public override IEnumerator <string> GetEnumerator()
{
var list = new JCG.List <string> {
DelegatingAtomicReader.FIELD_NAME
};
return(list.GetEnumerator());
}
private void TestCaseIterator(int itrsWithVal, int specifiedValsOnItr, bool removeDups)
{
// Build a random number of lists
IList <int?> expected = new JCG.List <int?>();
Random random = new Random(Random.Next());
int numLists = itrsWithVal + random.Next(1000 - itrsWithVal);
IList <int>[] lists = new IList <int> [numLists];
for (int i = 0; i < numLists; i++)
{
lists[i] = new JCG.List <int>();
}
int start = random.Next(1000000);
int end = start + VALS_TO_MERGE / itrsWithVal / Math.Abs(specifiedValsOnItr);
for (int i = start; i < end; i++)
{
int maxList = lists.Length;
int maxValsOnItr = 0;
int sumValsOnItr = 0;
for (int itrWithVal = 0; itrWithVal < itrsWithVal; itrWithVal++)
{
int list = random.Next(maxList);
int valsOnItr = specifiedValsOnItr < 0 ? (1 + random.Next(-specifiedValsOnItr)) : specifiedValsOnItr;
maxValsOnItr = Math.Max(maxValsOnItr, valsOnItr);
sumValsOnItr += valsOnItr;
for (int valOnItr = 0; valOnItr < valsOnItr; valOnItr++)
{
lists[list].Add(i);
}
maxList = maxList - 1;
ArrayUtil.Swap(lists, list, maxList);
}
int maxCount = removeDups ? maxValsOnItr : sumValsOnItr;
for (int count = 0; count < maxCount; count++)
{
expected.Add(i);
}
}
// Now check that they get merged cleanly
IEnumerator <int>[] itrs = new IEnumerator <int> [numLists];
for (int i = 0; i < numLists; i++)
{
itrs[i] = lists[i].GetEnumerator();
}
MergedIterator <int> mergedItr = new MergedIterator <int>(removeDups, itrs);
IEnumerator <int?> expectedItr = expected.GetEnumerator();
while (expectedItr.MoveNext())
{
Assert.IsTrue(mergedItr.MoveNext());
Assert.AreEqual(expectedItr.Current, mergedItr.Current);
}
Assert.IsFalse(mergedItr.MoveNext());
}
/**
* Get Test Queries. The InputStream is closed.
*/
public static IEnumerator <SpatialTestQuery> GetTestQueries(
SpatialArgsParser parser,
SpatialContext ctx,
string name,
Stream @in)
{
IList <SpatialTestQuery> results = new JCG.List <SpatialTestQuery>();
TextReader bufInput = new StreamReader(@in, Encoding.UTF8);
try
{
String line;
for (int lineNumber = 1; (line = bufInput.ReadLine()) != null; lineNumber++)
{
SpatialTestQuery test = new SpatialTestQuery();
test.line = line;
test.lineNumber = lineNumber;
try
{
// skip a comment
if (line.StartsWith("[", StringComparison.Ordinal))
{
int idx2 = line.IndexOf(']');
if (idx2 > 0)
{
line = line.Substring(idx2 + 1);
}
}
int idx = line.IndexOf('@');
StringTokenizer st = new StringTokenizer(line.Substring(0, idx - 0));
while (st.MoveNext())
{
test.ids.Add(st.Current.Trim());
}
test.args = parser.Parse(line.Substring(idx + 1).Trim(), ctx);
results.Add(test);
}
catch (Exception ex)
{
throw RuntimeException.Create("invalid query line: " + test.line, ex);
}
}
}
finally
{
bufInput.Dispose();
}
return(results.GetEnumerator());
}
public virtual void TestAllFoldings()
{
// Alternating strings of:
// 1. All non-ASCII characters to be folded, concatenated together as a
// single string.
