1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280
namespace Utilities { using System; using System.Collections.Generic; using System.Text; using System.Text.RegularExpressions; public static class StringExt { public static bool IsEmail(this string inputstr) { // exit if the string is null or empty if (inputstr.IsEmpty()) return false; string strRegex = @"^([a-zA-Z0-9_\-\.\+]+)@((\[[0-9]{1,3}" + @"\.[0-9]{1,3}\.[0-9]{1,3}\.)|(([a-zA-Z0-9\-]+\" + @".)+))([a-zA-Z]{2,4}|[0-9]{1,3})(\]?)$"; return inputstr.MatchRegex(strRegex); } public static bool IsZip(this string inputstr) { // exit if the string is null or empty if (inputstr.IsEmpty()) return false; string strRegex = @"^\d{5}$|^\d{5}-\d{4}$"; return inputstr.MatchRegex(strRegex); } public static bool IsStateAbbrv(this string inputstr) { return inputstr.IsStateAbbrv(false); } public static bool IsStateAbbrv(this string inputstr, bool CaseSensitive) { // exit if the string is null or empty if (inputstr.IsEmpty()) return false; string strRegex = @"^((AL)|(AK)|(AS)|(AZ)|(AR)|(CA)|(CO)|(CT)|(DE)|(DC)|(FM)|(FL)|" + @"(GA)|(GU)|(HI)|(ID)|(IL)|(IN)|(IA)|(KS)|(KY)|(LA)|(ME)|(MH)|(MD)|(MA)|(MI)|" + @"(MN)|(MS)|(MO)|(MT)|(NE)|(NV)|(NH)|(NJ)|(NM)|(NY)|(NC)|(ND)|(MP)|(OH)|(OK)|" + @"(OR)|(PW)|(PA)|(PR)|(RI)|(SC)|(SD)|(TN)|(TX)|(UT)|(VT)|(VI)|(VA)|(WA)|(WV)|" + @"(WI)|(WY))$"; return inputstr.MatchRegex(strRegex, CaseSensitive); } public static bool IsStateName(this string inputstr) { return inputstr.IsStateName(false); } public static bool IsStateName(this string inputstr, bool CaseSensitive) { // exit if the string is null or empty if (inputstr.IsEmpty()) return false; string strRegex = @"^((Alabama)|(Alaska)|(AmericanSamoa)|(Arizona)|(Arkansas)|(California)|" + @"(Colorado)|(Connecticut)|(Delaware)|(DistrictofColumbia)|(Florida)|(Georgia)|(Guam)|" + @"(Hawaii)|(Idaho)|(Illinois)|(Indiana)|(Iowa)|(Kansas)|(Kentucky)|(Louisiana)|(Maine)|" + @"(Maryland)|(Massachusetts)|(Michigan)|(Minnesota)|(Mississippi)|(Missouri)|(Montana)|" + @"(Nebraska)|(Nevada)|(NewHampshire)|(NewJersey)|(NewMexico)|(NewYork)|(NorthCarolina)|" + @"(NorthDakota)|(NorthernMarianasIslands)|(Ohio)|(Oklahoma)|(Oregon)|(Pennsylvania)|" + @"(PuertoRico)|(RhodeIsland)|(SouthCarolina)|(SouthDakota)|(Tennessee)|(Texas)|(Utah)|" + @"(Vermont)|(Virginia)|(VirginIslands)|(Washington)|(WestVirginia)|(Wisconsin)|(Wyoming))$"; return inputstr.MatchRegex(strRegex, CaseSensitive); } public static bool IsEmpty(this string inputstr) { if (inputstr == null || inputstr.Trim().Length == 0) { return true; } return false; } public static bool IsPhone(this string inputstr) { // exit if the string is null or empty if (inputstr.IsEmpty()) return false; string strRegex = @"^\D?(\d{3})\D?\D?(\d{3})\D?(\d{4})$"; return inputstr.MatchRegex(strRegex); } public static bool MatchRegex(this string inputstr, string regex) { return inputstr.MatchRegex(regex, false); } public static bool MatchRegex(this string inputstr, string regex, bool CaseSensitive) { var IsCaseSensitive = RegexOptions.IgnoreCase; if (CaseSensitive) { IsCaseSensitive = RegexOptions.None; } return System.Text.RegularExpressions.Regex.IsMatch(inputstr, regex, IsCaseSensitive); } public static bool EqualsIgnoreCase(this string s, string value) { return s.ToLowerInvariant() == value.ToLowerInvariant(); } // be nice to VB & CF devlopers public static string Left(this string s, int position) { return s.Substring(0, position); } // be nice to VB & CF devlopers public static string Right(this string s, int position) { return s.Substring(s.Length - position); } public static string Reverse(this string s) { char[] charArray = s.ToCharArray(); Array.Reverse(charArray); return new string(charArray); } public static string FormatTitleCase(this string s) { string[] words = s.Split(' '); string result = string.Empty; string temp = string.Empty; foreach (string i in words) { temp = i.ToLower(); result = result + i.Substring(0, 1).ToUpper() + i.Substring(1) + " "; } result = result.Substring(0, result.Length - 1); return result; } /// <summary> /// convert a string that is CSV formated into a List /// credit goes to www.usualdosage.com where I got most of this code /// </summary> /// <param