mirror of
https://github.com/morluto/rea.git
synced 2026-11-08 07:46:28 +00:00
* feat(desktop): read XML with a plain DOCTYPE, and check an element's whole text - Both readers accept a DOCTYPE with only a name and an optional PUBLIC or SYSTEM identifier, record it as the view's doctype, and never fetch the DTD or expand entities beyond XML's five; an internal subset, an external entity and a parameter entity stay refused alike. - text_equals and text_contains compare the concatenated text of the element (or text node or attribute) a pointer reaches, as XPath string() does, with optional normalize_whitespace; both evaluators agree, and a text check on a truncated element is undecided. - Whitespace-only text between elements is dropped only when the element holds no other text, so text split into runs keeps its spaces. - The draft suggests text_equals for an element whose text changed. So an AbiWord .abw reads as XML, and its paragraph's text is checked whole however AbiWord splits it into <c> runs, as Writer's spans are. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * fix(desktop): draft whole-text checks on the paragraph, read only text as text, and skip asctime stamps - A changed value is read at both ends, so text that became a run still marks its paragraph, and the drafted text_equals moves up out of mixed content to the nearest ancestor named by an attribute, such as AbiWord's p by its xid. - Text checks accept only a text node or an attribute value; element names and doctype fields fail, in both evaluators. - isTimestamp also recognises asctime dates (Www Mmm dd hh:mm:ss yyyy). - XML files are drafted with the keyed diff the archive entries use, so no suggestion reaches an element by position; the shared logic moves to appTaskDraftNamed.ts. - Text-check tests assert facts, not whole sentences. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * fix(desktop): keep checks on a changed attribute inside a paragraph whose text check replaces its runs' A drafted whole-text check on a paragraph hid every change inside it, so a link whose label and href both changed drafted only the paragraph's text and the new destination went unchecked. The text check now covers text and runs added or removed whole; a changed name or attribute of an element both versions hold keeps its own check. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * fix(desktop): read an attribute called name or attributes as an attribute when the draft keeps its check The owner of `.../attributes/name` was taken as `.../attributes`, so a changed `name` attribute inside a paragraph with a text check was dropped again. The owner is now read by segment, attributes first. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * fix(desktop): draft text checks from text in runs added whole, and name a text element by its own id before its container Text typed into a run the diff lists whole was never read, so the draft kept only a presence check on the run, which wrong text also passed. Such text now marks the nearest element both ends hold, or, when none can take the check, the added element's own text. The climb also names an element by an identifier of its own (id, xml:id, xid) before a larger container, so a headline under a long layer keeps a whole-text check that survives re-split runs. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * test(desktop): expect the whole-text check where #8988's pairing test meets text checks On this branch a changed element's text is drafted as `text_equals` on the element, so the identity pairing test now expects that check, under the same `[@role=body]` key. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * fix(desktop): keep checks for elements without text beside a text edit, and normalize DOCTYPE system id line endings A review found two gaps. - A paragraph's whole-text check covered every element added or removed inside it, including ones holding no text: an image frame, a line break. A solver who typed the text but never inserted the image passed. Such an element now keeps its own presence or absence check. - The Python reader kept a DOCTYPE system literal's CRLF where TypeScript normalizes it to LF. Both now report LF. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * test(desktop): import textSyntaxFormat once in the state format tests main's mixed-case JSON suffix fix and this branch both added the import, and the merge kept both. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
