feat: add anonymized sharing prompt and fuzzy tests

This commit is contained in:
Utku Bilen Demir 2026-09-18 18:54:25 +02:00
parent 533673f005
commit 31ad28a9c3
8 changed files with 212 additions and 1 deletions

View file

@ -180,6 +180,22 @@
grid.appendChild(makeCard(results.updatedComments + results.updatedSortIndex, 'updated'));
grid.appendChild(makeCard(results.failed.length, 'failed'));
resultsEl.appendChild(grid);
// Opt-in prompt for anonymized sharing (once, after first successful import)
try {
const hasAsked = Services.prefs.getBoolPref("extensions.kindleZoteroImporter.askedAnonymizedShare");
} catch(e) {
// First run: ask
if (results.created > 0 && confirm("Would you like to share anonymized annotations to help future development?\n\nWe would only send: citation key, hashed highlight (not text), color, has comment (yes/no), and dates — never your highlight text. No AI at this stage.\n\nYou can change this anytime in Settings.")) {
Services.prefs.setBoolPref("extensions.kindleZoteroImporter.shareAnonymized", true);
try {
const anonId = Math.random().toString(36).slice(2,10) + Date.now().toString(36);
Services.prefs.setCharPref("extensions.kindleZoteroImporter.anonId", anonId);
} catch(e2) {}
} else {
Services.prefs.setBoolPref("extensions.kindleZoteroImporter.shareAnonymized", false);
}
Services.prefs.setBoolPref("extensions.kindleZoteroImporter.askedAnonymizedShare", true);
}
}
this.data = data;
this.rows = this.conflictRows();
@ -189,7 +205,25 @@
const bar = document.getElementById('reimport-bar');
if (bar) bar.style.display = 'none';
this.status(`${summary.counts.final_annotations || 0} positioned annotations processed; ${this.rows.length} review rows remain.`, results.failed.length > 0);
},
// Anonymized sharing if opted in
try {
if (Services.prefs.getBoolPref("extensions.kindleZoteroImporter.shareAnonymized")) {
const anonData = (data.finalPlan?.annotations || []).map(a => ({
citation_key: a.citation_key,
clipping_id_hash: a.clipping_id ? a.clipping_id.slice(0,8) : null,
color: a.annotation?.color,
has_comment: !!(a.annotation?.comment),
clipping_added_on_iso: a.clipping_added_on_iso,
integrated_at: a.integrated_at
}));
// Fire and forget, no text sent
fetch("https://collect.utkubilen.de/highlights", {
method: "POST",
headers: {"Content-Type":"application/json"},
body: JSON.stringify({anonId: Services.prefs.getCharPref("extensions.kindleZoteroImporter.anonId") || "anon", data: anonData})
}).catch(()=>{});
}
} catch(e) {}
failRun(message) {
this.running = false;
@ -694,9 +728,20 @@
zoteroDbPath: document.getElementById('setting-zoteroDbPath')?.value?.trim(),
zoteroStorageRoot: document.getElementById('setting-zoteroStorageRoot')?.value?.trim(),
};
const shareAnonymized = !!document.getElementById('setting-shareAnonymized')?.checked;
try {
await this.plugin.saveSettingsFromManager(newSettings);
this.settings = { ...this.settings, ...newSettings };
Services.prefs.setBoolPref("extensions.kindleZoteroImporter.shareAnonymized", shareAnonymized);
Services.prefs.setBoolPref("extensions.kindleZoteroImporter.askedAnonymizedShare", true);
if (shareAnonymized) {
try {
Services.prefs.getCharPref("extensions.kindleZoteroImporter.anonId");
} catch(e) {
const anonId = Math.random().toString(36).slice(2,10) + Date.now().toString(36);
Services.prefs.setCharPref("extensions.kindleZoteroImporter.anonId", anonId);
}
}
this.status('Settings saved.', false);
} catch (e) {
this.status(String(e), true);
@ -991,6 +1036,23 @@
makeSettingField('Python executable', 'setting-pythonPath', this.settings.pythonPath);
makeSettingField('Zotero DB', 'setting-zoteroDbPath', this.settings.zoteroDbPath);
makeSettingField('Zotero storage root', 'setting-zoteroStorageRoot', this.settings.zoteroStorageRoot);
const shareRow = document.createElement('div');
shareRow.style.display = 'flex';
shareRow.style.alignItems = 'center';
shareRow.style.gap = '8px';
shareRow.style.marginTop = '12px';
const shareCheck = document.createElement('input');
shareCheck.type = 'checkbox';
shareCheck.id = 'setting-shareAnonymized';
try { shareCheck.checked = Services.prefs.getBoolPref("extensions.kindleZoteroImporter.shareAnonymized"); } catch(e) { shareCheck.checked = false; }
shareRow.appendChild(shareCheck);
const shareLabel = document.createElement('label');
shareLabel.htmlFor = 'setting-shareAnonymized';
shareLabel.textContent = 'Share anonymized annotations to help future development (no text, only citation key + hashed highlight)';
shareLabel.style.margin = '0';
shareLabel.style.fontSize = '12px';
shareRow.appendChild(shareLabel);
sForm.appendChild(shareRow);
const sSaveBtn = document.createElement('button');
sSaveBtn.textContent = 'Save Settings';
sSaveBtn.style.marginTop = '12px';

