sergio · April 7, 2017 18:06 · Jul 7, 2016 · Jul 7, 2016 · Mar 31, 2016 · Mar 31, 2016
diff --git a/diffpdf.sh b/diffpdf.sh
@@ -1,15 +1,16 @@
-#!/bin/sh
+#!/bin/bash
 
-# usage: diffpdf.sh file_1.pdf file_2.pdf
+# usage: diffpdf.sh fidle_1.pdf file_2.pdf
 
 # requirements:
 # - ImageMagick
-# - Poppler's pdftoppm and pdfinfo tools (works with 0.41.0, NOT with 0.42.0)
+# - Poppler's pdftoppm and pdfinfo tools (works with 0.18.4 and 0.41.0,
+#                                         fails with 0.42.0)
 #   (could be replaced with Ghostscript if speed is
 #    not important - see commented commands below)
 
-DIFFDIR="pdfdiff"   # directory to place diff images in
-MAXPROCS=8          # number of parallel processes
+DIFFDIR="pdfdiff"                        # directory to place diff images in
+MAXPROCS=$(getconf _NPROCESSORS_ONLN)    # number of parallel processes
 
 pdf_file1=$1
 pdf_file2=$2
@@ -44,12 +45,15 @@ function diff_page {
 #            -highlight-color blue pdfdiff/$page_number.png
 
     if (($? > 0)); then
+        echo "Problem running pdftoppm or convert!"
         exit 1
     fi
     grayscale=$(convert pdfdiff/$page_number.jpg -colorspace HSL -channel g -separate +channel -format "%[fx:mean]" info:)
     if [ "$grayscale" != "0" ]; then
         echo "page $page_number ($grayscale)"
-    fi 
+        return 1
+    fi
+    return 0
 }
 
 function num_pages {
@@ -75,6 +79,7 @@ min_pages=$(minimum $pdf1_num_pages $pdf2_num_pages)
 
 if [ "$pdf1_num_pages" -ne "$pdf2_num_pages" ]; then
     echo "PDF files have different lengths ($pdf1_num_pages and $pdf2_num_pages)"
+    rc=1
 fi
 
 if [ -d "$DIFFDIR" ]; then
@@ -83,12 +88,42 @@ else
     mkdir $DIFFDIR
 fi
 
+
+# get exit status from subshells http://stackoverflow.com/a/29535256/438249
+
+function wait_for_processes {
+    local rc=0
+
+    while (( "$#" )); do
+        # wait returns the exit status for the process
+        if ! wait "$1"; then
+            rc=1
+        fi
+        shift
+    done
+    return $rc
+}
+
+function howmany() {
+    echo $#
+}
+
+rc=0
+pids=""
 for page_number in `seq 1 $min_pages`;
 do
     diff_page $pdf_file1 $pdf_file2 $page_number &
-    # echo "$page_number \c"
-    if [ "$(($page_number % $MAXPROCS))" -eq "0" ]; then
-        wait
+    pids+=" $!"
+    if [ $(howmany $pids) -eq "$MAXPROCS" ]; then
+        if ! wait_for_processes $pids; then
+            rc=1
+        fi
+        pids=""
     fi
 done
-wait
+
+if ! wait_for_processes $pids; then
+    rc=1
+fi
+
+exit $rc
diff --git a/diffpdf.sh b/diffpdf.sh
@@ -4,7 +4,7 @@
 
 # requirements:
 # - ImageMagick
-# - Poppler's pdftoppm and pdfinfo tools
+# - Poppler's pdftoppm and pdfinfo tools (works with 0.41.0, NOT with 0.42.0)
 #   (could be replaced with Ghostscript if speed is
 #    not important - see commented commands below)
 

diff --git a/diffpdf.sh b/diffpdf.sh
@@ -4,7 +4,9 @@
 
 # requirements:
 # - ImageMagick
-# - poppler's pdftoppm (or Ghostscript if speed is not important)
+# - Poppler's pdftoppm and pdfinfo tools
+#   (could be replaced with Ghostscript if speed is
+#    not important - see commented commands below)
 
 DIFFDIR="pdfdiff"   # directory to place diff images in
 MAXPROCS=8          # number of parallel processes

diff --git a/diffpdf.sh b/diffpdf.sh
@@ -60,6 +60,12 @@ function minimum {
     echo $(( $1 < $2 ? $1 : $2 ))
 }
 
+# guard agains accidental deletion of files in the root directory
+if [ -z "$DIFFDIR" ]; then
+    echo "DIFFDIR needs to be set!"
+    exit 1
+fi
+
 pdf1_num_pages=$(num_pages $pdf_file1)
 pdf2_num_pages=$(num_pages $pdf_file2)
 
@@ -70,7 +76,7 @@ if [ "$pdf1_num_pages" -ne "$pdf2_num_pages" ]; then
 fi
 
 if [ -d "$DIFFDIR" ]; then
-    rm -rf $DIFFDIR/*
+    rm -f $DIFFDIR/*
 else
     mkdir $DIFFDIR
 fi

diff --git a/diffpdf.sh b/diffpdf.sh
@@ -0,0 +1,86 @@
+#!/bin/sh
+
+# usage: diffpdf.sh file_1.pdf file_2.pdf
+
+# requirements:
+# - ImageMagick
+# - poppler's pdftoppm (or Ghostscript if speed is not important)
+
+DIFFDIR="pdfdiff"   # directory to place diff images in
+MAXPROCS=8          # number of parallel processes
+
+pdf_file1=$1
+pdf_file2=$2
+
+function diff_page {
+    # based on http://stackoverflow.com/a/33673440/438249
+    pdf_file1=$1
+    pdf_file2=$2
+    page_number=$3
+    page_index=$(($page_number - 1))
+
+    # 2+x faster
+    (cat $pdf_file1 | pdftoppm -f $page_number -singlefile -gray - | convert - miff:- ; \
+     cat $pdf_file2 | pdftoppm -f $page_number -singlefile -gray - | convert - miff:- ) | \
+    convert - \( -clone 0-1 -compose darken -composite \) \
+            -channel RGB -combine $DIFFDIR/$page_number.jpg
+
+    # 2x faster (breaks when using TIFF format instead of JPEG, and PNG is slow)
+#    (pdftocairo -f $page_number -singlefile -jpeg $pdf_file1 -gray - | convert - miff:- ; \
+#     pdftocairo -f $page_number -singlefile -jpeg $pdf_file2 -gray - | convert - miff:- ) | \
+#    convert - \( -clone 0-1 -compose darken -composite \) \
+#            -channel RGB -combine $DIFFDIR/$page_number.jpg
+
+    # 1x (using Ghostscript for PDF to bitmap conversion)
+#    convert -respect-parenthesis \
+#            \( $pdf_file1[$page_index] -flatten -colorspace gray \) \
+#            \( $pdf_file2[$page_index] -flatten -colorspace gray \) \
+#            \( -clone 0-1 -compose darken -composite \) \
+#            -channel RGB -combine $DIFFDIR/$page_number.jpg
+
+#    compare $pdf_file1[$page_index] $pdf_file2[$page_index] \
+#            -highlight-color blue pdfdiff/$page_number.png
+
+    if (($? > 0)); then
+        exit 1
+    fi
+    grayscale=$(convert pdfdiff/$page_number.jpg -colorspace HSL -channel g -separate +channel -format "%[fx:mean]" info:)
+    if [ "$grayscale" != "0" ]; then
+        echo "page $page_number ($grayscale)"
+    fi 
+}
+
+function num_pages {
+    pdf_file=$1
+
+    pdfinfo $pdf_file | grep "Pages:" | awk '{print $2}'
+}
+
+function minimum {
+    echo $(( $1 < $2 ? $1 : $2 ))
+}
+
+pdf1_num_pages=$(num_pages $pdf_file1)
+pdf2_num_pages=$(num_pages $pdf_file2)
+
+min_pages=$(minimum $pdf1_num_pages $pdf2_num_pages)
+
+if [ "$pdf1_num_pages" -ne "$pdf2_num_pages" ]; then
+    echo "PDF files have different lengths ($pdf1_num_pages and $pdf2_num_pages)"
+fi
+
+if [ -d "$DIFFDIR" ]; then
+    rm -rf $DIFFDIR/*
+else
+    mkdir $DIFFDIR
+fi
+
+for page_number in `seq 1 $min_pages`;
+do
+    diff_page $pdf_file1 $pdf_file2 $page_number &
+    # echo "$page_number \c"
+    if [ "$(($page_number % $MAXPROCS))" -eq "0" ]; then
+        wait
+    fi
+done
+wait
No results found