[PATCH 2 of 2 V3] fileset: add a lightweight file filtering language

[Matt Harbison]

# HG changeset patch
# User Matt Harbison <matt_harbison at yahoo.com>
# Date 1515641014 18000
#      Wed Jan 10 22:23:34 2018 -0500
# Node ID b66e906f11f758eb3b3b0f5bc56cf66229f343b7
# Parent  2201fc4fd6d3d9dda72459c6642c16acbe6fc0a4
fileset: add a lightweight file filtering language

This patch was inspired by one that Jun Wu authored for the fb-experimental
repo, to avoid using matcher for efficiency[1].  We want a way to specify what
files will be converted to LFS at commit time.  And per discussion, we also want
to specify what files to skip, text diff, or merge in another config option.
The current `lfs.threshold` config option could not satisfy complex needs.  I'm
putting it in a core package because Augie floated the idea of also using it for
narrow and sparse.

Yuya suggested farming out to fileset.parse(), which added support for more
symbols.  The only fileset element not supported here is 'negate'.  (List isn't
supported by filesets either.)  I also changed the 'always' token to the 'all()'
predicate for consistency, and introduced 'none()' to improve readability in a
future tracked file based config.  The extension operator was changed from '.'
to '**', to match how recursive path globs are specified.  Finally, I changed
the path matcher from '/' to 'path:' at Yuya's suggestion, for consistency with
matcher.  Unfortunately, ':' is currently reserved in filesets, so this has to
be quoted to be processed as a string instead of a symbol[2].  We should
probably revisit that, because it's seriously ugly.  But it's only used by an
experimental extension, and I think using a file based config for LFS may drive
some more tweaks, so I'm settling for this for now.

I reserved all of the glob characters in fileset except '.' and '_' for the
extension test because those are likely valid extension characters.

Sample filter settings:

  all()                        # everything
  size(">20MB")                # larger than 20MB
  !**.txt                      # except for .txt files
  **.zip | **.tar.gz | **.7z   # some types of compressed files
  "path:bin"                   # files under "bin" in the project root

[1] https://www.mercurial-scm.org/pipermail/mercurial-devel/2017-December/109387.html
[2] https://www.mercurial-scm.org/pipermail/mercurial-devel/2018-January/109729.html

