metadata scripts

quiethost/metadata_rank_from_list.py

@@ -0,0 +1,205 @@
+#!/usr/bin/env python3
+
+import argparse
+import re
+import subprocess
+from pathlib import Path
+from difflib import SequenceMatcher
+from turtledemo.lindenmayer import replace
+
+AUDIO_EXTENSIONS = {
+    ".mp3",
+    ".m4b",
+    ".m4a",
+}
+
+RED = "\033[31m"
+GREEN = "\033[32m"
+RESET = "\033[0m"
+USE_KID3 = True
+def normalize(text: str) -> str:
+    return re.sub(r"[^a-z0-9]", "", text.lower())
+
+
+def get_tag(path, tag):
+    if USE_KID3:
+        result = subprocess.run(
+            ["kid3-cli", "-c", f"get {tag}", str(path)],
+            capture_output=True,
+            text=True,
+            check=True,
+        )
+        return result.stdout.strip()
+
+    # id3v2 frame mapping
+    frames = {
+        "album": "TALB",
+        "artist": "TPE1",
+        "title": "TIT2",
+        "year": "TYER",
+        "grouping": "TIT1",  # Content group description
+        "work": "TIT1",      # No separate WORK frame in id3v2
+    }
+
+    frame = frames[tag]
+
+    result = subprocess.run(
+        ["id3v2", "-R", str(path)],
+        capture_output=True,
+        text=True,
+        check=True,
+    )
+
+    for line in result.stdout.splitlines():
+        if line.startswith(frame):
+            return line.split(":", 1)[1].strip()
+
+    return ""
+
+def tag_file(path: Path, rank: int, year: str, dry_run: bool):
+    work = get_tag(path, "work")
+    grouping = get_tag(path, "grouping")
+    existing_year = get_tag(path, "year")
+
+    if work:
+        tag = "work"
+        existing = work
+    elif grouping:
+        tag = "grouping"
+        existing = grouping
+    else:
+        tag = "grouping"
+        existing = ""
+    pattern = r"Top 100 SciFi Books #\d+"
+#    pattern = r"Enderverse"
+    replace = r"Top 100 SciFi Books"
+    if existing:
+        if re.search(pattern, existing):
+            new_group = re.sub(
+                pattern,
+                f"{replace} #{rank};",
+                existing,
+            )
+        else:
+            new_group = f"{existing}; {replace} #{rank};"
+    else:
+        new_group = f"{replace} #{rank};"
+
+    new_group = re.sub(r";+", ";", new_group)
+    # Skip if nothing changes
+    if existing == new_group and existing_year == str(year):
+        print("Skipping (already tagged)")
+        return "skip"
+    print(f"Would tag {path.name}: {new_group} {year}")
+
+    if dry_run:
+        return
+
+    subprocess.run(
+        [
+            "kid3-cli",
+            "-c", f'set {tag} "{new_group}"',
+            "-c", f"set year {year}",
+            str(path),
+        ],
+        check=True,
+    )
+
+def main():
+    parser = argparse.ArgumentParser()
+
+    parser.add_argument("library")
+    parser.add_argument("booklist")
+    parser.add_argument("--dry-run", action="store_true")
+    parser.add_argument("--find-missing", action="store_true")
+
+    args = parser.parse_args()
+
+    library = Path(args.library)
+
+    found = set()
+
+    with open(args.booklist, encoding="utf-8") as f:
+        books = [
+            line.strip()
+            for line in f
+            if line.strip() and not line.startswith("#")
+        ]
+
+    author_dirs = {
+        normalize(p.name): p
+        for p in library.iterdir()
+        if p.is_dir()
+    }
+    rank_list=[]
+#    print(books)
+    for line in books:
+        line = line.strip()
+
+        if not line:
+            continue  # skip empty lines
+
+        parts = line.split(" - ")
+
+        if len(parts) == 4:
+            rank, author, title, year = parts
+        elif len(parts) == 3:
+            rank, author, title = parts
+            year = None
+        else:
+            raise ValueError(f"Invalid line: {line}")
+        author_key = normalize(author)
+        title_key = normalize(title)
+        rank_list.append(rank)
+        author_dir = author_dirs.get(author_key)
+
+        if author_dir is None:
+            print(f"{RED}AUTHOR{RESET} {author} ")
+            continue
+
+        book_dir = None
+        best_score = 0.0
+
+        for subdir in author_dir.rglob("*"):
+            if not subdir.is_dir():
+                continue
+            score = SequenceMatcher(
+                None,
+                title_key,
+                normalize(subdir.name),
+            ).ratio()
+
+            if score > best_score:
+                best_score = score
+                book_dir = subdir
+
+        if best_score < 0.6:
+            book_dir = None
+            print(f"{RED}TITLE{RESET} {title}, Score {best_score} ")
+            for subdir in author_dir.rglob("*"):
+                if not subdir.is_dir():
+                    continue
+                else:
+                    print(subdir)
+
+            continue
+
+        found.add(rank)
+
+        print(f"{GREEN}FOUND{RESET}   #{int(rank):3} {title} in {book_dir}")
+
+        if args.find_missing:
+            continue
+
+        for file in book_dir.iterdir():
+            if file.suffix.lower() not in AUDIO_EXTENSIONS:
+                continue
+
+            ret=tag_file(file, int(rank), year, args.dry_run)
+            if ret == "skip":
+                break
+       # print("next")
+
+if __name__ == "__main__":
+    main()
+

quiethost/metadata_write_ranking.sh

@@ -0,0 +1,137 @@
+#!/usr/bin/env bash
+
+set -euo pipefail
+RED=$'\e[31m'
+GREEN=$'\e[32m'
+RESET=$'\e[0m'
+usage() {
+    cat <<EOF
+Usage:
+  $(basename "$0") <library-root> <book-list> [--dry-run|--find-missing]
+
+Arguments:
+  library-root   Root containing author/*/book/
+  book-list      Text file containing:
+                   rank|title|author|year
+
+Options:
+  --dry-run      Show what would be tagged without writing tags
+  --find-missing List books from the ranking that were not found
+EOF
+    exit 1
+}
+
+[[ $# -ge 2 ]] || usage
+
+ROOT="$1"
+BOOKLIST="$2"
+MODE="write"
+
+case "${3:-}" in
+    --dry-run)
+        MODE="dryrun"
+        ;;
+    --find-missing)
+        MODE="missing"
+        ;;
+    "")
+        ;;
+    *)
+        usage
+        ;;
+esac
+
+[[ -d "$ROOT" ]] || {
+    echo "Library not found: $ROOT" >&2
+    exit 1
+}
+
+[[ -f "$BOOKLIST" ]] || {
+    echo "Book list not found: $BOOKLIST" >&2
+    exit 1
+}
+echo "Using MODE $MODE"
+echo "Libary: $ROOT"
+echo "File: $BOOKLIST"
+
+normalize() {
+    echo "$1" |
+        tr '[:upper:]' '[:lower:]' |
+        sed -E "s/[^a-z0-9]+//g"
+}
+
+declare -A FOUND
+
+while IFS='|' read -r RANK TITLE AUTHOR YEAR; do
+
+    # Skip blank lines and comments
+    [[ -z "$RANK" ]] && continue
+    [[ "$RANK" =~ ^# ]] && continue
+
+    NTITLE=$(normalize "$TITLE")
+    NAUTHOR=$(normalize "$AUTHOR")
+
+    MATCH=""
+
+AUTHOR_PATH=$(find "$ROOT" -type d -iname "*$AUTHOR*" | head -n1)
+
+[[ -z "$AUTHOR_PATH" ]] && continue
+
+BOOK_PATH="$AUTHOR_PATH/book"
+[[ -d "$BOOK_PATH" ]] || continue
+
+while IFS= read -r FILE; do
+    FILE_NAME="${FILE##*/}"
+    FILE_BASE="${FILE_NAME%.*}"
+
+    echo "Checking: $FILE_BASE"
+
+    if [[ "$(normalize "$FILE_BASE")" == "$NTITLE" ]]; then
+        MATCH="$FILE"
+        break
+    fi
+done < <(find "$BOOK_PATH" -maxdepth 1 -type f)
+    if [[ -n "$MATCH" ]]; then
+        FOUND["$RANK"]=1
+
+        GROUP="Sci Fi Top 100 Books #$RANK"
+
+        case "$MODE" in
+            dryrun)
+                echo "Would tag:"
+                echo "  File : $MATCH"
+                echo "  Album: $GROUP"
+                echo "  Year : $YEAR"
+                echo
+                ;;
+
+            write)
+                echo "Tagging: $MATCH"
+
+                id3v2 \
+                    --TALB "$GROUP" \
+                    --TYER "$YEAR" \
+                    "$MATCH"
+                ;;
+
+            missing)
+                ;;
+        esac
+    fi
+
+done < "$BOOKLIST"
+
+if [[ "$MODE" == "missing" ]]; then
+    while IFS='|' read -r RANK TITLE AUTHOR YEAR; do
+        [[ -z "$RANK" ]] && continue
+        [[ "$RANK" =~ ^# ]] && continue
+
+        if [[ -n "${FOUND[$RANK]:-}" ]]; then
+            printf "${GREEN}FOUND${RESET}   #%3d | %s | %s | %s\n" \
+                "$RANK" "$TITLE" "$AUTHOR" "$YEAR"
+        else
+            printf "${RED}MISSING${RESET} #%3d | %s | %s | %s\n" \
+                "$RANK" "$TITLE" "$AUTHOR" "$YEAR"
+        fi
+    done < "$BOOKLIST"
+fi

quiethost/metadate_generate_for_pdf.sh

@@ -0,0 +1,40 @@
+#!/bin/bash
+
+BASE="${1:-.}"
+
+for dir in "$BASE"/*/; do
+    [ -d "$dir" ] || continue
+
+    title=$(basename "$dir")
+
+    # Skip directories starting with a number
+    [[ "$title" =~ ^[0-9] ]] && continue
+
+    # Author = parent directory of book directory
+    author=$(basename "$(dirname "$dir")")
+
+    # Fix author name formatting
+    author="${author//JRR/J. R. R.}"
+
+    for pdf in "$dir"/*.pdf; do
+        [ -f "$pdf" ] || continue
+
+        opf="$dir/metadata.opf"
+
+        cat > "$opf" <<EOF
+<?xml version="1.0" encoding="UTF-8"?>
+<package xmlns:dc="http://purl.org/dc/elements/1.1/"
+         xmlns:opf="http://www.idpf.org/2007/opf"
+         version="2.0">
+  <metadata>
+    <dc:title>$title</dc:title>
+    <dc:creator opf:role="aut">$author</dc:creator>
+    <dc:language>en</dc:language>
+    <dc:format>application/pdf</dc:format>
+  </metadata>
+</package>
+EOF
+
+        echo "Created: $opf"
+    done
+done