Skip to content

Commit

Permalink
[api-minor] Change the "dc:creator" Metadata field to an Array
Browse files Browse the repository at this point in the history
 - add scripting support for doc.info.authors
 - doc.info.metadata is the raw string with xml code
  • Loading branch information
calixteman committed Jan 11, 2021
1 parent 35845d1 commit 43d5512
Show file tree
Hide file tree
Showing 10 changed files with 97 additions and 33 deletions.
4 changes: 1 addition & 3 deletions src/core/writer.js
Original file line number Diff line number Diff line change
Expand Up @@ -130,9 +130,7 @@ function updateXFA(datasetsRef, newRefs, xref) {
}
const datasets = xref.fetchIfRef(datasetsRef);
const str = bytesToString(datasets.getBytes());
const xml = new SimpleXMLParser(/* hasAttributes */ true).parseFromString(
str
);
const xml = new SimpleXMLParser({ hasAttributes: true }).parseFromString(str);

for (const { xfa } of newRefs) {
if (!xfa) {
Expand Down
62 changes: 47 additions & 15 deletions src/display/metadata.js
Original file line number Diff line number Diff line change
Expand Up @@ -24,14 +24,15 @@ class Metadata {
data = this._repair(data);

// Convert the string to an XML document.
const parser = new SimpleXMLParser();
const parser = new SimpleXMLParser({ lowerCaseName: true });
const xmlDocument = parser.parseFromString(data);

this._metadataMap = new Map();

if (xmlDocument) {
this._parse(xmlDocument);
}
this._data = data;
}

_repair(data) {
Expand Down Expand Up @@ -79,40 +80,71 @@ class Metadata {
});
}

_getSequence(entry) {
const name = entry.nodeName;
if (name !== "rdf:bag" && name !== "rdf:seq" && name !== "rdf:alt") {
return null;
}

return entry.childNodes.filter(node => node.nodeName === "rdf:li");
}

_getCreators(entry) {
if (entry.nodeName !== "dc:creator") {
return false;
}
if (!entry.hasChildNodes()) {
return true;
}

// Child must be a Bag (unordered array) or a Seq.
const seqNode = entry.childNodes[0];
const authors = this._getSequence(seqNode) || [];
this._metadataMap.set(
entry.nodeName,
authors.map(node => node.textContent.trim())
);

return true;
}

_parse(xmlDocument) {
let rdf = xmlDocument.documentElement;

if (rdf.nodeName.toLowerCase() !== "rdf:rdf") {
if (rdf.nodeName !== "rdf:rdf") {
// Wrapped in <xmpmeta>
rdf = rdf.firstChild;
while (rdf && rdf.nodeName.toLowerCase() !== "rdf:rdf") {
while (rdf && rdf.nodeName !== "rdf:rdf") {
rdf = rdf.nextSibling;
}
}

const nodeName = rdf ? rdf.nodeName.toLowerCase() : null;
if (!rdf || nodeName !== "rdf:rdf" || !rdf.hasChildNodes()) {
if (!rdf || rdf.nodeName !== "rdf:rdf" || !rdf.hasChildNodes()) {
return;
}

const children = rdf.childNodes;
for (let i = 0, ii = children.length; i < ii; i++) {
const desc = children[i];
if (desc.nodeName.toLowerCase() !== "rdf:description") {
for (const desc of rdf.childNodes) {
if (desc.nodeName !== "rdf:description") {
continue;
}

for (let j = 0, jj = desc.childNodes.length; j < jj; j++) {
if (desc.childNodes[j].nodeName.toLowerCase() !== "#text") {
const entry = desc.childNodes[j];
const name = entry.nodeName.toLowerCase();

this._metadataMap.set(name, entry.textContent.trim());
for (const entry of desc.childNodes) {
const name = entry.nodeName;
if (name === "#text") {
continue;
}
if (this._getCreators(entry)) {
continue;
}
this._metadataMap.set(name, entry.textContent.trim());
}
}
}

getRaw() {
return this._data;
}

get(name) {
return this._metadataMap.has(name) ? this._metadataMap.get(name) : null;
}
Expand Down
15 changes: 8 additions & 7 deletions src/scripting_api/doc.js
Original file line number Diff line number Diff line change
Expand Up @@ -42,7 +42,7 @@ class Doc extends PDFObject {
this._dirty = false;
this._disclosed = false;
this._media = undefined;
this._metadata = data.metadata;
this._metadata = data.metadata || "";
this._noautocomplete = undefined;
this._nocache = undefined;
this._spellDictionaryOrder = [];
Expand Down Expand Up @@ -74,12 +74,13 @@ class Doc extends PDFObject {
// and they're are read-only.
this._info = new Proxy(
{
title: this.title,
author: this.author,
subject: this.subject,
keywords: this.keywords,
creator: this.creator,
producer: this.producer,
title: this._title,
author: this._author,
authors: data.authors || [this._author],
subject: this._subject,
keywords: this._keywords,
creator: this._creator,
producer: this._producer,
creationdate: this._creationDate,
moddate: this._modDate,
trapped: data.Trapped || "Unknown",
Expand Down
6 changes: 5 additions & 1 deletion src/shared/xml_parser.js
Original file line number Diff line number Diff line change
Expand Up @@ -427,12 +427,13 @@ class SimpleDOMNode {
}

