class CreateByImportDelimForm(forms.Form):
"""Form for step 2 (picking delimiter) of the import wizard"""
delimiter = ChoiceOrOtherField(required=False, initial=TERMINATOR_CHOICES[0][0],
choices=TERMINATOR_CHOICES)
file_type = forms.CharField(widget=forms.HiddenInput, required=True)
def clean(self):
# ChoiceOrOtherField doesn't work with required=True
delimiter = self.cleaned_data.get('delimiter')
if not delimiter:
raise forms.ValidationError('Delimiter value is required')
_clean_terminator(delimiter)
return self.cleaned_data
def old(self):
if delimiter.isdigit():
try:
chr(int(delimiter))
return int(delimiter)
except ValueError:
raise forms.ValidationError('Delimiter value must be smaller than 256')
val = delimiter.decode('string_escape')
if len(val) != 1:
raise forms.ValidationError('Delimiter must be exactly one character')
return ord(val)
class CreateByImportDelimForm(forms.Form):
"""Form for step 2 (picking delimiter) of the import wizard"""
delimiter = ChoiceOrOtherField(label=_t('Delimiter'),
required=False,
initial=TERMINATOR_CHOICES[0][0],
choices=TERMINATOR_CHOICES)
file_type = forms.CharField(widget=forms.HiddenInput, required=True)
read_column_headers = forms.BooleanField(
required=False,
initial=False,
label=_t("Read column headers"),
help_text=_t("Read first row of the file as column headers."))
def clean(self):
# ChoiceOrOtherField doesn't work with required=True
delimiter = self.cleaned_data.get('delimiter')
if delimiter.isdigit():
try:
chr(int(delimiter))
return int(delimiter)
except ValueError:
raise forms.ValidationError(
_('Delimiter value must be smaller than 256.'))
if not delimiter:
raise forms.ValidationError(_('Delimiter value is required.'))
_clean_terminator(delimiter)
return self.cleaned_data
class CreateTableFromFileForm(forms.Form):
"""
Form used in the create table from file page
"""
# Basic Data
name = common.HiveIdentifierField(label="Table Name", required=False)
comment = forms.CharField(label="Description", required=False)
path = filebrowser.forms.PathField(label="Input File")
# csv/tsv files
encoding = UnicodeEncodingField()
delimiter = ChoiceOrOtherField(required=False, initial=TERMINATOR_CHOICES[0][0], choices=TERMINATOR_CHOICES)
replace_delimiter_with = ChoiceOrOtherField(required=False, initial=TERMINATOR_CHOICES[0][0], choices=TERMINATOR_CHOICES,
label="Replace delimiter with")
read_column_headers = forms.BooleanField(required=False, initial=True,
label="Read column headers",
help_text="")
import_data = forms.BooleanField(required=False, initial=True,
label="Import data",
help_text="")
autodetect_delimiter = forms.BooleanField(required=False, initial=True,
label="Autodetect delimiter",
help_text="")
ignore_whitespaces = forms.BooleanField(required=False, initial=False,
label="Ignore whitespaces",
help_text="")
ignore_tabs = forms.BooleanField(required=False, initial=False,
label="Ignore tabs",
help_text="")
single_line_comment = forms.CharField(label="Single line comment", required=False)
java_style_comments = forms.BooleanField(required=False, initial=False,
label="Java-style comments",
help_text="")
apply_excel_dialect = forms.BooleanField(required=False, initial=True,
label="Read column headers",
help_text="")
# xls/xlsx files
xls_sheet = ChoiceFieldExtended(label="Sheet", required=False)
xls_cell_range = forms.CharField(label="Cell range", required=False)
xls_read_column_headers = forms.BooleanField(required=False, initial=True,
label="Read column headers",
help_text="")
class CreateTableForm(DependencyAwareForm):
"""
Form used in the create table page
"""
dependencies = []
# Basic Data
name = common.HiveIdentifierField(label=_t("Table Name"), required=True)
comment = forms.CharField(label=_t("Description"), required=False)
# Row Formatting
row_format = forms.ChoiceField(required=True,
choices=common.to_choices([ "Delimited", "SerDe" ]),
initial="Delimited")
# Delimited Row
# These initials are per LazySimpleSerDe.DefaultSeparators
field_terminator = ChoiceOrOtherField(label=_t("Field terminator"), required=False, initial=TERMINATOR_CHOICES[0][0],
choices=TERMINATOR_CHOICES)
