Mercurial > cpython-lru_cache-weakref

annotate Lib/csv.py @ 47787:b32101c19bf8 legacy-trunk

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Grammar fixes
author Andrew M. Kuchling <amk@amk.ca>
date Fri, 20 Jun 2008 23:14:32 +0000
parents 85fbd1d265a2
children 47967690b585
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
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
7 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
8 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
9 field_size_limit, \
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
10 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
11 __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
12 from _csv import Dialect as _Dialect
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
13
28828
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
14 try:
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
15 from cStringIO import StringIO
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
16 except ImportError:
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
17 from StringIO import StringIO
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
18
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
19 __all__ = [ "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
20 "Error", "Dialect", "excel", "excel_tab", "reader", "writer",
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
21 "register_dialect", "get_dialect", "list_dialects", "Sniffer",
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
22 "unregister_dialect", "__version__", "DictReader", "DictWriter" ]
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
23
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
24 class Dialect:
34325
ee808e08dd6f add a couple missing docstrings
Skip Montanaro <skip@pobox.com>
parents: 30632
diff changeset
25 """Describe an Excel dialect.
ee808e08dd6f add a couple missing docstrings
Skip Montanaro <skip@pobox.com>
parents: 30632
diff changeset
26
ee808e08dd6f add a couple missing docstrings
Skip Montanaro <skip@pobox.com>
parents: 30632
diff changeset
27 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
28 delimiter, quotechar, escapechar, doublequote, skipinitialspace,
ee808e08dd6f add a couple missing docstrings
Skip Montanaro <skip@pobox.com>
parents: 30632
diff changeset
29 lineterminator, quoting.
ee808e08dd6f add a couple missing docstrings
Skip Montanaro <skip@pobox.com>
parents: 30632
diff changeset
30
ee808e08dd6f add a couple missing docstrings
Skip Montanaro <skip@pobox.com>
parents: 30632
diff changeset
31 """
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
32 _name = ""
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
33 _valid = False
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
34 # placeholders
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
35 delimiter = None
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
36 quotechar = None
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
37 escapechar = None
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
38 doublequote = None
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
39 skipinitialspace = None
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
40 lineterminator = None
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
41 quoting = None
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
42
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
43 def __init__(self):
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
44 if self.__class__ != Dialect:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
45 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
46 self._validate()
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
47
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
48 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
49 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
50 _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
51 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
52 # 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
53 raise Error(str(e))
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
54
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
55 class excel(Dialect):
34325
ee808e08dd6f add a couple missing docstrings
Skip Montanaro <skip@pobox.com>
parents: 30632
diff changeset
56 """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
57 delimiter = ','
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
58 quotechar = '"'
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
59 doublequote = True
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
60 skipinitialspace = False
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
61 lineterminator = '\r\n'
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
62 quoting = QUOTE_MINIMAL
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
63 register_dialect("excel", excel)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
64
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
65 class excel_tab(excel):
34325
ee808e08dd6f add a couple missing docstrings
Skip Montanaro <skip@pobox.com>
parents: 30632
diff changeset
66 """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
67 delimiter = '\t'
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
68 register_dialect("excel-tab", excel_tab)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
69
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
70
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
71 class DictReader:
30632
f9dfdcb897bb Make the fieldnames argument optional in the DictReader. If self.fieldnames
Skip Montanaro <skip@pobox.com>
parents: 30356
diff changeset
72 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
73 dialect="excel", *args, **kwds):
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
74 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
75 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
76 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
77 self.reader = reader(f, dialect, *args, **kwds)
45981
85fbd1d265a2 Issue #2432: give DictReader the dialect and line_num attributes
Georg Brandl <georg@python.org>
parents: 41145
diff changeset
78 self.dialect = dialect
85fbd1d265a2 Issue #2432: give DictReader the dialect and line_num attributes
Georg Brandl <georg@python.org>
parents: 41145
diff changeset
79 self.line_num = 0
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
80
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
81 def __iter__(self):
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
