pypy / lib_pypy / _csv.py

  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
"""CSV parsing and writing.

This module provides classes that assist in the reading and writing
of Comma Separated Value (CSV) files, and implements the interface
described by PEP 305.  Although many CSV files are simple to parse,
the format is not formally defined by a stable specification and
is subtle enough that parsing lines of a CSV file with something
like line.split(\",\") is bound to fail.  The module supports three
basic APIs: reading, writing, and registration of dialects.


DIALECT REGISTRATION:

Readers and writers support a dialect argument, which is a convenient
handle on a group of settings.  When the dialect argument is a string,
it identifies one of the dialects previously registered with the module.
If it is a class or instance, the attributes of the argument are used as
the settings for the reader or writer:

    class excel:
        delimiter = ','
        quotechar = '\"'
        escapechar = None
        doublequote = True
        skipinitialspace = False
        lineterminator = '\\r\\n'
        quoting = QUOTE_MINIMAL

SETTINGS:

    * quotechar - specifies a one-character string to use as the 
        quoting character.  It defaults to '\"'.
    * delimiter - specifies a one-character string to use as the 
        field separator.  It defaults to ','.
    * skipinitialspace - specifies how to interpret whitespace which
        immediately follows a delimiter.  It defaults to False, which
        means that whitespace immediately following a delimiter is part
        of the following field.
    * lineterminator -  specifies the character sequence which should 
        terminate rows.
    * quoting - controls when quotes should be generated by the writer.
        It can take on any of the following module constants:

        csv.QUOTE_MINIMAL means only when required, for example, when a
            field contains either the quotechar or the delimiter
        csv.QUOTE_ALL means that quotes are always placed around fields.
        csv.QUOTE_NONNUMERIC means that quotes are always placed around
            fields which do not parse as integers or floating point
            numbers.
        csv.QUOTE_NONE means that quotes are never placed around fields.
    * escapechar - specifies a one-character string used to escape 
        the delimiter when quoting is set to QUOTE_NONE.
    * doublequote - controls the handling of quotes inside fields.  When
        True, two consecutive quotes are interpreted as one during read,
        and when writing, each quote character embedded in the data is
        written as two quotes.
"""

__version__ = "1.0"

QUOTE_MINIMAL, QUOTE_ALL, QUOTE_NONNUMERIC, QUOTE_NONE = range(4)
_dialects = {}
_field_limit = 128 * 1024 # max parsed field size

class Error(Exception):
    pass

class Dialect(object):
    """CSV dialect

    The Dialect type records CSV parsing and generation options."""

    __slots__ = ["_delimiter", "_doublequote", "_escapechar",
                 "_lineterminator", "_quotechar", "_quoting",
                 "_skipinitialspace", "_strict"]

    def __new__(cls, dialect, **kwargs):

        for name in kwargs:
            if '_' + name not in Dialect.__slots__:
                raise TypeError("unexpected keyword argument '%s'" %
                                (name,))

        if dialect is not None:
            if isinstance(dialect, basestring):
                dialect = get_dialect(dialect)
        
            # Can we reuse this instance?
            if (isinstance(dialect, Dialect)
                and all(value is None for value in kwargs.itervalues())):
                return dialect

        self = object.__new__(cls)


        def set_char(x):
            if x is None:
                return None
            if isinstance(x, str) and len(x) <= 1:
                return x
            raise TypeError("%r must be a 1-character string" % (name,))
        def set_str(x):
            if isinstance(x, str):
                return x
            raise TypeError("%r must be a string" % (name,))
        def set_quoting(x):
            if x in range(4):
                return x
            raise TypeError("bad 'quoting' value")
        
        attributes = {"delimiter": (',', set_char),
                      "doublequote": (True, bool),
                      "escapechar": (None, set_char),
                      "lineterminator": ("\r\n", set_str),
                      "quotechar": ('"', set_char),
                      "quoting": (QUOTE_MINIMAL, set_quoting),
                      "skipinitialspace": (False, bool),
                      "strict": (False, bool),
                      }

        # Copy attributes
        notset = object()
        for name in Dialect.__slots__:
            name = name[1:]
            value = notset
            if name in kwargs:
                value = kwargs[name]
            elif dialect is not None:
                value = getattr(dialect, name, notset)

