node-native-win-utils 1.4.0 → 2.1.1

package/include/tesseract/renderer.h

@@ -1,334 +0,0 @@
-// SPDX-License-Identifier: Apache-2.0
-// File:        renderer.h
-// Description: Rendering interface to inject into TessBaseAPI
-//
-// (C) Copyright 2011, Google Inc.
-// Licensed under the Apache License, Version 2.0 (the "License");
-// you may not use this file except in compliance with the License.
-// You may obtain a copy of the License at
-// http://www.apache.org/licenses/LICENSE-2.0
-// Unless required by applicable law or agreed to in writing, software
-// distributed under the License is distributed on an "AS IS" BASIS,
-// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-// See the License for the specific language governing permissions and
-// limitations under the License.
-
-#ifndef TESSERACT_API_RENDERER_H_
-#define TESSERACT_API_RENDERER_H_
-
-#include "export.h"
-
-// 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 <cstdint>
-#include <string> // for std::string
-#include <vector> // for std::vector
-
-struct Pix;
-
-namespace tesseract {
-
-class TessBaseAPI;
-
-/**
- * Interface for rendering tesseract results into a document, such as text,
- * HOCR or pdf. This class is abstract. Specific classes handle individual
- * formats. This interface is then used to inject the renderer class into
- * tesseract when processing images.
- *
- * For simplicity implementing this with tesseract version 3.01,
- * the renderer contains document state that is cleared from document
- * to document just as the TessBaseAPI is. This way the base API can just
- * delegate its rendering functionality to injected renderers, and the
- * renderers can manage the associated state needed for the specific formats
- * in addition to the heuristics for producing it.
- */
-class TESS_API TessResultRenderer {
-public:
-  virtual ~TessResultRenderer();
-
-  // Takes ownership of pointer so must be new'd instance.
-  // Renderers aren't ordered, but appends the sequences of next parameter
-  // and existing next(). The renderers should be unique across both lists.
-  void insert(TessResultRenderer *next);
-
-  // Returns the next renderer or nullptr.
-  TessResultRenderer *next() {
-    return next_;
-  }
-
-  /**
-   * Starts a new document with the given title.
-   * This clears the contents of the output data.
-   * Title should use UTF-8 encoding.
-   */
-  bool BeginDocument(const char *title);
-
-  /**
-   * Adds the recognized text from the source image to the current document.
-   * Invalid if BeginDocument not yet called.
-   *
-   * Note that this API is a bit weird but is designed to fit into the
-   * current TessBaseAPI implementation where the api has lots of state
-   * information that we might want to add in.
-   */
-  bool AddImage(TessBaseAPI *api);
-
-  /**
-   * Finishes the document and finalizes the output data
-   * Invalid if BeginDocument not yet called.
-   */
-  bool EndDocument();
-
-  const char *file_extension() const {
-    return file_extension_;
-  }
-  const char *title() const {
-    return title_.c_str();
-  }
-
-  // Is everything fine? Otherwise something went wrong.
-  bool happy() const {
-    return happy_;
-  }
-
-  /**
-   * Returns the index of the last image given to AddImage
-   * (i.e. images are incremented whether the image succeeded or not)
-   *
-   * This is always defined. It means either the number of the
-   * current image, the last image ended, or in the completed document
-   * depending on when in the document lifecycle you are looking at it.
-   * Will return -1 if a document was never started.
-   */
-  int imagenum() const {
-    return imagenum_;
-  }
-
-protected:
-  /**
-   * Called by concrete classes.
-   *
-   * outputbase is the name of the output file excluding
-   * extension. For example, "/path/to/chocolate-chip-cookie-recipe"
-   *
-   * extension indicates the file extension to be used for output
-   * files. For example "pdf" will produce a .pdf file, and "hocr"
-   * will produce .hocr files.
-   */
-  TessResultRenderer(const char *outputbase, const char *extension);
-
-  // Hook for specialized handling in BeginDocument()
-  virtual bool BeginDocumentHandler();
-
-  // This must be overridden to render the OCR'd results
-  virtual bool AddImageHandler(TessBaseAPI *api) = 0;
-
-  // Hook for specialized handling in EndDocument()
-  virtual bool EndDocumentHandler();
-
-  // Renderers can call this to append '\0' terminated strings into
-  // the output string returned by GetOutput.
