Hermit/app/src/core/PdfTools.cpp

/* The window's own tools, in Qt rather than in the engine: a document the
 * person asked for, laid out as a PDF.
 *
 * Why here and not in the C engine: laying text out on pages is exactly what
 * Qt does (QTextDocument + QPdfWriter, both in QtGui, which the app already
 * links), while the engine has no layout code at all -- and md_to_html, its
 * sibling, lives in the engine because rendering markdown is a shared
 * capability. This one is a front-end capability: it is registered under
 * owner "app:qt" and is available on every platform the app runs on.
 *
 * The path of a document is the one md_to_html walks: markdown (or a
 * workspace .md/.html file) -> cst_web_md_document() -> a file inside the
 * workspace -> cst_attach_import_artifact(), which is what turns it into a
 * file card the person can open or share. The bytes never reach the model.
 *
 * Pagination is ours on purpose: QPrinter/PrintSupport is a desktop-only
 * module (a phone has no print subsystem), and a round of
 * pageSize + translate + drawContents per page is all a paginated PDF needs.
 * The tool runs on the turn's worker thread, so a long document does not
 * freeze the window. */

#include <QByteArray>
#include <QDir>
#include <QFile>
#include <QFileInfo>
#include <QMarginsF>
#include <QPageLayout>
#include <QPageSize>
#include <QPainter>
#include <QPdfWriter>
#include <QRectF>
#include <QString>
#include <QTextDocument>

#include <cstdio>
#include <cstdlib>
#include <cstring>
#include <memory>

#include "core/AgentCore.h"
#include "core/ToolProvider.h"
#include "cst_agent.h"
#include "cst_attach.h"
#include "cst_tools.h"
#include "cst_web_md.h"

namespace app {
namespace {

/* md_to_html caps its input the same way: a document nobody could read is
 * not worth laying out. */
constexpr int kMaxInputBytes = 8 * 1024 * 1024;
/* 150 dpi: crisp enough for text, and a good deal lighter on a phone than the
 * default 300 (a 40-page document is laid out and written in a moment). */
constexpr int kPdfDpi = 150;

const char *argOf(const ctl_tool_call_t *call, const char *key) {
  for (int i = 0; i < call->nargs; i++)
    if (strcmp(call->args[i].key, key) == 0)
      return call->args[i].value;
  return nullptr;
}

int setOut(cst_tool_result_t *r, const QString &text, int rc) {
  const QByteArray b = text.toUtf8();
  r->out = strdup(b.constData());
  r->out_len = r->out ? strlen(r->out) : 0;
  r->exit_code = rc;
  return rc;
}

/* "docs/notes.md" -> "notes". */
QString stemOf(const QString &path) {
  QString base = path;
  const int slash = qMax(base.lastIndexOf(QLatin1Char('/')),
                         base.lastIndexOf(QLatin1Char('\\')));
  if (slash >= 0)
    base = base.mid(slash + 1);
  const int dot = base.lastIndexOf(QLatin1Char('.'));
  if (dot > 0)
    base = base.left(dot);
  return base.isEmpty() ? QStringLiteral("document") : base;
}

/* What the file is called: `out` when given (a directory takes the source's
 * name inside it), otherwise the source's stem, or the title. */
QString outPathOf(const ctl_tool_call_t *c, const QString &stem) {
  const char *out = argOf(c, "out");
  QString name = out && out[0] ? QString::fromUtf8(out) : QString();
  if (name.isEmpty())
    return stem + QStringLiteral(".pdf");
  if (name.endsWith(QLatin1Char('/')) || name.endsWith(QLatin1Char('\\')))
    return name + stem + QStringLiteral(".pdf");
  if (!QFileInfo(name).fileName().contains(QLatin1Char('.')))
    name += QStringLiteral(".pdf");
  return name;
}

