SYMBOL INDEX (294 symbols across 71 files) FILE: src/opensemanticetl/clean_title.py class clean_title (line 6) | class clean_title(object): method process (line 8) | def process(self, parameters=None, data=None): FILE: src/opensemanticetl/enhance_annotations.py class enhance_annotations (line 10) | class enhance_annotations(etl_plugin_core.Plugin): method process (line 12) | def process(self, parameters=None, data=None): FILE: src/opensemanticetl/enhance_contenttype_group.py class enhance_contenttype_group (line 9) | class enhance_contenttype_group(object): method process (line 46) | def process(self, parameters=None, data=None): FILE: src/opensemanticetl/enhance_csv.py class enhance_csv (line 12) | class enhance_csv(object): method __init__ (line 14) | def __init__(self, verbose=False): method read_parameters (line 41) | def read_parameters(self, parameters, data): method add_csv_parameters_from_meta_settings (line 96) | def add_csv_parameters_from_meta_settings(self, metaserver): method get_csv_dialect (line 109) | def get_csv_dialect(self): method set_titles (line 164) | def set_titles(self, row): method export_row_data_to_index (line 177) | def export_row_data_to_index(self, data, rownumber): method import_row (line 205) | def import_row(self, row, rownumber, docid): method enhance_csv (line 259) | def enhance_csv(self, parameters, data): method process (line 377) | def process(self, parameters=None, data=None): FILE: src/opensemanticetl/enhance_detect_language_tika_server.py class enhance_detect_language_tika_server (line 9) | class enhance_detect_language_tika_server(object): method process (line 11) | def process(self, parameters=None, data=None): FILE: src/opensemanticetl/enhance_entity_linking.py function taxonomy2fields (line 17) | def taxonomy2fields(taxonomy, field, separator="\t", subfields_suffix="_... class enhance_entity_linking (line 48) | class enhance_entity_linking(etl_plugin_core.Plugin): method process (line 50) | def process(self, parameters=None, data=None): FILE: src/opensemanticetl/enhance_extract_email.py class enhance_extract_email (line 11) | class enhance_extract_email(object): method process (line 12) | def process(self, parameters=None, data=None): FILE: src/opensemanticetl/enhance_extract_hashtags.py class enhance_extract_hashtags (line 4) | class enhance_extract_hashtags(object): method process (line 6) | def process(self, parameters=None, data=None): FILE: src/opensemanticetl/enhance_extract_law.py function get_taxonomy (line 16) | def get_taxonomy(law_clause, law_code = None): class enhance_extract_law (line 32) | class enhance_extract_law(etl_plugin_core.Plugin): method process (line 34) | def process(self, parameters=None, data=None): FILE: src/opensemanticetl/enhance_extract_money.py class enhance_extract_money (line 12) | class enhance_extract_money(etl_plugin_core.Plugin): method process (line 17) | def process(self, parameters=None, data=None): FILE: src/opensemanticetl/enhance_extract_phone.py function normalize_phonenumber (line 12) | def normalize_phonenumber(phone): class enhance_extract_phone (line 31) | class enhance_extract_phone(object): method process (line 32) | def process(self, parameters=None, data=None): FILE: src/opensemanticetl/enhance_extract_text_tika_server.py function in_parsers (line 8) | def in_parsers(parser, parsers): class enhance_extract_text_tika_server (line 23) | class enhance_extract_text_tika_server(object): method process (line 33) | def process(self, parameters=None, data=None): FILE: src/opensemanticetl/enhance_file_mtime.py class enhance_file_mtime (line 12) | class enhance_file_mtime(object): method process (line 13) | def process(self, parameters=None, data=None): FILE: src/opensemanticetl/enhance_file_size.py class enhance_file_size (line 11) | class enhance_file_size(object): method process (line 12) | def process(self, parameters=None, data=None): FILE: src/opensemanticetl/enhance_html.py class enhance_html (line 8) | class enhance_html(object): method elements2data (line 10) | def elements2data(self, element, data, path=None, recursive=True): method process (line 40) | def