/// <summary>
/// Describe hash set
/// </summary>
new public string Describe(HashSet <char> label)
{
var ranges = new Internal.Utilities.Ranges();
foreach (char c in label)
{
ranges.Add((int)c);
}
string res = "";
for (int i = 0; i < ranges.ranges.Count; i++)
{
var range = ranges.ranges[i];
if (range[0] == range[1])
{
res += Rex.RexEngine.Escape((char)range[0]);
}
else
{
res += "[";
res += Rex.RexEngine.Escape((char)range[0]);
res += "-";
res += Rex.RexEngine.Escape((char)range[1]);
res += "]";
}
if (i < ranges.ranges.Count - 1)
{
res += "|";
}
}
description[label] = res;
return(res);
}
private static void WriteRangeFields(BitWidth encoding, StreamWriter sw, string field)
{
int bits = (int)encoding;
int maxChar = (1 << bits) - 1;
var catMap = new Dictionary <UnicodeCategory, Ranges>();
for (int c = 0; c < 30; c++)
{
catMap[(UnicodeCategory)c] = new Ranges();
}
Ranges whitespace = new Ranges();
Ranges wordcharacter = new Ranges();
for (int i = 0; i <= maxChar; i++)
{
char ch = (char)i;
if (char.IsWhiteSpace(ch))
{
whitespace.Add(i);
}
UnicodeCategory cat = char.GetUnicodeCategory(ch);
catMap[cat].Add(i);
int catCode = (int)cat;
//in .NET 3.5
if (bits == 7)
{
if (catCode == 0 || catCode == 1 || catCode == 2 || catCode == 3 || catCode == 4 || catCode == 5 || catCode == 8 || catCode == 18)
{
wordcharacter.Add(i);
}
}
}
//generate bdd reprs for each of the category ranges
BDD[] catBDDs = new BDD[30];
CharSetSolver bddb = new CharSetSolver(encoding);
for (int c = 0; c < 30; c++)
{
catBDDs[c] = bddb.MkBddForIntRanges(catMap[(UnicodeCategory)c].ranges);
}
BDD whitespaceBdd = bddb.MkBddForIntRanges(whitespace.ranges);
//in .NET 3.5 category 5 was NOT a word character
//union of categories 0,1,2,3,4,8,18
BDD wordCharBdd = bddb.MkOr(catBDDs[0],
bddb.MkOr(catBDDs[1],
bddb.MkOr(catBDDs[2],
bddb.MkOr(catBDDs[3],
bddb.MkOr(catBDDs[4],
bddb.MkOr(catBDDs[5],
bddb.MkOr(catBDDs[8], catBDDs[18])))))));
if (bits == 7)
{
sw.WriteLine(@"/// <summary>
/// Array of 30 UnicodeCategory ranges. Each entry is a pair of integers.
/// corresponding to the lower and upper bounds of the unicodes of the characters
/// that have the given UnicodeCategory code (between 0 and 29).
/// </summary>");
sw.WriteLine("public static int[][][] " + field + " = new int[][][]{");
foreach (UnicodeCategory c in catMap.Keys)
{
sw.WriteLine("//{0}({1}):", c, (int)c);
if (catMap[c].Count == 0)
{
sw.WriteLine("null,");
}
else
{
sw.WriteLine("new int[][]{");
foreach (int[] range in catMap[c].ranges)
{
sw.WriteLine(" new int[]{" + string.Format("{0},{1}", range[0], range[1]) + "},");
}
sw.WriteLine("},");
}
}
sw.WriteLine("};");
}
sw.WriteLine(@"/// <summary>
/// Compact BDD encodings of the categories.
/// </summary>");
sw.WriteLine("public static int[][] " + field + "Bdd = new int[][]{");
foreach (UnicodeCategory c in catMap.Keys)
{
sw.WriteLine("//{0}({1}):", c, (int)c);
BDD catBdd = catBDDs[(int)c];
if (catBdd == null || catBdd.IsEmpty)
{
sw.WriteLine("null, //false");
}
else if (catBdd.IsFull)
{
sw.WriteLine("new int[]{0,0}, //true");
}
else
{
sw.WriteLine("new int[]{");
foreach (var arc in bddb.SerializeCompact(catBdd))
{
sw.WriteLine("{0},", arc);
}
sw.WriteLine("},");
}
}
sw.WriteLine("};");
if (bits == 7)
{
sw.WriteLine(@"/// <summary>
/// Whitespace character ranges.
/// </summary>");
sw.WriteLine("public static int[][] " + field + "Whitespace = new int[][]{");
foreach (int[] range in whitespace.ranges)
{
sw.WriteLine(" new int[]{" + string.Format("{0},{1}", range[0], range[1]) + "},");
}
sw.WriteLine("};");
sw.WriteLine(@"/// <summary>
/// Word character ranges.
/// </summary>");
sw.WriteLine("public static int[][] " + field + "WordCharacter = new int[][]{");
foreach (int[] range in wordcharacter.ranges)
{
sw.WriteLine(" new int[]{" + string.Format("{0},{1}", range[0], range[1]) + "},");
}
sw.WriteLine("};");
}
sw.WriteLine(@"/// <summary>
/// Compact BDD encoding of the whitespace characters.
