01: // plasmaCrawlEURL.java
02: // (C) 2004 by Michael Peter Christen; mc@anomic.de, Frankfurt a. M., Germany
03: // first published 09.08.2004 on http://www.anomic.de
04: //
05: // This is a part of YaCy, a peer-to-peer based web search engine
06: //
07: // $LastChangedDate: 2006-04-02 22:40:07 +0200 (So, 02 Apr 2006) $
08: // $LastChangedRevision: 1986 $
09: // $LastChangedBy: orbiter $
10: //
11: // LICENSE
12: //
13: // This program is free software; you can redistribute it and/or modify
14: // it under the terms of the GNU General Public License as published by
15: // the Free Software Foundation; either version 2 of the License, or
16: // (at your option) any later version.
17: //
18: // This program is distributed in the hope that it will be useful,
19: // but WITHOUT ANY WARRANTY; without even the implied warranty of
20: // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
21: // GNU General Public License for more details.
22: //
23: // You should have received a copy of the GNU General Public License
24: // along with this program; if not, write to the Free Software
25: // Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
26:
27: package de.anomic.plasma;
28:
29: public class plasmaCrawlEURL {
30:
31: /* =======================================================================
32: * Failure reason constants
33: * ======================================================================= */
34:
35: // invalid urls
36: public static final String DENIED_URL_NULL = "denied_(url_null)";
37: public static final String DENIED_MALFORMED_URL = "denied_(malformed_url)";
38: public static final String DENIED_UNSUPPORTED_PROTOCOL = "denied_(unsupported_protocol)";
39: public static final String DENIED_IP_ADDRESS_NOT_IN_DECLARED_DOMAIN = "denied_(address_not_in_declared_domain)";
40: public static final String DENIED_LOOPBACK_IP_ADDRESS = "denied_(loopback_ip_address)";
41: public static final String DENIED_CACHEFILE_PATH_TOO_LONG = "denied_(cachefile_path_too_long)";
42: public static final String DENIED_INVALID_CACHEFILE_PATH = "denied_(invalid_cachefile_path)";
43:
44: // blacklisted/blocked urls
45: public static final String DENIED_URL_IN_BLACKLIST = "denied_(url_in_blacklist)";
46: public static final String DENIED_URL_DOES_NOT_MATCH_FILTER = "denied_(does_not_match_filter)";
47: public static final String DENIED_CGI_URL = "denied_(cgi_url)";
48: public static final String DENIED_POST_URL = "denied_(post_url)";
49: public static final String DENIED_NO_MATCH_WITH_DOMAIN_FILTER = "denied_(no_match_with_domain_filter)";
50: public static final String DENIED_DOMAIN_COUNT_EXCEEDED = "denied_(domain_count_exceeded)";
51: public static final String DENIED_ROBOTS_TXT = "denied_(robots.txt)";
52:
53: // wrong content
54: public static final String DENIED_WRONG_MIMETYPE_OR_EXT = "denied_(wrong_mimetype_or_extension)";
55: public static final String DENIED_UNSUPPORTED_CHARSET = "denied_(unsupported_charset)";
56: public static final String DENIED_REDIRECTION_HEADER_EMPTY = "denied_(redirection_header_empty)";
57: public static final String DENIED_REDIRECTION_COUNTER_EXCEEDED = "denied_(redirection_counter_exceeded)";
58: public static final String DENIED_REDIRECTION_TO_DOUBLE_CONTENT = "denied_(redirection_to_double_content)";
59: public static final String DENIED_WRONG_HTTP_STATUSCODE = "denied_(wrong_http_status_code_";
60: public static final String DENIED_CONTENT_DECODING_ERROR = "denied_(content_decoding_error)";
61: public static final String DENIED_FILESIZE_LIMIT_EXCEEDED = "denied_(filesize_limit_exceeded)";
62: public static final String DENIED_FILESIZE_UNKNOWN = "denied_(filesize_unknown)";
63:
64: // network errors
65: public static final String DENIED_UNKNOWN_HOST = "denied_(unknown_host)";
66: public static final String DENIED_NO_ROUTE_TO_HOST = "denied_(no_route_to_host)";
67: public static final String DENIED_NETWORK_IS_UNREACHABLE = "denied_(Network_is_unreachable)";
68:
69: // connection errors
70: public static final String DENIED_CONNECTION_ERROR = "denied_(connection_error)";
71: public static final String DENIED_CONNECTION_BIND_EXCEPTION = "denied_(connection_bind_exception)";
72: public static final String DENIED_CONNECTION_TIMEOUT = "denied_(connection_timeout)";
73: public static final String DENIED_CONNECTION_REFUSED = "denied_(connection_refused)";
74: public static final String DENIED_SSL_UNTRUSTED_CERT = "denied_(No_trusted_ssl_certificate_found)";
75:
76: // double registered errors
77: public static final String DOUBLE_REGISTERED = "double_(registered_in_";
78:
79: // server errors
80: public static final String DENIED_OUT_OF_DISK_SPACE = "denied_(out_of_disk_space)";
81: public static final String DENIED_SERVER_SHUTDOWN = "denied_(server_shutdown)";
82: public static final String DENIED_SERVER_LOGIN_FAILED = "denied_(server_login_failed)";
83: public static final String DENIED_SERVER_TRASFER_MODE_PROBLEM = "denied_(server_transfermode_problem)";
84: public static final String DENIED_SERVER_DOWNLOAD_ERROR = "denied_(server_download_error)";
85:
86: // Parser errors
87: public static final String DENIED_PARSER_ERROR = "denied_(parser_error)";
88: public static final String DENIED_DOCUMENT_ENCRYPTED = "denied_(document_encrypted)";
89: public static final String DENIED_NOT_PARSEABLE_NO_CONTENT = "denied_(not_parseabel_no_content)";
90:
91: // indexing errors
92: public static final String DENIED_UNSPECIFIED_INDEXING_ERROR = "denied_(unspecified_indexing_error)";
93: public static final String DENIED_UNKNOWN_INDEXING_PROCESS_CASE = "denied_(unknown_indexing_process_case)";
94:
95: }
|