good day, i have a folder with 400 files and i want to print a "name" from the filenames
this is the structure
ej:
20201323223_vendo.perfil01_17872513294967257_1601950878_live.mp4
20201323223__vvcastrillon_12_17949951031375250_1601939874_live.mp4
2020323123_yessromero.g_17849208194340047_1601945592_live.mp4
2020323223_ziizii_08_17979840166310477_1601929868_live.mp4
and what i need is
vendo.perfil01
_vvcastrillon_12
yessromero.g
ziizii_08
Im try to loop in the files and separate whit the _ and extract the 2 and 3 token numeral conditioning but the result is wrong and missing variables
#echo off
setlocal EnableDelayedExpansion
:loop
SET max=5000
for /F "delims=" %%I in ('dir "*_*_*.mp4" /A-D /B /S 2^>nul ^| %SystemRoot%\System32\findstr.exe /I /L /V "\\outdir\\"') do (for /F "eol=| tokens=2,3 delims=_" %%J in ("%%~nI") do (SET "var="&for /f "delims=0123456789" %%a in ("%%K") do SET var=%%a
if defined var ( set nam=%%J_%%K ) else ( set nam=%%J )
)
echo/!nam!
)
timeout 10 > nul
goto loop
i think the answer is remove the first number before the _ then the string _xxxxxx_xxxxxxx_live.mp4 at the end but i dont know how read in reverse the tokens
tanks for any help
Since you have got different numbers of _-separated items in your file names and even adjacent _, so using for /F to split them into specific tokens with delims=_ is not the best choice.
I would use a standard for-loop instead, which receives modified file names, namely with each _ replaced by " " and enclosed within "", which leads to SPACE-separated partial name items. So:
20201323223_vendo.perfil01_17872513294967257_1601950878_live.mp4
is changed to:
"20201323223" "vendo.perfil01" "17872513294967257" "1601950878" "live.mp4"
before looping. Within the loop implement an index counter and just append those items to a buffer whose index numbers lie within a certain range that depends on the total number of items.
Here is an example script that demonstrates what I mean:
#echo off
setlocal EnableExtensions DisableDelayedExpansion
rem // Define constants here:
set "_ROOT=%~dp0." & rem // (full path to target directory)
set "_MASK=*_*_*_*_live.mp4" & rem // (pattern to match file names)
set "_FILT=^[0123456789][0123456789]*_..*_[0123456789][0123456789]*_[0123456789][0123456789]*_live\.mp4$"
rem // (additional `findstr` filter for file names)
set /A "_POS=1" & rem /* (index of first `_`-separated item to extract;
rem `0` is the first item, `-1` is the last) */
set /A "_NUM=-4" & rem /* (number of `_`-separated items to extract;
rem `-1` means all up to the last item) */
rem // Change into target directory:
pushd "%_ROOT%" && (
rem // Loop through all matching non-hidden, non-system files:
for /F "delims= eol=|" %%F in ('
dir /B /A:-D-H-S "%_MASK%" ^| findstr /I /R /C:"%_FILT%"
') do (
rem // Store current file name, initialise item index, counter and buffer:
set "FILE=%%F" & set /A "IDX=-1, CNT=-1" & set "BUFF=_"
rem // Toggle delayed expansion to avoid troubles with `!`:
setlocal EnableDelayedExpansion
rem // Count number of items and store one less:
rem set "TEST=%FILE:_=" & set /A "CNT+=1" & set "TEST=%"
for %%I in ("!FILE:_=" "!") do set /A "CNT+=1"
rem // Determine item index position from given index and number:
if !_POS! lss 0 (set /A "BEG=CNT+_POS+1") else set /A "BEG=_POS"
if !_NUM! lss 0 (set /A "END=CNT+_NUM+1") else set /A "END=_POS+_NUM-1"
rem // Transport numbers over `endlocal` barrier:
for %%C in (!CNT!) do for %%B in (!BEG!) do for %%A in (!END!) do (
rem // Loop through `_`-separated items of file name:
for %%I in ("!FILE:_=" "!") do (
rem // Store current item, increment item index:
endlocal & set "ITEM=%%~I" & set /A "IDX+=1"
setlocal EnableDelayedExpansion
rem // Append current item to buffer if in range:
if !IDX! geq %%B if !IDX! leq %%A (
rem // Transport buffer over `endlocal` barrier:
for /F "delims=" %%E in ("BUFF=!BUFF!_!ITEM!") do (
endlocal & set "%%E"
setlocal EnableDelayedExpansion
)
)
)
)
rem // Return buffer:
echo(!BUFF:~2!
endlocal
)
rem // Return from target directory:
popd
)
endlocal
exit /B
Something like this should help:
#echo off
setlocal enabledelayedexpansion
for /f "tokens=1* delims=_." %%i in ('dir /b /s /a-d "*_*_*.mp4"2^>nul ^| findstr.exe /ILV "\\outdir\\"') do (
set "var=%%j"
for /f "tokens=2,* delims=_." %%a in ("%%j") do echo !var:_%%b=!
