0

在 java 中，它可以使用“MatchAllDocsQuery()”来完成，但是 Pylucene 没有文档提到它是如何完成的。

这是发布单个查询然后从检索到的文档中提取所有字段的 python 代码。

INDEX_DIR = "directory/where/the/document/index/is/stored"

import sys, os, lucene

from java.nio.file import Paths
from org.apache.lucene.analysis.standard import StandardAnalyzer
from org.apache.lucene.index import DirectoryReader
from org.apache.lucene.queryparser.classic import QueryParser
from org.apache.lucene.store import SimpleFSDirectory
from org.apache.lucene.search import IndexSearcher

def run(searcher, analyzer):
    while True:
        print
        print("Hit enter with no input to quit.")
        command = input("Query:")
        if command == '':
            return

        print
        print("Searching for:", command)
        query = QueryParser("contents", analyzer).parse(command)
        #query = "MatchAllDocsQuery()"
        scoreDocs = searcher.search(query, 50).scoreDocs
        print("%s total matching documents." % len(scoreDocs))

        for scoreDoc in scoreDocs:
            doc = searcher.doc(scoreDoc.doc)
            table = dict((field.name(), field.stringValue()) for field in doc.getFields())
            print(table['doi'])
            #print('path:', doc.get("path"), 'name:', doc.get("name"), 'title:', doc.get("text"))


if __name__ == '__main__':
    lucene.initVM()
    print('lucene', lucene.VERSION)
    base_dir = os.path.dirname(os.path.abspath(sys.argv[0]))
    directory = SimpleFSDirectory.open(Paths.get(INDEX_DIR))
    print("Directory name is given below")
    print(directory)

    searcher = IndexSearcher(DirectoryReader.open(directory))
    print(searcher)
    analyzer = StandardAnalyzer()

    # Calling the run function for execution
    run(searcher, analyzer)
    del searcher
4

1 回答 1

1

查询中的微小更改可以使 Lucene 检索所有索引文档。这只是将命令变量替换为 (command = ".✱.")。.✱. 搜索所有文档中的所有字段和字段值（使用星号标记）。

INDEX_DIR = "directory/where/the/document/index/is/stored"

import sys, os, lucene

from java.nio.file import Paths
from org.apache.lucene.analysis.standard import StandardAnalyzer
from org.apache.lucene.index import DirectoryReader
from org.apache.lucene.queryparser.classic import QueryParser
from org.apache.lucene.store import SimpleFSDirectory
from org.apache.lucene.search import IndexSearcher

def run(searcher, analyzer):
    command = ".*."
    print("Searching for:", command)
    query = QueryParser("contents", analyzer).parse(command)
    #query = "MatchAllDocsQuery()"
    scoreDocs = searcher.search(query, 50).scoreDocs
    print("%s total matching documents." % len(scoreDocs))

    for scoreDoc in scoreDocs:
        doc = searcher.doc(scoreDoc.doc)
        table = dict((field.name(), field.stringValue()) for field in doc.getFields())
        print(table['doi'])
            #print('path:', doc.get("path"), 'name:', doc.get("name"), 'title:', doc.get("text"))


if __name__ == '__main__':
    lucene.initVM()
    print('lucene', lucene.VERSION)
    base_dir = os.path.dirname(os.path.abspath(sys.argv[0]))
    directory = SimpleFSDirectory.open(Paths.get(INDEX_DIR))
    print("Directory name is given below")
    print(directory)

    searcher = IndexSearcher(DirectoryReader.open(directory))
    print(searcher)
    analyzer = StandardAnalyzer()

    # Calling the run function for execution
    run(searcher, analyzer)
    del searcher
于 2019-02-07T11:57:30.623 回答