process(self, parameters=None, data=None): FILE: src/opensemanticetl/enhance_mapping_id.py class enhance_mapping_id (line 9) | class enhance_mapping_id(object): method process (line 11) | def process(self, parameters=None, data=None): function mapping (line 25) | def mapping(value, mappings=None): function mapping_reverse (line 53) | def mapping_reverse(value, mappings=None): FILE: src/opensemanticetl/enhance_mimetype.py class enhance_mimetype (line 10) | class enhance_mimetype(object): method process (line 12) | def process(self, parameters=None, data=None): FILE: src/opensemanticetl/enhance_multilingual.py class enhance_multilingual (line 10) | class enhance_multilingual(object): method process (line 23) | def process(self, parameters=None, data=None): FILE: src/opensemanticetl/enhance_ner_spacy.py class enhance_ner_spacy (line 14) | class enhance_ner_spacy(object): method process (line 16) | def process(self, parameters=None, data=None): FILE: src/opensemanticetl/enhance_ner_stanford.py class enhance_ner_stanford (line 11) | class enhance_ner_stanford(object): method multi_word_entities (line 14) | def multi_word_entities(self, entities): method process (line 53) | def process(self, parameters=None, data=None): FILE: src/opensemanticetl/enhance_ocr.py class enhance_ocr (line 7) | class enhance_ocr(object): method process (line 20) | def process(self, parameters=None, data=None): FILE: src/opensemanticetl/enhance_path.py class enhance_path (line 7) | class enhance_path(object): method process (line 9) | def process(self, parameters=None, data=None): FILE: src/opensemanticetl/enhance_pdf_ocr.py function pdfimages2text (line 15) | def pdfimages2text(filename, lang='eng', verbose=False, function load_cache (line 71) | def load_cache(filename, cache, lang='eng', function append_page (line 86) | def append_page(dct, n, page): class enhance_pdf_ocr (line 98) | class enhance_pdf_ocr(etl_plugin_core.Plugin): method process (line 116) | def process(self, parameters=None, data=None): FILE: src/opensemanticetl/enhance_pdf_page.py class enhance_pdf_page (line 15) | class enhance_pdf_page(etl_plugin_core.Plugin): method process (line 31) | def process(self, parameters=None, data=None): FILE: src/opensemanticetl/enhance_pdf_page_preview.py class enhance_pdf_page_preview (line 11) | class enhance_pdf_page_preview(etl_plugin_core.Plugin): method process (line 18) | def process(self, parameters=None, data=None): FILE: src/opensemanticetl/enhance_pst.py class enhance_pst (line 15) | class enhance_pst(etl_plugin_core.Plugin): method process (line 20) | def process(self, parameters=None, data=None): FILE: src/opensemanticetl/enhance_rdf.py class enhance_rdf (line 18) | class enhance_rdf(etl_plugin_core.Plugin): method __init__ (line 20) | def __init__(self, verbose=False): method get_labels (line 32) | def get_labels(self, subject): method get_values (line 65) | def get_values(self, obj): method get_preferred_label (line 98) | def get_preferred_label(self, subject, lang='en'): method etl_graph (line 130) | def etl_graph(self, parameters): method etl_graph_file (line 268) | def etl_graph_file(self, docid, filename, parameters=None): method process (line 277) | def process(self, parameters=None, data=None): FILE: src/opensemanticetl/enhance_rdf_annotations_by_http_request.py function metaserver_url (line 11) | def metaserver_url(metaserver, docid): function getmeta_modified (line 27) | def getmeta_modified(metaservers, docid, verbose=False): function getmeta_rdf_from_server (line 68) | def getmeta_rdf_from_server(metaserver, data, property2facet, docid, ver... class enhance_rdf_annotations_by_http_request (line 145) | class enhance_rdf_annotations_by_http_request(object): method process (line 147) | def process(self, parameters=None, data=None): FILE: src/opensemanticetl/enhance_regex.py function regex2facet (line 8) | def regex2facet(data, text, regex, group, facet, verbose=False): function readregexesfromfile (line 33) | def readregexesfromfile(data, text, filename, verbose=False): class enhance_regex (line 71) | class enhance_regex(object): method process (line 72) | def