// 2. The string of ASCII characters to which each of the above
// characters should be folded.
string[] foldings = new string[] { "À" + "Á" + "Â" + "Ã" + "Ä" + "Å" + "Ā" + "Ă" + "Ą" + "Ə" + "Ǎ" + "Ǟ" + "Ǡ" + "Ǻ" + "Ȁ" + "Ȃ" + "Ȧ" + "Ⱥ" + "ᴀ" + "Ḁ" + "Ạ" + "Ả" + "Ấ" + "Ầ" + "Ẩ" + "Ẫ" + "Ậ" + "Ắ" + "Ằ" + "Ẳ" + "Ẵ" + "Ặ" + "Ⓐ" + "Ａ", "A", "à" + "á" + "â" + "ã" + "ä" + "å" + "ā" + "ă" + "ą" + "ǎ" + "ǟ" + "ǡ" + "ǻ" + "ȁ" + "ȃ" + "ȧ" + "ɐ" + "ə" + "ɚ" + "ᶏ" + "ḁ" + "ᶕ" + "ẚ" + "ạ" + "ả" + "ấ" + "ầ" + "ẩ" + "ẫ" + "ậ" + "ắ" + "ằ" + "ẳ" + "ẵ" + "ặ" + "ₐ" + "ₔ" + "ⓐ" + "ⱥ" + "Ɐ" + "ａ", "a", "Ꜳ", "AA", "Æ" + "Ǣ" + "Ǽ" + "ᴁ", "AE", "Ꜵ", "AO", "Ꜷ", "AU", "Ꜹ" + "Ꜻ", "AV", "Ꜽ", "AY", "⒜", "(a)", "ꜳ", "aa", "æ" + "ǣ" + "ǽ" + "ᴂ", "ae", "ꜵ", "ao", "ꜷ", "au", "ꜹ" + "ꜻ", "av", "ꜽ", "ay", "Ɓ" + "Ƃ" + "Ƀ" + "ʙ" + "ᴃ" + "Ḃ" + "Ḅ" + "Ḇ" + "Ⓑ" + "Ｂ", "B", "ƀ" + "ƃ" + "ɓ" + "ᵬ" + "ᶀ" + "ḃ" + "ḅ" + "ḇ" + "ⓑ" + "ｂ", "b", "⒝", "(b)", "Ç" + "Ć" + "Ĉ" + "Ċ" + "Č" + "Ƈ" + "Ȼ" + "ʗ" + "ᴄ" + "Ḉ" + "Ⓒ" + "Ｃ", "C", "ç" + "ć" + "ĉ" + "ċ" + "č" + "ƈ" + "ȼ" + "ɕ" + "ḉ" + "ↄ" + "ⓒ" + "Ꜿ" + "ꜿ" + "ｃ", "c", "⒞", "(c)", "Ð" + "Ď" + "Đ" + "Ɖ" + "Ɗ" + "Ƌ" + "ᴅ" + "ᴆ" + "Ḋ" + "Ḍ" + "Ḏ" + "Ḑ" + "Ḓ" + "Ⓓ" + "Ꝺ" + "Ｄ", "D", "ð" + "ď" + "đ" + "ƌ" + "ȡ" + "ɖ" + "ɗ" + "ᵭ" + "ᶁ" + "ᶑ" + "ḋ" + "ḍ" + "ḏ" + "ḑ" + "ḓ" + "ⓓ" + "ꝺ" + "ｄ", "d", "DŽ" + "DZ", "DZ", "Dž" + "Dz", "Dz", "⒟", "(d)", "ȸ", "db", "dž" + "dz" + "ʣ" + "ʥ", "dz", "È" + "É" + "Ê" + "Ë" + "Ē" + "Ĕ" + "Ė" + "Ę" + "Ě" + "Ǝ" + "Ɛ" + "Ȅ" + "Ȇ" + "Ȩ" + "Ɇ" + "ᴇ" + "Ḕ" + "Ḗ" + "Ḙ" + "Ḛ" + "Ḝ" + "Ẹ" + "Ẻ" + "Ẽ" + "Ế" + "Ề" + "Ể" + "Ễ" + "Ệ" + "Ⓔ" + "ⱻ" + "Ｅ", "E", "è" + "é" + "ê" + "ë" + "ē" + "ĕ" + "ė" + "ę" + "ě" + "ǝ" + "ȅ" + "ȇ" + "ȩ" + "ɇ" + "ɘ" + "ɛ" + "ɜ" + "ɝ" + "ɞ" + "ʚ" + "ᴈ" + "ᶒ" + "ᶓ" + "ᶔ" + "ḕ" + "ḗ" + "ḙ" + "ḛ" + "ḝ" + "ẹ" + "ẻ" + "ẽ" + "ế" + "ề" + "ể" + "ễ" + "ệ" + "ₑ" + "ⓔ" + "ⱸ" + "ｅ", "e", "⒠", "(