@fiduswriter/document 0.1.0-alpha.1

package/src/exporter/docx/lists.js

@@ -0,0 +1,260 @@
+import {descendantNodes} from "../tools/doc_content.js"
+
+const DEFAULT_LISTPARAGRAPH_XML = `
+    <w:style w:type="paragraph" w:styleId="ListParagraph">
+    <w:name w:val="List Paragraph"/>
+    <w:basedOn w:val="Normal"/>
+    <w:uiPriority w:val="34"/>
+    <w:qFormat/>
+    <w:rsid w:val="006E68A6"/>
+    <w:pPr>
+      <w:ind w:left="720"/>
+      <w:contextualSpacing/>
+    </w:pPr>
+    </w:style>
+    `
+
+const DEFAULT_NUMBERING_XML = `<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+    <w:numbering xmlns:wpc="http://schemas.microsoft.com/office/word/2010/wordprocessingCanvas" xmlns:cx="http://schemas.microsoft.com/office/drawing/2014/chartex" xmlns:cx1="http://schemas.microsoft.com/office/drawing/2015/9/8/chartex" xmlns:cx2="http://schemas.microsoft.com/office/drawing/2015/10/21/chartex" xmlns:cx3="http://schemas.microsoft.com/office/drawing/2016/5/9/chartex" xmlns:cx4="http://schemas.microsoft.com/office/drawing/2016/5/10/chartex" xmlns:cx5="http://schemas.microsoft.com/office/drawing/2016/5/11/chartex" xmlns:cx6="http://schemas.microsoft.com/office/drawing/2016/5/12/chartex" xmlns:cx7="http://schemas.microsoft.com/office/drawing/2016/5/13/chartex" xmlns:cx8="http://schemas.microsoft.com/office/drawing/2016/5/14/chartex" xmlns:mc="http://schemas.openxmlformats.org/markup-compatibility/2006" xmlns:aink="http://schemas.microsoft.com/office/drawing/2016/ink" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships" xmlns:m="http://schemas.openxmlformats.org/officeDocument/2006/math" xmlns:v="urn:schemas-microsoft-com:vml" xmlns:wp14="http://schemas.microsoft.com/office/word/2010/wordprocessingDrawing" xmlns:wp="http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing" xmlns:w10="urn:schemas-microsoft-com:office:word" xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main" xmlns:w14="http://schemas.microsoft.com/office/word/2010/wordml" xmlns:w15="http://schemas.microsoft.com/office/word/2012/wordml" xmlns:w16se="http://schemas.microsoft.com/office/word/2015/wordml/symex" xmlns:wpg="http://schemas.microsoft.com/office/word/2010/wordprocessingGroup" xmlns:wpi="http://schemas.microsoft.com/office/word/2010/wordprocessingInk" xmlns:wne="http://schemas.microsoft.com/office/word/2006/wordml" xmlns:wps="http://schemas.microsoft.com/office/word/2010/wordprocessingShape" mc:Ignorable="w14 w15 w16se wp14">
+    </w:numbering>`
+
+export class DOCXExporterLists {
+    constructor(docContent, xml, rels) {
+        this.docContent = docContent
+        this.xml = xml
+        this.rels = rels
+        this.useBulletList = false
+        this.usedNumberedList = []
+        this.styleXML = false
+        this.numberingXML = false
+        this.abstractNumIdCounter = 0
+        this.numIdCounter = 0
+        // We only need one bulletType for all bullet lists, but a new
+        // numberedType for each numbered list so that the numbering starts in 1
+        // each time.
