menekis/OCRmyPDF
Public Access
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

OCRmyPDF.sh: metadata not added anymore

Browse Source 
Removed feature to add metadata in final pdf file (because it lead to to
final PDF file that does not comply to the PDF/A-1 format)
This commit is contained in:
fritz-hh
2013-05-06 21:26:33 +02:00
parent ab536d5678
commit 7e8481186a
1 changed files with 21 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files
OCRmyPDF.sh
+21 -21
View File
@@ -4,7 +4,7 @@
##############################################################################
TOOLNAME="OCRmyPDF"
VERSION="v1.0-rc2"
VERSION="v1.0-stable"
START=`date +%s`
@@ -309,28 +309,28 @@ done < "$FILE_SIZE_PAGES"
[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Output file: Converting to PDF/A"
! gs -dQUIET -dPDFA -dBATCH -dNOPAUSE -dUseCIEColor \
-sProcessColorModel=DeviceCMYK -sDEVICE=pdfwrite -sPDFACompatibilityPolicy=2 \
-sOutputFile="$FILE_OUTPUT_PDFA_WO_META" "$FILE_OUTPUT_PDF_CAT" 1> /dev/null 2> /dev/null \
-sOutputFile="$FILE_OUTPUT_PDFA" "$FILE_OUTPUT_PDF_CAT" 1> /dev/null 2> /dev/null \
&& echo "Could not convert PDF file \"$FILE_OUTPUT_PDF_CAT\" to PDF/A. Exiting..." >&2 && exit $EXIT_OTHER_ERROR
# Write metadata
# Needs to be done after converting to PDF/A, as gs does not preserve metadata
[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Output file: Update metadata (creator, producer, and title)"
title=`basename "$FILE_INPUT_PDF" | sed 's/[.][^.]*//' | \
sed 's/_/ /g' | sed 's/-/ /g' | \
sed 's/\([[:lower:]]\)\([[:upper:]]\)/\1 \2/g' | \
sed 's/\([[:alpha:]]\)\([[:digit:]]\)/\1 \2/g' | \
sed 's/\([[:digit:]]\)\([[:alpha:]]\)/\1 \2/g'` # transform the file name (with extension) into distinct words
pdftk "$FILE_OUTPUT_PDFA_WO_META" update_info_utf8 - output "$FILE_OUTPUT_PDFA" << EOF
InfoBegin
InfoKey: Title
InfoValue: $title
InfoBegin
InfoKey: Creator
InfoValue: $TOOLNAME $VERSION
InfoBegin
InfoKey: Producer
InfoValue: ghostcript `gs --version`, pdftk
EOF
# # Write metadata
# # Needs to be done after converting to PDF/A, as gs does not preserve metadata
# [ $VERBOSITY -ge $LOG_DEBUG ] && echo "Output file: Update metadata (creator, producer, and title)"
# title=`basename "$FILE_INPUT_PDF" | sed 's/[.][^.]*//' | \
# sed 's/_/ /g' | sed 's/-/ /g' | \
# sed 's/\([[:lower:]]\)\([[:upper:]]\)/\1 \2/g' | \
# sed 's/\([[:alpha:]]\)\([[:digit:]]\)/\1 \2/g' | \
# sed 's/\([[:digit:]]\)\([[:alpha:]]\)/\1 \2/g'` # transform the file name (with extension) into distinct words
# pdftk "$FILE_OUTPUT_PDFA_WO_META" update_info_utf8 - output "$FILE_OUTPUT_PDFA" << EOF
# InfoBegin
# InfoKey: Title
# InfoValue: $title
# InfoBegin
# InfoKey: Creator
# InfoValue: $TOOLNAME $VERSION
# InfoBegin
# InfoKey: Producer
# InfoValue: ghostcript `gs --version`, pdftk
# EOF
# validate generated pdf file (compliance to PDF/A)
[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Output file: Checking compliance to PDF/A standard"