Mercurial > cpython-lru_cache-weakref

annotate Lib/csv.py @ 48416:fb02fedfe647

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Merged revisions 64677 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ........ r64677 | brett.cannon | 2008-07-02 14:52:42 -0700 (Wed, 02 Jul 2008) | 2 lines Revert r64673 and instead just change the file encoding. ........
author Brett Cannon <bcannon@gmail.com>
date Wed, 02 Jul 2008 22:06:12 +0000
parents 85d4671565c8
children 1a11717a154b
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
41760
1a9cd76364e3 Change some uses of cStringIO.StringIO to io.StringIO.
Guido van Rossum <guido@python.org>
parents: 41554
diff changeset
14 from io import StringIO
28828
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
15
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
16 __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
17 "Error", "Dialect", "excel", "excel_tab", "reader", "writer",
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
18 "register_dialect", "get_dialect", "list_dialects", "Sniffer",
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
19 "unregister_dialect", "__version__", "DictReader", "DictWriter" ]
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
20
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
21 class Dialect:
34325
ee808e08dd6f add a couple missing docstrings
Skip Montanaro <skip@pobox.com>
parents: 30632
diff changeset
22 """Describe an Excel dialect.
ee808e08dd6f add a couple missing docstrings
Skip Montanaro <skip@pobox.com>
parents: 30632
diff changeset
23
ee808e08dd6f add a couple missing docstrings
Skip Montanaro <skip@pobox.com>
parents: 30632
diff changeset
24 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
25 delimiter, quotechar, escapechar, doublequote, skipinitialspace,
ee808e08dd6f add a couple missing docstrings
Skip Montanaro <skip@pobox.com>
parents: 30632
diff changeset
26 lineterminator, quoting.
ee808e08dd6f add a couple missing docstrings
Skip Montanaro <skip@pobox.com>
parents: 30632
diff changeset
27
ee808e08dd6f add a couple missing docstrings
Skip Montanaro <skip@pobox.com>
parents: 30632
diff changeset
28 """
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
29 _name = ""
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
30 _valid = False
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
31 # placeholders
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
32 delimiter = None
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
33 quotechar = None
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
34 escapechar = None
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
35 doublequote = None
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
36 skipinitialspace = None
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
37 lineterminator = None
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
38 quoting = None
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
39
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
40 def __init__(self):
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
41 if self.__class__ != Dialect:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
42 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
43 self._validate()
28804
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 _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
46 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
47 _Dialect(self)
40587
6b18a095c2e7 SF patch 1631942 by Collin Winter:
Guido van Rossum <guido@python.org>
parents: 39627
diff changeset
48 except TypeError as e:
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 # 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
50 raise Error(str(e))
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
51
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
52 class excel(Dialect):
34325
ee808e08dd6f add a couple missing docstrings
Skip Montanaro <skip@pobox.com>
parents: 30632
diff changeset
53 """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
54 delimiter = ','
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
55 quotechar = '"'
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
56 doublequote = True
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
57 skipinitialspace = False
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
58 lineterminator = '\r\n'
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
59 quoting = QUOTE_MINIMAL
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
60 register_dialect("excel", excel)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
61
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
62 class excel_tab(excel):
34325
ee808e08dd6f add a couple missing docstrings
Skip Montanaro <skip@pobox.com>
parents: 30632
diff changeset
63 """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
64 delimiter = '\t'
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
65 register_dialect("excel-tab", excel_tab)
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
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
68 class DictReader:
30632
f9dfdcb897bb Make the fieldnames argument optional in the DictReader. If self.fieldnames
Skip Montanaro <skip@pobox.com>
parents: 30356
diff changeset
69 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
70 dialect="excel", *args, **kwds):
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
71 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
72 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
73 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
74 self.reader = reader(f, dialect, *args, **kwds)
45996
376b5cb8a014 Merged revisions 61687-61688,61696,61700,61704-61705,61707-61709,61711-61712,61714-61716,61718-61722 via svnmerge from
Christian Heimes <christian@cheimes.de>
parents: 43020
diff changeset
75 self.dialect = dialect
376b5cb8a014 Merged revisions 61687-61688,61696,61700,61704-61705,61707-61709,61711-61712,61714-61716,61718-61722 via svnmerge from
Christian Heimes <christian@cheimes.de>
parents: 43020
diff changeset
76 self.line_num = 0
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
77
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
78 def __iter__(self):
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
79 return self
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
80
41501
0c5019afc55b PEP 3114: rename .next() to .__next__() and add next() builtin.
