h#ddlZddlZddlmZddlmZmZddlZddl m Z m Z ddl Z ddl Z ddl mZddlmZddlmZmZdd lmZd Zed ZeeeZgd Zd gezZedZdZdZgdZeeDcgc]}|dz c}z ZdZ d)dZ!dZ"dZ#dZ$dZ% d*dZ& d+dZ'd,dZ(d-dZ)d-dZ*dZ+dZ,d Z- d.d!Z.d-d"Z/d#Z0d$Z1d%Z2d&Z3d'Z4d(Z5ycc}w)/N)Version)Literalget_args) DataFrameSeries) GeoDataFrame)import_optional_dependency) from_shapelyfrom_wkb) _expand_user1.0.0)0.1.0z0.4.0z 1.0.0-beta.1r1.1.0)point linestringpolygon multipointmultilinestring multipolygonWKB)rgeoarrowcVt|txrd|vxr|jd S)Nz://)zhttp://zhttps://) isinstancestr startswith)urls E/var/www/html/immo/lib/python3.12/site-packages/geopandas/io/arrow.py_is_fsspec_urlr<s23 8 SL 867 7c|jD]Q\}}t|tr t|"|dk(s(t|ts9|D]}|j ddSy)aL Older PROJ versions will not recognize IDs of datum ensemble members that were added in more recent PROJ database versions. Cf https://github.com/opengeospatial/geoparquet/discussions/110 and https://github.com/OSGeo/PROJ/pull/3221 Mimicking the patch to GDAL from https://github.com/OSGeo/gdal/pull/5872 membersidN)itemsrdict#_remove_id_from_member_of_ensembleslistpop) json_dictkeyvaluemembers rr&r&Ds^ oo'' U eT " / 6 I *UD"9 ' 4& ' 'r )Point LineStringr.Polygon MultiPointMultiLineString MultiPolygonGeometryCollectionz Zctj|jj}tj|jj}||xxdz cc<t |j j}d|vr|jdt|Dcgc] }t| c}Scc}w)z+Get unique geometry types from a GeoSeries.) shapely get_type_idarray_datahas_zruniquetolistremovesorted_geometry_type_names)seriesarr_geometry_typesr;geometry_typesidxs r_get_geometry_typesrEds ,,V\\-?-?@ MM&,,,, -Eu"./668??AN ^b! G',G HHGs%B<c(|+|r#td|jDrd}nt}|tvr!t ddj ti}|j |jdk(D]}||}t|}|ddk(rd }t|d k(r|d}nd }d} |jrE|d k(r|jj} n%|jj} t| d |r ||vr||ndd| ||i||<|jj} t!j"| j%r| ||d<|sdddgddgddgddgdi||d<|j&||dt(j*ddS)aCreate and encode geo metadata dict. Parameters ---------- df : GeoDataFrame schema_version : {'0.1.0', '0.4.0', '1.0.0-beta.1', '1.0.0', '1.1.0', None} GeoParquet specification version; if not provided will default to latest supported version. geometry_encoding : dict, default None GeoParquet encoding per geometry column. Defaults to "WKB" for columns that are not present in the dictionary. write_covering_bbox : bool, default False Writes the bounding box column for each row entry with column name 'bbox'. Writing a bbox column can be computationally expensive, hence is default setting is False. Returns ------- dict Nc3&K|] }|dk7 yw)rN).0encodings r z#_create_metadata..s% "*H % srzschema_version must be one of: z, geometryr0 geometry_typer rCrrJrcrsbboxxminyminxmaxymaxrQrRrSrTcovering geopandas)libraryversion)primary_columncolumnsrYcreator)anyvaluesMETADATA_VERSIONSUPPORTED_VERSIONS ValueErrorjoinr[dtypesrElenrOto_wkt to_json_dictr& total_boundsr=npisfiniteall_geometry_column_namerW __version__) dfschema_versiongeometry_encodingwrite_covering_bboxcolumn_metadatacolrArCgeometry_types_namerOrPs r_create_metadatartss. % .?.F.F.H% " %N-N//-dii8J.K-L M  Ozz"))z12*C,V4 !  #"1 >"a'!/!2"2  ::(jj'')jj--/3C8 $0A)A"#& 3  ""))+ ;;t  "+/OC  ( #V,#V,#V,#V, 0OC  ,G*Z22"!