{"id":50588,"date":"2023-07-01T12:00:57","date_gmt":"2023-07-01T12:00:57","guid":{"rendered":"https:\/\/informaticsjournal.net\/?p=50588"},"modified":"2026-10-25T13:59:36","modified_gmt":"2026-10-25T13:59:36","slug":"%d8%a3%d8%aa%d9%85%d8%aa%d8%a9-%d8%a7%d9%84%d8%b9%d9%85%d9%84-%d8%a7%d9%84%d9%8a%d9%88%d9%85%d9%8a-%d9%84%d9%84%d9%85%d8%b3%d8%aa%d9%88%d8%af%d8%b9-%d8%a7%d9%84%d9%85%d8%a4%d8%b3%d8%b3%d9%8a-%d8%a8","status":"publish","type":"post","link":"https:\/\/informaticsjournal.net\/?p=50588","title":{"rendered":"\u0623\u062a\u0645\u062a\u0629 \u0627\u0644\u0639\u0645\u0644 \u0627\u0644\u064a\u0648\u0645\u064a \u0644\u0644\u0645\u0633\u062a\u0648\u062f\u0639 \u0627\u0644\u0645\u0624\u0633\u0633\u064a \u0628\u0627\u0633\u062a\u062e\u062f\u0627\u0645 R \u0648\u0628\u0627\u064a\u062b\u0648\u0646"},"content":{"rendered":"

\u0645\u0642\u062f\u0645\u0629 \u0648\u062e\u0644\u0641\u064a\u0629:<\/strong><\/p>\n

R \u0644\u063a\u0629 \u0648\u0628\u064a\u0626\u0629 \u0628\u0631\u0645\u062c\u064a\u0629 \u0644\u0644\u062d\u0648\u0633\u0628\u0629 \u0627\u0644\u0625\u062d\u0635\u0627\u0626\u064a\u0629 \u0648\u062a\u062d\u0644\u064a\u0644 \u0627\u0644\u0628\u064a\u0627\u0646\u0627\u062a \u0648\u062a\u0645\u062b\u064a\u0644\u0647\u0627 \u0631\u0633\u0648\u0645\u064a\u064b\u0627. \u0648\u062a\u0648\u0641\u0631 \u062a\u0642\u0646\u064a\u0627\u062a \u0645\u062a\u0646\u0648\u0639\u0629: \u0627\u0644\u0646\u0645\u0630\u062c\u0629 \u0627\u0644\u062e\u0637\u064a\u0629 \u0648\u063a\u064a\u0631 \u0627\u0644\u062e\u0637\u064a\u0629\u060c \u0648\u0627\u0644\u0627\u062e\u062a\u0628\u0627\u0631\u0627\u062a \u0627\u0644\u062a\u0642\u0644\u064a\u062f\u064a\u0629\u060c \u0648\u0627\u0644\u0633\u0644\u0627\u0633\u0644 \u0627\u0644\u0632\u0645\u0646\u064a\u0629 \u0648\u0627\u0644\u062a\u0635\u0646\u064a\u0641 \u0648\u0627\u0644\u062a\u062c\u0645\u064a\u0639\u060c \u0648\u0642\u0627\u0628\u0644\u064a\u0629 \u0643\u0628\u064a\u0631\u0629 \u0644\u0644\u062a\u0648\u0633\u0639[1]. \u0623\u0645\u0627 \u0628\u0627\u064a\u062b\u0648\u0646 \u0641\u062a\u064f\u0633\u062a\u062e\u062f\u0645 \u0644\u0628\u0646\u0627\u0621 \u0627\u0644\u0645\u0648\u0627\u0642\u0639 \u0648\u0627\u0644\u0628\u0631\u0627\u0645\u062c \u0648\u0623\u062a\u0645\u062a\u0629 \u0627\u0644\u0645\u0647\u0627\u0645 \u0648\u0627\u0644\u062a\u062d\u0644\u064a\u0644\u060c \u0648\u0647\u064a \u0639\u0627\u0645\u0629 \u0627\u0644\u0623\u063a\u0631\u0627\u0636 \u0644\u0627 \u062a\u062e\u062a\u0635 \u0628\u0645\u0634\u0643\u0644\u0629 \u0628\u0639\u064a\u0646\u0647\u0627\u060c \u0648\u062c\u0639\u0644\u0647\u0627 \u062a\u0646\u0648\u0639\u0647\u0627 \u0648\u0633\u0647\u0648\u0644\u062a\u0647\u0627 \u0644\u0644\u0645\u0628\u062a\u062f\u0626\u064a\u0646 \u0645\u0646 \u0623\u0643\u062b\u0631 \u0627\u0644\u0644\u063a\u0627\u062a \u0627\u0633\u062a\u062e\u062f\u0627\u0645\u064b\u0627[2].<\/p>\n

\u0648\u0641\u064a 2021 \u0646\u0642\u0644\u062a \u0645\u0643\u062a\u0628\u0627\u062a \u062c\u0627\u0645\u0639\u0629 \u0648\u0644\u0627\u064a\u0629 \u0643\u0648\u0644\u0648\u0631\u0627\u062f\u0648 CSUL \u0645\u0648\u0627\u062f \u0627\u0644\u062a\u0631\u0627\u062b \u0645\u0646 DSpace \u0625\u0644\u0649 CONTENTdm. \u0648\u0644\u062a\u0628\u0633\u064a\u0637 \u0627\u0644\u0627\u0646\u062a\u0642\u0627\u0644\u060c \u0627\u0633\u062a\u062e\u062f\u0645\u0646\u0627 \u0628\u0631\u0627\u0645\u062c R \u0648\u0628\u0640\u0627\u064a\u062b\u0648\u0646 \u0644\u0645\u0647\u0627\u0645 \u0645\u0633\u062a\u0647\u0644\u0643\u0629 \u0644\u0644\u0648\u0642\u062a: \u062a\u063a\u064a\u064a\u0631 \u0623\u062d\u062c\u0627\u0645 \u0627\u0644\u0635\u0648\u0631 \u062f\u0641\u0639\u0629 \u0628\u0635\u0631\u0641 \u0627\u0644\u0646\u0638\u0631 \u0639\u0646 \u0627\u062a\u062c\u0627\u0647\u0647\u0627\u060c \u0648\u0645\u0637\u0627\u0628\u0642\u0629 \u0627\u0644\u062a\u0641\u0631\u064a\u063a\u0627\u062a \u0628\u0627\u0644\u0635\u0648\u0631\u060c \u0648\u0625\u0646\u0634\u0627\u0621 PDF \u0648\u0641\u0642 \u0623\u0633\u0645\u0627\u0621 \u0627\u0644\u0645\u0644\u0641\u0627\u062a\u060c \u0648\u0628\u0646\u0627\u0621 \u0645\u062c\u0644\u062f\u0627\u062a \u0644\u0644\u0625\u062f\u062e\u0627\u0644 \u0627\u0644\u062c\u0645\u0627\u0639\u064a \u0644\u0644\u0643\u0627\u0626\u0646\u0627\u062a \u0627\u0644\u0645\u0631\u0643\u0628\u0629.<\/p>\n

\u0627\u0644\u0625\u0639\u062f\u0627\u062f:<\/strong><\/p>\n

\u0642\u062f \u064a\u0635\u0639\u0628 \u0639\u0644\u0649 \u0627\u0644\u0645\u0628\u062a\u062f\u0626 \u0625\u0639\u062f\u0627\u062f \u0628\u064a\u0626\u0629 \u0627\u0644\u062a\u0634\u063a\u064a\u0644. \u0648\u062a\u0633\u0627\u0639\u062f \u0627\u0644\u0648\u0631\u0634 \u0648\u0627\u0644\u062f\u0631\u0648\u0633\u061b \u0641\u0645\u062b\u0644\u064b\u0627 \u062a\u062a\u0639\u0627\u0648\u0646 \u0627\u0644\u062c\u0627\u0645\u0639\u0629 \u0645\u0639 Software Carpentry \u0644\u062a\u0648\u0641\u064a\u0631 \u0648\u0631\u0634 \u0645\u062c\u0627\u0646\u064a\u0629 \u0644\u0644\u0645\u0648\u0638\u0641\u064a\u0646 \u0641\u064a R \u0648\u0628\u0627\u064a\u062b\u0648\u0646: https:\/\/software-carpentry.org\/ . \u0648\u062a\u0648\u0641\u0631 Coursera \u062f\u0631\u0648\u0633\u064b\u0627 \u062a\u0645\u0647\u064a\u062f\u064a\u0629 \u0645\u062b\u0644 Python for Everyone: https:\/\/www.coursera.org\/specializations\/python . \u0648\u062a\u0634\u0631\u062d \u0647\u0630\u0647 \u0627\u0644\u0628\u0631\u0627\u0645\u062c \u0627\u0644\u0625\u0639\u062f\u0627\u062f \u062a\u0641\u0635\u064a\u0644\u064b\u0627\u060c \u0648\u062a\u062a\u064a\u062d \u0627\u0644\u0645\u0633\u0627\u0639\u062f\u0629 \u0639\u0646\u062f \u0627\u0644\u062a\u0639\u062b\u0631.<\/p>\n

