doc-rst: Programmatically render MAINTAINERS into ReST

In order to have the MAINTAINERS file visible in the rendered ReST
output, this makes some small changes to the existing MAINTAINERS file
to allow for better machine processing, and adds a new Sphinx directive
"maintainers-include" to perform the rendering.

Features include:
- Per-subsystem reference links: subsystem maintainer entries can be
  trivially linked to both internally and external. For example:
  https://www.kernel.org/doc/html/latest/process/maintainers.html#secure-computing

- Internally referenced .rst files are linked so they can be followed
  when browsing the resulting rendering. This allows, for example, the
  future addition of maintainer profiles to be automatically linked.

- Field name expansion: instead of the short fields (e.g. "M", "F",
  "K"), use the indicated inline "full names" for the fields (which are
  marked with "*"s in MAINTAINERS) so that a rendered subsystem entry
  is more human readable. Email lists are additionally comma-separated.
  For example:

    SECURE COMPUTING
	Mail:	  Kees Cook <keescook@chromium.org>
	Reviewer: Andy Lutomirski <luto@amacapital.net>,
		  Will Drewry <wad@chromium.org>
	SCM:	  git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git seccomp
	Status:	  Supported
	Files:	  kernel/seccomp.c include/uapi/linux/seccomp.h
		  include/linux/seccomp.h tools/testing/selftests/seccomp/*
		  tools/testing/selftests/kselftest_harness.h
		  userspace-api/seccomp_filter
	Content regex:	\bsecure_computing \bTIF_SECCOMP\b

Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>

4 files changed, 201 insertions, 1 deletions

diff --git a/Documentation/conf.py b/Documentation/conf.py
index a8fe845832bc..3c7bdf4cd31f 100644
--- a/Documentation/conf.py
+++ b/Documentation/conf.py
@@ -37,7 +37,8 @@ needs_sphinx = '1.3'
 # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
 # ones.
 extensions = ['kerneldoc', 'rstFlatTable', 'kernel_include', 'cdomain',
-              'kfigure', 'sphinx.ext.ifconfig', 'automarkup']
+              'kfigure', 'sphinx.ext.ifconfig', 'automarkup',
+              'maintainers_include']
 
 # The name of the math extension changed on Sphinx 1.4
 if (major == 1 and minor > 3) or (major > 1):
diff --git a/Documentation/process/index.rst b/Documentation/process/index.rst
index e2c9ffc682c5..e2fb0c9652ac 100644
--- a/Documentation/process/index.rst
+++ b/Documentation/process/index.rst
@@ -46,6 +46,7 @@ Other guides to the community that are of interest to most developers are:
    kernel-docs
    deprecated
    embargoed-hardware-issues
+   maintainers
 
