1# © 2020 James R. Barlow: github.com/jbarlow83 2# 3# Permission is hereby granted, free of charge, to any person obtaining a 4# copy of this software and associated documentation files (the 5# "Software"), to deal in the Software without restriction, including 6# without limitation the rights to use, copy, modify, merge, publish, 7# distribute, sublicense, and/or sell copies of the Software, and to 8# permit persons to whom the Software is furnished to do so, subject to 9# the following conditions: 10# 11# The above copyright notice and this permission notice shall be included 12# in all copies or substantial portions of the Software. 13# 14# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS 15# OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF 16# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. 17# IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY 18# CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, 19# TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE 20# SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. 21 22"""Tesseract no-op plugin 23 24To quickly run tests where getting OCR output is not necessary. 25 26In 'hocr' mode, create a .hocr file that specifies no text found. 27 28In 'pdf' mode, convert the image to PDF using another program. 29 30In orientation check mode, report the orientation is upright. 31""" 32 33import pikepdf 34from PIL import Image 35 36from ocrmypdf import OcrEngine, OrientationConfidence, hookimpl 37 38HOCR_TEMPLATE = '''<?xml version="1.0" encoding="UTF-8"?> 39<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" 40 "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"> 41<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"> 42 <head> 43 <title></title> 44 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 45 <meta name='ocr-system' content='tesseract 4.0.0' /> 46 <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word'/> 47 </head> 48 <body> 49 <div class='ocr_page' id='page_1' title='image "x.tif"; bbox 0 0 {0} {1}; ppageno 0'> 50 <div class='ocr_carea' id='block_1_1' title="bbox 0 1 {0} {1}"> 51 <p class='ocr_par' dir='ltr' id='par_1' title="bbox 0 1 {0} {1}"> 52 <span class='ocr_line' id='line_1' title="bbox 0 1 {0} {1}"><span class='ocrx_word' id='word_1' title="bbox 0 1 {0} {1}"> </span> 53 </span> 54 </p> 55 </div> 56 </div> 57 </body> 58</html>''' 59 60 61class NoopOcrEngine(OcrEngine): 62 @staticmethod 63 def version(): 64 return '4.0.0' 65 66 @staticmethod 67 def creator_tag(options): 68 tag = '-PDF' if options.pdf_renderer == 'sandwich' else '' 69 return f"NO-OP {tag} {NoopOcrEngine.version()}" 70 71 def __str__(self): 72 return f"NO-OP {NoopOcrEngine.version()}" 73 74 @staticmethod 75 def languages(options): 76 return {'eng'} 77 78 @staticmethod 79 def get_orientation(input_file, options): 80 return OrientationConfidence(angle=0, confidence=0.0) 81 82 @staticmethod 83 def generate_hocr(input_file, output_hocr, output_text, options): 84 with Image.open(input_file) as im, open( 85 output_hocr, 'w', encoding='utf-8' 86 ) as f: 87 w, h = im.size 88 f.write(HOCR_TEMPLATE.format(str(w), str(h))) 89 with open(output_text, 'w') as f: 90 f.write('') 91 92 @staticmethod 93 def generate_pdf(input_file, output_pdf, output_text, options): 94 with Image.open(input_file) as im: 95 dpi = im.info['dpi'] 96 pagesize = im.size[0] / dpi[0], im.size[1] / dpi[1] 97 ptsize = pagesize[0] * 72, pagesize[1] * 72 98 pdf = pikepdf.new() 99 pdf.add_blank_page(page_size=ptsize) 100 pdf.save(output_pdf, static_id=True) 101 output_text.write_text('') 102 103 104@hookimpl 105def get_ocr_engine(): 106 return NoopOcrEngine() 107