This file is indexed.

/usr/lib/python2.7/dist-packages/fabio/cbfimage.py is in python-fabio 0.3.0+dfsg-1build1.

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
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
# coding: utf-8
#
#    Project: X-ray image reader
#             https://github.com/kif/fabio
#
#
#    Copyright (C) European Synchrotron Radiation Facility, Grenoble, France
#
#    Principal author:       Jérôme Kieffer (Jerome.Kieffer@ESRF.eu)
#
#    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 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, see <http://www.gnu.org/licenses/>.
#

"""
Authors: Jérôme Kieffer, ESRF
         email:jerome.kieffer@esrf.fr

Cif Binary Files images are 2D images written by the Pilatus detector and others.
They use a modified (simplified) byte-offset algorithm.

CIF is a library for manipulating Crystallographic information files and tries
to conform to the specification of the IUCR
"""

# get ready for python3
from __future__ import with_statement, print_function, absolute_import

__author__ = "Jérôme Kieffer"
__contact__ = "jerome.kieffer@esrf.eu"
__license__ = "GPLv3+"
__date__ = "30/10/2015"
__copyright__ = "European Synchrotron Radiation Facility, Grenoble, France"
__version__ = ["Generated by CIF.py: Jan 2005 - Oct 2015",
              "Written by Jerome Kieffer: Jerome.Kieffer@esrf.eu",
              "On-line data analysis / ISDD ", "ESRF Grenoble (France)"]


import os, logging
import numpy
from .fabioimage import FabioImage
from .fabioutils import six
from .compression import compByteOffset, decByteOffset, md5sum

logger = logging.getLogger("CbfImage")

# import time
try:
    from ._cif import split_tokens
except ImportError:
    split_tokens = None

DATA_TYPES = { "signed 8-bit integer"   : "int8",
               "signed 16-bit integer"  : "int16",
               "signed 32-bit integer"  : "int32",
               "signed 64-bit integer"  : "int64",
               "unsigned 8-bit integer" : "uint8",
               "unsigned 16-bit integer": "uint16",
               "unsigned 32-bit integer": "uint32",
               "unsigned 64-bit integer": "uint64"
                }

MINIMUM_KEYS = ["X-Binary-Size-Fastest-Dimension",
                "X-Binary-Size-Second-Dimension",
                "X-Binary-Size",
                "X-Binary-Number-of-Elements",
                'X-Binary-Element-Type',
                'X-Binary-Number-of-Elements']


STARTER = b"\x0c\x1a\x04\xd5"
PADDING = 512
BINARAY_SECTION = b"--CIF-BINARY-FORMAT-SECTION--"
CIF_BINARY_BLOCK_KEY = "_array_data.data"

class CbfImage(FabioImage):
    """
    Read the Cif Binary File data format
    """
    def __init__(self, data=None , header=None, fname=None):
        """
        Constructor of the class CIF Binary File reader.

        @param _strFilename: the name of the file to open
        @type  _strFilename: string
        """
        FabioImage.__init__(self, data, header)
        self.cif = CIF()
        self.cbs = None
        self.start_binary = None
        if fname is not None:  # load the file)
            self.read(fname)

    @staticmethod
    def checkData(data=None):
        if data is None:
            return None
        elif numpy.issubdtype(data.dtype, int):
            return data
        else:
            return data.astype(int)


    def _readheader(self, inStream):
        """
        Read in a header in some CBF format from a string representing binary stuff

        @param inStream: file containing the Cif Binary part.
        @type inStream: opened file.
        """
        self._read_cif_header(inStream)
        self._read_binary_section_header(inStream)

    def _read_cif_header(self, inStream):
        """
        Read in a ASCII CIF header

        @param inStream: file containing the Cif Binary part.
        @type inStream: opened file.
        """
        blocks = []
        last = ""
        header_data = None
        for i in range(16):
            # up to 512*16 = 8k headers
            ablock = inStream.read(PADDING)
            blocks.append(ablock)
            if last:
                extra = len(BINARAY_SECTION)
                extblock = last[-extra:] + ablock
            else:
                extra = 0
                extblock = ablock
            res = extblock.find(BINARAY_SECTION)
            if res >= 0:
                start_cbs = i * PADDING - extra + res
                all_blocks = b"".join(blocks)
                header_data = all_blocks[:start_cbs] + b"CIF Binary Section\n;\n"
                self.cbs = all_blocks[start_cbs:]
                break
            last = ablock
        else:
            header_data = b"".join(blocks) + inStream.read()
        self.cif._parseCIF(header_data)

