This is an automated email from the ASF dual-hosted git repository.
snoopdave pushed a commit to branch roller-6.1.x
in repository https://gitbox.apache.org/repos/asf/roller.git
The following commit(s) were added to refs/heads/roller-6.1.x by this push:
new a8d5ece82 Drop an unclosed tag in removeHTML and print the weblog
description as text on the main menu (#228)
a8d5ece82 is described below
commit a8d5ece82591c2c62404534f1543df3f8bcf943f
Author: David M. Johnson <[email protected]>
AuthorDate: Thu Oct 29 17:19:39 2026 -0400
Drop an unclosed tag in removeHTML and print the weblog description as text
on the main menu (#228)
* Drop an unclosed tag in removeHTML and print the weblog description as
text on the main menu
* Keep scanning after a less-than sign that is text in removeHTML; note the
change in CHANGES.md
* Keep text such as x<y in removeHTML; drop only unclosed tags with
attributes
Claude-Session: https://claude.ai/code/session_01C5X1Z1eoSH7o25gZskPGzb
---
CHANGES.md | 6 +++
.../apache/roller/weblogger/util/Utilities.java | 59 +++++++++++++++++++---
app/src/main/webapp/WEB-INF/jsps/core/MainMenu.jsp | 2 +-
.../roller/weblogger/util/UtilitiesTest.java | 37 ++++++++++++++
4 files changed, 95 insertions(+), 9 deletions(-)
diff --git a/CHANGES.md b/CHANGES.md
index 7fc107bd1..c0070846e 100644
--- a/CHANGES.md
+++ b/CHANGES.md
@@ -58,6 +58,12 @@
- **Startup fails if the XML-RPC parser cannot be configured.** Roller used to
log an error and continue. It now stops at startup, so check the log if a
custom XML parser is on the classpath.
+- **Text with an unclosed tag loses the tag.** Where Roller strips HTML from
+ plain-text fields (for example a weblog's description), a tag with attributes
+ and no closing `>`, such as `text <img src=x`, is now dropped. Other text
with
+ a `<`, as in `a < b`, `x<y` or `C<C++ fans`, is kept, and no longer gets a
+ space added before the `<`. The Your Weblogs page shows a weblog's
+ description as text.
### Bug fixes
diff --git a/app/src/main/java/org/apache/roller/weblogger/util/Utilities.java
b/app/src/main/java/org/apache/roller/weblogger/util/Utilities.java
index f8a74602c..643c7834c 100644
--- a/app/src/main/java/org/apache/roller/weblogger/util/Utilities.java
+++ b/app/src/main/java/org/apache/roller/weblogger/util/Utilities.java
@@ -170,23 +170,32 @@ public class Utilities {
while (beginTag >= start) {
if (beginTag > 0) {
ret.append(str.substring(start, beginTag));
-
- // replace each tag with a space (looks better)
- if (addSpace) {
- ret.append(" ");
- }
}
endTag = str.indexOf('>', beginTag);
// if endTag found move "cursor" forward
if (endTag > -1) {
+ // replace each tag with a space (looks better)
+ if (addSpace && beginTag > 0) {
+ ret.append(" ");
+ }
start = endTag + 1;
beginTag = str.indexOf('<', start);
}
- // if no endTag found, get rest of str and break
+ // if no endTag found, drop the rest if this '<' starts a tag,
+ // which a browser would still parse as markup; otherwise keep the
+ // '<' as text and look at the next one
else {
- ret.append(str.substring(beginTag));
- break;
+ if (startsTag(str, beginTag)) {
+ break;
+ }
+ ret.append('<');
+ start = beginTag + 1;
+ beginTag = str.indexOf('<', start);
+ if (beginTag == -1) {
+ ret.append(str.substring(start));
+ break;
+ }
}
}
// append everything after the last endTag
@@ -196,6 +205,40 @@ public class Utilities {
return ret.toString().trim();
}
+ /**
+ * True if the unclosed '<' at the given index opens a comment, a
+ * declaration, an end tag, or a tag with attributes: a tag name, then
+ * whitespace or '/', and an '=' later on. Text such as "x<y" or
+ * "a<b and b<c" is not a tag.
