diff options
Diffstat (limited to 'Documentation/sphinx/automarkup.py')
| -rw-r--r-- | Documentation/sphinx/automarkup.py | 310 |
1 files changed, 267 insertions, 43 deletions
diff --git a/Documentation/sphinx/automarkup.py b/Documentation/sphinx/automarkup.py index 5b6119ff69f4..a413f8dd5115 100644 --- a/Documentation/sphinx/automarkup.py +++ b/Documentation/sphinx/automarkup.py @@ -5,9 +5,19 @@ # has been done. # from docutils import nodes +import sphinx from sphinx import addnodes -from sphinx.environment import NoUri +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. @@ -16,7 +26,36 @@ import re # :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'([\w_][\w\d_]+\(\))') +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 @@ -29,70 +68,255 @@ Skipfuncs = [ 'open', 'close', 'read', 'write', 'fcntl', 'mmap', 'select', 'poll', 'fork', 'execve', 'clone', 'ioctl', 'socket' ] +c_namespace = '' + # -# Find all occurrences of function() and try to replace them with -# appropriate cross references. +# Detect references to commits. # -def markup_funcs(docname, app, node): - cdom = app.env.domains['c'] +RE_git = re.compile(r'commit\s+(?P<rev>[0-9a-f]{12,40})(?:\s+\(".*?"\))?', + flags=re.IGNORECASE | re.DOTALL) + +def markup_refs(docname, app, node): t = node.astext() done = 0 repl = [ ] - for m in RE_function.finditer(t): + # + # 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, + RE_git: markup_git} + + 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 function() as a normal text node. + # Include any text prior to match as a normal text node. # if m.start() > done: repl.append(nodes.Text(t[done:m.start()])) + # - # Go through the dance of getting an xref out of the C domain - # - target = m.group(1)[:-2] - target_text = nodes.Text(target + '()') - xref = None - if target not in Skipfuncs: - lit_text = nodes.literal(classes=['xref', 'c', 'c-func']) - lit_text += target_text - pxref = addnodes.pending_xref('', refdomain = 'c', - reftype = 'function', - 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, - 'function', target, pxref, lit_text) - except NoUri: - xref = None - # - # Toss the xref into the list if we got it; otherwise just put - # the function text. + # Call the function associated with the regex that matched this text and + # append its return to the text # - if xref: - repl.append(xref) - else: - repl.append(target_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 +# +# Keep track of cross-reference lookups that failed so we don't have to +# do them again. +# +failed_lookups = { } +def failure_seen(target): + return (target) in failed_lookups +def note_failure(target): + failed_lookups[target] = True + +# +# 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): + 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) and not failure_seen(target): + lit_text = nodes.literal(classes=['xref', 'c', 'c-func']) + lit_text += target_text + pxref = addnodes.pending_xref('', refdomain = 'c', + reftype = 'function', + 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, + 'function', target, pxref, + lit_text) + except NoUri: + xref = None + + if xref: + return xref + note_failure(target) + + 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 markup_git(docname, app, match): + # While we could probably assume that we are running in a git + # repository, we can't know for sure, so let's just mechanically + # turn them into git.kernel.org links without checking their + # validity. (Maybe we can do something in the future to warn about + # these references if this is explicitly requested.) + text = match.group(0) + rev = match.group('rev') + return nodes.reference('', nodes.Text(text), + refuri=f'https://git.kernel.org/torvalds/c/{rev}') + 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_funcs(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) |