Crawl-delay: 5.5
Crawl-delay:
Allow:    # empty value

# Case 3: Multiple colons in directive
User-agent: MultiColonBot
Disallow: http://example.com:8080/path
Allow: /path:with:colons

# Case 4: Extra whitespace
User-agent:    ExtraSpaceBot
Disallow:     /spaced/
   Allow:   /also-spaced/

# Case 5: Mixed case directives (should still work)
UsEr-AgEnT: MixedCaseBot
DiSaLlOw: /test1/
AlLoW: /test2/
CrAwL-dElAy: 2

- Input stream validation (not consumption)
- Edge cases (long filenames, paths, whitespace)

**Test Count**: 10 tests

**Key Scenarios**:
- ✅ Valid filename extraction
- ✅ Null parameters handling
- ✅ Empty/missing resource name
- ✅ Special characters in filename (Japanese, paths)
- ✅ Input stream not consumed (only validated)
- ✅ Whitespace and empty string handling

---

### 3. ArchiveExtractorErrorHandlingTest.java

# This file contains only comments and whitespace

 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

package com.google.common.io;

import static com.google.common.base.CharMatcher.whitespace;
import static com.google.common.truth.Truth.assertThat;
import static java.nio.charset.StandardCharsets.US_ASCII;
import static java.nio.charset.StandardCharsets.UTF_8;
import static org.junit.Assert.assertThrows;

        final ExtractData result = filenameExtractor.getText(in, params);

        assertNotNull(result);
        assertEquals("", result.getContent());
    }

    /**
     * Test extraction with whitespace-only filename.
     */
    public void test_getText_withWhitespaceFilename() {
        final InputStream in = new ByteArrayInputStream(new byte[0]);
        final Map<String, String> params = new HashMap<>();

        assertEquals(10, item.getQueryFreq());
    }

    @Test
    public void test_parseSearchWordsWithExcludedWords() throws Exception {
        String[] words = new String[] { "　　　", "エンジン" }; // First word is whitespace only
        String[] fields = new String[] { "content" };

        SuggestAnalyzer analyzer = suggester.settings().analyzer().new DefaultContentsAnalyzer();

        assertFalse(robotsTxt.allows("http://example.com:8080/path", "MultiColonBot"));
        assertTrue(robotsTxt.allows("/path:with:colons", "MultiColonBot"));

        // Test ExtraSpaceBot - extra whitespace should be handled
        assertFalse(robotsTxt.allows("/spaced/", "ExtraSpaceBot"));
        assertTrue(robotsTxt.allows("/also-spaced/", "ExtraSpaceBot"));

        // Test MixedCaseBot - mixed case directives should work

        final ExtractData result = textExtractor.getText(in, null);

        assertNotNull(result);
        assertNotNull(result.getContent());
    }

    /**
     * Test extraction with whitespace-only content.
     */
    public void test_getText_whitespaceOnly_extractsAsIs() {
        final String whitespaceContent = "   \t\n\r   ";

    assertEquals(s, xmlEscaper.escape(s));

    // Test ASCII control characters.
    for (char ch = 0; ch < 0x20; ch++) {
      if (ch == '\t' || ch == '\n' || ch == '\r') {
        // Only these whitespace chars are permitted in XML,
        if (shouldEscapeWhitespaceChars) {
          assertEscaping(xmlEscaper, "&#x" + Integer.toHexString(ch).toUpperCase() + ";", ch);
        } else {
          assertUnescaped(xmlEscaper, ch);

 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

package com.google.common.base;

import static com.google.common.base.CharMatcher.whitespace;
import static com.google.common.truth.Truth.assertThat;
import static org.junit.Assert.assertThrows;

import com.google.common.annotations.GwtCompatible;
import com.google.common.annotations.GwtIncompatible;