-  // This method will grow the output buffer if needed.
-  void AppendString(const char *s);
-
-  // Renderers can call this to append binary byte sequences into
-  // the output string returned by GetOutput. Note that s is not necessarily
-  // '\0' terminated (and can contain '\0' within it).
-  // This method will grow the output buffer if needed.
-  void AppendData(const char *s, int len);
-
-  template <typename T>
-  auto AppendData(T &&d) {
-    AppendData(d.data(), d.size());
-    return d.size();
-  }
-
-private:
-  TessResultRenderer *next_;   // Can link multiple renderers together
-  FILE *fout_;                 // output file pointer
-  const char *file_extension_; // standard extension for generated output
-  std::string title_;          // title of document being rendered
-  int imagenum_;               // index of last image added
-  bool happy_;                 // I get grumpy when the disk fills up, etc.
-};
-
-/**
- * Renders tesseract output into a plain UTF-8 text string
- */
-class TESS_API TessTextRenderer : public TessResultRenderer {
-public:
-  explicit TessTextRenderer(const char *outputbase);
-
-protected:
-  bool AddImageHandler(TessBaseAPI *api) override;
-};
-
-/**
- * Renders tesseract output into an hocr text string
- */
-class TESS_API TessHOcrRenderer : public TessResultRenderer {
-public:
-  explicit TessHOcrRenderer(const char *outputbase, bool font_info);
-  explicit TessHOcrRenderer(const char *outputbase);
-
-protected:
-  bool BeginDocumentHandler() override;
-  bool AddImageHandler(TessBaseAPI *api) override;
-  bool EndDocumentHandler() override;
-
-private:
-  bool font_info_; // whether to print font information
-};
-
-/**
- * Renders tesseract output into an alto text string
- */
-class TESS_API TessAltoRenderer : public TessResultRenderer {
-public:
-  explicit TessAltoRenderer(const char *outputbase);
-
-protected:
-  bool BeginDocumentHandler() override;
-  bool AddImageHandler(TessBaseAPI *api) override;
-  bool EndDocumentHandler() override;
-
-private:
-  bool begin_document;
-};
-
-/**
- * Renders Tesseract output into a PAGE XML text string
- */
-class TESS_API TessPAGERenderer : public TessResultRenderer {
-public:
-  explicit TessPAGERenderer(const char *outputbase);
-
-protected:
-  bool BeginDocumentHandler() override;
-  bool AddImageHandler(TessBaseAPI *api) override;
-  bool EndDocumentHandler() override;
-
-private:
-  bool begin_document;
-};
-
-
-/**
- * Renders Tesseract output into a TSV string
- */
-class TESS_API TessTsvRenderer : public TessResultRenderer {
-public:
-  explicit TessTsvRenderer(const char *outputbase, bool font_info);
-  explicit TessTsvRenderer(const char *outputbase);
-
-protected:
-  bool BeginDocumentHandler() override;
-  bool AddImageHandler(TessBaseAPI *api) override;
-  bool EndDocumentHandler() override;
-
-private:
-  bool font_info_; // whether to print font information
-};
-
-/**
- * Renders tesseract output into searchable PDF
- */
-class TESS_API TessPDFRenderer : public TessResultRenderer {
-public:
-  // datadir is the location of the TESSDATA. We need it because
-  // we load a custom PDF font from this location.
-  TessPDFRenderer(const char *outputbase, const char *datadir,
-                  bool textonly = false);
-
-protected:
-  bool BeginDocumentHandler() override;
-  bool AddImageHandler(TessBaseAPI *api) override;
-  bool EndDocumentHandler() override;
-
-private:
-  // We don't want to have every image in memory at once,
-  // so we store some metadata as we go along producing
-  // PDFs one page at a time. At the end, that metadata is
-  // used to make everything that isn't easily handled in a
-  // streaming fashion.
