--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/symbian-qemu-0.9.1-12/python-2.6.1/Doc/library/csv.rst Fri Jul 31 15:01:17 2009 +0100
@@ -0,0 +1,569 @@
+
+:mod:`csv` --- CSV File Reading and Writing
+===========================================
+
+.. module:: csv
+ :synopsis: Write and read tabular data to and from delimited files.
+.. sectionauthor:: Skip Montanaro <skip@pobox.com>
+
+
+.. versionadded:: 2.3
+
+.. index::
+ single: csv
+ pair: data; tabular
+
+The so-called CSV (Comma Separated Values) format is the most common import and
+export format for spreadsheets and databases. There is no "CSV standard", so
+the format is operationally defined by the many applications which read and
+write it. The lack of a standard means that subtle differences often exist in
+the data produced and consumed by different applications. These differences can
+make it annoying to process CSV files from multiple sources. Still, while the
+delimiters and quoting characters vary, the overall format is similar enough
+that it is possible to write a single module which can efficiently manipulate
+such data, hiding the details of reading and writing the data from the
+programmer.
+
+The :mod:`csv` module implements classes to read and write tabular data in CSV
+format. It allows programmers to say, "write this data in the format preferred
+by Excel," or "read data from this file which was generated by Excel," without
+knowing the precise details of the CSV format used by Excel. Programmers can
+also describe the CSV formats understood by other applications or define their
+own special-purpose CSV formats.
+
+The :mod:`csv` module's :class:`reader` and :class:`writer` objects read and
+write sequences. Programmers can also read and write data in dictionary form
+using the :class:`DictReader` and :class:`DictWriter` classes.
+
+.. note::
+
+ This version of the :mod:`csv` module doesn't support Unicode input. Also,
+ there are currently some issues regarding ASCII NUL characters. Accordingly,
+ all input should be UTF-8 or printable ASCII to be safe; see the examples in
+ section :ref:`csv-examples`. These restrictions will be removed in the future.
+
+
+.. seealso::
+
+ :pep:`305` - CSV File API
+ The Python Enhancement Proposal which proposed this addition to Python.
+
+
+.. _csv-contents:
+
+Module Contents
+---------------
+
+The :mod:`csv` module defines the following functions:
+
+
+.. function:: reader(csvfile[, dialect='excel'][, fmtparam])
+
+ Return a reader object which will iterate over lines in the given *csvfile*.
+ *csvfile* can be any object which supports the :term:`iterator` protocol and returns a
+ string each time its :meth:`next` method is called --- file objects and list
+ objects are both suitable. If *csvfile* is a file object, it must be opened
+ with the 'b' flag on platforms where that makes a difference. An optional
+ *dialect* parameter can be given which is used to define a set of parameters
+ specific to a particular CSV dialect. It may be an instance of a subclass of
+ the :class:`Dialect` class or one of the strings returned by the
+ :func:`list_dialects` function. The other optional *fmtparam* keyword arguments
+ can be given to override individual formatting parameters in the current
+ dialect. For full details about the dialect and formatting parameters, see
+ section :ref:`csv-fmt-params`.
+
+ All data read are returned as strings. No automatic data type conversion is
+ performed.
+
+ A short usage example::
+
+ >>> import csv
+ >>> spamReader = csv.reader(open('eggs.csv'), delimiter=' ', quotechar='|')
+ >>> for row in spamReader:
+ ... print ', '.join(row)
+ Spam, Spam, Spam, Spam, Spam, Baked Beans
+ Spam, Lovely Spam, Wonderful Spam
+
+ .. versionchanged:: 2.5
+ The parser is now stricter with respect to multi-line quoted fields. Previously,
+ if a line ended within a quoted field without a terminating newline character, a
+ newline would be inserted into the returned field. This behavior caused problems
+ when reading files which contained carriage return characters within fields.
+ The behavior was changed to return the field without inserting newlines. As a
+ consequence, if newlines embedded within fields are important, the input should
+ be split into lines in a manner which preserves the newline characters.
