feat: page history diff (#1891)

* Show actual history changes
* V2 - WIP
* feat: page history diff
* fix: exclude content from history listing

---------

Co-authored-by: Jason Norwood-Young <jason@10layer.com>
This commit is contained in:
Philip Okugbe
2026-02-03 11:55:20 -08:00
committed by GitHub
parent f32bb298e0
commit 5506eb194b
34 changed files with 1434 additions and 154 deletions
+1
View File
@@ -24,3 +24,4 @@ export * from "./lib/highlight";
export * from "./lib/heading/heading";
export * from "./lib/unique-id";
export * from "./lib/shared-storage";
export * from "./lib/recreate-transform";
@@ -0,0 +1,3 @@
export function copy<T>(value: T): T {
return JSON.parse(JSON.stringify(value));
}
@@ -0,0 +1,17 @@
import { AnyObject } from "./types";
/**
* get target value from json-pointer (e.g. /content/0/content)
* @param {AnyObject} obj object to resolve path into
* @param {string} path json-pointer
* @return {any} target value
*/
export function getFromPath(obj: AnyObject, path: string): any {
const pathParts = path.split("/");
pathParts.shift(); // remove root-entry
while (pathParts.length) {
const property = pathParts.shift();
obj = obj[property];
}
return obj;
}
@@ -0,0 +1,29 @@
import { ReplaceStep } from "@tiptap/pm/transform";
import { Node } from "@tiptap/pm/model";
export function getReplaceStep(fromDoc: Node, toDoc: Node) {
let start = toDoc.content.findDiffStart(fromDoc.content);
if (start === null) {
return false;
}
// @ts-ignore property access to content
let { a: endA, b: endB } = toDoc.content.findDiffEnd(fromDoc.content);
const overlap = start - Math.min(endA, endB);
if (overlap > 0) {
// If there is an overlap, there is some freedom of choice in how to calculate the
// start/end boundary. for an inserted/removed slice. We choose the extreme with
// the lowest depth value.
if (
fromDoc.resolve(start - overlap).depth <
toDoc.resolve(endA + overlap).depth
) {
start -= overlap;
} else {
endA += overlap;
endB += overlap;
}
}
return new ReplaceStep(start, endB, toDoc.slice(start, endA));
}
@@ -0,0 +1,4 @@
// https://gitlab.com/mpapp-public/prosemirror-recreate-steps - MIT
// https://github.com/sueddeutsche/prosemirror-recreate-transform - MIT
export { recreateTransform, RecreateTransform } from "./recreateTransform";
export type { Options } from "./recreateTransform";
@@ -0,0 +1,279 @@
import { Transform } from "@tiptap/pm/transform";
import { Node, Schema } from "@tiptap/pm/model";
import { applyPatch, createPatch, Operation } from "rfc6902";
import { diffWordsWithSpace, diffChars } from "diff";
import { AnyObject } from "./types";
import { getReplaceStep } from "./getReplaceStep";
import { simplifyTransform } from "./simplifyTransform";
import { removeMarks } from "./removeMarks";
import { getFromPath } from "./getFromPath";
import { copy } from "./copy";
export interface Options {
complexSteps?: boolean;
wordDiffs?: boolean;
simplifyDiff?: boolean;
}
export class RecreateTransform {
fromDoc: Node;
toDoc: Node;
complexSteps: boolean;
wordDiffs: boolean;
simplifyDiff: boolean;
schema: Schema;
tr: Transform;
/* current working document data, may get updated while recalculating node steps */
currentJSON: AnyObject;
/* final document as json data */
finalJSON: AnyObject;
ops: Array<Operation>;
constructor(fromDoc: Node, toDoc: Node, options: Options = {}) {
const o = {
complexSteps: true,
wordDiffs: false,
simplifyDiff: true,
...options,
};
this.fromDoc = fromDoc;
this.toDoc = toDoc;
this.complexSteps = o.complexSteps; // Whether to return steps other than ReplaceSteps
this.wordDiffs = o.wordDiffs; // Whether to make text diffs cover entire words
this.simplifyDiff = o.simplifyDiff;
this.schema = fromDoc.type.schema;
this.tr = new Transform(fromDoc);
}
init() {
if (this.complexSteps) {
// For First steps: we create versions of the documents without marks as
// these will only confuse the diffing mechanism and marks won't cause
// any mapping changes anyway.