)
Keep in mind that using delims will also split on consecutive characters like double underscore. for those you need to predetermine which has double underscore and let the script add it for you.
#ECHO OFF
SETLOCAL
for %%a in (
20201323223_vendo.perfil01_17872513294967257_1601950878_live.mp4
20201323223__vvcastrillon_12_17949951031375250_1601939874_live.mp4
2020323123_yessromero.g_17849208194340047_1601945592_live.mp4
2020323223_ziizii_08_17979840166310477_1601929868_live.mp4
) do set "filename=%%a" &call :process&echo --------------------------------------
GOTO :EOF
:process
echo stage 1 %filename%
:: step 1 : delete all characters up to and including the first underscore
set "filename=%filename:*_=%"
echo stage 2 %filename%
:: step 2 : find all numeric strings of length 4 or more in remainder
call :strsgt4 %filename:_= %
:: step 3 : replace each numeric string of length 4 or more + preceding underscore with "/" (invalid filename character)
echo stage 3 %filename%
:proc3lp
if "%zapstrings%" neq " " for %%v in (%zapstrings%) do call set "filename=%%filename:_%%v=/%%"&call set "zapstrings=%%zapstrings: %%v=%%"&goto proc3lp
echo stage 4 %filename%
:: step 5 : Remove all charactersincluding and after the first "/"
for /f "delims=/" %%v in ("%filename%") do echo result %%v
goto :eof
:strsgt4
set "zapstrings= "
:strsgt4loop
set "test=%1"
if not defined test goto :eof
set "test=%test:~4%"
if defined test call :isnum %test%&if not defined notnumber set "zapstrings=%zapstrings% %1"
shift
goto strsgt4loop
:: Determine whether %1 is purely numeric
:isnum
SET "notnumber=9%~1"
FOR /l %%z IN (0,1,9) DO CALL SET "notnumber=%%notnumber:%%z=%%"
GOTO :eof
Really a question of working out what your rules are.
I decided that your rules were: string after the first underscore, until before the first subsequent underscore that precedes a numeric string or length greater than 3
The %%a loop simply submits a sequence of sample strings to :process
The inline comments should explain the remainder.
Related
So what I'm trying to do is create a find for multiple people where it in the text file it will say names and numbers like
Example of text file:
Beth
1234567891
Jay
2134456544
This is the best way I can explain what I'm trying to do:
#echo off
set "file=Test1.txt"
setlocal EnableDelayedExpansion
<"!file!" (
for /f %%i in ('type "!file!" ^| find /c /v ""') do set /a n=%%i && for /l %%j in (1 1 %%i) do (
set /p "line_%%j="
)
)
set /a Name=1
set /a Number=2
Echo Line_%Name%> %Name%.txt (Im trying to get this to say line_2 to say 1st line in the text file)
Echo Line_%Number%> %Name%.txt (Im trying to get this to say line_2 to say 2nd line in the text file)
:Start
set /a Name=%Name%+2 (These are meant to take off after 1 so lines 3,5,7,9 so on)
set /a Number=%Number%+2 (These are meant to take off after 2 so lines 4,6,8,10 so on)
Echo Line_%Name%
Echo Line_%Number%
GOTO :Start
so the outcome would be
In Beth.txt:
Beth
1234567891
So every name will be a file name and the first line in a file. I will change it later so I can do a addition in each text file.
Name: Beth
Number: 1234567891
#ECHO OFF
SETLOCAL ENABLEDELAYEDEXPANSION
SET "sourcedir=u:\your files"
SET "destdir=u:\your results"
SET "filename1=%sourcedir%\q65417881.txt"
rem make sure arrays are empty
For %%b IN (name number) DO FOR /F "delims==" %%a In ('set %%b[ 2^>Nul') DO SET "%%a="
rem Initialise counter and entry array
SET /a count=0
SET "number[0]=dummy"
FOR /f "usebackqdelims=" %%a IN ("%filename1%") DO (
IF DEFINED number[!count!] (SET /a count+=1&SET "name[!count!]=%%a") ELSE (SET "number[!count!]=%%a")
)
rem clear out dummy entry
SET "number[0]=dummy"
FOR /L %%c IN (1,1,%count%) DO (
rem replace spaces with dashes
SET "name[%%c]=!name[%%c]: =-!"
rem report to console rem report to console
ECHO Name: !name[%%c]! Number: !number[%%c]!
rem generate name.txt file
(
ECHO !name[%%c]!
