This is merely a sketch for a bare-bones XML 1.0 generator.I wrote it for working on little tasks for which other generators seem to be too much complex. Python version used to test this code was 2.4.3 on a Win32 platform.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 | __name__ = 'xmlfetch.py'
__author__ = 'Trionice'
__date__ = '9-11-2006'
__version__ = '0.1.1'
__license__ = 'GPL'
__copyright__ = 'Copyright (c) Ivan Furone, 2006'
__all__ = ['xmlfetch','operator','repr','types']
filter(__import__, __all__)
class XMLObj(object):
tree = str()
def __init__(self,tree=''):
self.tree = tree + XMLObj.tree
return self.tree
class XMLFetch(XMLObj):
def __init__(self, version=1.0, charset="UTF-8", standalone="yes"):
self.version = version
self.charset = charset
self.standalone = standalone
self.tree = XMLObj.__init__(self,tree=XMLObj.tree)
self.nodes = ()
def _gendecl(self):
"""
Returns a string representing a standard XML 1.0 declaration equal
as it is default initialized in __init__.
"""
return '<? xml version="%f" charset="%s" standalone="%s"?>' \
% (self.version,self.charset,self.standalone)
def _embedparser(self, tree, XMLparser='xml.sax'):
"""
Returns a correctly parsed chunk of valid xml according to the parsing
libraries it relies on (currently it relies on xml.sax only)
"""
from xml.sax.handler import ContentHandler
if XMLparser == 'xml.sax':import xml.sax
pstring = tree;TempHandler = ContentHandler()
try:
do_parse = xml.sax.parseString(pstring,TempHandler)
except:
return False
return True
def _is_node(self, node):
"""
Checks if a given node is present in the class dict that holds the nodes for
further processing.
"""
is_node = node in self.__dict__[nodes]
if is_node:
flag = True
return flag
def _diffnode(self, node):
"""
Find equivalence between two nodes.
"""
if map (self._is_node,(nodeA, nodeB))[0] == True:
diff = cmp(self, nodeA, nodeB)
if diff == 0:
return nodeA
else: return None
def yieldattr(self, attr):
"""
Takes as argument a dictionary which keys are the names of a node's
attributes,each one bound with their value.It processes the dict's items,
returning a string from the resulting list of just-unpacked tuples.
"""
t = attr.items()
t2 = []
for item in t[:]:
t2.append(' %s = "%s" ' %(item[0],item[1]))
if not item:
break
try :
return ''
except :
pass
else :
continue
return str(t2).lstrip("['").rstrip("']").replace("'","").replace(",","")
def buildnode(self, nodename, splitargs, attrib={}, content=''):
"""
Takes a node's name,attributes and content - a string,a mapping and another
string respectively - and returns an XML node crafted accordingly with
the parameters aforementioned.
nodename is the node's name expressed as a string;splitargs is a boolean
which when set to zero returns the node as a whole element,and when set to
1 will return each one separately inspite.
"""
node1 = '<' + nodename + self.yieldattr(attrib) + '>'
node2 = '</' + nodename + '>'
if splitargs == 0:
node = node1 + content + node2
return node
else:
return node1,content,node2
def enclosenode(self, parent, node, pcontent='',ncontent='',\
pattrib=None, nattrib=None):
"""
Takes as arguments the name of a parent node,that of a child one,their
attributes and contents respectively expressed;returns a new entity formed
by the two nodes - in other words the child folded in the parent.
Wrapper around buildnode
"""
tmparent = parent
tmpnode = node
tmparent = self.buildnode(parent,1,attrib = pattrib,content = pcontent)
tmpnode = self.buildnode(node,0,attrib = nattrib, content = ncontent)
node = tmparent[0] + pcontent + tmpnode + tmparent[2]
return node
def buildcdata(self, text):
"""
Returns a CDATA section out of a string.
"""
cdata = text
return '<!CDATA[' + cdata + ']]>'
def buildcomment(self, text, center=0):
"""
Returns a comment out of a string.
"""
comment = text
return '<!--' + comment + '-->'
def appendnode(self, node, tree):
"""
Appends a node - without interpolation - to the XMLFetch's classdict
returns True if the node has been inserted,and ValueError if it is not.
(This happens usually if the mapping that holds the nodes itself has been
altered to be read-only.)
"""
if node is not StringTypes:
tmpnode = str(node)
node = tmpnode
else :
pass
self.__dict__[nodes].append(node)
return node in self.__dict__[nodes]
def getnodesfromdict(self):
"""
Acquires the node list from self.__dict__ .
"""
nodelist = []
for node in self.__dict__[nodes]:
nodelist.append(node)
return nodelist
def composeXML(self, tree, add_decl=1):
"""
Retrieves a XML tree previously defined elsewhere and declaration is added
if add_decl is 1.
"""
worktree = tree
tmptree = str(getnodes())
if add_decl == 0:
decl = self._gendecl()
tree = decl + tmptree
else: tree = worktree
return tree
def XMLtoFileObject(self, fname, tree=None):
"""
Gets as arguments a filename and a tree then writes the tree to a file with
the given filename.Returns true if everything has been accomplished
correctly.A IO error is also raised in the bad case.
"""
try :
import os.path
xmlworktree = tree
if os.path.exists(fname):
xmlobj = file(fname,mode='ab+')
else:
xmlobj = file(fname,mode='wb+')
xmlobj.write(xmlworktree)
xmlobj.close()
return True
except ImportError:
raise ImportError, "os.path missing or behaving uncorrectly.Review your \
Python's version notes"
|
I feel to be still very far to write a general-purpose code starting from this but the bulk functionalities are implemented and (almost completely) tested,so making use of it is at your choice.Please let me know your impressions if you try this one.