Georg Brandl <georg@python.org>
parents: 40809
diff changeset
81 def __next__(self):
0c5019afc55b PEP 3114: rename .next() to .__next__() and add next() builtin.
Georg Brandl <georg@python.org>
parents: 40809
diff changeset
82 row = next(self.reader)
30632
f9dfdcb897bb Make the fieldnames argument optional in the DictReader. If self.fieldnames
Skip Montanaro <skip@pobox.com>
parents: 30356
diff changeset
83 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
84 self.fieldnames = row
41501
0c5019afc55b PEP 3114: rename .next() to .__next__() and add next() builtin.
Georg Brandl <georg@python.org>
parents: 40809
diff changeset
85 row = next(self.reader)
45996
376b5cb8a014 Merged revisions 61687-61688,61696,61700,61704-61705,61707-61709,61711-61712,61714-61716,61718-61722 via svnmerge from
Christian Heimes <christian@cheimes.de>
parents: 43020
diff changeset
86 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
87
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
88 # 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
89 # 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
90 # values
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
91 while row == []:
41501
0c5019afc55b PEP 3114: rename .next() to .__next__() and add next() builtin.
Georg Brandl <georg@python.org>
parents: 40809
diff changeset
92 row = next(self.reader)
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
93 d = dict(zip(self.fieldnames, row))
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
94 lf = len(self.fieldnames)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
95 lr = len(row)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
96 if lf < lr:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
97 d[self.restkey] = row[lf:]
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
98 elif lf > lr:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
99 for key in self.fieldnames[lr:]:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
100 d[key] = self.restval
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
101 return d
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
102
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
103
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
104 class DictWriter:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
105 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
106 dialect="excel", *args, **kwds):
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
107 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
108 self.restval = restval # for writing short dicts
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
109 if extrasaction.lower() not in ("raise", "ignore"):
43020
907a45df1295 Raise statement normalization in Lib/.
Collin Winter <collinw@gmail.com>
parents: 42142
diff changeset
110 raise ValueError("extrasaction (%s) must be 'raise' or 'ignore'"
907a45df1295 Raise statement normalization in Lib/.
Collin Winter <collinw@gmail.com>
parents: 42142
diff changeset
111 % extrasaction)
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
112 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
113 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
114
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
115 def _dict_to_list(self, rowdict):
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
116 if self.extrasaction == "raise":
41554
06145fbc7ab9 Merged revisions 53952-54987 via svnmerge from
Guido van Rossum <guido@python.org>
parents: 41501
diff changeset
117 wrong_fields = [k for k in rowdict if k not in self.fieldnames]
06145fbc7ab9 Merged revisions 53952-54987 via svnmerge from
Guido van Rossum <guido@python.org>
parents: 41501
diff changeset
118 if wrong_fields:
43020
907a45df1295 Raise statement normalization in Lib/.
Collin Winter <collinw@gmail.com>
parents: 42142
diff changeset
119 raise ValueError("dict contains fields not in fieldnames: "
907a45df1295 Raise statement normalization in Lib/.
