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.
+See detailed installation instructions at
+http://phdru.name/Software/mc/xml_INSTALL.html.
+
The VFS represents tags as directories; the directories are numbered to
-distinguish tags with the same name; also numbering helps to sort tags by their
-order in XML instead of sorting them by name. Attributes, text nodes and
-comments are represented as text files; attributes are shown in a file named
-"attributes", attributes are listed in the file as name=value lines (I
-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
+distinguish tags with the same name; numbering also helps to sort tags by their
+order in XML instead of sorting them by name and prevents name clash when tag
+names coincide with the names of special files used by XML VFS. Attributes,
+text nodes and comments are represented as text files; attributes are shown in
+a file named "attributes", attributes are listed in the file as name=value
+lines (I 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.
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.
+separate file "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__ = "0.5.1"
+__version__ = "1.1.4"
__author__ = "Oleg Broytman <phd@phdru.name>"
-__copyright__ = "Copyright (C) 2013 PhiloSoft Design"
+__copyright__ = "Copyright (C) 2013-2015 PhiloSoft Design"
__license__ = "GPL"
-default_implementation = None # Can be None for default choice,
- # 'lxml', 'elementtree' or 'minidom'
+force_implementation = None # Can be None for default choice,
+ # 'lxml', 'elementtree' or 'minidom'
use_minidom = True
use_elementtree = False
class XmlVfs(object):
+ """Abstract base class"""
+
+ supports_namespaces = False
+
def __init__(self):
self.parse()
def list(self):
+ root_comments = self.get_root_comments()
+ if root_comments:
+ print "-r--r--r-- 1 user group %d Jan 1 00:00 text" % (len(root_comments))
self._list(self.getroot())
- def has_ns(self, node):
- return False
-
- def get_child_node(self, node, i):
+ def _list(self, node, path=''):
+ n = len(self.getchildren(node))
+ if n:
+ width = int(math.log10(n)) + 1
+ template = "%%0%dd" % width
+ else:
+ template = "%d"
+ n = 0
+ for element in self.getchildren(node):
+ if not self.istag(element):
+ continue
+ n += 1
+ tag = self.getlocalname(self.gettag(element))
+ if path:
+ subpath = '%s/%s %s' % (path, template % n, tag)
+ else:
+ subpath = '%s %s' % (template % n, tag)
+ subpath_encoded = subpath.encode(default_encoding, "replace")
+ print "dr-xr-xr-x 1 user group 0 Jan 1 00:00 %s" % subpath_encoded
+ if self.getattrs(element):
+ 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 self.supports_namespaces and self.has_ns(element):
+ 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" % (
+ len(text), subpath_encoded)
+ self._list(element, subpath)
+
+ def get_tag_node(self, node, i):
n = 0
for element in self.getchildren(node):
if self.istag(element):
return element
xml_error('There are less than %d nodes' % i)
+ def attrs2text(self, node):
+ attr_accumulator = []
+ for name, value in self.getattrs(node):
+ name = self.getlocalname(name).encode(default_encoding, "replace")
+ value = value.encode(default_encoding, "replace")
+ attr_accumulator.append("%s=%s" % (name, value))
+ return '\n'.join(attr_accumulator)
+
+ def has_ns(self, node):
+ return False
+
class MiniDOMXmlVfs(XmlVfs):
def parse(self):
self.document = xml.dom.minidom.parse(sys.argv[2])
- def hasattrs(self, node):
- return bool(node.attributes)
-
- def attrs2text(self, node):
+ def getattrs(self, node):
attrs = node.attributes
- 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"))
- for a in attrs])
+ attrs = [attrs.item(i) for i in range(attrs.length)]
+ return [(a.name, a.value) for a in attrs]
def collect_text(self, node):
text_accumulator = []
if text: text_accumulator.append(text)
