/**
* Get Test Queries. The InputStream is closed.
*/
public static IEnumerator<SpatialTestQuery> GetTestQueries(
SpatialArgsParser parser,
SpatialContext ctx,
string name,
Stream @in)
{
List<SpatialTestQuery> results = new 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.HasMoreTokens())
{
test.ids.Add(st.NextToken().Trim());
}
test.args = parser.Parse(line.Substring(idx + 1).Trim(), ctx);
results.Add(test);
}
catch (Exception ex)
{
throw new ApplicationException("invalid query line: " + test.line, ex);
}
}
}
finally
{
bufInput.Dispose();
}
return results.GetEnumerator();
}
private static void AssertTrie(Trie trie, string file, bool usefull,
bool storeorig)
{
using (TextReader @in =
new StreamReader(new FileStream(file, FileMode.Open), Encoding.UTF8))
{
for (string line = @in.ReadLine(); line != null; line = @in.ReadLine())
{
try
{
line = line.ToLowerInvariant();
StringTokenizer st = new StringTokenizer(line);
string stem = st.NextToken();
if (storeorig)
{
string cmd = (usefull) ? trie.GetFully(stem) : trie
.GetLastOnPath(stem);
StringBuilder stm = new StringBuilder(stem);
Diff.Apply(stm, cmd);
assertEquals(stem.ToLowerInvariant(), stm.ToString().ToLowerInvariant());
}
while (st.HasMoreTokens())
{
string token = st.NextToken();
if (token.Equals(stem))
{
continue;
}
string cmd = (usefull) ? trie.GetFully(token) : trie
.GetLastOnPath(token);
StringBuilder stm = new StringBuilder(token);
Diff.Apply(stm, cmd);
assertEquals(stem.ToLowerInvariant(), stm.ToString().ToLowerInvariant());
}
}
catch (InvalidOperationException /*x*/)
{
// no base token (stem) on a line
}
}
}
}
/**
* Entry point to the Compile application.
* <p>
* This program takes any number of arguments: the first is the name of the
* desired stemming algorithm to use (a list is available in the package
* description) , all of the rest should be the path or paths to a file or
* files containing a stemmer table to compile.
*
* @param args the command line arguments
*/
public static void Main(string[] args)
{
if (args.Length < 1)
{
return;
}
args[0].ToUpperInvariant();
backward = args[0][0] == '-';
int qq = (backward) ? 1 : 0;
bool storeorig = false;
if (args[0][qq] == '0')
{
storeorig = true;
qq++;
}
multi = args[0][qq] == 'M';
if (multi)
{
qq++;
}
// LUCENENET TODO: Is this any different than Encoding.UTF8?
//String charset = System.getProperty("egothor.stemmer.charset", "UTF-8");
char[] optimizer = new char[args[0].Length - qq];
for (int i = 0; i < optimizer.Length; i++)
{
optimizer[i] = args[0][qq + i];
}
for (int i = 1; i < args.Length; i++)
{
TextReader @in;
// System.out.println("[" + args[i] + "]");
Diff diff = new Diff();
//int stems = 0; // not used
int words = 0;
AllocTrie();
Console.WriteLine(args[i]);
using (@in = new StreamReader(
new FileStream(args[i], FileMode.Open, FileAccess.Read), Encoding.UTF8))
{
for (string line = @in.ReadLine(); line != null; line = @in.ReadLine())
{
try
{
line = line.ToLowerInvariant();
StringTokenizer st = new StringTokenizer(line);
string stem = st.NextToken();
if (storeorig)
{
trie.Add(stem, "-a");
words++;
}
while (st.HasMoreTokens())
{
string token = st.NextToken();
if (token.Equals(stem) == false)
{
trie.Add(token, diff.Exec(token, stem));
words++;
}
}
}
catch (InvalidOperationException /*x*/)
{
// no base token (stem) on a line
}
}
}
Optimizer o = new Optimizer();
Optimizer2 o2 = new Optimizer2();
Lift l = new Lift(true);
Lift e = new Lift(false);
Gener g = new Gener();
for (int j = 0; j < optimizer.Length; j++)
{
string prefix;
switch (optimizer[j])
{
case 'G':
trie = trie.Reduce(g);
prefix = "G: ";
break;
case 'L':
trie = trie.Reduce(l);
prefix = "L: ";
break;
case 'E':
trie = trie.Reduce(e);
prefix = "E: ";
break;
case '2':
trie = trie.Reduce(o2);
prefix = "2: ";
break;
case '1':
trie = trie.Reduce(o);
prefix = "1: ";
break;
default:
continue;
}
trie.PrintInfo(System.Console.Out, prefix + " ");
}
using (DataOutputStream os = new DataOutputStream(
new FileStream(args[i] + ".out", FileMode.OpenOrCreate, FileAccess.Write)))
{
os.WriteUTF(args[0]);
trie.Store(os);
}
}
}
/// <summary>
/// Entry point to the DiffIt application.
