locat.sh : locate files much more quickly and precisely than find -- with glob and colored extended regex.

locat.sh

#!/usr/bin/env bash
#              bash 4.1.5(1)     Linux Ubuntu 10.04           Date : 2012-03-20
#
# _______________|  locat : find files with glob and colored extended regex.
#
#           Usage:  locat  [extended regex]  [glob pattern]
#
#        Examples:  % locat pdf$
#                   #       pdf files stemmed under present working directory,
#                   #                 ^so seemingly recursive.
#                   % locat /b  '/var/log/*.log' 
#                   #       log files under /var/log starting with letter b.
#                   #       regex and glob pattern should be in single quotes.
#
#    Dependencies:  mlocate (which in turn depends on an updated database).
#                           ___ATTN___ mlocate is also known as "locate" 
#                                      and is much faster than using "find".
#                   egrep   (which operates on output from locate command).


#  CHANGE LOG  LATEST version available:   https://bitbucket.org/rsvp/gists/src
#
#  2012-03-20  Make default glob option very precise by adding star.
#  2012-03-17  The mlocate command does not seem to handle extglob,
#                 which is why regex comes in handy. Supplement error handling. 
#  2012-03-16  First version with EOF NOTES.
#                 Stale date of database is given via stderr.


#           _____ PREAMBLE_v2: settings, variables, and error handling.
#
LC_ALL=POSIX
#      locale means "ASCII, US English, no special rules, 
#      output per ISO and RFC standards." 
#      Esp. use ASCII encoding for glob and sorting characters. 
shopt -s   extglob
#     ^set extended glob for pattern matching.
set -e
#   ^errors checked: immediate exit if a command has non-zero status. 
set -u
#   ^unassigned variables shall be errors.
#    Example of default VARIABLE ASSIGNMENT:  arg1=${1:-'foo'}


arg1=${1:-'\.pdf$'}
arg2=${2:-"$PWD/*"}
#         ^default specializes to PRESENT WORKING DIRECTORY.
#          (Star is important, else two stars are used for non-globs.)
#          Args will apply to files on entire disk,
#          except as specified in /etc/updatedb.conf (see notes below).
locatdb='/var/lib/mlocate/mlocate.db'
#        ^this is the standard database for locate.


program=${0##*/}   #  similar to using basename
memf=$( mktemp /dev/shm/88_${program}_tmp.XXXXXXXXXX )


cleanup () {
     #  Delete temporary files, then optionally exit given status.
     local status=${1:-'0'}
     rm -f $memf
     [ $status = '-1' ] ||  exit $status      #  thus -1 prevents exit.
} #--------------------------------------------------------------------
warn () {
     #  Message with basename to stderr.          Usage: warn "message"
     echo -e "\n !!  ${program}: $1 "  >&2
} #--------------------------------------------------------------------
die () {
     #  Exit with status of most recent command or custom status, after
     #  cleanup and warn.      Usage: command || die "message" [status]
     local status=${2:-"$?"}
     cleanup -1  &&   warn "$1"  &&  exit $status
} #--------------------------------------------------------------------
trap "die 'SIG disruption, but cleanup finished.' 114" 1 2 3 15
#    Cleanup after INTERRUPT: 1=SIGHUP, 2=SIGINT, 3=SIGQUIT, 15=SIGTERM
#
# _______________     ::  BEGIN  Script ::::::::::::::::::::::::::::::::::::::::


dbmtime=$( stat --format="%y" $locatdb )
#                         ^modification time of database.
dbmtime=${dbmtime:0:16}
#   extract only "2012-02-14 15:05" from "2012-02-14 15:05:19.014722601 -0800"
warn "NOTICE last database UPDATE on $dbmtime  <=!"
#    ^message to stderr


#       _case-insensitive
#          _existence check (omits deleted files, see notes below).
#             _ENTIRE PATHNAME
mlocate -i -e --wholename "$arg2" > $memf                              \
     ||  die "bad second argument. Try glob pattern in single quotes."  113 
#
#  If --regex is not specified in locate, arg2 can contain globbing characters.  
#  However, extglob (extended globs) does NOT seem to work for locate.
#  ___ATTN___ If any PATTERN contains no globbing characters, 
#             locate behaves as if the pattern were *PATTERN*.


