U di@sdZddlmZddlmZddlmZddlmZmZm Z m Z m Z ddl m Z ddlmZdZd Zd Zd Zd ZGd ddZGdddZGdddZddZdddZdddZe dS)z tablib.core ~~~~~~~~~~~ This module implements the central Tablib objects. :copyright: (c) 2016 by Kenneth Reitz. 2019 Jazzband. :license: MIT, see LICENSE for more details. ) OrderedDict)copy) itemgetter) HeadersNeededInvalidDatasetIndexInvalidDatasetTypeInvalidDimensionsUnsupportedFormat)registry)normalize_inputZtablibz Kenneth ReitzMITz,Copyright 2017 Kenneth Reitz. 2019 Jazzband.Zrestructuredtextc@seZdZdZddgZd(ddZddZd d Zd d Zd dZ ddZ ddZ ddZ ddZ ddZddZddZddZdd Zed!d"Zed#d$Zd%d&Zd'S))Rowz/Internal Row object. Mainly used for filtering._rowtagscCst||_t||_dSN)listrrselfrowrrr//tmp/pip-unpacked-wheel-_3ph8cfy/tablib/core.py__init__%s z Row.__init__cCsdd|jDS)Ncss|] }|VqdSrr).0colrrr *szRow.__iter__..rrrrr__iter__)sz Row.__iter__cCs t|jSr)lenrrrrr__len__,sz Row.__len__cCs t|jSr)reprrrrrr__repr__/sz Row.__repr__cCs |j|Srrrirrr __getitem__2szRow.__getitem__cCs||j|<dSrr)rr#valuerrr __setitem__5szRow.__setitem__cCs |j|=dSrrr"rrr __delitem__8szRow.__delitem__cCs |j|jfSrrrrrrr __getstate__;szRow.__getstate__cCs|\|_|_dSrr()rstaterrr __setstate__>szRow.__setstate__cCs|t|j|dSr)insertrrrr%rrrrpushAsz Row.rpushcCs|d|dS)Nrr,r-rrrlpushDsz Row.lpushcCs||dSrr.r-rrrappendGsz Row.appendcCs|j||dSr)rr,)rindexr%rrrr,Jsz Row.insertcCs ||jkSrr)ritemrrr __contains__MszRow.__contains__cCs t|jS)z%Tuple representation of :class:`Row`.)tuplerrrrrr6Psz Row.tuplecCs t|jS)z$List representation of :class:`Row`.)rrrrrrrUszRow.listcCs>|dkr dSt|tr ||jkSttt|t|j@SdS)z)Returns true if current row contains tag.NF) isinstancestrrboolrset)rtagrrrhas_tagZs   z Row.has_tagN)rr)__name__ __module__ __qualname____doc__ __slots__rrrr!r$r&r'r)r+r.r0r2r,r5propertyr6rr<rrrrr s*   r c@seZdZdZddZddZddZdd Zd d Zd d Z ddZ ddZ ddZ d_ddZ d`ddZddZddZeeeZdd Zd!d"ZeeeZd#d$Zed%d&Zed'd(Zdad)d*Zd+d,Zdbd.d/Zdcd0d1Zddd2d3Zded4d5Zdfd6d7Zd8d9Z d:d;Z!dd?Z#dhd@dAZ$didBdCZ%djdEdFZ&dkdGdHZ'dldIdJZ(dKdLZ)dMdNZ*dOdPZ+dmdQdRZ,dSdTZ-dUdVZ.dWdXZ/dYdZZ0d[d\Z1dnd]d^Z2dS)oDatasetaThe :class:`Dataset` object is the heart of Tablib. It provides all core functionality. Usually you create a :class:`Dataset` instance in your main module, and append rows as you collect data. :: data = tablib.Dataset() data.headers = ('name', 'age') for (name, age) in some_collector(): data.append((name, age)) Setting columns is similar. The column data length must equal the current height of the data and headers must be set. :: data = tablib.Dataset() data.headers = ('first_name', 'last_name') data.append(('John', 'Adams')) data.append(('George', 'Washington')) data.append_col((90, 67), header='age') You can also set rows and headers upon instantiation. This is useful if dealing with dozens or hundreds of :class:`Dataset` objects. :: headers = ('first_name', 'last_name') data = [('John', 'Adams'), ('George', 'Washington')] data = tablib.Dataset(*data, headers=headers) :param \*args: (optional) list of rows to populate Dataset :param headers: (optional) list strings for Dataset header row :param title: (optional) string to use as title of the Dataset .. admonition:: Format Attributes Definition If you look at the code, the various output/import formats are not defined within the :class:`Dataset` object. To add support for a new format, see :ref:`Adding New Formats `. cOsBtdd|D|_d|_g|_g|_|d|_|d|_dS)Ncss|]}t|VqdSrr )rargrrrrsz#Dataset.__init__..headerstitle)r_data_Dataset__headers _separators _formattersgetrFrG)rargskwargsrrrrs  zDataset.__init__cCs|jSr)heightrrrrrszDataset.__len__csft|tr:||jkr4|j|fdd|jDStn(|j|}t|trT|jSdd|DSdS)Ncsg|] }|qSrrrrposrr sz'Dataset.__getitem__..cSsg|] }|jqSr)r6)rresultrrrrSs)r7r8rFr3rHKeyErrorr r6)rkeyZ_resultsrrQrr$s     zDataset.__getitem__cCs||t||j|<dSr) _validater rH)rrVr%rrrr&s zDataset.__setitem__cCs`t|trT||jkrN|j|}|j|=t|jD]\}}||=||j|<q2q\tn|j|=dSr)r7r8rFr3 enumeraterHrU)rrVrRr#rrrrr's   zDataset.__delitem__cCs,zd|jWStk r&YdSXdS)Nz <%s dataset>zrGlowerAttributeErrorrrrrr!szDataset.__repr__csg}|jr |dd|jD|dd|jDdd|D}tttt|}|jrr|ddd|Dd d dt |Dd fd d|DS) NcSsg|] }t|qSr)r8)rhrrrrSsz#Dataset.__str__..css|]}ttt|VqdSr)rmapr8rPrrrrsz"Dataset.__str__..cSsg|]}ttt|qSr)rr]rrPrrrrSscSsg|] }d|qS)-r)rlengthrrrrSs|css|]}d|VqdS)z{%s:%s}Nr)rr4rrrrs c3s|]}j|VqdSr)formatrP format_stringrrrs) rIr2extendrHrr]maxzipr,joinrX)rrTZlensZ field_lensrrdr__str__szDataset.__str__cKst|j|f|Sr)r get_format export_set)rfmt_keyrNrrr_get_in_formatszDataset._get_in_formatcKst|}t|j||f|Sr)r r rk import_set)rrm in_streamrNrrr_set_in_formatszDataset._set_in_formatNFcs~|rjrt|jknd}nH|rNt|dkr4d}qfjrHt|jknd}ntfddjD}|rndS|svtdSdS)z>Assures size of every row in dataset is of proper proportions.Tr^c3s|]}t|jkVqdSr)rwidth)rxrrrrsz$Dataset._validate..FN)rrrrOallrHr)rrrZsafetyZis_validrrrrWs zDataset._validateTc stj}|rtntjrt|D]v\}}jD]f\}}zD|dkrjt|D]\}} || |||<qNn||||||<Wq4tk rtYq4Xq4q&jr|rfdd|D} qtjgt|} ndd|D} | S)z=Packages Dataset into lists of dictionaries for transmission.Ncs g|]}ttj|qSr)rrhrF)rdata_row dict_packrrrrSsz$Dataset._package..cSsg|] }t|qSr)rrPrrrrSs) rrHrdictrKrX IndexErrorrrF) rZdictsorderedrHZrow_irrcallbackjcdatarrvr_packages( zDataset._packagecCs|jS)zAn *optional* list of strings to be used for header rows and attribute names. This must be set manually. The given list length must equal :attr:`Dataset.width`. )rIrrrr _get_headers#szDataset._get_headerscCsB|||r8zt||_Wq>tk r4tYq>Xnd|_dS)zValidating headers setter.N)rWrrI TypeError)rZ collectionrrr _set_headers+s  zDataset._set_headerscCs|S)aA native Python representation of the :class:`Dataset` object. If headers have been set, a list of Python dictionaries will be returned. If no headers have been set, a list of tuples (rows) will be returned instead. A dataset object can also be imported by setting the `Dataset.dict` attribute: :: data = tablib.Dataset() data.dict = [{'age': 90, 'first_name': 'Kenneth', 'last_name': 