From ef897b418a4487196e1dbc18a97046f8f0aea2e8 Mon Sep 17 00:00:00 2001
From: Robin Haberkorn <robin.haberkorn@googlemail.com>
Date: Tue, 24 Dec 2024 13:29:32 +0300
Subject: introduced true block and EOL comments

* The previous convention of !* ... *! are now true block comments,
  i.e. they are parsed faster, don't spam the goto table and allow
  embedding of exclamation marks - only "*!" terminates the comment.
* It is therefore now forbidden to have goto labels beginning with "*".
* Also support "!!" to introduce EOL comments (like C++'s //).
  This disallows empty labels, but they weren't useful anyway.
  This is the shortest way to begin a comment.
* All comment labels have been converted to true comments, to ensure
  that syntax highlighting works correctly.
  EOL comments are used for single line commented-out code, since it's
  easiest to uncomment - you don't have to jump to the line end.
  This is a pure convention / coding style.
  Other people might do it differently.
* It's of course still possible to abuse goto labels as comments
  as TECO did for ages.
* In lexing / syntax highlighting, labels and comments are highlighted differently.
* When syntax highlighting, a single "!" will first be highlighted as a label
  since it's not yet unambiguous. Once you type the second character (* or !),
  the first character is retroactively styled as a comment as well.
---
 src/lexer.c | 51 +++++++++++++++++++++++++++++++--------------------
 1 file changed, 31 insertions(+), 20 deletions(-)

(limited to 'src/lexer.c')

diff --git a/src/lexer.c b/src/lexer.c
index ff43c1b..c0c7847 100644
--- a/src/lexer.c
+++ b/src/lexer.c
@@ -19,6 +19,8 @@
 #include "config.h"
 #endif
 
+#include <string.h>
+
 #include <glib.h>
 
 #include "sciteco.h"
@@ -39,20 +41,12 @@ teco_lexer_getstyle(teco_view_t *view, teco_machine_main_t *machine,
 	 * FIXME: What about ^* and ^/?
 	 * They are currently highlighted as commands.
 	 */
-	if (machine->parent.current->keymacro_mask & TECO_KEYMACRO_MASK_START) {
-		switch (chr) {
-		case '0'...'9':
+	if (machine->parent.current->keymacro_mask & TECO_KEYMACRO_MASK_START &&
+	    chr <= 0xFF) {
+		if (g_ascii_isdigit(chr))
 			style = SCE_SCITECO_NUMBER;
-			break;
-		case '+':
-		case '-':
-		case '*':
-		case '/':
-		case '#':
-		case '&':
+		else if (strchr("+-*/#&", chr))
 			style = SCE_SCITECO_OPERATOR;
-			break;
-		}
 	}
 
 	/*
@@ -64,10 +58,7 @@ teco_lexer_getstyle(teco_view_t *view, teco_machine_main_t *machine,
 		/*
 		 * Probably a syntax error, so the erroneous symbol
 		 * is highlighted and we reset the parser's state machine.
-		 */
-		style = SCE_SCITECO_INVALID;
-
-		/*
+		 *
 		 * FIXME: Perhaps we should simply reset the state to teco_state_start?
 		 */
 		gsize macro_pc = machine->macro_pc;
@@ -75,9 +66,22 @@ teco_lexer_getstyle(teco_view_t *view, teco_machine_main_t *machine,
 		teco_machine_main_init(machine, NULL, FALSE);
 		machine->mode = TECO_MODE_LEXING;
 		machine->macro_pc = macro_pc;
-	} else if (machine->parent.current->style == SCE_SCITECO_LABEL) {
-		/* don't highlight the leading `!` as SCE_SCITECO_COMMAND */
-		style = SCE_SCITECO_LABEL;
+
+		return SCE_SCITECO_INVALID;
+	}
+
+	/*
+	 * Don't highlight the leading `!` in comments as SCE_SCITECO_COMMAND.
+	 * True comments also begin with `!`, so make sure they are highlighted
+	 * already from the second character.
+	 * This is then extended back by one character in teco_lexer_step().
+	 */
+	switch (machine->parent.current->style) {
+	case SCE_SCITECO_COMMENT:
+	case SCE_SCITECO_LABEL:
+		return machine->parent.current->style;
+	default:
+		break;
 	}
 
 	return style;
@@ -100,7 +104,7 @@ teco_lexer_step(teco_view_t *view, teco_machine_main_t *machine,
 		return;
 	}
 
-	gsize old_pc = machine->macro_pc;
+	gssize old_pc = machine->macro_pc;
 
 	teco_style_t style = SCE_SCITECO_DEFAULT;
 
@@ -140,6 +144,13 @@ teco_lexer_step(teco_view_t *view, teco_machine_main_t *machine,
 
 	*cur_col += machine->macro_pc - old_pc;
 
+	/*
+	 * True comments begin with `!*` or `!!`, but only the second character gets
+	 * the correct style by default, so we extend it backwards.
+	 */
+	if (style == SCE_SCITECO_COMMENT)
+		old_pc--;
+
 	teco_view_ssm(view, SCI_STARTSTYLING, start+old_pc, 0);
 	teco_view_ssm(view, SCI_SETSTYLING, machine->macro_pc-old_pc, style);
 
-- 
cgit v1.2.3