+
+
+.. function:: writer(csvfile[, dialect='excel'][, fmtparam])
+
+ Return a writer object responsible for converting the user's data into delimited
+ strings on the given file-like object. *csvfile* can be any object with a
+ :func:`write` method. If *csvfile* is a file object, it must be opened with the
+ 'b' flag on platforms where that makes a difference. An optional *dialect*
+ parameter can be given which is used to define a set of parameters specific to a
+ particular CSV dialect. It may be an instance of a subclass of the
+ :class:`Dialect` class or one of the strings returned by the
+ :func:`list_dialects` function. The other optional *fmtparam* keyword arguments
+ can be given to override individual formatting parameters in the current
+ dialect. For full details about the dialect and formatting parameters, see
+ section :ref:`csv-fmt-params`. To make it
+ as easy as possible to interface with modules which implement the DB API, the
+ value :const:`None` is written as the empty string. While this isn't a
+ reversible transformation, it makes it easier to dump SQL NULL data values to
+ CSV files without preprocessing the data returned from a ``cursor.fetch*`` call.
+ All other non-string data are stringified with :func:`str` before being written.
+
+ A short usage example::
+
+ >>> import csv
+ >>> spamWriter = csv.writer(open('eggs.csv', 'w'), delimiter=' ',
+ ... quotechar='|', quoting=QUOTE_MINIMAL)
+ >>> spamWriter.writerow(['Spam'] * 5 + ['Baked Beans'])
+ >>> spamWriter.writerow(['Spam', 'Lovely Spam', 'Wonderful Spam'])
+
+
+.. function:: register_dialect(name[, dialect][, fmtparam])
+
+ Associate *dialect* with *name*. *name* must be a string or Unicode object. The
+ dialect can be specified either by passing a sub-class of :class:`Dialect`, or
+ by *fmtparam* keyword arguments, or both, with keyword arguments overriding
+ parameters of the dialect. For full details about the dialect and formatting
+ parameters, see section :ref:`csv-fmt-params`.
+
+
+.. function:: unregister_dialect(name)
+
+ Delete the dialect associated with *name* from the dialect registry. An
+ :exc:`Error` is raised if *name* is not a registered dialect name.
+
+
+.. function:: get_dialect(name)
+
+ Return the dialect associated with *name*. An :exc:`Error` is raised if *name*
+ is not a registered dialect name.
+
+ .. versionchanged:: 2.5
+ This function now returns an immutable :class:`Dialect`. Previously an
+ instance of the requested dialect was returned. Users could modify the
+ underlying class, changing the behavior of active readers and writers.
+
+.. function:: list_dialects()
+
+ Return the names of all registered dialects.
+
+
+.. function:: field_size_limit([new_limit])
+
+ Returns the current maximum field size allowed by the parser. If *new_limit* is
+ given, this becomes the new limit.
+
+ .. versionadded:: 2.5
+
+The :mod:`csv` module defines the following classes:
+
+
+.. class:: DictReader(csvfile[, fieldnames=None[, restkey=None[, restval=None[, dialect='excel'[, *args, **kwds]]]]])
+
+ Create an object which operates like a regular reader but maps the information
+ read into a dict whose keys are given by the optional *fieldnames* parameter.
+ If the *fieldnames* parameter is omitted, the values in the first row of the
+ *csvfile* will be used as the fieldnames. If the row read has fewer fields than
+ the fieldnames sequence, the value of *restval* will be used as the default
+ value. If the row read has more fields than the fieldnames sequence, the
+ remaining data is added as a sequence keyed by the value of *restkey*. If the
+ row read has fewer fields than the fieldnames sequence, the remaining keys take
+ the value of the optional *restval* parameter. Any other optional or keyword
+ arguments are passed to the underlying :class:`reader` instance.
+
+
+.. class:: DictWriter(csvfile, fieldnames[, restval=''[, extrasaction='raise'[, dialect='excel'[, *args, **kwds]]]])
+
+ Create an object which operates like a regular writer but maps dictionaries onto
+ output rows. The *fieldnames* parameter identifies the order in which values in
+ the dictionary passed to the :meth:`writerow` method are written to the
+ *csvfile*. The optional *restval* parameter specifies the value to be written
+ if the dictionary is missing a key in *fieldnames*. If the dictionary passed to
+ the :meth:`writerow` method contains a key not found in *fieldnames*, the
+ optional *extrasaction* parameter indicates what action to take. If it is set
+ to ``'raise'`` a :exc:`ValueError` is raised. If it is set to ``'ignore'``,
+ extra values in the dictionary are ignored. Any other optional or keyword
+ arguments are passed to the underlying :class:`writer` instance.
