Fixed a lot of compiler/clang warnings

git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@1015 d0cd1f9f-072b-0410-8dd7-cf729c803f20
vuthanh86 · Jan 25, 2014 · d11dc04 · d11dc04
1 parent aa62157
commit d11dc04
Show file tree

Hide file tree

Showing 51 changed files with 154 additions and 368 deletions.
diff --git a/api/baseapi.cpp b/api/baseapi.cpp
@@ -2282,7 +2282,6 @@ void TessBaseAPI::AdaptToCharacter(const char *unichar_repr,
                                     tesseract_->classify_bln_numeric_mode,
                                     tesseract_->pix_binary());
   float threshold;
-  UNICHAR_ID best_class = 0;
   float best_rating = -100;
 
 
@@ -2295,7 +2294,6 @@ void TessBaseAPI::AdaptToCharacter(const char *unichar_repr,
        choice_it.forward()) {
     if (choice_it.data()->rating() > best_rating) {
       best_rating = choice_it.data()->rating();
-      best_class = choice_it.data()->unichar_id();
     }
   }
 

diff --git a/api/baseapi.h b/api/baseapi.h
@@ -37,7 +37,7 @@ template <typename T> class GenericVector;
 class PAGE_RES;
 class PAGE_RES_IT;
 class ParagraphModel;
-class BlamerBundle;
+struct BlamerBundle;
 class BLOCK_LIST;
 class DENORM;
 class IMAGE;

diff --git a/api/pdfrenderer.cpp b/api/pdfrenderer.cpp
@@ -177,12 +177,10 @@ char* TessPDFRenderer::GetPDFTextObjects(TessBaseAPI* api,
           break;
       }
 
-      const char *font_name;
       bool bold, italic, underlined, monospace, serif, smallcaps;
       int font_id;
-      font_name = res_it->WordFontAttributes(&bold, &italic, &underlined,
-                                             &monospace, &serif, &smallcaps,
-                                             &pointsize, &font_id);
+      res_it->WordFontAttributes(&bold, &italic, &underlined, &monospace,
+                                 &serif, &smallcaps, &pointsize, &font_id);
 
       if (pointsize != old_pointsize) {
         char textfont[20];
@@ -209,7 +207,6 @@ char* TessPDFRenderer::GetPDFTextObjects(TessBaseAPI* api,
     old_y = y;
 
     bool last_word_in_line = res_it->IsAtFinalElement(RIL_TEXTLINE, RIL_WORD);
-    bool last_word_in_para = res_it->IsAtFinalElement(RIL_PARA, RIL_WORD);
     bool last_word_in_block = res_it->IsAtFinalElement(RIL_BLOCK, RIL_WORD);
     STRING pdf_word("");
     int pdf_word_len = 0;
@@ -221,7 +218,7 @@ char* TessPDFRenderer::GetPDFTextObjects(TessBaseAPI* api,
         string_32 utf32;
         CubeUtils::UTF8ToUTF32(grapheme, &utf32);
         char utf16[20];
-        for (int i = 0; i < utf32.length(); i++) {
+        for (int i = 0; i < static_cast<int>(utf32.length()); i++) {
           snprintf(utf16, sizeof(utf16), "<%04X>", utf32[i]);
           pdf_word += utf16;
           pdf_word_len++;
@@ -262,7 +259,6 @@ bool TessPDFRenderer::BeginDocumentHandler() {
   AppendPDFObject(buf);
 
   // CATALOG
-  long int catalog = obj_;
   snprintf(buf, sizeof(buf),
            "1 0 obj\n"
            "<<\n"
@@ -479,7 +475,8 @@ bool TessPDFRenderer::fileToPDFObj(char *filename, long int objnum,
   if (!pdf_object)
     return false;
   memcpy(*pdf_object, b1, b1_len);
-  if (fread(*pdf_object + b1_len, 1, jpeg_size, fp) != jpeg_size) {
+  if (static_cast<int>(fread(*pdf_object + b1_len, 1, jpeg_size, fp)) !=
+      jpeg_size) {
     delete[] pdf_object;
     return false;
   }

diff --git a/api/tesseractmain.cpp b/api/tesseractmain.cpp
@@ -245,7 +245,8 @@ int main(int argc, char **argv) {
     pixs = pixReadMem(&ch_data[0], ch_data.size());
   }
 