#        backport contents of the CIF data to the headers
        for key, value in self.cif.items():
            if key == CIF_BINARY_BLOCK_KEY:
                if self.cbs is None:
                    self.cbs = value
            else:
                self.header[key] = (self.cif[key].strip(" \"\n\r\t"))

    def _read_binary_section_header(self, inStream):
        """
        Read the binary section header
        """
        self.start_binary = self.cbs.find(STARTER)
        while self.start_binary < 0:
            self.cbs += inStream.read(PADDING)
            self.start_binary = self.cbs.find(STARTER)
        bin_headers = self.cbs[:self.start_binary]
        lines = bin_headers.split(b"\n")
        for line in lines[1:]:
            if len(line) < 10:
                break
            try:
                key, val = line.split(b':' , 1)
            except ValueError:
                key, val = line.split(b'=' , 1)
            key = key.strip().decode("ASCII")
            self.header[key] = val.strip(b" \"\n\r\t").decode("ASCII")
        missing = []
        for item in MINIMUM_KEYS:
            if item not in self.header:
                missing.append(item)
        if missing:
            logger.info("Mandatory keys missing in CBF file: " + ", ".join(missing))
        # Compute image size
        try:
            self.dim1 = int(self.header['X-Binary-Size-Fastest-Dimension'])
            self.dim2 = int(self.header['X-Binary-Size-Second-Dimension'])
        except:
            raise IOError("CBF file %s is corrupt, no dimensions in it" % fname)
        try:
            self.bytecode = DATA_TYPES[self.header['X-Binary-Element-Type']]
        except KeyError:
            self.bytecode = "int32"
            logger.warning("Defaulting type to int32")
        self.bpp = numpy.dtype(self.bytecode).itemsize

    def read(self, fname, frame=None):
        """
        Read in header into self.header and
            the data   into self.data
        """
        self.filename = fname
        self.header = self.check_header()
        self.resetvals()

        infile = self._open(fname, "rb")
        self._readheader(infile)
        if CIF_BINARY_BLOCK_KEY not in self.cif:
            err = "Not key %s in CIF, no CBF image in %s" % (CIF_BINARY_BLOCK_KEY, fname)
            logger.error(err)
            for kv in self.cif.items():
                print("%s: %s" % kv)
            raise RuntimeError(err)
        if self.cif[CIF_BINARY_BLOCK_KEY] == "CIF Binary Section":
            self.cbs += infile.read(len(STARTER) + int(self.header["X-Binary-Size"]) - len(self.cbs) + self.start_binary)
        else:
            if len(self.cif[CIF_BINARY_BLOCK_KEY]) > int(self.header["X-Binary-Size"]) + self.start_binary + len(STARTER):
                self.cbs = self.cif[CIF_BINARY_BLOCK_KEY][:int(self.header["X-Binary-Size"]) + self.start_binary + len(STARTER)]
            else:
                self.cbs = self.cif[CIF_BINARY_BLOCK_KEY]
        binary_data = self.cbs[self.start_binary + len(STARTER):]
        logger.debug("CBS type %s len %s" % (type(self.cbs), len(self.cbs)))

        if "Content-MD5" in self.header:
                ref = numpy.string_(self.header["Content-MD5"])
                obt = md5sum(binary_data)
                if ref != obt:
                    logger.error("Checksum of binary data mismatch: expected %s, got %s" % (ref, obt))

        if self.header["conversions"] == "x-CBF_BYTE_OFFSET":
            self.data = self._readbinary_byte_offset(binary_data).astype(self.bytecode).reshape((self.dim2, self.dim1))
        else:
            raise Exception(IOError, "Compression scheme not yet supported, please contact the author")

        self.resetvals()
#        # ensure the PIL image is reset
        self.pilimage = None
        return self



    def _readbinary_byte_offset(self, raw_bytes):
        """
        Read in a binary part of an x-CBF_BYTE_OFFSET compressed image

