"""General helper functions for WAeUP. """ import os import re import sys import shutil import grok from cStringIO import StringIO from docutils.core import publish_string from zope.component.interfaces import IFactory from zope.interface import implementedBy from zope.schema import getFieldNames from zope.schema.fieldproperty import FieldProperty def removeFileOrDirectory(filepath): """Remove a file or directory. Different to :func:`shutil.rmtree` we also accept not existing paths (returning silently) and if a dir turns out to be a regular file, we remove that. """ filepath = os.path.abspath(filepath) if not os.path.exists(filepath): return if os.path.isdir(filepath): shutil.rmtree(filepath) else: os.unlink(filepath) return def copyFileSystemTree(src, dst, overwrite=False, del_old=False): """Copy contents of directory src to directory dst. Both directories must exists. If `overwrite` is true, any same named objects will be overwritten. Otherwise these files will not be touched. If `del_old` is true, copied files and directories will be removed from the src directory. This functions returns a list of non-copied files. Unix hidden files and directories (starting with '.') are not processed by this function. """ if not os.path.exists(src): raise ValueError('source path does not exist: %s' % src) if not os.path.exists(dst): raise ValueError('destination path does not exist: %s' % dst) if not os.path.isdir(src): raise ValueError('source path is not a directory: %s' % src) if not os.path.isdir(dst): raise ValueError('destination path is not a directory: %s' % dst) not_copied = [] for item in os.listdir(src): if item.startswith('.'): continue # We do not copy hidden stuff... itemsrc = os.path.join(src, item) itemdst = os.path.join(dst, item) if os.path.exists(itemdst): if overwrite is True: removeFileOrDirectory(itemdst) else: not_copied.append(item) continue if os.path.isdir(itemsrc): shutil.copytree(itemsrc, itemdst) else: shutil.copy2(itemsrc, itemdst) if del_old: removeFileOrDirectory(itemsrc) return not_copied def getInnerHTMLPart(html_code): """Return the 'inner' part of a complete HTML snippet. If there is a form part, get this. If there is no form part, try to return the body part contents. If there is no body, return as-is. Let's see how that works. If we deliver some doc with form, we will get that form only: >>> doc = '
My Form
Outside the form' >>> getInnerHTMLPart(doc) '
My Form
' No form? Then seek for a body part and get the contents: >>> doc = 'My BodyTrailing Trash' >>> getInnerHTMLPart(doc) 'My Body' If none of these is included, return what we got: >>> doc = 'without body nor form' >>> getInnerHTMLPart(doc) 'without body nor form' """ try: result = re.match('^.+(]*>.*).+$', html_code, re.DOTALL).groups()[0] return result except AttributeError: # No
part included try: result = re.match('^.+]*>(.*).*$', html_code, re.DOTALL).groups()[0] return result except AttributeError: # No and no tag... pass return html_code class FactoryBase(grok.GlobalUtility): """A factory for things. This is a baseclass for easier creation of factories. Factories are utilities that are registered under a certain name and return instances of certain classes when called. In :mod:`waeup.sirp` we use factories extensively for batching. While processing a batch some importer looks up a factory to create real-world instances that then get filled with data from imported CSV files. To get rid of reimplementing the same stuff over and over again, most notably the methods defined here, we offer this base class (which will *not* be registered as a factory itself). Real factories can then be created like this: >>> import grok >>> from waeup.sirp.utils.helpers import FactoryBase >>> class MyObject(object): ... # Some class we want to get instances of. ... pass >>> class MyObjectFactory(FactoryBase): ... # This is the factory for MyObject instances ... grok.name(u'waeup.sirp.factory.MyObject') ... factory = MyObject That's it. It is essential to set the ``factory`` attribute, which will determine the class of which instances should be created when called. The given name must even be unique amongst all utilities registered during runtime. While you can pick any name you like you might want to prepend ``waeup.sirp.factory.`` to the name string to make sure it does not clash with names of other utilities one day. Before all this works we have to grok the baseclass once and our freshly defined factory. This executes all the component registration stuff we don't want to do ourselves. In daily use this is done automatically on startup of a :mod:`waeup.sirp` system. >>> grok.testing.grok('waeup.sirp.utils.helpers') >>> grok.testing.grok_component( ... 'MyObjectFactory', MyObjectFactory ... ) True After grokking we (and importers) can create objects without knowing about the location of the real class definition, just by the factory name: >>> from zope.component import createObject >>> obj = createObject('waeup.sirp.factory.MyObject') >>> isinstance(obj, MyObject) True We can also use the regular utility lookups to find our new factory: >>> from zope.component import getUtility >>> from zope.component.interfaces import IFactory >>> factory = getUtility( ... IFactory, name='waeup.sirp.factory.MyObject' ... ) >>> isinstance(factory, MyObjectFactory) True And this factory generates `MyObject` instances: >>> obj = factory() >>> isinstance(obj, MyObject) True """ grok.baseclass() # Do not grok this class, do not register us. grok.implements(IFactory) # You can override any of the following attributes in derived # classes. The `grok.name` setting *must* even be set to some # unique value. grok.name(u'waeup.Factory') title = u"Create instances of ``factory``.", description = u"This factory instantiates new applicant instances." factory = None def __call__(self, *args, **kw): """The main factory function. Returns an instance of the requested object. """ return self.factory() def getInterfaces(self): # Required by IFactory return implementedBy(self.factory) def ReST2HTML_w_warnings(source_string): """Convert a reStructuredText string to HTML preserving warnings. Returns a tuple ``(, )``, both being strings. Where ```` is the HTML code generated from the source string (in unicode), ```` is a string containing any warning messages or ``None``. Regular multi-line ReStructuredText strings will be returned as HTML code: >>> from waeup.sirp.utils.helpers import ReST2HTML >>> source = ''' ... Headline ... ======== ... ... - A list item ... - Another item ... ... Thanks for watching! ... ''' >>> html, warnings = ReST2HTML_w_warnings(source) >>> print html