'Reitz'}] )rrrrr _get_dict8s zDataset._get_dictcCst|s dSt|dtr<||D]}|t|q&nNt|dtr|t|d|_|D]}|tt| qhnt dS)aA native Python representation of the Dataset object. If headers have been set, a list of Python dictionaries will be returned. If no headers have been set, a list of tuples (rows) will be returned instead. A dataset object can also be imported by setting the :attr:`Dataset.dict` attribute. :: data = tablib.Dataset() data.dict = [{'age': 90, 'first_name': 'Kenneth', 'last_name': 'Reitz'}] Nr) rr7rwiper2r rxkeysrFvaluesr )rpicklerrrr _set_dictEs zDataset._set_dictcCs^t|}|jr|dg}ng}t|dkrNt|ddrNtt|d|j}t||}|S)z,Prepares the given column for insert/append.rr^__call__)rrFpoprhasattrr]rHr6rrheaderrrr _clean_coles zDataset._clean_colcCs t|jS)zfThe number of rows currently in the :class:`Dataset`. Cannot be directly modified. )rrHrrrrrOvszDataset.heightc CsTzt|jdWStk rNzt|jWYStk rHYYdSXYnXdS)ziThe number of columns currently in the :class:`Dataset`. Cannot be directly modified. rN)rrHryrFrrrrrrr}sz Dataset.widthcKs`t|}|st|}t|}t|ds8td|dtsLtd|d|j||f||S)z Import `in_stream` to the :class:`Dataset` object using the `format`. `in_stream` can be a file-like object, a string, or a bytestring. :param \*\*kwargs: (optional) custom configuration to the format `import_set`. roFormat z cannot be imported.)r detect_formatr rkrr rorrprcrNstreamfmtrrrloads  z Dataset.loadcKs2t|}t|ds$td|d|j|f|S)z Export :class:`Dataset` object to `format`. :param \*\*kwargs: (optional) custom configuration to the format `export_set`. rlr cannot be exported.)r rkrr rlrrcrNrrrrexports  zDataset.exportrcCs$|||j|t||ddS)zInserts a row to the :class:`Dataset` at the given index. Rows inserted must be the correct size (height or width). The default behaviour is to insert the given row to the :class:`Dataset` object at the given index. )rN)rWrHr,r )rr3rrrrrr,s zDataset.insertcCs|j|j||ddS)zzAdds a row to the end of the :class:`Dataset`. See :method:`Dataset.insert` for additional documentation. rrN)r,rOrrrrr.sz Dataset.rpushcCs|jd||ddS)zzAdds a row to the top of the :class:`Dataset`. See :method:`Dataset.insert` for additional documentation. rrNr/rrrrr0sz Dataset.lpushcCs|||dS)zoAdds a row to the :class:`Dataset`. See :method:`Dataset.insert` for additional documentation. Nr1rrrrr2szDataset.appendcCs|D]}|||qdS)z[Adds a list of rows to the :class:`Dataset` using :method:`Dataset.append` N)r2)rrowsrrrrrrfszDataset.extendcCs|d}|d=|S)z:Removes and returns the first row of the :class:`Dataset`.rrrcacherrrlpopsz Dataset.lpopcCs|d}|d=|S)9Removes and returns the last row of the :class:`Dataset`.rrrrrrpopsz Dataset.rpopcCs|S)r)rrrrrrsz Dataset.popcCs|dkr g}t|dr&tt||j}||}|j|d|jrv|sNtn|rh|jdkrht |rht |j |||jr|j rt |jD]"\}}| |||||j|<qndd|D|_dS)aInserts a column to the :class:`Dataset` at the given index. Columns inserted must be the correct height. You can also insert a column of a single callable object, which will add a new column with the