将字符串替换为一个巨大的（70GB）一行文本文件

#1 楼

<corpus.txt tr '\n;' ';\n' |
sed 's/<unk>/<raw_unk>/g' |
tr '\n;' ';\n' >corpus.txt.new

<corpus.txt tr '\n<' '<\n' |
sed 's/^unk>/raw_unk>/g' |
tr '\n<' '<\n' >corpus.txt.new

<corpus.txt tr '\n>' '>\n' |
sed 's/<unk$/<raw_unk/g' |
tr '\n>' '>\n' >corpus.txt.new

#2 楼

%%
\<unk\>     printf("<raw_unk>");  
%%

$ flex -o unk.c  unk.l
$ cc -o unk -O2 unk.c -lfl
$ unk < corpus.txt > corpus.txt.new

#3 楼

 #!/usr/bin/python3
# This script takes input from stdin
# (but it must be a regular file, to support mapping it),
# and writes the result to stdout.

search = b'<unk>'
replace = b'<raw_unk>'


import sys
import os
import mmap

# sys.stdout requires str, but we want to write bytes
out_bytes = sys.stdout.buffer

mem = mmap.mmap(sys.stdin.fileno(), 0, access=mmap.ACCESS_READ)
i = mem.find(search)
if i < 0:
    sys.exit("Search string not found")

# mmap object subscripts to bytes (making a copy)
# memoryview object subscripts to a memoryview object
# (it implements the buffer protocol).
view = memoryview(mem)

out_bytes.write(view[:i])
out_bytes.write(replace)
out_bytes.write(view[i+len(search):])
 

#4 楼

#5 楼

 #include <stdio.h>
#include <string.h>

#define PAT_LEN 5

int main()
{
    /* note this is not a general solution. In particular the pattern
     * must not have a repeated sequence at the start, so <unk> is fine
     * but aardvark is not, because it starts with "a" repeated, and ababc
     * is not because it starts with "ab" repeated. */
    char pattern[] = "<unk>";          /* set PAT_LEN to length of this */
    char replacement[] = "<raw_unk>"; 
    int c;
    int i, j;

    for (i = 0; (c = getchar()) != EOF;) {
        if (c == pattern[i]) {
            i++;
            if (i == PAT_LEN) {
                printf("%s", replacement);
                i = 0;
            }
        } else {
            if (i > 0) {
                for (j = 0; j < i; j++) {
                    putchar(pattern[j]);
                }
                i = 0;
            }
            if (c == pattern[0]) {
                i = 1;
            } else {
                putchar(c);
            }
        }
    }
    /* TODO: fix up end of file if it ends with a part of pattern */
    return 0;
}
 

#6 楼

file=...
newfile=...
replace='<raw_unk>'
grep -o -b -a -F '<unk>' <"$file" |
(   pos=0
    while IFS=$IFS: read offset pattern
    do size=${#pattern}
       let skip=offset-pos
       let big=skip/1048576
       let skip=skip-big*1048576
       dd bs=1048576 count=$big <&3
       dd bs=1 count=$skip <&3
       dd bs=1 count=$size of=/dev/null <&3
       printf "%s" "$replace"
       let pos=offset+size
    done
    cat <&3
) 3<"$file" >"$newfile"

#7 楼

fold -w 1024 -s corpus.txt | sed 's/<unk>/<raw_unk>/g' | tr '/n' '/0'

[root@alpha ~]# cat mailtest.txt
test XJS C4JD QADN1 NSBN3 2IDNEN GTUBE STANDARD ANTI UBE-TEST EMAIL*C.34X test

[root@alpha ~]# fold -w 20 -s mailtest.txt
test XJS C4JD QADN1
NSBN3 2IDNEN GTUBE
STANDARD ANTI
UBE-TEST
EMAIL*C.34X test

[root@alpha ~]# fold -w 20 -s mailtest.txt | sed 's/N/n/g'
test XJS C4JD QADn1
nSBn3 2IDnEn GTUBE
STAnDARD AnTI
UBE-TEST
EMAIL*C.34X test

[root@alpha ~]# fold -w 20 -s mailtest.txt | sed 's/N/n/g' | tr '\n' 'q4312078q'
test XJS C4JD QADn1 nSBn3 2IDnEn GTUBE STAnDARD AnTI UBE-TEST EMAIL*C.34X test

#8 楼

use strict;
use warnings;
use Fcntl qw(:flock O_RDWR);
use autodie;
use bytes;

use constant CHUNK_SIZE => 1024 * 32;

sysopen my $fh, 'file', O_RDWR;
flock($fh, LOCK_EX);

my $chunk = 1;
while ( sysread $fh, my $bytes, CHUNK_SIZE * $chunk ) {
  if ( $bytes =~ s/<unk>/<raw_unk>/g ) {
    seek( $fh, ($chunk-1)* CHUNK_SIZE, 0 );
    syswrite( $fh, $bytes, 1024);
    seek( $fh, $chunk * CHUNK_SIZE, 0 );
  }
  $chunk++;
}

#9 楼

#10 楼

perl -pe 'BEGIN{$/=e8}
          s/<unk>/<raw_unk>/g' < corpus.txt > corpus.txt.new

#11 楼

 package main

import (
    "bufio"
    "fmt"
    "log"
    "os"
)

func main() {
    const (
        pattern     = "<unk>"
        replacement = "<raw_unk>"
    )
    var match int
    var char rune
    scanner := bufio.NewScanner(os.Stdin)
    scanner.Split(bufio.ScanRunes)
    for scanner.Scan() {
        char = rune(scanner.Text()[0])
        if char == []rune(pattern)[match] {
            match++
            if match == len(pattern) {
                fmt.Print(replacement)
                match = 0
            }
        } else {
            if match > 0 {
                fmt.Print(string(pattern[:match]))
                match = 0
            }
            if char == rune(pattern[0]) {
                match = 1
            } else {
                fmt.Print(string(char))
            }
        }
    }
    if err := scanner.Err(); err != nil {
        log.Fatal(err)
    }
}
 

#12 楼

#13 楼

awk -v RS="<unk>" -v ORS="<raw_unk>" 1

#14 楼