Kanzi 0.6.20: kanzi.xpi only, dedup identical highlights, pagination 50
- scripts/build_plugin.py: OUTPUT kanzi.xpi (was kindle-zotero-importer.xpi), clean legacy - plugin/manifest.json: homepage/update_url -> kanzi repo, name Kanzi 0.6.20 - README: Install kanzi.xpi from kanzi/releases, build -> dist/kanzi.xpi - updates.json: 0.6.20 link -> kanzi/kanzi.xpi - src/kindle_zotero_importer/clippings.py: dedup_clippings() collapse identical highlights (same title + norm text) to fix badiou yellow×3 - plugin/bootstrap.js: norm dedup for existing yellow over yellow, mergeComments bracket stripped
This commit is contained in:
parent
7345eee997
commit
1e3b002c21
6 changed files with 75 additions and 9 deletions
|
|
@ -13,7 +13,7 @@ Import Kindle `My Clippings.txt` highlights into Zotero as native annotations, d
|
||||||
|
|
||||||
# Install
|
# Install
|
||||||
|
|
||||||
1. Download `kindle-zotero-importer.xpi` from [Releases](../../releases) (latest `0.6.19`, or `0.6.18-beta` for preview).
|
1. Download `kanzi.xpi` from [Releases](https://github.com/UtkuBilenDemir/kanzi/releases) (latest `0.6.20`, or `0.6.19-beta` for preview).
|
||||||
2. In Zotero: `Tools` → `Plugins` → `gear` → `Install Plugin From File…` → pick the `.xpi` → restart Zotero.
|
2. In Zotero: `Tools` → `Plugins` → `gear` → `Install Plugin From File…` → pick the `.xpi` → restart Zotero.
|
||||||
3. `Tools` → `Kanzi…` to open the manager.
|
3. `Tools` → `Kanzi…` to open the manager.
|
||||||
|
|
||||||
|
|
@ -79,7 +79,7 @@ Incremental is default. Only new, changed or colour-changed highlights are repos
|
||||||
# For developers / CLI
|
# For developers / CLI
|
||||||
|
|
||||||
```sh
|
```sh
|
||||||
python scripts/build_plugin.py # → dist/kindle-zotero-importer.xpi
|
python scripts/build_plugin.py # → dist/kanzi.xpi
|
||||||
python -m kindle_zotero_importer run "/path/to/My Clippings.txt" --workdir . --pretty
|
python -m kindle_zotero_importer run "/path/to/My Clippings.txt" --workdir . --pretty
|
||||||
python -m kindle_zotero_importer run ... --full # ignore incremental and reprocess all
|
python -m kindle_zotero_importer run ... --full # ignore incremental and reprocess all
|
||||||
```
|
```
|
||||||
|
|
@ -88,7 +88,7 @@ PDF positioning uses Poppler (`pdftotext`, `pdftohtml`, `pdfinfo`) plus `qpdf` f
|
||||||
|
|
||||||
# Releases
|
# Releases
|
||||||
|
|
||||||
Stable releases are on `Releases` with `kindle-zotero-importer.xpi` and `updates.json` attached. Pre-releases (`beta`) are marked `Pre-release` on GitHub. Zotero auto-updates from `releases/latest/download/updates.json`.
|
Stable releases are on `Releases` with `kanzi.xpi` and `updates.json` attached. Pre-releases (`beta`) are marked `Pre-release` on GitHub. Zotero auto-updates from `releases/latest/download/updates.json`.
