mirrors/zotero
2
0
Fork 0
Code Issues Pull requests Projects Releases Packages 1 Wiki Activity Actions

Closes #5, Fix Retrieve Metadata for Google Books

Browse source 
It doesn't look like Google Books PDFs actually have any OCRed text, nor do they have any obvious identifying information, so we just blacklist them for now.
This commit is contained in:
Simon Kornblith 2011-12-31 18:49:09 +00:00
parent 3b42e71c77
commit 3976f7afb1
1 changed files with 2 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
chrome/content/zotero/recognizePDF.js
View file

@ -310,7 +310,8 @@ Zotero_RecognizePDF.Recognizer.prototype.recognize = function(file, libraryID, c
// get (not quite) median length
var lineLengthsLength = lineLengths.length;
if(lineLengthsLength < 20) {
if(lineLengthsLength < 20
|| lines[0] === "This is a digital copy of a book that was preserved for generations on library shelves before it was carefully scanned by Google as part of a project") {
this._callback(false, "recognizePDF.noOCR");
} else {
var sortedLengths = lineLengths.sort();
@ -329,9 +330,6 @@ Zotero_RecognizePDF.Recognizer.prototype.recognize = function(file, libraryID, c
}
this._startLine = this._iteration = 0;
}
if(lineLengthsLength >= 20) {
this._queryGoogle();
}
}