Json 从文本文件中提取多个匹配模式

我需要从文本文件中的每一行提取所有K[A-Z]{4}和US[C，W][0-9]{8}值

我正在使用下面的代码尝试实现这一点，但是，我需要根据以下条件提取这些值：只有两个值都出现在给定的行中（即下面数据中的最后三行）

尝试的代码：

#Filters out any values matching K[A-Z]{4}
grep -Po '"\K[A-Z]{4}\b' usc.matched > out.1

#Filters out any values matching US[C,W][0-9]{8}
grep -Po '\bUS\w*' usc.matched > out.2

#Pastes two datasets together, separated by a comma
paste -d',' out.1 out.2 > stations.filtered

#Removes any lines that do not lead with "K"
sed -i '/^[^K]/d' stations.filtered

{"sids": ["94737 1", "RUT 3", "KRUT 5"], "name": "RUTLAND STATE AP"},
{"sids": ["54740 1", "VSF 3", "KVSF 5", "USW00054740 6"], "name": "SPRINGFIELD HARTNESS AP"},
{"sids": ["94601 1", "RKD 3", "KRKD 5"], "name": "ROCKLAND KNOX CO RGNL AP"},
{"sids": ["20B 3"], "name": "ROCKLAND STN"},
{"sids": ["177250 2", "USC00177250 6"], "name": "ROCKLAND"},
{"sids": ["177255 2", "USC00177255 6", "RCKM1 7"], "name": "ROCKLAND"},
{"sids": ["177260 2"], "name": "ROCKLAND MOORING LBS"},
{"sids": [], "name": "ROCKLAND"},
{"sids": ["14612 1"], "name": "ROCKLAND"},
{"sids": ["274380 2", "USC00274380 6"], "name": "KEARSARGE"},
{"sids": ["192770 2", "USC00192770 6"], "name": "FISKDALE"},
{"sids": ["US1CTNL0005 6", "CTNL0005 10"], "name": "OAKDALE 2.6 WNW"},
{"sids": ["063989 2", "USC00063989 6"], "name": "LAKE KONOMOC"},
{"sids": ["14740 1", "14721 1", "063456 2", "069704 2", "BDL 3", "72508 4", "KBDL 5", "USW00014740 6", "BDL 7"], "name": "HARTFORD-BRADLEY INTL AP"},
{"sids": ["94702 1", "060806 2", "BDR 3", "72504 4", "KBDR 5", "USW00094702 6", "BDR 7"], "name": "IGOR I SIKORSKY MEMORI AP"},
{"sids": ["54734 1", "DXR 3", "KDXR 5", "USW00054734 6"], "name": "DANBURY MUNI AP"},

KRUT,
KVSF,USW00054740
KRKD

USC00177250
USC00177255


USC00274380
USC00192770
US1CTNL0005
USC00063989
KBDL,USW00014740
KBDR,USW00094702
KDXR,USW00054734

KVSF,USW00054740
KBDL,USW00014740
KBDR,USW00094702
KDXR,USW00054734

JSON数据：

#Filters out any values matching K[A-Z]{4}
grep -Po '"\K[A-Z]{4}\b' usc.matched > out.1

#Filters out any values matching US[C,W][0-9]{8}
grep -Po '\bUS\w*' usc.matched > out.2

#Pastes two datasets together, separated by a comma
paste -d',' out.1 out.2 > stations.filtered

