private void Evaluate(IndentedTextWriter wrt, Delegate del, DataViewType typeRes, DataViewType[] types,
string text, int ichMin, int ichLim)
{
Contracts.AssertValue(del);
Contracts.AssertNonEmpty(types);
var args = new object[types.Length];
var getters = new Func <ReadOnlyMemory <char>, bool> [types.Length];
for (int i = 0; i < getters.Length; i++)
{
getters[i] = GetGetter(i, types[i], args);
}
StringBuilder sb = new StringBuilder();
Action <object> printer = GetPrinter(typeRes, sb);
ReadOnlyMemory <char> chars = text.AsMemory().Slice(ichMin, ichLim - ichMin);
for (bool more = true; more;)
{
ReadOnlyMemory <char> line;
if (RuntimeInformation.IsOSPlatform(OSPlatform.Windows))
{
more = ReadOnlyMemoryUtils.SplitOne(chars, '\x0D', out line, out chars);
}
else
{
more = ReadOnlyMemoryUtils.SplitOne(chars, '\x0A', out line, out chars);
}
line = ReadOnlyMemoryUtils.TrimWhiteSpace(line);
if (line.IsEmpty)
{
continue;
}
// Note this "hack" to map _ to empty. It's easier than fully handling quoting and is sufficient
// for these tests.
var vals = ReadOnlyMemoryUtils.Split(line, new char[] { ',' })
.Select(x => ReadOnlyMemoryUtils.TrimWhiteSpace(x))
.Select(x => ReadOnlyMemoryUtils.EqualsStr("_", x) ? ReadOnlyMemory <char> .Empty : x)
.ToArray();
Contracts.Assert(vals.Length == getters.Length);
for (int i = 0; i < getters.Length; i++)
{
if (!getters[i](vals[i]))
{
wrt.Write("*** Parsing {0} Failed *** ", vals[i]);
}
}
var res = del.DynamicInvoke(args);
printer(res);
wrt.WriteLine(sb);
}
}
private void LoadStopWords(IHostEnvironment env, IChannel ch, ArgumentsBase loaderArgs, out NormStr.Pool stopWordsMap)
{
Contracts.AssertValue(env);
env.AssertValue(ch);
ch.AssertValue(loaderArgs);
if ((!string.IsNullOrEmpty(loaderArgs.Stopwords) || Utils.Size(loaderArgs.Stopword) > 0) &&
(!string.IsNullOrWhiteSpace(loaderArgs.DataFile) || loaderArgs.Loader != null ||
!string.IsNullOrWhiteSpace(loaderArgs.StopwordsColumn)))
{
ch.Warning("Explicit stopwords list specified. Data file arguments will be ignored");
}
var src = default(ReadOnlyMemory <char>);
stopWordsMap = new NormStr.Pool();
var buffer = new StringBuilder();
var stopwords = loaderArgs.Stopwords.AsMemory();
stopwords = ReadOnlyMemoryUtils.TrimSpaces(stopwords);
if (!stopwords.IsEmpty)
{
bool warnEmpty = true;
for (bool more = true; more;)
{
ReadOnlyMemory <char> stopword;
more = ReadOnlyMemoryUtils.SplitOne(stopwords, ',', out stopword, out stopwords);
stopword = ReadOnlyMemoryUtils.TrimSpaces(stopword);
if (!stopword.IsEmpty)
{
buffer.Clear();
ReadOnlyMemoryUtils.AddLowerCaseToStringBuilder(stopword.Span, buffer);
stopWordsMap.Add(buffer);
}
else if (warnEmpty)
{
ch.Warning("Empty strings ignored in 'stopwords' specification");
warnEmpty = false;
}
}
ch.CheckUserArg(stopWordsMap.Count > 0, nameof(Arguments.Stopwords), "stopwords is empty");
}
else if (Utils.Size(loaderArgs.Stopword) > 0)
{
bool warnEmpty = true;
foreach (string word in loaderArgs.Stopword)
{
var stopword = word.AsSpan();
stopword = stopword.Trim(' ');
if (!stopword.IsEmpty)
{
buffer.Clear();
ReadOnlyMemoryUtils.AddLowerCaseToStringBuilder(stopword, buffer);
stopWordsMap.Add(buffer);
}
else if (warnEmpty)
{
ch.Warning("Empty strings ignored in 'stopword' specification");
warnEmpty = false;
}
}
}
else
{
string srcCol = loaderArgs.StopwordsColumn;
var loader = LoadStopwords(env, ch, loaderArgs.DataFile, loaderArgs.Loader, ref srcCol);
int colSrc;
if (!loader.Schema.TryGetColumnIndex(srcCol, out colSrc))
{
throw ch.ExceptUserArg(nameof(Arguments.StopwordsColumn), "Unknown column '{0}'", srcCol);
}
var typeSrc = loader.Schema[colSrc].Type;
ch.CheckUserArg(typeSrc.IsText, nameof(Arguments.StopwordsColumn), "Must be a scalar text column");
// Accumulate the stopwords.
using (var cursor = loader.GetRowCursor(col => col == colSrc))
{
bool warnEmpty = true;
var getter = cursor.GetGetter <ReadOnlyMemory <char> >(colSrc);
while (cursor.MoveNext())
{
getter(ref src);
if (!src.IsEmpty)
{
buffer.Clear();
ReadOnlyMemoryUtils.AddLowerCaseToStringBuilder(src.Span, buffer);
stopWordsMap.Add(buffer);
}
else if (warnEmpty)
{
ch.Warning("Empty rows ignored in data file");
warnEmpty = false;
}
}
}
ch.CheckUserArg(stopWordsMap.Count > 0, nameof(Arguments.DataFile), "dataFile is empty");
}
}