+ */
+ private static boolean startsTag(String str, int index) {
+ int i = index + 1;
+ if (i >= str.length()) {
+ return false;
+ }
+ char next = str.charAt(i);
+ if (next == '/' || next == '!' || next == '?') {
+ return true;
+ }
+ if (!isAsciiLetter(next)) {
+ return false;
+ }
+ while (i < str.length() && (isAsciiLetter(str.charAt(i))
+ || Character.isDigit(str.charAt(i)) || str.charAt(i) == '-')) {
+ i++;
+ }
+ if (i >= str.length()) {
+ return false;
+ }
+ char after = str.charAt(i);
+ return (Character.isWhitespace(after) || after == '/')
+ && str.indexOf('=', i) > -1;
+ }
+
+ private static boolean isAsciiLetter(char c) {
+ return (c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z');
+ }
+
// ------------------------------------------------------------------------
/**
* Run both removeHTML and escapeHTML on a string.
diff --git a/app/src/main/webapp/WEB-INF/jsps/core/MainMenu.jsp
b/app/src/main/webapp/WEB-INF/jsps/core/MainMenu.jsp
index d81dce008..c90f69006 100644
--- a/app/src/main/webapp/WEB-INF/jsps/core/MainMenu.jsp
+++ b/app/src/main/webapp/WEB-INF/jsps/core/MainMenu.jsp
@@ -71,7 +71,7 @@
<p> <a href='<s:property value="#perms.weblog.absoluteURL" />'>
<s:property value="#perms.weblog.absoluteURL" /></a></p>
- <p><s:property value="#perms.weblog.about" escapeHtml="false"
/></p>
+ <p><s:property value="#perms.weblog.about" /></p>
<p>You have
<s:if test='#perms.hasAction("admin")'>ADMIN </s:if>
diff --git
a/app/src/test/java/org/apache/roller/weblogger/util/UtilitiesTest.java
b/app/src/test/java/org/apache/roller/weblogger/util/UtilitiesTest.java
index 7e008aeb2..2ab81ecdf 100644
--- a/app/src/test/java/org/apache/roller/weblogger/util/UtilitiesTest.java
+++ b/app/src/test/java/org/apache/roller/weblogger/util/UtilitiesTest.java
@@ -99,6 +99,43 @@ public class UtilitiesTest {
assertEquals(expect, result);
}
+ @Test
+ public void testRemoveHTMLUnclosedTag() {
+ assertEquals("about", Utilities.removeHTML("about <img src=x", false));
+ assertEquals("about", Utilities.removeHTML("about <p>", false).trim());
+ assertEquals("a", Utilities.removeHTML("a </p", false));
+ assertEquals("a", Utilities.removeHTML("a <!-- note", false));
+ assertEquals("", Utilities.removeHTML("<img src=x", false));
+ }
+
+ @Test
+ public void testRemoveHTMLKeepsLessThanText() {
+ assertEquals("a < b", Utilities.removeHTML("a < b", false));
+ assertEquals("1 <2", Utilities.removeHTML("1 <2", false));
+ assertEquals("x <", Utilities.removeHTML("x <", false));
+ assertEquals("x<y", Utilities.removeHTML("x<y", false));
+ assertEquals("List<String", Utilities.removeHTML("List<String",
false));
+ assertEquals("C<C++ fans", Utilities.removeHTML("C<C++ fans", false));
+ assertEquals("a<b and b<c", Utilities.removeHTML("a<b and b<c",
false));
+ }
+
+ @Test
+ public void testRemoveHTMLDefaultAddsSpaceOnlyForTags() {
+ assertEquals("about", Utilities.removeHTML("about <img src=x"));
+ assertEquals("about", Utilities.removeHTML("about<img/src=x"));
+ assertEquals("x<y", Utilities.removeHTML("x<y"));
+ assertEquals("C<C++ fans", Utilities.removeHTML("C<C++ fans"));
+ assertEquals("a < b", Utilities.removeHTML("a < b"));
+ assertEquals("a b", Utilities.removeHTML("a<br>b"));
+ }
+
+ @Test
+ public void testRemoveHTMLUnclosedTagAfterLessThanText() {
+ assertEquals("a < b", Utilities.removeHTML("a < b <img src=x", false));
+ assertEquals("a < b < c", Utilities.removeHTML("a < b < c", false));
+ assertEquals("1 <2 <3", Utilities.removeHTML("1 <2 <3", false));
+ }
+
@Test
public void testTruncateNicely1() {
String test = "blah blah blah blah blah";