#Removes any lines that do not lead with "K"
sed -i '/^[^K]/d' stations.filtered

{"sids": ["94737 1", "RUT 3", "KRUT 5"], "name": "RUTLAND STATE AP"},
{"sids": ["54740 1", "VSF 3", "KVSF 5", "USW00054740 6"], "name": "SPRINGFIELD HARTNESS AP"},
{"sids": ["94601 1", "RKD 3", "KRKD 5"], "name": "ROCKLAND KNOX CO RGNL AP"},
{"sids": ["20B 3"], "name": "ROCKLAND STN"},
{"sids": ["177250 2", "USC00177250 6"], "name": "ROCKLAND"},
{"sids": ["177255 2", "USC00177255 6", "RCKM1 7"], "name": "ROCKLAND"},
{"sids": ["177260 2"], "name": "ROCKLAND MOORING LBS"},
{"sids": [], "name": "ROCKLAND"},
{"sids": ["14612 1"], "name": "ROCKLAND"},
{"sids": ["274380 2", "USC00274380 6"], "name": "KEARSARGE"},
{"sids": ["192770 2", "USC00192770 6"], "name": "FISKDALE"},
{"sids": ["US1CTNL0005 6", "CTNL0005 10"], "name": "OAKDALE 2.6 WNW"},
{"sids": ["063989 2", "USC00063989 6"], "name": "LAKE KONOMOC"},
{"sids": ["14740 1", "14721 1", "063456 2", "069704 2", "BDL 3", "72508 4", "KBDL 5", "USW00014740 6", "BDL 7"], "name": "HARTFORD-BRADLEY INTL AP"},
{"sids": ["94702 1", "060806 2", "BDR 3", "72504 4", "KBDR 5", "USW00094702 6", "BDR 7"], "name": "IGOR I SIKORSKY MEMORI AP"},
{"sids": ["54734 1", "DXR 3", "KDXR 5", "USW00054734 6"], "name": "DANBURY MUNI AP"},

KRUT,
KVSF,USW00054740
KRKD

USC00177250
USC00177255


USC00274380
USC00192770
US1CTNL0005
USC00063989
KBDL,USW00014740
KBDR,USW00094702
KDXR,USW00054734

KVSF,USW00054740
KBDL,USW00014740
KBDR,USW00094702
KDXR,USW00054734

电流输出：

#Filters out any values matching K[A-Z]{4}
grep -Po '"\K[A-Z]{4}\b' usc.matched > out.1

#Filters out any values matching US[C,W][0-9]{8}
grep -Po '\bUS\w*' usc.matched > out.2

#Pastes two datasets together, separated by a comma
paste -d',' out.1 out.2 > stations.filtered

#Removes any lines that do not lead with "K"
sed -i '/^[^K]/d' stations.filtered

{"sids": ["94737 1", "RUT 3", "KRUT 5"], "name": "RUTLAND STATE AP"},
{"sids": ["54740 1", "VSF 3", "KVSF 5", "USW00054740 6"], "name": "SPRINGFIELD HARTNESS AP"},
{"sids": ["94601 1", "RKD 3", "KRKD 5"], "name": "ROCKLAND KNOX CO RGNL AP"},
{"sids": ["20B 3"], "name": "ROCKLAND STN"},
{"sids": ["177250 2", "USC00177250 6"], "name": "ROCKLAND"},
{"sids": ["177255 2", "USC00177255 6", "RCKM1 7"], "name": "ROCKLAND"},
{"sids": ["177260 2"], "name": "ROCKLAND MOORING LBS"},
{"sids": [], "name": "ROCKLAND"},
{"sids": ["14612 1"], "name": "ROCKLAND"},
{"sids": ["274380 2", "USC00274380 6"], "name": "KEARSARGE"},
{"sids": ["192770 2", "USC00192770 6"], "name": "FISKDALE"},
{"sids": ["US1CTNL0005 6", "CTNL0005 10"], "name": "OAKDALE 2.6 WNW"},
{"sids": ["063989 2", "USC00063989 6"], "name": "LAKE KONOMOC"},
{"sids": ["14740 1", "14721 1", "063456 2", "069704 2", "BDL 3", "72508 4", "KBDL 5", "USW00014740 6", "BDL 7"], "name": "HARTFORD-BRADLEY INTL AP"},
{"sids": ["94702 1", "060806 2", "BDR 3", "72504 4", "KBDR 5", "USW00094702 6", "BDR 7"], "name": "IGOR I SIKORSKY MEMORI AP"},
{"sids": ["54734 1", "DXR 3", "KDXR 5", "USW00054734 6"], "name": "DANBURY MUNI AP"},

KRUT,
KVSF,USW00054740
KRKD

USC00177250
USC00177255


USC00274380
USC00192770
US1CTNL0005
USC00063989
KBDL,USW00014740
KBDR,USW00094702
KDXR,USW00054734

KVSF,USW00054740
KBDL,USW00014740
KBDR,USW00094702
KDXR,USW00054734

预期输出：

#Filters out any values matching K[A-Z]{4}
grep -Po '"\K[A-Z]{4}\b' usc.matched > out.1