+
+ Note that unlike the :class:`DictReader` class, the *fieldnames* parameter of
+ the :class:`DictWriter` is not optional. Since Python's :class:`dict` objects
+ are not ordered, there is not enough information available to deduce the order
+ in which the row should be written to the *csvfile*.
+
+
+.. class:: Dialect
+
+ The :class:`Dialect` class is a container class relied on primarily for its
+ attributes, which are used to define the parameters for a specific
+ :class:`reader` or :class:`writer` instance.
+
+
+.. class:: excel()
+
+ The :class:`excel` class defines the usual properties of an Excel-generated CSV
+ file. It is registered with the dialect name ``'excel'``.
+
+
+.. class:: excel_tab()
+
+ The :class:`excel_tab` class defines the usual properties of an Excel-generated
+ TAB-delimited file. It is registered with the dialect name ``'excel-tab'``.
+
+
+.. class:: Sniffer()
+
+ The :class:`Sniffer` class is used to deduce the format of a CSV file.
+
+ The :class:`Sniffer` class provides two methods:
+
+ .. method:: sniff(sample[, delimiters=None])
+
+ Analyze the given *sample* and return a :class:`Dialect` subclass
+ reflecting the parameters found. If the optional *delimiters* parameter
+ is given, it is interpreted as a string containing possible valid
+ delimiter characters.
+
+
+ .. method:: has_header(sample)
+
+ Analyze the sample text (presumed to be in CSV format) and return
+ :const:`True` if the first row appears to be a series of column headers.
+
+An example for :class:`Sniffer` use::
+
+ csvfile = open("example.csv")
+ dialect = csv.Sniffer().sniff(csvfile.read(1024))
+ csvfile.seek(0)
+ reader = csv.reader(csvfile, dialect)
+ # ... process CSV file contents here ...
+
+
+The :mod:`csv` module defines the following constants:
+
+.. data:: QUOTE_ALL
+
+ Instructs :class:`writer` objects to quote all fields.
+
+
+.. data:: QUOTE_MINIMAL
+
+ Instructs :class:`writer` objects to only quote those fields which contain
+ special characters such as *delimiter*, *quotechar* or any of the characters in
+ *lineterminator*.
+
+
+.. data:: QUOTE_NONNUMERIC
+
+ Instructs :class:`writer` objects to quote all non-numeric fields.
+
+ Instructs the reader to convert all non-quoted fields to type *float*.
+
+
+.. data:: QUOTE_NONE
+
+ Instructs :class:`writer` objects to never quote fields. When the current
+ *delimiter* occurs in output data it is preceded by the current *escapechar*
+ character. If *escapechar* is not set, the writer will raise :exc:`Error` if
+ any characters that require escaping are encountered.
+
+ Instructs :class:`reader` to perform no special processing of quote characters.
+
+The :mod:`csv` module defines the following exception:
+
+
+.. exception:: Error
+
+ Raised by any of the functions when an error is detected.
+
+
+.. _csv-fmt-params:
+
+Dialects and Formatting Parameters
+----------------------------------
+
+To make it easier to specify the format of input and output records, specific
+formatting parameters are grouped together into dialects. A dialect is a
+subclass of the :class:`Dialect` class having a set of specific methods and a
+single :meth:`validate` method. When creating :class:`reader` or
+:class:`writer` objects, the programmer can specify a string or a subclass of
+the :class:`Dialect` class as the dialect parameter. In addition to, or instead
+of, the *dialect* parameter, the programmer can also specify individual
+formatting parameters, which have the same names as the attributes defined below
+for the :class:`Dialect` class.
+
+Dialects support the following attributes:
+
+
+.. attribute:: Dialect.delimiter
+
+ A one-character string used to separate fields. It defaults to ``','``.
+
+
+.. attribute:: Dialect.doublequote
+
+ Controls how instances of *quotechar* appearing inside a field should be
+ themselves be quoted. When :const:`True`, the character is doubled. When
+ :const:`False`, the *escapechar* is used as a prefix to the *quotechar*. It
+ defaults to :const:`True`.
