make-man-index.py

   1 #  -*- Mode: python; coding: utf-8; indent-tabs-mode: nil -*- */
   2 #
   3 #  This file is part of systemd.
   4 #
   5 #  Copyright 2012 Lennart Poettering
   6 #  Copyright 2013 Zbigniew Jędrzejewski-Szmek
   7 #
   8 #  systemd is free software; you can redistribute it and/or modify it
   9 #  under the terms of the GNU Lesser General Public License as published by
  10 #  the Free Software Foundation; either version 2.1 of the License, or
  11 #  (at your option) any later version.
  12 #
  13 #  systemd is distributed in the hope that it will be useful, but
  14 #  WITHOUT ANY WARRANTY; without even the implied warranty of
  15 #  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
  16 #  Lesser General Public License for more details.
  17 #
  18 #  You should have received a copy of the GNU Lesser General Public License
  19 #  along with systemd; If not, see <http://www.gnu.org/licenses/>.
  20
  21 import collections
  22 try:
  23     from lxml import etree as tree
  24     PRETTY = dict(pretty_print=True)
  25 except ImportError:
  26     import xml.etree.ElementTree as tree
  27     PRETTY = {}
  28 import sys
  29 import re
  30 MDASH = ' — ' if sys.version_info.major >= 3 else ' -- '
  31
  32 TEMPLATE = '''\
  33 <refentry id="systemd.index" conditional="HAVE_PYTHON">
  34
  35   <refentryinfo>
  36     <title>systemd.index</title>
  37     <productname>systemd</productname>
  38
  39     <authorgroup>
  40       <author>
  41         <contrib>Developer</contrib>
  42         <firstname>Lennart</firstname>
  43         <surname>Poettering</surname>
  44         <email>lennart@poettering.net</email>
  45       </author>
  46     </authorgroup>
  47   </refentryinfo>
  48
  49   <refmeta>
  50     <refentrytitle>systemd.index</refentrytitle>
  51     <manvolnum>7</manvolnum>
  52   </refmeta>
  53
  54   <refnamediv>
  55     <refname>systemd.index</refname>
  56     <refpurpose>List all manpages from the systemd project</refpurpose>
  57   </refnamediv>
  58 </refentry>
  59 '''
  60
  61 SUMMARY = '''\
  62   <refsect1>
  63     <title>See Also</title>
  64     <para>
  65       <citerefentry><refentrytitle>systemd.directives</refentrytitle><manvolnum>7</manvolnum></citerefentry>
  66     </para>
  67
  68     <para id='counts' />
  69   </refsect1>
  70 '''
  71
  72 COUNTS = '\
  73 This index contains {count} entries, referring to {pages} individual manual pages.'
  74
  75 def check_id(page, t):
  76     id = t.getroot().get('id')
  77     if not re.search('/' + id + '[.]', page):
  78         raise ValueError("id='{}' is not the same as page name '{}'".format(id, page))
  79
  80 def make_index(pages):
  81     index = collections.defaultdict(list)
  82     for p in pages:
  83         t = tree.parse(p)
  84         check_id(p, t)
  85         section = t.find('./refmeta/manvolnum').text
  86         refname = t.find('./refnamediv/refname').text
  87         purpose = ' '.join(t.find('./refnamediv/refpurpose').text.split())
  88         for f in t.findall('./refnamediv/refname'):
  89             infos = (f.text, section, purpose, refname)
  90             index[f.text[0].upper()].append(infos)
  91     return index
  92
  93 def add_letter(template, letter, pages):
  94     refsect1 = tree.SubElement(template, 'refsect1')
  95     title = tree.SubElement(refsect1, 'title')
  96     title.text = letter
  97     para = tree.SubElement(refsect1, 'para')
  98     for info in sorted(pages, key=lambda info: str.lower(info[0])):
  99         refname, section, purpose, realname = info
 100
 101         b = tree.SubElement(para, 'citerefentry')
 102         c = tree.SubElement(b, 'refentrytitle')
 103         c.text = refname
 104         d = tree.SubElement(b, 'manvolnum')
 105         d.text = section
 106
 107         b.tail = MDASH + purpose # + ' (' + p + ')'
 108
 109         tree.SubElement(para, 'sbr')
 110
 111 def add_summary(template, indexpages):
 112     count = 0
 113     pages = set()
 114     for group in indexpages:
 115         count += len(group)
 116         for info in group:
 117             refname, section, purpose, realname = info
 118             pages.add((realname, section))
 119
 120     refsect1 = tree.fromstring(SUMMARY)
 121     template.append(refsect1)
 122
 123     para = template.find(".//para[@id='counts']")
 124     para.text = COUNTS.format(count=count, pages=len(pages))
 125
 126 def make_page(xml_files):
 127     template = tree.fromstring(TEMPLATE)
 128     index = make_index(xml_files)
 129
 130     for letter in sorted(index):
 131         add_letter(template, letter, index[letter])
 132
 133     add_summary(template, index.values())
 134
 135     return template
 136
 137 if __name__ == '__main__':
 138     tree.dump(make_page(sys.argv[1:]), **PRETTY)