82 return self
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
83
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
84 def next(self):
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
85 row = self.reader.next()
30632
f9dfdcb897bb Make the fieldnames argument optional in the DictReader. If self.fieldnames
Skip Montanaro <skip@pobox.com>
parents: 30356
diff changeset
86 if self.fieldnames is None:
f9dfdcb897bb Make the fieldnames argument optional in the DictReader. If self.fieldnames
Skip Montanaro <skip@pobox.com>
parents: 30356
diff changeset
87 self.fieldnames = row
f9dfdcb897bb Make the fieldnames argument optional in the DictReader. If self.fieldnames
Skip Montanaro <skip@pobox.com>
parents: 30356
diff changeset
88 row = self.reader.next()
45981
85fbd1d265a2 Issue #2432: give DictReader the dialect and line_num attributes
Georg Brandl <georg@python.org>
parents: 41145
diff changeset
89 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
90
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
91 # 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
92 # 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
93 # values
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
94 while row == []:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
95 row = self.reader.next()
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
96 d = dict(zip(self.fieldnames, row))
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
97 lf = len(self.fieldnames)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
98 lr = len(row)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
99 if lf < lr:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
100 d[self.restkey] = row[lf:]
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
101 elif lf > lr:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
102 for key in self.fieldnames[lr:]:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
103 d[key] = self.restval
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
104 return d
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
105
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
106
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
107 class DictWriter:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
108 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
109 dialect="excel", *args, **kwds):
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
110 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
111 self.restval = restval # for writing short dicts
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
112 if extrasaction.lower() not in ("raise", "ignore"):
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
113 raise ValueError, \
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
114 ("extrasaction (%s) must be 'raise' or 'ignore'" %
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
115 extrasaction)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
116 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
117 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
118
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
119 def _dict_to_list(self, rowdict):
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
120 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
121 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
122 if wrong_fields:
bbaf6c935663 Patch #1635454: the csv.DictWriter class now includes the offending
Georg Brandl <georg@python.org>
parents: 36157
diff changeset
123 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
124 ", ".join(wrong_fields))
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
125 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
126
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
127 def writerow(self, rowdict):
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
128 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
129
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
130 def writerows(self, rowdicts):
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
131 rows = []
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
132 for rowdict in rowdicts:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
133 rows.append(self._dict_to_list(rowdict))
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
134 return self.writer.writerows(rows)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
135
29411
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
136 # 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
137 try:
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
138 complex
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
139 except NameError:
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
140 complex = float
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
141
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
142 class Sniffer:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
143 '''
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
144 "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
145 Returns a Dialect object.
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
146 '''
28828
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
147 def __init__(self):
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
148 # 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
149 self.preferred = [',', '\t', ';', ' ', ':']
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
150
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
151
29169
434ef174f478 * Correct Sniffer doc to correspond to the implementation.
Skip Montanaro <skip@pobox.com>
parents: 28828
diff changeset
152 def sniff(self, sample, delimiters=None):
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
153 """
28828
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
154 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
155 """
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
156
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
157 quotechar, delimiter, skipinitialspace = \
29169
434ef174f478 * Correct Sniffer doc to correspond to the implementation.
Skip Montanaro <skip@pobox.com>
parents: 28828
diff changeset
158 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
159 if not delimiter:
29169
434ef174f478 * Correct Sniffer doc to correspond to the implementation.
Skip Montanaro <skip@pobox.com>
parents: 28828
diff changeset
160 delimiter, skipinitialspace = self._guess_delimiter(sample,
434ef174f478 * Correct Sniffer doc to correspond to the implementation.
