module Cadmium::Util::Sentence

Defined in:

Constant Summary

ABBR_DETECT = /(?:\s(?:(?:(?:\w\.){2,}\w?)|(?:\w\.\w)))/: Finds abbreviations, like e.g., i.e., U.S., u.S., U.S.S.R.
CORRECT_ABBR = /(#{ABBR_DETECT})#{EOS}(\s+[a-z0-9])/
DAYS = ["mon", "tue", "wed", "thu", "fri", "sat", "sun"]
ENTITIES = ["dept", "univ", "uni", "assn", "bros", "inc", "ltd", "co", "corp", "plc"]
EOS = "\u0001"
MISC = ["vs", "etc", "no", "esp", "cf"]
MONTHS = ["jan", "feb", "mar", "apr", "may", "jun", "jul", "aug", "sep", "oct", "nov", "dec", "sept"]
PUNCTUATION_DETECT = /((?:[\.?!]|[\r\n]+)(?:\"|\'|\)|\]|\})?)(\s+)/: Finds punctuation that ends paragraphs.
STREETS = ["ave", "bld", "blvd", "cl", "ct", "cres", "dr", "rd", "st"]
TITLES = ["jr", "mr", "mrs", "ms", "dr", "prof", "sr", "sen", "rep", "rev", "gov", "atty", "supt", "det", "rev", "col", "gen", "lt", "cmdr", "adm", "capt", "sgt", "cpl", "maj"]

Class Method Summary

.abbreviation(*abbreviations)
Adds a list of abbreviations to the list that's used to detect false sentence ends.
.sentences(text)
Split the passed text into individual sentences, trim these and return as an array.

Class Method Detail

def self.abbreviation(*abbreviations) #

Adds a list of abbreviations to the list that's used to detect false sentence ends. Return the current list of abbreviations in use.

[View source]

def self.sentences(text) #

Split the passed text into individual sentences, trim these and return as an array. A sentence is marked by one of the punctuation marks ".", "?" or "!" followed by whitespace. Sequences of full stops (such as an ellipsis marker "..." and stops after a known abbreviation are ignored.