return '\n'.join(text_accumulator).encode(default_encoding, "replace")
- def _list(self, node, path=''):
- childNodes = node.childNodes
- n = 0
- for element in childNodes:
- if element.localName:
- n += 1
- if n:
- width = int(math.log10(n))+1
- template = "%%0%dd" % width
- else:
- template = "%d"
- n = 0
- for element in childNodes:
- if element.localName:
- n += 1
- if path:
- subpath = '%s/%s %s' % (path, template % n, element.localName)
- else:
- subpath = '%s %s' % (template % n, element.localName)
- subpath_encoded = subpath.encode(default_encoding, "replace")
- print "dr-xr-xr-x 1 user group 0 Jan 1 00:00 %s" % subpath_encoded
- if self.hasattrs(element):
- attr_text = self.attrs2text(element)
- print "-r--r--r-- 1 user group %d Jan 1 00:00 %s/attributes" % (
- len(attr_text), subpath_encoded)
- text = self.collect_text(element)
- if text:
- print "-r--r--r-- 1 user group %d Jan 1 00:00 %s/text" % (
- len(text), subpath_encoded)
- self._list(element, subpath)
-
def getroot(self):
return self.document
+ def get_root_comments(self):
+ return self.collect_text(self.document)
+
def getchildren(self, node):
return node.childNodes
+ def gettag(self, node):
+ return node.localName
+
def istag(self, node):
return bool(node.localName)
+ def getlocalname(self, name):
+ return name
+
if use_elementtree or use_lxml:
class CommonEtreeXmlVfs(XmlVfs):
- def hasattrs(self, node):
- return bool(node.attrib)
+ def getattrs(self, node):
+ return node.attrib.items()
def collect_text(self, node):
text_accumulator = []
if text: text_accumulator.append(text)
return '\n'.join(text_accumulator).encode(default_encoding, "replace")
- def getroot(self):
- return self.document.getroot()
-
def getchildren(self, node):
return list(node)
+ def gettag(self, node):
+ return node.tag
+
def istag(self, node):
return isinstance(node.tag, basestring)
if use_elementtree:
class ElementTreeXmlVfs(CommonEtreeXmlVfs):
def parse(self):
- # Copied from http://effbot.org/zone/element-pi.ht
+ # Copied from http://effbot.org/zone/element-pi.htm
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())
- def attrs2text(self, node):
- attr_accumulator = []
- for name, value in node.attrib.items():
- name = name.encode(default_encoding, "replace")
- value = value.encode(default_encoding, "replace")
- if name.startswith('{'):
- name = name.split('}', 1)[1] # Remove XML namespace
- attr_accumulator.append("%s=%s" % (name, value))
- return '\n'.join(attr_accumulator)
-
- def _list(self, node, path=''):
- n = len(node)
- if n:
- width = int(math.log10(n))+1
- template = "%%0%dd" % width
- else:
- template = "%d"
- n = 0
- for element in node:
- if not isinstance(element.tag, basestring):
- continue
- n += 1
- tag = element.tag
- if tag.startswith('{'):
- tag = tag.split('}', 1)[1] # Remove XML namespace
- if path:
- subpath = '%s/%s %s' % (path, template % n, tag)
- else:
- subpath = '%s %s' % (template % n, tag)
- subpath_encoded = subpath.encode(default_encoding, "replace")
- print "dr-xr-xr-x 1 user group 0 Jan 1 00:00 %s" % subpath_encoded
- if self.hasattrs(element):
- attr_text = self.attrs2text(element)
- print "-r--r--r-- 1 user group %d Jan 1 00:00 %s/attributes" % (
- len(attr_text), subpath_encoded)
- text = self.collect_text(element)
- if text:
- print "-r--r--r-- 1 user group %d Jan 1 00:00 %s/text" % (
- len(text), subpath_encoded)
- self._list(element, subpath)
+ def getroot(self):
+ return self.document.getroot()
+
+ def get_root_comments(self):
+ text_accumulator = []
+ for element in self.getroot():
+ if not self.istag(element):
+ text = u"<!--%s-->" % element.text
+ text_accumulator.append(text)
+ return '\n'.join(text_accumulator).encode(default_encoding, "replace")
+
+ def getlocalname(self, name):
+ if name.startswith('{'):
+ name = name.split('}', 1)[1] # Remove XML namespace
+ return name
