87: The HtmlParser should preserve the Ideographic (CJK) Space (U+3000)

Task-Url: #87
eclipse-mylyn · May 2, 2023 · b5ab9d7 · b5ab9d7
1 parent 5ae90cc
commit b5ab9d7
Show file tree

Hide file tree

Showing 2 changed files with 32 additions and 1 deletion.
diff --git a/.../src/main/java/org/eclipse/mylyn/wikitext/internal/parser/html/AbstractSaxHtmlParser.java b/.../src/main/java/org/eclipse/mylyn/wikitext/internal/parser/html/AbstractSaxHtmlParser.java
@@ -295,7 +295,8 @@ private void append(ElementState elementState, char[] ch, int start, int length)
 				for (int x = 0; x < length; ++x) {
 					int index = start + x;
 					char c = ch[index];
-					if (Character.isWhitespace(c)) {
+					// preserve ideographic whitespace U+3000
+					if (Character.isWhitespace(c) && c != '\u3000') {
 						if (previousWhitespaceIndex == index - 1) {
 							previousWhitespaceIndex = index;
 							continue;

diff --git a/...ikitext/src/test/java/org/eclipse/mylyn/wikitext/internal/parser/html/HtmlParserTest.java b/...ikitext/src/test/java/org/eclipse/mylyn/wikitext/internal/parser/html/HtmlParserTest.java
@@ -245,6 +245,36 @@ public void blockPreformatted() {
 		assertParse("<pre>some\ncode</pre>", "<body><pre>some\ncode</pre></body>");
 	}
 
+	@Test
+	public void paragraphWithSpacePreserved() {
+		assertParse("<p>foo bar</p>", "<body><p>foo bar</p></body>");
+	}
+
+	@Test
+	public void preformattedWithSpacePreserved() {
+		assertParse("<pre>foo bar</pre>", "<body><pre>foo bar</pre></body>");
+	}
+
+	@Test
+	public void paragraphWithExtraSpacesCollapsed() {
+		assertParse("<p>foo bar</p>", "<body><p>foo  bar</p></body>");
+	}
+
+	@Test
+	public void preformattedWithExtraSpacesPreserved() {
+		assertParse("<pre>foo  bar</pre>", "<body><pre>foo  bar</pre></body>");
+	}
+
+	@Test
+	public void paragraphWithIdeographicSpacePreserved() {
+		assertParse("<p>foo　bar</p>", "<body><p>foo　bar</p></body>");
+	}
+
+	@Test
+	public void preformattedWithIdeographicSpacePreserved() {
+		assertParse("<pre>foo　bar</pre>", "<body><pre>foo　bar</pre></body>");
+	}
+
 	private void assertParse(String expected, String content) {
 		StringWriter out = new StringWriter();
 		DocumentBuilder builder = new HtmlDocumentBuilder(out);