Web   ·   Wiki   ·   Activities   ·   Blog   ·   Lists   ·   Chat   ·   Meeting   ·   Bugs   ·   Git   ·   Translate   ·   Archive   ·   People   ·   Donate
summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rwxr-xr-x.hg/00changelog.ibin0 -> 57 bytes
-rwxr-xr-x.hg/dirstatebin0 -> 358 bytes
-rwxr-xr-x.hg/requires2
-rwxr-xr-x.hg/store/00changelog.ibin0 -> 397 bytes
-rwxr-xr-x.hg/store/00manifest.ibin0 -> 842 bytes
-rwxr-xr-x.hg/store/data/_beautiful_soup.py.ibin0 -> 21139 bytes
-rwxr-xr-x.hg/store/data/activity/activity.info.ibin0 -> 186 bytes
-rwxr-xr-x.hg/store/data/activity/journalmanager-activity.svg.ibin0 -> 644 bytes
-rwxr-xr-x.hg/store/data/activity/permissions.info.ibin0 -> 78 bytes
-rwxr-xr-x.hg/store/data/journalmanager.py.ibin0 -> 224 bytes
-rwxr-xr-x.hg/store/data/listview.py.ibin0 -> 1609 bytes
-rwxr-xr-x.hg/store/data/objectchooser.py.ibin0 -> 1460 bytes
-rwxr-xr-x.hg/store/data/objectfetch.py.ibin0 -> 1498 bytes
-rwxr-xr-x.hg/store/data/xoconfig.ibin0 -> 282 bytes
-rwxr-xr-x.hg/store/undobin0 -> 35 bytes
-rwxr-xr-x.hg/undo.branch1
-rwxr-xr-x.hg/undo.dirstatebin0 -> 358 bytes
-rwxr-xr-xBeautifulSoup.py2000
-rwxr-xr-xactivity/activity.info7
-rwxr-xr-xactivity/datamanager-activity.svg11
-rwxr-xr-xactivity/permissions.info1
-rwxr-xr-xdatamanager.py12
-rwxr-xr-xfilelisting.py168
-rwxr-xr-xlistview.py144
-rwxr-xr-xobjectchooser.py118
-rwxr-xr-xobjectfetch.py120
-rwxr-xr-xpath.py971
-rwxr-xr-xxoconfig25
28 files changed, 3580 insertions, 0 deletions
diff --git a/.hg/00changelog.i b/.hg/00changelog.i
new file mode 100755
index 0000000..d3a8311
--- /dev/null
+++ b/.hg/00changelog.i
Binary files differ
diff --git a/.hg/dirstate b/.hg/dirstate
new file mode 100755
index 0000000..ea9d567
--- /dev/null
+++ b/.hg/dirstate
Binary files differ
diff --git a/.hg/requires b/.hg/requires
new file mode 100755
index 0000000..57601b5
--- /dev/null
+++ b/.hg/requires
@@ -0,0 +1,2 @@
+revlogv1
+store
diff --git a/.hg/store/00changelog.i b/.hg/store/00changelog.i
new file mode 100755
index 0000000..37b9876
--- /dev/null
+++ b/.hg/store/00changelog.i
Binary files differ
diff --git a/.hg/store/00manifest.i b/.hg/store/00manifest.i
new file mode 100755
index 0000000..738f818
--- /dev/null
+++ b/.hg/store/00manifest.i
Binary files differ
diff --git a/.hg/store/data/_beautiful_soup.py.i b/.hg/store/data/_beautiful_soup.py.i
new file mode 100755
index 0000000..6074600
--- /dev/null
+++ b/.hg/store/data/_beautiful_soup.py.i
Binary files differ
diff --git a/.hg/store/data/activity/activity.info.i b/.hg/store/data/activity/activity.info.i
new file mode 100755
index 0000000..fed86ea
--- /dev/null
+++ b/.hg/store/data/activity/activity.info.i
Binary files differ
diff --git a/.hg/store/data/activity/journalmanager-activity.svg.i b/.hg/store/data/activity/journalmanager-activity.svg.i
new file mode 100755
index 0000000..cce66cd
--- /dev/null
+++ b/.hg/store/data/activity/journalmanager-activity.svg.i
Binary files differ
diff --git a/.hg/store/data/activity/permissions.info.i b/.hg/store/data/activity/permissions.info.i
new file mode 100755
index 0000000..7900069
--- /dev/null
+++ b/.hg/store/data/activity/permissions.info.i
Binary files differ
diff --git a/.hg/store/data/journalmanager.py.i b/.hg/store/data/journalmanager.py.i
new file mode 100755
index 0000000..1f5a47a
--- /dev/null
+++ b/.hg/store/data/journalmanager.py.i
Binary files differ
diff --git a/.hg/store/data/listview.py.i b/.hg/store/data/listview.py.i
new file mode 100755
index 0000000..f2a99b7
--- /dev/null
+++ b/.hg/store/data/listview.py.i
Binary files differ
diff --git a/.hg/store/data/objectchooser.py.i b/.hg/store/data/objectchooser.py.i
new file mode 100755
index 0000000..4d62422
--- /dev/null
+++ b/.hg/store/data/objectchooser.py.i
Binary files differ
diff --git a/.hg/store/data/objectfetch.py.i b/.hg/store/data/objectfetch.py.i
new file mode 100755
index 0000000..b2c77b6
--- /dev/null
+++ b/.hg/store/data/objectfetch.py.i
Binary files differ
diff --git a/.hg/store/data/xoconfig.i b/.hg/store/data/xoconfig.i
new file mode 100755
index 0000000..115635c
--- /dev/null
+++ b/.hg/store/data/xoconfig.i
Binary files differ
diff --git a/.hg/store/undo b/.hg/store/undo
new file mode 100755
index 0000000..7b9bbbd
--- /dev/null
+++ b/.hg/store/undo
Binary files differ
diff --git a/.hg/undo.branch b/.hg/undo.branch
new file mode 100755
index 0000000..331d858
--- /dev/null
+++ b/.hg/undo.branch
@@ -0,0 +1 @@
+default \ No newline at end of file
diff --git a/.hg/undo.dirstate b/.hg/undo.dirstate
new file mode 100755
index 0000000..7365d63
--- /dev/null
+++ b/.hg/undo.dirstate
Binary files differ
diff --git a/BeautifulSoup.py b/BeautifulSoup.py
new file mode 100755
index 0000000..34204e7
--- /dev/null
+++ b/BeautifulSoup.py
@@ -0,0 +1,2000 @@
+"""Beautiful Soup
+Elixir and Tonic
+"The Screen-Scraper's Friend"
+http://www.crummy.com/software/BeautifulSoup/
+
+Beautiful Soup parses a (possibly invalid) XML or HTML document into a
+tree representation. It provides methods and Pythonic idioms that make
+it easy to navigate, search, and modify the tree.
+
+A well-formed XML/HTML document yields a well-formed data
+structure. An ill-formed XML/HTML document yields a correspondingly
+ill-formed data structure. If your document is only locally
+well-formed, you can use this library to find and process the
+well-formed part of it.
+
+Beautiful Soup works with Python 2.2 and up. It has no external
+dependencies, but you'll have more success at converting data to UTF-8
+if you also install these three packages:
+
+* chardet, for auto-detecting character encodings
+ http://chardet.feedparser.org/
+* cjkcodecs and iconv_codec, which add more encodings to the ones supported
+ by stock Python.
+ http://cjkpython.i18n.org/
+
+Beautiful Soup defines classes for two main parsing strategies:
+
+ * BeautifulStoneSoup, for parsing XML, SGML, or your domain-specific
+ language that kind of looks like XML.
+
+ * BeautifulSoup, for parsing run-of-the-mill HTML code, be it valid
+ or invalid. This class has web browser-like heuristics for
+ obtaining a sensible parse tree in the face of common HTML errors.
+
+Beautiful Soup also defines a class (UnicodeDammit) for autodetecting
+the encoding of an HTML or XML document, and converting it to
+Unicode. Much of this code is taken from Mark Pilgrim's Universal Feed Parser.
+
+For more than you ever wanted to know about Beautiful Soup, see the
+documentation:
+http://www.crummy.com/software/BeautifulSoup/documentation.html
+
+Here, have some legalese:
+
+Copyright (c) 2004-2009, Leonard Richardson
+
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are
+met:
+
+ * Redistributions of source code must retain the above copyright
+ notice, this list of conditions and the following disclaimer.
+
+ * Redistributions in binary form must reproduce the above
+ copyright notice, this list of conditions and the following
+ disclaimer in the documentation and/or other materials provided
+ with the distribution.
+
+ * Neither the name of the the Beautiful Soup Consortium and All
+ Night Kosher Bakery nor the names of its contributors may be
+ used to endorse or promote products derived from this software
+ without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
+CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE, DAMMIT.
+
+"""
+from __future__ import generators
+
+__author__ = "Leonard Richardson (leonardr@segfault.org)"
+__version__ = "3.1.0.1"
+__copyright__ = "Copyright (c) 2004-2009 Leonard Richardson"
+__license__ = "New-style BSD"
+
+import codecs
+import markupbase
+import types
+import re
+from HTMLParser import HTMLParser, HTMLParseError
+try:
+ from htmlentitydefs import name2codepoint
+except ImportError:
+ name2codepoint = {}
+try:
+ set
+except NameError:
+ from sets import Set as set
+
+#These hacks make Beautiful Soup able to parse XML with namespaces
+markupbase._declname_match = re.compile(r'[a-zA-Z][-_.:a-zA-Z0-9]*\s*').match
+
+DEFAULT_OUTPUT_ENCODING = "utf-8"
+
+# First, the classes that represent markup elements.
+
+def sob(unicode, encoding):
+ """Returns either the given Unicode string or its encoding."""
+ if encoding is None:
+ return unicode
+ else:
+ return unicode.encode(encoding)
+
+class PageElement:
+ """Contains the navigational information for some part of the page
+ (either a tag or a piece of text)"""
+
+ def setup(self, parent=None, previous=None):
+ """Sets up the initial relations between this element and
+ other elements."""
+ self.parent = parent
+ self.previous = previous
+ self.next = None
+ self.previousSibling = None
+ self.nextSibling = None
+ if self.parent and self.parent.contents:
+ self.previousSibling = self.parent.contents[-1]
+ self.previousSibling.nextSibling = self
+
+ def replaceWith(self, replaceWith):
+ oldParent = self.parent
+ myIndex = self.parent.contents.index(self)
+ if hasattr(replaceWith, 'parent') and replaceWith.parent == self.parent:
+ # We're replacing this element with one of its siblings.
+ index = self.parent.contents.index(replaceWith)
+ if index and index < myIndex:
+ # Furthermore, it comes before this element. That
+ # means that when we extract it, the index of this
+ # element will change.
+ myIndex = myIndex - 1
+ self.extract()
+ oldParent.insert(myIndex, replaceWith)
+
+ def extract(self):
+ """Destructively rips this element out of the tree."""
+ if self.parent:
+ try:
+ self.parent.contents.remove(self)
+ except ValueError:
+ pass
+
+ #Find the two elements that would be next to each other if
+ #this element (and any children) hadn't been parsed. Connect
+ #the two.
+ lastChild = self._lastRecursiveChild()
+ nextElement = lastChild.next
+
+ if self.previous:
+ self.previous.next = nextElement
+ if nextElement:
+ nextElement.previous = self.previous
+ self.previous = None
+ lastChild.next = None
+
+ self.parent = None
+ if self.previousSibling:
+ self.previousSibling.nextSibling = self.nextSibling
+ if self.nextSibling:
+ self.nextSibling.previousSibling = self.previousSibling
+ self.previousSibling = self.nextSibling = None
+ return self
+
+ def _lastRecursiveChild(self):
+ "Finds the last element beneath this object to be parsed."
+ lastChild = self
+ while hasattr(lastChild, 'contents') and lastChild.contents:
+ lastChild = lastChild.contents[-1]
+ return lastChild
+
+ def insert(self, position, newChild):
+ if (isinstance(newChild, basestring)
+ or isinstance(newChild, unicode)) \
+ and not isinstance(newChild, NavigableString):
+ newChild = NavigableString(newChild)
+
+ position = min(position, len(self.contents))
+ if hasattr(newChild, 'parent') and newChild.parent != None:
+ # We're 'inserting' an element that's already one
+ # of this object's children.
+ if newChild.parent == self:
+ index = self.find(newChild)
+ if index and index < position:
+ # Furthermore we're moving it further down the
+ # list of this object's children. That means that
+ # when we extract this element, our target index
+ # will jump down one.
+ position = position - 1
+ newChild.extract()
+
+ newChild.parent = self
+ previousChild = None
+ if position == 0:
+ newChild.previousSibling = None
+ newChild.previous = self
+ else:
+ previousChild = self.contents[position-1]
+ newChild.previousSibling = previousChild
+ newChild.previousSibling.nextSibling = newChild
+ newChild.previous = previousChild._lastRecursiveChild()
+ if newChild.previous:
+ newChild.previous.next = newChild
+
+ newChildsLastElement = newChild._lastRecursiveChild()
+
+ if position >= len(self.contents):
+ newChild.nextSibling = None
+
+ parent = self
+ parentsNextSibling = None
+ while not parentsNextSibling:
+ parentsNextSibling = parent.nextSibling
+ parent = parent.parent
+ if not parent: # This is the last element in the document.
+ break
+ if parentsNextSibling:
+ newChildsLastElement.next = parentsNextSibling
+ else:
+ newChildsLastElement.next = None
+ else:
+ nextChild = self.contents[position]
+ newChild.nextSibling = nextChild
+ if newChild.nextSibling:
+ newChild.nextSibling.previousSibling = newChild
+ newChildsLastElement.next = nextChild
+
+ if newChildsLastElement.next:
+ newChildsLastElement.next.previous = newChildsLastElement
+ self.contents.insert(position, newChild)
+
+ def append(self, tag):
+ """Appends the given tag to the contents of this tag."""
+ self.insert(len(self.contents), tag)
+
+ def findNext(self, name=None, attrs={}, text=None, **kwargs):
+ """Returns the first item that matches the given criteria and
+ appears after this Tag in the document."""
+ return self._findOne(self.findAllNext, name, attrs, text, **kwargs)
+
+ def findAllNext(self, name=None, attrs={}, text=None, limit=None,
+ **kwargs):
+ """Returns all items that match the given criteria and appear
+ after this Tag in the document."""
+ return self._findAll(name, attrs, text, limit, self.nextGenerator,
+ **kwargs)
+
+ def findNextSibling(self, name=None, attrs={}, text=None, **kwargs):
+ """Returns the closest sibling to this Tag that matches the
+ given criteria and appears after this Tag in the document."""
+ return self._findOne(self.findNextSiblings, name, attrs, text,
+ **kwargs)
+
+ def findNextSiblings(self, name=None, attrs={}, text=None, limit=None,
+ **kwargs):
+ """Returns the siblings of this Tag that match the given
+ criteria and appear after this Tag in the document."""
+ return self._findAll(name, attrs, text, limit,
+ self.nextSiblingGenerator, **kwargs)
+ fetchNextSiblings = findNextSiblings # Compatibility with pre-3.x
+
+ def findPrevious(self, name=None, attrs={}, text=None, **kwargs):
+ """Returns the first item that matches the given criteria and
+ appears before this Tag in the document."""
+ return self._findOne(self.findAllPrevious, name, attrs, text, **kwargs)
+
+ def findAllPrevious(self, name=None, attrs={}, text=None, limit=None,
+ **kwargs):
+ """Returns all items that match the given criteria and appear
+ before this Tag in the document."""
+ return self._findAll(name, attrs, text, limit, self.previousGenerator,
+ **kwargs)
+ fetchPrevious = findAllPrevious # Compatibility with pre-3.x
+
+ def findPreviousSibling(self, name=None, attrs={}, text=None, **kwargs):
+ """Returns the closest sibling to this Tag that matches the
+ given criteria and appears before this Tag in the document."""
+ return self._findOne(self.findPreviousSiblings, name, attrs, text,
+ **kwargs)
+
+ def findPreviousSiblings(self, name=None, attrs={}, text=None,
+ limit=None, **kwargs):
+ """Returns the siblings of this Tag that match the given
+ criteria and appear before this Tag in the document."""
+ return self._findAll(name, attrs, text, limit,
+ self.previousSiblingGenerator, **kwargs)
+ fetchPreviousSiblings = findPreviousSiblings # Compatibility with pre-3.x
+
+ def findParent(self, name=None, attrs={}, **kwargs):
+ """Returns the closest parent of this Tag that matches the given
+ criteria."""