Collin Winter <collinw@gmail.com>
parents: 42142
diff changeset
120 + ", ".join(wrong_fields))
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
121 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
122
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
123 def writerow(self, rowdict):
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
124 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
125
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
126 def writerows(self, rowdicts):
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
127 rows = []
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
128 for rowdict in rowdicts:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
129 rows.append(self._dict_to_list(rowdict))
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
130 return self.writer.writerows(rows)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
131
29411
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
132 # 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
133 try:
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
134 complex
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
135 except NameError:
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
136 complex = float
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
137
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
138 class Sniffer:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
139 '''
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
140 "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
141 Returns a Dialect object.
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
142 '''
28828
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
143 def __init__(self):
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
144 # 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
145 self.preferred = [',', '\t', ';', ' ', ':']
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
29169
434ef174f478 * Correct Sniffer doc to correspond to the implementation.
Skip Montanaro <skip@pobox.com>
parents: 28828
diff changeset
148 def sniff(self, sample, delimiters=None):
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
149 """
28828
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
150 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
151 """
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
152
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
153 quotechar, delimiter, skipinitialspace = \
29169
434ef174f478 * Correct Sniffer doc to correspond to the implementation.
Skip Montanaro <skip@pobox.com>
parents: 28828
diff changeset
154 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
155 if not delimiter:
29169
434ef174f478 * Correct Sniffer doc to correspond to the implementation.
Skip Montanaro <skip@pobox.com>
parents: 28828
diff changeset
156 delimiter, skipinitialspace = self._guess_delimiter(sample,
434ef174f478 * Correct Sniffer doc to correspond to the implementation.
Skip Montanaro <skip@pobox.com>
parents: 28828
diff changeset
157 delimiters)
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
158
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:
43020
907a45df1295 Raise statement normalization in Lib/.
Collin Winter <collinw@gmail.com>
parents: 42142
diff changeset
160 raise Error("Could not determine delimiter")
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
161
28828
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
162 class dialect(Dialect):
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
163 _name = "sniffed"
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
164 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
165 quoting = QUOTE_MINIMAL
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
166 # escapechar = ''
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
167 doublequote = False
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
168
28828
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
169 dialect.delimiter = delimiter
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
170 # _csv.reader won't accept a quotechar of ''
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
171 dialect.quotechar = quotechar or '"'
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
172 dialect.skipinitialspace = skipinitialspace
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
173
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
174 return dialect
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
29169
434ef174f478 * Correct Sniffer doc to correspond to the implementation.
Skip Montanaro <skip@pobox.com>
parents: 28828
diff changeset
177 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
178 """
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
179 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
180 (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
181 by the same character (the probable delimiter).
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
182 For example:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
183 ,'some text',
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
184 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
185 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
186 this way.
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
187 """
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
188
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
189 matches = []
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
190 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
191 '(?:^|\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
192 '(?P<delim>>[^\w\n"\'])(?P<space> ?)(?P<quote>["\']).*?(?P=quote)(?:$|\n)', # ,".*?"
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
193 '(?:^|\n)(?P<quote>["\']).*?(?P=quote)(?:$|\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
194 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
195 matches = regexp.findall(data)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
196 if matches:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
197 break
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
198
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
199 if not matches:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
200 return ('', None, 0) # (quotechar, delimiter, skipinitialspace)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
201
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
202 quotes = {}
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
203 delims = {}
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
204 spaces = 0
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
205 for m in matches:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
206 n = regexp.groupindex['quote'] - 1
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
207 key = m[n]
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
208 if key:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
209 quotes[key] = quotes.get(key, 0) + 1
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
210 try:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
211 n = regexp.groupindex['delim'] - 1
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
212 key = m[n]
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
213 except KeyError:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
214 continue
29169
434ef174f478 * Correct Sniffer doc to correspond to the implementation.
Skip Montanaro <skip@pobox.com>
parents: 28828
diff changeset
215 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
216 delims[key] = delims.get(key, 0) + 1
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
217 try:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
218 n = regexp.groupindex['space'] - 1
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
219 except KeyError:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
220 continue
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
221 if m[n]:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
222 spaces += 1
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
223
39627
e86c0b29b4a2 Kill reduce(). A coproduction of John Reese, Jacques Frechet, and Alex M.
