1 /********************************************************************** 2 * File: boxread.cpp 3 * Description: Read data from a box file. 4 * Author: Ray Smith 5 * Created: Fri Aug 24 17:47:23 PDT 2007 6 * 7 * (C) Copyright 2007, Google Inc. 8 ** Licensed under the Apache License, Version 2.0 (the "License"); 9 ** you may not use this file except in compliance with the License. 10 ** You may obtain a copy of the License at 11 ** http://www.apache.org/licenses/LICENSE-2.0 12 ** Unless required by applicable law or agreed to in writing, software 13 ** distributed under the License is distributed on an "AS IS" BASIS, 14 ** WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 15 ** See the License for the specific language governing permissions and 16 ** limitations under the License. 17 * 18 **********************************************************************/ 19 20 #ifndef TESSERACT_CCUTIL_BOXREAD_H__ 21 #define TESSERACT_CCUTIL_BOXREAD_H__ 22 23 #include <stdio.h> 24 25 // Size of buffer used to read a line from a box file. 26 const int kBoxReadBufSize = 256; 27 28 // read_next_box factors out the code to interpret a line of a box 29 // file so that applybox and unicharset_extractor interpret the same way. 30 // This function returns the next valid box file utf8 string and coords 31 // and returns true, or false on eof (and closes the file). 32 // If ignores the uft8 file signature, checks for valid utf-8 and allows 33 // space or tab between fields. 34 // utf8_str must be at least kBoxReadBufSize in length. 35 // If there are page numbers in the file, it reads them all. 36 bool read_next_box(FILE* box_file, char* utf8_str, 37 int* x_min, int* y_min, int* x_max, int* y_max); 38 // As read_next_box above, but get a specific page number. (0-based) 39 // Use -1 to read any page number. Files without page number all 40 // read as if they are page 0. 41 bool read_next_box(int page, FILE* box_file, char* utf8_str, 42 int* x_min, int* y_min, int* x_max, int* y_max); 43 44 #endif // TESSERACT_CCUTIL_BOXREAD_H__ 45