/* Copyright (c) Jython Developers */
package org.python.modules._csv;
import org.python.core.ArgParser;
import org.python.core.ClassDictInit;
import org.python.core.Py;
import org.python.core.PyBaseString;
import org.python.core.PyDictionary;
import org.python.core.PyException;
import org.python.core.PyInteger;
import org.python.core.PyObject;
import org.python.core.PyString;
import org.python.core.PyStringMap;
/**
* The Python _csv module.
*
* Provides the low-level underpinnings of a CSV reading/writing module. Users should not
* use this module directly, but import the csv.py module instead.
*/
public class _csv implements ClassDictInit {
public static PyString __doc__ = Py.newString(
"CSV parsing and writing.\n" +
"\n" +
"This module provides classes that assist in the reading and writing\n" +
"of Comma Separated Value (CSV) files, and implements the interface\n" +
"described by PEP 305. Although many CSV files are simple to parse,\n" +
"the format is not formally defined by a stable specification and\n" +
"is subtle enough that parsing lines of a CSV file with something\n" +
"like line.split(\",\") is bound to fail. The module supports three\n" +
"basic APIs: reading, writing, and registration of dialects.\n" +
"\n" +
"\n" +
"DIALECT REGISTRATION:\n" +
"\n" +
"Readers and writers support a dialect argument, which is a convenient\n" +
"handle on a group of settings. When the dialect argument is a string,\n" +
"it identifies one of the dialects previously registered with the module.\n" +
"If it is a class or instance, the attributes of the argument are used as\n" +
"the settings for the reader or writer:\n" +
"\n" +
" class excel:\n" +
" delimiter = ','\n" +
" quotechar = '\"'\n" +
" escapechar = None\n" +
" doublequote = True\n" +
" skipinitialspace = False\n" +
" lineterminator = '\r\n'\n" +
" quoting = QUOTE_MINIMAL\n" +
"\n" +
"SETTINGS:\n" +
"\n" +
" * quotechar - specifies a one-character string to use as the \n" +
" quoting character. It defaults to '\"'.\n" +
" * delimiter - specifies a one-character string to use as the \n" +
" field separator. It defaults to ','.\n" +
" * skipinitialspace - specifies how to interpret whitespace which\n" +
" immediately follows a delimiter. It defaults to False, which\n" +
" means that whitespace immediately following a delimiter is part\n" +
" of the following field.\n" +
" * lineterminator - specifies the character sequence which should \n" +
" terminate rows.\n" +
" * quoting - controls when quotes should be generated by the writer.\n" +
" It can take on any of the following module constants:\n" +
"\n" +
" csv.QUOTE_MINIMAL means only when required, for example, when a\n" +
" field contains either the quotechar or the delimiter\n" +
" csv.QUOTE_ALL means that quotes are always placed around fields.\n" +
" csv.QUOTE_NONNUMERIC means that quotes are always placed around\n" +
" fields which do not parse as integers or floating point\n" +
" numbers.\n" +
" csv.QUOTE_NONE means that quotes are never placed around fields.\n" +
" * escapechar - specifies a one-character string used to escape \n" +
" the delimiter when quoting is set to QUOTE_NONE.\n" +
" * doublequote - controls the handling of quotes inside fields. When\n" +
" True, two consecutive quotes are interpreted as one during read,\n" +
" and when writing, each quote character embedded in the data is\n" +
" written as two quotes\n" +
"\n");
// XXX: should be per PySystemState
/** Dialect registry. */
public static PyDictionary _dialects = new PyDictionary();
// XXX: should be per PySystemState
/** Max parsed field size */
public static volatile int field_limit = 128 * 1024;
/** _csv.Error exception. */
public static final PyObject Error = Py.makeClass("Error", Py.Exception, exceptionNamespace());
public static PyException Error(String message) {
return new PyException(Error, message);
}
/** Module version. */
public static PyString __version__ = new PyString("1.0");
public static void classDictInit(PyObject dict) {
