def test_word_segmentation(workspace):
CalamariRecognize(
workspace,
input_file_grp="OCR-D-GT-SEG-LINE",
output_file_grp="OCR-D-OCR-CALAMARI",
parameter={
"checkpoint": CHECKPOINT,
"textequiv_level": "word", # Note that we're going down to word level here
}
).process()
workspace.save_mets()
page1 = os.path.join(workspace.directory, "OCR-D-OCR-CALAMARI/OCR-D-OCR-CALAMARI_0001.xml")
assert os.path.exists(page1)
tree = etree.parse(page1)
# The result should contain a TextLine that contains the text "December"
line = tree.xpath(".//pc:TextLine[pc:TextEquiv/pc:Unicode[contains(text(),'December')]]", namespaces=NSMAP)[0]
assert line
# The textline should a. contain multiple words and b. these should concatenate fine to produce the same line text
words = line.xpath(".//pc:Word", namespaces=NSMAP)
assert len(words) >= 2
words_text = " ".join(word.xpath("pc:TextEquiv/pc:Unicode", namespaces=NSMAP)[0].text for word in words)
line_text = line.xpath("pc:TextEquiv/pc:Unicode", namespaces=NSMAP)[0].text
assert words_text == line_text
# For extra measure, check that we're not seeing any glyphs, as we asked for textequiv_level == "word"
glyphs = tree.xpath("//pc:Glyph", namespaces=NSMAP)
assert len(glyphs) == 0
def test_recognize(workspace):
CalamariRecognize(workspace,
input_file_grp="OCR-D-GT-SEG-WORD-GLYPH",
output_file_grp="OCR-D-OCR-CALAMARI",
parameter={
"checkpoint_dir": CHECKPOINT_DIR,
}).process()
workspace.save_mets()
page1 = os.path.join(workspace.directory,
"OCR-D-OCR-CALAMARI/OCR-D-OCR-CALAMARI_0001.xml")
assert os.path.exists(page1)
assertFileContains(page1, "verſchuldeten")
def test_recognize_should_warn_if_given_rgb_image_and_single_channel_model(
workspace, caplog):
caplog.set_level(logging.WARNING)
CalamariRecognize(workspace,
input_file_grp="OCR-D-GT-SEG-WORD-GLYPH",
output_file_grp="OCR-D-OCR-CALAMARI-BROKEN",
parameter={
'checkpoint_dir': CHECKPOINT_DIR
}).process()
interesting_log_messages = [
t[2] for t in caplog.record_tuples if "Using raw image" in t[2]
]
assert len(interesting_log_messages) > 10 # For every line!
def test_recognize(workspace):
CalamariRecognize(
workspace,
input_file_grp="OCR-D-GT-SEG-LINE",
output_file_grp="OCR-D-OCR-CALAMARI",
parameter={
"checkpoint": CHECKPOINT,
}
).process()
workspace.save_mets()
page1 = os.path.join(workspace.directory, "OCR-D-OCR-CALAMARI/OCR-D-OCR-CALAMARI_0001.xml")
assert os.path.exists(page1)
with open(page1, "r", encoding="utf-8") as f:
assert "verſchuldeten" in f.read()
def test_glyphs(workspace):
CalamariRecognize(
workspace,
input_file_grp="OCR-D-GT-SEG-LINE",
output_file_grp="OCR-D-OCR-CALAMARI",
parameter={
"checkpoint": CHECKPOINT,
"textequiv_level": "glyph", # Note that we're going down to glyph level here
}
).process()
workspace.save_mets()
page1 = os.path.join(workspace.directory, "OCR-D-OCR-CALAMARI/OCR-D-OCR-CALAMARI_0001.xml")
assert os.path.exists(page1)
tree = etree.parse(page1)
# The result should contain a lot of glyphs
glyphs = tree.xpath("//pc:Glyph", namespaces=NSMAP)
assert len(glyphs) >= 100