\u0648\u0644\u062a\u0640\u0634\u063a\u064a\u0644 R \u064a\u0644\u0632\u0645 \u062a\u062b\u0628\u064a\u062a \u0627\u0644\u0644\u063a\u0629 \u0648 RStudio Desktop \u060c \u0648\u064a\u0631\u062f \u0631\u0627\u0628\u0637\u0627\u0647\u0645\u0627 \u0641\u064a \u0625\u062d\u0627\u0644\u0627\u062a \u0627\u0644\u0623\u0635\u0644. \u0648\u0644\u0628\u0627\u064a\u062b\u0648\u0646 \u064a\u0645\u0643\u0646 \u0627\u0633\u062a\u062e\u062f\u0627\u0645 \u0623\u0645\u0631 python \u0641\u064a \u0627\u0644\u0637\u0631\u0641\u064a\u0629 \u0639\u0644\u0649 \u0645\u0627\u0643 \u0648\u0648\u064a\u0646\u062f\u0648\u0632 \u0648\u0644\u064a\u0646\u0643\u0633\u060c \u0623\u0648 \u062a\u0648\u0632\u064a\u0639\u0629 Anaconda \u0627\u0644\u0645\u0641\u062a\u0648\u062d\u0629. \u0648\u0644\u0644\u062a\u062d\u0631\u064a\u0631 Jupyter Notebook \u0623\u0648 Atom \u0623\u0648 \u062d\u062a\u0649 Notepad.<\/p>\n

\u062a\u0637\u0628\u064a\u0639 \u0627\u0644\u0628\u064a\u0627\u0646\u0627\u062a \u0627\u0644\u0648\u0635\u0641\u064a\u0629 \u0628\u0627\u0633\u062a\u062e\u062f\u0627\u0645 R: \u0627\u0644\u062a\u062d\u062f\u064a\u0627\u062a:<\/strong><\/p>\n

\u0627\u0633\u062a\u0636\u0627\u0641\u062a \u0627\u0644\u0645\u0643\u062a\u0628\u0629 \u0633\u0627\u0628\u0642\u064b\u0627 \u0627\u0644\u062a\u0631\u0627\u062b \u0648\u0627\u0644\u0628\u064a\u0627\u0646\u0627\u062a \u0648\u0627\u0644\u0645\u0633\u062a\u0648\u062f\u0639 \u0627\u0644\u062a\u0642\u0644\u064a\u062f\u064a \u0641\u064a DSpace \u0627\u0644\u0645\u0633\u062a\u062e\u062f\u0645 \u0644\u062f\u0628\u0644\u0646 \u0643\u0648\u0631\u060c \u0648\u0643\u0627\u0646 Qualified Dublin Core \u0645\u062e\u0637\u0637\u0646\u0627 \u0627\u0644\u0627\u0641\u062a\u0631\u0627\u0636\u064a. \u0648\u0645\u0646 \u0623\u0645\u062b\u0644\u0629 \u0645\u0624\u0647\u0644\u0627\u062a dc.contributor: author \u0648 advisor \u0648 committeemember. \u0648\u0639\u0646\u062f \u0627\u0644\u062a\u0631\u062d\u064a\u0644 \u0632\u0627\u062f \u0639\u062f\u062f\u0647\u0627 \u0639\u0644\u0649 \u0639\u0634\u0631\u064a\u0646\u060c \u0648\u0647\u0648 \u0645\u0627 \u0639\u064f\u062f \u063a\u064a\u0631 \u0645\u0633\u062a\u062f\u0627\u0645\u060c \u0641\u0642\u0631\u0631 \u0627\u0644\u0641\u0631\u064a\u0642 \u062a\u0628\u0646\u064a \u0625\u0631\u0634\u0627\u062f\u0627\u062a RDA \u0644\u0644\u0641\u0647\u0631\u0633\u0629 \u0627\u0644\u0648\u0635\u0641\u064a\u0629[3].<\/p>\n

\u0641\u0645\u062b\u0644\u064b\u0627 \u064a\u0638\u0647\u0631 \u0627\u0644\u0645\u0624\u0644\u0641 \u0641\u064a DSpace \u0628\u0635\u064a\u063a\u0629 dc.contributor.author Bright, Donald E. \u060c \u0648\u064a\u0635\u0628\u062d \u0641\u064a CONTENTdm: dc.creator Bright, Donald E., author . \u0648\u0645\u0639 \u0623\u0643\u062b\u0631 \u0645\u0646 90000 \u0633\u062c\u0644 \u0645\u0637\u0644\u0648\u0628 \u062a\u0646\u0638\u064a\u0641\u0647\u0627 \u0641\u064a \u0623\u0633\u0628\u0648\u0639\u064a\u0646\u060c \u0627\u0633\u062a\u062d\u0627\u0644 \u0627\u0644\u0639\u0645\u0644 \u0627\u0644\u064a\u062f\u0648\u064a. \u0648\u0645\u0646\u0639 \u0627\u0644\u062a\u0639\u0642\u064a\u062f \u0627\u0633\u062a\u062e\u062f\u0627\u0645 \u0628\u0631\u0646\u0627\u0645\u062c \u062c\u0627\u0647\u0632\u060c \u0641\u0627\u062e\u062a\u064a\u0631\u062a R \u0644\u0642\u062f\u0631\u062a\u0647\u0627 \u0639\u0644\u0649 \u0627\u0644\u0645\u0639\u0627\u0644\u062c\u0629.<\/p>\n

\u0627\u0644\u062d\u0644:<\/strong><\/p>\n

\u0635\u064f\u062f\u0631\u062a \u0628\u064a\u0627\u0646\u0627\u062a \u0643\u0644 \u0627\u0644\u0645\u062c\u0645\u0648\u0639\u0627\u062a \u0625\u0644\u0649 CSV \u060c \u062b\u0645 \u0642\u0631\u0623\u0647\u0627 \u0628\u0631\u0646\u0627\u0645\u062c R \u0648\u062d\u0648\u0644 dc.contributor.* \u0625\u0644\u0649 dc.creator \u060c \u0648\u062d\u064f\u062f\u062b\u062a \u0645\u062c\u0645\u0648\u0639\u0627\u062a DSpace \u0628\u0627\u0644\u0645\u0644\u0641\u0627\u062a \u0627\u0644\u062c\u062f\u064a\u062f\u0629\u060c \u062b\u0645 \u0646\u0642\u0644\u062a\u0647\u0627 OCLC \u0625\u0644\u0649 CONTENTdm.<\/p>\n

\u0643\u064a\u0641 \u064a\u0639\u0645\u0644 \u0627\u0644\u0628\u0631\u0646\u0627\u0645\u062c\u061f<\/p>\n

\u064a\u0642\u0631\u0623 \u0645\u0644\u0641 \u0627\u0644\u0645\u062c\u0645\u0648\u0639\u0629\u060c \u0648\u064a\u0646\u0634\u0626 \u0646\u0633\u062e\u0629\u060c \u0648\u064a\u0636\u064a\u0641 \u0639\u0645\u0648\u062f dc.creator \u0625\u0646 \u0644\u0645 \u064a\u0648\u062c\u062f. \u062b\u0645 \u064a\u0641\u062d\u0635 \u0627\u0644\u0635\u0641\u0648\u0641\u061b \u0641\u0639\u0646\u062f \u0627\u0644\u0639\u062b\u0648\u0631 \u0639\u0644\u0649 dc.contributor \u064a\u0639\u0627\u0644\u062c \u0627\u0644\u0642\u064a\u0645\u0629 \u0648\u064a\u0646\u0642\u0644\u0647\u0627 \u0625\u0644\u0649 creator \u0648\u064a\u0645\u062d\u0648 \u0627\u0644\u0623\u0635\u0644\u060c \u0648\u064a\u0648\u0627\u0635\u0644 \u062d\u062a\u0649 \u062c\u0645\u064a\u0639 \u0627\u0644\u0623\u0639\u0645\u062f\u0629 \u0648\u0627\u0644\u0635\u0641\u0648\u0641. \u062b\u0645 \u064a\u0643\u0631\u0631 \u0630\u0644\u0643 \u0644\u0645\u0644\u0641\u0627\u062a \u0627\u0644\u0645\u062c\u0645\u0648\u0639\u0627\u062a \u0641\u064a \u0627\u0644\u0645\u062c\u0644\u062f.<\/p>\n

\u0648\u0646\u064f\u0642\u0644\u062a \u0623\u0633\u0645\u0627\u0621 \u0627\u0644\u0645\u0624\u0647\u0644\u064a\u0646 \u062c\u0645\u064a\u0639\u064b\u0627\u060c \u0633\u0648\u0627\u0621 \u0645\u0624\u0644\u0641 \u0648\u0627\u062d\u062f \u0623\u0648 \u0639\u062f\u0629 \u0645\u0624\u0644\u0641\u064a\u0646 \u0628\u0623\u062f\u0648\u0627\u0631 \u0645\u062e\u062a\u0644\u0641\u0629. \u0648\u0643\u0627\u0646 author \u0627\u0644\u0623\u0635\u0639\u0628\u060c \u0644\u0623\u0646 DSpace \u064a\u0644\u062d\u0642 \u0628\u0627\u0644\u0642\u064a\u0645 \u0645\u0639\u0631\u0651\u0641\u0627\u062a UUID \u0627\u0644\u0639\u0627\u0644\u0645\u064a\u0629 \u0627\u0644\u0641\u0631\u064a\u062f\u0629[4]. \u0648\u0645\u062b\u0627\u0644\u0647\u0627 ff4d344e-a2c5-4bfc-8271-553b416db8f0. \u0648\u064a\u0638\u0647\u0631 \u0645\u062b\u0627\u0644 \u0627\u0644\u0634\u0643\u0644 1 \u0623\u0633\u0645\u0627\u0621 Albertson, Maurice L. \u0648 Birky-Kreutzer, Pauline \u0645\u0639 \u0645\u0639\u0631\u0651\u0641\u064a\u0647\u0645\u0627\u060c \u062b\u0645 Peace Corps(U.S.).<\/p>\n

