types/winattrs
+import utils/luwrap
 import utils/mimeguess
 import utils/strwidth
 import utils/twtstr
+import utils/wordbreak
 
 import chagashi/charset
 
@@ -595,7 +597,7 @@ proc cursorLineTextStart(container: Container) {.jsfunc.} =
   if container.numLines == 0: return
   var x = 0
   for r in container.currentLine.runes:
-    if not r.isWhitespace():
+    if not r.isWhiteSpaceLU():
       break
     x += r.twidth(x)
   if x == 0:
diff --git a/src/local/lineedit.nim b/src/local/lineedit.nim
index 2db59e7b..e2b89f89 100644
--- a/src/local/lineedit.nim
+++ b/src/local/lineedit.nim
@@ -8,6 +8,7 @@ import types/opt
 import types/winattrs
 import utils/strwidth
 import utils/twtstr
+import utils/wordbreak
 
 import chagashi/charset
 import chagashi/validator