node-native-win-utils 1.4.0 → 2.1.0

package/include/tesseract/pageiterator.h

@@ -1,364 +0,0 @@
-// SPDX-License-Identifier: Apache-2.0
-// File:        pageiterator.h
-// Description: Iterator for tesseract page structure that avoids using
-//              tesseract internal data structures.
-// Author:      Ray Smith
-//
-// (C) Copyright 2010, 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_PAGEITERATOR_H_
-#define TESSERACT_CCMAIN_PAGEITERATOR_H_
-
-#include "export.h"
-#include "publictypes.h"
-
-struct Pix;
-struct Pta;
-
-namespace tesseract {
-
-struct BlamerBundle;
-class C_BLOB_IT;
-class PAGE_RES;
-class PAGE_RES_IT;
-class WERD;
-
-class Tesseract;
-
-/**
- * Class to iterate over tesseract page structure, providing access to all
- * levels of the page hierarchy, without including any tesseract headers or
- * having to handle any tesseract structures.
- * WARNING! This class points to data held within the TessBaseAPI class, and
- * therefore can only be used while the TessBaseAPI class still exists and
- * has not been subjected to a call of Init, SetImage, Recognize, Clear, End
- * DetectOS, or anything else that changes the internal PAGE_RES.
- * See tesseract/publictypes.h for the definition of PageIteratorLevel.
- * See also ResultIterator, derived from PageIterator, which adds in the
- * ability to access OCR output with text-specific methods.
- */
-
-class TESS_API PageIterator {
-public:
-  /**
-   * page_res and tesseract come directly from the BaseAPI.
-   * The rectangle parameters are copied indirectly from the Thresholder,
-   * via the BaseAPI. They represent the coordinates of some rectangle in an
-   * original image (in top-left-origin coordinates) and therefore the top-left
-   * needs to be added to any output boxes in order to specify coordinates
-   * in the original image. See TessBaseAPI::SetRectangle.
-   * The scale and scaled_yres are in case the Thresholder scaled the image
-   * rectangle prior to thresholding. Any coordinates in tesseract's image
-   * must be divided by scale before adding (rect_left, rect_top).
-   * The scaled_yres indicates the effective resolution of the binary image
-   * that tesseract has been given by the Thresholder.
-   * After the constructor, Begin has already been called.
-   */
-  PageIterator(PAGE_RES *page_res, Tesseract *tesseract, int scale,
-               int scaled_yres, int rect_left, int rect_top, int rect_width,
-               int rect_height);
-  virtual ~PageIterator();
-
-  /**
-   * Page/ResultIterators may be copied! This makes it possible to iterate over
-   * all the objects at a lower level, while maintaining an iterator to
-   * objects at a higher level. These constructors DO NOT CALL Begin, so
-   * iterations will continue from the location of src.
-   */
-  PageIterator(const PageIterator &src);
-  const PageIterator &operator=(const PageIterator &src);
-
-  /** Are we positioned at the same location as other? */
-  bool PositionedAtSameWord(const PAGE_RES_IT *other) const;
-
-  // ============= Moving around within the page ============.
-
-  /**
-   * Moves the iterator to point to the start of the page to begin an
-   * iteration.
-   */
-  virtual void Begin();
-
-  /**
-   * Moves the iterator to the beginning of the paragraph.
-   * This class implements this functionality by moving it to the zero indexed
-   * blob of the first (leftmost) word on the first row of the paragraph.
-   */
-  virtual void RestartParagraph();
-
-  /**
-   * Return whether this iterator points anywhere in the first textline of a
-   * paragraph.
-   */
-  bool IsWithinFirstTextlineOfParagraph() const;
-
-  /**
-   * Moves the iterator to the beginning of the text line.
-   * This class implements this functionality by moving it to the zero indexed
-   * blob of the first (leftmost) word of the row.
-   */
-  virtual void RestartRow();
-
-  /**
-   * Moves to the start of the next object at the given level in the
-   * page hierarchy, 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.
