Rename 'changes' format and property to 'changeTracking'

Co-Authored-By: mogery@sideguide.dev <mogery@sideguide.dev>
This commit is contained in:
Devin AI 2025-04-08 16:58:06 +00:00
parent 0a9b7e96f7
commit 89ffac85ab
5 changed files with 19 additions and 19 deletions

View File

@ -85,15 +85,15 @@ describe("Scrape tests", () => {
// }, 30000); // }, 30000);
// }); // });
describe("Changes format", () => { describe("Change Tracking format", () => {
it.concurrent("works", async () => { it.concurrent("works", async () => {
const response = await scrape({ const response = await scrape({
url: "https://example.com", url: "https://example.com",
formats: ["markdown", "changes"], formats: ["markdown", "changeTracking"],
}); });
expect(response.changes).toBeDefined(); expect(response.changeTracking).toBeDefined();
expect(response.changes?.previousScrapeAt).not.toBeNull(); expect(response.changeTracking?.previousScrapeAt).not.toBeNull();
}); });
}); });

View File

@ -21,7 +21,7 @@ export type Format =
| "screenshot" | "screenshot"
| "screenshot@fullPage" | "screenshot@fullPage"
| "extract" | "extract"
| "changes"; | "changeTracking";
export const url = z.preprocess( export const url = z.preprocess(
(x) => { (x) => {
@ -166,7 +166,7 @@ const baseScrapeOptions = z
"screenshot@fullPage", "screenshot@fullPage",
"extract", "extract",
"json", "json",
"changes", "changeTracking",
]) ])
.array() .array()
.optional() .optional()
@ -176,8 +176,8 @@ const baseScrapeOptions = z
"You may only specify either screenshot or screenshot@fullPage", "You may only specify either screenshot or screenshot@fullPage",
) )
.refine( .refine(
(x) => !x.includes("changes") || x.includes("markdown"), (x) => !x.includes("changeTracking") || x.includes("markdown"),
"The changes format requires the markdown format to be specified as well", "The changeTracking format requires the markdown format to be specified as well",
), ),
headers: z.record(z.string(), z.string()).optional(), headers: z.record(z.string(), z.string()).optional(),
includeTags: z.string().array().optional(), includeTags: z.string().array().optional(),
@ -552,7 +552,7 @@ export type Document = {
value: unknown value: unknown
}[]; }[];
}; };
changes?: { changeTracking?: {
previousScrapeAt: string | null; previousScrapeAt: string | null;
changeStatus: "new" | "same" | "changed" | "removed"; changeStatus: "new" | "same" | "changed" | "removed";
visibility: "visible" | "hidden"; visibility: "visible" | "hidden";

View File

@ -3,7 +3,7 @@ import { Document } from "../../../controllers/v1/types";
import { Meta } from "../index"; import { Meta } from "../index";
export async function deriveDiff(meta: Meta, document: Document): Promise<Document> { export async function deriveDiff(meta: Meta, document: Document): Promise<Document> {
if (meta.options.formats.includes("changes")) { if (meta.options.formats.includes("changeTracking")) {
const res = await supabase_service const res = await supabase_service
.rpc("diff_get_last_scrape_1", { .rpc("diff_get_last_scrape_1", {
i_team_id: meta.internalOptions.teamId, i_team_id: meta.internalOptions.teamId,
@ -21,13 +21,13 @@ export async function deriveDiff(meta: Meta, document: Document): Promise<Docume
const transformer = (x: string) => [...x.replace(/\s+/g, "").replace(/\[iframe\]\(.+?\)/g, "")].sort().join(""); const transformer = (x: string) => [...x.replace(/\s+/g, "").replace(/\[iframe\]\(.+?\)/g, "")].sort().join("");
document.changes = { document.changeTracking = {
previousScrapeAt: data.o_date_added, previousScrapeAt: data.o_date_added,
changeStatus: document.metadata.statusCode === 404 ? "removed" : transformer(previousMarkdown) === transformer(currentMarkdown) ? "same" : "changed", changeStatus: document.metadata.statusCode === 404 ? "removed" : transformer(previousMarkdown) === transformer(currentMarkdown) ? "same" : "changed",
visibility: meta.internalOptions.urlInvisibleInCurrentCrawl ? "hidden" : "visible", visibility: meta.internalOptions.urlInvisibleInCurrentCrawl ? "hidden" : "visible",
} }
} else if (!res.error) { } else if (!res.error) {
document.changes = { document.changeTracking = {
previousScrapeAt: null, previousScrapeAt: null,
changeStatus: document.metadata.statusCode === 404 ? "removed" : "new", changeStatus: document.metadata.statusCode === 404 ? "removed" : "new",
visibility: meta.internalOptions.urlInvisibleInCurrentCrawl ? "hidden" : "visible", visibility: meta.internalOptions.urlInvisibleInCurrentCrawl ? "hidden" : "visible",

View File

@ -148,14 +148,14 @@ export function coerceFieldsToFormats(
); );
} }
if (!formats.has("changes") && document.changes !== undefined) { if (!formats.has("changeTracking") && document.changeTracking !== undefined) {
meta.logger.warn( meta.logger.warn(
"Removed changes from Document because it wasn't in formats -- this is extremely wasteful and indicates a bug.", "Removed changeTracking from Document because it wasn't in formats -- this is extremely wasteful and indicates a bug.",
); );
delete document.changes; delete document.changeTracking;
} else if (formats.has("changes") && document.changes === undefined) { } else if (formats.has("changeTracking") && document.changeTracking === undefined) {
meta.logger.warn( meta.logger.warn(
"Request had format changes, but there was no changes field in the result.", "Request had format changeTracking, but there was no changeTracking field in the result.",
); );
} }

View File

@ -68,7 +68,7 @@ export interface FirecrawlDocument<T = any, ActionsSchema extends (ActionsResult
screenshot?: string; screenshot?: string;
metadata?: FirecrawlDocumentMetadata; metadata?: FirecrawlDocumentMetadata;
actions: ActionsSchema; actions: ActionsSchema;
changes?: { changeTracking?: {
previousScrapeAt: string | null; previousScrapeAt: string | null;
changeStatus: "new" | "same" | "changed" | "removed"; changeStatus: "new" | "same" | "changed" | "removed";
visibility: "visible" | "hidden"; visibility: "visible" | "hidden";
@ -83,7 +83,7 @@ export interface FirecrawlDocument<T = any, ActionsSchema extends (ActionsResult
* Defines the options and configurations available for scraping web content. * Defines the options and configurations available for scraping web content.
*/ */
export interface CrawlScrapeOptions { export interface CrawlScrapeOptions {
formats?: ("markdown" | "html" | "rawHtml" | "content" | "links" | "screenshot" | "screenshot@fullPage" | "extract" | "json" | "changes")[]; formats?: ("markdown" | "html" | "rawHtml" | "content" | "links" | "screenshot" | "screenshot@fullPage" | "extract" | "json" | "changeTracking")[];
headers?: Record<string, string>; headers?: Record<string, string>;
includeTags?: string[]; includeTags?: string[];
excludeTags?: string[]; excludeTags?: string[];