I've faced this before, and decided I had to roll my own. Mine doesn't worry about times, though, is it would need modification. It's built to accept an email and scan it, sentence by sentence, looking for any dates, then add them to my calendar file. It also tries to limit it to dates in the future (so it'll add "tomorrow" but not "yesterday", and because calendar only runs for me once a night, not "today"). So it'll need some modification for you, but it might be a starting point, if no one can provide a better solution for finding the date buried inside text. Produces lines like
11/04/2004 Bruce Schneier :CRYPTO-GRAM, October 15, 2004:RSA Euro +pe in Barcelona, on 4 November
#!/usr/bin/perl -lw use diagnostics; use strict; use POSIX; use Time::Local; my ($from, $subject) = ("", ""); while(<>){ last if /^$/; chomp; if (/^From: (.*)/i){ $from = $1; $from =~ s/"?([^"]+)"?\s*<[^<]+>/$1/; $from =~ s/^([^,]+),\s*(.*)$/$2 $1/; } if (/^Subject: (.*)/i){ $subject = $1; $subject =~ s/\bRe://ig; $subject =~ s/\[.*?\]//ig; $subject =~ s/\s+/ /g; $subject =~ s/^ //; $subject =~ s/ $//; } } my %month; @month{qw( jan feb mar apr may jun jul aug sep oct nov dec )} = (1 .. +12); my $month = qr/ \b(?: a(?:pr(?:il)? |ug(?:ust)?) |(?:dec|nov|sept?)(?:ember)? |(?:febr?|jan)(?:uary)? |ju(?:ly?|ne?) |ma(?:y|r(?:ch)?) |oct(?:ober)? )\b/ix; my $text = ""; while (<>){ last if /^\s*-+Original Message-+$/; last if /^\s*Processing Initiated:/; last if /^Content-Type:\stext\/html/; next if /^[>:]/; next if /^On /; next if /\bwrote:\s*$/; chomp; $text .= $_ . " "; } for (split /(?<!\.\S)\.\s+|\s\s+/, $text){ if (/\b(?<![.\/\d:])(\d\d?)(?:(?:st|nd|rd|th)? of)? ($month)(?:,?\s+(? +:\d\d\d\d))?\b/oi) { test_date_text($2, $1, $3); } elsif (/($month)\s+(\d\d?)(?:st|nd|rd|th)?,?\s*(\d\d\d\d)?\b/oi){ test_date_text($1, $2, $3); } elsif (/\b(?<![.\/\d:])(\d\d\d\d)([-\/])(\d\d?)\2(\d\d?)(?![.\/])\b/ +){ test_date($3, $4, $1); } elsif (/\b(?<![.\/\d:])(\d\d?)([-\/])(\d\d?)(?:\2((?:\d\d){1,2}))?(? +![.\/])\b/){ test_date($1, $3, $4); } elsif (/\btomorrow\b/i) { print_report(time() + 86400); } else { test_date_weekday(); } } sub print_report { my ($time) = shift; # my $comment = /ed\b|\b(?:(?:w|sp?)ent|left|took|w(?:as|ere)|came) +\b/ ? "#" : ""; open CALENDAR, ">> $ENV{HOME}/calendar"; print CALENDAR strftime("%m/%d/%Y\t$from:$subject:$_", localtime($ +time)); close CALENDAR; } sub test_date_weekday { return if /$month/; return unless /\b(?<!')(Sunday|(?:Mon|Tues?|Wed(?:nes)?|Thu(?:rs)?|Fri|Satur +)(?:day)?)\b/i; my $weekday = lc substr($1, 0,3); my %weekdays; @weekdays{qw( sun mon tue wed thu fri sat )} = (-1 .. 5); print_report (time()+ 86400 * (($weekdays{$weekday} - (localtime())[6]) % 7 + 1)); } sub test_date { my ($m, $d, $y) = @_; if (defined $y){ return unless $y =~ /^(?:20)?0/; } else { $y = (localtime)[5]; } my $time = 0; eval { $time = timelocal(0,0,0, $d, $m-1, $y) }; if ($time > time){ print_report $time; return 1; } return; } sub test_date_text { my ($m, $d, $y) = @_; return test_date($month{lc substr($m, 0, 3)}, $d, $y); }
In reply to Re: Extracting time/date from english text
by Eimi Metamorphoumai
in thread Extracting time/date from english text
by fce2
| For: | Use: | ||
| & | & | ||
| < | < | ||
| > | > | ||
| [ | [ | ||
| ] | ] |