-  long int obj_;                  // counter for PDF objects
-  std::vector<uint64_t> offsets_; // offset of every PDF object in bytes
-  std::vector<long int> pages_;   // object number for every /Page object
-  std::string datadir_;           // where to find the custom font
-  bool textonly_;                 // skip images if set
-  // Bookkeeping only. DIY = Do It Yourself.
-  void AppendPDFObjectDIY(size_t objectsize);
-  // Bookkeeping + emit data.
-  void AppendPDFObject(const char *data);
-  // Create the /Contents object for an entire page.
-  char *GetPDFTextObjects(TessBaseAPI *api, double width, double height);
-  // Turn an image into a PDF object. Only transcode if we have to.
-  static bool imageToPDFObj(Pix *pix, const char *filename, long int objnum,
-                            char **pdf_object, long int *pdf_object_size,
-                            int jpg_quality);
-};
-
-/**
- * Renders tesseract output into a plain UTF-8 text string
- */
-class TESS_API TessUnlvRenderer : public TessResultRenderer {
-public:
-  explicit TessUnlvRenderer(const char *outputbase);
-
-protected:
-  bool AddImageHandler(TessBaseAPI *api) override;
-};
-
-/**
- * Renders tesseract output into a plain UTF-8 text string for LSTMBox
- */
-class TESS_API TessLSTMBoxRenderer : public TessResultRenderer {
-public:
-  explicit TessLSTMBoxRenderer(const char *outputbase);
-
-protected:
-  bool AddImageHandler(TessBaseAPI *api) override;
-};
-
-/**
- * Renders tesseract output into a plain UTF-8 text string
- */
-class TESS_API TessBoxTextRenderer : public TessResultRenderer {
-public:
-  explicit TessBoxTextRenderer(const char *outputbase);
-
-protected:
-  bool AddImageHandler(TessBaseAPI *api) override;
-};
-
-/**
- * Renders tesseract output into a plain UTF-8 text string in WordStr format
- */
-class TESS_API TessWordStrBoxRenderer : public TessResultRenderer {
-public:
-  explicit TessWordStrBoxRenderer(const char *outputbase);
-
-protected:
-  bool AddImageHandler(TessBaseAPI *api) override;
-};
-
-#ifndef DISABLED_LEGACY_ENGINE
-
-/**
- * Renders tesseract output into an osd text string
- */
-class TESS_API TessOsdRenderer : public TessResultRenderer {
-public:
-  explicit TessOsdRenderer(const char *outputbase);
-
-protected:
-  bool AddImageHandler(TessBaseAPI *api) override;
-};
-
-#endif // ndef DISABLED_LEGACY_ENGINE
-
-} // namespace tesseract.
-
-#endif // TESSERACT_API_RENDERER_H_

package/include/tesseract/resultiterator.h

@@ -1,250 +0,0 @@
-// SPDX-License-Identifier: Apache-2.0
-// File:        resultiterator.h
-// Description: Iterator for tesseract results that is capable of
-//              iterating in proper reading order over Bi Directional
-//              (e.g. mixed Hebrew and English) text.
-// Author:      David Eger
-//
-// (C) Copyright 2011, Google Inc.
-// Licensed under the Apache License, Version 2.0 (the "License");
-// you may not use this file except in compliance with the License.
-// You may obtain a copy of the License at
-// http://www.apache.org/licenses/LICENSE-2.0
-// Unless required by applicable law or agreed to in writing, software
-// distributed under the License is distributed on an "AS IS" BASIS,
-// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-// See the License for the specific language governing permissions and
-// limitations under the License.
-
-#ifndef TESSERACT_CCMAIN_RESULT_ITERATOR_H_
-#define TESSERACT_CCMAIN_RESULT_ITERATOR_H_
-
-#include "export.h"            // for TESS_API, TESS_LOCAL
-#include "ltrresultiterator.h" // for LTRResultIterator
-#include "publictypes.h"       // for PageIteratorLevel
-#include "unichar.h"           // for StrongScriptDirection
-
-#include <set>    // for std::pair
-#include <vector> // for std::vector
-
-namespace tesseract {
-
-class TESS_API ResultIterator : public LTRResultIterator {
-public:
-  static ResultIterator *StartOfParagraph(const LTRResultIterator &resit);
-
-  /**
-   * ResultIterator is copy constructible!
