nex_shift/native/macos/doc-render.swift

458 lines
17 KiB
Swift
Raw Normal View History

import AppKit
import Foundation
2026-10-25 04:24:05 +00:00
import PDFKit
import Vision
2026-10-27 10:45:32 +00:00
import WebKit
func fail(_ message: String) -> Never {
FileHandle.standardError.write((message + "\n").data(using: .utf8)!)
exit(1)
}
2026-10-25 04:24:05 +00:00
func hasTextLayer(_ page: PDFPage) -> Bool {
let characters = (page.string ?? "").filter { !$0.isWhitespace }
return characters.count >= 20
}
/// Renders a PDF page on a white background, matching FileFlipper's PDFKit path.
func renderPage(_ page: PDFPage, scale: CGFloat) -> CGImage? {
let box = page.bounds(for: .mediaBox)
let sideways = page.rotation % 180 != 0
let width = Int(((sideways ? box.height : box.width) * scale).rounded())
let height = Int(((sideways ? box.width : box.height) * scale).rounded())
guard width > 0, height > 0,
let context = CGContext(
data: nil,
width: width,
height: height,
bitsPerComponent: 8,
bytesPerRow: 0,
space: CGColorSpace(name: CGColorSpace.sRGB)!,
bitmapInfo: CGImageAlphaInfo.premultipliedLast.rawValue
) else {
return nil
}
context.setFillColor(CGColor(red: 1, green: 1, blue: 1, alpha: 1))
context.fill(CGRect(x: 0, y: 0, width: width, height: height))
context.interpolationQuality = .high
context.scaleBy(x: scale, y: scale)
page.draw(with: .mediaBox, to: context)
return context.makeImage()
}
/// Uses Vision, the system's on-device Live Text engine, for scanned pages.
func recognizeText(_ page: PDFPage) -> String {
guard let image = renderPage(page, scale: 3) else { return "" }
let request = VNRecognizeTextRequest()
request.recognitionLevel = .accurate
request.usesLanguageCorrection = true
request.automaticallyDetectsLanguage = true
let preferred = [
"zh-Hans", "zh-Hant", "en-US", "ja-JP", "ko-KR",
"fr-FR", "de-DE", "es-ES", "it-IT", "pt-BR", "ru-RU",
]
let supported = (try? request.supportedRecognitionLanguages()) ?? []
let languages = preferred.filter { supported.contains($0) }
if !languages.isEmpty {
request.recognitionLanguages = languages
}
do {
try VNImageRequestHandler(cgImage: image).perform([request])
} catch {
return ""
}
let pieces = (request.results ?? []).compactMap { observation -> (CGRect, String)? in
guard let text = observation.topCandidates(1).first?.string else { return nil }
return (observation.boundingBox, text)
}
let sorted = pieces.sorted { $0.0.midY > $1.0.midY }
var rows: [[(CGRect, String)]] = []
for piece in sorted {
if let last = rows.last?.first,
abs(last.0.midY - piece.0.midY) < min(last.0.height, piece.0.height) / 2 {
rows[rows.count - 1].append(piece)
} else {
rows.append([piece])
}
}
return rows.map { row in
row.sorted { $0.0.minX < $1.0.minX }.map { $0.1 }.joined(separator: " ")
}.joined(separator: "\n")
}
/// PDF -> editable DOCX through PDFKit and Cocoa's native OOXML writer.