e)", "Ƒ" + "Ḟ" + "Ⓕ" + "ꜰ" + "Ꝼ" + "ꟻ" + "Ｆ", "F", "ƒ" + "ᵮ" + "ᶂ" + "ḟ" + "ẛ" + "ⓕ" + "ꝼ" + "ｆ", "f", "⒡", "(f)", "ff", "ff", "ffi", "ffi", "ffl", "ffl", "fi", "fi", "fl", "fl", "Ĝ" + "Ğ" + "Ġ" + "Ģ" + "Ɠ" + "Ǥ" + "ǥ" + "Ǧ" + "ǧ" + "Ǵ" + "ɢ" + "ʛ" + "Ḡ" + "Ⓖ" + "Ᵹ" + "Ꝿ" + "Ｇ", "G", "ĝ" + "ğ" + "ġ" + "ģ" + "ǵ" + "ɠ" + "ɡ" + "ᵷ" + "ᵹ" + "ᶃ" + "ḡ" + "ⓖ" + "ꝿ" + "ｇ", "g", "⒢", "(g)", "Ĥ" + "Ħ" + "Ȟ" + "ʜ" + "Ḣ" + "Ḥ" + "Ḧ" + "Ḩ" + "Ḫ" + "Ⓗ" + "Ⱨ" + "Ⱶ" + "Ｈ", "H", "ĥ" + "ħ" + "ȟ" + "ɥ" + "ɦ" + "ʮ" + "ʯ" + "ḣ" + "ḥ" + "ḧ" + "ḩ" + "ḫ" + "ẖ" + "ⓗ" + "ⱨ" + "ⱶ" + "ｈ", "h", "Ƕ", "HV", "⒣", "(h)", "ƕ", "hv", "Ì" + "Í" + "Î" + "Ï" + "Ĩ" + "Ī" + "Ĭ" + "Į" + "İ" + "Ɩ" + "Ɨ" + "Ǐ" + "Ȉ" + "Ȋ" + "ɪ" + "ᵻ" + "Ḭ" + "Ḯ" + "Ỉ" + "Ị" + "Ⓘ" + "ꟾ" + "Ｉ", "I", "ì" + "í" + "î" + "ï" + "ĩ" + "ī" + "ĭ" + "į" + "ı" + "ǐ" + "ȉ" + "ȋ" + "ɨ" + "ᴉ" + "ᵢ" + "ᵼ" + "ᶖ" + "ḭ" + "ḯ" + "ỉ" + "ị" + "ⁱ" + "ⓘ" + "ｉ", "i", "IJ", "IJ", "⒤", "(i)", "ij", "ij", "Ĵ" + "Ɉ" + "ᴊ" + "Ⓙ" + "Ｊ", "J", "ĵ" + "ǰ" + "ȷ" + "ɉ" + "ɟ" + "ʄ" + "ʝ" + "ⓙ" + "ⱼ" + "ｊ", "j", "⒥", "(j)", "Ķ" + "Ƙ" + "Ǩ" + "ᴋ" + "Ḱ" + "Ḳ" + "Ḵ" + "Ⓚ" + "Ⱪ" + "Ꝁ" + "Ꝃ" + "Ꝅ" + "Ｋ", "K", "ķ" + "ƙ" + "ǩ" + "ʞ" + "ᶄ" + "ḱ" + "ḳ" + "ḵ" + "ⓚ" + "ⱪ" + "ꝁ" + "ꝃ" + "ꝅ" + "ｋ", "k", "⒦", "(k)", "Ĺ" + "Ļ" + "Ľ" + "Ŀ" + "Ł" + "Ƚ" + "ʟ" + "ᴌ" + "Ḷ" + "Ḹ" + "Ḻ" + "Ḽ" + "Ⓛ" + "Ⱡ" + "Ɫ" + "Ꝇ" + "Ꝉ" + "Ꞁ" + "Ｌ", "L", "ĺ" + "ļ" + "ľ" + "ŀ" + "ł" + "ƚ" + "ȴ" + "ɫ" + "ɬ" + "ɭ" + "ᶅ" + "ḷ" + "ḹ" + "ḻ" + "ḽ" + "ⓛ" + "ⱡ" + "ꝇ" + "ꝉ" + "ꞁ" + "ｌ", "l", "LJ", "LJ", "Ỻ", "LL", "Lj", "Lj", "⒧", "(l)", "lj", "lj", "ỻ", "ll", "ʪ", "ls", "ʫ", "lz", "Ɯ" + "ᴍ" + "Ḿ" + "Ṁ" + "Ṃ" + "Ⓜ" + "Ɱ" + "ꟽ" + "ꟿ" + "Ｍ", "M", "ɯ" + "ɰ" + "ɱ" + "ᵯ" + "ᶆ" + "ḿ" + "ṁ" + "ṃ" + "ⓜ" + "ｍ", "m", "⒨", "(m)", "Ñ" + "Ń" + "Ņ" + "Ň" + "Ŋ" + "Ɲ" + "Ǹ" + "Ƞ" + "ɴ" + "ᴎ" + "Ṅ" + "Ṇ" + "Ṉ" + "Ṋ" + "Ⓝ" + "Ｎ", "N", "ñ" + "ń" + "ņ" + "ň" + "ʼn" + "ŋ" + "ƞ" + "ǹ" + "ȵ" + "ɲ" + "ɳ" + "ᵰ" + "ᶇ" + "ṅ" + "ṇ" + "ṉ" + "ṋ" + "ⁿ" + "ⓝ" + "ｎ", "n", "NJ", "NJ", "Nj", "Nj", "⒩", "(n)", "nj", "nj", "Ò" + "Ó" + "Ô" + "Õ" + "Ö" + "Ø" + "Ō" + "Ŏ" + "Ő" + "Ɔ" + "Ɵ" + "Ơ" + "Ǒ" + "Ǫ" + "Ǭ" + "Ǿ" + "Ȍ" + "Ȏ" + "Ȫ" + "Ȭ" + "Ȯ" + "Ȱ" + "ᴏ" + "ᴐ" + "Ṍ" + "Ṏ" + "Ṑ" + "Ṓ" + "Ọ" + "Ỏ" + "Ố" + "Ồ" + "Ổ" + "Ỗ" + "Ộ" + "Ớ" + "Ờ" + "Ở" + "Ỡ" + "Ợ" + "Ⓞ" + "Ꝋ" + "Ꝍ" + "Ｏ", "O", "ò" + "ó" + "ô" + "õ" + "ö" + "ø" + "ō" + "ŏ" + "ő" + "ơ" + "ǒ" + "ǫ" + "ǭ" + "ǿ" + "ȍ" + "ȏ" + "ȫ" + "ȭ" + "ȯ" + "ȱ" + "ɔ" + "ɵ" + "ᴖ" + "ᴗ" + "ᶗ" + "ṍ" + "ṏ" + "ṑ" + "ṓ" + "ọ" + "ỏ" + "ố" + "ồ" + "ổ" + "ỗ" + "ộ" + "ớ" + "ờ" + "ở" + "ỡ" + "ợ" + "ₒ" + "ⓞ" + "ⱺ" + "ꝋ" + "ꝍ" + "ｏ", "o", "Œ" + "ɶ", "OE", "Ꝏ", "OO", "Ȣ" + "ᴕ", "OU", "⒪", "(o)", "œ" + "ᴔ", "oe", "ꝏ", "oo", "ȣ", "ou", "Ƥ" + "ᴘ" + "Ṕ" + "Ṗ" + "Ⓟ" + "Ᵽ" + "Ꝑ" + "Ꝓ" + "Ꝕ" + "Ｐ", "P", "ƥ" + "ᵱ" + "ᵽ" + "ᶈ" + "ṕ" + "ṗ" + "ⓟ" + "ꝑ" + "ꝓ" + "ꝕ" + "ꟼ" + "ｐ", "p", "⒫", "(p)", "Ɋ" + "Ⓠ" + "Ꝗ" + "Ꝙ" + "Ｑ", "Q", "ĸ" + "ɋ" + "ʠ" + "ⓠ" + "ꝗ" + "ꝙ" + "ｑ", "q", "⒬", "(q)", "ȹ", "qp", "Ŕ" + "Ŗ" + "Ř" + "Ȑ" + "Ȓ" + "Ɍ" + "ʀ" + "ʁ" + "ᴙ" + "ᴚ" + "Ṙ" + "Ṛ" + "Ṝ" + "Ṟ" + "Ⓡ" + "Ɽ" + "Ꝛ" + "Ꞃ" + "Ｒ", "R", "ŕ" + "ŗ" + "ř" + "ȑ" + "ȓ" + "ɍ" + "ɼ" + "ɽ" + "ɾ" + "ɿ" + "ᵣ" + "ᵲ" + "ᵳ" + "ᶉ" + "ṙ" + "ṛ" + "ṝ" + "ṟ" + "ⓡ" + "ꝛ" + "ꞃ" + "ｒ", "r", "⒭", "(r)", "Ś" + "Ŝ" + "Ş" + "Š" + "Ș" + "Ṡ" + "Ṣ" + "Ṥ" + "Ṧ" + "Ṩ" + "Ⓢ" + "ꜱ" + "ꞅ" + "Ｓ", "S", "ś" + "ŝ" + "ş" + "š" + "ſ" + "ș" + "ȿ" + "ʂ" + "ᵴ" + "ᶊ" + "ṡ" + "ṣ" + "ṥ" + "ṧ" + "ṩ" + "ẜ" + "ẝ" + "ⓢ" + "Ꞅ" + "ｓ", "s", "ẞ", "SS", "⒮", "(s)", "ß", "ss", "st", "st", "Ţ" + "Ť" + "Ŧ" + "Ƭ" + "Ʈ" + "Ț" + "Ⱦ" + "ᴛ" + "Ṫ" + "Ṭ" + "Ṯ" + "Ṱ" + "Ⓣ" + "Ꞇ" + "Ｔ", "T", "ţ" + "ť" + "ŧ" + "ƫ" + "ƭ" + "ț" + "ȶ" + "ʇ" + "ʈ" + "ᵵ" + "ṫ" + "ṭ" + "ṯ" + "ṱ" + "ẗ" + "ⓣ" + "ⱦ" + "ｔ", "t", "Þ" + "Ꝧ", "TH", "Ꜩ", "TZ", "⒯", "(t)", "ʨ", "tc", "þ" + "ᵺ" + "ꝧ", "th", "ʦ", "ts", "ꜩ", "tz", "Ù" + "Ú" + "Û" + "Ü" + "Ũ" + "Ū" + "Ŭ" + "Ů" + "Ű" + "Ų" + "Ư" + "Ǔ" + "Ǖ" + "Ǘ" + "Ǚ" + "Ǜ" + "Ȕ" + "Ȗ" + "Ʉ" + "ᴜ" + "ᵾ" + "Ṳ" + "Ṵ" + "Ṷ" + "Ṹ" + "Ṻ" + "Ụ" + "Ủ" + "Ứ" + "Ừ" + "Ử" + "Ữ" + "Ự" + "Ⓤ" + "Ｕ", "U", "ù" + "ú" + "û" + "ü" + "ũ" + "ū" + "ŭ" + "ů" + "ű" + "ų" + "ư" + "ǔ" + "ǖ" + "ǘ" + "ǚ" + "ǜ" + "ȕ" + "ȗ" + "ʉ" + "ᵤ" + "ᶙ" + "ṳ" + "ṵ" + "ṷ" + "ṹ" + "ṻ" + "ụ" + "ủ" + "ứ" + "ừ" + "ử" + "ữ" + "ự" + "ⓤ" + "ｕ", "u", "⒰", "(u)", "ᵫ", "ue", "Ʋ" + "Ʌ" + "ᴠ" + "Ṽ" + "Ṿ" + "Ỽ" + "Ⓥ" + "Ꝟ" + "Ꝩ" + "Ｖ", "V", "ʋ" + "ʌ" + "ᵥ" + "ᶌ" + "ṽ" + "ṿ" + "ⓥ" + "ⱱ" + "ⱴ" + "ꝟ" + "ｖ", "v", "Ꝡ", "VY", "⒱", "(v)", "ꝡ", "vy", "Ŵ" + "Ƿ" + "ᴡ" + "Ẁ" + "Ẃ" + "Ẅ" + "Ẇ" + "Ẉ" + "Ⓦ" + "Ⱳ" + "Ｗ", "W", "ŵ" + "ƿ" + "ʍ" + "ẁ" + "ẃ" + "ẅ" + "ẇ" + "ẉ" + "ẘ" + "ⓦ" + "ⱳ" + "ｗ", "w", "⒲", "(w)", "Ẋ" + "Ẍ" + "Ⓧ" + "Ｘ", "X", "ᶍ" + "ẋ" + "ẍ" + "ₓ" + "ⓧ" + "ｘ", "x", "⒳", "(x)", "Ý" + "Ŷ" + "Ÿ" + "Ƴ" + "Ȳ" + "Ɏ" + "ʏ" + "Ẏ" + "Ỳ" + "Ỵ" + "Ỷ" + "Ỹ" + "Ỿ" + "Ⓨ" + "Ｙ", "Y", "ý" + "ÿ" + "ŷ" + "ƴ" + "ȳ" + "ɏ" + "ʎ" + "ẏ" + "ẙ" + "ỳ" + "ỵ" + "ỷ" + "ỹ" + "ỿ" + "ⓨ" + "ｙ", "y", "⒴", "(y)", "Ź" + "Ż" + "Ž" + "Ƶ" + "Ȝ" + "Ȥ" + "ᴢ" + "Ẑ" + "Ẓ" + "Ẕ" + "Ⓩ" + "Ⱬ" + "Ꝣ" + "Ｚ", "Z", "ź" + "ż" + "ž" + "ƶ" + "ȝ" + "ȥ" + "ɀ" + "ʐ" + "ʑ" + "ᵶ" + "ᶎ" + "ẑ" + "ẓ" + "ẕ" + "ⓩ" + "ⱬ" + "ꝣ" + "ｚ", "z", "⒵", "(z)", "⁰" + "₀" + "⓪" + "⓿" + "０", "0", "¹" + "₁" + "①" + "⓵" + "❶" + "➀" + "➊" + "１", "1", "⒈", "1.", "⑴", "(1)", "²" + "₂" + "②" + "⓶" + "❷" + "➁" + "➋" + "２", "2", "⒉", "2.", "⑵", "(2)", "³" + "₃" + "③" + "⓷" + "❸" + "➂" + "➌" + "３", "3", "⒊", "3.", "⑶", "(3)", "⁴" + "₄" + "④" + "⓸" + "❹" + "➃" + "➍" + "４", "4", "⒋", "4.", "⑷", "(4)", "⁵" + "₅" + "⑤" + "⓹" + "❺" + "➄" + "➎" + "５", "5", "⒌", "5.", "⑸", "(5)", "⁶" + "₆" + "⑥" + "⓺" + "❻" + "➅" + "➏" + "６", "6", "⒍", "6.", "⑹", "(6)", "⁷" + "₇" + "⑦" + "⓻" + "❼" + "➆" + "➐" + "７", "7", "⒎", "7.", "⑺", "(7)", "⁸" + "₈" + "⑧" + "⓼