From 7cc4c09269109d31fc325fb8390e452d7e558de0 Mon Sep 17 00:00:00 2001 From: James Clark Date: Wed, 5 Jan 2022 14:36:39 +0000 Subject: docs: automarkup.py: Fix invalid HTML link output and broken URI fragments MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since commit d18b01789ae5 ("docs: Add automatic cross-reference for documentation pages"), references that were already explicitly defined with "ref:" and referred to other pages with a path have been doubled. This is reported as the following error by Firefox: Start tag "a" seen but an element of the same type was already open. End tag "a" violates nesting rules. As well as the invalid HTML, this also obscures the URI fragment links to subsections because the second link overrides the first. For example on the page admin-guide/hw-vuln/mds.html the last link should be to the "Default Mitigations" subsection using a # URI fragment: admin-guide/hw-vuln/l1tf.html#default-mitigations But it is obsured by a second link to the whole page: admin-guide/hw-vuln/l1tf.html The full HTML with the double tags looks like this: L1TF - L1 Terminal Fault After this commit, there is only a single link: Documentation/admin-guide/hw-vuln//l1tf.rst Now that the second link is removed, the browser correctly jumps to the default-mitigations subsection when clicking the link. The fix is to check that nodes in the document to be modified are not already references. A reference is counted as any text that is a descendant of a reference type node. Only plain text should be converted to new references, otherwise the doubling occurs. Testing ======= * Test that the build stdout is the same (ignoring ordering), and that no new warnings are printed. * Diff all .html files and check that the only modifications occur to the bad double links. * The auto linking of bare references to pages without "ref:" is still working. Fixes: d18b01789ae5 ("docs: Add automatic cross-reference for documentation pages") Reviewed-by: Nícolas F. R. A. Prado Signed-off-by: James Clark Link: https://lore.kernel.org/r/20220105143640.330602-2-james.clark@arm.com Signed-off-by: Jonathan Corbet --- Documentation/sphinx/automarkup.py | 25 ++++++++++++++++++------- 1 file changed, 18 insertions(+), 7 deletions(-) (limited to 'Documentation/sphinx') diff --git a/Documentation/sphinx/automarkup.py b/Documentation/sphinx/automarkup.py index acf5473002f3..cc348b219fca 100644 --- a/Documentation/sphinx/automarkup.py +++ b/Documentation/sphinx/automarkup.py @@ -271,19 +271,30 @@ def get_c_namespace(app, docname): def auto_markup(app, doctree, name): global c_namespace c_namespace = get_c_namespace(app, name) + def text_but_not_a_reference(node): + # The nodes.literal test catches ``literal text``, its purpose is to + # avoid adding cross-references to functions that have been explicitly + # marked with cc:func:. + if not isinstance(node, nodes.Text) or isinstance(node.parent, nodes.literal): + return False + + child_of_reference = False + parent = node.parent + while parent: + if isinstance(parent, nodes.Referential): + child_of_reference = True + break + parent = parent.parent + return not child_of_reference + # # This loop could eventually be improved on. Someday maybe we # want a proper tree traversal with a lot of awareness of which # kinds of nodes to prune. But this works well for now. # - # The nodes.literal test catches ``literal text``, its purpose is to - # avoid adding cross-references to functions that have been explicitly - # marked with cc:func:. - # for para in doctree.traverse(nodes.paragraph): - for node in para.traverse(nodes.Text): - if not isinstance(node.parent, nodes.literal): - node.parent.replace(node, markup_refs(name, app, node)) + for node in para.traverse(condition=text_but_not_a_reference): + node.parent.replace(node, markup_refs(name, app, node)) def setup(app): app.connect('doctree-resolved', auto_markup) -- cgit v1.2.3