+ # NOTE: We can't use _findOne because findParents takes a different
+ # set of arguments.
+ r = None
+ l = self.findParents(name, attrs, 1)
+ if l:
+ r = l[0]
+ return r
+
+ def findParents(self, name=None, attrs={}, limit=None, **kwargs):
+ """Returns the parents of this Tag that match the given
+ criteria."""
+
+ return self._findAll(name, attrs, None, limit, self.parentGenerator,
+ **kwargs)
+ fetchParents = findParents # Compatibility with pre-3.x
+
+ #These methods do the real heavy lifting.
+
+ def _findOne(self, method, name, attrs, text, **kwargs):
+ r = None
+ l = method(name, attrs, text, 1, **kwargs)
+ if l:
+ r = l[0]
+ return r
+
+ def _findAll(self, name, attrs, text, limit, generator, **kwargs):
+ "Iterates over a generator looking for things that match."
+
+ if isinstance(name, SoupStrainer):
+ strainer = name
+ else:
+ # Build a SoupStrainer
+ strainer = SoupStrainer(name, attrs, text, **kwargs)
+ results = ResultSet(strainer)
+ g = generator()
+ while True:
+ try:
+ i = g.next()
+ except StopIteration:
+ break
+ if i:
+ found = strainer.search(i)
+ if found:
+ results.append(found)
+ if limit and len(results) >= limit:
+ break
+ return results
+
+ #These Generators can be used to navigate starting from both
+ #NavigableStrings and Tags.
+ def nextGenerator(self):
+ i = self
+ while i:
+ i = i.next
+ yield i
+
+ def nextSiblingGenerator(self):
+ i = self
+ while i:
+ i = i.nextSibling
+ yield i
+
+ def previousGenerator(self):
+ i = self
+ while i:
+ i = i.previous
+ yield i
+
+ def previousSiblingGenerator(self):
+ i = self
+ while i:
+ i = i.previousSibling
+ yield i
+
+ def parentGenerator(self):
+ i = self
+ while i:
+ i = i.parent
+ yield i
+
+ # Utility methods
+ def substituteEncoding(self, str, encoding=None):
+ encoding = encoding or "utf-8"
+ return str.replace("%SOUP-ENCODING%", encoding)
+
+ def toEncoding(self, s, encoding=None):
+ """Encodes an object to a string in some encoding, or to Unicode.
+ ."""
+ if isinstance(s, unicode):
+ if encoding:
+ s = s.encode(encoding)
+ elif isinstance(s, str):
+ if encoding:
+ s = s.encode(encoding)
+ else:
+ s = unicode(s)
+ else:
+ if encoding:
+ s = self.toEncoding(str(s), encoding)
+ else:
+ s = unicode(s)
+ return s
+
+class NavigableString(unicode, PageElement):
+
+ def __new__(cls, value):
+ """Create a new NavigableString.
+
+ When unpickling a NavigableString, this method is called with
+ the string in DEFAULT_OUTPUT_ENCODING. That encoding needs to be
+ passed in to the superclass's __new__ or the superclass won't know
+ how to handle non-ASCII characters.
+ """
+ if isinstance(value, unicode):
+ return unicode.__new__(cls, value)
+ return unicode.__new__(cls, value, DEFAULT_OUTPUT_ENCODING)
+
+ def __getnewargs__(self):
+ return (unicode(self),)
+
+ def __getattr__(self, attr):
+ """text.string gives you text. This is for backwards
+ compatibility for Navigable*String, but for CData* it lets you
+ get the string without the CData wrapper."""
+ if attr == 'string':
+ return self
+ else:
+ raise AttributeError, "'%s' object has no attribute '%s'" % (self.__class__.__name__, attr)
+
+ def encode(self, encoding=DEFAULT_OUTPUT_ENCODING):
+ return self.decode().encode(encoding)
+
+ def decodeGivenEventualEncoding(self, eventualEncoding):
+ return self
+
+class CData(NavigableString):
+
+ def decodeGivenEventualEncoding(self, eventualEncoding):
+ return u'<![CDATA[' + self + u']]>'
+
+class ProcessingInstruction(NavigableString):
+
+ def decodeGivenEventualEncoding(self, eventualEncoding):
+ output = self
+ if u'%SOUP-ENCODING%' in output:
+ output = self.substituteEncoding(output, eventualEncoding)
+ return u'<?' + output + u'?>'
+
+class Comment(NavigableString):
+ def decodeGivenEventualEncoding(self, eventualEncoding):
+ return u'<!--' + self + u'-->'
+
+class Declaration(NavigableString):
+ def decodeGivenEventualEncoding(self, eventualEncoding):
+ return u'<!' + self + u'>'
+
+class Tag(PageElement):
+
+ """Represents a found HTML tag with its attributes and contents."""
+
+ def _invert(h):
+ "Cheap function to invert a hash."
+ i = {}
+ for k,v in h.items():
+ i[v] = k
+ return i
+
+ XML_ENTITIES_TO_SPECIAL_CHARS = { "apos" : "'",
+ "quot" : '"',
+ "amp" : "&",
+ "lt" : "<",
+ "gt" : ">" }
+
+ XML_SPECIAL_CHARS_TO_ENTITIES = _invert(XML_ENTITIES_TO_SPECIAL_CHARS)
+
+ def _convertEntities(self, match):
+ """Used in a call to re.sub to replace HTML, XML, and numeric
+ entities with the appropriate Unicode characters. If HTML
+ entities are being converted, any unrecognized entities are
+ escaped."""
+ x = match.group(1)
+ if self.convertHTMLEntities and x in name2codepoint:
+ return unichr(name2codepoint[x])
+ elif x in self.XML_ENTITIES_TO_SPECIAL_CHARS:
+ if self.convertXMLEntities:
+ return self.XML_ENTITIES_TO_SPECIAL_CHARS[x]
+ else:
+ return u'&%s;' % x
+ elif len(x) > 0 and x[0] == '#':
+ # Handle numeric entities
+ if len(x) > 1 and x[1] == 'x':
+ return unichr(int(x[2:], 16))
+ else:
+ return unichr(int(x[1:]))
+
+ elif self.escapeUnrecognizedEntities:
+ return u'&amp;%s;' % x
+ else:
+ return u'&%s;' % x
+
+ def __init__(self, parser, name, attrs=None, parent=None,
+ previous=None):
+ "Basic constructor."
+
+ # We don't actually store the parser object: that lets extracted
+ # chunks be garbage-collected
+ self.parserClass = parser.__class__
+ self.isSelfClosing = parser.isSelfClosingTag(name)
+ self.name = name
+ if attrs == None:
+ attrs = []
+ self.attrs = attrs
+ self.contents = []
+ self.setup(parent, previous)
+ self.hidden = False
+ self.containsSubstitutions = False
+ self.convertHTMLEntities = parser.convertHTMLEntities
+ self.convertXMLEntities = parser.convertXMLEntities
+ self.escapeUnrecognizedEntities = parser.escapeUnrecognizedEntities
+
+ def convert(kval):
+ "Converts HTML, XML and numeric entities in the attribute value."
+ k, val = kval
+ if val is None:
+ return kval
+ return (k, re.sub("&(#\d+|#x[0-9a-fA-F]+|\w+);",
+ self._convertEntities, val))
+ self.attrs = map(convert, self.attrs)
+
+ def get(self, key, default=None):
+ """Returns the value of the 'key' attribute for the tag, or
+ the value given for 'default' if it doesn't have that
+ attribute."""
+ return self._getAttrMap().get(key, default)
+
+ def has_key(self, key):
+ return self._getAttrMap().has_key(key)
+
+ def __getitem__(self, key):
+ """tag[key] returns the value of the 'key' attribute for the tag,
+ and throws an exception if it's not there."""
+ return self._getAttrMap()[key]
+
+ def __iter__(self):
+ "Iterating over a tag iterates over its contents."
+ return iter(self.contents)
+
+ def __len__(self):
+ "The length of a tag is the length of its list of contents."
+ return len(self.contents)
+
+ def __contains__(self, x):
+ return x in self.contents
+
+ def __nonzero__(self):
+ "A tag is non-None even if it has no contents."
+ return True
+
+ def __setitem__(self, key, value):
+ """Setting tag[key] sets the value of the 'key' attribute for the
+ tag."""
+ self._getAttrMap()
+ self.attrMap[key] = value
+ found = False
+ for i in range(0, len(self.attrs)):
+ if self.attrs[i][0] == key:
+ self.attrs[i] = (key, value)
+ found = True
+ if not found:
+ self.attrs.append((key, value))
+ self._getAttrMap()[key] = value
+
+ def __delitem__(self, key):
+ "Deleting tag[key] deletes all 'key' attributes for the tag."
+ for item in self.attrs:
+ if item[0] == key:
+ self.attrs.remove(item)
+ #We don't break because bad HTML can define the same
+ #attribute multiple times.
+ self._getAttrMap()
+ if self.attrMap.has_key(key):
+ del self.attrMap[key]
+
+ def __call__(self, *args, **kwargs):
+ """Calling a tag like a function is the same as calling its
+ findAll() method. Eg. tag('a') returns a list of all the A tags
+ found within this tag."""
+ return apply(self.findAll, args, kwargs)
+
+ def __getattr__(self, tag):
+ #print "Getattr %s.%s" % (self.__class__, tag)
+ if len(tag) > 3 and tag.rfind('Tag') == len(tag)-3:
+ return self.find(tag[:-3])
+ elif tag.find('__') != 0:
+ return self.find(tag)
+ raise AttributeError, "'%s' object has no attribute '%s'" % (self.__class__, tag)
+
+ def __eq__(self, other):
+ """Returns true iff this tag has the same name, the same attributes,
+ and the same contents (recursively) as the given tag.
+
+ NOTE: right now this will return false if two tags have the
+ same attributes in a different order. Should this be fixed?"""
+ if not hasattr(other, 'name') or not hasattr(other, 'attrs') or not hasattr(other, 'contents') or self.name != other.name or self.attrs != other.attrs or len(self) != len(other):
+ return False
+ for i in range(0, len(self.contents)):
+ if self.contents[i] != other.contents[i]:
+ return False
+ return True
+
+ def __ne__(self, other):
+ """Returns true iff this tag is not identical to the other tag,
+ as defined in __eq__."""
+ return not self == other
+
+ def __repr__(self, encoding=DEFAULT_OUTPUT_ENCODING):
+ """Renders this tag as a string."""
+ return self.decode(eventualEncoding=encoding)
+
+ BARE_AMPERSAND_OR_BRACKET = re.compile("([<>]|"
+ + "&(?!#\d+;|#x[0-9a-fA-F]+;|\w+;)"
+ + ")")
+
+ def _sub_entity(self, x):
+ """Used with a regular expression to substitute the
+ appropriate XML entity for an XML special character."""
+ return "&" + self.XML_SPECIAL_CHARS_TO_ENTITIES[x.group(0)[0]] + ";"
+
+ def __unicode__(self):
+ return self.decode()
+
+ def __str__(self):
+ return self.encode()
+
+ def encode(self, encoding=DEFAULT_OUTPUT_ENCODING,
+ prettyPrint=False, indentLevel=0):
+ return self.decode(prettyPrint, indentLevel, encoding).encode(encoding)
+
+ def decode(self, prettyPrint=False, indentLevel=0,
+ eventualEncoding=DEFAULT_OUTPUT_ENCODING):
+ """Returns a string or Unicode representation of this tag and
+ its contents. To get Unicode, pass None for encoding."""
+
+ attrs = []
+ if self.attrs:
+ for key, val in self.attrs:
+ fmt = '%s="%s"'
+ if isString(val):
+ if (self.containsSubstitutions
+ and eventualEncoding is not None
+ and '%SOUP-ENCODING%' in val):
+ val = self.substituteEncoding(val, eventualEncoding)
+
+ # The attribute value either:
+ #
+ # * Contains no embedded double quotes or single quotes.
+ # No problem: we enclose it in double quotes.
+ # * Contains embedded single quotes. No problem:
+ # double quotes work here too.
+ # * Contains embedded double quotes. No problem:
+ # we enclose it in single quotes.
+ # * Embeds both single _and_ double quotes. This
+ # can't happen naturally, but it can happen if
+ # you modify an attribute value after parsing
+ # the document. Now we have a bit of a
+ # problem. We solve it by enclosing the
+ # attribute in single quotes, and escaping any
+ # embedded single quotes to XML entities.
+ if '"' in val:
+ fmt = "%s='%s'"
+ if "'" in val:
+ # TODO: replace with apos when
+ # appropriate.
+ val = val.replace("'", "&squot;")
+
+ # Now we're okay w/r/t quotes. But the attribute
+ # value might also contain angle brackets, or
+ # ampersands that aren't part of entities. We need
+ # to escape those to XML entities too.
+ val = self.BARE_AMPERSAND_OR_BRACKET.sub(self._sub_entity, val)
+ if val is None:
+ # Handle boolean attributes.
+ decoded = key
+ else:
+ decoded = fmt % (key, val)
+ attrs.append(decoded)
+ close = ''
+ closeTag = ''
+ if self.isSelfClosing:
+ close = ' /'
+ else:
+ closeTag = '</%s>' % self.name
+
+ indentTag, indentContents = 0, 0
+ if prettyPrint:
+ indentTag = indentLevel
+ space = (' ' * (indentTag-1))
+ indentContents = indentTag + 1
+ contents = self.decodeContents(prettyPrint, indentContents,
+ eventualEncoding)
+ if self.hidden:
+ s = contents
+ else:
+ s = []
+ attributeString = ''
+ if attrs:
+ attributeString = ' ' + ' '.join(attrs)
+ if prettyPrint:
+ s.append(space)
+ s.append('<%s%s%s>' % (self.name, attributeString, close))
+ if prettyPrint:
+ s.append("\n")
+ s.append(contents)
+ if prettyPrint and contents and contents[-1] != "\n":
+ s.append("\n")
+ if prettyPrint and closeTag:
+ s.append(space)
+ s.append(closeTag)
+ if prettyPrint and closeTag and self.nextSibling:
+ s.append("\n")
+ s = ''.join(s)
+ return s
+
+ def decompose(self):
+ """Recursively destroys the contents of this tree."""
+ contents = [i for i in self.contents]
+ for i in contents:
+ if isinstance(i, Tag):
+ i.decompose()
+ else:
+ i.extract()
+ self.extract()
+
+ def prettify(self, encoding=DEFAULT_OUTPUT_ENCODING):
+ return self.encode(encoding, True)
+
+ def encodeContents(self, encoding=DEFAULT_OUTPUT_ENCODING,
+ prettyPrint=False, indentLevel=0):
+ return self.decodeContents(prettyPrint, indentLevel).encode(encoding)
+
+ def decodeContents(self, prettyPrint=False, indentLevel=0,
+ eventualEncoding=DEFAULT_OUTPUT_ENCODING):
+ """Renders the contents of this tag as a string in the given
+ encoding. If encoding is None, returns a Unicode string.."""
+ s=[]
+ for c in self:
+ text = None
+ if isinstance(c, NavigableString):
+ text = c.decodeGivenEventualEncoding(eventualEncoding)
+ elif isinstance(c, Tag):
+ s.append(c.decode(prettyPrint, indentLevel, eventualEncoding))
+ if text and prettyPrint:
+ text = text.strip()
+ if text:
+ if prettyPrint:
+ s.append(" " * (indentLevel-1))
+ s.append(text)
+ if prettyPrint:
+ s.append("\n")
+ return ''.join(s)
+
+ #Soup methods
+
+ def find(self, name=None, attrs={}, recursive=True, text=None,
+ **kwargs):
+ """Return only the first child of this Tag matching the given
+ criteria."""
+ r = None
+ l = self.findAll(name, attrs, recursive, text, 1, **kwargs)
+ if l:
+ r = l[0]
+ return r
+ findChild = find
+
+ def findAll(self, name=None, attrs={}, recursive=True, text=None,
+ limit=None, **kwargs):
+ """Extracts a list of Tag objects that match the given
+ criteria. You can specify the name of the Tag and any
+ attributes you want the Tag to have.
+
+ The value of a key-value pair in the 'attrs' map can be a
+ string, a list of strings, a regular expression object, or a
+ callable that takes a string and returns whether or not the
+ string matches for some custom definition of 'matches'. The
+ same is true of the tag name."""
+ generator = self.recursiveChildGenerator
+ if not recursive:
+ generator = self.childGenerator
+ return self._findAll(name, attrs, text, limit, generator, **kwargs)
+ findChildren = findAll
+
+ # Pre-3.x compatibility methods. Will go away in 4.0.
