vis

commit bcb86378e81e931220dc3abb9f857afbf68f312a
parent 146fda51894e770b7d3eaa90ef8f7c507723a837
Author: Marc André Tanner <mat@brain-dump.org>
Date:   Thu, 23 Jan 2020 14:01:41 +0100

text: fix spurious regex anchor matches

The regex anchors ^ and $ must not match at the start/end of the search
range unless it is preceded/succeeded by a new line.

This is implemented at the text-motion layer by passing the appropriate
REG_NOT{B,E}OL flags to the search backend, meaning the caller can
influence the anchor behavior depending on the context. This is important
as for example in the command language the anchors apply to existing
selections, not line boundaries.

Diffstat:
M
text-motions.c
 | 
15
+++++++++++----
M
text-regex-tre.c
 | 
6
++++++
M
text-regex.c
 | 
4
++++

3 files changed, 21 insertions(+), 4 deletions(-)
diff --git a/text-motions.c b/text-motions.c
@@ -618,11 +618,15 @@ size_t text_search_forward(Text *txt, size_t pos, Regex *regex) {
 	size_t start = pos + 1;
 	size_t end = text_size(txt);
 	RegexMatch match[1];
-	bool found = start < end && !text_search_range_forward(txt, start, end - start, regex, 1, match, 0);
+	char c;
+	int flags = text_byte_get(txt, pos, &c) && c == '\n' ? 0 : REG_NOTBOL;
+	bool found = start < end && !text_search_range_forward(txt, start, end - start, regex, 1, match, flags);
 
 	if (!found) {
 		start = 0;
-		found = !text_search_range_forward(txt, start, end - start, regex, 1, match, 0);
+		end = pos;
+		flags = text_byte_get(txt, end, &c) && c == '\n' ? 0 : REG_NOTEOL;
+		found = !text_search_range_forward(txt, start, end - start, regex, 1, match, flags);
 	}
 
 	return found ? match[0].start : pos;
@@ -632,12 +636,15 @@ size_t text_search_backward(Text *txt, size_t pos, Regex *regex) {
 	size_t start = 0;
 	size_t end = pos;
 	RegexMatch match[1];
-	bool found = !text_search_range_backward(txt, start, end, regex, 1, match, 0);
+	char c;
+	int flags = text_byte_get(txt, end, &c) && c == '\n' ? 0 : REG_NOTEOL;
+	bool found = !text_search_range_backward(txt, start, end, regex, 1, match, flags);
 
 	if (!found) {
 		start = pos + 1;
 		end = text_size(txt);
-		found = start < end && !text_search_range_backward(txt, start, end - start, regex, 1, match, 0);
+		flags = text_byte_get(txt, pos, &c) && c == '\n' ? 0 : REG_NOTBOL;
+		found = start < end && !text_search_range_backward(txt, start, end - start, regex, 1, match, flags);
 	}
 
 	return found ? match[0].start : pos;
diff --git a/text-regex-tre.c b/text-regex-tre.c
@@ -162,6 +162,12 @@ int text_search_range_backward(Text *txt, size_t pos, size_t len, Regex *r, size
 		}
 		pos = next;
 		len = end - pos;
+
+		char c;
+		if (text_byte_get(txt, pos-1, &c) && c == '\n')
+			eflags &= ~REG_NOTBOL;
+		else
+			eflags |= REG_NOTBOL;
 	}
 
 	return ret;
diff --git a/text-regex.c b/text-regex.c
@@ -101,6 +101,10 @@ int text_search_range_backward(Text *txt, size_t pos, size_t len, Regex *r, size
 		}
 		junk = next - cur;
 		cur = next;
+		if (cur[-1] == '\n')
+			eflags &= ~REG_NOTBOL;
+		else
+			eflags |= REG_NOTBOL;
 	}
 	free(buf);
 	return ret;