SYMBOL INDEX (289 symbols across 30 files) FILE: fabfile.py function test (line 6) | def test(): function lint (line 10) | def lint(): function view_cover (line 15) | def view_cover(): function clean (line 19) | def clean(): FILE: nlpre/Grammars/parenthesis_nester.py class parenthesis_nester (line 4) | class parenthesis_nester(object): method __init__ (line 10) | def __init__(self): method __call__ (line 25) | def __call__(self, line): FILE: nlpre/Grammars/reference_patterns.py class reference_patterns (line 5) | class reference_patterns: method __init__ (line 6) | def __init__(self): FILE: nlpre/decaps_text.py class decaps_text (line 5) | class decaps_text(object): method __init__ (line 12) | def __init__(self): method diffn (line 16) | def diffn(self, s1, s2): method modify_word (line 20) | def modify_word(self, org): method __call__ (line 38) | def __call__(self, text): FILE: nlpre/dedash.py class dedash (line 8) | class dedash: method __init__ (line 18) | def __init__(self): method __call__ (line 26) | def __call__(self, text): class dedash_spaCy (line 30) | class dedash_spaCy: method __init__ (line 34) | def __init__(self, nlp): method load_vocab (line 53) | def load_vocab(self): method requires_merge (line 62) | def requires_merge(self, tokens): method __call__ (line 66) | def __call__(self, doc): FILE: nlpre/identify_parenthetical_phrases.py class identify_parenthetical_phrases (line 7) | class identify_parenthetical_phrases(object): method __init__ (line 14) | def __init__(self): method __call__ (line 19) | def __call__(self, text): method _is_valid_abbr (line 48) | def _is_valid_abbr(self, item): method _check_matching (line 73) | def _check_matching(self, word, k, tokens): FILE: nlpre/pos_tokenizer.py class pos_tokenizer (line 5) | class pos_tokenizer(object): method __init__ (line 28) | def __init__(self, POS_blacklist): method _keep_root (line 80) | def _keep_root(self, token, word_order=0): method __call__ (line 88) | def __call__(self, text, use_base=True): FILE: nlpre/presets/__init__.py class Generic_Preprocessing_Pipeline (line 8) | class Generic_Preprocessing_Pipeline: method __init__ (line 9) | def __init__(self, n_cores=1): method __call__ (line 15) | def __call__(self, text): method batch (line 22) | def batch(self, text_list): class Grants (line 31) | class Grants(Generic_Preprocessing_Pipeline): method __init__ (line 32) | def __init__(self, *args, **kwargs): FILE: nlpre/replace_acronyms.py class replace_acronyms (line 7) | class replace_acronyms(object): method __init__ (line 34) | def __init__( method _build_acronym_dict (line 70) | def _build_acronym_dict(self, counter): method check_self_counter (line 83) | def check_self_counter(self, token, doc_counter): method word_belongs (line 100) | def word_belongs(self, word, acronym_phrases): method check_acronym (line 127) | def check_acronym(self, token): method check_phrase (line 142) | def check_phrase(self, token, pos, tokens, counter): method __call__ (line 190) | def __call__(self, document, doc_counter=None): FILE: nlpre/replace_from_dictionary.py class replace_from_dictionary (line 9) | class replace_from_dictionary(object): method __init__ (line 22) | def __init__(self, f_dict=None, prefix="", suffix=""): method __call__ (line 55) | def __call__(self, doc): FILE: nlpre/separate_reference.py class separate_reference (line 11) | class separate_reference: method __init__ (line 26) | def __init__(self, reference_token=False, f_wordlist=None): method __call__ (line 47) | def __call__(self, text): method single_number_pattern (line 108) | def single_number_pattern(self, token): method identify_reference_punctuation_pattern (line 143) | def identify_reference_punctuation_pattern( method end_parens_match (line 211) | def end_parens_match( FILE: nlpre/separated_parenthesis.py class separated_parenthesis (line 7) | class separated_parenthesis(object): method __init__ (line 25) | def __init__(self, min_keep_length=0): method __call__ (line 39) | def __call__(self, text): method paren_pop (line 106) | def paren_pop(self, parsed_tokens): method paren_pop_helper (line 123) | def paren_pop_helper(self, tokens): function remove_trailing_space (line 190) | def remove_trailing_space(s, punctuation="!?.,"): FILE: nlpre/spacy_init.py function dash_merger (line 19) | def dash_merger(doc): FILE: