tests/test-newcgi

findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.

We speed up 'findrenames' for the usecase when a user specifies they
want a similarity of 100% by matching files by their exact SHA1 hash
value. This reduces the number of comparisons required to find exact
matches from O(n^2) to O(n).

While it would be nice if we could just use mercurial's pre-calculated
SHA1 hash for existing files, this hash includes the file's ancestor
information making it unsuitable for our purposes. Instead, we calculate
the hash of old content from scratch.

The following benchmarks were taken on the current head of crew:

addremove 100% similarity:
  rm -rf *; hg up -C; mv tests tests.new
  hg --time addremove -s100 --dry-run

  before:  real 176.350 secs (user 128.890+0.000 sys 47.430+0.000)
  after:   real   2.130 secs (user   1.890+0.000 sys  0.240+0.000)

addremove 75% similarity:
  rm -rf *; hg up -C; mv tests tests.new; \
      for i in tests.new/*; do echo x >> $i; done
  hg --time addremove -s75  --dry-run

  before: real 264.560 secs (user 215.130+0.000 sys 49.410+0.000)
  after:  real 218.710 secs (user 172.790+0.000 sys 45.870+0.000)

#!/bin/sh
# This tests if CGI files from after d0db3462d568 but
# before d74fc8dec2b4 still work.

hg init test

cat >hgweb.cgi <<HGWEB
#!/usr/bin/env python
#
# An example CGI script to use hgweb, edit as necessary

import cgitb
cgitb.enable()

from mercurial import demandimport; demandimport.enable()
from mercurial.hgweb import hgweb
from mercurial.hgweb import wsgicgi
from mercurial.hgweb.request import wsgiapplication

def make_web_app():
	return hgweb("test", "Empty test repository")

wsgicgi.launch(wsgiapplication(make_web_app))
HGWEB
chmod 755 hgweb.cgi

cat >hgweb.config <<HGWEBDIRCONF
[paths]
test = test
HGWEBDIRCONF

cat >hgwebdir.cgi <<HGWEBDIR
#!/usr/bin/env python
#
# An example CGI script to export multiple hgweb repos, edit as necessary

import cgitb
cgitb.enable()

from mercurial import demandimport; demandimport.enable()
from mercurial.hgweb import hgwebdir
from mercurial.hgweb import wsgicgi
from mercurial.hgweb.request import wsgiapplication

def make_web_app():
	return hgwebdir("hgweb.config")

wsgicgi.launch(wsgiapplication(make_web_app))
HGWEBDIR
chmod 755 hgwebdir.cgi

DOCUMENT_ROOT="/var/www/hg"; export DOCUMENT_ROOT
GATEWAY_INTERFACE="CGI/1.1"; export GATEWAY_INTERFACE
HTTP_ACCEPT="text/xml,application/xml,application/xhtml+xml,text/html;q=0.9,text/plain;q=0.8,image/png,*/*;q=0.5"; export HTTP_ACCEPT
HTTP_ACCEPT_CHARSET="ISO-8859-1,utf-8;q=0.7,*;q=0.7"; export HTTP_ACCEPT_CHARSET
HTTP_ACCEPT_ENCODING="gzip,deflate"; export HTTP_ACCEPT_ENCODING
HTTP_ACCEPT_LANGUAGE="en-us,en;q=0.5"; export HTTP_ACCEPT_LANGUAGE
HTTP_CACHE_CONTROL="max-age=0"; export HTTP_CACHE_CONTROL
HTTP_CONNECTION="keep-alive"; export HTTP_CONNECTION
HTTP_HOST="hg.omnifarious.org"; export HTTP_HOST
HTTP_KEEP_ALIVE="300"; export HTTP_KEEP_ALIVE
HTTP_USER_AGENT="Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.8.0.4) Gecko/20060608 Ubuntu/dapper-security Firefox/1.5.0.4"; export HTTP_USER_AGENT
PATH_INFO="/"; export PATH_INFO
PATH_TRANSLATED="/var/www/hg/index.html"; export PATH_TRANSLATED
QUERY_STRING=""; export QUERY_STRING
REMOTE_ADDR="127.0.0.2"; export REMOTE_ADDR
REMOTE_PORT="44703"; export REMOTE_PORT
REQUEST_METHOD="GET"; export REQUEST_METHOD
REQUEST_URI="/test/"; export REQUEST_URI
SCRIPT_FILENAME="/home/hopper/hg_public/test.cgi"; export SCRIPT_FILENAME
SCRIPT_NAME="/test"; export SCRIPT_NAME
SCRIPT_URI="http://hg.omnifarious.org/test/"; export SCRIPT_URI
SCRIPT_URL="/test/"; export SCRIPT_URL
SERVER_ADDR="127.0.0.1"; export SERVER_ADDR
SERVER_ADMIN="eric@localhost"; export SERVER_ADMIN
SERVER_NAME="hg.omnifarious.org"; export SERVER_NAME
SERVER_PORT="80"; export SERVER_PORT
SERVER_PROTOCOL="HTTP/1.1"; export SERVER_PROTOCOL
SERVER_SIGNATURE="<address>Apache/2.0.53 (Fedora) Server at hg.omnifarious.org Port 80</address>\; export SERVER_SIGNATURE
"
SERVER_SOFTWARE="Apache/2.0.53 (Fedora)"; export SERVER_SOFTWARE
python hgweb.cgi >page1 2>&1 ; echo $?
python hgwebdir.cgi >page2 2>&1 ; echo $?
PATH_INFO="/test/"
PATH_TRANSLATED="/var/something/test.cgi"
REQUEST_URI="/test/test/"
SCRIPT_URI="http://hg.omnifarious.org/test/test/"
SCRIPT_URL="/test/test/"
python hgwebdir.cgi >page3 2>&1 ; echo $?
fgrep -i error page1 page2 page3 && exit 1
exit 0