improved pdfcreator

1- use CLI
2- refactor code

python/pdfcreator/tests.py

@@ -0,0 +1,128 @@
+import unittest
+from pypdf import PdfWriter, PageObject
+from types import SimpleNamespace
+from pdfaggregator import parse_inputs, strip_numbering, crop_page, extract_page_range, extract_section_prefix, parse_page_range, find_section_with_level, find_end_page
+
+
+class TestPdfExtractionFunctions(unittest.TestCase):
+    def setUp(self):
+        # Dummy PDF with 5 blank pages
+        self.writer = PdfWriter()
+        for _ in range(5):
+            self.writer.add_page(
+                PageObject.create_blank_page(width=600, height=800))
+        self.reader = self.writer  # pypdf writer can be used as reader for pages list
+        self.content_writer = PdfWriter()
+        self.outline_tree = [{"title": "Section1", "page": 0, "children": [
+            {"title": "Section1.1", "page": 1, "children": []}]}]
+
+    def test_extract_page_range(self):
+        current_page, REFERENCE_BOX, toc = extract_page_range(
+            "@1-3", self.reader, self.content_writer, 0, None)
+        self.assertEqual(len(self.content_writer.pages), 3)  # pages 0 and 1
+        self.assertEqual(toc["title"], "Pages 1-3")
+        self.assertEqual(current_page, 3)
+
+    def test_extract_section_prefix(self):
+        current_page, REFERENCE_BOX, toc = extract_section_prefix(
+            "Section1", self.reader, self.content_writer, 0, None, self.outline_tree)
+        self.assertEqual(len(self.content_writer.pages),
+                         5)  # page 0 + subsection 1
+        self.assertEqual(toc["title"], "Section1")
+        self.assertEqual(current_page, 5)
+
+
+class TestPdfAggregator(unittest.TestCase):
+
+    def test_parse_page_range(self):
+        self.assertEqual(parse_page_range("@1-5"), [0, 1, 2, 3, 4])
+        self.assertEqual(parse_page_range("@10-12"), [9, 10, 11])
+        self.assertIsNone(parse_page_range("1.3"))
+        self.assertIsNone(parse_page_range("Introduction-Overview"))
+
+    def test_strip_numbering(self):
+        self.assertEqual(strip_numbering("1.3 Background"), "Background")
+        self.assertEqual(strip_numbering(
+            "2.1.5 Experimental Setup"), "Experimental Setup")
+        self.assertEqual(strip_numbering("NoNumberingHere"), "NoNumberingHere")
+
+    def test_crop_page(self):
+        page = PageObject.create_blank_page(width=600, height=800)
+        crop_page(page, top_ratio=0.1, bottom_ratio=0.05)
+        llx, lly = page.cropbox.lower_left
+        urx, ury = page.cropbox.upper_right
+        self.assertAlmostEqual(ury - lly, 800 * 0.85)
+
+
+class TestParseInputs(unittest.TestCase):
+
+    def test_single_pdf_single_section(self):
+        args = SimpleNamespace(
+            inputs=["doc1.pdf:1.3"]
+        )
+
+        result = parse_inputs(args)
+
+        self.assertEqual(result, [
+            {
+                "file": "doc1.pdf",
+                "sections": ["1.3"]
+            }
+        ])
+
+    def test_single_pdf_multiple_sections(self):
+        args = SimpleNamespace(
+            inputs=["doc1.pdf:1.3,2.1,@10-20"]
+        )
+
+        result = parse_inputs(args)
+
+        self.assertEqual(result, [
+            {
+                "file": "doc1.pdf",
+                "sections": ["1.3", "2.1", "@10-20"]
+            }
+        ])
+
+    def test_multiple_pdfs(self):
+        args = SimpleNamespace(
+            inputs=[
+                "doc1.pdf:1.3,@5-10",
+                "doc2.pdf:Introduction,3.2"
+            ]
+        )
+
+        result = parse_inputs(args)
+
+        self.assertEqual(result, [
+            {
+                "file": "doc1.pdf",
+                "sections": ["1.3", "@5-10"]
+            },
+            {
+                "file": "doc2.pdf",
+                "sections": ["Introduction", "3.2"]
+            }
+        ])
+
+    def test_whitespace_is_trimmed(self):
+        args = SimpleNamespace(
+            inputs=["doc1.pdf: 1.3 , @5-10 , Introduction "]
+        )
+
+        result = parse_inputs(args)
+
+        self.assertEqual(result[0]["sections"], [
+                         "1.3", "@5-10", "Introduction"])
+
+    def test_missing_colon_raises_error(self):
+        args = SimpleNamespace(
+            inputs=["doc1.pdf"]
+        )
+
+        with self.assertRaises(ValueError):
+            parse_inputs(args)
+
+
+if __name__ == "__main__":
+    unittest.main()