dishuostec/hanlp repository overview

version: '2.4'
services:
    hanlp:
        image: moozhou/hanlp:1.0
        container_name: hanlp
        restart: always
        mem_limit: 2g
        environment:
            HANLP_PROPERTIES_PATH: /app/hanlp.properties
            JAVA_OPTS: "-Xms120m -Xmx2g -Xmn64m"
        volumes:
            - ./hanlp.properties:/app/hanlp.properties:ro
            - ./data:/app/data
        ports:
            - 8088:8080
        logging:
            options:
                max-size: "1m"
                max-file: "2"

root=/app

# 使用自定义词典
enableCustomDictionary=true
# 中国人名识别
enableNameRecognize=true
# 音译人名识别
enableTranslatedNameRecognize=true
# 日本人名识别
enableJapaneseNameRecognize=true
# 地名识别
enablePlaceRecognize=true
# 机构名识别
enableOrganizationRecognize=true


#所有词典统一使用UTF-8编码，每一行代表一个单词，格式遵从[单词] [词性A] [A的频次] [词性B] [B的频次] ... 如果不填词性则表示采用词典的默认词性。
#用;隔开多个自定义词典，空格开头表示在同一个目录，使用“文件名 词性”形式则表示这个词典的词性默认是该词性。优先级递减。

#核心词典路径
CoreDictionaryPath=data/dictionary/CoreNatureDictionary.txt
#2元语法词典路径
BiGramDictionaryPath=data/dictionary/CoreNatureDictionary.ngram.txt
#自定义词典路径
CustomDictionaryPath=data/dictionary/custom/CustomDictionary.txt; 现代汉语补充词库.txt; 全国地名大全.txt ns; 人名词典.txt; 机构名词典.txt; 上海地名.txt ns;data/dictionary/person/nrf.txt nrf;
#停用词词典路径
CoreStopWordDictionaryPath=data/dictionary/stopwords.txt
#同义词词典路径
CoreSynonymDictionaryDictionaryPath=data/dictionary/synonym/CoreSynonym.txt
#人名词典路径
PersonDictionaryPath=data/dictionary/person/nr.txt
#人名词典转移矩阵路径
PersonDictionaryTrPath=data/dictionary/person/nr.tr.txt
#繁简词典根目录
#tcDictionaryRoot=data/dictionary/tc
#HMM分词模型
#HMMSegmentModelPath=data/model/segment/HMMSegmentModel.bin
#分词结果是否展示词性
#ShowTermNature=true
#IO适配器，实现com.hankcs.hanlp.corpus.io.IIOAdapter接口以在不同的平台（Hadoop、Redis等）上运行HanLP
#默认的IO适配器如下，该适配器是基于普通文件系统的。
#IOAdapter=com.hankcs.hanlp.corpus.io.FileIOAdapter
#感知机词法分析器
#PerceptronCWSModelPath=data/model/perceptron/pku1998/cws.bin
#PerceptronPOSModelPath=data/model/perceptron/pku1998/pos.bin
#PerceptronNERModelPath=data/model/perceptron/pku1998/ner.bin
#CRF词法分析器
#CRFCWSModelPath=data/model/crf/pku199801/cws.txt
#CRFPOSModelPath=data/model/crf/pku199801/pos.txt
#CRFNERModelPath=data/model/crf/pku199801/ner.txt
#更多配置项请参考 https://github.com/hankcs/HanLP/blob/master/src/main/java/com/hankcs/hanlp/HanLP.java#L59 自行添加