#Filters out any values matching US[C,W][0-9]{8}
grep -Po '\bUS\w*' usc.matched > out.2

#Pastes two datasets together, separated by a comma
paste -d',' out.1 out.2 > stations.filtered

#Removes any lines that do not lead with "K"
sed -i '/^[^K]/d' stations.filtered

{"sids": ["94737 1", "RUT 3", "KRUT 5"], "name": "RUTLAND STATE AP"},
{"sids": ["54740 1", "VSF 3", "KVSF 5", "USW00054740 6"], "name": "SPRINGFIELD HARTNESS AP"},
{"sids": ["94601 1", "RKD 3", "KRKD 5"], "name": "ROCKLAND KNOX CO RGNL AP"},
{"sids": ["20B 3"], "name": "ROCKLAND STN"},
{"sids": ["177250 2", "USC00177250 6"], "name": "ROCKLAND"},
{"sids": ["177255 2", "USC00177255 6", "RCKM1 7"], "name": "ROCKLAND"},
{"sids": ["177260 2"], "name": "ROCKLAND MOORING LBS"},
{"sids": [], "name": "ROCKLAND"},
{"sids": ["14612 1"], "name": "ROCKLAND"},
{"sids": ["274380 2", "USC00274380 6"], "name": "KEARSARGE"},
{"sids": ["192770 2", "USC00192770 6"], "name": "FISKDALE"},
{"sids": ["US1CTNL0005 6", "CTNL0005 10"], "name": "OAKDALE 2.6 WNW"},
{"sids": ["063989 2", "USC00063989 6"], "name": "LAKE KONOMOC"},
{"sids": ["14740 1", "14721 1", "063456 2", "069704 2", "BDL 3", "72508 4", "KBDL 5", "USW00014740 6", "BDL 7"], "name": "HARTFORD-BRADLEY INTL AP"},
{"sids": ["94702 1", "060806 2", "BDR 3", "72504 4", "KBDR 5", "USW00094702 6", "BDR 7"], "name": "IGOR I SIKORSKY MEMORI AP"},
{"sids": ["54734 1", "DXR 3", "KDXR 5", "USW00054734 6"], "name": "DANBURY MUNI AP"},

KRUT,
KVSF,USW00054740
KRKD

USC00177250
USC00177255


USC00274380
USC00192770
US1CTNL0005
USC00063989
KBDL,USW00014740
KBDR,USW00094702
KDXR,USW00054734

KVSF,USW00054740
KBDL,USW00014740
KBDR,USW00094702
KDXR,USW00054734

---

在awk中。根据您的喜好调整正则表达式：

$ awk -v OFS=, '
/K[A-Z]{3} / && /US[C,W][0-9]{8}/ {
    b=""
    while(match($0,/K[A-Z]{3} |US[C,W][0-9]{8}/)) {
        b=b (b==""?"":OFS) substr( $0, RSTART, RLENGTH)
        $0=substr($0,RSTART+RLENGTH)
    } 
print b}' file
KVSF ,USW00054740
KBDL ,USW00014740
KBDR ,USW00094702
KDXR ,USW00054734

您可以使用：

awk -F '[][" \t{},:]+' '{
a=b=""
for(i=2; i<=NF; i++)
   if ($i ~ /^K[A-Z]{3}$/)
      a=$i
   else if ($i ~ /^US[CW][0-9]+/)
      b=$i
   if (a != "" && b != "")
      print a, b
}' OFS=, file

KVSF,USW00054740
KBDL,USW00014740
KBDR,USW00094702
KDXR,USW00054734

awk-F'[][”\t{}，：]+'{
a=b=“”
对于（i=2；i如果
perl
正常（假设
K
字符串在
US
字符串之前在同一行中）


if/“（K[A-Z]{3}）\b.*”（US[CW]\d{8}\b）/
仅当此条件匹配时

打印“$1，$2”
打印两个捕获的组
“（K[A-Z]{3}）\b
匹配
K
后接三个大写字母，前提是前面加
”
并以单词边界结尾
“（US[CW]\d{8}\b
匹配
US
，后跟
C
或
W
，只有在前面加
”
并以单词边界结尾时才有八位数字

有关
-lne
选项的详细信息，请参阅
是的，我已经安装了
jq
。我还附加了当前输出和预期输出，以帮助进一步定义我要做的事情