+ first = find
+ fetch = findAll
+
+ def fetchText(self, text=None, recursive=True, limit=None):
+ return self.findAll(text=text, recursive=recursive, limit=limit)
+
+ def firstText(self, text=None, recursive=True):
+ return self.find(text=text, recursive=recursive)
+
+ # 3.x compatibility methods. Will go away in 4.0.
+ def renderContents(self, encoding=DEFAULT_OUTPUT_ENCODING,
+ prettyPrint=False, indentLevel=0):
+ if encoding is None:
+ return self.decodeContents(prettyPrint, indentLevel, encoding)
+ else:
+ return self.encodeContents(encoding, prettyPrint, indentLevel)
+
+
+ #Private methods
+
+ def _getAttrMap(self):
+ """Initializes a map representation of this tag's attributes,
+ if not already initialized."""
+ if not getattr(self, 'attrMap'):
+ self.attrMap = {}
+ for (key, value) in self.attrs:
+ self.attrMap[key] = value
+ return self.attrMap
+
+ #Generator methods
+ def recursiveChildGenerator(self):
+ if not len(self.contents):
+ raise StopIteration
+ stopNode = self._lastRecursiveChild().next
+ current = self.contents[0]
+ while current is not stopNode:
+ yield current
+ current = current.next
+
+ def childGenerator(self):
+ if not len(self.contents):
+ raise StopIteration
+ current = self.contents[0]
+ while current:
+ yield current
+ current = current.nextSibling
+ raise StopIteration
+
+# Next, a couple classes to represent queries and their results.
+class SoupStrainer:
+ """Encapsulates a number of ways of matching a markup element (tag or
+ text)."""
+
+ def __init__(self, name=None, attrs={}, text=None, **kwargs):
+ self.name = name
+ if isString(attrs):
+ kwargs['class'] = attrs
+ attrs = None
+ if kwargs:
+ if attrs:
+ attrs = attrs.copy()
+ attrs.update(kwargs)
+ else:
+ attrs = kwargs
+ self.attrs = attrs
+ self.text = text
+
+ def __str__(self):
+ if self.text:
+ return self.text
+ else:
+ return "%s|%s" % (self.name, self.attrs)
+
+ def searchTag(self, markupName=None, markupAttrs={}):
+ found = None
+ markup = None
+ if isinstance(markupName, Tag):
+ markup = markupName
+ markupAttrs = markup
+ callFunctionWithTagData = callable(self.name) \
+ and not isinstance(markupName, Tag)
+
+ if (not self.name) \
+ or callFunctionWithTagData \
+ or (markup and self._matches(markup, self.name)) \
+ or (not markup and self._matches(markupName, self.name)):
+ if callFunctionWithTagData:
+ match = self.name(markupName, markupAttrs)
+ else:
+ match = True
+ markupAttrMap = None
+ for attr, matchAgainst in self.attrs.items():
+ if not markupAttrMap:
+ if hasattr(markupAttrs, 'get'):
+ markupAttrMap = markupAttrs
+ else:
+ markupAttrMap = {}
+ for k,v in markupAttrs:
+ markupAttrMap[k] = v
+ attrValue = markupAttrMap.get(attr)
+ if not self._matches(attrValue, matchAgainst):
+ match = False
+ break
+ if match:
+ if markup:
+ found = markup
+ else:
+ found = markupName
+ return found
+
+ def search(self, markup):
+ #print 'looking for %s in %s' % (self, markup)
+ found = None
+ # If given a list of items, scan it for a text element that
+ # matches.
+ if isList(markup) and not isinstance(markup, Tag):
+ for element in markup:
+ if isinstance(element, NavigableString) \
+ and self.search(element):
+ found = element
+ break
+ # If it's a Tag, make sure its name or attributes match.
+ # Don't bother with Tags if we're searching for text.
+ elif isinstance(markup, Tag):
+ if not self.text:
+ found = self.searchTag(markup)
+ # If it's text, make sure the text matches.
+ elif isinstance(markup, NavigableString) or \
+ isString(markup):
+ if self._matches(markup, self.text):
+ found = markup
+ else:
+ raise Exception, "I don't know how to match against a %s" \
+ % markup.__class__
+ return found
+
+ def _matches(self, markup, matchAgainst):
+ #print "Matching %s against %s" % (markup, matchAgainst)
+ result = False
+ if matchAgainst == True and type(matchAgainst) == types.BooleanType:
+ result = markup != None
+ elif callable(matchAgainst):
+ result = matchAgainst(markup)
+ else:
+ #Custom match methods take the tag as an argument, but all
+ #other ways of matching match the tag name as a string.
+ if isinstance(markup, Tag):
+ markup = markup.name
+ if markup is not None and not isString(markup):
+ markup = unicode(markup)
+ #Now we know that chunk is either a string, or None.
+ if hasattr(matchAgainst, 'match'):
+ # It's a regexp object.
+ result = markup and matchAgainst.search(markup)
+ elif (isList(matchAgainst)
+ and (markup is not None or not isString(matchAgainst))):
+ result = markup in matchAgainst
+ elif hasattr(matchAgainst, 'items'):
+ result = markup.has_key(matchAgainst)
+ elif matchAgainst and isString(markup):
+ if isinstance(markup, unicode):
+ matchAgainst = unicode(matchAgainst)
+ else:
+ matchAgainst = str(matchAgainst)
+
+ if not result:
+ result = matchAgainst == markup
+ return result
+
+class ResultSet(list):
+ """A ResultSet is just a list that keeps track of the SoupStrainer
+ that created it."""
+ def __init__(self, source):
+ list.__init__([])
+ self.source = source
+
+# Now, some helper functions.
+
+def isList(l):
+ """Convenience method that works with all 2.x versions of Python
+ to determine whether or not something is listlike."""
+ return ((hasattr(l, '__iter__') and not isString(l))
+ or (type(l) in (types.ListType, types.TupleType)))
+
+def isString(s):
+ """Convenience method that works with all 2.x versions of Python
+ to determine whether or not something is stringlike."""
+ try:
+ return isinstance(s, unicode) or isinstance(s, basestring)
+ except NameError:
+ return isinstance(s, str)
+
+def buildTagMap(default, *args):
+ """Turns a list of maps, lists, or scalars into a single map.
+ Used to build the SELF_CLOSING_TAGS, NESTABLE_TAGS, and
+ NESTING_RESET_TAGS maps out of lists and partial maps."""
+ built = {}
+ for portion in args:
+ if hasattr(portion, 'items'):
+ #It's a map. Merge it.
+ for k,v in portion.items():
+ built[k] = v
+ elif isList(portion) and not isString(portion):
+ #It's a list. Map each item to the default.
+ for k in portion:
+ built[k] = default
+ else:
+ #It's a scalar. Map it to the default.
+ built[portion] = default
+ return built
+
+# Now, the parser classes.
+
+class HTMLParserBuilder(HTMLParser):
+
+ def __init__(self, soup):
+ HTMLParser.__init__(self)
+ self.soup = soup
+
+ # We inherit feed() and reset().
+
+ def handle_starttag(self, name, attrs):
+ if name == 'meta':
+ self.soup.extractCharsetFromMeta(attrs)
+ else:
+ self.soup.unknown_starttag(name, attrs)
+
+ def handle_endtag(self, name):
+ self.soup.unknown_endtag(name)
+
+ def handle_data(self, content):
+ self.soup.handle_data(content)
+
+ def _toStringSubclass(self, text, subclass):
+ """Adds a certain piece of text to the tree as a NavigableString
+ subclass."""
+ self.soup.endData()
+ self.handle_data(text)
+ self.soup.endData(subclass)
+
+ def handle_pi(self, text):
+ """Handle a processing instruction as a ProcessingInstruction
+ object, possibly one with a %SOUP-ENCODING% slot into which an
+ encoding will be plugged later."""
+ if text[:3] == "xml":
+ text = u"xml version='1.0' encoding='%SOUP-ENCODING%'"
+ self._toStringSubclass(text, ProcessingInstruction)
+
+ def handle_comment(self, text):
+ "Handle comments as Comment objects."
+ self._toStringSubclass(text, Comment)
+
+ def handle_charref(self, ref):
+ "Handle character references as data."
+ if self.soup.convertEntities:
+ data = unichr(int(ref))
+ else:
+ data = '&#%s;' % ref
+ self.handle_data(data)
+
+ def handle_entityref(self, ref):
+ """Handle entity references as data, possibly converting known
+ HTML and/or XML entity references to the corresponding Unicode
+ characters."""
+ data = None
+ if self.soup.convertHTMLEntities:
+ try:
+ data = unichr(name2codepoint[ref])
+ except KeyError:
+ pass
+
+ if not data and self.soup.convertXMLEntities:
+ data = self.soup.XML_ENTITIES_TO_SPECIAL_CHARS.get(ref)
+
+ if not data and self.soup.convertHTMLEntities and \
+ not self.soup.XML_ENTITIES_TO_SPECIAL_CHARS.get(ref):
+ # TODO: We've got a problem here. We're told this is
+ # an entity reference, but it's not an XML entity
+ # reference or an HTML entity reference. Nonetheless,
+ # the logical thing to do is to pass it through as an
+ # unrecognized entity reference.
+ #
+ # Except: when the input is "&carol;" this function
+ # will be called with input "carol". When the input is
+ # "AT&T", this function will be called with input
+ # "T". We have no way of knowing whether a semicolon
+ # was present originally, so we don't know whether
+ # this is an unknown entity or just a misplaced
+ # ampersand.
+ #
+ # The more common case is a misplaced ampersand, so I
+ # escape the ampersand and omit the trailing semicolon.
+ data = "&amp;%s" % ref
+ if not data:
+ # This case is different from the one above, because we
+ # haven't already gone through a supposedly comprehensive
+ # mapping of entities to Unicode characters. We might not
+ # have gone through any mapping at all. So the chances are
+ # very high that this is a real entity, and not a
+ # misplaced ampersand.
+ data = "&%s;" % ref
+ self.handle_data(data)
+
+ def handle_decl(self, data):
+ "Handle DOCTYPEs and the like as Declaration objects."
+ self._toStringSubclass(data, Declaration)
+
+ def parse_declaration(self, i):
+ """Treat a bogus SGML declaration as raw data. Treat a CDATA
+ declaration as a CData object."""
+ j = None
+ if self.rawdata[i:i+9] == '<![CDATA[':
+ k = self.rawdata.find(']]>', i)
+ if k == -1:
+ k = len(self.rawdata)
+ data = self.rawdata[i+9:k]
+ j = k+3
+ self._toStringSubclass(data, CData)
+ else:
+ try:
+ j = HTMLParser.parse_declaration(self, i)
+ except HTMLParseError:
+ toHandle = self.rawdata[i:]
+ self.handle_data(toHandle)
+ j = i + len(toHandle)
+ return j
+
+
+class BeautifulStoneSoup(Tag):
+
+ """This class contains the basic parser and search code. It defines
+ a parser that knows nothing about tag behavior except for the
+ following:
+
+ You can't close a tag without closing all the tags it encloses.
+ That is, "<foo><bar></foo>" actually means
+ "<foo><bar></bar></foo>".
+
+ [Another possible explanation is "<foo><bar /></foo>", but since
+ this class defines no SELF_CLOSING_TAGS, it will never use that
+ explanation.]
+
+ This class is useful for parsing XML or made-up markup languages,
+ or when BeautifulSoup makes an assumption counter to what you were
+ expecting."""
+
+ SELF_CLOSING_TAGS = {}
+ NESTABLE_TAGS = {}
+ RESET_NESTING_TAGS = {}
+ QUOTE_TAGS = {}
+ PRESERVE_WHITESPACE_TAGS = []
+
+ MARKUP_MASSAGE = [(re.compile('(<[^<>]*)/>'),
+ lambda x: x.group(1) + ' />'),
+ (re.compile('<!\s+([^<>]*)>'),
+ lambda x: '<!' + x.group(1) + '>')
+ ]
+
+ ROOT_TAG_NAME = u'[document]'
+
+ HTML_ENTITIES = "html"
+ XML_ENTITIES = "xml"
+ XHTML_ENTITIES = "xhtml"
+ # TODO: This only exists for backwards-compatibility
+ ALL_ENTITIES = XHTML_ENTITIES
+
+ # Used when determining whether a text node is all whitespace and
+ # can be replaced with a single space. A text node that contains
+ # fancy Unicode spaces (usually non-breaking) should be left
+ # alone.
+ STRIP_ASCII_SPACES = { 9: None, 10: None, 12: None, 13: None, 32: None, }
+
+ def __init__(self, markup="", parseOnlyThese=None, fromEncoding=None,
+ markupMassage=True, smartQuotesTo=XML_ENTITIES,
+ convertEntities=None, selfClosingTags=None, isHTML=False,
+ builder=HTMLParserBuilder):
+ """The Soup object is initialized as the 'root tag', and the
+ provided markup (which can be a string or a file-like object)
+ is fed into the underlying parser.
+
+ HTMLParser will process most bad HTML, and the BeautifulSoup
+ class has some tricks for dealing with some HTML that kills
+ HTMLParser, but Beautiful Soup can nonetheless choke or lose data
+ if your data uses self-closing tags or declarations
+ incorrectly.
+
+ By default, Beautiful Soup uses regexes to sanitize input,
+ avoiding the vast majority of these problems. If the problems
+ don't apply to you, pass in False for markupMassage, and
+ you'll get better performance.
+
+ The default parser massage techniques fix the two most common
+ instances of invalid HTML that choke HTMLParser:
+
+ <br/> (No space between name of closing tag and tag close)
+ <! --Comment--> (Extraneous whitespace in declaration)
+
+ You can pass in a custom list of (RE object, replace method)
+ tuples to get Beautiful Soup to scrub your input the way you
+ want."""
+
+ self.parseOnlyThese = parseOnlyThese
+ self.fromEncoding = fromEncoding
+ self.smartQuotesTo = smartQuotesTo
+ self.convertEntities = convertEntities
+ # Set the rules for how we'll deal with the entities we
+ # encounter
+ if self.convertEntities:
+ # It doesn't make sense to convert encoded characters to
+ # entities even while you're converting entities to Unicode.
+ # Just convert it all to Unicode.
+ self.smartQuotesTo = None
+ if convertEntities == self.HTML_ENTITIES:
+ self.convertXMLEntities = False
+ self.convertHTMLEntities = True
+ self.escapeUnrecognizedEntities = True
+ elif convertEntities == self.XHTML_ENTITIES:
+ self.convertXMLEntities = True
+ self.convertHTMLEntities = True
+ self.escapeUnrecognizedEntities = False
+ elif convertEntities == self.XML_ENTITIES:
+ self.convertXMLEntities = True
+ self.convertHTMLEntities = False
+ self.escapeUnrecognizedEntities = False
+ else:
+ self.convertXMLEntities = False
+ self.convertHTMLEntities = False
+ self.escapeUnrecognizedEntities = False
+
+ self.instanceSelfClosingTags = buildTagMap(None, selfClosingTags)
+ self.builder = builder(self)
+ self.reset()
+
+ if hasattr(markup, 'read'): # It's a file-type object.
+ markup = markup.read()
+ self.markup = markup
+ self.markupMassage = markupMassage
+ try:
+ self._feed(isHTML=isHTML)
+ except StopParsing:
+ pass
+ self.markup = None # The markup can now be GCed.
+ self.builder = None # So can the builder.
+
+ def _feed(self, inDocumentEncoding=None, isHTML=False):
+ # Convert the document to Unicode.
+ markup = self.markup
+ if isinstance(markup, unicode):
+ if not hasattr(self, 'originalEncoding'):
+ self.originalEncoding = None
+ else:
+ dammit = UnicodeDammit\
+ (markup, [self.fromEncoding, inDocumentEncoding],
+ smartQuotesTo=self.smartQuotesTo, isHTML=isHTML)
+ markup = dammit.unicode
+ self.originalEncoding = dammit.originalEncoding
+ self.declaredHTMLEncoding = dammit.declaredHTMLEncoding
+ if markup:
+ if self.markupMassage:
+ if not isList(self.markupMassage):
+ self.markupMassage = self.MARKUP_MASSAGE
+ for fix, m in self.markupMassage:
+ markup = fix.sub(m, markup)
+ # TODO: We get rid of markupMassage so that the
+ # soup object can be deepcopied later on. Some
+ # Python installations can't copy regexes. If anyone
+ # was relying on the existence of markupMassage, this
+ # might cause problems.
+ del(self.markupMassage)
+ self.builder.reset()
+
+ self.builder.feed(markup)
+ # Close out any unfinished strings and close all the open tags.