/// <para>
/// This application takes one argument, the path to a file containing a
/// stemmer table. The program reads the file and generates the patch commands
/// for the stems.
/// </para>
/// </summary>
/// <param name="args">the path to a file containing a stemmer table</param>
public static void Main(string[] args)
{
int ins = Get(0, args[0]);
int del = Get(1, args[0]);
int rep = Get(2, args[0]);
int nop = Get(3, args[0]);
for (int i = 1; i < args.Length; i++)
{
TextReader @in;
// System.out.println("[" + args[i] + "]");
Diff diff = new Diff(ins, del, rep, nop);
// LUCENENET TODO: Is using Encoding.UTF8 good enough?
//String charset = System.getProperty("egothor.stemmer.charset", "UTF-8");
@in = new StreamReader(new FileStream(args[i], FileMode.Open, FileAccess.Read), Encoding.UTF8);
for (string line = @in.ReadLine(); line != null; line = @in.ReadLine())
{
try
{
line = line.ToLowerInvariant();
StringTokenizer st = new StringTokenizer(line);
string stem = st.NextToken();
Console.WriteLine(stem + " -a");
while (st.HasMoreTokens())
{
String token = st.NextToken();
if (token.Equals(stem) == false)
{
Console.WriteLine(stem + " " + diff.Exec(token, stem));
}
}
}
catch (InvalidOperationException /*x*/)
{
// no base token (stem) on a line
}
}
}
}
//Helper method to construct Lucene documents used in our tests
Document getDocumentFromString(String nameValuePairs)
{
Document result = new Document();
StringTokenizer st = new StringTokenizer(nameValuePairs, "\t=");
while (st.HasMoreTokens())
{
String name = st.NextToken().Trim();
if (st.HasMoreTokens())
{
String value = st.NextToken().Trim();
result.Add(NewTextField(name, value, Field.Store.YES));
}
}
return result;
}
//Helper method to construct Lucene query forms used in our test
IDictionary<string, string> getPropsFromString(String nameValuePairs)
{
IDictionary<string, string> result = new Dictionary<string, string>();
StringTokenizer st = new StringTokenizer(nameValuePairs, "\t=");
while (st.HasMoreTokens())
{
String name = st.NextToken().Trim();
if (st.HasMoreTokens())
{
String value = st.NextToken().Trim();
result[name] = value;
}
}
return result;
}
/// <summary>
/// Parses "a=b c=d f" (whitespace separated) into name-value pairs. If there
/// is no '=' as in 'f' above then it's short for f=f.
/// </summary>
protected static IDictionary<string, string> ParseMap(string body)
{
var map = new Dictionary<string, string>();
StringTokenizer st = new StringTokenizer(body, " \n\t");
while (st.HasMoreTokens())
{
string a = st.NextToken();
int idx = a.IndexOf('=');
if (idx > 0)
{
string k = a.Substring(0, idx - 0);
string v = a.Substring(idx + 1);
map[k] = v;
}
else
{
map[a] = a;
}
}
return map;
}