Headline

  • A list item
  • Another item

Thanks for watching!

Here no warnings happened, so the `warnings` are ``None``: >>> warnings is None True If warnings happen then they can be retrieved in the returned ``warnings``. We try to render an erraneous document: >>> source = ''' ... Headline ... ====== ... ... Thanks for watching! ... ''' >>> html, warnings = ReST2HTML_w_warnings(source) >>> print html

Headline

Thanks for watching!

>>> print warnings :3: (WARNING/2) Title underline too short. Headline ====== As you can see, the warnings are not displayed inline the document but can be retrieved from the returned warnings, which is a string or ``None``. """ warnings = StringIO() fulldoc = publish_string( source_string, writer_name='html4css1', settings_overrides={ 'report_level': 0, 'warning_stream': warnings, }) warnings.seek(0) warning_msgs = warnings.read() if warning_msgs: # Render again, this time with no warnings inline... fulldoc = publish_string( source_string, writer_name='html4css1', settings_overrides={ 'report_level': 10000, 'halt_level': 10000, 'warning_stream': warnings, }) if warning_msgs == '': warning_msgs = None result = getInnerHTMLPart(fulldoc).strip() if not isinstance(result, unicode): result = result.decode('utf-8') return result, warning_msgs def ReST2HTML(source_string): """Render a string containing ReStructuredText to HTML. Any warnings about too short headings, etc. are silently discarded. Use :func:`ReST2HTML_w_warnings` if you want to get any warnings. The returned string will be unicode. A regular document will be rendered like this: >>> source = ''' ... Headline ... ======== ... ... Thanks for watching! ... ''' >>> html = ReST2HTML(source) >>> print html

Headline

Thanks for watching!

A document with markup problems (here: the underline is too short) will look similar: >>> source = ''' ... Headline ... ====== ... ... Thanks for watching! ... ''' >>> html = ReST2HTML(source) >>> print html

Headline

Thanks for watching!

""" html, warnings = ReST2HTML_w_warnings(source_string) return html def attrs_to_fields(cls): """Turn the attributes of a class into FieldProperty instances. With Python >= 2.6 we can even use this function as a class decorator. """ iface = list(implementedBy(cls))[0] for field_name in getFieldNames(iface): setattr(cls, field_name, FieldProperty(iface[field_name])) return cls