Fix a bug in handling comments

[extfs.d.git] / xml

diff --git a/xml b/xml
index 084a78483553f2f6cfed759bcce5b5efdfc85904..3d40d375e081a976a2b9c55d0572c564223e78f3 100755 (executable)
--- a/xml
+++ b/xml
@@ -4,13 +4,13 @@
 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
@@ -21,8 +21,12 @@ comments are represented as text files; attributes are shown in a file named
 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
@@ -33,7 +37,7 @@ The VFS was inspired by a FUSE xmlfs: https://github.com/halhen/xmlfs
 
 """
 
-__version__ = "0.5.0"
+__version__ = "0.5.1"
 __author__ = "Oleg Broytman <phd@phdru.name>"
 __copyright__ = "Copyright (C) 2013 PhiloSoft Design"
 __license__ = "GPL"
@@ -117,6 +121,9 @@ class XmlVfs(object):
     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):
@@ -209,7 +216,7 @@ if use_elementtree or use_lxml:
                 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()
@@ -311,6 +318,17 @@ if use_lxml:
                 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())
 
@@ -337,6 +355,10 @@ if use_lxml:
                     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" % (
@@ -382,7 +404,7 @@ def mcxml_copyout():
         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')
@@ -393,9 +415,18 @@ def mcxml_copyout():
         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()