+
+ On output, if *doublequote* is :const:`False` and no *escapechar* is set,
+ :exc:`Error` is raised if a *quotechar* is found in a field.
+
+
+.. attribute:: Dialect.escapechar
+
+ A one-character string used by the writer to escape the *delimiter* if *quoting*
+ is set to :const:`QUOTE_NONE` and the *quotechar* if *doublequote* is
+ :const:`False`. On reading, the *escapechar* removes any special meaning from
+ the following character. It defaults to :const:`None`, which disables escaping.
+
+
+.. attribute:: Dialect.lineterminator
+
+ The string used to terminate lines produced by the :class:`writer`. It defaults
+ to ``'\r\n'``.
+
+ .. note::
+
+ The :class:`reader` is hard-coded to recognise either ``'\r'`` or ``'\n'`` as
+ end-of-line, and ignores *lineterminator*. This behavior may change in the
+ future.
+
+
+.. attribute:: Dialect.quotechar
+
+ A one-character string used to quote fields containing special characters, such
+ as the *delimiter* or *quotechar*, or which contain new-line characters. It
+ defaults to ``'"'``.
+
+
+.. attribute:: Dialect.quoting
+
+ Controls when quotes should be generated by the writer and recognised by the
+ reader. It can take on any of the :const:`QUOTE_\*` constants (see section
+ :ref:`csv-contents`) and defaults to :const:`QUOTE_MINIMAL`.
+
+
+.. attribute:: Dialect.skipinitialspace
+
+ When :const:`True`, whitespace immediately following the *delimiter* is ignored.
+ The default is :const:`False`.
+
+
+Reader Objects
+--------------
+
+Reader objects (:class:`DictReader` instances and objects returned by the
+:func:`reader` function) have the following public methods:
+
+
+.. method:: csvreader.next()
+
+ Return the next row of the reader's iterable object as a list, parsed according
+ to the current dialect.
+
+Reader objects have the following public attributes:
+
+
+.. attribute:: csvreader.dialect
+
+ A read-only description of the dialect in use by the parser.
+
+
+.. attribute:: csvreader.line_num
+
+ The number of lines read from the source iterator. This is not the same as the
+ number of records returned, as records can span multiple lines.
+
+ .. versionadded:: 2.5
+
+
+DictReader objects have the following public attribute:
+
+
+.. attribute:: csvreader.fieldnames
+
+ If not passed as a parameter when creating the object, this attribute is
+ initialized upon first access or when the first record is read from the
+ file.
+
+ .. versionchanged:: 2.6
+
+
+Writer Objects
+--------------
+
+:class:`Writer` objects (:class:`DictWriter` instances and objects returned by
+the :func:`writer` function) have the following public methods. A *row* must be
+a sequence of strings or numbers for :class:`Writer` objects and a dictionary
+mapping fieldnames to strings or numbers (by passing them through :func:`str`
+first) for :class:`DictWriter` objects. Note that complex numbers are written
+out surrounded by parens. This may cause some problems for other programs which
+read CSV files (assuming they support complex numbers at all).
+
+
+.. method:: csvwriter.writerow(row)
+
+ Write the *row* parameter to the writer's file object, formatted according to
+ the current dialect.
+
+
+.. method:: csvwriter.writerows(rows)
+
+ Write all the *rows* parameters (a list of *row* objects as described above) to
+ the writer's file object, formatted according to the current dialect.
+
+Writer objects have the following public attribute:
+
+
+.. attribute:: csvwriter.dialect
+
+ A read-only description of the dialect in use by the writer.
