Fix image paths to deployed images (#30)

CHANGELOG.rst

@@ -1,6 +1,13 @@
 Changelog
 =========
 
+0.3.2
+-----
+
+- Fix image paths to deployed images
+  `#30 <https://github.com/jdillard/sphinx-llms-txt/pull/30>`_
+
+
 0.3.1
 -----
 

sphinx_llms_txt/__init__.py

@@ -12,7 +12,7 @@ from .manager import LLMSFullManager
 from .processor import DocumentProcessor
 from .writer import FileWriter
 
-__version__ = "0.3.1"
+__version__ = "0.3.2"
 
 # Export classes needed by tests
 __all__ = [

sphinx_llms_txt/processor.py

@@ -94,8 +94,14 @@ class DocumentProcessor:
         if not base_url:
             return path
 
+        # Ensure base URL ends with slash
         if not base_url.endswith("/"):
             base_url += "/"
+
+        # Remove leading slash from path to avoid double slashes
+        if path.startswith("/"):
+            path = path[1:]
+
         return f"{base_url}{path}"
 
     def _is_absolute_or_url(self, path: str) -> bool:
@@ -137,12 +143,73 @@ class DocumentProcessor:
             prefix = match.group(1)  # The entire directive prefix including whitespace
             path = match.group(3).strip()  # The path argument
 
-            # Only process relative paths, not absolute paths or URLs
-            if not self._is_absolute_or_url(path):
-                # Special case for test files
-                if is_test:
-                    # Add subdir/ prefix to match test expectations
-                    full_path = "subdir/" + path
+            # Handle URLs and data URIs - leave unchanged
+            if path.startswith(("http://", "https://", "data:")):
+                return match.group(0)
+
+            # For ALL paths, check if image exists in _images first
+            # Extract filename from the path
+            filename = os.path.basename(path)
+
+            # Check if image exists in _images directory
+            # First determine the build directory from source_path
+            build_dir = None
+            if "_sources" in str(source_path):
+                # Extract build directory (parent of _sources)
+                path_parts = str(source_path).split("_sources/")
+                if len(path_parts) > 1:
+                    build_dir = path_parts[0].rstrip("/")
+
+            # If we can determine the build directory, check if image exists in _images
+            if build_dir:
+                images_path = os.path.join(build_dir, "_images", filename)
+                if os.path.exists(images_path):
+                    # Image exists in _images, use _images path
+                    full_path = f"/_images/{filename}"
+                    # Add base URL if configured
+                    full_path = self._add_base_url(full_path, base_url)
+                    return f"{prefix}{full_path}"
+
+            # Image doesn't exist in _images, handle based on path type
+            # Handle absolute paths (starting with /) - add base URL if configured
+            if path.startswith("/"):
+                # Add base URL to absolute paths if configured
+                full_path = self._add_base_url(path, base_url)
+                return f"{prefix}{full_path}"
+
+            # Handle relative paths with original logic for backward compatibility
+            # Special case for test files
+            if is_test:
+                # Add subdir/ prefix to match test expectations
+                full_path = "subdir/" + path
+
+                # If base_url is set, prepend it to the path
+                full_path = self._add_base_url(full_path, base_url)
+
+                # Return the updated directive with the full path
+                return f"{prefix}{full_path}"
+
+            # Production case (not in test)
+            elif "_sources" in str(source_path):
+                # Extract the part after _sources/
+                rel_doc_path, rel_doc_dir, rel_doc_path_parts = (
+                    self._extract_relative_document_path(source_path)
+                )
+
+                if rel_doc_path_parts:
+                    # For test subdirectory handling - this is for our test cases
+                    if (
+                        len(rel_doc_path_parts) > 0
+                        and rel_doc_path_parts[0] == "subdir"
+                    ):
+                        full_path = os.path.normpath(os.path.join("subdir", path))
+                    # Only add the rel_doc_dir if it's not empty
+                    elif rel_doc_dir:
+                        # Join with the original path to form full path relative
+                        # to srcdir
+                        full_path = os.path.normpath(os.path.join(rel_doc_dir, path))
+                    else:
+                        full_path = path
 