-  if (pagesegmode == tesseract::PSM_AUTO_OSD) {
+  if (pagesegmode == tesseract::PSM_AUTO_ONLY ||
+      pagesegmode == tesseract::PSM_OSD_ONLY) {
     tesseract::Orientation orientation;
     tesseract::WritingDirection direction;
     tesseract::TextlineOrder order;

diff --git a/ccmain/ltrresultiterator.cpp b/ccmain/ltrresultiterator.cpp
@@ -331,7 +331,6 @@ bool LTRResultIterator::SymbolIsDropcap() const {
 ChoiceIterator::ChoiceIterator(const LTRResultIterator& result_it) {
   ASSERT_HOST(result_it.it_->word() != NULL);
   word_res_ = result_it.it_->word();
-  PAGE_RES_IT res_it(*result_it.it_);
   BLOB_CHOICE_LIST* choices = NULL;
   if (word_res_->ratings != NULL)
     choices = word_res_->GetBlobChoices(result_it.blob_index_);

diff --git a/ccmain/osdetect.cpp b/ccmain/osdetect.cpp
@@ -395,10 +395,8 @@ bool OrientationDetector::detect_blob(BLOB_CHOICE_LIST* scores) {
   float first = -1;
   float second = -1;
 
-  int idx = -1;
   for (int i = 0; i < 4; ++i) {
     if (osr_->orientations[i] > first) {
-      idx = i;
       second = first;
       first = osr_->orientations[i];
     } else if (osr_->orientations[i] > second) {
@@ -443,14 +441,9 @@ void ScriptDetector::detect_blob(BLOB_CHOICE_LIST* scores) {
     float prev_score = -1;
     int script_count = 0;
     int prev_id = -1;
-    int prev_script;
-    int prev_class_id = -1;
     int prev_fontinfo_id = -1;
     const char* prev_unichar = "";
     const char* unichar = "";
-    float next_best_score = -1.0;
-    int next_best_script_id = -1;
-    const char* next_best_unichar = "";
 
     for (choice_it.mark_cycle_pt(); !choice_it.cycled_list();
          choice_it.forward()) {
@@ -466,15 +459,10 @@ void ScriptDetector::detect_blob(BLOB_CHOICE_LIST* scores) {
         prev_score = -choice->certainty();
         script_count = 1;
         prev_id = id;
-        prev_script = choice->script_id();
         prev_unichar = unichar;
-        prev_class_id = choice->unichar_id();
         prev_fontinfo_id = choice->fontinfo_id();
       } else if (-choice->certainty() < prev_score + kNonAmbiguousMargin) {
         ++script_count;
-        next_best_score = -choice->certainty();
-        next_best_script_id = choice->script_id();
-        next_best_unichar = tess_->unicharset.id_to_unichar(choice->unichar_id());
       }
 
       if (strlen(prev_unichar) == 1)

diff --git a/ccmain/output.cpp b/ccmain/output.cpp
@@ -70,7 +70,6 @@ void Tesseract::output_pass(  //Tess output pass //send to api
                             PAGE_RES_IT &page_res_it,
                             const TBOX *target_word_box) {
   BLOCK_RES *block_of_last_word;
-  inT16 block_id;
   BOOL8 force_eol;               //During output
   BLOCK *nextblock;              //block of next word
   WERD *nextword;                //next word
@@ -95,7 +94,6 @@ void Tesseract::output_pass(  //Tess output pass //send to api
     if (tessedit_write_block_separators &&
     block_of_last_word != page_res_it.block ()) {
       block_of_last_word = page_res_it.block ();
-      block_id = block_of_last_word->block->index();
     }
 
