1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
|
#!/usr/bin/env python3
# SPDX-License-Identifier: LGPL-2.1-or-later
import sys
import collections
import re
import concurrent.futures
from xml_helper import xml_parse, xml_print, tree
COLOPHON = '''\
This index contains {count} entries in {sections} sections,
referring to {pages} individual manual pages.
'''
def _extract_directives(page, names):
directive_groups = {name:collections.defaultdict(set) for name in names}
t = xml_parse(page)
section = t.find('./refmeta/manvolnum').text
pagename = t.find('./refmeta/refentrytitle').text
formatting = {}
storopt = directive_groups['options']
for variablelist in t.iterfind('.//variablelist'):
klass = variablelist.attrib.get('class')
searchpath = variablelist.attrib.get('xpath','./varlistentry/term/varname')
storvar = directive_groups[klass or 'miscellaneous']
# <option>s go in OPTIONS, unless class is specified
for xpath, stor in ((searchpath, storvar),
('./varlistentry/term/option',
storvar if klass else storopt)):
for name in variablelist.iterfind(xpath):
text = re.sub(r'([= ]).*', r'\1', name.text).rstrip()
if text.startswith('-'):
# for options, merge options with and without mandatory arg
text = text.partition('=')[0]
stor[text].add((pagename, section))
if text not in formatting:
# use element as formatted display
if name.text[-1] in "= '":
name.clear()
else:
name.tail = ''
name.text = text
formatting[text] = name
extra = variablelist.attrib.get('extra-ref')
if extra:
stor[extra].add((pagename, section))
if extra not in formatting:
elt = tree.Element("varname")
elt.text= extra
formatting[extra] = elt
storfile = directive_groups['filenames']
for xpath, absolute_only in (('.//refsynopsisdiv//filename', False),
('.//refsynopsisdiv//command', False),
('.//filename', True)):
for name in t.iterfind(xpath):
if absolute_only and not (name.text and name.text.startswith('/')):
continue
if name.attrib.get('index') == 'false':
continue
name.tail = ''
if name.text:
if name.text.endswith('*'):
name.text = name.text[:-1]
if not name.text.startswith('.'):
text = name.text.partition(' ')[0]
if text != name.text:
name.clear()
name.text = text
if text.endswith('/'):
text = text[:-1]
storfile[text].add((pagename, section))
if text not in formatting:
# use element as formatted display
formatting[text] = name
else:
text = ' '.join(name.itertext())
storfile[text].add((pagename, section))
formatting[text] = name
storfile = directive_groups['constants']
for name in t.iterfind('.//constant'):
if name.attrib.get('index') == 'false':
continue
name.tail = ''
if name.text.startswith('('): # a cast, strip it
name.text = name.text.partition(' ')[2]
storfile[name.text].add((pagename, section))
formatting[name.text] = name
storfile = directive_groups['specifiers']
for name in t.iterfind(".//table[@class='specifiers']//entry/literal"):
if name.text[0] != '%' or name.getparent().text is not None:
continue
if name.attrib.get('index') == 'false':
continue
storfile[name.text].add((pagename, section))
formatting[name.text] = name
for name in t.iterfind(".//literal[@class='specifiers']"):
storfile[name.text].add((pagename, section))
formatting[name.text] = name
# Serialize to allow pickling
formatting = {name:xml_print(value) for name, value in formatting.items()}
return directive_groups, formatting
def extract_directives(arg):
page, names = arg
try:
return _extract_directives(page, names)
except Exception:
raise ValueError("Failed to process {}".format(page))
def _make_section(template, name, directives, formatting):
varlist = template.find(".//*[@id='{}']".format(name))
for varname, manpages in sorted(directives.items()):
entry = tree.SubElement(varlist, 'varlistentry')
term = tree.SubElement(entry, 'term')
display = tree.fromstring(formatting[varname])
term.append(display)
para = tree.SubElement(tree.SubElement(entry, 'listitem'), 'para')
b = None
for manpage, manvolume in sorted(set(manpages)):
if b is not None:
b.tail = ', '
b = tree.SubElement(para, 'citerefentry')
c = tree.SubElement(b, 'refentrytitle')
c.text = manpage
c.attrib['target'] = varname
d = tree.SubElement(b, 'manvolnum')
d.text = manvolume
entry.tail = '\n\n'
def _make_colophon(template, groups):
count = 0
pages = set()
for group in groups:
count += len(group)
for pagelist in group.values():
pages |= set(pagelist)
para = template.find(".//para[@id='colophon']")
para.text = COLOPHON.format(count=count,
sections=len(groups),
pages=len(pages))
def _make_page(template, directive_groups, formatting):
"""Create an XML tree from directive_groups.
directive_groups = {
'class': {'variable': [('manpage', 'manvolume'), ...],
'variable2': ...},
...
}
"""
for name, directives in directive_groups.items():
_make_section(template, name, directives, formatting)
_make_colophon(template, directive_groups.values())
return template
def make_page(template_path, xml_files):
"Extract directives from xml_files and return XML index tree."
template = xml_parse(template_path)
names = [vl.get('id') for vl in template.iterfind('.//variablelist')]
with concurrent.futures.ProcessPoolExecutor() as pool:
args = ((xml_file, names) for xml_file in xml_files)
results = list(pool.map(extract_directives, args))
directive_groups = {name:collections.defaultdict(set) for name in names}
formatting = {}
for d_g, f in reversed(results):
for group, mapping in d_g.items():
for name, value in mapping.items():
directive_groups[group][name].update(value)
formatting.update(f)
return _make_page(template, directive_groups, formatting)
def main(output, template_path, *xml_files):
with open(output, 'wb') as f:
xml = make_page(template_path, xml_files)
f.write(xml_print(xml))
if __name__ == '__main__':
main(*sys.argv[1:])
|