213 lines
7.1 KiB
TypeScript
213 lines
7.1 KiB
TypeScript
import { writeFile } from "node:fs/promises";
|
|
import { join } from "node:path";
|
|
import { pathToFileURL } from "node:url";
|
|
|
|
import { describe, expect, it } from "vitest";
|
|
|
|
import type { DesktopTaskCheck } from "../../../src/domain/desktop/appTask.js";
|
|
import { xmlView } from "../../../src/domain/desktop/stateFormats.js";
|
|
import { createTestTempDirectory } from "../../fixtures/temporaryDirectory.js";
|
|
import {
|
|
expectSameCheckResults,
|
|
expectSameFileViews,
|
|
odtOf,
|
|
pythonXmlViews,
|
|
savedEnds,
|
|
typescriptFileView,
|
|
} from "../../support/desktopExportPython.js";
|
|
|
|
/** The meeting note as AbiWord saves it, before and after its time was changed. */
|
|
const notes = () => savedEnds("abiword", "meeting.abw");
|
|
|
|
/** Writer's flyer before and after an edit split its body paragraph into runs, zipped with its mimetype. */
|
|
const flyers = () =>
|
|
savedEnds("libreoffice-runs", "content.xml", "flyer.odt", odtOf);
|
|
|
|
const NOTE = "Documents/meeting.abw";
|
|
const PARAGRAPH = "/root/children/[name=section]/children/[name=p][@xid=3]";
|
|
const MEETING = "The team meeting starts at 3:30 in room 4.";
|
|
|
|
/** The paragraph's whole text, a time within it, and its first text node, which the edit split. */
|
|
const NOTE_CHECKS: DesktopTaskCheck[] = [
|
|
{
|
|
id: "time",
|
|
kind: "text_equals",
|
|
file: NOTE,
|
|
pointer: PARAGRAPH,
|
|
value: MEETING,
|
|
},
|
|
{
|
|
id: "within",
|
|
kind: "text_contains",
|
|
file: NOTE,
|
|
pointer: PARAGRAPH,
|
|
value: "at 3:30 in",
|
|
},
|
|
{
|
|
id: "first-node",
|
|
kind: "value_equals",
|
|
file: NOTE,
|
|
pointer: `${PARAGRAPH}/children/0`,
|
|
value: MEETING,
|
|
},
|
|
];
|
|
|
|
const FLYER = "Documents/flyer.odt";
|
|
const BODY =
|
|
"/entries/[name=content.xml]/view/root/children/[name=office:body]/children/[name=office:text]/children/[name=text:p][@text:style-name=Standard]";
|
|
const CAKES = "Cakes, biscuits and bread from 9:30 in the village green.";
|
|
|
|
const FLYER_CHECKS: DesktopTaskCheck[] = [
|
|
{ id: "body", kind: "text_equals", file: FLYER, pointer: BODY, value: CAKES },
|
|
{
|
|
id: "time",
|
|
kind: "text_contains",
|
|
file: FLYER,
|
|
pointer: BODY,
|
|
value: " 9:30\n",
|
|
normalize_whitespace: true,
|
|
},
|
|
{
|
|
id: "reflowed",
|
|
kind: "text_equals",
|
|
file: FLYER,
|
|
pointer: BODY,
|
|
value: " Cakes, biscuits and bread\n from 9:30 in the village green. ",
|
|
normalize_whitespace: true,
|
|
},
|
|
{
|
|
id: "first-run",
|
|
kind: "value_equals",
|
|
file: FLYER,
|
|
pointer: `${BODY}/children/0`,
|
|
value: CAKES,
|
|
},
|
|
];
|
|
|
|
const passes = (outcomes: readonly { passed: boolean }[] | undefined) =>
|
|
outcomes?.map(({ passed }) => passed);
|
|
|
|
describe("XML with a DOCTYPE in the exported module", () => {
|
|
it("reads an AbiWord document, which names its DTD, as REA does: the element tree and the declaration", async () => {
|
|
const files = await notes();
|
|
await expectSameFileViews(files);
|
|
|
|
const [, after] = files;
|
|
if (after === undefined) throw new Error("fixture");
|
|
const { format, view } = await typescriptFileView(after);
|
|
expect(format).toBe("xml");
|
|
expect(view).toMatchObject({
|
|
doctype: {
|
|
name: "abiword",
|
|
public_id: "-//ABISOURCE//DTD AWML 1.0 Strict//EN",
|
|
system_id: "http://www.abisource.com/awml.dtd",
|
|
},
|
|
