paleolimbot commented on code in PR #45459:
URL: https://github.com/apache/arrow/pull/45459#discussion_r2017865043
##########
python/pyarrow/_parquet.pyx:
##########
@@ -319,6 +319,84 @@ cdef _box_flba(ParquetFLBA val, uint32_t len):
return cp.PyBytes_FromStringAndSize(<char*> val.ptr, <Py_ssize_t> len)
+cdef class GeoStatistics(_Weakrefable):
+ """Statistics for columns with geospatial data types"""
+
+ def __cinit__(self):
+ pass
+
+ def __repr__(self):
+ return f"""{object.__repr__(self)}
+ geospatial_types: {self.geospatial_types}
+ xmin: {self.xmin}, xmax: {self.xmax}
+ ymin: {self.ymin}, ymax: {self.ymax}
+ zmin: {self.zmin}, zmax: {self.zmax}
+ mmin: {self.mmin}, mmax: {self.mmax}"""
+
+ def to_dict(self):
+ out = {
+ "geospatial_types": self.geospatial_types,
+ "xmin": self.xmin,
+ "xmax": self.xmax,
+ "ymin": self.ymin,
+ "ymax": self.ymax,
+ "zmin": self.zmin,
+ "zmax": self.zmax,
+ "mmin": self.mmin,
+ "mmax": self.mmax
+ }
+
+ return out
+
+ @property
+ def geospatial_types(self):
+ return list(self.statistics.geospatial_types)
Review Comment:
I'm hesitant to depart from the names/definitions in the Parquet format
Thrift too much but I don't feel all that strongly about it if you think this
would be helpful.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: github-unsubscr...@arrow.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
