docx-generator/DocxBuilder.cpp

#include "DocxBuilder.h"

#include <QFile>
#include <QFileInfo>
#include <QByteArray>
#include <QSet>
#include <QDebug>

// zlib входит в состав Qt и доступна на любой платформе без дополнительных зависимостей
#include <zlib.h>

// ============================================================
//  Минимальный ZIP-writer без внешних библиотек
//  (только zlib, которая есть везде)
// ============================================================
namespace {

quint32 crc32_buf(const QByteArray& data) {
    return static_cast<quint32>(
        ::crc32(0, reinterpret_cast<const Bytef*>(data.constData()),
                static_cast<uInt>(data.size())));
}

QByteArray deflateRaw(const QByteArray& input) {
    z_stream zs{};
    deflateInit2(&zs, Z_DEFAULT_COMPRESSION, Z_DEFLATED,
                 -15, 8, Z_DEFAULT_STRATEGY);

    QByteArray out;
    out.resize(static_cast<int>(deflateBound(&zs, static_cast<uLong>(input.size()))));
    zs.next_in   = reinterpret_cast<Bytef*>(const_cast<char*>(input.constData()));
    zs.avail_in  = static_cast<uInt>(input.size());
    zs.next_out  = reinterpret_cast<Bytef*>(out.data());
    zs.avail_out = static_cast<uInt>(out.size());
    deflate(&zs, Z_FINISH);
    out.resize(static_cast<int>(zs.total_out));
    deflateEnd(&zs);
    return out;
}

void u16(QByteArray& b, quint16 v) {
    b += char(v & 0xFF); b += char(v >> 8);
}
void u32(QByteArray& b, quint32 v) {
    b += char(v & 0xFF); b += char((v>>8)&0xFF);
    b += char((v>>16)&0xFF); b += char((v>>24)&0xFF);
}

struct ZEntry { QString name; QByteArray comp, orig; quint32 crc, off; quint16 meth; };

class ZipWriter {
public:
    bool open(const QString& p) {
        f.setFileName(p);
        return f.open(QIODevice::WriteOnly | QIODevice::Truncate);
    }
    void add(const QString& name, const QByteArray& data) {
        ZEntry e;
        e.name = name; e.orig = data;
        e.crc  = crc32_buf(data);
        e.off  = static_cast<quint32>(f.pos());
        QByteArray c = deflateRaw(data);
        if (c.size() < data.size()) { e.comp = c; e.meth = 8; }
        else                        { e.comp = data; e.meth = 0; }

        QByteArray nb = name.toUtf8();
        QByteArray lh;
        u32(lh,0x04034b50); u16(lh,20); u16(lh,0x0800); u16(lh,e.meth);
        u16(lh,0); u16(lh,0);
        u32(lh,e.crc);
        u32(lh,static_cast<quint32>(e.comp.size()));
        u32(lh,static_cast<quint32>(e.orig.size()));
        u16(lh,static_cast<quint16>(nb.size())); u16(lh,0);
        lh += nb;
        f.write(lh); f.write(e.comp);
        entries << e;
    }
    void close() {
        quint32 cdOff = static_cast<quint32>(f.pos());
        for (auto& e : entries) {
            QByteArray nb = e.name.toUtf8(), cd;
            u32(cd,0x02014b50); u16(cd,20); u16(cd,20); u16(cd,0x0800);
            u16(cd,e.meth); u16(cd,0); u16(cd,0);
            u32(cd,e.crc);
            u32(cd,static_cast<quint32>(e.comp.size()));
            u32(cd,static_cast<quint32>(e.orig.size()));
            u16(cd,static_cast<quint16>(nb.size()));
            u16(cd,0); u16(cd,0); u16(cd,0); u16(cd,0); u32(cd,0); u32(cd,e.off);
            cd += nb; f.write(cd);
        }
        quint32 cdSz = static_cast<quint32>(f.pos()) - cdOff;
        QByteArray eocd;
        u32(eocd,0x06054b50); u16(eocd,0); u16(eocd,0);
        u16(eocd,static_cast<quint16>(entries.size()));
        u16(eocd,static_cast<quint16>(entries.size()));
        u32(eocd,cdSz); u32(eocd,cdOff); u16(eocd,0);
        f.write(eocd); f.close();
    }
private:
    QFile f; QList<ZEntry> entries;
};