" + "❽" + "➇" + "➑" + "８", "8", "⒏", "8.", "⑻", "(8)", "⁹" + "₉" + "⑨" + "⓽" + "❾" + "➈" + "➒" + "９", "9", "⒐", "9.", "⑼", "(9)", "⑩" + "⓾" + "❿" + "➉" + "➓", "10", "⒑", "10.", "⑽", "(10)", "⑪" + "⓫", "11", "⒒", "11.", "⑾", "(11)", "⑫" + "⓬", "12", "⒓", "12.", "⑿", "(12)", "⑬" + "⓭", "13", "⒔", "13.", "⒀", "(13)", "⑭" + "⓮", "14", "⒕", "14.", "⒁", "(14)", "⑮" + "⓯", "15", "⒖", "15.", "⒂", "(15)", "⑯" + "⓰", "16", "⒗", "16.", "⒃", "(16)", "⑰" + "⓱", "17", "⒘", "17.", "⒄", "(17)", "⑱" + "⓲", "18", "⒙", "18.", "⒅", "(18)", "⑲" + "⓳", "19", "⒚", "19.", "⒆", "(19)", "⑳" + "⓴", "20", "⒛", "20.", "⒇", "(20)", "«" + "»" + "“" + "”" + "„" + "″" + "‶" + "❝" + "❞" + "❮" + "❯" + "＂", "\"", "‘" + "’" + "‚" + "‛" + "′" + "‵" + "‹" + "›" + "❛" + "❜" + "＇", "'", "‐" + "‑" + "‒" + "–" + "—" + "⁻" + "₋" + "－", "-", "⁅" + "❲" + "［", "[", "⁆" + "❳" + "］", "]", "⁽" + "₍" + "❨" + "❪" + "（", "(", "⸨", "((", "⁾" + "₎" + "❩" + "❫" + "）", ")", "⸩", "))", "❬" + "❰" + "＜", "<", "❭" + "❱" + "＞", ">", "❴" + "｛", "{", "❵" + "｝", "}", "⁺" + "₊" + "＋", "+", "⁼" + "₌" + "＝", "=", "！", "!", "‼", "!!", "⁉", "!?", "＃", "#", "＄", "$", "⁒" + "％", "%", "＆", "&", "⁎" + "＊", "*", "，", ",", "．", ".", "⁄" + "／", "/", "：", ":", "⁏" + "；", ";", "？", "?", "⁇", "??", "⁈", "?!", "＠", "@", "＼", "\\", "‸" + "＾", "^", "＿", "_", "⁓" + "～", "~" };
// Construct input text and expected output tokens
IList <string> expectedUnfoldedTokens = new JCG.List <string>();
IList <string> expectedFoldedTokens = new JCG.List <string>();
StringBuilder inputText = new StringBuilder();
for (int n = 0; n < foldings.Length; n += 2)
{
if (n > 0)
{
inputText.Append(' '); // Space between tokens
}
inputText.Append(foldings[n]);
// Construct the expected output tokens: both the unfolded and folded string,
// with the folded duplicated as many times as the number of characters in
// the input text.
