def __init__(self, configdict, section, produces):
Input.__init__(self, configdict, section, produces)
# Create the list of files to be used as input
self.file_list = Util.make_file_list(self.file_path, None, self.filename_pattern, self.depth_search)
log.info("file_list=%s" % str(self.file_list))
if not len(self.file_list):
raise Exception('File list is empty!!')
self.file_list_done = []
def __init__(self, configdict, section, produces):
Input.__init__(self, configdict, section, produces)
# Create the list of files to be used as input
self.file_list = Util.make_file_list(self.file_path, None, self.filename_pattern, self.depth_search)
log.info("file_list=%s" % str(self.file_list))
if not len(self.file_list):
raise Exception('File list is empty!!')
self.cur_file_path = None
self.file_list_done = []
def __init__(self, configdict, section):
Input.__init__(self, configdict, section, produces=FORMAT.etree_doc)
self.cur_feature_blob = None
self.rowcount = 0
# http://www.mkyong.com/regular-expressions/how-to-extract-html-links-with-regular-expression/
self.regex_xlink_href = re.compile("\\s*(?i)xlink:href\\s*=\\s*(\"#([^\"]*\")|'#[^']*'|(#[^'\">\\s]+))")
self.db = None
self.xlink_db = None
self.buffer = None
self.feature_count = 0
# Reusable XML parser
self.xml_parser = etree.XMLParser(remove_blank_text=True)
def __init__(self, configdict, section):
Input.__init__(self, configdict, section, produces=FORMAT.etree_doc)
self.cur_feature_blob = None
self.rowcount = 0
# http://www.mkyong.com/regular-expressions/how-to-extract-html-links-with-regular-expression/
self.regex_xlink_href = re.compile("\\s*(?i)xlink:href\\s*=\\s*(\"#([^\"]*\")|'#[^']*'|(#[^'\">\\s]+))")
self.db = None
self.xlink_db = None
self.buffer = None
self.feature_count = 0
# Reusable XML parser
self.xml_parser = etree.XMLParser(remove_blank_text=True)
def __init__(self, configdict, section, produces):
Input.__init__(self, configdict, section, produces)
# path to file or files: can be a dir or files or even multiple, comma separated
self.file_path = self.cfg.get('file_path')
# The filename pattern according to Python glob.glob
self.filename_pattern = self.cfg.get('filename_pattern', '*.[gxGX][mM][lL]')
# Recurse into directories ?
self.depth_search = self.cfg.get_bool('depth_search', False)
# Create the list of files to be used as input
self.file_list = Util.make_file_list(self.file_path, None, self.filename_pattern, self.depth_search)
log.info("file_list=%s" % str(self.file_list))
def __init__(self, configdict, section, produces=FORMAT.any):
Input.__init__(self, configdict, section, produces)
# url and optional parameters
self.url = self.cfg.get('url')
self.parameters = self.cfg.get('parameters')
# http://docs.python.org/2/howto/urllib2.html
self.query_string = None
if self.parameters:
# http://stackoverflow.com/questions/988228/converting-a-string-to-dictionary
import ast
self.parameters = ast.literal_eval(self.parameters)
self.query_string = urllib.urlencode(self.parameters)
log.info("url=%s" % self.url)
def __init__(self, configdict, section, produces):
Input.__init__(self, configdict, section, produces)
# path to file or files: can be a dir or files or even multiple, comma separated
self.file_path = self.cfg.get('file_path')
# The filename pattern according to Python glob.glob
self.filename_pattern = self.cfg.get('filename_pattern',
'*.[gxGX][mM][lL]')
# Recurse into directories ?
self.depth_search = self.cfg.get_bool('depth_search', False)
# Create the list of files to be used as input
self.file_list = Util.make_file_list(self.file_path, None,
self.filename_pattern,
self.depth_search)
log.info("file_list=%s" % str(self.file_list))
def __init__(self, configdict, section):
Input.__init__(self, configdict, section, produces=[FORMAT.ogr_feature, FORMAT.ogr_feature_array])
def __init__(self, configdict, section):
Input.__init__(self, configdict, section, produces=FORMAT.xml_line_stream)
def __init__(self, configdict, section, produces):
Input.__init__(self, configdict, section, produces=produces)
def __init__(self, configdict, section, produces):
Input.__init__(self, configdict, section, produces=produces)
def __init__(self, configdict, section, produces=FORMAT.any):
Input.__init__(self, configdict, section, produces)
log.info("url=%s parameters=%s" % (self.url, self.parameters))
def __init__(self, configdict, section):
Input.__init__(self,
configdict,
section,
produces=FORMAT.xml_line_stream)
def __init__(self, configdict, section):
Input.__init__(self, configdict, section, produces=[FORMAT.ogr_feature, FORMAT.ogr_feature_array])
def __init__(self, configdict, section, produces=FORMAT.any):
Input.__init__(self, configdict, section, produces)
log.info("url=%s parameters=%s" % (self.url, self.parameters))