/* The HTML that goes into the page: an .html file is already a document, a
 * .md file (or the `markdown` argument) goes through the engine's renderer,
 * which is the same one the WebUI and md_to_html use. */
bool sourceHtml(const cst_tool_ctx_t *ctx, const ctl_tool_call_t *c,
                QString *html, QString *out_name, QString *err) {
  const char *md = argOf(c, "markdown");
  const char *file = argOf(c, "file");
  const char *given = argOf(c, "title");
  QString title = given && given[0] ? QString::fromUtf8(given) : QString();
  QByteArray text;
  QString stem;
  if (file && file[0]) {
    char rel[4096] = "";
    if (cst_sandbox_resolve(ctx->workspace_root, file, rel, sizeof(rel)) != 0) {
      *err = QStringLiteral("error: path outside the workspace or missing "
                            "parent: %1")
                 .arg(QString::fromUtf8(file));
      return false;
    }
    QFile in(QString::fromUtf8(rel));
    if (!in.open(QIODevice::ReadOnly)) {
      *err = QStringLiteral("error: cannot read %1")
                 .arg(QString::fromUtf8(file));
      return false;
    }
    if (in.size() > kMaxInputBytes) {
      *err = QStringLiteral("error: %1 is larger than %2 MB")
                 .arg(QString::fromUtf8(file))
                 .arg(kMaxInputBytes >> 20);
      return false;
    }
    text = in.readAll();
    stem = stemOf(QString::fromUtf8(file));
    const QString lower = QString::fromUtf8(file).toLower();
    if (lower.endsWith(QLatin1String(".html")) ||
        lower.endsWith(QLatin1String(".htm"))) {
      /* already a document: what md_to_html wrote, or anything else */
      *html = QString::fromUtf8(text);
      if (title.isEmpty())
        title = stem;
      *out_name = outPathOf(c, stem);
      return true;
    }
  } else if (md && md[0]) {
    text = QByteArray(md);
    if (stem.isEmpty())
      stem = title.isEmpty() ? QStringLiteral("document") : stemOf(title);
  } else {
    *err = QStringLiteral("error: give markdown, or a workspace .md or .html "
                          "file to render");
    return false;
  }
  if (title.isEmpty())
    title = stem;
  char *doc =
      cst_web_md_document(text.constData(), static_cast<size_t>(text.size()),
                          title.toUtf8().constData());
  if (!doc) {
    *err = QStringLiteral("error: cannot render the markdown");
    return false;
  }
  *html = QString::fromUtf8(doc);
  free(doc);
  *out_name = outPathOf(c, stem);
  return true;
}

/* Write `html` into `path` as an A4 PDF with 15 mm margins: one page rect,
 * translated down per page, and the document is asked for exactly that much
 * text at a time -- which is what makes Qt lay out pages instead of one long
 * strip. */
bool writePdf(const QString &html, const QString &path, const QString &title,
              QString *err) {
  std::unique_ptr<QTextDocument> doc(paperDocument(html));
  if (!title.isEmpty())
    doc->setMetaInformation(QTextDocument::DocumentTitle, title);

  QPdfWriter writer(path);
  writer.setPageSize(QPageSize(QPageSize::A4));
  writer.setPageMargins(QMarginsF(15, 15, 15, 15), QPageLayout::Millimeter);
  writer.setResolution(kPdfDpi);
  if (!title.isEmpty())
    writer.setTitle(title);

  QPainter painter(&writer);
  if (!painter.isActive()) {
    *err = QStringLiteral("error: cannot draw into %1").arg(path);
    return false;
  }
  const QRectF page = writer.pageLayout().paintRectPixels(writer.resolution());
  doc->setPageSize(page.size());
  const int pages = qMax(1, doc->pageCount());
  for (int i = 0; i < pages; i++) {
    if (i)
      writer.newPage();
    painter.save();
    painter.translate(page.topLeft());
    painter.translate(0, -i * page.height());
    doc->drawContents(&painter,
                      QRectF(0, 0, page.width(), page.height())
                          .translated(0, i * page.height()));
    painter.restore();
  }
  painter.end();
  /* The painter says nothing about the file: the only proof the PDF landed is
   * that there is one with bytes in it. */
  if (QFileInfo(path).size() <= 0) {
    *err = QStringLiteral("error: nothing was written to %1").arg(path);
    return false;
  }
  return true;
}

int mdToPdfPreview(const cst_tool_ctx_t *ctx, const ctl_tool_call_t *c,
                   char **out) {
  (void)ctx;
  const char *md = argOf(c, "markdown");
  const char *file = argOf(c, "file");
  if ((!md || !md[0]) && (!file || !file[0])) {
    *out = strdup("error: give markdown, or a .md or .html file to render");
    return -1;
  }
  const QString stem =
      file && file[0] ? stemOf(QString::fromUtf8(file)) : QStringLiteral("document");
  const QString name = outPathOf(c, stem);
  QByteArray line;
  if (file && file[0])
    line = QStringLiteral("lay out %1 → %2 as a PDF\n")
               .arg(QString::fromUtf8(file), name)
               .toUtf8();
  else
    line = QStringLiteral("lay out %1 bytes of markdown → %2 as a PDF\n")
               .arg(md ? qstrlen(md) : 0)
               .arg(name)
               .toUtf8();
  *out = strdup(line.constData());
  return 0;
}