class SimpleXMLParser extends XMLParserBase {
constructor(hasAttributes = false) {
constructor({ hasAttributes = false, lowerCaseName = false }) {
super();
this._currentFragment = null;
this._stack = null;
this._errorCode = XMLParserErrorCode.NoError;
this._hasAttributes = hasAttributes;
this._lowerCaseName = lowerCaseName;
}

parseFromString(data) {
Expand Down Expand Up @@ -476,6 +477,9 @@ class SimpleXMLParser extends XMLParserBase {
}

onBeginElement(name, attributes, isEmpty) {
if (this._lowerCaseName) {
name = name.toLowerCase();
}
const node = new SimpleDOMNode(name);
node.childNodes = [];
if (this._hasAttributes) {
Expand Down
25 changes: 25 additions & 0 deletions test/integration/scripting_spec.js
Original file line number Diff line number Diff line change
Expand Up @@ -451,4 +451,29 @@ describe("Interaction", () => {
);
});
});

describe("in js-authors.pdf", () => {
let pages;

beforeAll(async () => {
pages = await loadAndWait("js-authors.pdf", "#\\32 5R");
});

afterAll(async () => {
await closePages(pages);
});

it("must print authors in a text field", async () => {
await Promise.all(
pages.map(async ([browserName, page]) => {
const text = await actAndWaitForInput(page, "#\\32 5R", async () => {
await page.click("[data-annotation-id='26R']");
});
expect(text)
.withContext(`In ${browserName}`)
.toEqual("author1::author2::author3::author4::author5");
})
);
});
});
});
1 change: 1 addition & 0 deletions test/pdfs/.gitignore
Original file line number Diff line number Diff line change
Expand Up @@ -324,6 +324,7 @@
!tensor-allflags-withfunction.pdf
!issue10084_reduced.pdf
!issue4246.pdf
!js-authors.pdf
!issue4461.pdf
!issue4573.pdf
!issue4722.pdf
Expand Down
Binary file added test/pdfs/js-authors.pdf
Binary file not shown.
4 changes: 2 additions & 2 deletions test/unit/metadata_spec.js
Original file line number Diff line number Diff line change
Expand Up @@ -96,7 +96,7 @@ describe("metadata", function () {
expect(metadata.get("dc:qux")).toEqual(null);

expect(metadata.getAll()).toEqual({
"dc:creator": "ODIS",
"dc:creator": ["ODIS"],
"dc:title": "L'Odissee thématique logo Odisséé - décembre 2008.pub",
"xap:creatortool": "PDFCreator Version 0.9.6",
});
Expand Down Expand Up @@ -168,7 +168,7 @@ describe("metadata", function () {
expect(metadata.get("dc:qux")).toEqual(null);

expect(metadata.getAll()).toEqual({
"dc:creator": "",
"dc:creator": [""],
"dc:description": "",
"dc:format": "application/pdf",
"dc:subject": "",
Expand Down
10 changes: 6 additions & 4 deletions test/unit/xml_spec.js
Original file line number Diff line number Diff line change
Expand Up @@ -47,8 +47,9 @@ describe("XML", function () {
<g a="121110"/>
</b>
</a>`;
const root = new SimpleXMLParser(true).parseFromString(xml)
.documentElement;
const root = new SimpleXMLParser({ hasAttributes: true }).parseFromString(
xml
).documentElement;
function getAttr(path) {
return root.searchNode(parseXFAPath(path), 0).attributes[0].value;
}
Expand Down Expand Up @@ -96,8 +97,9 @@ describe("XML", function () {
<g a="121110"/>
</b>
</a>`;
const root = new SimpleXMLParser(true).parseFromString(xml)
.documentElement;
const root = new SimpleXMLParser({ hasAttributes: true }).parseFromString(
xml
).documentElement;
const buffer = [];
root.dump(buffer);

Expand Down
3 changes: 2 additions & 1 deletion web/app.js
Original file line number Diff line number Diff line change
Expand Up @@ -1655,7 +1655,8 @@ const PDFViewerApplication = {
baseURL: this.baseUrl,
filesize: this._contentLength,
filename: this._docFilename,
metadata: this.metadata,
metadata: this.metadata?.getRaw(),
authors: this.metadata?.get("dc:creator"),
numPages: pdfDocument.numPages,
URL: this.url,
actions: docActions,
Expand Down

0 comments on commit 43d5512

Please sign in to comment.