                     # If base_url is set, prepend it to the path
                     full_path = self._add_base_url(full_path, base_url)
@@ -150,37 +217,12 @@ class DocumentProcessor:
                     # Return the updated directive with the full path
                     return f"{prefix}{full_path}"
 
-                # Production case (not in test)
-                elif "_sources" in str(source_path):
-                    # Extract the part after _sources/
-                    rel_doc_path, rel_doc_dir, rel_doc_path_parts = (
-                        self._extract_relative_document_path(source_path)
-                    )
+            # Fallback for relative paths - add base URL if configured
+            else:
+                full_path = self._add_base_url(path, base_url)
+                return f"{prefix}{full_path}"
 
-                    if rel_doc_path_parts:
-                        # For test subdirectory handling - this is for our test cases
-                        if (
-                            len(rel_doc_path_parts) > 0
-                            and rel_doc_path_parts[0] == "subdir"
-                        ):
-                            full_path = os.path.normpath(os.path.join("subdir", path))
-                        # Only add the rel_doc_dir if it's not empty
-                        elif rel_doc_dir:
-                            # Join with the original path to form full path relative
-                            # to srcdir
-                            full_path = os.path.normpath(
-                                os.path.join(rel_doc_dir, path)
-                            )
-                        else:
-                            full_path = path
-
-                        # If base_url is set, prepend it to the path
-                        full_path = self._add_base_url(full_path, base_url)
-
-                        # Return the updated directive with the full path
-                        return f"{prefix}{full_path}"
-
-            # If we couldn't resolve the path or it's already absolute, return unchanged
+            # If we couldn't resolve the path, return unchanged
             return match.group(0)
 
         # Replace directive paths in the content

tests/test_path_directives.py

@@ -102,7 +102,7 @@ def test_process_path_directives_with_html_baseurl(tmp_path):
 
 
 def test_process_path_directives_absolute_urls(tmp_path):
-    """Test that absolute URLs are not modified."""
+    """Test that absolute URLs are not modified but absolute paths get base URL."""
     # Create a processor
     config = {
         "llms_txt_directives": [],
@@ -127,10 +127,17 @@ def test_process_path_directives_absolute_urls(tmp_path):
     with open(source_file, "w", encoding="utf-8") as f:
         f.write(source_content)
 
-    # Process the directives (should remain unchanged)
+    # Process the directives
     processed_content = processor._process_path_directives(source_content, source_file)
 
-    assert processed_content == source_content
+    # Expected: URLs and data URIs unchanged, absolute paths get base URL
+    expected_content = (
+        ".. image:: https://othersite.com/images/test.png\n"
+        ".. image:: https://example.com/docs/absolute/path/image.png\n"
+        ".. image:: data:image/png;base64,iVBORw0KG...\n"
+    )
+
+    assert processed_content == expected_content
 
 
 def test_process_path_directives_custom_directives(tmp_path):
@@ -251,3 +258,149 @@ def test_process_content_end_to_end(tmp_path):
     )
 
