Regex_Cookbook_2_Code_Samples.html

    if (lines[i].match(regexp)) {
        // The regex matches lines[i]
    } else {
        // The regex does not match lines[i]
    }
}</pre>
<h4>PHP</h4>
<pre>$lines = preg_split('/\r?\n/', $subject)</pre>
<pre>foreach ($lines as $line) {
    if (preg_match('/regex pattern/', $line)) {
        // The regex matches $line
    } else {
        // The regex does not match $line
    }
}</pre>
<h4>Perl</h4>
<pre>@lines = split(m/\r?\n/, $subject)</pre>
<pre>foreach $line (@lines) {
    if ($line =~ m/regex pattern/) {
        # The regex matches $line
    } else {
        # The regex does not match $line
    }
}</pre>
<h4>Python</h4>
<pre>lines = re.split("\r?\n", subject)</pre>
<pre>reobj = re.compile("regex pattern")
for line in lines[:]:
    if reobj.search(line):
        # The regex matches line
    else:
        # The regex does not match line</pre>
<h4>Ruby</h4>
<pre>lines = subject.split(/\r?\n/)</pre>
<pre>re = /regex pattern/
lines.each { |line|
    if line =~ re
        # The regex matches line
    else
        # The regex does not match line
}</pre>
<h2>3.22. Construct a Parser</h2>
<h3>Problem</h3>
<pre>table %First table%
  row cell %A1% cell %B1% cell%C1%cell%D1%
  ROW row CELL %The previous row was blank%
  cell %B3%
  row
    cell %A4% %second line%
    cEll %B4%
         %second line%
    cell %C4
second line%
  row cell %%%string%%%
    cell %%
    cell %%%%
    cell %%%%%%</pre>
<h3>Solution</h3>
<h4>C#</h4>
<pre>static RECTable ImportTable(string fileContents) {
  RECTable table = null;
  RECRow row = null;
  RECCell cell = null;
  Regex regexObj = new Regex(
      @"  \b(?&lt;keyword&gt;table|row|cell)\b
      | %(?&lt;string&gt;[^%]*(?:%%[^%]*)*)%
      | (?&lt;error&gt;\S+)",
    RegexOptions.IgnoreCase | RegexOptions.IgnorePatternWhitespace);
  Match match = regexObj.Match(fileContents);
  while (match.Success) {
    if (match.Groups["keyword"].Success) {
      string keyword = match.Groups["keyword"].Value.ToLower();
      if (keyword == "table") {
        table = new RECTable();
        row = null;
        cell = null;
      } else if (keyword == "row") {
        if (table == null)
          throw new Exception("Invalid data: row without table");
        row = table.addRow();
        cell = null;
      } else if (keyword == "cell") {
        if (row == null)
          throw new Exception("Invalid data: cell without row");
        cell = row.addCell();
      } else {
        throw new Exception("Parser bug: unknown keyword");
      }
    } else if (match.Groups["string"].Success) {
      string content = match.Groups["string"].Value.Replace("%%", "%");
      if (cell != null)
        cell.addContent(content);
      else if (row != null)
        throw new Exception("Invalid data: string after row keyword");
      else if (table != null)
        table.addCaption(content);
      else
        throw new Exception("Invalid data: string before table keyword");
    } else if (match.Groups["error"].Success) {
      throw new Exception("Invalid data: " + match.Groups["error"].Value);
    } else {
      throw new Exception("Parser bug: no capturing group matched");
    }
    match = match.NextMatch();
  }
  if (table == null)
    throw new Exception("Invalid data: table keyword missing");
  return table;
}</pre>
<h4>VB.NET</h4>
<pre>Function ImportTable(ByVal FileContents As String)
  Dim Table As RECTable = Nothing
  Dim Row As RECRow = Nothing
  Dim Cell As RECCell = Nothing
  Dim RegexObj As New Regex(
      "  \b(?&lt;keyword&gt;table|row|cell)\b" &amp; _
      "| %(?&lt;string&gt;[^%]*(?:%%[^%]*)*)%" &amp; _
      "| (?&lt;error&gt;\S+)",
      RegexOptions.IgnoreCase Or RegexOptions.IgnorePatternWhitespace)
  Dim MatchResults As Match = RegexObj.Match(FileContents)
  While MatchResults.Success
    If MatchResults.Groups("keyword").Success Then
      Dim Keyword As String = MatchResults.Groups("keyword").Value
      Keyword = Keyword.ToLower()
      If Keyword = "table" Then
        Table = New RECTable
        Row = Nothing
        Cell = Nothing
      ElseIf Keyword = "row" Then
        If Table Is Nothing Then
          Throw New Exception("Invalid data: row without table")
        End If
        Row = Table.addRow
        Cell = Nothing
      ElseIf Keyword = "cell" Then
        If Row Is Nothing Then
          Throw New Exception("Invalid data: cell without row")
        End If
        Cell = Row.addCell
      Else
        Throw New Exception("Parser bug: unknown keyword")
      End If
    ElseIf MatchResults.Groups("string").Success Then
      Dim Content As String = MatchResults.Groups("string").Value
      Content = Content.Replace("%%", "%")
      If Cell IsNot Nothing Then
        Cell.addContent(Content)
      ElseIf Row IsNot Nothing Then
        Throw New Exception("Invalid data: string after row keyword")
      ElseIf Table IsNot Nothing Then
        Table.addCaption(Content)
      Else
        Throw New Exception("Invalid data: string before table keyword")
      End If
    ElseIf MatchResults.Groups("error").Success Then
      Throw New Exception("Invalid data")
    Else
      Throw New Exception("Parser bug: no capturing group matched")
    End If
    MatchResults = MatchResults.NextMatch()
  End While
  If Table Is Nothing Then
