def runTest():
OcrHelper.setMinTextLayer(8)
print("text layer is: " + str(OcrHelper.getMinTextLayer()))
pdf_path = "file:///" + os.getcwd(
) + "/../ocr/src/test/resources/pdfs/"
data = OcrHelper.createDataset(spark=SparkContextForTest.spark,
input_path=pdf_path,
output_col="region",
metadata_col="metadata")
data.show()
OcrHelper.setMinTextLayer(0)
print("Text layer disabled")
data = OcrHelper.createDataset(spark=SparkContextForTest.spark,
input_path=pdf_path,
output_col="region",
metadata_col="metadata")
data.show()
OcrHelper.setMinTextLayer(10)
content = OcrHelper.createMap(
input_path="../ocr/src/test/resources/pdfs")
print(content)
document_assembler = DocumentAssembler() \
.setInputCol("region") \
.setOutputCol("document")
document_assembler.transform(data).show()
def runTest():
data = OcrHelper.createDataset(
spark=SparkContextForTest.spark,
input_path="../ocr/src/test/resources/pdfs/",
output_col="region",
metadata_col="metadata")
data.show()
content = OcrHelper.createMap(
input_path="../ocr/src/test/resources/pdfs/")
print(content)
document_assembler = DocumentAssembler() \
.setInputCol("region") \
.setOutputCol("document")
document_assembler.transform(data).show()
def runTest():
OcrHelper.setPreferredMethod('text')
print("text layer is: " + str(OcrHelper.getPreferredMethod()))
pdf_path = "file:///" + os.getcwd() + "/../ocr/src/test/resources/pdfs/"
data = OcrHelper.createDataset(
spark=SparkContextForTest.spark,
input_path=pdf_path)
data.show()
OcrHelper.setPreferredMethod('image')
print("Text layer disabled")
data = OcrHelper.createDataset(
spark=SparkContextForTest.spark,
input_path=pdf_path)
data.show()
OcrHelper.setPreferredMethod('text')
content = OcrHelper.createMap(input_path="../ocr/src/test/resources/pdfs")
print(content)
document_assembler = DocumentAssembler() \
.setInputCol("text") \
.setOutputCol("document")
document_assembler.transform(data).show()