patch: implement a new worddiff algorithm
The previous worddiff algorithm has many problems. The major problem is it
does a "similarity check" that selects a subset of matched lines to do
inline diffs. It is a bad idea because:
- The "similarity check" is non-obvious to users. For example, a simple
change from "long long x" to "int64_t x" will fail the similarity check
and won't be diff-ed as expected.
- Selecting "lines" to diff won't work as people expect if there are line
wrapping changes.
- It has a sad time complexity if lines do not match, could be O(N^2)-ish.
There are other problems in implementation details.
- Lines can match across distant hunks (if the next hunk does not have
"-" lines).
- "difflib" is slow.
The solution would be removing the "similarity check", and just diff all
words in a same hunk. So no content will be missed and everything will be
diff-ed as expected. This is similar to what code review tool like
Phabricator does.
This diff implements the word diff algorithm as described above. It also
avoids difflib to be faster.
Note about colors: To be consistent, "changed inserted" parts and "purely
insertion blocks" should have a same color, since they do not exist in the
previous version. Instead of highlighting differences, this patch chooses to
dim common parts. This is also more consistent with Phabricator or GitHub
webpage. That said, the labels are defined in a way that people can still
highlight changed parts and leave purely inserted/deleted hunks use the
"non-highlighted" color.
As one example, running:
hg log -pr df50b87d8f736aff8dc281f816bddcd6f306930c mercurial/commands.py \
--config experimental.worddiff=1 --color=debug --config diff.unified=0
The previous algorithm outputs:
[diff.file_a|--- a/mercurial/commands.py Fri Mar 09 15:53:41 2018 +0100]
[diff.file_b|+++ b/mercurial/commands.py Sat Mar 10 12:33:19 2018 +0530]
[diff.hunk|@@ -2039,1 +2039,4 @@]
[diff.deleted|-][diff.deleted.highlight|@command('^forget',][diff.deleted| ][diff.deleted.highlight|walkopts,][diff.deleted| _('[OPTION]... FILE...'), inferrepo=True)]
[diff.inserted|+@command(]
[diff.inserted|+ '^forget',]
[diff.inserted|+ walkopts + dryrunopts,]
[diff.inserted|+ ][diff.inserted.highlight| ][diff.inserted| _('[OPTION]... FILE...'), inferrepo=True)]
[diff.hunk|@@ -2074,1 +2077,3 @@]
[diff.deleted|- rejected = cmdutil.forget(ui, repo, m, prefix="",][diff.deleted.highlight| explicitonly=False)[0]]
[diff.inserted|+ dryrun = opts.get(r'dry_run')]
[diff.inserted|+ rejected = cmdutil.forget(ui, repo, m, prefix="",]
[diff.inserted|+ explicitonly=False, dryrun=dryrun)[0]]
The new algorithm outputs:
[diff.file_a|--- a/mercurial/commands.py Fri Mar 09 15:53:41 2018 +0100]
[diff.file_b|+++ b/mercurial/commands.py Sat Mar 10 12:33:19 2018 +0530]
[diff.hunk|@@ -2039,1 +2039,4 @@]
[diff.deleted|-][diff.deleted.unchanged|@command(][diff.deleted.unchanged|'^forget',][diff.deleted.unchanged| ][diff.deleted.changed|walkopts][diff.deleted.unchanged|,][diff.deleted.changed| ][diff.deleted.unchanged|_('[OPTION]... FILE...'), inferrepo=True)]
[diff.inserted|+][diff.inserted.unchanged|@command(]
[diff.inserted|+][diff.inserted.changed| ][diff.inserted.unchanged|'^forget',]
[diff.inserted|+][diff.inserted.changed| walkopts][diff.inserted.unchanged| ][diff.inserted.changed|+ dryrunopts][diff.inserted.unchanged|,]
[diff.inserted|+][diff.inserted.changed| ][diff.inserted.unchanged|_('[OPTION]... FILE...'), inferrepo=True)]
[diff.hunk|@@ -2074,1 +2077,3 @@]
[diff.deleted|-][diff.deleted.unchanged| rejected = cmdutil.forget(ui, repo, m, prefix="",][diff.deleted.changed| ][diff.deleted.unchanged|explicitonly=False][diff.deleted.unchanged|)[0]]
[diff.inserted|+][diff.inserted.changed| dryrun = opts.get(r'dry_run')]
[diff.inserted|+][diff.inserted.unchanged| rejected = cmdutil.forget(ui, repo, m, prefix="",]
[diff.inserted|+][diff.inserted.changed| ][diff.inserted.unchanged|explicitonly=False][diff.inserted.changed|, dryrun=dryrun][diff.inserted.unchanged|)[0]]
Practically, when diffing a 8k line change, the time spent on worddiff
reduces from 4 seconds to 0.14 seconds.
Differential Revision: https://phab.mercurial-scm.org/D3212
from __future__ import absolute_import
from .i18n import _
from . import (
registrar,
templatekw,
util,
)
def tolist(val):
"""
a convenience method to return an empty list instead of None
"""
if val is None:
return []
else:
return [val]
class namespaces(object):
"""provides an interface to register and operate on multiple namespaces. See
the namespace class below for details on the namespace object.
