diff --git a/doc/README.Converters.md b/doc/README.Converters.md index 32a73f72f..8c4e5df98 100644 --- a/doc/README.Converters.md +++ b/doc/README.Converters.md @@ -29,37 +29,35 @@ php-fpm's configuration. On Debian this is done in the file Conversion to text for fulltext search ======================================= -text/plain -text/csv -application/csv - cat '%s' +* text/plain, text/csv, application/csv + `cat '%s'` -application/pdf - pdftotext -q -nopgbrk %s - | sed -e 's/ [a-zA-Z0-9.]\{1\} / /g' -e 's/[0-9.]//g' +* application/pdf + `pdftotext -q -nopgbrk %s - | sed -e 's/ [a-zA-Z0-9.]\{1\} / /g' -e 's/[0-9.]//g'` If pdftotext takes too long on large document you may want to pass parameter - -l to specify the last page to be converted. -q is for suppressing error/warnings + `-l` to specify the last page to be converted. `-q` is for suppressing error/warnings send to stderr - mutool draw -F txt -q -N -o - %s + `mutool draw -F txt -q -N -o - %s ` -application/vnd.openxmlformats-officedocument.wordprocessingml.document - docx2txt '%s' - +* application/vnd.openxmlformats-officedocument.wordprocessingml.document + `docx2txt '%s' -` -application/msword - catdoc %s +* application/msword + `catdoc %s` -application/vnd.oasis.opendocument.text - odt2txt %s +* application/vnd.oasis.opendocument.text + `odt2txt %s` -application/vnd.openxmlformats-officedocument.spreadsheetml.sheet - xlsx2csv -d tab %s +* application/vnd.openxmlformats-officedocument.spreadsheetml.sheet + `xlsx2csv -d tab %s` -application/vnd.ms-excel - xls2csv -d tab %s +* application/vnd.ms-excel + `xls2csv -d tab %s` -text/html - html2text %s +* text/html + `html2text %s` Many office formats unoconv -d document -f txt --stdout '%s'