func writeWordDocument(from pdf: URL, to output: URL) throws {
guard let document = PDFDocument(url: pdf) else {
throw NSError(domain: "Shift", code: 1, userInfo: [
NSLocalizedDescriptionKey: "Could not open PDF: \(pdf.path)",
])
}
if document.isLocked {
throw NSError(domain: "Shift", code: 2, userInfo: [
NSLocalizedDescriptionKey: "This PDF is password protected.",
])
}
let combined = NSMutableAttributedString()
for index in 0..<document.pageCount {
guard let page = document.page(at: index) else { continue }
let pageText: NSAttributedString
if hasTextLayer(page), let attributed = page.attributedString {
pageText = attributed
} else {
pageText = NSAttributedString(
string: recognizeText(page),
attributes: [.font: NSFont.systemFont(ofSize: 12)]
)
}
guard pageText.length > 0 else { continue }
if combined.length > 0 {
combined.append(NSAttributedString(string: "\n\u{0C}"))
}
combined.append(pageText)
}
guard combined.length > 0 else {
throw NSError(domain: "Shift", code: 3, userInfo: [
NSLocalizedDescriptionKey: "No text could be read from this PDF.",
])
}
let data = try combined.data(
from: NSRange(location: 0, length: combined.length),
documentAttributes: [.documentType: NSAttributedString.DocumentType.officeOpenXML]
)
try data.write(to: output, options: .atomic)
}
2026-10-27 10:45:32 +00:00
guard (3...5).contains(CommandLine.arguments.count) else {
fail("usage: doc-render <input> <output> [html-base-dir] [--webkit]")
}
let input = URL(fileURLWithPath: CommandLine.arguments[1])
let output = URL(fileURLWithPath: CommandLine.arguments[2])
2026-10-25 04:24:05 +00:00
let app = NSApplication.shared
app.setActivationPolicy(.prohibited)
if output.pathExtension.lowercased() == "docx" {
guard input.pathExtension.lowercased() == "pdf" else {
fail("PDF-to-Word input must be a PDF")
}
do {
try writeWordDocument(from: input, to: output)
exit(0)
} catch {
fail(error.localizedDescription)
}
}
let extensionName = input.pathExtension.lowercased()
var documentType: NSAttributedString.DocumentType?
switch extensionName {
case "docx":
documentType = .officeOpenXML
case "doc":
documentType = .docFormat
case "odt":
documentType = .openDocument
case "rtf":
documentType = .rtf
case "rtfd":
documentType = .rtfd
case "html", "htm":
documentType = .html
case "txt", "md", "markdown":
documentType = .plain
default:
documentType = nil
}
var options: [NSAttributedString.DocumentReadingOptionKey: Any] = [:]
if let documentType {
options[.documentType] = documentType
}
2026-10-27 10:45:32 +00:00
if documentType == .html {
2026-10-25 04:24:05 +00:00
let baseDirectory = CommandLine.arguments.count == 4
? URL(fileURLWithPath: CommandLine.arguments[3], isDirectory: true)
2026-10-27 10:45:32 +00:00
: CommandLine.arguments.count == 5
? URL(fileURLWithPath: CommandLine.arguments[3], isDirectory: true)
2026-10-25 04:24:05 +00:00
: input.deletingLastPathComponent()
options[.baseURL] = baseDirectory
}
2026-10-27 10:45:32 +00:00
if documentType == .html,
CommandLine.arguments.count == 5,
CommandLine.arguments[4] == "--webkit" {
let baseDirectory = URL(fileURLWithPath: CommandLine.arguments[3], isDirectory: true)
let renderer = HTMLRenderer(input: input, output: output, baseDirectory: baseDirectory)
renderer.run()
app.run()
exit(0)
}
let data: Data
do {
data = try Data(contentsOf: input)
} catch {
fail("could not read input: \(error.localizedDescription)")
}
let attributed: NSAttributedString
do {
attributed = try NSAttributedString(data: data, options: options, documentAttributes: nil)
} catch {
fail("could not parse document: \(error.localizedDescription)")
}
fix(docx): keep figures when a DOCX is printed to PDF Two bugs, both visible in 平台技术方案(带图测试专用).docx: one figure, eleven tables and 357 paragraphs, whose PDF came out as a text-only document. First, AppKit's OOXML reader returns the text of a DOCX and silently drops every inline drawing - an attributed string with zero attachments for a document with a picture in it. That is not a rendering loss, it is a parse loss, so no margin, print setting or layout change can recover the figure: by the time the page is drawn, the picture is simply not in the attributed string. A DOCX whose body contains an image is now converted by Pandoc into HTML with its media extracted beside it, and the HTML - which Pandoc reads faithfully, headings, tables and pictures - goes to the same printer. Image-only DOCX files keep the existing page-scan path, which runs first, and a machine without Pandoc falls back to the old text-only behaviour rather than failing. Second, once pictures could arrive they printed as a cropped fragment of themselves. The layout sizes an attachment from the density header inside the file, assumes 72 dpi when there is none, and ignores both bounds and CSS width: a 1600 px screenshot at 96 dpi asks for 1200 points and lands on a 595 pt page. Measured across PNG pHYs and JPEG JFIF, the placed width is exactly pixels / dpi * 64. A plain NSTextAttachment does honour bounds, so the renderer now replaces any oversized attachment with one that fits the text column; the print operation scales it to the page with the text, landing at 499pt, which is the printable width the body text already uses. Nothing is resampled, only the size the layout asks for changes. This also fixes Markdown and HTML documents with wide images, which had the same overflow. Both halves are pinned by tests, and both fail against the previous build: keeps_pictures_when_rendering_a_text_docx_to_pdf sees no image at all, and fits_a_wide_picture_onto_the_page reports a picture placed 1066.77pt wide on a 595pt page. The second reads the Form XObject's /BBox, so it needs no content stream decoded and no pixel compared.