Guido van Rossum <guido@python.org>
parents: 36157
diff changeset
224 quotechar = max(quotes, key=quotes.get)
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
225
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
226 if delims:
39627
e86c0b29b4a2 Kill reduce(). A coproduction of John Reese, Jacques Frechet, and Alex M.
Guido van Rossum <guido@python.org>
parents: 36157
diff changeset
227 delim = max(delims, key=delims.get)
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
228 skipinitialspace = delims[delim] == spaces
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
229 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
230 delim = ''
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
231 else:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
232 # 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
233 delim = ''
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
234 skipinitialspace = 0
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
235
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
236 return (quotechar, delim, skipinitialspace)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
237
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
238
29169
434ef174f478 * Correct Sniffer doc to correspond to the implementation.
Skip Montanaro <skip@pobox.com>
parents: 28828
diff changeset
239 def _guess_delimiter(self, data, delimiters):
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
240 """
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
241 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
242 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
243 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
244 number.
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
245 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
246 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
247 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
248 7 times in 2 rows'
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
249 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
250 frequency for that character
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
251 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
252 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
253 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
254 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
255 additional chunks as necessary.
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
256 """
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
257
42142
a53e48be6df9 Merged revisions 56125-56153 via svnmerge from
Guido van Rossum <guido@python.org>
parents: 41760
diff changeset
258 data = list(filter(None, data.split('\n')))
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
259
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
260 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
261
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
262 # build frequency tables
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
263 chunkLength = min(10, len(data))
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
264 iteration = 0
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
265 charFrequency = {}
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
266 modes = {}
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
267 delims = {}
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
268 start, end = 0, min(chunkLength, len(data))
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
269 while start < len(data):
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
270 iteration += 1
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
271 for line in data[start:end]:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
272 for char in ascii:
28828
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
273 metaFrequency = charFrequency.get(char, {})
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
274 # 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
275 freq = line.count(char)
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
276 # value is the mode
28828
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
277 metaFrequency[freq] = metaFrequency.get(freq, 0) + 1
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
278 charFrequency[char] = metaFrequency
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
279
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
280 for char in charFrequency.keys():
40809
f340cb045bf9 - PEP 3106: dict.iterkeys(), .iteritems(), .itervalues() are now gone;
Guido van Rossum <guido@python.org>
parents: 40644
diff changeset
281 items = list(charFrequency[char].items())
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
282 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
283 continue
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
284 # get the mode of the frequencies
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
285 if len(items) > 1:
39627
e86c0b29b4a2 Kill reduce(). A coproduction of John Reese, Jacques Frechet, and Alex M.
Guido van Rossum <guido@python.org>
parents: 36157
diff changeset
286 modes[char] = max(items, key=lambda x: x[1])
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
287 # 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
288 # other frequencies
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
289 items.remove(modes[char])
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
290 modes[char] = (modes[char][0], modes[char][1]
39627
e86c0b29b4a2 Kill reduce(). A coproduction of John Reese, Jacques Frechet, and Alex M.
Guido van Rossum <guido@python.org>
parents: 36157
diff changeset
291 - sum(item[1] for item in items))
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
292 else:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
293 modes[char] = items[0]
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 # build a list of possible delimiters
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
296 modeList = modes.items()
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
297 total = float(chunkLength * iteration)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
298 # (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
299 consistency = 1.0
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
300 # minimum consistency threshold
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
301 threshold = 0.9
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
302 while len(delims) == 0 and consistency >= threshold:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
303 for k, v in modeList:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
304 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
305 if ((v[1]/total) >= consistency and
434ef174f478 * Correct Sniffer doc to correspond to the implementation.