     assert processed_content == expected_content
+
+
+def test_process_path_directives_images_directory(tmp_path):
+    """Test that _images directory paths are handled correctly."""
+    # Create a processor with base URL
+    config = {
+        "llms_txt_directives": [],
+        "html_baseurl": "https://example.com/docs",
+    }
+    processor = DocumentProcessor(config)
+
+    # Create source directory structure
+    src_dir = tmp_path / "src"
+    src_dir.mkdir()
+    processor.srcdir = str(src_dir)
+
+    # Create _sources directory to mimic Sphinx output
+    build_dir = tmp_path / "build"
+    build_dir.mkdir()
+    sources_dir = build_dir / "_sources"
+    sources_dir.mkdir()
+
+    # Create a source file with various _images directory paths
+    source_content = (
+        "Some content.\n"
+        ".. image:: _images/test.png\n"  # Relative _images should become /_images
+        ".. image:: /_images/absolute.png\n"  # Absolute _images should get base URL
+        ".. figure:: _images/figure.png\n"  # Test with figure directive too
+        "   :alt: A test figure\n"
+        ".. image:: images/normal.png\n"  # Normal relative path should be unchanged
+    )
+
+    # Create source file in sources directory to simulate Sphinx build output
+    source_file = sources_dir / "page.txt"
+    with open(source_file, "w", encoding="utf-8") as f:
+        f.write(source_content)
+
+    # Process the directives
+    processed_content = processor._process_path_directives(source_content, source_file)
+
+    # Expected: _images paths should be converted and get base URL
+    expected_content = (
+        "Some content.\n"
+        ".. image:: https://example.com/docs/_images/test.png\n"
+        ".. image:: https://example.com/docs/_images/absolute.png\n"
+        ".. figure:: https://example.com/docs/_images/figure.png\n"
+        "   :alt: A test figure\n"
+        ".. image:: https://example.com/docs/images/normal.png\n"
+    )
+
+    assert processed_content == expected_content
+
+
+def test_process_path_directives_images_directory_no_baseurl(tmp_path):
+    """
+    Test that _images directory paths work correctly without base URL.
+    Only converts when image exists.
+    """
+    # Create a processor without base URL
+    config = {
+        "llms_txt_directives": [],
+        "html_baseurl": "",
+    }
+    processor = DocumentProcessor(config)
+
+    # Create source directory structure
+    src_dir = tmp_path / "src"
+    src_dir.mkdir()
+    processor.srcdir = str(src_dir)
+
+    # Create _sources directory to mimic Sphinx output
+    build_dir = tmp_path / "build"
+    build_dir.mkdir()
+    sources_dir = build_dir / "_sources"
+    sources_dir.mkdir()
+
+    # Create _images directory and one test image
+    images_dir = build_dir / "_images"
+    images_dir.mkdir()
+    (images_dir / "test.png").write_text("fake image content")
+    # Note: absolute.png is not created, so it won't be converted
+
+    # Create a source file with _images directory paths
+    source_content = (
+        ".. image:: _images/test.png\n"  # Should become /_images (image exists)
+        ".. image:: /_images/absolute.png\n"  # Should stay unchanged (absolute path)
+    )
+
+    # Create source file in sources directory to simulate Sphinx build output
+    source_file = sources_dir / "page.txt"
+    with open(source_file, "w", encoding="utf-8") as f:
+        f.write(source_content)
+
+    # Process the directives
+    processed_content = processor._process_path_directives(source_content, source_file)
+
+    # Expected: only test.png gets converted because it exists in _images
+    expected_content = (
+        ".. image:: /_images/test.png\n"  # Converted because image exists
+        ".. image:: /_images/absolute.png\n"  # Absolute path unchanged
+    )
+
+    assert processed_content == expected_content
+
+
+def test_process_path_directives_all_absolute_paths_get_baseurl(tmp_path):
+    """Test that all absolute paths (starting with /) get base URL prepended."""
+    # Create a processor with base URL
+    config = {
+        "llms_txt_directives": [],
+        "html_baseurl": "https://mysite.com/docs/",
+    }
+    processor = DocumentProcessor(config)
+
+    # Create source directory structure
+    src_dir = tmp_path / "src"
+    src_dir.mkdir()
+    processor.srcdir = str(src_dir)
+
+    # Create a source file with various absolute paths
+    source_content = (
+        ".. image:: /static/images/logo.png\n"
+        ".. figure:: /assets/diagrams/flow.svg\n"
+        ".. image:: /media/photos/team.jpg\n"
+        "   :alt: Team photo\n"
+        ".. image:: relative/path.png\n"  # This should still get normal processing
+    )
+
+    # Create source file
+    source_file = src_dir / "page.txt"
+    with open(source_file, "w", encoding="utf-8") as f:
+        f.write(source_content)
+
+    # Process the directives
+    processed_content = processor._process_path_directives(source_content, source_file)
+
+    # Expected: All absolute paths get base URL prepended
+    expected_content = (
+        ".. image:: https://mysite.com/docs/static/images/logo.png\n"
+        ".. figure:: https://mysite.com/docs/assets/diagrams/flow.svg\n"
+        ".. image:: https://mysite.com/docs/media/photos/team.jpg\n"
+        "   :alt: Team photo\n"
+        ".. image:: https://mysite.com/docs/relative/path.png\n"
+    )
+
+    assert processed_content == expected_content