ECHO !number[%%c]!
)>"%destdir%\!name[%%c]!.txt"
)
GOTO :EOF
You would need to change the values assigned to sourcedir and destdir to suit your circumstances. The listing uses a setting that suits my system.
I deliberately include spaces in names to ensure that the spaces are processed correctly.
I used a file named q65417881.txt containing your data for my testing.
The line data read from the file is assigned to %%a is assigned to and number[!count!] alternately. The data is retained in these arrays for use by further processing.
[Edited to include conversion of spaces within names to dashes]
If I understand correctly, you want to precede every second line with Number: + SPACE and every other line with Name: + SPACE. For this you do not need to store each line in a variable first, you can use a single for /F loop lo read the file line by line and process every line individually. There are two possibilities:
Temporarily precede every line with a line number plus : using findstr /N:
#echo off
rem // Loop through lines and precede each with line number plus `:`:
for /F "tokens=1* delims=:" %%K in ('findstr /N "^" "Test1.txt"') do (
rem // Calculate remainder of division by two:
set /A "MOD=%%K%%2" 2> nul
rem // Toggle delayed expansion to avoid issues with `!`:
setlocal EnableDelayedExpansion
rem // Conditionally return line string with adequate prefix:
if !MOD! neq 0 (
endlocal & echo Name: %%L
) else (
endlocal & echo Number: %%L
)
)
This will fail when a line begins with the a :.
Check whether numeric representation of current line string is greater than 0:
#echo off
rem // Loop through (non-empty) lines:
for /F "usebackq delims=" %%L in ("Test1.txt") do (
rem // Determine numeric representation of current line string:
set /A "NUM=%%L" 2> nul
rem // Toggle delayed expansion to avoid issues with `!`:
setlocal EnableDelayedExpansion
rem // Conditionally return line string with adequate prefix:
if !NUM! equ 0 (
endlocal & echo Name: %%L
) else (
endlocal & echo Number: %%L
)
)
This fails when a name begins with numerals and/or when a numeric line is 0.
And just for the sake of posting something different:
#SetLocal EnableExtensions DisableDelayedExpansion & (Set LF=^
% 0x0A %
) & For /F %%G In ('Copy /Z "%~f0" NUL') Do #Set "CR=%%G"
#For /F "Tokens=1,2* Delims=:" %%G In ('%__AppDir__%cmd.exe /D/V/C ^
"%__AppDir__%findstr.exe /NR "^[a-Z]*!CR!!LF![0123456789]" "Test1?.txt" 2>NUL"
') Do #(SetLocal EnableDelayedExpansion
(Set /P "=Name: %%I!CR!!LF!Number: " 0<NUL & Set "_="
For /F Delims^=^ EOL^= %%J In ('%__AppDir__%more.com +%%H "%%G"') Do #(
If Not Defined _ Set "_=_" & Echo %%J)) 1>"%%I.txt" & EndLocal)
This file should be run with the Test1.txt file in the current working directory. It is important that along side Test1.txt, there are no other .txt files with the same basename followed by one other character, (for example Test1a.txt or Test12.txt). Should you wish to change your filename, just remember that you must suffix its basename in the above code with a ? character, (e.g. MyTextFile.log ⇒ MyTextFile?.log).
I had the rare opportunity to verify that this script worked against the following example Test1.txt file:
Beth
1234567891
Jay
2134456544
Bob
2137856514
Jimmy
4574459540
Mary
3734756547
Gemma
6938456114
Albert
0134056504
I started using batch commands last week and I've reached a real obstacle with a script I made.
What I want to do
Move a PDF file from C:\Users\JK\Documents\reports PDFs into pre-made subfolders in the destination W:\Departments\QA\cases.
For example the script would move 2223 report.pdf to W:\Departments\QA\cases\2201 - 2300\2223
What I tried
I made a script based off the answer in this thread
cls
#pushd %~dp0
#echo off
setlocal EnableExtensions DisableDelayedExpansion
set "SourceDir=C:\Users\JK\Documents\reports PDFs"
set "DestDir=W:\Departments\QA\cases\"
for /F "eol=| delims=" %%A in ('dir /B /A-D-H "%SourceDir%\*.pdf" 2^>nul') do (
for /F "eol=| tokens=1" %%B in ("%%~nA") do (
for /D %%C in ("%DestDir%\%%B*") do move /Y "%SourceDir%\%%A" "%%C\"
)
)
endlocal
popd
pause
Where I am stuck
How could I add subfolders or account for them in the destination directory?