"""
_names_version = 0
def __init__(self):
self._names = util.sortdict()
columns = templatekw.getlogcolumns()
# we need current mercurial named objects (bookmarks, tags, and
# branches) to be initialized somewhere, so that place is here
bmknames = lambda repo: repo._bookmarks.keys()
bmknamemap = lambda repo, name: tolist(repo._bookmarks.get(name))
bmknodemap = lambda repo, node: repo.nodebookmarks(node)
n = namespace("bookmarks", templatename="bookmark",
logfmt=columns['bookmark'],
listnames=bmknames,
namemap=bmknamemap, nodemap=bmknodemap,
builtin=True)
self.addnamespace(n)
tagnames = lambda repo: [t for t, n in repo.tagslist()]
tagnamemap = lambda repo, name: tolist(repo._tagscache.tags.get(name))
tagnodemap = lambda repo, node: repo.nodetags(node)
n = namespace("tags", templatename="tag",
logfmt=columns['tag'],
listnames=tagnames,
namemap=tagnamemap, nodemap=tagnodemap,
deprecated={'tip'},
builtin=True)
self.addnamespace(n)
bnames = lambda repo: repo.branchmap().keys()
bnamemap = lambda repo, name: tolist(repo.branchtip(name, True))
bnodemap = lambda repo, node: [repo[node].branch()]
n = namespace("branches", templatename="branch",
logfmt=columns['branch'],
listnames=bnames,
namemap=bnamemap, nodemap=bnodemap,
builtin=True)
self.addnamespace(n)
def __getitem__(self, namespace):
"""returns the namespace object"""
return self._names[namespace]
def __iter__(self):
return self._names.__iter__()
def items(self):
return self._names.iteritems()
iteritems = items
def addnamespace(self, namespace, order=None):
"""register a namespace
namespace: the name to be registered (in plural form)
order: optional argument to specify the order of namespaces
(e.g. 'branches' should be listed before 'bookmarks')
"""
if order is not None:
self._names.insert(order, namespace.name, namespace)
else:
self._names[namespace.name] = namespace
# we only generate a template keyword if one does not already exist
if namespace.name not in templatekw.keywords:
templatekeyword = registrar.templatekeyword(templatekw.keywords)
@templatekeyword(namespace.name, requires={'repo', 'ctx'})
def generatekw(context, mapping):
return templatekw.shownames(context, mapping, namespace.name)
def singlenode(self, repo, name):
"""
Return the 'best' node for the given name. Best means the first node
in the first nonempty list returned by a name-to-nodes mapping function
in the defined precedence order.
Raises a KeyError if there is no such node.
"""
for ns, v in self._names.iteritems():
n = v.namemap(repo, name)
if n:
# return max revision number
if len(n) > 1:
cl = repo.changelog
maxrev = max(cl.rev(node) for node in n)
return cl.node(maxrev)
return n[0]
raise KeyError(_('no such name: %s') % name)
class namespace(object):
"""provides an interface to a namespace
Namespaces are basically generic many-to-many mapping between some
(namespaced) names and nodes. The goal here is to control the pollution of
jamming things into tags or bookmarks (in extension-land) and to simplify
internal bits of mercurial: log output, tab completion, etc.
More precisely, we define a mapping of names to nodes, and a mapping from
nodes to names. Each mapping returns a list.
Furthermore, each name mapping will be passed a name to lookup which might
not be in its domain. In this case, each method should return an empty list
and not raise an error.
This namespace object will define the properties we need:
'name': the namespace (plural form)
'templatename': name to use for templating (usually the singular form
of the plural namespace name)
'listnames': list of all names in the namespace (usually the keys of a
dictionary)
'namemap': function that takes a name and returns a list of nodes
'nodemap': function that takes a node and returns a list of names
'deprecated': set of names to be masked for ordinary use
'builtin': bool indicating if this namespace is supported by core
Mercurial.
"""
def __init__(self, name, templatename=None, logname=None, colorname=None,
logfmt=None, listnames=None, namemap=None, nodemap=None,
deprecated=None, builtin=False):
"""create a namespace
name: the namespace to be registered (in plural form)
templatename: the name to use for templating
logname: the name to use for log output; if not specified templatename
is used
colorname: the name to use for colored log output; if not specified
logname is used
logfmt: the format to use for (i18n-ed) log output; if not specified
it is composed from logname
listnames: function to list all names
namemap: function that inputs a name, output node(s)
nodemap: function that inputs a node, output name(s)
deprecated: set of names to be masked for ordinary use
builtin: whether namespace is implemented by core Mercurial
"""
self.name = name
self.templatename = templatename
self.logname = logname
self.colorname = colorname
self.logfmt = logfmt
self.listnames = listnames
self.namemap = namemap
self.nodemap = nodemap
# if logname is not specified, use the template name as backup
if self.logname is None:
self.logname = self.templatename
# if colorname is not specified, just use the logname as a backup
if self.colorname is None:
self.colorname = self.logname
# if logfmt is not specified, compose it from logname as backup
if self.logfmt is None:
# i18n: column positioning for "hg log"
self.logfmt = ("%s:" % self.logname).ljust(13) + "%s\n"
if deprecated is None:
self.deprecated = set()
else:
self.deprecated = deprecated
self.builtin = builtin
def names(self, repo, node):
"""method that returns a (sorted) list of names in a namespace that
match a given node"""
return sorted(self.nodemap(repo, node))
def nodes(self, repo, name):
"""method that returns a list of nodes in a namespace that
match a given name.
"""
return sorted(self.namemap(repo, name))