sed: fix handling of 1d;1,3p and 1d;1,REGEXp

function                                             old     new   delta
process_files                                       2084    2173     +89

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>

editors/sed.c

@@ -865,63 +865,80 @@ static void process_files(void)
 	/* Prime the pump */
 	next_line = get_next_line(&next_gets_char);
 
-	/* go through every line in each file */
+	/* Go through every line in each file */
  again:
 	substituted = 0;
 
 	/* Advance to next line.  Stop if out of lines. */
 	pattern_space = next_line;
-	if (!pattern_space) return;
+	if (!pattern_space)
+		return;
 	last_gets_char = next_gets_char;
 
 	/* Read one line in advance so we can act on the last line,
 	 * the '$' address */
 	next_line = get_next_line(&next_gets_char);
 	linenum++;
+
+	/* For every line, go through all the commands */
  restart:
-	/* for every line, go through all the commands */
 	for (sed_cmd = G.sed_cmd_head.next; sed_cmd; sed_cmd = sed_cmd->next) {
 		int old_matched, matched;
 
 		old_matched = sed_cmd->in_match;
 
 		/* Determine if this command matches this line: */
-
 			/* Are we continuing a previous multi-line match? */
 		sed_cmd->in_match = sed_cmd->in_match
 			/* Or is no range necessary? */
 			|| (!sed_cmd->beg_line && !sed_cmd->end_line
 				&& !sed_cmd->beg_match && !sed_cmd->end_match)
 			/* Or did we match the start of a numerical range? */
-			|| (sed_cmd->beg_line > 0 && (sed_cmd->beg_line == linenum))
+			|| (sed_cmd->beg_line > 0 && (sed_cmd->beg_line == linenum
+							/* "shadowed beginning" case: "1d;1,ENDp" - p still matches at line 2
+							 * even though 1d skipped line 1 which is a start line for p */
+							|| (sed_cmd->end_line && sed_cmd->beg_line < linenum && sed_cmd->end_line >= linenum)
+							|| (sed_cmd->end_match && sed_cmd->beg_line < linenum)
+						)
+			)
 			/* Or does this line match our begin address regex? */
 			|| (beg_match(sed_cmd, pattern_space))
 			/* Or did we match last line of input? */
 			|| (sed_cmd->beg_line == -1 && next_line == NULL);
 
-		/* Snapshot the value */
-
 		matched = sed_cmd->in_match;
 
-		/* Is this line the end of the current match? */
+		//bb_error_msg("cmd:'%c' matched:%d beg_line:%d end_line:%d linenum:%d",
+		//sed_cmd->cmd, matched, sed_cmd->beg_line, sed_cmd->end_line, linenum);
 
+		/* Is this line the end of the current match? */
 		if (matched) {
-			sed_cmd->in_match = !(
+			int n = (
 				/* has the ending line come, or is this a single address command? */
-				(sed_cmd->end_line ?
+				sed_cmd->end_line ?
 					sed_cmd->end_line == -1 ?
 						!next_line
 						: (sed_cmd->end_line <= linenum)
 					: !sed_cmd->end_match
-				)
-				/* or does this line matches our last address regex */
-				|| (sed_cmd->end_match && old_matched
-				     && (regexec(sed_cmd->end_match,
-				                 pattern_space, 0, NULL, 0) == 0))
 				);
+			if (!n) {
+				/* or does this line matches our last address regex */
+				n = (sed_cmd->end_match
+				     && old_matched
+				     && (regexec(sed_cmd->end_match,
+				                 pattern_space, 0, NULL, 0) == 0)
+				);
+				if (n && sed_cmd->beg_line > 0) {
+					/* Once matched, "n,regex" range is dead, disabling it */
+					regfree(sed_cmd->end_match);
+					free(sed_cmd->end_match);
+					sed_cmd->end_match = NULL;
+				}
+			}
+			sed_cmd->in_match = !n;
 		}
 
-		/* Skip blocks of commands we didn't match. */
+		/* Skip blocks of commands we didn't match */
 		if (sed_cmd->cmd == '{') {
 			if (sed_cmd->invert ? matched : !matched) {
 				while (sed_cmd->cmd != '}') {
@@ -934,7 +951,9 @@ static void process_files(void)
 		}
 
 		/* Okay, so did this line match? */
-		if (sed_cmd->invert ? !matched : matched) {
+		if (sed_cmd->invert ? matched : !matched)
+			continue; /* no */
+
 		/* Update last used regex in case a blank substitute BRE is found */
 		if (sed_cmd->beg_match) {
 			G.previous_regex_ptr = sed_cmd->beg_match;
@@ -1175,12 +1194,11 @@ static void process_files(void)
 			G.hold_space = tmp;
 			break;
 		}
-			}
+		} /* switch */
-		}
+	} /* for each cmd */
-	}
 
 	/*
-	 * exit point from sedding...
+	 * Exit point from sedding...
 	 */
  discard_commands:
 	/* we will print the line unless we were told to be quiet ('-n')

testsuite/sed.tests

@@ -207,4 +207,17 @@ testing "sed n command must reset 'substituted' bit" \
 	"sed 's/1/x/;T;n;: next;s/3/y/;t quit;n;b next;: quit;q'" \
 	"0\nx\n2\ny\n" "" "0\n1\n2\n3\n"
 
+testing "sed d does not break n,m matching" \
+	"sed -n '1d;1,3p'" \
+	"second\nthird\n" "" "first\nsecond\nthird\nfourth\n"
+
+testing "sed d does not break n,regex matching" \
+	"sed -n '1d;1,/hir/p'" \
+	"second\nthird\n" "" "first\nsecond\nthird\nfourth\n"
+
+testing "sed d does not break n,regex matching #2" \
+	"sed -n '1,5d;1,/hir/p'" \
+	"second2\nthird2\n" "" \
+	"first\nsecond\nthird\nfourth\n""first2\nsecond2\nthird2\nfourth2\n"
+
 exit $FAILCOUNT