process(self, parameters=None, data=None): FILE: src/opensemanticetl/enhance_sentence_segmentation.py class enhance_sentence_segmentation (line 14) | class enhance_sentence_segmentation(object): method process (line 16) | def process(self, parameters=None, data=None): FILE: src/opensemanticetl/enhance_warc.py class enhance_warc (line 14) | class enhance_warc(etl_plugin_core.Plugin): method process (line 20) | def process(self, parameters=None, data=None): FILE: src/opensemanticetl/enhance_xml.py class enhance_xml (line 6) | class enhance_xml(object): method elements2data (line 8) | def elements2data(self, element, data, path="xml"): method get_xml_filename (line 28) | def get_xml_filename(self, filename, mapping): method process (line 43) | def process(self, parameters=None, data=None): FILE: src/opensemanticetl/enhance_xmp.py function get_xmp_filename (line 10) | def get_xmp_filename(filename): class enhance_xmp (line 32) | class enhance_xmp(object): method process (line 33) | def process(self, parameters=None, data=None): FILE: src/opensemanticetl/enhance_zip.py class enhance_zip (line 10) | class enhance_zip(object): method process (line 12) | def process(self, parameters=None, data=None): method unzip_and_index_files (line 38) | def unzip_and_index_files(self, zipfilename, parameters=None, verbose=... FILE: src/opensemanticetl/etl.py class ETL (line 21) | class ETL(object): method __init__ (line 23) | def __init__(self, plugins=(), verbose=False): method set_configdefaults (line 33) | def set_configdefaults(self): method init_exporter (line 48) | def init_exporter(self): method read_configfile (line 56) | def read_configfile(self, configfile): method is_plugin_blacklisted_for_contenttype (line 71) | def is_plugin_blacklisted_for_contenttype(self, plugin, parameters, da... method process (line 147) | def process(self, parameters=None, data=None): method commit (line 270) | def commit(self): function append (line 279) | def append(data, facet, values): function error_message (line 309) | def error_message(docid, data, plugin, e): function sort_plugins (line 343) | def sort_plugins(plugins): FILE: src/opensemanticetl/etl_delete.py class Delete (line 9) | class Delete(ETL): method __init__ (line 10) | def __init__(self, verbose=False, quiet=True): method set_configdefaults (line 28) | def set_configdefaults(self): method read_configfiles (line 39) | def read_configfiles(self): method delete (line 52) | def delete(self, uri): method empty (line 62) | def empty(self): FILE: src/opensemanticetl/etl_enrich.py class ETL_Enrich (line 19) | class ETL_Enrich(ETL): method __init__ (line 21) | def __init__(self, plugins=(), verbose=False): method getfieldnames_from_plugins (line 68) | def getfieldnames_from_plugins(self): method enrich_document (line 92) | def enrich_document(self, docid): method enrich (line 161) | def enrich(self): method enrich_query (line 182) | def enrich_query(self, query): FILE: src/opensemanticetl/etl_file.py class Connector_File (line 10) | class Connector_File(ETL): method __init__ (line 12) | def __init__(self, verbose=False, quiet=True): method set_configdefaults (line 22) | def set_configdefaults(self): method read_configfiles (line 77) | def read_configfiles(self): method clean_filename (line 98) | def clean_filename(self, filename): method index (line 108) | def index(self, filename): method index_dir (line 138) | def index_dir(self, rootDir, followlinks=False): method index_file (line 174) | def index_file(self, filename, additional_plugins=()): function key_val (line 215) | def key_val(s): FILE: src/opensemanticetl/etl_filedirectory.py class Connector_Filedirectory (line 11) | class Connector_Filedirectory(Connector_File): method __init__ (line 13) | def __init__(self, verbose=False, quiet=False): FILE: src/opensemanticetl/etl_filemonitoring.py class EventHandler (line 17) | class EventHandler(pyinotify.ProcessEvent): method __init__ (line 19) | def __init__(self): method process_IN_CLOSE_WRITE (line 24) | def process_IN_CLOSE_WRITE(self, event): method process_IN_MOVED_TO (line 30) | def process_IN_MOVED_TO(self, event): method