@quillmark/quillify 0.0.0-stage → 0.3.0

package/dist/xfa.js

@@ -0,0 +1,345 @@
+import { PDFAcroCheckBox, PDFAcroComboBox, PDFAcroRadioButton, PDFAcroText, PDFCheckBox, PDFDocument, PDFDropdown, PDFFont, PDFField, PDFHexString, PDFName, PDFOperator, PDFOperatorNames, PDFPage, PDFRadioGroup, PDFTextField, StandardFonts, degrees, rgb } from 'pdf-lib';
+import { displayList } from './display-list.js';
+import { openPdf } from './pdfjs.js';
+import { Refused } from './refusal.js';
+import { MAX_PAGES, MAX_PICTURE_PIXELS } from './types.js';
+import { XfaStage } from './xfa-layer.js';
+import { harvestWidgets } from './xfa-widgets.js';
+/**
+ * A dynamic Adobe LiveCycle form as an ordinary static AcroForm, or the input
+ * unchanged when it is not one.
+ *
+ * In a dynamic form the fields exist only as XML inside `/AcroForm /XFA`:
+ * `/Fields` is empty, and the one page in the file is a placeholder, most often
+ * a "Please wait" notice. Converting one takes an XFA layout engine, and pdf.js
+ * has one. This runs it, reads the geometry the browser solved off the DOM, and
+ * writes both the printed page and the fields back out as a PDF the later
+ * stages already take.
+ *
+ * It is a normalization: bytes in, bytes out, and every later stage reads the
+ * result as it reads a static form.
+ */
+export async function xfaToAcroForm(bytes, signal) {
+    const stage = new XfaStage();
+    let opened;
+    try {
+        // pdf.js adds the faces a form embeds to this document's font set.
+        opened = await openPdf(bytes, { enableXfa: true, ownerDocument: await stage.ready }, signal);
+        const { pdf, within } = opened;
+        if (!pdf.isPureXfa)
+            return bytes;
+        // pdf.js counts a dynamic form's pages as it opens the file.
+        if (pdf.numPages > MAX_PAGES)
+            throw new Refused({ code: 'too_many_pages', pages: pdf.numPages, limit: MAX_PAGES });
+        const out = await PDFDocument.create();
+        const fonts = new Map();
+        const widgets = [];
+        let pixels = 0;
+        for (let number = 1; number <= pdf.numPages; number++) {
+            const laid = await within(pdf.getPage(number).then((page) => stage.lay(page)));
+            // The shipped worker writes a span of one of these classes where the page's
+            // text embeds a page number or a page count that a layout script fills.
+            for (const span of laid.layer.querySelectorAll('.xfaPageNumber'))
+                span.textContent = String(number);
+            for (const span of laid.layer.querySelectorAll('.xfaPageCount'))
+                span.textContent = String(pdf.numPages);
+            const list = displayList(laid, number);
+            for (const { image } of list.pictures)
+                pixels += image.naturalWidth * image.naturalHeight;
+            if (pixels > MAX_PICTURE_PIXELS)
+                throw new Refused({
+                    code: 'unpaintable',
+                    page: number - 1,
+                    construct: 'image',
+                    detail: 'pixels'
+                });
+            for (const widget of harvestWidgets(laid, number))
+                widgets.push(widget);
+            await paint(out.addPage([list.width, list.height]), number, list, async (name) => {
+                let font = fonts.get(name);
+                if (!font)
+                    fonts.set(name, (font = await out.embedFont(name)));
+                return font;
+            });
+        }
+        stamp(out, widgets);
+        return await out.save();
+    }
+    finally {
+        stage.close();
+        await opened?.close();
+    }
+}
+/** PDF's origin is bottom-left; every primitive arrives top-left. */
+async function paint(page, pageNumber, list, font) {
+    const H = list.height;
+    for (let box of list.boxes) {
+        if (box.radius) {
+            // An SVG rect's outline runs along the middle of its stroke, and each
+            // radius stops at half the side it lies along.
