Counting the number of unique applications, tutorials, ... (#702)

* Counting the number of unique applications, tutorials, ... * Fix lint Signed-off-by: Julien Jomier <[email protected]> * Update README to link to searchable HoloHub component catalog instead of badges Signed-off-by: Julien Jomier <[email protected]> --------- Signed-off-by: Julien Jomier <[email protected]>
nvidia-holoscan · Feb 24, 2025 · 6e4e377 · 6e4e377
1 parent 9f67b0f
commit 6e4e377
Show file tree

Hide file tree

Showing 2 changed files with 22 additions and 22 deletions.
diff --git a/README.md b/README.md
@@ -5,9 +5,7 @@
 ![Metadata](https://img.shields.io/github/actions/workflow/status/nvidia-holoscan/holohub/check_metadata.yml?branch=main&label=Metadata
 )
 
-[![Applications](https://img.shields.io/badge/Applications-91-59A700)](https://github.com/nvidia-holoscan/holohub/tree/main/applications)
-[![Operators](https://img.shields.io/badge/Operators-42-59A700)](https://github.com/nvidia-holoscan/holohub/tree/main/operators)
-[![Tutorials](https://img.shields.io/badge/Tutorials-12-59A700)](https://github.com/nvidia-holoscan/holohub/tree/main/tutorials)
+Visit [https://nvidia-holoscan.github.io/holohub](https://nvidia-holoscan.github.io/holohub) for a searchable catalog of all available components.
 
 This is a central repository for the NVIDIA Holoscan AI sensor processing community to share reference applications, operators, tutorials and benchmarks. We invite users and developers of the Holoscan platform to reuse and contribute to this repository.
 

diff --git a/doc/website/scripts/generate_pages.py b/doc/website/scripts/generate_pages.py
@@ -74,31 +74,34 @@ def parse_metadata_file(metadata_file: Path, statistics) -> None:
     # Read the file
     # Parse the JSON data
     with open(metadata_file, "r") as metadatafile:
-        print(metadatafile)
         metadata = json.load(metadatafile)
         key = list(metadata.keys())[0]
         dest_dir = str(key) + "s"
 
-    # Extract the application name
+    # Extract the application name, removing cpp/python from the path for counting
     if dest_dir == "applications":
         path = re.sub(r".*/applications/", "", str(metadata_file)).removesuffix("/metadata.json")
-        statistics["applications"] += 1
+        base_path = re.sub(r"/(cpp|python)$", "", path)
+        statistics["unique_applications"].add(base_path)
     elif dest_dir == "workflows":
         path = re.sub(r".*/workflows/", "", str(metadata_file)).removesuffix("/metadata.json")
-        statistics["workflows"] += 1
-    # For operators we put a flat list
+        base_path = re.sub(r"/(cpp|python)$", "", path)
+        statistics["unique_workflows"].add(base_path)
     elif dest_dir == "operators":
         path = str(metadata_file).removesuffix("/metadata.json")
         path = path.split("/")[-1]
-        statistics["operators"] += 1
+        base_path = re.sub(r"/(cpp|python)$", "", path)
+        statistics["unique_operators"].add(base_path)
     elif dest_dir == "tutorials":
         path = str(metadata_file).removesuffix("/metadata.json")
         path = path.split("/")[-1]
-        statistics["tutorials"] += 1
+        base_path = re.sub(r"/(cpp|python)$", "", path)
+        statistics["unique_tutorials"].add(base_path)
     elif dest_dir == "benchmarks":
         path = str(metadata_file).removesuffix("/metadata.json")
         path = path.split("/")[-1]
-        statistics["benchmarks"] += 1
+        base_path = re.sub(r"/(cpp|python)$", "", path)
+        statistics["unique_benchmarks"].add(base_path)
     else:
         logger.error(f"Don't know the output path for: {dest_dir}")
         return
@@ -178,7 +181,6 @@ def parse_metadata_file(metadata_file: Path, statistics) -> None:
                     imgmatch = match[1:]
                 if imgmatch.startswith("/"):
                     imgmatch = imgmatch[1:]
-                logger.info(f"TEST: {match} = {imgmatch}")
                 readme_text = readme_text.replace(
                     match,
                     "https://github.com/nvidia-holoscan/holohub/blob/main/"
@@ -261,11 +263,11 @@ def generate_pages() -> None:
     root = Path(__file__).parent.parent.parent.parent
 
     statistics = {
-        "operators": 0,
-        "tutorials": 0,
-        "applications": 0,
-        "workflows": 0,
-        "benchmarks": 0,
+        "unique_operators": set(),
+        "unique_tutorials": set(),
+        "unique_applications": set(),
+        "unique_workflows": set(),
+        "unique_benchmarks": set(),
     }
 
     logger.info(f"root: {root}")
@@ -279,11 +281,11 @@ def generate_pages() -> None:
     homefile_path = str(Path(__file__).parent.parent) + "/docs/index.md"
     with open(homefile_path, "r") as home_file:
         home_text = home_file.read()
-        home_text = home_text.replace("#operators", str(statistics["operators"]))
-        home_text = home_text.replace("#tutorials", str(statistics["tutorials"]))
-        home_text = home_text.replace("#applications", str(statistics["applications"]))
-        home_text = home_text.replace("#workflows", str(statistics["workflows"]))
-        home_text = home_text.replace("#benchmarks", str(statistics["benchmarks"]))
+        home_text = home_text.replace("#operators", str(len(statistics["unique_operators"])))
+        home_text = home_text.replace("#tutorials", str(len(statistics["unique_tutorials"])))
+        home_text = home_text.replace("#applications", str(len(statistics["unique_applications"])))
+        home_text = home_text.replace("#workflows", str(len(statistics["unique_workflows"])))
+        home_text = home_text.replace("#benchmarks", str(len(statistics["unique_benchmarks"])))
 
     with mkdocs_gen_files.open("index.md", "w") as fd:
         fd.write(home_text)