From 685507922b0b75da5935076395a5b1ec1ef58356 Mon Sep 17 00:00:00 2001 From: Robin Haberkorn Date: Sat, 25 Jul 2026 01:55:28 +0200 Subject: revised and improved the Unicode glyph-to-byte conversion heuristics Previously almost all glyph-to-byte offset conversions consulted Scintilla's line index and counted characters on the resulting line. For instance a simple expression like `.+1J` would scan the same line twice completely, which would be very slow on pathologically long lines. Even insertions did that due to having to update the ^Y ranges. If you repeat such an operation over all characters as in `<.+1:J;>` you would have complexity O(n^2) for n = line length. Only commands with an explicit relative nature like `C` and `A` would use teco_view_glyph2bytes_relative() which scans beginning at dot as long as the relative movement is less than 1024 glyphs. Wit the new heuristics almost all glyph-to-byte and byte-to-glyph conversions can make use of that optimization. This requires that dot must at all times be known in glyphs as well - the byte position is managed by Scintilla (SCI_GETCURRENTPOS). We therefore introduced teco_current_doc_set_dot() and teco_current_doc_get_dot() to update dot in the current buffer or Q-Register -- it cannot be stored along with the view since Q-Registers share a single view. A number of auxiliary functions have been introduced for converting relative to a known (glyphs,bytes) offset pair and for converting absolute and relative positions with regard to the current doc and SCI_GETCURRENTPOS position. Of course this is error-prone since the glyph and dot positions are interdependant - they must always be kept in sync. With these new optimizations even pathologically long lines can (usually) be managed even in UTF-8 documents. It does not address slow-downs in Scintilla's line layout, yet. grosciteco.tes for instance runs twice as fast now. --- src/doc.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'src/doc.c') diff --git a/src/doc.c b/src/doc.c index 9bc9dc8..40217f4 100644 --- a/src/doc.c +++ b/src/doc.c @@ -77,7 +77,7 @@ teco_doc_edit(teco_doc_t *ctx, guint default_cp) (sptr_t)teco_doc_get_scintilla(ctx)); teco_view_ssm(teco_qreg_view, SCI_SETFIRSTVISIBLELINE, ctx->first_line, 0); teco_view_ssm(teco_qreg_view, SCI_SETXOFFSET, ctx->xoffset, 0); - teco_view_ssm(teco_qreg_view, SCI_SETSEL, ctx->anchor, (sptr_t)ctx->dot); + teco_view_ssm(teco_qreg_view, SCI_SETSEL, ctx->anchor, (sptr_t)ctx->pos); /* * NOTE: Thanks to a custom Scintilla patch, representations @@ -124,7 +124,7 @@ teco_doc_undo_edit(teco_doc_t *ctx) */ //undo__teco_view_set_representations(teco_qreg_view); - undo__teco_view_ssm(teco_qreg_view, SCI_SETSEL, ctx->anchor, (sptr_t)ctx->dot); + undo__teco_view_ssm(teco_qreg_view, SCI_SETSEL, ctx->anchor, (sptr_t)ctx->pos); undo__teco_view_ssm(teco_qreg_view, SCI_SETXOFFSET, ctx->xoffset, 0); undo__teco_view_ssm(teco_qreg_view, SCI_SETFIRSTVISIBLELINE, ctx->first_line, 0); undo__teco_view_ssm(teco_qreg_view, SCI_SETDOCPOINTER, 0, @@ -222,9 +222,11 @@ void teco_doc_update_from_view(teco_doc_t *ctx, teco_view_t *from) { ctx->anchor = teco_view_ssm(from, SCI_GETANCHOR, 0, 0); - ctx->dot = teco_view_ssm(from, SCI_GETCURRENTPOS, 0, 0); + ctx->pos = teco_view_ssm(from, SCI_GETCURRENTPOS, 0, 0); ctx->first_line = teco_view_ssm(from, SCI_GETFIRSTVISIBLELINE, 0, 0); ctx->xoffset = teco_view_ssm(from, SCI_GETXOFFSET, 0, 0); + + ctx->dot = teco_view_bytes2glyphs_rel(from, 0, 0, ctx->pos); } /** @memberof teco_doc_t */ @@ -232,9 +234,11 @@ void teco_doc_update_from_doc(teco_doc_t *ctx, const teco_doc_t *from) { ctx->anchor = from->anchor; - ctx->dot = from->dot; + ctx->pos = from->pos; ctx->first_line = from->first_line; ctx->xoffset = from->xoffset; + + ctx->dot = from->dot; } /** @@ -252,7 +256,6 @@ teco_doc_exchange(teco_doc_t *ctx, teco_doc_t *other) memcpy(other, &temp, sizeof(*other)); } -/** @memberof teco_doc_t */ void teco_doc_clear(teco_doc_t *ctx) { -- cgit v1.2.3