+ self.endData()
+ while self.currentTag.name != self.ROOT_TAG_NAME:
+ self.popTag()
+
+ def isSelfClosingTag(self, name):
+ """Returns true iff the given string is the name of a
+ self-closing tag according to this parser."""
+ return self.SELF_CLOSING_TAGS.has_key(name) \
+ or self.instanceSelfClosingTags.has_key(name)
+
+ def reset(self):
+ Tag.__init__(self, self, self.ROOT_TAG_NAME)
+ self.hidden = 1
+ self.builder.reset()
+ self.currentData = []
+ self.currentTag = None
+ self.tagStack = []
+ self.quoteStack = []
+ self.pushTag(self)
+
+ def popTag(self):
+ tag = self.tagStack.pop()
+ # Tags with just one string-owning child get the child as a
+ # 'string' property, so that soup.tag.string is shorthand for
+ # soup.tag.contents[0]
+ if len(self.currentTag.contents) == 1 and \
+ isinstance(self.currentTag.contents[0], NavigableString):
+ self.currentTag.string = self.currentTag.contents[0]
+
+ #print "Pop", tag.name
+ if self.tagStack:
+ self.currentTag = self.tagStack[-1]
+ return self.currentTag
+
+ def pushTag(self, tag):
+ #print "Push", tag.name
+ if self.currentTag:
+ self.currentTag.contents.append(tag)
+ self.tagStack.append(tag)
+ self.currentTag = self.tagStack[-1]
+
+ def endData(self, containerClass=NavigableString):
+ if self.currentData:
+ currentData = u''.join(self.currentData)
+ if (currentData.translate(self.STRIP_ASCII_SPACES) == '' and
+ not set([tag.name for tag in self.tagStack]).intersection(
+ self.PRESERVE_WHITESPACE_TAGS)):
+ if '\n' in currentData:
+ currentData = '\n'
+ else:
+ currentData = ' '
+ self.currentData = []
+ if self.parseOnlyThese and len(self.tagStack) <= 1 and \
+ (not self.parseOnlyThese.text or \
+ not self.parseOnlyThese.search(currentData)):
+ return
+ o = containerClass(currentData)
+ o.setup(self.currentTag, self.previous)
+ if self.previous:
+ self.previous.next = o
+ self.previous = o
+ self.currentTag.contents.append(o)
+
+
+ def _popToTag(self, name, inclusivePop=True):
+ """Pops the tag stack up to and including the most recent
+ instance of the given tag. If inclusivePop is false, pops the tag
+ stack up to but *not* including the most recent instqance of
+ the given tag."""
+ #print "Popping to %s" % name
+ if name == self.ROOT_TAG_NAME:
+ return
+
+ numPops = 0
+ mostRecentTag = None
+ for i in range(len(self.tagStack)-1, 0, -1):
+ if name == self.tagStack[i].name:
+ numPops = len(self.tagStack)-i
+ break
+ if not inclusivePop:
+ numPops = numPops - 1
+
+ for i in range(0, numPops):
+ mostRecentTag = self.popTag()
+ return mostRecentTag
+
+ def _smartPop(self, name):
+
+ """We need to pop up to the previous tag of this type, unless
+ one of this tag's nesting reset triggers comes between this
+ tag and the previous tag of this type, OR unless this tag is a
+ generic nesting trigger and another generic nesting trigger
+ comes between this tag and the previous tag of this type.
+
+ Examples:
+ <p>Foo<b>Bar *<p>* should pop to 'p', not 'b'.
+ <p>Foo<table>Bar *<p>* should pop to 'table', not 'p'.
+ <p>Foo<table><tr>Bar *<p>* should pop to 'tr', not 'p'.
+
+ <li><ul><li> *<li>* should pop to 'ul', not the first 'li'.
+ <tr><table><tr> *<tr>* should pop to 'table', not the first 'tr'
+ <td><tr><td> *<td>* should pop to 'tr', not the first 'td'
+ """
+
+ nestingResetTriggers = self.NESTABLE_TAGS.get(name)
+ isNestable = nestingResetTriggers != None
+ isResetNesting = self.RESET_NESTING_TAGS.has_key(name)
+ popTo = None
+ inclusive = True
+ for i in range(len(self.tagStack)-1, 0, -1):
+ p = self.tagStack[i]
+ if (not p or p.name == name) and not isNestable:
+ #Non-nestable tags get popped to the top or to their
+ #last occurance.
+ popTo = name
+ break
+ if (nestingResetTriggers != None
+ and p.name in nestingResetTriggers) \
+ or (nestingResetTriggers == None and isResetNesting
+ and self.RESET_NESTING_TAGS.has_key(p.name)):
+
+ #If we encounter one of the nesting reset triggers
+ #peculiar to this tag, or we encounter another tag
+ #that causes nesting to reset, pop up to but not
+ #including that tag.
+ popTo = p.name
+ inclusive = False
+ break
+ p = p.parent
+ if popTo:
+ self._popToTag(popTo, inclusive)
+
+ def unknown_starttag(self, name, attrs, selfClosing=0):
+ #print "Start tag %s: %s" % (name, attrs)
+ if self.quoteStack:
+ #This is not a real tag.
+ #print "<%s> is not real!" % name
+ attrs = ''.join(map(lambda(x, y): ' %s="%s"' % (x, y), attrs))
+ self.handle_data('<%s%s>' % (name, attrs))
+ return
+ self.endData()
+
+ if not self.isSelfClosingTag(name) and not selfClosing:
+ self._smartPop(name)
+
+ if self.parseOnlyThese and len(self.tagStack) <= 1 \
+ and (self.parseOnlyThese.text or not self.parseOnlyThese.searchTag(name, attrs)):
+ return
+
+ tag = Tag(self, name, attrs, self.currentTag, self.previous)
+ if self.previous:
+ self.previous.next = tag
+ self.previous = tag
+ self.pushTag(tag)
+ if selfClosing or self.isSelfClosingTag(name):
+ self.popTag()
+ if name in self.QUOTE_TAGS:
+ #print "Beginning quote (%s)" % name
+ self.quoteStack.append(name)
+ self.literal = 1
+ return tag
+
+ def unknown_endtag(self, name):
+ #print "End tag %s" % name
+ if self.quoteStack and self.quoteStack[-1] != name:
+ #This is not a real end tag.
+ #print "</%s> is not real!" % name
+ self.handle_data('</%s>' % name)
+ return
+ self.endData()
+ self._popToTag(name)
+ if self.quoteStack and self.quoteStack[-1] == name:
+ self.quoteStack.pop()
+ self.literal = (len(self.quoteStack) > 0)
+
+ def handle_data(self, data):
+ self.currentData.append(data)
+
+ def extractCharsetFromMeta(self, attrs):
+ self.unknown_starttag('meta', attrs)
+
+
+class BeautifulSoup(BeautifulStoneSoup):
+
+ """This parser knows the following facts about HTML:
+
+ * Some tags have no closing tag and should be interpreted as being
+ closed as soon as they are encountered.
+
+ * The text inside some tags (ie. 'script') may contain tags which
+ are not really part of the document and which should be parsed
+ as text, not tags. If you want to parse the text as tags, you can
+ always fetch it and parse it explicitly.
+
+ * Tag nesting rules:
+
+ Most tags can't be nested at all. For instance, the occurance of
+ a <p> tag should implicitly close the previous <p> tag.
+
+ <p>Para1<p>Para2
+ should be transformed into:
+ <p>Para1</p><p>Para2
+
+ Some tags can be nested arbitrarily. For instance, the occurance
+ of a <blockquote> tag should _not_ implicitly close the previous
+ <blockquote> tag.
+
+ Alice said: <blockquote>Bob said: <blockquote>Blah
+ should NOT be transformed into:
+ Alice said: <blockquote>Bob said: </blockquote><blockquote>Blah
+
+ Some tags can be nested, but the nesting is reset by the
+ interposition of other tags. For instance, a <tr> tag should
+ implicitly close the previous <tr> tag within the same <table>,
+ but not close a <tr> tag in another table.
+
+ <table><tr>Blah<tr>Blah
+ should be transformed into:
+ <table><tr>Blah</tr><tr>Blah
+ but,
+ <tr>Blah<table><tr>Blah
+ should NOT be transformed into
+ <tr>Blah<table></tr><tr>Blah
+
+ Differing assumptions about tag nesting rules are a major source
+ of problems with the BeautifulSoup class. If BeautifulSoup is not
+ treating as nestable a tag your page author treats as nestable,
+ try ICantBelieveItsBeautifulSoup, MinimalSoup, or
+ BeautifulStoneSoup before writing your own subclass."""
+
+ def __init__(self, *args, **kwargs):
+ if not kwargs.has_key('smartQuotesTo'):
+ kwargs['smartQuotesTo'] = self.HTML_ENTITIES
+ kwargs['isHTML'] = True
+ BeautifulStoneSoup.__init__(self, *args, **kwargs)
+
+ SELF_CLOSING_TAGS = buildTagMap(None,
+ ['br' , 'hr', 'input', 'img', 'meta',
+ 'spacer', 'link', 'frame', 'base'])
+
+ PRESERVE_WHITESPACE_TAGS = set(['pre', 'textarea'])
+
+ QUOTE_TAGS = {'script' : None, 'textarea' : None}
+
+ #According to the HTML standard, each of these inline tags can
+ #contain another tag of the same type. Furthermore, it's common
+ #to actually use these tags this way.
+ NESTABLE_INLINE_TAGS = ['span', 'font', 'q', 'object', 'bdo', 'sub', 'sup',
+ 'center']
+
+ #According to the HTML standard, these block tags can contain
+ #another tag of the same type. Furthermore, it's common
+ #to actually use these tags this way.
+ NESTABLE_BLOCK_TAGS = ['blockquote', 'div', 'fieldset', 'ins', 'del']
+
+ #Lists can contain other lists, but there are restrictions.
+ NESTABLE_LIST_TAGS = { 'ol' : [],
+ 'ul' : [],
+ 'li' : ['ul', 'ol'],
+ 'dl' : [],
+ 'dd' : ['dl'],
+ 'dt' : ['dl'] }
+
+ #Tables can contain other tables, but there are restrictions.
+ NESTABLE_TABLE_TAGS = {'table' : [],
+ 'tr' : ['table', 'tbody', 'tfoot', 'thead'],
+ 'td' : ['tr'],
+ 'th' : ['tr'],
+ 'thead' : ['table'],
+ 'tbody' : ['table'],
+ 'tfoot' : ['table'],
+ }
+
+ NON_NESTABLE_BLOCK_TAGS = ['address', 'form', 'p', 'pre']
+
+ #If one of these tags is encountered, all tags up to the next tag of
+ #this type are popped.
+ RESET_NESTING_TAGS = buildTagMap(None, NESTABLE_BLOCK_TAGS, 'noscript',
+ NON_NESTABLE_BLOCK_TAGS,
+ NESTABLE_LIST_TAGS,
+ NESTABLE_TABLE_TAGS)
+
+ NESTABLE_TAGS = buildTagMap([], NESTABLE_INLINE_TAGS, NESTABLE_BLOCK_TAGS,
+ NESTABLE_LIST_TAGS, NESTABLE_TABLE_TAGS)
+
+ # Used to detect the charset in a META tag; see start_meta
+ CHARSET_RE = re.compile("((^|;)\s*charset=)([^;]*)", re.M)
+
+ def extractCharsetFromMeta(self, attrs):
+ """Beautiful Soup can detect a charset included in a META tag,
+ try to convert the document to that charset, and re-parse the
+ document from the beginning."""
+ httpEquiv = None
+ contentType = None
+ contentTypeIndex = None
+ tagNeedsEncodingSubstitution = False
+
+ for i in range(0, len(attrs)):
+ key, value = attrs[i]
+ key = key.lower()
+ if key == 'http-equiv':
+ httpEquiv = value
+ elif key == 'content':
+ contentType = value
+ contentTypeIndex = i
+
+ if httpEquiv and contentType: # It's an interesting meta tag.
+ match = self.CHARSET_RE.search(contentType)
+ if match:
+ if (self.declaredHTMLEncoding is not None or
+ self.originalEncoding == self.fromEncoding):
+ # An HTML encoding was sniffed while converting
+ # the document to Unicode, or an HTML encoding was
+ # sniffed during a previous pass through the
+ # document, or an encoding was specified
+ # explicitly and it worked. Rewrite the meta tag.
+ def rewrite(match):
+ return match.group(1) + "%SOUP-ENCODING%"
+ newAttr = self.CHARSET_RE.sub(rewrite, contentType)
+ attrs[contentTypeIndex] = (attrs[contentTypeIndex][0],
+ newAttr)
+ tagNeedsEncodingSubstitution = True
+ else:
+ # This is our first pass through the document.
+ # Go through it again with the encoding information.
+ newCharset = match.group(3)
+ if newCharset and newCharset != self.originalEncoding:
+ self.declaredHTMLEncoding = newCharset
+ self._feed(self.declaredHTMLEncoding)
+ raise StopParsing
+ pass
+ tag = self.unknown_starttag("meta", attrs)
+ if tag and tagNeedsEncodingSubstitution:
+ tag.containsSubstitutions = True
+
+
+class StopParsing(Exception):
+ pass
+
+class ICantBelieveItsBeautifulSoup(BeautifulSoup):
+
+ """The BeautifulSoup class is oriented towards skipping over
+ common HTML errors like unclosed tags. However, sometimes it makes
+ errors of its own. For instance, consider this fragment:
+
+ <b>Foo<b>Bar</b></b>
+
+ This is perfectly valid (if bizarre) HTML. However, the
+ BeautifulSoup class will implicitly close the first b tag when it
+ encounters the second 'b'. It will think the author wrote
+ "<b>Foo<b>Bar", and didn't close the first 'b' tag, because
+ there's no real-world reason to bold something that's already
+ bold. When it encounters '</b></b>' it will close two more 'b'
+ tags, for a grand total of three tags closed instead of two. This
+ can throw off the rest of your document structure. The same is
+ true of a number of other tags, listed below.
+
+ It's much more common for someone to forget to close a 'b' tag
+ than to actually use nested 'b' tags, and the BeautifulSoup class
+ handles the common case. This class handles the not-co-common
+ case: where you can't believe someone wrote what they did, but
+ it's valid HTML and BeautifulSoup screwed up by assuming it
+ wouldn't be."""
+
+ I_CANT_BELIEVE_THEYRE_NESTABLE_INLINE_TAGS = \
+ ['em', 'big', 'i', 'small', 'tt', 'abbr', 'acronym', 'strong',
+ 'cite', 'code', 'dfn', 'kbd', 'samp', 'strong', 'var', 'b',
+ 'big']
+
+ I_CANT_BELIEVE_THEYRE_NESTABLE_BLOCK_TAGS = ['noscript']
+
+ NESTABLE_TAGS = buildTagMap([], BeautifulSoup.NESTABLE_TAGS,
+ I_CANT_BELIEVE_THEYRE_NESTABLE_BLOCK_TAGS,
+ I_CANT_BELIEVE_THEYRE_NESTABLE_INLINE_TAGS)
+
+class MinimalSoup(BeautifulSoup):
+ """The MinimalSoup class is for parsing HTML that contains
+ pathologically bad markup. It makes no assumptions about tag
+ nesting, but it does know which tags are self-closing, that
+ <script> tags contain Javascript and should not be parsed, that
+ META tags may contain encoding information, and so on.
+
+ This also makes it better for subclassing than BeautifulStoneSoup
+ or BeautifulSoup."""
+
+ RESET_NESTING_TAGS = buildTagMap('noscript')
+ NESTABLE_TAGS = {}
+
+class BeautifulSOAP(BeautifulStoneSoup):
+ """This class will push a tag with only a single string child into
+ the tag's parent as an attribute. The attribute's name is the tag
+ name, and the value is the string child. An example should give
+ the flavor of the change:
+
+ <foo><bar>baz</bar></foo>
+ =>
+ <foo bar="baz"><bar>baz</bar></foo>
+
+ You can then access fooTag['bar'] instead of fooTag.barTag.string.
+
+ This is, of course, useful for scraping structures that tend to
+ use subelements instead of attributes, such as SOAP messages. Note
+ that it modifies its input, so don't print the modified version
+ out.
+
+ I'm not sure how many people really want to use this class; let me
+ know if you do. Mainly I like the name."""
