Merge branch 'bugger' into dev

# Conflicts:
#	include/tesseract/baseapi.h
#	src/api/baseapi.cpp
#	src/api/pagerenderer.cpp
#	src/ccutil/ccutil.cpp
#	src/tesseract.cpp

include/tesseract/baseapi.h

@@ -830,7 +830,7 @@ class TESS_API TessBaseAPI {
    */
   char *GetAltoText(int page_number);
 
-  /**
+   /**
    * Make an XML-formatted string with PAGE markup from the internal
    * data structures.
    *
@@ -841,12 +841,13 @@ class TESS_API TessBaseAPI {
   /**
    * Make an XML-formatted string with PAGE markup from the internal
    * data structures.
+   *
+   * Returned string must be freed with the delete [] operator.
    */
   char *GetPAGEText(int page_number);
 
   /**
    * Make a TSV-formatted string from the internal data structures.
-   * Allows additional column with detected language.
    * page_number is 0-based but will appear in the output as 1-based.
    *
    * Returned string must be freed with the delete [] operator.

src/api/baseapi.cpp

@@ -3518,8 +3518,6 @@ void TessBaseAPI::SetupDebugAllPreset() {
   tess.debug_baseline_fit.set_value(1, SRC); // 0..3
   tess.debug_baseline_y_coord.set_value(-2000, SRC);
 
-  tess.showcase_threshold_methods.set_value((debug_all > 2), SRC);
-
   tess.debug_write_unlv.set_value(true, SRC);
   tess.debug_line_finding.set_value(true, SRC);
   tess.debug_image_normalization.set_value(true, SRC);

src/api/pagerenderer.cpp

@@ -30,8 +30,8 @@
 #include <unordered_set>
 
 #include <leptonica/allheaders.h>
-#include <leptonica/pix_internal.h>
 #include <leptonica/array_internal.h>
+#include <leptonica/pix_internal.h>
 
 #include <tesseract/renderer.h>
 #include "tesseractclass.h" // for Tesseract
@@ -722,19 +722,6 @@ char *TessBaseAPI::GetPAGEText(ETEXT_DESC *monitor, int page_number) {
     SetInputName(nullptr);
   }
 
-#if defined(_WIN32) && 0
-  // convert input name from ANSI encoding to utf-8
-  int str16_len = MultiByteToWideChar(CP_ACP, 0, input_file_.c_str(), -1, nullptr, 0);
-  wchar_t *uni16_str = new WCHAR[str16_len];
-  str16_len = MultiByteToWideChar(CP_ACP, 0, input_file_.c_str(), -1, uni16_str, str16_len);
-  int utf8_len = WideCharToMultiByte(CP_UTF8, 0, uni16_str, str16_len, nullptr, 0, nullptr, nullptr);
-  char *utf8_str = new char[utf8_len];
-  WideCharToMultiByte(CP_UTF8, 0, uni16_str, str16_len, utf8_str, utf8_len, nullptr, nullptr);
-  input_file_ = utf8_str;
-  delete[] uni16_str;
-  delete[] utf8_str;
-#endif
-
   // Used variables
 
   std::stringstream reading_order_str;
@@ -771,7 +758,9 @@ char *TessBaseAPI::GetPAGEText(ETEXT_DESC *monitor, int page_number) {
   #define LEVELFLAG tesseract_->page_xml_level
 
   if (LEVELFLAG != 0 && LEVELFLAG != 1) {
-    tprintError("For now, only line level and word level are available, and the level is reset to line level.\n");
+    tprintWarn(
+        "page_xml_level: for now, only line level (0) and word level (1) are available, and the level "
+        "is reset to line level.\n");
     LEVELFLAG = 0;
   }
 

src/ccstruct/pageres.cpp

@@ -1227,7 +1227,7 @@ int PAGE_RES_IT::cmp(const PAGE_RES_IT &other) const {
           return 1;
         }
       }
-      ASSERT_HOST(!"Error: Incomparable PAGE_RES_ITs");
+      ASSERT_HOST_MSG(false, "Error: Incomparable PAGE_RES_ITs");
     }
 
     // we both point to the same block, but different rows.
@@ -1240,7 +1240,7 @@ int PAGE_RES_IT::cmp(const PAGE_RES_IT &other) const {
         return 1;
       }
     }
-    ASSERT_HOST(!"Error: Incomparable PAGE_RES_ITs");
+    ASSERT_HOST_MSG(false, "Error: Incomparable PAGE_RES_ITs");
   }
 
   // We point to different blocks.
@@ -1254,7 +1254,7 @@ int PAGE_RES_IT::cmp(const PAGE_RES_IT &other) const {
     }
   }
   // Shouldn't happen...
-  ASSERT_HOST(!"Error: Incomparable PAGE_RES_ITs");
+  ASSERT_HOST_MSG(false, "Error: Incomparable PAGE_RES_ITs");
   return 0;
 }
 

src/ccutil/ccutil.cpp

@@ -147,7 +147,7 @@ static bool determine_datadir(std::string &datadir, const std::string &argv0, co
 
   // Ignore TESSDATA_PREFIX if there is no matching filesystem entry.
   if (tessdata_prefix != nullptr && !std::filesystem::exists(tessdata_prefix)) {
-    tprintf("Warning: TESSDATA_PREFIX %s does not exist, ignore it\n", tessdata_prefix);
+    tprintWarn("Environment variable TESSDATA_PREFIX's value '{}' is not a directory that exists in your filesystem; tesseract will ignore it.\n", tessdata_prefix);
     tessdata_prefix = nullptr;
   }
 

src/ccutil/tprintf.cpp

@@ -196,7 +196,7 @@ static loglevel_return_type ParseLogLevel(const char *loglevel) {
     std::transform(loglevel_string.begin(), loglevel_string.end(), loglevel_string.begin(), ::toupper);
     int loglevel = loglevels.at(loglevel_string);
     return loglevel;
-  } catch (const std::out_of_range &e) {
+  } catch (const std::out_of_range &) {
     // TODO: Allow numeric argument?
     tprintError("Unsupported --loglevel {}\n", loglevel);
     return cpp::fail(false);

src/ccutil/winutils.cpp

@@ -56,6 +56,16 @@ std::string Utf16ToUtf8(const wchar_t* utf16Str) {
   return result;
 }
 