    Throw New Exception("Invalid data: table keyword missing")
  End If
  Return Table
End Function</pre>
<h4>Java</h4>
<pre>RECTable ImportTable(String fileContents) throws Exception {
  RECTable table = null;
  RECRow row = null;
  RECCell cell = null;
  final int groupkeyword = 1;
  final int groupstring = 2;
  final int grouperror = 3;
  Pattern regex = Pattern.compile(
      "  \\b(table|row|cell)\\b\n" +
      "| %([^%]*(?:%%[^%]*)*)%\n" +
      "| (\\S+)",
      Pattern.CASE_INSENSITIVE | Pattern.COMMENTS);
  Matcher regexMatcher = regex.matcher(fileContents);
  while (regexMatcher.find()) {
    if (regexMatcher.start(groupkeyword) &gt;= 0) {
      String keyword = regexMatcher.group(groupkeyword).toLowerCase();
      if (keyword.equals("table")) {
        table = new RECTable();
        row = null;
        cell = null;
      } else if (keyword.equals("row")) {
        if (table == null)
          throw new Exception("Invalid data: row without table");
        row = table.addRow();
        cell = null;
      } else if (keyword.equals("cell")) {
        if (row == null)
          throw new Exception("Invalid data: cell without row");
        cell = row.addCell();
      } else {
        throw new Exception("Parser bug: unknown keyword");
      }
    } else if (regexMatcher.start(groupstring) &gt;= 0) {
      String content = regexMatcher.group(groupstring);
      content = content.replaceAll("%%", "%");
      if (cell != null)
        cell.addContent(content);
      else if (row != null)
        throw new Exception("Invalid data: String after row keyword");
      else if (table != null)
        table.addCaption(content);
      else
        throw new Exception("Invalid data: String before table keyword");
    } else if (regexMatcher.start(grouperror) &gt;= 0) {
      throw new Exception("Invalid data: " + 
                          regexMatcher.group(grouperror));
    } else {
      throw new Exception("Parser bug: no capturing group matched");
    }
  }
  if (table == null)
    throw new Exception("Invalid data: table keyword missing");
  return table;
}</pre>
<h4>JavaScript</h4>
<pre>function importTable(fileContents) {
  var table = null;
  var row = null;
  var cell = null;
  var groupkeyword = 1;
  var groupstring = 2;
  var grouperror = 3;
  var myregexp = /\b(table|row|cell)\b|%([^%]*(?:%%[^%]*)*)%|(\S+)/ig;
  var match;
  var keyword;
  var content;
  while (match = myregexp.exec(fileContents)) {
    if (match[groupkeyword] !== undefined) {
      keyword = match[groupkeyword].toLowerCase();
      if (keyword == "table") {
        table = new RECTable();
        row = null;
        cell = null;
      } else if (keyword == "row") {
        if (!table)
          throw new Error("Invalid data: row without table");
        row = table.addRow();
        cell = null;
      } else if (keyword == "cell") {
        if (!row)
          throw new Error("Invalid data: cell without row");
        cell = row.addCell();
      } else {
        throw new Error("Parser bug: unknown keyword");
      }
    } else if (match[groupstring] !== undefined) {
      content = match[groupstring].replace(/%%/g, "%");
      if (cell)
        cell.addContent(content);
      else if (row)
        throw new Error("Invalid data: string after row keyword");
      else if (table)
        table.addCaption(content);
      else
        throw new Error("Invalid data: string before table keyword");
    } else if (match[grouperror] !== undefined) {
      throw new Error("Invalid data: " + match[grouperror]);
    } else {
      throw new Error("Parser bug: no capturing group matched");
    }
  }
  if (!table)
    throw new Error("Invalid data: table keyword missing");
  return table;
}</pre>
<h4>XRegExp</h4>
<pre>function importTable(fileContents) {
  var table = null;
  var row = null;
  var cell = null;
  var myregexp = XRegExp("(?ix)\\b(?&lt;keyword&gt;table|row|cell)\\b" +
                         "   | %(?&lt;string&gt;[^%]*(?:%%[^%]*)*)%" +
                         "   | (?&lt;error&gt;\\S+)");
  XRegExp.forEach(fileContents, myregexp, function(match) {
    var keyword;
    var content;
    if (match.keyword !== undefined) {
      keyword = match.keyword.toLowerCase();
      if (keyword == "table") {
        table = new RECTable();
        row = null;
        cell = null;
      } else if (keyword == "row") {
        if (!table)
          throw new Error("Invalid data: row without table");
        row = table.addRow();
        cell = null;
      } else if (keyword == "cell") {
        if (!row)
          throw new Error("Invalid data: cell without row");
        cell = row.addCell();
      } else {
        throw new Error("Parser bug: unknown keyword");
      }
    } else if (match.string !== undefined) {
      content = match.string.replace(/%%/g, "%");
      if (cell)
        cell.addContent(content);
      else if (row)
        throw new Error("Invalid data: string after row keyword");
      else if (table)
        table.addCaption(content);
      else
        throw new Error("Invalid data: string before table keyword");
    } else if (match.error !== undefined) {
      throw new Error("Invalid data: " + match.error);
    } else {
      throw new Error("Parser bug: no capturing group matched");
    }
  });
  if (!table)
    throw new Error("Invalid data: table keyword missing");
