电商日志数据分析

需求：

        日志的ETL操作

        （ETL：数据从来源端经过抽取（Extract）、转换（Transform）、加载（Load）至目的端的过程）

思路：

        只需要解析出：ip、url、pageId（topicId对应的页面Id）、country、province、city

开发步骤：

        Map

protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        // 解析日志记录
        Map<String, String> logInfo = logParser.parse(value.toString());

        if (logInfo == null) {
            logger.error("日志记录的格式不正确或解析失败：" + value.toString());
            return;
        }

        // 获取需要的字段
        String ip = logInfo.get("ip");
        String url = logInfo.get("url");
        String country = logInfo.get("country");
        String province = logInfo.get("province");
        String city = logInfo.get("city");

        // 调用 GetPageId 获取 topicId
        String topicId = GetPageId.getPageId(url);
        logInfo.put("pageId", topicId);

        // 检查所有字段是否全部为空
        if (ip != null || url != null || topicId != null || country != null || province != null || city != null) {
            StringBuilder sb = new StringBuilder();

            if (ip != null && !ip.isEmpty()) sb.append("IP: ").append(ip).append(", ");
            if (url != null && !url.isEmpty()) sb.append("URL: ").append(url).append(", ");
            if (topicId != null && !topicId.isEmpty()) sb.append("PageId: ").append(topicId).append(", ");
            if (country != null && !country.isEmpty()) sb.append("Country: ").append(country).append(", ");
            if (province != null && !province.isEmpty()) sb.append("Province: ").append(province).append(", ");
            if (city != null && !city.isEmpty()) sb.append("City: ").append(city);

            // 移除末尾的逗号和空格
            String outputString = sb.toString().replaceAll(", $", "");
            outputKey.set(outputString);
            context.write(outputKey, one);
        } else {
            logger.error("所有字段为空，日志记录：" + value.toString());
        }
    }

        Reduce:

    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        int sum = 0;
        for (IntWritable val : values) {
            sum += val.get();
        }
        result.set(sum);
        context.write(key, result);
    }