Allow exclusions when extracting example code

docs/CMakeLists.txt

@@ -2,7 +2,6 @@ project(msft_proxy_docs)
 
 find_package(Python3 REQUIRED COMPONENTS Interpreter)
 
-file(GLOB_RECURSE DOC_FILES "*.md")
 set(EXTRACTION_SCRIPT ${CMAKE_SOURCE_DIR}/tools/extract_example_code_from_docs.py)
 set(EXAMPLES_DIR ${CMAKE_BINARY_DIR}/examples_from_docs)
 file(MAKE_DIRECTORY "${EXAMPLES_DIR}")

tools/extract_example_code_from_docs.py

@@ -1,42 +1,63 @@
 import os
 import re
 import sys
-
-def extract_cpp_code(md_path, cpp_path):
-    with open(md_path, 'r', encoding='utf-8') as f:
+from typing import Set
+
+def extract_cpp_code(input_dir: str, output_dir: str, md_rel_path: str) -> None:
+    """
+    Extract every C++ code block that immediately follows a '## Example'
+    header in *input_dir/md_rel_path*.
+
+    • If exactly one block is found, create:
+        example_<rel_path_no_ext>.cpp
+    • If multiple blocks are found, create:
+        example_<rel_path_no_ext>_1.cpp, _2.cpp, …
+
+    Directory separators in *md_rel_path* are replaced by '_' so the output
+    lives flat inside *output_dir*.
+    """
+    md_path = os.path.join(input_dir, md_rel_path)
+    with open(md_path, "r", encoding="utf-8") as f:
         content = f.read()
 
     pattern = r'## Example\r?\n\r?\n```cpp\r?\n(.*?)\r?\n```'
     code_blocks = re.findall(pattern, content, re.DOTALL)
-
     if len(code_blocks) == 0:
         return  # No match, skip
-    elif len(code_blocks) > 1:
-        raise ValueError(f"File '{md_path}' contains more than one '## Example' C++ code block.")
 
-    cpp_code = code_blocks[0]
-    header = f"// This file was auto-generated from: {md_path}\n// Do not edit this file manually.\n\n"
+    rel_base = os.path.splitext(md_rel_path)[0].replace(os.sep, '_')
+    if len(code_blocks) == 1:
+        targets = [os.path.join(output_dir, f"example_{rel_base}.cpp")]
+    else:
+        targets = [
+            os.path.join(output_dir, f"example_{rel_base}_{i}.cpp")
+            for i in range(1, len(code_blocks) + 1)
+        ]
 
-    with open(cpp_path, 'w', encoding='utf-8') as out:
-        out.write(header)
-        out.write(cpp_code)
+    header = f"// This file was auto-generated from: {md_path}\n// Do not edit this file manually.\n\n"
+    for cpp_path, cpp_code in zip(targets, code_blocks):
+        with open(cpp_path, "w", encoding="utf-8") as out:
+            out.write(header)
+            out.write(cpp_code)
 
 def main():
-    if len(sys.argv) != 3:
-        print("Usage: python extract_example_code_from_docs.py <input_dir> <output_dir>")
+    if len(sys.argv) < 3:
+        print("Usage: python extract_example_code_from_docs.py <input_dir> <output_dir> [exclusion ...]")
         sys.exit(1)
 
     input_dir = sys.argv[1]
     output_dir = sys.argv[2]
+    exclusions: Set[str] = {os.path.normpath(p) for p in sys.argv[3:]}
 
     for root, _, files in os.walk(input_dir):
         for file in files:
-            if file.endswith('.md'):
-                md_path = os.path.join(root, file)
-                rel_path = os.path.relpath(md_path, input_dir)
-                rel_base = os.path.splitext(rel_path)[0].replace(os.sep, '_')
-                cpp_path = os.path.join(output_dir, f"example_{rel_base}.cpp")
-                extract_cpp_code(md_path, cpp_path)
+            if not file.endswith('.md'):
+                continue
+            md_path = os.path.join(root, file)
+            rel_path = os.path.relpath(md_path, input_dir)
+            if rel_path in exclusions:
+                continue
+            extract_cpp_code(input_dir, output_dir, rel_path)
 
 if __name__ == '__main__':
     main()