def testLoadWikipediaTitlesIgnoresIgnorablePages(self):
"""
L{loadWikipediaTitles} ignores category, file, portal, etc. pages.
"""
path = sibpath(__file__, 'ignored.xml')
loadWikipediaTitles(path, self.pageHandler)
self.assertEqual([], self.pageHandler.pages)
def testLoadWikipediaTitlesClosesPageHandler(self):
"""
The C{close} method on the page handler will be called when
L{loadWikipediaTitles} finishes parsing the XML document.
"""
path = sibpath(__file__, 'basic.xml')
loadWikipediaTitles(path, self.pageHandler)
self.assertTrue(self.pageHandler.closed)
def testLoadWikipediaTitles(self):
"""
L{loadWikipediaTitles} yields a L{WikipediaPage} instance for each
C{page} element in the specified XML file.
"""
path = sibpath(__file__, 'basic.xml')
loadWikipediaTitles(path, self.pageHandler)
[page] = self.pageHandler.pages
self.assertEqual('Anaconda', page.title)
def main(inputFilename, outputPath):
"""Load Wikipedia page titles from an XML file and write out JSON files.
@param inputFilename: The path to the Wikipedia XML file to load data from.
@param outputPath: The path to write JSON files to.
"""
basicConfig(format='%(asctime)s %(levelname)8s %(message)s', level=INFO)
pageHandler = WikipediaPageHandler(outputPath)
loadWikipediaTitles(inputFilename, pageHandler)
def testLoadWikipediaTitlesIgnoresDisambiguationPages(self):
"""L{loadWikipediaTitles} ignores disambiguation pages."""
path = sibpath(__file__, 'disambiguation.xml')
loadWikipediaTitles(path, self.pageHandler)
self.assertEqual([], self.pageHandler.pages)
def testLoadWikipediaTitlesIgnoresRedirectPages(self):
"""L{loadWikipediaTitles} ignores pages that are redirects."""
path = sibpath(__file__, 'redirect.xml')
loadWikipediaTitles(path, self.pageHandler)
self.assertEqual([], self.pageHandler.pages)