From f173925dc0791a4b62fbf305464f0192096d4d5e Mon Sep 17 00:00:00 2001 From: Magese Date: Fri, 31 Dec 2021 17:17:47 +0800 Subject: [PATCH] =?UTF-8?q?=E4=BC=98=E5=8C=96=E8=AF=8D=E5=89=8D=E7=BD=AE?= =?UTF-8?q?=E5=88=A4=E6=96=AD=E9=80=BB=E8=BE=91=EF=BC=9B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .../java/org/wltea/analyzer/core/CJKSegmenter.java | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/src/main/java/org/wltea/analyzer/core/CJKSegmenter.java b/src/main/java/org/wltea/analyzer/core/CJKSegmenter.java index 83818d0..3689a97 100644 --- a/src/main/java/org/wltea/analyzer/core/CJKSegmenter.java +++ b/src/main/java/org/wltea/analyzer/core/CJKSegmenter.java @@ -80,17 +80,16 @@ class CJKSegmenter implements ISegmenter { // ********************************* // 再对当前指针位置的字符进行单字匹配 Hit singleCharHit = Dictionary.getSingleton().matchInMainDict(context.getSegmentBuff(), context.getCursor(), 1); - if (singleCharHit.isMatch()) {// 首字成词 + + // 首字为词前缀 + if (singleCharHit.isMatch()) { // 输出当前的词 Lexeme newLexeme = new Lexeme(context.getBufferOffset(), context.getCursor(), 1, Lexeme.TYPE_CNWORD); context.addLexeme(newLexeme); + } - // 同时也是词前缀 - if (singleCharHit.isPrefix()) { - // 前缀匹配则放入hit列表 - this.tmpHits.add(singleCharHit); - } - } else if (singleCharHit.isPrefix()) {// 首字为词前缀 + // 前缀匹配则放入hit列表 + if (singleCharHit.isPrefix()) { // 前缀匹配则放入hit列表 this.tmpHits.add(singleCharHit); }