ocrclass.h

来自「一个google的OCR源码」· C头文件 代码 · 共 346 行 · 第 1/2 页

  OCR_ERR_INTERNAL6,             /*internal error type 1 */
  OCR_ERR_INTERNAL7,             /*internal error type 1 */
  OCR_ERR_INTERNAL8,             /*internal error type 1 */
  OCR_ERR_TIMEOUT                /*timed out in comms */
};                               /*for calls to ocr_error */

/**********************************************************************
 * EFONT_DESC
 * Description of one font.
 * The information required is basically that used by RTF.
 * The name may be either a valid font on the system or the empty string.
 **********************************************************************/

typedef struct                   /*font description */
{
  uinT16 language;               /*default language */
  uinT8 font_family;             /*serif/not, fixed/not */
  uinT8 char_set;                /*character set standard */
  uinT8 pitch;                   /*fixed or prop */
  inT8 name[MAX_FONT_NAME + 1];  /*plain ascii name */
} EFONT_DESC;                    /*font description */

/**********************************************************************
 * EOCR_DESC
 * Description of the OCR engine provided at startup.
 * The name and version may be reported to the user at some point.
 * The fonts array should indicate the fonts that the OCR system
 * can recognize.
 **********************************************************************/

typedef struct                   /*startup info */
{
  inT32 protocol;                /*interface version */
  uinT32 font_count;             /*number of fonts */
  uinT16 language;               /*default language */
  uinT16 name[MAX_OCR_NAME + 1]; /*name of engine */
                                 /*version of engine */
  uinT16 version[MAX_OCR_VERSION + 1];
  EFONT_DESC fonts[1];           /*array of fonts */
} EOCR_DESC;                     /*startup info */

/**********************************************************************
 * ESTRIP_DESC
 * Description of the image strip as it is passed to the engine.
 * The image is always 1 bit, with 1=black.
 * The width is always a multiple of 32, so padding is always OK.
 * The height of the full image is always a multiple of 32.
 * The top y coordinate is 0, and increases down.
 * The top leftmost pixel is in the most significant bit of the first byte.
 **********************************************************************/

typedef struct                   /*bitmap strip */
{
  inT16 x_size;                  /*width in pixels */
  inT16 y_size;                  /*of full image */
  inT16 strip_size;              /*of this strip */
  inT16 resolution;              /*pixels per inch */
  uinT8 data[8];                 /*image data */
} ESTRIP_DESC;                   /*bitmap strip */

/**********************************************************************
 * EANYCODE_CHAR
 * Description of a single character. The character code is defined by
 * the character set of the current font.
 * Output text is sent as an array of these structures.
 * Spaces and line endings in the output are represented in the
 * structures of the surrounding characters. They are not directly
 * represented as characters.
 * The first character in a word has a positive value of blanks.
 * Missing information should be set to the defaults in the comments.
 * If word bounds are known, but not character bounds, then the top and
 * bottom of each character should be those of the word. The left of the
 * first and right of the last char in each word should be set. All other
 * lefts and rights should be set to -1.
 * If set, the values of right and bottom are left+width and top+height.
 * Most of the members come directly from the parameters to ocr_append_char.
 * The formatting member uses the enhancement parameter and combines the
 * line direction stuff into the top 3 bits.
 * The coding is 0=RL char, 1=LR char, 2=DR NL, 3=UL NL, 4=DR Para,
 * 5=UL Para, 6=TB char, 7=BT char. API users do not need to know what
 * the coding is, only that it is backwards compatible with the previous
 * version.
 **********************************************************************/

typedef struct                   /*single character */
{
// It should be noted that the format for char_code for version 2.0 and beyond 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 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.
  uinT16 char_code;              /*character itself */
  inT16 left;                    /*of char (-1) */
  inT16 right;                   /*of char (-1) */
  inT16 top;                     /*of char (-1) */
  inT16 bottom;                  /*of char (-1) */
  inT16 font_index;              /*what font (0) */
  uinT8 confidence;              /*0=perfect, 100=reject (0/100) */
  uinT8 point_size;              /*of char, 72=i inch, (10) */
  inT8 blanks;                   /*no of spaces before this char (1) */
  uinT8 formatting;              /*char formatting (0) */
} EANYCODE_CHAR;                 /*single character */

/**********************************************************************
 * ETEXT_DESC
 * Description of the output of the OCR engine.
 * This structure is used as both a progress monitor and the final
 * output header, since it needs to be a valid progress monitor while
 * the OCR engine is storing its output to shared memory.
 * During progress, all the buffer info is -1.
 * Progress starts at 0 and increases to 100 during OCR. No other constraint.
 * Every progress callback, the OCR engine must set ocr_alive to 1.
 * The HP side will set ocr_alive to 0. Repeated failure to reset
 * to 1 indicates that the OCR engine is dead.
 * If the cancel function is not null then it is called with the number of
 * user words found. If it returns true then operation is cancelled.
 **********************************************************************/
typedef bool (*CANCEL_FUNC)(void* cancel_this, int words);

typedef struct ETEXT_STRUCT      /*output header */
{
  inT16 count;                   /*chars in this buffer(0) */
  inT16 progress;                /*percent complete increasing (0-100) */
  inT8 more_to_come;             /*true if not last */
  inT8 ocr_alive;                /*ocr sets to 1, HP 0 */
  inT8 err_code;                 /*for errcode use */
  CANCEL_FUNC cancel;            /*returns true to cancel */
  void* cancel_this;             /*this or other data for cancel*/
  clock_t end_time;              /*time to stop if not 0*/
  EANYCODE_CHAR text[1];         /*character data */
} ETEXT_DESC;                    /*output header */

#ifdef __MSW32__
/**********************************************************************
 * ESHM_INFO
 * This data structure is used internally to the API to hold the handles
 * to the operating system tools used for interprocess communications.
 * API users do not access this structure directly.
 **********************************************************************/
typedef struct                   /*shared mem info */
{
  HANDLE shm_hand;               /*handle to shm */
  HANDLE mutex;                  /*alive check */
  HANDLE ocr_sem;                /*ocr semaphore */
  HANDLE hp_sem;                 /*hp semaphore */
  void *shm_mem;                 /*shared memory */
  inT32 shm_size;                /*size of shm */
} ESHM_INFO;                     /*shared mem info */
#elif defined (__MAC__)
typedef struct                   /*shared mem info */
{
  Boolean mutex;                 /*alive check */
  Boolean ocr_sem;               /*ocr semaphore */
  Boolean hp_sem;                /*hp semaphore */
  void *shm_mem;                 /*shared memory */
  inT32 shm_size;                /*size of shm */
  inT16 language;

  // Process management information follows:
  ProcessSerialNumber IPEProcess;
  ProcessSerialNumber OCRProcess;
} ESHM_INFO;
#elif defined (__UNIX__)
typedef struct                   /*shared mem info */
{
  void *shm_mem;                 /*shared memory */
  inT32 shm_size;                /*size of shm */
} ESHM_INFO;
#endif
#endif