From 2d1e8a273dc45fc10f4d5628e406ab970b720381 Mon Sep 17 00:00:00 2001 From: Louie S Date: Tue, 16 Jan 2024 09:31:12 -0500 Subject: Index terms --- src/index-pages.sh | 34 ++++++++++++++++++++++++++++++++++ src/index-terms.sh | 37 +++++++++++++++++++++++++++++++++++++ src/index.sh | 34 ---------------------------------- 3 files changed, 71 insertions(+), 34 deletions(-) create mode 100755 src/index-pages.sh create mode 100755 src/index-terms.sh delete mode 100755 src/index.sh (limited to 'src') diff --git a/src/index-pages.sh b/src/index-pages.sh new file mode 100755 index 0000000..0b6e693 --- /dev/null +++ b/src/index-pages.sh @@ -0,0 +1,34 @@ +#!/usr/bin/env sh + +# shellcheck source=./lib/create_table +. "$(dirname "$0")"/lib/create_table +# shellcheck source=./lib/insert +. "$(dirname "$0")"/lib/insert + +DB_PATH="$1" +shift + +get_title() { + FILE="$1" + + pup -p -f "$FILE" 'title text{}' | \ + tr -d \\n | \ + sed 's/\"/\"\"/g' +} + +insert_pages() { + # Get title and insert into table for each html file + while [ -n "$1" ]; do + unset PAGE_NAME + unset PAGE_TYPE + PAGE_NAME="$(get_title "$1")" + PAGE_TYPE="Guide" + if [ -n "$PAGE_NAME" ]; then + insert "$DB_PATH" "$PAGE_NAME" "$PAGE_TYPE" "$(basename "$1")" + fi + shift + done +} + +create_table "$DB_PATH" +insert_pages "$@" diff --git a/src/index-terms.sh b/src/index-terms.sh new file mode 100755 index 0000000..a7cd014 --- /dev/null +++ b/src/index-terms.sh @@ -0,0 +1,37 @@ +#!/usr/bin/env sh + +# shellcheck source=./lib/create_table +. "$(dirname "$0")"/lib/create_table +# shellcheck source=./lib/insert +. "$(dirname "$0")"/lib/insert + +TYPE="$1" +shift +CATEGORY="$1" # should refer to how the href is "Reference-manual_$CATEGORY" +shift +DB_PATH="$1" +shift + +insert_index_terms() { + # Get each term from an index page and insert + while [ -n "$1" ]; do + while read -r line; do + if echo "$line" | pup -p 'a' | grep -Eoq "Reference-manual_$CATEGORY"; then + insert_term "$line" + fi + done < "$1" + + 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 "$@" diff --git a/src/index.sh b/src/index.sh deleted file mode 100755 index 0b6e693..0000000 --- a/src/index.sh +++ /dev/null @@ -1,34 +0,0 @@ -#!/usr/bin/env sh - -# shellcheck source=./lib/create_table -. "$(dirname "$0")"/lib/create_table -# shellcheck source=./lib/insert -. "$(dirname "$0")"/lib/insert - -DB_PATH="$1" -shift - -get_title() { - FILE="$1" - - pup -p -f "$FILE" 'title text{}' | \ - tr -d \\n | \ - sed 's/\"/\"\"/g' -} - -insert_pages() { - # Get title and insert into table for each html file - while [ -n "$1" ]; do - unset PAGE_NAME - unset PAGE_TYPE - PAGE_NAME="$(get_title "$1")" - PAGE_TYPE="Guide" - if [ -n "$PAGE_NAME" ]; then - insert "$DB_PATH" "$PAGE_NAME" "$PAGE_TYPE" "$(basename "$1")" - fi - shift - done -} - -create_table "$DB_PATH" -insert_pages "$@" -- cgit