7. OCR Textsadd chapter
Special feature: You specify the file name and target folder in the script, not in the “Basic” tab of the workflow.
7..1 OCR Texts per Page
Output one TXT file per page.
// -----------------------------------------------------------------
// Date: 01-09-2018
// Purpose: Generate a text file with the OCR text per page
// -----------------------------------------------------------------
var filename;
var folder = "C:/exports/ocr/";
var page;
for (i = 0; i < job.numPages; i++) {
page = job.pages[i];
// ut.notifyUser('seite ' + i+1, '"'+page.ocrText+'"');
filename = folder + page.pageNumber8 + '.txt';
// ut.notifyUser('filename' , filename);
ut.writeStringToFile (filename, page.ocrText);
} // for i
BCS-2 creates the storage path automatically if the KeyMaps are filled. The file name corresponds to the index value.
Name: FOLDER_FOLDER Value: job.index1 Name: LOCAL_MASTER_FOLDER Valuet: C:/
// -----------------------------------------------------------------
// Date: 01-22-2021
// Purpose: Generate a text file with the OCR text per page
// -----------------------------------------------------------------
var folder = job.getWfKeyValue('MASTER_FOLDER') + '/' + eval(job.getWfKeyValue('FOLDER_NAME'));
var file_name;
var page;
ut.createCompletePath(folder);
for (i = 0; i < job.numPages; i++) {
page = job.pages[i];
ut.notifyUser('seite ' + i+1, '"'+page.ocrText+'"');
file_name = folder + '/' + page.pageNumber8 + '.txt';
ut.notifyUser('file_name' , file_name);
ut.writeStringToFile(file_name, page.ocrText);
} // for i
7..2 OCR Texts for the Entire Job
Alternative 1: You define the file name and path as usual under “Basic”.
// -----------------------------------------------------------------
// Date: 08-13-2019
// Purpose: Generate a text file with the OCR texts of all pages
// -----------------------------------------------------------------
var ocr_texts = "";
for (i = 0; i < job.numPages; i++) {
ocr_texts += job.pages[i].ocrText + '\n';
} // for i...
ocr_texts;
Alternative 2:
// -----------------------------------------------------------------
// Datum: 09.01.2018
// Purpose: Generate a text file with the OCR texts of all pages
// -----------------------------------------------------------------
var filename = "C:/exports/ocr/ocr_job.txt";
var page;
var ocr_texts = "";
for (i = 0; i < job.numPages; i++) {
page = job.pages[i];
ocr_texts += page.ocrText + '\n';
} // for i
ut.writeStringToFile (filename, ocr_texts);
Alternative 3 – BCS-2 creates the storage path automatically if the KeyMaps are filled. The file name corresponds to the index value.
- Name: FOLDER_FOLDER
- Value: job.index1
- Name: LOCAL_MASTER_FOLDER
- Value: C:/
// -----------------------------------------------------------------
// Date: 08-13-2019
// Purpose: Generate a text file with the OCR texts of all pages
// -----------------------------------------------------------------
var ocr_texts = "";
var folder = job.getWfKeyValue('MASTER_FOLDER') + '/' + eval(job.getWfKeyValue('FOLDER_NAME'));
var file_name = folder +'/' + job.index1 + '.txt';
for (i = 0; i < job.numPages; i++) {
ocr_texts += job.pages[i].ocrText + '\n';
} // for i...
ut.createCompletePath(folder);
ut.writeStringToFile(file_name, ocr_texts);
