The script requires Midnight Commander 3.1+
(http://www.midnight-commander.org/), Python 2.4+ (http://www.python.org/).
-For mc 4.7+ put the script in $HOME/[.local/share/].mc/extfs.d.
+For mc 4.7+ just put the script in $HOME/[.local/share/].mc/extfs.d.
For older versions put it in /usr/[local/][lib|share]/mc/extfs
and add a line "xml" to the /usr/[local/][lib|share]/mc/extfs/extfs.ini.
Make the script executable.
For mc 4.7+ run this "cd" command in the Midnight Commander (in the "bindings"
-file the command is "%cd"): cd file/xml://; In older versions it is
+file the command is "%cd"): cd file/xml://; in older versions it is
cd file#xml, where "file" is the name of your XML file.
The VFS represents tags as directories; the directories are numbered to
deliberately ignore a small chance of newline characters in values); names and
values are reencoded to the console encoding. Text nodes and comments are
collected in a file named "text", stripped and reencoded. The filesystem is
-read-only. ElementTree- and lxml.etree-based implementations don't show
-namespaces as attributes.
+read-only.
+
+Implementation based on minidom doesn't understand namespaces, it just shows
+them among other attributes. ElementTree-based implementation doesn't show
+namespaces at all. Implementation based on lxml.etree shows namespaces in a
+separate file "namespaces"; every child tag includes its parent's namespaces.
It is useful to have a top-down view on an XML structure but it's especially
convenient to extract text values from tags. One can get, for example, a
"""
-__version__ = "0.5.0"
+__version__ = "0.5.1"
__author__ = "Oleg Broytman <phd@phdru.name>"
__copyright__ = "Copyright (C) 2013 PhiloSoft Design"
__license__ = "GPL"
-default_implementation = None # Can be None for default choice,
- # 'lxml', 'elementtree' or 'minidom'
+default_implementation = None # Can be None for default choice,
+ # 'lxml', 'elementtree' or 'minidom'
use_minidom = True
use_elementtree = False
def list(self):
self._list(self.getroot())
+ def has_ns(self, node):
+ return False
+
def get_child_node(self, node, i):
n = 0
for element in self.getchildren(node):
def attrs2text(self, node):
attrs = node.attributes
- attrs = [attrs.item(i) for i in range (attrs.length)]
+ attrs = [attrs.item(i) for i in range(attrs.length)]
return '\n'.join(["%s=%s" %
(a.name.encode(default_encoding, "replace"),
a.value.encode(default_encoding, "replace"))
if element.localName:
n += 1
if n:
- width = int(math.log10(n))+1
+ width = int(math.log10(n)) + 1
template = "%%0%dd" % width
else:
template = "%d"
if text: text_accumulator.append(text)
for element in node:
if not self.istag(element):
- text = u"<!--%s-->" % text
+ text = u"<!--%s-->" % element.text
text_accumulator.append(text)
if node.tail:
text = node.tail.strip()
class PIParser(ET.XMLTreeBuilder):
- def __init__(self):
- ET.XMLTreeBuilder.__init__(self)
- # assumes ElementTree 1.2.X
- self._parser.CommentHandler = self.handle_comment
- self._parser.ProcessingInstructionHandler = self.handle_pi
- self._target.start("document", {})
+ def __init__(self):
+ ET.XMLTreeBuilder.__init__(self)
+ # assumes ElementTree 1.2.X
+ self._parser.CommentHandler = self.handle_comment
+ self._parser.ProcessingInstructionHandler = self.handle_pi
+ self._target.start("document", {})
- def close(self):
- self._target.end("document")
- return ET.XMLTreeBuilder.close(self)
+ def close(self):
+ self._target.end("document")
+ return ET.XMLTreeBuilder.close(self)
- def handle_comment(self, data):
- self._target.start(ET.Comment, {})
- self._target.data(data)
- self._target.end(ET.Comment)
+ def handle_comment(self, data):
+ self._target.start(ET.Comment, {})
+ self._target.data(data)
+ self._target.end(ET.Comment)
- def handle_pi(self, target, data):
- self._target.start(ET.PI, {})
- self._target.data(target + " " + data)
- self._target.end(ET.PI)
+ def handle_pi(self, target, data):
+ self._target.start(ET.PI, {})
+ self._target.data(target + " " + data)
+ self._target.end(ET.PI)
self.document = ET.parse(sys.argv[2], PIParser())
attr_accumulator.append("%s=%s" % (name, value))
return '\n'.join(attr_accumulator)
+ def has_ns(self, node):
+ return bool(node.nsmap)
+
+ def ns2text(self, node):
+ ns_accumulator = []
+ for name, value in node.nsmap.items():
+ name = name.encode(default_encoding, "replace")
+ value = value.encode(default_encoding, "replace")
+ ns_accumulator.append("%s=%s" % (name, value))
+ return '\n'.join(ns_accumulator)
+
def list(self):
self._list(self.getroot())
attr_text = self.attrs2text(element)
print "-r--r--r-- 1 user group %d Jan 1 00:00 %s/attributes" % (
len(attr_text), subpath_encoded)
+ if element.nsmap:
+ ns_text = self.ns2text(element)
+ print "-r--r--r-- 1 user group %d Jan 1 00:00 %s/namespaces" % (
+ len(ns_text), subpath_encoded)
text = self.collect_text(element)
if text:
print "-r--r--r-- 1 user group %d Jan 1 00:00 %s/text" % (
if ' ' in path_comp:
i = int(path_comp.split(' ', 1)[0])
node = xmlvfs.get_child_node(node, i)
- elif path_comp in ('attributes', 'text'):
+ elif path_comp in ('attributes', 'namespaces', 'text'):
break
else:
xml_error('Unknown file')
else:
xml_error('There are no attributes')
- if path_comp == 'text':
+ elif path_comp == 'namespaces':
+ if xmlvfs.has_ns(node):
+ text = xmlvfs.ns2text(node)
+ else:
+ xml_error('There are no attributes')
+
+ elif path_comp == 'text':
text = xmlvfs.collect_text(node)
+ else:
+ xml_error('Unknown file')
+
outfile = open(real_filename, 'w')
outfile.write(text)
outfile.close()