            # mapping by name: (default, converter)
            if value is notset:
                value = attributes[name][0]
                if name == 'quoting' and not self.quotechar:
                    value = QUOTE_NONE
            else:
                converter = attributes[name][1]
                if converter:
                    value = converter(value)

            setattr(self, '_' + name, value)

        if not self.delimiter:
            raise TypeError("delimiter must be set")

        if self.quoting != QUOTE_NONE and not self.quotechar:
            raise TypeError("quotechar must be set if quoting enabled")

        if not self.lineterminator:
            raise TypeError("lineterminator must be set")

        return self

    delimiter        = property(lambda self: self._delimiter)
    doublequote      = property(lambda self: self._doublequote)
    escapechar       = property(lambda self: self._escapechar)
    lineterminator   = property(lambda self: self._lineterminator)
    quotechar        = property(lambda self: self._quotechar)
    quoting          = property(lambda self: self._quoting)
    skipinitialspace = property(lambda self: self._skipinitialspace)
    strict           = property(lambda self: self._strict)


def _call_dialect(dialect_inst, kwargs):
    return Dialect(dialect_inst, **kwargs)

def register_dialect(name, dialect=None, **kwargs):
    """Create a mapping from a string name to a dialect class.
    dialect = csv.register_dialect(name, dialect)"""
    if not isinstance(name, basestring):
        raise TypeError("dialect name must be a string or unicode")

    dialect = _call_dialect(dialect, kwargs)
    _dialects[name] = dialect

def unregister_dialect(name):
    """Delete the name/dialect mapping associated with a string name.\n
    csv.unregister_dialect(name)"""
    try:
        del _dialects[name]
    except KeyError:
        raise Error("unknown dialect")

def get_dialect(name):
    """Return the dialect instance associated with name.
    dialect = csv.get_dialect(name)"""
    try:
        return _dialects[name]
    except KeyError:
        raise Error("unknown dialect")

def list_dialects():
    """Return a list of all know dialect names
    names = csv.list_dialects()"""
    return list(_dialects)

class Reader(object):
    """CSV reader

    Reader objects are responsible for reading and parsing tabular data
    in CSV format."""
    

    (START_RECORD, START_FIELD, ESCAPED_CHAR, IN_FIELD,
     IN_QUOTED_FIELD, ESCAPE_IN_QUOTED_FIELD, QUOTE_IN_QUOTED_FIELD,
     EAT_CRNL) = range(8)
    
    def __init__(self, iterator, dialect=None, **kwargs):
        self.dialect = _call_dialect(dialect, kwargs)
        self.input_iter = iter(iterator)
        self.line_num = 0

        self._parse_reset()

    def _parse_reset(self):
        self.field = ''
        self.fields = []
        self.state = self.START_RECORD
        self.numeric_field = False

    def __iter__(self):
        return self

    def next(self):
        self._parse_reset()
        while True:
            try:
                line = self.input_iter.next()
            except StopIteration:
                # End of input OR exception
                if len(self.field) > 0:
                    raise Error("newline inside string")
                raise

            self.line_num += 1

            if '\0' in line:
                raise Error("line contains NULL byte")
            pos = 0
            while pos < len(line):
                pos = self._parse_process_char(line, pos)
            self._parse_eol()

            if self.state == self.START_RECORD:
                break

        fields = self.fields
        self.fields = []
        return fields
            
    def _parse_process_char(self, line, pos):
        c = line[pos]
        if self.state == self.IN_FIELD:
            # in unquoted field
            pos2 = pos
            while True:
                if c in '\n\r':
                    # end of line - return [fields]
                    if pos2 > pos:
                        self._parse_add_char(line[pos:pos2])
                        pos = pos2
                    self._parse_save_field()
                    self.state = self.EAT_CRNL
                elif c == self.dialect.escapechar:
                    # possible escaped character
                    pos2 -= 1
                    self.state = self.ESCAPED_CHAR
                elif c == self.dialect.delimiter:
                    # save field - wait for new field
                    if pos2 > pos:
                        self._parse_add_char(line[pos:pos2])
                        pos = pos2
                    self._parse_save_field()
                    self.state = self.START_FIELD
                else:
                    # normal character - save in field
                    pos2 += 1
                    if pos2 < len(line):
                        c = line[pos2]
                        continue
                break
            if pos2 > pos:
                self._parse_add_char(line[pos:pos2])
                pos = pos2 - 1

        elif self.state == self.START_RECORD:
            if c in '\n\r':
                self.state = self.EAT_CRNL
            else:
                self.state = self.START_FIELD
                # restart process
                self._parse_process_char(line, pos)

