summaryrefslogtreecommitdiffstats
path: root/util/bin
diff options
context:
space:
mode:
authortv <tv@nomic.retiolum>2013-09-02 16:34:52 +0200
committertv <tv@nomic.retiolum>2013-09-02 16:34:52 +0200
commit0e0be4892ca1ab6af60e1e2067b098b98e8de466 (patch)
treeba5b15b3ebd99c868d9438032b4cb711e24b0d3a /util/bin
parent9324d6dd679ca1da2433e83aa1ba174f22f9908a (diff)
util bin dic: initial import from the past
Diffstat (limited to 'util/bin')
-rwxr-xr-xutil/bin/dic84
1 files changed, 84 insertions, 0 deletions
diff --git a/util/bin/dic b/util/bin/dic
new file mode 100755
index 00000000..d9f0a77f
--- /dev/null
+++ b/util/bin/dic
@@ -0,0 +1,84 @@
+#! /bin/sh
+# usage: dic WORD [LANG]
+# where LANG may be one of en, fr, es, it, ch, ru, pt, pl
+# multiple WORDs may be seperated by + like this: multiple+words
+set -euf
+
+# all three are used by GET
+search="$1"
+langlang="${2-en}de"
+lang="de"
+
+main() {
+ GET | simplify | tac
+}
+
+GET() {
+ curl -sS -b 'LEOABTEST=T; browser=webkit%3B5%3Bajax' \
+ "https://dict.leo.org/dictQuery/m-vocab/$langlang/query.xml?tolerMode=nof&lp=$langlang&lang=$lang&rmWords=off&rmSearch=on&search=$search&searchLoc=0&resultOrder=basic&multiwordShowSingle=on"
+}
+
+simplify() {
+ sed '
+ s|<repr>|\nREPR: |g
+ s|</repr>|\n|g
+ ' | grep ^REPR |
+ sed '
+ s/^REPR: //
+ 1~2{s/$//}
+ 2~2{s/$//}
+ ' |
+ tr -d \\n |
+ sed '
+ s// - /g
+ s//\n/g
+
+ #q
+
+ s/&#8660;/⇔/g
+ s/&#160;/ /g; # &nbsp;
+ s/ */ /g
+
+ # <!-- undefined_translation: en:pl_ext -->
+ s/ *<!--[^>]*-->//g
+
+ s|<i> *|/|g
+ s| *</i>|/|g
+
+ s:<sup>1</sup>:¹:g; s:<sup>2</sup>:²:g; s:<sup>3</sup>:³:g;
+ s:<sup>:^(:g
+ s:</sup>:):g
+
+ s:<sub>0</sub>:₀:g;
+ s:<sub>1</sub>:₁:g; s:<sub>2</sub>:₂:g; s:<sub>3</sub>:₃:g;
+ s:<sub>4</sub>:₄:g; s:<sub>5</sub>:₅:g; s:<sub>6</sub>:₆:g;
+ s:<sub>7</sub>:₇:g; s:<sub>8</sub>:₈:g; s:<sub>9</sub>:₉:g;
+ s:<sub>:_(:g
+ s:</sub>:):g
+
+ s:<b> *::g
+ s: *</b>::g
+
+ s|<small> *||g
+ s| *</small>||g
+
+ '
+}
+
+main "$@"
+exit
+
+ #s|<repr>\([^<]\|<[^/]\|</[^r]\|</r[^e]\|</re[^p]\|</rep[^r]\|</repr[^>]\)*</repr>|\nREPR: &\n|g
+ #s/<xml[^>]*>//g
+ #s/<[^>]*>//g
+| {
+ IFS="`printf '\t'`"
+ while read a b; do
+ printf '%30s %-30s\n' "$a" "$b"
+ done
+}
+}
+#| tr -d \\n |
+#tr \\n
+#s/^REPR: /en:/;
+#s/^REPR: /de:/;