diff --git a/mercurial/minifileset.py b/mercurial/minifileset.py
new file mode 100644
--- /dev/null
+++ b/mercurial/minifileset.py
@@ -0,0 +1,94 @@
+# minifileset.py - a simple language to select files
+#
+# Copyright 2017 Facebook, Inc.
+#
+# 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 (
+    error,
+    fileset,
+    util,
+)
+
+def _compile(tree):
+    if not tree:
+        raise error.ParseError(_("missing argument"))
+    op = tree[0]
+    if op == 'symbol':
+        name = fileset.getstring(tree, _('invalid file pattern'))
+        if name.startswith('**'): # file extension test, ex. "**.tar.gz"
+            ext = name[2:]
+            for c in ext:
+                if c in '*{}[]?/\\':
+                    raise error.ParseError(_('reserved character: %s') % c)
+            return lambda n, s: n.endswith(ext)
+        else:
+            raise error.ParseError(_('invalid symbol: %s') % name)
+    elif op == 'or':
+        func1 = _compile(tree[1])
+        func2 = _compile(tree[2])
+        return lambda n, s: func1(n, s) or func2(n, s)
+    elif op == 'and':
+        func1 = _compile(tree[1])
+        func2 = _compile(tree[2])
+        return lambda n, s: func1(n, s) and func2(n, s)
+    elif op == 'not':
+        return lambda n, s: not _compile(tree[1])(n, s)
+    elif op == 'group':
+        return _compile(tree[1])
+    elif op == 'func':
+        symbols = {
+            'all': lambda n, s: True,
+            'none': lambda n, s: False,
+            'size': lambda n, s: fileset.sizematcher(tree[2])(s),
+        }
+
+        x = tree[1]
+        name = x[1]
+        if x[0] == 'symbol' and name in symbols:
+            return symbols[name]
+
+        raise error.UnknownIdentifier(name, symbols.keys())
+    elif op == 'minus':     # equivalent to 'x and not y'
+        func1 = _compile(tree[1])
+        func2 = _compile(tree[2])
+        return lambda n, s: func1(n, s) and not func2(n, s)
+    elif op == 'negate':
+        raise error.ParseError(_("can't use negate operator in this context"))
+    elif op == 'string':
+        # TODO: teach fileset about 'path:', so that this can be a symbol and
+        # not require quoting.
+        name = fileset.getstring(tree, _('invalid path literal'))
+        if name.startswith('path:'): # directory or full path test
+            p = name[5:] # prefix
+            pl = len(p)
+            f = lambda n, s: n.startswith(p) and (len(n) == pl or n[pl] == '/')
+            return f
+        raise error.ParseError(_("invalid string"),
+                               hint=_('paths must be prefixed with "path:"'))
+    elif op == 'list':
+        raise error.ParseError(_("can't use a list in this context"),
+                               hint=_('see hg help "filesets.x or y"'))
+    else:
+        raise error.ProgrammingError('illegal tree: %r' % (tree,))
+
+def compile(text):
+    """generate a function (path, size) -> bool from filter specification.
+
+    "text" could contain the operators defined by the fileset language for
+    common logic operations, and parenthesis for grouping.  The supported path
+    tests are '**.extname' for file extension test, and '"path:dir/subdir"'
+    for prefix test.  The ``size()`` predicate is borrowed from filesets to test
+    file size.  The predicates ``all()`` and ``none()`` are also supported.
+
+    '(**.php & size(">10MB")) | **.zip | ("path:bin" & !"path:bin/README")' for
+    example, will catch all php files whose size is greater than 10 MB, all
+    files whose name ends with ".zip", and all files under "bin" in the repo
+    root except for "bin/README".
+    """
+    tree = fileset.parse(text)
+    return _compile(tree)
diff --git a/tests/test-minifileset.py b/tests/test-minifileset.py
new file mode 100644
--- /dev/null
+++ b/tests/test-minifileset.py
@@ -0,0 +1,38 @@
+from __future__ import absolute_import
+from __future__ import print_function
+
+import os
+import sys
+
+# make it runnable directly without run-tests.py
+sys.path[0:0] = [os.path.join(os.path.dirname(__file__), '..')]
+
+from mercurial import minifileset
+
+def check(text, truecases, falsecases):
+    f = minifileset.compile(text)
+    for args in truecases:
+        if not f(*args):
+            print('unexpected: %r should include %r' % (text, args))
+    for args in falsecases:
+        if f(*args):
+            print('unexpected: %r should exclude %r' % (text, args))
+
+check('all()', [('a.php', 123), ('b.txt', 0)], [])
+check('none()', [], [('a.php', 123), ('b.txt', 0)])
+check('!!!!((!(!!all())))', [], [('a.php', 123), ('b.txt', 0)])
+
+check('"path:a" & (**.b | **.c)', [('a/b.b', 0), ('a/c.c', 0)], [('b/c.c', 0)])
+check('("path:a" & **.b) | **.c',
+      [('a/b.b', 0), ('a/c.c', 0), ('b/c.c', 0)], [])
+
+check('**.bin - size("<20B")', [('b.bin', 21)], [('a.bin', 11), ('b.txt', 21)])
+
+check('!!**.bin or size(">20B") + "path:bin" or !size(">10")',
+      [('a.bin', 11), ('b.txt', 21), ('bin/abc', 11)],
+      [('a.notbin', 11), ('b.txt', 11), ('bin2/abc', 11)])
+
+check('(**.php and size(">10KB")) | **.zip | ("path:bin" & !"path:bin/README") '
+      ' | size(">1M")',
+      [('a.php', 15000), ('a.zip', 0), ('bin/a', 0), ('bin/README', 1e7)],
+      [('a.php', 5000), ('b.zip2', 0), ('t/bin/a', 0), ('bin/README', 1)])