Added extra Init that takes a memory buffer or a filereader function pointer to enable read of traineddata from memory or foreign file systems. Updated existing readers to use TFile API instead of FILE. This does not yet add big-endian capability to LSTM, but it is very easy from here.

Author: theraysmith

api/baseapi.cpp

@@ -108,26 +108,30 @@ const int kMinCredibleResolution = 70;
 const int kMaxCredibleResolution = 2400;
 
 TessBaseAPI::TessBaseAPI()
-  : tesseract_(NULL),
-    osd_tesseract_(NULL),
-    equ_detect_(NULL),
-    // Thresholder is initialized to NULL here, but will be set before use by:
-    // A constructor of a derived API,  SetThresholder(), or
-    // created implicitly when used in InternalSetImage.
-    thresholder_(NULL),
-    paragraph_models_(NULL),
-    block_list_(NULL),
-    page_res_(NULL),
-    input_file_(NULL),
-    output_file_(NULL),
-    datapath_(NULL),
-    language_(NULL),
-    last_oem_requested_(OEM_DEFAULT),
-    recognition_done_(false),
-    truth_cb_(NULL),
-    rect_left_(0), rect_top_(0), rect_width_(0), rect_height_(0),
-    image_width_(0), image_height_(0) {
-}
+    : tesseract_(nullptr),
+      osd_tesseract_(nullptr),
+      equ_detect_(nullptr),
+      reader_(nullptr),
+      // Thresholder is initialized to NULL here, but will be set before use by:
+      // A constructor of a derived API,  SetThresholder(), or
+      // created implicitly when used in InternalSetImage.
+      thresholder_(nullptr),
+      paragraph_models_(nullptr),
+      block_list_(nullptr),
+      page_res_(nullptr),
+      input_file_(nullptr),
+      output_file_(nullptr),
+      datapath_(nullptr),
+      language_(nullptr),
+      last_oem_requested_(OEM_DEFAULT),
+      recognition_done_(false),
+      truth_cb_(NULL),
+      rect_left_(0),
+      rect_top_(0),
+      rect_width_(0),
+      rect_height_(0),
+      image_width_(0),
+      image_height_(0) {}
 
 TessBaseAPI::~TessBaseAPI() {
   End();
@@ -275,20 +279,33 @@ int TessBaseAPI::Init(const char* datapath, const char* language,
                       const GenericVector<STRING> *vars_vec,
                       const GenericVector<STRING> *vars_values,
                       bool set_only_non_debug_params) {
+  return Init(datapath, 0, language, oem, configs, configs_size, vars_vec,
+              vars_values, set_only_non_debug_params, nullptr);
+}
+
+// In-memory version reads the traineddata file directly from the given
+// data[data_size] array. Also implements the version with a datapath in data,
+// flagged by data_size = 0.
+int TessBaseAPI::Init(const char* data, int data_size, const char* language,
+                      OcrEngineMode oem, char** configs, int configs_size,
+                      const GenericVector<STRING>* vars_vec,
+                      const GenericVector<STRING>* vars_values,
+                      bool set_only_non_debug_params, FileReader reader) {
   PERF_COUNT_START("TessBaseAPI::Init")
   // Default language is "eng".
-  if (language == NULL) language = "eng";
+  if (language == nullptr) language = "eng";
+  STRING datapath = data_size == 0 ? data : language;
   // If the datapath, OcrEngineMode or the language have changed - start again.
   // Note that the language_ field stores the last requested language that was
   // initialized successfully, while tesseract_->lang stores the language
   // actually used. They differ only if the requested language was NULL, in
   // which case tesseract_->lang is set to the Tesseract default ("eng").
-  if (tesseract_ != NULL &&
-      (datapath_ == NULL || language_ == NULL ||
-       *datapath_ != datapath || last_oem_requested_ != oem ||
+  if (tesseract_ != nullptr &&
+      (datapath_ == nullptr || language_ == nullptr || *datapath_ != datapath ||
+       last_oem_requested_ != oem ||
        (*language_ != language && tesseract_->lang != language))) {
     delete tesseract_;
-    tesseract_ = NULL;
+    tesseract_ = nullptr;
   }
   // PERF_COUNT_SUB("delete tesseract_")
 #ifdef USE_OPENCL
@@ -297,27 +314,33 @@ int TessBaseAPI::Init(const char* datapath, const char* language,
 #endif
   PERF_COUNT_SUB("OD::InitEnv()")
   bool reset_classifier = true;
-  if (tesseract_ == NULL) {
+  if (tesseract_ == nullptr) {
     reset_classifier = false;
     tesseract_ = new Tesseract;
+    if (reader != nullptr) reader_ = reader;
+    TessdataManager mgr(reader_);
+    if (data_size != 0) {
+      mgr.LoadMemBuffer(language, data, data_size);
+    }
     if (tesseract_->init_tesseract(
-        datapath, output_file_ != NULL ? output_file_->string() : NULL,
-        language, oem, configs, configs_size, vars_vec, vars_values,
-        set_only_non_debug_params) != 0) {
+            datapath.string(),
+            output_file_ != nullptr ? output_file_->string() : nullptr,
+            language, oem, configs, configs_size, vars_vec, vars_values,
+            set_only_non_debug_params, &mgr) != 0) {
       return -1;
     }
   }
   PERF_COUNT_SUB("update tesseract_")
   // Update datapath and language requested for the last valid initialization.
-  if (datapath_ == NULL)
+  if (datapath_ == nullptr)
     datapath_ = new STRING(datapath);
   else
     *datapath_ = datapath;
   if ((strcmp(datapath_->string(), "") == 0) &&
       (strcmp(tesseract_->datadir.string(), "") != 0))
      *datapath_ = tesseract_->datadir;
 