StringBuilder expected = new StringBuilder();
int numChars = foldings[n].Length;
for (int m = 0; m < numChars; ++m)
{
expected.Append(foldings[n + 1]);
}
expectedUnfoldedTokens.Add(foldings[n]);
expectedFoldedTokens.Add(expected.ToString());
}
TokenStream stream = new MockTokenizer(new StringReader(inputText.ToString()), MockTokenizer.WHITESPACE, false);
ASCIIFoldingFilter filter = new ASCIIFoldingFilter(stream, Random.NextBoolean());
ICharTermAttribute termAtt = filter.GetAttribute <ICharTermAttribute>();
IEnumerator <string> unfoldedIter = expectedUnfoldedTokens.GetEnumerator();
IEnumerator <string> foldedIter = expectedFoldedTokens.GetEnumerator();
filter.Reset();
while (foldedIter.MoveNext())
{
unfoldedIter.MoveNext();
assertNextTerms(unfoldedIter.Current, foldedIter.Current, filter, termAtt);
}
assertFalse(filter.IncrementToken());
}
/** Reads the stream, consuming a format that is a tab-separated values of 3 columns:
* an "id", a "name" and the "shape". Empty lines and lines starting with a '#' are skipped.
* The stream is closed.
*/
public static IEnumerator <SpatialTestData> GetTestData(Stream @in, SpatialContext ctx)
{
IList <SpatialTestData> results = new JCG.List <SpatialTestData>();
TextReader bufInput = new StreamReader(@in, Encoding.UTF8);
try
{
String line;
while ((line = bufInput.ReadLine()) != null)
{
if (line.Length == 0 || line[0] == '#')
{
continue;
}
SpatialTestData data = new SpatialTestData();
String[] vals = line.Split('\t').TrimEnd();
if (vals.Length != 3)
{
throw RuntimeException.Create("bad format; expecting 3 tab-separated values for line: " + line);
}
data.id = vals[0];
data.name = vals[1];
try
{
data.shape = ctx.ReadShapeFromWkt(vals[2]);
}
catch (Spatial4n.Exceptions.ParseException e) // LUCENENET: Spatial4n has its own ParseException that is different than the one in Support
{
throw RuntimeException.Create(e);
}
results.Add(data);
}
}
finally
{
bufInput.Dispose();
}
return(results.GetEnumerator());
}
public virtual void TestFilteredDocIdSet()
{
const int maxdoc = 10;
DocIdSet innerSet = new DocIdSetAnonymousClass(this, maxdoc);
DocIdSet filteredSet = new FilteredDocIdSetAnonymousClass(this, innerSet);
DocIdSetIterator iter = filteredSet.GetIterator();
IList <int> list = new JCG.List <int>();
int doc = iter.Advance(3);
if (doc != DocIdSetIterator.NO_MORE_DOCS)
{
list.Add(Convert.ToInt32(doc));
while ((doc = iter.NextDoc()) != DocIdSetIterator.NO_MORE_DOCS)
{
list.Add(Convert.ToInt32(doc));
}
}
int[] docs = new int[list.Count];
int c = 0;
using IEnumerator <int> intIter = list.GetEnumerator();
while (intIter.MoveNext())
{
docs[c++] = intIter.Current;
}
int[] answer = new int[] { 4, 6, 8 };
bool same = Arrays.Equals(answer, docs);
if (!same)
{
Console.WriteLine("answer: " + Arrays.ToString(answer));
Console.WriteLine("gotten: " + Arrays.ToString(docs));
Assert.Fail();
}
}
/*
* Need to worry about multiple scenarios:
* - need to go for the longest match
* a b => foo #shouldn't match if "a b" is followed by "c d"
* a b c d => bar
* - need to backtrack - retry matches for tokens already read
* a b c d => foo
* b c => bar
* If the input stream is "a b c x", one will consume "a b c d"
* trying to match the first rule... all but "a" should be
* pushed back so a match may be made on "b c".
* - don't try and match generated tokens (thus need separate queue)
* matching is not recursive.
* - handle optional generation of original tokens in all these cases,
* merging token streams to preserve token positions.
