Mercurial > cpython-lru_cache-weakref

annotate Lib/csv.py @ 80661:94de77bd0b4b 2.7

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Issue #16194: document imp.load_dynamic problems when read several extension modules from the same binary object file.
author Andrew Svetlov <andrew.svetlov@gmail.com>
date Thu, 29 Nov 2012 19:51:28 +0200
parents cd8d3c2d3bce
children 0e1d538d36dc
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
1
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
2 """
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
3 csv.py - read/write/investigate CSV files
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
4 """
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
5
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
6 import re
48206
30135b6e38fd Silence warnings in csv about using reduce() when run under -3 by using
Brett Cannon <bcannon@gmail.com>
parents: 48198
diff changeset
7 from functools import reduce
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
8 from _csv import Error, __version__, writer, reader, register_dialect, \
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
9 unregister_dialect, get_dialect, list_dialects, \
34406
b93845ce4454 Rename csv.set_field_limit to csv.field_size_limit (since it both sets and
Andrew McNamara <andrewm@object-craft.com.au>
parents: 34396
diff changeset
10 field_size_limit, \
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
11 QUOTE_MINIMAL, QUOTE_ALL, QUOTE_NONNUMERIC, QUOTE_NONE, \
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
12 __doc__
34393
b6ec1b3b9fce Replace python-coded validation of csv dialect with a call to the C
Andrew McNamara <andrewm@object-craft.com.au>
parents: 34340
diff changeset
13 from _csv import Dialect as _Dialect
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
14
28828
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
15 try:
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
16 from cStringIO import StringIO
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
17 except ImportError:
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
18 from StringIO import StringIO
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
19
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
20 __all__ = [ "QUOTE_MINIMAL", "QUOTE_ALL", "QUOTE_NONNUMERIC", "QUOTE_NONE",
48278
62c69d88e985 Update __all__ for cookielib, csv, os, and urllib2 for objects imported into
Brett Cannon <bcannon@gmail.com>
parents: 48206
diff changeset
21 "Error", "Dialect", "__doc__", "excel", "excel_tab",
62c69d88e985 Update __all__ for cookielib, csv, os, and urllib2 for objects imported into
Brett Cannon <bcannon@gmail.com>
parents: 48206
diff changeset
22 "field_size_limit", "reader", "writer",
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
23 "register_dialect", "get_dialect", "list_dialects", "Sniffer",
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
24 "unregister_dialect", "__version__", "DictReader", "DictWriter" ]
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
25
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
26 class Dialect:
34325
ee808e08dd6f add a couple missing docstrings
Skip Montanaro <skip@pobox.com>
parents: 30632
diff changeset
27 """Describe an Excel dialect.
ee808e08dd6f add a couple missing docstrings
Skip Montanaro <skip@pobox.com>
parents: 30632
diff changeset
28
ee808e08dd6f add a couple missing docstrings
Skip Montanaro <skip@pobox.com>
parents: 30632
diff changeset
29 This must be subclassed (see csv.excel). Valid attributes are:
ee808e08dd6f add a couple missing docstrings
Skip Montanaro <skip@pobox.com>
parents: 30632
diff changeset
30 delimiter, quotechar, escapechar, doublequote, skipinitialspace,
ee808e08dd6f add a couple missing docstrings
Skip Montanaro <skip@pobox.com>
parents: 30632
diff changeset
31 lineterminator, quoting.
