Index

A

argv2conf() (in module corpustools.clean_corpus), [1]

C

char_data_handler() (corpustools.format.tmxparser.TMXParser method), [1] clean_corpus() (in module corpustools.clean_corpus), [1] clean_html() (in module corpustools.clean.html) clean_htmltag() (in module corpustools.clean.html) compile_relist() (corpustools.clean.regex.RegexClean method), [1] corpustools.case.lowercase (module) corpustools.clean.html (module) corpustools.clean.length_diff (module) corpustools.clean.length_limit (module) corpustools.clean.lowercase (module), [1] corpustools.clean.regex (module), [1]

corpustools.clean.sentence_ratio (module) corpustools.clean.tokenize (module), [1] corpustools.clean.url (module) corpustools.clean.zstring (module) corpustools.clean_corpus (module), [1] corpustools.format.tmxparser (module), [1] corpustools.lib.languagecode (module) corpustools.token.chasen (module), [1] corpustools.token.moses (module), [1] corpustools.token.stanford_segmenter (module), [1] COUNTRY_ROOT (corpustools.clean.url.URLClean attribute)

E

end_element_handler() (corpustools.format.tmxparser.TMXParser method), [1]

G

GENERAL_ROOT (corpustools.clean.url.URLClean attribute)

L

LanguageCode (class in corpustools.lib.languagecode) lowercase_corpus() (in module corpustools.clean.lowercase), [1]

lowercase_file() (in module corpustools.case.lowercase) lowercase_fp() (in module corpustools.case.lowercase)

M

main() (in module corpustools.clean_corpus), [1]

O

output_dir (corpustools.format.tmxparser.TMXParser attribute)

P

parse_file() (corpustools.format.tmxparser.TMXParser method), [1] predicate() (in module corpustools.clean.length_diff), [1] (in module corpustools.clean.length_limit), [1] (in module corpustools.clean.sentence_ratio), [1]

predicate_clean() (in module corpustools.clean_corpus), [1] prepare_pattern() (corpustools.clean.url.URLClean method) PROTOCAL (corpustools.clean.url.URLClean attribute)

R

re_clean() (corpustools.clean.regex.RegexClean method), [1] re_del() (corpustools.clean.regex.RegexClean method), [1] re_repl() (corpustools.clean.regex.RegexClean method), [1] RegexClean (class in corpustools.clean.regex), [1] relist_clean() (corpustools.clean.regex.RegexClean method), [1] run() (corpustools.clean.regex.RegexClean method), [1] (corpustools.clean.url.URLClean method) (in module corpustools.clean.html) (in module corpustools.clean.lowercase), [1] (in module corpustools.clean.regex), [1] (in module corpustools.clean.tokenize), [1] (in module corpustools.clean.url) (in module corpustools.clean.zstring)

S

start_element_handler() (corpustools.format.tmxparser.TMXParser method), [1]

T

TMX_form() (corpustools.lib.languagecode.LanguageCode method) TMXParser (class in corpustools.format.tmxparser), [1] tokenize() (in module corpustools.clean.tokenize), [1] (in module corpustools.token.chasen), [1] (in module corpustools.token.moses), [1] (in module corpustools.token.stanford_segmenter), [1]

U

URLClean (class in corpustools.clean.url)

urlclean_line() (corpustools.clean.url.URLClean method)

V

validate() (in module corpustools.clean.html) (in module corpustools.clean.length_diff) (in module corpustools.clean.length_limit) (in module corpustools.clean.regex) (in module corpustools.clean.sentence_ratio) (in module corpustools.clean.url) (in module corpustools.clean.zstring)

X

xx() (corpustools.lib.languagecode.LanguageCode method)

xx_XX() (corpustools.lib.languagecode.LanguageCode method)

Z

zstring_unescape() (in module corpustools.clean.zstring)