this.currentJSON = removeMarks(this.fromDoc).toJSON();
this.finalJSON = removeMarks(this.toDoc).toJSON();
this.ops = createPatch(this.currentJSON, this.finalJSON);
this.recreateChangeContentSteps();
this.recreateChangeMarkSteps();
} else {
// We don't differentiate between mark changes and other changes.
this.currentJSON = this.fromDoc.toJSON();
this.finalJSON = this.toDoc.toJSON();
this.ops = createPatch(this.currentJSON, this.finalJSON);
this.recreateChangeContentSteps();
}
if (this.simplifyDiff) {
this.tr = simplifyTransform(this.tr) || this.tr;
}
return this.tr;
}
/** convert json-diff to prosemirror steps */
recreateChangeContentSteps() {
// First step: find content changing steps.
let ops = [];
while (this.ops.length) {
// get next
let op = this.ops.shift();
ops.push(op);
let toDoc;
const afterStepJSON = copy(this.currentJSON); // working document receiving patches
const pathParts = op.path.split("/");
// collect operations until we receive a valid document:
// apply ops-patches until a valid prosemirror document is retrieved,
// then try to create a transformation step or retry with next operation
while (toDoc == null) {
applyPatch(afterStepJSON, [op]);
try {
toDoc = this.schema.nodeFromJSON(afterStepJSON);
toDoc.check();
} catch (error) {
toDoc = null;
if (this.ops.length > 0) {
op = this.ops.shift();
ops.push(op);
} else {
throw new Error(`No valid diff possible applying ${op.path}`);
}
}
}
// apply operation (ignoring afterStepJSON)
if (
this.complexSteps &&
ops.length === 1 &&
(pathParts.includes("attrs") || pathParts.includes("type"))
) {
// Node markup is changing
this.addSetNodeMarkup(); // a lost update is ignored
ops = [];
// console.log("%cop", logStyle, "- update node", ops);
} else if (
ops.length === 1 &&
op.op === "replace" &&
pathParts[pathParts.length - 1] === "text"
) {
// Text is being replaced, we apply text diffing to find the smallest possible diffs.
this.addReplaceTextSteps(op, afterStepJSON);
ops = [];
// console.log("%cop", logStyle, "- replace", ops);
} else if (this.addReplaceStep(toDoc, afterStepJSON)) {
// operations have been applied
ops = [];
// console.log("%cop", logStyle, "- other", ops);
}
}
}
/** update node with attrs and marks, may also change type */
addSetNodeMarkup() {
// first diff in document is supposed to be a node-change (in type and/or attributes)
// thus simply find the first change and apply a node change step, then recalculate the diff
// after updating the document
const fromDoc = this.schema.nodeFromJSON(this.currentJSON);
const toDoc = this.schema.nodeFromJSON(this.finalJSON);
const start = toDoc.content.findDiffStart(fromDoc.content);
// @note start is the same (first) position for current and target document
const fromNode = fromDoc.nodeAt(start);
const toNode = toDoc.nodeAt(start);
if (start != null) {
// @note this completly updates all attributes in one step, by completely replacing node
const nodeType = fromNode.type === toNode.type ? null : toNode.type;
try {
this.tr.setNodeMarkup(start, nodeType, toNode.attrs, toNode.marks);
} catch (e) {
// if nodetypes differ, the updated node-type and contents might not be compatible
// with schema and requires a replace
if (nodeType && e.message.includes("Invalid content")) {
// @todo add test-case for this scenario
this.tr.replaceWith(start, start + fromNode.nodeSize, toNode);
} else {
throw e;
}
}
this.currentJSON = removeMarks(this.tr.doc).toJSON();
// setting the node markup may have invalidated the following ops, so we calculate them again.
this.ops = createPatch(this.currentJSON, this.finalJSON);
return true;
}
return false;
}
recreateChangeMarkSteps() {
// Now the documents should be the same, except their marks, so everything should map 1:1.
