Fix bug in to_wikitext() with caption attributes

When translating a WikiNode TABLE_CAPTION with attributes
back into wikitext, we omitted a final `|` pipe character
necessary for proper parsing of caption attributes.

Note that this is not necessary for TABLE attributes.

This bug was only recently discovered because we didn't
do anything with table captions before...

Author: kristian-clausal

src/wikitextprocessor/node_expand.py

@@ -139,7 +139,10 @@ def recurse(node: Union[GeneralNode, WikiNodeListArgs]) -> str:
             parts.append(recurse(node.children))
             parts.append("\n|}\n")
         elif kind == NodeKind.TABLE_CAPTION:
-            parts.append("\n|+ {}\n".format(to_attrs(node)))
+            if tc_attrs := to_attrs(node):
+                parts.append("\n|+ {} |\n".format(tc_attrs))
+            else:
+                parts.append("\n|+\n")
             parts.append(recurse(node.children))
         elif kind == NodeKind.TABLE_ROW:
             parts.append("\n|- {}\n".format(to_attrs(node)))

src/wikitextprocessor/parser.py

@@ -1414,7 +1414,8 @@ def table_start_fn(ctx: "Wtp", token: str) -> None:
 
 # something=other, something="other", something = 'other'
 attr_assignment_pair = (
-    r"""\s*[^"'>/=\0-\037\s]+""" r"""\s*=\s*("[^"]*"|'[^']*'|[^"'<>`\s]+)"""
+    r"""\s*[^"'>/=\0-\037\s]+"""
+    r"""\s*=\s*("[^"]*"|'[^']*'|[^"'<>`\s]+)"""
 )
 
 attr_assignments_re = re.compile(
@@ -1428,7 +1429,7 @@ def check_for_attributes(ctx: "Wtp", node: WikiNode) -> tuple[bool, str]:
 
     # Old behavior added here to return earlier without needing
     # to use regex matching; if the old version worked, why not?
-    # If this fail, then resort to the reverse parsing + regex.
+    # If this fails, then resort to the reverse parsing + regex.
     _parser_merge_str_children(ctx)
     if len(node.children) == 1 and isinstance(node.children[0], str):
         ret = node.children.pop()
@@ -1623,7 +1624,10 @@ def table_cell_fn(ctx: "Wtp", token: str) -> None:
                 if len(node.children) == 1 and isinstance(
                     attrs := node.children[0], str
                 ):
-                    node.children.pop()
+                    # At this point of parsing, we're just behind the start
+                    # of one of the above node types; if they are followed
+                    # by a `|`, that means the first child is an attr section
+                    node.children.pop(0)
                     # Using the walrus operator and pop()ing without return
                     # is just to make the type-checker happy without using
                     # an assert that attrs is definitely a str...

tests/test_node_expand.py

@@ -154,7 +154,13 @@ def test_table2(self):
         self.backcvt('{| class="x"\n|}', '\n{| class="x"\n\n|}\n')
 
     def test_tablecaption1(self):
-        self.backcvt("{|\n|+\ncapt\n|}", "\n{| \n\n|+ \n\ncapt\n\n|}\n")
+        self.backcvt("{|\n|+\ncapt\n|}", "\n{| \n\n|+\n\ncapt\n\n|}\n")
+
+    def test_tablecaption2(self):
+        self.backcvt(
+            "{|\n |+ class='foo' |\ncapt\n|}",
+            '\n{| \n\n|+ class="foo" |\n\ncapt\n\n|}\n',
+        )
 
     def test_tablerowcell1(self):
         self.backcvt(