ee808e08dd6f add a couple missing docstrings
Skip Montanaro <skip@pobox.com>
parents: 30632
diff changeset
32
ee808e08dd6f add a couple missing docstrings
Skip Montanaro <skip@pobox.com>
parents: 30632
diff changeset
33 """
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
34 _name = ""
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
35 _valid = False
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
36 # placeholders
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
37 delimiter = None
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
38 quotechar = None
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
39 escapechar = None
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
40 doublequote = None
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
41 skipinitialspace = None
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
42 lineterminator = None
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
43 quoting = None
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
44
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
45 def __init__(self):
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
46 if self.__class__ != Dialect:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
47 self._valid = True
34393
b6ec1b3b9fce Replace python-coded validation of csv dialect with a call to the C
Andrew McNamara <andrewm@object-craft.com.au>
parents: 34340
diff changeset
48 self._validate()
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
49
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
50 def _validate(self):
34393
b6ec1b3b9fce Replace python-coded validation of csv dialect with a call to the C
Andrew McNamara <andrewm@object-craft.com.au>
parents: 34340
diff changeset
51 try:
b6ec1b3b9fce Replace python-coded validation of csv dialect with a call to the C
Andrew McNamara <andrewm@object-craft.com.au>
parents: 34340
diff changeset
52 _Dialect(self)
b6ec1b3b9fce Replace python-coded validation of csv dialect with a call to the C
Andrew McNamara <andrewm@object-craft.com.au>
parents: 34340
diff changeset
53 except TypeError, e:
b6ec1b3b9fce Replace python-coded validation of csv dialect with a call to the C
Andrew McNamara <andrewm@object-craft.com.au>
parents: 34340
diff changeset
54 # We do this for compatibility with py2.3
b6ec1b3b9fce Replace python-coded validation of csv dialect with a call to the C
Andrew McNamara <andrewm@object-craft.com.au>
parents: 34340
diff changeset
55 raise Error(str(e))
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
56
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
57 class excel(Dialect):
34325
ee808e08dd6f add a couple missing docstrings
Skip Montanaro <skip@pobox.com>
parents: 30632
diff changeset
58 """Describe the usual properties of Excel-generated CSV files."""
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
59 delimiter = ','
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
60 quotechar = '"'
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
61 doublequote = True
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
62 skipinitialspace = False
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
63 lineterminator = '\r\n'
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
64 quoting = QUOTE_MINIMAL
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
65 register_dialect("excel", excel)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
66
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
67 class excel_tab(excel):
34325
ee808e08dd6f add a couple missing docstrings
Skip Montanaro <skip@pobox.com>
parents: 30632
diff changeset
68 """Describe the usual properties of Excel-generated TAB-delimited files."""
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
69 delimiter = '\t'
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
70 register_dialect("excel-tab", excel_tab)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
71
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
72
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
73 class DictReader:
30632
f9dfdcb897bb Make the fieldnames argument optional in the DictReader. If self.fieldnames
Skip Montanaro <skip@pobox.com>
parents: 30356
diff changeset
74 def __init__(self, f, fieldnames=None, restkey=None, restval=None,
30356
7504812fdb7e **kwds arg was missing from __init__ for Dict{Reader,Writer} classes.
Skip Montanaro <skip@pobox.com>
parents: 30292
diff changeset
75 dialect="excel", *args, **kwds):
48198
47967690b585 accept issue 3436
Skip Montanaro <skip@pobox.com>
parents: 45981
diff changeset
76 self._fieldnames = fieldnames # list of keys for the dict
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
77 self.restkey = restkey # key to catch long rows
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
78 self.restval = restval # default value for short rows
30356
7504812fdb7e **kwds arg was missing from __init__ for Dict{Reader,Writer} classes.
Skip Montanaro <skip@pobox.com>
parents: 30292
diff changeset
79 self.reader = reader(f, dialect, *args, **kwds)
45982
441527bfc79c Issue #2432: give DictReader the dialect and line_num attributes
Georg Brandl <georg@python.org>
parents: 36157
diff changeset
80 self.dialect = dialect
441527bfc79c Issue #2432: give DictReader the dialect and line_num attributes
Georg Brandl <georg@python.org>
parents: 36157
diff changeset
81 self.line_num = 0
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
82
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
83 def __iter__(self):
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
84 return self
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
85
48198
47967690b585 accept issue 3436
Skip Montanaro <skip@pobox.com>
parents: 45981
diff changeset
86 @property
47967690b585 accept issue 3436
Skip Montanaro <skip@pobox.com>
parents: 45981
diff changeset
87 def fieldnames(self):
47967690b585 accept issue 3436
Skip Montanaro <skip@pobox.com>
parents: 45981
diff changeset
88 if self._fieldnames is None:
47967690b585 accept issue 3436
Skip Montanaro <skip@pobox.com>
parents: 45981
diff changeset
89 try:
47967690b585 accept issue 3436
Skip Montanaro <skip@pobox.com>
parents: 45981
diff changeset
90 self._fieldnames = self.reader.next()
47967690b585 accept issue 3436
Skip Montanaro <skip@pobox.com>
parents: 45981
diff changeset
91 except StopIteration:
47967690b585 accept issue 3436
Skip Montanaro <skip@pobox.com>
parents: 45981
diff changeset
92 pass
47967690b585 accept issue 3436
Skip Montanaro <skip@pobox.com>
parents: 45981
diff changeset
93 self.line_num = self.reader.line_num
47967690b585 accept issue 3436
Skip Montanaro <skip@pobox.com>
parents: 45981
diff changeset
94 return self._fieldnames
47967690b585 accept issue 3436
Skip Montanaro <skip@pobox.com>
parents: 45981
diff changeset
95
47967690b585 accept issue 3436
Skip Montanaro <skip@pobox.com>
parents: 45981
diff changeset
96 @fieldnames.setter
47967690b585 accept issue 3436
Skip Montanaro <skip@pobox.com>
parents: 45981
diff changeset
97 def fieldnames(self, value):
47967690b585 accept issue 3436
Skip Montanaro <skip@pobox.com>
parents: 45981
diff changeset
98 self._fieldnames = value
47967690b585 accept issue 3436
Skip Montanaro <skip@pobox.com>
parents: 45981
diff changeset
99
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
100 def next(self):
48198
47967690b585 accept issue 3436
Skip Montanaro <skip@pobox.com>
parents: 45981
diff changeset
101 if self.line_num == 0:
47967690b585 accept issue 3436
Skip Montanaro <skip@pobox.com>
parents: 45981
diff changeset
102 # Used only for its side effect.
47967690b585 accept issue 3436
Skip Montanaro <skip@pobox.com>
parents: 45981
diff changeset
103 self.fieldnames
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
104 row = self.reader.next()
45982
441527bfc79c Issue #2432: give DictReader the dialect and line_num attributes
Georg Brandl <georg@python.org>
parents: 36157
diff changeset
105 self.line_num = self.reader.line_num
30632
f9dfdcb897bb Make the fieldnames argument optional in the DictReader. If self.fieldnames
Skip Montanaro <skip@pobox.com>
parents: 30356
diff changeset
106
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
107 # unlike the basic reader, we prefer not to return blanks,
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
108 # because we will typically wind up with a dict full of None
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
109 # values
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
110 while row == []:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
111 row = self.reader.next()
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
112 d = dict(zip(self.fieldnames, row))
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
113 lf = len(self.fieldnames)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
114 lr = len(row)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
115 if lf < lr:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
116 d[self.restkey] = row[lf:]
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
117 elif lf > lr:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
118 for key in self.fieldnames[lr:]:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
119 d[key] = self.restval
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
120 return d
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
121
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
122
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
123 class DictWriter:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
124 def __init__(self, f, fieldnames, restval="", extrasaction="raise",
30356
7504812fdb7e **kwds arg was missing from __init__ for Dict{Reader,Writer} classes.
Skip Montanaro <skip@pobox.com>
parents: 30292
diff changeset
125 dialect="excel", *args, **kwds):
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
126 self.fieldnames = fieldnames # list of keys for the dict
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
127 self.restval = restval # for writing short dicts
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
128 if extrasaction.lower() not in ("raise", "ignore"):
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
129 raise ValueError, \
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
130 ("extrasaction (%s) must be 'raise' or 'ignore'" %
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
131 extrasaction)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
132 self.extrasaction = extrasaction
30356
7504812fdb7e **kwds arg was missing from __init__ for Dict{Reader,Writer} classes.
Skip Montanaro <skip@pobox.com>
parents: 30292
diff changeset
133 self.writer = writer(f, dialect, *args, **kwds)
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
134
59078
dda5165a2374 Fix #1537721: add writeheader() method to csv.DictWriter.
Dirkjan Ochtman <dirkjan@ochtman.nl>
parents: 56253
diff changeset
135 def writeheader(self):
dda5165a2374 Fix #1537721: add writeheader() method to csv.DictWriter.
