diff mercurial/fileset.py @ 14511:30506b894359

filesets: introduce basic fileset expression parser

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/mercurial/fileset.py	Wed Jun 01 19:12:18 2011 -0500
@@ -0,0 +1,79 @@
+# fileset.py - file set queries for mercurial
+#
+# Copyright 2010 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.
+
+import parser, error
+from i18n import _
+
+elements = {
+    "(": (20, ("group", 1, ")"), ("func", 1, ")")),
+    "-": (5, ("negate", 19), ("minus", 5)),
+    "not": (10, ("not", 10)),
+    "!": (10, ("not", 10)),
+    "and": (5, None, ("and", 5)),
+    "&": (5, None, ("and", 5)),
+    "or": (4, None, ("or", 4)),
+    "|": (4, None, ("or", 4)),
+    "+": (4, None, ("or", 4)),
+    ",": (2, None, ("list", 2)),
+    ")": (0, None, None),
+    "symbol": (0, ("symbol",), None),
+    "string": (0, ("string",), None),
+    "end": (0, None, None),
+}
+
+keywords = set(['and', 'or', 'not'])
+
+def tokenize(program):
+    pos, l = 0, len(program)
+    while pos < l:
+        c = program[pos]
+        if c.isspace(): # skip inter-token whitespace
+            pass
+        elif c in "(),-|&+!": # handle simple operators
+            yield (c, None, pos)
+        elif (c in '"\'' or c == 'r' and
+              program[pos:pos + 2] in ("r'", 'r"')): # handle quoted strings
+            if c == 'r':
+                pos += 1
+                c = program[pos]
+                decode = lambda x: x
+            else:
+                decode = lambda x: x.decode('string-escape')
+            pos += 1
+            s = pos
+            while pos < l: # find closing quote
+                d = program[pos]
+                if d == '\\': # skip over escaped characters
+                    pos += 2
+                    continue
+                if d == c:
+                    yield ('string', decode(program[s:pos]), s)
+                    break
+                pos += 1
+            else:
+                raise error.ParseError(_("unterminated string"), s)
+        elif c.isalnum() or c in '.*{}[]?' or ord(c) > 127: # gather up a symbol/keyword
+            s = pos
+            pos += 1
+            while pos < l: # find end of symbol
+                d = program[pos]
+                if not (d.isalnum() or d in ".*{}[]?," or ord(d) > 127):
+                    break
+                pos += 1
+            sym = program[s:pos]
+            if sym in keywords: # operator keywords
+                yield (sym, None, s)
+            else:
+                yield ('symbol', sym, s)
+            pos -= 1
+        else:
+            raise error.ParseError(_("syntax error"), pos)
+        pos += 1
+    yield ('end', None, pos)
+
+parse = parser.parser(tokenize, elements).parse
+