name="s"></param> /// <returns>List</returns> public static List<string> CSVToList(this string s) { char CHAR_COMMA = Convert.ToChar(44); char CHAR_QUOTE = Convert.ToChar(34); char CHAR_PIPE = Convert.ToChar(124); char CHAR_BACKQUOTE = Convert.ToChar(96); // Create a new array to contain the return values string strCurrent = s; string[] arrTokens = null; // Replace any instance of double quotes with a back quote strCurrent = strCurrent.Replace("\"\"", "`"); if (!strCurrent.Contains(CHAR_QUOTE.ToString())) // No quotes, so just split on commas { arrTokens = strCurrent.Split(CHAR_COMMA); } else // Contains quotes, so more detailed parsing needed { bool bQuote = false; bool bEscape = false; // Convert temp to a char array to make it easier to check each char char[] arrTempChars = strCurrent.ToCharArray(); for (int i = 0; i < arrTempChars.Length; i++) { // Loop through until we find a quote. If found, flip the bool value if (arrTempChars[i] == CHAR_QUOTE) { if (!bEscape) bQuote = !bQuote; } // If we’re in a quote group and find a comma, change it to a temp char for the moment if (bQuote && (arrTempChars[i] == CHAR_COMMA)) { arrTempChars[i] = CHAR_PIPE; } } // Parse out the modified character array into a string string strReassemble = string.Empty; for (int j = 0; j < arrTempChars.Length; j++) { strReassemble = strReassemble + arrTempChars[j].ToString(); } // Remove the quotes, which will leave just commas, and split strReassemble = strReassemble.Replace(CHAR_QUOTE.ToString(), string.Empty); arrTokens = strReassemble.Split(CHAR_COMMA); // Loop through the array, and reset the temp chars back to // commas, and replace the back quotes with double quotes for (int k = 0; k < arrTokens.Length; k++) { arrTokens[k] = arrTokens[k].Replace(CHAR_PIPE, CHAR_COMMA); arrTokens[k] = arrTokens[k].Replace(CHAR_BACKQUOTE, CHAR_QUOTE); } } List<string> rtrnList = new List<string>(); foreach (string entry in arrTokens) { rtrnList.Add(entry); } return rtrnList; } /// <summary> /// convert a string that is CSV formated into a List /// credit goes to www.usualdosage.com where I got most of this code /// </summary> /// <param name="s"></param> /// <returns>List</returns> public static string[] CSVToArray(this string s) { return s.CSVToList().ToArray(); } /// <summary> /// Convert a string[] into a single string that is seperated by a /// delimiter /// </summary> /// <param name="s"></param> /// <returns></returns> public static string ToDelimitedString(this string[] s) { return s.ToDelimitedString(",", false); } public static string ToDelimitedString(this string[] s, string vDelimeter) { return s.ToDelimitedString(vDelimeter, false); } public static string ToDelimitedString(this string[] s, bool QuoteEachEntry) { return s.ToDelimitedString(",", QuoteEachEntry); } public static string ToDelimitedString(this string[] s, string Delimeter, bool QuoteEachEntry) { string result = string.Empty; string vDelim = string.Empty; foreach (string element in s) { if(QuoteEachEntry) result += vDelim + "\"" + element + "\""; else result += vDelim + element; vDelim = Delimeter; } return result; } } }
Refactorings
No refactoring yet !
Rik Hemsley
August 6, 2008, August 06, 2008 19:26, permalink
Quite a few of your new methods already exist in .NET.
For example:
IsEmpty(this string inputstr) already exists as string.IsNullOrEmpty(...)
ToDelimitedString(this string[] s) exists as string.Join(...)
Your email address 'validator' is incorrect. The only way to correctly validate an email address is according to RFC 2822. This cannot be done using a regular expression, only with a proper parser. It's almost always best to avoid trying to validate email addresses.
I'd also say that you're likely to slightly annoy other developers with so many tiny utility methods - especially where it's not clear exactly how they differ from the almost identical built-in methods.
For example: If I see 'inputstr.MatchRegex(strRegex)', I don't know whether that performs matches against the given regex, or whether it checks whether the string matches. The English is unclear.
Regex.IsMatch() from System.Text.RegularExpressions is clear in its purpose and I'd probably prefer to simply use it unadorned.