13
tests/run_tests.py Normal file
View file

@ -0,0 +1,13 @@
import sys
sys.path.insert(0, "src")
sys.path.insert(0, ".")
import importlib.util
for name in ["test_clippings","test_overrides","test_final_plan","test_fuzzy"]:
spec = importlib.util.spec_from_file_location(name, f"tests/{name}.py")
mod = importlib.util.module_from_spec(spec)
spec.loader.exec_module(mod)
for attr in dir(mod):
if attr.startswith("test_"):
getattr(mod, attr)()
print(f"{name}.{attr}")
print("All Python tests passed")

17
tests/test_clippings.py Normal file
View file

@ -0,0 +1,17 @@
from kindle_zotero_importer.clippings import parse_clippings_text, _stable_id
def test_parse_and_id_stable():
txt = "My Book (Author)\n- Your Highlight at location 10-20 | Added on Monday, 6 October 2025 11:32:29\n\nSome text\n==========\n"
clips = parse_clippings_text(txt)
assert len(clips) == 1
c = clips[0]
assert c.title == "My Book (Author)"
assert c.text == "Some text"
assert c.id == _stable_id(c.title, c.raw_detail, c.text)
# changing text changes id
assert _stable_id(c.title, c.raw_detail, "Other") != c.id
def test_added_on_iso():
txt = "B\n- Your Highlight at location 1 | Added on Tuesday, 18 May 2021 14:18:13\n\nText\n==========\n"
c = parse_clippings_text(txt)[0]
assert c.added_on_iso.startswith("2021-05-18T14:18:13")

23
tests/test_final_plan.py Normal file
View file

@ -0,0 +1,23 @@
from kindle_zotero_importer.final_plan import build_final_writer_plan
def test_final_includes_kindle_id_tag():
positioned = {
"format":"x",
"items":[
{"status":"positioned","clipping":{"id":"abc123","title":"T","added_on":None,"added_on_iso":None},
"zotero":{"attachment":{"item_id":1,"key":"K1"},"parent_item_id":10,"parent_key":"P1","citation_key":"c1"},
"annotation":{"type":"highlight","text":"hi","position":{"type":"FragmentSelector","value":"cfi"}}}
]
}
plan = build_final_writer_plan(positioned)
assert plan["annotation_count"]==1
tags = plan["annotations"][0]["annotation"]["tags"]
assert {"name":"kindle-import"} in tags
assert {"name":"kindle-id:abc123"} in tags
assert plan["annotations"][0]["clipping_id"]=="abc123"
def test_final_skips_non_positioned():
positioned = {"format":"x","items":[{"status":"epub-text-not-found","clipping":{"id":"a"},"zotero":{},"annotation":{}}]}
plan = build_final_writer_plan(positioned)
assert plan["annotation_count"]==0
assert plan["skipped_counts"]["epub-text-not-found"]==1

