ZenBrowserMirrors/pdf.js
1
0
Fork 0
mirror of https://github.com/zen-browser/pdf.js.git synced 2025-07-08 17:30:09 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

[api-minor] Remove the normalizeWhitespace option in the PDFPageProxy.{getTextContent, streamTextContent} methods (issue 14519, PR 14428 follow-up)

Browse source 
With these changes, we'll now *always* replace all whitespaces with standard spaces (0x20). This behaviour is already, since many years, the default in both the viewer and the browser-tests.
This commit is contained in:
Jonas Jenwald 2022-01-31 17:48:35 +01:00
parent 48c8831a79
commit 403baa7bba
8 changed files with 8 additions and 16 deletions
Download patch file Download diff file Expand all files Collapse all files

10
src/display/api.js
View file

@ -1069,8 +1069,6 @@ class PDFDocumentProxy {
* Page getTextContent parameters.
*
* @typedef {Object} getTextContentParameters
* @property {boolean} normalizeWhitespace - Replaces all occurrences of
* whitespace with standard spaces (0x20). The default value is `false`.
* @property {boolean} disableCombineTextItems - Do not attempt to combine
* same line {@link TextItem}'s. The default value is `false`.
* @property {boolean} [includeMarkedContent] - When true include marked
@ -1585,11 +1583,13 @@ class PDFPageProxy {
}
/**
* NOTE: All occurrences of whitespace will be replaced by
* standard spaces (0x20).
*
* @param {getTextContentParameters} params - getTextContent parameters.
* @returns {ReadableStream} Stream for reading text content chunks.
*/
streamTextContent({
normalizeWhitespace = false,
disableCombineTextItems = false,
includeMarkedContent = false,
} = {}) {
@ -1599,7 +1599,6 @@ class PDFPageProxy {
"GetTextContent",
{
pageIndex: this._pageIndex,
normalizeWhitespace: normalizeWhitespace === true,
combineTextItems: disableCombineTextItems !== true,
includeMarkedContent: includeMarkedContent === true,
},
@ -1613,6 +1612,9 @@ class PDFPageProxy {
}
/**
* NOTE: All occurrences of whitespace will be replaced by
* standard spaces (0x20).
*
* @param {getTextContentParameters} params - getTextContent parameters.
* @returns {Promise<TextContent>} A promise that is resolved with a
* {@link TextContent} object that represents the page's text content.