poetry-source
/
indexGenerator.html

<!DOCTYPE html>
<html lang="en">

<head>
    <meta charset="UTF-8">
    <meta name="viewport" content="width=device-width, initial-scale=1.0">
    <meta http-equiv="X-UA-Compatible" content="ie=edge">
    <title>Document</title>
</head>

<body>

    <button id="download">下载索引</button>
    <button id="downloadAuthorSql">下载作者表结构</button>
    <button id="downloadPoetrySql">下载内容表结构</button>
    <script src="./js/util/saveData.js"></script>
    <script src="./js/index/file_path_idx.js"></script>
    <script>
        let log = console.log.bind(console)

        // 异步请求
        let httpRequest = function (url) {
            return new Promise((resolve, reject) => {
                var xhr = new XMLHttpRequest();
                xhr.open("GET", url, true);
                xhr.onreadystatechange = function () {
                    if (xhr.readyState == 4) {
                        resolve(JSON.parse(xhr.responseText));
                    }
                }
                xhr.send();
            })
        }

        let contentCutIndex = function (source) {
            if (!source || !source.length) {
                return 0
            }
            const cutChar = ['，', '。', '？', '！']
            let minIdx = source.length
            for (let i = 0; i < cutChar.length; i++) {
                let cutIndex = source.indexOf(cutChar[i])
                if (cutIndex != -1) {
                    minIdx = Math.min(minIdx, cutIndex)
                }
            }

            return minIdx;
        }

        let main_author = [
            "苏轼", "李白", "陆游", "王维", "杜甫", "杜牧", "屈原", "柳永", "李煜",
            "王勃", "李贺", "秦观", "曹操", "曹植", "李商隐", "辛弃疾", "李清照", "白居易",
            "陶渊明", "温庭筠", "欧阳修", "晏几道", "刘禹锡", "孟浩然", "张若虚",
            "陈子昂", "贺知章", "王昌龄", "孟郊", "贾岛", "周邦彦", "晏殊", "姜夔", "纳兰性德"
        ]
        let is_main_index = true

        let fullIndex = {}
        let fileCount = file_path_idx.length
        let dealFileCount = 0
        function buildFullIndex() {
            file_path_idx.forEach((path, f_idx) => {
                httpRequest(`/source/${path}`).then(data => {
                    // console.log(path)
                    // console.log(data.length)
                    let currIndex = {}
                    data.map((item, i_idx) => {
                        if (is_main_index) {
                            if (main_author.includes(item.authorName)) {
                                currIndex[
                                    `${item.dynasty}-${item.title}-${item.authorName}-${item.content ? item.content[0].substr(0, contentCutIndex(item.content[0])) : ''}`
                                ] = `${f_idx}-${i_idx}`
                            }
                        } else {
                            currIndex[
                                `${item.dynasty}-${item.title}-${item.authorName}-${item.content ? item.content[0].substr(0, contentCutIndex(item.content[0])) : ''}`
                            ] = `${f_idx}-${i_idx}`
                        }

                    })
                    return currIndex
                }).then(idx_list => {
                    Object.assign(fullIndex, idx_list)
                    dealFileCount++
                })
            });
        }

        download.onclick = function () {
            fullIndex = {}
            dealFileCount = 0
            buildFullIndex()

            let timer = setInterval(() => {
                if (dealFileCount !== fileCount) {
                    log("等待解析中..." + dealFileCount + "/" + fileCount)
                } else {
                    clearInterval(timer);
                    log("已解析完成..." + dealFileCount + "/" + fileCount)
                    saveData.setDataConver({
                        name: `${is_main_index ? 'main' : 'full'}_data_index.js`,
                        data: 'search_data_index = ' + JSON.stringify(fullIndex)
                    })
                }
            }, 500)

            // saveData.setDataConver({ name: 'full_data_index.json', data: JSON.stringify(fullIndex, null, 2) })
        }


        function sqlNormalize(inStr) {
            if (Array.isArray(inStr)) {
                inStr = inStr.join("\n")
            }

            return inStr.replace(/\r?\n/g, "\\n")
                .replace(/'/g, "\\'")
        }

        function sqlBuilder(tableName, titleList, data, defaultMap) {
            let columnSeg = titleList.map(title => `\`${title}\``).join(', ')
            return data.map(
                    item => titleList.map(
                        title => item[title] ? `'${sqlNormalize(item[title])}'` :
                            defaultMap[title] ? `'${sqlNormalize(defaultMap[title])}'` : 'null'
                    ).join(', ')
                )
                .map(seg => `insert into ${tableName} (${columnSeg}) values (${seg});`)
                .join('\n');
        }

        downloadAuthorSql.onclick = function () {
            let titleList = ['id', 'name', 'dynasty', 'birthYear', 'deathYear', 'desc']
            httpRequest('source/作者.json').then(data => {
                let sql = sqlBuilder('t_author', titleList, data)
                saveData.setDataConver({
                    name: `author.sql`,
                    data: sql
                })
            })
        }

        downloadPoetrySql.onclick = function () {
            let titleList = ['id', 'title', 'authorName', 'authorId', 'dynasty', 'appreciation', 'content', 'comment', 'translation', 'intro', 'foreword', 'annotation', 'kindCN']

            let sqlList = []
            let sql_file_idx = 0
            file_path_idx.forEach((path, f_idx) => {
                let kindCN = path.substr(0, 1)
                httpRequest(`/source/${path}`).then(data => sqlBuilder('t_work', titleList, data, {kindCN: kindCN}))
                .then(sql => {
                    dealFileCount++
                    sqlList.push(sql)
                    if (dealFileCount === fileCount) {
                        saveData.setDataConver({
                            name: `work_${sql_file_idx}.sql`,
                            data: sqlList.join('\n')
                        })
                        sql_file_idx++
                        sqlList = []
                    }
                })
            });
        }


    </script>
</body>

</html>