-   */
-  virtual bool Next(PageIteratorLevel level);
-
-  /**
-   * Returns true if the iterator is at the start of an object at the given
-   * level.
-   *
-   * For instance, suppose an iterator it is pointed to the first symbol of the
-   * first word of the third line of the second paragraph of the first block in
-   * a page, then:
-   *   it.IsAtBeginningOf(RIL_BLOCK) = false
-   *   it.IsAtBeginningOf(RIL_PARA) = false
-   *   it.IsAtBeginningOf(RIL_TEXTLINE) = true
-   *   it.IsAtBeginningOf(RIL_WORD) = true
-   *   it.IsAtBeginningOf(RIL_SYMBOL) = true
-   */
-  virtual bool IsAtBeginningOf(PageIteratorLevel level) const;
-
-  /**
-   * Returns whether the iterator is positioned at the last element in a
-   * given level. (e.g. the last word in a line, the last line in a block)
-   *
-   *     Here's some two-paragraph example
-   *   text.  It starts off innocuously
-   *   enough but quickly turns bizarre.
-   *     The author inserts a cornucopia
-   *   of words to guard against confused
-   *   references.
-   *
-   * Now take an iterator it pointed to the start of "bizarre."
-   *  it.IsAtFinalElement(RIL_PARA, RIL_SYMBOL) = false
-   *  it.IsAtFinalElement(RIL_PARA, RIL_WORD) = true
-   *  it.IsAtFinalElement(RIL_BLOCK, RIL_WORD) = false
-   */
-  virtual bool IsAtFinalElement(PageIteratorLevel level,
-                                PageIteratorLevel element) const;
-
-  /**
-   * Returns whether this iterator is positioned
-   *   before other:   -1
-   *   equal to other:  0
-   *   after other:     1
-   */
-  int Cmp(const PageIterator &other) const;
-
-  // ============= Accessing data ==============.
-  // Coordinate system:
-  // Integer coordinates are at the cracks between the pixels.
-  // The top-left corner of the top-left pixel in the image is at (0,0).
-  // The bottom-right corner of the bottom-right pixel in the image is at
-  // (width, height).
-  // Every bounding box goes from the top-left of the top-left contained
-  // pixel to the bottom-right of the bottom-right contained pixel, so
-  // the bounding box of the single top-left pixel in the image is:
-  // (0,0)->(1,1).
-  // If an image rectangle has been set in the API, then returned coordinates
-  // relate to the original (full) image, rather than the rectangle.
-
-  /**
-   * Controls what to include in a bounding box. Bounding boxes of all levels
-   * between RIL_WORD and RIL_BLOCK can include or exclude potential diacritics.
-   * Between layout analysis and recognition, it isn't known where all
-   * diacritics belong, so this control is used to include or exclude some
-   * diacritics that are above or below the main body of the word. In most cases
-   * where the placement is obvious, and after recognition, it doesn't make as
-   * much difference, as the diacritics will already be included in the word.
-   */
-  void SetBoundingBoxComponents(bool include_upper_dots,
-                                bool include_lower_dots) {
-    include_upper_dots_ = include_upper_dots;
-    include_lower_dots_ = include_lower_dots;
-  }
-
-  /**
-   * Returns the bounding rectangle of the current object at the given level.
-   * See comment on coordinate system above.
-   * Returns false if there is no such object at the current position.
-   * The returned bounding box is guaranteed to match the size and position
-   * of the image returned by GetBinaryImage, but may clip foreground pixels
-   * from a grey image. The padding argument to GetImage can be used to expand
-   * the image to include more foreground pixels. See GetImage below.
-   */
-  bool BoundingBox(PageIteratorLevel level, int *left, int *top, int *right,
-                   int *bottom) const;
-  bool BoundingBox(PageIteratorLevel level, int padding, int *left, int *top,
-                   int *right, int *bottom) const;
-  /**
-   * Returns the bounding rectangle of the object in a coordinate system of the
-   * working image rectangle having its origin at (rect_left_, rect_top_) with
-   * respect to the original image and is scaled by a factor scale_.
