kindle-zotero_importer/tests/test_fuzzy.py
2026-10-15 14:01:05 +02:00

233 lines
8.9 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

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","related_items":[{"item_id":20,"key":"P2","citation_key":"c2"}]},
"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)
assert plan["annotations"][0]["related_items"][0]["item_id"] == 20
def test_pdf_tolerates_of_split_artifact():
from kindle_zotero_importer.pdf_position import find_pdf_text_page, find_pdf_rects, PDFPageXML, PDFWord
quote = "nothing other than idolatry of the machine and which"
page_text = "nothing other than idolatry o f the machine and which"
assert find_pdf_text_page([page_text], quote) == 0
words = []
cursor = 0
for w in page_text.split():
words.append(PDFWord(text=w, left=0.0, top=0.0, width=10.0, height=10.0, start=cursor, end=cursor + len(w)))
cursor += len(w) + 1
page = PDFPageXML(index=0, width=100.0, height=100.0, words=words)
rects = find_pdf_rects("dummy.pdf", page, quote, {("dummy.pdf", 0): (100.0, 100.0)})
assert rects is not None
assert rects["pageIndex"] == 0
assert rects["rects"]
def test_pdf_tolerates_punctuation_and_quotes():
from kindle_zotero_importer.pdf_position import find_pdf_text_page
quote = "This, then, gives rise to “intemperate technicism”."
page = "this then gives rise to intemperate technicism"
assert find_pdf_text_page([page], quote) == 0
def test_pdf_partial_half_anchors_spanning_text():
from kindle_zotero_importer.pdf_position import find_pdf_text_page
first = "A" * 70
second = "Z" * 70
quote = first + second
page = "xx " + first.lower() + " yy"
assert find_pdf_text_page([page], quote) == 0
def test_pdf_shingle_fallback_scattered_ocr_errors():
from kindle_zotero_importer.pdf_position import find_pdf_text_page
quote = (
"Gerçekçi zındıklık yolunu tutuşsa bir mucize görse bile kendinde "
"buna inanmamasım sağlayacak güç ve yeteneği bulur mucize yadsınaraz "
"dururda bile olsa boyun eğmez"
)
page = (
"gerçekçi zındıklık yolunu tutuşsa bir mucize görse bile kendinde "
"buna inanmaması sağlayacak güç ve yeteneği bulur mucize yadsınamaz "
"dururda bile olsa boyun eğmez"
)
assert find_pdf_text_page([page], quote) == 0
def test_page_hint_snippet_around_kindle_page():
from kindle_zotero_importer.pdf_position import _page_hint_text
pages = ["", "intro words here", "target page words here", "trailing words"]
hint = _page_hint_text(pages, "3")
assert hint is not None
assert hint["kindle_page"] == "3"
assert "target page words" in hint["text"]
assert _page_hint_text(pages, None) is None
assert _page_hint_text(pages, "99") is None
def test_citekey_mentions_become_zotero_links():
from kindle_zotero_importer.import_plan import build_import_plan
clippings_payload = {
"format": "x",
"clippings": [
{
"id": "c1",
"title": "Book A",
"kind": "highlight",
"text": "As argued by @bookb2020, this follows.",
"page": None,
"location": "10",
}
],
}
zotero_index = {
"format": "x",
"items": [
{
"item_id": 1,
"key": "PARENT01",
"title": "Book A",
"fields": {"citationKey": "booka2020"},
"attachments": [
{
"item_id": 11,
"key": "ATTACH01",
"title": "pdf",
"content_type": "application/pdf",
"path": "x.pdf",
"resolved_path": "x.pdf",
}
],
},
{
"item_id": 2,
"key": "TARGET02",
"title": "Book B",
"fields": {"citationKey": "bookb2020"},
"attachments": [],
},
],
}
match_report = {
"format": "x",
"matches": [
{
"clipping_title": "Book A",
"status": "matched",
"candidates": [{"item_id": 1}],
}
],
}
plan = build_import_plan(clippings_payload, zotero_index, match_report, None)
comment = plan["items"][0]["annotation"]["comment"] or ""
assert "@bookb2020" in comment
assert "zotero://select/library/items/TARGET02" in comment
assert plan["items"][0]["zotero"]["related_items"] == [
{
"item_id": 2,
"key": "TARGET02",
"citation_key": "bookb2020",
"link": "zotero://select/library/items/TARGET02",
}
]
# self-links are skipped
clippings_payload["clippings"][0]["text"] = "See @booka2020 here."
plan = build_import_plan(clippings_payload, zotero_index, match_report, None)
assert "zotero://select" not in (plan["items"][0]["annotation"]["comment"] or "")
assert plan["items"][0]["zotero"]["related_items"] == []
def test_historical_annotations_gain_citekey_relations():
from kindle_zotero_importer.cli import _refresh_history_relations
history = [
{
"clipping_id": "old",
"parent_item_id": 1,
"annotation": {
"text": "An old highlight",
"comment": "body without organs @deleuze1983",
},
}
]
zotero_index = {
"items": [
{
"item_id": 1,
"key": "SOURCE01",
"fields": {"citationKey": "simondon2017a"},
},
{
"item_id": 2,
"key": "TARGET02",
"fields": {"citationKey": "deleuze1983"},
},
]
}
_refresh_history_relations(history, zotero_index)
assert history[0]["related_items"] == [
{
"item_id": 2,
"key": "TARGET02",
"citation_key": "deleuze1983",
"link": "zotero://select/library/items/TARGET02",
}
]
def test_group_library_targets_use_group_select_links():
from kindle_zotero_importer.import_plan import _select_link
assert (
_select_link({"key": "ABC123", "group_id": 6644344})
== "zotero://select/groups/6644344/items/ABC123"
)
assert (
_select_link({"key": "ABC123", "group_id": None})
== "zotero://select/library/items/ABC123"
)
assert (
_select_link({"key": "ABC123"})
== "zotero://select/library/items/ABC123"
)
def test_epub_tolerates_extraction_artifacts():
from kindle_zotero_importer.epub_position import find_epub_cfi, TextNode
nodes = [TextNode(spine_index=0, cfi_parent_path="/4/2", text_step="1", text="idolatry o f the machine", start=0, end=24)]
quote = "idolatry of the machine and which"
# quote is longer than node, so exact fails; use full haystack variant
nodes = [TextNode(spine_index=0, cfi_parent_path="/4/2", text_step="1", text="nothing other than idolatry o f the machine and which", start=0, end=53)]
result = find_epub_cfi(nodes, quote)
assert result is not None
assert result["selector"]["value"].startswith("epubcfi(")