  return table;
}</pre>
<h4>Perl</h4>
<pre>sub importtable {
  my $filecontents = shift;
  my $table;
  my $row;
  my $cell;
  while ($filecontents =~ 
          m/  \b(table|row|cell)\b
          | %([^%]*(?:%%[^%]*)*)%
          | (\S+)/ixg) {
    if (defined($1)) { # Keyword
      my $keyword = lc($1);
      if ($keyword eq "table") {
        $table = new RECTable();
        undef $row;
        undef $cell;
      } elsif ($keyword eq "row") {
        if (!defined($table)) {
          die "Invalid data: row without table";
        }
        $row = $table-&gt;addRow();
        undef $cell;
      } elsif ($keyword eq "cell") {
        if (!defined($row)) {
          die "Invalid data: cell without row";
        }
        $cell = $row-&gt;addCell();
      } else {
        die "Parser bug: unknown keyword";
      }
    } elsif (defined($2)) { # String
      my $content = $2;
      $content =~ s/%%/%/g;
      if (defined($cell)) {
        $cell-&gt;addContent($content);
      } elsif (defined($row)) {
        die "Invalid data: string after row keyword";
      } elsif (defined($table)) {
        $table-&gt;addCaption($content);
      } else {
        die "Invalid data: string before table keyword";
      }
    } elsif (defined($3)) { # Error
      die "Invalid data: $3";
    } else {
      die "Parser bug: no capturing group matched";
    }
  }
  if (!defined(table)) {
    die "Invalid data: table keyword missing";
  }
  return table;
}</pre>
<h4>Python</h4>
<pre>def importtable(filecontents):
  table = None
  row = None
  cell = None
  for match in re.finditer(
    r"""(?ix)\b(?P&lt;keyword&gt;table|row|cell)\b
             | %(?P&lt;string&gt;[^%]*(?:%%[^%]*)*)%
             | (?P&lt;error&gt;\S+)""", filecontents):
    if match.group("keyword") != None:
      keyword = match.group("keyword").lower()
      if keyword == "table":
        table = RECTable()
        row = None
        cell = None
      elif keyword == "row":
        if table == None:
          raise Exception("Invalid data: row without table")
        row = table.addRow()
        cell = None
      elif keyword == "cell":
        if row == None:
          raise Exception("Invalid data: cell without row")
        cell = row.addCell()
      else:
        raise Exception("Parser bug: unknown keyword")
    elif match.group("string") != None:
      content = match.group("string").replace("%%", "%")
      if cell != None:
        cell.addContent(content)
      elif row != None:
        raise Exception("Invalid data: string after row keyword")
      elif table != None:
        table.addCaption(content)
      else:
        raise Exception("Invalid data: string before table keyword")
    elif match.group("error") != None:
      raise Exception("Invalid data: " + match.group("error"))
    else:
      raise Exception("Parser bug: no capturing group matched")
  if table == None:
    raise Exception("Invalid data: table keyword missing")
  return table</pre>
<h4>PHP</h4>
<pre>function importTable($fileContents) {
  preg_match_all(
    '/  \b(?P&lt;keyword&gt;table|row|cell)\b
      | (?P&lt;string&gt;%[^%]*(?:%%[^%]*)*%)
      | (?P&lt;error&gt;\S+)/ix',
    $fileContents, $matches, PREG_PATTERN_ORDER);
  $table = NULL;
  $row = NULL;
  $cell = NULL;
  for ($i = 0; $i &lt; count($matches[0]); $i++) {
    if ($matches['keyword'][$i] != NULL) {
      $keyword = strtolower($matches['keyword'][$i]);
      if ($keyword == "table") {
        $table = new RECTable();
        $row = NULL;
        $cell = NULL;
      } elseif ($keyword == "row") {
        if ($table == NULL)
          throw new Exception("Invalid data: row without table");
        $row = $table-&gt;addRow();
        $cell = NULL;
      } elseif ($keyword == "cell") {
        if ($row == NULL)
          throw new Exception("Invalid data: cell without row");
        $cell = $row-&gt;addCell();
      } else {
        throw new Exception("Parser bug: unknown keyword");
      }
    } elseif ($matches['string'][$i] != NULL) {
      $content = $matches['string'][$i];
      $content = substr($content, 1, strlen($content)-2);
      $content = str_replace('%%', '%', $content);
      if ($cell != NULL)
        $cell-&gt;addContent($content);
      elseif ($row != NULL)
        throw new Exception("Invalid data: string after row keyword");
      elseif ($table != NULL)
        $table-&gt;addCaption($content);
      else
        throw new Exception("Invalid data: string before table keyword");
    } elseif ($matches['error'][$i] != NULL) {
      throw new Exception("Invalid data: " + $matches['error'][$i]);
    } else {
      throw new Exception("Parser bug: no capturing group matched");
    }
  }
  if ($table == NULL)
    throw new Exception("Invalid data: table keyword missing");
  return $table;
}</pre>
<h4>Ruby</h4>
<pre>def importtable(filecontents)
  table = nil
  row = nil
  cell = nil
  groupkeyword = 0;
  groupstring = 1;
  grouperror = 2;
  regexp = /  \b(table|row|cell)\b
            | %([^%]*(?:%%[^%]*)*)%
            | (\S+)/ix
  filecontents.scan(regexp) do |match|
    if match[groupkeyword]
      keyword = match[groupkeyword].downcase
      if keyword == "table"
        table = RECTable.new()
        row = nil
        cell = nil
      elsif keyword == "row"
        if table.nil?
