linux-stable/Documentation/sphinx/automarkup.py
James Clark 7cc4c09269 docs: automarkup.py: Fix invalid HTML link output and broken URI fragments
Since commit d18b01789a ("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 <a> tags looks like this:

  <a class="reference internal" href="l1tf.html#default-mitigations">
    <span class="std std-ref">
      <a class="reference internal" href="l1tf.html">
        <span class="doc">L1TF - L1 Terminal Fault</span>
      </a>
    </span>
  </a>

After this commit, there is only a single link:

  <a class="reference internal" href="l1tf.html#default-mitigations">
    <span class="std std-ref">Documentation/admin-guide/hw-vuln//l1tf.rst</span>
  </a>

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: d18b01789a ("docs: Add automatic cross-reference for documentation pages")
Reviewed-by: Nícolas F. R. A. Prado <n@nfraprado.net>
Signed-off-by: James Clark <james.clark@arm.com>
Link: https://lore.kernel.org/r/20220105143640.330602-2-james.clark@arm.com
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
2022-01-07 09:32:58 -07:00

304 lines
10 KiB
Python

# SPDX-License-Identifier: GPL-2.0
# Copyright 2019 Jonathan Corbet <corbet@lwn.net>
#
# Apply kernel-specific tweaks after the initial document processing
# has been done.
#
from docutils import nodes
import sphinx
from sphinx import addnodes
if sphinx.version_info[0] < 2 or \
sphinx.version_info[0] == 2 and sphinx.version_info[1] < 1:
from sphinx.environment import NoUri
else:
from sphinx.errors import NoUri
import re
from itertools import chain
#
# Python 2 lacks re.ASCII...
#
try:
ascii_p3 = re.ASCII
except AttributeError:
ascii_p3 = 0
#
# Regex nastiness. Of course.
# Try to identify "function()" that's not already marked up some
# other way. Sphinx doesn't like a lot of stuff right after a
# :c:func: block (i.e. ":c:func:`mmap()`s" flakes out), so the last
# bit tries to restrict matches to things that won't create trouble.
#
RE_function = re.compile(r'\b(([a-zA-Z_]\w+)\(\))', flags=ascii_p3)
#
# Sphinx 2 uses the same :c:type role for struct, union, enum and typedef
#
RE_generic_type = re.compile(r'\b(struct|union|enum|typedef)\s+([a-zA-Z_]\w+)',
flags=ascii_p3)
#
# Sphinx 3 uses a different C role for each one of struct, union, enum and
# typedef
#
RE_struct = re.compile(r'\b(struct)\s+([a-zA-Z_]\w+)', flags=ascii_p3)
RE_union = re.compile(r'\b(union)\s+([a-zA-Z_]\w+)', flags=ascii_p3)
RE_enum = re.compile(r'\b(enum)\s+([a-zA-Z_]\w+)', flags=ascii_p3)
RE_typedef = re.compile(r'\b(typedef)\s+([a-zA-Z_]\w+)', flags=ascii_p3)
#
# Detects a reference to a documentation page of the form Documentation/... with
# an optional extension
#
RE_doc = re.compile(r'(\bDocumentation/)?((\.\./)*[\w\-/]+)\.(rst|txt)')
RE_namespace = re.compile(r'^\s*..\s*c:namespace::\s*(\S+)\s*$')
#
# Reserved C words that we should skip when cross-referencing
#
Skipnames = [ 'for', 'if', 'register', 'sizeof', 'struct', 'unsigned' ]
#
# Many places in the docs refer to common system calls. It is
# pointless to try to cross-reference them and, as has been known
# to happen, somebody defining a function by these names can lead
# to the creation of incorrect and confusing cross references. So
# just don't even try with these names.
#
Skipfuncs = [ 'open', 'close', 'read', 'write', 'fcntl', 'mmap',
'select', 'poll', 'fork', 'execve', 'clone', 'ioctl',
'socket' ]
c_namespace = ''
def markup_refs(docname, app, node):
t = node.astext()
done = 0
repl = [ ]
#
# Associate each regex with the function that will markup its matches
#
markup_func_sphinx2 = {RE_doc: markup_doc_ref,
RE_function: markup_c_ref,
RE_generic_type: markup_c_ref}
markup_func_sphinx3 = {RE_doc: markup_doc_ref,
RE_function: markup_func_ref_sphinx3,
RE_struct: markup_c_ref,
RE_union: markup_c_ref,
RE_enum: markup_c_ref,
RE_typedef: markup_c_ref}
if sphinx.version_info[0] >= 3:
markup_func = markup_func_sphinx3
else:
markup_func = markup_func_sphinx2
match_iterators = [regex.finditer(t) for regex in markup_func]
#
# Sort all references by the starting position in text
#
sorted_matches = sorted(chain(*match_iterators), key=lambda m: m.start())
for m in sorted_matches:
#
# Include any text prior to match as a normal text node.
#
if m.start() > done:
