# revset.py - revision set queries for mercurial

#

# Copyright 2010 Matt Mackall <mpm@selenic.com>

#

# This software may be used and distributed according to the terms of the

# GNU General Public License version 2 or any later version.

import re

import parser, util, error, discovery, hbisect

import bookmarks as bookmarksmod

import match as matchmod

from i18n import _

elements = {

    "(": (20, ("group", 1, ")"), ("func", 1, ")")),

    "~": (18, None, ("ancestor", 18)),

    "^": (18, None, ("parent", 18), ("parentpost", 18)),

    "-": (5, ("negate", 19), ("minus", 5)),

    "::": (17, ("dagrangepre", 17), ("dagrange", 17),

           ("dagrangepost", 17)),

    "..": (17, ("dagrangepre", 17), ("dagrange", 17),

           ("dagrangepost", 17)),

    ":": (15, ("rangepre", 15), ("range", 15), ("rangepost", 15)),

    "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 == ':' and program[pos:pos + 2] == '::': # look ahead carefully

            yield ('::', None, pos)

            pos += 1 # skip ahead

        elif c == '.' and program[pos:pos + 2] == '..': # look ahead carefully

            yield ('..', None, pos)

            pos += 1 # skip ahead

        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

                if d == '.' and program[pos - 1] == '.': # special case for ..

                    pos -= 1

                    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)

# helpers

def getstring(x, err):

    if x and (x[0] == 'string' or x[0] == 'symbol'):

        return x[1]

    raise error.ParseError(err)

def getlist(x):

    if not x:

        return []

    if x[0] == 'list':

        return getlist(x[1]) + [x[2]]

    return [x]

def getargs(x, min, max, err):

    l = getlist(x)

    if len(l) < min or len(l) > max:

        raise error.ParseError(err)

    return l

def getset(repo, subset, x):

    if not x:

        raise error.ParseError(_("missing argument"))

    return methods[x[0]](repo, subset, *x[1:])

# operator methods

def stringset(repo, subset, x):

    x = repo[x].rev()

    if x == -1 and len(subset) == len(repo):

        return [-1]

    if len(subset) == len(repo) or x in subset:

        return [x]

    return []

def symbolset(repo, subset, x):

    if x in symbols:

        raise error.ParseError(_("can't use %s here") % x)

    return stringset(repo, subset, x)

def rangeset(repo, subset, x, y):

    m = getset(repo, subset, x)

    if not m:

        m = getset(repo, range(len(repo)), x)

    n = getset(repo, subset, y)

    if not n:

        n = getset(repo, range(len(repo)), y)

    if not m or not n:

        return []

    m, n = m[0], n[-1]

    if m < n:

        r = range(m, n + 1)

    else:

        r = range(m, n - 1, -1)

    s = set(subset)

    return [x for x in r if x in s]

def andset(repo, subset, x, y):

    return getset(repo, getset(repo, subset, x), y)

def orset(repo, subset, x, y):

    xl = getset(repo, subset, x)

    s = set(xl)

    yl = getset(repo, [r for r in subset if r not in s], y)

    return xl + yl

def notset(repo, subset, x):

    s = set(getset(repo, subset, x))

    return [r for r in subset if r not in s]

def listset(repo, subset, a, b):

    raise error.ParseError(_("can't use a list in this context"))

def func(repo, subset, a, b):

    if a[0] == 'symbol' and a[1] in symbols:

        return symbols[a[1]](repo, subset, b)

    raise error.ParseError(_("not a function: %s") % a[1])

# functions

def adds(repo, subset, x):

    """``adds(pattern)``

    Changesets that add a file matching pattern.

    """

    # i18n: "adds" is a keyword

    pat = getstring(x, _("adds requires a pattern"))

    return checkstatus(repo, subset, pat, 1)

def ancestor(repo, subset, x):

    """``ancestor(single, single)``

    Greatest common ancestor of the two changesets.

    """

    # i18n: "ancestor" is a keyword

    l = getargs(x, 2, 2, _("ancestor requires two arguments"))

    r = range(len(repo))

    a = getset(repo, r, l[0])

    b = getset(repo, r, l[1])

    if len(a) != 1 or len(b) != 1:

        # i18n: "ancestor" is a keyword

        raise error.ParseError(_("ancestor arguments must be single revisions"))

    an = [repo[a[0]].ancestor(repo[b[0]]).rev()]

    return [r for r in an if r in subset]

def ancestors(repo, subset, x):

    """``ancestors(set)``

    Changesets that are ancestors of a changeset in set.

