[PATCH 1/2] Docs: An initial automarkup extension for sphinx

From: Jonathan Corbet <corbet@lwn.net>
To: linux-doc@vger.kernel.org
Cc: linux-kernel@vger.kernel.org,
	Matthew Wilcox <willy@infradead.org>,
	Mauro Carvalho Chehab <mchehab@kernel.org>,
	Jonathan Corbet <corbet@lwn.net>
Subject: [PATCH 1/2] Docs: An initial automarkup extension for sphinx
Date: Thu, 25 Apr 2019 14:01:24 -0600	[thread overview]
Message-ID: <20190425200125.12302-2-corbet@lwn.net> (raw)
In-Reply-To: <20190425200125.12302-1-corbet@lwn.net>

Rather than fill our text files with :c:func:`function()` syntax, just do
the markup via a hook into the sphinx build process.  As is always the
case, the real problem is detecting the situations where this markup should
*not* be done.

Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/conf.py              |  3 +-
 Documentation/sphinx/automarkup.py | 90 ++++++++++++++++++++++++++++++
 2 files changed, 92 insertions(+), 1 deletion(-)
 create mode 100644 Documentation/sphinx/automarkup.py

diff --git a/Documentation/conf.py b/Documentation/conf.py
index 72647a38b5c2..ba7b2846b1c5 100644
--- a/Documentation/conf.py
+++ b/Documentation/conf.py
@@ -34,7 +34,8 @@ needs_sphinx = '1.3'
 # Add any Sphinx extension module names here, as strings. They can be
 # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
 # ones.
-extensions = ['kerneldoc', 'rstFlatTable', 'kernel_include', 'cdomain', 'kfigure', 'sphinx.ext.ifconfig']
+extensions = ['kerneldoc', 'rstFlatTable', 'kernel_include', 'cdomain',
+              'kfigure', 'sphinx.ext.ifconfig', 'automarkup']
 
 # The name of the math extension changed on Sphinx 1.4
 if major == 1 and minor > 3:
diff --git a/Documentation/sphinx/automarkup.py b/Documentation/sphinx/automarkup.py
new file mode 100644
index 000000000000..c47469372bae
--- /dev/null
+++ b/Documentation/sphinx/automarkup.py
@@ -0,0 +1,90 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# This is a little Sphinx extension that tries to apply certain kinds
+# of markup automatically so we can keep it out of the text files
+# themselves.
+#
+# It's possible that this could be done better by hooking into the build
+# much later and traversing through the doctree.  That would eliminate the
+# need to duplicate some RST parsing and perhaps be less fragile, at the
+# cost of some more complexity and the need to generate the cross-reference
+# links ourselves.
+#
+# Copyright 2019 Jonathan Corbet <corbet@lwn.net>
+#
+from __future__ import print_function
+import re
+import sphinx
+
+#
+# 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'(^|\s+)([\w\d_]+\(\))([.,/\s]|$)')
+#
+# Lines consisting of a single underline character.
+#
+RE_underline = re.compile(r'^([-=~])\1+$')
+#
+# Starting a literal block.
+#
+RE_literal = re.compile(r'^(\s*)(.*::\s*|\.\.\s+code-block::.*)$')
+#
+# Just get the white space beginning a line.
+#
+RE_whitesp = re.compile(r'^(\s*)')
+
+def MangleFile(app, docname, text):
+    ret = [ ]
+    previous = ''
+    literal = False
+    for line in text[0].split('\n'):
+        #
+        # See if we might be ending a literal block, as denoted by
+        # an indent no greater than when we started.
+        #
+        if literal and len(line) > 0:
+            m = RE_whitesp.match(line)  # Should always match
+            if len(m.group(1).expandtabs()) <= lit_indent:
+                literal = False
+        #
+        # Blank lines, directives, and lines within literal blocks
+        # should not be messed with.
+        #
+        if literal or len(line) == 0 or line[0] == '.':
+            ret.append(line)
+        #
+        # Is this an underline line?  If so, and it is the same length
+        # as the previous line, we may have mangled a heading line in
+        # error, so undo it.
+        #
+        elif RE_underline.match(line):
+            if len(line) == len(previous):
+                ret[-1] = previous
+            ret.append(line)
+        #
+        # Normal line - perform substitutions.
+        #
+        else:
+            ret.append(RE_function.sub(r'\1:c:func:`\2`\3', line))
+        #
+        # Might we be starting a literal block?  If so make note of
+        # the fact.
+        #
+        m = RE_literal.match(line)
+        if m:
+            literal = True
+            lit_indent = len(m.group(1).expandtabs())
+        previous = line
+    text[0] = '\n'.join(ret)
+
+def setup(app):
+    app.connect('source-read', MangleFile)
+
+    return dict(
+        parallel_read_safe = True,
+        parallel_write_safe = True
+    )
-- 
2.21.0

