Formatando XML com ElementTree
Uma busca rápida na web sobre como formatar um arquivo XML de forma que ele fique "bonito" para humanos resulta em poucas ocorrências. Com Python, uma das poucas coisas é um artigo de BruceEckel de 2003 - que também não dá a resposta.
Felizmente temos vários geradores de XML na biblioteca padrão. E, para alterar um gerador de XML bem escrito de forma que ele insira quebras de linha e identação num arquivo XML são necessárias bem poucas alterações.
Escolhi o ElementTree por ter um código python bem fácil de entender. Poderia ter herdado o ElementTree e feito as alterações necessárias na sub-classe, (o jeito "certo" ) - mas para o que eu precisava aqui, uma alteração do tipo "monkey patch" se prestava melhor.
Como é CookBook, também fica exemplo de como fazer o Monkey Patching - sempre lembrando que todos os outros usuários do módulo alterado na mesma aplicação serão afetados.
Formatador de XML
#coding: utf-8
# Author: Firederich Lung, João S. O. Bueno
# Copyright (c) 1999-2005 by Fredrik Lundh (geração de XML)
#Copyrigjt (c) 2009 Fundação CPqD - Formatação do XML e partes auxiliares do script
#
# By obtaining, using, and/or copying this software and/or its
# associated documentation, you agree that you have read, understood,
# and will comply with the following terms and conditions:
#
# Permission to use, copy, modify, and distribute this software and
# its associated documentation for any purpose and without fee is
# hereby granted, provided that the above copyright notice appears in
# all copies, and that both that copyright notice and this permission
# notice appear in supporting documentation, and that the name of
# Secret Labs AB or the author not be used in advertising or publicity
# pertaining to distribution of the software without specific, written
# prior permission.
#
# SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD
# TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANT-
# ABILITY AND FITNESS. IN NO EVENT SHALL SECRET LABS AB OR THE AUTHOR
# BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY
# DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
# WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
# ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
# OF THIS SOFTWARE.
# --------------------------------------------------------------------
# Licensed to PSF under a Contributor Agreement.
# See http://www.python.org/2.4/license for licensing details.
"""
Modifies the XML generator in ElementTree in order to create
a "human-readable", indentend by level, XML output.
Can be used as a stand alone script, or to change ElementTree XML generation
on the fly through a call to "monkey_patch_etree" function.
"""
import xml.etree.ElementTree
from xml.etree.ElementTree import Comment, _encode, ProcessingInstruction,\
QName, fixtag, _escape_attrib, _escape_cdata
def Etree_pretty__write(self, file, node, encoding, namespaces,
level=0, identator=" "):
# write XML to file
tag = node.tag
if tag is Comment:
file.write(level * identator + "<!-- %s -->" % _escape_cdata(node.text, encoding))
elif tag is ProcessingInstruction:
file.write("<?%s?>" % _escape_cdata(node.text, encoding))
else:
items = node.items()
xmlns_items = [] # new namespaces in this scope
try:
if isinstance(tag, QName) or tag[:1] == "{":
tag, xmlns = fixtag(tag, namespaces)
if xmlns: xmlns_items.append(xmlns)
except TypeError:
_raise_serialization_error(tag)
file.write("\n" + level * identator + "<" + _encode(tag, encoding))
if items or xmlns_items:
items.sort() # lexical order
for k, v in items:
try:
if isinstance(k, QName) or k[:1] == "{":