        @param inStream: the binary image (without any CIF decorators)
        @type inStream: python string.
        @return: a linear numpy array without shape and dtype set
        @rtype: numpy array
        """
        myData = decByteOffset(raw_bytes, size=self.dim1 * self.dim2)
        assert len(myData) == self.dim1 * self.dim2
        return myData


    def write(self, fname):
        """
        write the file in CBF format
        @param fname: name of the file
        @type: string
        """
        if self.data is not None:
            self.dim2, self.dim1 = self.data.shape
        else:
            raise RuntimeError("CBF image contains no data")
        binary_blob = compByteOffset(self.data)
#        l = len(binary_blob)
#        if (l % PADDING) != 0:
#            rem = PADDING - (l % PADDING)
#            binary_blob += "\x00" * rem
        dtype = "Unknown"
        for key, value in DATA_TYPES.items():
            if value == self.data.dtype:
                dtype = key
        binary_block = [
                        b"--CIF-BINARY-FORMAT-SECTION--",
                        b"Content-Type: application/octet-stream;",
                        b'     conversions="x-CBF_BYTE_OFFSET"',
                        b'Content-Transfer-Encoding: BINARY',
                        numpy.string_("X-Binary-Size: %d" % (len(binary_blob))),
                        b"X-Binary-ID: 1",
                        numpy.string_('X-Binary-Element-Type: "%s"' % (dtype)),
                        b"X-Binary-Element-Byte-Order: LITTLE_ENDIAN" ,
                        b"Content-MD5: " + md5sum(binary_blob),
                        numpy.string_("X-Binary-Number-of-Elements: %d" % (self.dim1 * self.dim2)),
                        numpy.string_("X-Binary-Size-Fastest-Dimension: %d" % self.dim1),
                        numpy.string_("X-Binary-Size-Second-Dimension: %d" % self.dim2),
                        b"X-Binary-Size-Padding: 1",
                        b"",
                        STARTER + binary_blob,
                        b"",
                        b"--CIF-BINARY-FORMAT-SECTION----"
                        ]

        if "_array_data.header_contents" not in self.header:
            nonCifHeaders = []
        else:
            nonCifHeaders = [i.strip()[2:] for i in self.header["_array_data.header_contents"].split("\n") if i.find("# ") >= 0]

        for key in self.header:
            if key.startswith("_") :
                if key not in self.cif or self.cif[key] != self.header[key]:
                    self.cif[key] = self.header[key]
            elif key.startswith("X-Binary-"):
                pass
            elif key.startswith("Content-"):
                pass
            elif key.startswith("conversions"):
                pass
            elif key.startswith("filename"):
                pass
            elif key in self.header:
                nonCifHeaders.append("%s %s" % (key, self.header[key]))
        if len(nonCifHeaders) > 0:
            self.cif["_array_data.header_contents"] = "\r\n".join(["# %s" % i for i in nonCifHeaders])

        self.cbf = b"\r\n".join(binary_block)
        block = b"\r\n".join([b"", CIF_BINARY_BLOCK_KEY.encode("ASCII"), b";", self.cbf, b";"])
        self.cif.pop(CIF_BINARY_BLOCK_KEY, None)
        with open(fname, "wb") as out_file:
            out_file.write(self.cif.tostring(fname, "\r\n").encode("ASCII"))
            out_file.write(block)

################################################################################
# CIF class
################################################################################
class CIF(dict):
    """
    This is the CIF class, it represents the CIF dictionary;
    and as a a python dictionary thus inherits from the dict built in class.

    keys are always unicode (str in python3)
    values are bytes
    """
    EOL = [numpy.string_(i) for i in ("\r", "\n", "\r\n", "\n\r")]
    BLANK = [numpy.string_(i) for i in (" ", "\t")] + EOL
    SINGLE_QUOTE = numpy.string_("'")
    DOUBLE_QUOTE = numpy.string_('"')
    SEMICOLUMN = numpy.string_(';')
    START_COMMENT = (SINGLE_QUOTE, DOUBLE_QUOTE)
    BINARY_MARKER = numpy.string_("--CIF-BINARY-FORMAT-SECTION--")
    HASH = numpy.string_("#")
    LOOP = numpy.string_("loop_")
    UNDERSCORE = ord("_") if six.PY3 else b"_"
    QUESTIONMARK = ord("?") if six.PY3 else b"?"
    STOP = numpy.string_("stop_")
    GLOBAL = numpy.string_("global_")
    DATA = numpy.string_("data_")
    SAVE = numpy.string_("save_")



    def __init__(self, _strFilename=None):
        """
        Constructor of the class.

