view mercurial/similar.py @ 34391:6797f1fbc642

hgweb: add HTML elements to control whitespace settings for annotate

Building on top of the new URL query string arguments to control
whitespace settings for annotate, this commit adds HTML checkboxes
reflecting the values of these arguments to the paper and gitweb
themes.

The actual diff settings are now exported to the templating layer.
The HTML templates add these as data-* attributes so they are
accessible to the DOM.

A new <form> with various <input> elements is added. The <form>
is initially hidden via CSS. A shared JavaScript function (which
runs after the <form> has been rendered but before the annotate
HTML (because annotate HTML could take a while to load and we want
the form to render quickly) takes care of setting the checked state
of each box from the data-* attributes. It also registers an event
handler to modify the URL and refresh the page whenever the checkbox
state is changed.

I'm using the URLSearchParams interface to perform URL manipulation.
https://developer.mozilla.org/en-US/docs/Web/API/URLSearchParams tells
me this may not be supported on older web browsers. Yes, apparently
the web API didn't have a standard API to parse and format query
strings until recently. Hence the check for the presence of this
feature in the JavaScript. If the browser doesn't support the
feature, the <form> will remain hidden and behavior will like it
currently is. We could polyfill this feature or implement our own
query string parsing. But I'm lazy and this could be done as a
follow-up if people miss it.

We could certainly expand this feature to support more diff options
(such as lines of context). That's why the potentially reusable code
is stored in a reusable place. It is also certainly possible to
add diff controls to other pages that display diffs. But since
Mozillians are making noise about controlling which revisions
annotate shows, I figured I'd start there.

.. feature::

   Control whitespace settings for annotation on hgweb

   /annotate URLs on hgweb now accept query string arguments to
   influence how whitespace changes impact results.

   The arguments "ignorews," "ignorewsamount," "ignorewseol," and
   "ignoreblanklines" now have the same meaning as their [annotate]
   config section counterparts. Any provided setting overrides the
   server default.

   HTML checkboxes have been added to the paper and gitweb themes
   to expose current whitespace settings and to easily modify the
   current view.

Differential Revision: https://phab.mercurial-scm.org/D850

# similar.py - mechanisms for finding similar files
#
# Copyright 2005-2007 Matt Mackall <[e-mail]>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from __future__ import absolute_import

from .i18n import _
from . import (
    mdiff,
)

def _findexactmatches(repo, added, removed):
    '''find renamed files that have no changes

    Takes a list of new filectxs and a list of removed filectxs, and yields
    (before, after) tuples of exact matches.
    '''
    numfiles = len(added) + len(removed)

    # Build table of removed files: {hash(fctx.data()): [fctx, ...]}.
    # We use hash() to discard fctx.data() from memory.
    hashes = {}
    for i, fctx in enumerate(removed):
        repo.ui.progress(_('searching for exact renames'), i, total=numfiles,
                         unit=_('files'))
        h = hash(fctx.data())
        if h not in hashes:
            hashes[h] = [fctx]
        else:
            hashes[h].append(fctx)

    # For each added file, see if it corresponds to a removed file.
    for i, fctx in enumerate(added):
        repo.ui.progress(_('searching for exact renames'), i + len(removed),
                total=numfiles, unit=_('files'))
        adata = fctx.data()
        h = hash(adata)
        for rfctx in hashes.get(h, []):
            # compare between actual file contents for exact identity
            if adata == rfctx.data():
                yield (rfctx, fctx)
                break

    # Done
    repo.ui.progress(_('searching for exact renames'), None)

def _ctxdata(fctx):
    # lazily load text
    orig = fctx.data()
    return orig, mdiff.splitnewlines(orig)

def _score(fctx, otherdata):
    orig, lines = otherdata
    text = fctx.data()
    # mdiff.blocks() returns blocks of matching lines
    # count the number of bytes in each
    equal = 0
    matches = mdiff.blocks(text, orig)
    for x1, x2, y1, y2 in matches:
        for line in lines[y1:y2]:
            equal += len(line)

    lengths = len(text) + len(orig)
    return equal * 2.0 / lengths

def score(fctx1, fctx2):
    return _score(fctx1, _ctxdata(fctx2))

def _findsimilarmatches(repo, added, removed, threshold):
    '''find potentially renamed files based on similar file content

    Takes a list of new filectxs and a list of removed filectxs, and yields
    (before, after, score) tuples of partial matches.
    '''
    copies = {}
    for i, r in enumerate(removed):
        repo.ui.progress(_('searching for similar files'), i,
                         total=len(removed), unit=_('files'))

        data = None
        for a in added:
            bestscore = copies.get(a, (None, threshold))[1]
            if data is None:
                data = _ctxdata(r)
            myscore = _score(a, data)
            if myscore > bestscore:
                copies[a] = (r, myscore)
    repo.ui.progress(_('searching'), None)

    for dest, v in copies.iteritems():
        source, bscore = v
        yield source, dest, bscore

def _dropempty(fctxs):
    return [x for x in fctxs if x.size() > 0]

def findrenames(repo, added, removed, threshold):
    '''find renamed files -- yields (before, after, score) tuples'''
    wctx = repo[None]
    pctx = wctx.p1()

    # Zero length files will be frequently unrelated to each other, and
    # tracking the deletion/addition of such a file will probably cause more
    # harm than good. We strip them out here to avoid matching them later on.
    addedfiles = _dropempty(wctx[fp] for fp in sorted(added))
    removedfiles = _dropempty(pctx[fp] for fp in sorted(removed) if fp in pctx)

    # Find exact matches.
    matchedfiles = set()
    for (a, b) in _findexactmatches(repo, addedfiles, removedfiles):
        matchedfiles.add(b)
        yield (a.path(), b.path(), 1.0)

    # If the user requested similar files to be matched, search for them also.
    if threshold < 1.0:
        addedfiles = [x for x in addedfiles if x not in matchedfiles]
        for (a, b, score) in _findsimilarmatches(repo, addedfiles,
                                                 removedfiles, threshold):
            yield (a.path(), b.path(), score)