我有一个地址类,使用正则表达式从地址的第一行解析房屋号码,街道名称和街道类型.这段代码通常运行良好,但我发布在这里与社区分享,看看有没有人有改进的建议.
注意：STREETTYPES和QUADRANT常量分别包含所有相关的街道类型和象限.
我在这里添加了一个子集：
private const string STREETTYPES = @"ALLEY|ALY|ANNEX|AX|ARCADE|ARC|AVENUE|AV|AVE|BAYOU|BYU|BEACH|..."; private const string QUADRANTS = "N|NORTH|S|SOUTH|E|EAST|W|WEST|NE|NORTHEAST|NW|NORTHWEST|SE|SOUTHEAST|SW|SOUTHWEST";
HouseNumber,Quadrant,StreetName和StreetType都是该类的属性.
private void Parse(string line1)
{
HouseNumber = string.Empty;
Quadrant = string.Empty;
StreetName = string.Empty;
StreetType = string.Empty;
if (!String.IsNullOrEmpty(line1))
{
string noPeriodsLine1 = String.Copy(line1);
noPeriodsLine1 = noPeriodsLine1.Replace(".","");
string addressParseRegEx =
@"(?ix)
^
\s*
(?:
(?<housenumber>\d+)
(?:(?:\s+|-)(?<quadrant>" +
QUADRANTS +
@"))?
(?:(?:\s+|-)(?<streetname>\S+(?:\s+\S+)*?))??
(?:(?:\s+|-)(?<quadrant>" +
QUADRANTS + @"))?
(?:(?:\s+|-)(?<streettype>" + STREETTYPES +
@"))?
(?:(?:\s+|-)(?<streettypequalifier>(?!(?:" +
QUADRANTS +
@"))(?:\d+|\S+)))?
(?:(?:\s+|-)(?<streettypequadrant>(" +
QUADRANTS + @")))??
(?:(?:\s+|-)(?<suffix>(?:ste|suite|po\sBox|apt)\s*\S*))?
|
(?:(?:po|postoffice|post\s+office)\s+Box\s+(?<postofficeBox>\S+))
)
\s*
$
";
Match match = Regex.Match(noPeriodsLine1,addressParseRegEx);
if (match.Success)
{
HouseNumber = match.Groups["housenumber"].Value;
Quadrant = (string.IsNullOrEmpty(match.Groups["quadrant"].Value)) ? match.Groups["streettypequadrant"].Value : match.Groups["quadrant"].Value;
if (match.Groups["streetname"].Captures.Count > 1)
{
foreach (Capture capture in match.Groups["streetname"].Captures)
{
StreetName += capture.Value + " ";
}
StreetName = StreetName.Trim();
}
else
{
StreetName = (string.IsNullOrEmpty(match.Groups["streetname"].Value)) ? match.Groups["streettypequalifier"].Value : match.Groups["streetname"].Value;
}
StreetType = match.Groups["streettype"].Value;
//if the matched street type is found
//use the abbreviated version...especially for credit bureau calls
string streetTypeAbbreviation;
if (StreetTypes.TryGetValue(StreetType.ToUpper(),out streetTypeAbbreviation))
{
StreetType = streetTypeAbbreviation;
}
}
}
}