          raise "Invalid data: row without table"
        end
        row = table.addRow()
        cell = nil
      elsif keyword == "cell"
        if row.nil?
          raise "Invalid data: cell without row"
        end
        cell = row.addCell()
      else
        raise "Parser bug: unknown keyword"
      end
    elsif not match[groupstring].nil?
      content = match[groupstring].gsub("%%", "%")
      if not cell.nil?
        cell.addContent(content)
      elsif not row.nil?
        raise "Invalid data: string after row keyword"
      elsif not table.nil?
        table.addCaption(content)
      else
        raise "Invalid data: string before table keyword"
      end
    elsif not match[grouperror].nil?
      raise "Invalid data: " + match.group("error")
    else
      raise "Parser bug: no capturing group matched"
    end
  end
  if table.nil?
    raise "Invalid data: table keyword missing"
  end
  return table
end</pre>
<h3>Discussion</h3>
<pre>  \b(?&lt;keyword&gt;table|row|cell)\b
| %(?&lt;string&gt;[^%]*(?:%%[^%]*)*)%
| (?&lt;error&gt;\S+)</pre>
<p>Regex options: Free-spacing, case insensitive<br>
Regex flavors: .NET,
        Java 7, XRegExp, PCRE 7, Perl 5.10, Ruby 1.9</p>
<pre>  \b(?P&lt;keyword&gt;table|row|cell)\b
| %(?P&lt;string&gt;[^%]*(?:%%[^%]*)*)%
| (?P&lt;error&gt;\S+)</pre>
<p>Regex options: Free-spacing, case insensitive<br>
Regex flavors: PCRE 4
        and later, Perl 5.10, Python</p>
<pre>  \b(table|row|cell)\b
| %([^%]*(?:%%[^%]*)*)%
| (\S+)</pre>
<p>Regex options: Free-spacing, case insensitive<br>
Regex flavors: .NET,
        Java, XRegExp, PCRE, Perl, Python, Ruby</p>
<pre>\b(table|row|cell)\b|%([^%]*+(?:%%[^%]*+)*+)%|(\S+)</pre>
<p>Regex options: Case
        insensitive<br>
Regex flavors: .NET,
        Java, JavaScript, PCRE, Perl, Python, Ruby</p>
<h1>4. Validation and Formatting</h1>
<h2>4.1. Validate Email Addresses</h2>
<h3>Solution</h3>
<h4>Simple</h4>
<pre>^\S+@\S+$</pre>
<p>Regex options: None<br>
Regex flavors: .NET,
          Java, JavaScript, PCRE, Perl, Python</p>
<pre>\A\S+@\S+\Z</pre>
<p>Regex options: None<br>
Regex flavors: .NET,
          Java, PCRE, Perl, Python, Ruby</p>
<h4>Simple, with restrictions on characters</h4>
<pre>^[A-Z0-9+_.-]+@[A-Z0-9.-]+$</pre>
<p>Regex options: Case
          insensitive<br>
Regex flavors: .NET,
          Java, JavaScript, PCRE, Perl, Python</p>
<pre>\A[A-Z0-9+_.-]+@[A-Z0-9.-]+\Z</pre>
<p>Regex options: Case
          insensitive<br>
Regex flavors: .NET,
          Java, PCRE, Perl, Python, Ruby</p>
<h4>Simple, with all valid local part characters</h4>
<pre>^[A-Z0-9_!#$%&amp;'*+/=?`{|}~^.-]+@[A-Z0-9.-]+$</pre>
<p>Regex options: Case
          insensitive<br>
Regex flavors: .NET,
          Java, JavaScript, PCRE, Perl, Python</p>
<pre>\A[A-Z0-9_!#$%&amp;'*+/=?`{|}~^.-]+@[A-Z0-9.-]+\Z</pre>
<p>Regex options: Case
          insensitive<br>
Regex flavors: .NET,
          Java, PCRE, Perl, Python, Ruby</p>
<h4>No leading, trailing, or consecutive dots</h4>
<pre>^[A-Z0-9_!#$%&amp;'*+/=?`{|}~^-]+(?:\.[A-Z0-9_!#$%&amp;'*+/=?`{|}~^-]+)*@[A-Z0-9-]+(?:\.[A-Z0-9-]+)*$</pre>
<p>Regex options: Case
          insensitive<br>
Regex flavors: .NET,
          Java, JavaScript, PCRE, Perl, Python</p>
<pre>\A[A-Z0-9_!#$%&amp;'*+/=?`{|}~^-]+(?:\.[A-Z0-9_!#$%&amp;'*+/=?`{|}~^-]+)*@[A-Z0-9-]+(?:\.[A-Z0-9-]+)*\Z</pre>
<p>Regex options: Case
          insensitive<br>
Regex flavors: .NET,
          Java, PCRE, Perl, Python, Ruby</p>
<h4>Top-level domain has two to six letters</h4>
<pre>^[\w!#$%&amp;'*+/=?`{|}~^-]+(?:\.[\w!#$%&amp;'*+/=?`{|}~^-]+)*@(?:[A-Z0-9-]+\.)+[A-Z]{2,6}$</pre>