-   * The default copy constructor works just fine for us.
-   */
-  ~ResultIterator() override = default;
-
-  // ============= Moving around within the page ============.
-  /**
-   * Moves the iterator to point to the start of the page to begin
-   * an iteration.
-   */
-  void Begin() override;
-
-  /**
-   * Moves to the start of the next object at the given level in the
-   * page hierarchy in the appropriate reading order and returns false if
-   * the end of the page was reached.
-   * NOTE that RIL_SYMBOL will skip non-text blocks, but all other
-   * PageIteratorLevel level values will visit each non-text block once.
-   * Think of non text blocks as containing a single para, with a single line,
-   * with a single imaginary word.
-   * Calls to Next with different levels may be freely intermixed.
-   * This function iterates words in right-to-left scripts correctly, if
-   * the appropriate language has been loaded into Tesseract.
-   */
-  bool Next(PageIteratorLevel level) override;
-
-  /**
-   * IsAtBeginningOf() returns whether we're at the logical beginning of the
-   * given level.  (as opposed to ResultIterator's left-to-right top-to-bottom
-   * order).  Otherwise, this acts the same as PageIterator::IsAtBeginningOf().
-   * For a full description, see pageiterator.h
-   */
-  bool IsAtBeginningOf(PageIteratorLevel level) const override;
-
-  /**
-   * Implement PageIterator's IsAtFinalElement correctly in a BiDi context.
-   * For instance, IsAtFinalElement(RIL_PARA, RIL_WORD) returns whether we
-   * point at the last word in a paragraph.  See PageIterator for full comment.
-   */
-  bool IsAtFinalElement(PageIteratorLevel level,
-                        PageIteratorLevel element) const override;
-
-  // ============= Functions that refer to words only ============.
-  // Returns the number of blanks before the current word.
-  int BlanksBeforeWord() const;
-
-  // ============= Accessing data ==============.
-
-  /**
-   * Returns the null terminated UTF-8 encoded text string for the current
-   * object at the given level. Use delete [] to free after use.
-   */
-  virtual char *GetUTF8Text(PageIteratorLevel level) const;
-
-  /**
-   * Returns the LSTM choices for every LSTM timestep for the current word.
-   */
-  virtual std::vector<std::vector<std::vector<std::pair<const char *, float>>>>
-      *GetRawLSTMTimesteps() const;
-  virtual std::vector<std::vector<std::pair<const char *, float>>>
-      *GetBestLSTMSymbolChoices() const;
-
-  /**
-   * Return whether the current paragraph's dominant reading direction
-   * is left-to-right (as opposed to right-to-left).
-   */
-  bool ParagraphIsLtr() const;
-
-  // ============= Exposed only for testing =============.
-
-  /**
-   * Yields the reading order as a sequence of indices and (optional)
-   * meta-marks for a set of words (given left-to-right).
-   * The meta marks are passed as negative values:
-   *   kMinorRunStart  Start of minor direction text.
-   *   kMinorRunEnd    End of minor direction text.
-   *   kComplexWord    The next indexed word contains both left-to-right and
-   *                    right-to-left characters and was treated as neutral.
-   *
-   * For example, suppose we have five words in a text line,
-   * indexed [0,1,2,3,4] from the leftmost side of the text line.
-   * The following are all believable reading_orders:
-   *
-   * Left-to-Right (in ltr paragraph):
-   *     { 0, 1, 2, 3, 4 }
-   * Left-to-Right (in rtl paragraph):
-   *     { kMinorRunStart, 0, 1, 2, 3, 4, kMinorRunEnd }
-   * Right-to-Left (in rtl paragraph):
-   *     { 4, 3, 2, 1, 0 }
-   * Left-to-Right except for an RTL phrase in words 2, 3 in an ltr paragraph:
-   *     { 0, 1, kMinorRunStart, 3, 2, kMinorRunEnd, 4 }
-   */
-  static void CalculateTextlineOrder(
-      bool paragraph_is_ltr,
-      const std::vector<StrongScriptDirection> &word_dirs,
-      std::vector<int> *reading_order);
-
-  static const int kMinorRunStart;
-  static const int kMinorRunEnd;
-  static const int kComplexWord;
-
-protected:
-  /**
-   * We presume the data associated with the given iterator will outlive us.
