def test_langs_error(self, popen):
self.stdout.stdout.read.return_value = b"No languages\n"
self.stdout.wait.return_value = 1
popen.return_value = self.stdout
with self.assertRaises(tesseract.TesseractError) as te:
tesseract.get_available_languages()
self.assertEqual(te.exception.status, 1)
self.assertEqual("unable to get languages", te.exception.message)
popen.assert_called_once_with(["tesseract", "--list-langs"],
startupinfo=None,
creationflags=0,
stdout=subprocess.PIPE,
stderr=subprocess.STDOUT)
def test_langs(self):
langs = tesseract.get_available_languages()
self.assertTrue("eng" in langs,
("English training does not appear to be installed."
" (required for the tests)"))
self.assertTrue("fra" in langs,
("French training does not appear to be installed."
" (required for the tests)"))
self.assertTrue("jpn" in langs,
("Japanese training does not appear to be installed."
" (required for the tests)"))
def test_langs(self):
langs = tesseract.get_available_languages()
self.assertTrue("eng" in langs,
("English training does not appear to be installed."
" (required for the tests)"))
self.assertTrue("fra" in langs,
("French training does not appear to be installed."
" (required for the tests)"))
self.assertTrue("jpn" in langs,
("Japanese training does not appear to be installed."
" (required for the tests)"))
def test_langs(self, popen):
message = ("List of available languages (4):\n"
"eng\n"
"fra\n"
"jpn\n"
"osd\n")
self.stdout.stdout.read.return_value = message.encode()
popen.return_value = self.stdout
langs = tesseract.get_available_languages()
for lang in ("eng", "fra", "jpn", "osd"):
self.assertIn(lang, langs)
popen.assert_called_once_with(["tesseract", "--list-langs"],
startupinfo=None,
creationflags=0,
stdout=subprocess.PIPE,
stderr=subprocess.STDOUT)
#!/usr/bin/env python
# codeing=utf-8
from PIL import Image
import sys
from pyocr import pyocr
from pyocr import tesseract
if __name__ == '__main__':
print tesseract.get_available_languages()
tools = pyocr.get_available_tools()[:]
if len(tools) == 0:
print("No OCR tool found")
sys.exit(1)
print("Using '%s'" % (tools[0].get_name()))
tools[0].image_to_string(Image.open('test.png'),
lang='fra',
builder=TextBuilder())
# # # # # #
# # # # # #
# # # # # #
# Module 5: Convert PDFs to text data
# # # # # #
# # # # # #
# # # # # #
from wand.image import Image
from PIL import Image as PI
import pyocr
import pyocr.builders
import io
from pyocr import tesseract as tool # tool = pyocr.get_available_tools()[0]
lang = tool.get_available_languages()[0]
import time
import datetime
import pandas as pd
pd.set_option('display.max_columns', None)
import numpy as np
import shutil
import os
import sys
import local_filepaths as fp
# # # # # #
# Ascertain which PDFs are still to be processed
# # # # # #