FYI, I also tried adding a wildcard symbol at the end of the destination directory by changing %DestDir%\%%B to %DestDir%\*\%%B*.
I would probably accomplish the task with the following script (see all the explanatory rem remarks):
#echo off
setlocal EnableExtensions DisableDelayedExpansion
rem // Define constants here:
set "_SOURCE=C:\Users\JK\Documents\reports PDFs" & rem // (source directory; `.` or `` is current, `%~dp0.` is script parent)
set "_TARGET=W:\Departments\QA\cases" & rem // (target directory; `.` or `` is current, `%~dp0.` is script parent)
set "_SUBDIR=#" & rem // (set to non-blank value in order to create individual sub-directories)
set "_FMASK=????*.pdf" & rem // (pattern to match source files)
set "_DMASK=???? - ????*" & rem // (pattern to match target directories)
set "_FFIL1=^[0123456789][0123456789][0123456789][0123456789] .*\.pdf$" & rem // (filter 1 for source files)
set "_FFIL2=^[0123456789][0123456789][0123456789][0123456789]\.pdf$" & rem // (filter 2 for source files)
set "_DFIL1=^[0123456789][0123456789][0123456789][0123456789] - [0123456789][0123456789][0123456789][0123456789] .*$"
set "_DFIL2=^[0123456789][0123456789][0123456789][0123456789] - [0123456789][0123456789][0123456789][0123456789]$"
rem // Change into source directory:
pushd "%_SOURCE%" && (
rem // Iterate through all files matching the specified pattern and filters:
for /F "eol=| delims=" %%F in ('
dir /B /A:-D-H-S "%_FMASK%" ^| findstr /I /R /C:"%_FFIL1%" /C:"%_FFIL2%"
') do (
rem // Store full path of currently iterated file:
set "FILE=%%~fF"
rem // Extract the leading numeric part of the file name:
for /F "eol=| delims= " %%N in ("%%~nF") do (
rem // Store the numeric part:
set "NUM=%%N"
rem /* Remove any leading zeros from the numeric part of the file name, because
rem such cause the number to be unintentionally interpreted as octal: */
set /A "INT=0" & for /F "eol=| tokens=* delims=0" %%Z in ("%%N") do 2> nul set /A "INT=%%Z"
)
rem // Change into target directory:
pushd "%_TARGET%" && (
rem // Iterate through all directories matching the specified pattern and filters:
for /F "eol=| delims=" %%D in ('
cmd /V /C 2^> nul dir /B /A:D-H-S "!_DMASK:|=%%I!" ^| findstr /I /R /C:"%_DFIL1%" /C:"%_DFIL2%"
') do (
rem // Store name of currently iterated directory:
set "TDIR=%%D"
rem // Extract first (from) and second (to) numeric parts of directory names:
for /F "eol=| tokens=1-2 delims=- " %%S in ("%%D") do (
rem // Remove any leading zeros from first (from) numeric part:
set /A "FRM=0" & for /F "eol=| tokens=* delims=0" %%Z in ("%%S") do set /A "FRM=%%Z"
rem // Remove any leading zeros from second (to) numeric part:
set /A "TOO=0" & for /F "eol=| tokens=* delims=0" %%Z in ("%%T") do set /A "TOO=%%Z"
)
rem // Toggle delayed variable expansion to avoid trouble with `!`:
setlocal EnableDelayedExpansion
rem /* Do integer comparisons to check whether the numeric part of the file name
rem lies within the range given by the directory name (from/to): */
if !INT! geq !FRM! if !INT! leq !TOO! (
rem // Numeric part of file name lies within range, hence try to move file:
if defined _SUBDIR (
2> nul md "!TDIR!\!NUM!"
ECHO move "!FILE!" "!TDIR!\!NUM!\"
) else (
ECHO move "!FILE!" "!TDIR!\"
)
)
endlocal
)
rem // Return from target directory:
popd
)
)
rem // Return from source directory:
popd
)
endlocal
exit /B
You may need to adapt a few constants to your situation in the section commented with Define constants here: at the top.
After having tested the script for the correct output, remove the upper-case ECHO commands in front of the move commands! In order to avoid multiple 1 file(s) moved. messages, replace these ECHO commands by > nul.
