Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 10 of 96 for directive (1.14 sec)

  1. fess-crawler/src/main/java/org/codelibs/fess/crawler/entity/RobotsTxt.java

         */
        public int getCrawlDelay(final String userAgent) {
            final Directive directive = getMatchedDirective(userAgent);
            if (directive == null) {
                return 0;
            }
            return directive.getCrawlDelay();
        }
    
        /**
         * Returns the most specific directive matching the given user agent.
         * The method finds the longest matching user agent pattern in the directives,
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Mon Nov 24 03:59:47 UTC 2025
    - 18.5K bytes
    - Viewed (0)
  2. fess-crawler/src/test/java/org/codelibs/fess/crawler/entity/RobotsTxtTest.java

            Directive directive = new Directive("MyBot");
    
            assertNotNull(directive);
            assertEquals("MyBot", directive.getUserAgent());
            assertEquals(0, directive.getCrawlDelay());
        }
    
        public void test_directiveCrawlDelay() {
            // Test Directive crawl delay
            Directive directive = new Directive("MyBot");
    
            directive.setCrawlDelay(10);
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Thu Nov 13 13:29:22 UTC 2025
    - 14.4K bytes
    - Viewed (0)
  3. fess-crawler/src/main/java/org/codelibs/fess/crawler/helper/RobotsTxtHelper.java

                                for (final Directive directive : currentDirectiveList) {
                                    directive.addAllow(value);
                                }
                            }
                            continue;
                        }
    
                        // Try to parse as Crawl-delay directive
                        value = getValue(CRAWL_DELAY_RECORD, line);
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Fri Nov 14 12:52:01 UTC 2025
    - 11.4K bytes
    - Viewed (0)
  4. api/go1.26.txt

    pkg go/ast, func ParseDirective(token.Pos, string) (Directive, bool) #68021
    pkg go/ast, method (*Directive) End() token.Pos #68021
    pkg go/ast, method (*Directive) ParseArgs() ([]DirectiveArg, error) #68021
    pkg go/ast, method (*Directive) Pos() token.Pos #68021
    pkg go/ast, type BasicLit struct, ValueEnd token.Pos #76031
    pkg go/ast, type Directive struct #68021
    pkg go/ast, type Directive struct, Args string #68021
    Registered: Tue Dec 30 11:13:12 UTC 2025
    - Last Modified: Thu Dec 11 19:57:52 UTC 2025
    - 11.5K bytes
    - Viewed (0)
  5. doc/asm.html

    </p>
    
    <p>
    Global data symbols are defined by a sequence of initializing
    <code>DATA</code> directives followed by a <code>GLOBL</code> directive.
    Each <code>DATA</code> directive initializes a section of the
    corresponding memory.
    The memory not explicitly initialized is zeroed.
    The general form of the <code>DATA</code> directive is
    
    <pre>
    DATA	symbol+offset(SB)/width, value
    </pre>
    
    <p>
    Registered: Tue Dec 30 11:13:12 UTC 2025
    - Last Modified: Fri Nov 14 19:09:46 UTC 2025
    - 36.5K bytes
    - Viewed (0)
  6. src/cmd/asm/internal/lex/input.go

    func (in *Input) enabled() bool {
    	return len(in.ifdefStack) == 0 || in.ifdefStack[len(in.ifdefStack)-1]
    }
    
    func (in *Input) expectNewline(directive string) {
    	tok := in.Stack.Next()
    	if tok != '\n' {
    		in.expectText("expected newline after", directive)
    	}
    }
    
    func (in *Input) Next() ScanToken {
    	if in.peek {
    		in.peek = false
    		tok := in.peekToken
    		in.text = in.peekText
    		return tok
    	}
    Registered: Tue Dec 30 11:13:12 UTC 2025
    - Last Modified: Wed Nov 12 03:59:40 UTC 2025
    - 12.4K bytes
    - Viewed (0)
  7. fess-crawler/src/test/resources/org/codelibs/fess/crawler/helper/robots_malformed.txt

    # Test file for malformed robots.txt parsing
    # This file contains various malformed directives that should be handled gracefully
    
    # Case 1: Directives before any User-agent (should be ignored)
    Disallow: /orphaned1/
    Allow: /orphaned2/
    
    # Case 2: Valid user-agent with various malformed directives
    User-agent: GoodBot
    Disallow: /admin/
    InvalidDirective: some-value
    unknown-field: test
    Disallow /missing-colon
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Fri Nov 14 12:52:01 UTC 2025
    - 2.6K bytes
    - Viewed (0)
  8. fess-crawler/src/main/java/org/codelibs/fess/crawler/client/http/HcHttpClient.java

                            }
    
                            final RobotsTxt.Directive directive = robotsTxt.getMatchedDirective(userAgent);
                            if (directive != null) {
                                if (useRobotsTxtDisallows) {
                                    for (String urlPattern : directive.getDisallows()) {
                                        if (StringUtil.isNotBlank(urlPattern)) {
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sun Nov 23 12:19:14 UTC 2025
    - 53.7K bytes
    - Viewed (0)
  9. doc/godebug.md

    Only the work module's `go.mod` is consulted for `godebug` directives.
    Any directives in required dependency modules are ignored.
    It is an error to list a `godebug` with an unrecognized setting.
    (Toolchains older than Go 1.23 reject all `godebug` lines, since they do not
    understand `godebug` at all.) When a workspace is in use, `godebug`
    directives in `go.mod` files are ignored, and `go.work` will be consulted
    Registered: Tue Dec 30 11:13:12 UTC 2025
    - Last Modified: Wed Dec 03 00:18:09 UTC 2025
    - 24.7K bytes
    - Viewed (0)
  10. fess-crawler/src/test/java/org/codelibs/fess/crawler/helper/RobotsTxtHelperTest.java

            assertNotNull(robotsTxt);
    
            // Test that orphaned directives (before any User-agent) are ignored
            // These should not affect any bot
            assertTrue(robotsTxt.allows("/orphaned1/", "AnyBot"));
            assertTrue(robotsTxt.allows("/orphaned2/", "AnyBot"));
    
            // Test GoodBot - should parse valid directives and ignore invalid ones
            assertNotNull(robotsTxt.getDirective("goodbot"));
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Mon Nov 24 03:59:47 UTC 2025
    - 20.6K bytes
    - Viewed (0)
Back to top