fix #2699 add dc:title

This commit is contained in:
Shinsuke Sugaya 2022-12-15 10:11:49 +09:00
parent 6f4d8a9f5c
commit 37edba8802
2 changed files with 4 additions and 1 deletions

View file

@ -390,6 +390,7 @@ public interface FessConfig extends FessEnv, org.codelibs.fess.mylasta.direction
/** The key of the configuration. e.g. title=title:string<br>
* Title=title:string<br>
* dc:title=title:string<br>
* */
String CRAWLER_METADATA_NAME_MAPPING = "crawler.metadata.name.mapping";
@ -2857,6 +2858,7 @@ public interface FessConfig extends FessEnv, org.codelibs.fess.mylasta.direction
* Get the value for the key 'crawler.metadata.name.mapping'. <br>
* The value is, e.g. title=title:string<br>
* Title=title:string<br>
* dc:title=title:string<br>
* <br>
* @return The value of found property. (NotNull: if not found, exception but basically no way)
*/
@ -10538,7 +10540,7 @@ public interface FessConfig extends FessEnv, org.codelibs.fess.mylasta.direction
defaultMap.put(FessConfig.CRAWLER_HOTTHREAD_TYPE, "cpu");
defaultMap.put(FessConfig.CRAWLER_METADATA_CONTENT_EXCLUDES,
"resourceName,X-Parsed-By,Content-Encoding.*,Content-Type.*,X-TIKA.*");
defaultMap.put(FessConfig.CRAWLER_METADATA_NAME_MAPPING, "title=title:string\nTitle=title:string\n");
defaultMap.put(FessConfig.CRAWLER_METADATA_NAME_MAPPING, "title=title:string\nTitle=title:string\ndc:title=title:string\n");
defaultMap.put(FessConfig.CRAWLER_DOCUMENT_HTML_CONTENT_XPATH, "//BODY");
defaultMap.put(FessConfig.CRAWLER_DOCUMENT_HTML_LANG_XPATH, "//HTML/@lang");
defaultMap.put(FessConfig.CRAWLER_DOCUMENT_HTML_DIGEST_XPATH, "//META[@name='description']/@content");

View file

@ -229,6 +229,7 @@ crawler.metadata.content.excludes=resourceName,X-Parsed-By,Content-Encoding.*,Co
crawler.metadata.name.mapping=\
title=title:string\n\
Title=title:string\n\
dc:title=title:string\n\
# html
crawler.document.html.content.xpath=//BODY