contrib/bdiff-torture.py

hgweb: parse WSGI request into a data structure

Currently, our WSGI applications (hgweb_mod and hgwebdir_mod) process
the raw WSGI request instance themselves. This means they have to
talk in terms of system strings. And they need to know details
about what's in the WSGI request. And in the case of hgweb_mod, it
is doing some very funky things with URL parsing to impact
dispatching. The code is difficult to read and maintain.

This commit introduces parsing of the WSGI request into a higher-level
and easier-to-reason-about data structure.

To prove it works, we hook it up to hgweb_mod and use it for populating
the relative URL on the request instance.

We hold off on using it in more places because the logic in hgweb_mod
is crazy and I don't want to involve those changes with review of
the parsing code.

The URL construction code has variations that use the HTTP: Host header
(the canonical WSGI way of reconstructing the URL) and with the use
of SERVER_NAME. We need to differentiate because hgweb is currently
using SERVER_NAME for URL construction.

Differential Revision: https://phab.mercurial-scm.org/D2734

# Randomized torture test generation for bdiff

from __future__ import absolute_import, print_function
import random
import sys

from mercurial import (
    mdiff,
)

def reducetest(a, b):
    tries = 0
    reductions = 0
    print("reducing...")
    while tries < 1000:
        a2 = "\n".join(l for l in a.splitlines()
                       if random.randint(0, 100) > 0) + "\n"
        b2 = "\n".join(l for l in b.splitlines()
                       if random.randint(0, 100) > 0) + "\n"
        if a2 == a and b2 == b:
            continue
        if a2 == b2:
            continue
        tries += 1

        try:
            test1(a, b)
        except Exception as inst:
            reductions += 1
            tries = 0
            a = a2
            b = b2

    print("reduced:", reductions, len(a) + len(b),
          repr(a), repr(b))
    try:
        test1(a, b)
    except Exception as inst:
        print("failed:", inst)

    sys.exit(0)

def test1(a, b):
    d = mdiff.textdiff(a, b)
    if not d:
        raise ValueError("empty")
    c = mdiff.patches(a, [d])
    if c != b:
        raise ValueError("bad")

def testwrap(a, b):
    try:
        test1(a, b)
        return
    except Exception as inst:
        pass
    print("exception:", inst)
    reducetest(a, b)

def test(a, b):
    testwrap(a, b)
    testwrap(b, a)

def rndtest(size, noise):
    a = []
    src = "                aaaaaaaabbbbccd"
    for x in xrange(size):
        a.append(src[random.randint(0, len(src) - 1)])

    while True:
        b = [c for c in a if random.randint(0, 99) > noise]
        b2 = []
        for c in b:
            b2.append(c)
            while random.randint(0, 99) < noise:
                b2.append(src[random.randint(0, len(src) - 1)])
        if b2 != a:
            break

    a = "\n".join(a) + "\n"
    b = "\n".join(b2) + "\n"

    test(a, b)

maxvol = 10000
startsize = 2
while True:
    size = startsize
    count = 0
    while size < maxvol:
        print(size)
        volume = 0
        while volume < maxvol:
            rndtest(size, 2)
            volume += size
            count += 2
        size *= 2
    maxvol *= 4
    startsize *= 4