<p>Regex options: Case
          insensitive<br>
Regex flavors: .NET,
          Java, JavaScript, PCRE, Perl, Python</p>
<pre>\A[\w!#$%&amp;'*+/=?`{|}~^-]+(?:\.[\w!#$%&amp;'*+/=?`{|}~^-]+)*@(?:[A-Z0-9-]+\.)+[A-Z]{2,6}\Z</pre>
<p>Regex options: Case
          insensitive<br>
Regex flavors: .NET,
          Java, PCRE, Perl, Python, Ruby</p>
<h2>4.2. Validate and Format North American Phone Numbers</h2>
<h3>Solution</h3>
<h4>Regular expression</h4>
<pre>^\(?([0-9]{3})\)?[-. ]?([0-9]{3})[-. ]?([0-9]{4})$</pre>
<p>Regex options: None<br>
Regex flavors: .NET,
          Java, JavaScript, PCRE, Perl, Python, Ruby</p>
<h4>Replacement</h4>
<pre>($1) $2-$3</pre>
<pre>(\1) \2-\3</pre>
<h4>C# example</h4>
<pre>Regex phoneRegex =
    new Regex(@"^\(?([0-9]{3})\)?[-. ]?([0-9]{3})[-. ]?([0-9]{4})$");

if (phoneRegex.IsMatch(subjectString)) {
    string formattedPhoneNumber =
        phoneRegex.Replace(subjectString, "($1) $2-$3");
} else {
    // Invalid phone number
}</pre>
<h4>JavaScript example</h4>
<pre>var phoneRegex = /^\(?([0-9]{3})\)?[-. ]?([0-9]{3})[-. ]?([0-9]{4})$/;

if (phoneRegex.test(subjectString)) {
    var formattedPhoneNumber =
        subjectString.replace(phoneRegex, "($1) $2-$3");
} else {
    // Invalid phone number
}</pre>
<h3>Discussion</h3>
<pre>^        # Assert position at the beginning of the string.
\(       # Match a literal "("
  ?      #   between zero and one time.
(        # Capture the enclosed match to backreference 1:
  [0-9]  #   Match a digit
    {3}  #     exactly three times.
)        # End capturing group 1.
\)       # Match a literal ")"
  ?      #   between zero and one time.
[-. ]    # Match one hyphen, dot, or space
  ?      #   between zero and one time.
…       # [Match the remaining digits and separator.]
$        # Assert position at the end of the string.</pre>
<h3>Variations</h3>
<h4>Eliminate invalid phone numbers</h4>
<pre>^\(?([2-9][0-8][0-9])\)?[-. ]?([2-9][0-9]{2})[-. ]?([0-9]{4})$</pre>
<p>Regex options: None<br>
Regex flavors: .NET,
          Java, JavaScript, PCRE, Perl, Python, Ruby</p>
<h4>Find phone numbers in documents</h4>
<pre>\(?\b([0-9]{3})\)?[-. ]?([0-9]{3})[-. ]?([0-9]{4})\b</pre>
<p>Regex options: None<br>
Regex flavors: .NET,
          Java, JavaScript, PCRE, Perl, Python, Ruby</p>
<h4>Allow a leading “1”</h4>
<pre>^(?:\+?1[-. ]?)?\(?([0-9]{3})\)?[-. ]?([0-9]{3})[-. ]?([0-9]{4})$</pre>
<p>Regex options: None<br>
Regex flavors: .NET,
          Java, JavaScript, PCRE, Perl, Python, Ruby</p>
<h4>Allow seven-digit phone numbers</h4>
<pre>^(?:\(?([0-9]{3})\)?[-. ]?)?([0-9]{3})[-. ]?([0-9]{4})$</pre>
<p>Regex options: None<br>
Regex flavors: .NET,
          Java, JavaScript, PCRE, Perl, Python, Ruby</p>
<h2>4.3. Validate International Phone Numbers</h2>
<h3>Solution</h3>
<h4>Regular expression</h4>
<pre>^\+(?:[0-9] ?){6,14}[0-9]$</pre>
<p>Regex options: None<br>
Regex flavors: .NET,
          Java, JavaScript, PCRE, Perl, Python, Ruby</p>
<h4>JavaScript example</h4>
<pre>function validate(phone) {
    var regex = /^\+(?:[0-9] ?){6,14}[0-9]$/;

    if (regex.test(phone)) {
        // Valid international phone number
    } else {
        // Invalid international phone number
    }
}</pre>
<h3>Discussion</h3>
<pre>^         # Assert position at the beginning of the string.
\+        # Match a literal "+" character.
(?:       # Group but don't capture:
  [0-9]   #   Match a digit.
  \x20    #   Match a space character
    ?     #     between zero and one time.
)         # End the noncapturing group.
  {6,14}  #   Repeat the group between 6 and 14 times.
[0-9]     # Match a digit.
