Grammalecte  Check-in [01d15e4e8d]

// JavaScript

/* jshint esversion:6, -W097 */
/* jslint esversion:6 */
/* global require, exports, console */

"use strict";


var text = {

    _zEndOfSentence: new RegExp ('[.?!:;…]+[   ]+[»”’]?(?=[«"“‘–—   ]?[A-ZÀÂÉÈÊÎÔÇ])', "g"),
    _zEndOfSentence: new RegExp ('[.?!:;…]+[»”’)]?[   ]+[»”’]?(?=[«"“‘–—   ]*[A-ZÀÂÉÈÊÎÔÇ])', "g"),

    getSentenceBoundaries: function* (sText) {
        // generator: returns start and end of sentences found in <sText>
        let iStart = 0;
        let m;
        while ((m = this._zEndOfSentence.exec(sText)) !== null) {
            yield [iStart, this._zEndOfSentence.lastIndex];

#!python3

"""
Text tools
"""

import re
import textwrap
from itertools import chain


_zEndOfSentence = re.compile(r'[.?!:;…]+[   ]+[»”’]?(?=[«"“‘–—   ]?[A-ZÀÂÉÈÊÎÔÇ])')
_zEndOfSentence = re.compile(r'[.?!:;…]+[»”’)]?[   ]+[»”’]?(?=[«"“‘–—   ]*[A-ZÀÂÉÈÊÎÔÇ])')

def getSentenceBoundaries (sText):
    "generator: returns start and end of sentences found in <sText>"
    iStart = 0
    for m in _zEndOfSentence.finditer(sText):
        yield (iStart, m.end())
        iStart = m.end()