Skip Montanaro <skip@pobox.com>
parents: 28828
diff changeset
306 (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
307 delims[k] = v
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
308 consistency -= 0.01
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
309
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
310 if len(delims) == 1:
40809
f340cb045bf9 - PEP 3106: dict.iterkeys(), .iteritems(), .itervalues() are now gone;
Guido van Rossum <guido@python.org>
parents: 40644
diff changeset
311 delim = list(delims.keys())[0]
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
312 skipinitialspace = (data[0].count(delim) ==
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
313 data[0].count("%c " % delim))
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
314 return (delim, skipinitialspace)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
315
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
316 # analyze another chunkLength lines
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
317 start = end
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
318 end += chunkLength
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
319
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
320 if not delims:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
321 return ('', 0)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
322
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
323 # 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
324 if len(delims) > 1:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
325 for d in self.preferred:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
326 if d in delims.keys():
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
327 skipinitialspace = (data[0].count(d) ==
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
328 data[0].count("%c " % d))
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
329 return (d, skipinitialspace)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
330
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
331 # 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
332 # 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
333 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
334 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
335 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
336
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
337 skipinitialspace = (data[0].count(delim) ==
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
338 data[0].count("%c " % delim))
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
339 return (delim, skipinitialspace)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
340
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
341
28828
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
342 def has_header(self, sample):
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
343 # 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
344 # 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
345 # 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
346 # 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
347 # 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
348 # 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
349 # 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
350 # 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
351
28828
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
352 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
353
41501
0c5019afc55b PEP 3114: rename .next() to .__next__() and add next() builtin.
Georg Brandl <georg@python.org>
parents: 40809
diff changeset
354 header = next(rdr) # assume first row is header
28804
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 columns = len(header)
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
357 columnTypes = {}
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
358 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
359
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
360 checked = 0
28828
b37af21b77be rework Sniffer api significantly
Skip Montanaro <skip@pobox.com>
parents: 28825
diff changeset
361 for row in rdr:
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
362 # 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
363 if checked > 20:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
364 break
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
365 checked += 1
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
366
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
367 if len(row) != columns:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
368 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
369
40809
f340cb045bf9 - PEP 3106: dict.iterkeys(), .iteritems(), .itervalues() are now gone;
Guido van Rossum <guido@python.org>
parents: 40644
diff changeset
370 for col in list(columnTypes.keys()):
29411
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
371
46548
85d4671565c8 Obvious simplification, now that "long" has disappeared.
Amaury Forgeot d'Arc <amauryfa@gmail.com>
parents: 45996
diff changeset
372 for thisType in [int, float, complex]:
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
373 try:
29411
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
374 thisType(row[col])
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
375 break
29420
f87fcd0870bf The multiple exception catch should be in a tuple.
Raymond Hettinger <python@rcn.com>
parents: 29411
diff changeset
376 except (ValueError, OverflowError):
29411
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
377 pass
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
378 else:
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
379 # fallback to length of string
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
380 thisType = len(row[col])
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
381
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
382 if thisType != columnTypes[col]:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
383 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
384 columnTypes[col] = thisType
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
385 else:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
386 # type is inconsistent, remove column from
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
387 # consideration
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
388 del columnTypes[col]
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
389
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
390 # 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
391 # on whether it's a header
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
392 hasHeader = 0
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
393 for col, colType in columnTypes.items():
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
394 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
395 if len(header[col]) != colType:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
396 hasHeader += 1
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 hasHeader -= 1
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
399 else: # attempt typecast
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
400 try:
29411
bac2c0e7c20a SF Patch #744104: Remove eval() from csv
Raymond Hettinger <python@rcn.com>
parents: 29169
diff changeset
401 colType(header[col])
29422
cf8ae3b0dcdc One more multiple exception catch should be in a tuple.
Raymond Hettinger <python@rcn.com>
parents: 29420
diff changeset
402 except (ValueError, TypeError):
28804
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
403 hasHeader += 1
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
404 else:
0c950e3323ee cvs is going to be a module again
Skip Montanaro <skip@pobox.com>
parents:
diff changeset
405 hasHeader -= 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 return hasHeader > 0