Patchwork [3,of,7,V2] parser: move alias declaration parser to common rule-set class

login
register
mail settings
Submitter Yuya Nishihara
Date April 2, 2016, 8:30 a.m.
Message ID <1ec19dfcfbcfed50e8c3.1459585818@mimosa>
Download mbox | patch
Permalink /patch/14250/
State Superseded
Headers show

Comments

Yuya Nishihara - April 2, 2016, 8:30 a.m.
# HG changeset patch
# User Yuya Nishihara <yuya@tcha.org>
# Date 1456736043 -32400
#      Mon Feb 29 17:54:03 2016 +0900
# Node ID 1ec19dfcfbcfed50e8c3a5beacf7e8ea2171390c
# Parent  cc42f3a9895fe3d2922e07d44483051a4b7b90da
parser: move alias declaration parser to common rule-set class

The original _parsealiasdecl() function is split into common _builddecl()
and revset-specific _parsealiasdecl(). And the original _parsealiasdecl()
call is temporarily replaced by rules._builddecl(), which should be eliminated
later.

The doctests are mostly ported by using the dummy parse(), but the test for
'foo bar' is kept in _parsealiasdecl() as it checks if "pos != len(decl)" is
working. Also, 'foo($1)' test is added to make sure the alias tokenizer can
handle '$1' symbol, which is the only reason why we need _parsealiasdecl().

Patch

diff --git a/mercurial/parser.py b/mercurial/parser.py
--- a/mercurial/parser.py
+++ b/mercurial/parser.py
@@ -254,3 +254,104 @@  class aliasrules(object):
         self._getlist = getlist
         self._symbolnode = symbolnode
         self._funcnode = funcnode
+
+    def _builddecl(self, decl):
+        """Parse an alias declaration into ``(name, tree, args, errorstr)``
+
+        This function analyzes the parsed tree. The parsing rule is provided
+        by ``_parsedecl()``.
+
+        - ``name``: of declared alias (may be ``decl`` itself at error)
+        - ``tree``: parse result (or ``None`` at error)
+        - ``args``: list of argument names (or None for symbol declaration)
+        - ``errorstr``: detail about detected error (or None)
+
+        >>> sym = lambda x: ('symbol', x)
+        >>> symlist = lambda *xs: ('list',) + tuple(sym(x) for x in xs)
+        >>> func = lambda n, a: ('func', sym(n), a)
+        >>> parsemap = {
+        ...     'foo': sym('foo'),
+        ...     '$foo': sym('$foo'),
+        ...     'foo::bar': ('dagrange', sym('foo'), sym('bar')),
+        ...     'foo()': func('foo', None),
+        ...     '$foo()': func('$foo', None),
+        ...     'foo($1, $2)': func('foo', symlist('$1', '$2')),
+        ...     'foo(bar_bar, baz.baz)':
+        ...         func('foo', symlist('bar_bar', 'baz.baz')),
+        ...     'foo(bar($1, $2))':
+        ...         func('foo', func('bar', symlist('$1', '$2'))),
+        ...     'foo($1, $2, nested($1, $2))':
+        ...         func('foo', (symlist('$1', '$2') +
+        ...                      (func('nested', symlist('$1', '$2')),))),
+        ...     'foo("bar")': func('foo', ('string', 'bar')),
+        ...     'foo($1, $2': error.ParseError('unexpected token: end', 10),
+        ...     'foo("bar': error.ParseError('unterminated string', 5),
+        ...     'foo($1, $2, $1)': func('foo', symlist('$1', '$2', '$1')),
+        ... }
+        >>> def parse(expr):
+        ...     x = parsemap[expr]
+        ...     if isinstance(x, Exception):
+        ...         raise x
+        ...     return x
+        >>> def getlist(tree):
+        ...     if not tree:
+        ...         return []
+        ...     if tree[0] == 'list':
+        ...         return list(tree[1:])
+        ...     return [tree]
+        >>> builddecl = aliasrules('', parse, parse, getlist)._builddecl
+        >>> builddecl('foo')
+        ('foo', ('symbol', 'foo'), None, None)
+        >>> builddecl('$foo')
+        ('$foo', None, None, "'$' not for alias arguments")
+        >>> builddecl('foo::bar')
+        ('foo::bar', None, None, 'invalid format')
+        >>> builddecl('foo()')
+        ('foo', ('func', ('symbol', 'foo')), [], None)
+        >>> builddecl('$foo()')
+        ('$foo()', None, None, "'$' not for alias arguments")
+        >>> builddecl('foo($1, $2)')
+        ('foo', ('func', ('symbol', 'foo')), ['$1', '$2'], None)
+        >>> builddecl('foo(bar_bar, baz.baz)')
+        ('foo', ('func', ('symbol', 'foo')), ['bar_bar', 'baz.baz'], None)
+        >>> builddecl('foo($1, $2, nested($1, $2))')
+        ('foo($1, $2, nested($1, $2))', None, None, 'invalid argument list')
+        >>> builddecl('foo(bar($1, $2))')
+        ('foo(bar($1, $2))', None, None, 'invalid argument list')
+        >>> builddecl('foo("bar")')
+        ('foo("bar")', None, None, 'invalid argument list')
+        >>> builddecl('foo($1, $2')
+        ('foo($1, $2', None, None, 'at 10: unexpected token: end')
+        >>> builddecl('foo("bar')
+        ('foo("bar', None, None, 'at 5: unterminated string')
+        >>> builddecl('foo($1, $2, $1)')
+        ('foo', None, None, 'argument names collide with each other')
+        """
+        try:
+            tree = self._parsedecl(decl)
+        except error.ParseError as inst:
+            return (decl, None, None, parseerrordetail(inst))
+
+        if tree[0] == self._symbolnode:
+            # "name = ...." style
+            name = tree[1]
+            if name.startswith('$'):
+                return (decl, None, None, _("'$' not for alias arguments"))
+            return (name, tree, None, None)
+
+        if tree[0] == self._funcnode and tree[1][0] == self._symbolnode:
+            # "name(arg, ....) = ...." style
+            name = tree[1][1]
+            if name.startswith('$'):
+                return (decl, None, None, _("'$' not for alias arguments"))
+            args = []
+            for arg in self._getlist(tree[2]):
+                if arg[0] != self._symbolnode:
+                    return (decl, None, None, _("invalid argument list"))
+                args.append(arg[1])
+            if len(args) != len(set(args)):
+                return (name, None, None,
+                        _("argument names collide with each other"))
+            return (name, tree[:2], args, None)
+
+        return (decl, None, None, _("invalid format"))
diff --git a/mercurial/revset.py b/mercurial/revset.py
--- a/mercurial/revset.py
+++ b/mercurial/revset.py
@@ -2241,75 +2241,18 @@  def _tokenizealias(program):
 def _parsealiasdecl(decl):
     """Parse alias declaration ``decl``
 
