tools/make-man-index.py

   1 #!/usr/bin/env python3
   2 #  -*- Mode: python; coding: utf-8; indent-tabs-mode: nil -*- */
   3 # SPDX-License-Identifier: LGPL-2.1+
   4
   5 import collections
   6 import sys
   7 import re
   8 from xml_helper import xml_parse, xml_print, tree
   9
  10 MDASH = ' — ' if sys.version_info.major >= 3 else ' -- '
  11
  12 TEMPLATE = '''\
  13 <refentry id="systemd.index" conditional="HAVE_PYTHON">
  14
  15   <refentryinfo>
  16     <title>systemd.index</title>
  17     <productname>systemd</productname>
  18
  19     <authorgroup>
  20       <author>
  21         <contrib>Developer</contrib>
  22         <firstname>Lennart</firstname>
  23         <surname>Poettering</surname>
  24         <email>lennart@poettering.net</email>
  25       </author>
  26     </authorgroup>
  27   </refentryinfo>
  28
  29   <refmeta>
  30     <refentrytitle>systemd.index</refentrytitle>
  31     <manvolnum>7</manvolnum>
  32   </refmeta>
  33
  34   <refnamediv>
  35     <refname>systemd.index</refname>
  36     <refpurpose>List all manpages from the systemd project</refpurpose>
  37   </refnamediv>
  38 </refentry>
  39 '''
  40
  41 SUMMARY = '''\
  42   <refsect1>
  43     <title>See Also</title>
  44     <para>
  45       <citerefentry><refentrytitle>systemd.directives</refentrytitle><manvolnum>7</manvolnum></citerefentry>
  46     </para>
  47
  48     <para id='counts' />
  49   </refsect1>
  50 '''
  51
  52 COUNTS = '\
  53 This index contains {count} entries, referring to {pages} individual manual pages.'
  54
  55
  56 def check_id(page, t):
  57     id = t.getroot().get('id')
  58     if not re.search('/' + id + '[.]', page):
  59         raise ValueError("id='{}' is not the same as page name '{}'".format(id, page))
  60
  61 def make_index(pages):
  62     index = collections.defaultdict(list)
  63     for p in pages:
  64         t = xml_parse(p)
  65         check_id(p, t)
  66         section = t.find('./refmeta/manvolnum').text
  67         refname = t.find('./refnamediv/refname').text
  68         purpose = ' '.join(t.find('./refnamediv/refpurpose').text.split())
  69         for f in t.findall('./refnamediv/refname'):
  70             infos = (f.text, section, purpose, refname)
  71             index[f.text[0].upper()].append(infos)
  72     return index
  73
  74 def add_letter(template, letter, pages):
  75     refsect1 = tree.SubElement(template, 'refsect1')
  76     title = tree.SubElement(refsect1, 'title')
  77     title.text = letter
  78     para = tree.SubElement(refsect1, 'para')
  79     for info in sorted(pages, key=lambda info: str.lower(info[0])):
  80         refname, section, purpose, realname = info
  81
  82         b = tree.SubElement(para, 'citerefentry')
  83         c = tree.SubElement(b, 'refentrytitle')
  84         c.text = refname
  85         d = tree.SubElement(b, 'manvolnum')
  86         d.text = section
  87
  88         b.tail = MDASH + purpose # + ' (' + p + ')'
  89
  90         tree.SubElement(para, 'sbr')
  91
  92 def add_summary(template, indexpages):
  93     count = 0
  94     pages = set()
  95     for group in indexpages:
  96         count += len(group)
  97         for info in group:
  98             refname, section, purpose, realname = info
  99             pages.add((realname, section))
 100
 101     refsect1 = tree.fromstring(SUMMARY)
 102     template.append(refsect1)
 103
 104     para = template.find(".//para[@id='counts']")
 105     para.text = COUNTS.format(count=count, pages=len(pages))
 106
 107 def make_page(*xml_files):
 108     template = tree.fromstring(TEMPLATE)
 109     index = make_index(xml_files)
 110
 111     for letter in sorted(index):
 112         add_letter(template, letter, index[letter])
 113
 114     add_summary(template, index.values())
 115
 116     return template
 117
 118 if __name__ == '__main__':
 119     with open(sys.argv[1], 'wb') as f:
 120         f.write(xml_print(make_page(*sys.argv[2:])))