public static class HtmlHelper {
public static string StripHtmlComments(string html) {
if (html == null) {
throw new ArgumentNullException("html");
}
if (html.IndexOf("<!", StringComparison.Ordinal) < 0) {
return html;
}
var cleanedHtml = new char[html.Length];
bool inHtmlComment = false;
bool inHtmlTag = false;
int cleanCount = 0;
for (int i = 0; i < html.Length; i++) {
char current = html[i];
if (!inHtmlComment && !inHtmlTag) {
if (current == '<') {
if (i + 1 < html.Length) {
char nextChar = html[i + 1];
if (nextChar == '!') {
inHtmlComment = true;
continue;
}
else {
if (IsEnglishLetter(nextChar)) {
inHtmlTag = true;
}
}
}
}
}
else if(inHtmlComment) {
if (current == '>') {
if (inHtmlComment) {
inHtmlComment = false;
continue;
}
}
continue;
}
else if (inHtmlTag) {
if (current == '>') {
inHtmlTag = false;
}
}
cleanedHtml[cleanCount++] = current;
}
return new String(cleanedHtml, 0, cleanCount);
}
private static bool IsEnglishLetter(char nextChar) {
return ('a' <= nextChar && nextChar <= 'z') || ('A' <= nextChar && nextChar <= 'Z');
}
}
//Unit Tests
[TestMethod]
public void NullStringReturnsThrowsArgumentNullException() {
try {
HtmlHelper.StripHtmlComments(null);
Assert.Fail();
}
catch (ArgumentNullException) {
}
}
[TestMethod]
public void EmptyStringReturnsEmpty() {
Assert.AreEqual(string.Empty, HtmlHelper.StripHtmlComments(string.Empty));
}
[TestMethod]
public void StringWithoutCommentReturnsSameString() {
string s = "This has <strong>No Comments</strong>!";
Assert.AreEqual(s, HtmlHelper.StripHtmlComments(s));
}
[TestMethod]
public void StringWithOnlyCommentReturnsEmptyString() {
string s = "<!-- this go bye bye>";
Assert.AreEqual(string.Empty, HtmlHelper.StripHtmlComments(s));
}
[TestMethod]
public void Html_WithNonDashDashComment_ReturnsEmptyString() {
string s = "<! this go bye bye>";
Assert.AreEqual(string.Empty, HtmlHelper.StripHtmlComments(s));
}
[TestMethod]
public void StringWithTwoConsecutiveCommentsReturnsEmptyString() {
string s = "<!-- this go bye bye><!-- another comment>";
Assert.AreEqual(string.Empty, HtmlHelper.StripHtmlComments(s));
}
[TestMethod]
public void CommentWithStringBeforeReturnsString() {
string s = "Hello<!-- this go bye bye -->";
Assert.AreEqual("Hello", HtmlHelper.StripHtmlComments(s));
}
[TestMethod]
public void CommentWithStringAfterReturnsString() {
string s = "<!-- this go bye bye -->World";
Assert.AreEqual("World", HtmlHelper.StripHtmlComments(s));
}
[TestMethod]
public void Html_WithAngleBracketsButNotHtml_NotSripped() {
string s = "<$)*(@&$(@*>";
Assert.AreEqual(s, HtmlHelper.StripHtmlComments(s));
}
[TestMethod]
public void Html_WithCommentInterleavedWithText_RendersText() {
string s = "Hello <!-- this go bye bye --> World <!--> This is fun";
Assert.AreEqual("Hello World This is fun", HtmlHelper.StripHtmlComments(s));
}
[TestMethod]
public void Html_WithHtmlTags_DoesNotStripHtml() {
string s = "<strong>Hello</strong><!this go bye bye>";
Assert.AreEqual("<strong>Hello</strong>", HtmlHelper.StripHtmlComments(s));
}
[TestMethod]
public void Html_WithCommentInAttribute_DoesNotStripAttributeValue() {
string s = "<img alt=\"<!-- This should remain -->\" />";
Assert.AreEqual(s, HtmlHelper.StripHtmlComments(s));
}
[TestMethod]
public void Html_WithCommentInSingleQuotedAttribute_DoesNotStripAttributeValue() {