+
+ def popTag(self):
+ if len(self.tagStack) > 1:
+ tag = self.tagStack[-1]
+ parent = self.tagStack[-2]
+ parent._getAttrMap()
+ if (isinstance(tag, Tag) and len(tag.contents) == 1 and
+ isinstance(tag.contents[0], NavigableString) and
+ not parent.attrMap.has_key(tag.name)):
+ parent[tag.name] = tag.contents[0]
+ BeautifulStoneSoup.popTag(self)
+
+#Enterprise class names! It has come to our attention that some people
+#think the names of the Beautiful Soup parser classes are too silly
+#and "unprofessional" for use in enterprise screen-scraping. We feel
+#your pain! For such-minded folk, the Beautiful Soup Consortium And
+#All-Night Kosher Bakery recommends renaming this file to
+#"RobustParser.py" (or, in cases of extreme enterprisiness,
+#"RobustParserBeanInterface.class") and using the following
+#enterprise-friendly class aliases:
+class RobustXMLParser(BeautifulStoneSoup):
+ pass
+class RobustHTMLParser(BeautifulSoup):
+ pass
+class RobustWackAssHTMLParser(ICantBelieveItsBeautifulSoup):
+ pass
+class RobustInsanelyWackAssHTMLParser(MinimalSoup):
+ pass
+class SimplifyingSOAPParser(BeautifulSOAP):
+ pass
+
+######################################################
+#
+# Bonus library: Unicode, Dammit
+#
+# This class forces XML data into a standard format (usually to UTF-8
+# or Unicode). It is heavily based on code from Mark Pilgrim's
+# Universal Feed Parser. It does not rewrite the XML or HTML to
+# reflect a new encoding: that happens in BeautifulStoneSoup.handle_pi
+# (XML) and BeautifulSoup.start_meta (HTML).
+
+# Autodetects character encodings.
+# Download from http://chardet.feedparser.org/
+try:
+ import chardet
+# import chardet.constants
+# chardet.constants._debug = 1
+except ImportError:
+ chardet = None
+
+# cjkcodecs and iconv_codec make Python know about more character encodings.
+# Both are available from http://cjkpython.i18n.org/
+# They're built in if you use Python 2.4.
+try:
+ import cjkcodecs.aliases
+except ImportError:
+ pass
+try:
+ import iconv_codec
+except ImportError:
+ pass
+
+class UnicodeDammit:
+ """A class for detecting the encoding of a *ML document and
+ converting it to a Unicode string. If the source encoding is
+ windows-1252, can replace MS smart quotes with their HTML or XML
+ equivalents."""
+
+ # This dictionary maps commonly seen values for "charset" in HTML
+ # meta tags to the corresponding Python codec names. It only covers
+ # values that aren't in Python's aliases and can't be determined
+ # by the heuristics in find_codec.
+ CHARSET_ALIASES = { "macintosh" : "mac-roman",
+ "x-sjis" : "shift-jis" }
+
+ def __init__(self, markup, overrideEncodings=[],
+ smartQuotesTo='xml', isHTML=False):
+ self.declaredHTMLEncoding = None
+ self.markup, documentEncoding, sniffedEncoding = \
+ self._detectEncoding(markup, isHTML)
+ self.smartQuotesTo = smartQuotesTo
+ self.triedEncodings = []
+ if markup == '' or isinstance(markup, unicode):
+ self.originalEncoding = None
+ self.unicode = unicode(markup)
+ return
+
+ u = None
+ for proposedEncoding in overrideEncodings:
+ u = self._convertFrom(proposedEncoding)
+ if u: break
+ if not u:
+ for proposedEncoding in (documentEncoding, sniffedEncoding):
+ u = self._convertFrom(proposedEncoding)
+ if u: break
+
+ # If no luck and we have auto-detection library, try that:
+ if not u and chardet and not isinstance(self.markup, unicode):
+ u = self._convertFrom(chardet.detect(self.markup)['encoding'])
+
+ # As a last resort, try utf-8 and windows-1252:
+ if not u:
+ for proposed_encoding in ("utf-8", "windows-1252"):
+ u = self._convertFrom(proposed_encoding)
+ if u: break
+
+ self.unicode = u
+ if not u: self.originalEncoding = None
+
+ def _subMSChar(self, match):
+ """Changes a MS smart quote character to an XML or HTML
+ entity."""
+ orig = match.group(1)
+ sub = self.MS_CHARS.get(orig)
+ if type(sub) == types.TupleType:
+ if self.smartQuotesTo == 'xml':
+ sub = '&#x'.encode() + sub[1].encode() + ';'.encode()
+ else:
+ sub = '&'.encode() + sub[0].encode() + ';'.encode()
+ else:
+ sub = sub.encode()
+ return sub
+
+ def _convertFrom(self, proposed):
+ proposed = self.find_codec(proposed)
+ if not proposed or proposed in self.triedEncodings:
+ return None
+ self.triedEncodings.append(proposed)
+ markup = self.markup
+
+ # Convert smart quotes to HTML if coming from an encoding
+ # that might have them.
+ if self.smartQuotesTo and proposed.lower() in("windows-1252",
+ "iso-8859-1",
+ "iso-8859-2"):
+ smart_quotes_re = "([\x80-\x9f])"
+ smart_quotes_compiled = re.compile(smart_quotes_re)
+ markup = smart_quotes_compiled.sub(self._subMSChar, markup)
+
+ try:
+ # print "Trying to convert document to %s" % proposed
+ u = self._toUnicode(markup, proposed)
+ self.markup = u
+ self.originalEncoding = proposed
+ except Exception, e:
+ # print "That didn't work!"
+ # print e
+ return None
+ #print "Correct encoding: %s" % proposed
+ return self.markup
+
+ def _toUnicode(self, data, encoding):
+ '''Given a string and its encoding, decodes the string into Unicode.
+ %encoding is a string recognized by encodings.aliases'''
+
+ # strip Byte Order Mark (if present)
+ if (len(data) >= 4) and (data[:2] == '\xfe\xff') \
+ and (data[2:4] != '\x00\x00'):
+ encoding = 'utf-16be'
+ data = data[2:]
+ elif (len(data) >= 4) and (data[:2] == '\xff\xfe') \
+ and (data[2:4] != '\x00\x00'):
+ encoding = 'utf-16le'
+ data = data[2:]
+ elif data[:3] == '\xef\xbb\xbf':
+ encoding = 'utf-8'
+ data = data[3:]
+ elif data[:4] == '\x00\x00\xfe\xff':
+ encoding = 'utf-32be'
+ data = data[4:]
+ elif data[:4] == '\xff\xfe\x00\x00':
+ encoding = 'utf-32le'
+ data = data[4:]
+ newdata = unicode(data, encoding)
+ return newdata
+
+ def _detectEncoding(self, xml_data, isHTML=False):
+ """Given a document, tries to detect its XML encoding."""
+ xml_encoding = sniffed_xml_encoding = None
+ try:
+ if xml_data[:4] == '\x4c\x6f\xa7\x94':
+ # EBCDIC
+ xml_data = self._ebcdic_to_ascii(xml_data)
+ elif xml_data[:4] == '\x00\x3c\x00\x3f':
+ # UTF-16BE
+ sniffed_xml_encoding = 'utf-16be'
+ xml_data = unicode(xml_data, 'utf-16be').encode('utf-8')
+ elif (len(xml_data) >= 4) and (xml_data[:2] == '\xfe\xff') \
+ and (xml_data[2:4] != '\x00\x00'):
+ # UTF-16BE with BOM
+ sniffed_xml_encoding = 'utf-16be'
+ xml_data = unicode(xml_data[2:], 'utf-16be').encode('utf-8')
+ elif xml_data[:4] == '\x3c\x00\x3f\x00':
+ # UTF-16LE
+ sniffed_xml_encoding = 'utf-16le'
+ xml_data = unicode(xml_data, 'utf-16le').encode('utf-8')
+ elif (len(xml_data) >= 4) and (xml_data[:2] == '\xff\xfe') and \
+ (xml_data[2:4] != '\x00\x00'):
+ # UTF-16LE with BOM
+ sniffed_xml_encoding = 'utf-16le'
+ xml_data = unicode(xml_data[2:], 'utf-16le').encode('utf-8')
+ elif xml_data[:4] == '\x00\x00\x00\x3c':
+ # UTF-32BE
+ sniffed_xml_encoding = 'utf-32be'
+ xml_data = unicode(xml_data, 'utf-32be').encode('utf-8')
+ elif xml_data[:4] == '\x3c\x00\x00\x00':
+ # UTF-32LE
+ sniffed_xml_encoding = 'utf-32le'
+ xml_data = unicode(xml_data, 'utf-32le').encode('utf-8')
+ elif xml_data[:4] == '\x00\x00\xfe\xff':
+ # UTF-32BE with BOM
+ sniffed_xml_encoding = 'utf-32be'
+ xml_data = unicode(xml_data[4:], 'utf-32be').encode('utf-8')
+ elif xml_data[:4] == '\xff\xfe\x00\x00':
+ # UTF-32LE with BOM
+ sniffed_xml_encoding = 'utf-32le'
+ xml_data = unicode(xml_data[4:], 'utf-32le').encode('utf-8')
+ elif xml_data[:3] == '\xef\xbb\xbf':
+ # UTF-8 with BOM
+ sniffed_xml_encoding = 'utf-8'
+ xml_data = unicode(xml_data[3:], 'utf-8').encode('utf-8')
+ else:
+ sniffed_xml_encoding = 'ascii'
+ pass
+ except:
+ xml_encoding_match = None
+ xml_encoding_re = '^<\?.*encoding=[\'"](.*?)[\'"].*\?>'.encode()
+ xml_encoding_match = re.compile(xml_encoding_re).match(xml_data)
+ if not xml_encoding_match and isHTML:
+ meta_re = '<\s*meta[^>]+charset=([^>]*?)[;\'">]'.encode()
+ regexp = re.compile(meta_re, re.I)
+ xml_encoding_match = regexp.search(xml_data)
+ if xml_encoding_match is not None:
+ xml_encoding = xml_encoding_match.groups()[0].decode(
+ 'ascii').lower()
+ if isHTML:
+ self.declaredHTMLEncoding = xml_encoding
+ if sniffed_xml_encoding and \
+ (xml_encoding in ('iso-10646-ucs-2', 'ucs-2', 'csunicode',
+ 'iso-10646-ucs-4', 'ucs-4', 'csucs4',
+ 'utf-16', 'utf-32', 'utf_16', 'utf_32',
+ 'utf16', 'u16')):
+ xml_encoding = sniffed_xml_encoding
+ return xml_data, xml_encoding, sniffed_xml_encoding
+
+
+ def find_codec(self, charset):
+ return self._codec(self.CHARSET_ALIASES.get(charset, charset)) \
+ or (charset and self._codec(charset.replace("-", ""))) \
+ or (charset and self._codec(charset.replace("-", "_"))) \
+ or charset
+
+ def _codec(self, charset):
+ if not charset: return charset
+ codec = None
+ try:
+ codecs.lookup(charset)
+ codec = charset
+ except (LookupError, ValueError):
+ pass
+ return codec
+
+ EBCDIC_TO_ASCII_MAP = None
+ def _ebcdic_to_ascii(self, s):
+ c = self.__class__
+ if not c.EBCDIC_TO_ASCII_MAP:
+ emap = (0,1,2,3,156,9,134,127,151,141,142,11,12,13,14,15,
+ 16,17,18,19,157,133,8,135,24,25,146,143,28,29,30,31,
+ 128,129,130,131,132,10,23,27,136,137,138,139,140,5,6,7,
+ 144,145,22,147,148,149,150,4,152,153,154,155,20,21,158,26,
+ 32,160,161,162,163,164,165,166,167,168,91,46,60,40,43,33,
+ 38,169,170,171,172,173,174,175,176,177,93,36,42,41,59,94,
+ 45,47,178,179,180,181,182,183,184,185,124,44,37,95,62,63,
+ 186,187,188,189,190,191,192,193,194,96,58,35,64,39,61,34,
+ 195,97,98,99,100,101,102,103,104,105,196,197,198,199,200,
+ 201,202,106,107,108,109,110,111,112,113,114,203,204,205,
+ 206,207,208,209,126,115,116,117,118,119,120,121,122,210,
+ 211,212,213,214,215,216,217,218,219,220,221,222,223,224,
+ 225,226,227,228,229,230,231,123,65,66,67,68,69,70,71,72,
+ 73,232,233,234,235,236,237,125,74,75,76,77,78,79,80,81,
+ 82,238,239,240,241,242,243,92,159,83,84,85,86,87,88,89,
+ 90,244,245,246,247,248,249,48,49,50,51,52,53,54,55,56,57,
+ 250,251,252,253,254,255)
+ import string
+ c.EBCDIC_TO_ASCII_MAP = string.maketrans( \
+ ''.join(map(chr, range(256))), ''.join(map(chr, emap)))
+ return s.translate(c.EBCDIC_TO_ASCII_MAP)
+
+ MS_CHARS = { '\x80' : ('euro', '20AC'),
+ '\x81' : ' ',
+ '\x82' : ('sbquo', '201A'),
+ '\x83' : ('fnof', '192'),
+ '\x84' : ('bdquo', '201E'),
+ '\x85' : ('hellip', '2026'),
+ '\x86' : ('dagger', '2020'),
+ '\x87' : ('Dagger', '2021'),
+ '\x88' : ('circ', '2C6'),
+ '\x89' : ('permil', '2030'),
+ '\x8A' : ('Scaron', '160'),
+ '\x8B' : ('lsaquo', '2039'),
+ '\x8C' : ('OElig', '152'),
+ '\x8D' : '?',
+ '\x8E' : ('#x17D', '17D'),
+ '\x8F' : '?',
+ '\x90' : '?',
+ '\x91' : ('lsquo', '2018'),
+ '\x92' : ('rsquo', '2019'),
+ '\x93' : ('ldquo', '201C'),
+ '\x94' : ('rdquo', '201D'),
+ '\x95' : ('bull', '2022'),
+ '\x96' : ('ndash', '2013'),
+ '\x97' : ('mdash', '2014'),
+ '\x98' : ('tilde', '2DC'),
+ '\x99' : ('trade', '2122'),
+ '\x9a' : ('scaron', '161'),
+ '\x9b' : ('rsaquo', '203A'),
+ '\x9c' : ('oelig', '153'),
+ '\x9d' : '?',
+ '\x9e' : ('#x17E', '17E'),
+ '\x9f' : ('Yuml', ''),}
+
+#######################################################################
+
+
+#By default, act as an HTML pretty-printer.
