# 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

import match as matchmod

from i18n import _, gettext

elements = {

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

    "-": (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 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):

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

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

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

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 node(repo, subset, x):

    """``id(string)``

    Revision non-ambiguously specified by the given hex string prefix.

    """

    # i18n: "id" is a keyword

    l = getargs(x, 1, 1, _("id requires one argument"))

    # i18n: "id" is a keyword

    n = getstring(l[0], _("id requires a string"))

    if len(n) == 40:

        rn = repo[n].rev()

    else:

        rn = repo.changelog.rev(repo.changelog._partialmatch(n))

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

def rev(repo, subset, x):

    """``rev(number)``

    Revision with the given numeric identifier.

    """

    # i18n: "rev" is a keyword

    l = getargs(x, 1, 1, _("rev requires one argument"))

    try:

        # i18n: "rev" is a keyword

        l = int(getstring(l[0], _("rev requires a number")))

    except ValueError:

        # i18n: "rev" is a keyword

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

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

def p1(repo, subset, x):

    """``p1(set)``

    First parent of changesets in set.

    """

    ps = set()

    cl = repo.changelog

    for r in getset(repo, range(len(repo)), x):

        ps.add(cl.parentrevs(r)[0])

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

def p2(repo, subset, x):

    """``p2(set)``

    Second parent of changesets in set.

    """

    ps = set()

    cl = repo.changelog

    for r in getset(repo, range(len(repo)), x):

        ps.add(cl.parentrevs(r)[1])

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

def parents(repo, subset, x):

    """``parents(set)``

    The set of all parents for all changesets in set.

    """

    ps = set()

    cl = repo.changelog

    for r in getset(repo, range(len(repo)), x):

        ps.update(cl.parentrevs(r))

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

def maxrev(repo, subset, x):

    """``max(set)``

    Changeset with highest revision number in set.

    """

    s = getset(repo, subset, x)

    if s:

        m = max(s)

        if m in subset:

            return [m]

    return []

def minrev(repo, subset, x):

    """``min(set)``

    Changeset with lowest revision number in set.

    """

    s = getset(repo, subset, x)

    if s:

        m = min(s)

        if m in subset:

            return [m]

    return []

def limit(repo, subset, x):

    """``limit(set, n)``

    First n members of set.

    """

    # i18n: "limit" is a keyword

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

    try:

        # i18n: "limit" is a keyword

        lim = int(getstring(l[1], _("limit requires a number")))

    except ValueError:

        # i18n: "limit" is a keyword

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

    return getset(repo, subset, l[0])[:lim]

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 branch(repo, subset, x):

    """``branch(set)``

    All changesets belonging to the branches of changesets in set.

    """

    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 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 descendants(repo, subset, x):

    """``descendants(set)``

    Changesets which are descendants of changesets in set.

    """

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

    if not args:

        return []

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

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

def follow(repo, subset, x):

    """``follow()``

    An alias for ``::.`` (ancestors of the working copy's first parent).

    """

    # i18n: "follow" is a keyword

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

    p = repo['.'].rev()

    s = set(repo.changelog.ancestors(p)) | set([p])

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

def date(repo, subset, x):

    """``date(interval)``

    Changesets within the interval, see :hg:`help dates`.

    """

    # i18n: "date" is a keyword

    ds = getstring(x, _("date requires a string"))

    dm = util.matchdate(ds)

    return [r for r in subset if dm(repo[r].date()[0])]

def keyword(repo, subset, x):

    """``keyword(string)``

    Search commit message, user name, and names of changed files for

    string.

    """

    # i18n: "keyword" is a keyword

    kw = getstring(x, _("keyword requires a string")).lower()

    l = []

    for r in subset:

        c = repo[r]

        t = " ".join(c.files() + [c.user(), c.description()])