yujunjun/OCRmyPDF
1
0
Fork 0
mirror of https://github.com/ocrmypdf/OCRmyPDF.git synced 2026-01-05 11:41:19 +00:00
Code Issues Packages Projects Releases Wiki Activity

Use --gnu in parralell and XX for mktemp

Browse Source 
Signed-off-by: Mansour Behabadi <mansour@oxplot.com>
This commit is contained in:
Mansour Behabadi 2014-01-14 17:49:24 +11:00
parent f581a55544
commit 6653066784
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
OCRmyPDF.sh Normal file → Executable file
View File

@ -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="$?"