/// </summary>");
sw.WriteLine("public static int[] " + field + "WhitespaceBdd = new int[]{");
foreach (var arc in bddb.SerializeCompact(whitespaceBdd))
{
sw.WriteLine("{0},", arc);
}
sw.WriteLine("};");
sw.WriteLine(@"/// <summary>
/// Compact BDD encoding of word characters
/// </summary>");
sw.WriteLine("public static int[] " + field + "WordCharacterBdd = new int[]{");
foreach (var arc in bddb.SerializeCompact(wordCharBdd))
{
sw.WriteLine("{0},", arc);
}
sw.WriteLine("};");
}
private static void WriteRangeFields(BitWidth encoding, StreamWriter sw, string field)
{
int bits = (int)encoding;
int maxChar = (1 << bits) - 1;
var catMap = new Dictionary<UnicodeCategory, Ranges>();
for (int c = 0; c < 30; c++)
catMap[(UnicodeCategory)c] = new Ranges();
Ranges whitespace = new Ranges();
Ranges wordcharacter = new Ranges();
for (int i = 0; i <= maxChar; i++)
{
char ch = (char)i;
if (char.IsWhiteSpace(ch))
whitespace.Add(i);
UnicodeCategory cat = char.GetUnicodeCategory(ch);
catMap[cat].Add(i);
int catCode = (int)cat;
//in .NET 3.5
if (bits == 7)
if (catCode == 0 || catCode == 1 || catCode == 2 || catCode == 3 || catCode == 4 || catCode == 5 || catCode == 8 || catCode == 18)
wordcharacter.Add(i);
}
//generate bdd reprs for each of the category ranges
BDD[] catBDDs = new BDD[30];
CharSetSolver bddb = new CharSetSolver(encoding);
for (int c = 0; c < 30; c++)
catBDDs[c] = bddb.MkBddForIntRanges(catMap[(UnicodeCategory)c].ranges);
BDD whitespaceBdd = bddb.MkBddForIntRanges(whitespace.ranges);
//in .NET 3.5 category 5 was NOT a word character
//union of categories 0,1,2,3,4,8,18
BDD wordCharBdd = bddb.MkOr(catBDDs[0],
bddb.MkOr(catBDDs[1],
bddb.MkOr(catBDDs[2],
bddb.MkOr(catBDDs[3],
bddb.MkOr(catBDDs[4],
bddb.MkOr(catBDDs[5],
bddb.MkOr(catBDDs[8], catBDDs[18])))))));
if (bits == 7)
{
sw.WriteLine(@"/// <summary>
/// Array of 30 UnicodeCategory ranges. Each entry is a pair of integers.
/// corresponding to the lower and upper bounds of the unicodes of the characters
/// that have the given UnicodeCategory code (between 0 and 29).
/// </summary>");
sw.WriteLine("public static int[][][] " + field + " = new int[][][]{");
foreach (UnicodeCategory c in catMap.Keys)
{
sw.WriteLine("//{0}({1}):", c, (int)c);
if (catMap[c].Count == 0)
sw.WriteLine("null,");
else
{
sw.WriteLine("new int[][]{");
foreach (int[] range in catMap[c].ranges)
sw.WriteLine(" new int[]{" + string.Format("{0},{1}", range[0], range[1]) + "},");
sw.WriteLine("},");
}
}
sw.WriteLine("};");
}
sw.WriteLine(@"/// <summary>
/// Compact BDD encodings of the categories.
/// </summary>");
sw.WriteLine("public static int[][] " + field + "Bdd = new int[][]{");
foreach (UnicodeCategory c in catMap.Keys)
{
sw.WriteLine("//{0}({1}):", c, (int)c);
BDD catBdd = catBDDs[(int)c];
if (catBdd == null || catBdd.IsEmpty)
sw.WriteLine("null, //false");
else if (catBdd.IsFull)
sw.WriteLine("new int[]{0,0}, //true");
else
{
sw.WriteLine("new int[]{");
foreach (var arc in bddb.SerializeCompact(catBdd))
sw.WriteLine("{0},", arc);
sw.WriteLine("},");
}
}
sw.WriteLine("};");
if (bits == 7)
{
sw.WriteLine(@"/// <summary>
/// Whitespace character ranges.
/// </summary>");
sw.WriteLine("public static int[][] " + field + "Whitespace = new int[][]{");
foreach (int[] range in whitespace.ranges)
sw.WriteLine(" new int[]{" + string.Format("{0},{1}", range[0], range[1]) + "},");
sw.WriteLine("};");
sw.WriteLine(@"/// <summary>
/// Word character ranges.
/// </summary>");
sw.WriteLine("public static int[][] " + field + "WordCharacter = new int[][]{");
foreach (int[] range in wordcharacter.ranges)
sw.WriteLine(" new int[]{" + string.Format("{0},{1}", range[0], range[1]) + "},");
sw.WriteLine("};");
}
sw.WriteLine(@"/// <summary>
/// Compact BDD encoding of the whitespace characters.
/// </summary>");
sw.WriteLine("public static int[] " + field + "WhitespaceBdd = new int[]{");
foreach (var arc in bddb.SerializeCompact(whitespaceBdd))
sw.WriteLine("{0},", arc);
sw.WriteLine("};");
sw.WriteLine(@"/// <summary>
/// Compact BDD encoding of word characters
/// </summary>");
sw.WriteLine("public static int[] " + field + "WordCharacterBdd = new int[]{");
foreach (var arc in bddb.SerializeCompact(wordCharBdd))
sw.WriteLine("{0},", arc);
sw.WriteLine("};");
}