使用 shell 绘制图表以获取总文件数和创建日期
Plot graph using shell for total file count and date created
我想创建一个直方图,Y 轴上的文件总数间隔为 50,X 轴上的创建时间以周为单位(即,如果新文件是在第 1 周和第 2 周之间创建的,依此类推)
类似于
某周内创建了 200、150、100、50 个文件
Y 轴上的 7、14、21、28 天。有点迷失了如何实现这一点。感谢任何帮助
更新:我正在尝试这些方法
find <dirname> -type f -ctime -1 -ctime -7 | wc -l
find <dirname> -type f -ctime +7 -ctime -14 | wc -l
找到最大数并将其用作我的 X 轴上限。然后将这个数字分成相等的间隔来绘制我的X轴
抱歉是 ksh 而不是 bash(bash 水平接近回声 "Hello World"):)...
这会满足您的需要吗?
#!/bin/ksh
######################################
#
# statDirReport.sh
#
version="1.0"
# Andre Gelinas, 2018
#
######################################
#############
# Variables
#############
typeset -F2 SCALE
# Max value of X
X_SCALE=30
#############
# Main
#############
if [[ -n ]]; then
DIRNAME=
else
print -n "Enter full path to stat : "; read DIRNAME
fi
if [[ ! -d $DIRNAME || ! -r $DIRNAME || ! -x $DIRNAME ]]; then
print "ERROR - Directory unusable - Exiting"
exit
fi
## Getting the data
CTIME1=1
CTIME2=0
for ((i=1;i<=4;i++)); do
CTIME2=$(($i*7))
FILE_COUNT[$i]=$(find $DIRNAME -type f -ctime +$CTIME1 -ctime -$CTIME2 | wc -l)
#To find late on the max amount
F_COUNT[${FILE_COUNT[$i]}]=${FILE_COUNT[$i]}
#
CTIME1=$CTIME2
done
#Doing some math
## Highest number of file
MAX_COUNT=${F_COUNT[-1]}
## Find the value of each tick
SCALE=$(($MAX_COUNT/$X_SCALE))
## Find the real length of the histogram for each week
## having the highest amount using full x scale (integer mathematics)
for ((i=1;i<=4;i++)); do
DATA_2_SCALE[$i]=$(((${FILE_COUNT[$i]}*$X_SCALE)/$MAX_COUNT))
done
# Getting the report
typeset -L2 Col1
typeset -L1 Col2
typeset -L$(($X_SCALE+5)) Col3
typeset -L5 Col4
Col1="Wk"
Col2=" "
Col3="Data"
Col4="Real"
clear
print "statDirReport v$version\tScale is #=$SCALE\n"
print "$Col1$Col2$Col3$Col4\n"
for ((i=1;i<=4;i++)); do
Col1=$i
Col2="|"
graph=""
Col4=${FILE_COUNT[$i]}
for ((j=1;j<=${DATA_2_SCALE[$i]};j++)); do
graph+="#"
done
Col3=$graph
print "$Col1$Col2$Col3$Col4"
done
编辑修改以添加日期作为直方图的标题。在 "DATA_2_SCALE" 循环之后修改最后一部分,使用 :
#Setting the title of each histogram
## Finding how many sec since the beginning of time
TODAY_SEC=$(date +"%s")
## Finding real date for find range
SEC_PER_DAY=86400
lastDate=$(date -u -d @"$TODAY_SEC" +"%m/%d")
for ((i=1;i<=4;i++)); do
firstDate=$(date -u -d @"$(($TODAY_SEC-(7*$i*$SEC_PER_DAY)))" +"%m/%d")
WEEK[$i]=$firstDate" to "$lastDate" "
lastDate=$firstDate
done
# Getting the report
typeset -L15 Col1
typeset -L1 Col2
typeset -L$(($X_SCALE+5)) Col3
typeset -L5 Col4
Col1="Wk"
Col2=" "
Col3="Data"
Col4="Real"
clear
print "statDirReport v$version\tScale is #=$SCALE\n"
print "$Col1$Col2$Col3$Col4\n"
for ((i=1;i<=4;i++)); do
Col1=${WEEK[$i]}
Col2="|"
graph=""
Col4=${FILE_COUNT[$i]}
for ((j=1;j<=${DATA_2_SCALE[$i]};j++)); do
graph+="#"
done
Col3=$graph
print "$Col1$Col2$Col3$Col4"
done
在主目录上使用 feedgnuplot
:
dirname=~
e=0
for f in `seq 7 7 28` ; do
