sansguidon/bookmarks
1
0
Fork 0
Code Issues 16 Pull Requests 1 Packages Projects 1 Releases Activity

fix for illegal byte sequence with sed on MacOS X

Browse Source
This commit is contained in:
Morgan 2019-10-16 22:29:34 +02:00
parent ff41f4f2e3
commit 9e6294e7d5
1 changed files with 5 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
top_words.sh
View File

@ -3,8 +3,11 @@ set -o errexit
set -o nounset set -o nounset
set -o pipefail set -o pipefail
cmd_args=" | sed -e 's/\[.*\]//g' \ sed_bin="LANG=C LC_CTYPE=C sed" # workaround for the illegal byte sequence on MacOS X
| sed 's!http\(s\)\{0,1\}://[^[:space:]]*!!g' \ # see also https://stackoverflow.com/questions/11287564/getting-sed-error-illegal-byte-sequence-in-bash
# and https://unix.stackexchange.com/questions/141420/tr-complains-of-illegal-byte-sequence
cmd_args=" | $sed_bin -e 's/\[.*\]//g' \
| $sed_bin 's!http\(s\)\{0,1\}://[^[:space:]]*!!g' \
| \grep --only-matching --extended-regexp '[a-zA-Z]{3,}' \ | \grep --only-matching --extended-regexp '[a-zA-Z]{3,}' \
| tr '[:upper:]' '[:lower:]' \ | tr '[:upper:]' '[:lower:]' \
| \grep --invert-match --word-regexp --fixed-strings --file=stopwords.txt \ | \grep --invert-match --word-regexp --fixed-strings --file=stopwords.txt \