process_IN_DELETE (line 39) | def process_IN_DELETE(self, event): method move_file (line 50) | def move_file(self, src, dest): method move_dir (line 58) | def move_dir(self, src, dest): method index_file (line 66) | def index_file(self, filename): method delete_file (line 73) | def delete_file(self, filename): class Filemonitor (line 85) | class Filemonitor(ETL): method __init__ (line 87) | def __init__(self, verbose=False): method read_configfiles (line 117) | def read_configfiles(self): method add_watch (line 125) | def add_watch(self, filename): method add_watches_from_file (line 131) | def add_watches_from_file(filename): method watch (line 140) | def watch(self): FILE: src/opensemanticetl/etl_hypothesis.py class Connector_Hypothesis (line 19) | class Connector_Hypothesis(ETL): method etl_document (line 45) | def etl_document(self, uri): method etl_annotation (line 78) | def etl_annotation(self, annotation): method etl_annotations (line 119) | def etl_annotations(self, last_update="", user=None, group=None, tag=N... FILE: src/opensemanticetl/etl_plugin_core.py class Plugin (line 10) | class Plugin(object): method filter (line 16) | def filter(self, parameters=None, data=None): function get_text (line 85) | def get_text(data): function append (line 166) | def append(data, facet, values): function get_preflabels (line 196) | def get_preflabels(values): function get_all_matchtexts (line 214) | def get_all_matchtexts(values): FILE: src/opensemanticetl/etl_rss.py class Connector_RSS (line 12) | class Connector_RSS(Connector_Web): method __init__ (line 14) | def __init__(self, verbose=False, quiet=True): method read_configfiles (line 21) | def read_configfiles(self): method index (line 47) | def index(self, uri): FILE: src/opensemanticetl/etl_sitemap.py class Connector_Sitemap (line 12) | class Connector_Sitemap(Connector_Web): method __init__ (line 14) | def __init__(self, verbose=False, quiet=True): method read_configfiles (line 22) | def read_configfiles(self): method index (line 45) | def index(self, sitemap): FILE: src/opensemanticetl/etl_sparql.py function download_rdf_from_sparql_endpoint (line 17) | def download_rdf_from_sparql_endpoint(endpoint, query): function sparql_select_to_list_file (line 40) | def sparql_select_to_list_file(endpoint, query, filename=None): class Connector_SPARQL (line 71) | class Connector_SPARQL(ETL): method __init__ (line 73) | def __init__(self, verbose=False, quiet=True): method read_configfiles (line 81) | def read_configfiles(self): method index_rdf (line 99) | def index_rdf(self, endpoint, query): method index_select (line 116) | def index_select(self, endpoint, query): method index (line 139) | def index(self, endpoint, query): FILE: src/opensemanticetl/etl_twitter_scraper.py function index_tweet (line 19) | def index_tweet(obj, config): function index (line 64) | def index(search=None, username=None, Profile_full=False, limit=None, In... FILE: src/opensemanticetl/etl_web.py class Connector_Web (line 13) | class Connector_Web(Connector_File): method __init__ (line 15) | def __init__(self, verbose=False, quiet=True): method set_configdefaults (line 23) | def set_configdefaults(self): method read_configfiles (line 61) | def read_configfiles(self): method read_mtime_from_html (line 80) | def read_mtime_from_html(self, tempfilename): method index (line 125) | def index(self, uri, last_modified=False, downloaded_file=False, downl... FILE: src/opensemanticetl/etl_web_crawl.py class OpenSemanticETL_Spider (line 15) | class OpenSemanticETL_Spider(CrawlSpider): method parse_item (line 19) | def parse_item(self, response): function index (line 42) | def index(uri, crawler_type="PATH"): FILE: src/opensemanticetl/export_elasticsearch.py class export_elasticsearch (line 6) | class export_elasticsearch(object): method __init__ (line 8) | def __init__(self, config=None): method process (line 24) | def process(self, parameters=None, data=None): method update (line 38) | def update(self, docid=None, data=None, parameters=None): method get_lastmodified (line 56) | def get_lastmodified(self, docid, parameters=None): method commit (line 