remove pages and cleanup

This commit is contained in:
Felix Kaspar 2024-05-17 18:13:15 +02:00
parent df10eacf92
commit 2420e59cd8
4 changed files with 64 additions and 32 deletions

View File

@ -1,17 +1,22 @@
/**
* @param selection An array of page indexes already selected.
* @param pages A list of page indexes, or the number of total pages in the document (which will be converted into a list of page indexes).
* @param pageCount The number of pages of the pdfDocument.
* @returns An inverted selection array of page indexes.
*/
export function invertSelection(selection: number[], pages: number|number[]): number[] {
const indexes = Array.isArray(pages) ? pages : [...Array(pages).keys()];
const pageIndexesCopy = [...indexes];
return pageIndexesCopy.filter(x => !selection.includes(x));
export function invertSelection(selection: number[], pageCount: number): number[] {
const newSelection = [];
for (let pageIndex = 0; pageIndex < pageCount; pageIndex++) {
if(!selection.includes(pageIndex))
newSelection.push(pageIndex);
}
return newSelection;
}
// TODO: Port this to CommaArrayJoiExt.ts
/**
* Parse the page selector string used in the 'PDF Page Organizer'
* Parse the page selector string
* @param specification
* @param totalPages
* @returns

View File

@ -7,7 +7,6 @@ import { JoiPDFFileSchema } from "../wrappers/PdfFileJoi";
import i18next from "i18next";
import { getPages } from "./common/getPagesByIndex";
import { parsePageIndexSpecification } from "./common/pageIndexesUtils";
import CommaArrayJoiExt from "../wrappers/CommaArrayJoiExt";
export class ExtractPages extends Operator {
@ -39,15 +38,8 @@ export class ExtractPages extends Operator {
/** PDF extraction, specify pages from one pdf and output them to a new pdf */
async run(input: PdfFile[], progressCallback: (state: Progress) => void): Promise<PdfFile[]> {
return oneToOne<PdfFile, PdfFile>(input, async (input, index, max) => {
const pdfLibDocument = await input.pdfLibDocument;
let indexes = this.actionValues.pageIndexes;
if (!Array.isArray(indexes)) {
indexes = parsePageIndexSpecification(indexes, pdfLibDocument.getPageCount());
}
const newFile = await getPages(input, indexes);
const newFile = await getPages(input, this.actionValues.pageIndexes);
newFile.filename += "_extractedPages";
progressCallback({ curFileProgress: 1, operationProgress: index/max });

View File

@ -1,21 +1,56 @@
import { PdfFile } from "../wrappers/PdfFile";
import { Operator, Progress, oneToOne } from ".";
import Joi from "@stirling-tools/joi";
import { JoiPDFFileSchema } from "../wrappers/PdfFileJoi";
import i18next from "i18next";
import { getPages } from "./common/getPagesByIndex";
import { invertSelection, parsePageIndexSpecification } from "./common/pageIndexesUtils";
import CommaArrayJoiExt from "../wrappers/CommaArrayJoiExt";
export interface RemovePagesParamsType {
file: PdfFile;
pageSelector: string;
}
export async function removePages(params: RemovePagesParamsType) {
const { file, pageSelector } = params;
const pdfDoc = await file.pdfLibDocument;
const pageCount = pdfDoc.getPageCount();
import { invertSelection } from "./common/pageIndexesUtils";
const pageSelection = parsePageIndexSpecification(pageSelector, pageCount);
const pagesToKeep = invertSelection(pageSelection, pageCount);
export class RemovePages extends Operator {
static type = "removePages";
const newFile = await getPages(file, pagesToKeep);
newFile.filename += "_removedPages";
return newFile;
/**
* Validation & Localisation
*/
protected static inputSchema = JoiPDFFileSchema.label(i18next.t("inputs.pdffile.name")).description(i18next.t("inputs.pdffile.description"));
protected static valueSchema = Joi.object({
pageIndexes: CommaArrayJoiExt.comma_array().items(Joi.number().integer()).required()
.label(i18next.t("values.pageIndexes.friendlyName", { ns: "removePages" })).description(i18next.t("values.pageIndexes.description", { ns: "removePages" }))
.example("1").example("1, 2, 3, 4").example("4, 2, 4, 3").required()
});
protected static outputSchema = JoiPDFFileSchema.label(i18next.t("outputs.pdffile.name")).description(i18next.t("outputs.pdffile.description"));
static schema = Joi.object({
input: RemovePages.inputSchema,
values: RemovePages.valueSchema.required(),
output: RemovePages.outputSchema
}).label(i18next.t("friendlyName", { ns: "removePages" })).description(i18next.t("description", { ns: "removePages" }));
/**
* Logic
*/
/** PDF extraction, specify pages from one pdf and output them to a new pdf */
async run(input: PdfFile[], progressCallback: (state: Progress) => void): Promise<PdfFile[]> {
return oneToOne<PdfFile, PdfFile>(input, async (input, index, max) => {
const pdfDoc = await input.pdfLibDocument;
const pageCount = pdfDoc.getPageCount();
const pagesToKeep = invertSelection(this.actionValues.pageIndexes, pageCount);
const newFile = await getPages(input, pagesToKeep);
newFile.filename += "_removedPages";
progressCallback({ curFileProgress: 1, operationProgress: index/max });
return newFile;
});
}
}

View File

@ -6,13 +6,13 @@ export default Joi.extend((joi) => {
type: 'comma_array',
base: joi.array(),
messages: {
'million.base': '{{#label}} must be a comma seperated list',
'comma_array.base': '{{#label}} must be a comma seperated list',
},
coerce: {
from: 'string',
method(value, helpers) {
if (typeof value !== 'string' || !/(\d+)(,\s*\d+)*/.test(value)) {
if (typeof value !== 'string' || !/(\d+)(,\s*\d+)*/.test(value)) { // is string and in format "[number], [number]"
return;
}