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
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
|
# Copyright (c) 2016 Comcast Cable Communications Management, LLC.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at:
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# Generation template class
import logging, os,sys, cgi, json, jinja2, HTMLParser
# Classes register themselves in this dictionary
"""Mapping of known processors to their classes"""
siphons = {}
"""Mapping of known output formats to their classes"""
formats = {}
"""Generate rendered output for siphoned data."""
class Siphon(object):
# Set by subclasses
"""Our siphon name"""
name = None
# Set by subclasses
"""Name of an identifier used by this siphon"""
identifier = None
# Set by subclasses
"""The pyparsing object to use to parse with"""
_parser = None
"""The input data"""
_cmds = None
"""Group key to (directory,file) mapping"""
_group = None
"""Logging handler"""
log = None
"""Directory to look for siphon rendering templates"""
template_directory = None
"""Template environment, if we're using templates"""
_tplenv = None
def __init__(self, template_directory, format):
super(Siphon, self).__init__()
self.log = logging.getLogger("siphon.process.%s" % self.name)
# Get our output format details
fmt_klass = formats[format]
fmt = fmt_klass()
self._format = fmt
# Sort out the template search path
def _tpldir(name):
return os.sep.join((template_directory, fmt.name, name))
self.template_directory = template_directory
searchpath = [
_tpldir(self.name),
_tpldir("default"),
]
loader = jinja2.FileSystemLoader(searchpath=searchpath)
self._tplenv = jinja2.Environment(
loader=loader,
trim_blocks=True,
keep_trailing_newline=True)
# Convenience, get a reference to the internal escape and
# unescape methods in cgi and HTMLParser. These then become
# available to templates to use, if needed.
self._h = HTMLParser.HTMLParser()
self.escape = cgi.escape
self.unescape = self._h.unescape
# Output renderers
"""Returns an object to be used as the sorting key in the item index."""
def index_sort_key(self, group):
return group
"""Returns a string to use as the header at the top of the item index."""
def index_header(self):
return self.template("index_header")
"""Returns the string fragment to use for each section in the item
index."""
def index_section(self, group):
return self.template("index_section", group=group)
"""Returns the string fragment to use for each entry in the item index."""
def index_entry(self, meta, item):
return self.template("index_entry", meta=meta, item=item)
"""Returns an object, typically a string, to be used as the sorting key
for items within a section."""
def item_sort_key(self, item):
return item['name']
"""Returns a key for grouping items together."""
def group_key(self, directory, file, macro, name):
_global = self._cmds['_global']
if file in _global and 'group_label' in _global[file]:
self._group[file] = (directory, file)
return file
self._group[directory] = (directory, None)
return directory
"""Returns a key for identifying items within a grouping."""
def item_key(self, directory, file, macro, name):
return name
"""Returns a string to use as the header when rendering the item."""
def item_header(self, group):
return self.template("item_header", group=group)
"""Returns a string to use as the body when rendering the item."""
def item_format(self, meta, item):
return self.template("item_format", meta=meta, item=item)
"""Returns a string to use as the label for the page reference."""
def page_label(self, group):
return "_".join((
self.name,
self.sanitize_label(group)
))
"""Returns a title to use for a page."""
def page_title(self, group):
_global = self._cmds['_global']
(directory, file) = self._group[group]
if file and file in _global and 'group_label' in _global[file]:
return _global[file]['group_label']
if directory in _global and 'group_label' in _global[directory]:
return _global[directory]['group_label']
return directory
"""Returns a string to use as the label for the section reference."""
def item_label(self, group, item):
return "__".join((
self.name,
item
))
"""Label sanitizer; for creating Doxygen references"""
def sanitize_label(self, value):
return value.replace(" ", "_") \
.replace("/", "_") \
.replace(".", "_")
"""Template processor"""
def template(self, name, **kwargs):
tpl = self._tplenv.get_template(name + self._format.extension)
return tpl.render(
this=self,
**kwargs)
# Processing methods
"""Parse the input file into a more usable dictionary structure."""
def load_json(self, files):
self._cmds = {}
self._group = {}
line_num = 0
line_start = 0
for filename in files:
filename = os.path.relpath(filename)
self.log.info("Parsing items in file \"%s\"." % filename)
data = None
with open(filename, "r") as fd:
data = json.load(fd)
self._cmds['_global'] = data['global']
# iterate the items loaded and regroup it
for item in data["items"]:
try:
o = self._parser.parse(item['block'])
except:
self.log.error("Exception parsing item: %s\n%s" \
% (json.dumps(item, separators=(',', ': '),
indent=4),
item['block']))
raise
# Augment the item with metadata
o["meta"] = {}
for key in item:
if key == 'block':
continue
o['meta'][key] = item[key]
# Load some interesting fields
directory = item['directory']
file = item['file']
macro = o["macro"]
name = o["name"]
# Generate keys to group items by
group_key = self.group_key(directory, file, macro, name)
item_key = self.item_key(directory, file, macro, name)
if group_key not in self._cmds:
self._cmds[group_key] = {}
self._cmds[group_key][item_key] = o
"""Iterate over the input data, calling render methods to generate the
output."""
def process(self, out=None):
if out is None:
out = sys.stdout
# Accumulated body contents
contents = ""
# Write the header for this siphon type
out.write(self.index_header())
# Sort key helper for the index
def group_sort_key(group):
return self.index_sort_key(group)
# Iterate the dictionary and process it
for group in sorted(self._cmds.keys(), key=group_sort_key):
if group.startswith('_'):
continue
self.log.info("Processing items in group \"%s\" (%s)." % \
(group, group_sort_key(group)))
# Generate the section index entry (write it now)
out.write(self.index_section(group))
# Generate the item header (save for later)
contents += self.item_header(group)
def item_sort_key(key):
return self.item_sort_key(self._cmds[group][key])
for key in sorted(self._cmds[group].keys(), key=item_sort_key):
self.log.debug("--- Processing key \"%s\" (%s)." % \
(key, item_sort_key(key)))
o = self._cmds[group][key]
meta = {
"directory": o['meta']['directory'],
"file": o['meta']['file'],
"macro": o['macro'],
"name": o['name'],
"key": key,
"label": self.item_label(group, key),
}
# Generate the index entry for the item (write it now)
out.write(self.index_entry(meta, o))
# Generate the item itself (save for later)
contents += self.item_format(meta, o)
# Deliver the accumulated body output
out.write(contents)
"""Output format class"""
class Format(object):
"""Name of this output format"""
name = None
"""Expected file extension of templates that build this format"""
extension = None
"""Markdown output format"""
class FormatMarkdown(Format):
name = "markdown"
extension = ".md"
# Register 'markdown'
formats["markdown"] = FormatMarkdown
"""Itemlist output format"""
class FormatItemlist(Format):
name = "itemlist"
extension = ".itemlist"
# Register 'itemlist'
formats["itemlist"] = FormatItemlist
|