-   * NB: This is private because it does something that is non-obvious:
-   *   it resets to the beginning of the paragraph instead of staying wherever
-   *   resit might have pointed.
-   */
-  explicit ResultIterator(const LTRResultIterator &resit);
-
-private:
-  /**
-   * Calculates the current paragraph's dominant writing direction.
-   * Typically, members should use current_paragraph_ltr_ instead.
-   */
-  bool CurrentParagraphIsLtr() const;
-
-  /**
-   * Returns word indices as measured from resit->RestartRow() = index 0
-   * for the reading order of words within a textline given an iterator
-   * into the middle of the text line.
-   * In addition to non-negative word indices, the following negative values
-   * may be inserted:
-   *   kMinorRunStart  Start of minor direction text.
-   *   kMinorRunEnd    End of minor direction text.
-   *   kComplexWord    The previous word contains both left-to-right and
-   *                   right-to-left characters and was treated as neutral.
-   */
-  void CalculateTextlineOrder(bool paragraph_is_ltr,
-                              const LTRResultIterator &resit,
-                              std::vector<int> *indices) const;
-  /** Same as above, but the caller's ssd gets filled in if ssd != nullptr. */
-  void CalculateTextlineOrder(bool paragraph_is_ltr,
-                              const LTRResultIterator &resit,
-                              std::vector<StrongScriptDirection> *ssd,
-                              std::vector<int> *indices) const;
-
-  /**
-   * What is the index of the current word in a strict left-to-right reading
-   * of the row?
-   */
-  int LTRWordIndex() const;
-
-  /**
-   * Given an iterator pointing at a word, returns the logical reading order
-   * of blob indices for the word.
-   */
-  void CalculateBlobOrder(std::vector<int> *blob_indices) const;
-
-  /** Precondition: current_paragraph_is_ltr_ is set. */
-  void MoveToLogicalStartOfTextline();
-
-  /**
-   * Precondition: current_paragraph_is_ltr_ and in_minor_direction_
-   * are set.
-   */
-  void MoveToLogicalStartOfWord();
-
-  /** Are we pointing at the final (reading order) symbol of the word? */
-  bool IsAtFinalSymbolOfWord() const;
-
-  /** Are we pointing at the first (reading order) symbol of the word? */
-  bool IsAtFirstSymbolOfWord() const;
-
-  /**
-   * Append any extra marks that should be appended to this word when printed.
-   * Mostly, these are Unicode BiDi control characters.
-   */
-  void AppendSuffixMarks(std::string *text) const;
-
-  /** Appends the current word in reading order to the given buffer.*/
-  void AppendUTF8WordText(std::string *text) const;
-
-  /**
-   * Appends the text of the current text line, *assuming this iterator is
-   * positioned at the beginning of the text line*  This function
-   * updates the iterator to point to the first position past the text line.
-   * Each textline is terminated in a single newline character.
-   * If the textline ends a paragraph, it gets a second terminal newline.
-   */
-  void IterateAndAppendUTF8TextlineText(std::string *text);
-
-  /**
-   * Appends the text of the current paragraph in reading order
-   * to the given buffer.
-   * Each textline is terminated in a single newline character, and the
-   * paragraph gets an extra newline at the end.
-   */
-  void AppendUTF8ParagraphText(std::string *text) const;
-
-  /** Returns whether the bidi_debug flag is set to at least min_level. */
-  bool BidiDebug(int min_level) const;
-
-  bool current_paragraph_is_ltr_;
-
-  /**
-   * Is the currently pointed-at character at the beginning of
-   * a minor-direction run?
-   */
-  bool at_beginning_of_minor_run_;
-
-  /** Is the currently pointed-at character in a minor-direction sequence? */
-  bool in_minor_direction_;
-
-  /**
-   * Should detected inter-word spaces be preserved, or "compressed" to a single
-   * space character (default behavior).
-   */
-  bool preserve_interword_spaces_;
-};
-
-} // namespace tesseract.