     force_eol = (tessedit_write_block_separators &&
@@ -137,18 +135,10 @@ void Tesseract::write_results(PAGE_RES_IT &page_res_it,
                               BOOL8 force_eol) {  // override tilde crunch?
   WERD_RES *word = page_res_it.word();
   const UNICHARSET &uchset = *word->uch_set;
-  STRING repetition_code;
-  const STRING *wordstr;
-  STRING wordstr_lengths;
   int i;
-  char unrecognised = STRING (unrecognised_char)[0];
-  char ep_chars[32];             //Only for unlv_tilde_crunch
-  int ep_chars_index = 0;
-  char txt_chs[32];              //Only for unlv_tilde_crunch
-  char map_chs[32];              //Only for unlv_tilde_crunch
-  int txt_index = 0;
   BOOL8 need_reject = FALSE;
   UNICHAR_ID space = uchset.unichar_to_id(" ");
+
   if ((word->unlv_crunch_mode != CR_NONE ||
        word->best_choice->length() == 0) &&
       !tessedit_zero_kelvin_rejection && !tessedit_word_for_word) {
@@ -162,10 +152,6 @@ void Tesseract::write_results(PAGE_RES_IT &page_res_it,
           (word->word->space () > 0) &&
           !word->word->flag (W_FUZZY_NON) &&
           !word->word->flag (W_FUZZY_SP)) {
-        // Write a space to separate from preceeding good text.
-        txt_chs[txt_index] = ' ';
-        map_chs[txt_index++] = '1';
-        ep_chars[ep_chars_index++] = ' ';
         stats_.last_char_was_tilde = false;
       }
       need_reject = TRUE;
@@ -174,50 +160,16 @@ void Tesseract::write_results(PAGE_RES_IT &page_res_it,
         (force_eol && stats_.write_results_empty_block)) {
       /* Write a reject char - mark as rejected unless zero_rejection mode */
       stats_.last_char_was_tilde = TRUE;
-      txt_chs[txt_index] = unrecognised;
-      if (tessedit_zero_rejection || (suspect_level == 0)) {
-        map_chs[txt_index++] = '1';
-        ep_chars[ep_chars_index++] = unrecognised;
-      }
-      else {
-        map_chs[txt_index++] = '0';
-        /*
-           The ep_choice string is a faked reject to allow newdiff to sync the
-           .etx with the .txt and .map files.
-         */
-        ep_chars[ep_chars_index++] = CTRL_INSET; // escape code
-                                 //dummy reject
-        ep_chars[ep_chars_index++] = 1;
-                                 //dummy reject
-        ep_chars[ep_chars_index++] = 1;
-                                 //type
-        ep_chars[ep_chars_index++] = 2;
-                                 //dummy reject
-        ep_chars[ep_chars_index++] = 1;
-                                 //dummy reject
-        ep_chars[ep_chars_index++] = 1;
-      }
       stats_.tilde_crunch_written = true;
       stats_.last_char_was_newline = false;
       stats_.write_results_empty_block = false;
     }
 
     if ((word->word->flag (W_EOL) && !stats_.last_char_was_newline) || force_eol) {
-      /* Add a new line output */
-      txt_chs[txt_index] = '\n';
-      map_chs[txt_index++] = '\n';
-                                 //end line
-      ep_chars[ep_chars_index++] = newline_type;
-
-                                 //Cos of the real newline
       stats_.tilde_crunch_written = false;
       stats_.last_char_was_newline = true;
       stats_.last_char_was_tilde = false;
     }
-    txt_chs[txt_index] = '\0';
-    map_chs[txt_index] = '\0';
-    ep_chars[ep_chars_index] = '\0';  // terminate string
-    word->ep_choice = new WERD_CHOICE(ep_chars, uchset);
 
     if (force_eol)
       stats_.write_results_empty_block = true;
@@ -266,13 +218,7 @@ void Tesseract::write_results(PAGE_RES_IT &page_res_it,
              word->best_choice->debug_string().string(),
              dict_word(*(word->best_choice)));
   }
-  if (word->word->flag (W_REP_CHAR) && tessedit_write_rep_codes) {
-    repetition_code = "|^~R";
-    wordstr_lengths = "\001\001\001\001";
-    repetition_code += uchset.id_to_unichar(get_rep_char(word));
-    wordstr_lengths += strlen(uchset.id_to_unichar(get_rep_char(word)));
-    wordstr = &repetition_code;
-  } else {
+  if (!word->word->flag (W_REP_CHAR) || !tessedit_write_rep_codes) {
     if (tessedit_zero_rejection) {
       /* OVERRIDE ALL REJECTION MECHANISMS - ONLY REJECT TESS FAILURES */
       for (i = 0; i < word->best_choice->length(); ++i) {

diff --git a/ccmain/pageiterator.h b/ccmain/pageiterator.h
@@ -24,7 +24,7 @@
 #include "publictypes.h"
 #include "platform.h"
 