Dirkjan Ochtman <dirkjan@ochtman.nl>
parents: 56253
diff changeset
136 header = dict(zip(self.fieldnames, self.fieldnames))
dda5165a2374 Fix #1537721: add writeheader() method to csv.DictWriter.
Dirkjan Ochtman <dirkjan@ochtman.nl>
parents: 56253
diff changeset
137 self.writerow(header)
dda5165a2374 Fix #1537721: add writeheader() method to csv.DictWriter.
Dirkjan Ochtman <dirkjan@ochtman.nl>
parents: 56253
diff changeset
138
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
139 def _dict_to_list(self, rowdict):
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
140 if self.extrasaction == "raise":
41145
bbaf6c935663 Patch #1635454: the csv.DictWriter class now includes the offending
Georg Brandl <georg@python.org>
parents: 36157
diff changeset
141 wrong_fields = [k for k in rowdict if k not in self.fieldnames]
bbaf6c935663 Patch #1635454: the csv.DictWriter class now includes the offending
Georg Brandl <georg@python.org>
parents: 36157
diff changeset
142 if wrong_fields:
bbaf6c935663 Patch #1635454: the csv.DictWriter class now includes the offending
Georg Brandl <georg@python.org>
parents: 36157
diff changeset
143 raise ValueError("dict contains fields not in fieldnames: " +
bbaf6c935663 Patch #1635454: the csv.DictWriter class now includes the offending
Georg Brandl <georg@python.org>
parents: 36157
diff changeset
144 ", ".join(wrong_fields))
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
145 return [rowdict.get(key, self.restval) for key in self.fieldnames]
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
146
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
147 def writerow(self, rowdict):
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
148 return self.writer.writerow(self._dict_to_list(rowdict))
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
149
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
150 def writerows(self, rowdicts):
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
151 rows = []
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
152 for rowdict in rowdicts:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
153 rows.append(self._dict_to_list(rowdict))
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
154 return self.writer.writerows(rows)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
155
29411
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
156 # Guard Sniffer's type checking against builds that exclude complex()
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
157 try:
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
158 complex
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
159 except NameError:
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
160 complex = float
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
161
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
162 class Sniffer:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
163 '''
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
164 "Sniffs" the format of a CSV file (i.e. delimiter, quotechar)
28828
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
165 Returns a Dialect object.
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
166 '''
28828
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
167 def __init__(self):
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
168 # in case there is more than one possible delimiter
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
169 self.preferred = [',', '\t', ';', ' ', ':']
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
170
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
171
29169
434ef174f478 * Correct Sniffer doc to correspond to the implementation.
Skip Montanaro <skip@pobox.com>
parents: 28828
diff changeset
172 def sniff(self, sample, delimiters=None):
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
173 """
28828
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
174 Returns a dialect (or None) corresponding to the sample
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
175 """
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
176
56253
c76674c2d74d Patch from Thomas Barr so that csv.Sniffer will set doublequote property.
Skip Montanaro <skip@pobox.com>
parents: 48278
diff changeset
177 quotechar, doublequote, delimiter, skipinitialspace = \
29169
434ef174f478 * Correct Sniffer doc to correspond to the implementation.
Skip Montanaro <skip@pobox.com>
parents: 28828
diff changeset
178 self._guess_quote_and_delimiter(sample, delimiters)
36157
96eb2a5cfbef Fix a delimiter detection problem in sniffer. Sniffing "a|b|c\r\n" was
Skip Montanaro <skip@pobox.com>
parents: 36146
diff changeset
179 if not delimiter:
29169
434ef174f478 * Correct Sniffer doc to correspond to the implementation.
Skip Montanaro <skip@pobox.com>
parents: 28828
diff changeset
180 delimiter, skipinitialspace = self._guess_delimiter(sample,
434ef174f478 * Correct Sniffer doc to correspond to the implementation.