        @param _strFilename: the name of the file to open
        @type  _strFilename: filename (str) or file object
        """
        dict.__init__(self)
        self._ordered = []
        if _strFilename is not None:  # load the file)
            self.loadCIF(_strFilename)

    def __setitem__(self, key, value):
        if key not in self._ordered:
            self._ordered.append(key)
        return dict.__setitem__(self, key, value)

    def pop(self, key, default=None):
        if key  in self._ordered:
            self._ordered.remove(key)
        return dict.pop(self, key, default)

    def popitem(self, key, default=None):
        if key  in self._ordered:
            self._ordered.remove(key)
        return dict.popitem(self, key, None)


    def loadCIF(self, _strFilename, _bKeepComment=False):
        """Load the CIF file and populates the CIF dictionary into the object
        @param _strFilename: the name of the file to open
        @type  _strFilename: string
        @param _strFilename: the name of the file to open
        @type  _strFilename: string
        @return: None
        """
        own_fd = False
        if isinstance(_strFilename, (six.binary_type, six.text_type)):
            if os.path.isfile(_strFilename):
                infile = open(_strFilename, "rb")
                own_fd = True
            else:
                raise RuntimeError("CIF.loadCIF: No such file to open: %s" % _strFilename)
        elif "read" in dir(_strFilename):
            infile = _strFilename
        else:
            raise RuntimeError("CIF.loadCIF: what is %s type %s" % (_strFilename, type(_strFilename)))
        if _bKeepComment:
            self._parseCIF(numpy.string_(infile.read()))
        else:
            self._parseCIF(CIF._readCIF(infile))
        if own_fd:
            infile.close()
    readCIF = loadCIF

    @staticmethod
    def isAscii(text):
        """
        Check if all characters in a string are ascii,

        @param _strIn: input string
        @type _strIn: python string
        @return: boolean
        @rtype: boolean
        """
        try:
            text.decode("ascii")
        except UnicodeDecodeError:
            return False
        else:
            return True


    @staticmethod
    def _readCIF(instream):
        """
        - Check if the filename containing the CIF data exists
        - read the cif file
        - removes the comments

        @param instream: opened file object containing the CIF data
        @return: a set of bytes (8-bit string) containing the raw data
        @rtype: string
        """
        if not "read" in dir(instream):
            raise RuntimeError("CIF._readCIF(instream): I expected instream to be an opened file,\
             here I got %s type %s" % (instream, type(instream)))
        out_bytes = numpy.string_("")
        for sLine in instream:
            nline = numpy.string_(sLine)
            pos = nline.find(self.HASH)
            if pos >= 0:
                if self.isAscii(nLine):
                    out_bytes += nLine[:pos] + numpy.string_(os.linesep)
                if pos > 80:
                    logger.warning("This line is too long and could cause problems in PreQuest: %s", sLine)
            else :
                out_bytes += nLine
                if len(sLine.strip()) > 80 :
                    logger.warning("This line is too long and could cause problems in PreQuest: %s", sLine)
        return out_bytes


    def _parseCIF(self, bytes_text):
        """
        - Parses the text of a CIF file
        - Cut it in fields
        - Find all the loops and process
        - Find all the keys and values

        @param bytes_text: the content of the CIF - file
        @type bytes_text: 8-bit string (str in python2 or bytes in python3)
        @return: Nothing, the data are incorporated at the CIF object dictionary
        @rtype: None
        """
        loopidx = []
        looplen = []
        loop = []
        if split_tokens:
            logger.debug("using cython split_tokens")
            fields = split_tokens(bytes_text)
        else:
            logger.debug("using python split")
            fields = self._splitCIF(bytes_text.strip())

        logger.debug("After split got %s fileds" % len(fields))

        for idx, field in enumerate(fields):
            if field.lower() == self.LOOP:
                loopidx.append(idx)
        if loopidx:
            for i in loopidx:
                loopone, length, keys = CIF._analyseOneLoop(fields, i)
                loop.append([keys, loopone])
                looplen.append(length)


