diff options
Diffstat (limited to 'src/scripts/gnu')
-rwxr-xr-x | src/scripts/gnu/index-terms-class.sh | 35 | ||||
-rwxr-xr-x | src/scripts/gnu/index-terms-colon.sh (renamed from src/scripts/gnu/index-terms.sh) | 0 |
2 files changed, 35 insertions, 0 deletions
diff --git a/src/scripts/gnu/index-terms-class.sh b/src/scripts/gnu/index-terms-class.sh new file mode 100755 index 0000000..dc14178 --- /dev/null +++ b/src/scripts/gnu/index-terms-class.sh @@ -0,0 +1,35 @@ +#!/usr/bin/env sh + +# shellcheck source=../create_table.sh +. "$(dirname "$0")"/../create_table.sh +# shellcheck source=../insert.sh +. "$(dirname "$0")"/../insert.sh + +TYPE="$1" +shift +INDEX_ENTRY_CLASS="$1" +shift +DB_PATH="$1" +shift + +insert_index_terms() { + # Get each term from an index page and insert + while [ -n "$1" ]; do + grep -Eo "class=${INDEX_ENTRY_CLASS}.*<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 "$@" diff --git a/src/scripts/gnu/index-terms.sh b/src/scripts/gnu/index-terms-colon.sh index e82aff2..e82aff2 100755 --- a/src/scripts/gnu/index-terms.sh +++ b/src/scripts/gnu/index-terms-colon.sh |