Added pdf & epub parsing

spec/EbookParserTest.py

@@ -0,0 +1,13 @@
+from unittest import TestCase
+from parsing import EbookParser
+
+
+class EbookParserTest(TestCase):
+
+    def test_parse_content(self):
+
+        parser = EbookParser([], 1000)
+
+        info = parser.parse("test_files/epub1.epub")
+
+        self.assertEqual(len(info["content"]), 1000)

spec/FontParser_spec.py

@@ -10,7 +10,7 @@ class FontParserTest(TestCase):
 
         info = parser.parse("test_files/truetype1.ttf")
 
-        self.assertEqual(info["font_name"], "Liberation Mono Bold")
+        self.assertEqual(info["content"], "Liberation Mono Bold")
 
     def test_parse_name_openType(self):
 
@@ -18,7 +18,7 @@ class FontParserTest(TestCase):
 
         info = parser.parse("test_files/opentype1.otf")
 
-        self.assertEqual(info["font_name"], "Linux Biolinum Keyboard O")
+        self.assertEqual(info["content"], "Linux Biolinum Keyboard O")
 
     def test_parse_name_woff(self):
 
@@ -26,7 +26,7 @@ class FontParserTest(TestCase):
 
         info = parser.parse("test_files/woff.woff")
 
-        self.assertEqual(info["font_name"], "Heart of Gold")
+        self.assertEqual(info["content"], "Heart of Gold")
 
     def test_parse_name_woff2(self):
 
@@ -34,4 +34,4 @@ class FontParserTest(TestCase):
 
         info = parser.parse("test_files/woff2.woff2")
 
-        self.assertEqual(info["font_name"], "Heart of Gold")
+        self.assertEqual(info["content"], "Heart of Gold")

spec/PdfFileParser.py

@@ -0,0 +1,14 @@
+from unittest import TestCase
+from parsing import PdfFileParser
+
+
+class PdfParserTest(TestCase):
+
+    def test_parse_content(self):
+
+        parser = PdfFileParser([], 12488)
+
+        info = parser.parse("test_files/pdf1.pdf")
+
+        self.assertEqual(len(info["content"]), 12488)
+        self.assertTrue(info["content"].startswith("Rabies\n03/11/2011\nRabies"))