* - preserve original positionIncrement of first matched token
*/
public override bool IncrementToken()
{
while (true)
{
// if there are any generated tokens, return them... don't try any
// matches against them, as we specifically don't want recursion.
if (replacement != null && replacement.MoveNext())
{
Copy(this, replacement.Current);
return(true);
}
// common case fast-path of first token not matching anything
AttributeSource firstTok = NextTok();
if (firstTok == null)
{
return(false);
}
var termAtt = firstTok.AddAttribute <ICharTermAttribute>();
SlowSynonymMap result = map.Submap != null?map.Submap.Get(termAtt.Buffer, 0, termAtt.Length) : null;
if (result == null)
{
Copy(this, firstTok);
return(true);
}
// fast-path failed, clone ourselves if needed
if (firstTok == this)
{
firstTok = CloneAttributes();
}
// OK, we matched a token, so find the longest match.
matched = new LinkedList <AttributeSource>();
result = Match(result);
if (result == null)
{
// no match, simply return the first token read.
Copy(this, firstTok);
return(true);
}
// reuse, or create new one each time?
IList <AttributeSource> generated = new JCG.List <AttributeSource>(result.Synonyms.Length + matched.Count + 1);
//
// there was a match... let's generate the new tokens, merging
// in the matched tokens (position increments need adjusting)
//
AttributeSource lastTok = matched.Count == 0 ? firstTok : matched.Last.Value;
bool includeOrig = result.IncludeOrig;
AttributeSource origTok = includeOrig ? firstTok : null;
IPositionIncrementAttribute firstPosIncAtt = firstTok.AddAttribute <IPositionIncrementAttribute>();
int origPos = firstPosIncAtt.PositionIncrement; // position of origTok in the original stream
int repPos = 0; // curr position in replacement token stream
int pos = 0; // current position in merged token stream
for (int i = 0; i < result.Synonyms.Length; i++)
{
Token repTok = result.Synonyms[i];
AttributeSource newTok = firstTok.CloneAttributes();
ICharTermAttribute newTermAtt = newTok.AddAttribute <ICharTermAttribute>();
IOffsetAttribute newOffsetAtt = newTok.AddAttribute <IOffsetAttribute>();
IPositionIncrementAttribute newPosIncAtt = newTok.AddAttribute <IPositionIncrementAttribute>();
IOffsetAttribute lastOffsetAtt = lastTok.AddAttribute <IOffsetAttribute>();
newOffsetAtt.SetOffset(newOffsetAtt.StartOffset, lastOffsetAtt.EndOffset);
newTermAtt.CopyBuffer(repTok.Buffer, 0, repTok.Length);
repPos += repTok.PositionIncrement;
if (i == 0) // make position of first token equal to original
{
repPos = origPos;
}
// if necessary, insert original tokens and adjust position increment
while (origTok != null && origPos <= repPos)
{
IPositionIncrementAttribute origPosInc = origTok.AddAttribute <IPositionIncrementAttribute>();
origPosInc.PositionIncrement = origPos - pos;
generated.Add(origTok);
pos += origPosInc.PositionIncrement;
//origTok = matched.Count == 0 ? null : matched.RemoveFirst();
if (matched.Count == 0)
{
origTok = null;
}
else
{
origTok = matched.First.Value;
matched.Remove(origTok);
}
if (origTok != null)
{
origPosInc = origTok.AddAttribute <IPositionIncrementAttribute>();
origPos += origPosInc.PositionIncrement;
}
}
newPosIncAtt.PositionIncrement = repPos - pos;
generated.Add(newTok);
pos += newPosIncAtt.PositionIncrement;
}
// finish up any leftover original tokens
while (origTok != null)
{
IPositionIncrementAttribute origPosInc = origTok.AddAttribute <IPositionIncrementAttribute>();
origPosInc.PositionIncrement = origPos - pos;
generated.Add(origTok);
pos += origPosInc.PositionIncrement;
if (matched.Count == 0)
{
origTok = null;
}
else
{
origTok = matched.First.Value;
matched.Remove(origTok);
}
if (origTok != null)
{
origPosInc = origTok.AddAttribute <IPositionIncrementAttribute>();
origPos += origPosInc.PositionIncrement;
}
}
// what if we replaced a longer sequence with a shorter one?
// a/0 b/5 => foo/0
// should I re-create the gap on the next buffered token?
replacement = generated.GetEnumerator();
// Now return to the top of the loop to read and return the first
// generated token.. The reason this is done is that we may have generated
// nothing at all, and may need to continue with more matching logic.
}
}
