ImportDocuments - Replace pdfminer3k with pypdf

orangecontrib/text/import_documents.py

@@ -25,10 +25,7 @@
 from Orange.data.util import get_unique_names
 from Orange.misc.utils.embedder_utils import get_proxies
 from Orange.util import Registry, dummy_callback
-from pdfminer.converter import PDFPageAggregator
-from pdfminer.layout import LAParams, LTTextBox, LTTextLine
-from pdfminer.pdfinterp import PDFPageInterpreter, PDFResourceManager
-from pdfminer.pdfparser import PDFDocument, PDFParser
+from pypdf import PdfReader as PyPDFReader
 from requests.exceptions import ConnectionError
 
 from orangecontrib.text.corpus import Corpus
@@ -130,28 +127,9 @@ class PdfReader(Reader):
     ext = [".pdf"]
 
     def read_file(self):
-        with open(self.path, 'rb') as f:
-            parser = PDFParser(f)
-        doc = PDFDocument()
-        parser.set_document(doc)
-        doc.set_parser(parser)
-        doc.initialize('')
-        rsrcmgr = PDFResourceManager()
-        laparams = LAParams()
-        laparams.char_margin = 0.1
-        laparams.word_margin = 1.0
-        device = PDFPageAggregator(rsrcmgr, laparams=laparams)
-        interpreter = PDFPageInterpreter(rsrcmgr, device)
-        extracted_text = []
-
-        for page in doc.get_pages():
-            interpreter.process_page(page)
-            layout = device.get_result()
-            for lt_obj in layout:
-                if isinstance(lt_obj, LTTextBox) or isinstance(lt_obj,
-                                                               LTTextLine):
-                    extracted_text.append(lt_obj.get_text())
-        self.content = ' '.join(extracted_text).replace('\x00', '')
+        reader = PyPDFReader(self.path)
+        texts = [page.extract_text() for page in reader.pages]
+        self.content = " ".join(texts)
 
 
 class XmlReader(Reader):

orangecontrib/text/tests/test_import_documents.py

@@ -16,6 +16,7 @@
     TxtReader,
     TextData,
     XmlReader,
+    PdfReader,
 )
 
 
@@ -296,5 +297,36 @@ def test_error(self):
         os.remove(fp.name)
 
 
+DATA_PATH = os.path.join(os.path.dirname(__file__), "data", "documents")
+
+
+class TestPdfReader(unittest.TestCase):
+    def test_file(self):
+        reader = PdfReader(os.path.join(DATA_PATH, "good", "minimal-document.pdf"))
+        res = reader.read()[0]
+        exp = (
+            "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam "
+            "nonumy eirmod"
+        )
+        self.assertTrue(res.content.startswith(exp))
+
+        path = os.path.join(DATA_PATH, "good", "sample_pdf.pdf")
+        reader = PdfReader(path)
+        res = reader.read()[0]
+        self.assertEqual("This is a test pdf file", res.content)
+        self.assertEqual("sample_pdf", res.name)
+        self.assertEqual(os.path.join(path), res.path)
+        self.assertListEqual([".pdf"], res.ext)
+        self.assertEqual("good", res.category)
+
+    def test_error(self):
+        reader = PdfReader(
+            os.path.join(DATA_PATH, "corrupted", "sample_pdf_corrupted.pdf")
+        )
+        res = reader.read()
+        self.assertIsNone(res[0])
+        self.assertEqual("sample_pdf_corrupted.pdf", res[1])
+
+
 if __name__ == "__main__":
     unittest.main()

requirements.txt

@@ -15,7 +15,7 @@ orange-widget-base >=4.20.0
 orange-canvas-core
 owlready2
 pandas
-pdfminer3k>=1.3.1
+pypdf
 pyqtgraph
 pyyaml
 requests