Coq_lex: direct accounting of utf8 extra bytes in offsets

 We directly produce in Coq_lex a utf8 char offset instead of
 a byte offset, by counting the utf8 extra byte during the lexing.
 This way, no need anymore for converting later with complex
 byte_offset_to_char_offset.

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/coq/trunk@16059 85f007b7-540e-0410-9357-904b9bb8a0f7

1 files changed, 3 insertions, 7 deletions

diff --git a/ide/sentence.ml b/ide/sentence.ml
index f6bc99207..01add490e 100644
--- a/ide/sentence.ml
+++ b/ide/sentence.ml
@@ -16,14 +16,10 @@
 let split_slice_lax (buffer:GText.buffer) start stop =
   List.iter (buffer#remove_tag ~start ~stop) Tags.Script.all;
   let slice = buffer#get_text ~start ~stop () in
-  let mkiter =
-    (* caveat : partial application with effects *)
-    let convert = Ideutils.byte_offset_to_char_offset slice in
-    fun off -> start#forward_chars (convert off)
-  in
   let apply_tag off tag =
-    let start = mkiter off in
-    buffer#apply_tag ~start ~stop:start#forward_char tag
+    (* off is now a utf8-compliant char offset, cf Coq_lex.utf8_adjust *)
+    let iter = start#forward_chars off in
+    buffer#apply_tag ~start:iter ~stop:iter#forward_char tag
   in
   Coq_lex.delimit_sentences apply_tag slice