+        this.bulletType = false
+        this.numberFormat = "decimal"
+        this.numberedTypes = []
+        this.styleFilePath = "word/styles.xml"
+        this.numberingFilePath = "word/numbering.xml"
+        this.ctFilePath = "[Content_Types].xml"
+    }
+
+    init() {
+        this.findLists()
+        if (this.usedNumberedList.length > 0 || this.useBulletList) {
+            const p = []
+
+            p.push(
+                new Promise(resolve => {
+                    this.initCt().then(() => resolve())
+                })
+            )
+
+            p.push(
+                new Promise(resolve => {
+                    this.addNumberingXml().then(() => resolve())
+                })
+            )
+
+            p.push(
+                new Promise(resolve => {
+                    this.addListParagraphStyle().then(() => resolve())
+                })
+            )
+            return Promise.all(p)
+        } else {
+            return Promise.resolve()
+        }
+    }
+
+    initCt() {
+        return this.xml.getXml(this.ctFilePath).then(ctXML => {
+            this.ctXML = ctXML
+            this.addRelsToCt()
+            return Promise.resolve()
+        })
+    }
+
+    addRelsToCt() {
+        const override = this.ctXML.query("Override", {
+            PartName: `/${this.numberingFilePath}`
+        })
+        if (!override) {
+            const types = this.ctXML.query("Types")
+            types.appendXML(
+                `<Override PartName="/${this.numberingFilePath}" ContentType="application/vnd.openxmlformats-officedocument.wordprocessingml.numbering+xml"/>`
+            )
+        }
+    }
+
+    findLists() {
+        descendantNodes(this.docContent).forEach(node => {
+            if (node.type === "bullet_list") {
+                this.useBulletList = true
+            } else if (node.type === "ordered_list") {
+                this.usedNumberedList.push(node.attrs.order)
+            }
+        })
+    }
+
+    addNumberingXml() {
+        return this.xml
+            .getXml(this.numberingFilePath, DEFAULT_NUMBERING_XML)
+            .then(numberingXML => {
+                this.numberingXML = numberingXML
+                this.rels.addNumberingRel()
+                this.addUsedListTypes()
+                return Promise.resolve()
+            })
+    }
+
+    addListParagraphStyle() {
+        return this.xml.getXml(this.styleFilePath).then(styleXML => {
+            this.styleXML = styleXML
+            if (
+                !this.styleXML.query("w:style", {"w:styleId": "ListParagraph"})
+            ) {
+                const stylesEl = this.styleXML.query("w:styles")
+                stylesEl.appendXML(DEFAULT_LISTPARAGRAPH_XML)
+            }
+            return Promise.resolve()
+        })
+    }
+
+    addUsedListTypes() {
+        const allAbstractNum = this.numberingXML.queryAll("w:abstractNum")
+        allAbstractNum.forEach(abstractNum => {
+            // We check the format for the lowest level list and use the first
+            // one we find  for 'bullet' or 'not bullet'
+            // This means that if a list is defined using anything else than
+            // bullets, it will be accepted as the format of
+            // the numeric list.
+            const levelZeroFormat = abstractNum
+                .query("w:lvl", {"w:ilvl": "0"})
+                .query("w:numFmt")
+                .getAttribute("w:val")
+            const abstractNumId = Number.parseInt(
+                abstractNum.getAttribute("w:abstractNumId")
+            )
+            if (levelZeroFormat === "bullet" && !this.bulletAbstractType) {
+                const numEl = this.numberingXML.query("w:abstractNumId", {
+                    "w:val": abstractNumId
+                }).parentElement
+                const numId = Number.parseInt(numEl.getAttribute("w:numId"))
+                this.bulletType = numId
+            } else if (levelZeroFormat !== "bullet" && !this.numberFormat) {
+                this.numberFormat = levelZeroFormat
+            }
+            if (this.abstractNumIdCounter < abstractNumId) {
+                this.abstractNumIdCounter = abstractNumId
+            }
+        })
+        const allNum = this.numberingXML.queryAll("w:num")
+        allNum.forEach(numEl => {