        elif self.state == self.START_FIELD:
            if c in '\n\r':
                # save empty field - return [fields]
                self._parse_save_field()
                self.state = self.EAT_CRNL
            elif (c == self.dialect.quotechar
                  and self.dialect.quoting != QUOTE_NONE):
                # start quoted field
                self.state = self.IN_QUOTED_FIELD
            elif c == self.dialect.escapechar:
                # possible escaped character
                self.state = self.ESCAPED_CHAR
            elif c == ' ' and self.dialect.skipinitialspace:
                # ignore space at start of field
                pass
            elif c == self.dialect.delimiter:
                # save empty field
                self._parse_save_field()
            else:
                # begin new unquoted field
                if self.dialect.quoting == QUOTE_NONNUMERIC:
                    self.numeric_field = True
                self._parse_add_char(c)
                self.state = self.IN_FIELD
        
        elif self.state == self.ESCAPED_CHAR:
            self._parse_add_char(c)
            self.state = self.IN_FIELD
        
        elif self.state == self.IN_QUOTED_FIELD:
            if c == self.dialect.escapechar:
                # possible escape character
                self.state = self.ESCAPE_IN_QUOTED_FIELD
            elif (c == self.dialect.quotechar
                  and self.dialect.quoting != QUOTE_NONE):
                if self.dialect.doublequote:
                    # doublequote; " represented by ""
                    self.state = self.QUOTE_IN_QUOTED_FIELD
                else:
                    #end of quote part of field
                    self.state = self.IN_FIELD
            else:
                # normal character - save in field
                self._parse_add_char(c)
                
        elif self.state == self.ESCAPE_IN_QUOTED_FIELD:
            self._parse_add_char(c)
            self.state = self.IN_QUOTED_FIELD
                
        elif self.state == self.QUOTE_IN_QUOTED_FIELD:
            # doublequote - seen a quote in a quoted field
            if (c == self.dialect.quotechar
                and self.dialect.quoting != QUOTE_NONE):
                # save "" as "
                self._parse_add_char(c)
                self.state = self.IN_QUOTED_FIELD
            elif c == self.dialect.delimiter:
                # save field - wait for new field
                self._parse_save_field()
                self.state = self.START_FIELD
            elif c in '\r\n':
                # end of line - return [fields]
                self._parse_save_field()
                self.state = self.EAT_CRNL
            elif not self.dialect.strict:
                self._parse_add_char(c)
                self.state = self.IN_FIELD
            else:
                raise Error("'%c' expected after '%c'" %
                            (self.dialect.delimiter, self.dialect.quotechar))

        elif self.state == self.EAT_CRNL:
            if c in '\r\n':
                pass
            else:
                raise Error("new-line character seen in unquoted field - "
                            "do you need to open the file "
                            "in universal-newline mode?")

        else:
            raise RuntimeError("unknown state: %r" % (self.state,))

        return pos + 1

    def _parse_eol(self):
        if self.state == self.EAT_CRNL:
            self.state = self.START_RECORD
        elif self.state == self.START_RECORD:
            # empty line - return []
            pass
        elif self.state == self.IN_FIELD:
            # in unquoted field
            # end of line - return [fields]
            self._parse_save_field()
            self.state = self.START_RECORD
        elif self.state == self.START_FIELD:
            # save empty field - return [fields]
            self._parse_save_field()
            self.state = self.START_RECORD
        elif self.state == self.ESCAPED_CHAR:
            self._parse_add_char('\n')
            self.state = self.IN_FIELD
        elif self.state == self.IN_QUOTED_FIELD:
            pass
        elif self.state == self.ESCAPE_IN_QUOTED_FIELD:
            self._parse_add_char('\n')
            self.state = self.IN_QUOTED_FIELD
        elif self.state == self.QUOTE_IN_QUOTED_FIELD:
            # end of line - return [fields]
            self._parse_save_field()
            self.state = self.START_RECORD
        else:
            raise RuntimeError("unknown state: %r" % (self.state,))

    def _parse_save_field(self):
        field, self.field = self.field, ''
        if self.numeric_field:
            self.numeric_field = False
            field = float(field)
        self.fields.append(field)

    def _parse_add_char(self, c):
        if len(self.field) + len(c) > _field_limit:
            raise Error("field larget than field limit (%d)" % (_field_limit))
        self.field += c
        

class Writer(object):
    """CSV writer

    Writer objects are responsible for generating tabular data
    in CSV format from sequence input."""