I have a folder with files that are (ideally) sequentially named. But sometimes I want to add a new file into the sequence, which I do by appending a letter, so that it still sorts in the right order, e.g.
I want a batch that renames these back into a proper sequence, i.e. P01.svg, P02.svg, P03.svg, etc. Of course, the correct order must be preserved in the process.
I've tried various things, but can't find a solution that preserves the order... sometimes the renaming appears to be done in the wrong order so that the files get out of sequence. My latest attempt is:
#echo off
setlocal EnableExtensions EnableDelayedExpansion
REM first rename with xxx prefix to avoid name clashes, then do a second loop to remove the xxx prefix
set /a i=1
for /f "delims=" %%a in ('dir *.svg /b /a-d-h-s') do (
set "p=0!i!"
ren "%%a" "xxxP!p:~-2!.svg"
set /a i = i + 1
)
REM second loop...
set /a i=1
for /f "delims=" %%a in ('dir *.svg /b /a-d-h-s') do (
set "p=0!i!"
ren "%%a" "P!p:~-2!.svg"
set /a i = i + 1
)
Why are the renamed files not in the correct order every time?
You don't need you first loop. A simple ren command is sufficient.
For the correct order (by name), just expand the dircommand with the /on option ("Order by Name")
#echo off
setlocal enabledelayedexpansion
ren *.svg *.svg.tmp
set nr=100
for /f "delims=" %%a in ('dir /b /a-d-h-s /on *.svg.tmp') do (
set /a nr+=1
ECHO ren "%%a" "P!nr:~-2!.svg"
)
Note: I disabled the ren command for security reasons. When the output fits your needs, just remove the ECHO
You do not need to use two loops and neither do you have to rename the files twice. If you simply count the number of files in advance and then rename then in descending order (hence from highest to lowest) there should not be any collisions possible, given that the files have got consecutive numbers (no gaps allowed).
Here is a script that does exactly this (see all the explanatory rem remarks in the code):
#echo off
setlocal EnableExtensions DisableDelayedExpansion
rem // Define constants here:
set "_ROOT=" & rem /* (root directory; empty or `.` is current,
rem `%~dp0.` is location of this script) */
set "_PREF=P" & rem // (desired file name prefix)
set "_MASK=%_PREF%*.svg" & rem // (search pattern for files)
set /A "_DIGS=2" & rem // (number of digits in the new names)
rem // Get limit of number of files that can be handled:
set /A "CNT=1" & for /L %%D in (1,1,%_DIGS%) do set /A "CNT*=10"
rem // Change into root directory:
pushd "%_ROOT%" && (
rem // Count number of matching files, quit if there are too many:
for /F %%C in ('dir /B /A:-D-H-S "P*.svg" ^| find /C /V ""') do (
set /A "CNT+=%%C" & if %%C geq %CNT% exit /B 2
)
rem /* List files sorted in descending order by name and prepend
rem with an ascending index number: */
for /F "tokens=1* delims=:" %%E in ('
dir /B /A:-D-H-S /O:-N "P*.svg" ^| findstr /N "^"
') do (
rem /* Split off the index number and determine the new number
rem to be used in the new file name: */
set /A "FNUM=CNT-%%E+1"
rem // Store the current file base name and extension:
set "FILE=%%~nF" & set "FEXT=%%~xF"
setlocal EnableDelayedExpansion
rem // Actually rename the file:
ECHO ren "!FILE!!FEXT!" "!_PREF!!FNUM:~-%_DIGS%!!FEXT!"
endlocal
)
popd
)
endlocal
exit /B
After having tested for the correct output, remove the upper-case ECHO command!