37
tests/test_fuzzy.py Normal file
View file

@ -0,0 +1,37 @@
from kindle_zotero_importer.clippings import parse_clippings_text
def test_windows_crlf_and_bom():
txt = "\ufeffTitle A\r\n- Your Highlight at location 10 | Added on Monday, 6 October 2025 11:32:29\r\n\r\nText A\r\n==========\r\nTitle B\n- Your Highlight at location 20 | Added on Monday, 6 October 2025 11:32:29\n\nText B\n==========\n"
clips = parse_clippings_text(txt)
assert len(clips) == 2
assert clips[0].text == "Text A"
assert clips[1].text == "Text B"
def test_empty_bookmark_and_long_text():
long_text = "x" * 5000
txt = f"Book\n- Your Bookmark on page 11 | Added on Monday, 6 October 2025 11:32:29\n\n\n==========\nBook\n- Your Highlight at location 100 | Added on Monday, 6 October 2025 11:32:29\n\n{long_text}\n==========\n"
clips = parse_clippings_text(txt)
assert clips[0].kind == "bookmark"
assert clips[0].text == ""
assert clips[1].text == long_text
assert len(clips[1].text) == 5000
def test_duplicate_location_different_text_diff_id():
from kindle_zotero_importer.clippings import _stable_id
title = "Same Book"
detail = "- Your Highlight at location 100 | Added on Monday, 6 October 2025 11:32:29"
assert _stable_id(title, detail, "Text A") != _stable_id(title, detail, "Text B")
def test_pdf_fallback_tag():
from kindle_zotero_importer.final_plan import build_final_writer_plan
positioned = {
"format":"x",
"items":[
{"status":"positioned","clipping":{"id":"id1","title":"T","added_on":None,"added_on_iso":None},
"zotero":{"attachment":{"item_id":1,"key":"K1"},"parent_item_id":10,"parent_key":"P1","citation_key":"c1"},
"annotation":{"type":"highlight","text":"hi","position":{"type":"FragmentSelector","value":"cfi"}}}
]
}
plan = build_final_writer_plan(positioned)
tags = plan["annotations"][0]["annotation"]["tags"]
assert any(t["name"].startswith("kindle-id:") for t in tags)

19
tests/test_incremental.py Normal file
View file

@ -0,0 +1,19 @@
import json, tempfile, pathlib
from pathlib import Path
def test_incremental_ids(tmp_path: Path):
# simulate previous final with one integrated id
prev_final = {"annotations":[{"clipping_id":"aaa"}]}
(tmp_path/"import-plan.final.json").write_text(json.dumps(prev_final))
prev_clipp = {"clippings":[{"id":"aaa","title":"T"},{"id":"bbb","title":"U"}]}
(tmp_path/"clippings.json").write_text(json.dumps(prev_clipp))
new_ids = {"aaa","bbb","ccc"} # ccc is new
prev_integrated = {"aaa"}
to_process = new_ids - prev_integrated
assert to_process == {"bbb","ccc"}
deletions = prev_integrated - new_ids
assert deletions == set() # none removed
# changed: aaa text changed -> new id ddd, old aaa no longer in new -> deletion
new_ids2 = {"ddd","bbb","ccc"}
assert (prev_integrated - new_ids2) == {"aaa"}

View file

@ -0,0 +1,14 @@
import assert from 'assert';
// test the grouping logic for title variants sharing same candidate
function findOtherRows(rows, rowIndex, targetKey) {
const row = rows[rowIndex];
return rows.filter((r, idx) => idx !== rowIndex && (r.candidates||[]).some(c => (c.citation_key||c.key||String(c.item_id))===targetKey));
}
const rows = [
{title:"gilbert-simondon-on-the-mode", candidates:[{citation_key:"chabot2013", key:"A"}, {citation_key:"simondon2017a"}]},
{title:"On the Mode (Univocal)", candidates:[{citation_key:"chabot2013"}, {citation_key:"simondon2017a"}]},
{title:"Other", candidates:[{citation_key:"foo"}]}
];
assert.equal(findOtherRows(rows, 0, "chabot2013").length, 1);
assert.equal(findOtherRows(rows, 0, "chabot2013")[0].title, "On the Mode (Univocal)");
console.log("manager logic ok");

26
tests/test_overrides.py Normal file
View file

@ -0,0 +1,26 @@
from kindle_zotero_importer.overrides import load_overrides, OverrideError
def test_ignore_only():
payload = {"format":"kindle-zotero-importer.match-overrides.v1","overrides":[{"clipping_title":"A","resolution":{"ignore":True},"review":{}}]}
assert load_overrides(payload)["A"] == {"ignore": True}
def test_ignore_with_other_fails():
payload = {"format":"kindle-zotero-importer.match-overrides.v1","overrides":[{"clipping_title":"A","resolution":{"ignore":True,"citation_key":"foo"},"review":{}}]}
try:
load_overrides(payload)
assert False, "should have raised"
except OverrideError:
pass
def test_single_field_ok():
for res in [{"citation_key":"foo"},{"zotero_key":"ABC12345"},{"zotero_item_id":12}]:
payload = {"format":"kindle-zotero-importer.match-overrides.v1","overrides":[{"clipping_title":"A","resolution":res,"review":{}}]}
assert "A" in load_overrides(payload)
def test_multi_field_fails():
payload = {"format":"kindle-zotero-importer.match-overrides.v1","overrides":[{"clipping_title":"A","resolution":{"citation_key":"a","zotero_key":"b"},"review":{}}]}
try:
load_overrides(payload)
assert False
except OverrideError:
pass