76) | def commit(self): FILE: src/opensemanticetl/export_json.py class export_json (line 4) | class export_json(object): method __init__ (line 6) | def __init__(self, config=None): method process (line 16) | def process(self, parameters=None, data=None): FILE: src/opensemanticetl/export_neo4j.py class export_neo4j (line 10) | class export_neo4j(object): method __init__ (line 12) | def __init__(self, config=None): method process (line 17) | def process(self, parameters=None, data=None): FILE: src/opensemanticetl/export_print.py class export_print (line 4) | class export_print(object): method __init__ (line 6) | def __init__(self, config=None): method process (line 16) | def process(self, parameters=None, data=None): FILE: src/opensemanticetl/export_queue_files.py class export_queue_files (line 8) | class export_queue_files(object): method __init__ (line 10) | def __init__(self, config=None): method process (line 15) | def process(self, parameters=None, data=None): FILE: src/opensemanticetl/export_solr.py class export_solr (line 16) | class export_solr(object): method __init__ (line 18) | def __init__(self, config=None): method process (line 45) | def process(self, parameters=None, data=None): method update (line 98) | def update(self, data, add=False, fields_set=(), commit=None): method post (line 117) | def post(self, data=None, docid=None, commit=None): method tag (line 195) | def tag(self, docid=None, field=None, value=None, data=None): method update_by_query (line 219) | def update_by_query(self, query, field=None, value=None, data=None, qu... method get_data (line 294) | def get_data(self, docid, fields): method commit (line 312) | def commit(self): method get_lastmodified (line 320) | def get_lastmodified(self, docid): method delete (line 337) | def delete(self, parameters, docid=None, query=None,): method append_synonyms (line 362) | def append_synonyms(self, resourceid, synonyms): function solr_mask (line 370) | def solr_mask(string_to_mask, solr_specialchars='\+-&|!(){}[]^"~*?:/'): FILE: src/opensemanticetl/filter_blacklist.py function is_in_lists (line 7) | def is_in_lists(listfiles, value, match=None): function is_in_list (line 28) | def is_in_list(filename, value, match=None): class filter_blacklist (line 68) | class filter_blacklist(object): method process (line 70) | def process(self, parameters=None, data=None): FILE: src/opensemanticetl/filter_file_not_modified.py class filter_file_not_modified (line 14) | class filter_file_not_modified(object): method __init__ (line 16) | def __init__(self): method process (line 25) | def process(self, parameters=None, data=None): FILE: src/opensemanticetl/move_indexed_file.py function move_files (line 9) | def move_files(host: str, moves: dict, prefix=""): function move_dir (line 37) | def move_dir(host: str, src: str, dest: str, prefix=""): function change_path (line 57) | def change_path(prefix: str): function change_dir (line 71) | def change_dir(prefix: str, src: str, dest: str): function _change_path (line 100) | def _change_path(data: dict, dest_components: tuple, prefix: str = "") -... function prepare_payload (line 121) | def prepare_payload(adds, delete_ids): class DuplicateKey (line 131) | class DuplicateKey(str): method __hash__ (line 134) | def __hash__(self): function extract_path (line 138) | def extract_path(data: dict) -> str: function extract_path_components (line 144) | def extract_path_components(data: dict): function dict_map (line 158) | def dict_map(mapping: dict): function append_prefix (line 165) | def append_prefix(prefix: str): function get_files (line 172) | def get_files(host: str, ids: list) -> list: function get_files_in_dir (line 180) | def get_files_in_dir(host: str, path: str) -> list: function get (line 190) | def get(host: str, query: str) -> list: function get_pages (line 194) | def get_pages(host: str, query: str, limit=50): function post (line 209) | def post(host: str, data: dict): FILE: src/opensemanticetl/tasks.py function delete (line 56) | def delete(uri): function index_file (line 65) | def index_file(filename, additional_plugins=(), wait=0, commit=False, co... function