Revert "Workaround and test for #56 and euske/pdfminer#118"

This reverts commit 7c31351.

src/textcode/pdf.py

@@ -27,35 +27,30 @@
 import contextlib
 from StringIO import StringIO
 
-from pdfminer.converter import TextConverter
-from pdfminer.layout import LAParams
-from pdfminer.pdfdocument import PDFDocument
 from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
 from pdfminer.pdfpage import PDFPage
 from pdfminer.pdfparser import PDFParser
-from pdfminer.pdftypes import PDFException
-
+from pdfminer.pdfdocument import PDFDocument
+from pdfminer.converter import TextConverter
+from pdfminer.layout import LAParams
 
+"""
+Extracts text from a pdf file.
+"""
 
 def get_text_lines(location):
-    """
-    Return a list of text lines extracted from a pdf file at location.
-    """
     extracted_text = StringIO()
     laparams = LAParams()
     with open(location, 'rb') as pdf_file:
-        try:
-            with contextlib.closing(PDFParser(pdf_file)) as parser:
-                document = PDFDocument(parser)
-                manager = PDFResourceManager()
-                with contextlib.closing(TextConverter(manager, extracted_text,
-                                                      laparams=laparams)) as extractor:
-                    interpreter = PDFPageInterpreter(manager, extractor)
-                    pages = PDFPage.create_pages(document)
-                    for page in pages:
-                        interpreter.process_page(page)
-                    extracted_text.seek(0)
-                    lines = extracted_text.readlines()
-        except PDFException:
-            return []
+        with contextlib.closing(PDFParser(pdf_file)) as parser:
+            document = PDFDocument(parser)
+            manager = PDFResourceManager()
+            with contextlib.closing(TextConverter(manager, extracted_text,
+                                                  laparams=laparams)) as extractor:
+                interpreter = PDFPageInterpreter(manager, extractor)
+                pages = PDFPage.create_pages(document)
+                for page in pages:
+                    interpreter.process_page(page)
+                extracted_text.seek(0)
+                lines = extracted_text.readlines()
     return lines

tests/textcode/test_pdf.py

@@ -64,23 +64,3 @@ def get_text(location):
 \x0c'''.splitlines(True)
 
         self.assertEqual(expected, result)
-
-    def test_pdfminer_cant_parse_faulty_broadcom_doc(self):
-        # test for https://github.com/euske/pdfminer/issues/118
-        test_file = self.get_test_loc('pdf/pdfminer_bug_118/faulty.pdf')
-        from pdfminer.pdfparser import PDFParser
-        from pdfminer.pdfdocument import PDFDocument
-        from pdfminer.pdfdocument import PDFEncryptionError
-        with open(test_file,'rb') as inputfile:
-            parser=PDFParser(inputfile)
-            try:
-                PDFDocument(parser)
-            except PDFEncryptionError:
-                #this should not fail of course, and will when upstream is fixed
-                pass
-
-    def test_get_text_lines_skip_parse_faulty_broadcom_doc(self):
-        # test for 
-        test_file = self.get_test_loc('pdf/pdfminer_bug_118/faulty.pdf')
-        result = pdf.get_text_lines(test_file)
-        assert [] == result