find "${dirname}" -type f -ctime +$e -ctime -$f | wc -l
e=$f
done 2> /dev/null |
feedgnuplot --terminal 'dumb 50,15' --with boxes --unset grid --exit
输出:
5500 +-+-----+-------+------+-------+-----+-+
5000 +-+ ********* + + + +-+
4500 +-+ * * ******** +-+
4000 +-+ * * * * +-+
3500 +-+ * * * * +-+
3000 +-+ * * * * +-+
2500 +-+ * ********* * +-+
2000 +-+ * * * * +-+
1500 +-+ * * * * +-+
1000 +-+ * + * + * + ********* +-+
500 +-+-********************************-+-+
0 1 2 3 4 5
这是将 GNU awk 用于时间函数的开始(未经测试,因为您没有提供我们可以测试的简洁、可测试的样本输入):
find "" -type f -printf '%T@ %p[=10=]' |
awk -v RS='[=10=]' '
BEGIN {
nowSecs = systime()
}
{
fileName = gensub(/\S+\s+/,"",1)
fileModSecs = int()
fileAgeSecs = nowSecs - fileModSecs
fileAgeDays = int(fileAgeSecs / (24 * 60 * 60))
fileAgeWeeks = int(fileAgeDays / 7)
weekNr = fileAgeWeeks + 1
fileCnts[weekNr]++
numWeeks = (weekNr > numWeeks ? weekNr : numWeeks)
maxFileCnt = (fileCnts[weekNr] > maxFileCnt ? fileCnts[weekNr] : maxFileCnt)
print nowSecs, fileModSecs, fileAgeSecs, fileAgeDays, fileAgeWeeks, weekNr, fileName | "cat>&2"
}
END {
for (fileCnt=maxFileCnt; fileCnt>0; fileCnt--) {
for (weekNr=1; weekNr<=numWeeks; weekNr++) {
if (weekNr in fileCnts) {
char[weekNr] = "*"
}
printf "%s%s", char[weekNr], (weekNr<numWeeks ? OFS : ORS)
}
}
for (weekNr=1; weekNr<=numWeeks; weekNr++) {
printf "%s%s", weekNr, (weekNr<numWeeks ? OFS : ORS)
}
}
'
您需要找出 END 部分中用于打印直方图的循环的详细信息,但上面至少向您展示了如何在不多次调用 find 和硬编码数字的情况下按周获取文件数每周的天数。
我想创建一个直方图,Y 轴上的文件总数间隔为 50,X 轴上的创建时间以周为单位(即,如果新文件是在第 1 周和第 2 周之间创建的,依此类推)
类似于
某周内创建了 200、150、100、50 个文件 Y 轴上的 7、14、21、28 天。有点迷失了如何实现这一点。感谢任何帮助
更新:我正在尝试这些方法
find <dirname> -type f -ctime -1 -ctime -7 | wc -l
find <dirname> -type f -ctime +7 -ctime -14 | wc -l
找到最大数并将其用作我的 X 轴上限。然后将这个数字分成相等的间隔来绘制我的X轴
抱歉是 ksh 而不是 bash(bash 水平接近回声 "Hello World"):)...
这会满足您的需要吗?
#!/bin/ksh
######################################
#
# statDirReport.sh
#
version="1.0"
# Andre Gelinas, 2018
#
######################################
#############
# Variables
#############
typeset -F2 SCALE
# Max value of X
X_SCALE=30
#############
# Main
#############
if [[ -n ]]; then
DIRNAME=
else
print -n "Enter full path to stat : "; read DIRNAME
fi
if [[ ! -d $DIRNAME || ! -r $DIRNAME || ! -x $DIRNAME ]]; then
print "ERROR - Directory unusable - Exiting"
exit
fi
## Getting the data
CTIME1=1
CTIME2=0
for ((i=1;i<=4;i++)); do
CTIME2=$(($i*7))
FILE_COUNT[$i]=$(find $DIRNAME -type f -ctime +$CTIME1 -ctime -$CTIME2 | wc -l)
#To find late on the max amount
F_COUNT[${FILE_COUNT[$i]}]=${FILE_COUNT[$i]}
#
CTIME1=$CTIME2
done
#Doing some math
## Highest number of file
MAX_COUNT=${F_COUNT[-1]}
## Find the value of each tick
SCALE=$(($MAX_COUNT/$X_SCALE))
## Find the real length of the histogram for each week
## having the highest amount using full x scale (integer mathematics)
for ((i=1;i<=4;i++)); do