 These are some overall technical guides that have been put here for now for
 lack of a better place.
diff --git a/Documentation/process/maintainers.rst b/Documentation/process/maintainers.rst
new file mode 100644
index 000000000000..6174cfb4138f
--- /dev/null
+++ b/Documentation/process/maintainers.rst
@@ -0,0 +1 @@
+.. maintainers-include::
diff --git a/Documentation/sphinx/maintainers_include.py b/Documentation/sphinx/maintainers_include.py
new file mode 100755
index 000000000000..dc8fed48d3c2
--- /dev/null
+++ b/Documentation/sphinx/maintainers_include.py
@@ -0,0 +1,197 @@
+#!/usr/bin/env python
+# SPDX-License-Identifier: GPL-2.0
+# -*- coding: utf-8; mode: python -*-
+# pylint: disable=R0903, C0330, R0914, R0912, E0401
+
+u"""
+    maintainers-include
+    ~~~~~~~~~~~~~~~~~~~
+
+    Implementation of the ``maintainers-include`` reST-directive.
+
+    :copyright:  Copyright (C) 2019  Kees Cook <keescook@chromium.org>
+    :license:    GPL Version 2, June 1991 see linux/COPYING for details.
+
+    The ``maintainers-include`` reST-directive performs extensive parsing
+    specific to the Linux kernel's standard "MAINTAINERS" file, in an
+    effort to avoid needing to heavily mark up the original plain text.
+"""
+
+import sys
+import re
+import os.path
+
+from docutils import statemachine
+from docutils.utils.error_reporting import ErrorString
+from docutils.parsers.rst import Directive
+from docutils.parsers.rst.directives.misc import Include
+
+__version__  = '1.0'
+
+def setup(app):
+    app.add_directive("maintainers-include", MaintainersInclude)
+    return dict(
+        version = __version__,
+        parallel_read_safe = True,
+        parallel_write_safe = True
+    )
+
+class MaintainersInclude(Include):
+    u"""MaintainersInclude (``maintainers-include``) directive"""
+    required_arguments = 0
+
+    def parse_maintainers(self, path):
+        """Parse all the MAINTAINERS lines into ReST for human-readability"""
+
+        result = list()
+        result.append(".. _maintainers:")
+        result.append("")
+
+        # Poor man's state machine.
+        descriptions = False
+        maintainers = False
+        subsystems = False
+
+        # Field letter to field name mapping.
+        field_letter = None
+        fields = dict()
+
+        prev = None
+        field_prev = ""
+        field_content = ""
+
+        for line in open(path):
+            if sys.version_info.major == 2:
+                line = unicode(line, 'utf-8')
+            # Have we reached the end of the preformatted Descriptions text?
+            if descriptions and line.startswith('Maintainers'):
+                descriptions = False
+                # Ensure a blank line following the last "|"-prefixed line.
+                result.append("")
+
+            # Start subsystem processing? This is to skip processing the text
+            # between the Maintainers heading and the first subsystem name.
+            if maintainers and not subsystems:
+                if re.search('^[A-Z0-9]', line):
+                    subsystems = True
+
+            # Drop needless input whitespace.
+            line = line.rstrip()
+
+            # Linkify all non-wildcard refs to ReST files in Documentation/.
+            pat = '(Documentation/([^\s\?\*]*)\.rst)'
+            m = re.search(pat, line)
+            if m:
+                # maintainers.rst is in a subdirectory, so include "../".
+                line = re.sub(pat, ':doc:`%s <../%s>`' % (m.group(2), m.group(2)), line)
+
+            # Check state machine for output rendering behavior.
+            output = None
+            if descriptions:
+                # Escape the escapes in preformatted text.
+                output = "| %s" % (line.replace("\\", "\\\\"))
+                # Look for and record field letter to field name mappings:
+                #   R: Designated *reviewer*: FullName <address@domain>
+                m = re.search("\s(\S):\s", line)
+                if m:
+                    field_letter = m.group(1)
+                if field_letter and not field_letter in fields:
+                    m = re.search("\*([^\*]+)\*", line)
+                    if m:
+                        fields[field_letter] = m.group(1)
+            elif subsystems:
+                # Skip empty lines: subsystem parser adds them as needed.
+                if len(line) == 0:
+                    continue
+                # Subsystem fields are batched into "field_content"
+                if line[1] != ':':
+                    # Render a subsystem entry as:
+                    #   SUBSYSTEM NAME
+                    #   ~~~~~~~~~~~~~~
+
+                    # Flush pending field content.
+                    output = field_content + "\n\n"
+                    field_content = ""
+
+                    # Collapse whitespace in subsystem name.
+                    heading = re.sub("\s+", " ", line)
+                    output = output + "%s\n%s" % (heading, "~" * len(heading))
+                    field_prev = ""
+                else:
+                    # Render a subsystem field as:
+                    #   :Field: entry
+                    #           entry...
+                    field, details = line.split(':', 1)
+                    details = details.strip()
+
+                    # Mark paths (and regexes) as literal text for improved
+                    # readability and to escape any escapes.
+                    if field in ['F', 'N', 'X', 'K']:
+                        # But only if not already marked :)
+                        if not ':doc:' in details:
+                            details = '``%s``' % (details)
+
+                    # Comma separate email field continuations.
+                    if field == field_prev and field_prev in ['M', 'R', 'L']:
+                        field_content = field_content + ","
+
+                    # Do not repeat field names, so that field entries
+                    # will be collapsed together.
+                    if field != field_prev:
+                        output = field_content + "\n"
+                        field_content = ":%s:" % (fields.get(field, field))
+                    field_content = field_content + "\n\t%s" % (details)
+                    field_prev = field
+            else:
+                output = line
+
+            # Re-split on any added newlines in any above parsing.
+            if output != None:
+                for separated in output.split('\n'):
+                    result.append(separated)
+
+            # Update the state machine when we find heading separators.
+            if line.startswith('----------'):
+                if prev.startswith('Descriptions'):
+                    descriptions = True
+                if prev.startswith('Maintainers'):
+                    maintainers = True
+
+            # Retain previous line for state machine transitions.
+            prev = line
+
+        # Flush pending field contents.
+        if field_content != "":
+            for separated in field_content.split('\n'):
+                result.append(separated)
+
+        output = "\n".join(result)
+        # For debugging the pre-rendered results...
+        #print(output, file=open("/tmp/MAINTAINERS.rst", "w"))
+
+        self.state_machine.insert_input(
+          statemachine.string2lines(output), path)
+
+    def run(self):
+        """Include the MAINTAINERS file as part of this reST file."""
+        if not self.state.document.settings.file_insertion_enabled:
+            raise self.warning('"%s" directive disabled.' % self.name)
+
+        # Walk up source path directories to find Documentation/../
+        path = self.state_machine.document.attributes['source']
+        path = os.path.realpath(path)
+        tail = path
+        while tail != "Documentation" and tail != "":
+            (path, tail) = os.path.split(path)
+
+        # Append "MAINTAINERS"
+        path = os.path.join(path, "MAINTAINERS")
+
+        try:
+            self.state.document.settings.record_dependencies.add(path)
+            lines = self.parse_maintainers(path)
+        except IOError as error:
+            raise self.severe('Problems with "%s" directive path:\n%s.' %
+                      (self.name, ErrorString(error)))
+
+        return []