Extensions/LatinWordExtensions.cs

这里只显示每个文件的开头 60 行。登录后可以解锁完整代码。

微信扫码关注公众号，代码整理好后第一时间通知你。

using System;
using System.Linq;
using System.Text;

namespace ComLib.Extensions
{
    /// <summary>
    /// Collection of extension utility methods useful for processing latin
    /// text.
    /// </summary>
    public static class LatinWordExtensions
    {
        /// <summary>
        /// A very liberal list of whitespace characters used in unicode.
        /// Char.isWhitespace() only checks for latin1 values, this list is
        /// more comprehensive and should not be used unintelligently for
        /// stripping whitespace because it may make the target language
        /// unreadable.
        /// </summary>
        public static readonly char[] WhiteSpaceCharacters = new char[]
        {
            '\x0020', // standard space
            '\x0009', // horizontal tab
            '\x000a', // LF
            '\x000b', // line tabulation
            '\x000c', // FF (form feed)
            '\x000d', // CR
            '\x00a0', // non-breaking space
            '\x0085', // NEL (next line)
            '\x1680', // OGHAM space mark
            '\x2000', // En quad
            '\x2001', // Em quad
            '\x2002', // En space
            '\x2003', // Em space
            '\x2004', // three-per-em space
            '\x2005', // four-per-em space
            '\x2006', // six-per-em space
            '\x2007', // figure space
            '\x2008', // punctuation space
            '\x2009', // thin space
            '\x200a', // hair space
            '\x200b', // zero width space
            '\x2028', // LS (unicode line separator)
            '\x2029', // paragraph separator
            '\x202f', // narrow no-break space
            '\x205f', // medium mathematical space
            '\x3000', // ideographic space (CJKV)
        };

        /// <summary>
        /// Small list of english words that commonly excluded from abbreviations
        /// and initials.
        /// </summary>
        public static readonly string[] EnglishInitialsExclusionWords = new string[] 
        { 
            "a", "an", "as", "at", "by", "for", "from", "in", "into", "of", "on",
            "to", "the", "with"
        };

        /// <summary>