Element identification in database

摘要

This document describes, among other things, a computer-implemented method. The method includes obtaining a structured data object that having a plurality of nodes that represent elements in the data object. One or more tables that define a table representation of the data object can be generated. The one or more tables can include a plurality of table entries that correspond to the plurality of nodes, respectively. For each of one or more first nodes from among the plurality of nodes, the method can include identifying information about one or more second nodes that are determined to be adjacent or otherwise related to the first node by performing window functions along two or more coordinate systems in the one or more tables. The window function can be centered on a particular table entry that corresponds to the first node of the data object.

主权项

1. A computer-implemented method, comprising:
obtaining a structured data object that includes a plurality of nodes arranged relative to each other in respective positions of the structured data object; generating one or more tables in a database management system (DBMS) that define a table representation of the structured data object, the one or more tables including, for each of the plurality of nodes in the structured data object, a table entry that includes (i) a data value for the node and (ii) one or more position values for the node that represent the respective position of the node in the structured data object; and for each of one or more first nodes from among the plurality of nodes:
(i) performing, by the DBMS on the one or more tables, a first window function that returns the data value for a first neighboring node of the first node based on the first neighboring node being positioned in the structured data object at a first pre-defined offset relative to the respective position of the first node in a first dimension of the structured data object defined by a first coordinate system; and(ii) performing, by the DBMS on the one or more tables, a second window function that returns the data value for a second neighboring node of the first node based on the second neighboring node being positioned in the structured data object at a second pre-defined offset relative to the respective position of the first node in a second dimension of the structured data object defined by a second coordinate system, wherein the second dimension of the structured data object is not defined by the first coordinate system and runs in a different direction in the structured data object than the first dimension; and adjusting, by the DBMS using the data values returned by the first and second window functions for at least some of the first nodes, the data values for particular ones of the plurality of nodes in the structured data object.