Your variable naming is slightly non-standard - please see Microsoft's guidelines for .NET code. For example, we don't use type prefixes in .NET, except for on interfaces (which have 'I').
I'm not entirely sure why you've made some of these methods extensions. What does a string have to do with the states of the USA or phone numbers? Left(), FormatTitleCase() etc. I can understand, as they deal with strings.
One last thing I would mention is that you didn't post your unit tests. It would be interesting to see them, to get an idea of how you intend to use your utility methods.
Hope this helps and isn't too negative!
snafu918
August 6, 2008, August 06, 2008 20:05, permalink
Thanks Rik, I am new to .Net so any code review is useful. Thanks for the tip on Join and IsNullOrEmpty when you start a new language the function names are always different so I didn't even know they existed. I'll rework some of my naming so it's a bit more understandable I can see how some of them would be confusing. Some of those functions like left and FormatTitleCase are just formatting functions that I built as proof of concepts so I could get used to using .net.
volothamp
August 8, 2008, August 08, 2008 13:09, permalink
Some refactorings, didn't touch your csv algorithm.
Use always string buffer when you are concatenating strings.
The purpose of FormatTitleCase is unknown to me.
Bye! :)
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226
using System; using System.Collections.Generic; using System.Text; using System.Text.RegularExpressions; namespace Utilities { public static class StringExt { public static bool MatchRegexWithCheck(this string s, string pattern, bool casesensitive) { return !String.IsNullOrEmpty(s) && (casesensitive ? Regex.Match(s, pattern) : Regex.Match(s, pattern, RegexOptions.IgnoreCase)) .Success; } public static bool MatchRegexWithCheck(this string s, string pattern) { MatchRegexWithCheck(s, pattern, true); } public static bool IsEmail(this string inputstr) { return inputstr.MatchRegexWithCheck(@"^([a-zA-Z0-9_\-\.\+]+)@((\[[0-9]{1,3}" + @"\.[0-9]{1,3}\.[0-9]{1,3}\.)|(([a-zA-Z0-9\-]+\" + @".)+))([a-zA-Z]{2,4}|[0-9]{1,3})(\]?)$"); } public static bool IsZip(this string inputstr) { return inputstr.MatchRegexWithCheck(@"^\d{5}$|^\d{5}-\d{4}$"); } public static bool IsStateAbbrv(this string inputstr, bool casesensitive) { return inputstr.MatchRegexWithCheck(@"^((AL)|(AK)|(AS)|(AZ)|(AR)|(CA)|(CO)|(CT)|(DE)|(DC)|(FM)|(FL)|" + @"(GA)|(GU)|(HI)|(ID)|(IL)|(IN)|(IA)|(KS)|(KY)|(LA)|(ME)|(MH)|(MD)|(MA)|(MI)|" + @"(MN)|(MS)|(MO)|(MT)|(NE)|(NV)|(NH)|(NJ)|(NM)|(NY)|(NC)|(ND)|(MP)|(OH)|(OK)|" + @"(OR)|(PW)|(PA)|(PR)|(RI)|(SC)|(SD)|(TN)|(TX)|(UT)|(VT)|(VI)|(VA)|(WA)|(WV)|" + @"(WI)|(WY))$", casesensitive); } public static bool IsStateName(this string inputstr, bool casesensitive) { return inputstr.MatchRegex(@"^((Alabama)|(Alaska)|(AmericanSamoa)|(Arizona)|(Arkansas)|(California)|" + @"(Colorado)|(Connecticut)|(Delaware)|(DistrictofColumbia)|(Florida)|(Georgia)|(Guam)|" + @"(Hawaii)|(Idaho)|(Illinois)|(Indiana)|(Iowa)|(Kansas)|(Kentucky)|(Louisiana)|(Maine)|" + @"(Maryland)|(Massachusetts)|(Michigan)|(Minnesota)|(Mississippi)|(Missouri)|(Montana)|" + @"(Nebraska)|(Nevada)|(NewHampshire)|(NewJersey)|(NewMexico)|(NewYork)|(NorthCarolina)|" + @"(NorthDakota)|(NorthernMarianasIslands)|(Ohio)|(Oklahoma)|(Oregon)|(Pennsylvania)|" + @"(PuertoRico)|(RhodeIsland)|(SouthCarolina)|(SouthDakota)|(Tennessee)|(Texas)|(Utah)|" + @"(Vermont)|(Virginia)|(VirginIslands)|(Washington)|(WestVirginia)|(Wisconsin)|(Wyoming))$", casesensitive); } public static bool IsStateAbbrv(this string inputstr) { return inputstr.IsStateAbbrv(false); } public static bool IsStateName(this string inputstr) { return inputstr.IsStateName(false); } public static bool IsPhone(this string inputstr) { return inputstr.MatchRegexWithCheck(@"^\D?(\d{3})\D?\D?(\d{3})\D?