            for i in range(len(loopidx) - 1, -1, -1):
                f1 = fields[:loopidx[i]] + fields[loopidx[i] + looplen[i]:]
                fields = f1

            self[self.LOOP.decode("ASCII")] = loop

        for i in range(len(fields) - 1):
            if len(fields[i + 1]) == 0 :
                fields[i + 1] = self.QUESTIONMARK
            if fields[i][0] == self.UNDERSCORE and fields[i + 1][0] != self.UNDERSCORE:
                try:
                    data = fields[i + 1].decode("ASCII")
                except UnicodeError:
                    logger.warning("Unable to decode in ascii: %s" % fields[i + 1])
                    data = fields[i + 1]
                self[(fields[i]).decode("ASCII")] = data

    @classmethod
    def _splitCIF(cls, bytes_text):
        """
        Separate the text in fields as defined in the CIF

        @param bytes_text: the content of the CIF - file
        @type bytes_text:  8-bit string (str in python2 or bytes in python3)
        @return: list of all the fields of the CIF
        @rtype: list
        """
        fields = []
        while True:
            if len(bytes_text) == 0:
                break
            elif bytes_text[0] == cls.SINGLE_QUOTE:
                idx = 0
                finished = False
                while not finished:
                    idx += 1 + bytes_text[idx + 1:].find(cls.SINGLE_QUOTE)
                    if idx >= len(bytes_text) - 1:
                        fields.append(bytes_text[1:-1].strip())
                        bytes_text = numpy.string_("")
                        finished = True
                        break

                    if bytes_text[idx + 1] in cls.BLANK:
                        fields.append(bytes_text[1:idx].strip())
                        tmp_text = bytes_text[idx + 1:]
                        bytes_text = tmp_text.strip()
                        finished = True

            elif bytes_text[0] == cls.DOUBLE_QUOTE:
                idx = 0
                finished = False
                while not finished:
                    idx += 1 + bytes_text[idx + 1:].find(cls.DOUBLE_QUOTE)
                    if idx >= len(bytes_text) - 1:
                        fields.append(bytes_text[1:-1].strip())
                        bytes_text = numpy.string_("")
                        finished = True
                        break

                    if bytes_text[idx + 1] in cls.BLANK:
                        fields.append(bytes_text[1:idx].strip())
                        tmp_text = bytes_text[idx + 1:]
                        bytes_text = tmp_text.strip()
                        finished = True

            elif bytes_text[0] == cls.SEMICOLUMN:
                if bytes_text[1:].strip().find(cls.BINARY_MARKER) == 0:
                    idx = bytes_text[32:].find(cls.BINARY_MARKER)
                    if idx == -1:
                        idx = 0
                    else:
                        idx += 32 + len(cls.BINARY_MARKER)
                else:
                    idx = 0
                finished = False
                while not finished:
                    idx += 1 + bytes_text[idx + 1:].find(cls.SEMICOLUMN)
                    if bytes_text[idx - 1] in cls.EOL:
                        fields.append(bytes_text[1:idx - 1].strip())
                        tmp_text = bytes_text[idx + 1:]
                        bytes_text = tmp_text.strip()
                        finished = True
            else:
                res = bytes_text.split(None, 1)
                if len(res) == 2:
                    first, second = bytes_text.split(None, 1)
                    if cls.isAscii(first):
                        fields.append(first)
                        bytes_text = second.strip()
                        continue
                start_binary = bytes_text.find(cls.BINARY_MARKER)
                if start_binary > 0:
                    end_binary = bytes_text[start_binary + 1:].find(cls.BINARY_MARKER) + start_binary + 1 + len(cls.BINARY_MARKER)
                    fields.append(bytes_text[:end_binary])
                    bytes_text = bytes_text[end_binary:].strip()
                else:
                    fields.append(bytes_text)
                    bytes_text = numpy.string_("")
                    break
        return fields