nlpre/titlecaps.py class titlecaps (line 5) | class titlecaps(object): method __init__ (line 14) | def __init__(self, min_length=4): method __call__ (line 25) | def __call__(self, text): function is_any_lowercase (line 54) | def is_any_lowercase(sentence): FILE: nlpre/token_replacement.py class token_replacement (line 1) | class token_replacement(object): method __init__ (line 32) | def __init__(self, remove=False): method __call__ (line 62) | def __call__(self, text): FILE: nlpre/unidecoder.py class unidecoder (line 5) | class unidecoder(object): method __init__ (line 15) | def __init__(self): method __call__ (line 19) | def __call__(self, unicode_text): FILE: nlpre/url_replacement.py class url_replacement (line 4) | class url_replacement(object): method __init__ (line 11) | def __init__(self, email_replacement="", url_replacement=""): method __call__ (line 18) | def __call__(self, text): FILE: tests/decaps_text_tests.py class Decaps_Text_Test (line 5) | class Decaps_Text_Test: method setup_class (line 7) | def setup_class(cls): method first_capital_single_sentence_test (line 10) | def first_capital_single_sentence_test(self): method capital_in_middle_test (line 17) | def capital_in_middle_test(self): method multiple_capital_test (line 24) | def multiple_capital_test(self): method capital_multiple_sentence_test (line 31) | def capital_multiple_sentence_test(self): FILE: tests/dedash_tests.py class Dedash_Test (line 5) | class Dedash_Test: method setup_class (line 7) | def setup_class(cls): method single_word_dash_test (line 10) | def single_word_dash_test(self): method single_word_multi_space_dash_test (line 17) | def single_word_multi_space_dash_test(self): method dash_not_word_test (line 24) | def dash_not_word_test(self): method firstword_not_alpha_test (line 31) | def firstword_not_alpha_test(self): method multiple_caps_test (line 38) | def multiple_caps_test(self): method multiple_caps_second_word_test (line 45) | def multiple_caps_second_word_test(self): method one_letter_word_test (line 52) | def one_letter_word_test(self): method no_dash_test (line 59) | def no_dash_test(self): method no_alpha_dash_test (line 66) | def no_alpha_dash_test(self): method dash_no_space_test (line 73) | def dash_no_space_test(self): method dash_capitalized_word_test (line 80) | def dash_capitalized_word_test(self): FILE: tests/full_test.py class Full_Test (line 11) | class Full_Test: method __init__ (line 12) | def __init__(self): method full_run (line 57) | def full_run(self, text): method acronym_counter (line 64) | def acronym_counter(self, *docs): method document1_test (line 67) | def document1_test(self): method document2_test (line 78) | def document2_test(self): method check_line_by_line (line 88) | def check_line_by_line(self, docA, docB): FILE: tests/identify_parenthetical_phrases_tests.py class Parenthetical_Phrases_Tests (line 5) | class Parenthetical_Phrases_Tests: method setup_class (line 7) | def setup_class(cls): method OD_of_the_not_included_test (line 10) | def OD_of_the_not_included_test(self): method EPA_test (line 16) | def EPA_test(self): method EPA_multiple_words_in_parans_test (line 24) | def EPA_multiple_words_in_parans_test(self): method EPA_multiple_test (line 29) | def EPA_multiple_test(self): method EPA_nestedParans_test (line 40) | def EPA_nestedParans_test(self): method EPA_nestedParans2_test (line 45) | def EPA_nestedParans2_test(self): method EPA_curly_test (line 50) | def EPA_curly_test(self): method EPA_bracket_test (line 58) | def EPA_bracket_test(self): method EPA_lowercase_test (line 66) | def EPA_lowercase_test(self): method single_letter_test (line 71) | def single_letter_test(self): method HHS_and_not_included_test (line 76) | def HHS_and_not_included_test(self): method HHS_incomplete_phrase_test (line 84) | def HHS_incomplete_phrase_test(self): method EPA_incomplete_phrase_test (line 89) | def EPA_incomplete_phrase_test(self): method EPA_incomplete_phrase2_test (line 94) | def EPA_incomplete_phrase2_test(self): method HHS_and_included_test (line 99) | def HHS_and_included_test(self): method BIA_of_not_included_test (line 105) | def BIA_of_not_included_test(self): method ADA_with_not_included_test (line 111) | def ADA_with_not_included_test(self): method CADE_for_not_included_test (line 119) | def CADE_for_not_included_test(self): method