+if __name__ == '__main__':
+ import sys
+ soup = BeautifulSoup(sys.stdin)
+ print soup.prettify()
diff --git a/activity/activity.info b/activity/activity.info
new file mode 100755
index 0000000..23398d2
--- /dev/null
+++ b/activity/activity.info
@@ -0,0 +1,7 @@
+[Activity]
+name = Data Manager
+service_name = org.olenepal.DataManager
+class = datamanager.DataManager
+icon = datamanager-activity
+activity_version = 1
+show_launcher = yes
diff --git a/activity/datamanager-activity.svg b/activity/datamanager-activity.svg
new file mode 100755
index 0000000..1ae35db
--- /dev/null
+++ b/activity/datamanager-activity.svg
@@ -0,0 +1,11 @@
+<?xml version="1.0" ?><!DOCTYPE svg PUBLIC '-//W3C//DTD SVG 1.1//EN' 'http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd' [
+ <!ENTITY stroke_color "#666666">
+ <!ENTITY fill_color "#ffffff">
+]><svg enable-background="new 0 0 55 55" height="55px" id="Layer_1" version="1.1" viewBox="0 0 55 55" width="55px" x="0px" xml:space="preserve" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" y="0px"><g display="block" id="activity-journal">
+ <path d="M45.866,44.669 c0,2.511-1.528,4.331-4.332,4.331H12.077V6h29.458c2.15,0,4.332,2.154,4.332,4.33L45.866,44.669L45.866,44.669z" fill="&fill_color;" stroke="&stroke_color;" stroke-linecap="round" stroke-linejoin="round" stroke-width="3.5"/>
+
+ <line fill="none" stroke="&stroke_color;" stroke-linecap="round" stroke-linejoin="round" stroke-width="3.5" x1="21.341" x2="21.341" y1="6.121" y2="48.881"/>
+ <path d="M7.384,14.464 c0,0,2.084,0.695,4.17,0.695c2.086,0,4.173-0.695,4.173-0.695" fill="none" stroke="&stroke_color;" stroke-linecap="round" stroke-linejoin="round" stroke-width="3.5"/>
+ <path d="M7.384,28.021 c0,0,1.912,0.695,4.345,0.695s3.999-0.695,3.999-0.695" fill="none" stroke="&stroke_color;" stroke-linecap="round" stroke-linejoin="round" stroke-width="3.5"/>
+ <path d="M7.384,41.232 c0,0,1.736,0.695,4.518,0.695c2.781,0,3.825-0.695,3.825-0.695" fill="none" stroke="&stroke_color;" stroke-linecap="round" stroke-linejoin="round" stroke-width="3.5"/>
+</g></svg> \ No newline at end of file
diff --git a/activity/permissions.info b/activity/permissions.info
new file mode 100755
index 0000000..585d713
--- /dev/null
+++ b/activity/permissions.info
@@ -0,0 +1 @@
+constant-uid
diff --git a/datamanager.py b/datamanager.py
new file mode 100755
index 0000000..0dc5ba4
--- /dev/null
+++ b/datamanager.py
@@ -0,0 +1,12 @@
+from sugar.activity import activity
+import listview
+
+class DataManager(activity.Activity):
+
+ def __init__(self, handle):
+ activity.Activity.__init__(self, handle)
+ toolbox = activity.ActivityToolbox(self)
+ self.set_toolbox(toolbox)
+ toolbox.show()
+ listview.pyApp(self)
+
diff --git a/filelisting.py b/filelisting.py
new file mode 100755
index 0000000..f0a1aa0
--- /dev/null
+++ b/filelisting.py
@@ -0,0 +1,168 @@
+#!/usr/bin/env python
+
+import os, stat, time
+import pygtk
+pygtk.require('2.0')
+import gtk
+
+folderxpm = [
+ "17 16 7 1",
+ " c #000000",
+ ". c #808000",
+ "X c yellow",
+ "o c #808080",
+ "O c #c0c0c0",
+ "+ c white",
+ "@ c None",
+ "@@@@@@@@@@@@@@@@@",
+ "@@@@@@@@@@@@@@@@@",
+ "@@+XXXX.@@@@@@@@@",
+ "@+OOOOOO.@@@@@@@@",
+ "@+OXOXOXOXOXOXO. ",
+ "@+XOXOXOXOXOXOX. ",
+ "@+OXOXOXOXOXOXO. ",
+ "@+XOXOXOXOXOXOX. ",
+ "@+OXOXOXOXOXOXO. ",
+ "@+XOXOXOXOXOXOX. ",
+ "@+OXOXOXOXOXOXO. ",
+ "@+XOXOXOXOXOXOX. ",
+ "@+OOOOOOOOOOOOO. ",
+ "@ ",
+ "@@@@@@@@@@@@@@@@@",
+ "@@@@@@@@@@@@@@@@@"
+ ]
+folderpb = gtk.gdk.pixbuf_new_from_xpm_data(folderxpm)
+
+filexpm = [
+ "12 12 3 1",
+ " c #000000",
+ ". c #ffff04",
+ "X c #b2c0dc",
+ "X XXX",
+ "X ...... XXX",
+ "X ...... X",
+ "X . ... X",
+ "X ........ X",
+ "X . .... X",
+ "X ........ X",
+ "X . .. X",
+ "X ........ X",
+ "X . .. X",
+ "X ........ X",
+ "X X"
+ ]
+filepb = gtk.gdk.pixbuf_new_from_xpm_data(filexpm)
+
+class FileListingCellDataExample:
+ column_names = ['Name', 'Size', 'Mode', 'Last Changed']
+
+ def delete_event(self, widget, event, data=None):
+ gtk.main_quit()
+ return False
+
+ def __init__(self, dname = None):
+ cell_data_funcs = (None, self.file_size, self.file_mode,
+ self.file_last_changed)
+
+ # Create a new window
+ self.window = gtk.Window(gtk.WINDOW_TOPLEVEL)
+
+ self.window.set_size_request(400, 300)
+
+ self.window.connect("delete_event", self.delete_event)
+
+ listmodel = self.make_list(dname)
+
+ # create the TreeView
+ self.treeview = gtk.TreeView()
+
+ # create the TreeViewColumns to display the data
+ self.tvcolumn = [None] * len(self.column_names)
+ cellpb = gtk.CellRendererPixbuf()
+ self.tvcolumn[0] = gtk.TreeViewColumn(self.column_names[0], cellpb)
+ self.tvcolumn[0].set_cell_data_func(cellpb, self.file_pixbuf)
+ cell = gtk.CellRendererText()
+ self.tvcolumn[0].pack_start(cell, False)
+ self.tvcolumn[0].set_cell_data_func(cell, self.file_name)
+ self.treeview.append_column(self.tvcolumn[0])
+ for n in range(1, len(self.column_names)):
+ cell = gtk.CellRendererText()
+ self.tvcolumn[n] = gtk.TreeViewColumn(self.column_names[n], cell)
+ if n == 1:
+ cell.set_property('xalign', 1.0)
+ self.tvcolumn[n].set_cell_data_func(cell, cell_data_funcs[n])
+ self.treeview.append_column(self.tvcolumn[n])
+
+ self.treeview.connect('row-activated', self.open_file)
+ self.scrolledwindow = gtk.ScrolledWindow()
+ self.scrolledwindow.add(self.treeview)
+ self.window.add(self.scrolledwindow)
+ self.treeview.set_model(listmodel)
+
+ self.window.show_all()
+ return
+
+ def make_list(self, dname=None):
+ if not dname:
+ self.dirname = os.path.expanduser('~')
+ else:
+ self.dirname = os.path.abspath(dname)
+ self.window.set_title(self.dirname)
+ files = [f for f in os.listdir(self.dirname) if f[0] <> '.']
+ files.sort()
+ files = ['..'] + files
+ listmodel = gtk.ListStore(object)
+ for f in files:
+ listmodel.append([f])
+ return listmodel
+
+ def open_file(self, treeview, path, column):
+ model = treeview.get_model()
+ iter = model.get_iter(path)
+ filename = os.path.join(self.dirname, model.get_value(iter, 0))
+ filestat = os.stat(filename)
+ if stat.S_ISDIR(filestat.st_mode):
+ new_model = self.make_list(filename)
+ treeview.set_model(new_model)
+ return
+
+ def file_pixbuf(self, column, cell, model, iter):
+ filename = os.path.join(self.dirname, model.get_value(iter, 0))
+ filestat = os.stat(filename)
+ if stat.S_ISDIR(filestat.st_mode):
+ pb = folderpb
+ else:
+ pb = filepb
+ cell.set_property('pixbuf', pb)
+ return
+
+ def file_name(self, column, cell, model, iter):
+ cell.set_property('text', model.get_value(iter, 0))
+ return
+
+ def file_size(self, column, cell, model, iter):
+ filename = os.path.join(self.dirname, model.get_value(iter, 0))
+ filestat = os.stat(filename)
+ cell.set_property('text', filestat.st_size)
+ return
+
+ def file_mode(self, column, cell, model, iter):
+ filename = os.path.join(self.dirname, model.get_value(iter, 0))
+ filestat = os.stat(filename)
+ cell.set_property('text', oct(stat.S_IMODE(filestat.st_mode)))
+ return
+
+
+ def file_last_changed(self, column, cell, model, iter):
+ filename = os.path.join(self.dirname, model.get_value(iter, 0))
+ filestat = os.stat(filename)
+ cell.set_property('text', time.ctime(filestat.st_mtime))
+ return
+
+def main():
+ gtk.main()
+
+if __name__ == "__main__":
+ flcdexample = FileListingCellDataExample()
+ main()
+
diff --git a/listview.py b/listview.py
new file mode 100755
index 0000000..67b6d6a
--- /dev/null
+++ b/listview.py
@@ -0,0 +1,144 @@
+#!/usr/bin/python
+
+# ZetCode PyGTK tutorial
+#
+# This example shows a TreeView widget
+# in a list view mode
+#
+# author: jan bodnar
+# website: zetcode.com
+# last edited: February 2009
+
+import sys, os
+import gtk
+import objectfetch
+import urllib2
+from BeautifulSoup import BeautifulSoup
+from xml.dom.minidom import parse, parseString
+from sugar.activity import activity
+from sugar.datastore import datastore
+from path import path
+
+ACTIVITYPATH = path(activity.get_bundle_path())
+global online
+online = False
+
+class PyApp(gtk.Window):
+ def __init__(self):
+ super(PyApp, self).__init__()
+ self.set_size_request(350, 250)
+ self.set_position(gtk.WIN_POS_CENTER)
+
+ self.connect("destroy", gtk.main_quit)
+ self.set_title("DataManager")
+
+ vbox = gtk.VBox(False, 8)
+
+ sw = gtk.ScrolledWindow()
+ sw.set_shadow_type(gtk.SHADOW_ETCHED_IN)
+ sw.set_policy(gtk.POLICY_AUTOMATIC, gtk.POLICY_AUTOMATIC)
+
+ vbox.pack_start(sw, True, True, 0)
+
+ store = self.create_model()
+
+ treeView = gtk.TreeView(store)
+ treeView.connect("row-activated", self.on_activated)
+ treeView.set_rules_hint(True)
+ sw.add(treeView)
+
+ self.create_columns(treeView)
+ self.statusbar = gtk.Statusbar()
+
+ vbox.pack_start(self.statusbar, False, False, 0)
+
+ self.add(vbox)
+ self.show_all()
+
+
+ def create_model(self):
+ global online
+ store = gtk.ListStore(str, str, str)
+ #let's display objects from the schoolserver
+ pth = ACTIVITYPATH / 'xoconfig'
+ configf = open(pth, "r")
+ config = configf.read()
+ configf.close()
+ pos = config.find('[Server]')
+ if pos < 0:
+ print 'schoolserver not found'
+ xoserial = None
+ store.append(["schoolserver not found", "",""])
+ else:
+ pos = pos + 8
+ print 'config', config[pos:]
+ pos1 = pos + config[pos:].find("= ") + 2
+ pos2 = pos + config[pos:].find("@")
+ xoserial = config[pos1:pos2]
+ print 'xoserial', xoserial, config[pos1:pos2+1]
+ #temp for testing
+ xoserial = 'SHC84201F3B'
+ if xoserial:
+ url = "http://schoolserver/ds-restore/" + xoserial + "/datastore-latest"
+ print 'url', url
+ try:
+ response = urllib2.urlopen(url)
+ except:
+ print 'schoolserver not found'
+ response = None
+ if response:
+ soup = BeautifulSoup(response)
+ online = True
+ else:
+ print 'schoolserver not found at', url
+ if online:
+ print 'soup=', soup.prettify()
+ entries = soup.findAll("li")
+ print len(entries)
+ for i in range(10):
+ print len(entries[i].contents), entries[i].contents
+ colx = str(entries[i].contents[0])
+ pos1 = colx.find('<')
+ pos2 = colx.find('>')
+ col0 = colx[pos1:pos2]
+ col1 = 'col1' + colx[pos2+1:]
+ temp = entries[i].contents[1].split(' ')
+ col2 = 'col2:' + temp[0]
+ col3 = 'col3:' + temp[1]
+ store.append([col1, col2, col3])
+ #print 'sample', entries[0].toprettyxml()
+ #objects from the local datastore
+ results, count = datastore.find(dict())
+ print 'number of datastore items', count
+ for f in results:
+ obj = datastore.get(f.object_id)
+ f.destroy()
+ store.append([obj.get_file_path(), obj.metadata['title'], obj.metadata['mime_type']])
+ #ignore for the moment
+ return store
+
+
+ def create_columns(self, treeView):
+
+ rendererText = gtk.CellRendererText()
+ column = gtk.TreeViewColumn("Title", rendererText, text=1)
+ column.set_sort_column_id(0)
+ treeView.append_column(column)
+
+ rendererText = gtk.CellRendererText()
+ column = gtk.TreeViewColumn("Mime_type", rendererText, text=2)
+ column.set_sort_column_id(1)
+ treeView.append_column(column)
+
+
+ def on_activated(self, widget, row, col):
+
+ model = widget.get_model()
+ text = model[row][0] + ", " + model[row][1] + ", " + model[row][2]
+ self.statusbar.push(0, text)
+
+
+
+PyApp()
+gtk.main()
+
diff --git a/objectchooser.py b/objectchooser.py
new file mode 100755
index 0000000..861d0ab
--- /dev/null
+++ b/objectchooser.py
@@ -0,0 +1,118 @@
+# Copyright (C) 2007, One Laptop Per Child
+#
+# This library is free software; you can redistribute it and/or
+# modify it under the terms of the GNU Lesser General Public
+# License as published by the Free Software Foundation; either
+# version 2 of the License, or (at your option) any later version.
+#
+# This library is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+# Lesser General Public License for more details.
+#
+# You should have received a copy of the GNU Lesser General Public
+# License along with this library; if not, write to the
+# Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+# Boston, MA 02111-1307, USA.
+
+import logging
+
+import gobject
+import gtk
+import dbus
+
+from sugar.datastore import datastore
+
+J_DBUS_SERVICE = 'org.laptop.Journal'
+J_DBUS_INTERFACE = 'org.laptop.Journal'
+J_DBUS_PATH = '/org/laptop/Journal'
+
+class ObjectChooser(object):
+ def __init__(self, title=None, parent=None, flags=None, buttons=None):
+ # For backwards compatibility:
+ # - We ignore title, flags and buttons.
+ # - 'parent' can be a xid or a gtk.Window
+
+ if title is not None or flags is not None or buttons is not None:
+ logging.warning('Invocation of ObjectChooser() has deprecated '
+ 'parameters.')
+
+ if parent is None:
+ parent_xid = 0
+ elif hasattr(parent, 'window') and hasattr(parent.window, 'xid'):
+ parent_xid = parent.window.xid
+ else:
+ parent_xid = parent
+
+ self._parent_xid = parent_xid
+ self._main_loop = None
+ self._object_id = None
+ self._bus = None
+ self._chooser_id = None
+ self._response_code = gtk.RESPONSE_NONE
+
+ def run(self):
+ self._object_id = None
+
+ self._main_loop = gobject.MainLoop()
+
+ self._bus = dbus.SessionBus(mainloop=self._main_loop)
+ self._bus.add_signal_receiver(
+ self.__name_owner_changed_cb,
+ signal_name="NameOwnerChanged",
+ dbus_interface="org.freedesktop.DBus",
+ arg0=J_DBUS_SERVICE)
+
+ obj = self._bus.get_object(J_DBUS_SERVICE, J_DBUS_PATH)
+ journal = dbus.Interface(obj, J_DBUS_INTERFACE)
+ journal.connect_to_signal('ObjectChooserResponse',
+ self.__chooser_response_cb)
+ journal.connect_to_signal('ObjectChooserCancelled',
+ self.__chooser_cancelled_cb)
+ self._chooser_id = journal.ChooseObject(self._parent_xid)
+
+ gtk.gdk.threads_leave()
+ try:
+ self._main_loop.run()
+ finally:
+ gtk.gdk.threads_enter()
+ self._main_loop = None
+
+ return self._response_code
+
+ def get_selected_object(self):
+ if self._object_id is None:
+ return None
+ else:
+ return datastore.get(self._object_id)
+
+ def destroy(self):
+ self._cleanup()
+
+ def _cleanup(self):
+ if self._main_loop is not None:
+ self._main_loop.quit()
+ self._main_loop = None
+ self._bus = None
+
+ def __chooser_response_cb(self, chooser_id, object_id):
+ if chooser_id != self._chooser_id:
+ return
+ logging.debug('ObjectChooser.__chooser_response_cb: %r' % object_id)
+ self._response_code = gtk.RESPONSE_ACCEPT
+ self._object_id = object_id
+ self._cleanup()
+
+ def __chooser_cancelled_cb(self, chooser_id):
+ if chooser_id != self._chooser_id:
+ return
+ logging.debug('ObjectChooser.__chooser_cancelled_cb: %r' % chooser_id)
+ self._response_code = gtk.RESPONSE_CANCEL
+ self._cleanup()
+
+ def __name_owner_changed_cb(self, name, old, new):
+ logging.debug('ObjectChooser.__name_owner_changed_cb')
+ # Journal service disappeared from the bus
+ self._response_code = gtk.RESPONSE_CANCEL
+ self._cleanup()
+
diff --git a/objectfetch.py b/objectfetch.py
new file mode 100755
index 0000000..6c3bb92
--- /dev/null
+++ b/objectfetch.py
@@ -0,0 +1,120 @@
+# Copyright (C) 2007, One Laptop Per Child
+#
+# This library is free software; you can redistribute it and/or
+# modify it under the terms of the GNU Lesser General Public
+# License as published by the Free Software Foundation; either
+# version 2 of the License, or (at your option) any later version.
+#
+# This library is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+# Lesser General Public License for more details.
+#
+# You should have received a copy of the GNU Lesser General Public
+# License along with this library; if not, write to the
+# Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+# Boston, MA 02111-1307, USA.