collection_terminator = ChoiceOrOtherField(label=_t("Collection terminator"), required=False, initial=TERMINATOR_CHOICES[1][0],
choices=TERMINATOR_CHOICES)
map_key_terminator = ChoiceOrOtherField(label=_t("Map key terminator"), required=False, initial=TERMINATOR_CHOICES[2][0],
choices=TERMINATOR_CHOICES)
dependencies += [
("row_format", "Delimited", "field_terminator"),
("row_format", "Delimited", "collection_terminator"),
("row_format", "Delimited", "map_key_terminator"),
]
# Serde Row
serde_name = forms.CharField(required=False, label=_t("SerDe Name"))
serde_properties = forms.CharField(
required=False,
help_text=_t("Comma-separated list of key-value pairs. E.g. 'p1=v1, p2=v2'"))
dependencies += [
("row_format", "SerDe", "serde_name"),
("row_format", "SerDe", "serde_properties"),
]
# File Format
file_format = forms.ChoiceField(required=False, initial="TextFile",
choices=common.to_choices(["TextFile", "SequenceFile", "InputFormat"]),
widget=forms.RadioSelect)
input_format_class = forms.CharField(required=False, label=_t("InputFormat Class"))
output_format_class = forms.CharField(required=False, label=_t("OutputFormat Class"))
dependencies += [
("file_format", "InputFormat", "input_format_class"),
("file_format", "InputFormat", "output_format_class"),
]
# External?
use_default_location = forms.BooleanField(required=False, initial=True, label=_t("Use default location."))
external_location = forms.CharField(required=False, help_text=_t("Path to HDFS directory or file of table data."))
dependencies += [
("use_default_location", False, "external_location")
]
def clean_field_terminator(self):
return _clean_terminator(self.cleaned_data.get('field_terminator'))
def clean_collection_terminator(self):
return _clean_terminator(self.cleaned_data.get('collection_terminator'))
def clean_map_key_terminator(self):
return _clean_terminator(self.cleaned_data.get('map_key_terminator'))
def clean_name(self):
return _clean_tablename(self.db, self.cleaned_data['name'], self.database)
class DjangoForm(forms.Form):
input = PathListField(
required=True,
initial=["$input"],
help_text="Input paths (may be files or folders).")
output = CharField(
required=True,
initial="$output",
help_text="Output directory. Must not already exist.")
mapper_cmd = CharField(
required=True,
initial="<python yourscript.py --map>",
help_text=
"Command to execute for map tasks (exclusive with mapper_class).")
mapper_class = CharField(
required=False,
initial="",
help_text=
"Class to execute for map tasks (exclusive with mapper_cmd).")
combiner_class = CharField(
required=False,
help_text="(Optional) Class to execute as combiner.")
reducer_cmd = CharField(
required=False,
initial="<python yourscript.py --reduce>",
help_text=
"(Optional.) Command to execute for reduce tasks (exclusive with reducer_class)"
)
reducer_class = CharField(
required=False,
initial="",
help_text=
"Class to execute for reduce tasks (exclusive with reducer_cmd)")
inputformat_class = ChoiceOrOtherField(
required=False,
initial="org.apache.hadoop.mapred.TextInputFormat",
choices=(
pair_up("org.apache.hadoop.mapred.TextInputFormat"),
pair_up(
"org.apache.hadoop.mapred.SequenceFileAsTextInputFormat"),
),
help_text="Built-in input format, or class of custom input format."
)
outputformat_class = ChoiceOrOtherField(
required=False,
initial="org.apache.hadoop.mapred.TextOutputFormat",
choices=(pair_up("org.apache.hadoop.mapred.TextOutputFormat"), ),
help_text="Built-in output format, or class of custom input format."
)
partitioner_class = CharField(
required=False, help_text="(Optional) class name of partitioner.")
num_reduce_tasks = IntegerField(
required=False,
initial=1,
help_text="Number of reduce tasks. Set to 0 to disable reducers.")
inputreader = CharField(required=False,
help_text="(Optional) Inputreader spec.")
cache_files = PathListField(
required=False,
initial=["<yourscript.py>"],
label="Required Files",
help_text="Files (on cluster) to send as part of job.")
cache_archives = PathListField(
required=False,
help_text="Archives (zip, jar) (on cluster) to send as part of job."
)
hadoop_properties = KeyValueField(
required=False,
help_text='Hadoop options in format property=value.')
