From 607dc4605f0a81540dcc648ef94a5093bc86790b Mon Sep 17 00:00:00 2001
From: Robert Haase <haesleinhuepf@users.noreply.github.com>
Date: Thu, 10 Oct 2024 20:51:30 +0200
Subject: [PATCH] conditional hints for bia-bob depending on what's installed

---
 .../_bia_bob_plugins.py                       | 57 ++++++++++++-------
 1 file changed, 37 insertions(+), 20 deletions(-)

diff --git a/napari_segment_blobs_and_things_with_membranes/_bia_bob_plugins.py b/napari_segment_blobs_and_things_with_membranes/_bia_bob_plugins.py
index 85e6bc6..e186ba7 100644
--- a/napari_segment_blobs_and_things_with_membranes/_bia_bob_plugins.py
+++ b/napari_segment_blobs_and_things_with_membranes/_bia_bob_plugins.py
@@ -1,25 +1,25 @@
 def list_bia_bob_plugins():
     """List of function hints for bia_bob"""
-    return """    ## napari-segment-blobs-and-things-with-membranes (nsbatwm)
-    nsbatwm is a Python library that processes images, mostly using the scikit-image library, but with simpler access.
-    When you use it, you always start by importing the library: `import napari_segment_blobs_and_things_with_membranes as nsbatwm`.
-    When asked for how to use nsbatwm, you can adapt one of the following code snippets:
-  
-    * Splits touching objects in a binary image using an algorithm similar to the ImageJ watershed.
-      nsbatwm.split_touching_objects(binary_image)
-   
+    try:
+        import pyclesperanto
+        good_alternative_installed = True
+    except:
+        pass
+    try:
+        import pyclesperanto_prototype
+        good_alternative_installed = True
+    except:
+        pass
+
+    if not good_alternative_installed:
+        basic_hints = """
+    
     * Applies Otsu's method to binarize an intensity image (also works with yen, isodata, li, mean, minimum, triangle instead of otsu).
       nsbatwm.threshold_otsu(image)
-      
-    * Labels connected components in a binary image.
-      nsbatwm.connected_component_labeling(binary_image)
-      
-    * Applies seeded watershed segmentation using labeled objects, e.g. nuclei, and an image showing bright borders between objects such as cell membranes.
-      nsbatwm.seeded_watershed(image, labeled_objects)
-      
+    
     * Segments blob-like structures using Voronoi-Otsu labeling.
       nsbatwm.voronoi_otsu_labeling(image, spot_sigma=4, outline_sigma=1)
-     
+    
     * Applies a Gaussian blur for noise reduction.
       nsbatwm.gaussian_blur(image, sigma=5)
       
@@ -28,9 +28,6 @@ def list_bia_bob_plugins():
       
     * Smooth a label image using a local most popular intensity (mode) filter.
       nsbatwm.mode_filter(labels)
-      
-    * Applies a percentile filter.
-      nsbatwm.percentile_filter(image)
     
     * Removes background in an image using the top-hat filter.
       nsbatwm.white_tophat(image)
@@ -46,10 +43,30 @@ def list_bia_bob_plugins():
     
     * Expands labels by a specified distance.
       nsbatwm.expand_labels(label_image, distance=2)
+    """
+
+    return f"""    ## napari-segment-blobs-and-things-with-membranes (nsbatwm)
+    nsbatwm is a Python library that processes images, mostly using the scikit-image library, but with simpler access.
+    When you use it, you always start by importing the library: `import napari_segment_blobs_and_things_with_membranes as nsbatwm`.
+    When asked for how to use nsbatwm, you can adapt one of the following code snippets:
+    
+    {basic_hints}
+  
+    * Splits touching objects in a binary image using an algorithm similar to the ImageJ watershed.
+      nsbatwm.split_touching_objects(binary_image)
+      
+    * Labels connected components in a binary image.
+      nsbatwm.connected_component_labeling(binary_image)
+      
+    * Applies seeded watershed segmentation using labeled objects, e.g. nuclei, and an image showing bright borders between objects such as cell membranes.
+      nsbatwm.seeded_watershed(image, labeled_objects)
+      
+    * Applies a percentile filter.
+      nsbatwm.percentile_filter(image)
     
     * Segments using seeded watershed with local minima as seeds.
       nsbatwm.local_minima_seeded_watershed(image, spot_sigma=10, outline_sigma=2)
     
     * Skeletonizes labeled objects.
       nsbatwm.skeletonize(image)
-"""
\ No newline at end of file
+    """
\ No newline at end of file