index_filedirectory (line 89) | def index_filedirectory(filename, config=None): function index_web (line 110) | def index_web(uri, wait=0, downloaded_file=False, downloaded_headers=None): function index_web_crawl (line 126) | def index_web_crawl(uri, crawler_type="PATH"): function index_sitemap (line 138) | def index_sitemap(uri): function index_rss (line 154) | def index_rss(uri): function enrich (line 166) | def enrich(plugins, uri, wait=0): function index_twitter_scraper (line 194) | def index_twitter_scraper(search=None, username=None, Profile_full=False... FILE: src/opensemanticetl/test_enhance_detect_language_tika_server.py class Test_enhance_detect_language_tika_server (line 8) | class Test_enhance_detect_language_tika_server(unittest.TestCase): method test (line 10) | def test(self): FILE: src/opensemanticetl/test_enhance_extract_email.py class Test_enhance_extract_email (line 8) | class Test_enhance_extract_email(unittest.TestCase): method test (line 10) | def test(self): FILE: src/opensemanticetl/test_enhance_extract_law.py class Test_enhance_extract_law (line 8) | class Test_enhance_extract_law(unittest.TestCase): method test (line 10) | def test(self): method test_blacklist (line 50) | def test_blacklist(self): FILE: src/opensemanticetl/test_enhance_extract_money.py class Test_enhance_extract_money (line 8) | class Test_enhance_extract_money(unittest.TestCase): method test (line 10) | def test(self): method test_numerizer (line 58) | def test_numerizer(self): FILE: src/opensemanticetl/test_enhance_extract_text_tika_server.py class TestEnhanceExtractTextTikaServer (line 9) | class TestEnhanceExtractTextTikaServer(unittest.TestCase): method delete_ocr_cache_entries (line 12) | def delete_ocr_cache_entries(self): method setUp (line 23) | def setUp(self): method tearDown (line 25) | def tearDown(self): method test_text_extraction_pdf (line 28) | def test_text_extraction_pdf(self): method test_text_extraction_pdf_ocr (line 53) | def test_text_extraction_pdf_ocr(self): method test_text_extraction_pdf_ocr_cache (line 78) | def test_text_extraction_pdf_ocr_cache(self): method test_ocr_png (line 112) | def test_ocr_png(self): method test_ocr_jpg (line 128) | def test_ocr_jpg(self): method test_disabled_ocr_png (line 144) | def test_disabled_ocr_png(self): FILE: src/opensemanticetl/test_enhance_mapping_id.py class Test_enhance_mapping_id (line 8) | class Test_enhance_mapping_id(unittest.TestCase): method test (line 10) | def test(self): method test_reverse (line 33) | def test_reverse(self): FILE: src/opensemanticetl/test_enhance_ner_spacy.py class Test_enhance_ner_spacy (line 15) | class Test_enhance_ner_spacy(unittest.TestCase): method test_en (line 17) | def test_en(self): method test_de (line 34) | def test_de(self): FILE: src/opensemanticetl/test_enhance_path.py class Test_enhance_path (line 8) | class Test_enhance_path(unittest.TestCase): method test (line 10) | def test(self): FILE: src/opensemanticetl/test_enhance_pdf_ocr.py class Test_enhance_pdf_ocr (line 9) | class Test_enhance_pdf_ocr(unittest.TestCase): method test_pdf_ocr (line 12) | def test_pdf_ocr(self): FILE: src/opensemanticetl/test_enhance_regex.py class Test_enhance_regex (line 8) | class Test_enhance_regex(unittest.TestCase): method test (line 10) | def test(self): FILE: src/opensemanticetl/test_enhance_warc.py class Test_enhance_warc (line 11) | class Test_enhance_warc(unittest.TestCase): method test_warc (line 14) | def test_warc(self): FILE: src/opensemanticetl/test_etl_file.py class Test_ETL_file (line 10) | class Test_ETL_file(unittest.TestCase): method test_pdf_and_ocr_by_tika (line 12) | def test_pdf_and_ocr_by_tika(self): method test_ocr_by_plugin_enhance_pdf_ocr (line 57) | def test_ocr_by_plugin_enhance_pdf_ocr(self): FILE: src/opensemanticetl/test_move_indexed_files.py class TestMove (line 10) | class TestMove(unittest.TestCase): method test_move_files (line 11) | def test_move_files(self): method test_move_dir (line 45) | def test_move_dir(self): method test_get_pages (line 82) | def test_get_pages(self): function mock_response (line 109) | def mock_response(data):