} // namespace

// ============================================================
DocxBuilder::DocxBuilder() = default;

void DocxBuilder::clear() { m_elements.clear(); m_images.clear(); m_imageCounter = 0; }

void DocxBuilder::addHeading(const QString& text, int level) {
    DocElement el;
    el.text = text;
    el.type = (level==1) ? DocElementType::Heading1
            : (level==2) ? DocElementType::Heading2
                         : DocElementType::Heading3;
    el.style.font     = "Times New Roman";
    el.style.bold     = true;
    el.style.fontSize = (level==1) ? 36 : (level==2) ? 30 : 26;
    m_elements.append(el);
}

void DocxBuilder::addParagraph(const QString& text, const DocStyle& style) {
    DocElement el; el.type = DocElementType::NormalText; el.text = text; el.style = style;
    m_elements.append(el);
}

void DocxBuilder::addTable(const TableData& table) {
    DocElement el; el.type = DocElementType::Table; el.table = table;
    m_elements.append(el);
}

void DocxBuilder::addImage(const QString& imagePath, int widthEmu, int heightEmu) {
    QFileInfo fi(imagePath);
    if (!fi.exists()) { qWarning() << "Image not found:" << imagePath; return; }
    m_imageCounter++;
    ImageEntry e;
    e.sourcePath = imagePath; e.ext = fi.suffix().toLower();
    e.rId = QString("rId%1").arg(10+m_imageCounter); e.index = m_imageCounter;
    m_images.append(e);

    DocElement el; el.type = DocElementType::Image; el.imagePath = imagePath;
    el.imageWidthEmu = widthEmu; el.imageHeightEmu = heightEmu;
    el.style.fontSize = m_imageCounter;
    m_elements.append(el);
}

void DocxBuilder::addPageBreak() {
    DocElement el; el.type = DocElementType::NormalText; el.text = "\f";
    m_elements.append(el);
}

bool DocxBuilder::save(const QString& filePath) {
    ZipWriter zip;
    if (!zip.open(filePath)) { qWarning() << "Cannot open:" << filePath; return false; }

    zip.add("[Content_Types].xml",            buildContentTypesXml().toUtf8());
    zip.add("_rels/.rels",                    buildRelsXml().toUtf8());
    zip.add("word/document.xml",              buildDocumentXml().toUtf8());
    zip.add("word/_rels/document.xml.rels",   buildDocumentRelsXml().toUtf8());
    zip.add("word/styles.xml",                buildStylesXml().toUtf8());
    zip.add("word/settings.xml",              buildSettingsXml().toUtf8());

    for (const ImageEntry& img : m_images) {
        QFile f(img.sourcePath);
        if (f.open(QIODevice::ReadOnly))
            zip.add(QString("word/media/image%1.%2").arg(img.index).arg(img.ext), f.readAll());
    }
    zip.close();
    return true;
}

// ============================================================
//  XML helpers
// ============================================================

QString DocxBuilder::escapeXml(const QString& t) {
    QString o=t; o.replace("&","&amp;"); o.replace("<","&lt;"); o.replace(">","&gt;"); return o;
}

QString DocxBuilder::makeRunProps(const DocStyle& s) {
    return QString("<w:rPr><w:rFonts w:ascii=\"%1\" w:hAnsi=\"%1\"/>"
                   "<w:sz w:val=\"%2\"/><w:szCs w:val=\"%2\"/>%3%4</w:rPr>")
        .arg(s.font).arg(s.fontSize)
        .arg(s.bold   ? "<w:b/><w:bCs/>" : "")
        .arg(s.italic ? "<w:i/><w:iCs/>" : "");
}

QString DocxBuilder::makeParaProps(const DocStyle& s, const QString& styleId) {
    QString p = "<w:pPr>";
    if (!styleId.isEmpty()) p += QString("<w:pStyle w:val=\"%1\"/>").arg(styleId);
    if (s.center) p += "<w:jc w:val=\"center\"/>";
    if (styleId.isEmpty()) p += "<w:spacing w:line=\"276\" w:lineRule=\"auto\"/>";
    return p + "</w:pPr>";
}

QString DocxBuilder::makeParagraph(const QString& text, const DocStyle& s, const QString& styleId) {
    QString r;
    for (const QString& line : text.split('\n'))
        r += "<w:p>" + makeParaProps(s, styleId) + "<w:r>" + makeRunProps(s)
           + "<w:t xml:space=\"preserve\">" + escapeXml(line) + "</w:t></w:r></w:p>";
    return r;
}

QString DocxBuilder::makeTable(const TableData& table) {
    int cols = table.headers.isEmpty()
             ? (table.rows.isEmpty() ? 1 : table.rows[0].size()) : table.headers.size();
    int cw = (cols>0) ? 9356/cols : 9356;