\u0648\u0644\u0645 \u0646\u062c\u062f \u0622\u0646\u0630\u0627\u0643 \u0623\u062f\u0627\u0629 \u062a\u0646\u0638\u0641 \u0647\u0630\u0647 \u0627\u0644\u0642\u064a\u0645 \u0628\u0643\u0641\u0627\u0621\u0629\u060c \u0644\u0643\u0646\u0646\u0627 \u0644\u0627\u062d\u0638\u0646\u0627 \u0646\u0645\u0637\u064b\u0627: \u064a\u0628\u062f\u0623 \u0627\u0644\u062c\u0632\u0621 \u0627\u0644\u0645\u0636\u0627\u0641 \u0628\u0640:: \u062b\u0645 39 \u0623\u0648 41 \u0645\u062d\u0631\u0641\u064b\u0627 \u0623\u0628\u062c\u062f\u064a\u064b\u0627 \u0631\u0642\u0645\u064a\u064b\u0627\u060c \u0648\u062a\u0641\u0635\u0644 || \u0627\u0644\u0623\u0633\u0645\u0627\u0621 \u0627\u0644\u0645\u062a\u0639\u062f\u062f\u0629. \u0641\u064a\u0633\u0647\u0644 \u0627\u0633\u062a\u062e\u0631\u0627\u062c\u0647\u0627 \u0628\u0631\u0645\u062c\u064a\u064b\u0627 \u0648\u0625\u0644\u062d\u0627\u0642 \u062d\u0642\u0648\u0644 contributor \u0627\u0644\u0623\u062e\u0631\u0649. \u0648\u062a\u0635\u0628\u062d \u0627\u0644\u0646\u062a\u064a\u062c\u0629: Albertson, Maurice L., author||Birky-Kreutzer, Pauline, author||Peace Corps(U.S.), institution . \u0648\u064a\u0642\u0627\u0631\u0646 \u0627\u0644\u0634\u0643\u0644 1 \u0627\u0644\u0628\u064a\u0627\u0646\u0627\u062a \u0627\u0644\u0623\u0635\u0644\u064a\u0629 \u0648\u0627\u0644\u062c\u062f\u064a\u062f\u0629.<\/p>\n

\u062a\u0634\u063a\u064a\u0644 R \u0641\u064a RStudio:<\/strong><\/p>\n

\u0628\u0631\u0646\u0627\u0645\u062c R \u0645\u0644\u0641 \u0646\u0635\u064a \u064a\u0645\u0643\u0646 \u062a\u0634\u063a\u064a\u0644\u0647 \u0628\u0627\u0644\u0648\u0627\u062c\u0647\u0629 \u0623\u0648 \u0628\u0627\u0644\u0623\u0648\u0627\u0645\u0631. \u0648\u0627\u062e\u062a\u0631\u0646\u0627 RStudio \u060c \u0628\u064a\u0626\u0629 \u062a\u0637\u0648\u064a\u0631 \u0645\u062c\u0627\u0646\u064a\u0629 \u0645\u0641\u062a\u0648\u062d\u0629 \u062a\u062a\u064a\u062d \u0631\u0624\u064a\u0629 \u0627\u0644\u0631\u0633\u0648\u0645 \u0648\u0627\u0644\u062c\u062f\u0627\u0648\u0644 \u0648\u0627\u0644\u0634\u064a\u0641\u0631\u0629 \u0648\u0627\u0644\u0645\u062e\u0631\u062c\u0627\u062a \u0645\u0639\u064b\u0627[5]. \u0648\u064a\u0639\u0631\u0636 \u0627\u0644\u0634\u0643\u0644 2 \u0627\u0644\u0634\u064a\u0641\u0631\u0629 \u0623\u0639\u0644\u0649\u060c \u0648\u0627\u0644\u062a\u0646\u0641\u064a\u0630 \u0648\u0627\u0644\u0623\u062e\u0637\u0627\u0621 \u0648\u0627\u0644\u062a\u062d\u0630\u064a\u0631\u0627\u062a \u0648\u0627\u0644\u0637\u0628\u0627\u0639\u0629 \u0623\u0633\u0641\u0644.<\/p>\n

\u0623\u0645\u062b\u0644\u0629 \u0627\u0644\u0634\u064a\u0641\u0631\u0629:<\/strong><\/p>\n

\u062a\u062a\u0648\u0641\u0631 \u0648\u062d\u062f\u0627\u062a \u0643\u062b\u064a\u0631\u0629 \u0628\u062f\u0648\u0627\u0644 \u0645\u0641\u064a\u062f\u0629\u061b \u0648\u0627\u0633\u062a\u062e\u062f\u0645\u0646\u0627 sjmisc \u0648 stringr:<\/strong><\/p>\n