root: { name: "abiword", attributes: { "xml:space": "preserve" } },
|
|
truncated: false,
|
|
});
|
|
});
|
|
|
|
it("reads a DOCTYPE that only names a DTD alike, and refuses an internal subset or an undeclared entity in both", () => {
|
|
const accepted = [
|
|
"<!DOCTYPE a><a/>",
|
|
'<?xml version="1.0"?><!--c--><!DOCTYPE b SYSTEM "x[1].dtd"><a>t</a>',
|
|
"<!DOCTYPE a PUBLIC ' -//A\r\n B//EN ' 's y'><a/>",
|
|
'<!DOCTYPE a PUBLIC "" ""><a b="<A">&"'></a>',
|
|
'<!DOCTYPE svg:svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd"><svg:svg xmlns:svg="http://www.w3.org/2000/svg"/>',
|
|
'<!DOCTYPE a SYSTEM "x\r\ny\rz\n"><a/>',
|
|
];
|
|
const refused = [
|
|
"<!DOCTYPE a []><a/>",
|
|
'<!DOCTYPE a [<!ENTITY e "boom">]><a/>',
|
|
'<!DOCTYPE a [<!ENTITY e "boom">]><a>&e;</a>',
|
|
'<!DOCTYPE a SYSTEM "a.dtd" [<!ENTITY e SYSTEM "file:///etc/hostname">]><a>&e;</a>',
|
|
'<!DOCTYPE a [<!ENTITY % p SYSTEM "file:///etc/hostname"> %p;]><a/>',
|
|
'<!DOCTYPE a SYSTEM "a.dtd"><a>&e;</a>',
|
|
'<!DOCTYPE a SYSTEM "a.dtd"><a><b c="x &e; y"/></a>',
|
|
'<!DOCTYPE a PUBLIC "-//A//EN"><a/>',
|
|
'<!DOCTYPE a PUBLIC "x{" "y"><a/>',
|
|
"<a/><!DOCTYPE a>",
|
|
"<!DOCTYPE a><!DOCTYPE a><a/>",
|
|
];
|
|
const texts = [...accepted, ...refused];
|
|
|
|
const ours = texts.map((text) => xmlView(text) ?? null);
|
|
|
|
expect(pythonXmlViews(texts)).toEqual(ours);
|
|
expect(ours.slice(0, accepted.length)).not.toContain(null);
|
|
expect(ours.slice(accepted.length)).toEqual(refused.map(() => null));
|
|
expect(ours[2]).toMatchObject({
|
|
doctype: { name: "a", public_id: "-//A B//EN", system_id: "s y" },
|
|
});
|
|
expect(ours[5]).toMatchObject({
|
|
doctype: { name: "a", public_id: null, system_id: "x\ny\nz\n" },
|
|
});
|
|
});
|
|
|
|
it("never reads the DTD a DOCTYPE names: neither its entities nor its default attributes apply", async () => {
|
|
const folder = await createTestTempDirectory("desktop-xml-dtd-");
|
|
const dtd = join(folder, "a.dtd");
|
|
await writeFile(
|
|
dtd,
|
|
'<!ENTITY e "from the DTD"><!ATTLIST a injected CDATA "from the DTD">',
|
|
);
|
|
const system = pathToFileURL(dtd).href;
|
|
const texts = [
|
|
`<!DOCTYPE a SYSTEM "${system}"><a/>`,
|
|
`<!DOCTYPE a SYSTEM "${system}"><a>&e;</a>`,
|
|
`<!DOCTYPE a SYSTEM "${system}"><a b="&e;"/>`,
|
|
];
|
|
|
|
const ours = texts.map((text) => xmlView(text) ?? null);
|
|
|
|
expect(pythonXmlViews(texts)).toEqual(ours);
|
|
expect(ours).toEqual([
|
|
{
|
|
doctype: { name: "a", public_id: null, system_id: system },
|
|
root: { name: "a", attributes: {}, children: [] },
|
|
truncated: false,
|
|
},
|
|
null,
|
|
null,
|
|
]);
|
|
});
|
|
});
|
|
|
|
describe("whole-text checks in both evaluators", () => {
|
|
it("checks the meeting time across AbiWord's runs: the whole text fails before and passes after, its first node does not", async () => {
|
|
const [before, after] = await expectSameCheckResults(
|
|
NOTE,
|
|
NOTE_CHECKS,
|
|
await notes(),
|
|
);
|
|
|
|
expect(passes(before)).toEqual([false, false, false]);
|
|
for (const fact of [
|
|
PARAGRAPH,
|
|
JSON.stringify("The team meeting starts at 2:00 in room 4."),
|
|
])
|
|
expect(before?.[0]?.description).toContain(fact);
|
|
expect(passes(after)).toEqual([true, true, false]);
|
|
// The first text node holds only the text before the first run.
|
|
expect(after?.[2]?.description).toContain(
|
|
JSON.stringify("The team meeting starts at "),
|
|
);
|
|
});
|
|
|
|
it("reads Writer's runs in its archive alike, the space between two runs included", async () => {
|
|
const files = await flyers();
|
|
await expectSameFileViews(files);
|
|
|
|
const [before, after] = await expectSameCheckResults(
|
|
FLYER,
|
|
FLYER_CHECKS,
|
|
files,
|
|
);
|
|
|
|
expect(passes(before)).toEqual([false, false, false, false]);
|
|
expect(passes(after)).toEqual([true, true, true, false]);
|
|
// The value searched for is the collapsed one, " 9:30\n" read as "9:30".
|
|
expect(after?.[1]?.description).toContain(JSON.stringify("9:30"));
|
|
});
|
|
});
|