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/spawn.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'src/spawn.c') diff --git a/src/spawn.c b/src/spawn.c index 0492bbf..b1cd305 100644 --- a/src/spawn.c +++ b/src/spawn.c @@ -222,8 +222,8 @@ teco_state_execute_initial(teco_machine_main_t *ctx, GError **error) default: /* pipe and replace character range */ - teco_spawn_ctx.to = teco_interface_glyphs2bytes(teco_expressions_pop_num(0)); - teco_spawn_ctx.from = teco_interface_glyphs2bytes(teco_expressions_pop_num(0)); + teco_spawn_ctx.to = teco_interface_glyphs2bytes_absdot(teco_expressions_pop_num(0)); + teco_spawn_ctx.from = teco_interface_glyphs2bytes_absdot(teco_expressions_pop_num(0)); rc = teco_bool(teco_spawn_ctx.from <= teco_spawn_ctx.to && teco_spawn_ctx.from >= 0 && teco_spawn_ctx.to >= 0); } @@ -424,6 +424,8 @@ teco_state_execute_done(teco_machine_main_t *ctx, teco_string_t str, GError **er g_source_attach(teco_spawn_ctx.stdout_src, teco_spawn_ctx.mainctx); if (!teco_spawn_ctx.register_argument) { + teco_undo_int(teco_ranges[0].from) = teco_interface_bytes2glyphs_absdot(teco_spawn_ctx.from); + if (teco_current_doc_must_undo()) undo__teco_interface_ssm(SCI_GOTOPOS, teco_interface_ssm(SCI_GETCURRENTPOS, 0, 0), 0); @@ -438,9 +440,12 @@ teco_state_execute_done(teco_machine_main_t *ctx, teco_string_t str, GError **er teco_spawn_ctx.to - teco_spawn_ctx.from); sptr_t pos = teco_interface_ssm(SCI_GETCURRENTPOS, 0, 0); - teco_undo_int(teco_ranges[0].from) = teco_interface_bytes2glyphs(teco_spawn_ctx.from); - teco_undo_int(teco_ranges[0].to) = teco_interface_bytes2glyphs(pos); + teco_int_t to = teco_interface_bytes2glyphs_rel(teco_ranges[0].from, teco_spawn_ctx.from, + pos - teco_spawn_ctx.from); + teco_undo_int(teco_ranges[0].to) = to; teco_undo_guint(teco_ranges_count) = 1; + + teco_current_doc_set_dot(to); } teco_interface_ssm(SCI_ENDUNDOACTION, 0, 0); -- cgit v1.2.3