    def __init__(self, file, dialect=None, **kwargs):
        if not (hasattr(file, 'write') and callable(file.write)):
            raise TypeError("argument 1 must have a 'write' method")
        self.writeline = file.write
        self.dialect = _call_dialect(dialect, kwargs)

    def _join_reset(self):
        self.rec = []
        self.num_fields = 0

    def _join_append(self, field, quoted, quote_empty):
        dialect = self.dialect
        # If this is not the first field we need a field separator
        if self.num_fields > 0:
            self.rec.append(dialect.delimiter)

        if dialect.quoting == QUOTE_NONE:
            need_escape = tuple(dialect.lineterminator) + (
                dialect.escapechar,  # escapechar always first
                dialect.delimiter, dialect.quotechar)
                
        else:
            for c in tuple(dialect.lineterminator) + (
                dialect.delimiter, dialect.escapechar):
                if c and c in field:
                    quoted = True

            need_escape = ()
            if dialect.quotechar in field:
                if dialect.doublequote:
                    field = field.replace(dialect.quotechar,
                                          dialect.quotechar * 2)
                    quoted = True
                else:
                    need_escape = (dialect.quotechar,)


        for c in need_escape:
            if c and c in field:
                if not dialect.escapechar:
                    raise Error("need to escape, but no escapechar set")
                field = field.replace(c, dialect.escapechar + c)

        # If field is empty check if it needs to be quoted
        if field == '' and quote_empty:
            if dialect.quoting == QUOTE_NONE:
                raise Error("single empty field record must be quoted")
            quoted = 1

        if quoted:
            field = dialect.quotechar + field + dialect.quotechar

        self.rec.append(field)
        self.num_fields += 1



    def writerow(self, row):
        dialect = self.dialect
        try:
            rowlen = len(row)
        except TypeError:
            raise Error("sequence expected")

        # join all fields in internal buffer
        self._join_reset()
        
        for field in row:
            quoted = False
            if dialect.quoting == QUOTE_NONNUMERIC:
                try:
                    float(field)
                except:
                    quoted = True
                # This changed since 2.5:
                # quoted = not isinstance(field, (int, long, float))
            elif dialect.quoting == QUOTE_ALL:
                quoted = True

            if field is None:
                self._join_append("", quoted, rowlen == 1)
            else:
                self._join_append(str(field), quoted, rowlen == 1)

        # add line terminator
        self.rec.append(dialect.lineterminator)

        self.writeline(''.join(self.rec))

    def writerows(self, rows):
        for row in rows:
            self.writerow(row)

def reader(*args, **kwargs):
    """
    csv_reader = reader(iterable [, dialect='excel']
                       [optional keyword args])
    for row in csv_reader:
        process(row)

    The "iterable" argument can be any object that returns a line
    of input for each iteration, such as a file object or a list.  The
    optional \"dialect\" parameter is discussed below.  The function
    also accepts optional keyword arguments which override settings
    provided by the dialect.

    The returned object is an iterator.  Each iteration returns a row
    of the CSV file (which can span multiple input lines)"""
    
    return Reader(*args, **kwargs)

def writer(*args, **kwargs):
    """
    csv_writer = csv.writer(fileobj [, dialect='excel']
                            [optional keyword args])
    for row in sequence:
        csv_writer.writerow(row)

    [or]

    csv_writer = csv.writer(fileobj [, dialect='excel']
                            [optional keyword args])
    csv_writer.writerows(rows)

    The \"fileobj\" argument can be any object that supports the file API."""
    return Writer(*args, **kwargs)


undefined = object()
def field_size_limit(limit=undefined):
    """Sets an upper limit on parsed fields.
    csv.field_size_limit([limit])

    Returns old limit. If limit is not given, no new limit is set and
    the old limit is returned"""

    global _field_limit
    old_limit = _field_limit
    
    if limit is not undefined:
        if not isinstance(limit, (int, long)):
            raise TypeError("int expected, got %s" %
                            (limit.__class__.__name__,))
        _field_limit = limit

    return old_limit
Tip: Filter by directory path e.g. /media app.js to search for public/media/app.js.
Tip: Use camelCasing e.g. ProjME to search for ProjectModifiedEvent.java.
Tip: Filter by extension type e.g. /repo .js to search for all .js files in the /repo directory.
Tip: Separate your search with spaces e.g. /ssh pom.xml to search for src/ssh/pom.xml.
Tip: Use ↑ and ↓ arrow keys to navigate and return to view the file.
Tip: You can also navigate files with Ctrl+j (next) and Ctrl+k (previous) and view the file with Ctrl+o.
Tip: You can also navigate files with Alt+j (next) and Alt+k (previous) and view the file with Alt+o.