-   */
-  bool BoundingBoxInternal(PageIteratorLevel level, int *left, int *top,
-                           int *right, int *bottom) const;
-
-  /** Returns whether there is no object of a given level. */
-  bool Empty(PageIteratorLevel level) const;
-
-  /**
-   * Returns the type of the current block.
-   * See tesseract/publictypes.h for PolyBlockType.
-   */
-  PolyBlockType BlockType() const;
-
-  /**
-   * Returns the polygon outline of the current block. The returned Pta must
-   * be ptaDestroy-ed after use. Note that the returned Pta lists the vertices
-   * of the polygon, and the last edge is the line segment between the last
-   * point and the first point. nullptr will be returned if the iterator is
-   * at the end of the document or layout analysis was not used.
-   */
-  Pta *BlockPolygon() const;
-
-  /**
-   * Returns a binary image of the current object at the given level.
-   * The position and size match the return from BoundingBoxInternal, and so
-   * this could be upscaled with respect to the original input image.
-   * Use pixDestroy to delete the image after use.
-   */
-  Pix *GetBinaryImage(PageIteratorLevel level) const;
-
-  /**
-   * Returns an image of the current object at the given level in greyscale
-   * if available in the input. To guarantee a binary image use BinaryImage.
-   * NOTE that in order to give the best possible image, the bounds are
-   * expanded slightly over the binary connected component, by the supplied
-   * padding, so the top-left position of the returned image is returned
-   * in (left,top). These will most likely not match the coordinates
-   * returned by BoundingBox.
-   * If you do not supply an original image, you will get a binary one.
-   * Use pixDestroy to delete the image after use.
-   */
-  Pix *GetImage(PageIteratorLevel level, int padding, Pix *original_img,
-                int *left, int *top) const;
-
-  /**
-   * Returns the baseline of the current object at the given level.
-   * The baseline is the line that passes through (x1, y1) and (x2, y2).
-   * WARNING: with vertical text, baselines may be vertical!
-   * Returns false if there is no baseline at the current position.
-   */
-  bool Baseline(PageIteratorLevel level, int *x1, int *y1, int *x2,
-                int *y2) const;
-
-  // Returns the attributes of the current row.
-  void RowAttributes(float *row_height, float *descenders,
-                     float *ascenders) const;
-
-  /**
-   * Returns orientation for the block the iterator points to.
-   *   orientation, writing_direction, textline_order: see publictypes.h
-   *   deskew_angle: after rotating the block so the text orientation is
-   *                 upright, how many radians does one have to rotate the
-   *                 block anti-clockwise for it to be level?
-   *                   -Pi/4 <= deskew_angle <= Pi/4
-   */
-  void Orientation(tesseract::Orientation *orientation,
-                   tesseract::WritingDirection *writing_direction,
-                   tesseract::TextlineOrder *textline_order,
-                   float *deskew_angle) const;
-
-  /**
-   * Returns information about the current paragraph, if available.
-   *
-   *   justification -
-   *     LEFT if ragged right, or fully justified and script is left-to-right.
-   *     RIGHT if ragged left, or fully justified and script is right-to-left.
-   *     unknown if it looks like source code or we have very few lines.
-   *   is_list_item -
-   *     true if we believe this is a member of an ordered or unordered list.
-   *   is_crown -
-   *     true if the first line of the paragraph is aligned with the other
-   *     lines of the paragraph even though subsequent paragraphs have first
-   *     line indents.  This typically indicates that this is the continuation
-   *     of a previous paragraph or that it is the very first paragraph in
-   *     the chapter.
-   *   first_line_indent -
-   *     For LEFT aligned paragraphs, the first text line of paragraphs of
-   *     this kind are indented this many pixels from the left edge of the
-   *     rest of the paragraph.
-   *     for RIGHT aligned paragraphs, the first text line of paragraphs of
-   *     this kind are indented this many pixels from the right edge of the
-   *     rest of the paragraph.
-   *     NOTE 1: This value may be negative.
