Question

例如：

class Springboard {
    static let springboard = XCUIApplication(privateWithPath: nil, bundleID: "com.apple.springboard")

    class func launchHealth() {

        springboard.resolve()

        let icon = springboard.icons["Health"]
        if icon.exists {
            icon.tap()

            // To query elements in the Health app
            let health = XCUIApplication(privateWithPath: nil, bundleID: "com.apple.Health")
        }
    }
}

结果： doc1 = "I got the new Apple iPhone 8"; doc2 = "have you seen the new Apple iPhone 8?"; doc3 = "the Apple iPhone 8 is out"; doc4 = "another doc without the common words"; find_commons(["doc1", "doc2", "doc3", "doc4"]);或类似的东西

其他问题：使用Lucene的数据是否有更好的库/系统来实现这一目标？

Answer 1

是的，您可以使用TermVector来检索此信息。

首先，您需要确保TermVectors存储在索引中，例如：

private static Document createDocument(String title, String content) {
    Document doc = new Document();

    doc.add(new StringField("title", title, Field.Store.YES));
    FieldType type = new FieldType();
    type.setTokenized(true);
    type.setStoreTermVectors(true);
    type.setStored(false);
    type.setIndexOptions(IndexOptions.DOCS_AND_FREQS_AND_POSITIONS_AND_OFFSETS);
    doc.add(new Field("content", content, type));

    return doc;
}

然后，您可以检索给定文档ID的术语向量：

private static List<String> getTermsForDoc(int docId, String field, IndexReader reader) throws IOException {
    List<String> result = new ArrayList<>();

    Terms terms = reader.getTermVector(docId, field);
    TermsEnum it = terms.iterator();
    for(BytesRef br = it.next(); br != null; br = it.next()) {
        result.add(br.utf8ToString());
    }

    return result;
}

最后，您可以检索两个文档的常用术语：

private static List<String> getCommonTerms(int docId1, int docId2, IndexSearcher searcher) throws IOException {
    // Using the field "content" is just an example here.
    List<String> termList1 = getTermsForDoc(docId1, "content", searcher);
    List<String> termList2 = getTermsForDoc(docId2, "content", searcher);

    termList1.retainAll(termList2);
    return termList1;
}

当然，这可以很容易地扩展到允许任意数量的文档。

是否有可能在特定的Lucene文档中找到常用词？

例如：

1 个答案: