private void btn_WordFreq_Click(object sender, RibbonControlEventArgs e)
{
ProgressDialog d = new ProgressDialog();
d.Show();
Stopwatch watch = new Stopwatch();
watch.Start();
Word.Document doc = Globals.ThisAddIn.Application.ActiveDocument;
Dictionary <string, uint> wordlist = new Dictionary <string, uint>();
Regex re_allnums = new Regex(@"^\d+$");
IEnumerable <Word.Range> textranges = TextHelpers.GetText(doc);
d.pbMax = textranges.Count();
d.pbVal = 0;
foreach (Word.Range rng in textranges)
{
d.pbVal++;
string txt = rng.Text;
//strip punctuation
txt = TextHelpers.StripPunctuation(txt);
string[] substrs = Regex.Split(txt, @"\s+");
foreach (string word in substrs)
{
Match m = re_allnums.Match(word);
if (!m.Success)
{
if (word.Trim() != "")
{
if (wordlist.ContainsKey(word))
{
wordlist[word]++;
}
else
{
wordlist.Add(word, 1);
}
}
}
}
}
Debug.WriteLine("Counts tabulated. Time elapsed: " + watch.Elapsed.ToString());
watch.Restart();
//Create new document
Word.Document newdoc = Globals.ThisAddIn.Application.Documents.Add();
Word.Paragraph pgraph;
//Intro text
pgraph = newdoc.Content.Paragraphs.Add();
pgraph.set_Style(newdoc.Styles["Heading 1"]);
pgraph.Range.Text = "Word Frequency List\n";
pgraph = newdoc.Content.Paragraphs.Add();
pgraph.set_Style(newdoc.Styles["Normal"]);
pgraph.Range.Text = "Capitalization is retained as is. That means that words that appear at the beginning of a sentence will appear capitalized. Don't forget that you can sort the table!\n";
pgraph = newdoc.Content.Paragraphs.Add();
pgraph.set_Style(newdoc.Styles["Normal"]);
pgraph.Range.Text = "Total words found (case sensitive): " + wordlist.Count.ToString() + "\n";
pgraph = newdoc.Content.Paragraphs.Add();
pgraph.Range.InsertBreak(Word.WdBreakType.wdSectionBreakContinuous);
Word.Section sec = newdoc.Sections[2];
sec.PageSetup.TextColumns.SetCount(3);
var words = wordlist.ToList();
words.Sort((pair1, pair2) => pair2.Value.CompareTo(pair1.Value));
newdoc.Tables.Add(pgraph.Range, words.Count, 2);
//newdoc.Tables.Add(pgraph.Range, 1, 2);
newdoc.Tables[1].AutoFitBehavior(Word.WdAutoFitBehavior.wdAutoFitContent);
newdoc.Tables[1].AllowAutoFit = true;
d.pbMax = words.Count;
d.pbVal = 0;
int row = 1;
foreach (var pair in words)
{
d.pbVal++;
//newdoc.Tables[1].Rows.Add();
Word.Cell cell = newdoc.Tables[1].Cell(row, 1);
cell.Range.Text = pair.Key;
cell = newdoc.Tables[1].Cell(row, 2);
cell.Range.Text = pair.Value.ToString();
row++;
}
pgraph = newdoc.Content.Paragraphs.Add();
pgraph.Range.InsertBreak(Word.WdBreakType.wdSectionBreakContinuous);
newdoc.GrammarChecked = true;
Debug.WriteLine("All done. Time elapsed: " + watch.Elapsed.ToString());
watch.Stop();
d.Hide();
}
private void btn_SingData_Click(object sender, RibbonControlEventArgs e)
{
Word.Document doc = Globals.ThisAddIn.Application.ActiveDocument;
Word.Paragraphs pgraphs;
Word.Selection sel = Globals.ThisAddIn.Application.Selection;
bool fromSelection = false;
if (sel != null && sel.Range != null && sel.Characters.Count > 1)
{
pgraphs = sel.Paragraphs;
fromSelection = true;
}
else
{
pgraphs = doc.Paragraphs;
}
Debug.WriteLine("From selection: " + fromSelection.ToString());
ProgressDialog d = new ProgressDialog();
d.pbMax = pgraphs.Count;
d.pbVal = 0;
d.Show();
foreach (Word.Paragraph pgraph in pgraphs)
{
d.pbVal++;
Word.Range rng = pgraph.Range;
foreach (Word.Range sentence in rng.Sentences)
{
// POS
var tsentence = MaxentTagger.tokenizeText(new java.io.StringReader(sentence.Text)).toArray();
var taggedSentence = tagger.tagSentence((ArrayList)tsentence[0]);
var taglist = taggedSentence.toArray();
Boolean singular = false;
Boolean hasdata = false;
//First find obviously singular "data"
foreach (TaggedWord entry in taglist)
{
if (entry.word().ToLower() == "data")
{
hasdata = true;
if ((entry.tag() == "NN") || (entry.tag() == "NNP"))
{
singular = true;
break;
}
}
}
//Now look for plural tags with singular verbs
if ((hasdata) && (!singular))
{
foreach (TaggedWord entry in taglist)
{
if (entry.tag() == "VBZ")
{
singular = true;
break;
}
}
}
//Highlight problematic sentences
if ((hasdata) && (singular))
{
sentence.HighlightColorIndex = Word.WdColorIndex.wdGray50;
}
}
//var sentences = MaxentTagger.tokenizeText(new java.io.StringReader(rng.Text)).toArray();
//foreach (ArrayList sentence in sentences)
//{
// String origsent = String.Join(" ", sentence.toArray());
// Debug.WriteLine(origsent);
// var taggedSentence = tagger.tagSentence(sentence);
// var taglist = taggedSentence.toArray();
// foreach (TaggedWord entry in taglist)
// {
// if (entry.word().ToLower() == "data")
// {
// if ( (entry.tag() == "NN") || (entry.tag() == "NNP") )
// {
// Debug.WriteLine("Found singular 'data' in the following sentence: " + origsent);
// TextHelpers.highlightText(pgraph.Range, "", Word.WdColorIndex.wdGray50);
// }
// }
// }
//}
//// Typed Dependencies
//foreach (Word.Range sentence in rng.Sentences)
//{
// var tokenizerFactory = PTBTokenizer.factory(new CoreLabelTokenFactory(), "");
// var sent2Reader = new java.io.StringReader(sentence.Text);
// var rawWords = tokenizerFactory.getTokenizer(sent2Reader).tokenize();
// sent2Reader.close();
// var tree = lp.apply(rawWords);
// var tlp = new PennTreebankLanguagePack();
// var gsf = tlp.grammaticalStructureFactory();
// var gs = gsf.newGrammaticalStructure(tree);
// var tdl = gs.typedDependenciesCCprocessed();
// foreach (var dep in tdl.toArray())
// {
// Debug.WriteLine(dep);
// }
// Debug.WriteLine("=-=-=-=-=-");
//}
}
d.Hide();
MessageBox.Show("Possible uses of 'data' as a singular noun have been highlighted in grey.");
}