mirrors/pdf.js
1
0
Fork 0
mirror of https://github.com/mozilla/pdf.js.git synced 2025-04-26 01:58:06 +02:00
Code Activity

[api-minor] Add a parameter to PDFPageProxy_getTextContent that controls whether PartialEvaluator_getTextContent will attempt to combine same line text items

Browse source 
From the discussion in issue 7445, it seems that there may be cases where an API consumer would want to get the text content as is, without combined text items.
This commit is contained in:
Jonas Jenwald 2016-07-03 18:29:47 +02:00
parent 9228a04061
commit f297e4d17c
8 changed files with 42 additions and 27 deletions
Download patch file Download diff file Expand all files Collapse all files

12
src/core/evaluator.js
View file

@ -1110,7 +1110,8 @@ var PartialEvaluator = (function PartialEvaluatorClosure() {
getTextContent:
function PartialEvaluator_getTextContent(stream, task, resources,
stateManager,
normalizeWhitespace) {
normalizeWhitespace,
combineTextItems) {
stateManager = (stateManager || new StateManager(new TextState()));
@ -1421,7 +1422,8 @@ var PartialEvaluator = (function PartialEvaluatorClosure() {
var isSameTextLine = !textState.font ? false :
((textState.font.vertical ? args[0] : args[1]) === 0);
advance = args[0] - args[1];
if (isSameTextLine && textContentItem.initialized &&
if (combineTextItems &&
isSameTextLine && textContentItem.initialized &&
advance > 0 &&
advance <= textContentItem.fakeMultiSpaceMax) {
textState.translateTextLineMatrix(args[0], args[1]);
@ -1453,7 +1455,8 @@ var PartialEvaluator = (function PartialEvaluatorClosure() {
// Optimization to treat same line movement as advance.
advance = textState.calcTextLineMatrixAdvance(
args[0], args[1], args[2], args[3], args[4], args[5]);
if (advance !== null && textContentItem.initialized &&
if (combineTextItems &&
advance !== null && textContentItem.initialized &&
advance.value > 0 &&
advance.value <= textContentItem.fakeMultiSpaceMax) {
textState.translateTextLineMatrix(advance.width,
@ -1594,7 +1597,8 @@ var PartialEvaluator = (function PartialEvaluatorClosure() {
next(self.getTextContent(xobj, task,
xobj.dict.get('Resources') || resources, stateManager,
normalizeWhitespace).then(function (formTextContent) {
normalizeWhitespace, combineTextItems).then(
function (formTextContent) {
Util.appendToArray(textContent.items, formTextContent.items);
Util.extendObj(textContent.styles, formTextContent.styles);
stateManager.restore();