This file is indexed.

/usr/share/pyshared/tegakitools/unipen.py is in python-tegakitools 0.3.1-1.

This file is owned by root:root, with mode 0o644.

The actual contents of the file can be viewed below.

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
#!/usr/bin/env python
# -*- coding: utf-8 -*-

# Copyright (C) 2009 The Tegaki project contributors
#
# 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 2 of the License, 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.

# Contributors to this file:
# - Mathieu Blondel

# Incomplete unipen format parser
# See http://hwr.nici.kun.nl/unipen/unipen.def for the format specification

import re
import os

from tegaki.character import Point, Stroke, Writing, Character
from tegaki.charcol import CharacterCollection

class UnipenEventParser(object):
    """SAX-like event-based parser"""

    KEYWORD_LINE_REGEXP = re.compile(r"^\.[A-Z]+")

    def __init__(self):
        self._parsed_file = None

    def parse_file(self, path):
        self._parsed_file = path
        f = open(path)

        keyword, args = None, None
        for line in f.readlines():
            if self._is_keyword_line(line):
                if keyword is not None and args is not None:
                    self.handle_keyword(keyword.strip(), args.strip())
                    keyword, args = None, None

                arr = line.split(" ", 1)

                keyword = arr[0][1:]
                if len(arr) == 1: 
                    args = ""
                else: 
                    args = arr[1]

            elif keyword is not None and args is not None:
                args += line

        if keyword is not None and args is not None:
            self.handle_keyword(keyword, args)

        f.close()

        self.handle_eof()

        self._parsed_file = None

    def handle_keyword(self, keyword, args):
        # default keyword handler
        print keyword, args

    def handle_eof(self):
        # default end-of-file handler
        print "end of file"

    def _is_keyword_line(self, line):
        return (self.KEYWORD_LINE_REGEXP.match(line) is not None)

class UnipenProxyParser(UnipenEventParser):
    
    def __init__(self, redirect):
        UnipenEventParser.__init__(self)
        self._redirect = redirect

    def handle_keyword(self, keyword, args):
        self._redirect(keyword, args)

    def handle_eof(self):
        pass

class UnipenParser(UnipenEventParser):

    def __init__(self):
        UnipenEventParser.__init__(self)
        self._labels = []
        self._characters = []
        self._char = None

    def _handle_SEGMENT(self, args):
        seg_type, delimit, quality, label = args.split(" ")
        if seg_type == "CHARACTER":
            label = label.strip()[1:-1]
            self._labels.append(label)

    def _handle_START_BOX(self, args):
        if self._char:
            self._characters.append(self._char)
        self._char = Character() 

    def _handle_PEN_DOWN(self, args):
        writing = self._char.get_writing()
        points = [[int(p_) for p_ in p.split(" ")] \
                    for p in args.strip().split("\n")]
        stroke = Stroke()
        for x, y in points:
            stroke.append_point(Point(x,y))
        writing.append_stroke(stroke)

    def _handle_INCLUDE(self, args):
        if not self._parsed_file: return

        include_filename = args.upper()
        currdir = os.path.dirname(os.path.abspath(self._parsed_file))

        # FIXME: don't hardcode include paths
        include1 = os.path.join(currdir, "INCLUDE")
        include2 = os.path.join(currdir, "..", "INCLUDE")

        for include in (include1, include2, currdir):   
            path = os.path.join(include, include_filename)
            if os.path.exists(path):
                parser = UnipenProxyParser(self.handle_keyword)
                parser.parse_file(path)
                break

    def handle_keyword(self, keyword, args):
        try:
            func = getattr(self, "_handle_" + keyword)
        except AttributeError:
            pass
        else:
            func(args)

    def get_character_collection(self):
        charcol = CharacterCollection()
        assert(len(self._labels) == len(self._characters))

        # group characters with the same label into sets
        sets = {}
        for i in range(len(self._characters)):
            utf8 = self._labels[i]
            self._characters[i].set_utf8(utf8)
            sets[utf8] = sets.get(utf8, []) + [self._characters[i]]

        charcol.add_sets(sets.keys())

        for set_name, characters in sets.items():
            charcol.append_characters(set_name, characters)

        return charcol