+
+import logging
+
+import gobject
+import gtk
+import dbus
+
+from sugar.datastore import datastore
+
+J_DBUS_SERVICE = 'org.laptop.Journal'
+J_DBUS_INTERFACE = 'org.laptop.Journal'
+J_DBUS_PATH = '/org/laptop/Journal'
+
+class ObjectChooser(object):
+ def __init__(self, title=None, parent=None, flags=None, buttons=None):
+ # For backwards compatibility:
+ # - We ignore title, flags and buttons.
+ # - 'parent' can be a xid or a gtk.Window
+
+ if title is not None or flags is not None or buttons is not None:
+ logging.warning('Invocation of ObjectChooser() has deprecated '
+ 'parameters.')
+
+ if parent is None:
+ parent_xid = 0
+ elif hasattr(parent, 'window') and hasattr(parent.window, 'xid'):
+ parent_xid = parent.window.xid
+ else:
+ parent_xid = parent
+
+ self._parent_xid = parent_xid
+ self._main_loop = None
+ self._object_id = None
+ self._bus = None
+ self._chooser_id = None
+ self._response_code = gtk.RESPONSE_NONE
+
+ def run(self):
+ self._object_id = None
+
+ self._main_loop = gobject.MainLoop()
+
+ self._bus = dbus.SessionBus(mainloop=self._main_loop)
+ self._bus.add_signal_receiver(
+ self.__name_owner_changed_cb,
+ signal_name="NameOwnerChanged",
+ dbus_interface="org.freedesktop.DBus",
+ arg0=J_DBUS_SERVICE)
+
+ obj = self._bus.get_object(J_DBUS_SERVICE, J_DBUS_PATH)
+ print 'obj', obj.get_metadata['title']
+ print 'obj', obj.file_path
+ journal = dbus.Interface(obj, J_DBUS_INTERFACE)
+ journal.connect_to_signal('ObjectChooserResponse',
+ self.__chooser_response_cb)
+ journal.connect_to_signal('ObjectChooserCancelled',
+ self.__chooser_cancelled_cb)
+ self._chooser_id = journal.ChooseObject(self._parent_xid)
+
+ gtk.gdk.threads_leave()
+ try:
+ self._main_loop.run()
+ finally:
+ gtk.gdk.threads_enter()
+ self._main_loop = None
+
+ return self._response_code
+
+ def get_selected_object(self):
+ if self._object_id is None:
+ return None
+ else:
+ return datastore.get(self._object_id)
+
+ def destroy(self):
+ self._cleanup()
+
+ def _cleanup(self):
+ if self._main_loop is not None:
+ self._main_loop.quit()
+ self._main_loop = None
+ self._bus = None
+
+ def __chooser_response_cb(self, chooser_id, object_id):
+ if chooser_id != self._chooser_id:
+ return
+ logging.debug('ObjectChooser.__chooser_response_cb: %r' % object_id)
+ self._response_code = gtk.RESPONSE_ACCEPT
+ self._object_id = object_id
+ self._cleanup()
+
+ def __chooser_cancelled_cb(self, chooser_id):
+ if chooser_id != self._chooser_id:
+ return
+ logging.debug('ObjectChooser.__chooser_cancelled_cb: %r' % chooser_id)
+ self._response_code = gtk.RESPONSE_CANCEL
+ self._cleanup()
+
+ def __name_owner_changed_cb(self, name, old, new):
+ logging.debug('ObjectChooser.__name_owner_changed_cb')
+ # Journal service disappeared from the bus
+ self._response_code = gtk.RESPONSE_CANCEL
+ self._cleanup()
+
diff --git a/path.py b/path.py
new file mode 100755
index 0000000..01c2c04
--- /dev/null
+++ b/path.py
@@ -0,0 +1,971 @@
+""" path.py - An object representing a path to a file or directory.
+
+Example:
+
+from path import path
+d = path('/home/guido/bin')
+for f in d.files('*.py'):
+ f.chmod(0755)
+
+This module requires Python 2.2 or later.
+
+
+URL: http://www.jorendorff.com/articles/python/path
+Author: Jason Orendorff <jason.orendorff\x40gmail\x2ecom> (and others - see the url!)
+Date: 9 Mar 2007
+"""
+
+
+# TODO
+# - Tree-walking functions don't avoid symlink loops. Matt Harrison
+# sent me a patch for this.
+# - Bug in write_text(). It doesn't support Universal newline mode.
+# - Better error message in listdir() when self isn't a
+# directory. (On Windows, the error message really sucks.)
+# - Make sure everything has a good docstring.
+# - Add methods for regex find and replace.
+# - guess_content_type() method?
+# - Perhaps support arguments to touch().
+
+from __future__ import generators
+
+import sys, warnings, os, fnmatch, glob, shutil, codecs, md5
+
+__version__ = '2.2'
+__all__ = ['path']
+
+# Platform-specific support for path.owner
+if os.name == 'nt':
+ try:
+ import win32security
+ except ImportError:
+ win32security = None
+else:
+ try:
+ import pwd
+ except ImportError:
+ pwd = None
+
+# Pre-2.3 support. Are unicode filenames supported?
+_base = str
+_getcwd = os.getcwd
+try:
+ if os.path.supports_unicode_filenames:
+ _base = unicode
+ _getcwd = os.getcwdu
+except AttributeError:
+ pass
+
+# Pre-2.3 workaround for booleans
+try:
+ True, False
+except NameError:
+ True, False = 1, 0
+
+# Pre-2.3 workaround for basestring.
+try:
+ basestring
+except NameError:
+ basestring = (str, unicode)
+
+# Universal newline support
+_textmode = 'r'
+if hasattr(file, 'newlines'):
+ _textmode = 'U'
+
+
+class TreeWalkWarning(Warning):
+ pass
+
+class path(_base):
+ """ Represents a filesystem path.
+
+ For documentation on individual methods, consult their
+ counterparts in os.path.
+ """
+
+ # --- Special Python methods.
+
+ def __repr__(self):
+ return 'path(%s)' % _base.__repr__(self)
+
+ # Adding a path and a string yields a path.
+ def __add__(self, more):
+ try:
+ resultStr = _base.__add__(self, more)
+ except TypeError: #Python bug
+ resultStr = NotImplemented
+ if resultStr is NotImplemented:
+ return resultStr
+ return self.__class__(resultStr)
+
+ def __radd__(self, other):
+ if isinstance(other, basestring):
+ return self.__class__(other.__add__(self))
+ else:
+ return NotImplemented
+
+ # The / operator joins paths.
+ def __div__(self, rel):
+ """ fp.__div__(rel) == fp / rel == fp.joinpath(rel)
+
+ Join two path components, adding a separator character if
+ needed.
+ """
+ return self.__class__(os.path.join(self, rel))
+
+ # Make the / operator work even when true division is enabled.
+ __truediv__ = __div__
+
+ def getcwd(cls):
+ """ Return the current working directory as a path object. """
+ return cls(_getcwd())
+ getcwd = classmethod(getcwd)
+
+
+ # --- Operations on path strings.
+
+ isabs = os.path.isabs
+ def abspath(self): return self.__class__(os.path.abspath(self))
+ def normcase(self): return self.__class__(os.path.normcase(self))
+ def normpath(self): return self.__class__(os.path.normpath(self))
+ def realpath(self): return self.__class__(os.path.realpath(self))
+ def expanduser(self): return self.__class__(os.path.expanduser(self))
+ def expandvars(self): return self.__class__(os.path.expandvars(self))
+ def dirname(self): return self.__class__(os.path.dirname(self))
+ basename = os.path.basename
+
+ def expand(self):
+ """ Clean up a filename by calling expandvars(),
+ expanduser(), and normpath() on it.
+
+ This is commonly everything needed to clean up a filename
+ read from a configuration file, for example.
+ """
+ return self.expandvars().expanduser().normpath()
+
+ def _get_namebase(self):
+ base, ext = os.path.splitext(self.name)
+ return base
+
+ def _get_ext(self):
+ f, ext = os.path.splitext(_base(self))
+ return ext
+
+ def _get_drive(self):
+ drive, r = os.path.splitdrive(self)
+ return self.__class__(drive)
+
+ parent = property(
+ dirname, None, None,
+ """ This path's parent directory, as a new path object.
+
+ For example, path('/usr/local/lib/libpython.so').parent == path('/usr/local/lib')
+ """)
+
+ name = property(
+ basename, None, None,
+ """ The name of this file or directory without the full path.
+
+ For example, path('/usr/local/lib/libpython.so').name == 'libpython.so'
+ """)
+
+ namebase = property(
+ _get_namebase, None, None,
+ """ The same as path.name, but with one file extension stripped off.
+
+ For example, path('/home/guido/python.tar.gz').name == 'python.tar.gz',
+ but path('/home/guido/python.tar.gz').namebase == 'python.tar'
+ """)
+
+ ext = property(
+ _get_ext, None, None,
+ """ The file extension, for example '.py'. """)
+
+ drive = property(
+ _get_drive, None, None,
+ """ The drive specifier, for example 'C:'.
+ This is always empty on systems that don't use drive specifiers.
+ """)
+
+ def splitpath(self):
+ """ p.splitpath() -> Return (p.parent, p.name). """
+ parent, child = os.path.split(self)
+ return self.__class__(parent), child
+
+ def splitdrive(self):
+ """ p.splitdrive() -> Return (p.drive, <the rest of p>).
+
+ Split the drive specifier from this path. If there is
+ no drive specifier, p.drive is empty, so the return value
+ is simply (path(''), p). This is always the case on Unix.
+ """
+ drive, rel = os.path.splitdrive(self)
+ return self.__class__(drive), rel
+
+ def splitext(self):
+ """ p.splitext() -> Return (p.stripext(), p.ext).
+
+ Split the filename extension from this path and return
+ the two parts. Either part may be empty.
+
+ The extension is everything from '.' to the end of the
+ last path segment. This has the property that if
+ (a, b) == p.splitext(), then a + b == p.
+ """
+ filename, ext = os.path.splitext(self)
+ return self.__class__(filename), ext
+
+ def stripext(self):
+ """ p.stripext() -> Remove one file extension from the path.
+
+ For example, path('/home/guido/python.tar.gz').stripext()
+ returns path('/home/guido/python.tar').
+ """
+ return self.splitext()[0]
+
+ if hasattr(os.path, 'splitunc'):
+ def splitunc(self):
+ unc, rest = os.path.splitunc(self)
+ return self.__class__(unc), rest
+
+ def _get_uncshare(self):
+ unc, r = os.path.splitunc(self)
+ return self.__class__(unc)
+
+ uncshare = property(
+ _get_uncshare, None, None,
+ """ The UNC mount point for this path.
+ This is empty for paths on local drives. """)
+
+ def joinpath(self, *args):
+ """ Join two or more path components, adding a separator
+ character (os.sep) if needed. Returns a new path
+ object.
+ """
+ return self.__class__(os.path.join(self, *args))
+
+ def splitall(self):
+ r""" Return a list of the path components in this path.
+
+ The first item in the list will be a path. Its value will be
+ either os.curdir, os.pardir, empty, or the root directory of
+ this path (for example, '/' or 'C:\\'). The other items in
+ the list will be strings.
+
+ path.path.joinpath(*result) will yield the original path.
+ """
+ parts = []
+ loc = self
+ while loc != os.curdir and loc != os.pardir:
+ prev = loc
+ loc, child = prev.splitpath()
+ if loc == prev:
+ break
+ parts.append(child)
+ parts.append(loc)
+ parts.reverse()
+ return parts
+
+ def relpath(self):
+ """ Return this path as a relative path,
+ based from the current working directory.
+ """
+ cwd = self.__class__(os.getcwd())
+ return cwd.relpathto(self)
+
+ def relpathto(self, dest):
+ """ Return a relative path from self to dest.
+
+ If there is no relative path from self to dest, for example if
+ they reside on different drives in Windows, then this returns
+ dest.abspath().
+ """
+ origin = self.abspath()
+ dest = self.__class__(dest).abspath()
+
+ orig_list = origin.normcase().splitall()
+ # Don't normcase dest! We want to preserve the case.
+ dest_list = dest.splitall()
+
+ if orig_list[0] != os.path.normcase(dest_list[0]):
+ # Can't get here from there.
+ return dest
+
+ # Find the location where the two paths start to differ.
+ i = 0
+ for start_seg, dest_seg in zip(orig_list, dest_list):
+ if start_seg != os.path.normcase(dest_seg):
+ break
+ i += 1
+
+ # Now i is the point where the two paths diverge.
+ # Need a certain number of "os.pardir"s to work up
+ # from the origin to the point of divergence.
+ segments = [os.pardir] * (len(orig_list) - i)
+ # Need to add the diverging part of dest_list.
+ segments += dest_list[i:]
+ if len(segments) == 0:
+ # If they happen to be identical, use os.curdir.
+ relpath = os.curdir
+ else:
+ relpath = os.path.join(*segments)
+ return self.__class__(relpath)
+
+ # --- Listing, searching, walking, and matching
+
+ def listdir(self, pattern=None):
+ """ D.listdir() -> List of items in this directory.
+
+ Use D.files() or D.dirs() instead if you want a listing
+ of just files or just subdirectories.
+
+ The elements of the list are path objects.
+
+ With the optional 'pattern' argument, this only lists
+ items whose names match the given pattern.
+ """
+ names = os.listdir(self)
+ if pattern is not None:
+ names = fnmatch.filter(names, pattern)
+ return [self / child for child in names]
+
+ def dirs(self, pattern=None):
+ """ D.dirs() -> List of this directory's subdirectories.
+
+ The elements of the list are path objects.
+ This does not walk recursively into subdirectories
+ (but see path.walkdirs).
+
+ With the optional 'pattern' argument, this only lists
+ directories whose names match the given pattern. For
+ example, d.dirs('build-*').
+ """
+ return [p for p in self.listdir(pattern) if p.isdir()]
+
+ def files(self, pattern=None):
+ """ D.files() -> List of the files in this directory.
+
+ The elements of the list are path objects.
+ This does not walk into subdirectories (see path.walkfiles).
+
+ With the optional 'pattern' argument, this only lists files
+ whose names match the given pattern. For example,
+ d.files('*.pyc').
+ """
+
+ return [p for p in self.listdir(pattern) if p.isfile()]
+
+ def walk(self, pattern=None, errors='strict'):
+ """ D.walk() -> iterator over files and subdirs, recursively.
+
+ The iterator yields path objects naming each child item of
+ this directory and its descendants. This requires that
+ D.isdir().
+
+ This performs a depth-first traversal of the directory tree.
+ Each directory is returned just before all its children.
+
+ The errors= keyword argument controls behavior when an
+ error occurs. The default is 'strict', which causes an
+ exception. The other allowed values are 'warn', which
+ reports the error via warnings.warn(), and 'ignore'.
+ """
+ if errors not in ('strict', 'warn', 'ignore'):
+ raise ValueError("invalid errors parameter")
+
+ try:
+ childList = self.listdir()
+ except Exception:
+ if errors == 'ignore':
+ return
+ elif errors == 'warn':
+ warnings.warn(
+ "Unable to list directory '%s': %s"
+ % (self, sys.exc_info()[1]),
+ TreeWalkWarning)
+ return
+ else:
+ raise
+
+ for child in childList:
+ if pattern is None or child.fnmatch(pattern):
+ yield child
+ try:
+ isdir = child.isdir()
+ except Exception:
+ if errors == 'ignore':
+ isdir = False
+ elif errors == 'warn':
+ warnings.warn(
+ "Unable to access '%s': %s"
+ % (child, sys.exc_info()[1]),
+ TreeWalkWarning)
+ isdir = False
+ else:
+ raise
+
+ if isdir:
+ for item in child.walk(pattern, errors):
+ yield item
+
+ def walkdirs(self, pattern=None, errors='strict'):
+ """ D.walkdirs() -> iterator over subdirs, recursively.
+
+ With the optional 'pattern' argument, this yields only
+ directories whose names match the given pattern. For
+ example, mydir.walkdirs('*test') yields only directories
+ with names ending in 'test'.
+
+ The errors= keyword argument controls behavior when an
+ error occurs. The default is 'strict', which causes an
+ exception. The other allowed values are 'warn', which
+ reports the error via warnings.warn(), and 'ignore'.
