Skip to content

ES5 returning data in scroll for the first data response along with scroll_id #518

@spendyala

Description

@spendyala
 def _do_search(self, auto_increment=False):
        self.iterpos = 0
        process_post_query = True  #used to skip results in first scan
        if self.scroller_id is None:
            if auto_increment:
                self.start += self.chuck_size

            self._results = self._search_raw(self.start, self.chuck_size)

            do_scan = self.query_params.pop("search_type", None) == "scan"
            if do_scan:
                self.scroller_parameters['search_type'] = "scan"
                if 'scroll' in self.query_params:
                    self.scroller_parameters['scroll'] = self.query_params.pop('scroll')
                if 'size' in self.query_params:
                    self.chuck_size = self.scroller_parameters['size'] = self.query_params.pop('size')

            if '_scroll_id' in self._results:
                #scan query, let's load the first bulk of data
                self.scroller_id = self._results['_scroll_id']
                # self._do_search()
                process_post_query = True
        else:
            try:
                self._results = self.connection.search_scroll(self.scroller_id,
                                                              self.scroller_parameters.get("scroll", "10m"))
                self.scroller_id = self._results['_scroll_id']
            except ReduceSearchPhaseException:
                #bad hack, should be not hits on the last iteration
                self._results['hits']['hits'] = []

        if process_post_query:
            self._post_process_query()

ES5 returning results in the scroll search first bulk of data.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions