This file is indexed.

/usr/lib/python2.7/dist-packages/pdfminer/utils.py is in python-pdfminer 20140328+dfsg-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
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
#!/usr/bin/env python
"""
Miscellaneous Routines.
"""
import struct
from sys import maxint as INF


##  PNG Predictor
##
def apply_png_predictor(pred, colors, columns, bitspercomponent, data):
    if bitspercomponent != 8:
        # unsupported
        raise ValueError(bitspercomponent)
    nbytes = colors*columns*bitspercomponent//8
    i = 0
    buf = ''
    line0 = '\x00' * columns
    for i in xrange(0, len(data), nbytes+1):
        ft = data[i]
        i += 1
        line1 = data[i:i+nbytes]
        line2 = ''
        if ft == '\x00':
            # PNG none
            line2 += line1
        elif ft == '\x01':
            # PNG sub (UNTESTED)
            c = 0
            for b in line1:
                c = (c+ord(b)) & 255
                line2 += chr(c)
        elif ft == '\x02':
            # PNG up
            for (a, b) in zip(line0, line1):
                c = (ord(a)+ord(b)) & 255
                line2 += chr(c)
        elif ft == '\x03':
            # PNG average (UNTESTED)
            c = 0
            for (a, b) in zip(line0, line1):
                c = ((c+ord(a)+ord(b))//2) & 255
                line2 += chr(c)
        else:
            # unsupported
            raise ValueError(ft)
        buf += line2
        line0 = line2
    return buf


##  Matrix operations
##
MATRIX_IDENTITY = (1, 0, 0, 1, 0, 0)


def mult_matrix((a1, b1, c1, d1, e1, f1), (a0, b0, c0, d0, e0, f0)):
    """Returns the multiplication of two matrices."""
    return (a0*a1+c0*b1,    b0*a1+d0*b1,
            a0*c1+c0*d1,    b0*c1+d0*d1,
            a0*e1+c0*f1+e0, b0*e1+d0*f1+f0)


def translate_matrix((a, b, c, d, e, f), (x, y)):
    """Translates a matrix by (x, y)."""
    return (a, b, c, d, x*a+y*c+e, x*b+y*d+f)


def apply_matrix_pt((a, b, c, d, e, f), (x, y)):
    """Applies a matrix to a point."""
    return (a*x+c*y+e, b*x+d*y+f)


def apply_matrix_norm((a, b, c, d, e, f), (p, q)):
    """Equivalent to apply_matrix_pt(M, (p,q)) - apply_matrix_pt(M, (0,0))"""
    return (a*p+c*q, b*p+d*q)


##  Utility functions
##

# isnumber
def isnumber(x):
    return isinstance(x, (int, long, float))

# uniq
def uniq(objs):
    """Eliminates duplicated elements."""
    done = set()
    for obj in objs:
        if obj in done:
            continue
        done.add(obj)
        yield obj
    return


# csort
def csort(objs, key=lambda x: x):
    """Order-preserving sorting function."""
    idxs = dict((obj, i) for (i, obj) in enumerate(objs))
    return sorted(objs, key=lambda obj: (key(obj), idxs[obj]))


# fsplit
def fsplit(pred, objs):
    """Split a list into two classes according to the predicate."""
    t = []
    f = []
    for obj in objs:
        if pred(obj):
            t.append(obj)
        else:
            f.append(obj)
    return (t, f)


# drange
def drange(v0, v1, d):
    """Returns a discrete range."""
    assert v0 < v1
    return xrange(int(v0)//d, int(v1+d)//d)


# get_bound
def get_bound(pts):
    """Compute a minimal rectangle that covers all the points."""
    (x0, y0, x1, y1) = (INF, INF, -INF, -INF)
    for (x, y) in pts:
        x0 = min(x0, x)
        y0 = min(y0, y)
        x1 = max(x1, x)
        y1 = max(y1, y)
    return (x0, y0, x1, y1)


# pick
def pick(seq, func, maxobj=None):
    """Picks the object obj where func(obj) has the highest value."""
    maxscore = None
    for obj in seq:
        score = func(obj)
        if maxscore is None or maxscore < score:
            (maxscore, maxobj) = (score, obj)
    return maxobj


# choplist
def choplist(n, seq):
    """Groups every n elements of the list."""
    r = []
    for x in seq:
        r.append(x)
        if len(r) == n:
            yield tuple(r)
            r = []
    return


# nunpack
def nunpack(s, default=0):
    """Unpacks 1 to 4 byte integers (big endian)."""
    l = len(s)
    if not l:
        return default
    elif l == 1:
        return ord(s)
    elif l == 2:
        return struct.unpack('>H', s)[0]
    elif l == 3:
        return struct.unpack('>L', '\x00'+s)[0]
    elif l == 4:
        return struct.unpack('>L', s)[0]
    else:
        raise TypeError('invalid length: %d' % l)