library(sjmisc)\r\nlibrary(stringr)<\/pre>\n
\u062a\u062d\u062f\u062f setwd \u0645\u062c\u0644\u062f \u0627\u0644\u0639\u0645\u0644 \u0644\u0644\u0645\u0644\u0641\u0627\u062a \u0627\u0644\u0623\u0635\u0644\u064a\u0629 \u0648\u0627\u0644\u062c\u062f\u064a\u062f\u0629\u060c \u0648\u062a\u062c\u0644\u0628 list.files \u0645\u062d\u062a\u0648\u064a\u0627\u062a\u0647:<\/strong><\/p>\n
setwd(\"~\/Desktop\/R\/batch1\") \r\nfile_list <- list.files()<\/pre>\n
\u0648\u062a\u0642\u0631\u0623 \u0627\u0644\u0623\u0648\u0627\u0645\u0631 \u0627\u0644\u062a\u0627\u0644\u064a\u0629 CSV:<\/strong><\/p>\n
orgdata <- read.csv(file_list[[Z]])\r\nnewdata <- orgdata[,names(orgdata)!=\"\"]<\/pre>\n
\u0648\u062a\u0639\u0631\u0651\u0641 \u0647\u0630\u0647 \u0627\u0644\u062f\u0627\u0644\u0629 \u062a\u0639\u062f\u064a\u0644 \u0627\u0644\u0623\u0633\u0645\u0627\u0621:<\/strong><\/p>\n
add_new_authors <- function(authorList, column, title){\r\n    for (c in 1:total_rows){ \u2026 }<\/pre>\n
\u0648\u062a\u062d\u062f\u062f gregexpr \u0645\u0648\u0627\u0636\u0639::[6]:<\/strong><\/p>\n
positions <-  gregexpr(pattern='::', org_names, ignore.case=FALSE)<\/pre>\n
\u062b\u0645 \u062a\u0633\u062a\u062e\u0631\u062c substr \u0627\u0633\u0645 \u0627\u0644\u0645\u0624\u0644\u0641:<\/strong><\/p>\n
authorname <- substr(org_names,name_first_char, name_last_char)<\/pre>\n
\u0648\u062a\u0644\u062d\u0642 paste0 \u0648\u0635\u0641 author \u0628\u0627\u0644\u0627\u0633\u0645:<\/strong><\/p>\n
authorList[[c]] <- paste0(authorname,\", author\")<\/pre>\n
\u0648\u0644\u0633\u0628\u0628 \u0644\u0645 \u0646\u0639\u0631\u0641\u0647\u060c \u064a\u0646\u0634\u0626 DSpace \u0623\u062d\u064a\u0627\u0646\u064b\u0627 \u0623\u0639\u0645\u062f\u0629 \u0628\u0623\u0642\u0648\u0627\u0633 []\u060c \u0641\u064a\u0638\u0647\u0631 author \u0648\/\u0623\u0648 author[]. \u0648\u0644\u0644\u062a\u062d\u0642\u0642 \u0646\u0633\u062a\u062e\u062f\u0645 %in% \u0627\u0644\u0630\u064a \u064a\u062e\u062a\u0628\u0631 \u0627\u0646\u062a\u0645\u0627\u0621 \u0639\u0646\u0635\u0631 \u0644\u0645\u062a\u062c\u0647 \u0623\u0648 DataFrame. \u0648\u062a\u0642\u0631\u0623 R \u0627\u0644\u0623\u0642\u0648\u0627\u0633 \u0646\u0642\u0637\u062a\u064a\u0646\u061b \u0644\u0630\u0627 \u0646\u0641\u062d\u0635 dc.contributor.author..\u060c \u0648\u0646\u0633\u062a\u062f\u0639\u064a add_new_authors \u0644\u0625\u0646\u0634\u0627\u0621 creator \u0639\u0646\u062f \u0648\u062c\u0648\u062f\u0647\u0627:<\/p>\n
if(\"dc.contributor.author\" %in% colnames(newdata))\r\n  {  cList <- add_new_authors(cList, newdata$dc.contributor.author,\"author\")\r\n     newdata$dc.contributor.author <- \"\"\r\n  }\r\n  if(\"dc.contributor.author..\" %in% colnames(newdata))\r\n  {  cList <- add_new_authors(cList, newdata$dc.contributor.author..,\"author\")\r\n     newdata$dc.contributor.author.. <- \"\"\r\n  }<\/pre>\n
\u0648\u0628\u0639\u062f \u062c\u0645\u0639 \u0627\u0644\u0628\u064a\u0627\u0646\u0627\u062a\u060c \u062a\u0643\u062a\u0628 write.csv \u0645\u0644\u0641\u064b\u0627 \u062c\u062f\u064a\u062f\u064b\u0627 \u0628\u0628\u0627\u062f\u0626\u0629 creators-:<\/strong><\/p>\n
newFileName <- paste0(\"creators-\",file_list[[Z]]) \r\nwrite.csv(newdata, file = newFileName, row.names = FALSE)<\/pre>\n
\u0627\u0644\u062a\u062d\u0633\u064a\u0646\u0627\u062a:<\/strong><\/p>\n
\u0643\u0627\u0646 \u0647\u0630\u0627 \u0623\u0648\u0644 \u0628\u0631\u0646\u0627\u0645\u062c \u0644\u0644\u0645\u0624\u0644\u0641\u0629 \u0628\u0644\u063a\u0629 R \u060c \u0648\u0644\u064a\u0633 \u0645\u062b\u0627\u0644\u064a\u064b\u0627\u060c \u0648\u064a\u0645\u0643\u0646 \u062a\u062d\u0633\u064a\u0646 \u0645\u0639\u0627\u0644\u062c\u0629 \u0627\u0644\u0623\u062e\u0637\u0627\u0621 \u062e\u0635\u0648\u0635\u064b\u0627. \u0644\u0643\u0646\u0647 \u0631\u063a\u0645 \u0646\u0642\u0635\u0647 \u0639\u0627\u0644\u062c \u0622\u0644\u0627\u0641 \u0627\u0644\u0642\u064a\u0645 \u0628\u062b\u0648\u0627\u0646\u064d\u060c \u0648\u0633\u0627\u0639\u062f\u0646\u0627 \u0639\u0644\u0649 \u0627\u0644\u0648\u0641\u0627\u0621 \u0628\u0645\u0648\u0639\u062f \u0627\u0644\u062a\u0631\u062d\u064a\u0644.<\/p>\n
\u062a\u063a\u064a\u064a\u0631 \u0623\u062d\u062c\u0627\u0645 \u0627\u0644\u0635\u0648\u0631 \u0628\u0628\u0627\u064a\u062b\u0648\u0646:<\/strong><\/p>\n
\u064a\u0648\u0641\u0631 CONTENTdm \u0645\u0644\u062d\u0642 OCR \u0641\u064a Project Client \u0644\u062a\u0648\u0644\u064a\u062f \u062a\u0641\u0631\u064a\u063a\u0627\u062a \u0627\u0644\u0635\u0648\u0631[7]\u060c \u0628\u062a\u0631\u062e\u064a\u0635 \u0645\u0646\u0641\u0635\u0644 \u064a\u062a\u064a\u062d 10000 \u0635\u0641\u062d\u0629 \u0634\u0647\u0631\u064a\u064b\u0627 \u0641\u0642\u0637. \u0648\u0625\u0630\u0627 \u062a\u062c\u0627\u0648\u0632\u062a \u0627\u0644\u0635\u0648\u0631\u0629 8.27\u00d711.69 \u0628\u0648\u0635\u0629\u060c \u062a\u064f\u062d\u0633\u0628 \u0635\u0641\u062d\u062a\u064a\u0646 \u0623\u0648 \u0623\u0643\u062b\u0631 \u062d\u0633\u0628 \u0627\u0644\u062d\u062c\u0645.<\/p>\n
\u0648\u0643\u0627\u0646\u062a \u0645\u0633\u0648\u062d A4 \u0630\u0627\u062a \u0627\u0644\u062d\u0648\u0627\u0641 \u0627\u0644\u0632\u0627\u0626\u062f\u0629 \u062a\u062a\u062c\u0627\u0648\u0632 \u0627\u0644\u062d\u062f\u060c \u0641\u062a\u0633\u062a\u0646\u0632\u0641 \u0627\u0644\u062d\u0635\u0629 \u0648\u062a\u0624\u062e\u0631 \u0627\u0644\u0625\u062f\u062e\u0627\u0644. \u0648\u0631\u063a\u0645 \u062a\u063a\u064a\u064a\u0631 Photoshop \u0648 Bridge \u0627\u0644\u0623\u062d\u062c\u0627\u0645 \u062f\u0641\u0639\u0629\u060c \u0644\u0627 \u064a\u0639\u0627\u0644\u062c\u0627\u0646 \u0627\u0644\u0627\u062a\u062c\u0627\u0647 \u0648\u0645\u062c\u0644\u062f\u0627\u062a \u0645\u062a\u0639\u062f\u062f\u0629 \u0628\u0627\u0644\u0637\u0631\u064a\u0642\u0629 \u0627\u0644\u0645\u0637\u0644\u0648\u0628\u0629. \u0648\u064a\u0639\u0645\u0644 Lightroom \u0628\u0627\u0644\u0636\u0644\u0639 \u0627\u0644\u0623\u0637\u0648\u0644 \u0644\u0643\u0646\u0647 \u064a\u062a\u0637\u0644\u0628 \u0627\u0644\u0627\u0633\u062a\u064a\u0631\u0627\u062f \u0644\u0645\u0643\u062a\u0628\u062a\u0647\u060c \u0648\u0647\u0648 \u0648\u0642\u062a \u0625\u0636\u0627\u0641\u064a. \u0644\u0630\u0644\u0643 \u0623\u0646\u0634\u0623\u0646\u0627 \u0628\u0631\u0646\u0627\u0645\u062c\u064b\u0627 \u0628\u0633\u064a\u0637\u064b\u0627 \u064a\u0631\u0627\u0639\u064a \u0627\u0644\u0627\u062a\u062c\u0627\u0647\u060c \u0648\u064a\u0639\u0627\u0644\u062c \u0627\u0644\u0645\u062c\u0644\u062f\u0627\u062a\u060c \u0648\u064a\u0646\u0634\u0626 \u0645\u062c\u0644\u062f\u0627\u062a \u0644\u0644\u0646\u062a\u0627\u0626\u062c.<\/p>\n
\u0627\u0644\u0634\u064a\u0641\u0631\u0629 \u0627\u0644\u0628\u0634\u0631\u064a\u0629 \u0648\u0627\u0644\u0645\u0648\u0644\u062f\u0629 \u0628\u0627\u0644\u0630\u0643\u0627\u0621 \u0627\u0644\u0627\u0635\u0637\u0646\u0627\u0639\u064a:<\/strong><\/p>\n
