cpython python 区别_维基百科：PyPy 和 CPython 的性能比较测试

从enwiki.xml中筛选类别

为了方便工作，我需要从enwiki-pages-articles.xml中过滤类别，并将它们存储相同的XML格式的类别。因此我选用了SAX解析器，在PyPy和CPython中都适用的包装器解析。对外的原生编译包(同事在PyPy和CPython 中) 。

代码非常简单：

class WikiCategoryHandler(handler.ContentHandler):

"""Class which detecs category pages and stores them separately

"""

ignored = set(('contributor', 'comment', 'meta'))

def __init__(self, f_out):

handler.ContentHandler.__init__(self)

self.f_out = f_out

self.curr_page = None

self.curr_tag = ''

self.curr_elem = Element('root', {})

self.root = self.curr_elem

self.stack = Stack()

self.stack.push(self.curr_elem)

self.skip = 0

def startElement(self, name, attrs):

if self.skip>0 or name in self.ignored:

self.skip += 1

return

self.curr_tag = name

elem = Element(name, attrs)

if name == 'page':

elem.ns = -1

self.curr_page = elem

else: # we don't want to keep old pages in memory

self.curr_elem.append(elem)

self.stack.push(elem)

self.curr_elem = elem

def endElement(self, name):

if self.skip>0:

self.skip -= 1

return

if name == 'page':

self.task()

self.curr_page = None

self.stack.pop()

self.curr_elem = self.stack.top()

self.curr_tag = self.curr_elem.tag

def characters(self, content):

if content.isspace(): return

if self.skip == 0:

self.curr_elem.append(TextElement(content))

if self.curr_tag == 'ns':

self.curr_page.ns = int(content)

def startDocument(self):

self.f_out.write("\n")

def endDocument(self):

self.f_out.write("\n")

print("FINISH PROCESSING WIKIPEDIA")

def task(self):

if self.curr_page.ns == 14:

self.f_out.write(self.curr_page.render())

class Element(object):

def __init__(self, tag, attrs):

self.tag = tag

self.attrs = attrs

self.childrens = []

self.append = self.childrens.append

def __repr__(self):

return "Element {}".format(self.tag)

def render(self, margin=0):

if not self.childrens:

return u"{0}".format(

" "*margin,

self.tag,

"".join([' {}="{}"'.format(k,v) for k,v in {}.iteritems()]))

if isinstance(self.childrens[0], TextElement) and len(self.childrens)==1:

return u"{0}{3}{1}>".format(

" "*margin,

self.tag,

"".join([u' {}="{}"'.format(k,v) for k,v in {}.iteritems()]),

self.childrens[0].render())

return u"{0}\n{3}\n{0}{1}>".format(

" "*margin,

self.tag,

"".join([u' {}="{}"'.format(k,v) for k,v in {}.iteritems()]),

"\n".join((c.render(margin+2) for c in self.childrens)))

class TextElement(object):

def __init__(self, content):

self.content = content

def __repr__(self):

return "TextElement" def render(self, margin=0):

return self.content

Element和TextElement元素包换tag和body信息，同时提供了一个方法来渲染它。

下面是我想要的PyPy和CPython比较结果。

/

time

PyPy

2169.90s

CPython

4494.69s

我很对PyPy的结果很吃惊。