+
+
+.. _csv-examples:
+
+Examples
+--------
+
+The simplest example of reading a CSV file::
+
+ import csv
+ reader = csv.reader(open("some.csv", "rb"))
+ for row in reader:
+ print row
+
+Reading a file with an alternate format::
+
+ import csv
+ reader = csv.reader(open("passwd", "rb"), delimiter=':', quoting=csv.QUOTE_NONE)
+ for row in reader:
+ print row
+
+The corresponding simplest possible writing example is::
+
+ import csv
+ writer = csv.writer(open("some.csv", "wb"))
+ writer.writerows(someiterable)
+
+Registering a new dialect::
+
+ import csv
+
+ csv.register_dialect('unixpwd', delimiter=':', quoting=csv.QUOTE_NONE)
+
+ reader = csv.reader(open("passwd", "rb"), 'unixpwd')
+
+A slightly more advanced use of the reader --- catching and reporting errors::
+
+ import csv, sys
+ filename = "some.csv"
+ reader = csv.reader(open(filename, "rb"))
+ try:
+ for row in reader:
+ print row
+ except csv.Error, e:
+ sys.exit('file %s, line %d: %s' % (filename, reader.line_num, e))
+
+And while the module doesn't directly support parsing strings, it can easily be
+done::
+
+ import csv
+ for row in csv.reader(['one,two,three']):
+ print row
+
+The :mod:`csv` module doesn't directly support reading and writing Unicode, but
+it is 8-bit-clean save for some problems with ASCII NUL characters. So you can
+write functions or classes that handle the encoding and decoding for you as long
+as you avoid encodings like UTF-16 that use NULs. UTF-8 is recommended.
+
+:func:`unicode_csv_reader` below is a :term:`generator` that wraps :class:`csv.reader`
+to handle Unicode CSV data (a list of Unicode strings). :func:`utf_8_encoder`
+is a :term:`generator` that encodes the Unicode strings as UTF-8, one string (or row) at
+a time. The encoded strings are parsed by the CSV reader, and
+:func:`unicode_csv_reader` decodes the UTF-8-encoded cells back into Unicode::
+
+ import csv
+
+ def unicode_csv_reader(unicode_csv_data, dialect=csv.excel, **kwargs):
+ # csv.py doesn't do Unicode; encode temporarily as UTF-8:
+ csv_reader = csv.reader(utf_8_encoder(unicode_csv_data),
+ dialect=dialect, **kwargs)
+ for row in csv_reader:
+ # decode UTF-8 back to Unicode, cell by cell:
+ yield [unicode(cell, 'utf-8') for cell in row]
+
+ def utf_8_encoder(unicode_csv_data):
+ for line in unicode_csv_data:
+ yield line.encode('utf-8')
+
+For all other encodings the following :class:`UnicodeReader` and
+:class:`UnicodeWriter` classes can be used. They take an additional *encoding*
+parameter in their constructor and make sure that the data passes the real
+reader or writer encoded as UTF-8::
+
+ import csv, codecs, cStringIO
+
+ class UTF8Recoder:
+ """
+ Iterator that reads an encoded stream and reencodes the input to UTF-8
+ """
+ def __init__(self, f, encoding):
+ self.reader = codecs.getreader(encoding)(f)
+
+ def __iter__(self):
+ return self
+
+ def next(self):
+ return self.reader.next().encode("utf-8")
+
+ class UnicodeReader:
+ """
+ A CSV reader which will iterate over lines in the CSV file "f",
+ which is encoded in the given encoding.
+ """
+
+ def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds):
+ f = UTF8Recoder(f, encoding)
+ self.reader = csv.reader(f, dialect=dialect, **kwds)
+
+ def next(self):
+ row = self.reader.next()
+ return [unicode(s, "utf-8") for s in row]
+
+ def __iter__(self):
+ return self
+
+ class UnicodeWriter:
+ """
+ A CSV writer which will write rows to CSV file "f",
+ which is encoded in the given encoding.
+ """
+
+ def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds):
+ # Redirect output to a queue
+ self.queue = cStringIO.StringIO()
+ self.writer = csv.writer(self.queue, dialect=dialect, **kwds)
+ self.stream = f
+ self.encoder = codecs.getincrementalencoder(encoding)()
+
+ def writerow(self, row):
+ self.writer.writerow([s.encode("utf-8") for s in row])
+ # Fetch UTF-8 output from the queue ...
+ data = self.queue.getvalue()
+ data = data.decode("utf-8")
+ # ... and reencode it into the target encoding
+ data = self.encoder.encode(data)
+ # write to the target stream
+ self.stream.write(data)
+ # empty queue
+ self.queue.truncate(0)
+
+ def writerows(self, rows):
+ for row in rows:
+ self.writerow(row)
+