\u062c\u0631\u0628\u0646\u0627 \u0644\u0627\u062d\u0642\u064b\u0627 ChatGPT \u0644\u0644\u0645\u0647\u0645\u0629 \u0646\u0641\u0633\u0647\u0627\u060c \u0648\u0627\u062d\u062a\u062c\u0646\u0627 \u0625\u0644\u0649 \u062a\u0639\u062f\u064a\u0644 \u0627\u0644\u0637\u0644\u0628 \u0645\u0631\u0627\u062a \u062d\u062a\u0649 \u062d\u0642\u0642 \u0627\u0644\u0648\u0638\u064a\u0641\u0629 \u0648\u0627\u0644\u062a\u062c\u0631\u0628\u0629 \u0627\u0644\u0645\u0637\u0644\u0648\u0628\u062a\u064a\u0646\u060c \u0648\u0646\u0642\u0644 \u0633\u0637\u0631 \u0644\u062a\u062d\u0633\u064a\u0646 \u0627\u0644\u0643\u0641\u0627\u0621\u0629. \u0648\u0643\u0627\u0646 \u0627\u0644\u0637\u0644\u0628: \u0627\u0643\u062a\u0628 \u0628\u0631\u0646\u0627\u0645\u062c \u0628\u0627\u064a\u062b\u0648\u0646 \u0644\u062a\u063a\u064a\u064a\u0631 \u062d\u062c\u0645 \u0627\u0644\u0635\u0648\u0631 \u0648\u0641\u0642 \u0627\u0644\u0636\u0644\u0639 \u0627\u0644\u0623\u0637\u0648\u0644\u061b \u0627\u0637\u0644\u0628 \u0645\u062c\u0644\u062f \u0627\u0644\u0623\u0635\u0644 \u0627\u0644\u0630\u064a \u0642\u062f \u064a\u062a\u0636\u0645\u0646 \u0645\u062c\u0644\u062f\u0627\u062a \u0641\u0631\u0639\u064a\u0629\u061b \u0648\u0627\u0633\u0645 \u0645\u062c\u0644\u062f \u062c\u0630\u0631\u064a \u0644\u0644\u0646\u062a\u0627\u0626\u062c \u0628\u062c\u0648\u0627\u0631 \u0627\u0644\u0623\u0635\u0644\u061b \u0648\u062d\u0627\u0641\u0638 \u0639\u0644\u0649 \u0628\u0646\u064a\u0629 \u0627\u0644\u0645\u062c\u0644\u062f\u0627\u062a \u0648\u0623\u0633\u0645\u0627\u0626\u0647\u0627\u061b \u0648\u0627\u0642\u0628\u0644 JPG \u0648 JPEG \u0648 PNG \u0648 TIF \u0648 TIFF \u0648\u0627\u062d\u0641\u0638 JPG \u061b \u0648\u0627\u0637\u0644\u0628 \u0627\u0644\u062d\u062c\u0645 \u0628\u0627\u0644\u0628\u0648\u0635\u0629\u060c \u0648\u0627\u062c\u0639\u0644 \u0627\u0644\u062f\u0642\u0629 300 \u0646\u0642\u0637\u0629\/\u0628\u0648\u0635\u0629 \u0648\u0627\u0644\u0636\u0644\u0639 \u0627\u0644\u0623\u0637\u0648\u0644 \u0628\u0627\u0644\u0642\u064a\u0645\u0629 \u0627\u0644\u0645\u062f\u062e\u0644\u0629.<\/p>\n
\u0648\u0627\u0643\u062a\u0634\u0641\u0646\u0627 \u0623\u0646\u0647 \u062d\u062a\u0649 \u0625\u0646 \u0623\u062e\u0641\u0642\u062a \u0627\u0644\u0645\u062d\u0627\u0648\u0644\u0629 \u0627\u0644\u0623\u0648\u0644\u0649\u060c \u064a\u0645\u0643\u0646 \u0627\u0644\u0631\u062c\u0648\u0639 \u0625\u0644\u0649 \u0627\u0644\u0634\u064a\u0641\u0631\u0629 \u0627\u0644\u0645\u0648\u0644\u062f\u0629 \u0648\u062a\u0639\u062f\u064a\u0644\u0647\u0627 \u0644\u0644\u0648\u0635\u0648\u0644 \u0628\u0643\u0641\u0627\u0621\u0629 \u0623\u0643\u0628\u0631.<\/p>\n
\u0627\u0644\u0634\u064a\u0641\u0631\u0629 \u0627\u0644\u062a\u064a \u0643\u062a\u0628\u0647\u0627 \u0627\u0644\u0625\u0646\u0633\u0627\u0646:<\/strong><\/p>\n
import os\r\nfrom PIL import Image, ImageOps\r\nImage.MAX_IMAGE_PIXELS = None<\/pre>\n
# Prompt for inputs
\norg_dir = input(‘Input the orginal folder name.’)
\nprint(org_dir)
\nresized_dir = input(‘Input a folder name for resized images.’)
\nprint(resized_dir)
\nos.mkdir(f'{resized_dir}’)
\ndir_list = os.listdir(org_dir)
\ninput_long_side = input(‘Input long side length in inches. (e.g. 8,9,10 or 11): ‘)
\nlong_side = int(input_long_side)
\nlong_side_pixels = long_side * 300<\/p>\n
# Batch process. Will process a directory with sub-directories.
\nfor subDir in dir_list:
\n    print(‘Now processing folder: ‘, subDir, ‘please wait…’)
\n    os.mkdir(f'{resized_dir}\/{subDir}’)
\n    og = f'{org_dir}\/{subDir}’
\n    orgScans = os.listdir(og)<\/p>\n
for orgImage in orgScans:
\n        orgFileName = f'{org_dir}\/{subDir}\/{orgImage}’
\n        newFileName = f'{resized_dir}\/{subDir}\/{orgImage}’
\n        if(orgImage.startswith(‘.’)):
\n            print(‘Ignore a hidden file: ‘, orgFileName, ‘still processing files. Please wait…’)
\n        elif(orgImage == ‘Thumbs.db’):
\n            print(‘Ignore file: ‘, orgFileName, ‘still processing files. Please wait…’)
\n        else:
\n            newJPG = newFileName.split(“.”)
\n            resizedJPG = newJPG[0] + “.jpg”
\n            img = Image.open(orgFileName)
\n            width,height = img.size
\n            area = width * height<\/p>\n
if (area >= 89478485):
\n                print(‘File: ‘, orgFileName, ‘exceeds pixel limitation and would not be converted. Please convert it manually.’)
\n            else:
\n                rgb_image = img.convert(‘RGB’)
\n                resizedImage = ImageOps.contain(rgb_image, (long_side_pixels,long_side_pixels))
\n                resizedImage.save(resizedJPG, dpi=(300, 300))<\/p>\n
print(‘Total processed ‘, len(dir_list), ‘folders.’)<\/p>\n
\u0627\u0644\u0634\u064a\u0641\u0631\u0629 \u0627\u0644\u0645\u0648\u0644\u062f\u0629 \u0622\u0644\u064a\u064b\u0627:<\/strong><\/p>\n
import os\r\nfrom PIL import Image<\/pre>\n
# Prompt for original directory
\norig_dir = input(“Enter the path of the directory containing original images to be resized: “)<\/p>\n
# Prompt for root folder name for resized images
\nroot_folder_name = input(“Enter the name of the root folder to hold all resized images: “)
\nroot_folder_path = os.path.join(os.path.dirname(orig_dir), root_folder_name)
\nlong_side_inches = float(input(“Enter the size in inches for the long side of a resized image: “))<\/p>\n
# Create root folder if it doesn’t already exist
\nif not os.path.exists(root_folder_path):
\n    os.mkdir(root_folder_path)<\/p>\n
# Walk through the original directory and its subdirectories
\nfor dirpath, dirnames, filenames in os.walk(orig_dir):
\n    # Create corresponding subdirectories in the root folder
\n    subfolder_path = os.path.join(root_folder_path, os.path.relpath(dirpath, orig_dir))
\n    if not os.path.exists(subfolder_path):
\n        os.mkdir(subfolder_path)<\/p>\n
# Loop through image files in current directory
\n    for filename in filenames:
\n        # Check if file is an image
\n        if filename.lower().endswith((‘.jpg’, ‘.jpeg’, ‘.png’, ‘.tif’, ‘.tiff’)):
\n            # Open image and get dimensions
\n            filepath = os.path.join(dirpath, filename)
\n            img = Image.open(filepath)
\n            width, height = img.size<\/p>\n
# Determine new dimensions based on user input and maintain aspect ratio
\n            if width >= height:
\n                new_width = int(long_side_inches * 300)
\n                new_height = int(height * new_width \/ width)
\n            else:
\n                new_height = int(long_side_inches * 300)
\n                new_width = int(width * new_height \/ height)<\/p>\n
# Resize image and save as .jpg
\n            resized_img = img.resize((new_width, new_height))
\n            new_filepath = os.path.join(subfolder_path, filename)
\n            new_filepath = os.path.splitext(new_filepath)[0] + ‘.jpg’
\n            resized_img.save(new_filepath, format=’JPEG’)<\/p>\n
