From 5043f7ed8c9d238c19cfc61d3b5bae25adc795c8 Mon Sep 17 00:00:00 2001 From: zjwave <594980947@qq.com> Date: Sat, 16 Feb 2019 18:28:50 +0800 Subject: [PATCH 1/6] default add --- .../module/article/service/search/ArticleSearcherFactory.java | 1 + 1 file changed, 1 insertion(+) diff --git a/module-article/module-article-service-provider/src/main/java/io/jpress/module/article/service/search/ArticleSearcherFactory.java b/module-article/module-article-service-provider/src/main/java/io/jpress/module/article/service/search/ArticleSearcherFactory.java index 075dcd2ea..703dc4daa 100644 --- a/module-article/module-article-service-provider/src/main/java/io/jpress/module/article/service/search/ArticleSearcherFactory.java +++ b/module-article/module-article-service-provider/src/main/java/io/jpress/module/article/service/search/ArticleSearcherFactory.java @@ -48,6 +48,7 @@ public class ArticleSearcherFactory { return Aop.get(ElasticSearcher.class); case "aliopensearch": return Aop.get(AliyunOpenSearcher.class); + default: } ArticleSearcher searcher = JbootSpiLoader.load(ArticleSearcher.class, engine); -- Gitee From 2a649b9c8ce6efc9b3dce82ce660e242afdf7a80 Mon Sep 17 00:00:00 2001 From: zjwave <594980947@qq.com> Date: Sat, 16 Feb 2019 21:54:38 +0800 Subject: [PATCH 2/6] default add --- .../io/jpress/commons/utils/CommonsUtils.java | 7 +++ .../jpress/module/article/model/Article.java | 20 +++++++++ .../service/search/ArticleSearcher.java | 2 + .../article/searcher/LuceneSearcher.java | 37 +++++++++++++--- starter/src/main/resources/undertow.txt | 43 +++++++++++++++++++ 5 files changed, 103 insertions(+), 6 deletions(-) create mode 100644 starter/src/main/resources/undertow.txt diff --git a/jpress-commons/src/main/java/io/jpress/commons/utils/CommonsUtils.java b/jpress-commons/src/main/java/io/jpress/commons/utils/CommonsUtils.java index 30bc41dbd..d2ee64a51 100644 --- a/jpress-commons/src/main/java/io/jpress/commons/utils/CommonsUtils.java +++ b/jpress-commons/src/main/java/io/jpress/commons/utils/CommonsUtils.java @@ -146,6 +146,13 @@ public class CommonsUtils { .replace("&", "&"); } + public static String removeHtmlTag(String content) { + if (StrUtil.isBlank(content)) { + return content; + } + return content.replaceAll("<[^>]*>", ""); + } + public static void main(String[] args) { String script = ""; diff --git a/module-article/module-article-model/src/main/java/io/jpress/module/article/model/Article.java b/module-article/module-article-model/src/main/java/io/jpress/module/article/model/Article.java index c2f72f5f6..ae9eef9af 100644 --- a/module-article/module-article-model/src/main/java/io/jpress/module/article/model/Article.java +++ b/module-article/module-article-model/src/main/java/io/jpress/module/article/model/Article.java @@ -38,6 +38,10 @@ public class Article extends BaseArticle
{ public static final String STATUS_TRASH = "trash"; + private String highlightContent; + + private String highlightTitle; + public boolean isNormal() { return STATUS_NORMAL.equals(getStatus()); } @@ -123,6 +127,22 @@ public class Article extends BaseArticle