dict.__setitem__("__name__", Py.newString("_csv"));
dict.__setitem__("__doc__", __doc__);
dict.__setitem__("Dialect", PyDialect.TYPE);
dict.__setitem__("Error", Error);
for (QuoteStyle style : QuoteStyle.values()) {
dict.__setitem__(style.name(), Py.newInteger(style.ordinal()));
}
dict.__setitem__("classDictInit", null);
dict.__setitem__("field_limit", null);
}
public static void register_dialect(PyObject[] args, String[] keywords) {
int argc = args.length - keywords.length;
if (argc > 2) {
throw Py.TypeError("register_dialect() expected at most 2 arguments, got " + argc);
}
ArgParser ap = parseArgs("register_dialect", args, keywords);
PyObject name = ap.getPyObject(0);
PyObject dialect = ap.getPyObject(1, null);
if (!(name instanceof PyBaseString)) {
throw Py.TypeError("dialect name must be a string or unicode");
}
_dialects.__setitem__(name, dialectFromKwargs(dialect, args, keywords));
return;
}
public static void unregister_dialect(PyObject name) {
if (!_dialects.has_key(name)) {
throw Error("unknown dialect");
}
_dialects.__delitem__(name);
}
public static PyObject get_dialect(PyObject name) {
return get_dialect_from_registry(name);
}
public static PyObject list_dialects() {
return _dialects.keys();
}
public static PyObject reader(PyObject[] args, String[] keywords) {
ArgParser ap = parseArgs("reader", args, keywords);
PyObject iterator = Py.iter(ap.getPyObject(0), "argument 1 must be an iterator");
PyObject dialect = ap.getPyObject(1, null);
return new PyReader(iterator, dialectFromKwargs(dialect, args, keywords));
}
public static PyObject writer(PyObject[] args, String[] keywords) {
ArgParser ap = parseArgs("writer", args, keywords);
PyObject outputFile = ap.getPyObject(0);
PyObject dialect = ap.getPyObject(1, null);
PyObject writeline = outputFile.__findattr__("write");
if (writeline == null || !writeline.isCallable()) {
throw Py.TypeError("argument 1 must have a \"write\" method");
}
return new PyWriter(writeline, dialectFromKwargs(dialect, args, keywords));
}
public static PyInteger field_size_limit() {
return Py.newInteger(field_limit);
}
public static PyInteger field_size_limit(PyObject new_limit) {
if (!(new_limit instanceof PyInteger)) {
throw Py.TypeError("limit must be an integer");
}
int old_limit = field_limit;
field_limit = new_limit.asInt();
return Py.newInteger(old_limit);
}
static PyObject get_dialect_from_registry(PyObject name) {
PyObject dialect = _dialects.__finditem__(name);
if (dialect == null) {
throw Error("unknown dialect");
}
return dialect;
}
/**
* Return an ArgParser that ignores keyword args.
*/
private static ArgParser parseArgs(String funcName, PyObject[] args, String[] keywords) {
// XXX: _weakref.ReferenceType has the same code
if (keywords.length > 0) {
int argc = args.length - keywords.length;
PyObject[] justArgs = new PyObject[argc];
System.arraycopy(args, 0, justArgs, 0, argc);
args = justArgs;
}
return new ArgParser(funcName, args, Py.NoKeywords, Py.NoKeywords);
}
/**
* Return a Dialect instance created or updated from keyword arguments.
*/
private static PyDialect dialectFromKwargs(PyObject dialect, PyObject[] args,
String[] keywords) {
PyObject[] dialectArgs;
int argc = args.length - keywords.length;
// was a dialect keyword specified?
boolean dialectKeyword = false;
for (String keyword : keywords) {
if (keyword.equals("dialect")) {
dialectKeyword = true;
}
}
if (dialect == null || dialectKeyword) {
// dialect wasn't passed as a positional arg
dialectArgs = new PyObject[keywords.length];
System.arraycopy(args, argc, dialectArgs, 0, keywords.length);
} else {
// have dialect -- pass it to dialect_new as a positional arg
dialectArgs = new PyObject[1 + keywords.length];
dialectArgs[0] = dialect;
System.arraycopy(args, argc, dialectArgs, 1, keywords.length);
}
return (PyDialect)PyDialect.TYPE.__call__(dialectArgs, keywords);
}
private static PyObject exceptionNamespace() {
PyObject dict = new PyStringMap();
dict.__setitem__("__module__", new PyString("_csv"));
return dict;
}
}