p/tdv
1
1
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Add sample dictionary downloaders/builders

Browse Source
This commit is contained in:
Přemysl Eric Janouch
2021-10-07 03:37:12 +02:00
parent 3881725904
commit ed8b1bcdad
4 changed files with 47 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
dicts/slovnik-cizich-slov.sh Executable file
View File

@@ -0,0 +1,8 @@
#!/bin/sh -e
# Slovník cizích slov, see https://slovnik-cizich-slov.abz.cz/web.php/o-slovniku
# TODO: Skipping the optional pronunciation field, tabfile can't handle it yet,
# but could be made to accept a lowercase sametypesequence
curl -Lo- https://slovnik-cizich-slov.abz.cz/export.php | \
iconv -f latin2 -t UTF-8 | perl -CSD -F\\\| -le '
print "$_\t" . $F[2] =~ s/\\/\\\\/gr =~ s/; /\\n/gr for split(", ", $F[0])
' | sort -u | tabfile slovnik-cizich-slov