Sakurai/pdf.js
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Ensure that fieldObjects and #collectFieldObjects handles References correctly

Browse Source 
The `fieldObjects`-getter itself is called, from `src/core/worker.js`, in a way that'll ensure that any `MissingDataException`s are handled. However the problem is that the actual data-lookups in `fieldObjects` and `#collectFieldObjects` are done inside of a Promise, which means that `MissingDataException`s won't be handled and parsing could thus break.

To address this we change all data-lookups to be asynchronous instead.
This commit is contained in:
Jonas Jenwald 2023-11-08 09:51:52 +01:00
parent c6a717f900
commit 65c827b0eb
1 changed files with 42 additions and 36 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

78
src/core/document.js
View File

@ -1711,13 +1711,15 @@ class PDFDocument {
: clearGlobalCaches();
}
#collectFieldObjects(name, fieldRef, promises, annotationGlobals) {
const field = this.xref.fetchIfRef(fieldRef);
async #collectFieldObjects(name, fieldRef, promises, annotationGlobals) {
const { xref } = this;
const field = await xref.fetchIfRefAsync(fieldRef);
if (!(field instanceof Dict)) {
return;
}
if (field.has("T")) {
const partName = stringToPDFString(field.get("T"));
const partName = stringToPDFString(await field.getAsync("T"));
name = name === "" ? partName : `${name}.${partName}`;
}
@ -1726,7 +1728,7 @@ class PDFDocument {
}
promises.get(name).push(
AnnotationFactory.create(
this.xref,
xref,
fieldRef,
annotationGlobals,
this._localIdFactory,
@ -1740,10 +1742,13 @@ class PDFDocument {
})
);
const kids = field.get("Kids");
if (!field.has("Kids")) {
return;
}
const kids = await field.getAsync("Kids");
if (Array.isArray(kids)) {
for (const kid of kids) {
this.#collectFieldObjects(name, kid, promises, annotationGlobals);
await this.#collectFieldObjects(name, kid, promises, annotationGlobals);
}
}
}
@ -1753,39 +1758,40 @@ class PDFDocument {
return shadow(this, "fieldObjects", Promise.resolve(null));
}
const promise = this.pdfManager
.ensureDoc("annotationGlobals")
.then(async annotationGlobals => {
if (!annotationGlobals) {
return null;
}
const promise = Promise.all([
this.pdfManager.ensureDoc("annotationGlobals"),
this.pdfManager.ensureCatalog("acroForm"),
]).then(async ([annotationGlobals, acroForm]) => {
if (!annotationGlobals) {
return null;
}
const allFields = Object.create(null);
const fieldPromises = new Map();
for (const fieldRef of this.catalog.acroForm.get("Fields")) {
this.#collectFieldObjects(
"",
fieldRef,
fieldPromises,
annotationGlobals
);
}
const allFields = Object.create(null);
const fieldPromises = new Map();
for (const fieldRef of await acroForm.getAsync("Fields")) {
await this.#collectFieldObjects(
"",
fieldRef,
fieldPromises,
annotationGlobals
);
}
const allPromises = [];
for (const [name, promises] of fieldPromises) {
allPromises.push(
Promise.all(promises).then(fields => {
fields = fields.filter(field => !!field);
if (fields.length > 0) {
allFields[name] = fields;
}
})
);
}
const allPromises = [];
for (const [name, promises] of fieldPromises) {
allPromises.push(
Promise.all(promises).then(fields => {
fields = fields.filter(field => !!field);
if (fields.length > 0) {
allFields[name] = fields;
}
})
);
}
await Promise.all(allPromises);
return allFields;
});
await Promise.all(allPromises);
return allFields;
});
return shadow(this, "fieldObjects", promise);
}