2026-10-26 06:50:52 +00:00
/// Fits every picture into the width of the printed page.
///
/// The layout sizes an attachment from the density header inside the file —
/// 72 dpi is assumed when the file carries none — and the cell AppKit builds
/// for an `<img>` honours neither `bounds` nor a CSS width, so a 1600 px
/// screenshot saved at 96 dpi asks for 1200 points and prints as a cropped
/// fragment of itself. A plain `NSTextAttachment` does honour `bounds`, and the
/// print operation then scales it onto the page along with the text. Aspect
/// ratio is kept and nothing is resampled: only the size the layout asks for
/// changes.
func fitAttachments(
_ source: NSAttributedString,
to containerWidth: CGFloat
) -> NSMutableAttributedString {
let mutable = NSMutableAttributedString(attributedString: source)
let wanted = max(1, containerWidth)
mutable.enumerateAttribute(
.attachment,
in: NSRange(location: 0, length: mutable.length),
options: []
) { value, range, _ in
guard let old = value as? NSTextAttachment,
let contents = old.fileWrapper?.regularFileContents,
let image = NSImage(data: contents),
image.size.width > wanted else { return }
let scale = wanted / image.size.width
let replacement = NSTextAttachment()
replacement.image = image
replacement.bounds = NSRect(
x: 0,
y: 0,
width: (image.size.width * scale).rounded(),
height: (image.size.height * scale).rounded()
)
mutable.addAttribute(.attachment, value: replacement, range: range)
}
return mutable
}
2026-10-27 10:45:32 +00:00
/// Writes the tall PDF WebKit produces from the page as A4-sized slices.
///
/// `createPDF` keeps the HTML layout as one continuous page. Printing the web
/// view directly can loop indefinitely on documents with positioned elements,
/// so draw the single page into clipped A4 pages instead.
func writePaginatedPDF(_ data: Data, to output: URL) {
let pageSize = CGSize(width: 595.2, height: 841.8)
guard let provider = CGDataProvider(data: data as CFData),
let document = CGPDFDocument(provider),
let source = document.page(at: 1) else {
fail("could not read the rendered web page")
}
let sourceBounds = source.getBoxRect(.mediaBox)
let height = max(1, sourceBounds.height)
let pageCount = max(1, Int(ceil(height / pageSize.height)))
var mediaBox = CGRect(origin: .zero, size: pageSize)
guard let context = CGContext(output as CFURL, mediaBox: &mediaBox, nil) else {
fail("could not create the PDF")
}
for index in 0..<pageCount {
context.beginPDFPage(nil)
context.saveGState()
context.clip(to: mediaBox)
let offset = max(0, height - CGFloat(index + 1) * pageSize.height)
let remaining = max(0, height - CGFloat(index) * pageSize.height)
// Full slices move up through the tall page. The final short slice is
// top-aligned so the trailing whitespace sits below the content.
let translationY = remaining < pageSize.height
? pageSize.height - remaining
: -offset
context.translateBy(x: 0, y: translationY)
context.drawPDFPage(source)
context.restoreGState()
context.endPDFPage()
}
context.closePDF()
}
/// Renders HTML with WebKit instead of flattening it into an attributed
/// string. Quick Look supplies Word page furniture and positioned tables as
/// HTML; AppKit's text conversion reflows that content, which changes the page
/// count and can move a footer onto a page of its own.
