#!/usr/local/bin/gawk -f #!/usr/bin/awk -f # @(#) uucon.gawk 2.1 97/01/08 # 91/04/19 john h. dubois iii (john@armory.com) # 91/06/30 Replaced * with + in split pattern (awk didn't care but gawk does) # 91/08/04 Added separate NOT_POLLED_WARN parameter # 91/08/05 Made awk script exit if no files found; added debug option # 91/12/31 Moved finds inside of awk program; made awk program a separate file # since this change made it larger than a command line can be # 92/03/03 Removed hardcoding of path to awk so it will work under UNIX # 92/03/06 Fixed error initializing last-login file # Don't exit if no files found if debugging is on # Don't use first field of last-login line # 92/03/10 Changed "startup" message searched for so that it will work with # both XENIX and UNIX # 92/05/02 Fixed check for files waiting for polling systems # Changed to be a #!awk script # 92/12/06 Print warnings if poll file or systems file can't be opened, # make sure track files are readable by all # 92/12/17 Added -n and -l options # 93/01/25 Changed from using last success startup line to using last # successful conversation line; # correctly note lack of succesful conversation line with -n & -l # 93/01/28 Cleaned up/bugfixes # 93/05/28 Added sorting by last connect time. Doesn't work across year # ends because logfiles don't contain year. # 93/11/10 Force WePoll[] to be an array # 93/11/15 Force LastConv[] to be an array # 94/03/09 Use gawk so - options can be given # 94/03/12 Close lots of files & commands. Avoid cding to nonexistant dirs. # 96/07/04 Cleaned up option processing. Added andcpurslL options. # Let system names be given on command line. More error checking. # Make dates from earlier years sort correctly. Added rcfile. # Truncate system names to 7 chars, because uucico does when creating # logfiles. # 96/07/07 Print incoming UUCP/TCP times in local time. Added t option. # 96/11/05 Exit if can't read Systems # 97/01/08 Made -l and -L sorting work correctly. BEGIN { Name = "uucon" LogDir = "/usr/spool/uucp/.Log/uucico" LCDir = LogDir Usage = \ "Usage: " Name " [-ahlLnurst] [-x] [-c]\n"\ " [-p] [-d] [system ...]" rcFiles = "/etc/default/uucon" ARGC = Opts(Name,Usage,"ac>p>d:rstlLuhx<",0,rcFiles, "ALL,NO_CON_WARN,NOT_POLLED_WARN,LC_DIR,RSORT,SITESORT,NOCONVERT",0,"n") debug = Options["x"] if (debug) print "debugging is on." if ("h" in Options) { help(Name,Usage,LCDir,rcFiles) exit(0) } if ("d" in Options) LCDir = Options["d"] toLocal = !("t" in Options) if (SitesGiven = (ARGC > 1)) { for (i = 1; i < ARGC; i++) Systems[ARGV[i]] if (debug) printf "%d sitename(s) given.\n",ARGC-1 > "/dev/stderr" } All = "a" in Options if (Options["L"] || Options["l"]) { # Print last-conversation lines Cmd = "uuname" while ((Cmd | getline System) == 1) allSystems[substr(System,1,7)] close(Cmd) CheckSysList(Systems,allSystems,SitesGiven,Name) # Report last conv with all systems DoLast(Options["l"],LogDir,LCDir,Systems,"r" in Options, "s" in Options,allSystems,All) exit(0) } # Read poll file and Systems file split("",WePoll,"") # make awk realize this is an array if (!Setup("/usr/lib/uucp/Poll.hour",allSystems,WeCall,Never,WePoll)) exit 1 CheckSysList(Systems,allSystems,SitesGiven,Name) # Get/save last-conv lines split("",LastConv,"") # convince awk this is an array FindLastConv(LogDir,Systems,LastConv) # read uucico logs if ("u" in Options) SaveLastConv(LCDir,LastConv) # write last-conv files ReadLastConv(LCDir,Systems,LastConv,allSystems) # read last-conv files if (All) CopySet(Systems,LastConv) # Set NoConSystems and WarnSystems according to dates on last-conv files # Convince awk that these are arrays split("",NoConSystems) split("",NotPolledSystems) if ("c" in Options) NoConWarn = Options["c"] else NoConWarn = 1 if ("p" in Options) NotPolledWarn = Options["p"] else NotPolledWarn = NoConWarn FindOldFiles(NoConSystems,NotPolledSystems,NoConWarn,NotPolledWarn) ReportNoConv(LastConv,NoConSystems,NotPolledSystems,WeCall,WePoll) } # Complain about any systems in Systems[] that are not also in allSystems[]. # If no systems given, copy allSystems[] to Systems[]. function CheckSysList(Systems,allSystems,SitesGiven,Name, sys) { if (SitesGiven) { for (sys in Systems) if (!