-class BlamerBundle;
+struct BlamerBundle;
 class C_BLOB_IT;
 class PAGE_RES;
 class PAGE_RES_IT;

diff --git a/ccmain/reject.cpp b/ccmain/reject.cpp
@@ -629,7 +629,6 @@ void Tesseract::flip_hyphens(WERD_RES *word_res) {
 
   int num_blobs = word_res->rebuild_word->NumBlobs();
   UNICHAR_ID unichar_dash = word_res->uch_set->unichar_to_id("-");
-  bool modified = false;
   for (i = 0; i < best_choice->length() && i < num_blobs; ++i) {
     TBLOB* blob = word_res->rebuild_word->blobs[i];
     out_box = blob->bounding_box();
@@ -647,7 +646,6 @@ void Tesseract::flip_hyphens(WERD_RES *word_res) {
             word_res->uch_set->get_enabled(unichar_dash)) {
           /* Certain HYPHEN */
           best_choice->set_unichar_id(unichar_dash, i);
-          modified = true;
           if (word_res->reject_map[i].rejected())
             word_res->reject_map[i].setrej_hyphen_accept();
         }
@@ -702,7 +700,6 @@ void Tesseract::flip_0O(WERD_RES *word_res) {
       !word_res->uch_set->get_enabled(unichar_O)) {
     return;  // 0 or O are not present/enabled in unicharset
   }
-  bool modified = false;
   for (i = 1; i < best_choice->length(); ++i) {
     if (best_choice->unichar_id(i) == unichar_0 ||
         best_choice->unichar_id(i) == unichar_O) {
@@ -711,7 +708,6 @@ void Tesseract::flip_0O(WERD_RES *word_res) {
           non_O_upper(*word_res->uch_set, best_choice->unichar_id(i-1)) &&
           non_O_upper(*word_res->uch_set, best_choice->unichar_id(i+1))) {
         best_choice->set_unichar_id(unichar_O, i);
-        modified = true;
       }
       /* A00A */
       if (non_O_upper(*word_res->uch_set, best_choice->unichar_id(i-1)) &&
@@ -721,7 +717,6 @@ void Tesseract::flip_0O(WERD_RES *word_res) {
           (i+2) < best_choice->length() &&
           non_O_upper(*word_res->uch_set, best_choice->unichar_id(i+2))) {
         best_choice->set_unichar_id(unichar_O, i);
-        modified = true;
         i++;
       }
       /* AA0<non digit or end of word> */
@@ -734,14 +729,12 @@ void Tesseract::flip_0O(WERD_RES *word_res) {
             !word_res->uch_set->eq(best_choice->unichar_id(i+1), "I")) ||
            (i == best_choice->length() - 1))) {
         best_choice->set_unichar_id(unichar_O, i);
-        modified = true;
       }
       /* 9O9 */
       if (non_0_digit(*word_res->uch_set, best_choice->unichar_id(i-1)) &&
           (i+1) < best_choice->length() &&
           non_0_digit(*word_res->uch_set, best_choice->unichar_id(i+1))) {
         best_choice->set_unichar_id(unichar_0, i);
-        modified = true;
       }
       /* 9OOO */
       if (non_0_digit(*word_res->uch_set, best_choice->unichar_id(i-1)) &&
@@ -753,7 +746,6 @@ void Tesseract::flip_0O(WERD_RES *word_res) {
         best_choice->set_unichar_id(unichar_0, i);
         best_choice->set_unichar_id(unichar_0, i+1);
         best_choice->set_unichar_id(unichar_0, i+2);
-        modified = true;
         i += 2;
       }
       /* 9OO<non upper> */
@@ -764,7 +756,6 @@ void Tesseract::flip_0O(WERD_RES *word_res) {
           !word_res->uch_set->get_isupper(best_choice->unichar_id(i+2))) {
         best_choice->set_unichar_id(unichar_0, i);
         best_choice->set_unichar_id(unichar_0, i+1);
-        modified = true;
         i++;
       }
       /* 9O<non upper> */
@@ -781,13 +772,11 @@ void Tesseract::flip_0O(WERD_RES *word_res) {
            best_choice->unichar_id(i-2) == unichar_O)) {
         if (best_choice->unichar_id(i-2) == unichar_O) {
           best_choice->set_unichar_id(unichar_0, i-2);
-          modified = true;
         }
         while (i < best_choice->length() &&
                (best_choice->unichar_id(i) == unichar_O ||
                 best_choice->unichar_id(i) == unichar_0)) {
           best_choice->set_unichar_id(unichar_0, i);
-          modified = true;
           i++;
         }
         i--;