final class HTMLRenderer: NSObject, WKNavigationDelegate {
private let input: URL
private let baseDirectory: URL
private let output: URL
private let webView: WKWebView
private var finished = false
init(input: URL, output: URL, baseDirectory: URL) {
self.input = input
self.output = output
self.baseDirectory = baseDirectory
let configuration = WKWebViewConfiguration()
configuration.websiteDataStore = .nonPersistent()
configuration.defaultWebpagePreferences.allowsContentJavaScript = false
self.webView = WKWebView(
frame: NSRect(x: 0, y: 0, width: 595.2, height: 841.8),
configuration: configuration
)
super.init()
webView.navigationDelegate = self
}
func run() {
webView.loadFileURL(input, allowingReadAccessTo: baseDirectory)
DispatchQueue.main.asyncAfter(deadline: .now() + 30) {
guard !self.finished else { return }
self.finished = true
fail("could not render HTML before the 30 second deadline")
}
}
func webView(_ webView: WKWebView, didFinish navigation: WKNavigation!) {
guard !finished else { return }
webView.evaluateJavaScript(
"""
(() => {
const pageWidth = document.documentElement.clientWidth;
for (const image of document.images) {
if (image.getBoundingClientRect().width > pageWidth) {
image.style.width = `${pageWidth}px`;
image.style.height = "auto";
image.style.maxWidth = "100%";
}
}
let contentBottom = 0;
const range = document.createRange();
const walker = document.createTreeWalker(
document.body,
NodeFilter.SHOW_TEXT
);
for (let node = walker.nextNode(); node; node = walker.nextNode()) {
if (!node.textContent.trim()) continue;
range.selectNodeContents(node);
const rect = range.getBoundingClientRect();
if (rect.width > 0 && rect.height > 0) {
contentBottom = Math.max(
contentBottom,
rect.bottom + window.scrollY
);
}
}
for (const element of document.querySelectorAll(
"img, svg, canvas, table, hr"
)) {
const rect = element.getBoundingClientRect();
if (rect.width > 0 && rect.height > 0) {
contentBottom = Math.max(
contentBottom,
rect.bottom + window.scrollY
);
}
}
return {
width: document.documentElement.scrollWidth,
height: Math.max(1, Math.ceil(contentBottom))
};
})()
"""
) { value, error in
guard !self.finished else { return }
self.finished = true
guard error == nil,
let size = value as? [String: Any],
let width = (size["width"] as? NSNumber)?.doubleValue,
let height = (size["height"] as? NSNumber)?.doubleValue,
width > 0,
height > 0 else {
fail("could not measure the rendered HTML")
}
let configuration = WKPDFConfiguration()
configuration.rect = CGRect(x: 0, y: 0, width: width, height: height)
webView.createPDF(configuration: configuration) { result in
switch result {
case .success(let data):
writePaginatedPDF(data, to: self.output)
NSApp.terminate(nil)
case .failure(let error):
fail("could not print HTML: \(error.localizedDescription)")
}
}
}
}
func webView(
_ webView: WKWebView,
didFail navigation: WKNavigation!,
withError error: Error
) {
guard !finished else { return }
finished = true
fail("could not load HTML: \(error.localizedDescription)")
}
func webView(
_ webView: WKWebView,
didFailProvisionalNavigation navigation: WKNavigation!,
withError error: Error
) {
guard !finished else { return }
finished = true
fail("could not load HTML: \(error.localizedDescription)")
}
}
let printInfo = NSPrintInfo.shared.copy() as! NSPrintInfo
printInfo.paperSize = NSSize(width: 595.2, height: 841.8)
printInfo.topMargin = 42
printInfo.bottomMargin = 42
printInfo.leftMargin = 48
printInfo.rightMargin = 48
printInfo.horizontalPagination = .fit
printInfo.verticalPagination = .automatic
printInfo.isHorizontallyCentered = false
printInfo.isVerticallyCentered = false
printInfo.jobDisposition = .save
printInfo.dictionary()[NSPrintInfo.AttributeKey.jobSavingURL] = output
let printable = printInfo.imageablePageBounds
fix(docx): keep figures when a DOCX is printed to PDF Two bugs, both visible in 平台技术方案(带图测试专用).docx: one figure, eleven tables and 357 paragraphs, whose PDF came out as a text-only document. First, AppKit's OOXML reader returns the text of a DOCX and silently drops every inline drawing - an attributed string with zero attachments for a document with a picture in it. That is not a rendering loss, it is a parse loss, so no margin, print setting or layout change can recover the figure: by the time the page is drawn, the picture is simply not in the attributed string. A DOCX whose body contains an image is now converted by Pandoc into HTML with its media extracted beside it, and the HTML - which Pandoc reads faithfully, headings, tables and pictures - goes to the same printer. Image-only DOCX files keep the existing page-scan path, which runs first, and a machine without Pandoc falls back to the old text-only behaviour rather than failing. Second, once pictures could arrive they printed as a cropped fragment of themselves. The layout sizes an attachment from the density header inside the file, assumes 72 dpi when there is none, and ignores both bounds and CSS width: a 1600 px screenshot at 96 dpi asks for 1200 points and lands on a 595 pt page. Measured across PNG pHYs and JPEG JFIF, the placed width is exactly pixels / dpi * 64. A plain NSTextAttachment does honour bounds, so the renderer now replaces any oversized attachment with one that fits the text column; the print operation scales it to the page with the text, landing at 499pt, which is the printable width the body text already uses. Nothing is resampled, only the size the layout asks for changes. This also fixes Markdown and HTML documents with wide images, which had the same overflow. Both halves are pinned by tests, and both fail against the previous build: keeps_pictures_when_rendering_a_text_docx_to_pdf sees no image at all, and fits_a_wide_picture_onto_the_page reports a picture placed 1066.77pt wide on a 595pt page. The second reads the Form XObject's /BBox, so it needs no content stream decoded and no pixel compared.