(sys in allSystems)) printf \ "%s: system \"%s\" does not exist in the Systems file.\n", Name,sys > "/dev/stderr" } else CopyArr(allSystems,Systems) if (debug) { print "Final systems list:" > "/dev/stderr" for (sys in Systems) print sys > "/dev/stderr" print "" > "/dev/stderr" } } # Report systems that there has been no successful conversation with for # more than the configured number of days. # A warning is printed only for systems that: are polled and are in # NoConSystems; are called on demand and have jobs waiting and are in # NoConSystems; or poll us and have jobs waiting and are in NotPolledSystems. # A system is in: # WeCall if it has a Systems line that has a call time other than Never. # WePoll if it is a system we poll. # NoConSystems if it has a last-conv file at least NoConWarn days old. # NotPolledSystems if it has a last-conv file at least NotPolledWarn days old. # # LastConv contains the last-conv line for each system, for use in warnings. # It contains an entry for every system in the UUCP configuration. function ReportNoConv(LastConv,NoConSystems,NotPolledSystems,WeCall,WePoll, NumFiles,System,Elem,Cmd,When,Warn,SysList,Line,SysType) { # Make SysType array so awk will not complain later if nothing is put in it split("",SysType) for (System in LastConv) { if ((System in NoConSystems) && (System in WePoll)) SysType[System] = "polled " else if ((System in NoConSystems) && (System in WeCall)) SysType[System] = "called " else if ((System in NotPolledSystems) && !(System in WeCall)) SysType[System] = "polling " else if (debug) { printf "Systems %s: no warning.\n",System continue } if (debug) printf "Systems %s is %s\n",System,SysType[System] } for (System in SysType) SysList = SysList System " " if (SysList == "") return # Check for waiting files. Cmd = "for system in " SysList "; do dir=/usr/spool/uucp/$system;"\ "[ ! -x $dir ] && continue; cd $dir; set -- *;"\ "[ $1 != '*' ] && echo $system $#; done" while ((Cmd | getline Line) == 1) { split(Line,Elem) NumFiles[Elem[1]] = Elem[2] } close(Cmd) for (System in SysType) { if (!(System in WePoll) && !NumFiles[System]) continue split(LastConv[System],Elem) if (Elem[3] == "NEVER") When = "EVER" else When = "since " substr(Elem[3],2,index(Elem[3],",") - 2) printf \ "No successful conversation with %ssystem %s %s;\n%d waiting files.\n", SysType[System],Elem[2],When,NumFiles[System] } } # Sets NoConSystems to systems with a last-conv file more than NoConWarn # days old, and NotPolledSystems to systems with a last-conv file more than # NotPolledWarn days old. function FindOldFiles(NoConSystems,NotPolledSystems,NoConWarn,NotPolledWarn, File) { # Get lists of .system files that were last # modified at warning threshold or longer ago # Set NoConList to last-conv files more than NoConWarn days old, and # NotPolledList to last-conv files more than NotPolledWarn days old. if (!(FilesByDate(LogDir,".??*","+" NoConWarn,NoConList) + \ FilesByDate(LogDir,".??*","+" NotPolledWarn,NotPolledList)) && !debug) return # quit if no files found if (debug) printf "Last-login files older than NoConWarn (%d) day(s): ", NoConWarn for (File in NoConList) { if (debug) printf "%s ",File # get rid of leading . NoConSystems[substr(File,2)] } if (debug) print "" if (debug) printf "Last-login files older than NotPolledWarn (%d) day(s): ", NotPolledWarn for (File in NotPolledList) { if (debug) printf "%s ",File NotPolledSystems[substr(File,2)] } if (debug) print "" } # Report last connection to systems. function DoLast(Long,LogDir,LCDir,Systems,ReverseSort,SiteSort,allSystems,All, System,LastConv,E,NFields,Time,NSys,Cmd,Month,Day,Hour,Minute,Second,CurYear, LastYear,Date,tty,Offset) { # Get info from uucico logs FindLastConv(LogDir,Systems,LastConv) # Get info from last-conv status files ReadLastConv(LCDir,Systems,LastConv,allSystems) if (All) CopySet(Systems,LastConv) # Expected format of .systemname files: #1 2 3 4 5 6 7 8 9 10 11 12 13 14 #uucp gorn (1/25-16:28:20,17495,0) OK (conversation complete tty3C 1) # month:3 day:4 hour:5 minute:6 second:7 tty:13 CurYear = strftime("%y") LastYear = sprintf("%02d",CurYear - 1) MakeTZOffset() if (debug) printf "TZ offset is %d\n",TZOffset for (System in LastConv) { NFields = split(LastConv[System],E,"[- \t(),/:]+") if (NFields > 3) { if (NFields < 13) { printf "Bad last-connnection record (not enough fields):\n%s\n", LastConv[System] > "/dev/stderr" continue } tty = E[13] Month = E[3]+0 Day = E[4]+0 Hour = E[5]+0 Minute = E[6]+0 Second = E[7]+0 if (Month < 1 || Month > 12 || Day < 1 || Day > 31 || Hour < 0 || \ Hour > 23 || Minute < 0 || Minute > 60 || Second < 0 || \ Second > 60) { printf "Bad date or time in last-connnection record:\n%s\n", LastConv[System] > "/dev/stderr" continue } Offset = (tty == "notty") ? 