Xml2Yaml.py

#!/usr/bin/env python

import sys, string, re, types
import yaml

from xml.dom import minidom
from xml.dom import Node


#
# Convert an XML document (file) to YAML and write it to stdout.
#
def convertXml2Yaml(inFileName):
    doc = minidom.parse(inFileName)
    out = []
    out.append('---\n')
    level = 0
    root = doc.childNodes[0]
    convertXml2YamlAux(root, level, out)
    content = "".join(out)
    sys.stdout.write(content)


def convertXml2YamlAux(obj, level, out):
    level += 1
    # Dump the attributes.
    attrs = obj.attributes
    if attrs.length > 0:
        level += 1
        for idx in range(attrs.length):
            attr = attrs.item(idx)
            out.append('  %s: %s\n' % (attr.name, attr.value))
        level -= 1
    # Dump the text.
    text = []
    for child in obj.childNodes:
        if child.nodeType == Node.TEXT_NODE and \
            not isAllWhiteSpace(child.nodeValue):
            text.append(child.nodeValue)
    if text:
        textStr = "".join(text)
        out.append('  value: "%s"\n' % textStr)
    # Dump the children.
    found = 0
    for child in obj.childNodes:
        if child.nodeType == Node.ELEMENT_NODE:
            found = 1
            break
    if found:
        level += 1
        for child in obj.childNodes:
            if child.nodeType == Node.ELEMENT_NODE:
                convertXml2YamlAux(child, level, out)


NonWhiteSpacePattern = re.compile('\S')

def isAllWhiteSpace(text):
    if NonWhiteSpacePattern.search(text):
        return 0
    return 1


USAGE_TEXT = """
Convert a file from YAML to XML or XML to YAML and write it to stdout.

Usage: python convertyaml.py <option> <in_file>

Options:
    -x2y    Convert XML document to YAML.
"""

def usage():
    print USAGE_TEXT
    sys.exit(-1)


def main():
    args = sys.argv[1:]
    if len(args) != 2:
        usage()
    option = args[0]
    inFileName = args[1]
    if option == '-x2y':
        convertXml2Yaml(inFileName)
    else:
        usage()


if __name__ == '__main__':
    main()
    #import pdb
    #pdb.run('main()')