This is an approved variant that can even handle collisions (meaning a file with a new name already exists), which may occur when there are gaps in the original (numeric) sequence of file names; in such cases, an additional suffix .tmp is temporarily appended and after having processed all files that suffix becomes removed by a single ren command:
#echo off
setlocal EnableExtensions DisableDelayedExpansion
rem // Define constants here:
set "_ROOT=" & rem /* (root directory; empty or `.` is current,
rem `%~dp0.` is location of this script) */
set "_PREF=P" & rem // (desired file name prefix)
set "_MASK=%_PREF%*.svg" & rem // (search pattern for files)
set "_SUFF=.tmp" & rem // (temporary suffix to handle collisions)
set /A "_DIGS=2" & rem // (number of digits in the new names)
rem // Get limit of number of files that can be handled:
set /A "CNT=1" & for /L %%D in (1,1,%_DIGS%) do set /A "CNT*=10"
rem // Change into root directory:
pushd "%_ROOT%" && (
rem // Terminate if there are files with the temporary suffix:
if defined _SUFF if exist "%_MASK%%_SUFF%" popd & exit /B 3
rem // Count number of matching files, quit if there are too many:
for /F %%C in ('dir /B /A:-D-H-S "P*.svg" ^| find /C /V ""') do (
set /A "CNT+=%%C" & if %%C geq %CNT% popd & exit /B 2
)
rem /* List files sorted in descending order by name and prepend
rem with an ascending index number: */
for /F "tokens=1* delims=:" %%E in ('
dir /B /A:-D-H-S /O:-N "P*.svg" ^| findstr /N "^"
') do (
rem /* Split off the index number and determine the new number
rem to be used in the new file name: */
set /A "FNUM=CNT-%%E+1"
rem // Store the current file base name and extension:
set "FILE=%%~nF" & set "EXTF=%%~xF" & set "EXTT="
setlocal EnableDelayedExpansion
rem /* Actually rename the file; in case of collisions, append
rem another suffix to the name and rename again later: */
set "NAME=!_PREF!!FNUM:~-%_DIGS%!!EXTF!"
if /I not "!FILE!!EXTF!"=="!NAME!" (
if exist "!NAME!" set "EXTT=!_SUFF!"
ECHO ren "!FILE!!EXTF!" "!NAME!!EXTT!"
)
endlocal
)
rem // Resolve potential collisions, so remove additional suffixes:
setlocal EnableDelayedExpansion
if defined _SUFF if exist "!_MASK!!_SUFF!" ren "!_MASK!!_SUFF!" "*."
endlocal & popd
)
endlocal
exit /B
Again remove the upper-case ECHO command to actually rename files!
I'm making a script that sorts video files into folders by checking for known keywords in the file. As the amount of keywords grows out of control the script becomes very slow, taking several seconds for each file to be processed.
#echo off
cd /d d:\videos\shorts
if /i not "%cd%"=="d:\videos\shorts" echo invalid shorts dir. && exit /b
:: auto detect folder name via anchor file
for /r %%i in (*spirit*science*chakras*) do set conspiracies=%%~dpi
if not exist "%conspiracies%" echo conscpiracies dir missing. && pause && exit /b
for /r %%i in (*modeselektor*evil*) do set musicvideos=%%~dpi
if not exist "%musicvideos%" echo musicvideos dir missing. && pause && exit /b
for %%s in (*) do set "file=%%~nxs" & set "full=%%s" & call :count
for %%v in (*) do echo can't sort "%%~nv"
exit /b
:count
set oldfile="%file%"
set newfile=%oldfile:&=and%
if not %oldfile%==%newfile% ren "%full%" %newfile%
set count=0
set words= & rem
echo "%~n1" | findstr /i /c:"music" >nul && set words=%words%, music&& set /a count+=1
echo "%~n1" | findstr /i /c:"official video" >nul && set words=%words%, official video&& set /a count+=2
set words=%words:has, =has %
set words=%words: , =%
if not %count%==0 echo "%file%" has "%words%" %count%p for music videos
set musicvideoscount=%count%
set count=0
set words= & rem
echo "%~n1" | findstr /i /c:"misinform" >nul && set words=%words%, misinform&& set /a count+=1
echo "%~n1" | findstr /i /c:"antikythera" >nul && set words=%words%, antikythera&& set /a count+=2
set words=%words:has, =has %
set words=%words: , =%
if not %count%==0 echo "%file%" has "%words%" %count%p for conspiracies
set conspiraciescount=%count%
set wanted=3
set winner=none
:loop
:: count points and set winner (in case of tie lowest in this list wins, sort accordingly)
if %conspiraciescount%==%wanted% set winner=%conspiracies%
if %musicvideoscount%==%wanted% set winner=%musicvideos%
set /a wanted+=1
if not %wanted%==15 goto loop
if not "%winner%"=="none" move "%full%" "%winner%" >nul && echo "%winner%%file%" && echo.
Notice the "weight value" for each keyword. It counts the total points for each category, finds the largest value and moves the file to the folder appointed to that category. It also displays the words it has found and lastly lists files it finds unsortable so I can add keywords or tweak weight values.
I have stripped the amount of folders and keywords in this sample to bare minimum. The full script has six folders and 64k size with all the keywords (and growing).