+// convert input name from ANSI encoding to utf-8
+std::string AnsiToUtf8(const char *AnsiStr) {
+  auto str16_len = MultiByteToWideChar(CP_ACP, 0, AnsiStr, -1, nullptr, 0);
+  wchar_t *uni16_str = new WCHAR[str16_len];
+  str16_len = MultiByteToWideChar(CP_ACP, 0, AnsiStr, -1, uni16_str, str16_len);
+  std::string utf8_str = Utf16ToUtf8(uni16_str);
+  delete[] uni16_str;
+  return utf8_str;
+}
+
 } // namespace winutils
 } // namespace tesseract
 

src/ccutil/winutils.h

@@ -20,6 +20,7 @@ namespace winutils {
 
 std::wstring Utf8ToUtf16(const char* utf8Str);
 std::string Utf16ToUtf8(const wchar_t* utf16Str);
+std::string AnsiToUtf8(const char *AnsiStr);
 
 } // namespace winutils
 } // namespace tesseract

src/tesseract.cpp

@@ -767,7 +767,7 @@ static bool PreloadRenderers(tesseract::TessBaseAPI &api,
       if (renderer->happy()) {
         renderers.push_back(std::move(renderer));
       } else {
-        tprintError("Could not create PAGE output file: %s\n", strerror(errno));
+        tprintError("Could not create PAGE output file: {}\n", strerror(errno));
         error = true;
       }
     }
@@ -899,7 +899,7 @@ static inline auto format_as(WritingDirection d) {
 
 }
 
-static void SetupDebugAllPreset(TessBaseAPI &api)
+void SetupDebugAllPreset(TessBaseAPI &api)
 {
   if (debug_all) {
     api.SetupDebugAllPreset();
@@ -1067,7 +1067,7 @@ extern "C" int tesseract_main(int argc, const char** argv)
     // second: grab the output_base_path if we haven't already:
     if (!outputbasepath_is_specified) {
       if (path_params.size() < 2) {
-        tprintError("Error, missing outputbase command line argument\n");
+        tprintError("Missing outputbase command line argument\n");
         return EXIT_FAILURE;
       }
 

src/textord/textord.cpp

@@ -224,12 +224,12 @@ void Textord::TextordPage(PageSegMode pageseg_mode, const FCOORD &reskew, int wi
   // Make the rows in the block.
   // Do it the old fashioned way.
   if (PSM_LINE_FIND_ENABLED(pageseg_mode)) {
-    gradient = make_rows(page_tr_, to_blocks);
+    *gradient = make_rows(page_tr_, to_blocks);
   } else if (!PSM_SPARSE(pageseg_mode)) {
     // RAW_LINE, SINGLE_LINE, SINGLE_WORD and SINGLE_CHAR all need a single row.
-    gradient = make_single_row(page_tr_, pageseg_mode != PSM_RAW_LINE, to_block, to_blocks);
+    *gradient = make_single_row(page_tr_, pageseg_mode != PSM_RAW_LINE, to_block, to_blocks);
   } else {
-    gradient = 0.0f;
+    *gradient = 0.0f;
   }
   const int debug_level_offset = std::max(0, textord_baseline_debug + 0 /* to implicitly use operator int() on the referenced variable */);
   int old_level = debug_baseline_detector_level;
@@ -241,7 +241,7 @@ void Textord::TextordPage(PageSegMode pageseg_mode, const FCOORD &reskew, int wi
   // Now make the words in the lines.
   if (PSM_WORD_FIND_ENABLED(pageseg_mode)) {
     // SINGLE_LINE uses the old word maker on the single line.
-    make_words(this, page_tr_, gradient, blocks, to_blocks);
+    make_words(this, page_tr_, *gradient, blocks, to_blocks);
   } else {
     // SINGLE_WORD and SINGLE_CHAR cram all the blobs into a
     // single word, and in SINGLE_CHAR mode, all the outlines

src/training/combine_tessdata.cpp

@@ -283,7 +283,7 @@ extern "C" int tesseract_combine_tessdata_main(int argc, const char** argv)
         tprintError("No LSTM Component found in {}!\n", argv[2]);
         return EXIT_FAILURE;
       }
-      tesseract::LSTMRecognizer recognizer;
+      tesseract::LSTMRecognizer recognizer(nullptr);
       recognizer.SetDebug(tess_debug_lstm);
       if (!recognizer.DeSerialize(&tm, &fp)) {
         tprintError("Failed to deserialize LSTM in {}!\n", argv[2]);

src/training/common/commontraining.cpp

@@ -71,6 +71,7 @@ int ParseArguments(int* argc, const char ***argv) {
 #  include "mastertrainer.h"
 #  include "mf.h"
 #  include "oldlist.h"
+#  include "commandlineflags.h"
 #  include <tesseract/params.h>
 #  include "shapetable.h"
 #  include "tessdatamanager.h"

src/training/common/trainingsampleset.cpp

@@ -31,6 +31,7 @@
 #include "trainingsample.h"
 #include "trainingsampleset.h"
 #include "unicity_table.h"
+#include "commandlineflags.h"
 
 namespace tesseract {