DATA_2_SCALE[$i]=$(((${FILE_COUNT[$i]}*$X_SCALE)/$MAX_COUNT))
done
# Getting the report
typeset -L2 Col1
typeset -L1 Col2
typeset -L$(($X_SCALE+5)) Col3
typeset -L5 Col4
Col1="Wk"
Col2=" "
Col3="Data"
Col4="Real"
clear
print "statDirReport v$version\tScale is #=$SCALE\n"
print "$Col1$Col2$Col3$Col4\n"
for ((i=1;i<=4;i++)); do
Col1=$i
Col2="|"
graph=""
Col4=${FILE_COUNT[$i]}
for ((j=1;j<=${DATA_2_SCALE[$i]};j++)); do
graph+="#"
done
Col3=$graph
print "$Col1$Col2$Col3$Col4"
done
编辑修改以添加日期作为直方图的标题。在 "DATA_2_SCALE" 循环之后修改最后一部分,使用 :
#Setting the title of each histogram
## Finding how many sec since the beginning of time
TODAY_SEC=$(date +"%s")
## Finding real date for find range
SEC_PER_DAY=86400
lastDate=$(date -u -d @"$TODAY_SEC" +"%m/%d")
for ((i=1;i<=4;i++)); do
firstDate=$(date -u -d @"$(($TODAY_SEC-(7*$i*$SEC_PER_DAY)))" +"%m/%d")
WEEK[$i]=$firstDate" to "$lastDate" "
lastDate=$firstDate
done
# Getting the report
typeset -L15 Col1
typeset -L1 Col2
typeset -L$(($X_SCALE+5)) Col3
typeset -L5 Col4
Col1="Wk"
Col2=" "
Col3="Data"
Col4="Real"
clear
print "statDirReport v$version\tScale is #=$SCALE\n"
print "$Col1$Col2$Col3$Col4\n"
for ((i=1;i<=4;i++)); do
Col1=${WEEK[$i]}
Col2="|"
graph=""
Col4=${FILE_COUNT[$i]}
for ((j=1;j<=${DATA_2_SCALE[$i]};j++)); do
graph+="#"
done
Col3=$graph
print "$Col1$Col2$Col3$Col4"
done
在主目录上使用 feedgnuplot
:
dirname=~
e=0
for f in `seq 7 7 28` ; do
find "${dirname}" -type f -ctime +$e -ctime -$f | wc -l
e=$f
done 2> /dev/null |
feedgnuplot --terminal 'dumb 50,15' --with boxes --unset grid --exit
输出:
5500 +-+-----+-------+------+-------+-----+-+
5000 +-+ ********* + + + +-+
4500 +-+ * * ******** +-+
4000 +-+ * * * * +-+
3500 +-+ * * * * +-+
3000 +-+ * * * * +-+
2500 +-+ * ********* * +-+
2000 +-+ * * * * +-+
1500 +-+ * * * * +-+
1000 +-+ * + * + * + ********* +-+
500 +-+-********************************-+-+
0 1 2 3 4 5
这是将 GNU awk 用于时间函数的开始(未经测试,因为您没有提供我们可以测试的简洁、可测试的样本输入):
find "" -type f -printf '%T@ %p[=10=]' |
awk -v RS='[=10=]' '
BEGIN {
nowSecs = systime()
}
{
fileName = gensub(/\S+\s+/,"",1)
fileModSecs = int()
fileAgeSecs = nowSecs - fileModSecs
fileAgeDays = int(fileAgeSecs / (24 * 60 * 60))
fileAgeWeeks = int(fileAgeDays / 7)
weekNr = fileAgeWeeks + 1
fileCnts[weekNr]++
numWeeks = (weekNr > numWeeks ? weekNr : numWeeks)
maxFileCnt = (fileCnts[weekNr] > maxFileCnt ? fileCnts[weekNr] : maxFileCnt)
print nowSecs, fileModSecs, fileAgeSecs, fileAgeDays, fileAgeWeeks, weekNr, fileName | "cat>&2"
}
END {
for (fileCnt=maxFileCnt; fileCnt>0; fileCnt--) {
for (weekNr=1; weekNr<=numWeeks; weekNr++) {
if (weekNr in fileCnts) {
char[weekNr] = "*"
}
printf "%s%s", char[weekNr], (weekNr<numWeeks ? OFS : ORS)
}
}
for (weekNr=1; weekNr<=numWeeks; weekNr++) {
printf "%s%s", weekNr, (weekNr<numWeeks ? OFS : ORS)
}
}
'
您需要找出 END 部分中用于打印直方图的循环的详细信息,但上面至少向您展示了如何在不多次调用 find 和硬编码数字的情况下按周获取文件数每周的天数。