diff --git a/ccmain/tfacepp.cpp b/ccmain/tfacepp.cpp
@@ -90,8 +90,8 @@ void Tesseract::recog_word(WERD_RES *word) {
   // Factored out from control.cpp
   ASSERT_HOST((word->best_choice == NULL) == (word->raw_choice == NULL));
   if (word->best_choice == NULL || word->best_choice->length() == 0 ||
-      strspn(word->best_choice->unichar_string().string(), " ") ==
-        word->best_choice->length()) {
+      static_cast<int>(strspn(word->best_choice->unichar_string().string(),
+                              " ")) == word->best_choice->length()) {
     word->tess_failed = true;
     word->reject_map.initialise(word->box_word->length());
     word->reject_map.rej_word_tess_failure();
@@ -145,8 +145,6 @@ void Tesseract::split_and_recog_word(WERD_RES *word) {
   // Find the biggest blob gap in the chopped_word.
   int bestgap = -MAX_INT32;
   int split_index = 0;
-  TBLOB* best_end = NULL;
-  TBLOB* prev_blob = NULL;
   for (int b = 1; b < word->chopped_word->NumBlobs(); ++b) {
     TBOX prev_box = word->chopped_word->blobs[b - 1]->bounding_box();
     TBOX blob_box = word->chopped_word->blobs[b]->bounding_box();

diff --git a/ccstruct/blobs.cpp b/ccstruct/blobs.cpp
@@ -306,7 +306,6 @@ static TESSLINE** ApproximateOutlineList(bool allow_detailed_fx,
 // contain pointers to the input C_OUTLINEs that enable higher-resolution
 // feature extraction that does not use the polygonal approximation.
 TBLOB* TBLOB::PolygonalCopy(bool allow_detailed_fx, C_BLOB* src) {
-  C_OUTLINE_IT ol_it = src->out_list();
   TBLOB* tblob = new TBLOB;
   ApproximateOutlineList(allow_detailed_fx, src->out_list(), false,
                          &tblob->outlines);

diff --git a/ccstruct/fontinfo.cpp b/ccstruct/fontinfo.cpp
@@ -156,7 +156,8 @@ bool read_info(FILE* f, FontInfo* fi, bool swap) {
     Reverse32(&size);
   char* font_name = new char[size + 1];
   fi->name = font_name;
-  if (fread(font_name, sizeof(*font_name), size, f) != size) return false;
+  if (static_cast<int>(fread(font_name, sizeof(*font_name), size, f)) != size)
+    return false;
   font_name[size] = '\0';
   if (fread(&fi->properties, sizeof(fi->properties), 1, f) != 1) return false;
   if (swap)
@@ -167,7 +168,8 @@ bool read_info(FILE* f, FontInfo* fi, bool swap) {
 bool write_info(FILE* f, const FontInfo& fi) {
   inT32 size = strlen(fi.name);
   if (fwrite(&size, sizeof(size), 1, f) != 1) return false;
-  if (fwrite(fi.name, sizeof(*fi.name), size, f) != size) return false;
+  if (static_cast<int>(fwrite(fi.name, sizeof(*fi.name), size, f)) != size)
+    return false;
   if (fwrite(&fi.properties, sizeof(fi.properties), 1, f) != 1) return false;
   return true;
 }