原文件中:Accessories通过下列样例读取后拆分显示为一个个单词,“-”符号读取空白断句 能否实现整句读取?
导出文件.pdf (657.5 KB)
原文件.pdf (522.3 KB)
Document doc = new Document(path);
// Instantiate ParagraphAbsorber
ParagraphAbsorber absorber = new ParagraphAbsorber();
absorber.Visit(doc);
int intStartLength = 0;
string stringSenderMessage = string.Empty;
for (int i = 0; i < absorber.PageMarkups.Count; i++)
{
PageMarkup markup = absorber.PageMarkups[i];
for (int j = markup.Sections.Count - 1; j >= 0; j--)
{
MarkupSection section = markup.Sections[j];
for (int k = section.Paragraphs.Count - 1; k >= 0; k--)
{
StringBuilder paragraphText = new StringBuilder();
MarkupParagraph paragraph = section.Paragraphs[k];
List<TextFragment> fragmentlist = paragraph.Fragments;
for (int t = 0; t < fragmentlist.Count; t++)
{
TextFragment fragment = fragmentlist[t];
if (fragment.Text.ToString().Trim() != string.Empty)
{
fragment.Text = "@" + fragment.Text.ToString() + "#";
}
}
}
}
}