+            const [edge] = box.edges;
+            const inset = (edge?.width ?? 0) / 2;
+            const w = box.w - 2 * inset;
+            const h = box.h - 2 * inset;
+            const rx = Math.min(box.radius, w / 2);
+            const ry = Math.min(box.radius, h / 2);
+            const turn = `a ${rx},${ry} 0 0 1`;
+            page.drawSvgPath(`M ${rx},0 h ${w - 2 * rx} ${turn} ${rx},${ry} v ${h - 2 * ry} ${turn} ${-rx},${ry} h ${2 * rx - w} ${turn} ${-rx},${-ry} v ${2 * ry - h} ${turn} ${rx},${-ry} z`, {
+                x: box.x + inset,
+                y: H - box.y - inset,
+                color: box.fill ? rgb(...box.fill) : undefined,
+                borderColor: edge ? rgb(...edge.colour) : undefined,
+                borderWidth: edge?.width
+            });
+            continue;
+        }
+        // The browser paints a box from a whole pixel to a whole pixel, and fits
+        // the gap of a dashed edge to the length that leaves it.
+        if (box.edges.some((edge) => edge?.dashed)) {
+            const [x, y] = [Math.round(box.x), Math.round(box.y)];
+            box = { ...box, x, y, w: Math.round(box.x + box.w) - x, h: Math.round(box.y + box.h) - y };
+        }
+        if (box.fill)
+            page.drawRectangle({
+                x: box.x,
+                y: H - box.y - box.h,
+                width: box.w,
+                height: box.h,
+                color: rgb(...box.fill),
+                borderWidth: 0
+            });
+        const [top, right, bottom, left] = box.edges;
+        const seg = (x1, y1, x2, y2, edge) => page.drawLine({
+            start: { x: x1, y: H - y1 },
+            end: { x: x2, y: H - y2 },
+            thickness: edge.width,
+            color: rgb(...edge.colour),
+            dashArray: edge.dashed ? dashes(edge.width, x2 - x1 + y2 - y1) : undefined
+        });
+        if (top)
+            seg(box.x, box.y + top.width / 2, box.x + box.w, box.y + top.width / 2, top);
+        if (bottom)
+            seg(box.x, box.y + box.h - bottom.width / 2, box.x + box.w, box.y + box.h - bottom.width / 2, bottom);
+        if (left)
+            seg(box.x + left.width / 2, box.y, box.x + left.width / 2, box.y + box.h, left);
+        if (right)
+            seg(box.x + box.w - right.width / 2, box.y, box.x + box.w - right.width / 2, box.y + box.h, right);
+    }
+    for (const { x, y, w, h, image } of list.pictures) {
+        // The pixels are read off a canvas of the host page's. The frame's policy
+        // governs what its document loads, and the picture is of the page's origin.
+        const canvas = document.createElement('canvas');
+        canvas.width = image.naturalWidth;
+        canvas.height = image.naturalHeight;
+        canvas.getContext('2d').drawImage(image, 0, 0);
+        const png = canvas.toDataURL('image/png');
+        // What a canvas with a side the browser will not make gives.
+        if (png === 'data:,')
+            throw new Refused({ code: 'unpaintable', page: pageNumber - 1, construct: 'image' });
+        page.drawImage(await page.doc.embedPng(png), { x, y: H - y - h, width: w, height: h });
+    }
+    for (const line of list.lines)
+        page.drawLine({
+            start: { x: line.x1, y: H - line.y1 },
+            end: { x: line.x2, y: H - line.y2 },
+            thickness: line.width,
+            color: rgb(...line.colour)
+        });
+    return drawRuns(page, pageNumber, list.runs, H, font);
+}
+/**
+ * The dash and the gap the browser paints along a dashed edge, or nothing for
+ * an edge it paints whole. A dash is three widths and a gap two for an edge
+ * under 3 px wide, and two and one from there. An edge too short for two
+ * dashes is whole, and one too short for two dashes and a whole gap has both
+ * shortened alike. On any other the gap is fitted so that the edge starts and
+ * ends on a whole dash: of the two counts of dashes its length lies between,
+ * it has the one whose gap is nearer.