    @classmethod
    def _analyseOneLoop(cls, fields, start_idx):
        """Processes one loop in the data extraction of the CIF file
        @param fields: list of all the words contained in the cif file
        @type fields: list
        @param start_idx: the starting index corresponding to the "loop_" key
        @type start_idx: integer
        @return: the list of loop dictionaries, the length of the data
            extracted from the fields and the list of all the keys of the loop.
        @rtype: tuple
        """
        loop = []
        keys = []
        i = start_idx + 1
        finished = False
        while not finished:
            if fields[i][0] == cls.UNDERSCORE:
                keys.append(fields[i])
                i += 1
            else:
                finished = True
        data = []
        while True:
            if i >= len(fields):
                break
            elif len(fields[i]) == 0:
                break
            elif fields[i][0] == cls.UNDERSCORE:
                break
            elif fields[i] in (cls.LOOP, cls.STOP, cls.GLOBAL, cls.DATA, cls.SAVE):
                break
            else:
                data.append(fields[i])
                i += 1
        k = 0

        if len(data) < len(keys):
            element = {}
            for j in keys:
                if k < len(data):
                    element[j] = data[k]
                else :
                    element[j] = self.QUESTIONMARK
                k += 1
            loop.append(element)

        else:
            for i in range(len(data) / len(keys)):
                element = {}
                for j in keys:
                    element[j] = data[k]
                    k += 1
                loop.append(element)
        return loop, 1 + len(keys) + len(data), keys






#############################################################################################
########     everything needed to  write a cif file #########################################
#############################################################################################

    def saveCIF(self, _strFilename="test.cif", linesep=os.linesep, binary=False):
        """Transforms the CIF object in string then write it into the given file
        @param _strFilename: the of the file to be written
        @param linesep: line separation used (to force compatibility with windows/unix)
        @param binary: Shall we write the data as binary (True only for imageCIF/CBF)
        @return: None
        """
        if binary:
            mode = "wb"
        else:
            mode = "w"
        try:
            fFile = open(_strFilename, mode)
        except IOError:
            logger.error("Error during the opening of file for write: %s" %
                                                            _strFilename)
            return
        fFile.write(self.tostring(_strFilename, linesep))
        try:
            fFile.close()
        except IOError:
            logger.error("Error during the closing of file for write: %s" % _strFilename)

    def tostring(self, _strFilename=None, linesep=os.linesep):
        """
        Converts a cif dictionnary to a string according to the CIF syntax

        @param _strFilename: the name of the filename to be appended in the header of the CIF file
        @type _strFilename: string
        @param linesep: default line separation: can be "\n" or "\r\n"
        @return: a string that corresponds to the content of the CIF-file.

        """
        lstStrCif = ["# " + i for i in __version__]
        if "_chemical_name_common" in self:
            t = self["_chemical_name_common"].split()[0]
        elif _strFilename is not None:
            t = os.path.splitext(os.path.split(str(_strFilename).strip())[1])[0]
        else:
            t = ""
        lstStrCif.append("data_%s" % (t))
        # first of all get all the keys :
        lKeys = list(self.keys())
        lKeys.sort()
        for key in lKeys[:]:
            if key in self._ordered:
                lKeys.remove(key)
        self._ordered += lKeys

        for sKey in self._ordered:
            if sKey == "loop_":
                continue
            if sKey not in self:
                self._ordered.remove(sKey)
                logger.debug("Skipping key %s from ordered list as no more present in dict")
                continue
            sValue = str(self[sKey])
            if sValue.find("\n") > -1:  # should add value  between ;;
                lLine = [sKey, ";", sValue, ";", ""]
            elif len(sValue.split()) > 1:  # should add value between ''
                sLine = "%s        '%s'" % (sKey, sValue)
                if len(sLine) > 80:
                    lLine = [str(sKey), sValue]
                else:
                    lLine = [sLine]
            else:
                sLine = "%s        %s" % (sKey, sValue)
                if len(sLine) > 80:
                    lLine = [str(sKey), sValue]
                else:
                    lLine = [sLine]
            lstStrCif += lLine
        if "loop_" in self:
            for loop in self["loop_"]:
                lstStrCif.append("loop_ ")
                lKeys = loop[0]
                llData = loop[1]
                lstStrCif += [" %s" % (sKey) for sKey in lKeys]
                for lData in llData:
                    sLine = " "
                    for key in lKeys:
                        sRawValue = lData[key]
                        if sRawValue.find("\n") > -1:  # should add value  between ;;
                            lstStrCif += [sLine, ";", str(sRawValue), ";"]
                            sLine = " "
                        else:
                            if len(sRawValue.split()) > 1:  # should add value between ''
                                value = "'%s'" % (sRawValue)
                            else:
                                value = str(sRawValue)
                            if len(sLine) + len(value) > 78:
                                lstStrCif += [sLine]
                                sLine = " " + value
                            else:
                                sLine += " " + value
                    lstStrCif.append(sLine)
                lstStrCif.append("")
        return linesep.join(lstStrCif)