*y7L7LM  r cJtj|jdS)zEncode metadata dict to UTF-8 JSON string. Parameters ---------- metadata : dict Returns ------- UTF-8 encoded JSON string utf-8)jsondumpsencode)metadatas r_encode_metadatar{s ::h  & &w //r cP|ytj|jdS)zDecode a UTF-8 encoded JSON string to dict. Parameters ---------- metadata_str : string (UTF-8 encoded) Returns ------- dict Nrv)rwloadsdecode) metadata_strs r_decode_metadatars' ::l))'2 33r ct|ts td|jjdvr tdt d|j jD}|s tdy)zValidate that the GeoDataFrame conforms to requirements for writing to Parquet format. Raises `ValueError` if the GeoDataFrame is not valid. copied from `pandas.io.parquet` Parameters ---------- df : GeoDataFrame z;Writing to Parquet/Feather only supports IO with DataFrames>emptystringunicodez7Writing to Parquet/Feather requires string column namesc3BK|]}|t|tywN)rr)rInames rrKz&_validate_dataframe..s!"&D= 1.1.0F)ror interleaved)rnrorprPz`An existing column 'bbox' already exists in the dataframe. Please rename to write covering bbox.minxminymaxxmaxyrU)rgeo)pyarrowrgeopandas.io._geoarrowrrrartr[bounds from_arrays append_columnschemarzupdater{replace_schema_metadata) rmrrornrprrtablegeometry_encoding_dict geo_metadatar bbox_arrayrzs r_geopandas_to_arrowrKs$9!  %.G*CT %7 /u%%!E !$ %0/ L RZZ 8  ,, F^VF^VF^VF^ L2- ##FJ7||$$H OOV-l;<=  ( ( 22r c tdd}t|}t|||||} |j| |fd|i|y)a Write a GeoDataFrame to the Parquet format. Any geometry columns present are serialized to WKB format in the file. Requires 'pyarrow'. This is tracking version 1.0.0 of the GeoParquet specification at: https://github.com/opengeospatial/geoparquet. Writing older versions is supported using the `schema_version` keyword. .. versionadded:: 0.8 Parameters ---------- path : str, path object index : bool, default None If ``True``, always include the dataframe's index(es) as columns in the file output. If ``False``, the index(es) will not be written to the file. If ``None``, the index(ex) will be included as columns in the file output except `RangeIndex` which is stored as metadata only. compression : {'snappy', 'gzip', 'brotli', None}, default 'snappy' Name of the compression to use. Use ``None`` for no compression. geometry_encoding : {'WKB', 'geoarrow'}, default 'WKB' The encoding to use for the geometry columns. Defaults to "WKB" for maximum interoperability. Specify "geoarrow" to use one of the native GeoArrow-based single-geometry type encodings. schema_version : {'0.1.0', '0.4.0', '1.0.0', '1.1.0', None} GeoParquet specification version; if not provided will default to latest supported version. write_covering_bbox : bool, default False Writes the bounding box column for each row entry with column name 'bbox'. Writing a bbox column can be computationally expensive, hence is default setting is False. **kwargs Additional keyword arguments passed to pyarrow.parquet.write_table(). pyarrow.parquet(pyarrow is required for Parquet support.extra)rrornrp compressionN)r r r write_table) rmpathrrrornrpkwargsparquetrs r _to_parquetrsX`)!KG  D  +%/  EGtGGGr c |tdd}t|}t|||}|j||fd|i|y)a Write a GeoDataFrame to the Feather format. Any geometry columns present are serialized to WKB format in the file. Requires 'pyarrow' >= 0.17. This is tracking version 1.0.0 of the GeoParquet specification for the metadata at: https://github.com/opengeospatial/geoparquet. Writing older versions is supported using the `schema_version` keyword. .. versionadded:: 0.8 Parameters ---------- path : str, path object index : bool, default None If ``True``, always include the dataframe's index(es) as columns in the file output. If ``False``, the index(es) will not be written to the file. If ``None``, the index(ex) will be included as columns in the file output except `RangeIndex` which