    QString t = "<w:tbl><w:tblPr><w:tblStyle w:val=\"TableGrid\"/>"
                "<w:tblW w:w=\"9356\" w:type=\"dxa\"/><w:tblBorders>"
                "<w:top w:val=\"single\" w:sz=\"4\" w:space=\"0\" w:color=\"000000\"/>"
                "<w:left w:val=\"single\" w:sz=\"4\" w:space=\"0\" w:color=\"000000\"/>"
                "<w:bottom w:val=\"single\" w:sz=\"4\" w:space=\"0\" w:color=\"000000\"/>"
                "<w:right w:val=\"single\" w:sz=\"4\" w:space=\"0\" w:color=\"000000\"/>"
                "<w:insideH w:val=\"single\" w:sz=\"4\" w:space=\"0\" w:color=\"000000\"/>"
                "<w:insideV w:val=\"single\" w:sz=\"4\" w:space=\"0\" w:color=\"000000\"/>"
                "</w:tblBorders></w:tblPr><w:tblGrid>";
    for (int c=0;c<cols;c++) t += QString("<w:gridCol w:w=\"%1\"/>").arg(cw);
    t += "</w:tblGrid>";

    if (!table.headers.isEmpty()) {
        t += "<w:tr>";
        for (const QString& h : table.headers) {
            t += QString("<w:tc><w:tcPr><w:tcW w:w=\"%1\" w:type=\"dxa\"/>"
                         "<w:shd w:val=\"clear\" w:color=\"auto\" w:fill=\"D9D9D9\"/></w:tcPr>"
                         "<w:p><w:pPr><w:jc w:val=\"center\"/></w:pPr>"
                         "<w:r><w:rPr><w:rFonts w:ascii=\"Times New Roman\" w:hAnsi=\"Times New Roman\"/>"
                         "<w:b/><w:sz w:val=\"24\"/><w:szCs w:val=\"24\"/></w:rPr>"
                         "<w:t>%2</w:t></w:r></w:p></w:tc>").arg(cw).arg(escapeXml(h));
        }
        t += "</w:tr>";
    }
    for (const QStringList& row : table.rows) {
        t += "<w:tr>";
        for (int c=0;c<cols;c++) {
            QString ct = (c<row.size()) ? row[c] : "";
            t += QString("<w:tc><w:tcPr><w:tcW w:w=\"%1\" w:type=\"dxa\"/></w:tcPr>"
                         "<w:p><w:r><w:rPr><w:rFonts w:ascii=\"Times New Roman\" w:hAnsi=\"Times New Roman\"/>"
                         "<w:sz w:val=\"24\"/><w:szCs w:val=\"24\"/></w:rPr>"
                         "<w:t xml:space=\"preserve\">%2</w:t></w:r></w:p></w:tc>")
                    .arg(cw).arg(escapeXml(ct));
        }
        t += "</w:tr>";
    }
    return t + "</w:tbl><w:p/>";
}

QString DocxBuilder::makeImageXml(int rId, int w, int h, int idx) {
    return QString(
        "<w:drawing><wp:inline distT=\"0\" distB=\"0\" distL=\"0\" distR=\"0\">"
        "<wp:extent cx=\"%1\" cy=\"%2\"/>"
        "<wp:effectExtent l=\"0\" t=\"0\" r=\"0\" b=\"0\"/>"
        "<wp:docPr id=\"%3\" name=\"Img%3\"/>"
        "<wp:cNvGraphicFramePr><a:graphicFrameLocks"
        " xmlns:a=\"http://schemas.openxmlformats.org/drawingml/2006/main\""
        " noChangeAspect=\"1\"/></wp:cNvGraphicFramePr>"
        "<a:graphic xmlns:a=\"http://schemas.openxmlformats.org/drawingml/2006/main\">"
        "<a:graphicData uri=\"http://schemas.openxmlformats.org/drawingml/2006/picture\">"
        "<pic:pic xmlns:pic=\"http://schemas.openxmlformats.org/drawingml/2006/picture\">"
        "<pic:nvPicPr><pic:cNvPr id=\"%3\" name=\"Img%3\"/><pic:cNvPicPr/></pic:nvPicPr>"
        "<pic:blipFill><a:blip r:embed=\"rId%4\"/>"
        "<a:stretch><a:fillRect/></a:stretch></pic:blipFill>"
        "<pic:spPr><a:xfrm><a:off x=\"0\" y=\"0\"/><a:ext cx=\"%1\" cy=\"%2\"/></a:xfrm>"
        "<a:prstGeom prst=\"rect\"><a:avLst/></a:prstGeom></pic:spPr>"
        "</pic:pic></a:graphicData></a:graphic>"
        "</wp:inline></w:drawing>"
    ).arg(w).arg(h).arg(idx).arg(rId);
}