+            const numId = Number.parseInt(numEl.getAttribute("w:val"))
+            if (this.numIdCounter < numId) {
+                this.numIdCounter = numId
+            }
+        })
+
+        if (!this.bulletType && this.useBulletList) {
+            this.addBulletNumType(
+                ++this.numIdCounter,
+                ++this.abstractNumIdCounter
+            )
+            this.bulletType = this.numIdCounter
+        }
+        if (this.usedNumberedList.length > 0) {
+            this.abstractNumIdCounter++
+
+            this.numberedAbstractType = this.abstractNumIdCounter
+        }
+        for (let i = 0; i < this.usedNumberedList.length; i++) {
+            const numId = ++this.numIdCounter
+            this.addNumberedNumType(numId, this.usedNumberedList[i])
+            this.numberedTypes.push(numId)
+        }
+    }
+
+    getBulletType() {
+        return this.bulletType
+    }
+
+    getNumberedType() {
+        return this.numberedTypes.shift()
+    }
+
+    addBulletNumType(numId, abstractNumId) {
+        const numberingEl = this.numberingXML.query("w:numbering")
+        numberingEl.appendXML(`
+            <w:abstractNum w:abstractNumId="${abstractNumId}" w15:restartNumberingAfterBreak="0">
+                <w:nsid w:val="3620195A" />
+                <w:multiLevelType w:val="hybridMultilevel" />
+                <w:tmpl w:val="A74C9E6A" />
+            </w:abstractNum>
+            <w:num w:numId="${numId}">
+                <w:abstractNumId w:val="${abstractNumId}" />
+            </w:num>
+        `)
+        const newAbstractNum = this.numberingXML.query("w:abstractNum", {
+            "w:abstractNumId": String(abstractNumId)
+        })
+        // Definition seem to always define 9 levels (0-8).
+        for (let level = 0; level < 9; level++) {
+            newAbstractNum.appendXML(`
+                <w:lvl w:ilvl="${level}" w:tplc="04090001" w:tentative="1">
+                    <w:start w:val="1" />
+                    <w:numFmt w:val="bullet" />
+                    <w:lvlText w:val="•" />
+                    <w:lvlJc w:val="left" />
+                    <w:pPr>
+                        <w:ind w:left="${(level + 1) * 720}" w:hanging="360" />
+                    </w:pPr>
+                    <w:rPr>
+                        <w:rFonts w:ascii="Symbol" w:hAnsi="Symbol" />
+                    </w:rPr>
+                </w:lvl>
+            `)
+        }
+    }
+
+    addNumberedNumType(numId, start) {
+        this.abstractNumIdCounter++
+        this.addNumberedAbstractNumType(this.abstractNumIdCounter, start)
+        const numberingEl = this.numberingXML.query("w:numbering")
+        numberingEl.appendXML(`
+            <w:num w:numId="${numId}">
+                <w:abstractNumId w:val="${this.abstractNumIdCounter}" />
+            </w:num>
+        `)
+    }
+
+    addNumberedAbstractNumType(abstractNumId, start) {
+        const numberingEl = this.numberingXML.query("w:numbering")
+        numberingEl.appendXML(`
+            <w:abstractNum w:abstractNumId="${abstractNumId}" w15:restartNumberingAfterBreak="0">
+                <w:nsid w:val="7F6635F3" />
+                <w:multiLevelType w:val="hybridMultilevel" />
+                <w:tmpl w:val="BFFEF214" />
+            </w:abstractNum>
+        `)
+        const newAbstractNum = this.numberingXML.query("w:abstractNum", {
+            "w:abstractNumId": String(abstractNumId)
+        })
+        // Definition seem to always define 9 levels (0-8).
+        for (let level = 0; level < 9; level++) {
+            newAbstractNum.appendXML(`
+                <w:lvl w:ilvl="${level}" w:tplc="0409000F">
+                    <w:start w:val="${start}" />
+                    <w:numFmt w:val="${this.numberFormat}" />
+                    <w:lvlText w:val="%${level + 1}." />
+                    <w:lvlJc w:val="left" />
+                    <w:pPr>
+                        <w:ind w:left="${(level + 1) * 720}" w:hanging="360" />
+                    </w:pPr>
+                </w:lvl>
+            `)
+        }
+    }
+}

package/src/exporter/docx/math.js

@@ -0,0 +1,46 @@
+import {mml2omml} from "mathml2omml"
+
+// Not entirely sure if we need this font here. This is included whenever Word
+// itself adds a formula, but our ooml doesn't refer to the font, so it may be pointless.