2026-10-26 06:50:52 +00:00
let fitted = fitAttachments(attributed, to: printable.width)
let textView = NSTextView(frame: NSRect(x: 0, y: 0, width: printable.width, height: 1))
textView.isEditable = false
textView.isSelectable = false
textView.drawsBackground = false
textView.textContainerInset = .zero
textView.textContainer?.lineFragmentPadding = 0
textView.textContainer?.widthTracksTextView = true
textView.textContainer?.containerSize = NSSize(
width: printable.width,
height: .greatestFiniteMagnitude
)
fix(docx): keep figures when a DOCX is printed to PDF Two bugs, both visible in 平台技术方案(带图测试专用).docx: one figure, eleven tables and 357 paragraphs, whose PDF came out as a text-only document. First, AppKit's OOXML reader returns the text of a DOCX and silently drops every inline drawing - an attributed string with zero attachments for a document with a picture in it. That is not a rendering loss, it is a parse loss, so no margin, print setting or layout change can recover the figure: by the time the page is drawn, the picture is simply not in the attributed string. A DOCX whose body contains an image is now converted by Pandoc into HTML with its media extracted beside it, and the HTML - which Pandoc reads faithfully, headings, tables and pictures - goes to the same printer. Image-only DOCX files keep the existing page-scan path, which runs first, and a machine without Pandoc falls back to the old text-only behaviour rather than failing. Second, once pictures could arrive they printed as a cropped fragment of themselves. The layout sizes an attachment from the density header inside the file, assumes 72 dpi when there is none, and ignores both bounds and CSS width: a 1600 px screenshot at 96 dpi asks for 1200 points and lands on a 595 pt page. Measured across PNG pHYs and JPEG JFIF, the placed width is exactly pixels / dpi * 64. A plain NSTextAttachment does honour bounds, so the renderer now replaces any oversized attachment with one that fits the text column; the print operation scales it to the page with the text, landing at 499pt, which is the printable width the body text already uses. Nothing is resampled, only the size the layout asks for changes. This also fixes Markdown and HTML documents with wide images, which had the same overflow. Both halves are pinned by tests, and both fail against the previous build: keeps_pictures_when_rendering_a_text_docx_to_pdf sees no image at all, and fits_a_wide_picture_onto_the_page reports a picture placed 1066.77pt wide on a 595pt page. The second reads the Form XObject's /BBox, so it needs no content stream decoded and no pixel compared.
2026-10-26 06:50:52 +00:00
textView.textStorage?.setAttributedString(fitted)
guard let layoutManager = textView.layoutManager,
let textContainer = textView.textContainer else {
fail("could not create text layout")
}
layoutManager.ensureLayout(for: textContainer)
let used = layoutManager.usedRect(for: textContainer)
let height = max(1, ceil(used.height))
textView.frame = NSRect(x: 0, y: 0, width: printable.width, height: height)
let operation = NSPrintOperation(view: textView, printInfo: printInfo)
operation.showsPrintPanel = false
operation.showsProgressPanel = false
if !operation.run() {
fail("could not render PDF")
}
guard FileManager.default.fileExists(atPath: output.path) else {
fail("PDF was not created")
}