[ -s $memf ] ||  die "no match for second argument."  114


#     _case-insensitive
egrep -i --color "$arg1" $memf                                          \
     ||  die "no match for first argument. Try regex in single quotes."  115 
#
#  Tip: search for BASENAME by using '/foo$' in arg1.


cleanup
# _______________ EOS ::  END of Script ::::::::::::::::::::::::::::::::::::::::



# _______________ locate and mlocate are the same under Ubuntu...
#
#  mlocate is /usr/bin/mlocate
#   locate is hashed (/usr/bin/locate)
#  lrwxrwxrwx 1 root root 24 2010-08-12 08:05     /usr/bin/locate -> /etc/alternatives/locate
#  
#    ::  sha256sum signature on Sat, 17 Mar 2012 08:59:25 -0700   :
#  ead6d6f94e59e8962599a158a20eef35b9154125638632328df4cfd57ba83212  /usr/bin/mlocate
#  ead6d6f94e59e8962599a158a20eef35b9154125638632328df4cfd57ba83212  /etc/alternatives/locate



#            _____ 2012-03-16 Fri 13:59 :: Linux-locate 
#            http://www.thegeekstuff.com/2012/03/locate-command-examples/          
#  
#  "find" is a good search utility but it is slow.  "locate" can search for files
#  very quickly.  "locate" does not search the files on disk rather it searches
#  for file paths in a database.  The locate database file is located at:
#  /var/lib/mlocate/mlocate.db
#  
#  
#  _______________ EXAMPLES of Locate Command
#  
#       __________ Search a File using locate
#  
#  To search a particular file using locate, just do the following
#  
#       $ locate sysctl.conf
#       /etc/sysctl.conf
#       /usr/share/man/man5/sysctl.conf.5.gz
#  
#  The following command searches for httpd.conf in the entire system.
#  
#       $ locate httpd.conf
#       /etc/httpd/conf/httpd.conf
#       /usr/local/apache2/conf/httpd.conf
#       /usr/local/apache2/conf/httpd.conf.bak
#  
#  You can also use “locate -0″ to display all the output in one line:
#  
#       $ locate -0 httpd.conf
#  
#  
#       __________ Use updatedb to Refresh mlocate Database
#  
#  Suppose you made a backup of an existing file:
#  
#       # cd /etc
#       # cp sysctl.conf sysctl.conf.orig
#  
#  If you try to search for sysctl.conf using the ‘locate’ utility, you’ll not
#  find the sysctl.conf.orig.
#  
#       # locate sysctl.conf
#       /etc/sysctl.conf
#       /usr/share/man/man5/sysctl.conf.5.gz
#  
#  The reason is that after the sysctl.conf.orig was create the database on which
#  the locate utility works is not updated. So lets update the database using the
#  updatedb command and execute locate again:
#  
#       $ updatedb
#       updatedb: can not open a temporary file for `/var/lib/mlocate/mlocate.db'
#  
#  Note that update db needs to be executed as root.
#       
#       % updatedb
#  
#  After updatedb, if you execute locate, you’ll find the sysctl.conf.orig file.
#  
#       # locate sysctl.conf
#       /etc/sysctl.conf
#       /etc/sysctl.conf.orig
#       /usr/share/man/man5/sysctl.conf.5.gz
#  
#  
#       __________ Check File Existence
#  
#  Now suppose the file sysctl.conf.orig that we created above got deleted, and
#  if you try to locate sysctl.conf, it will still display the sysctl.conf.orig
#  file.
#  
#       # cd /etc
#       # rm sysctl.conf.orig
#       # locate sysctl.conf
#       /etc/sysctl.conf
#       /etc/sysctl.conf.orig
#       /usr/share/man/man5/sysctl.conf.5.gz
#  
#  As you see from the above output, locate command shows sysctl.conf.orig even
#  after the file was deleted. This result is MISLEADING.
#  
#  Of course, you can execute updatedb, and try locate again, which will show proper results.
#  
#  Or, you can just use ‘locate -e’, which will display only the files that
#  exists in the system, when you are executing the locate command. i.e. even
#  when the file exist in the mlocate.db, it will still verify to make sure the
#  file is physically present in the system before displaying it.