# decode_text
PDFDocEncoding = ''.join(unichr(x) for x in (
    0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007,
    0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f,
    0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0017, 0x0017,
    0x02d8, 0x02c7, 0x02c6, 0x02d9, 0x02dd, 0x02db, 0x02da, 0x02dc,
    0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027,
    0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f,
    0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037,
    0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f,
    0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047,
    0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f,
    0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057,
    0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x005f,
    0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067,
    0x0068, 0x0069, 0x006a, 0x006b, 0x006c, 0x006d, 0x006e, 0x006f,
    0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077,
    0x0078, 0x0079, 0x007a, 0x007b, 0x007c, 0x007d, 0x007e, 0x0000,
    0x2022, 0x2020, 0x2021, 0x2026, 0x2014, 0x2013, 0x0192, 0x2044,
    0x2039, 0x203a, 0x2212, 0x2030, 0x201e, 0x201c, 0x201d, 0x2018,
    0x2019, 0x201a, 0x2122, 0xfb01, 0xfb02, 0x0141, 0x0152, 0x0160,
    0x0178, 0x017d, 0x0131, 0x0142, 0x0153, 0x0161, 0x017e, 0x0000,
    0x20ac, 0x00a1, 0x00a2, 0x00a3, 0x00a4, 0x00a5, 0x00a6, 0x00a7,
    0x00a8, 0x00a9, 0x00aa, 0x00ab, 0x00ac, 0x0000, 0x00ae, 0x00af,
    0x00b0, 0x00b1, 0x00b2, 0x00b3, 0x00b4, 0x00b5, 0x00b6, 0x00b7,
    0x00b8, 0x00b9, 0x00ba, 0x00bb, 0x00bc, 0x00bd, 0x00be, 0x00bf,
    0x00c0, 0x00c1, 0x00c2, 0x00c3, 0x00c4, 0x00c5, 0x00c6, 0x00c7,
    0x00c8, 0x00c9, 0x00ca, 0x00cb, 0x00cc, 0x00cd, 0x00ce, 0x00cf,
    0x00d0, 0x00d1, 0x00d2, 0x00d3, 0x00d4, 0x00d5, 0x00d6, 0x00d7,
    0x00d8, 0x00d9, 0x00da, 0x00db, 0x00dc, 0x00dd, 0x00de, 0x00df,
    0x00e0, 0x00e1, 0x00e2, 0x00e3, 0x00e4, 0x00e5, 0x00e6, 0x00e7,
    0x00e8, 0x00e9, 0x00ea, 0x00eb, 0x00ec, 0x00ed, 0x00ee, 0x00ef,
    0x00f0, 0x00f1, 0x00f2, 0x00f3, 0x00f4, 0x00f5, 0x00f6, 0x00f7,
    0x00f8, 0x00f9, 0x00fa, 0x00fb, 0x00fc, 0x00fd, 0x00fe, 0x00ff,
))


def decode_text(s):
    """Decodes a PDFDocEncoding string to Unicode."""
    if s.startswith('\xfe\xff'):
        return unicode(s[2:], 'utf-16be', 'ignore')
    else:
        return ''.join(PDFDocEncoding[ord(c)] for c in s)


# enc
def enc(x, codec='ascii'):
    """Encodes a string for SGML/XML/HTML"""
    x = x.replace('&', '&amp;').replace('>', '&gt;').replace('<', '&lt;').replace('"', '&quot;')
    return x.encode(codec, 'xmlcharrefreplace')


def bbox2str((x0, y0, x1, y1)):
    return '%.3f,%.3f,%.3f,%.3f' % (x0, y0, x1, y1)


def matrix2str((a, b, c, d, e, f)):
    return '[%.2f,%.2f,%.2f,%.2f, (%.2f,%.2f)]' % (a, b, c, d, e, f)


##  Plane
##
##  A set-like data structure for objects placed on a plane.
##  Can efficiently find objects in a certain rectangular area.
##  It maintains two parallel lists of objects, each of
##  which is sorted by its x or y coordinate.
##
class Plane(object):

    def __init__(self, bbox, gridsize=50):
        self._objs = set()
        self._grid = {}
        self.gridsize = gridsize
        (self.x0, self.y0, self.x1, self.y1) = bbox
        return

    def __repr__(self):
        return ('<Plane objs=%r>' % list(self))

    def __iter__(self):
        return iter(self._objs)

    def __len__(self):
        return len(self._objs)

    def __contains__(self, obj):
        return obj in self._objs

    def _getrange(self, (x0, y0, x1, y1)):
        if (x1 <= self.x0 or self.x1 <= x0 or
            y1 <= self.y0 or self.y1 <= y0): return
        x0 = max(self.x0, x0)
        y0 = max(self.y0, y0)
        x1 = min(self.x1, x1)
        y1 = min(self.y1, y1)
        for y in drange(y0, y1, self.gridsize):
            for x in drange(x0, x1, self.gridsize):
                yield (x, y)
        return

    # extend(objs)
    def extend(self, objs):
        for obj in objs:
            self.add(obj)
        return

    # add(obj): place an object.
    def add(self, obj):
        for k in self._getrange((obj.x0, obj.y0, obj.x1, obj.y1)):
            if k not in self._grid:
                r = []
                self._grid[k] = r
            else:
                r = self._grid[k]
            r.append(obj)
        self._objs.add(obj)
        return

    # remove(obj): displace an object.
    def remove(self, obj):
        for k in self._getrange((obj.x0, obj.y0, obj.x1, obj.y1)):
            try:
                self._grid[k].remove(obj)
            except (KeyError, ValueError):
                pass
        self._objs.remove(obj)
        return

    # find(): finds objects that are in a certain area.
    def find(self, (x0, y0, x1, y1)):
        done = set()
        for k in self._getrange((x0, y0, x1, y1)):
            if k not in self._grid:
                continue
            for obj in self._grid[k]:
                if obj in done:
                    continue
                done.add(obj)
                if (obj.x1 <= x0 or x1 <= obj.x0 or
                    obj.y1 <= y0 or y1 <= obj.y0):
                    continue
                yield obj
        return