Skip Montanaro <skip@pobox.com>
parents: 28828
diff changeset
181 delimiters)
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
182
36157
96eb2a5cfbef Fix a delimiter detection problem in sniffer. Sniffing "a|b|c\r\n" was
Skip Montanaro <skip@pobox.com>
parents: 36146
diff changeset
183 if not delimiter:
96eb2a5cfbef Fix a delimiter detection problem in sniffer. Sniffing "a|b|c\r\n" was
Skip Montanaro <skip@pobox.com>
parents: 36146
diff changeset
184 raise Error, "Could not determine delimiter"
96eb2a5cfbef Fix a delimiter detection problem in sniffer. Sniffing "a|b|c\r\n" was
Skip Montanaro <skip@pobox.com>
parents: 36146
diff changeset
185
28828
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
186 class dialect(Dialect):
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
187 _name = "sniffed"
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
188 lineterminator = '\r\n'
28825
2fad548391de Attempt to deal with some obvious errors in the code. These were all
Fred Drake <fdrake@acm.org>
parents: 28804
diff changeset
189 quoting = QUOTE_MINIMAL
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
190 # escapechar = ''
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
191
56253
c76674c2d74d Patch from Thomas Barr so that csv.Sniffer will set doublequote property.
Skip Montanaro <skip@pobox.com>
parents: 48278
diff changeset
192 dialect.doublequote = doublequote
28828
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
193 dialect.delimiter = delimiter
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
194 # _csv.reader won't accept a quotechar of ''
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
195 dialect.quotechar = quotechar or '"'
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
196 dialect.skipinitialspace = skipinitialspace
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
197
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
198 return dialect
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
199
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
200
29169
434ef174f478 * Correct Sniffer doc to correspond to the implementation.
Skip Montanaro <skip@pobox.com>
parents: 28828
diff changeset
201 def _guess_quote_and_delimiter(self, data, delimiters):
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
202 """
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
203 Looks for text enclosed between two identical quotes
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
204 (the probable quotechar) which are preceded and followed
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
205 by the same character (the probable delimiter).
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
206 For example:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
207 ,'some text',
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
208 The quote with the most wins, same with the delimiter.
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
209 If there is no quotechar the delimiter can't be determined
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
210 this way.
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
211 """
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
212
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
213 matches = []
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
214 for restr in ('(?P<delim>[^\w\n"\'])(?P<space> ?)(?P<quote>["\']).*?(?P=quote)(?P=delim)', # ,".*?",
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
215 '(?:^|\n)(?P<quote>["\']).*?(?P=quote)(?P<delim>[^\w\n"\'])(?P<space> ?)', # ".*?",
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
216 '(?P<delim>>[^\w\n"\'])(?P<space> ?)(?P<quote>["\']).*?(?P=quote)(?:$|\n)', # ,".*?"
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
217 '(?:^|\n)(?P<quote>["\']).*?(?P=quote)(?:$|\n)'): # ".*?" (no delim, no space)
30292
79b1a9ec5223 use the long names for re compilation options; this makes it easier to
Fred Drake <fdrake@acm.org>
parents: 29422
diff changeset
218 regexp = re.compile(restr, re.DOTALL | re.MULTILINE)
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
219 matches = regexp.findall(data)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
220 if matches:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
221 break
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
222
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
223 if not matches:
56253
c76674c2d74d Patch from Thomas Barr so that csv.Sniffer will set doublequote property.
Skip Montanaro <skip@pobox.com>
parents: 48278
diff changeset
224 # (quotechar, doublequote, delimiter, skipinitialspace)
c76674c2d74d Patch from Thomas Barr so that csv.Sniffer will set doublequote property.
Skip Montanaro <skip@pobox.com>
parents: 48278
diff changeset
225 return ('', False, None, 0)
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
226 quotes = {}
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
227 delims = {}
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
228 spaces = 0
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
229 for m in matches:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
230 n = regexp.groupindex['quote'] - 1
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
231 key = m[n]
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
232 if key:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
233 quotes[key] = quotes.get(key, 0) + 1
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
234 try:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
235 n = regexp.groupindex['delim'] - 1
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
236 key = m[n]
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
237 except KeyError:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
238 continue
29169
434ef174f478 * Correct Sniffer doc to correspond to the implementation.
