Add more tests

README.md

@@ -1,8 +1,8 @@
 # Marker
 
-Marker converts PDFs and images to markdown, JSON, and HTML quickly and accurately.
+Marker converts documents to markdown, JSON, and HTML quickly and accurately.
 
-- Supports a range of documents in all languages
+- Converts PDF, image, PPTX, DOCX, XLSX, HTML, EPUB in all languages
 - Formats tables, forms, equations, inline math, links, references, and code blocks
 - Extracts and saves images
 - Removes headers/footers/other artifacts
@@ -320,6 +320,7 @@ When running with the `--use_llm` flag, you have a choice of services you can us
 - `Gemini` - this will use the Gemini developer API by default.  You'll need to pass `--gemini_api_key` to configuration.
 - `Google Vertex` - this will use vertex, which can be more reliable.  You'll need to pass `--vertex_project_id`.  To use it, set `--llm_service=marker.services.vertex.GoogleVertexService`.
 - `Ollama` - this will use local models.  You can configure `--ollama_base_url` and `--ollama_model`. To use it, set `--llm_service=marker.services.ollama.OllamaService`.
+- `Claude` - this will use the anthropic API.  You can configure `--claude_api_key`, and `--claude_model_name`.  To use it, set `--llm_service=marker.services.claude.ClaudeService`.
 
 These services may have additional optional configuration as well - you can see it by viewing the classes.
 

tests/converters/test_pdf_converter.py

@@ -20,3 +20,51 @@ def test_pdf_converter(pdf_converter: PdfConverter, temp_doc):
     # Some assertions for line joining across columns
     assert "remain similar across a wide range of choices." in markdown  # pg: 2
     assert "a new scheme for designing more robust and efficient" in markdown  # pg: 8
+
+@pytest.mark.filename("manual.epub")
+@pytest.mark.config({"page_range": [0]})
+def test_epub_converter(pdf_converter: PdfConverter, temp_doc):
+    markdown_output: MarkdownOutput = pdf_converter(temp_doc.name)
+    markdown = markdown_output.markdown
+
+    # Basic assertions
+    assert "Simple Sabotage Field Manual" in markdown
+
+@pytest.mark.filename("single_sheet.xlsx")
+@pytest.mark.config({"page_range": [0]})
+def test_xlsx_converter(pdf_converter: PdfConverter, temp_doc):
+    markdown_output: MarkdownOutput = pdf_converter(temp_doc.name)
+    markdown = markdown_output.markdown
+
+    # Basic assertions
+    assert "four" in markdown
+
+
+@pytest.mark.filename("china.html")
+@pytest.mark.config({"page_range": [10]})
+def test_html_converter(pdf_converter: PdfConverter, temp_doc):
+    markdown_output: MarkdownOutput = pdf_converter(temp_doc.name)
+    markdown = markdown_output.markdown
+
+    # Basic assertions
+    assert "Beijing" in markdown
+
+
+@pytest.mark.filename("gatsby.docx")
+@pytest.mark.config({"page_range": [0]})
+def test_docx_converter(pdf_converter: PdfConverter, temp_doc):
+    markdown_output: MarkdownOutput = pdf_converter(temp_doc.name)
+    markdown = markdown_output.markdown
+
+    # Basic assertions
+    assert "The Decline of the American Dream in the 1920s" in markdown
+
+
+@pytest.mark.filename("lambda.pptx")
+@pytest.mark.config({"page_range": [0]})
+def test_pptx_converter(pdf_converter: PdfConverter, temp_doc):
+    markdown_output: MarkdownOutput = pdf_converter(temp_doc.name)
+    markdown = markdown_output.markdown
+
+    # Basic assertions
+    assert "Adam Doupé" in markdown