(\d{4})$"); } public static bool EqualsIgnoreCase(this string s, string value) { return s.ToLowerInvariant() == value.ToLowerInvariant(); } // be nice to VB & CF devlopers public static string Left(this string s, int position) { return s.Substring(0, position); } public static string Right(this string s, int position) { return s.Substring(s.Length - position); } public static string Reverse(this string s) { char[] charArray = s.ToCharArray(); Array.Reverse(charArray); return new string(charArray); } public static string FormatTitleCase(this string s) { string[] words = s.Split(' '); string result = string.Empty; string temp = string.Empty; foreach (string i in words) { temp = i.ToLower(); // This get replaced every time result = String.Format("{0}{1}{2} ", result, i.Substring(0, 1).ToUpper(), i.Substring(1)); } return result.Substring(0, result.Length - 1); } /// <summary> /// convert a string that is CSV formated into a List /// credit goes to www.usualdosage.com where I got most of this code /// </summary> /// <param name="s"></param> /// <returns>List</returns> public static List<string> CSVToList(this string s) { char CHAR_COMMA = ','; char CHAR_QUOTE = Convert.ToChar(34); char CHAR_PIPE = '|'; char CHAR_BACKQUOTE = "`"; string strCurrent = s; string[] arrTokens = null; // Replace any instance of double quotes with a back quote strCurrent = strCurrent.Replace("\"\"", CHAR_BACKQUOTE); if (!strCurrent.Contains(CHAR_QUOTE.ToString())) // No quotes, so just split on commas { arrTokens = strCurrent.Split(CHAR_COMMA); } else // Contains quotes, so more detailed parsing needed { bool bQuote = false; bool bEscape = false; // Convert temp to a char array to make it easier to check each char char[] arrTempChars = strCurrent.ToCharArray(); for (int i = 0; i < arrTempChars.Length; i++) { // Loop through until we find a quote. If found, flip the bool value if (arrTempChars[i] == CHAR_QUOTE) { if (!bEscape) bQuote = !bQuote; } // If we’re in a quote group and find a comma, change it to a temp char for the moment if (bQuote && (arrTempChars[i] == CHAR_COMMA)) { arrTempChars[i] = CHAR_PIPE; } } // Parse out the modified character array into a string string strReassemble = string.Empty; for (int j = 0; j < arrTempChars.Length; j++) { strReassemble = strReassemble + arrTempChars[j].ToString(); } // Remove the quotes, which will leave just commas, and split strReassemble = strReassemble.Replace(CHAR_QUOTE.ToString(), string.Empty); arrTokens = strReassemble.Split(CHAR_COMMA); // Loop through the array, and reset the temp chars back to // commas, and replace the back quotes with double quotes for (int k = 0; k < arrTokens.Length; k++) { arrTokens[k] = arrTokens[k].Replace(CHAR_PIPE, CHAR_COMMA); arrTokens[k] = arrTokens[k].Replace(CHAR_BACKQUOTE, CHAR_QUOTE); } } List<string> rtrnList = new List<string>(); foreach (string entry in arrTokens) { rtrnList.Add(entry); } return rtrnList; } /// <summary> /// convert a string that is CSV formated into a List /// credit goes to www.usualdosage.com where I got most of this code /// </summary> /// <param name="s"></param> /// <returns>List</returns> public static string[] CSVToArray(this string s) { return s.CSVToList().ToArray(); } /// <summary> /// Convert a string[] into a single string that is seperated by a /// delimiter /// </summary> /// <param name="s"></param> /// <returns></returns> public static string ToDelimitedString(this string[] s) { return s.ToDelimitedString(",", false); } public static string ToDelimitedString(this string[] s, string vDelimeter) { return s.ToDelimitedString(vDelimeter, false); } public static string ToDelimitedString(this string[] s, bool QuoteEachEntry) { return s.ToDelimitedString(",", QuoteEachEntry); } public static string ToDelimitedString(this string[] s, string delimeter, bool quoteEachEntry) { StringBuilder result = new StringBuilder(); foreach (string element in s) result.AppendFormat(quoteEachEntry ? "{0}\"{1}\"" : "{0}{1}", delimeter, element); return result.ToString(); } } }
John
October 17, 2008, October 17, 2008 17:02, permalink
For e-mail address, state, zip, etc., you're really better off creating separate classes to represent each of those objects. Like, create an EmailAddress class that is able to validate itself.
Roe
October 17, 2008, October 17, 2008 17:20, permalink
I agree that what you're suggesting is the better OO approach. What however would you suggest if you were going to refactor "THIS" code.
Ok take it easy on me, I just started c# and I'd love everyone's feed back on the following extension I made. I'd love to hear about best practices, speed improvements, or just better ways to code what I did. I came from a coldfusion background so I was trying to code in some of the methods I missed in cf as well as a few nice shortcut methods.