diff options
Diffstat (limited to 'src/index_terms.sh')
-rwxr-xr-x | src/index_terms.sh | 39 |
1 files changed, 39 insertions, 0 deletions
diff --git a/src/index_terms.sh b/src/index_terms.sh new file mode 100755 index 0000000..a2b39fb --- /dev/null +++ b/src/index_terms.sh @@ -0,0 +1,39 @@ +#!/usr/bin/env sh + +# shellcheck source=./lib/create_table +. "$(dirname "$0")"/lib/create_table +# shellcheck source=./lib/insert +. "$(dirname "$0")"/lib/insert +# shellcheck source=./lib/get_type +. "$(dirname "$0")"/lib/get_type + +DB_PATH="$1" +shift + +insert_index_terms() { + # Get each term from an index page and insert + while [ -n "$1" ]; do + grep -Eoi "^[a-zA-Z_ ]{45}<STRONG><A HREF=\"[^\"]*\">[^<]*</A></STRONG>" "$1" | while read -r line; do + insert_term "$line" + done + + shift + done +} + +insert_term() { + LINK="$1" + #NAME="$(echo "$LINK" | pup -p 'a text{}' | sed 's/\"\"//g' | tr -d \\n)" + NAME="$(echo "$LINK" | cut -d ' ' -f 1)" + PAGE_PATH="$(echo "$LINK" | pup -p 'a attr{href}')" + + TYPE=$(get_type "$PAGE_PATH") + if [ -z "$TYPE" ]; then + TYPE="Guide" + fi + + insert "$DB_PATH" "$NAME" "$TYPE" "man/$PAGE_PATH" +} + +create_table "$DB_PATH" +insert_index_terms "$@" |