diff options
Diffstat (limited to 'htmtojargon.awk')
| -rw-r--r-- | htmtojargon.awk | 5 |
1 files changed, 5 insertions, 0 deletions
diff --git a/htmtojargon.awk b/htmtojargon.awk index 16c5356..323b7ee 100644 --- a/htmtojargon.awk +++ b/htmtojargon.awk @@ -1,5 +1,6 @@ #!/usr/bin/awk -f # dirty xml reading is more fun +# requires nawk / gawk for sub() BEGIN { FS = "</hg>" @@ -8,6 +9,10 @@ BEGIN { { printdefs($1, $2); } function printdefs(word, defs) { + # split the headwords and other information about the word, + # to be used in conjuction with dictfmt's --index-data-separator + sub("<i>", " ", word); + n = split(defs, array, "<def>"); for(i=0; i<=n; i++) { if(array[i] != "") { |