minor changes (indentation and fct name)
This commit is contained in:
+7
-7
@@ -43,7 +43,7 @@ FORCE_OCR="${14}" # Force to OCR, even if the page already contains fonts
|
||||
# - 2: in case the page contains more than one image
|
||||
# - 3: in case the x,y resolutions are not equal
|
||||
##################################
|
||||
imageCharacteristics() {
|
||||
getImgInfo() {
|
||||
local page widthPDF heightPDF curImgCharacteristics nbImg curImg propCurImg widthCurImg heightCurImg colorspaceCurImg tmpval dpi_x dpi_y epsilon dpi
|
||||
|
||||
# page number
|
||||
@@ -126,16 +126,16 @@ widthPDF=`echo $PAGE_INFO | cut -f2 -d" "`
|
||||
heightPDF=`echo $PAGE_INFO | cut -f3 -d" "`
|
||||
|
||||
# create the name of the required temporary files
|
||||
curOrigImg="$TMP_FLD/${page}.orig-img" # original image available in the current PDF page
|
||||
# (the image file may have a different orientation than in the pdf file)
|
||||
curHocr="$TMP_FLD/${page}.hocr" # hocr file to be generated by the OCR SW for the current page
|
||||
curOCRedPDF="$TMP_FLD/${page}.ocred.pdf" # PDF file containing the image + the OCRed text for the current page
|
||||
curOCRedPDFDebug="$TMP_FLD/${page}.ocred-debug.pdf" # PDF file containing data required to find out if OCR worked correctly
|
||||
curOrigImg="$TMP_FLD/${page}.orig-img" # original image available in the current PDF page
|
||||
# (the image file may have a different orientation than in the pdf file)
|
||||
curHocr="$TMP_FLD/${page}.hocr" # hocr file to be generated by the OCR SW for the current page
|
||||
curOCRedPDF="$TMP_FLD/${page}.ocred.pdf" # PDF file containing the image + the OCRed text for the current page
|
||||
curOCRedPDFDebug="$TMP_FLD/${page}.ocred-debug.pdf" # PDF file containing data required to find out if OCR worked correctly
|
||||
curImgCharacteristics="$TMP_FLD/${page}.orig-img-info.txt" # Detected characteristics of the embedded image
|
||||
|
||||
|
||||
# auto-detect the characteristics of the embedded image
|
||||
imageCharacteristics "$page" "$widthPDF" "$heightPDF" "$curImgCharacteristics"
|
||||
getImgInfo "$page" "$widthPDF" "$heightPDF" "$curImgCharacteristics"
|
||||
ret_code="$?"
|
||||
# in case the page contains text do not OCR, unless the FORCE_OCR flag is set
|
||||
if [ "$ret_code" -eq "1" -a "$FORCE_OCR" -eq "0" ]; then
|
||||
|
||||
Reference in New Issue
Block a user