implemented the ^~ pattern match construct: the rest of the pattern will be an Advanced Regular Expression

* Allows searching by regular expressions.
  We will never support all ARE constructs in TECO patterns, so this is useful to have available.
* Can only be typed upcaret.
  This leaves ^E~q available as an escape-regexp string building construct.
* Once we replace the pattern2regexp converter with a custom terex lexer,
  we might want to restrict ^~ to the beginning of the pattern.
  Currently, however it can be anywhere, so you can mix TECO patterns with regular expressions.

1 files changed, 22 insertions, 7 deletions

diff --git a/src/search.c b/src/search.c
index 0df483f..ce4a338 100644
--- a/src/search.c
+++ b/src/search.c
@@ -425,14 +425,29 @@ teco_pattern2regexp(teco_string_t *pattern, teco_machine_qregspec_t *qreg_machin
 	g_auto(teco_string_t) re = {NULL, 0};
 
 	do {
-		/*
-		 * Previous character was caret.
-		 * Make sure it is handled like a control character.
-		 * This is necessary even though we have string building activated,
-		 * to support constructs like ^Q^Q (typed with carets) in order to
-		 * quote pattern matching characters.
-		 */
 		if (state == TECO_SEARCH_STATE_CTL) {
+			if (*pattern->data == '~') {
+				/* rest of pattern is a regular expression */
+				teco_string_append(&re, pattern->data+1, pattern->len-1);
+				/*
+				 * FIXME: In terex, it actually could contain null bytes.
+				 */
+				if (teco_string_contains(re, '\0')) {
+					g_set_error_literal(error, TECO_ERROR, TECO_ERROR_FAILED,
+					                    "Regular expression must not contain null-byte"
+					                    " - use \\0 instead");
+					return NULL;
+				}
+				return g_steal_pointer(&re.data) ? : g_strdup("");
+			}
+
+			/*
+			 * Previous character was caret.
+			 * Make sure it is handled like a control character.
+			 * This is necessary even though we have string building activated,
+			 * to support constructs like ^Q^Q (typed with carets) in order to
+			 * quote pattern matching characters.
+			 */
 			*pattern->data = TECO_CTL_KEY(g_ascii_toupper(*pattern->data));
 			state = TECO_SEARCH_STATE_START;
 		}