// Second step: Iterate through the toDoc and make sure all marks are the same in tr.doc
this.toDoc.descendants((tNode, tPos) => {
if (!tNode.isInline) {
return true;
}
this.tr.doc.nodesBetween(tPos, tPos + tNode.nodeSize, (fNode, fPos) => {
if (!fNode.isInline) {
return true;
}
const from = Math.max(tPos, fPos);
const to = Math.min(tPos + tNode.nodeSize, fPos + fNode.nodeSize);
fNode.marks.forEach((nodeMark) => {
if (!nodeMark.isInSet(tNode.marks)) {
this.tr.removeMark(from, to, nodeMark);
}
});
tNode.marks.forEach((nodeMark) => {
if (!nodeMark.isInSet(fNode.marks)) {
this.tr.addMark(from, to, nodeMark);
}
});
});
});
}
/**
* retrieve and possibly apply replace-step based from doc changes
* From http://prosemirror.net/examples/footnote/
*/
addReplaceStep(toDoc: Node, afterStepJSON: AnyObject) {
const fromDoc = this.schema.nodeFromJSON(this.currentJSON);
const step = getReplaceStep(fromDoc, toDoc);
if (!step) {
return false;
} else if (!this.tr.maybeStep(step).failed) {
this.currentJSON = afterStepJSON;
return true; // @change previously null
}
throw new Error("No valid step found.");
}
/** retrieve and possibly apply text replace-steps based from doc changes */
addReplaceTextSteps(op, afterStepJSON) {
// We find the position number of the first character in the string
const op1 = { ...op, value: "xx" };
const op2 = { ...op, value: "yy" };
const afterOP1JSON = copy(this.currentJSON);
const afterOP2JSON = copy(this.currentJSON);
applyPatch(afterOP1JSON, [op1]);
applyPatch(afterOP2JSON, [op2]);
const op1Doc = this.schema.nodeFromJSON(afterOP1JSON);
const op2Doc = this.schema.nodeFromJSON(afterOP2JSON);
// get text diffs
const finalText = op.value;
const currentText = getFromPath(this.currentJSON, op.path);
const textDiffs = this.wordDiffs
? diffWordsWithSpace(currentText, finalText)
: diffChars(currentText, finalText);
let offset = op1Doc.content.findDiffStart(op2Doc.content);
const marks = op1Doc.resolve(offset + 1).marks();
while (textDiffs.length) {
const diff = textDiffs.shift();
if (diff.added) {
const textNode = this.schema
.nodeFromJSON({ type: "text", text: diff.value })
.mark(marks);
if (textDiffs.length && textDiffs[0].removed) {
const nextDiff = textDiffs.shift();
this.tr.replaceWith(offset, offset + nextDiff.value.length, textNode);
} else {
this.tr.insert(offset, textNode);
}
offset += diff.value.length;
} else if (diff.removed) {
if (textDiffs.length && textDiffs[0].added) {
const nextDiff = textDiffs.shift();
const textNode = this.schema
.nodeFromJSON({ type: "text", text: nextDiff.value })
.mark(marks);
this.tr.replaceWith(offset, offset + diff.value.length, textNode);
offset += nextDiff.value.length;
} else {
this.tr.delete(offset, offset + diff.value.length);
}
} else {
offset += diff.value.length;
}
}
this.currentJSON = afterStepJSON;
}
}
export function recreateTransform(
fromDoc: Node,
toDoc: Node,
options: Options = {},
): Transform {
const recreator = new RecreateTransform(fromDoc, toDoc, options);
return recreator.init();
}
@@ -0,0 +1,8 @@
import { Transform } from "@tiptap/pm/transform";
import { Node } from "@tiptap/pm/model";
export function removeMarks(doc: Node) {
const tr = new Transform(doc);
tr.removeMark(0, doc.nodeSize - 2);
return tr.doc;
}
@@ -0,0 +1,30 @@
import { Transform, ReplaceStep, Step } from "@tiptap/pm/transform";
import { getReplaceStep } from "./getReplaceStep";
// join adjacent ReplaceSteps
export function simplifyTransform(tr: Transform) {
if (!tr.steps.length) {
return undefined;
}
const newTr = new Transform(tr.docs[0]);
const oldSteps = tr.steps.slice();
while (oldSteps.length) {
let step = oldSteps.shift();
while (oldSteps.length && step.merge(oldSteps[0])) {
const addedStep = oldSteps.shift();
if (step instanceof ReplaceStep && addedStep instanceof ReplaceStep) {
step = getReplaceStep(
newTr.doc,
addedStep.apply(step.apply(newTr.doc).doc).doc,
// @ts-ignore
) as Step<any>;
} else {
step = step.merge(addedStep);
}
}
newTr.step(step);
}
return newTr;
}
@@ -0,0 +1,3 @@
export interface AnyObject {
[p: string]: any;
}