0 : TZOffset Time = unixtime(CurYear,Month,Day,Hour,Minute,Second,Offset) # Log files don't include year, so if the month/day put it # in the future, assume it was from last year. # Get new systime each time it is used, just in case # logfiles are still being written. if (Time > systime()) { Time = \ unixtime(LastYear,Month,Day,Hour,Minute,Second,Offset) if (debug) printf "Record from previous year:\n%s\n", LastConv[System] > "/dev/stderr" } # SCO uucpd does not set TZ, so uucico writes logfiles in GMT. # Fortunately, this case can be recognized because uucico logs # tty as "notty". Use strftime() to convert to local time. # Otherwise, avoid the possibility that the above calculations # are incorrect by just reforatting the fields from the # logfile. if (toLocal && tty == "notty") Date = strftime("%m/%d %T",Time) else Date = sprintf("%02d/%02d %02d:%02d:%02d",Month,Day,Hour, Minute,Second) if (Long) PrintVal[System] = sprintf("%-8s %s %s",System,Date,tty) else PrintVal[System] = LastConv[System] if (debug) printf "Last login for %s was %s\n",System, strftime("%y/%m/%d %T",Time) > "/dev/stderr" } else { if (Long) PrintVal[System] = sprintf("%-8s NEVER",System) else PrintVal[System] = \ sprintf("---- %s No successful conversations",System) Time = 0 } if (SiteSort) SortVal[System] = System else SortVal[System] = sprintf("%010d",Time) if (debug) printf "Sort key for %s is: %s\n",System,SortVal[System] \ > "/dev/stderr" } if (debug) printf "Sorting...\n" > "/dev/stderr" NSys = qsortArbIndByValue(SortVal,k) print "System Last connection TTY" if (ReverseSort) for (i = NSys; i >= 1; i--) print PrintVal[k[i]] else for (i = 1; i <= NSys; i++) print PrintVal[k[i]] } function help(Name,Usage,LCDir,rcFile) { printf \ "%s: check whether remote UUCP systems have been successfully connected to.\n"\ "%s\n"\ " A warning is printed for systems that have not been connected to in\n"\ "a given period, by default one day. This warning is printed only for\n"\ "systems that are polled (called regularly regardless of whether there are\n"\ "jobs) or which have UUCP jobs waiting; the warning is not printed for\n"\ "systems that have no jobs waiting and which are never called or only\n"\ "called on demand.\n"\ " A similar warning is also for systems that must poll us (systems that\n"\ "are never called) that have jobs waiting. By default, the no-connection\n"\ "period is used for this warning, but a different value may be given with\n"\ "-p; it might be set higher than the no-connection warning period as\n"\ "failure to poll may be a common occurance and of less concern.\n"\ " %s searches the uucico logs for successful conversation lines.\n"\ "If no successful conversation line is found for a system, it is read from\n"\ "its last-conversation file, if it exists.\n"\ "Options:\n"\ "Some of the following options can also be set by assigning values to\n"\ "variables in the configuration file %s. Variables are\n"\ "assigned to with the syntax: varname=value or in the case of flags, by\n"\ "simply putting the indicated variable name in the file without a value.\n"\ "Flag options can be turned off on the command line by following them\n"\ "immediately with '-', e.g. -r- to turn off the r option in such a way that\n"\ "it cannot be turned on in the config file. Variable names appear in\n"\ "parentheses in the option descriptions.\n"\ "-a: Print warnings for or list last logins for all systems, including\n"\ " those who poll us and have no jobs queued up for them. (ALL)\n"\ "-u: The last-conversation file for each system that a successful\n"\ " conversation line is found for is udpated. The successful\n"\ " conversation line is written to its last-conversation file,\n"\ " %s/.