Skip Montanaro <skip@pobox.com>
parents: 28828
diff changeset
161 delimiters)
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
162
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
163 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
164 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
165
28828
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
166 class dialect(Dialect):
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
167 _name = "sniffed"
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
168 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
169 quoting = QUOTE_MINIMAL
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
170 # escapechar = ''
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
171 doublequote = False
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
172
28828
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
173 dialect.delimiter = delimiter
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
174 # _csv.reader won't accept a quotechar of ''
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
175 dialect.quotechar = quotechar or '"'
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
176 dialect.skipinitialspace = skipinitialspace
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
177
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
178 return dialect
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
179
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
180
29169
434ef174f478 * Correct Sniffer doc to correspond to the implementation.
Skip Montanaro <skip@pobox.com>
parents: 28828
diff changeset
181 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
182 """
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
183 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
184 (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
185 by the same character (the probable delimiter).
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
186 For example:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
187 ,'some text',
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
188 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
189 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
190 this way.
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
191 """
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
192
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
193 matches = []
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
194 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
195 '(?:^|\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
196 '(?P<delim>>[^\w\n"\'])(?P<space> ?)(?P<quote>["\']).*?(?P=quote)(?:$|\n)', # ,".*?"
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
197 '(?:^|\n)(?P<quote>["\']).*?(?P=quote)(?:$|\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
198 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
199 matches = regexp.findall(data)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
200 if matches:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
201 break
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 if not matches:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
204 return ('', None, 0) # (quotechar, delimiter, skipinitialspace)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
205
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
206 quotes = {}
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
207 delims = {}
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
208 spaces = 0
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
209 for m in matches:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
210 n = regexp.groupindex['quote'] - 1
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
211 key = m[n]
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
212 if key:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
213 quotes[key] = quotes.get(key, 0) + 1
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
214 try:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
215 n = regexp.groupindex['delim'] - 1
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
216 key = m[n]
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
217 except KeyError:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
218 continue
29169
434ef174f478 * Correct Sniffer doc to correspond to the implementation.
Skip Montanaro <skip@pobox.com>
parents: 28828
diff changeset
219 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
220 delims[key] = delims.get(key, 0) + 1
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
221 try:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
222 n = regexp.groupindex['space'] - 1
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
223 except KeyError:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
224 continue
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
225 if m[n]:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
226 spaces += 1
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
227
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
228 quotechar = reduce(lambda a, b, quotes = quotes:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
229 (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
230
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
231 if delims:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
232 delim = reduce(lambda a, b, delims = delims:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
233 (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
234 skipinitialspace = delims[delim] == spaces
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
235 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
236 delim = ''
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
237 else:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
238 # 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
239 delim = ''
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
240 skipinitialspace = 0
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
241
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
242 return (quotechar, delim, skipinitialspace)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
243
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
244
29169
434ef174f478 * Correct Sniffer doc to correspond to the implementation.
Skip Montanaro <skip@pobox.com>
parents: 28828
diff changeset
245 def _guess_delimiter(self, data, delimiters):
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
246 """
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
247 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
248 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
249 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
250 number.
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
251 1) build a table of the frequency of each character on every line.
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
252 2) build a table of freqencies of this frequency (meta-frequency?),
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
253 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
254 7 times in 2 rows'
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
255 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
256 frequency for that character
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
257 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
258 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
259 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
260 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
261 additional chunks as necessary.
