superset集成xspreadsheet

集成x-spreadsheet

准备工作

去github下载最新的xspreadsheet，5.20号更新了一个功能。下载之后，解压，npm install , npm run dev没问题后。把dist文件夹下所有文件复制，包括子目录。放在新建的文件夹\superset-frontend\src\xspreadsheet下面。这个文件就是一个组件，之后去调用就可以了。

后端

修改 viz.py , 模仿TableViz，添加 XspreadsheetViz，几乎只用修改 get_data

class XspreadsheetVix(BaseViz):

    """集成xspreadsheet"""

    viz_type = "xspreadsheet"
    verbose_name = _("Xspreadsheet")
    is_timeseries = False
    enforce_numerical_metrics = False

    def should_be_timeseries(self):
        fd = self.form_data
        # TODO handle datasource-type-specific code in datasource
        conditions_met = (fd.get("granularity") and fd.get("granularity") != "all") or (
            fd.get("granularity_sqla") and fd.get("time_grain_sqla")
        )
        if fd.get("include_time") and not conditions_met:
            raise Exception(
                _("Pick a granularity in the Time section or " "uncheck 'Include Time'")
            )
        return fd.get("include_time")

    def query_obj(self) -> Dict[str, Any]:  # Any类型兼容所有类型，赋值时不用安全检查
        '''
        重写 qurey_obj，处理查询条件
        :return: d
        '''
        d = super().query_obj()
        fd = self.form_data

        if fd.get("all_columns") and (
            fd.get("groupby") or fd.get("metrics") or fd.get("percent_metrics")
        ):
            raise Exception(
                _(
                    "Choose either fields to [Group By] and [Metrics] and/or "
                    "[Percentage Metrics], or [Columns], not both"
                )
            )

        sort_by = fd.get("timeseries_limit_metric")
        if fd.get("all_columns"):
            d["columns"] = fd.get("all_columns")
            d["groupby"] = []
            order_by_cols = fd.get("order_by_cols") or []
            d["orderby"] = [json.loads(t) for t in order_by_cols]
        elif sort_by:
            sort_by_label = utils.get_metric_name(sort_by)
            if sort_by_label not in utils.get_metric_names(d["metrics"]):
                d["metrics"] += [sort_by]
            d["orderby"] = [(sort_by, not fd.get("order_desc", True))]

        # Add all percent metrics that are not already in the list
        if "percent_metrics" in fd:
            d["metrics"].extend(
                m for m in fd["percent_metrics"] or [] if m not in d["metrics"]
            )

        d["is_timeseries"] = self.should_be_timeseries()
        return d


    @staticmethod
    def df2xspreadsheetjson(df) -> Dict:
        '''
        df对象转为 x-spreadsheet格式的json字符串
        :param df: 从数据库得到的 dataframe
        :return: str
        '''
        cols = []
        # 重命名标题行，主要考虑标题行空等情况
        for col in df.columns:
            if col == "":
                cols.append("N/A")  # 标题行空，一般不可能
            elif col is None:
                cols.append("NULL")  # 表是空的
            else:
                cols.append(col)  # 复制过去
        # print(cols)
        df.columns = cols

        if df.shape[0] < 1 or df.shape[1] < 1:
            return '{}'

        metrics = cols
        df = df[metrics]  # 取我们需要的字段
        # 直接拼接字符串
        info = ''