{ return StrUtil.isNotBlank(thumbnail) ? thumbnail : getFirstImage(); } + public String getHighlightContent() { + return highlightContent; + } + + public void setHighlightContent(String highlightContent) { + this.highlightContent = highlightContent; + } + + public String getHighlightTitle() { + return highlightTitle; + } + + public void setHighlightTitle(String highlightTitle) { + this.highlightTitle = highlightTitle; + } + @Override public boolean save() { CommonsUtils.escapeHtmlForAllAttrs(this, "content"); diff --git a/module-article/module-article-search-api/src/main/java/io/jpress/module/article/service/search/ArticleSearcher.java b/module-article/module-article-search-api/src/main/java/io/jpress/module/article/service/search/ArticleSearcher.java index fce5b1f82..44c945c10 100644 --- a/module-article/module-article-search-api/src/main/java/io/jpress/module/article/service/search/ArticleSearcher.java +++ b/module-article/module-article-search-api/src/main/java/io/jpress/module/article/service/search/ArticleSearcher.java @@ -6,6 +6,8 @@ import io.jpress.module.article.model.Article; public interface ArticleSearcher { + String HIGH_LIGHT_CLASS = "search-highlight"; + public void addArticle(Article article); public void deleteArticle(Object id); diff --git a/module-article/module-article-search-lucene/src/main/java/io/jpress/module/article/searcher/LuceneSearcher.java b/module-article/module-article-search-lucene/src/main/java/io/jpress/module/article/searcher/LuceneSearcher.java index fa9b34847..6ea1b2370 100644 --- a/module-article/module-article-search-lucene/src/main/java/io/jpress/module/article/searcher/LuceneSearcher.java +++ b/module-article/module-article-search-lucene/src/main/java/io/jpress/module/article/searcher/LuceneSearcher.java @@ -16,16 +16,19 @@ package io.jpress.module.article.searcher; import com.jfinal.kit.PathKit; +import com.jfinal.log.Log; import com.jfinal.plugin.activerecord.Page; import io.jpress.commons.utils.CommonsUtils; import io.jpress.module.article.model.Article; import io.jpress.module.article.service.search.ArticleSearcher; import org.apache.lucene.analysis.Analyzer; +import org.apache.lucene.analysis.cjk.CJKAnalyzer; import org.apache.lucene.document.*; import org.apache.lucene.index.*; import org.apache.lucene.queryparser.classic.ParseException; import org.apache.lucene.queryparser.classic.QueryParser; import org.apache.lucene.search.*; +import org.apache.lucene.search.highlight.*; import org.apache.lucene.store.Directory; import org.apache.lucene.store.NIOFSDirectory; import org.lionsoul.jcseg.analyzer.JcsegAnalyzer; @@ -33,12 +36,15 @@ import org.lionsoul.jcseg.tokenizer.core.JcsegTaskConfig; import java.io.File; import java.io.IOException; +import java.io.StringReader; import java.util.ArrayList; import java.util.Date; import java.util.List; public class LuceneSearcher implements ArticleSearcher { + private static final Log logger = Log.getLog(LuceneSearcher.class); + public static String INDEX_PATH = "~/indexes/"; private static Directory directory; @@ -100,9 +106,12 @@ public class LuceneSearcher implements ArticleSearcher { ScoreDoc lastScoreDoc = getLastScoreDoc(pageNum, pageSize, query, indexSearcher); TopDocs topDocs = indexSearcher.searchAfter(lastScoreDoc, query, pageSize); - List
articles = toArticleList(indexSearcher, topDocs); - int totalRow = getTotalRow(indexSearcher, query); + SimpleHTMLFormatter formatter = new SimpleHTMLFormatter("", ""); + Highlighter highlighter=new Highlighter(formatter, new QueryScorer(query)); + highlighter.setTextFragmenter(new SimpleFragmenter(100)); + List
