IK 分词器支持特殊符号、标点符号、驼峰分词

　　从 GitHub 下载对应版本的 IK 分词器源码，修改 CharacterUtil.identifyCharType 方法，将特殊符号、标点符号当做中文进行处理即可。

　　添加：

//驼峰作为分词点 
if (input >= 'A' && input <= 'Z') return CHAR_CHINESE;

　　　　　　　else if (ub == Character.UnicodeBlock.GREEK // 希腊符号
                    // 希腊扩展符号
                    || ub == Character.UnicodeBlock.GREEK_EXTENDED
                    // 拉丁字符
                    || ub == Character.UnicodeBlock.BASIC_LATIN
                    // 拉丁补充字符
                    || ub == Character.UnicodeBlock.LATIN_1_SUPPLEMENT
                    // 拉丁扩展A字符
                    || ub == Character.UnicodeBlock.LATIN_EXTENDED_A
                    // 拉丁扩展B字符
                    || ub == Character.UnicodeBlock.LATIN_EXTENDED_B) {
                return CHAR_CHINESE;
            } else if (ub == Character.UnicodeBlock.GENERAL_PUNCTUATION
                    || ub == Character.UnicodeBlock.CJK_SYMBOLS_AND_PUNCTUATION
                    || ub == Character.UnicodeBlock.HALFWIDTH_AND_FULLWIDTH_FORMS
                    || ub == Character.UnicodeBlock.CJK_COMPATIBILITY_FORMS
                    || ub == Character.UnicodeBlock.VERTICAL_FORMS) {
                // 标点符号
                return CHAR_CHINESE;
            }

　　完整的 CharacterUtil.identifyCharType 方法：

static int identifyCharType(char input) {
    if (input >= '0' && input <= '9') {
        return CHAR_ARABIC;
    } else if ((input >= 'a' && input <= 'z')
            || (input >= 'A' && input <= 'Z')) {
        // 驼峰作为分词点
        if (input >= 'A' && input <= 'Z') return CHAR_CHINESE;
        else return CHAR_ENGLISH;
    } else {
        Character.UnicodeBlock ub = Character.UnicodeBlock.of(input);
        if (ub == Character.UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS
                || ub == Character.UnicodeBlock.CJK_COMPATIBILITY_IDEOGRAPHS
                || ub == Character.UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A) {
            //目前已知的中文字符UTF-8集合
            return CHAR_CHINESE;
        } else if (ub == Character.UnicodeBlock.HALFWIDTH_AND_FULLWIDTH_FORMS //全角数字字符和日韩字符
                //韩文字符集
                || ub == Character.UnicodeBlock.HANGUL_SYLLABLES
                || ub == Character.UnicodeBlock.HANGUL_JAMO
                || ub == Character.UnicodeBlock.HANGUL_COMPATIBILITY_JAMO
                //日文字符集
                || ub == Character.UnicodeBlock.HIRAGANA //平假名
                || ub == Character.UnicodeBlock.KATAKANA //片假名
                || ub == Character.UnicodeBlock.KATAKANA_PHONETIC_EXTENSIONS) {
            return CHAR_OTHER_CJK;
        } else if (ub == Character.UnicodeBlock.GREEK // 希腊符号
                // 希腊扩展符号
                || ub == Character.UnicodeBlock.GREEK_EXTENDED
                // 拉丁字符
                || ub == Character.UnicodeBlock.BASIC_LATIN
                // 拉丁补充字符
                || ub == Character.UnicodeBlock.LATIN_1_SUPPLEMENT
                // 拉丁扩展A字符
                || ub == Character.UnicodeBlock.LATIN_EXTENDED_A
                // 拉丁扩展B字符
                || ub == Character.UnicodeBlock.LATIN_EXTENDED_B) {
            return CHAR_CHINESE;
        } else if (ub == Character.UnicodeBlock.GENERAL_PUNCTUATION
                || ub == Character.UnicodeBlock.CJK_SYMBOLS_AND_PUNCTUATION
                || ub == Character.UnicodeBlock.HALFWIDTH_AND_FULLWIDTH_FORMS
                || ub == Character.UnicodeBlock.CJK_COMPATIBILITY_FORMS
                || ub == Character.UnicodeBlock.VERTICAL_FORMS) {
            // 标点符号
            return CHAR_CHINESE;
        }

    }
    //其他的不做处理的字符
    return CHAR_USELESS;
}

　　之后通过 maven 打包为 jar，替换掉原来使用的 ik 包中的 jar 即可。

　　另外因为需要驼峰分词，而 IK 分词器默认会将英文进行大写转小写，这里也需要将相关方法修改一下（ CharacterUtil.regularize 方法）：

    static char regularize(char input, boolean lowercase) {
        if (input == 12288) {
            input = (char) 32;
        } else if (input > 65280 && input < 65375) {
            input = (char) (input - 65248);
        } else if (input >= 'A' && input <= 'Z' && lowercase) {
            input += 32;
        }
        return input;
    }

　　创建索引时再配合词根过滤器使用更佳：

{
  "settings": {
    "index.number_of_shards": 3,
    "index.max_result_window": 20000000,
    "number_of_replicas": 1,
    "index.refresh_interval": "60s",
    "index.highlight.max_analyzed_offset": "10000",
    "analysis": {
      "analyzer": {
        "ik_local_analyzer": {
          "type": "custom",
          "tokenizer": "ik_max_word",
          "filter": [
            "stemmer"
          ]
        }
      }
    }
  },
  "mappings": {
    "properties": {
      "id": {
        "type": "keyword"
      },
      "businessNumber": {
        "type": "keyword"
      },
      "remoteIp": {
        "type": "text"
      },
      "remoteSystemId": {
        "type": "keyword"
      },
      "remoteSystemName": {
        "type": "keyword"
      },
      "businessType": {
        "type": "keyword"
      },
      "logType": {
        "type": "keyword"
      },
      "logContent": {
        "type": "text",
        "analyzer": "ik_local_analyzer"
      },
      "createTime": {
        "type": "long"
      },
      "elasticAck": {
        "type": "keyword",
        "index": false
      }
    }
  }
}