Skip Montanaro <skip@pobox.com>
parents: 28828
diff changeset
239 if key and (delimiters is None or key in delimiters):
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
240 delims[key] = delims.get(key, 0) + 1
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
241 try:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
242 n = regexp.groupindex['space'] - 1
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
243 except KeyError:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
244 continue
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
245 if m[n]:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
246 spaces += 1
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
247
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
248 quotechar = reduce(lambda a, b, quotes = quotes:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
249 (quotes[a] > quotes[b]) and a or b, quotes.keys())
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
250
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
251 if delims:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
252 delim = reduce(lambda a, b, delims = delims:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
253 (delims[a] > delims[b]) and a or b, delims.keys())
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
254 skipinitialspace = delims[delim] == spaces
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
255 if delim == '\n': # most likely a file with a single column
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
256 delim = ''
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
257 else:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
258 # there is *no* delimiter, it's a single column of quoted data
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
259 delim = ''
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
260 skipinitialspace = 0
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
261
56253
c76674c2d74d Patch from Thomas Barr so that csv.Sniffer will set doublequote property.
Skip Montanaro <skip@pobox.com>
parents: 48278
diff changeset
262 # if we see an extra quote between delimiters, we've got a
c76674c2d74d Patch from Thomas Barr so that csv.Sniffer will set doublequote property.
Skip Montanaro <skip@pobox.com>
parents: 48278
diff changeset
263 # double quoted format
c76674c2d74d Patch from Thomas Barr so that csv.Sniffer will set doublequote property.
Skip Montanaro <skip@pobox.com>
parents: 48278
diff changeset
264 dq_regexp = re.compile(r"((%(delim)s)|^)\W*%(quote)s[^%(delim)s\n]*%(quote)s[^%(delim)s\n]*%(quote)s\W*((%(delim)s)|$)" % \
c76674c2d74d Patch from Thomas Barr so that csv.Sniffer will set doublequote property.
Skip Montanaro <skip@pobox.com>
parents: 48278
diff changeset
265 {'delim':delim, 'quote':quotechar}, re.MULTILINE)
c76674c2d74d Patch from Thomas Barr so that csv.Sniffer will set doublequote property.
Skip Montanaro <skip@pobox.com>
parents: 48278
diff changeset
266
c76674c2d74d Patch from Thomas Barr so that csv.Sniffer will set doublequote property.
Skip Montanaro <skip@pobox.com>
parents: 48278
diff changeset
267
c76674c2d74d Patch from Thomas Barr so that csv.Sniffer will set doublequote property.
Skip Montanaro <skip@pobox.com>
parents: 48278
diff changeset
268
c76674c2d74d Patch from Thomas Barr so that csv.Sniffer will set doublequote property.
Skip Montanaro <skip@pobox.com>
parents: 48278
diff changeset
269 if dq_regexp.search(data):
c76674c2d74d Patch from Thomas Barr so that csv.Sniffer will set doublequote property.
Skip Montanaro <skip@pobox.com>
parents: 48278
diff changeset
270 doublequote = True
c76674c2d74d Patch from Thomas Barr so that csv.Sniffer will set doublequote property.
Skip Montanaro <skip@pobox.com>
parents: 48278
diff changeset
271 else:
c76674c2d74d Patch from Thomas Barr so that csv.Sniffer will set doublequote property.
Skip Montanaro <skip@pobox.com>
parents: 48278
diff changeset
272 doublequote = False
c76674c2d74d Patch from Thomas Barr so that csv.Sniffer will set doublequote property.
Skip Montanaro <skip@pobox.com>
parents: 48278
diff changeset
273
c76674c2d74d Patch from Thomas Barr so that csv.Sniffer will set doublequote property.
Skip Montanaro <skip@pobox.com>
parents: 48278
diff changeset
274 return (quotechar, doublequote, delim, skipinitialspace)
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
275
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
276
29169
434ef174f478 * Correct Sniffer doc to correspond to the implementation.
Skip Montanaro <skip@pobox.com>
parents: 28828
diff changeset
277 def _guess_delimiter(self, data, delimiters):
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
278 """
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
279 The delimiter /should/ occur the same number of times on
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
280 each row. However, due to malformed data, it may not. We don't want
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
281 an all or nothing approach, so we allow for small variations in this
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
282 number.
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
283 1) build a table of the frequency of each character on every line.
68588
cd8d3c2d3bce #11565: Fix several typos. Patch by Piotr Kasprzyk.