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
262 """
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
263
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
264 data = filter(None, data.split('\n'))
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
265
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
266 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
267
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
268 # build frequency tables
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
269 chunkLength = min(10, len(data))
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
270 iteration = 0
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
271 charFrequency = {}
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
272 modes = {}
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
273 delims = {}
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
274 start, end = 0, min(chunkLength, len(data))
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
275 while start < len(data):
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
276 iteration += 1
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
277 for line in data[start:end]:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
278 for char in ascii:
28828
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
279 metaFrequency = charFrequency.get(char, {})
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
280 # 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
281 freq = line.count(char)
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
282 # value is the mode
28828
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
283 metaFrequency[freq] = metaFrequency.get(freq, 0) + 1
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
284 charFrequency[char] = metaFrequency
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
285
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
286 for char in charFrequency.keys():
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
287 items = charFrequency[char].items()
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
288 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
289 continue
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
290 # get the mode of the frequencies
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
291 if len(items) > 1:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
292 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
293 items)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
294 # 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
295 # other frequencies
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
296 items.remove(modes[char])
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
297 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
298 - 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
299 items)[1])
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
300 else:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
301 modes[char] = items[0]
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
302
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
303 # build a list of possible delimiters
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
304 modeList = modes.items()
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
305 total = float(chunkLength * iteration)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
306 # (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
307 consistency = 1.0
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
308 # minimum consistency threshold
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
309 threshold = 0.9
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
310 while len(delims) == 0 and consistency >= threshold:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
311 for k, v in modeList:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
312 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
313 if ((v[1]/total) >= consistency and
434ef174f478 * Correct Sniffer doc to correspond to the implementation.
Skip Montanaro <skip@pobox.com>
parents: 28828
diff changeset
314 (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
315 delims[k] = v
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
316 consistency -= 0.01
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 if len(delims) == 1:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
319 delim = delims.keys()[0]
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
320 skipinitialspace = (data[0].count(delim) ==
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
321 data[0].count("%c " % delim))
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
322 return (delim, skipinitialspace)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
323
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
324 # analyze another chunkLength lines
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
325 start = end
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
326 end += chunkLength
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
327
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
328 if not delims:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
329 return ('', 0)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
330
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
331 # 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
332 if len(delims) > 1:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
333 for d in self.preferred:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
334 if d in delims.keys():
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
335 skipinitialspace = (data[0].count(d) ==
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
336 data[0].count("%c " % d))
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
337 return (d, skipinitialspace)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
338
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
339 # 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
340 # 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
341 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
342 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
343 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
344
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
345 skipinitialspace = (data[0].count(delim) ==
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
346 data[0].count("%c " % delim))
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
347 return (delim, skipinitialspace)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
348
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
349
28828
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
350 def has_header(self, sample):
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
351 # 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
352 # 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
353 # 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
354 # 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
355 # 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
356 # 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
357 # 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
358 # 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
359
28828
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
360 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
361
28828
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
362 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
363
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
364 columns = len(header)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
365 columnTypes = {}
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
366 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
367
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
368 checked = 0
28828
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
369 for row in rdr:
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
370 # 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
371 if checked > 20:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
372 break
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
373 checked += 1
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
374
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
375 if len(row) != columns:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
376 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
377
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
378 for col in columnTypes.keys():
29411
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
379
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
380 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
381 try:
29411
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
382 thisType(row[col])
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
383 break
29420
f87fcd0870bf The multiple exception catch should be in a tuple.
Raymond Hettinger <python@rcn.com>
parents: 29411
diff changeset
384 except (ValueError, OverflowError):
29411
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
385 pass
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
386 else:
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
387 # fallback to length of string
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
388 thisType = len(row[col])
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
389
29411
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
390 # treat longs as ints
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
391 if thisType == long:
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
392 thisType = int
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
393
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
394 if thisType != columnTypes[col]:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
395 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
396 columnTypes[col] = thisType
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
397 else:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
398 # type is inconsistent, remove column from
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
399 # consideration
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
400 del columnTypes[col]
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
401
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
402 # 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
403 # on whether it's a header
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
404 hasHeader = 0
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
405 for col, colType in columnTypes.items():
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
406 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
407 if len(header[col]) != colType:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
408 hasHeader += 1
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
409 else:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
410 hasHeader -= 1
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
411 else: # attempt typecast
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
412 try:
29411
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
413 colType(header[col])
29422
cf8ae3b0dcdc One more multiple exception catch should be in a tuple.
Raymond Hettinger <python@rcn.com>
parents: 29420
diff changeset
414 except (ValueError, TypeError):
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
415 hasHeader += 1
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
416 else:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
417 hasHeader -= 1
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
418
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
419 return hasHeader > 0