def __init__(self, configdict, section='gml_splitter'):
Filter.__init__(self, configdict, section, consumes=FORMAT.xml_line_stream, produces=FORMAT.etree_doc)
log.info("cfg = %s" % self.cfg.to_string())
self.max_features = self.cfg.get_int('max_features', 10000)
# File preamble
self.start_container = self.cfg.get('start_container')
# File postamble
self.end_container = self.cfg.get('end_container')
self.container_tag = self.cfg.get('container_tag')
# self.feature_tags = self.cfg.get('feature_tags').split(',')
self.start_feature_markers = self.cfg.get('start_feature_markers').split(',')
self.end_feature_markers = self.cfg.get('end_feature_markers').split(',')
self.feature_count = 0
self.total_feature_count = 0
self.in_heading = True
# End of file is line with end_container_tag
self.end_container_tag = '</%s' % self.container_tag
# Derive start and end tags from feature_tags
# for feature_tag in self.feature_tags:
# self.start_feature_markers.append('<%s' % feature_tag)
# self.end_feature_markers.append('</%s>' % feature_tag)
self.expect_end_feature_markers = []
self.expect_end_feature_tag = None
self.buffer = None
# Reusable XML parser
self.xml_parser = etree.XMLParser(remove_blank_text=True)
def __init__(self, configdict, section):
Filter.__init__(self, configdict, section, consumes=FORMAT.string, produces=FORMAT.etree_element)
self.context = None
self.root = None
self.cur_file_path = None
self.elem_count = 0
log.info("Element tags to be matched: %s" % self.element_tags)
def __init__(self, configdict, section):
Filter.__init__(self, configdict, section, consumes=FORMAT.etree_element, produces=FORMAT.etree_element)
# Create specific preparer object from given class name string
self.prep_class = self.cfg.get('prep_class')
self.prep_class = factory.class_forname(self.prep_class)
self.preparer = self.prep_class('stetl')
def __init__(self, configdict, section):
Filter.__init__(self, configdict, section, consumes=FORMAT.etree_doc, produces=FORMAT.etree_doc)
self.xslt_file = open(self.script, 'r')
# Parse XSLT file only once
self.xslt_doc = etree.parse(self.xslt_file)
self.xslt_obj = etree.XSLT(self.xslt_doc)
self.xslt_file.close()
def __init__(self, configdict, section):
Filter.__init__(self, configdict, section, consumes=FORMAT.etree_element, produces=FORMAT.etree_doc)
log.info("cfg = %s" % self.cfg.to_string())
self.max_elements = self.cfg.get_int('max_elements', 10000)
self.container_doc = self.cfg.get('container_doc')
self.element_container_xpath = XmlAssembler.xpath_base % self.cfg.get('element_container_tag')
self.total_element_count = 0
self.element_arr = []
# Reusable XML parser
self.xml_parser = etree.XMLParser(remove_blank_text=True)
def __init__(self, configdict, section='gml_feature_extractor'):
Filter.__init__(self, configdict, section, consumes=FORMAT.etree_doc, produces=FORMAT.etree_feature_array)
log.info("cfg = %s" % self.cfg.to_string())
# Build the Xpath expresion from configures tagnames
self.feature_tags = self.cfg.get('feature_tags').split(',')
self.total_features = 0
self.xpath_expression = ''
index = 0
for feature_tag in self.feature_tags:
if index > 0:
self.xpath_expression += '|'
self.xpath_expression += GmlFeatureExtractor.xpath_base % feature_tag
index += 1
log.info("xpath expression = %s" % self.xpath_expression)
def __init__(self, configdict, section):
Filter.__init__(self, configdict, section, consumes=FORMAT.any, produces=FORMAT.any)
self.packet_list = []
def __init__(self, configdict, section):
Filter.__init__(self, configdict, section, consumes=FORMAT.record, produces=FORMAT.string)
self.cur_file_path = self.cfg.get('file_path')
def __init__(self, configdict, section, consumes, produces):
Filter.__init__(self, configdict, section, consumes, produces)
def __init__(self, configdict, section, consumes=FORMAT.any, produces=FORMAT.any):
Filter.__init__(self, configdict, section, consumes, produces)
def __init__(self, configdict, section):
Filter.__init__(self, configdict, section, consumes=FORMAT.record, produces=FORMAT.record_array)
self.current_record = None
def __init__(self, configdict, section):
Filter.__init__(self, configdict, section, consumes=FORMAT.geojson_collection, produces=FORMAT.geojson_collection)
def __init__(self, configdict, section):
Filter.__init__(self, configdict, section, consumes=FORMAT.any, produces=FORMAT.any)
self.packet_list = []
def __init__(self, configdict, section):
Filter.__init__(self, configdict, section, consumes=FORMAT.any, produces=FORMAT.any)
self.converter = None
def __init__(self, configdict, section):
Filter.__init__(self, configdict, section, consumes=FORMAT.etree_doc, produces=FORMAT.etree_doc)
def __init__(self, configdict, section, consumes, produces):
Filter.__init__(self, configdict, section, consumes, produces)
def __init__(self, configdict, section, consumes=FORMAT.string, produces=FORMAT.string):
Filter.__init__(self, configdict, section, consumes, produces)
def __init__(self, configdict, section, consumes=FORMAT.string, produces=FORMAT.record):
Filter.__init__(self, configdict, section, consumes, produces)
self.regex_object = re.compile(self.pattern_string, re.S)
def __init__(self, configdict, section):
Filter.__init__(self, configdict, section, consumes=FORMAT.etree_doc, produces=FORMAT.etree_doc)
self.enabled = self.cfg.get_bool('enabled', True)
self.xsd = self.cfg.get('xsd')
log.info("Building the Schema once with (GML XSD) dependencies for schema=%s (be patient...)" % self.xsd)
self.schema = etree.XMLSchema(etree.parse(self.xsd))
def __init__(self, configdict, section):
Filter.__init__(self, configdict, section, consumes=FORMAT.any, produces=FORMAT.string)
log.info("working dir %s" % os.getcwd())
def __init__(self, configdict, section):
Filter.__init__(self, configdict, section, consumes=FORMAT.line_stream, produces=FORMAT.record)
self.current_record = None