+const CAMBRIA_MATH_FONT_DECLARATION = `
+    <w:font w:name="Cambria Math">
+        <w:panose1 w:val="02040503050406030204" />
+        <w:charset w:val="00" />
+        <w:family w:val="roman" />
+        <w:pitch w:val="variable" />
+        <w:sig w:usb0="E00002FF" w:usb1="420024FF" w:usb2="00000000" w:usb3="00000000" w:csb0="0000019F" w:csb1="00000000" />
+    </w:font>`
+
+export class DOCXExporterMath {
+    constructor(xml) {
+        this.xml = xml
+        this.fontTableXML = false
+        this.addedCambriaMath = false
+        this.domParser = new DOMParser()
+    }
+
+    init() {
+        return this.xml
+            .getXml("word/fontTable.xml")
+            .then(fontTablesXML => {
+                this.fontTablesXML = fontTablesXML
+                return import("mathlive")
+            })
+            .then(MathLive => (this.mathLive = MathLive))
+    }
+
+    latexToMathML(latex) {
+        return this.mathLive.convertLatexToMathMl(latex)
+    }
+
+    getOmml(latex) {
+        if (!this.addedCambriaMath) {
+            const fontsEl = this.fontTablesXML.query("w:fonts")
+            fontsEl.appendXML(CAMBRIA_MATH_FONT_DECLARATION)
+            this.addedCambriaMath = true
+        }
+        const mathmlString = `<math xmlns="http://www.w3.org/1998/Math/MathML"><semantics>${this.latexToMathML(latex)}</semantics></math>`
+        const ommlString = mml2omml(mathmlString)
+        return ommlString
+    }
+}

package/src/exporter/docx/metadata.js

@@ -0,0 +1,289 @@
+import {escapeText} from "../../common/index.js"
+
+export class DOCXExporterMetadata {
+    constructor(xml, metadata, csl = null) {
+        this.xml = xml
+        this.metadata = metadata
+        this.csl = csl
+        this.coreXML = false
+        this.customXML = false
+    }
+
+    init() {
+        return this.xml.getXml("docProps/core.xml").then(coreXML => {
+            this.coreXML = coreXML
+            this.addMetadata()
+            return this.addCustomProperties()
+        })
+    }
+
+    async hasBibliography() {
+        if (!this.csl || !this.metadata.citationStyle) {
+            return "0"
+        }
+        try {
+            const style = await this.csl.getStyle(this.metadata.citationStyle)
+            // Check if the style has a bibliography section
+            const hasBib = style.children.some(
+                section => section.name === "bibliography"
+            )
+            return hasBib ? "1" : "0"
+        } catch (_error) {
+            return "0"
+        }
+    }
+
+    addMetadata() {
+        const corePropertiesEl = this.coreXML.query("cp:coreProperties")
+
+        // Title
+        let titleEl = this.coreXML.query("dc:title")
+        if (!titleEl) {
+            corePropertiesEl.appendXML("<dc:title></dc:title>")
+            titleEl = corePropertiesEl.lastElementChild
+        }
+        titleEl.innerXML = escapeText(this.metadata.title)
+        // Authors
+
+        const authors = this.metadata.authors.map(author => {
+            const nameParts = []
+            if (author.firstname) {
+                nameParts.push(author.firstname)
+            }
+            if (author.lastname) {
+                nameParts.push(author.lastname)
+            }
+            if (!nameParts.length && author.institution) {
+                // We have an institution but no names. Use institution as name.
