io.github.carlomicieli.footballdb.starter.parsers.Parser.java Source code

Introduction

Here is the source code for io.github.carlomicieli.footballdb.starter.parsers.Parser.java

Source

/*
 * Copyright 2014 the original author or authors.
 *
 *  Licensed under the Apache License, Version 2.0 (the "License");
 *  you may not use this file except in compliance with the License.
 *  You may obtain a copy of the License at
 *
 *   http://www.apache.org/licenses/LICENSE-2.0
 *
 *  Unless required by applicable law or agreed to in writing, software
 *  distributed under the License is distributed on an "AS IS" BASIS,
 *  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 *  See the License for the specific language governing permissions and
 *  limitations under the License.
 */
package io.github.carlomicieli.footballdb.starter.parsers;

import io.github.carlomicieli.footballdb.starter.documents.DocumentDownloader;
import io.github.carlomicieli.footballdb.starter.documents.DocumentNotFoundException;
import io.github.carlomicieli.footballdb.starter.documents.PathBuilder;
import org.apache.commons.lang3.Validate;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

import java.util.OptionalInt;
import java.util.function.Function;
import java.util.Optional;

/**
 * It represents a parser for NFL.com pages.
 *
 * @author Carlo Micieli
 */
public abstract class Parser<T> {
    private final DocumentDownloader documentsDownloader;

    protected Parser(DocumentDownloader docs) {
        Validate.notNull(docs, "A DocumentDownloader is required");
        this.documentsDownloader = docs;
    }

    /**
     * It parses the document at the provided path.
     * <p>
     *     The actual meaning for the <code>path</code> is determined by
     *     the concrete implementation of <code>DocumentDownloaded</code>.
     * </p>
     * <p>
     *     This method is not enforce validation for the path. It solely assume
     *     the provided value is not empty. A more tight validation could be performed
     *     by concrete implementation of <code>DocumentDownloaded</code>.
     * </p>
     *
     * @param path
     * @return
     */
    public Optional<T> parse(String path) {
        return parse(path, pathBuilder());
    }

    public Optional<T> parse(String path, PathBuilder pathBuilder) {
        Validate.notBlank(path, "A path value is required.");

        String url = pathBuilder.build(path);
        Document doc = documentsDownloader.from(url).orElseThrow(DocumentNotFoundException::new);

        return Optional.ofNullable(parseDocument(doc));
    }

    protected abstract T parseDocument(Document doc);

    protected abstract PathBuilder pathBuilder();

    protected static Optional<String> childValueAsString(Element e, int index) {
        return valueFromChild(e, index);
    }

    protected static Optional<Integer> childValueAsInt(Element e, int index) {
        return valueFromChild(e, index).map(Integer::parseInt);
    }

    protected static Optional<String> valueFromChild(Element e, int index) {
        Elements children = e.children();
        if (index > children.size())
            return Optional.empty();

        return Optional.ofNullable(children.get(index).text());
    }
}