\u0645\u0639\u0627\u0644\u062c\u0629 \u0627\u0644\u0645\u0633\u062a\u0646\u062f\u0627\u062a \u0627\u0644\u0645\u0645\u0633\u0648\u062d\u0629 \u0648\u0627\u0644\u062a\u0641\u0631\u064a\u063a\u0627\u062a:<\/strong><\/p>\n
\u064a\u062d\u0648\u064a \u0627\u0644\u0645\u0633\u062a\u0648\u062f\u0639 \u064a\u0648\u0645\u064a\u0627\u062a \u0648\u0631\u0633\u0627\u0626\u0644 \u0634\u062e\u0635\u064a\u0629 \u0643\u062b\u064a\u0631\u0629 \u0645\u0643\u062a\u0648\u0628\u0629 \u0628\u062e\u0637 \u0627\u0644\u064a\u062f\u060c \u0644\u0627 \u062a\u0646\u0627\u0633\u0628 OCR \u061b \u0641\u0641\u0631\u063a\u0647\u0627 \u0645\u062a\u0637\u0648\u0639\u0648\u0646 \u0623\u0648 \u0637\u0644\u0627\u0628. \u0648\u0623\u064f\u062f\u062e\u0644\u062a \u0627\u0644\u0645\u0633\u062a\u0646\u062f\u0627\u062a \u0648\u062a\u0641\u0631\u064a\u063a\u0627\u062a\u0647\u0627 \u0625\u0644\u0649 DSpace \u0645\u0644\u0641\u0627\u062a PDF \u060c \u0641\u064a\u0646\u0632\u0644 \u0627\u0644\u0645\u0633\u062a\u0641\u064a\u062f \u0643\u0644\u064a\u0647\u0645\u0627 \u0648\u064a\u0639\u0631\u0636\u0647\u0645\u0627 \u0628\u0646\u0627\u0641\u0630\u062a\u064a\u0646 \u0645\u062a\u062c\u0627\u0648\u0631\u062a\u064a\u0646. \u0648\u064a\u062a\u064a\u062d CONTENTdm \u0639\u0631\u0636 \u0627\u0644\u0646\u0635 \u0628\u062c\u0648\u0627\u0631 \u0627\u0644\u0635\u0648\u0631\u0629\u060c \u0648\u0647\u0648 \u0623\u0633\u0647\u0644 \u0643\u062b\u064a\u0631\u064b\u0627\u060c \u0643\u0645\u0627 \u0641\u064a \u0627\u0644\u0634\u0643\u0644 3.<\/p>\n
\u0648\u0627\u062e\u062a\u0631\u0646\u0627 \u0625\u062f\u062e\u0627\u0644 \u0643\u0627\u0626\u0646 \u0645\u0631\u0643\u0628 \u0628\u0628\u0646\u064a\u0629 \u0645\u062c\u0644\u062f\u0627\u062a. \u0641\u0644\u0643\u0644 \u0639\u0646\u0635\u0631 \u0645\u062c\u0644\u062f \u064a\u062d\u0648\u064a \u0645\u062c\u0644\u062f \u0627\u0644\u0635\u0648\u0631\u060c \u0648\u0645\u062c\u0644\u062f \u062a\u0641\u0631\u064a\u063a\u0627\u062a TXT \u0644\u0643\u0644 \u0635\u0641\u062d\u0629\u060c \u0648\u0645\u0644\u0641 \u0628\u064a\u0627\u0646\u0627\u062a \u0648\u0635\u0641\u064a\u0629 TXT \u0644\u0644\u0639\u0646\u0635\u0631.<\/p>\n
\u0627\u0644\u0645\u0644\u0641\u0627\u062a \u0627\u0644\u0623\u0635\u0644\u064a\u0629:<\/strong><\/p>\n
\u0644\u0643\u0644 \u0633\u062c\u0644 PDF \u0648\u062a\u0641\u0631\u064a\u063a TXT \u0648\u0645\u0644\u0641 CSV \u0644\u0648\u0635\u0641 \u0627\u0644\u0645\u062c\u0645\u0648\u0639\u0629 \u0635\u0627\u062f\u0631 \u0645\u0646 DSpace. \u0648\u0627\u0644\u0623\u062e\u064a\u0631 \u064a\u062d\u0648\u064a \u0628\u064a\u0627\u0646\u0627\u062a \u0639\u0634\u0631\u0627\u062a \u0623\u0648 \u0622\u0644\u0627\u0641 \u0627\u0644\u0633\u062c\u0644\u0627\u062a \u0627\u0644\u0623\u062e\u0631\u0649\u060c \u0643\u0645\u0627 \u064a\u0648\u0636\u062d \u0627\u0644\u0634\u0643\u0644 4.<\/p>\n
\u0627\u0644\u0639\u0645\u0644\u064a\u0629 \u0627\u0644\u064a\u062f\u0648\u064a\u0629:<\/strong><\/p>\n
\u062a\u062a\u0637\u0644\u0628 \u0625\u0646\u0634\u0627\u0621 \u062b\u0644\u0627\u062b\u0629 \u0645\u062c\u0644\u062f\u0627\u062a\u060c \u0648\u062a\u0635\u062f\u064a\u0631 PDF \u0625\u0644\u0649 \u0635\u0648\u0631\u060c \u0648\u0646\u0633\u062e \u0627\u0644\u062a\u0641\u0631\u064a\u063a \u0648\u0644\u0635\u0642\u0647 \u0641\u064a \u0645\u0644\u0641\u0627\u062a \u0635\u0641\u062d\u0627\u062a\u060c \u0648\u0647\u064a \u0623\u0643\u062b\u0631 \u0627\u0644\u062e\u0637\u0648\u0627\u062a \u0627\u0633\u062a\u0647\u0644\u0627\u0643\u064b\u0627 \u0644\u0644\u0648\u0642\u062a \u0643\u0645\u0627 \u0641\u064a \u0627\u0644\u0634\u0643\u0644 5. \u062b\u0645 \u0627\u0644\u0639\u062b\u0648\u0631 \u0639\u0644\u0649 \u0627\u0644\u0635\u0641\u0648\u0641 \u0627\u0644\u062b\u0644\u0627\u062b\u0629 \u0627\u0644\u062e\u0627\u0635\u0629 \u0628\u0627\u0644\u0639\u0646\u0635\u0631 \u0641\u064a \u0648\u0635\u0641 \u0627\u0644\u0645\u062c\u0645\u0648\u0639\u0629\u060c \u0648\u062f\u0645\u062c\u0647\u0627 \u0641\u064a \u0635\u0641 \u0648\u0625\u0646\u0634\u0627\u0621 TXT \u0645\u0641\u0635\u0648\u0644 \u0628\u0639\u0644\u0627\u0645\u0627\u062a \u0627\u0644\u062c\u062f\u0648\u0644\u0629\u060c \u0643\u0645\u0627 \u0641\u064a \u0627\u0644\u0634\u0643\u0644 6. \u0648\u0627\u0644\u0639\u0645\u0644 \u0637\u0648\u064a\u0644 \u0648\u0634\u062f\u064a\u062f \u0627\u0644\u062a\u0639\u0631\u0636 \u0644\u0644\u0623\u062e\u0637\u0627\u0621 \u0627\u0644\u062a\u064a \u062a\u0641\u0634\u0644 \u0627\u0644\u0625\u062f\u062e\u0627\u0644.<\/p>\n
\u0627\u0644\u0639\u0645\u0644\u064a\u0629 \u0627\u0644\u0628\u0631\u0645\u062c\u064a\u0629:<\/strong><\/p>\n
\u0623\u062a\u0645\u062a\u0646\u0627 \u0627\u0644\u062e\u0637\u0648\u0627\u062a \u0644\u0645\u0639\u0627\u0644\u062c\u0629 \u0639\u062f\u0629 \u0639\u0646\u0627\u0635\u0631\u060c \u0628\u0645\u062f\u062e\u0644\u0627\u062a \u062b\u0644\u0627\u062b\u0629: \u0645\u062c\u0644\u062f PDF \u060c \u0648\u0645\u062c\u0644\u062f \u0627\u0644\u062a\u0641\u0631\u064a\u063a\u0627\u062a \u0627\u0644\u0645\u0642\u0627\u0628\u0644\u0629 \u063a\u064a\u0631 \u0627\u0644\u0645\u0642\u0633\u0645\u0629 \u0625\u0644\u0649 \u0635\u0641\u062d\u0627\u062a\u060c \u0648 CSV \u0644\u0648\u0635\u0641 \u0627\u0644\u0645\u062c\u0645\u0648\u0639\u0629. \u0648\u064a\u0628\u064a\u0646 \u0627\u0644\u0634\u0643\u0644 7 \u0623\u0645\u0631 \u0627\u0644\u062a\u0634\u063a\u064a\u0644.<\/p>\n
\u0641\u064a\u0646\u0634\u0626 \u0627\u0644\u0628\u0631\u0646\u0627\u0645\u062c \u0645\u062c\u0644\u062f \u0625\u062f\u062e\u0627\u0644 \u062c\u0645\u0627\u0639\u064a \u0628\u0645\u062c\u0644\u062f\u0627\u062a \u0627\u0644\u0643\u0627\u0626\u0646\u0627\u062a\u060c \u0648\u064a\u0635\u062f\u0631 PDF \u0625\u0644\u0649 \u0645\u062c\u0644\u062f\u0627\u062a scans \u060c \u0648\u064a\u0642\u0631\u0623 \u0627\u0644\u062a\u0641\u0631\u064a\u063a \u0648\u064a\u0642\u0633\u0645\u0647 \u0625\u0644\u0649 TXT \u0644\u0644\u0635\u0641\u062d\u0627\u062a \u0628\u0623\u0633\u0645\u0627\u0621 \u0635\u0648\u0631\u0647\u0627\u060c \u0648\u064a\u0633\u062a\u062e\u0631\u062c \u0627\u0644\u0648\u0635\u0641 \u0627\u0644\u0641\u0631\u062f\u064a \u0645\u0646 \u0645\u0644\u0641 \u0627\u0644\u0645\u062c\u0645\u0648\u0639\u0629. \u0648\u064a\u0642\u0627\u0631\u0646 \u0627\u0644\u0634\u0643\u0644 \u0627\u0644\u062a\u0627\u0644\u064a \u0645\u0644\u0641\u0627\u062a \u0627\u0644\u0628\u062f\u0627\u064a\u0629 \u0628\u0627\u0644\u0645\u062e\u0631\u062c\u0627\u062a.<\/p>\n
\u0627\u0633\u062a\u064a\u0631\u0627\u062f \u0627\u0644\u0648\u062d\u062f\u0627\u062a:<\/strong><\/p>\n
\u0627\u0644\u0648\u062d\u062f\u0629 \u0645\u0643\u062a\u0628\u0629 \u0634\u064a\u0641\u0631\u0629 \u0628\u062f\u0648\u0627\u0644 \u0642\u0627\u0628\u0644\u0629 \u0644\u0644\u0627\u0633\u062a\u062e\u062f\u0627\u0645\u060c \u0648\u0627\u0633\u062a\u062e\u062f\u0645\u0646\u0627:<\/strong><\/p>\n
