diff options
Diffstat (limited to 'src')
-rwxr-xr-x | src/index-page.sh (renamed from src/index.sh) | 0 | ||||
-rwxr-xr-x | src/index-terms.sh | 33 |
2 files changed, 33 insertions, 0 deletions
diff --git a/src/index.sh b/src/index-page.sh index 7a1b60d..7a1b60d 100755 --- a/src/index.sh +++ b/src/index-page.sh diff --git a/src/index-terms.sh b/src/index-terms.sh new file mode 100755 index 0000000..f74af03 --- /dev/null +++ b/src/index-terms.sh @@ -0,0 +1,33 @@ +#!/usr/bin/env sh + +# shellcheck source=./lib/create_table +. "$(dirname "$0")"/lib/create_table +# shellcheck source=./lib/insert +. "$(dirname "$0")"/lib/insert + +TYPE="$1" +shift +DB_PATH="$1" +shift + +insert_index_terms() { + # Get each term from an index page and insert + while [ -n "$1" ]; do + grep -Eo "<a href.*</a>:" "$1" | while read -r line; do + insert_term "$line" + done + + shift + done +} + +insert_term() { + LINK="$1" + NAME="$(echo "$LINK" | pup -p 'a text{}' | sed 's/\"\"//g' | tr -d \\n)" + PAGE_PATH="$(echo "$LINK" | pup -p 'a attr{href}')" + + insert "$DB_PATH" "$NAME" "$TYPE" "$PAGE_PATH" +} + +create_table "$DB_PATH" +insert_index_terms "$@" |