+ """
+ if errors not in ('strict', 'warn', 'ignore'):
+ raise ValueError("invalid errors parameter")
+
+ try:
+ dirs = self.dirs()
+ except Exception:
+ if errors == 'ignore':
+ return
+ elif errors == 'warn':
+ warnings.warn(
+ "Unable to list directory '%s': %s"
+ % (self, sys.exc_info()[1]),
+ TreeWalkWarning)
+ return
+ else:
+ raise
+
+ for child in dirs:
+ if pattern is None or child.fnmatch(pattern):
+ yield child
+ for subsubdir in child.walkdirs(pattern, errors):
+ yield subsubdir
+
+ def walkfiles(self, pattern=None, errors='strict'):
+ """ D.walkfiles() -> iterator over files in D, recursively.
+
+ The optional argument, pattern, limits the results to files
+ with names that match the pattern. For example,
+ mydir.walkfiles('*.tmp') yields only files with the .tmp
+ extension.
+ """
+ if errors not in ('strict', 'warn', 'ignore'):
+ raise ValueError("invalid errors parameter")
+
+ try:
+ childList = self.listdir()
+ except Exception:
+ if errors == 'ignore':
+ return
+ elif errors == 'warn':
+ warnings.warn(
+ "Unable to list directory '%s': %s"
+ % (self, sys.exc_info()[1]),
+ TreeWalkWarning)
+ return
+ else:
+ raise
+
+ for child in childList:
+ try:
+ isfile = child.isfile()
+ isdir = not isfile and child.isdir()
+ except:
+ if errors == 'ignore':
+ continue
+ elif errors == 'warn':
+ warnings.warn(
+ "Unable to access '%s': %s"
+ % (self, sys.exc_info()[1]),
+ TreeWalkWarning)
+ continue
+ else:
+ raise
+
+ if isfile:
+ if pattern is None or child.fnmatch(pattern):
+ yield child
+ elif isdir:
+ for f in child.walkfiles(pattern, errors):
+ yield f
+
+ def fnmatch(self, pattern):
+ """ Return True if self.name matches the given pattern.
+
+ pattern - A filename pattern with wildcards,
+ for example '*.py'.
+ """
+ return fnmatch.fnmatch(self.name, pattern)
+
+ def glob(self, pattern):
+ """ Return a list of path objects that match the pattern.
+
+ pattern - a path relative to this directory, with wildcards.
+
+ For example, path('/users').glob('*/bin/*') returns a list
+ of all the files users have in their bin directories.
+ """
+ cls = self.__class__
+ return [cls(s) for s in glob.glob(_base(self / pattern))]
+
+
+ # --- Reading or writing an entire file at once.
+
+ def open(self, mode='r'):
+ """ Open this file. Return a file object. """
+ return file(self, mode)
+
+ def bytes(self):
+ """ Open this file, read all bytes, return them as a string. """
+ f = self.open('rb')
+ try:
+ return f.read()
+ finally:
+ f.close()
+
+ def write_bytes(self, bytes, append=False):
+ """ Open this file and write the given bytes to it.
+
+ Default behavior is to overwrite any existing file.
+ Call p.write_bytes(bytes, append=True) to append instead.
+ """
+ if append:
+ mode = 'ab'
+ else:
+ mode = 'wb'
+ f = self.open(mode)
+ try:
+ f.write(bytes)
+ finally:
+ f.close()
+
+ def text(self, encoding=None, errors='strict'):
+ r""" Open this file, read it in, return the content as a string.
+
+ This uses 'U' mode in Python 2.3 and later, so '\r\n' and '\r'
+ are automatically translated to '\n'.
+
+ Optional arguments:
+
+ encoding - The Unicode encoding (or character set) of
+ the file. If present, the content of the file is
+ decoded and returned as a unicode object; otherwise
+ it is returned as an 8-bit str.
+ errors - How to handle Unicode errors; see help(str.decode)
+ for the options. Default is 'strict'.
+ """
+ if encoding is None:
+ # 8-bit
+ f = self.open(_textmode)
+ try:
+ return f.read()
+ finally:
+ f.close()
+ else:
+ # Unicode
+ f = codecs.open(self, 'r', encoding, errors)
+ # (Note - Can't use 'U' mode here, since codecs.open
+ # doesn't support 'U' mode, even in Python 2.3.)
+ try:
+ t = f.read()
+ finally:
+ f.close()
+ return (t.replace(u'\r\n', u'\n')
+ .replace(u'\r\x85', u'\n')
+ .replace(u'\r', u'\n')
+ .replace(u'\x85', u'\n')
+ .replace(u'\u2028', u'\n'))
+
+ def write_text(self, text, encoding=None, errors='strict', linesep=os.linesep, append=False):
+ r""" Write the given text to this file.
+
+ The default behavior is to overwrite any existing file;
+ to append instead, use the 'append=True' keyword argument.
+
+ There are two differences between path.write_text() and
+ path.write_bytes(): newline handling and Unicode handling.
+ See below.
+
+ Parameters:
+
+ - text - str/unicode - The text to be written.
+
+ - encoding - str - The Unicode encoding that will be used.
+ This is ignored if 'text' isn't a Unicode string.
+
+ - errors - str - How to handle Unicode encoding errors.
+ Default is 'strict'. See help(unicode.encode) for the
+ options. This is ignored if 'text' isn't a Unicode
+ string.
+
+ - linesep - keyword argument - str/unicode - The sequence of
+ characters to be used to mark end-of-line. The default is
+ os.linesep. You can also specify None; this means to
+ leave all newlines as they are in 'text'.
+
+ - append - keyword argument - bool - Specifies what to do if
+ the file already exists (True: append to the end of it;
+ False: overwrite it.) The default is False.
+
+
+ --- Newline handling.
+
+ write_text() converts all standard end-of-line sequences
+ ('\n', '\r', and '\r\n') to your platform's default end-of-line
+ sequence (see os.linesep; on Windows, for example, the
+ end-of-line marker is '\r\n').
+
+ If you don't like your platform's default, you can override it
+ using the 'linesep=' keyword argument. If you specifically want
+ write_text() to preserve the newlines as-is, use 'linesep=None'.
+
+ This applies to Unicode text the same as to 8-bit text, except
+ there are three additional standard Unicode end-of-line sequences:
+ u'\x85', u'\r\x85', and u'\u2028'.
+
+ (This is slightly different from when you open a file for
+ writing with fopen(filename, "w") in C or file(filename, 'w')
+ in Python.)
+
+
+ --- Unicode
+
+ If 'text' isn't Unicode, then apart from newline handling, the
+ bytes are written verbatim to the file. The 'encoding' and
+ 'errors' arguments are not used and must be omitted.
+
+ If 'text' is Unicode, it is first converted to bytes using the
+ specified 'encoding' (or the default encoding if 'encoding'
+ isn't specified). The 'errors' argument applies only to this
+ conversion.
+
+ """
+ if isinstance(text, unicode):
+ if linesep is not None:
+ # Convert all standard end-of-line sequences to
+ # ordinary newline characters.
+ text = (text.replace(u'\r\n', u'\n')
+ .replace(u'\r\x85', u'\n')
+ .replace(u'\r', u'\n')
+ .replace(u'\x85', u'\n')
+ .replace(u'\u2028', u'\n'))
+ text = text.replace(u'\n', linesep)
+ if encoding is None:
+ encoding = sys.getdefaultencoding()
+ bytes = text.encode(encoding, errors)
+ else:
+ # It is an error to specify an encoding if 'text' is
+ # an 8-bit string.
+ assert encoding is None
+
+ if linesep is not None:
+ text = (text.replace('\r\n', '\n')
+ .replace('\r', '\n'))
+ bytes = text.replace('\n', linesep)
+
+ self.write_bytes(bytes, append)
+
+ def lines(self, encoding=None, errors='strict', retain=True):
+ r""" Open this file, read all lines, return them in a list.
+
+ Optional arguments:
+ encoding - The Unicode encoding (or character set) of
+ the file. The default is None, meaning the content
+ of the file is read as 8-bit characters and returned
+ as a list of (non-Unicode) str objects.
+ errors - How to handle Unicode errors; see help(str.decode)
+ for the options. Default is 'strict'
+ retain - If true, retain newline characters; but all newline
+ character combinations ('\r', '\n', '\r\n') are
+ translated to '\n'. If false, newline characters are
+ stripped off. Default is True.
+
+ This uses 'U' mode in Python 2.3 and later.
+ """
+ if encoding is None and retain:
+ f = self.open(_textmode)
+ try:
+ return f.readlines()
+ finally:
+ f.close()
+ else:
+ return self.text(encoding, errors).splitlines(retain)
+
+ def write_lines(self, lines, encoding=None, errors='strict',
+ linesep=os.linesep, append=False):
+ r""" Write the given lines of text to this file.
+
+ By default this overwrites any existing file at this path.
+
+ This puts a platform-specific newline sequence on every line.
+ See 'linesep' below.
+
+ lines - A list of strings.
+
+ encoding - A Unicode encoding to use. This applies only if
+ 'lines' contains any Unicode strings.
+
+ errors - How to handle errors in Unicode encoding. This
+ also applies only to Unicode strings.
+
+ linesep - The desired line-ending. This line-ending is
+ applied to every line. If a line already has any
+ standard line ending ('\r', '\n', '\r\n', u'\x85',
+ u'\r\x85', u'\u2028'), that will be stripped off and
+ this will be used instead. The default is os.linesep,
+ which is platform-dependent ('\r\n' on Windows, '\n' on
+ Unix, etc.) Specify None to write the lines as-is,
+ like file.writelines().
+
+ Use the keyword argument append=True to append lines to the
+ file. The default is to overwrite the file. Warning:
+ When you use this with Unicode data, if the encoding of the
+ existing data in the file is different from the encoding
+ you specify with the encoding= parameter, the result is
+ mixed-encoding data, which can really confuse someone trying
+ to read the file later.
+ """
+ if append:
+ mode = 'ab'
+ else:
+ mode = 'wb'
+ f = self.open(mode)
+ try:
+ for line in lines:
+ isUnicode = isinstance(line, unicode)
+ if linesep is not None:
+ # Strip off any existing line-end and add the
+ # specified linesep string.
+ if isUnicode:
+ if line[-2:] in (u'\r\n', u'\x0d\x85'):
+ line = line[:-2]
+ elif line[-1:] in (u'\r', u'\n',
+ u'\x85', u'\u2028'):
+ line = line[:-1]
+ else:
+ if line[-2:] == '\r\n':
+ line = line[:-2]
+ elif line[-1:] in ('\r', '\n'):
+ line = line[:-1]
+ line += linesep
+ if isUnicode:
+ if encoding is None:
+ encoding = sys.getdefaultencoding()
+ line = line.encode(encoding, errors)
+ f.write(line)
+ finally:
+ f.close()
+
+ def read_md5(self):
+ """ Calculate the md5 hash for this file.
+
+ This reads through the entire file.
+ """
+ f = self.open('rb')
+ try:
+ m = md5.new()
+ while True:
+ d = f.read(8192)
+ if not d:
+ break
+ m.update(d)
+ finally:
+ f.close()
+ return m.digest()
+
+ # --- Methods for querying the filesystem.
+
+ exists = os.path.exists
+ isdir = os.path.isdir
+ isfile = os.path.isfile
+ islink = os.path.islink
+ ismount = os.path.ismount
+
+ if hasattr(os.path, 'samefile'):
+ samefile = os.path.samefile
+
+ getatime = os.path.getatime
+ atime = property(
+ getatime, None, None,
+ """ Last access time of the file. """)
+
+ getmtime = os.path.getmtime
+ mtime = property(
+ getmtime, None, None,
+ """ Last-modified time of the file. """)
+
+ if hasattr(os.path, 'getctime'):
+ getctime = os.path.getctime
+ ctime = property(
+ getctime, None, None,
+ """ Creation time of the file. """)
+
+ getsize = os.path.getsize
+ size = property(
+ getsize, None, None,
+ """ Size of the file, in bytes. """)
+
+ if hasattr(os, 'access'):
+ def access(self, mode):
+ """ Return true if current user has access to this path.
+
+ mode - One of the constants os.F_OK, os.R_OK, os.W_OK, os.X_OK
+ """
+ return os.access(self, mode)
+
+ def stat(self):
+ """ Perform a stat() system call on this path. """
+ return os.stat(self)
+
+ def lstat(self):
+ """ Like path.stat(), but do not follow symbolic links. """
+ return os.lstat(self)
+
+ def get_owner(self):
+ r""" Return the name of the owner of this file or directory.
+
+ This follows symbolic links.
+
+ On Windows, this returns a name of the form ur'DOMAIN\User Name'.
+ On Windows, a group can own a file or directory.
+ """
+ if os.name == 'nt':
+ if win32security is None:
+ raise Exception("path.owner requires win32all to be installed")
+ desc = win32security.GetFileSecurity(
+ self, win32security.OWNER_SECURITY_INFORMATION)
+ sid = desc.GetSecurityDescriptorOwner()
+ account, domain, typecode = win32security.LookupAccountSid(None, sid)
+ return domain + u'\\' + account
+ else:
+ if pwd is None:
+ raise NotImplementedError("path.owner is not implemented on this platform.")
+ st = self.stat()
+ return pwd.getpwuid(st.st_uid).pw_name
+
+ owner = property(
+ get_owner, None, None,
+ """ Name of the owner of this file or directory. """)
+
+ if hasattr(os, 'statvfs'):
+ def statvfs(self):
+ """ Perform a statvfs() system call on this path. """
+ return os.statvfs(self)
+
+ if hasattr(os, 'pathconf'):
+ def pathconf(self, name):
+ return os.pathconf(self, name)
+
+
+ # --- Modifying operations on files and directories
+
+ def utime(self, times):
+ """ Set the access and modified times of this file. """
+ os.utime(self, times)
+
+ def chmod(self, mode):
+ os.chmod(self, mode)
+
+ if hasattr(os, 'chown'):
+ def chown(self, uid, gid):
+ os.chown(self, uid, gid)
+
+ def rename(self, new):
+ os.rename(self, new)
+
+ def renames(self, new):
+ os.renames(self, new)
+
+
+ # --- Create/delete operations on directories
+
+ def mkdir(self, mode=0777):
+ os.mkdir(self, mode)
+
+ def makedirs(self, mode=0777):
+ os.makedirs(self, mode)
+
+ def rmdir(self):
+ os.rmdir(self)
+
+ def removedirs(self):
+ os.removedirs(self)
+
+
+ # --- Modifying operations on files
+
+ def touch(self):
+ """ Set the access/modified times of this file to the current time.
+ Create the file if it does not exist.
+ """
+ fd = os.open(self, os.O_WRONLY | os.O_CREAT, 0666)
+ os.close(fd)
+ os.utime(self, None)
+
+ def remove(self):
+ os.remove(self)
+
+ def unlink(self):
+ os.unlink(self)
+
+
+ # --- Links
+
+ if hasattr(os, 'link'):
+ def link(self, newpath):
+ """ Create a hard link at 'newpath', pointing to this file. """
+ os.link(self, newpath)
+
+ if hasattr(os, 'symlink'):
+ def symlink(self, newlink):
+ """ Create a symbolic link at 'newlink', pointing here. """
+ os.symlink(self, newlink)
+
+ if hasattr(os, 'readlink'):
+ def readlink(self):
+ """ Return the path to which this symbolic link points.
+
+ The result may be an absolute or a relative path.
+ """
+ return self.__class__(os.readlink(self))
+
+ def readlinkabs(self):
+ """ Return the path to which this symbolic link points.
+
+ The result is always an absolute path.
+ """
+ p = self.readlink()
+ if p.isabs():
+ return p
+ else:
+ return (self.parent / p).abspath()
+
+
+ # --- High-level functions from shutil
+
+ copyfile = shutil.copyfile
+ copymode = shutil.copymode
+ copystat = shutil.copystat
+ copy = shutil.copy
+ copy2 = shutil.copy2
+ copytree = shutil.copytree
+ if hasattr(shutil, 'move'):
+ move = shutil.move
+ rmtree = shutil.rmtree
+
+
+ # --- Special stuff from os
+
+ if hasattr(os, 'chroot'):
+ def chroot(self):
+ os.chroot(self)
+
+ if hasattr(os, 'startfile'):
+ def startfile(self):
+ os.startfile(self)
+
+
diff --git a/xoconfig b/xoconfig
new file mode 100755
index 0000000..733851b
--- /dev/null
+++ b/xoconfig
@@ -0,0 +1,25 @@
+[Sound]
+volume = 100
+
+[Shell]
+favoriteslayout = ring-layout
+
+[Buddy]
+color = #FF8F00,#00B20D
+nickname = GOV007
+
+[Power]
+automaticpm = False
+extremepm = False
+
+[Frame]
+hotcorners = 0.0
+warmedges = 1000.0
+
+[Date]
+timezone = UTC
+
+[Jabber]
+registered = False
+server = schoolserver.schoolnet.gov.np
+