view tests/test-duplicateoptions.py @ 50400:95acba2c29f6

encoding: avoid quadratic time complexity when json-encoding non-UTF8 strings

Apparently the code uses "+=" with a bytes object, which is linear-time, so the
whole encoding is quadratic-time. This patch makes us use a bytearray object,
instead, which has a(n amortized-)constant-time append operation.

The encoding is still not particularly fast, but at least a 10MB file
takes tens of seconds, not many hours to encode.

import os
from mercurial import (
    commands,
    extensions,
    ui as uimod,
)

ignore = {b'highlight', b'win32text', b'factotum', b'beautifygraph'}

try:
    import sqlite3

    del sqlite3  # unused, just checking that import works
except ImportError:
    ignore.add(b'sqlitestore')

if os.name != 'nt':
    ignore.add(b'win32mbcs')

disabled = [ext for ext in extensions.disabled().keys() if ext not in ignore]

hgrc = open(os.environ["HGRCPATH"], 'wb')
hgrc.write(b'[extensions]\n')

for ext in disabled:
    hgrc.write(ext + b'=\n')

hgrc.close()

u = uimod.ui.load()
extensions.loadall(u)
extensions.populateui(u)

globalshort = set()
globallong = set()
for option in commands.globalopts:
    option[0] and globalshort.add(option[0])
    option[1] and globallong.add(option[1])

for cmd, entry in commands.table.items():
    seenshort = globalshort.copy()
    seenlong = globallong.copy()
    for option in entry[1]:
        if (option[0] and option[0] in seenshort) or (
            option[1] and option[1] in seenlong
        ):
            print("command '" + cmd + "' has duplicate option " + str(option))
        seenshort.add(option[0])
        seenlong.add(option[1])