-   *     NOTE 2: if *is_crown == true, the first line of this paragraph is
-   *             actually flush, and first_line_indent is set to the "common"
-   *             first_line_indent for subsequent paragraphs in this block
-   *             of text.
-   */
-  void ParagraphInfo(tesseract::ParagraphJustification *justification,
-                     bool *is_list_item, bool *is_crown,
-                     int *first_line_indent) const;
-
-  // If the current WERD_RES (it_->word()) is not nullptr, sets the BlamerBundle
-  // of the current word to the given pointer (takes ownership of the pointer)
-  // and returns true.
-  // Can only be used when iterating on the word level.
-  bool SetWordBlamerBundle(BlamerBundle *blamer_bundle);
-
-protected:
-  /**
-   * Sets up the internal data for iterating the blobs of a new word, then
-   * moves the iterator to the given offset.
-   */
-  void BeginWord(int offset);
-
-  /** Pointer to the page_res owned by the API. */
-  PAGE_RES *page_res_;
-  /** Pointer to the Tesseract object owned by the API. */
-  Tesseract *tesseract_;
-  /**
-   * The iterator to the page_res_. Owned by this ResultIterator.
-   * A pointer just to avoid dragging in Tesseract includes.
-   */
-  PAGE_RES_IT *it_;
-  /**
-   * The current input WERD being iterated. If there is an output from OCR,
-   * then word_ is nullptr. Owned by the API
-   */
-  WERD *word_;
-  /** The length of the current word_. */
-  int word_length_;
-  /** The current blob index within the word. */
-  int blob_index_;
-  /**
-   * Iterator to the blobs within the word. If nullptr, then we are iterating
-   * OCR results in the box_word.
-   * Owned by this ResultIterator.
-   */
-  C_BLOB_IT *cblob_it_;
-  /** Control over what to include in bounding boxes. */
-  bool include_upper_dots_;
-  bool include_lower_dots_;
-  /** Parameters saved from the Thresholder. Needed to rebuild coordinates.*/
-  int scale_;
-  int scaled_yres_;
-  int rect_left_;
-  int rect_top_;
-  int rect_width_;
-  int rect_height_;
-};
-
-} // namespace tesseract.
-
-#endif // TESSERACT_CCMAIN_PAGEITERATOR_H_

package/include/tesseract/publictypes.h

@@ -1,281 +0,0 @@
-// SPDX-License-Identifier: Apache-2.0
-// File:        publictypes.h
-// Description: Types used in both the API and internally
-// Author:      Ray Smith
-//
-// (C) Copyright 2010, 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_CCSTRUCT_PUBLICTYPES_H_
-#define TESSERACT_CCSTRUCT_PUBLICTYPES_H_
-
-namespace tesseract {
-
-// This file contains types that are used both by the API and internally
-// to Tesseract. In order to decouple the API from Tesseract and prevent cyclic
-// dependencies, THIS FILE SHOULD NOT DEPEND ON ANY OTHER PART OF TESSERACT.
-// Restated: It is OK for low-level Tesseract files to include publictypes.h,
-// but not for the low-level tesseract code to include top-level API code.
-// This file should not use other Tesseract types, as that would drag
-// their includes into the API-level.
-
-/** Number of printers' points in an inch. The unit of the pointsize return. */
-constexpr int kPointsPerInch = 72;
-/**
- * Minimum believable resolution. Used as a default if there is no other
- * information, as it is safer to under-estimate than over-estimate.
- */
-constexpr int kMinCredibleResolution = 70;
-/** Maximum believable resolution.  */
-constexpr int kMaxCredibleResolution = 2400;
-/**
- * Ratio between median blob size and likely resolution. Used to estimate
- * resolution when none is provided. This is basically 1/usual text size in
- * inches.  */
-constexpr int kResolutionEstimationFactor = 10;
-
-/**
- * Possible types for a POLY_BLOCK or ColPartition.
- * Must be kept in sync with kPBColors in polyblk.cpp and PTIs*Type functions
- * below, as well as kPolyBlockNames in layout_test.cc.