#ECHO OFF
SETLOCAL
SET "sourcedir=U:\sourcedir"
SET "tempfile=%temp%\somename"
SET "categories=music conspiracies"
REM SET "categories=conspiracies music"
(
FOR /f "tokens=1,2,*delims=," %%s IN (q45196316.txt) DO (
FOR /f "delims=" %%a IN (
'dir /b /a-d "%sourcedir%\*%%u*" 2^>nul'
) DO (
ECHO %%a^|%%s^|%%t
)
)
)>"%tempfile%"
SET "lastname="
FOR /f "tokens=1,2,*delims=|" %%a IN ('sort "%tempfile%"') DO (
CALL :resolve %%b %%c "%%a"
)
:: and the last entry...
CALL :resolve dummy 0
GOTO :EOF
:resolve
IF "%~3" equ "%lastname%" GOTO accum
:: report and reset accumulators
IF NOT DEFINED lastname GOTO RESET
SET "winner="
SET /a maxfound=0
FOR %%v IN (%categories%) DO (
FOR /f "tokens=1,2delims=$=" %%w IN ('set $%%v') DO CALL :compare %%w %%x
)
IF DEFINED winner ECHO %winner% %lastname:&=and%
:RESET
FOR %%v IN (%categories%) DO SET /a $%%v=0
SET "lastname=%~3"
:accum
SET /a $%1+=%2
GOTO :eof
:compare
IF %2 lss %maxfound% GOTO :EOF
IF %2 gtr %maxfound% GOTO setwinner
:: equal scores use categories to determine
IF DEFINED winner GOTO :eof
:Setwinner
SET "winner=%1"
SET maxfound=%2
GOTO :eof
You would need to change the setting of sourcedir to suit your circumstances.
I used a file named q45196316.txt containing this category data for my testing.
music,6,music
music,8,Official video
conspiracies,3,misinform
conspiracies,6,antikythera
missing,0,not appearing in this directory
I believe your problem is that repeatedly executing findstr is time-consuming.
This approach uses a data file containing lines of category,weight,mask. The categories variable contains a list of the categories in order of preference (for when the score is equal)
Read the data file, assigning category to %%s, weight to %%t and mask to %%u and then do a directory-scan using the mask. This will echo a line to the tempfile in the format name|category|weight for each name-match found. dir seems to be very fast after the first scan.
The resultant tempfile will thus have one line for each filename+category plus the weight, so if a filename fits into more than one category, more than one entry will be created.
We then scan a sorted version of that file and resolve the score.
First, if the filename changes, we can report on the last filename. This is done by comparing the values in the variables $categoryname. Since these are scanned in the order %categories% then the first category in the list is chosen if there is an equivalence of scores. The scores are then reset and lastname initialised to the new filename.
We then accumulate the score into $categoryname
So - I believe that will be a bit faster.
Revision
#ECHO OFF
SETLOCAL ENABLEDELAYEDEXPANSION
SET "sourcedir=U:\sourcedir"
SET "tempfile=%temp%\somename"
SET "categories="rock music" music conspiracies"
REM SET "categories=conspiracies music"
:: set up sorting categories
SET "sortingcategories="
FOR %%a IN (%categories%) DO SET "sortingcategories=!sortingcategories!,%%~a"
SET "sortingcategories=%sortingcategories: =_%"
:: Create "tempfile" containing lines of name|sortingcategory|weight
(
FOR /f "tokens=1,2,*delims=," %%s IN (q45196316.txt) DO (
SET "sortingcategory=%%s"
SET "sortingcategory=!sortingcategory: =_!"
FOR /f "delims=" %%a IN (
'dir /b /a-d "%sourcedir%\*%%u*" 2^>nul'
) DO (
ECHO %%a^|!sortingcategory!^|%%t^|%%s^|%%u
)
)
)>"%tempfile%"
SET "lastname="
SORT "%tempfile%">"%tempfile%.s"
FOR /f "usebackqtokens=1,2,3delims=|" %%a IN ("%tempfile%.s") DO (
CALL :resolve %%b %%c "%%a"
)
:: and the last entry...
CALL :resolve dummy 0
GOTO :EOF
:: resolve by totalling weights (%2) in sortingcategories (%1)
:: for each name (%3)
:resolve
IF "%~3" equ "%lastname%" GOTO accum
:: report and reset accumulators
IF NOT DEFINED lastname GOTO RESET
SET "winner=none"
SET /a maxfound=0
FOR %%v IN (%sortingcategories%) DO (
FOR /f "tokens=1,2delims=$=" %%w IN ('set $%%v') DO IF %%x gtr !maxfound! (SET "winner=%%v"&SET /a maxfound=%%x)
)
ECHO %winner:_= % %lastname:&=and%
:RESET
FOR %%v IN (%sortingcategories%) DO SET /a $%%v=0
SET "lastname=%~3"
:accum
SET /a $%1+=%2
GOTO :eof
I've added a few significant comments.
