o
;Di9= @ s d dl mZmZmZ zd dlmZ W n ey$ d dlm mZ Y nw d dl m
Z
d dl Z d dl m
Z
mZ d dlmZmZmZ d dlmZ d dlmZ d d
ZG d d d eZd
d Zdd Zdd Z d#ddZ dd Z dd Z dd Z d d Z d d Z!d!d" Z"dS )$ )absolute_importprint_functiondivision)etreeN)
attrgetter) string_types text_type)Table
fieldnamesiterpeek)read_source_from_arg)totextc O s t | } t| g|R i |S )a
Extract data from an XML file. E.g.::
>>> import petl as etl
>>> # setup a file to demonstrate with
... d = '''
...
... | foo | bar |
...
...
... | a | 1 |
...
...
... | b | 2 |
...
...
... | c | 2 |
...
...
'''
>>> with open('example.file1.xml', 'w') as f:
... f.write(d)
...
212
>>> table1 = etl.fromxml('example.file1.xml', 'tr', 'td')
>>> table1
+-----+-----+
| foo | bar |
+=====+=====+
| 'a' | '1' |
+-----+-----+
| 'b' | '2' |
+-----+-----+
| 'c' | '2' |
+-----+-----+
If the data values are stored in an attribute, provide the attribute
name as an extra positional argument::
>>> d = '''
...
... | |
...
...
... | |
...
...
... | |
...
...
... | |
...
...
'''
>>> with open('example.file2.xml', 'w') as f:
... f.write(d)
...
220
>>> table2 = etl.fromxml('example.file2.xml', 'tr', 'td', 'v')
>>> table2
+-----+-----+
| foo | bar |
+=====+=====+
| 'a' | '1' |
+-----+-----+
| 'b' | '2' |
+-----+-----+
| 'c' | '2' |
+-----+-----+
Data values can also be extracted by providing a mapping of field
names to element paths::
>>> d = '''
...
... a
...
...
... b
...
...
... c
...
...
'''
>>> with open('example.file3.xml', 'w') as f:
... f.write(d)
...
223
>>> table3 = etl.fromxml('example.file3.xml', 'row',
... {'foo': 'foo', 'bar': ('baz/bar', 'v')})
>>> table3
+------------+-----+
| bar | foo |
+============+=====+
| ('1', '3') | 'a' |
+------------+-----+
| '2' | 'b' |
+------------+-----+
| '2' | 'c' |
+------------+-----+
If `lxml `_ is installed, full XPath expressions can be
used.
Note that the implementation is currently **not** streaming, i.e.,
the whole document is loaded into memory.
If multiple elements match a given field, all values are reported as a
tuple.
If there is more than one element name used for row values, a tuple
or list of paths can be provided, e.g.,
``fromxml('example.file.html', './/tr', ('th', 'td'))``.
Optionally a custom parser can be provided, e.g.::
>>> from lxml import etree # doctest: +SKIP
... my_parser = etree.XMLParser(resolve_entities=False) # doctest: +SKIP
... table4 = etl.fromxml('example.file1.xml', 'tr', 'td', parser=my_parser) # doctest: +SKIP
)r XmlView)sourceargskwargs r D/var/www/Datamplify/venv/lib/python3.10/site-packages/petl/io/xml.pyfromxml s zr c @ s e Zd Zdd Zdd ZdS )r c O s || _ || _t|dkr't|d tttfr'|d | _|d | _d | _ d | _
n;t|dkrEt|d t rE|d | _d | _|d | _ d | _
n t|dkr^|d | _|d | _d | _ |d | _
nJ d| dd | _
| dd | _d S ) N r Fzbad parametersmissingparser)r r len
isinstancer tuplelistrmatchvmatchvdictattrdictgetr user_parser)selfr r r r r r __init__ s(
zXmlView.__init__c
# s j }j}jd}tj}tj||d}t|ds#|j |_
|d urd|
j D ]5j d u r9t
d nfdd t|trJ |}n tjfdd|D }t fd d
|D V q-nXtttt| }|V t t |D ]*}j| }t|tr||< tj|< qz|d |< |d } t| j|< qz|
j D ]tfd
d
|D V qW d d S W d d S 1 sw Y d S )Nrb)r iterfindtextc s | jS N)r# r! )e)r% r r s z"XmlView.__iter__..c g | ]} |qS r findall).0enm)rowelmr r
s z$XmlView.__iter__..c 3 s | ]} |V qd S r* r )r0 velm)getvr r s z#XmlView.__iter__..r r c 3 s& | ]}| | V qd S r* r. )r0 f)r2 vgettersvmatchesr r r6 s )r r r open_create_xml_parserr$ r parsehasattrr/ r( r r! r r r itertoolschainr sortedmapr keysr" element_text_getterr attribute_text_getter)
r% r r xmlfparser2treevelmsfldsr7 r! r )r5 r2 r% r8 r9 r __iter__ sT
/"zXmlView.__iter__N)__name__
__module__ __qualname__r& rJ r r r r r s r c C s0 | d ur| S zt jddW S ty Y d S w )NF)resolve_entities)r XMLParser TypeError)r$ r r r r; s r; c s fdd}|S )Nc s8 t | dkrtdd | D S t | dkr| d jS S )Nr c s s | ]}|j V qd S r* )r) r0 r+ r r r r6 s z4element_text_getter.._get..r )r r r) vr r r _get s
z!element_text_getter.._getr )r rU r rT r rC s rC c s fdd}|S )Nc s@ t | dkrt fdd| D S t | dkr | d S S )Nr c 3 s | ]}| V qd S r* )r# rQ )r! r r r6 s z6attribute_text_getter.._get..r )r r r# rR r! r r r rU s
z#attribute_text_getter.._getr )r! r rU r rV r rD s rD tagutf-8c C sx |s |s |s d}d}d}t | d\} }
t| } t|| |||||} t|| |d}
t||||}t|
||d|
| |d dS ) aH
Write the table into a new xml file according to elements defined in the
function arguments.