k, xmlns = fixtag(k, namespaces)
if xmlns: xmlns_items.append(xmlns)
except TypeError:
_raise_serialization_error(k)
try:
if isinstance(v, QName):
v, xmlns = fixtag(v, namespaces)
if xmlns: xmlns_items.append(xmlns)
except TypeError:
_raise_serialization_error(v)
file.write(" %s=\"%s\"" % (_encode(k, encoding),
_escape_attrib(v, encoding)))
for k, v in xmlns_items:
file.write(" %s=\"%s\"" % (_encode(k, encoding),
_escape_attrib(v, encoding)))
if node.text or len(node):
file.write(">")
if node.text:
file.write(_escape_cdata(node.text.replace("\n", (level + 1) * identator + "\n"), encoding))
for n in node:
self._write(file, n, encoding, namespaces, level + 1, identator)
file.write("\n" + level * identator + "</" + _encode(tag, encoding) + ">")
else:
file.write(" />")
for k, v in xmlns_items:
del namespaces[v]
if node.tail:
file.write(_escape_cdata(node.tail.replace("\n", level * identator + "\n"), encoding))
original__write = xml.etree.ElementTree.ElementTree._write
def monkey_patch_etree():
"""
Call this method to overwrite python's native library
xml.etree.ElementTree.ElementTree _write method in order to produce
humam-pleasant formated output
"""
xml.etree.ElementTree.ElementTree._write = Etree_pretty__write
def un_monkey_patch_etree():
"""Use to restore default behavior to ElementTree's XML generation"""
xml.etree.ElementTree.ElementTree._write = original__write
def de_tokenize(text):
"""removes html tokens from the "Ã" type """
r = re.compile(r"\&\#([0-9]{1,3})\;")
caracteres = set(r.findall(text))
textn = text
for caracter in caracteres:
caracter = int(caracter)
r = re.compile(r"\&\#%d\;" % caracter)
textn = r.subn(chr(caracter), textn)[0]
return textn
if __name__ == "__main__":
import sys, re
if len(sys.argv) != 3:
sys.stderr.write("Usage: prettyxml.py <inputfile> <outputfile>\n")
sys.exit(1)
infile = open(sys.argv[1], "rt")
outfile = open(sys.argv[2], "wt")
monkey_patch_etree()
xmldata = xml.etree.ElementTree.parse(infile)
xmlstring = de_tokenize(xml.etree.ElementTree.tostring(xmldata.getroot()))
outfile.write(xmlstring)
outfile.close()
Muita hora nessa calma
Embora o código que gera XML acima possa "assustar", é bom lembrar que foram feitas poucas alterações em cima do código original da ElementTree, qeu só foi copiado e colado.
Segue uma pequena listagem só com as diferenças entre o método _write do objeto Element de xml.etree.ElementTree e o méotodo que eu ponho em seu lugar - pode se observar que não fiz mais que inserir as uquberas de linha e espaçamento nos pontos em que eu gostaria:
--- orig.py 2009-02-09 11:12:44.000000000 -0200
+++ changed.py 2009-02-09 11:09:45.000000000 -0200
@@ -1 +1,2 @@
-def _write(self, file, node, encoding, namespaces):
+def Etree_pretty__write(self, file, node, encoding, namespaces,
+ level=0, identator=" "):
@@ -5 +6 @@
- file.write("<!-- %s -->" % _escape_cdata(node.text, encoding))
+ file.write(level * identator + "<!-- %s -->" % _escape_cdata(node.text, encoding))
@@ -17 +18 @@
- file.write("<" + _encode(tag, encoding))
+ file.write("\n" + level * identator + "<" + _encode(tag, encoding))
@@ -41 +42 @@
- file.write(_escape_cdata(node.text, encoding))
+ file.write(_escape_cdata(node.text.replace("\n", (level + 1) * identator + "\n"), encoding))
@@ -43,2 +44,2 @@
- self._write(file, n, encoding, namespaces)
- file.write("</" + _encode(tag, encoding) + ">")
+ self._write(file, n, encoding, namespaces, level + 1, identator)
+ file.write("\n" + level * identator + "</" + _encode(tag, encoding) + ">")
@@ -50 +51 @@
- file.write(_escape_cdata(node.tail, encoding))
+ file.write(_escape_cdata(node.tail.replace("\n", level * identator + "\n"), encoding))