Ezio Melotti <ezio.melotti@gmail.com>
parents: 68256
diff changeset
284 2) build a table of frequencies of this frequency (meta-frequency?),
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
285 e.g. 'x occurred 5 times in 10 rows, 6 times in 1000 rows,
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
286 7 times in 2 rows'
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
287 3) use the mode of the meta-frequency to determine the /expected/
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
288 frequency for that character
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
289 4) find out how often the character actually meets that goal
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
290 5) the character that best meets its goal is the delimiter
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
291 For performance reasons, the data is evaluated in chunks, so it can
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
292 try and evaluate the smallest portion of the data possible, evaluating
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
293 additional chunks as necessary.
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
294 """
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
295
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
296 data = filter(None, data.split('\n'))
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
297
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
298 ascii = [chr(c) for c in range(127)] # 7-bit ASCII
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
299
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
300 # build frequency tables
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
301 chunkLength = min(10, len(data))
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
302 iteration = 0
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
303 charFrequency = {}
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
304 modes = {}
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
305 delims = {}
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
306 start, end = 0, min(chunkLength, len(data))
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
307 while start < len(data):
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
308 iteration += 1
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
309 for line in data[start:end]:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
310 for char in ascii:
28828
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
311 metaFrequency = charFrequency.get(char, {})
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
312 # must count even if frequency is 0
36146
22dbf5818b0b Fix for problem with Sniffer class. If your delimiter is whitespace and the
Skip Montanaro <skip@pobox.com>
parents: 34406
diff changeset
313 freq = line.count(char)
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
314 # value is the mode
28828
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
315 metaFrequency[freq] = metaFrequency.get(freq, 0) + 1
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
316 charFrequency[char] = metaFrequency
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
317
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
318 for char in charFrequency.keys():
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
319 items = charFrequency[char].items()
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
320 if len(items) == 1 and items[0][0] == 0:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
321 continue
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
322 # get the mode of the frequencies
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
323 if len(items) > 1:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
324 modes[char] = reduce(lambda a, b: a[1] > b[1] and a or b,
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
325 items)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
326 # adjust the mode - subtract the sum of all
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
327 # other frequencies
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
328 items.remove(modes[char])
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
329 modes[char] = (modes[char][0], modes[char][1]
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
330 - reduce(lambda a, b: (0, a[1] + b[1]),
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
331 items)[1])
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
332 else:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
333 modes[char] = items[0]
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
334
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
335 # build a list of possible delimiters
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
336 modeList = modes.items()
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
337 total = float(chunkLength * iteration)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
338 # (rows of consistent data) / (number of rows) = 100%
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
339 consistency = 1.0
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
340 # minimum consistency threshold
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
341 threshold = 0.9
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
342 while len(delims) == 0 and consistency >= threshold:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
343 for k, v in modeList:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
344 if v[0] > 0 and v[1] > 0:
29169
434ef174f478 * Correct Sniffer doc to correspond to the implementation.
Skip Montanaro <skip@pobox.com>
parents: 28828
diff changeset
345 if ((v[1]/total) >= consistency and
434ef174f478 * Correct Sniffer doc to correspond to the implementation.
Skip Montanaro <skip@pobox.com>
parents: 28828
diff changeset
346 (delimiters is None or k in delimiters)):
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
347 delims[k] = v
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
348 consistency -= 0.01
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
349
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
350 if len(delims) == 1:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
351 delim = delims.keys()[0]
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
352 skipinitialspace = (data[0].count(delim) ==
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
353 data[0].count("%c " % delim))
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
354 return (delim, skipinitialspace)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
355
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
356 # analyze another chunkLength lines
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
357 start = end
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
358 end += chunkLength
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
359
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
360 if not delims:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
361 return ('', 0)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
362
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
363 # if there's more than one, fall back to a 'preferred' list
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
364 if len(delims) > 1:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
365 for d in self.preferred:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
366 if d in delims.keys():
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
367 skipinitialspace = (data[0].count(d) ==
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
368 data[0].count("%c " % d))
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
369 return (d, skipinitialspace)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
370
36157
96eb2a5cfbef Fix a delimiter detection problem in sniffer. Sniffing "a|b|c\r\n" was
Skip Montanaro <skip@pobox.com>
parents: 36146
diff changeset
371 # nothing else indicates a preference, pick the character that
96eb2a5cfbef Fix a delimiter detection problem in sniffer. Sniffing "a|b|c\r\n" was
Skip Montanaro <skip@pobox.com>
parents: 36146
diff changeset
372 # dominates(?)