repl.append(nodes.Text(t[done:m.start()]))
#
# Call the function associated with the regex that matched this text and
# append its return to the text
#
repl.append(markup_func[m.re](docname, app, m))
done = m.end()
if done < len(t):
repl.append(nodes.Text(t[done:]))
return repl
#
# In sphinx3 we can cross-reference to C macro and function, each one with its
# own C role, but both match the same regex, so we try both.
#
def markup_func_ref_sphinx3(docname, app, match):
class_str = ['c-func', 'c-macro']
reftype_str = ['function', 'macro']
cdom = app.env.domains['c']
#
# Go through the dance of getting an xref out of the C domain
#
base_target = match.group(2)
target_text = nodes.Text(match.group(0))
xref = None
possible_targets = [base_target]
# Check if this document has a namespace, and if so, try
# cross-referencing inside it first.
if c_namespace:
possible_targets.insert(0, c_namespace + "." + base_target)
if base_target not in Skipnames:
for target in possible_targets:
if target not in Skipfuncs:
for class_s, reftype_s in zip(class_str, reftype_str):
lit_text = nodes.literal(classes=['xref', 'c', class_s])
lit_text += target_text
pxref = addnodes.pending_xref('', refdomain = 'c',
reftype = reftype_s,
reftarget = target, modname = None,
classname = None)
#
# XXX The Latex builder will throw NoUri exceptions here,
# work around that by ignoring them.
#
try:
xref = cdom.resolve_xref(app.env, docname, app.builder,
reftype_s, target, pxref,
lit_text)
except NoUri:
xref = None
if xref:
return xref
return target_text
def markup_c_ref(docname, app, match):
class_str = {# Sphinx 2 only
RE_function: 'c-func',
RE_generic_type: 'c-type',
# Sphinx 3+ only
RE_struct: 'c-struct',
RE_union: 'c-union',
RE_enum: 'c-enum',
RE_typedef: 'c-type',
}
reftype_str = {# Sphinx 2 only
RE_function: 'function',
RE_generic_type: 'type',
# Sphinx 3+ only
RE_struct: 'struct',
RE_union: 'union',
RE_enum: 'enum',
RE_typedef: 'type',
}
cdom = app.env.domains['c']
#
# Go through the dance of getting an xref out of the C domain
#
base_target = match.group(2)
target_text = nodes.Text(match.group(0))
xref = None
possible_targets = [base_target]
# Check if this document has a namespace, and if so, try
# cross-referencing inside it first.
if c_namespace:
possible_targets.insert(0, c_namespace + "." + base_target)
if base_target not in Skipnames:
for target in possible_targets:
if not (match.re == RE_function and target in Skipfuncs):
lit_text = nodes.literal(classes=['xref', 'c', class_str[match.re]])
lit_text += target_text
pxref = addnodes.pending_xref('', refdomain = 'c',
reftype = reftype_str[match.re],
reftarget = target, modname = None,
classname = None)
#
# XXX The Latex builder will throw NoUri exceptions here,
# work around that by ignoring them.
#
try:
xref = cdom.resolve_xref(app.env, docname, app.builder,
reftype_str[match.re], target, pxref,
lit_text)
except NoUri:
xref = None
if xref:
return xref
return target_text
#
# Try to replace a documentation reference of the form Documentation/... with a
# cross reference to that page
#
def markup_doc_ref(docname, app, match):
stddom = app.env.domains['std']
#
# Go through the dance of getting an xref out of the std domain
#
absolute = match.group(1)
target = match.group(2)
if absolute:
target = "/" + target
xref = None
pxref = addnodes.pending_xref('', refdomain = 'std', reftype = 'doc',
reftarget = target, modname = None,
classname = None, refexplicit = False)
#
# XXX The Latex builder will throw NoUri exceptions here,
# work around that by ignoring them.
#
try:
xref = stddom.resolve_xref(app.env, docname, app.builder, 'doc',
target, pxref, None)
except NoUri:
xref = None
#
# Return the xref if we got it; otherwise just return the plain text.
#
if xref:
return xref
else:
return nodes.Text(match.group(0))
def get_c_namespace(app, docname):
source = app.env.doc2path(docname)
with open(source) as f:
for l in f:
match = RE_namespace.search(l)
if match:
return match.group(1)
return ''
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.
#
for para in doctree.traverse(nodes.paragraph):
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)
return {
'parallel_read_safe': True,
'parallel_write_safe': True,
}