add tagkey tag:: to data file in dir

add_tagkey_in_dir.bash

#!/bin/bash

get_line_tag(){
    tagval="$1"
    fpath="$2"
    # unable to check $? for this gawk
    line_tag=$(gawk -v ptn="$tagval([[:space:]]|$)" '$0~ptn && NR >= 3 && NR <= 5 {print NR":"$0;exit;}' "$fpath")
    #echo "line_tag: $line_tag"
}

check_is_target_line_tag(){
    # return 0: is target tagline;
    # return 1: is NOT target tagline;

    line_tag="$1"

    # check "" line_tag result
    # gawk won't add line num to unmatched result
    if [ "y" == "y$line_tag" ]
        then
        return 1
    fi

    # check "tag:" part in line_tag
    printf "$line_tag" | grep -q 'tag:'
    retval_grep=$?
    if [ 0 -eq $retval_grep ]
        then
        return 1
    fi
    
    taglist_inline="$(echo ${line_tag##*:})"
    #echo "taglist_inline:" $taglist_inline

    arr_taglist_inline=($taglist_inline)
    length_arr_taglist_inline=${#arr_taglist_inline[@]}
  
    if [ 1 -eq $length_arr_taglist_inline ]
        then
        return 0
    fi
    
    match_tag_inline_to_infile(){
        tag_inline=$1
                
        flag_matched=1
        for tag_infile in "${arr_taglist_infile[@]}"
            do
            if [ "$tag_infile" == "$tag_inline" ]
                then
                flag_matched=0
                break
            fi
        done
    }

    match_first_2_tags_to_tagfile(){
        # 0: all tags are matched in tag file
        # 1: a tag is not matched in tag file

        flag_tagline=0
        for i in `echo 0 1`
            do
            match_tag_inline_to_infile ${arr_taglist_inline[$i]}
            if [ 1 -eq $flag_matched ]
                then
                flag_tagline=1
                break
            fi
        done
    }
    
    if [ 2 -le $length_arr_taglist_inline ]
        then
        match_first_2_tags_to_tagfile
        return $flag_tagline
    fi
}

add_tagkey_to_file(){
    fpath="$1"
    
    for tag_infile in "${arr_taglist_infile[@]}"
        do
        get_line_tag "$tag_infile" "$fpath"
        line_num="${line_tag%%:*}"
        check_is_target_line_tag "$line_tag"
        retval=$?
        #echo "line_tag:" $line_tag "retval: " $retval
        if [ 0 -eq $retval ]
            then         
            line_filter="$line_num"
            tagkey="tag:: "
            substitute_operation="s/(^.*$)/$tagkey\1/"
            sed_directive="$line_filter $substitute_operation"
            sed -r "$sed_directive" -i "$fpath"
            break
        fi
    done
}

main(){
    fpath_taglist="$1"
    dpath_data="$2"

    mapfile -t arr_fpath_list < <(find "$dpath_data" -maxdepth 1 -type f)
    mapfile -t arr_taglist_infile < <(cat "$fpath_taglist")

    for fpath in "${arr_fpath_list[@]}"
        do
        add_tagkey_to_file "$fpath"
    done
}

main "$@"

test_add_tagkey_in_dir.bash

#!/bin/bash

init_time_log(){
    fpath_log=./time.log
    if [ -f $fpath_log ]
        then
        rm $fpath_log
    fi

    touch $fpath_log
}

log_datetime(){
    datef=`date '+%Y%m%d.%H%M%S'`
    echo "$1$datef" >> $fpath_log
}

init_script(){
    init_time_log
    log_datetime "Start script : "
}

finish_script(){
    log_datetime "Finish script : "
}

echo_start(){
    echo "$1 ============================="
}

init(){
    echo_start "Start $1 : "
    log_datetime "Start $1 : "
}

finish(){
    log_datetime "Finish $1 : "
}

run_tests(){     
    init_script

    for test in "$@"
        do
        init "$test"
        $test
        finish "$test"
    done
    
    finish_script
}

sed_line_tag(){
    tag_line="$1"
    fpath="$2"
    sed -r "3s/^.*$/$tag_line/" -i "$fpath"
}

test1(){
    fname1="200-earthquakes-detected-yellowstone..2018-02-21T19.09.09.md"
    fpath1=$dir_data/$fname1
    fname2="115-million-year-old-theropod-footprint-vandalised-australia-dinosaur-dreaming..2017-12-21T17.51.23.md"
    fpath2=$dir_data/$fname2
    fname3="50g宁夏生甘草茶2018-05-14T20.25.21.md"
    fpath3=$dir_data/$fname3
    fname4="45th_Legislative_District_Senate_Debate..2017-12-24T21.31.36.md"
    fpath4=$dir_data/$fname4
    fname5="2017 P&G Championships - Women - Day 2 - NBC Broadcast..2018-01-11T17.33.58.md"
    fpath5=$dir_data/$fname5
    sed_line_tag "bb vocabulary sciencealert" "$fpath1"
    sed_line_tag "vocabulary bb sciencealert" "$fpath2"
    sed_line_tag "中草药 甘草 bb" "$fpath3"
    sed -r "3s/^tag:: (.*)$/\1/" -i "$fpath4"
    sed_line_tag "vocabulary sciencealert" "$fpath5"
    ./add_tagkey_in_dir.bash "$fpath_taglist" "$dir_data"
    head "$fpath1"
    head "$fpath2"
    head "$fpath3"
    head "$fpath4"
    head "$fpath5"
}

test2(){
    fname="45th_Legislative_District_Senate_Debate..2017-12-24T21.31.36.md"
    fpath=$dir_data/$fname
    sed -r "3s/^tag:: (.*)$/\1/" -i "$fpath"
    head "$fpath"
    ./add_tagkey_in_dir.bash "$fpath_taglist" "$dir_data"
    head "$fpath"
}

fpath_taglist=./tag_list.txt
dir_data=~/data_mnt/txt_data_test/QOwnNotes/Notes.test
    
run_tests "test1"
#run_tests "test2"