HHS_comma_test (line 139) | def HHS_comma_test(self): method POC_of_included_test (line 147) | def POC_of_included_test(self): method ASDs_plural_test (line 153) | def ASDs_plural_test(self): method eQTLs_multiple_lower_case_test (line 159) | def eQTLs_multiple_lower_case_test(self): method C5aR_letter_test (line 165) | def C5aR_letter_test(self): method AFB_dash_test (line 171) | def AFB_dash_test(self): method SOCE_plus_sign_test (line 183) | def SOCE_plus_sign_test(self): method epa_od_hhs_test (line 189) | def epa_od_hhs_test(self): method bad_doc_test (line 206) | def bad_doc_test(self): method parser_error_with_two_mismatches (line 211) | def parser_error_with_two_mismatches(self): method iterating_over_parenthesis_crash_test (line 231) | def iterating_over_parenthesis_crash_test(self): FILE: tests/pos_tokenizer_tests.py class POS_Tokenizer_Test (line 5) | class POS_Tokenizer_Test: method setup_class (line 7) | def setup_class(cls): method keep_nouns_test1 (line 26) | def keep_nouns_test1(self): method keep_nouns_test2 (line 33) | def keep_nouns_test2(self): method keep_nouns_test3 (line 42) | def keep_nouns_test3(self): method keep_nouns_test4 (line 50) | def keep_nouns_test4(self): method keep_nouns_test5 (line 60) | def keep_nouns_test5(self): method keep_nouns_test6 (line 69) | def keep_nouns_test6(self): method keep_mesh_test (line 78) | def keep_mesh_test(self): method keep_phrase_test (line 85) | def keep_phrase_test(self): method possesive_word_test (line 92) | def possesive_word_test(self): method cardinal_word_test (line 99) | def cardinal_word_test(self): method symbol_test (line 106) | def symbol_test(self): method unknown_POS_test (line 113) | def unknown_POS_test(self): method implied_verb_test (line 117) | def implied_verb_test(self): FILE: tests/replace_acronyms_test.py class Parens_Replace_Test (line 6) | class Parens_Replace_Test: method setup_class (line 8) | def setup_class(cls): method acronym_without_counter_test (line 11) | def acronym_without_counter_test(self): method acronym_in_same_doc_test (line 24) | def acronym_in_same_doc_test(self): method counter_must_be_infered_test (line 41) | def counter_must_be_infered_test(self): method acronym_in_same_doc_underscore_default_test (line 58) | def acronym_in_same_doc_underscore_default_test(self): method acronym_in_same_doc_additional_words_test (line 76) | def acronym_in_same_doc_additional_words_test(self): method multiple_acronyms_same_doc_test (line 94) | def multiple_acronyms_same_doc_test(self): method almost_acronym_but_lowercase_test (line 118) | def almost_acronym_but_lowercase_test(self): method duplicate_acronyms_included_test (line 135) | def duplicate_acronyms_included_test(self): method preprocess_test (line 161) | def preprocess_test(self): method tokenize_phrase_test (line 192) | def tokenize_phrase_test(self): method tokenize_phrase_prefix_test (line 209) | def tokenize_phrase_prefix_test(self): method tokenize_phrase_suffix_test (line 227) | def tokenize_phrase_suffix_test(self): method dash_test (line 245) | def dash_test(self): method lowercase_first_letter_match_test (line 261) | def lowercase_first_letter_match_test(self): method parsing_parenthesis_test (line 272) | def parsing_parenthesis_test(self): method use_most_common_test (line 291) | def use_most_common_test(self): method ignore_most_common_test (line 303) | def ignore_most_common_test(self): method duplicate_acronyms_test (line 315) | def duplicate_acronyms_test(self): method count_multiple_docs_test (line 333) | def count_multiple_docs_test(self): method parsing_misidentifed_test (line 354) | def parsing_misidentifed_test(self): FILE: tests/replace_from_dictionary_tests.py class Replace_From_Dictionary_Test (line 6) | class Replace_From_Dictionary_Test: method setup_class (line 8) | def setup_class(cls): method bad_dictionary_test (line 11) | def bad_dictionary_test(self): method custom_dictionary_test (line 16) | def custom_dictionary_test(self): method default_dictionary_test (line 25) | def default_dictionary_test(self): method hydroxyethylrutoside_test1 (line 35) | def hydroxyethylrutoside_test1(self): method hydroxyethylrutoside_test2 (line 42) | def hydroxyethylrutoside_test2(self): method pandemic_test (line 49) | def pandemic_test(self): method dimethylethyl_test (line 