fixed minor memory leaks of per-state data in teco_machine_main_t

* These were leaked e.g. in case of end-of-macro errors,
  but also in case of syntax highlighting (teco_lexer_style()).
  I considered to solve this by overwriting more of the end_of_macro_cb,
  but it didn't turn out to be trivial always.
* Considering that the union in teco_machine_main_t saved only 3 machine words
  of memory, I decided to sacrifice those for more robust memory management.
* teco_machine_qregspec_t cannot be directly embedded into teco_machine_main_t
  due to recursive dependencies with teco_machine_stringbuilding_t.
  It could now and should perhaps be allocated only once in teco_machine_main_init(),
  but it would require more refactoring.

6 files changed, 23 insertions, 27 deletions

diff --git a/src/goto-commands.c b/src/goto-commands.c
index a0e6634..72be48e 100644
--- a/src/goto-commands.c
+++ b/src/goto-commands.c
@@ -39,13 +39,6 @@ TECO_DECLARE_STATE(teco_state_eolcomment);
 
 teco_string_t teco_goto_skip_label = {NULL, 0};
 
-static gboolean
-teco_state_label_initial(teco_machine_main_t *ctx, GError **error)
-{
-	memset(&ctx->goto_label, 0, sizeof(ctx->goto_label));
-	return TRUE;
-}
-
 /*
  * NOTE: The comma is theoretically not allowed in a label
  * (see <O> syntax), but is accepted anyway since labels
@@ -108,7 +101,6 @@ teco_state_label_input(teco_machine_main_t *ctx, gunichar chr, GError **error)
 }
 
 TECO_DEFINE_STATE(teco_state_label,
-	.initial_cb = (teco_state_initial_cb_t)teco_state_label_initial,
 	.style = SCE_SCITECO_LABEL
 );
 
diff --git a/src/lexer.c b/src/lexer.c
index 6bc696f..2f43b76 100644
--- a/src/lexer.c
+++ b/src/lexer.c
@@ -157,7 +157,9 @@ teco_lexer_step(teco_view_t *view, teco_machine_main_t *machine,
 		 * The curly braces will be styled like regular commands.
 		 *
 		 * FIXME: This works only for top-level macro definitions,
-		 * not for embedded definitions.
+		 * not for nested definitions.
+		 * FIXME: The macrodef_machine's end-of-macro callback could be used
+		 * to detect and highlight an error on the closing `}`.
 		 * FIXME: This cannot currently be disabled, not even with SCI_SETPROPERTY.
 		 * We could only map it to an ED flag or
 		 * rewrite the lexer against the ILexer5 interface, which requires C++.
diff --git a/src/parser.c b/src/parser.c
index ee705a0..33d2e7f 100644
--- a/src/parser.c
+++ b/src/parser.c
@@ -81,7 +81,7 @@ teco_machine_input(teco_machine_t *ctx, gunichar chr, GError **error)
 gboolean
 teco_state_end_of_macro(teco_machine_t *ctx, GError **error)
 {
-	g_set_error_literal(error, TECO_ERROR, TECO_ERROR_FAILED,
+	g_set_error_literal(error, TECO_ERROR, TECO_ERROR_SYNTAX,
 	                    "Unterminated command");
 	return FALSE;
 }
@@ -386,7 +386,8 @@ teco_machine_main_clear(teco_machine_main_t *ctx)
 	teco_goto_table_clear(&ctx->goto_table);
 	teco_string_clear(&ctx->expectstring.string);
 	teco_machine_stringbuilding_clear(&ctx->expectstring.machine);
-	// FIXME: Could leak ctx->goto_label, but it's in an union
+	teco_string_clear(&ctx->goto_label);
+	teco_machine_qregspec_free(ctx->expectqreg);
 }
 
 /** Append string to result with case folding. */
@@ -1012,8 +1013,7 @@ teco_machine_stringbuilding_escape(teco_machine_stringbuilding_t *ctx, const gch
 void
 teco_machine_stringbuilding_clear(teco_machine_stringbuilding_t *ctx)
 {
-	if (ctx->machine_qregspec)
-		teco_machine_qregspec_free(ctx->machine_qregspec);
+	teco_machine_qregspec_free(ctx->machine_qregspec);
 	teco_string_clear(&ctx->code);
 }
 
diff --git a/src/parser.h b/src/parser.h
index 36a0302..a1583d2 100644
--- a/src/parser.h
+++ b/src/parser.h
@@ -514,17 +514,19 @@ struct teco_machine_main_t {
 	/*
 	 * teco_state_t-dependent state.
 	 *
-	 * Some of these cannot be used concurrently and are therefore
-	 * grouped into unions.
-	 * We could further optimize memory usage by dynamically allocating
-	 * some of these structures on demand.
+	 * Some cannot theoretically be used at the same time
+	 * but it's hard to prevent memory leaks if putting them into
+	 * a common union.
 	 */
-	teco_machine_expectstring_t		expectstring;
-	union {
-		teco_string_t			goto_label;
-		teco_machine_qregspec_t		*expectqreg;
-		teco_machine_scintilla_t	scintilla;
-	};
+	teco_machine_expectstring_t	expectstring;
+	/**
+	 * State machine for parsing Q-reg specifications.
+	 * This could theoretically be inlined, but it would introduce
+	 * a recursive dependency between qreg.h and parser.h.
+	 */
+	teco_machine_qregspec_t		*expectqreg;
+	teco_string_t			goto_label;
+	teco_machine_scintilla_t	scintilla;
 };
 
 typedef struct teco_machine_main_flags_t teco_machine_main_flags_t;
diff --git a/src/qreg-commands.c b/src/qreg-commands.c
index 7189771..9407e6c 100644
--- a/src/qreg-commands.c
+++ b/src/qreg-commands.c
@@ -39,8 +39,8 @@ teco_state_expectqreg_initial(teco_machine_main_t *ctx, GError **error)
 	teco_state_t *current = ctx->parent.current;
 
 	/*
-	 * NOTE: We have to allocate a new instance always since `expectqreg`
-	 * is part of an union.
+	 * NOTE: This could theoretically be allocated once in
+	 * teco_machine_main_init(), but we'd have to set the type here anyway.
 	 */
 	ctx->expectqreg = teco_machine_qregspec_new(current->expectqreg.type, ctx->qreg_table_locals,
 	                                            ctx->parent.must_undo);
@@ -69,7 +69,7 @@ teco_state_expectqreg_input(teco_machine_main_t *ctx, gunichar chr, GError **err
 
 	/*
 	 * NOTE: ctx->expectqreg is preserved since we may want to query it from follow-up
-	 * states. This means, it must usually be stored manually in got_register_cb() via:
+	 * states. This means, it must usually be reset manually in got_register_cb() via:
 	 * teco_state_expectqreg_reset(ctx);
 	 */
 	return current->expectqreg.got_register_cb(ctx, qreg, table, error);
diff --git a/src/view.c b/src/view.c
index d08728d..972828a 100644
--- a/src/view.c
+++ b/src/view.c
@@ -315,7 +315,7 @@ cleanup:
 
 /**
  * Load file into view's document.
- * 
+ *
  * @param ctx The view to load.
  * @param filename File name to read
  * @param clear Whether to completely replace document