is stored as metadata only. compression : {'zstd', 'lz4', 'uncompressed'}, optional Name of the compression to use. Use ``"uncompressed"`` for no compression. By default uses LZ4 if available, otherwise uncompressed. schema_version : {'0.1.0', '0.4.0', '1.0.0', '1.1.0', None} GeoParquet specification version for the metadata; if not provided will default to latest supported version. kwargs Additional keyword arguments passed to pyarrow.feather.write_feather(). pyarrow.feather(pyarrow is required for Feather support.r)rrnrN)r r r write_feather)rmrrrrnrfeatherrs r _to_featherrsK@)!KG  D % OEG%I;I&Ir c |t|jj}|dDcgc]}||jvs|}}t |j ddj j}|j|jt|s td|d}t|r.||vr*|d}t|dkDrtjdd |j|}|i}|j di|}|D]}|d|} d | vr!| d } t| t rt#| nd } | d d k(r$t%t'j(||| } n1ddlm} t/| ||j1d| d z| } |j3|j||| t5||Scc}w)z{Convert a pyarrow Table to a GeoDataFrame. Helper function with main, shared logic for read_parquet/read_feather. r[r)r*No geometry columns are included in the columns read from the Parquet/Feather file. To read this file without geometry columns, use pandas.read_parquet/read_feather() instead.rZr zMultiple non-primary geometry columns read from Parquet/Feather file. The first column read was promoted to the primary geometry.rrOz OGC:CRS84rJr)rO)construct_shapely_arrayz geoarrow.)rLrH)_validate_and_decode_metadatarrz column_namesr'slice to_pandasr[sortrrdrarrdroprr%r&r rhr9rrr combine_chunksinsertr) rrto_pandas_kwargsrrgeometry_columnsresult_column_namesrL table_attrrm col_metadatarOgeom_arrrs r_arrow_to_geopandasrs 4U\\5J5JK $I.#9K9K2Ku{{1a0::<DDE1778   ?  ,-H 1A!A#A&  1 $ MMT  ,-J    1 0 1B A#I.s3 L u%C#t$3C8C  #u ,s 4#>H F#'#J--/|J?W1W H %++C0#x@/A2 X ..ws GGc(t|tr|| ddlm}|j |\}}t |r3|1tdd}|jj|fi|xsi\}}||rtd|d||fS#t $rY`wxYw)z Get the filesystem and path for a given filesystem and path. If the filesystem is not None then it's just returned as is. r) FileSystemfsspecz(fsspec is requred for 'storage_options'.rz7Cannot provide 'storage_options' with non-fsspec path 'r) rr pyarrow.fsrfrom_uri Exceptionrr core url_to_fsra)r filesystemstorage_optionsrrs r_get_filesystem_pathr2s $!8Z=O  -)2248 J d 2+ F 16;;00Q/:ORQ DoEdV1 M   t !   sB BBcddlm}t||jr|S ddl}t||j r |j |j|S|S#t$rY|SwxYw)aCheck if ``filesystem`` is a valid filesystem. Simplified version of pyarrow.fs._ensure_filesystem. This is only needed below because `pyarrow.parquet.read_metadata` does not yet accept a filesystem keyword (https://issues.apache.org/jira/browse/ARROW-16719) r)fsN) rrrrrAbstractFileSystem PyFileSystem FSSpecHandler ImportError)rrrs r_ensure_arrow_fsrQsr*bmm,A j&";"; <??2#3#3J#?@ @      sA A)(A)c|d|vr td t|jdd}t||S#ttj j f$r tdwxYw)NrziMissing geo metadata in Parquet/Feather file. Use pandas.read_parquet/read_feather() instead.r r)rarr TypeErrorrwdecoderJSONDecodeErrorr)rzdecoded_geo_metadatas rrris|61 ?  V/ VS0IJ/0  t||33 4VTUUVs ;/A*cddl}ddlm}i}t|jtdkr t d} |j |fd|i|j }|j}|d |vr" |j||j}||fS||fS#t$r|j||}YVwxYw#t$rY||fSwxYw) a>Open the Parquet file/dataset a first time to get the schema and metadata. TODO: we should look into how we can reuse opened dataset for reading the actual data, to avoid discovering the dataset twice (problem right now is that the ParquetDataset interface doesn't allow passing the filters on read) rN)rz15.0.0F)use_legacy_datasetr)rr) rrrrlr%ParquetDatasetrr read_schemarz read_metadata)rrrrrrrzs r!