$         # Assert position at the end of the string.</pre>
<p>Regex options: Free-spacing<br>
Regex flavors: .NET,
        Java, XRegExp, PCRE, Perl, Python, Ruby</p>
<h3>Variations</h3>
<h4>Validate international phone numbers in EPP format</h4>
<pre>^\+[0-9]{1,3}\.[0-9]{4,14}(?:x.+)?$</pre>
<p>Regex options: None<br>
Regex flavors: .NET,
          Java, JavaScript, PCRE, Perl, Python, Ruby</p>
<h2>4.4. Validate Traditional Date Formats</h2>
<h3>Solution</h3>
<pre>^[0-3]?[0-9]/[0-3]?[0-9]/(?:[0-9]{2})?[0-9]{2}$</pre>
<p>Regex options: None<br>
Regex flavors: .NET,
        Java, JavaScript, PCRE, Perl, Python, Ruby</p>
<pre>^[0-3][0-9]/[0-3][0-9]/(?:[0-9][0-9])?[0-9][0-9]$</pre>
<p>Regex options: None<br>
Regex flavors: .NET,
        Java, JavaScript, PCRE, Perl, Python, Ruby</p>
<pre>^(1[0-2]|0?[1-9])/(3[01]|[12][0-9]|0?[1-9])/(?:[0-9]{2})?[0-9]{2}$</pre>
<p>Regex options: None<br>
Regex flavors: .NET,
        Java, JavaScript, PCRE, Perl, Python, Ruby</p>
<pre>^(1[0-2]|0[1-9])/(3[01]|[12][0-9]|0[1-9])/[0-9]{4}$</pre>
<p>Regex options: None<br>
Regex flavors: .NET,
        Java, JavaScript, PCRE, Perl, Python, Ruby</p>
<pre>^(3[01]|[12][0-9]|0?[1-9])/(1[0-2]|0?[1-9])/(?:[0-9]{2})?[0-9]{2}$</pre>
<p>Regex options: None<br>
Regex flavors: .NET,
        Java, JavaScript, PCRE, Perl, Python, Ruby</p>
<pre>^(3[01]|[12][0-9]|0[1-9])/(1[0-2]|0[1-9])/[0-9]{4}$</pre>
<p>Regex options: None<br>
Regex flavors: .NET,
        Java, JavaScript, PCRE, Perl, Python, Ruby</p>
<pre>^(?:(1[0-2]|0?[1-9])/(3[01]|[12][0-9]|0?[1-9])|(3[01]|[12][0-9]|0?[1-9])/(1[0-2]|0?[1-9]))/(?:[0-9]{2})?[0-9]{2}$</pre>
<p>Regex options: None<br>
Regex flavors: .NET,
        Java, JavaScript, PCRE, Perl, Python, Ruby</p>
<pre>^(?:
  # m/d or mm/dd
  (1[0-2]|0?[1-9])/(3[01]|[12][0-9]|0?[1-9])
|
  # d/m or dd/mm
  (3[01]|[12][0-9]|0?[1-9])/(1[0-2]|0?[1-9])
)
# /yy or /yyyy
/(?:[0-9]{2})?[0-9]{2}$</pre>
<p>Regex options: Free-spacing<br>
Regex flavors: .NET,
        Java, XRegExp, PCRE, Perl, Python, Ruby</p>
<pre>^(?:(1[0-2]|0[1-9])/(3[01]|[12][0-9]|0[1-9])|(3[01]|[12][0-9]|0[1-9])/(1[0-2]|0[1-9]))/[0-9]{4}$</pre>
<p>Regex options: None<br>
Regex flavors: .NET,
        Java, JavaScript, PCRE, Perl, Python, Ruby</p>
<pre>^(?:
  # mm/dd
  (1[0-2]|0[1-9])/(3[01]|[12][0-9]|0[1-9])
|
  # dd/mm
  (3[01]|[12][0-9]|0[1-9])/(1[0-2]|0[1-9])
)
# /yyyy
/[0-9]{4}$</pre>
<p>Regex options: Free-spacing<br>
Regex flavors: .NET,
        Java, XRegExp, PCRE, Perl, Python, Ruby</p>
<h3>Variations</h3>
<pre>\b(1[0-2]|0[1-9])/(3[01]|[12][0-9]|0[1-9])/[0-9]{4}\b</pre>
<p>Regex options: None<br>
Regex flavors: .NET,
        Java, JavaScript, PCRE, Perl, Python, Ruby</p>
<h2>4.5. Validate Traditional Date Formats, Excluding Invalid Dates</h2>
<h3>Solution</h3>
<h4>C#</h4>
<pre>^(?&lt;month&gt;[0-3]?[0-9])/(?&lt;day&gt;[0-3]?[0-9])/(?&lt;year&gt;(?:[0-9]{2})?[0-9]{2})$</pre>
<p>Regex options: None<br>
Regex flavors: .NET,
          Java 7, XRegExp, PCRE 7, Perl 5.10</p>
<pre>DateTime foundDate;
Match matchResult = Regex.Match(SubjectString,
    "^(?&lt;month&gt;[0-3]?[0-9])/(?&lt;day&gt;[0-3]?[0-9])/" +
    "(?&lt;year&gt;(?:[0-9]{2})?[0-9]{2})$");
if (matchResult.Success) {
    int year = int.Parse(matchResult.Groups["year"].Value);
    if (year &lt; 50) year += 2000;
    else if (year &lt; 100) year += 1900;
    try {
        foundDate = new DateTime(year,
            int.Parse(matchResult.Groups["month"].Value),
            int.Parse(matchResult.Groups["day"].Value));
    } catch {
        // Invalid date
    }
}</pre>
<pre>^(?&lt;day&gt;[0-3]?[0-9])/(?&lt;month&gt;[0-3]?[0-9])/(?&lt;year&gt;(?:[0-9]{2})?[0-9]{2})$</pre>
<p>Regex options: None<br>
Regex flavors: .NET,
          Java 7, XRegExp, PCRE 7, Perl 5.10</p>
<pre>DateTime foundDate;
Match matchResult = Regex.Match(SubjectString,
    "^(?&lt;day&gt;[0-3]?[0-9])/(?&lt;month&gt;[0-3]?[0-9])/" +
    "(?&lt;year&gt;(?:[0-9]{2})?[0-9]{2})$");
if (matchResult.Success) {
    int year = int.Parse(matchResult.Groups["year"].Value);
    if (year &lt; 50) year += 2000;
    else if (year &lt; 100) year += 1900;
    try {
        foundDate = new DateTime(year,
            int.Parse(matchResult.Groups["month"].Value),
            int.Parse(matchResult.Groups["day"].Value));
    } catch {
        // Invalid date
    }
}</pre>
<h4>Perl</h4>
<pre>^([0-3]?[0-9])/([0-3]?[0-9])/((?:[0-9]{2})?[0-9]{2})$</pre>
<p>Regex options: None<br>
Regex flavors: .NET,
          Java, JavaScript, PCRE, Perl, Python, Ruby</p>
<pre>@daysinmonth = (31, 28, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31);
$validdate = 0;
if ($subject =~ m!^([0-3]?[0-9])/([0-3]?[0-9])/((?:[0-9]{2})?[0-9]{2})$!) 
