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
|
#!/bin/sh
# update feeds, merge with old feeds.
# NOTE: assumes "sfeed_*" executables are in $PATH.
# defaults
sfeedpath="$HOME/.sfeed/feeds"
# used for processing feeds concurrently: wait until ${maxjobs} amount of
# feeds are finished at a time.
maxjobs=16
# load config (evaluate shellscript).
# loadconfig(configfile)
loadconfig() {
# allow to specify config via argv[1].
if [ "$1" != "" ]; then
# get absolute path of config file required for including.
config="$1"
configpath=$(readlink -f "${config}" 2>/dev/null)
else
# default config location.
config="$HOME/.sfeed/sfeedrc"
configpath="${config}"
fi
# config is loaded here to be able to override $sfeedpath or functions.
if [ -r "${configpath}" ] && [ -f "${configpath}" ]; then
. "${configpath}"
else
printf "Configuration file \"%s\" cannot be read.\n" "${config}" >&2
echo "See the sfeedrc.example file or the sfeedrc(5) man page for an example." >&2
die
fi
}
# log(name, s)
log() {
printf '[%s] %-50.50s %s\n' "$(date +'%H:%M:%S')" "$1" "$2"
}
# log_error(name, s)
log_error() {
printf '[%s] %-50.50s %s\n' "$(date +'%H:%M:%S')" "$1" "$2" >&2
# set error exit status indicator for parallel jobs.
rm -f "${sfeedtmpdir}/ok"
}
# fetch a feed via HTTP/HTTPS etc.
# fetch(name, url, feedfile)
fetch() {
# fail on redirects, hide User-Agent, timeout is 15 seconds.
curl -L --max-redirs 0 -H "User-Agent:" -f -s -m 15 \
"$2" 2>/dev/null
}
# convert encoding from one encoding to another.
# convertencoding(name, from, to)
convertencoding() {
if [ "$2" != "" ] && [ "$3" != "" ] && [ "$2" != "$3" ]; then
iconv -cs -f "$2" -t "$3" 2> /dev/null
else
# else no convert, just output.
cat
fi
}
# parse and convert input, by default XML to the sfeed(5) TSV format.
# parse(name, feedurl, basesiteurl)
parse() {
sfeed "$3"
}
# filter fields.
# filter(name, url)
filter() {
cat
}
# merge raw files: unique sort by id, title, link.
# merge(name, oldfile, newfile)
merge() {
sort -t ' ' -u -k6,6 -k2,2 -k3,3 "$2" "$3" 2>/dev/null
}
# order by timestamp (descending).
# order(name, url)
order() {
sort -t ' ' -k1rn,1 2>/dev/null
}
# internal handler to fetch and process a feed.
# _feed(name, feedurl, [basesiteurl], [encoding])
_feed() {
name="$1"
feedurl="$2"
basesiteurl="$3"
encoding="$4"
filename="$(printf '%s' "${name}" | tr '/' '_')"
sfeedfile="${sfeedpath}/${filename}"
tmpfeedfile="${sfeedtmpdir}/feeds/${filename}"
# if file does not exist yet create it.
[ -e "${sfeedfile}" ] || touch "${sfeedfile}" 2>/dev/null
if ! fetch "${name}" "${feedurl}" "${sfeedfile}" > "${tmpfeedfile}.fetch"; then
log_error "${name}" "FAIL (FETCH)"
return 1
fi
# try to detect encoding (if not specified). if detecting the encoding fails assume utf-8.
[ "${encoding}" = "" ] && encoding=$(sfeed_xmlenc < "${tmpfeedfile}.fetch")
if ! convertencoding "${name}" "${encoding}" "utf-8" < "${tmpfeedfile}.fetch" > "${tmpfeedfile}.utf8"; then
log_error "${name}" "FAIL (ENCODING)"
return 1
fi
rm -f "${tmpfeedfile}.fetch"
# if baseurl is empty then use feedurl.
if ! parse "${name}" "${feedurl}" "${basesiteurl:-${feedurl}}" < "${tmpfeedfile}.utf8" > "${tmpfeedfile}.tsv"; then
log_error "${name}" "FAIL (PARSE)"
return 1
fi
rm -f "${tmpfeedfile}.utf8"
if ! filter "${name}" "${feedurl}" < "${tmpfeedfile}.tsv" > "${tmpfeedfile}.filter"; then
log_error "${name}" "FAIL (FILTER)"
return 1
fi
rm -f "${tmpfeedfile}.tsv"