The `root`, `head` and `rows` (string, optional) arguments define the tags
and the nesting of the xml file. Each one defines xml elements with tags
separated by slashes (`/`) like in `root/level/tag`. They can have a
arbitrary number of tags that will reflect in more nesting levels for the
header or record/row written in the xml file.
For details on tag naming and nesting rules check xml `specification`_ or
xml `references`_.
The `rows` argument define the elements for each row of data to be written
in the xml file. When specified, it must have at least 2 tags for defining
the tags for `row/column`. Additional tags will add nesting enclosing all
records/rows/lines.
The `head` argument is similar to the rows, but aplies only to one line/row
of header with fieldnames. When specified, it must have at least 2 tags for
`fields/name` and the remaining will increase nesting.
The `root` argument defines the elements enclosing `head` and `rows` and is
required when using `head` for specifying valid xml documents.
When none of this arguments are specified, they will default to tags that
generate output similar to a html table:
`root='table', head='there/tr/td', rows='tbody/tr/td'`.
The `prologue` argument (string, optional) could be a snippet of valid xml
that will be inserted before other elements in the xml. It can optionally
specify the `XML Prolog` of the file.
The `epilogue` argument (string, optional) could be a snippet of valid xml
that will be inserted after all other xml elements except the root closing
tag. It must specify a closing tag if the `root` argument is not specified.
The `style` argument select the format of the elements in the xml file. It
can be `tag` (default), `name`, `attribute` or a custom string to format
each row via
`str.format `_.
Example usage for writing files::
>>> import petl as etl
>>> table1 = [['foo', 'bar'],
... ['a', 1],
... ['b', 2]]
>>> etl.toxml(table1, 'example.file4.xml')
>>> # see what we did is similar a html table:
>>> print(open('example.file4.xml').read())
>>> # define the nesting in xml file:
>>> etl.toxml(table1, 'example.file5.xml', rows='plan/line/cell')
>>> print(open('example.file5.xml').read())
a | 1 |
b | 2 |
>>> # choose other style:
>>> etl.toxml(table1, 'example.file6.xml', rows='row/col', style='attribute')
>>> print(open('example.file6.xml').read())
>>> etl.toxml(table1, 'example.file6.xml', rows='row/col', style='name')
>>> print(open('example.file6.xml').read())
a1
b2
The `toxml()` function is just a wrapper over :func:`petl.io.text.totext`.
For advanced cases use a template with `totext()` for generating xml files.
.. versionadded:: 1.7.0
.. _specification: https://www.w3.org/TR/xml/
.. _references: https://www.w3schools.com/xml/xml_syntax.asp
tablez thead/tr/thz tbody/tr/tdr Tstrict)r encodingerrorstemplateprologueepilogueN)r r
_build_xml_header _build_cols_build_xml_footerr
)rY targetrootheadrowsr^ r_ styler[ sampletable2propstopr] bottomr r r toxml
s ^
rm c C s |rt |dd nd}| dv rdnd}|r/t |d|} t| ||d}
t |d|} d| |
| } nd} t |d|}
|rI|drId || |
}|| S |rO| nd
}d | }|r]|s]|d nd}|rg|rgd | nd}d
|||| |
|}|S )NF attributenameTz
{0}
{1}{2}z
z{0}
{1}{2}{3}{4}{5}
)_build_nestingra format
startswithupper)rg rj rd re rf r^ r[ tabnestedth1colth2thdtbdthbencxmlpreposresr r r r` x s$ r` c C s` | dv rdnd}t |d|}t |dd}|r |r |d nd}|r&|s&d| nd}|| | | S )Nro rr rs Tr rt rn )ru ) rg r_ rf rd rz r ry r r r r r rb s rb c sj | sdS |rdnd d| vr | S | d}|r |d| n|}|r'| fdd|D }d|S )Nrn zz<%s>/r c s g | ]} | qS r r rQ fmtr r r3 s z"_build_nesting..)splitreversejoin)pathclosingindexpartselementstagsr r r ru s
ru c C sL | }| dks |rt |||dS | dkrt |||dS | dkr$t||S | S )NrW Trq Frp )_build_cols_inline_build_cols_attribs)rg rj r is_value is_headerr r r ra s
ra c s | d}|r t|dk rtd| |d }|dd d }nd}|d }|r*dnd}d || fd
d | D }d |} d
|| }
|
S )Nr r z Tag not in format 'row/col': %srr rs r z{0}z{{{0}}}z<{0}>{1}c r- r rv rQ r r r r3 z&_build_cols_inline..rn z <{0}>{1}
)r r
ValueErrorrv r ) rj r r use_tagr r| rowfldcolsr r r r r r s
r c sB | d}|d }d fdd| D }d|}d||}|S )Nr rr z
{0}="{{{0}}}"c r- r r rQ r r r r3 r z'_build_cols_attribs.. z
<{0} {1} />
)r r rv )rj r r r r attsr r r r r s
r )NNNNNNrW rX )#
__future__r r r lxmlr ImportErrorxml.etree.ElementTree ElementTreeoperatorr r> petl.compatr r petl.util.baser r
r petl.io.sourcesr petl.io.textr
r r r; rC rD rm r` rb ru ra r r r r r r s6 ~Q
n