+                nameParts.push(author.institution)
+            }
+            return nameParts.join(" ")
+        })
+        const lastAuthor = authors.length
+            ? escapeText(authors[0])
+            : gettext("Unknown")
+        const allAuthors = authors.length
+            ? escapeText(authors.join(";"))
+            : gettext("Unknown")
+        let allAuthorsEl = this.coreXML.query("dc:creator")
+
+        if (!allAuthorsEl) {
+            corePropertiesEl.appendXML("<dc:creator></dc:creator>")
+            allAuthorsEl = corePropertiesEl.lastElementChild
+        }
+        allAuthorsEl.innerXML = allAuthors
+        let lastAuthorEl = this.coreXML.query("dc:lastModifiedBy")
+        if (!lastAuthorEl) {
+            corePropertiesEl.appendXML(
+                "<dc:lastModifiedBy></dc:lastModifiedBy>"
+            )
+            lastAuthorEl = corePropertiesEl.lastElementChild
+        }
+        lastAuthorEl.innerXML = lastAuthor
+        // Keywords
+        if (this.metadata.keywords.length) {
+            // It is not really clear how keywords should be separated in DOCX files,
+            // so we use ", ".
+            const keywordsString = escapeText(this.metadata.keywords.join(", "))
+
+            let keywordsEl = this.coreXML.query("cp:keywords")
+            if (!keywordsEl) {
+                corePropertiesEl.appendXML("<cp:keywords></cp:keywords>")
+                keywordsEl = corePropertiesEl.lastElementChild
+            }
+            keywordsEl.innerXML = keywordsString
+        }
+
+        // time
+        const date = new Date()
+        const dateString = date.toISOString().split(".")[0] + "Z"
+        const createdEl = this.coreXML.query("dcterms:created")
+        createdEl.innerXML = dateString
+        let modifiedEl = this.coreXML.query("dcterms:modified")
+        if (!modifiedEl) {
+            corePropertiesEl.appendXML(
+                '<dcterms:modified xsi:type="dcterms:W3CDTF"></dcterms:modified>'
+            )
+            modifiedEl = corePropertiesEl.lastElementChild
+        }
+        modifiedEl.innerXML = dateString
+    }
+
+    async addCustomProperties() {
+        // Create or update docProps/custom.xml with citation style information
+        const customXmlContent = `<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<Properties xmlns="http://schemas.openxmlformats.org/officeDocument/2006/custom-properties" xmlns:vt="http://schemas.openxmlformats.org/officeDocument/2006/docPropsVTypes">
+</Properties>`
+
+        const customXML = await this.xml.getXml(
+            "docProps/custom.xml",
+            Promise.resolve(customXmlContent)
+        )
+        this.customXML = customXML
+
+        // Add citation style property
+        if (this.metadata.citationStyle) {
+            const propertiesEl = this.customXML.query("Properties")
+
+            // Remove any existing ZOTERO_PREF_ properties
+            const existingZoteroProps = this.customXML
+                .queryAll("property")
+                .filter(
+                    prop =>
+                        prop.getAttribute("name") &&
+                        prop.getAttribute("name").startsWith("ZOTERO_PREF_")
+                )
+            existingZoteroProps.forEach(prop =>
+                prop.parentElement.removeChild(prop)
+            )
+
+            // Find the highest pid to determine the next one
+            const existingProperties = this.customXML.queryAll("property")
+            let maxPid = 0
+            existingProperties.forEach(prop => {
+                const pid = parseInt(prop.getAttribute("pid"))
+                if (pid > maxPid) {
+                    maxPid = pid
+                }
+            })
+
+            // Determine if the citation style has a bibliography
+            const hasBib = await this.hasBibliography()
+
+            // Create the data content
+            const citationStyleUrl = `http://www.zotero.org/styles/${escapeText(this.metadata.citationStyle)}`
+            const dataContent = `<data data-version="3" zotero-version="8.0.2"><session id=""/><style id="${citationStyleUrl}" locale="${escapeText(this.metadata.language || "en-US")}" hasBibliography="${hasBib}" bibliographyStyleHasBeenSet="1"/><prefs><pref name="fieldType" value="Field"/></prefs></data>`
+
+            // Split content into chunks of 255 characters (DOCX limit)
+            const chunkSize = 255
+            const chunks = []
+            for (let i = 0; i < dataContent.length; i += chunkSize) {
+                chunks.push(dataContent.substring(i, i + chunkSize))
+            }
+
+            // Create properties for each chunk