#  
#       # locate -e sysctl.conf
#       /etc/sysctl.conf
#       /usr/share/man/man5/sysctl.conf.5.gz
#  
#  
#       __________ Ignore Case in Locate Output
#  
#  The locate command by default is configured to accept the file name in a case
#  sensitive manner. In order to make the results case insensitive, we can use
#  the -i option :
#  
#  In the following example, we created two files with both lowercase and uppercase.
#  
#       # cd /tmp
#       # touch new.txt NEW.txt
#       # updatedb
#  
#  If you use the locate command only with the lowercase, it will find only the
#  lowercase file.
#  
#       # locate new.txt
#       /tmp/new.txt
#  
#  Use locate -i, which will ignore case, and look for both lowercase and uppercase file.
#  
#       $ locate -i new.txt
#       /tmp/NEW.txt
#       /tmp/new.txt
#       /usr/share/doc/samba-common/WHATSNEW.txt.gz 
#  
#  
#       __________ What keeps the mlocate database updated?  
#      
#  When you execute "updatedb", it scans the whole system and updates the
#  mlocate.db database file. Hence, in order to get the latest and reliable
#  results from "locate" command the database on which it works should be updated
#  at regular intervals.
#  
#  We can also configure the ‘updatedb’ utility by updating /etc/updatedb.conf
#  which updatedb reads before updating the database. 
#  
#       # cat /etc/updatedb.conf
#       PRUNE_BIND_MOUNTS="yes"
#       PRUNENAMES=".git .bzr .hg .svn"
#       PRUNEPATHS="/tmp /var/spool /media"
#       PRUNEFS="NFS nfs nfs4 rpc_pipefs afs binfmt_misc proc smbfs \
#  autofs iso9660 ncpfs coda devpts ftpfs devfs mfs shfs sysfs cifs \
#  lustre_lite tmpfs usbfs udf fuse.glusterfs fuse.sshfs ecryptfs fusesmb devtmpfs"
#  
#  updatedb.conf file contains information in the form of VARIABLES=VALUES. These
#  variables can be classified into :
#  
#       PRUNEFS : A  whitespace-separated  list of file system types (as used in
#       /etc/mtab) which should not be scanned by updatedb.  The file system type
#       matching is case-insensitive.  By default, no file system types are
#       skipped. When scanning a file system is skipped, all file systems mounted
#       in the subtree are skipped too, even if their  type  does  not  match  any
#       entry in PRUNEFS.
#  
#       PRUNENAMES : A  whitespace-separated list of directory names (without
#       paths) which should not be scanned by updatedb.  By default, no directory
#       names are skipped. Note that only directories can be specified, and no
#       pattern mechanism (e.g. globbing) is used.
#  
#       PRUNEPATHS : A whitespace-separated list of path names of directories
#       which should not be scanned by updatedb.  Each path name must be exactly
#       in the form in which the directory would be reported by locate.  By
#       default, no paths are skipped.
#  
#       PRUNE_BIND_MOUNTS :  One  of  the  strings  0,  no,  1  or yes.  If
#       PRUNE_BIND_MOUNTS is 1 or yes, bind mounts are not scanned by updatedb.
#       All file systems mounted in the subtree of a bind mount are skipped as
#       well, even if they are not bind mounts. By default, bind mounts are not
#       skipped.
#  
#  Note that all of the above configuration information can also be changed or
#  updated through the command line options to the utility updatedb.
#  
#  
#       __________ Changing mlocate Database Location
#  
#  The default database that locate utility reads is /var/lib/mlocate/mlocate.db,
#  but if you wish to link the locate command with some other database kept at
#  some other location, use the -d option.
#  
#  For example :
#  
#  $ locate -d <new db path> <filename>
#  
#  Note that the database path can also be taken from stdin and if an empty path
#  is mentioned then the default data base is picked.


#  vim: set fileencoding=utf-8 ff=unix tw=78 ai syn=sh :