articles = toArticleList(indexSearcher, topDocs,highlighter,keyword); + int totalRow = getTotalRow(indexSearcher, query); return newPage(pageNum, pageSize, totalRow, articles); } catch (IOException e) { e.printStackTrace(); @@ -115,8 +124,9 @@ public class LuceneSearcher implements ArticleSearcher { private static ScoreDoc getLastScoreDoc(int pageIndex, int pageSize, Query query, IndexSearcher indexSearcher) throws IOException { - if (pageIndex == 1) + if (pageIndex == 1){ return null; // 如果是第一页返回空 + } int num = pageSize * (pageIndex - 1); // 获取上一页的数量 TopDocs tds = indexSearcher.search(query, num); return tds.scoreDocs[num - 1]; @@ -188,14 +198,29 @@ public class LuceneSearcher implements ArticleSearcher { } - private List
toArticleList(IndexSearcher searcher, TopDocs topDocs) throws IOException { + private List
toArticleList(IndexSearcher searcher, TopDocs topDocs,Highlighter highlighter,String keyword) throws IOException { List
articles = new ArrayList<>(); + Analyzer luceneAnalyzer = new CJKAnalyzer(); for (ScoreDoc item : topDocs.scoreDocs) { Document doc = searcher.doc(item.doc); Article article = new Article(); + String title = doc.get("title"); + String content = doc.get("content"); article.setId(Long.valueOf(doc.get("aid"))); - article.setTitle(doc.get("title")); - article.setContent(doc.get("content")); + article.setTitle(title); + article.setContent(content); + //关键字高亮 + try { + String highlightTitle = highlighter.getBestFragment(luceneAnalyzer.tokenStream(keyword, new StringReader(title)), title); + article.setHighlightTitle(highlightTitle); + + String plainContent = CommonsUtils.removeHtmlTag(content); + plainContent.replaceAll("\\s*|\t|\r|\n",""); + String highlightContent = highlighter.getBestFragment(luceneAnalyzer.tokenStream(keyword, new StringReader(plainContent)), plainContent); + article.setHighlightContent(highlightContent); + } catch (InvalidTokenOffsetsException e) { + logger.error(e.getMessage(),e); + } articles.add(article); } return articles; diff --git a/starter/src/main/resources/undertow.txt b/starter/src/main/resources/undertow.txt new file mode 100644 index 000000000..c6e1f1e7b --- /dev/null +++ b/starter/src/main/resources/undertow.txt @@ -0,0 +1,43 @@ +# 配置 undertow + +undertow.devMode=true +undertow.host=0.0.0.0 +undertow.port=8080 + +# 开启 gzip 压缩 +undertow.gzip.enable=true +# 配置压缩级别，默认值 -1。 可配置 1 到 9。 1 拥有最快压缩速度，9 拥有最高压缩率 +undertow.gzip.level=-1 +# 触发压缩的最小内容长度 +undertow.gzip.minLength=1024 + + +# 下面两行命令生成密钥库 +# keytool -genkeypair -validity 3650 -alias club -keyalg RSA -keystore club.jks +# keytool -importkeystore -srckeystore club.jks -destkeystore club.pfx -deststoretype PKCS12 +# 生成过程中提示输入 "名字与姓氏" 时输入 localhost。生产环境从阿里云下载 tomcat 类型的密钥库 +# 是否开启 ssl +#undertow.ssl.enable=true +# ssl 监听端口号，部署环境设置为 443 +undertow.ssl.port=443 +# 密钥库类型，建议使用 PKCS12 +undertow.ssl.keyStoreType=PKCS12 +# 密钥库文件 +undertow.ssl.keyStore=club.pfx +# 密钥库密码 +undertow.ssl.keyStorePassword=111111 + + +# ssl 开启时，是否开启 http2。检测该配置是否生效在 chrome 地址栏中输入: chrome://net-internals/#http2 +undertow.http2.enable=true + + +# ssl 开启时，http 请求是否重定向到 https +# undertow.http.toHttps=false +# ssl 开启时，http 请求重定向到 https 使用的状态码 +# undertow.http.toHttpsStatusCode=302 +# ssl 开启时，是否关闭 http +# undertow.http.disable=false + + + -- Gitee From 8573aa0df187085f615b0847383cad527bed9432 Mon Sep 17 00:00:00 2001 From: zjwave <594980947@qq.com> Date: Sat, 16 Feb 2019 22:29:54 +0800 Subject: [PATCH 3/6] rollback --- .../main/java/io/jpress/commons/utils/CommonsUtils.java | 7 ------- 1 file changed, 7 deletions(-) diff --git a/jpress-commons/src/main/java/io/jpress/commons/utils/CommonsUtils.java b/jpress-commons/src/main/java/io/jpress/commons/utils/CommonsUtils.java index d2ee64a51..30bc41dbd 100644 --- a/jpress-commons/src/main/java/io/jpress/commons/utils/CommonsUtils.java +++ b/jpress-commons/src/main/java/io/jpress/commons/utils/CommonsUtils.java @@ -146,13 +146,6 @@ public class CommonsUtils { .replace("&", "&"); } - public static String removeHtmlTag(String content) { - if (StrUtil.isBlank(content)) { - return content; - } - return content.replaceAll("<[^>]*>", ""); - } - public static void main(String[] args) { String script = ""; -- Gitee From e7f055a98282729ee94d2eb0d2f51e5b11ab7049 Mon Sep 17 00:00:00 2001 From: zjwave <594980947@qq.com> Date: Sat, 16 Feb 2019 22:31:38 +0800 Subject: [PATCH 4/6] =?UTF-8?q?=E6=90=9C=E7=B4=A2=E9=AB=98=E4=BA=AE?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .../jpress/module/article/searcher/LuceneSearcher.java | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/module-article/module-article-search-lucene/src/main/java/io/jpress/module/article/searcher/LuceneSearcher.java b/module-article/module-article-search-lucene/src/main/java/io/jpress/module/article/searcher/LuceneSearcher.java index 6ea1b2370..7f522900f 100644 --- a/module-article/module-article-search-lucene/src/main/java/io/jpress/module/article/searcher/LuceneSearcher.java +++ b/module-article/module-article-search-lucene/src/main/java/io/jpress/module/article/searcher/LuceneSearcher.java @@ -19,6 +19,7 @@ import com.jfinal.kit.PathKit; import com.jfinal.log.Log; import com.jfinal.plugin.activerecord.Page; import io.jpress.commons.utils.CommonsUtils; +import io.jpress.commons.utils.JsoupUtils; import io.jpress.module.article.model.Article; import io.jpress.module.article.service.search.ArticleSearcher; import org.apache.lucene.analysis.Analyzer; @@ -200,7 +201,7 @@ public class LuceneSearcher implements ArticleSearcher { private List
toArticleList(IndexSearcher searcher, TopDocs topDocs,Highlighter highlighter,String keyword) throws IOException { List
articles = new ArrayList<>(); - Analyzer luceneAnalyzer = new CJKAnalyzer(); + Analyzer analyzer = new JcsegAnalyzer(JcsegTaskConfig.COMPLEX_MODE); for (ScoreDoc item : topDocs.scoreDocs) { Document doc = searcher.doc(item.doc); Article article = new Article(); @@ -211,12 +212,11 @@ public class LuceneSearcher implements ArticleSearcher { article.setContent(content); //关键字高亮 try { - String highlightTitle = highlighter.getBestFragment(luceneAnalyzer.tokenStream(keyword, new StringReader(title)), title); + String highlightTitle = highlighter.getBestFragment(analyzer.tokenStream(keyword, new StringReader(title)), title); article.setHighlightTitle(highlightTitle); - String plainContent = CommonsUtils.removeHtmlTag(content); - plainContent.replaceAll("\\s*|\t|\r|\n",""); - String highlightContent = highlighter.getBestFragment(luceneAnalyzer.tokenStream(keyword, new StringReader(plainContent)), plainContent); + String plainContent = JsoupUtils.getText(content); + String highlightContent = highlighter.getBestFragment(analyzer.tokenStream(keyword, new StringReader(plainContent)), plainContent); article.setHighlightContent(highlightContent); } catch (InvalidTokenOffsetsException e) { logger.error(e.getMessage(),e); -- Gitee From 672fada3f24e5b6d32a6d8098bad97b0ffbc65cd Mon Sep 17 00:00:00 2001 From: zjwave <594980947@qq.com> Date: Sat, 16 Feb 2019 22:33:20 +0800 Subject: [PATCH 5/6] rollback --- .../java/io/jpress/module/article/searcher/LuceneSearcher.java | 1 - 1 file changed, 1 deletion(-) diff --git