import os\r\nimport csv\r\nimport pandas as pd\r\nfrom pdf2image import convert_from_path<\/pre>\n
\u0627\u0644\u0645\u062f\u062e\u0644\u0627\u062a \u0648\u0627\u0644\u0645\u062c\u0644\u062f\u0627\u062a \u0627\u0644\u062c\u062f\u064a\u062f\u0629:<\/strong><\/p>\n
\u062a\u0623\u062e\u0630 \u0627\u0644\u0634\u064a\u0641\u0631\u0629 \u0627\u0644\u0645\u062f\u062e\u0644\u0627\u062a \u0627\u0644\u062b\u0644\u0627\u062b\u0629\u060c \u0648\u062a\u0639\u062b\u0631 \u0639\u0644\u0649 PDF \u060c \u0648\u062a\u0646\u0634\u0626 BatchIngest \u0644\u062d\u0641\u0638 \u0627\u0644\u0643\u0627\u0626\u0646\u0627\u062a:<\/strong><\/p>\n
pDir = input('Input a directory with original PDFs:')\r\norgTransDir = input('Input a directory with original transcript .txt files:')\r\norgMetadata = input('Input the master metadata file name in csv format:')\r\ndir_list = os.listdir(pDir)\r\nsubDir = \"BatchIngest\"\r\nos.mkdir(subDir)<\/pre>\n
\u0648\u062a\u0646\u0634\u0626 \u062d\u0644\u0642\u0629 \u0644\u0643\u0644 PDF \u0645\u062c\u0644\u062f\u064b\u0627 \u0628\u0627\u0633\u0645\u0647\u060c \u062f\u0627\u062e\u0644\u0647 \u0645\u062c\u0644\u062f \u0627\u0644\u0635\u0648\u0631 \u0648\u0622\u062e\u0631 \u0644\u0644\u0646\u0635\u0648\u0635:<\/strong><\/p>\n
for file in dir_list:\r\ny = file.strip(\".pdf\")\r\nos.mkdir(f'{subDir}\/{y}')\r\nos.mkdir(f'{subDir}\/{y}\/scans')\r\nos.mkdir(f'{subDir}\/{y}\/transcripts')<\/pre>\n
\u062a\u062d\u0648\u064a\u0644 PDF \u0625\u0644\u0649 JPG:<\/strong><\/p>\n
\u064a\u0644\u0632\u0645 pdf2image \u0644\u062a\u062d\u0648\u064a\u0644 \u0627\u0644\u0645\u0644\u0641 \u0625\u0644\u0649 \u0643\u0627\u0626\u0646 PIL \u060c \u0648 Poppler \u0644\u0642\u0631\u0627\u0621\u0629 PDF \u0648\u0639\u0631\u0636\u0647 \u0648\u0645\u0639\u0627\u0644\u062c\u062a\u0647. \u0648\u064a\u062d\u062a\u0627\u062c \u0645\u0633\u062a\u062e\u062f\u0645 \u0648\u064a\u0646\u062f\u0648\u0632 \u0625\u0644\u0649 \u0628\u0646\u0627\u0626\u0647 \u0623\u0648 \u062a\u0646\u0632\u064a\u0644\u0647[8]. \u0648\u0627\u0633\u062a\u062e\u062f\u0645\u0646\u0627 \u0646\u0633\u062e\u0629 \u0645\u0646 https:\/\/github.com\/oschwartz10612\/poppler-windows\/releases\/ \u0648\u0641\u0643\u0643\u0646\u0627\u0647\u0627 \u0641\u064a \u062c\u0630\u0631 C. \u0648\u064a\u0631\u062f \u0634\u0631\u062d \u0627\u0644\u062a\u062b\u0628\u064a\u062a \u0641\u064a https:\/\/pdf2image.readthedocs.io\/en\/latest\/installation.html \u060c \u0648\u062f\u0644\u064a\u0644 \u0627\u0644\u062a\u062d\u0648\u064a\u0644 \u0641\u064a https:\/\/www.geeksforgeeks.org\/convert-pdf-to-image-using-python\/ . \u0648\u0623\u0636\u0641\u0646\u0627:<\/p>\n
from pdf2image import convert_from_path\r\npoppath = r\"C:\\poppler-22.12.0\\Library\\bin\"<\/pre>\n
\u0648\u062a\u0633\u062a\u062e\u062f\u0645 pdftoimages \u0627\u0644\u062f\u0627\u0644\u0629 convert_from_path \u0644\u0644\u062a\u062d\u0648\u064a\u0644\u060c \u0648 zfill(4) \u0644\u062a\u0633\u0645\u064a\u0629 \u0645\u062a\u0648\u0627\u0641\u0642\u0629 \u0645\u0639 \u0645\u0639\u064a\u0627\u0631 \u0627\u0644\u062c\u0627\u0645\u0639\u0629: _page_0015.jpg \u0628\u062f\u0644 _page_15.jpg.<\/p>\n
def pdftoimages(pdfDir, pdfFile, imgDir):   # Omitted code\r\n  \t\t images = convert_from_path(pdf_file_name, poppler_path=poppath)\r\n  \t  for i in range(len(images)):   # Omitted code\r\nimages[i].save(f'{imgDir}\/{file_name_preceeding}_page_' + str(j).zfill(4)+'.jpg', 'JPEG')<\/pre>\n
\u062a\u0648\u0644\u064a\u062f \u0645\u0644\u0641\u0627\u062a \u0627\u0644\u062a\u0641\u0631\u064a\u063a:<\/strong><\/p>\n
\u0644\u0643\u0644 PDF \u062a\u0641\u0631\u064a\u063a \u0645\u0642\u0627\u0628\u0644. \u0648\u0627\u062a\u0641\u0642\u0646\u0627 \u0639\u0644\u0649 \u0623\u0631\u0628\u0639\u0629 \u0623\u0633\u0637\u0631 \u0641\u0627\u0631\u063a\u0629 \u0645\u062a\u062a\u0627\u0628\u0639\u0629 \u0639\u0644\u0627\u0645\u0629\u064b \u0644\u0635\u0641\u062d\u0629 \u062c\u062f\u064a\u062f\u0629. \u064a\u0642\u0631\u0623 \u0627\u0644\u0628\u0631\u0646\u0627\u0645\u062c \u0633\u0637\u0631\u064b\u0627 \u0633\u0637\u0631\u064b\u0627\u060c \u0648\u064a\u062c\u0645\u0639 \u0627\u0644\u0646\u0635 \u0648\u064a\u0639\u062f \u0627\u0644\u0641\u0631\u0627\u063a\u0627\u062a\u060c \u062b\u0645 \u064a\u0646\u0634\u0626 TXT \u0639\u0646\u062f \u0627\u0644\u0639\u0644\u0627\u0645\u0629. \u0641\u0627\u0644\u0635\u0648\u0631\u0629 WREG03014_page_0001.jpg \u064a\u0642\u0627\u0628\u0644\u0647\u0627 WREG03014_page_0001.txt.<\/p>\n
f = open(orgTrans, 'r')\r\nnewFile = []   \r\nfor file in imageNames:\r\n       newFile = file.replace('jpg','txt')\r\n\u2026\r\nif(len(aLine) == 1): # find empty lines           \r\n                lineBreakCount += 1\r\naLine = f.readline()\r\n        if not aLine:  #reach the end of file.\r\n            newFile.append(aLine)<\/pre>\n
\u062a\u0648\u0644\u064a\u062f \u0627\u0644\u0628\u064a\u0627\u0646\u0627\u062a \u0627\u0644\u0648\u0635\u0641\u064a\u0629:<\/strong><\/p>\n
\u062a\u0642\u0631\u0623 read_csv \u0627\u0644\u0645\u0644\u0641 \u0625\u0644\u0649 DataFrame \u0628\u0627\u0633\u0645 orgMD \u060c \u0648\u062a\u062d\u062f\u062f index \u0631\u0642\u0645 \u0635\u0641 \u0627\u0644\u0627\u0633\u0645 \u0627\u0644\u0645\u0648\u0627\u0641\u0642\u060c \u062b\u0645 loc \u0627\u0644\u0635\u0641 \u0627\u0644\u0630\u064a \u064a\u062d\u0648\u064a PDF \u0627\u0644\u0645\u0637\u0627\u0628\u0642\u060c \u0648\u062a\u062f\u0645\u062c \u0627\u0644\u0628\u064a\u0627\u0646\u0627\u062a \u0641\u064a resultRow \u060c \u0648\u062a\u0643\u062a\u0628\u0647\u0627 TXT \u0645\u0641\u0635\u0648\u0644\u064b\u0627 \u0628\u0627\u0644\u062c\u062f\u0648\u0644\u0629 \u0628\u0627\u0633\u062a\u062e\u062f\u0627\u0645 to_csv.<\/p>\n
orgMD = pd.read_csv(orgMetadata, encoding= 'unicode_escape', low_memory=False) matchingRowIndex = orgMD.index[orgMD['File Name'] == file]\r\nresultRow = orgMD.loc[[matchingRowIndex]]\r\nmdRow = int(matchingRowIndex[0])+2\r\nresultRow = orgMD.loc[[mdRow],'Title':'File Name']\r\ncsvFileName = f'{file.strip(\".pdf\")}.txt'\r\ntn = f'{csvPath}{csvFileName}'\r\nresultRow.to_csv(exportedFileName, mode='a', sep ='\\t', index=False, encoding='utf-8')<\/pre>\n
\u062e\u0627\u062a\u0645\u0629:<\/strong><\/p>\n