# new feed data is empty: no need for below stages.
if [ ! -s "${tmpfeedfile}.filter" ]; then
log "${name}" "OK"
return 0
fi
if ! merge "${name}" "${sfeedfile}" "${tmpfeedfile}.filter" > "${tmpfeedfile}.merge"; then
log_error "${name}" "FAIL (MERGE)"
return 1
fi
rm -f "${tmpfeedfile}.filter"
if ! order "${name}" "${feedurl}" < "${tmpfeedfile}.merge" > "${tmpfeedfile}.order"; then
log_error "${name}" "FAIL (ORDER)"
return 1
fi
rm -f "${tmpfeedfile}.merge"
# copy
if ! cp "${tmpfeedfile}.order" "${sfeedfile}"; then
log_error "${name}" "FAIL (COPY)"
return 1
fi
rm -f "${tmpfeedfile}.order"
# OK
log "${name}" "OK"
return 0
}
# fetch and process a feed in parallel.
# feed(name, feedurl, [basesiteurl], [encoding])
feed() {
# Output job parameters for xargs.
# Specify fields as a single parameter separated by a NUL byte.
# The parameter is split into fields later by the child process, this
# allows using xargs with empty fields across many implementations.
printf '%s\037%s\037%s\037%s\037%s\037%s\0' \
"${config}" "${sfeedtmpdir}" "$1" "$2" "$3" "$4"
}
# cleanup()
cleanup() {
# remove temporary directory with feed files.
rm -rf "${sfeedtmpdir}"
}
# die(statuscode)
die() {
statuscode="${1:-1}" # default: exit 1
# cleanup temporary files etc.
cleanup
exit "${statuscode}"
}
# sighandler(signo)
sighandler() {
signo="$1"
# ignore TERM signal for myself.
trap -- "" TERM
# kill all running children >:D
kill -TERM -$$
}
# feeds()
feeds() {
printf "Configuration file \"%s\" is invalid or does not contain a \"feeds\" function.\n" "${config}" >&2
echo "See sfeedrc.example for an example." >&2
die
}
# main(args...)
main() {
# signal number received for parent.
signo=0
# SIGINT: signal to interrupt parent.
trap -- "sighandler 2" "INT"
# SIGTERM: signal to terminate parent.
trap -- "sighandler 15" "TERM"
# load config file.
loadconfig "$1"
# fetch feeds and store in temporary directory.
sfeedtmpdir="$(mktemp -d "${TMPDIR:-/tmp}/sfeed_XXXXXX")" || die
mkdir -p "${sfeedtmpdir}/feeds"
touch "${sfeedtmpdir}/ok" || die
# make sure path exists.
mkdir -p "${sfeedpath}"
# print feeds for parallel processing with xargs.
feeds > "${sfeedtmpdir}/jobs" || die
SFEED_UPDATE_CHILD="1" xargs -x -0 -P "${maxjobs}" -n 1 \
"$(readlink -f "${argv0}")" < "${sfeedtmpdir}/jobs"
statuscode=$?
# check error exit status indicator for parallel jobs.
[ -f "${sfeedtmpdir}/ok" ] || statuscode=1
# on signal SIGINT and SIGTERM exit with signal number + 128.
[ ${signo} -ne 0 ] && die $((signo+128))
die ${statuscode}
}
# process a single feed.
# parameters are: config, tmpdir, name, feedurl, basesiteurl, encoding
if [ "${SFEED_UPDATE_CHILD}" = "1" ]; then
IFS="" # "\037"
[ "$1" = "" ] && exit 0 # must have an argument set
printf '%s\n' "$1" | \
while read -r _config _tmpdir _name _feedurl _basesiteurl _encoding; do
loadconfig "${_config}"
sfeedtmpdir="${_tmpdir}"
_feed "${_name}" "${_feedurl}" "${_basesiteurl}" "${_encoding}"
exit "$?"
done
exit 0
fi
# ...else parent mode:
argv0="$0" # store $0, in the zsh shell $0 is the name of the function.
[ "${SFEED_UPDATE_INCLUDE}" = "1" ] || main "$@"
|