    def exists(self, sKey):
        """
        Check if the key exists in the CIF and is non empty.
        @param sKey: CIF key
        @type sKey: string
        @param cif: CIF dictionary
        @return: True if the key exists in the CIF dictionary and is non empty
        @rtype: boolean
        """
        bExists = False
        if sKey in self:
            if len(self[sKey]) >= 1:
                if self[sKey][0] not in (self.QUESTIONMARK, numpy.string_(".")):
                    bExists = True
        return bExists

    def existsInLoop(self, sKey):
        """
        Check if the key exists in the CIF dictionary.
        @param sKey: CIF key
        @type sKey: string
        @param cif: CIF dictionary
        @return: True if the key exists in the CIF dictionary and is non empty
        @rtype: boolean
        """
        if not self.exists(self.LOOP):
            return False
        bExists = False
        if not bExists:
            for i in self[self.LOOP]:
                for j in i[0]:
                    if j == sKey:
                        bExists = True
        return bExists

    def loadCHIPLOT(self, _strFilename):
        """
        Load the powder diffraction CHIPLOT file and returns the
        pd_CIF dictionary in the object

        @param _strFilename: the name of the file to open
        @type  _strFilename: string
        @return: the CIF object corresponding to the powder diffraction
        @rtype: dictionary
        """
        if not os.path.isfile(_strFilename):
            errStr = "I cannot find the file %s" % _strFilename
            logger.error(errStr)
            raise IOError(errStr)
        lInFile = open(_strFilename, "r").readlines()
        self["_audit_creation_method"] = 'From 2-D detector using FIT2D and CIFfile'
        self["_pd_meas_scan_method"] = "fixed"
        self["_pd_spec_description"] = lInFile[0].strip()
        try:
            iLenData = int(lInFile[3])
        except ValueError:
            iLenData = None
        lOneLoop = []
        try:
            f2ThetaMin = float(lInFile[4].split()[0])
            last = ""
            for sLine in lInFile[-20:]:
                if sLine.strip() != "":
                    last = sLine.strip()
            f2ThetaMax = float(last.split()[0])
            limitsOK = True

        except (ValueError, IndexError):
            limitsOK = False
            f2ThetaMin = 180.0
            f2ThetaMax = 0
#        print "limitsOK:", limitsOK
        for sLine in lInFile[4:]:
            sCleaned = sLine.split("#")[0].strip()
            data = sCleaned.split()
            if len(data) == 2 :
                if not limitsOK:
                    f2Theta = float(data[0])
                    if f2Theta < f2ThetaMin :
                        f2ThetaMin = f2Theta
                    if f2Theta > f2ThetaMax :
                        f2ThetaMax = f2Theta
                lOneLoop.append({ "_pd_meas_intensity_total": data[1] })
        if not iLenData:
            iLenData = len(lOneLoop)
        assert (iLenData == len(lOneLoop))
        self[ "_pd_meas_2theta_range_inc" ] = "%.4f" % ((f2ThetaMax - f2ThetaMin) / (iLenData - 1))
        if self[ "_pd_meas_2theta_range_inc" ] < 0:
            self[ "_pd_meas_2theta_range_inc" ] = abs (self[ "_pd_meas_2theta_range_inc" ])
            tmp = f2ThetaMax
            f2ThetaMax = f2ThetaMin
            f2ThetaMin = tmp
        self[ "_pd_meas_2theta_range_max" ] = "%.4f" % f2ThetaMax
        self[ "_pd_meas_2theta_range_min" ] = "%.4f" % f2ThetaMin
        self[ "_pd_meas_number_of_points" ] = str(iLenData)
        self[self.LOOP] = [ [ ["_pd_meas_intensity_total" ], lOneLoop ] ]

    @staticmethod
    def LoopHasKey(loop, key):
        "Returns True if the key (string) exist in the array called loop"""
        try:
            loop.index(key)
            return True
        except ValueError:
            return False

cbfimage = CbfImage