Replace Hugo shortcodes in OpenAPI output (#2088)

Signed-off-by: Kévin Commaille <[email protected]>

Author: zecakeh

.github/workflows/main.yml

@@ -2,6 +2,7 @@ name: "Spec"
 
 env:
   HUGO_VERSION: 0.139.0
+  PYTHON_VERSION: 3.13
 
 on:
   push:
@@ -40,7 +41,7 @@ jobs:
       - name: "➕ Setup Python"
         uses: actions/setup-python@v5
         with:
-          python-version: '3.9'
+          python-version: ${{ env.PYTHON_VERSION }}
           cache: 'pip'
           cache-dependency-path: scripts/requirements.txt
       - name: "➕ Install dependencies"
@@ -59,7 +60,7 @@ jobs:
       - name: "➕ Setup Python"
         uses: actions/setup-python@v5
         with:
-          python-version: '3.9'
+          python-version: ${{ env.PYTHON_VERSION }}
           cache: 'pip'
           cache-dependency-path: scripts/requirements.txt
       - name: "➕ Install dependencies"
@@ -78,7 +79,7 @@ jobs:
       - name: "➕ Setup Python"
         uses: actions/setup-python@v5
         with:
-          python-version: '3.9'
+          python-version: ${{ env.PYTHON_VERSION }}
           cache: 'pip'
           cache-dependency-path: scripts/requirements.txt
       - name: "➕ Install dependencies"
@@ -120,7 +121,7 @@ jobs:
       - name: "➕ Setup Python"
         uses: actions/setup-python@v5
         with:
-          python-version: '3.9'
+          python-version: ${{ env.PYTHON_VERSION }}
           cache: 'pip'
           cache-dependency-path: scripts/requirements.txt
       - name: "➕ Install dependencies"
@@ -172,7 +173,7 @@ jobs:
       - name: "➕ Setup Python"
         uses: actions/setup-python@v5
         with:
-          python-version: '3.9'
+          python-version: ${{ env.PYTHON_VERSION }}
       - name: "➕ Install towncrier"
         run: "pip install 'towncrier'"
       - name: "Generate changelog"

changelogs/internal/newsfragments/2088.clarification

@@ -0,0 +1 @@
+Replace Hugo shortcodes in OpenAPI output.

scripts/dump-openapi.py

@@ -32,6 +32,35 @@
 scripts_dir = os.path.dirname(os.path.abspath(__file__))
 api_dir = os.path.join(os.path.dirname(scripts_dir), "data", "api")
 
+# Finds a Hugo shortcode in a string.
+#
+# A shortcode is defined as (newlines and whitespaces for presentation purpose):
+#
+# {{%
+#     <zero or more whitespaces>
+#     <name of shortcode>
+#     (optional <one or more whitespaces><list of parameters>)
+#     <zero or more whitespaces>
+# %}}
+#
+# With:
+#
+# * <name of shortcode>: any word character and `-` and `/`. `re.ASCII` is used to only match
+#   ASCII characters in the name.
+# * <list of parameters>: any character except `}`, must not start or end with a
+#   whitespace.
+shortcode_regex = re.compile(r"""\{\{\%                                   # {{%
+                                 \s*                                      # zero or more whitespaces
+                                 (?P<name>[\w/-]+)                        # name of shortcode
+                                 (?:\s+(?P<params>[^\s\}][^\}]+[^\s\}]))? # optional list of parameters
+                                 \s*                                      # zero or more whitespaces
+                                 \%\}\}                                   # %}}""", re.ASCII | re.VERBOSE)
+
+# Parses the parameters of a Hugo shortcode.
+#
+# For simplicity, this currently only supports the `key="value"` format.
+shortcode_params_regex = re.compile(r"(?P<key>\w+)=\"(?P<value>[^\"]+)\"", re.ASCII)
+
 def prefix_absolute_path_references(text, base_url):
     """Adds base_url to absolute-path references.
 
@@ -44,17 +73,90 @@ def prefix_absolute_path_references(text, base_url):
     """
     return text.replace("](/", "]({}/".format(base_url))
 
-def edit_links(node, base_url):
-    """Finds description nodes and makes any links in them absolute."""
+def replace_match(match, replacement):
+    """Replaces the regex match by the replacement in the text."""
+    return match.string[:match.start()] + replacement + match.string[match.end():]
+
+def replace_shortcode(shortcode):
+    """Replaces the shortcode by a Markdown fallback in the text.
+
+    The supported shortcodes are:
+
+    * boxes/note, boxes/rationale, boxes/warning
+    * added-in, changed-in
+    
+    All closing tags (`{{ /shortcode }}`) are replaced with the empty string.
+    """
+
+    if shortcode['name'].startswith("/"):
+        # This is the end of the shortcode, just remove it.
+        return replace_match(shortcode, "")
+
+    # Parse the parameters of the shortcode
+    params = {}
+    if shortcode['params']:
+        for param in shortcode_params_regex.finditer(shortcode['params']):
+            if param['key']:
+                params[param['key']] = param['value']
+
+    match shortcode['name']:
+        case "boxes/note":
+            return replace_match(shortcode, "**NOTE:** ")
+        case "boxes/rationale":
+            return replace_match(shortcode, "**RATIONALE:** ")
+        case "boxes/warning":
+            return replace_match(shortcode, "**WARNING:** ")
+        case "added-in":
+            version = params['v']
+            if not version:
+                raise ValueError("Missing parameter `v` for `added-in` shortcode")
+
+            return replace_match(shortcode, f"**[Added in `v{version}`]** ")
+        case "changed-in":
+            version = params['v']
+            if not version:
+                raise ValueError("Missing parameter `v` for `changed-in` shortcode")
+
+            return replace_match(shortcode, f"**[Changed in `v{version}`]** ")
+        case _:
+            raise ValueError("Unknown shortcode", shortcode['name'])
+
+
+def find_and_replace_shortcodes(text):
+    """Finds Hugo shortcodes and replaces them by a Markdown fallback.
+
+    The supported shortcodes are:
+
+    * boxes/note, boxes/rationale, boxes/warning
+    * added-in, changed-in
+    """
+    # We use a `while` loop with `search` instead of a `for` loop with
+    # `finditer`, because as soon as we start replacing text, the
+    # indices of the match are invalid.
+    while shortcode := shortcode_regex.search(text):
+        text = replace_shortcode(shortcode)
+
+    return text
+
+def edit_descriptions(node, base_url):
+    """Finds description nodes and apply fixes to them.
+
+    The fixes that are applied are:
+
+    * Make links absolute
+    * Replace Hugo shortcodes
+    """
     if isinstance(node, dict):
         for key in node:
             if isinstance(node[key], str):
                 node[key] = prefix_absolute_path_references(node[key], base_url)
+                node[key] = find_and_replace_shortcodes(node[key])
             else:
-                edit_links(node[key], base_url)
+                edit_descriptions(node[key], base_url)
     elif isinstance(node, list):
         for item in node:
-            edit_links(item, base_url)
+            edit_descriptions(item, base_url)
+
 
 parser = argparse.ArgumentParser(
     "dump-openapi.py - assemble the OpenAPI specs into a single JSON file"
@@ -164,7 +266,7 @@ def edit_links(node, base_url):
 if untagged != 0:
     print("{} untagged operations, you may want to look into fixing that.".format(untagged))
 
-edit_links(output, base_url)
+edit_descriptions(output, base_url)
 
 print("Generating %s" % output_file)