_read_parquet_schema_and_metadatarzs Fw""#gh&77/B'''NNvNUUH 61 ,,Tj,IRRH 8 68  B$$Tj$AB   8  s#B-B4B10B14 CCc tdd}ddl}|jdd}t|||\}}t |}t ||\} } t | } t| ddk(r td | t| |nd} t| } |s| r t| | }d |vr|jd }t|| }n| }d |d <|j|f|||d |}t|| |S)am Load a Parquet object from the file path, returning a GeoDataFrame. You can read a subset of columns in the file using the ``columns`` parameter. However, the structure of the returned GeoDataFrame will depend on which columns you read: * if no geometry columns are read, this will raise a ``ValueError`` - you should use the pandas `read_parquet` method instead. * if the primary geometry column saved to this file is not included in columns, the first available geometry column will be set as the geometry column of the returned GeoDataFrame. Supports versions 0.1.0, 0.4.0 and 1.0.0 of the GeoParquet specification at: https://github.com/opengeospatial/geoparquet If 'crs' key is not present in the GeoParquet metadata associated with the Parquet object, it will default to "OGC:CRS84" according to the specification. Requires 'pyarrow'. .. versionadded:: 0.8 Parameters ---------- path : str, path object columns : list-like of strings, default=None If not None, only these columns will be read from the file. If the primary geometry column is not included, the first secondary geometry read from the file will be set as the geometry column of the returned GeoDataFrame. If no geometry columns are present, a ``ValueError`` will be raised. storage_options : dict, optional Extra options that make sense for a particular storage connection, e.g. host, port, username, password, etc. For HTTP(S) URLs the key-value pairs are forwarded to urllib as header options. For other URLs (e.g. starting with "s3://", and "gcs://") the key-value pairs are forwarded to fsspec. Please see fsspec and urllib for more details. When no storage options are provided and a filesystem is implemented by both ``pyarrow.fs`` and ``fsspec`` (e.g. "s3://") then the ``pyarrow.fs`` filesystem is preferred. Provide the instantiated fsspec filesystem using the ``filesystem`` keyword if you wish to use its implementation. bbox : tuple, optional Bounding box to be used to filter selection from geoparquet data. This is only usable if the data was saved with the bbox covering metadata. Input is of the tuple format (xmin, ymin, xmax, ymax). to_pandas_kwargs : dict, optional Arguments passed to the `pa.Table.to_pandas` method for non-geometry columns. This can be used to control the behavior of the conversion of the non-geometry columns to a pandas DataFrame. For example, you can use this to control the dtype conversion of the columns. By default, the `to_pandas` method is called with no additional arguments. **kwargs Any additional kwargs passed to :func:`pyarrow.parquet.read_table`. Returns ------- GeoDataFrame Examples -------- >>> df = geopandas.read_parquet("data.parquet") # doctest: +SKIP Specifying columns to read: >>> df = geopandas.read_parquet( ... "data.parquet", ... columns=["geometry", "pop_est"] ... ) # doctest: +SKIP rrrrNr)rrr[rfiltersTuse_pandas_metadata)r[rr)r geopandas.io._pyarrow_hotfixr(rr rrrdra_get_parquet_bbox_filter"_check_if_covering_in_geo_metadata_get_non_bbox_columns_splice_bbox_and_filters read_tabler)rr[rrPrrrrWrrrzr bbox_filterif_bbox_column_exists filters_kwargrrs r _read_parquetrs6`)!KG(L$/J+ _J  D8zJFH0:L < "#q( ?  