wting_autojump/bin/autojump

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
  Copyright © 2008-2012 Joel Schaerer
  Copyright © 2012-2013 William Ting

  *  This program is free software; you can redistribute it and/or modify
  it under the terms of the GNU General Public License as published by
  the Free Software Foundation; either version 3, or (at your option)
  any later version.

  *  This program is distributed in the hope that it will be useful,
  but WITHOUT ANY WARRANTY; without even the implied warranty of
  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  GNU General Public License for more details.

  *  You should have received a copy of the GNU General Public License
  along with this program; if not, write to the Free Software
  Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
"""

from __future__ import print_function

from difflib import SequenceMatcher
from functools import partial
from itertools import chain
# FIXME(ting|2013-12-17): fix imports for Python 3 compatability
from itertools import ifilter
from itertools import imap
from math import sqrt
from operator import attrgetter
from operator import itemgetter
import os
import platform
import re
import sys

from argparse import ArgumentParser

from data import dictify
from data import entriefy
from data import Entry
from data import load
from data import save
from utils import decode
from utils import encode_local
from utils import first
from utils import get_pwd
from utils import has_uppercase
from utils import is_osx
from utils import last
from utils import print_entry
from utils import second
from utils import take

VERSION = 'release-v21.8.0'
FUZZY_MATCH_THRESHOLD = 0.6


def set_defaults():
    config = {}
    config['tab_menu_separator'] = '__'

    if is_osx():
        data_home = os.path.join(
                        os.path.expanduser('~'),
                        'Library',
                        'autojump')
    else:
        data_home = os.getenv(
                'XDG_DATA_HOME',
                os.path.join(
                        os.path.expanduser('~'),
                        '.local',
                        'share',
                        'autojump'))

    config['data_path'] = os.path.join(data_home, 'autojump.txt')
    config['backup_path'] = os.path.join(data_home, 'autojump.txt.bak')
    config['tmp_path'] = os.path.join(data_home, 'data.tmp')

    return config


def parse_environment(config):
    # TODO(ting|2013-12-16): add autojump_data_dir support
    # TODO(ting|2013-12-15): add ignore case / smartcase support
    # TODO(ting|2013-12-15): add symlink support

    return config


def parse_arguments():
    """Evaluate arguments and run appropriate logic, returning an error code."""
    parser = ArgumentParser(
            description='Automatically jump to directory passed as an argument.',
            epilog="Please see autojump(1) man pages for full documentation.")
    parser.add_argument(
            'directory', metavar='DIRECTORY', nargs='*', default='',
            help='directory to jump to')
    parser.add_argument(
            '-a', '--add', metavar='DIRECTORY',
            help='add path')
    parser.add_argument(
            '-i', '--increase', metavar='WEIGHT', nargs='?', type=int,
            const=20, default=False,
            help='increase current directory weight')
    parser.add_argument(
            '-d', '--decrease', metavar='WEIGHT', nargs='?', type=int,
            const=15, default=False,
            help='decrease current directory weight')
    # parser.add_argument(
            # '-b', '--bash', action="store_true", default=False,
            # help='enclose directory quotes to prevent errors')
    # parser.add_argument(
            # '--complete', action="store_true", default=False,
            # help='used for tab completion')
    parser.add_argument(
            '--purge', action="store_true", default=False,
            help='remove non-existent paths from database')
    parser.add_argument(
            '-s', '--stat', action="store_true", default=False,
            help='show database entries and their key weights')
    parser.add_argument(
            '-v', '--version', action="version", version="%(prog)s " +
            VERSION, help='show version information')

    return parser.parse_args()


def add_path(data, path, increment=10):
    """
    Add a new path or increment an existing one.

    os.path.realpath() is not used because users prefer to have short, symlinked
    paths with duplicate entries in the database than a single canonical path.
    """
    path = decode(path).rstrip(os.sep)
    if path == os.path.expanduser('~'):
        return data, Entry(path, 0)

    if path in data:
        data[path] = sqrt((data[path]**2) + (increment**2))
    else:
        data[path] = increment

    return data, Entry(path, data[path])


def decrease_path(data, path, increment=15):
    """Decrease weight of existing path."""
    path = decode(path).rstrip(os.sep)
    data[path] = max(0, data[path]-increment)
    return data, Entry(path, data[path])


def detect_smartcase(needles):
    """
    If any needles contain an uppercase letter then use case sensitive
    searching. Otherwise use case insensitive searching.
    """
    return not any(imap(has_uppercase, needles))


def find_matches(entries, needles):
    """Return an iterator to matching entries."""
    try:
        not_cwd = lambda entry: entry.path != os.getcwdu()
    except OSError:
        # tautology if current working directory no longer exists
        not_cwd = lambda x: True

    data = sorted(
            ifilter(not_cwd, entries),
            key=attrgetter('weight'),
            reverse=True)

    if not needles:
        return first(data).path

    sanitize = lambda x: decode(x).rstrip(os.sep)
    needles = map(sanitize, needles)
    ignore_case = detect_smartcase(needles)

    consecutive_matches = match_consecutive(needles, data, ignore_case)
    quicksilver_matches = match_quicksilver(needles, data, ignore_case)
    fuzzy_matches = match_fuzzy(needles, data, ignore_case)

    exists = lambda entry: os.path.exists(entry.path)
    return ifilter(
            exists,
            chain(consecutive_matches, quicksilver_matches, fuzzy_matches))


def match_consecutive(needles, haystack, ignore_case=False):
    """
    Matches consecutive needles at the end of a path.

