the ^EUq string building escape now respects the encoding (can insert bytes or codepoints) (refs #5)

* This is trickier than it sounds because there isn't one single place to consult.
  It depends on the context.
  If the string argument relates to buffer contents - as in <I>, <S>, <FR> etc. -
  the buffer's encoding is consulted.
  If it goes into a register (EU), the register's encoding is consulted.
  Everything else (O, EN, EC, ES...) expects only Unicode codepoints.
* This is communicated through a new field teco_machine_stringbuilding_t::codepage
  which must be set in the states' initial callback.
* Seems overkill just for ^EUq, but it can be used for context-sensitive
  processing of all the other string building constructs as well.
* ^V and ^W cannot be supported for Unicode characters for the time being without an Unicode-aware parser

1 files changed, 9 insertions, 3 deletions

diff --git a/src/parser.h b/src/parser.h
index 4b4a3a0..ba6054f 100644
--- a/src/parser.h
+++ b/src/parser.h
@@ -309,9 +309,6 @@ typedef enum {
 /**
  * A stringbuilding state machine.
  *
- * @fixme Should contain the escape char (currently in teco_machine_expectstring_t),
- * so that we can escape it via ^Q.
- *
  * @extends teco_machine_t
  */
 typedef struct teco_machine_stringbuilding_t {
@@ -350,6 +347,13 @@ typedef struct teco_machine_stringbuilding_t {
 	 * (see teco_state_stringbuilding_start_process_edit_cmd()).
 	 */
 	teco_string_t *result;
+
+	/**
+	 * Encoding of string in `result`.
+	 * This is inherited from the embedding command and may depend on
+	 * the buffer's or Q-Register's encoding.
+	 */
+	guint codepage;
 } teco_machine_stringbuilding_t;
 
 void teco_machine_stringbuilding_init(teco_machine_stringbuilding_t *ctx, gchar escape_char,
@@ -508,6 +512,7 @@ void teco_machine_main_clear(teco_machine_main_t *ctx);
 
 G_DEFINE_AUTO_CLEANUP_CLEAR_FUNC(teco_machine_main_t, teco_machine_main_clear);
 
+gboolean teco_state_expectstring_initial(teco_machine_main_t *ctx, GError **error);
 teco_state_t *teco_state_expectstring_input(teco_machine_main_t *ctx, gchar chr, GError **error);
 gboolean teco_state_expectstring_refresh(teco_machine_main_t *ctx, GError **error);
 
@@ -533,6 +538,7 @@ gboolean teco_state_expectstring_process_edit_cmd(teco_machine_main_t *ctx, teco
 		return teco_state_expectstring_input(ctx, chr, error); \
 	} \
 	TECO_DEFINE_STATE(NAME, \
+		.initial_cb = (teco_state_initial_cb_t)teco_state_expectstring_initial, \
 		.refresh_cb = (teco_state_refresh_cb_t)teco_state_expectstring_refresh, \
 		.process_edit_cmd_cb = (teco_state_process_edit_cmd_cb_t) \
 		                       teco_state_expectstring_process_edit_cmd, \