{
    $month = $1;
    $day = $2;
    $year = $3;
    $year += 2000 if $year &lt; 50;
    $year += 1900 if $year &lt; 100;
    if ($month == 2 &amp;&amp; $year % 4 == 0 &amp;&amp; ($year % 100 != 0 ||
                                          $year % 400 == 0)) {
    	$validdate = 1 if $day &gt;= 1 &amp;&amp; $day &lt;= 29;
    } elsif ($month &gt;= 1 &amp;&amp; $month &lt;= 12) {
        $validdate = 1 if $day &gt;= 1 &amp;&amp; $day &lt;= $daysinmonth[$month-1];
    }
}</pre>
<pre>@daysinmonth = (31, 28, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31);
$validdate = 0;
if ($subject =~ m!^([0-3]?[0-9])/([0-3]?[0-9])/((?:[0-9]{2})?[0-9]{2})$!) 
{
    $day = $1;
    $month = $2;
    $year = $3;
    $year += 2000 if $year &lt; 50;
    $year += 1900 if $year &lt; 100;
    if ($month == 2 &amp;&amp; $year % 4 == 0 &amp;&amp; ($year % 100 != 0 ||
                                          $year % 400 == 0)) {
    	$validdate = 1 if $day &gt;= 1 &amp;&amp; $day &lt;= 29;
    } elsif ($month &gt;= 1 &amp;&amp; $month &lt;= 12) {
        $validdate = 1 if $day &gt;= 1 &amp;&amp; $day &lt;= $daysinmonth[$month-1];
    }
}</pre>
<h4>Pure regular expression</h4>
<pre>^(?:
  # February (29 days every year)
  (?&lt;month&gt;0?2)/(?&lt;day&gt;[12][0-9]|0?[1-9])
|
  # 30-day months
  (?&lt;month&gt;0?[469]|11)/(?&lt;day&gt;30|[12][0-9]|0?[1-9])
|
  # 31-day months
  (?&lt;month&gt;0?[13578]|1[02])/(?&lt;day&gt;3[01]|[12][0-9]|0?[1-9])
)
# Year
/(?&lt;year&gt;(?:[0-9]{2})?[0-9]{2})$</pre>
<p>Regex options: Free-spacing<br>
Regex flavors: .NET,
          Perl 5.10, Ruby 1.9</p>
<pre>^(?:
  # February (29 days every year)
  (0?2)/([12][0-9]|0?[1-9])
|
  # 30-day months
  (0?[469]|11)/(30|[12][0-9]|0?[1-9])
|
  # 31-day months
  (0?[13578]|1[02])/(3[01]|[12][0-9]|0?[1-9])
)
# Year
/((?:[0-9]{2})?[0-9]{2})$</pre>
<p>Regex options: Free-spacing<br>
Regex flavors: .NET,
          Java, XRegExp, PCRE, Perl, Python, Ruby</p>
<pre>^(?:(0?2)/([12][0-9]|0?[1-9])|(0?[469]|11)/(30|[12][0-9]|0?[1-9])|(0?[13578]|1[02])/(3[01]|[12][0-9]|0?[1-9]))/((?:[0-9]{2})?[0-9]{2})$</pre>
<p>Regex options: None<br>
Regex flavors: .NET,
          Java, JavaScript, PCRE, Perl, Python, Ruby</p>
<pre>^(?:
  # February (29 days every year)
  (?&lt;day&gt;[12][0-9]|0?[1-9])/(?&lt;month&gt;0?2)
|
  # 30-day months
  (?&lt;day&gt;30|[12][0-9]|0?[1-9])/(?&lt;month&gt;0?[469]|11)
|
  # 31-day months
  (?&lt;day&gt;3[01]|[12][0-9]|0?[1-9])/(?&lt;month&gt;0?[13578]|1[02])
)
# Year
/(?&lt;year&gt;(?:[0-9]{2})?[0-9]{2})$</pre>
<p>Regex options: Free-spacing<br>
Regex flavors: .NET,
          Perl 5.10, Ruby 1.9</p>
<pre>^(?:
  # February (29 days every year)
  ([12][0-9]|0?[1-9])/(0?2)
|
  # 30-day months
  (30|[12][0-9]|0?[1-9])/([469]|11)
|
  # 31-day months
  (3[01]|[12][0-9]|0?[1-9])/(0?[13578]|1[02])
)
# Year
/((?:[0-9]{2})?[0-9]{2})$</pre>
<p>Regex options: Free-spacing<br>
Regex flavors: .NET,
          Java, XRegExp, PCRE, Perl, Python, Ruby</p>
