Devstudio changes for v2.00.

git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@81 d0cd1f9f-072b-0410-8dd7-cf729c803f20
lzpfmh · Jul 18, 2007 · f4baca2 · f4baca2
1 parent 47cd8b5
commit f4baca2
Show file tree

Hide file tree

Showing 19 changed files with 14,121 additions and 51 deletions.
diff --git a/ccutil/ocrclass.h b/ccutil/ocrclass.h
@@ -257,6 +257,13 @@ typedef struct                   /*bitmap strip */
 
 typedef struct                   /*single character */
 {
+// It should be noted that the format for char_code for version 2.0 and beyond is UTF8
+// which means that ASCII characters will come out as one structure but other characters
+// will be returned in two or more instances of this structure with a single byte of the
+// UTF8 code in each, but each will have the same bounding box.
+// Programs which want to handle languagues with different characters sets will need to
+// handle extended characters appropriately, but *all* code needs to be prepared to
+// receive UTF8 coded characters for characters such as bullet and fancy quotes.
   UINT16 char_code;              /*character itself */
   INT16 left;                    /*of char (-1) */
   INT16 right;                   /*of char (-1) */

diff --git a/classify/mfoutline.cpp b/classify/mfoutline.cpp
@@ -295,9 +295,9 @@ LIST ConvertOutlines(TESSLINE *Outline,
       if (OutlineType == outer)
         ConvertedOutlines = ConvertOutlines (Outline->child,
           ConvertedOutlines, hole);
-    else
-      ConvertedOutlines = ConvertOutlines (Outline->child,
-        ConvertedOutlines, outer);
+      else
+        ConvertedOutlines = ConvertOutlines (Outline->child,
+          ConvertedOutlines, outer);
 
     MFOutline = ConvertOutline (Outline);
     ConvertedOutlines = push (ConvertedOutlines, MFOutline);

diff --git a/dlltest/dlltest.cpp b/dlltest/dlltest.cpp
@@ -1,8 +1,8 @@
 /**********************************************************************
  * File:        dlltest.cpp
  * Description: Main program to test the tessdll interface.
- * Author:		  Ray Smith
- * Created:			Wed May 16 15:17:46 PDT 2007
+ * Author:      Ray Smith
+ * Created:     Wed May 16 15:17:46 PDT 2007
  *
  * (C) Copyright 2007, Google Inc.
  ** Licensed under the Apache License, Version 2.0 (the "License");
@@ -18,8 +18,8 @@
  **********************************************************************/
 
 #include "stdafx.h"
-#include "imgs.h"
-#include "tessdll.h"
+#include "imgs.h"
+#include "tessdll.h"
 
 /**********************************************************************
  *  main()
@@ -28,46 +28,62 @@
 
 int main(int argc, char **argv) {
   if (argc != 3) {
-    fprintf(stderr, "Usage:%s imagename outputname\n", argv[0]);
+    fprintf(stderr, "Usage:%s imagename outputname\n", argv[0]);
     exit(1);
   }
 
+
   IMAGE image;
   if (image.read_header(argv[1]) < 0) {
-    fprintf(stderr, "Can't open %s\n", argv[1]);
-    exit(1);
+    fprintf(stderr, "Can't open %s\n", argv[1]);
+    exit(1);
   }
   if (image.read(image.get_ysize ()) < 0) {
-    fprintf(stderr, "Can't read %s\n", argv[1]);
-    exit(1);
-  }
-  if (image.get_bpp() != 1) {
-    fprintf(stderr, "Image is not binary!\n");
-    exit(1);
-  }
-
-  TessDllAPI api("eng");
-  api.BeginPageUpright(image.get_xsize(), image.get_ysize(), image.get_buffer());
-  ETEXT_DESC* output = api.Recognize_all_Words();
-
-  FILE* fp = fopen(argv[2],"w");
-  if (fp == NULL) {
-    fprintf(stderr, "Can't create %s\n", argv[2]);
-    exit(1);
-  }
-
-  for (int i = 0; i < output->count; ++i) {
-    const EANYCODE_CHAR* ch = &output->text[i];
-    for (int b = 0; b < ch->blanks; ++b)
-      fprintf(fp, "\n");
-    fprintf(fp, "%C[%x](%d,%d)->(%d,%d)\n",
-      ch->char_code, ch->char_code,
-      ch->left, ch->bottom, ch->right, ch->top);
-    if (ch->formatting & 64)
-      fprintf(fp, "<nl>\n\n");
-    if (ch->formatting & 128)
-      fprintf(fp, "<para>\n\n");
-  }
-
-  return 0;
+    fprintf(stderr, "Can't read %s\n", argv[1]);
+    exit(1);
+  }
+
+
+
+  TessDllAPI api("eng");
+
+
+
+  api.BeginPageUpright(image.get_xsize(), image.get_ysize(), image.get_buffer(),
+		       image.get_bpp());
+
+  ETEXT_DESC* output = api.Recognize_all_Words();
+
+
+
+
+  FILE* fp = fopen(argv[2],"w");
+  if (fp == NULL) {
+    fprintf(stderr, "Can't create %s\n", argv[2]);
+    exit(1);
+  }
+
+  for (int i = 0; i < output->count; ++i) {
+// It should be noted that the format for char_code for version 2.0 and beyond is UTF8
+// which means that ASCII characters will come out as one structure but other characters
+// will be returned in two or more instances of this structure with a single byte of the
+// UTF8 code in each, but each will have the same bounding box.
+// Programs which want to handle languagues with different characters sets will need to
+// handle extended characters appropriately, but *all* code needs to be prepared to
+// receive UTF8 coded characters for characters such as bullet and fancy quotes.
+    const EANYCODE_CHAR* ch = &output->text[i];
+    for (int b = 0; b < ch->blanks; ++b)
+      fprintf(fp, "\n");
+    fprintf(fp, "%C[%x](%d,%d)->(%d,%d)\n",
+      ch->char_code, ch->char_code,
+      ch->left, ch->bottom, ch->right, ch->top);
+    if (ch->formatting & 64)
+      fprintf(fp, "<nl>\n\n");
+    if (ch->formatting & 128)
+      fprintf(fp, "<para>\n\n");
+  }
+
+  fclose(fp);
+
+  return 0;
 }