string s = "<img alt=\'<!-- This should remain -->\' />";
Assert.AreEqual(s, HtmlHelper.StripHtmlComments(s));
}
[TestMethod]
public void Html_WithCommentInNonQuotedAttribute_DoesNotStripAttributeValue() {
string s = "<p title=<!--Thisshouldremain-->Test</p>";
Assert.AreEqual(s, HtmlHelper.StripHtmlComments(s));
}
[TestMethod]
public void Html_WithCommentBetweenNonTagButLooksLikeTag_DoesStripComment() {
string s = @"<ç123 title=""<!bc def>"">";
Assert.AreEqual(@"<ç123 title="""">", HtmlHelper.StripHtmlComments(s));
}
Procedural style code to strip HTML comments. No attempt was made to make this code more OO/patterned base so it could be readable/maintainable. ;)
2008-11-11T01:14:04+00:00
597
C#
strip-html-comments
4
Strip Html Comments
2010-02-03T01:50:47+00:00
1151
public static class HtmlHelper {
public static string StripHtmlComments(string html) {
if (html == null) {
throw new ArgumentNullException("html");
}
System.Text.RegularExpressions.Regex regex =
new System.Text.RegularExpressions.Regex("((<!-- )((?!<!-- ).)*( -->))");
return regex.Replace(html, string.Empty);
}
}
597
haven't tested -- but if it doesn't work it'll just be a case of reviewing the regex
2008-11-11T04:52:44+00:00
67280
C#
4
1
On Strip Html Comments
309
Elij
public static class HtmlHelper
{
public static string StripHtmlComments(string pHtml)
{
if (pHtml == null)
throw new ArgumentNullException("pHtml");
// Contains cleaned content
StringBuilder oSb = new StringBuilder();
// Not comment --> skip
if (pHtml.IndexOf("<!", StringComparison.Ordinal) < 0)
oSb.Append(pHtml);
// Not comment --> skip
if (oSb.Length == 0)
{
bool InHtmlComment = false;
bool InHtmlTag = false;
char CurrentChar;
char NextChar;
for (int CharIndex = 0; CharIndex < pHtml.Length; CharIndex++)
{
CurrentChar = pHtml[CharIndex];
if (!InHtmlComment && !InHtmlTag)
{
if (CurrentChar == '<' && (CharIndex + 1 < pHtml.Length))
{
NextChar = pHtml[CharIndex + 1];
if (NextChar == '!')
{
InHtmlComment = true;
continue;
}
else if (NextChar.IsEnglishLetter())
InHtmlTag = true;
}
}
else if (InHtmlComment)
{
if (CurrentChar == '>')
{
if (InHtmlComment)
{
InHtmlComment = false;
continue;
}
}
continue;
}
else if (InHtmlTag && CurrentChar == '>')
InHtmlTag = false;
oSb.Append(CurrentChar);
}
}
// One entry point, one return point
return oSb.ToString();
}
private static bool IsEnglishLetter(this char nextChar)
{
return ('a' <= nextChar && nextChar <= 'z') || ('A' <= nextChar && nextChar <= 'Z');
}
}
597
I ran the test unit on the regex : 7/15 passed. If you still want to do it with a loop I've cleaned your code a little. I can take a look tomorrow too. I'm too tired to think tonight :)
2008-11-11T05:14:22+00:00
67296
C#
0
0
On Strip Html Comments
1025
Moonshield
www.analystik.ca
public static string StripHtmlComments(string html)
{
if (html == null)
{
throw new ArgumentNullException("html");
}
if (html.IndexOf("<!", StringComparison.Ordinal) < 0)
{
return html;
}
return Regex.Replace(html, "(?<!='|=\"|=)<![^>]+>", "");
}
597
That "invalid HTML tag" case is really tough, a real edge condition. If you discard that one, it's pretty easy. I'd recommend doing a first pass to remove all invalid HTML tags, first. Like.. er.. <ç123>.
2009-11-16T04:25:38+00:00
361815
C#
0
0
On Strip Html Comments
648
Jeff Atwood
http://www.codinghorror.com/blog/