dupword.awk

来自「gawk: linux下资料处理工具」· AWK 代码 · 共 22 行

# dupword.awk --- find duplicate words in text
#
# Arnold Robbins, [e-mail], Public Domain
# December 1991
# Revised October 2000

{
    $0 = tolower($0)
    gsub(/[^[:alnum:][:blank:]]/, " ");
    $0 = $0         # re-split
    if (NF == 0)
        next
    if ($1 == prev)
        printf("%s:%d: duplicate %s\n",
            FILENAME, FNR, $1)
    for (i = 2; i <= NF; i++)
        if ($i == $(i-1))
            printf("%s:%d: duplicate %s\n",
                FILENAME, FNR, $i)
    prev = $NF
}