A macro to generate pairs of people linked by email communications, given an email that links them

pairs.pig

/* Filter emails according to existence of header pairs, from and [to, cc, bcc]
project the pairs (may be more than one to/cc/bcc), then emit them, lowercased. */
DEFINE header_pairs(email, col1, col2) RETURNS pairs { 
  filtered = FILTER $email BY ($col1 IS NOT NULL) AND ($col2 IS NOT NULL);
  flat = FOREACH filtered GENERATE FLATTEN($col1) AS $col1, FLATTEN($col2) AS $col2;
  $pairs = FOREACH flat GENERATE LOWER($col1), LOWER($col2);
}

pairs = header_pairs(email)