-
-#endif // TESSERACT_CCMAIN_RESULT_ITERATOR_H_

package/include/tesseract/tesseract.h

@@ -1,40 +0,0 @@
-// The following ifdef block is the standard way of creating macros which make STATICTESSERACT_APIing
-// from a DLL simpler. All files within this DLL are compiled with the STATICTESSERACT_STATICTESSERACT_APIS
-// symbol defined on the command line. This symbol should not be defined on any project
-// that uses this DLL. This way any other project whose source files include this file see
-// STATICTESSERACT_API functions as being imported from a DLL, whereas this DLL sees symbols
-// defined with this macro as being STATICTESSERACT_APIed.
-#ifdef STATICTESSERACT_EXPORTS
-#define STATICTESSERACT_API __declspec(dllexport)
-#else
-#define STATICTESSERACT_API __declspec(dllimport)
-#endif
-#include <tesseract/baseapi.h>
-#include <tesseract/capi.h>
-
-
-extern "C"
-{
-	STATICTESSERACT_API tesseract::TessBaseAPI* Tesseract_Create();
-	STATICTESSERACT_API void Tesseract_Delete(tesseract::TessBaseAPI*& tesseract_ptr);
-	STATICTESSERACT_API int Tesseract_Init(tesseract::TessBaseAPI* tesseract_ptr, const char* datapath, const char* language);
-	STATICTESSERACT_API void Tesseract_End(tesseract::TessBaseAPI*& tesseract_ptr);
-	STATICTESSERACT_API void Tesseract_SetPageSegMode(tesseract::TessBaseAPI* tesseract_ptr, int mode);
-	STATICTESSERACT_API int Tesseract_GetPageSegMode(tesseract::TessBaseAPI* tesseract_ptr);
-	STATICTESSERACT_API float Tesseract_MeanTextConf(tesseract::TessBaseAPI* tesseract_ptr);
-	STATICTESSERACT_API void Tesseract_SetImage(tesseract::TessBaseAPI* tesseract_ptr, const unsigned char* imagedata, int width, int height, int bytes_per_pixel, int bytes_per_line);
-	STATICTESSERACT_API const char* Tesseract_GetUTF8Text(tesseract::TessBaseAPI* tesseract_ptr, int* len);
-	STATICTESSERACT_API void Tesseract_FreeUTF8Text(char*& utf8_text_ptr);
-	STATICTESSERACT_API bool Tesseract_SetVariable(tesseract::TessBaseAPI* tesseract_ptr, const char* name, const char* value);
-	STATICTESSERACT_API void Tesseract_Clear(tesseract::TessBaseAPI* tesseract_ptr);
-	STATICTESSERACT_API int Tesseract_GetBlockCount(tesseract::TessBaseAPI* tesseract_ptr);
-	STATICTESSERACT_API int Tesseract_GetLineCount(tesseract::TessBaseAPI* tesseract_ptr);
-	STATICTESSERACT_API int Tesseract_GetWordCount(tesseract::TessBaseAPI* tesseract_ptr);
-	STATICTESSERACT_API int Tesseract_GetCharacterCount(tesseract::TessBaseAPI* tesseract_ptr);
-	STATICTESSERACT_API void Tesseract_GetBlockMatch(tesseract::TessBaseAPI* tesseract_ptr, int index, char*& text, int* len, float* confidence, int* x1, int* y1, int* x2, int* y2);
-	STATICTESSERACT_API void Tesseract_GetLineMatch(tesseract::TessBaseAPI* tesseract_ptr, int index, char*& text, int* len, float* confidence, int* x1, int* y1, int* x2, int* y2);
-	STATICTESSERACT_API void Tesseract_GetWordMatch(tesseract::TessBaseAPI* tesseract_ptr, int index, char*& text, int* len, float* confidence, int* x1, int* y1, int* x2, int* y2);
-	STATICTESSERACT_API void Tesseract_GetCharacterMatch(tesseract::TessBaseAPI* tesseract_ptr, int index, char*& text, int* len, float* confidence, int* x1, int* y1, int* x2, int* y2);
-
-}
-