Simplify code to replace shortcodes

Signed-off-by: Kévin Commaille <zecakeh@tedomum.fr>

scripts/dump-openapi.py

@@ -37,10 +37,10 @@ api_dir = os.path.join(os.path.dirname(scripts_dir), "data", "api")
 # A shortcode is defined as (newlines and whitespaces for presentation purpose):
 #
 # {{%
-#     <one or more whitespaces>
+#     <zero or more whitespaces>
 #     <name of shortcode>
-#     <one or more whitespaces>
-#     (optional <list of parameters><one or more whitespaces>)
+#     (optional <one or more whitespaces><list of parameters>)
+#     <zero or more whitespaces>
 # %}}
 #
 # With:
@@ -48,9 +48,14 @@ api_dir = os.path.join(os.path.dirname(scripts_dir), "data", "api")
 # * <name of shortcode>: any word character and `-` and `/`.
 # * <list of parameters>: any character except `}`, must not start or end with a
 #   whitespace.
-shortcode_regex = re.compile(r"\{\{\%\s+(?P<name>[\w\/-]+)\s+(?:(?P<params>[^\s\}][^\}]+[^\s\}])\s+)?\%\}\}", re.ASCII)
+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. 
+# 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)
@@ -67,13 +72,13 @@ def prefix_absolute_path_references(text, base_url):
     """
     return text.replace("](/", "]({}/".format(base_url))
 
-def replace_match(text, match, replacement):
+def replace_match(match, replacement):
     """Replaces the regex match by the replacement in the text."""
-    return text[:match.start()] + replacement + text[match.end():]
+    return match.string[:match.start()] + replacement + match.string[match.end():]
 
-def replace_shortcode(text, shortcode):
+def replace_shortcode(shortcode):
     """Replaces the shortcode by a Markdown fallback in the text.
-    
+
     The supported shortcodes are:
 
     * boxes/note, boxes/rationale, boxes/warning
@@ -82,36 +87,41 @@ def replace_shortcode(text, shortcode):
 
     if shortcode['name'].startswith("/"):
         # This is the end of the shortcode, just remove it.
-        return replace_match(text, shortcode['match'], "")
-    
+        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":
-            text = replace_match(text, shortcode['match'], "**NOTE:** ")
+            return replace_match(shortcode, "**NOTE:** ")
         case "boxes/rationale":
-            text = replace_match(text, shortcode['match'], "**RATIONALE:** ")
+            return replace_match(shortcode, "**RATIONALE:** ")
         case "boxes/warning":
-            text = replace_match(text, shortcode['match'], "**WARNING:** ")
+            return replace_match(shortcode, "**WARNING:** ")
         case "added-in":
-            version = shortcode['params']['v']
+            version = params['v']
             if not version:
                 raise ValueError("Missing parameter `v` for `added-in` shortcode")
-        
-            text = replace_match(text, shortcode['match'], f"**[Added in `v{version}`]** ")
+
+            return replace_match(shortcode, f"**[Added in `v{version}`]** ")
         case "changed-in":
-            version = shortcode['params']['v']
+            version = params['v']
             if not version:
                 raise ValueError("Missing parameter `v` for `changed-in` shortcode")
-        
-            text = replace_match(text, shortcode['match'], f"**[Changed in `v{version}`]** ")
+
+            return replace_match(shortcode, f"**[Changed in `v{version}`]** ")
         case _:
             raise ValueError("Unknown shortcode", shortcode['name'])
 
-    return text
-
 
 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
@@ -120,30 +130,18 @@ def find_and_replace_shortcodes(text):
     # 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 match := shortcode_regex.search(text):
-        # Parse the parameters of the shortcode
-        params = {}
-        if match['params']:
-            for param in shortcode_params_regex.finditer(match['params']):
-                if param['key']:
-                    params[param['key']] = param['value']
-        
-        shortcode = {
-            'name': match['name'],
-            'params': params,
-            'match': match,
-        }
-        text = replace_shortcode(text, shortcode)
+    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 shortcodes
+    * Replace Hugo shortcodes
     """
     if isinstance(node, dict):
         for key in node: