remove parameters tessedit_pdf_jpg_quality, tessedit_pdf_compression …

…(reasons are in i1300 and i1285)
lsfjGitHub · Oct 7, 2014 · d0cb107 · d0cb107
1 parent 55d11ad
commit d0cb107
Show file tree

Hide file tree

Showing 4 changed files with 21 additions and 47 deletions.
diff --git a/api/pdfrenderer.cpp b/api/pdfrenderer.cpp
@@ -431,8 +431,7 @@ bool TessPDFRenderer::BeginDocumentHandler() {
   return true;
 }
 
-bool TessPDFRenderer::imageToPDFObj(TessBaseAPI* api,
-                                    Pix *pix,
+bool TessPDFRenderer::imageToPDFObj(Pix *pix,
                                     char *filename,
                                     long int objnum,
                                     char **pdf_object,
@@ -449,32 +448,25 @@ bool TessPDFRenderer::imageToPDFObj(TessBaseAPI* api,
     return false;
 
   L_COMP_DATA *cid = NULL;
-  int kJpegQuality;
-  int encoding_type;
-  api->GetIntVariable("tessedit_pdf_jpg_quality", &kJpegQuality);
-  api->GetIntVariable("tessedit_pdf_compression", &encoding_type);
-  if (encoding_type > 0 && encoding_type < 4) {
-    if (pixGenerateCIData(pix, encoding_type, kJpegQuality, 0, &cid) != 0)
-      return false;
+  const int kJpegQuality = 85;
+  l_generateCIDataForPdf(filename, pix, kJpegQuality, &cid);
+  // TODO(jbreiden) Leptonica 1.71 doesn't correctly handle certain
+  // types of PNG files, especially if there are 2 samples per pixel.
+  // We can get rid of this logic after Leptonica 1.72 is released and
+  // has propagated everywhere. Bug discussion as follows.
+  // https://code.google.com/p/tesseract-ocr/issues/detail?id=1300
+  int format, sad;
+  findFileFormat(filename, &format);
+  if (pixGetSpp(pix) == 4 && format == IFF_PNG) {
+    pixSetSpp(pix, 3);
+    sad = pixGenerateCIData(pix, L_FLATE_ENCODE, 0, 0, &cid);
   } else {
-    // TODO(jbreiden) Leptonica 1.71 doesn't correctly handle certain
-    // types of PNG files, especially if there are 2 samples per pixel.
-    // We can get rid of this logic after Leptonica 1.72 is released and
-    // has propagated everywhere. Bug discussion as follows.
-    // https://code.google.com/p/tesseract-ocr/issues/detail?id=1300
-    int format, sad;
-    findFileFormat(filename, &format);
-    if (pixGetSpp(pix) == 4 && format == IFF_PNG) {
-      pixSetSpp(pix, 3);
-      sad = pixGenerateCIData(pix, L_FLATE_ENCODE, 0, 0, &cid);
-    } else {
-      sad = l_generateCIDataForPdf(filename, pix, kJpegQuality, &cid);
-    }
+    sad = l_generateCIDataForPdf(filename, pix, kJpegQuality, &cid);
+  }
 
-    if (sad || !cid) {
-      l_CIDataDestroy(&cid);
-      return false;
-    }
+  if (sad || !cid) {
+    l_CIDataDestroy(&cid);
+    return false;
   }
 
   const char *group4 = "";
@@ -665,7 +657,7 @@ bool TessPDFRenderer::AddImageHandler(TessBaseAPI* api) {
   AppendPDFObjectDIY(objsize);
 
   char *pdf_object;
-  if (!imageToPDFObj(api, pix, filename, obj_, &pdf_object, &objsize)) {
+  if (!imageToPDFObj(pix, filename, obj_, &pdf_object, &objsize)) {
     return false;
   }
   AppendData(pdf_object, objsize);

diff --git a/api/renderer.h b/api/renderer.h
@@ -194,9 +194,8 @@ class TESS_API TessPDFRenderer : public TessResultRenderer {
   static char* GetPDFTextObjects(TessBaseAPI* api,
                                  double width, double height);
   // Turn an image into a PDF object. Only transcode if we have to.
-  static bool imageToPDFObj(tesseract::TessBaseAPI *api, Pix *pix,
-                            char *filename, long int objnum, char **pdf_object,
-                            long int *pdf_object_size);
+  static bool imageToPDFObj(Pix *pix, char *filename, long int objnum,
+                            char **pdf_object, long int *pdf_object_size);
 };
 
 

diff --git a/ccmain/tesseractclass.cpp b/ccmain/tesseractclass.cpp
@@ -318,16 +318,6 @@ Tesseract::Tesseract()
                 "Write .html hOCR output file", this->params()),
     BOOL_MEMBER(tessedit_create_pdf, false,
                 "Write .pdf output file", this->params()),
-    INT_MEMBER(tessedit_pdf_compression, 0,
-               "Type of image compression in pdf output: "
-               "0 - autoselection (default); "
-               "1 - jpeg; "
-               "2 - G4; "
-               "3 - flate",
-               this->params()),
-    INT_MEMBER(tessedit_pdf_jpg_quality, 85,
-               "Quality level of jpeg image compression in pdf output",
-               this->params()),
     STRING_MEMBER(unrecognised_char, "|",
                   "Output char for unidentified blobs", this->params()),
     INT_MEMBER(suspect_level, 99, "Suspect marker level", this->params()),

diff --git a/ccmain/tesseractclass.h b/ccmain/tesseractclass.h
@@ -930,13 +930,6 @@ class Tesseract : public Wordrec {
   BOOL_VAR_H(tessedit_create_txt, true, "Write .txt output file");
   BOOL_VAR_H(tessedit_create_hocr, false, "Write .html hOCR output file");
   BOOL_VAR_H(tessedit_create_pdf, false, "Write .pdf output file");
-  INT_VAR_H(tessedit_pdf_compression, 0, "Type of image encoding in pdf output:"
-            "0 - autoselection (default); "
-            "1 - jpeg; "
-            "2 - G4; "
-            "3 - flate");
-  INT_VAR_H(tessedit_pdf_jpg_quality, 85, "Quality level of jpeg image "
-            "compression in pdf output");
   STRING_VAR_H(unrecognised_char, "|",
                "Output char for unidentified blobs");
   INT_VAR_H(suspect_level, 99, "Suspect marker level");