- * Used extensively by ColPartition, and POLY_BLOCK.
- */
-enum PolyBlockType {
-  PT_UNKNOWN,         // Type is not yet known. Keep as the first element.
-  PT_FLOWING_TEXT,    // Text that lives inside a column.
-  PT_HEADING_TEXT,    // Text that spans more than one column.
-  PT_PULLOUT_TEXT,    // Text that is in a cross-column pull-out region.
-  PT_EQUATION,        // Partition belonging to an equation region.
-  PT_INLINE_EQUATION, // Partition has inline equation.
-  PT_TABLE,           // Partition belonging to a table region.
-  PT_VERTICAL_TEXT,   // Text-line runs vertically.
-  PT_CAPTION_TEXT,    // Text that belongs to an image.
-  PT_FLOWING_IMAGE,   // Image that lives inside a column.
-  PT_HEADING_IMAGE,   // Image that spans more than one column.
-  PT_PULLOUT_IMAGE,   // Image that is in a cross-column pull-out region.
-  PT_HORZ_LINE,       // Horizontal Line.
-  PT_VERT_LINE,       // Vertical Line.
-  PT_NOISE,           // Lies outside of any column.
-  PT_COUNT
-};
-
-/** Returns true if PolyBlockType is of line type */
-inline bool PTIsLineType(PolyBlockType type) {
-  return type == PT_HORZ_LINE || type == PT_VERT_LINE;
-}
-/** Returns true if PolyBlockType is of image type */
-inline bool PTIsImageType(PolyBlockType type) {
-  return type == PT_FLOWING_IMAGE || type == PT_HEADING_IMAGE ||
-         type == PT_PULLOUT_IMAGE;
-}
-/** Returns true if PolyBlockType is of text type */
-inline bool PTIsTextType(PolyBlockType type) {
-  return type == PT_FLOWING_TEXT || type == PT_HEADING_TEXT ||
-         type == PT_PULLOUT_TEXT || type == PT_TABLE ||
-         type == PT_VERTICAL_TEXT || type == PT_CAPTION_TEXT ||
-         type == PT_INLINE_EQUATION;
-}
-// Returns true if PolyBlockType is of pullout(inter-column) type
-inline bool PTIsPulloutType(PolyBlockType type) {
-  return type == PT_PULLOUT_IMAGE || type == PT_PULLOUT_TEXT;
-}
-
-/**
- *  +------------------+  Orientation Example:
- *  | 1 Aaaa Aaaa Aaaa |  ====================
- *  | Aaa aa aaa aa    |  To left is a diagram of some (1) English and
- *  | aaaaaa A aa aaa. |  (2) Chinese text and a (3) photo credit.
- *  |                2 |
- *  |   #######  c c C |  Upright Latin characters are represented as A and a.
- *  |   #######  c c c |  '<' represents a latin character rotated
- *  | < #######  c c c |      anti-clockwise 90 degrees.
- *  | < #######  c   c |
- *  | < #######  .   c |  Upright Chinese characters are represented C and c.
- *  | 3 #######      c |
- *  +------------------+  NOTA BENE: enum values here should match goodoc.proto
-
- * If you orient your head so that "up" aligns with Orientation,
- * then the characters will appear "right side up" and readable.
- *
- * In the example above, both the English and Chinese paragraphs are oriented
- * so their "up" is the top of the page (page up).  The photo credit is read
- * with one's head turned leftward ("up" is to page left).
- *
- * The values of this enum match the convention of Tesseract's osdetect.h
-*/
-enum Orientation {
-  ORIENTATION_PAGE_UP = 0,
-  ORIENTATION_PAGE_RIGHT = 1,
-  ORIENTATION_PAGE_DOWN = 2,
-  ORIENTATION_PAGE_LEFT = 3,
-};
-
-/**
- * The grapheme clusters within a line of text are laid out logically
- * in this direction, judged when looking at the text line rotated so that
- * its Orientation is "page up".