+ */
+function dashes(width, length) {
+    const [dash, gap] = width < 3 ? [3 * width, 2 * width] : [2 * width, width];
+    if (length <= 2 * dash)
+        return undefined;
+    const short = length / (2 * dash + gap);
+    if (short <= 1)
+        return [dash * short, gap * short];
+    const count = Math.floor((length + gap) / (dash + gap));
+    const fit = (dashes) => (length - dashes * dash) / (dashes - 1);
+    const [wide, narrow] = [fit(count), fit(count + 1)];
+    return [dash, narrow <= 0 || Math.abs(wide - gap) < Math.abs(narrow - gap) ? wide : narrow];
+}
+async function drawRuns(page, pageNumber, runs, H, get) {
+    for (const run of runs) {
+        const font = await get(standard14(run));
+        // The standard-14 fonts encode WinAnsi alone. Dropping the run would lose a
+        // line of the form without anything reporting it.
+        const encodable = font.getCharacterSet();
+        if ([...run.text].some((char) => !encodable.includes(char.codePointAt(0))))
+            throw new Refused({
+                code: 'unpaintable',
+                page: pageNumber - 1,
+                construct: 'glyph',
+                detail: run.text.slice(0, 40)
+            });
+        // The standard-14 substitute's advances differ from the embedded face's.
+        // Letter spacing goes in first, since it is a real property of the run;
+        // horizontal scaling then pins the whole run to the width the browser
+        // measured, so the error stays inside the run instead of drifting across
+        // the line.
+        // pdf-lib kerns the width it measures and writes no kerning, so the width
+        // it draws a run at is the sum of the widths of its characters.
+        let natural = 0;
+        for (const char of run.text)
+            natural += font.widthOfTextAtSize(char, run.size);
+        const spaced = natural + run.letterSpacing * Math.max(0, run.text.length - 1);
+        const scale = spaced > 0 && run.width > 0 ? Math.max(50, Math.min(200, (100 * run.width) / spaced)) : 100;
+        const scaled = Math.abs(scale - 100) > 3;
+        // Both are text-state parameters, so they persist across drawText's own
+        // BT/ET and have to be put back.
+        if (run.letterSpacing)
+            page.pushOperators(PDFOperator.of(PDFOperatorNames.SetCharacterSpacing, [
+                String(+run.letterSpacing.toFixed(4))
+            ]));
+        if (scaled)
+            page.pushOperators(PDFOperator.of(PDFOperatorNames.SetTextHorizontalScaling, [String(+scale.toFixed(3))]));
+        page.drawText(run.text, {
+            x: run.x,
+            y: H - run.baseline,
+            size: run.size,
+            font,
+            color: rgb(...run.colour),
+            rotate: degrees(90 * (run.turn ?? 0))
+        });
+        if (scaled)
+            page.pushOperators(PDFOperator.of(PDFOperatorNames.SetTextHorizontalScaling, ['100']));
+        if (run.letterSpacing)
+            page.pushOperators(PDFOperator.of(PDFOperatorNames.SetCharacterSpacing, ['0']));
+    }
+}
+function standard14(run) {
+    const family = run.family.toLowerCase();
+    if (family.includes('courier') || family.includes('mono'))
+        return run.bold && run.italic
+            ? StandardFonts.CourierBoldOblique
+            : run.bold
+                ? StandardFonts.CourierBold
+                : run.italic
+                    ? StandardFonts.CourierOblique
+                    : StandardFonts.Courier;
+    if (family.includes('times') || (family.includes('serif') && !family.includes('sans')))
+        return run.bold && run.italic
+            ? StandardFonts.TimesRomanBoldItalic
+            : run.bold
+                ? StandardFonts.TimesRomanBold
+                : run.italic
+                    ? StandardFonts.TimesRomanItalic
+                    : StandardFonts.TimesRoman;
+    return run.bold && run.italic
+        ? StandardFonts.HelveticaBoldOblique
+        : run.bold
+            ? StandardFonts.HelveticaBold
+            : run.italic
+                ? StandardFonts.HelveticaOblique
+                : StandardFonts.Helvetica;
+}
+/**
+ * The fields, as the shapes the inventory already understands. Radios become a
+ * real AcroForm radio group, so the inventory reads each option's group and
+ * on-state as it reads a static form's.
