Package TEES :: Package Utils :: Module ProteinNameSplitter

Module ProteinNameSplitter

source code

Classes

[hide private]

Token

Functions

[hide private]

addTokenization(tokenization, sentence, sentenceId)

source code

getTokenization(tokenization, sentence, sentenceId, remove=False)

source code

addParse(parse, tokenization, sentence, sentenceId)

source code

getParse(parse, tokenization, sentence, sentenceId, remove=False)

source code

cutPoints(tokStart, tokEnd, entityOffsets)

source code

resolveHeads(splitParts, logFile=None)

source code

splitTokens(tokenization, sentence, logFile=None)

source code

addTokensToTree(tokens, element)

source code

mainFunc(input, output=None, parseName='McCC', tokenizationName=None, newParseName=None, newTokenizationName=None, logFileName=None, removeOld=True) source code

Variables

[hide private]

tokenIdPrefix = 'st_'

splitTokenizationName = 'split'

newParseName = 'split_parse'

splitHyphenDepName = 'hyphen'

splitSlashDepName = 'slash'

splitParensDepName = 'appos'

splitDefaultDepName = 'dep'

__package__ = 'TEES.Utils'