You can now have spaces in category names - you need to quote the name (for reporting purposes) within the set catagories... statement.
sortingcategories is automatically derived - it's only used for sorting and is simply the categories with any space in a name replaced by an underscore.
In creating the tempfile, the category is processed to contain underscores (the sortingcategory) and when the final placement is resolved, the underscores are removed returning the category name.
Negative weights should now be processed appropriately.
-- further revision for "not append *"
FOR /f "tokens=1-5delims=," %%s IN (q45196316.txt) DO (
SET "sortingcategory=%%s"
SET "sortingcategory=!sortingcategory: =_!"
FOR %%z IN ("!sortingcategory!") DO (
SETLOCAL disabledelayedexpansion
FOR /f "delims=" %%a IN (
'dir /b /a-d "%sourcedir%\%%~v%%u%%~w" 2^>nul'
AND
add 2 extra columns to the q45196316 file
music,6,music,*,*
music,8,Official video,"",*
conspiracies,3,misinform,*,*
conspiracies,6,kythera,*anti,*
missing,0,not appearing in this directory,*,*
rock music,2,metal,*,*
conspiracies,-5,negative,*,*
The for /f ... %%s now generates %%v and %%w containing the last two columns (as tokens is nor 1-5)
These are applied as prefix and suffix to %%u in the dir command. Note that "" should be used for nothing as two successive , are parsed as a single separator. The ~ before the v/w in %%~v means remove the quotes.
I try to replace the n-th element of a CSV string, without knowing his value. For example, here is my string :
*;*;*;element_to_replace;*;*
With * an undefined string, it can be anything.
So i tried to use :
for /F "delims=" %%w in (file\workstation) do (
set line=%%w
if !compt! NEQ 0 (
set new_line=!line:*;*;*;*=*;*;*;new_value!
#echo !new_line! >> file\tmp_workstation
) else (
#echo !header_workstation! >> file\tmp_workstation
)
set /A "compt+=1"
)
It doesn't work. Am i doing something wrong ?
#echo off
setlocal enabledelayedexpansion
REM you want to replace token 4:
for /f "tokens=1-4,* delims=;" %%a in (t.csv) do (
echo %%a;%%b;%%c;replaced;%%e
)
tokens=1-4,* means: take the first four tokens, the fifth token is "the rest of the line". %%a is the first token, %%b is the second one etc.
You want to write token1;token2;token3,"replacement string for the fourth token(%%d)";"rest of the line" (fifth token).
Supposing the * characters do not appear literally within your data and it does also not contain any ? marks, you could use the following code snippet:
#echo off
setlocal EnableExtensions DisableDelayedExpansion
rem // Define constants here:
set "INFILE=file\workstation"
set "OUTFILE=file\tmp_workstation"
set "SEPARATOR=;"
set /A "COL_NUM=4"
set "COL_NEWVAL=new_value"
rem // A single redirection:
> "%OUTFILE%" (
set "HEADER=#"
rem // Read CSV file line by line:
for /F usebackq^ delims^=^ eol^= %%L in ("%INFILE%") do (
set "LINE=%%L"
if defined HEADER (
rem // Skip header from replacement:
set "NEW_LINE=%%L"
set "HEADER="
) else (
set "NEW_LINE=" & set "SEP=" & set /A "IDX=0"
rem // Toggle delayed expansion to not lose any `!`:
setlocal EnableDelayedExpansion
set "LINE=!LINE:"=""!^"
rem // Use standard `for` loop to enumerate column values:
for %%I in ("!LINE:%SEPARATOR%=","!") do (
endlocal
set /A "IDX+=1"
set "ITEM=%%~I"
setlocal EnableDelayedExpansion
rem // Replace column value if index matches:
if !IDX! EQU %COL_NUM% (
endlocal
set "ITEM=%COL_NEWVAL%"
setlocal EnableDelayedExpansion
) else (
if defined ITEM set "ITEM=!ITEM:""="!^"
)
rem /* Collect line string;
rem `for /F` loop to pass string beyond `endlocal` barrier: */
for /F delims^=^ eol^= %%E in ("!NEW_LINE!!SEP!!ITEM!") do (
endlocal
set "NEW_LINE=%%E"
setlocal EnableDelayedExpansion
)
endlocal
set "SEP=%SEPARATOR%"
setlocal EnableDelayedExpansion
)
endlocal
)
rem // Output newly built line:
setlocal EnableDelayedExpansion
echo(!NEW_LINE!
endlocal
)
)
endlocal
exit /B