- *
- * For English text, the writing direction is left-to-right.  For the
- * Chinese text in the above example, the writing direction is top-to-bottom.
- */
-enum WritingDirection {
-  WRITING_DIRECTION_LEFT_TO_RIGHT = 0,
-  WRITING_DIRECTION_RIGHT_TO_LEFT = 1,
-  WRITING_DIRECTION_TOP_TO_BOTTOM = 2,
-};
-
-/**
- * The text lines are read in the given sequence.
- *
- * In English, the order is top-to-bottom.
- * In Chinese, vertical text lines are read right-to-left.  Mongolian is
- * written in vertical columns top to bottom like Chinese, but the lines
- * order left-to right.
- *
- * Note that only some combinations make sense.  For example,
- * WRITING_DIRECTION_LEFT_TO_RIGHT implies TEXTLINE_ORDER_TOP_TO_BOTTOM
- */
-enum TextlineOrder {
-  TEXTLINE_ORDER_LEFT_TO_RIGHT = 0,
-  TEXTLINE_ORDER_RIGHT_TO_LEFT = 1,
-  TEXTLINE_ORDER_TOP_TO_BOTTOM = 2,
-};
-
-/**
- * Possible modes for page layout analysis. These *must* be kept in order
- * of decreasing amount of layout analysis to be done, except for OSD_ONLY,
- * so that the inequality test macros below work.
- */
-enum PageSegMode {
-  PSM_OSD_ONLY = 0,      ///< Orientation and script detection only.
-  PSM_AUTO_OSD = 1,      ///< Automatic page segmentation with orientation and
-                         ///< script detection. (OSD)
-  PSM_AUTO_ONLY = 2,     ///< Automatic page segmentation, but no OSD, or OCR.
-  PSM_AUTO = 3,          ///< Fully automatic page segmentation, but no OSD.
-  PSM_SINGLE_COLUMN = 4, ///< Assume a single column of text of variable sizes.
-  PSM_SINGLE_BLOCK_VERT_TEXT = 5, ///< Assume a single uniform block of
-                                  ///< vertically aligned text.
-  PSM_SINGLE_BLOCK = 6, ///< Assume a single uniform block of text. (Default.)
-  PSM_SINGLE_LINE = 7,  ///< Treat the image as a single text line.
-  PSM_SINGLE_WORD = 8,  ///< Treat the image as a single word.
-  PSM_CIRCLE_WORD = 9,  ///< Treat the image as a single word in a circle.
-  PSM_SINGLE_CHAR = 10, ///< Treat the image as a single character.
-  PSM_SPARSE_TEXT =
-      11, ///< Find as much text as possible in no particular order.
-  PSM_SPARSE_TEXT_OSD = 12, ///< Sparse text with orientation and script det.
-  PSM_RAW_LINE = 13, ///< Treat the image as a single text line, bypassing
-                     ///< hacks that are Tesseract-specific.
-
-  PSM_COUNT ///< Number of enum entries.
-};
-
-/**
- * Inline functions that act on a PageSegMode to determine whether components of
- * layout analysis are enabled.
- * *Depend critically on the order of elements of PageSegMode.*
- * NOTE that arg is an int for compatibility with INT_PARAM.