int mdToPdfRun(const cst_tool_ctx_t *ctx, const ctl_tool_call_t *c,
               cst_tool_result_t *r, void *ud) {
  (void)ud;
  QString html, out_name, err;
  if (!sourceHtml(ctx, c, &html, &out_name, &err))
    return setOut(r, err, 1);

  char full[4096] = "";
  if (cst_sandbox_resolve(ctx->workspace_root, out_name.toUtf8().constData(),
                          full, sizeof(full)) != 0)
    return setOut(r, QStringLiteral("error: path outside the workspace: %1")
                         .arg(out_name),
                  1);
  const QString target = QString::fromUtf8(full);
  /* A directory in the way of the name is what the engine's write tools call
   * "missing parent": make it, the same way md_to_html does. */
  QDir().mkpath(QFileInfo(target).absolutePath());

  const char *given = argOf(c, "title");
  const QString title = given && given[0] ? QString::fromUtf8(given) : QString();
  if (!writePdf(html, target, title, &err))
    return setOut(r, err, 1);

  const qint64 bytes = QFileInfo(target).size();
  const char *session = ctx->agent ? cst_agent_session_path(ctx->agent) : nullptr;
  cst_attachment_t *a = nullptr;
  char aerr[256] = "";
  if (session && session[0])
    a = cst_attach_import_artifact(session, full, nullptr, aerr, sizeof(aerr));

  QString text = QStringLiteral("wrote %1 (%2 KB, A4, 15 mm margins)\n")
                     .arg(out_name)
                     .arg(bytes / 1024);
  if (a)
    text += QStringLiteral("(the user sees it as a file card they can open or "
                           "share; you will not be shown its bytes again)\n");
  else if (aerr[0])
    text += QStringLiteral("(the file is in the workspace; handing it over "
                           "failed: %1)\n")
                .arg(QString::fromUtf8(aerr));
  const int rc = setOut(r, text, 0);
  if (a) {
    r->attach = a;
    r->nattach = 1;
  }
  return rc;
}

}  // namespace

/* The document writePdf lays out, with a colour filled in for text that names
 * none of its own.
 *
 * Paper is white and has no theme, but a QTextDocument takes its default text
 * colour from the application palette: in a window running a dark palette --
 * which is what a phone in dark mode hands Qt -- every plain markdown
 * paragraph came out #eeeeee on a white page, i.e. a PDF that looks blank
 * when printed, and reads as "the font is oddly faint" on screen. Naming the
 * colour makes the page depend on the paper rather than on the window. A
 * colour the document does name still wins (an .html file somebody handed us
 * keeps its own), so this only fills the holes. */
QTextDocument *paperDocument(const QString &html) {
  auto *doc = new QTextDocument;
  doc->setDefaultStyleSheet(QStringLiteral("body { color: #000000; }"));
  doc->setHtml(html);
  return doc;
}

int registerQtTools(AgentCore *core) {
  if (!core)
    return 0;
  static const cst_tool_param_t params[CST_TOOL_MAX_PARAMS] = {
      {"markdown", "string", 0, "markdown text to render"},
      {"file", "string", 0,
       "workspace .md file to render, or an .html one to lay out as it is"},
      {"out", "string", 0,
       "output path in the workspace (default: the source's name + .pdf)"},
      {"title", "string", 0, "document title (default: the file name)"},
      {nullptr, nullptr, 0, nullptr},
      {nullptr, nullptr, 0, nullptr}};
  static cst_tool_def_t def;
  memset(&def, 0, sizeof(def));
  setMeta(&def, "md_to_pdf",
          "Write a document as a PDF: markdown (or a workspace .md/.html "
          "file) in, a laid-out A4 PDF out, saved in the workspace and "
          "handed to the person as a card they can open, print or share. "
          "Use it when the answer should be something to keep or send.",
          CST_TP_WRITE, "pdf", nullptr, nullptr);
  memcpy(def.params, params, sizeof(params));
  def.run_ex = mdToPdfRun;
  def.preview = mdToPdfPreview;
  def.owner = "app:qt";
  return core->registerTool(&def) ? 1 : 0;
}

}  // namespace app