new-words
annotate grep-sentences.pl @ 28:7db7bbf96fad
temporary files names
author | Igor Chubin <igor@chub.in> |
---|---|
date | Tue Jun 15 05:46:50 2010 +0300 (2010-06-15) |
parents | 416394a87d9f |
children | c631833fa2be |
rev | line source |
---|---|
igor@5 | 1 #!/usr/bin/perl |
igor@5 | 2 |
igor@5 | 3 |
igor@6 | 4 $regexp=$ARGV[0]; |
igor@6 | 5 $page=$ARGV[1]; |
igor@5 | 6 #if (open(PAGE, "lynx -dump '$page'|")) { |
igor@5 | 7 if (open(PAGE, "$page")) { |
igor@5 | 8 local $/; |
igor@5 | 9 $text=<PAGE>; |
igor@5 | 10 $text =~ s@http://[a-zA-Z&_.:/0-9%?=,\#+()\[\]~-]*@@g; |
igor@5 | 11 $text =~ s@\n@@g; |
igor@28 | 12 $text =~ s@(Mr|Mrs|viz)\.@\1POINT@g; |
igor@28 | 13 $text =~ s@e\.g\.@ePOINTgPOINT@g; |
igor@28 | 14 $text =~ s@i\.e\.@iPOINTePOINT@g; |
igor@19 | 15 @sentences=split /[.!?]/, $text; |
igor@5 | 16 for (@sentences) { |
igor@28 | 17 s@iPOINTePOINT@i\.e\.@g; |
igor@28 | 18 s@ePOINTgPOINT@e\.g\.@g; |
igor@28 | 19 s@(Mr|Mrs|viz)POINT@\1.@g; |
igor@5 | 20 s/^\s*//; |
igor@5 | 21 s/\s*$//; |
igor@5 | 22 s/\[[0-9]+\]//g; |
igor@5 | 23 s/\s+/ /g; |
igor@5 | 24 print "$_.\n\n" if /\b$regexp\b/; |
igor@5 | 25 } |
igor@5 | 26 } |