Created
April 7, 2019 21:40
-
-
Save iemcd/683c379e0bc2cb5eb007a8fefff3fe64 to your computer and use it in GitHub Desktop.
PDF Annotation Tools
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/bin/perl | |
use strict; | |
use warnings; | |
use 5.22.3; | |
use List::Util qw( min max ); | |
# Fields are: char, x1, y1, x2, y2, pp | |
open(my $table, "<", $ARGV[0]) or die "Can't open $ARGV[0]: $!"; | |
my $text; | |
my @table; | |
while (<$table>) | |
{ | |
chomp; | |
$text .= lc((split("\t"))[0]); | |
push @table, $_; | |
} | |
while (<STDIN>) | |
{ | |
chomp(my $word = $_); | |
my $wordre = '\b'.$word.'\b'; | |
if ($text =~ /$wordre/) | |
{ | |
my $position = $-[0]; | |
my (@x1, @x2, @y1, @y2, $pp); | |
for (my $i = 0; $i < length($word); $i++) | |
{ | |
my @line = split("\t",$table[$position+$i]); | |
push @x1, $line[1]; | |
push @x2, $line[3]; | |
push @y1, $line[2]; | |
push @y2, $line[4]; | |
$pp = $line[5]; | |
} | |
# x1=xll, x2=xur, y1=yll, & y2=yur in the pdfmark reference | |
# annotations not rotated, so this fully describes rectangle | |
my $x1 = min @x1; | |
my $x2 = max @x2; | |
my $y1 = min @y1; | |
my $y2 = max @y2; | |
say "[ /Rect [$x1 $y1 $x2 $y2]"; | |
say " /Subtype /Highlight"; | |
say " /QuadPoints [$x1 $y2 $x2 $y2 $x1 $y1 $x2 $y1]"; | |
# QuadPoints does not work as specified, instead see: https://stackoverflow.com/questions/9855814/pdf-spec-vs-acrobat-creation-quadpoints | |
say " /SrcPg $pp"; | |
say " /Contents ($word)"; # mostly for troubleshooting | |
say " /Color [0 1 1]"; | |
say " /ANN pdfmark\n"; # extra newline is intentional | |
} | |
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/bin/perl | |
use strict; | |
use warnings; | |
use 5.22.3; | |
my $page=1; | |
while (<>) | |
{ | |
if (/^<page id=\"(\d+)\"/) | |
{ | |
$page = $1; | |
} | |
elsif (/^<text .+ bbox=\"([\d.]+),([\d.]+),([\d.]+),([\d.]+)\" .+>(.)<\/text>$/) | |
{ | |
say "$5\t$1\t$2\t$3\t$4\t$page"; | |
}; | |
}; |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment