internal void SaveStringOrNull(string str)
{
if (str == null)
{
Writer.Write(-1);
}
else
{
Writer.Write(Strings.Add(str).Id);
}
}
public void AddWordVector(IChannel ch, string word, float[] wordVector)
{
ch.Assert(wordVector.Length == Dimension);
if (_pool.Get(word) == null)
{
_pool.Add(word);
WordVectors.AddRange(wordVector);
}
}
private CustomStopWordsRemoverTransform(IHost host, ModelLoadContext ctx, IDataView input)
: base(host, ctx, input, TestIsTextVector)
{
Host.AssertValue(ctx);
using (var ch = Host.Start("Deserialization"))
{
// *** Binary format ***
// <base>
ch.AssertNonEmpty(Infos);
const string dir = "Stopwords";
NormStr.Pool stopwrods = null;
bool res = ctx.TryProcessSubModel(dir,
c =>
{
Host.CheckValue(c, nameof(ctx));
c.CheckAtModel(GetStopwrodsManagerVersionInfo());
// *** Binary format ***
// int: number of stopwords
// int[]: stopwords string ids
int cstr = ctx.Reader.ReadInt32();
Host.CheckDecode(cstr > 0);
stopwrods = new NormStr.Pool();
for (int istr = 0; istr < cstr; istr++)
{
var nstr = stopwrods.Add(ctx.LoadString());
Host.CheckDecode(nstr.Id == istr);
}
// All stopwords are distinct.
Host.CheckDecode(stopwrods.Count == cstr);
// The deserialized pool should not have the empty string.
Host.CheckDecode(stopwrods.Get("") == null);
});
if (!res)
{
throw Host.ExceptDecode();
}
_stopWordsMap = stopwrods;
ch.Done();
}
Metadata.Seal();
}
private static void AddResourceIfNotPresent(Language lang)
{
Contracts.Assert(0 <= (int)lang & (int)lang < Utils.Size(StopWords));
if (StopWords[(int)lang] == null)
{
Stream stopWordsStream = GetResourceFileStreamOrNull(lang);
Contracts.Assert(stopWordsStream != null);
var stopWordsList = new NormStr.Pool();
using (StreamReader reader = new StreamReader(stopWordsStream))
{
string stopWord;
while ((stopWord = reader.ReadLine()) != null)
{
if (!string.IsNullOrWhiteSpace(stopWord))
{
stopWordsList.Add(stopWord);
}
}
}
Interlocked.CompareExchange(ref StopWords[(int)lang], stopWordsList, null);
}
}
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");
}
}
public static NormStr AddToPool(ReadOnlyMemory <char> memory, NormStr.Pool pool)
{
Contracts.CheckValue(pool, nameof(pool));
return(pool.Add(memory));
}
public void AddKeyWord(string str, TokKind tid)
{
Contracts.AssertNonEmpty(str);
_mpnstrtidWord.Add(_pool.Add(str), new KeyWordKind(tid, false));
}
// REVIEW: Add method to NormStr.Pool that deal with DvText instead of the other way around.
public NormStr AddToPool(NormStr.Pool pool)
{
Contracts.Check(!IsNA);
Contracts.CheckValue(pool, nameof(pool));
return(pool.Add(_outerBuffer, _ichMin, IchLim));
}