if use_lxml:
class LxmlEtreeXmlVfs(CommonEtreeXmlVfs):
+ supports_namespaces = True
+
def parse(self):
self.document = etree.parse(sys.argv[2])
- def attrs2text(self, node):
- attr_accumulator = []
- for name, value in node.attrib.items():
- name = etree.QName(name).localname.encode(default_encoding, "replace")
- value = value.encode(default_encoding, "replace")
- attr_accumulator.append("%s=%s" % (name, value))
- return '\n'.join(attr_accumulator)
+ def getroot(self):
+ return [self.document.getroot()]
+
+ def get_root_comments(self):
+ text_accumulator = []
+ for element in self.document.getroot().itersiblings(tag=etree.Comment, preceding=True):
+ text = u"<!--%s-->" % element.text
+ text_accumulator.append(text)
+ return '\n'.join(text_accumulator).encode(default_encoding, "replace")
+
+ def getlocalname(self, name):
+ return etree.QName(name).localname
+
+ def _get_local_ns(self, node):
+ this_nsmap = node.nsmap
+ parent = node.getparent()
+ if parent is not None:
+ parent_nsmap = parent.nsmap
+ for key in parent_nsmap:
+ if this_nsmap[key] == parent_nsmap[key]:
+ del this_nsmap[key]
+ return this_nsmap
def has_ns(self, node):
- return bool(node.nsmap)
+ return bool(self._get_local_ns(node))
def ns2text(self, node):
ns_accumulator = []
- for name, value in node.nsmap.items():
- name = name.encode(default_encoding, "replace")
+ for name, value in self._get_local_ns(node).items():
+ if name:
+ name = name.encode(default_encoding, "replace")
+ else:
+ name = 'xmlns'
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())
-
- def _list(self, node, path=''):
- n = len(node)
- if n:
- width = int(math.log10(n))+1
- template = "%%0%dd" % width
- else:
- template = "%d"
- n = 0
- for element in node:
- if not isinstance(element.tag, basestring):
- continue
- n += 1
- tag = etree.QName(element.tag).localname
- if path:
- subpath = '%s/%s %s' % (path, template % n, tag)
- else:
- subpath = '%s %s' % (template % n, tag)
- subpath_encoded = subpath.encode(default_encoding, "replace")
- print "dr-xr-xr-x 1 user group 0 Jan 1 00:00 %s" % subpath_encoded
- if self.hasattrs(element):
- 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" % (
- len(text), subpath_encoded)
- self._list(element, subpath)
-
- def getroot(self):
- return [self.document.getroot()]
-
def build_xmlvfs():
- if default_implementation is None:
+ if force_implementation is None:
if use_lxml:
return LxmlEtreeXmlVfs()
elif use_elementtree:
return ElementTreeXmlVfs()
else:
return MiniDOMXmlVfs()
- elif default_implementation == 'minidom':
+ elif force_implementation == 'minidom':
return MiniDOMXmlVfs()
- elif default_implementation == 'elementtree':
+ elif force_implementation == 'elementtree':
return ElementTreeXmlVfs()
- elif default_implementation == 'lxml':
+ elif force_implementation == 'lxml':
return LxmlEtreeXmlVfs()
+ else:
+ raise ValueError('Unknown implementation "%s", expected "minidom", "elementtree" or "lxml"' % force_implementation)
def mcxml_list():
for path_comp in xml_filename.split('/'):
if ' ' in path_comp:
i = int(path_comp.split(' ', 1)[0])
- node = xmlvfs.get_child_node(node, i)
+ node = xmlvfs.get_tag_node(node, i)
elif path_comp in ('attributes', 'namespaces', 'text'):
break
else:
xml_error('Unknown file')
if path_comp == 'attributes':
- if xmlvfs.hasattrs(node):
+ if xmlvfs.getattrs(node):
text = xmlvfs.attrs2text(node)
else:
xml_error('There are no attributes')
elif path_comp == 'namespaces':
- if xmlvfs.has_ns(node):
+ if xmlvfs.supports_namespaces and xmlvfs.has_ns(node):
text = xmlvfs.ns2text(node)
else:
- xml_error('There are no attributes')
+ xml_error('There are no namespaces')
elif path_comp == 'text':
- text = xmlvfs.collect_text(node)
+ if '/' in xml_filename:
+ text = xmlvfs.collect_text(node)
+ else:
+ text = xmlvfs.get_root_comments()
else:
xml_error('Unknown file')