fix #1900: intraword spacing for slightly better pdf copy-paste perfo…

…rmance
tesseract-ocr · Apr 29, 2019 · 546a9e8 · 546a9e8
1 parent 137e6de
commit 546a9e8
Showing 1 changed file with 4 additions and 0 deletions.
diff --git a/src/api/pdfrenderer.cpp b/src/api/pdfrenderer.cpp
@@ -466,6 +466,10 @@ char* TessPDFRenderer::GetPDFTextObjects(TessBaseAPI* api,
       }
       res_it->Next(RIL_SYMBOL);
     } while (!res_it->Empty(RIL_BLOCK) && !res_it->IsAtBeginningOf(RIL_WORD));
+    if (res_it->IsAtBeginningOf(RIL_WORD)) {
+      pdf_word += "0020";
+      pdf_word_len++;
+    }
     if (word_length > 0 && pdf_word_len > 0) {
       double h_stretch =
           kCharWidth * prec(100.0 * word_length / (fontsize * pdf_word_len));