QString DocxBuilder::buildDocumentXml() {
    QString body;
    for (const DocElement& el : m_elements) {
        switch (el.type) {
        case DocElementType::Heading1: body += makeParagraph(el.text, el.style, "Heading1"); break;
        case DocElementType::Heading2: body += makeParagraph(el.text, el.style, "Heading2"); break;
        case DocElementType::Heading3: body += makeParagraph(el.text, el.style, "Heading3"); break;
        case DocElementType::NormalText:
            body += (el.text=="\f") ? QString(R"(<w:p><w:r><w:br w:type="page"/></w:r></w:p>)")
                                    : makeParagraph(el.text, el.style);
            break;
        case DocElementType::Table: body += makeTable(el.table); break;
        case DocElementType::Image:
            for (const ImageEntry& img : m_images)
                if (img.index == el.style.fontSize) {
                    body += "<w:p><w:r>" +
                            makeImageXml(img.rId.mid(3).toInt(),
                                         el.imageWidthEmu, el.imageHeightEmu, img.index) +
                            "</w:r></w:p>";
                    break;
                }
            break;
        }
    }
    return QString(
        "<?xml version=\"1.0\" encoding=\"UTF-8\" standalone=\"yes\"?>"
        "<w:document"
        " xmlns:w=\"http://schemas.openxmlformats.org/wordprocessingml/2006/main\""
        " xmlns:r=\"http://schemas.openxmlformats.org/officeDocument/2006/relationships\""
        " xmlns:wp=\"http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing\""
        " xmlns:a=\"http://schemas.openxmlformats.org/drawingml/2006/main\""
        " xmlns:pic=\"http://schemas.openxmlformats.org/drawingml/2006/picture\">"
        "<w:body>%1"
        "<w:sectPr><w:pgSz w:w=\"11906\" w:h=\"16838\"/>"
        "<w:pgMar w:top=\"1134\" w:right=\"850\" w:bottom=\"1134\""
        " w:left=\"1701\" w:header=\"709\" w:footer=\"709\" w:gutter=\"0\"/>"
        "</w:sectPr></w:body></w:document>"
    ).arg(body);
}

QString DocxBuilder::buildContentTypesXml() {
    QString ct =
        "<?xml version=\"1.0\" encoding=\"UTF-8\" standalone=\"yes\"?>"
        "<Types xmlns=\"http://schemas.openxmlformats.org/package/2006/content-types\">"
        "<Default Extension=\"rels\" ContentType=\"application/vnd.openxmlformats-package.relationships+xml\"/>"
        "<Default Extension=\"xml\"  ContentType=\"application/xml\"/>"
        "<Override PartName=\"/word/document.xml\""
        " ContentType=\"application/vnd.openxmlformats-officedocument.wordprocessingml.document.main+xml\"/>"
        "<Override PartName=\"/word/styles.xml\""
        " ContentType=\"application/vnd.openxmlformats-officedocument.wordprocessingml.styles+xml\"/>"
        "<Override PartName=\"/word/settings.xml\""
        " ContentType=\"application/vnd.openxmlformats-officedocument.wordprocessingml.settings+xml\"/>";
    QSet<QString> seen;
    for (const ImageEntry& img : m_images)
        if (!seen.contains(img.ext)) {
            ct += QString("<Default Extension=\"%1\" ContentType=\"%2\"/>")
                      .arg(img.ext).arg(img.ext=="png" ? "image/png" : "image/jpeg");
            seen.insert(img.ext);
        }
    return ct + "</Types>";
}

QString DocxBuilder::buildRelsXml() {
    return "<?xml version=\"1.0\" encoding=\"UTF-8\" standalone=\"yes\"?>"
           "<Relationships xmlns=\"http://schemas.openxmlformats.org/package/2006/relationships\">"
           "<Relationship Id=\"rId1\""
           " Type=\"http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument\""
           " Target=\"word/document.xml\"/>"
           "</Relationships>";
}

QString DocxBuilder::buildDocumentRelsXml() {
    QString r =
        "<?xml version=\"1.0\" encoding=\"UTF-8\" standalone=\"yes\"?>"
        "<Relationships xmlns=\"http://schemas.openxmlformats.org/package/2006/relationships\">"
        "<Relationship Id=\"rId1\""
        " Type=\"http://schemas.openxmlformats.org/officeDocument/2006/relationships/styles\""
        " Target=\"styles.xml\"/>"
        "<Relationship Id=\"rId2\""
        " Type=\"http://schemas.openxmlformats.org/officeDocument/2006/relationships/settings\""
        " Target=\"settings.xml\"/>";
    for (const ImageEntry& img : m_images)
        r += QString("<Relationship Id=\"%1\""
                     " Type=\"http://schemas.openxmlformats.org/officeDocument/2006/relationships/image\""
                     " Target=\"media/image%2.%3\"/>")
                 .arg(img.rId).arg(img.index).arg(img.ext);
    return r + "</Relationships>";
}