+ *
+ * For a text field, a checkbox and a dropdown pdf-lib asks whether
+ * `backgroundColor` and `borderColor` are `in` the options, and defaults a
+ * missing background to white and a missing border to black, so both are
+ * passed as undefined. Left out, each paints a white box with a black border
+ * over the page. A radio option takes those defaults whatever is passed, with
+ * a border of no width.
+ *
+ * The fields are flat, each made from pdf-lib's own field class with its whole
+ * name as its `/T`. pdf-lib's form would read a period in the name as a level
+ * of its field tree, and holds no name as both a field and the parent of one,
+ * which a field named as the subform beside it asks for. pdf.js joins the `/T`
+ * of a field's ancestors with periods, so the inventory reads the whole name.
+ *
+ * A signature field is a dictionary of the keys the inventory reads, since
+ * pdf-lib has no class that creates one.
+ */
+function stamp(doc, widgets) {
+    const { acroForm } = doc.getForm();
+    const pages = doc.getPages();
+    const chrome = { borderWidth: 0, backgroundColor: undefined, borderColor: undefined };
+    const groups = new Map();
+    const states = new Map();
+    const rooted = (acro, name, of) => {
+        acro.setPartialName(name);
+        acroForm.addField(acro.ref);
+        return of(acro, acro.ref, doc);
+    };
+    for (const widget of widgets) {
+        const page = pages[widget.page];
+        const box = {
+            x: widget.x,
+            y: page.getHeight() - widget.y - widget.h,
+            width: widget.w,
+            height: widget.h,
+            ...chrome
+        };
+        if (widget.kind === 'radio' && widget.group) {
+            let group = groups.get(widget.group);
+            if (!group) {
+                group = rooted(PDFAcroRadioButton.create(doc.context), widget.group, PDFRadioGroup.of);
+                groups.set(widget.group, group);
+                states.set(widget.group, new Set());
+            }
+            // Two members of one group cannot share an on-state, or picking either
+            // picks both.
+            const used = states.get(widget.group);
+            let on = widget.on || 'option';
+            for (let n = 2; used.has(on); n++)
+                on = `${widget.on || 'option'}${n}`;
+            used.add(on);
+            group.addOptionToPage(on, page, box);
+            tooltip(group, widget.tooltip);
+            continue;
+        }
+        if (widget.kind === 'checkbox') {
+            const tick = rooted(PDFAcroCheckBox.create(doc.context), widget.name, PDFCheckBox.of);
+            tick.addToPage(page, box);
+            tooltip(tick, widget.tooltip);
+            continue;
+        }
+        if (widget.kind === 'choice') {
+            const dropdown = rooted(PDFAcroComboBox.create(doc.context), widget.name, PDFDropdown.of);
+            dropdown.addOptions(widget.options.length ? widget.options : ['']);
+            dropdown.addToPage(page, box);
+            tooltip(dropdown, widget.tooltip);
+            continue;
+        }
+        if (widget.kind === 'signature') {
+            const ref = doc.context.register(doc.context.obj({
+                FT: 'Sig',
+                Subtype: 'Widget',
+                T: PDFHexString.fromText(widget.name),
+                Rect: [box.x, box.y, box.x + box.width, box.y + box.height],
+                ...(widget.tooltip ? { TU: PDFHexString.fromText(widget.tooltip) } : {})
+            }));
+            page.node.addAnnot(ref);
+            acroForm.addField(ref);
+            continue;
+        }
+        const field = rooted(PDFAcroText.create(doc.context), widget.name, PDFTextField.of);
+        if (widget.kind === 'multiline')
+            field.enableMultiline();
+        field.addToPage(page, box);
+        tooltip(field, widget.tooltip);
+    }
+}
+/** `/TU`, which the inventory reads as the widget's tooltip. */
+function tooltip(field, text) {
+    if (!text)
+        return;
+    // Written on the widget just added. `addToPage` and `addOptionToPage` push
+    // into `/Kids`, so writing to every kid would give each option of a radio
+    // group the last option's caption.