    For example:
        needles = ['foo', 'baz']
        haystack = [
            (path="/foo/bar/baz", weight=10),
            (path="/foo/baz/moo", weight=10),
            (path="/moo/foo/baz", weight=10),
            (path="/foo/baz", weight=10)]

        regex_needle = re.compile(r'''
            foo     # needle #1
            [^/]*   # all characters except os.sep zero or more times
            /       # os.sep
            [^/]*   # all characters except os.sep zero or more times
            baz     # needle #2
            [^/]*   # all characters except os.sep zero or more times
            $       # end of string
            ''')

        result = [
            (path="/moo/foo/baz", weight=10),
            (path="/foo/baz", weight=10)]
    """
    regex_no_sep = '[^' + os.sep + ']*'
    regex_one_sep = regex_no_sep + os.sep + regex_no_sep
    regex_no_sep_end = regex_no_sep + '$'
    # can't use compiled regex because of flags
    regex_needle = regex_one_sep.join(needles) + regex_no_sep_end
    regex_flags = re.IGNORECASE | re.UNICODE if ignore_case else re.UNICODE

    found = lambda entry: re.search(
            regex_needle,
            entry.path,
            flags=regex_flags)
    return ifilter(found, haystack)


def match_fuzzy(needles, haystack, ignore_case=False):
    """
    Performs an approximate match with the last needle against the end of
    every path past an acceptable threshold (FUZZY_MATCH_THRESHOLD).

    For example:
        needles = ['foo', 'bar']
        haystack = [
            (path="/foo/bar/baz", weight=11),
            (path="/foo/baz/moo", weight=10),
            (path="/moo/foo/baz", weight=10),
            (path="/foo/baz", weight=10),
            (path="/foo/bar", weight=10)]

    result = [
            (path="/foo/bar/baz", weight=11),
            (path="/moo/foo/baz", weight=10),
            (path="/foo/baz", weight=10),
            (path="/foo/bar", weight=10)]

    This is a weak heuristic and be used as a last resort to find matches.
    """
    needle = last(needles)
    end_dir = lambda path: last(os.path.split(path))
    match_percent = lambda entry: SequenceMatcher(
            a=needle,
            b=end_dir(entry.path)).ratio()
    meets_threshold = lambda entry: match_percent(entry) \
            >= FUZZY_MATCH_THRESHOLD
    return ifilter(meets_threshold, haystack)


def match_quicksilver(needles, haystack, ignore_case=False):
    """
    """
    return []


def purge_missing_paths(entries):
    """Remove non-existent paths from a list of entries."""
    exists = lambda entry: os.path.exists(entry.path)
    return ifilter(exists, entries)


def print_stats(data, data_path):
    for path, weight in sorted(data.iteritems(), key=itemgetter(1)):
        print_entry(Entry(path, weight))

    print("________________________________________\n")
    print("%d:\t total weight" % sum(data.itervalues()))
    print("%d:\t number of entries" % len(data))

    try:
        print("%.2f:\t current directory weight" % data.get(os.getcwdu(), 0))
    except OSError:
        pass

    print("\ndata:\t %s" % data_path)


def main():
    config = parse_environment(set_defaults())
    args = parse_arguments()

    if args.add:
        save(config, first(add_path(load(config), args.add)))
    # elif args.complete:
        # config['match_cnt'] = 9
        # config['ignore_case'] = True
    elif args.decrease:
        data, entry = decrease_path(load(config), get_pwd(), args.decrease)
        save(config, data)
        print_entry(entry)
    elif args.increase:
        data, entry = add_path(load(config), get_pwd(), args.decrease)
        save(config, data)
        print_entry(entry)
    elif args.purge:
        old_data = load(config)
        new_data = dictify(purge_missing_paths(entriefy(old_data)))
        save(config, new_data)
        print("Purged %d entries." % (len(old_data)-len(new_data)))
    elif args.stat:
        print_stats(load(config), config['data_path'])
    else:
        # default behavior, no optional arguments
        result = first(find_matches(entriefy(load(config)), args.directory))

        if result:
            print(encode_local(surround_quotes(result.path)))
        else:
            # always return something so the calling shell function has an
            # argument to `cd` to
            print(encode_local('.'))

    return 0


if __name__ == "__main__":
    sys.exit(main())