| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120 |
- # -*- coding: utf-8
- import re
- from HTMLParser import HTMLParser
- from difflib import unified_diff
- class FortuneHTMLParser(HTMLParser):
- body = []
- valid = '<!doctype html><html><head><title>Fortunes</title></head><body><table><tr><th>id</th><th>message</th></tr><tr><td>11</td><td><script>alert("This should not be displayed in a browser alert box.");</script></td></tr><tr><td>4</td><td>A bad random number generator: 1, 1, 1, 1, 1, 4.33e+67, 1, 1, 1</td></tr><tr><td>5</td><td>A computer program does what you tell it to do, not what you want it to do.</td></tr><tr><td>2</td><td>A computer scientist is someone who fixes things that aren't broken.</td></tr><tr><td>8</td><td>A list is only as strong as its weakest link. — Donald Knuth</td></tr><tr><td>0</td><td>Additional fortune added at request time.</td></tr><tr><td>3</td><td>After enough decimal places, nobody gives a damn.</td></tr><tr><td>7</td><td>Any program that runs right is obsolete.</td></tr><tr><td>10</td><td>Computers make very fast, very accurate mistakes.</td></tr><tr><td>6</td><td>Emacs is a nice operating system, but I prefer UNIX. — Tom Christaensen</td></tr><tr><td>9</td><td>Feature: A bug with seniority.</td></tr><tr><td>1</td><td>fortune: No such file or directory</td></tr><tr><td>12</td><td>フレームワークのベンチマーク</td></tr></table></body></html>'
- # Is called when a doctype or other such tag is read in.
- # For our purposes, we assume this is only going to be
- # "DOCTYPE html", so we will surround it with "<!" and ">".
- def handle_decl(self, decl):
- # The spec says that for HTML this is case insensitive,
- # and since we did not specify xml compliance (where
- # incorrect casing would throw a syntax error), we must
- # allow all casings. We will lower for our normalization.
- self.body.append("<!{d}>".format(d=decl.lower()))
- # This is called when an HTML character is parsed (i.e.
- # "). There are a number of issues to be resolved
- # here. For instance, some tests choose to leave the
- # "+" character as-is, which should be fine as far as
- # character escaping goes, but others choose to use the
- # character reference of "+", which is also fine.
- # Therefore, this method looks for all possible character
- # references and normalizes them so that we can
- # validate the input against a single valid spec string.
- # Another example problem: """ is valid, but so is
- # """
- def handle_charref(self, name):
- val = name.lower()
- # """ is a valid escaping, but we are normalizing
- # it so that our final parse can just be checked for
- # equality.
- if val == "34" or val == "034" or val == "x22":
- # Append our normalized entity reference to our body.
- self.body.append(""")
- # "'" is a valid escaping of "-", but it is not
- # required, so we normalize for equality checking.
- if val == "39" or val == "039" or val == "x27":
- self.body.append("'")
- # Again, "+" is a valid escaping of the "+", but
- # it is not required, so we need to normalize for out
- # final parse and equality check.
- if val == "43" or val == "043" or val == "x2b":
- self.body.append("+")
- # Again, ">" is a valid escaping of ">", but we
- # need to normalize to ">" for equality checking.
- if val == "62" or val == "062" or val == "x3e":
- self.body.append(">")
- # Again, "<" is a valid escaping of "<", but we
- # need to normalize to "<" for equality checking.
- if val == "60" or val == "060" or val == "x3c":
- self.body.append("<")
- # Not sure why some are escaping '/'
- if val == "47" or val == "047" or val == "x2f":
- self.body.append("/")
- def handle_entityref(self, name):
- # Again, "—" is a valid escaping of "—", but we
- # need to normalize to "—" for equality checking.
- if name == "mdash":
- self.body.append("—")
- else:
- self.body.append("&{n};".format(n=name))
- # This is called every time a tag is opened. We append
- # each one wrapped in "<" and ">".
- def handle_starttag(self, tag, attrs):
- self.body.append("<{t}>".format(t=tag))
- # This is called whenever data is presented inside of a
- # start and end tag. Generally, this will only ever be
- # the contents inside of "<td>" and "</td>", but there
- # are also the "<title>" and "</title>" tags.
- def handle_data (self, data):
- if data.strip() != '':
- # After a LOT of debate, these are now considered
- # valid in data. The reason for this approach is
- # because a few tests use tools which determine
- # at compile time whether or not a string needs
- # a given type of html escaping, and our fortune
- # test has apostrophes and quotes in html data
- # rather than as an html attribute etc.
- # example:
- # <td>A computer scientist is someone who fixes things that aren't broken.</td>
- # Semanticly, that apostrophe does not NEED to
- # be escaped. The same is currently true for our
- # quotes.
- # In fact, in data (read: between two html tags)
- # even the '>' need not be replaced as long as
- # the '<' are all escaped.
- # We replace them with their escapings here in
- # order to have a noramlized string for equality
- # comparison at the end.
- data = data.replace('\'', ''')
- data = data.replace('"', '"')
- data = data.replace('>', '>')
- self.body.append("{d}".format(d=data))
- # This is called every time a tag is closed. We append
- # each one wrapped in "</" and ">".
- def handle_endtag(self, tag):
- self.body.append("</{t}>".format(t=tag))
- # Returns whether the HTML input parsed by this parser
- # is valid against our known "fortune" spec.
- # The parsed data in 'body' is joined on empty strings
- # and checked for equality against our spec.
- def isValidFortune(self, out):
- body = ''.join(self.body)
- diff = self.valid == body
- if not diff:
- out.write("Fortune invalid. Diff following:\n")
- diff_str = ''.join(unified_diff(self.valid.split(' '), body.split(' '), fromfile='Valid', tofile='Response', n=5))
- out.write(diff_str)
- return diff
|