64) | def dimethylethyl_test(self): method dimethylethyl_test (line 71) | def dimethylethyl_test(self): method dimethylethyl_parens_test (line 78) | def dimethylethyl_parens_test(self): method multiple_paranthesis_test (line 85) | def multiple_paranthesis_test(self): method extra_paranthesis_test (line 92) | def extra_paranthesis_test(self): method methyl_test (line 99) | def methyl_test(self): method mesh_middle_sentence (line 108) | def mesh_middle_sentence(self): method punctuation_after_mesh (line 115) | def punctuation_after_mesh(self): method apostrophe_test (line 122) | def apostrophe_test(self): method plus_test (line 129) | def plus_test(self): method colon_test (line 136) | def colon_test(self): FILE: tests/separate_reference_test.py class References_Test (line 5) | class References_Test: method setup_class (line 7) | def setup_class(cls): method number_test (line 11) | def number_test(self): method number_in_parenthesis_test (line 18) | def number_in_parenthesis_test(self): method number_with_letter_test (line 25) | def number_with_letter_test(self): method number_with_multiple_letter_test (line 32) | def number_with_multiple_letter_test(self): method number_reference_token_test (line 39) | def number_reference_token_test(self): method reference_in_parenthesis_test (line 46) | def reference_in_parenthesis_test(self): method parenthetical_reference_in_parenthesis_test (line 54) | def parenthetical_reference_in_parenthesis_test(self): method parenthetical_reference_in_parenthesis_tokens_test (line 62) | def parenthetical_reference_in_parenthesis_tokens_test(self): method standard_word_in_reference_in_parenthesis_test (line 70) | def standard_word_in_reference_in_parenthesis_test(self): method standard_word_in_reference_in_parenthesis_token_test (line 78) | def standard_word_in_reference_in_parenthesis_token_test(self): method parenthesis_with_dashes_test (line 86) | def parenthesis_with_dashes_test(self): method parenthesis_with_dashes_period_test (line 94) | def parenthesis_with_dashes_period_test(self): method parenthesis_with_dashes_period_token_test (line 102) | def parenthesis_with_dashes_period_token_test(self): method bracket_test (line 110) | def bracket_test(self): method word_that_begins_with_number_parenthetical_reference_test (line 134) | def word_that_begins_with_number_parenthetical_reference_test(self): method period_one_number_test (line 141) | def period_one_number_test(self): method period_one_number_in_parens_test (line 148) | def period_one_number_in_parens_test(self): method dashed_word_period_one_number_test (line 155) | def dashed_word_period_one_number_test(self): method dash_with_letters_period_test (line 162) | def dash_with_letters_period_test(self): method period_dash_test (line 169) | def period_dash_test(self): method period_dash_reference_token_test (line 176) | def period_dash_reference_token_test(self): method comma_dash_test (line 183) | def comma_dash_test(self): method dash_test (line 190) | def dash_test(self): method dash_with_letters_test (line 197) | def dash_with_letters_test(self): method comma_test (line 204) | def comma_test(self): method multiple_comma_test (line 211) | def multiple_comma_test(self): method multiple_comma_in_parens_test (line 218) | def multiple_comma_in_parens_test(self): method chemical_dash_test (line 225) | def chemical_dash_test(self): method word_that_should_end_with_number_test (line 232) | def word_that_should_end_with_number_test(self): method word_that_begins_with_number_test (line 239) | def word_that_begins_with_number_test(self): method pattern_in_middle_of_word_test (line 246) | def pattern_in_middle_of_word_test(self): method non_word_with_reference_test (line 253) | def non_word_with_reference_test(self): method number_in_word_with_reference_test (line 260) | def number_in_word_with_reference_test(self): method single_letter_false_positive_test (line 267) | def single_letter_false_positive_test(self): FILE: tests/separated_parenthesis_tests.py class Separated_Parenthesis_Tests (line 6) | class Separated_Parenthesis_Tests: method setup_class (line 8) | def setup_class(cls): method single_parenthesis_pair_test (line 11) | def single_parenthesis_pair_test(self): method single_brackets_pair_test (line 18) | def single_brackets_pair_test(self): method single_curly_pair_test (line 25) | def single_curly_pair_test(self): method multiple_brackets_pair_test (line 32) | def multiple_brackets_pair_test(self): method multiple_curly_pair_test (line 39) | def multiple_curly_pair_test(self): method multiple_parenthesis_pair_test (line 46) | def multiple_parenthesis_pair_test(self): method multiple_parenthesis_pair_expand_test (line 53) | def multiple_parenthesis_pair_expand_test(self): method multiple_parenthesis_multiple_inner_pair_test (line 60) | def multiple_parenthesis_multiple_inner_pair_test(self): method single_parenthesis_test (line 68) | def single_parenthesis_test(self): method single_bracket_test (line 75) | def single_bracket_test(self): method single_curly_test (line 82) | def single_curly_test(self): method unbalanced_parenthesis_test (line 89) | def unbalanced_parenthesis_test(self): method single_sentence_parens_test (line 96) | def single_sentence_parens_test(self): method empty_parens_test (line 103) | def empty_parens_test(self): method multiple_parens_single_sentence_test (line 110) | def multiple_parens_single_sentence_test(self): method clipped_sentences_test (line 117) | def clipped_sentences_test(self): method mixed_parens_with_punctuation_test (line 131) | def mixed_parens_with_punctuation_test(self): method mixed_parens_with_punctuation_expanded_test (line 138) | def mixed_parens_with_punctuation_expanded_test(self): method remove_trailing_space_with_small_n_test (line 144) | def remove_trailing_space_with_small_n_test(self): FILE: tests/titlecaps_tests.py class Titlecaps_Test (line 5) | class Titlecaps_Test: method setup_class (line 7) | def setup_class(cls): method allcaps_test (line 10) | def allcaps_test(self): method mostlycaps_test (line 17) | def mostlycaps_test(self): method multiple_sentance_test (line 24) | def multiple_sentance_test(self): method numbers_test (line 31) | def numbers_test(self): method long_enough_sentence_test (line 38) | def long_enough_sentence_test(self): class Titlecaps_With_DeDash_Test (line 48) | class Titlecaps_With_DeDash_Test: method setup_class (line 55) | def setup_class(cls): method caps_before_dedash_test (line 61) | def caps_before_dedash_test(self): FILE: tests/token_replacement_tests.py class Token_Test (line 8) | class Token_Test: method setup_class (line 10) | def setup_class(cls): method ampersand_test (line 13) | def ampersand_test(self): method percent_test (line 19) | def percent_test(self): method remove_test (line 25) | def remove_test(self): method greater_test (line 31) | def greater_test(self): method less_test (line 37) | def less_test(self): method equal_test (line 43) | def equal_test(self): method pound_test (line 49) | def pound_test(self): method tilde_test (line 55) | def tilde_test(self): method forwardslash_test (line 61) | def forwardslash_test(self): method backslash_test (line 67) | def backslash_test(self): method line_test (line 73) | def line_test(self): method dollar_test (line 79) | def dollar_test(self): method colon_test (line 85) | def colon_test(self): method doubledash_test (line 91) | def doubledash_test(self): method singlequote_test (line 104) | def singlequote_test(self): method doublequote_test (line 110) | def doublequote_test(self): FILE: tests/unidecoder_tests.py class Unidecoder_Test (line 6) | class Unidecoder_Test: method setup_class (line 8) | def setup_class(cls): method greek_test (line 11) | def greek_test(self): method german_test (line 17) | def german_test(self): method dutch_test (line 23) | def dutch_test(self): method more_greek_test (line 29) | def more_greek_test(self): FILE: tests/url_replacement_tests.py class Unidecoder_Test (line 6) | class Unidecoder_Test: method setup_class (line 8) | def setup_class(cls): method HTTP_link_test (line 13) | def HTTP_link_test(self): method HTTPS_link_test (line 19) | def HTTPS_link_test(self): method www_link_test (line 25) | def www_link_test(self): method ftp_link_test (line 31) | def ftp_link_test(self): method parens_around_link_test (line 37) | def parens_around_link_test(self): method HTTP_link_replacement_test (line 43) | def HTTP_link_replacement_test(self): method www_edu_link_test (line 49) | def www_edu_link_test(self): method www_email_test (line 55) | def www_email_test(self): method www_email_replace_test (line 61) | def www_email_replace_test(self):