\u0648\u0641\u0631\u062a \u0628\u0631\u0627\u0645\u062c R \u0648\u0628\u0627\u064a\u062b\u0648\u0646 \u0627\u0644\u0645\u062e\u0635\u0635\u0629 \u0633\u0627\u0639\u0627\u062a \u0643\u062b\u064a\u0631\u0629 \u0648\u0642\u0644\u0644\u062a \u0627\u0644\u0623\u062e\u0637\u0627\u0621 \u0627\u0644\u0628\u0634\u0631\u064a\u0629. \u0648\u0625\u0644\u0649 \u062c\u0627\u0646\u0628 \u0627\u0644\u062d\u0627\u0644\u0627\u062a \u0627\u0644\u0645\u0639\u0631\u0648\u0636\u0629\u060c \u0627\u0633\u062a\u064f\u062e\u062f\u0645\u062a \u0644\u062a\u062d\u0644\u064a\u0644 GIS \u0648\u0627\u0644\u062a\u062d\u0642\u0642 \u0628\u0639\u062f \u0627\u0644\u0625\u062f\u062e\u0627\u0644. \u0648\u0645\u0639 \u0634\u064a\u0648\u0639\u0647\u0627 \u0644\u062f\u0649 \u0639\u0644\u0645\u0627\u0621 \u0627\u0644\u0628\u064a\u0627\u0646\u0627\u062a \u0648\u0627\u0644\u0645\u0647\u0646\u062f\u0633\u064a\u0646 \u0648\u0627\u0644\u0627\u062e\u062a\u0635\u0627\u0635\u064a\u064a\u0646 \u0627\u0644\u062c\u063a\u0631\u0627\u0641\u064a\u064a\u0646\u060c \u0641\u0647\u064a \u0645\u0641\u064a\u062f\u0629 \u0644\u0644\u0645\u0643\u062a\u0628\u064a\u064a\u0646 \u0623\u064a\u0636\u064b\u0627. \u0648\u0646\u0634\u062c\u0639 \u062a\u0639\u0644\u0645\u0647\u0627 \u0628\u062f\u0631\u0648\u0633 \u0623\u0648 \u0648\u0631\u0634 \u0645\u062c\u0627\u0646\u064a\u0629 \u062b\u0645 \u062a\u0637\u0628\u064a\u0642\u0647\u0627 \u0641\u064a \u0645\u0634\u0631\u0648\u0639\u0627\u062a \u0628\u0633\u064a\u0637\u0629\u061b \u0641\u0645\u0639 \u0627\u0644\u062e\u0628\u0631\u0629 \u062a\u062a\u0643\u0634\u0641 \u0641\u0631\u0635 \u0623\u0643\u062b\u0631.<\/p>\n
\u0627\u0644\u0645\u0631\u0627\u062c\u0639:<\/strong><\/p>\n
https:\/\/<\/span>software-carpentry.org\/<\/span><\/p>\n
https:\/\/<\/span>www.coursera.org\/specializations\/python<\/span><\/p>\n
http:\/\/<\/span>ftp.ussg.iu.edu\/CRAN\/<\/span><\/p>\n
https:\/\/<\/span>www.rstudio.com\/products\/rstudio\/download\/#download<\/span><\/p>\n
https:\/\/<\/span>github.com\/oschwartz10612\/poppler-windows\/releases\/<\/span><\/p>\n
https:\/\/<\/span>pdf2image.readthedocs.io\/en\/latest\/installation.html<\/span><\/p>\n
https:\/\/<\/span>www.geeksforgeeks.org\/convert-pdf-to-image-using-python\/<\/span><\/p>\n
https:\/\/<\/span>www.r-project.org\/about.html<\/span><\/p>\n
https:\/\/<\/span>www.coursera.org\/articles\/what-is-python-used-for-a-beginners-guide-to-using-python<\/span><\/p>\n
https:\/\/<\/span>www.rdatoolkit.org\/about#:~:text=RDA%3A%20Resource%20Description%20and%20Access,user%2Dfocused%20linked%20data%20applications<\/span><\/p>\n
https:\/\/<\/span>duo.com\/labs\/tech-notes\/breaking-down-uuids#:~:text=Universally%20Unique%20Identifiers%2C%20or%20UUIDS,both%20the%20IETF%20and%20ITU<\/span><\/p>\n
https:\/\/<\/span>libguides.library.kent.edu\/statconsulting\/r<\/span><\/p>\n
https:\/\/<\/span>www.rdocumentation.org\/packages\/micropan\/versions\/1.0\/topics\/gregexpr<\/span><\/p>\n
https:\/\/<\/span>help.oclc.org\/Metadata_Services\/CONTENTdm\/Project_Client\/Enter_metadata\/OCR?sl=en<\/span><\/p>\n
\u062d\u0648\u0627\u0634\u064a \u0627\u0644\u0623\u0635\u0644 \u0628\u0644\u063a\u062a\u0647\u0627 \u0627\u0644\u0623\u0635\u0644\u064a\u0629:<\/strong><\/p>\n
[1] \u201cWhat is R?\u201d The R Foundation, accessed December 1, 2022, https:\/\/www.r-project.org\/about.html. [2] \u201cWhat is Python?\u201d Coursera Inc., accessed December 12, 2022, https:\/\/www.coursera.org\/articles\/what-is-python-used-for-a-beginners-guide-to-using-python. [3] \u201cRDA, Resource Description & Access Toolkit\u201d, American Library Association, accessed December 12, 2022, https:\/\/www.rdatoolkit.org\/about#:~:text=RDA%3A%20Resource%20Description%20and%20Access,user%2Dfocused%20linked%20data%20applications. [4] Steele, Nick. \u201cBreaking Down UUIDS\u201d, accessed December 12, 2022, https:\/\/duo.com\/labs\/tech-notes\/breaking-down-uuids#:~:text=Universally%20Unique%20Identifiers%2C%20or%20UUIDS,both%20the%20IETF%20and%20ITU. [5] \u201cStatistical & Qualitative Data Analysis Software: About R and RStudio\u201d, 26, October er, 2022, accessed December 12, 2022, https:\/\/libguides.library.kent.edu\/statconsulting\/r. [6] \u201cgregexpr: Extended gregexpr with substring retrieval\u201d, RDocumentation.org, accessed December 12, 2022, https:\/\/www.rdocumentation.org\/packages\/micropan\/versions\/1.0\/topics\/gregexpr. [7] \u201cOCR\u201d, OCLC, 1 January, 2023, accessed March 23, 2023, https:\/\/help.oclc.org\/Metadata_Services\/CONTENTdm\/Project_Client\/Enter_metadata\/OCR?sl=en. [8 kumar_satyam. \u201cConvert PDF to Image using Python.\u201d 21 Jan, 2021, accessed December 9, 2022, https:\/\/www.geeksforgeeks.org\/convert-pdf-to-image-using-python\/.<\/p>\n","protected":false},"excerpt":{"rendered":"
\u0645\u0642\u062f\u0645\u0629 \u0648\u062e\u0644\u0641\u064a\u0629: R \u0644\u063a\u0629 \u0648\u0628\u064a\u0626\u0629 \u0628\u0631\u0645\u062c\u064a\u0629 \u0644\u0644\u062d\u0648\u0633\u0628\u0629 \u0627\u0644\u0625\u062d\u0635\u0627\u0626\u064a\u0629 \u0648\u062a\u062d\u0644\u064a\u0644 \u0627\u0644\u0628\u064a\u0627\u0646\u0627\u062a \u0648\u062a\u0645\u062b\u064a\u0644\u0647\u0627 \u0631\u0633\u0648\u0645\u064a\u064b\u0627. \u0648\u062a\u0648\u0641\u0631 \u062a\u0642\u0646\u064a\u0627\u062a \u0645\u062a\u0646\u0648\u0639\u0629: \u0627\u0644\u0646\u0645\u0630\u062c\u0629 \u0627\u0644\u062e\u0637\u064a\u0629 \u0648\u063a\u064a\u0631 \u0627\u0644\u062e\u0637\u064a\u0629\u060c \u0648\u0627\u0644\u0627\u062e\u062a\u0628\u0627\u0631\u0627\u062a \u0627\u0644\u062a\u0642\u0644\u064a\u062f\u064a\u0629\u060c \u0648\u0627\u0644\u0633\u0644\u0627\u0633\u0644 \u0627\u0644\u0632\u0645\u0646\u064a\u0629 \u0648\u0627\u0644\u062a\u0635\u0646\u064a\u0641 \u0648\u0627\u0644\u062a\u062c\u0645\u064a\u0639\u060c \u0648\u0642\u0627\u0628\u0644\u064a\u0629 \u0643\u0628\u064a\u0631\u0629 \u0644\u0644\u062a\u0648\u0633\u0639[1]. \u0623\u0645\u0627 \u0628\u0627\u064a\u062b\u0648\u0646 \u0641\u062a\u064f\u0633\u062a\u062e\u062f\u0645 \u0644\u0628\u0646\u0627\u0621\u2026<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[641,629,640],"tags":[],"class_list":["post-50588","post","type-post","status-publish","format-standard","hentry","category-technology-digital-transformation","category-issue-83","category-information-knowledge-management"],"_links":{"self":[{"href":"https:\/\/informaticsjournal.net\/index.php?rest_route=\/wp\/v2\/posts\/50588","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/informaticsjournal.net\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/informaticsjournal.net\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/informaticsjournal.net\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/informaticsjournal.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=50588"}],"version-history":[{"count":7,"href":"https:\/\/informaticsjournal.net\/index.php?rest_route=\/wp\/v2\/posts\/50588\/revisions"}],"predecessor-version":[{"id":52372,"href":"https:\/\/informaticsjournal.net\/index.php?rest_route=\/wp\/v2\/posts\/50588\/revisions\/52372"}],"wp:attachment":[{"href":"https:\/\/informaticsjournal.net\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=50588"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/informaticsjournal.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=50588"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/informaticsjournal.net\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=50588"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}