|
||||||
|
|
||||||
# Support
|
# Support
|
||||||
|
|
||||||
|
|
|
||||||
22
plugin/bootstrap.js
vendored
22
plugin/bootstrap.js
vendored
|
|
@ -701,12 +701,34 @@ var KindleZoteroImporter = {
|
||||||
}
|
}
|
||||||
const existingByAttachment = new Map();
|
const existingByAttachment = new Map();
|
||||||
|
|
||||||
|
const normForDedup = (s) => String(s || "").toLowerCase().normalize("NFKC").replace(/-\s*\n\s*/g, "").replace(/[^\w\s]+/g, " ").replace(/\s+/g, " ").trim();
|
||||||
const getExistingAnnotations = async (attachment) => {
|
const getExistingAnnotations = async (attachment) => {
|
||||||
if (!existingByAttachment.has(attachment.id)) {
|
if (!existingByAttachment.has(attachment.id)) {
|
||||||
const annotations = attachment.getAnnotations ? attachment.getAnnotations() : [];
|
const annotations = attachment.getAnnotations ? attachment.getAnnotations() : [];
|
||||||
const byFingerprint = new Map();
|
const byFingerprint = new Map();
|
||||||
|
const byNorm = new Map();
|
||||||
|
|
||||||
for (const annotation of annotations) {
|
for (const annotation of annotations) {
|
||||||
|
const norm = normForDedup(annotation.annotationText || "");
|
||||||
|
const dupNorm = byNorm.get(norm);
|
||||||
|
if (dupNorm && norm) {
|
||||||
|
// collapse identical highlights (e.g. My Clippings duplicates "forged its might…" x5)
|
||||||
|
const kept = dupNorm;
|
||||||
|
const keptHasComment = Boolean(kept.annotationComment);
|
||||||
|
const curHasComment = Boolean(annotation.annotationComment);
|
||||||
|
const duplicate = keptHasComment || !curHasComment ? annotation : kept;
|
||||||
|
const replacement = duplicate === annotation ? kept : annotation;
|
||||||
|
byNorm.set(norm, replacement);
|
||||||
|
// also update fingerprint map
|
||||||
|
const fpDup = this.existingAnnotationFingerprint(duplicate);
|
||||||
|
const fpKeep = this.existingAnnotationFingerprint(replacement);
|
||||||
|
byFingerprint.delete(fpDup);
|
||||||
|
byFingerprint.set(fpKeep, replacement);
|
||||||
|
if (!dryRun) await duplicate.eraseTx();
|
||||||
|
results.removedDuplicates += 1;
|
||||||
|
continue;
|
||||||
|
}
|
||||||
|
if (norm) byNorm.set(norm, annotation);
|
||||||
const fingerprint = this.existingAnnotationFingerprint(annotation);
|
const fingerprint = this.existingAnnotationFingerprint(annotation);
|
||||||
const kept = byFingerprint.get(fingerprint);
|
const kept = byFingerprint.get(fingerprint);
|
||||||
if (!kept) {
|
if (!kept) {
|
||||||
|
|
|
||||||
|
|
@ -1,14 +1,14 @@
|
||||||
{
|
{
|
||||||
"manifest_version": 2,
|
"manifest_version": 2,
|
||||||
"name": "Kanzi",
|
"name": "Kanzi",
|
||||||
"version": "0.6.19",
|
"version": "0.6.20",
|
||||||
"description": "Kindle annotations to Zotero — My Clippings.txt → native annotations.",
|
"description": "Kindle annotations to Zotero — My Clippings.txt → native annotations.",
|
||||||
"homepage_url": "https://github.com/UtkuBilenDemir/kindle-zotero_importer",
|
"homepage_url": "https://github.com/UtkuBilenDemir/kanzi",
|
||||||
"author": "Utku Bilen Demir",
|
"author": "Utku Bilen Demir",
|
||||||
"applications": {
|
"applications": {
|
||||||
"zotero": {
|
"zotero": {
|
||||||
"id": "kindlezoteroimporter@utkubilen.de",
|
"id": "kindlezoteroimporter@utkubilen.de",
|
||||||
"update_url": "https://github.com/UtkuBilenDemir/kindle-zotero_importer/releases/latest/download/updates.json",
|
"update_url": "https://github.com/UtkuBilenDemir/kanzi/releases/latest/download/updates.json",
|
||||||
"strict_min_version": "6.999",
|
"strict_min_version": "6.999",
|
||||||
"strict_max_version": "10.0.*"
|
"strict_max_version": "10.0.*"
|
||||||
}
|
}
|
||||||
|