QString DocxBuilder::buildSettingsXml() {
    return "<?xml version=\"1.0\" encoding=\"UTF-8\" standalone=\"yes\"?>"
           "<w:settings xmlns:w=\"http://schemas.openxmlformats.org/wordprocessingml/2006/main\">"
           "<w:defaultTabStop w:val=\"720\"/>"
           "<w:compat><w:compatSetting w:name=\"compatibilityMode\""
           " w:uri=\"http://schemas.microsoft.com/office/word\" w:val=\"15\"/></w:compat>"
           "</w:settings>";
}

QString DocxBuilder::buildStylesXml() {
    return
        "<?xml version=\"1.0\" encoding=\"UTF-8\" standalone=\"yes\"?>"
        "<w:styles xmlns:w=\"http://schemas.openxmlformats.org/wordprocessingml/2006/main\">"

        "<w:style w:type=\"paragraph\" w:default=\"1\" w:styleId=\"Normal\">"
        "<w:name w:val=\"Normal\"/>"
        "<w:rPr><w:rFonts w:ascii=\"Times New Roman\" w:hAnsi=\"Times New Roman\"/>"
        "<w:sz w:val=\"24\"/><w:szCs w:val=\"24\"/></w:rPr></w:style>"

        "<w:style w:type=\"paragraph\" w:styleId=\"Heading1\">"
        "<w:name w:val=\"heading 1\"/><w:basedOn w:val=\"Normal\"/>"
        "<w:pPr><w:outlineLvl w:val=\"0\"/><w:spacing w:before=\"240\" w:after=\"120\"/></w:pPr>"
        "<w:rPr><w:rFonts w:ascii=\"Times New Roman\" w:hAnsi=\"Times New Roman\"/>"
        "<w:b/><w:sz w:val=\"36\"/><w:szCs w:val=\"36\"/></w:rPr></w:style>"

        "<w:style w:type=\"paragraph\" w:styleId=\"Heading2\">"
        "<w:name w:val=\"heading 2\"/><w:basedOn w:val=\"Normal\"/>"
        "<w:pPr><w:outlineLvl w:val=\"1\"/><w:spacing w:before=\"200\" w:after=\"100\"/></w:pPr>"
        "<w:rPr><w:rFonts w:ascii=\"Times New Roman\" w:hAnsi=\"Times New Roman\"/>"
        "<w:b/><w:sz w:val=\"30\"/><w:szCs w:val=\"30\"/></w:rPr></w:style>"

        "<w:style w:type=\"paragraph\" w:styleId=\"Heading3\">"
        "<w:name w:val=\"heading 3\"/><w:basedOn w:val=\"Normal\"/>"
        "<w:pPr><w:outlineLvl w:val=\"2\"/><w:spacing w:before=\"160\" w:after=\"80\"/></w:pPr>"
        "<w:rPr><w:rFonts w:ascii=\"Times New Roman\" w:hAnsi=\"Times New Roman\"/>"
        "<w:b/><w:sz w:val=\"26\"/><w:szCs w:val=\"26\"/></w:rPr></w:style>"

        "<w:style w:type=\"table\" w:styleId=\"TableGrid\">"
        "<w:name w:val=\"Table Grid\"/><w:tblPr><w:tblBorders>"
        "<w:top    w:val=\"single\" w:sz=\"4\" w:space=\"0\" w:color=\"000000\"/>"
        "<w:left   w:val=\"single\" w:sz=\"4\" w:space=\"0\" w:color=\"000000\"/>"
        "<w:bottom w:val=\"single\" w:sz=\"4\" w:space=\"0\" w:color=\"000000\"/>"
        "<w:right  w:val=\"single\" w:sz=\"4\" w:space=\"0\" w:color=\"000000\"/>"
        "<w:insideH w:val=\"single\" w:sz=\"4\" w:space=\"0\" w:color=\"000000\"/>"
        "<w:insideV w:val=\"single\" w:sz=\"4\" w:space=\"0\" w:color=\"000000\"/>"
        "</w:tblBorders></w:tblPr></w:style>"

        "</w:styles>";
}