+    const widget = field.acroField.getWidgets().at(-1);
+    widget?.dict.set(PDFName.of('TU'), PDFHexString.fromText(text));
+}

package/licenses/LiberationSans-LICENSE

@@ -0,0 +1,102 @@
+Digitized data copyright (c) 2010 Google Corporation
+	with Reserved Font Arimo, Tinos and Cousine.
+Copyright (c) 2012 Red Hat, Inc.
+	with Reserved Font Name Liberation.
+
+This Font Software is licensed under the SIL Open Font License,
+Version 1.1.
+
+This license is copied below, and is also available with a FAQ at:
+http://scripts.sil.org/OFL
+
+SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007
+
+PREAMBLE The goals of the Open Font License (OFL) are to stimulate
+worldwide development of collaborative font projects, to support the font
+creation efforts of academic and linguistic communities, and to provide
+a free and open framework in which fonts may be shared and improved in
+partnership with others.
+
+The OFL allows the licensed fonts to be used, studied, modified and
+redistributed freely as long as they are not sold by themselves.
+The fonts, including any derivative works, can be bundled, embedded,
+redistributed and/or sold with any software provided that any reserved
+names are not used by derivative works.  The fonts and derivatives,
+however, cannot be released under any other type of license.  The
+requirement for fonts to remain under this license does not apply to
+any document created using the fonts or their derivatives.
+
+ 
+
+DEFINITIONS
+"Font Software" refers to the set of files released by the Copyright
+Holder(s) under this license and clearly marked as such.
+This may include source files, build scripts and documentation.
+
+"Reserved Font Name" refers to any names specified as such after the
+copyright statement(s).
+
+"Original Version" refers to the collection of Font Software components
+as distributed by the Copyright Holder(s).
+
+"Modified Version" refers to any derivative made by adding to, deleting,
+or substituting ? in part or in whole ?
+any of the components of the Original Version, by changing formats or
+by porting the Font Software to a new environment.
+
+"Author" refers to any designer, engineer, programmer, technical writer
+or other person who contributed to the Font Software.
+
+
+PERMISSION & CONDITIONS
+
+Permission is hereby granted, free of charge, to any person obtaining a
+copy of the Font Software, to use, study, copy, merge, embed, modify,
+redistribute, and sell modified and unmodified copies of the Font
+Software, subject to the following conditions:
+
+1) Neither the Font Software nor any of its individual components,in
+   Original or Modified Versions, may be sold by itself.
+
+2) Original or Modified Versions of the Font Software may be bundled,
+   redistributed and/or sold with any software, provided that each copy
+   contains the above copyright notice and this license. These can be
+   included either as stand-alone text files, human-readable headers or
+   in the appropriate machine-readable metadata fields within text or
+   binary files as long as those fields can be easily viewed by the user.
+
+3) No Modified Version of the Font Software may use the Reserved Font
+   Name(s) unless explicit written permission is granted by the
+   corresponding Copyright Holder. This restriction only applies to the
+   primary font name as presented to the users.
+
+4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font
+   Software shall not be used to promote, endorse or advertise any
+   Modified Version, except to acknowledge the contribution(s) of the
+   Copyright Holder(s) and the Author(s) or with their explicit written
+   permission.
+
+5) The Font Software, modified or unmodified, in part or in whole, must
+   be distributed entirely under this license, and must not be distributed
+   under any other license. The requirement for fonts to remain under
+   this license does not apply to any document created using the Font
+   Software.
+
+
+ 
+TERMINATION
+This license becomes null and void if any of the above conditions are not met.
+
+ 
+
+DISCLAIMER
+THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT
+OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT.  IN NO EVENT SHALL THE
+COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL
+DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM OTHER
+DEALINGS IN THE FONT SOFTWARE.
+