- */
-inline bool PSM_OSD_ENABLED(int pageseg_mode) {
-  return pageseg_mode <= PSM_AUTO_OSD || pageseg_mode == PSM_SPARSE_TEXT_OSD;
-}
-inline bool PSM_ORIENTATION_ENABLED(int pageseg_mode) {
-  return pageseg_mode <= PSM_AUTO || pageseg_mode == PSM_SPARSE_TEXT_OSD;
-}
-inline bool PSM_COL_FIND_ENABLED(int pageseg_mode) {
-  return pageseg_mode >= PSM_AUTO_OSD && pageseg_mode <= PSM_AUTO;
-}
-inline bool PSM_SPARSE(int pageseg_mode) {
-  return pageseg_mode == PSM_SPARSE_TEXT || pageseg_mode == PSM_SPARSE_TEXT_OSD;
-}
-inline bool PSM_BLOCK_FIND_ENABLED(int pageseg_mode) {
-  return pageseg_mode >= PSM_AUTO_OSD && pageseg_mode <= PSM_SINGLE_COLUMN;
-}
-inline bool PSM_LINE_FIND_ENABLED(int pageseg_mode) {
-  return pageseg_mode >= PSM_AUTO_OSD && pageseg_mode <= PSM_SINGLE_BLOCK;
-}
-inline bool PSM_WORD_FIND_ENABLED(int pageseg_mode) {
-  return (pageseg_mode >= PSM_AUTO_OSD && pageseg_mode <= PSM_SINGLE_LINE) ||
-         pageseg_mode == PSM_SPARSE_TEXT || pageseg_mode == PSM_SPARSE_TEXT_OSD;
-}
-
-/**
- * enum of the elements of the page hierarchy, used in ResultIterator
- * to provide functions that operate on each level without having to
- * have 5x as many functions.
- */
-enum PageIteratorLevel {
-  RIL_BLOCK,    // Block of text/image/separator line.
-  RIL_PARA,     // Paragraph within a block.
-  RIL_TEXTLINE, // Line within a paragraph.
-  RIL_WORD,     // Word within a textline.
-  RIL_SYMBOL    // Symbol/character within a word.
-};
-
-/**
- * JUSTIFICATION_UNKNOWN
- *   The alignment is not clearly one of the other options.  This could happen
- *   for example if there are only one or two lines of text or the text looks
- *   like source code or poetry.
- *
- * NOTA BENE: Fully justified paragraphs (text aligned to both left and right
- *    margins) are marked by Tesseract with JUSTIFICATION_LEFT if their text
- *    is written with a left-to-right script and with JUSTIFICATION_RIGHT if
- *    their text is written in a right-to-left script.
- *
- * Interpretation for text read in vertical lines:
- *   "Left" is wherever the starting reading position is.
- *
- * JUSTIFICATION_LEFT
- *   Each line, except possibly the first, is flush to the same left tab stop.
- *
- * JUSTIFICATION_CENTER
- *   The text lines of the paragraph are centered about a line going
- *   down through their middle of the text lines.
- *
- * JUSTIFICATION_RIGHT
- *   Each line, except possibly the first, is flush to the same right tab stop.
- */
-enum ParagraphJustification {
-  JUSTIFICATION_UNKNOWN,
-  JUSTIFICATION_LEFT,
-  JUSTIFICATION_CENTER,
-  JUSTIFICATION_RIGHT,
-};
-
-/**
- * When Tesseract/Cube is initialized we can choose to instantiate/load/run
- * only the Tesseract part, only the Cube part or both along with the combiner.
- * The preference of which engine to use is stored in tessedit_ocr_engine_mode.
- *
- * ATTENTION: When modifying this enum, please make sure to make the
- * appropriate changes to all the enums mirroring it (e.g. OCREngine in
- * cityblock/workflow/detection/detection_storage.proto). Such enums will
- * mention the connection to OcrEngineMode in the comments.
- */
-enum OcrEngineMode {
-  OEM_TESSERACT_ONLY,          // Run Tesseract only - fastest; deprecated
-  OEM_LSTM_ONLY,               // Run just the LSTM line recognizer.
-  OEM_TESSERACT_LSTM_COMBINED, // Run the LSTM recognizer, but allow fallback
-                               // to Tesseract when things get difficult.
-                               // deprecated
-  OEM_DEFAULT,                 // Specify this mode when calling init_*(),
-                               // to indicate that any of the above modes
-                               // should be automatically inferred from the
-                               // variables in the language-specific config,
-                               // command-line configs, or if not specified
-                               // in any of the above should be set to the
-                               // default OEM_TESSERACT_ONLY.
-  OEM_COUNT                    // Number of OEMs
-};
-
-} // namespace tesseract.
-
-#endif // TESSERACT_CCSTRUCT_PUBLICTYPES_H_