Merge branch 'main' of https://github.com/tesseract-ocr/tesseract

.github/workflows/cmake-win64.yml

@@ -26,7 +26,7 @@ jobs:
         run: |
              $git_info=$(git describe --tags HEAD)
              echo "version=${git_info}" >> $env:GITHUB_OUTPUT
-      - name: Setup Instalation Location
+      - name: Setup Installation Location
         run: |
              mkdir ${{env.ILOC}}
       - name: Uninstall Perl

include/tesseract/ocrclass.h

@@ -61,7 +61,7 @@ struct EANYCODE_CHAR { /*single character */
   // 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
+  // the same bounding box. Programs which want to handle languages 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.

src/ccmain/resultiterator.cpp

@@ -149,7 +149,7 @@ void ResultIterator::CalculateBlobOrder(std::vector<int> *blob_indices) const {
   for (int i = 0; i < word_length_; i++) {
     letter_types.push_back(it_->word()->SymbolDirection(i));
   }
-  // Convert a single separtor sandwiched between two EN's into an EN.
+  // Convert a single separator sandwiched between two ENs into an EN.
   for (int i = 0; i + 2 < word_length_; i++) {
     if (letter_types[i] == U_EURO_NUM && letter_types[i + 2] == U_EURO_NUM &&
         (letter_types[i + 1] == U_EURO_NUM_SEP || letter_types[i + 1] == U_COMMON_NUM_SEP)) {

src/ccstruct/stepblob.cpp

@@ -314,7 +314,7 @@ int32_t C_BLOB::outer_area() { // area
  * C_BLOB::count_transitions
  *
  * Return the total x and y maxes and mins in the blob.
- * Chlid outlines are not counted.
+ * Child outlines are not counted.
  **********************************************************************/
 
 int32_t C_BLOB::count_transitions( // area

src/dict/dict.cpp

@@ -114,7 +114,7 @@ Dict::Dict(CCUtil *ccutil)
                     " for each dict char above small word size.",
                     getCCUtil()->params())
     , double_MEMBER(stopper_allowable_character_badness, 3.0,
-                    "Max certaintly variation allowed in a word (in sigma)", getCCUtil()->params())
+                    "Max certainty variation allowed in a word (in sigma)", getCCUtil()->params())
     , INT_MEMBER(stopper_debug_level, 0, "Stopper debug level", getCCUtil()->params())
     , BOOL_MEMBER(stopper_no_acceptable_choices, false,
                   "Make AcceptableChoice() always return false. Useful"
@@ -171,7 +171,7 @@ Dict::~Dict() {
 
 DawgCache *Dict::GlobalDawgCache() {
   // This global cache (a singleton) will outlive every Tesseract instance
-  // (even those that someone else might declare as global statics).
+  // (even those that someone else might declare as global static variables).
   static DawgCache cache;
   return &cache;
 }

src/textord/topitch.cpp

@@ -398,9 +398,8 @@ bool try_doc_fixed(             // determine pitch
   int16_t mid_cuts; // no of cheap cuts
   float pitch_sd;   // sync rating
 
-  if (block_it.empty()
-      //      || block_it.data()==block_it.data_relative(1)
-      || !textord_blockndoc_fixed) {
+  if (!textord_blockndoc_fixed ||
+      block_it.empty() || block_it.data()->get_rows()->empty()) {
     return false;
   }
   shift_factor = gradient / (gradient * gradient + 1);