<pre>^(?:([12][0-9]|0?[1-9])/(0?2)|(30|[12][0-9]|0?[1-9])/([469]|11)|(3[01]|[12][0-9]|0?[1-9])/(0?[13578]|1[02]))/((?:[0-9]{2})?[0-9]{2})$</pre>
<p>Regex options: None<br>
Regex flavors: .NET,
          Java, JavaScript, PCRE, Perl, Python, Ruby</p>
<h3>Variations</h3>
<pre># 2 May 2007 till 29 August 2008
^(?:
  # 2 May 2007 till 31 December 2007
  (?:
    # 2 May till 31 May
    (?&lt;day&gt;3[01]|[12][0-9]|0?[2-9])/(?&lt;month&gt;0?5)/(?&lt;year&gt;2007)
  |
    # 1 June till 31 December
    (?:
      # 30-day months
      (?&lt;day&gt;30|[12][0-9]|0?[1-9])/(?&lt;month&gt;0?[69]|11)
    |
      # 31-day months
      (?&lt;day&gt;3[01]|[12][0-9]|0?[1-9])/(?&lt;month&gt;0?[78]|1[02])
    )
    /(?&lt;year&gt;2007)
  )
|
  # 1 January 2008 till 29 August 2008
  (?:
    # 1 August till 29 August
    (?&lt;day&gt;[12][0-9]|0?[1-9])/(?&lt;month&gt;0?8)/(?&lt;year&gt;2008)
  |
    # 1 Janary till 30 June
    (?:
      # February
      (?&lt;day&gt;[12][0-9]|0?[1-9])/(?&lt;month&gt;0?2)
    |
      # 30-day months
      (?&lt;day&gt;30|[12][0-9]|0?[1-9])/(?&lt;month&gt;0?[46])
    |
      # 31-day months
      (?&lt;day&gt;3[01]|[12][0-9]|0?[1-9])/(?&lt;month&gt;0?[1357])
    )
    /(?&lt;year&gt;2008)
  )
)$</pre>
<p>Regex options: Free-spacing<br>
Regex flavors: .NET,
        Perl 5.10, Ruby 1.9</p>
<h2>4.6. Validate Traditional Time Formats</h2>
<h3>Solution</h3>
<pre>^(1[0-2]|0?[1-9]):([0-5]?[0-9])( ?[AP]M)?$</pre>
<p>Regex options: None<br>
Regex flavors: .NET,
        Java, JavaScript, PCRE, Perl, Python, Ruby</p>
<pre>^(2[0-3]|[01]?[0-9]):([0-5]?[0-9])$</pre>
<p>Regex options: None<br>
Regex flavors: .NET,
        Java, JavaScript, PCRE, Perl, Python, Ruby</p>
<pre>^(1[0-2]|0?[1-9]):([0-5]?[0-9]):([0-5]?[0-9])( ?[AP]M)?$</pre>
<p>Regex options: None<br>
Regex flavors: .NET,
        Java, JavaScript, PCRE, Perl, Python, Ruby</p>
<pre>^(2[0-3]|[01]?[0-9]):([0-5]?[0-9]):([0-5]?[0-9])$</pre>
<p>Regex options: None<br>
Regex flavors: .NET,
        Java, JavaScript, PCRE, Perl, Python, Ruby</p>
<h3>Variations</h3>
<pre>\b(2[0-3]|[01]?[0-9]):([0-5]?[0-9])\b</pre>
<p>Regex options: None<br>
Regex flavors: .NET,
        Java, JavaScript, PCRE, Perl, Python, Ruby</p>
<pre>(?&lt;![:\w])(2[0-3]|[01]?[0-9]):([0-5]?[0-9])(?![:\w])</pre>
<p>Regex options: None<br>
Regex flavors: .NET,
        Java, PCRE, Perl, Python, Ruby 1.9</p>
<h2>4.7. Validate ISO 8601 Dates and Times</h2>
<h3>Solution</h3>
<h4>Dates</h4>
<pre>^([0-9]{4})-(1[0-2]|0[1-9])$</pre>
<p>Regex options: None<br>
Regex flavors: .NET,
          Java, JavaScript, PCRE, Perl, Python, Ruby</p>
<pre>^(?&lt;year&gt;[0-9]{4})-(?&lt;month&gt;1[0-2]|0[1-9])$</pre>
<p>Regex options: None<br>
Regex flavors: .NET,
          Java 7, XRegExp, PCRE 7, Perl 5.10, Ruby 1.9</p>
<pre>^(?P&lt;year&gt;[0-9]{4})-(?P&lt;month&gt;1[0-2]|0[1-9])$</pre>
<p>Regex options: None<br>
Regex flavors: PCRE,
          Python</p>
<pre>^([0-9]{4})-?(1[0-2]|0[1-9])-?(3[01]|0[1-9]|[12][0-9])$</pre>
<p>Regex options: None<br>