96eb2a5cfbef Fix a delimiter detection problem in sniffer. Sniffing "a|b|c\r\n" was
Skip Montanaro <skip@pobox.com>
parents: 36146
diff changeset
373 items = [(v,k) for (k,v) in delims.items()]
96eb2a5cfbef Fix a delimiter detection problem in sniffer. Sniffing "a|b|c\r\n" was
Skip Montanaro <skip@pobox.com>
parents: 36146
diff changeset
374 items.sort()
96eb2a5cfbef Fix a delimiter detection problem in sniffer. Sniffing "a|b|c\r\n" was
Skip Montanaro <skip@pobox.com>
parents: 36146
diff changeset
375 delim = items[-1][1]
96eb2a5cfbef Fix a delimiter detection problem in sniffer. Sniffing "a|b|c\r\n" was
Skip Montanaro <skip@pobox.com>
parents: 36146
diff changeset
376
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
377 skipinitialspace = (data[0].count(delim) ==
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
378 data[0].count("%c " % delim))
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
379 return (delim, skipinitialspace)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
380
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
381
28828
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
382 def has_header(self, sample):
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
383 # Creates a dictionary of types of data in each column. If any
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
384 # column is of a single type (say, integers), *except* for the first
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
385 # row, then the first row is presumed to be labels. If the type
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
386 # can't be determined, it is assumed to be a string in which case
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
387 # the length of the string is the determining factor: if all of the
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
388 # rows except for the first are the same length, it's a header.
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
389 # Finally, a 'vote' is taken at the end for each column, adding or
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
390 # subtracting from the likelihood of the first row being a header.
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
391
28828
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
392 rdr = reader(StringIO(sample), self.sniff(sample))
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
393
28828
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
394 header = rdr.next() # assume first row is header
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
395
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
396 columns = len(header)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
397 columnTypes = {}
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
398 for i in range(columns): columnTypes[i] = None
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
399
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
400 checked = 0
28828
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
401 for row in rdr:
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
402 # arbitrary number of rows to check, to keep it sane
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
403 if checked > 20:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
404 break
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
405 checked += 1
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
406
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
407 if len(row) != columns:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
408 continue # skip rows that have irregular number of columns
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
409
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
410 for col in columnTypes.keys():
29411
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
411
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
412 for thisType in [int, long, float, complex]:
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
413 try:
29411
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
414 thisType(row[col])
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
415 break
29420
f87fcd0870bf The multiple exception catch should be in a tuple.
Raymond Hettinger <python@rcn.com>
parents: 29411
diff changeset
416 except (ValueError, OverflowError):
29411
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
417 pass
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
418 else:
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
419 # fallback to length of string
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
420 thisType = len(row[col])
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
421
29411
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
422 # treat longs as ints
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
423 if thisType == long:
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
424 thisType = int
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
425
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
426 if thisType != columnTypes[col]:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
427 if columnTypes[col] is None: # add new column type
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
428 columnTypes[col] = thisType
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
429 else:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
430 # type is inconsistent, remove column from
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
431 # consideration
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
432 del columnTypes[col]
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
433
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
434 # finally, compare results against first row and "vote"
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
435 # on whether it's a header
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
436 hasHeader = 0
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
437 for col, colType in columnTypes.items():
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
438 if type(colType) == type(0): # it's a length
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
439 if len(header[col]) != colType:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
440 hasHeader += 1
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
441 else:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
442 hasHeader -= 1
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
443 else: # attempt typecast
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
444 try:
29411
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
445 colType(header[col])
29422
cf8ae3b0dcdc One more multiple exception catch should be in a tuple.
Raymond Hettinger <python@rcn.com>
parents: 29420
diff changeset
446 except (ValueError, TypeError):
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
447 hasHeader += 1
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
448 else:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
449 hasHeader -= 1
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
450
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
451 return hasHeader > 0