From 6653066784275ccacd2d600405b23bf88d0b9e41 Mon Sep 17 00:00:00 2001 From: Mansour Behabadi Date: Tue, 14 Jan 2014 17:49:24 +1100 Subject: [PATCH 1/2] Use --gnu in parralell and XX for mktemp Signed-off-by: Mansour Behabadi --- OCRmyPDF.sh | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) mode change 100644 => 100755 OCRmyPDF.sh diff --git a/OCRmyPDF.sh b/OCRmyPDF.sh old mode 100644 new mode 100755 index bf64b51b..bbc56447 --- a/OCRmyPDF.sh +++ b/OCRmyPDF.sh @@ -210,7 +210,7 @@ fi today=$(date +"%Y%m%d_%H%M") fld=$(basename "$FILE_INPUT_PDF" | sed 's/[.][^.]*$//') prefix="${today}.filename.${fld}" -TMP_FLD=`TMPDIR=${TMP} mktemp -d -t "${prefix}"` +TMP_FLD=`TMPDIR=${TMP} mktemp -d -t "${prefix}XXXXXXXX"` FILE_TMP="${TMP_FLD}/tmp.txt" # temporary file with a very short lifetime (may be used for several things) FILE_PAGES_INFO="${TMP_FLD}/pages-info.txt" # for each page: page #; width in pt; height in pt FILE_OUTPUT_PDF_CAT="${TMP_FLD}/ocred.pdf" # concatenated OCRed PDF files @@ -229,7 +229,7 @@ sed '/^$/d' "$FILE_TMP" | awk '{printf "%04d %s\n", NR, $0}' > "$FILE_PAGES_INFO numpages=`tail -n 1 "$FILE_PAGES_INFO" | cut -f1 -d" "` # process each page of the input pdf file -parallel -q -k --halt-on-error 1 "$OCR_PAGE" "$FILE_INPUT_PDF" "{}" "$numpages" "$TMP_FLD" \ +parallel --gnu -q -k --halt-on-error 1 "$OCR_PAGE" "$FILE_INPUT_PDF" "{}" "$numpages" "$TMP_FLD" \ "$VERBOSITY" "$LAN" "$KEEP_TMP" "$PREPROCESS_DESKEW" "$PREPROCESS_CLEAN" "$PREPROCESS_CLEANTOPDF" "$OVERSAMPLING_DPI" \ "$PDF_NOIMG" "$TESS_CFG_FILES" "$FORCE_OCR" < "$FILE_PAGES_INFO" ret_code="$?" From a78630ce99c9ec8844f3c6a14b1a195b535909c0 Mon Sep 17 00:00:00 2001 From: Mansour Behabadi Date: Tue, 14 Jan 2014 17:50:46 +1100 Subject: [PATCH 2/2] Make src scripts executable Signed-off-by: Mansour Behabadi --- src/hocrTransform.py | 0 src/ocrPage.sh | 0 2 files changed, 0 insertions(+), 0 deletions(-) mode change 100644 => 100755 src/hocrTransform.py mode change 100644 => 100755 src/ocrPage.sh diff --git a/src/hocrTransform.py b/src/hocrTransform.py old mode 100644 new mode 100755 diff --git a/src/ocrPage.sh b/src/ocrPage.sh old mode 100644 new mode 100755