return values of the callable each as an item in the column. :: data.append_col(col=random.randint) If inserting a column, and :attr:`Dataset.headers` is set, the header attribute must be set, and will be considered the header for that row. See :ref:`dyncols` for an in-depth example. .. versionchanged:: 0.9.0 If inserting a column, and :attr:`Dataset.headers` is set, the header attribute must be set, and will be considered the header for that row. .. versionadded:: 0.9.0 If inserting a row, you can add :ref:`tags ` to the row you are inserting. This gives you the ability to :method:`filter ` your :class:`Dataset` later. NrrrcSsg|]}t|gqSrrDrPrrrrS,sz&Dataset.insert_col..)rrr]rHrrWrFrrOrrr,rrrX)rr3rrr#rrrr insert_cols"    zDataset.insert_colcCs|j|j||ddS)z}Adds a column to the end of the :class:`Dataset`. See :method:`Dataset.insert` for additional documentation. rN)rrrrrrr rpush_col.szDataset.rpush_colcCs|jd||ddS)z}Adds a column to the top of the :class:`Dataset`. See :method:`Dataset.insert` for additional documentation. rrN)rrrrr lpush_col5szDataset.lpush_colr_cCs||f}|j|dS)z4Adds a separator to :class:`Dataset` at given index.N)rJr2)rr3textseprrrinsert_separator<szDataset.insert_separatorcCs<|js|jr|jnd}n|jr(|jdnd}|||dS)z=Adds a :ref:`separator ` to the :class:`Dataset`.rr^N)rFrOr)rrr3rrrappend_separatorBszDataset.append_separatorcCs|||dS)zvAdds a column to the :class:`Dataset`. See :method:`Dataset.insert_col` for additional documentation. N)rrrrr append_colMszDataset.append_colcsfdd|jDS)z@Returns the column from the :class:`Dataset` at the given index.csg|] }|qSrrrPr3rrrSWsz#Dataset.get_col..)rH)rr3rrrget_colTszDataset.get_colcCsJt|tr&||jkr"|j|}nt||jksB|j||fntdS)aAdds a formatter to the :class:`Dataset`. .. versionadded:: 0.9.5 :param col: column to. Accepts index int or header str. :param handler: reference to callback function to execute against each cell value. T) r7r8rFr3rUrrrKr2r)rrhandlerrrr add_formatter]s   zDataset.add_formattercs"t|}fdd|jD|_|S)zReturns a new instance of the :class:`Dataset`, excluding any rows that do not contain the given :ref:`tags `. csg|]}|r|qSr)r<rPr;rrrSys z"Dataset.filter..)rrH)rr;_dsetrrrfiltertszDataset.filtercst|trd|jstt|jt||d}t|j|jd}|D]$fdd|jD}|j |dq.rcsg|] }|qSrrrrrrrSs) r7r8rFrsortedrxrrCrGr2)rrrZ_sortedrrrrrsort}s$  z Dataset.sortcCsz|sdSt}|jdg||jd}||_t|jD]<\}}||jdkrPq8|g||}t|}|j|dq8|S)zTranspose a :class:`Dataset`, turning rows into columns and vice versa, returning a new ``Dataset`` instance. The first row of the original instance becomes the new header row.Nrr)rCrFrXrr r2)rr new_headersr3columnZrow_datarrr transposeszDataset.transposecCsZt|tsdS|j|jkrtt|}dd|jD}dd|jD}||||_|S)zStack two :class:`Dataset` instances together by joining at the row level, and return new combined ``Dataset`` instance.NcSsg|]}|qSrrrPrrrrSsz!Dataset.stack..cSsg|]}|qSrrrPrrrrSs)r7rCrrrrrHrf)rotherrZ rows_to_stackZ other_rowsrrrstacks   z Dataset.stackcCst|tsdS|js|jr*|jr&|js*t|j|jkr:tz|j|j}Wntk