9=8H t4d?|L ,' =F 9- *=+F$(F ! G    *g IO E ul4D EEr c ~tdd}ddl}t|}|j|fd|i|}t ||S)a Load a Feather object from the file path, returning a GeoDataFrame. You can read a subset of columns in the file using the ``columns`` parameter. However, the structure of the returned GeoDataFrame will depend on which columns you read: * if no geometry columns are read, this will raise a ``ValueError`` - you should use the pandas `read_feather` method instead. * if the primary geometry column saved to this file is not included in columns, the first available geometry column will be set as the geometry column of the returned GeoDataFrame. Supports versions 0.1.0, 0.4.0, 1.0.0 and 1.1.0 of the GeoParquet specification at: https://github.com/opengeospatial/geoparquet If 'crs' key is not present in the Feather metadata associated with the Parquet object, it will default to "OGC:CRS84" according to the specification. Requires 'pyarrow' >= 0.17. .. versionadded:: 0.8 Parameters ---------- path : str, path object columns : list-like of strings, default=None If not None, only these columns will be read from the file. If the primary geometry column is not included, the first secondary geometry read from the file will be set as the geometry column of the returned GeoDataFrame. If no geometry columns are present, a ``ValueError`` will be raised. to_pandas_kwargs : dict, optional Arguments passed to the `pa.Table.to_pandas` method for non-geometry columns. This can be used to control the behavior of the conversion of the non-geometry columns to a pandas DataFrame. For example, you can use this to control the dtype conversion of the columns. By default, the `to_pandas` method is called with no additional arguments. **kwargs Any additional kwargs passed to pyarrow.feather.read_table(). Returns ------- GeoDataFrame Examples -------- >>> df = geopandas.read_feather("data.feather") # doctest: +SKIP Specifying columns to read: >>> df = geopandas.read_feather( ... "data.feather", ... columns=["geometry", "pop_est"] ... ) # doctest: +SKIP rrrrNr[)r)r rr rr)rr[rrrrWrs r _read_featherrsNr)!KG(  D G  t ?W ? ?E u7G HHr c\|d}t|rt|}t||S|d|ddk(rmddlm}|j |df|dk\|j |df|dkz|j |df|d k\z|j |df|d kzSt d ) NrZr[rJrrxyr rz}Specifying 'bbox' not supported for this Parquet file (it should either have a bbox covering column or use 'point' encoding).)r_get_bbox_encoding_column_name_convert_bbox_to_parquet_filterpyarrow.computecomputefieldra)rrPrZbbox_column_namepcs rrras!"23N),79,G.t5EFF i  0 < G$XX~s+ ,Q 7xx-.$q'9 ;xx-.$q'9 ;xx-.$q'9 ;  D  r cddlm}|j|df|dkD|j|df|dkDz|j|df|dkz|j|df|dkzS) NrrQr rRrrSrTr )r rr)rPrrs rr r ys  #V, -Q 7 88%v. /$q' 9 ; 88%v. /$q' 9 ; 88%v. /$q' 9 ; r c<|d}d|d|jvS)NrZrVr[)rrrZs rrrs+!"23N i0@EEG GGr c4|d}|d|ddddS)NrZr[rVrPrQrrHrs rr r s1!"23N  "> 2: >v Fv Nq QQr c^t|}|j}||vr|j||Sr)r rr>)rrrr[s rrrs05lCllG7"'( Nr cPtdd}||S|j|}||zS)Nrrr)r filters_to_expression) kwarg_filtersrrfilters_expressions rrrs=(!KG 66}E + ++r )NNF)NrNN)NsnappyrNF)NNN)NN)NNNN)6rwrpackaging.versionrtypingrrnumpyrhpandasrrr7rWrgeopandas._compatr geopandas.arrayr r filer r_SUPPORTED_VERSIONS_LITERALr'r`rrPARQUET_GEOMETRY_ENCODINGSrr&r@rErtr{rrrrrrrrrrrrrrr rr rr) geom_types0rr&s_ %$$"82$%WX(#=>?g 22$%67<'& ;OPiT)PP I JOWt 04">6ASL  33r <H~&JRF/R>0 "H   ~FBAIH 0H R ,kQs8 C"