+            chunks.forEach((chunk, index) => {
+                const propName = `ZOTERO_PREF_${index + 1}`
+                const propertyXML = `<property fmtid="{D5CDD505-2E9C-101B-9397-08002B2CF9AE}" pid="${maxPid + index + 1}" name="${propName}">
+<vt:lpwstr></vt:lpwstr>
+</property>`
+                propertiesEl.appendXML(propertyXML)
+                // Set the text content after appending (textContent escapes XML characters)
+                const lpwstrEl =
+                    propertiesEl.lastElementChild.query("vt:lpwstr")
+                if (lpwstrEl) {
+                    lpwstrEl.textContent = chunk
+                }
+            })
+        }
+
+        // Add structured contributor metadata properties
+        await this.addContributorProperties()
+
+        return Promise.resolve()
+    }
+
+    async addContributorProperties() {
+        if (!this.metadata.contributors || !this.metadata.contributors.length) {
+            return Promise.resolve()
+        }
+
+        const propertiesEl = this.customXML.query("Properties")
+
+        // Remove any existing fidus_contributor_ properties
+        const existingContributorProps = this.customXML
+            .queryAll("property")
+            .filter(
+                prop =>
+                    prop.getAttribute("name") &&
+                    prop.getAttribute("name").startsWith("fidus_contributor_")
+            )
+        existingContributorProps.forEach(prop =>
+            prop.parentElement.removeChild(prop)
+        )
+
+        // Find the highest pid
+        const existingProperties = this.customXML.queryAll("property")
+        let maxPid = 0
+        existingProperties.forEach(prop => {
+            const pid = parseInt(prop.getAttribute("pid"))
+            if (pid > maxPid) {
+                maxPid = pid
+            }
+        })
+
+        const contributors = this.metadata.contributors
+
+        // Add contributor count
+        maxPid++
+        const countXML = `<property fmtid="{D5CDD505-2E9C-101B-9397-08002B2CF9AE}" pid="${maxPid}" name="fidus_contributor_count">
+<vt:i4></vt:i4>
+</property>`
+        propertiesEl.appendXML(countXML)
+        const countEl = propertiesEl.lastElementChild.query("vt:i4")
+        if (countEl) {
+            countEl.textContent = String(contributors.length)
+        }
+
+        // Add property for each contributor
+        contributors.forEach((contributor, index) => {
+            const num = index + 1
+            const nameParts = []
+            if (contributor.firstname) {
+                nameParts.push(contributor.firstname)
+            }
+            if (contributor.lastname) {
+                nameParts.push(contributor.lastname)
+            }
+            const fullName =
+                nameParts.join(" ") || contributor.institution || ""
+
+            const fields = [
+                {
+                    name: `fidus_contributor_${num}_role`,
+                    value: contributor.role || ""
+                },
+                {name: `fidus_contributor_${num}_name`, value: fullName},
+                {
+                    name: `fidus_contributor_${num}_firstname`,
+                    value: contributor.firstname || ""
+                },
+                {
+                    name: `fidus_contributor_${num}_lastname`,
+                    value: contributor.lastname || ""
+                },
+                {
+                    name: `fidus_contributor_${num}_institution`,
+                    value: contributor.institution || ""
+                },
+                {
+                    name: `fidus_contributor_${num}_email`,
+                    value: contributor.email || ""
+                },
+                {
+                    name: `fidus_contributor_${num}_id_type`,
+                    value: contributor.id_type || ""
+                },
+                {
+                    name: `fidus_contributor_${num}_id_value`,
+                    value: contributor.id_value || ""
+                }
+            ]
+
+            fields.forEach(field => {
+                maxPid++
+                const propertyXML = `<property fmtid="{D5CDD505-2E9C-101B-9397-08002B2CF9AE}" pid="${maxPid}" name="${field.name}">
+<vt:lpwstr></vt:lpwstr>
+</property>`
+                propertiesEl.appendXML(propertyXML)
+                const lpwstrEl =
+                    propertiesEl.lastElementChild.query("vt:lpwstr")
+                if (lpwstrEl) {
+                    lpwstrEl.textContent = field.value
+                }
+            })
+        })
+
+        return Promise.resolve()
+    }
+}