-  if (language_ == NULL)
+  if (language_ == nullptr)
     language_ = new STRING(language);
   else
     *language_ = language;
@@ -421,7 +444,8 @@ int TessBaseAPI::InitLangMod(const char* datapath, const char* language) {
     tesseract_ = new Tesseract;
   else
     ParamUtils::ResetToDefaults(tesseract_->params());
-  return tesseract_->init_tesseract_lm(datapath, NULL, language);
+  TessdataManager mgr;
+  return tesseract_->init_tesseract_lm(datapath, NULL, language, &mgr);
 }
 
 /**
@@ -431,7 +455,7 @@ int TessBaseAPI::InitLangMod(const char* datapath, const char* language) {
 void TessBaseAPI::InitForAnalysePage() {
   if (tesseract_ == NULL) {
     tesseract_ = new Tesseract;
-    tesseract_->InitAdaptiveClassifier(false);
+    tesseract_->InitAdaptiveClassifier(nullptr);
   }
 }
 
@@ -2239,7 +2263,7 @@ int TessBaseAPI::FindLines() {
   }
   if (tesseract_ == NULL) {
     tesseract_ = new Tesseract;
-    tesseract_->InitAdaptiveClassifier(false);
+    tesseract_->InitAdaptiveClassifier(nullptr);
   }
   if (tesseract_->pix_binary() == NULL)
     Threshold(tesseract_->mutable_pix_binary());
@@ -2261,22 +2285,24 @@ int TessBaseAPI::FindLines() {
 
   Tesseract* osd_tess = osd_tesseract_;
   OSResults osr;
-  if (PSM_OSD_ENABLED(tesseract_->tessedit_pageseg_mode) && osd_tess == NULL) {
+  if (PSM_OSD_ENABLED(tesseract_->tessedit_pageseg_mode) &&
+      osd_tess == nullptr) {
     if (strcmp(language_->string(), "osd") == 0) {
       osd_tess = tesseract_;
     } else {
       osd_tesseract_ = new Tesseract;
-      if (osd_tesseract_->init_tesseract(
-          datapath_->string(), NULL, "osd", OEM_TESSERACT_ONLY,
-          NULL, 0, NULL, NULL, false) == 0) {
+      TessdataManager mgr(reader_);
+      if (osd_tesseract_->init_tesseract(datapath_->string(), nullptr, "osd",
+                                         OEM_TESSERACT_ONLY, nullptr, 0,
+                                         nullptr, nullptr, false, &mgr) == 0) {
         osd_tess = osd_tesseract_;
         osd_tesseract_->set_source_resolution(
             thresholder_->GetSourceYResolution());
       } else {
         tprintf("Warning: Auto orientation and script detection requested,"
                 " but osd language failed to load\n");
         delete osd_tesseract_;
-        osd_tesseract_ = NULL;
+        osd_tesseract_ = nullptr;
       }
     }
   }

api/baseapi.h

@@ -29,14 +29,15 @@
 // To avoid collision with other typenames include the ABSOLUTE MINIMUM
 // complexity of includes here. Use forward declarations wherever possible
 // and hide includes of complex types in baseapi.cpp.
-#include "platform.h"
 #include "apitypes.h"
-#include "thresholder.h"
-#include "unichar.h"
-#include "tesscallback.h"
-#include "publictypes.h"
 #include "pageiterator.h"
+#include "platform.h"
+#include "publictypes.h"
 #include "resultiterator.h"
+#include "serialis.h"
+#include "tesscallback.h"
+#include "thresholder.h"
+#include "unichar.h"
 
 template <typename T> class GenericVector;
 class PAGE_RES;
@@ -237,6 +238,13 @@ class TESS_API TessBaseAPI {
   int Init(const char* datapath, const char* language) {
     return Init(datapath, language, OEM_DEFAULT, NULL, 0, NULL, NULL, false);
   }
+  // In-memory version reads the traineddata file directly from the given
+  // data[data_size] array, and/or reads data via a FileReader.
+  int Init(const char* data, int data_size, const char* language,
+           OcrEngineMode mode, char** configs, int configs_size,
+           const GenericVector<STRING>* vars_vec,
+           const GenericVector<STRING>* vars_values,
+           bool set_only_non_debug_params, FileReader reader);
 
   /**
    * Returns the languages string used in the last valid initialization.
@@ -859,6 +867,7 @@ class TESS_API TessBaseAPI {
   Tesseract*        tesseract_;       ///< The underlying data object.
   Tesseract*        osd_tesseract_;   ///< For orientation & script detection.
   EquationDetect*   equ_detect_;      ///<The equation detector.
+  FileReader reader_;                 ///< Reads files from any filesystem.
   ImageThresholder* thresholder_;     ///< Image thresholding module.
   GenericVector<ParagraphModel *>* paragraph_models_;
   BLOCK_LIST*       block_list_;      ///< The page layout.