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/glob.c | 21 ++++++++++++++------- 1 file changed, 14 insertions(+), 7 deletions(-) (limited to 'src/glob.c') diff --git a/src/glob.c b/src/glob.c index 0917e5c..24f2647 100644 --- a/src/glob.c +++ b/src/glob.c @@ -38,6 +38,7 @@ #include "expressions.h" #include "qreg.h" #include "ring.h" +#include "view.h" #include "error.h" #include "undo.h" #include "glob.h" @@ -527,21 +528,24 @@ teco_state_glob_filename_done(teco_machine_main_t *ctx, teco_string_t str, GErro gint rc = tere_exec(&pattern, (chr *)filename, strlen(filename), NULL, 0, NULL, 0); if (rc == REG_OKAY && (teco_test_mode == 0 || g_file_test(filename, file_flags))) { if (!colon_modified) { - sptr_t pos = teco_interface_ssm(SCI_GETCURRENTPOS, 0, 0); - /* * FIXME: Filenames may contain linefeeds. * But if we add them null-terminated, they will be relatively hard to parse. */ gsize len = strlen(filename); filename[len] = '\n'; + + sptr_t pos = teco_interface_ssm(SCI_GETCURRENTPOS, 0, 0); + teco_undo_int(teco_ranges[0].from) = teco_current_doc_get_dot(); + teco_interface_ssm(SCI_BEGINUNDOACTION, 0, 0); teco_interface_ssm(SCI_ADDTEXT, len+1, (sptr_t)filename); teco_interface_ssm(SCI_ENDUNDOACTION, 0, 0); - teco_undo_int(teco_ranges[0].from) = teco_interface_bytes2glyphs(pos); - teco_undo_int(teco_ranges[0].to) = teco_interface_bytes2glyphs(pos + len + 1); + teco_int_t to = teco_interface_bytes2glyphs_rel(teco_ranges[0].from, pos, len + 1); + teco_undo_int(teco_ranges[0].to) = to; teco_undo_guint(teco_ranges_count) = 1; + teco_current_doc_set_dot(to); } matching = TRUE; @@ -565,14 +569,15 @@ teco_state_glob_filename_done(teco_machine_main_t *ctx, teco_string_t str, GErro globber = teco_globber_new(pattern_str.data, file_flags); sptr_t pos = teco_interface_ssm(SCI_GETCURRENTPOS, 0, 0); - teco_undo_int(teco_ranges[0].from) = teco_interface_bytes2glyphs(pos); + gsize total_len = 0; + teco_undo_int(teco_ranges[0].from) = teco_current_doc_get_dot(); teco_interface_ssm(SCI_BEGINUNDOACTION, 0, 0); gchar *globbed_filename; while ((globbed_filename = teco_globber_next(globber))) { gsize len = strlen(globbed_filename); - pos += len+1; + total_len += len+1; /* * FIXME: Filenames may contain linefeeds. @@ -587,8 +592,10 @@ teco_state_glob_filename_done(teco_machine_main_t *ctx, teco_string_t str, GErro teco_interface_ssm(SCI_ENDUNDOACTION, 0, 0); - teco_undo_int(teco_ranges[0].to) = teco_interface_bytes2glyphs(pos); + teco_int_t to = teco_interface_bytes2glyphs_rel(teco_ranges[0].from, pos, total_len); + teco_undo_int(teco_ranges[0].to) = to; teco_undo_guint(teco_ranges_count) = 1; + teco_current_doc_set_dot(to); } if (colon_modified) { -- cgit v1.2.3