a/module-article/module-article-search-lucene/src/main/java/io/jpress/module/article/searcher/LuceneSearcher.java b/module-article/module-article-search-lucene/src/main/java/io/jpress/module/article/searcher/LuceneSearcher.java index 7f522900f..27c73ad0a 100644 --- a/module-article/module-article-search-lucene/src/main/java/io/jpress/module/article/searcher/LuceneSearcher.java +++ b/module-article/module-article-search-lucene/src/main/java/io/jpress/module/article/searcher/LuceneSearcher.java @@ -23,7 +23,6 @@ import io.jpress.commons.utils.JsoupUtils; import io.jpress.module.article.model.Article; import io.jpress.module.article.service.search.ArticleSearcher; import org.apache.lucene.analysis.Analyzer; -import org.apache.lucene.analysis.cjk.CJKAnalyzer; import org.apache.lucene.document.*; import org.apache.lucene.index.*; import org.apache.lucene.queryparser.classic.ParseException; -- Gitee From f7c16423ba10c28373a7074d5657c034e6c8f325 Mon Sep 17 00:00:00 2001 From: zjwave <594980947@qq.com> Date: Sat, 16 Feb 2019 22:54:22 +0800 Subject: [PATCH 6/6] =?UTF-8?q?=E6=90=9C=E7=B4=A2=E9=AB=98=E4=BA=AE?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .../jpress/module/article/searcher/LuceneSearcher.java | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/module-article/module-article-search-lucene/src/main/java/io/jpress/module/article/searcher/LuceneSearcher.java b/module-article/module-article-search-lucene/src/main/java/io/jpress/module/article/searcher/LuceneSearcher.java index 27c73ad0a..19552352b 100644 --- a/module-article/module-article-search-lucene/src/main/java/io/jpress/module/article/searcher/LuceneSearcher.java +++ b/module-article/module-article-search-lucene/src/main/java/io/jpress/module/article/searcher/LuceneSearcher.java @@ -161,6 +161,7 @@ public class LuceneSearcher implements ArticleSearcher { Document doc = new Document(); doc.add(new StringField("aid", article.getId().toString(), Field.Store.YES)); doc.add(new TextField("content", article.getContent(), Field.Store.YES)); + doc.add(new TextField("text", article.getText(), Field.Store.YES)); doc.add(new TextField("title", article.getTitle(), Field.Store.YES)); doc.add(new StringField("created", DateTools.dateToString(article.getCreated() == null ? new Date() : article.getCreated(), DateTools.Resolution.YEAR), Field.Store.NO)); return doc; @@ -177,8 +178,8 @@ public class LuceneSearcher implements ArticleSearcher { try { Analyzer analyzer = new JcsegAnalyzer(JcsegTaskConfig.COMPLEX_MODE); - - QueryParser queryParser1 = new QueryParser("content", analyzer); + //这里使用text，防止搜索出html的tag或者tag中属性 + QueryParser queryParser1 = new QueryParser("text", analyzer); Query termQuery1 = queryParser1.parse(keyword); BooleanClause booleanClause1 = new BooleanClause(termQuery1, BooleanClause.Occur.SHOULD); @@ -213,9 +214,8 @@ public class LuceneSearcher implements ArticleSearcher { try { String highlightTitle = highlighter.getBestFragment(analyzer.tokenStream(keyword, new StringReader(title)), title); article.setHighlightTitle(highlightTitle); - - String plainContent = JsoupUtils.getText(content); - String highlightContent = highlighter.getBestFragment(analyzer.tokenStream(keyword, new StringReader(plainContent)), plainContent); + String text = article.getText(); + String highlightContent = highlighter.getBestFragment(analyzer.tokenStream(keyword, new StringReader(text)), text); article.setHighlightContent(highlightContent); } catch (InvalidTokenOffsetsException e) { logger.error(e.getMessage(),e); -- Gitee