# SPDX-FileCopyrightText: 2022 James R. Barlow
# SPDX-License-Identifier: MIT
"""Tesseract no-op plugin
To quickly run tests where getting OCR output is not necessary.
In 'hocr' mode, create a .hocr file that specifies no text found.
In 'pdf' mode, convert the image to PDF using another program.
In orientation check mode, report the orientation is upright.
"""
from __future__ import annotations
import pikepdf
from PIL import Image
from ocrmypdf import OcrEngine, OrientationConfidence, hookimpl
HOCR_TEMPLATE = '''
'''
class NoopOcrEngine(OcrEngine):
@staticmethod
def version():
return '4.1.1'
@staticmethod
def creator_tag(options):
tag = '-PDF' if options.pdf_renderer == 'sandwich' else ''
return f"NO-OP {tag} {NoopOcrEngine.version()}"
def __str__(self):
return f"NO-OP {NoopOcrEngine.version()}"
@staticmethod
def languages(options):
return {'eng'}
@staticmethod
def get_orientation(input_file, options):
return OrientationConfidence(angle=0, confidence=0.0)
@staticmethod
def get_deskew(input_file, options):
return 0.0
@staticmethod
def generate_hocr(input_file, output_hocr, output_text, options):
with Image.open(input_file) as im, open(
output_hocr, 'w', encoding='utf-8'
) as f:
w, h = im.size
f.write(HOCR_TEMPLATE.format(str(w), str(h)))
with open(output_text, 'w') as f:
f.write('')
@staticmethod
def generate_pdf(input_file, output_pdf, output_text, options):
with Image.open(input_file) as im:
dpi = im.info['dpi']
pagesize = im.size[0] / dpi[0], im.size[1] / dpi[1]
ptsize = pagesize[0] * 72, pagesize[1] * 72
pdf = pikepdf.new()
pdf.add_blank_page(page_size=ptsize)
pdf.save(output_pdf, static_id=True)
output_text.write_text('')
@hookimpl
def get_ocr_engine():
return NoopOcrEngine()