    """

    args = getset(repo, range(len(repo)), x)

    if not args:

        return []

    s = set(repo.changelog.ancestors(*args)) | set(args)

    return [r for r in subset if r in s]

def ancestorspec(repo, subset, x, n):

    """``set~n``

    Changesets that are the Nth ancestor (first parents only) of a changeset in set.

    """

    try:

        n = int(n[1])

    except (TypeError, ValueError):

        raise error.ParseError(_("~ expects a number"))

    ps = set()

    cl = repo.changelog

    for r in getset(repo, subset, x):

        for i in range(n):

            r = cl.parentrevs(r)[0]

        ps.add(r)

    return [r for r in subset if r in ps]

def author(repo, subset, x):

    """``author(string)``

    Alias for ``user(string)``.

    """

    # i18n: "author" is a keyword

    n = getstring(x, _("author requires a string")).lower()

    return [r for r in subset if n in repo[r].user().lower()]

def bisected(repo, subset, x):

    """``bisected(string)``

    Changesets marked in the specified bisect state (good, bad, skip).

    """

    state = getstring(x, _("bisect requires a string")).lower()

    if state not in ('good', 'bad', 'skip', 'unknown'):

        raise error.ParseError(_('invalid bisect state'))

    marked = set(repo.changelog.rev(n) for n in hbisect.load_state(repo)[state])

    return [r for r in subset if r in marked]

def bookmark(repo, subset, x):

    """``bookmark([name])``

    The named bookmark or all bookmarks.

    """

    # i18n: "bookmark" is a keyword

    args = getargs(x, 0, 1, _('bookmark takes one or no arguments'))

    if args:

        bm = getstring(args[0],

                       # i18n: "bookmark" is a keyword

                       _('the argument to bookmark must be a string'))

        bmrev = bookmarksmod.listbookmarks(repo).get(bm, None)

        if not bmrev:

            raise util.Abort(_("bookmark '%s' does not exist") % bm)

        bmrev = repo[bmrev].rev()

        return [r for r in subset if r == bmrev]

    bms = set([repo[r].rev()

               for r in bookmarksmod.listbookmarks(repo).values()])

    return [r for r in subset if r in bms]

def branch(repo, subset, x):

    """``branch(string or set)``

    All changesets belonging to the given branch or the branches of the given

    changesets.

    """

    try:

        b = getstring(x, '')

        if b in repo.branchmap():

            return [r for r in subset if repo[r].branch() == b]

    except error.ParseError:

        # not a string, but another revspec, e.g. tip()

        pass

    s = getset(repo, range(len(repo)), x)

    b = set()

    for r in s:

        b.add(repo[r].branch())

    s = set(s)

    return [r for r in subset if r in s or repo[r].branch() in b]

def checkstatus(repo, subset, pat, field):

    m = matchmod.match(repo.root, repo.getcwd(), [pat])

    s = []

    fast = (m.files() == [pat])

    for r in subset:

        c = repo[r]

        if fast:

            if pat not in c.files():

                continue

        else:

            for f in c.files():

                if m(f):

                    break

            else:

                continue

        files = repo.status(c.p1().node(), c.node())[field]

        if fast:

            if pat in files:

                s.append(r)

        else:

            for f in files:

                if m(f):

                    s.append(r)

                    break

    return s

def children(repo, subset, x):

    """``children(set)``

    Child changesets of changesets in set.

    """

    cs = set()

    cl = repo.changelog

    s = set(getset(repo, range(len(repo)), x))

    for r in xrange(0, len(repo)):

        for p in cl.parentrevs(r):

            if p in s:

                cs.add(r)

    return [r for r in subset if r in cs]

def closed(repo, subset, x):

    """``closed()``

    Changeset is closed.

    """

    # i18n: "closed" is a keyword

    getargs(x, 0, 0, _("closed takes no arguments"))

    return [r for r in subset if repo[r].extra().get('close')]

def contains(repo, subset, x):

    """``contains(pattern)``

    Revision contains a file matching pattern. See :hg:`help patterns`

    for information about file patterns.

    """

    # i18n: "contains" is a keyword

    pat = getstring(x, _("contains requires a pattern"))

    m = matchmod.match(repo.root, repo.getcwd(), [pat])

    s = []

    if m.files() == [pat]:

        for r in subset:

            if pat in repo[r]:

                s.append(r)

    else:

        for r in subset:

            for f in repo[r].manifest():

                if m(f):

                    s.append(r)

                    break

    return s

def date(repo, subset, x):