|
|
||||||
|
|
@ -8,13 +8,15 @@ from pathlib import Path
|
||||||
ROOT = Path(__file__).resolve().parents[1]
|
ROOT = Path(__file__).resolve().parents[1]
|
||||||
PLUGIN_DIR = ROOT / "plugin"
|
PLUGIN_DIR = ROOT / "plugin"
|
||||||
DIST_DIR = ROOT / "dist"
|
DIST_DIR = ROOT / "dist"
|
||||||
OUTPUT = DIST_DIR / "kindle-zotero-importer.xpi"
|
OUTPUT = DIST_DIR / "kanzi.xpi"
|
||||||
|
LEGACY_OUTPUT = DIST_DIR / "kindle-zotero-importer.xpi"
|
||||||
|
|
||||||
|
|
||||||
def main() -> int:
|
def main() -> int:
|
||||||
DIST_DIR.mkdir(exist_ok=True)
|
DIST_DIR.mkdir(exist_ok=True)
|
||||||
if OUTPUT.exists():
|
for p in [OUTPUT, LEGACY_OUTPUT]:
|
||||||
OUTPUT.unlink()
|
if p.exists():
|
||||||
|
p.unlink()
|
||||||
|
|
||||||
manifest_path = PLUGIN_DIR / "manifest.json"
|
manifest_path = PLUGIN_DIR / "manifest.json"
|
||||||
manifest = json.loads(manifest_path.read_text(encoding="utf-8"))
|
manifest = json.loads(manifest_path.read_text(encoding="utf-8"))
|
||||||
|
|
|
||||||
|
|
@ -80,7 +80,40 @@ def load_clippings(path: str) -> list[Clipping]:
|
||||||
return parse_clippings_text(file.read())
|
return parse_clippings_text(file.read())
|
||||||
|
|
||||||
|
|
||||||
|
def _norm_text(text: str) -> str:
|
||||||
|
import unicodedata
|
||||||
|
|
||||||
|
t = unicodedata.normalize("NFKC", text or "").lower()
|
||||||
|
t = re.sub(r"-\s*\n\s*", "", t)
|
||||||
|
t = re.sub(r"[^\w\s]+", " ", t)
|
||||||
|
t = re.sub(r"\s+", " ", t).strip()
|
||||||
|
return t
|
||||||
|
|
||||||
|
|
||||||
|
def dedup_clippings(clippings: list[Clipping]) -> list[Clipping]:
|
||||||
|
seen: dict[tuple[str, str], Clipping] = {}
|
||||||
|
for c in clippings:
|
||||||
|
if c.kind not in {"highlight", "note"}:
|
||||||
|
# keep bookmarks etc. as is
|
||||||
|
key = (c.title, c.id)
|
||||||
|
if key not in seen:
|
||||||
|
seen[key] = c
|
||||||
|
continue
|
||||||
|
key = (c.title, _norm_text(c.text))
|
||||||
|
# keep earliest added_on, or first seen
|
||||||
|
if key not in seen:
|
||||||
|
seen[key] = c
|
||||||
|
else:
|
||||||
|
# if same norm text, keep the one with earlier added_on or shorter location range
|
||||||
|
prev = seen[key]
|
||||||
|
# prefer the one with more complete text (longer) or earlier date
|
||||||
|
if len(c.text) > len(prev.text):
|
||||||
|
seen[key] = c
|
||||||
|
return list(seen.values())
|
||||||
|
|
||||||
|
|
||||||
def clippings_to_jsonable(clippings: list[Clipping]) -> dict[str, Any]:
|
def clippings_to_jsonable(clippings: list[Clipping]) -> dict[str, Any]:
|
||||||
|
clippings = dedup_clippings(clippings)
|
||||||
return {
|
return {
|
||||||
"format": "kindle-zotero-importer.clippings.v1",
|
"format": "kindle-zotero-importer.clippings.v1",
|
||||||
"count": len(clippings),
|
"count": len(clippings),
|
||||||
|
|
|
||||||
|
|
@ -2,6 +2,15 @@
|
||||||
"addons": {
|
"addons": {
|
||||||
"kindlezoteroimporter@utkubilen.de": {
|
"kindlezoteroimporter@utkubilen.de": {
|
||||||
"updates": [
|
"updates": [
|
||||||
|
{
|
||||||
|
"version": "0.6.20",
|
||||||
|
"update_link": "https://github.com/UtkuBilenDemir/kanzi/releases/download/v0.6.20/kanzi.xpi",
|
||||||
|
"applications": {
|
||||||
|
"zotero": {
|
||||||
|
"strict_min_version": "6.999"
|
||||||
|
}
|
||||||
|
}
|
||||||
|
},
|
||||||
{
|
{
|
||||||
"version": "0.6.19",
|
"version": "0.6.19",
|
||||||
"update_link": "https://github.com/UtkuBilenDemir/kindle-zotero_importer/releases/download/v0.6.19/kindle-zotero-importer.xpi",
|
"update_link": "https://github.com/UtkuBilenDemir/kindle-zotero_importer/releases/download/v0.6.19/kindle-zotero-importer.xpi",
|
||||||
|
|
|
||||||
Loading…
Add table
Reference in a new issue