-    This returns ``(name, tree, args, errorstr)`` tuple:
-
-    - ``name``: of declared alias (may be ``decl`` itself at error)
-    - ``tree``: parse result (or ``None`` at error)
-    - ``args``: list of alias argument names (or None for symbol declaration)
-    - ``errorstr``: detail about detected error (or None)
-
-    >>> _parsealiasdecl('foo')
-    ('foo', ('symbol', 'foo'), None, None)
-    >>> _parsealiasdecl('$foo')
-    ('$foo', None, None, "'$' not for alias arguments")
-    >>> _parsealiasdecl('foo::bar')
-    ('foo::bar', None, None, 'invalid format')
+    >>> _parsealiasdecl('foo($1)')
+    ('func', ('symbol', 'foo'), ('symbol', '$1'))
     >>> _parsealiasdecl('foo bar')
-    ('foo bar', None, None, 'at 4: invalid token')
-    >>> _parsealiasdecl('foo()')
-    ('foo', ('func', ('symbol', 'foo')), [], None)
-    >>> _parsealiasdecl('$foo()')
-    ('$foo()', None, None, "'$' not for alias arguments")
-    >>> _parsealiasdecl('foo($1, $2)')
-    ('foo', ('func', ('symbol', 'foo')), ['$1', '$2'], None)
-    >>> _parsealiasdecl('foo(bar_bar, baz.baz)')
-    ('foo', ('func', ('symbol', 'foo')), ['bar_bar', 'baz.baz'], None)
-    >>> _parsealiasdecl('foo($1, $2, nested($1, $2))')
-    ('foo($1, $2, nested($1, $2))', None, None, 'invalid argument list')
-    >>> _parsealiasdecl('foo(bar($1, $2))')
-    ('foo(bar($1, $2))', None, None, 'invalid argument list')
-    >>> _parsealiasdecl('foo("string")')
-    ('foo("string")', None, None, 'invalid argument list')
-    >>> _parsealiasdecl('foo($1, $2')
-    ('foo($1, $2', None, None, 'at 10: unexpected token: end')
-    >>> _parsealiasdecl('foo("string')
-    ('foo("string', None, None, 'at 5: unterminated string')
-    >>> _parsealiasdecl('foo($1, $2, $1)')
-    ('foo', None, None, 'argument names collide with each other')
+    Traceback (most recent call last):
+      ...
+    ParseError: ('invalid token', 4)
     """
     p = parser.parser(elements)
-    try:
-        tree, pos = p.parse(_tokenizealias(decl))
-        if (pos != len(decl)):
-            raise error.ParseError(_('invalid token'), pos)
-        tree = parser.simplifyinfixops(tree, ('list',))
-    except error.ParseError as inst:
-        return (decl, None, None, parser.parseerrordetail(inst))
-
-    if True:  # XXX to be removed
-        if tree[0] == 'symbol':
-            # "name = ...." style
-            name = tree[1]
-            if name.startswith('$'):
-                return (decl, None, None, _("'$' not for alias arguments"))
-            return (name, tree, None, None)
-
-        if tree[0] == 'func' and tree[1][0] == 'symbol':
-            # "name(arg, ....) = ...." style
-            name = tree[1][1]
-            if name.startswith('$'):
-                return (decl, None, None, _("'$' not for alias arguments"))
-            args = []
-            for arg in getlist(tree[2]):
-                if arg[0] != 'symbol':
-                    return (decl, None, None, _("invalid argument list"))
-                args.append(arg[1])
-            if len(args) != len(set(args)):
-                return (name, None, None,
-                        _("argument names collide with each other"))
-            return (name, tree[:2], args, None)
-
-        return (decl, None, None, _("invalid format"))
+    tree, pos = p.parse(_tokenizealias(decl))
+    if pos != len(decl):
+        raise error.ParseError(_('invalid token'), pos)
+    return parser.simplifyinfixops(tree, ('list',))
 
 def _relabelaliasargs(tree, args):
     if not isinstance(tree, tuple):
@@ -2381,7 +2324,9 @@  class revsetalias(object):
         h = heads(default)
         b($1) = ancestors($1) - ancestors(default)
         '''
-        self.name, self.tree, self.args, self.error = _parsealiasdecl(name)
+        rules = parser.aliasrules(_('revset alias'),
+                                  _parsealiasdecl, None, getlist)
+        self.name, self.tree, self.args, self.error = rules._builddecl(name)
         if self.error:
             self.error = _('failed to parse the declaration of revset alias'
                            ' "%s": %s') % (self.name, self.error)