rbd}YnXt}|jD]}|j||dqp|jD]}|j||dq||_|S)zStack two :class:`Dataset` instances together by joining at the column level, and return a new combined ``Dataset`` instance. If either ``Dataset`` has headers set, than the other must as well.Nr)r7rCrFrrOrrr)rrrrrrrr stack_colss$       zDataset.stack_colscs(tfdd|jD|jdd<dS)ziRemoves all duplicate rows from the :class:`Dataset` object while maintaining the original order.cs*g|]"}t|kst|s|qSr)r6addrPseenrrrSs z-Dataset.remove_duplicates..N)r:rHrrrrremove_duplicatesszDataset.remove_duplicatescCst|_d|_dS)zARemoves all content and headers from the :class:`Dataset` object.N)rrHrIrrrrrsz Dataset.wipec ssdS|dkrttj}|dkr0tj}fdd|D}fdd|D}t}t||_g|_tjD]Z\}}g}|jD].}|jkrj|}|||qt q||krt|jt |dqt|S)zkReturns a new instance of the :class:`Dataset`, including only specified rows and columns. Ncsg|]}|tjkr|qSr)rangerOrPrrrrSsz"Dataset.subset..csg|]}|jkr|qSr)rF)rrrrrrSs r) rrrOrFrCrHrXr3r2rUr ) rrcolsrZrow_norrurVrRrrrsubsets*     zDataset.subset)NNF)TT)N)r)r)r)r)r)NN)N)N)r_)r_)N)F)NN)3r=r>r?r@rrr$r&r'r!rjrnrqrWrrrrBrFrrrxrrOrrrrr,r.r0r2rfrrrrrrrrrrrrrrrrrrrrrrrrCesb.  "          ;      %!rCc@s`eZdZdZdddZddZddZd d Zd d ZdddZ e ddZ ddZ ddZ dS)Databookz(A book of :class:`Dataset` objects. NcCs|pg|_dSr _datasets)rZsetsrrrr,szDatabook.__init__cCs,zd|jWStk r&YdSXdS)Nz <%s databook>zrYrrrrr!/szDatabook.__repr__cCs g|_dS)z@Removes all :class:`Dataset` objects from the :class:`Databook`.Nrrrrrr5sz Databook.wipecCs|jSrrrrrrsheets9szDatabook.sheetscCs t|tr|j|ntdS)z5Adds given :class:`Dataset` to the :class:`Databook`.N)r7rCrr2r)rZdatasetrrr add_sheet<s zDatabook.add_sheetTcCs>g}|rt}nt}|jD] }|||j|j|ddq|S)z(Packages :class:`Databook` for delivery.)rz)rGr~)rrxrr2rGr)rrz collectorrwZdsetrrrrCs  zDatabook._packagecCs t|jS)zDThe number of the :class:`Dataset` objects within :class:`Databook`.)rrrrrrsizeSsz Databook.sizecKsLt|}|st|}t|}t|ds8td|d|j||f||S)z Import `in_stream` to the :class:`Databook` object using the `format`. `in_stream` can be a file-like object, a string, or a bytestring. :param \*\*kwargs: (optional) custom configuration to the format `import_book`. import_bookrz cannot be loaded.)r rr rkrr rrrrrrXs  z Databook.loadcKs2t|}t|ds$td|d|j|f|S)z Export :class:`Databook` object to `format`. :param \*\*kwargs: (optional) custom configuration to the format `export_book`. export_bookrr)r rkrr rrrrrrks  zDatabook.export)N)T)r=r>r?r@rr!rrrrrBrrrrrrrr(s   rc Csnt|}d}tD]T}z8z||r6|j}WW qjWntk rLYnXW5t|drf|dXq|S)zMReturn format name of given stream (file-like object, string, or bytestring).Nseekr)r r formatsrrdetectrGr[)rZ fmt_titlerrrrrxs    rNcKstjt||f|SzIReturn dataset of given stream (file-like object, string, or bytestring).)rCrr rrcrNrrrrosrocKstjt||f|Sr)rrr rrrrrsr)N)N)r@ collectionsrroperatorrZtablib.exceptionsrrrrr Ztablib.formatsr Z tablib.utilsr __title__ __author__ __license__ __copyright__Z __docformat__r rCrrrorZregister_builtinsrrrrs.     EHP