\n"\ " %s should generally be run with the -u option once a day, immediately\n"\ " before the uucico logfiles are cleaned up (for example, by putting\n"\ " \"uucon -u\" near the top of the uudemon.clean script). This allows\n"\ " long-term tracking of the last successful connection to a system.\n"\ "-x: Turn on debugging output at level . Higher\n"\ " values produce more output.\n"\ "-t: By default, logfile times for incoming UUCP/TCP connections are taken\n"\ " to be in GMT (because SCO uucpd does not set TZ), and are converted to\n"\ " local time. If -t is given, this conversion is not done. (NOCONVERT)\n"\ "-h: Print this help.\n"\ "-L: Print last-conversation lines from the uucico logs or last-conversation\n"\ " files for all systems. No warnings are printed, and no attempt is\n"\ " made to read the Systems file or to write to last-conversation files.\n"\ " Lines are printed in order from oldest to most recent connection.\n"\ "-l: Like -L except that a header is printed and the lines are printed in\n"\ " a more readable format.\n"\ "-s: Sort -l and -L output by site name. (SITESORT)\n"\ "-r: Print -l and -L output in reverse order. (RSORT)\n"\ "-c: Set the no-connection warning period to\n"\ " days. This also set the not-polled warning\n"\ " period, unless -p is also given. (NO_CON_WARN)\n"\ "-p: Set the not-polled warning period to\n"\ " days. (NOT_POLLED_WARN)\n"\ "-d: Store last-conversation files for each system in \n"\ " instead of the default directory %s. (LC_DIR)\n"\ "-n: Do not read the configuration file (%s).\n", Name,Usage,Name,rcFile,LCDir,Name,LCDir,rcFile } function GetLastFiles(LCDir,LastConvFiles,allSystems, Cmd,LogFiles,Num,Elem,i,System) { Cmd = "cd " LCDir "; echo .??*" Cmd | getline LogFiles close(Cmd) Num = split(LogFiles,Elem," ") for (i = 1; i <= Num; i++) { System = Elem[i] if (System == ".??*" || System == "") continue if (debug) print "File found in last-conv dir: " System > "/dev/stderr" System = substr(System,2) if (!(System in allSystems)) printf \ "%s: Warning: In %s, found last-conversation file\n"\ "for a system that does not exist in the Systems file: %s\n", Name,LCDir,System else LastConvFiles[System] } } # Read last-successful-conversation files of systems that do not have # a successful-conversation line in their uucico logfiles. function ReadLastConv(LCDir,Systems,LastConv,allSystems, File,System,LastConvFiles) { # Find what last conv files exist, party to make sure there are not any # obsolete files and party so we know whether to complain about files that # cannot be opened. GetLastFiles(LCDir,LastConvFiles,allSystems) for (System in Systems) { if ((!(System in LastConv) || LastConv[System] == "") && System in LastConvFiles) { if (debug) printf "Reading last-successful-conversation file for %s\n", System File = LCDir "/." System if ((ret = (getline LastConv[System] < File)) != 1) printf \ "Could not open status file \"%s\":\ngetline returned %d.\n", File,ret close(File) } else if (debug) printf "Found successful-conversation line in uucico log for %s;\n"\ "skipping status file\n",System } } # Finds files that match Pattern and were last modified Days days # ago (a number optionally preceded by + or - as in find(C)) # A list of the files is put in List # The number of matching files found is returned function FilesByDate(Dir,Pattern,Days,List, num) { num = 0 FindCmd = "cd " Dir "; find " Pattern " -mtime " Days " -print 2>&1" while ((FindCmd | getline FileName) == 1) if (FileName !~ "find: stat.. failed") { List[FileName] num++ } close(FindCmd) return num } # Sets these: # WeCall: systems we call, from Systems # Never: systems we never call, from Systems # WePoll: systems we poll, from poll file # Systems in poll file that are not in Systems file or are listed # as Never called in Systems file are not included in WePoll. # Systems: all systems listed in Systems file function Setup(PollFile,Systems,WeCall,Never,WePoll, result,SystemsFile,Sysfiles,SysList,System) { # SysList: all systems listed in uucp config, from poll file & Systems file # read Sysfiles records & get name of uucico systems file if (ReadRecFile("/usr/lib/uucp/Sysfiles",Sysfiles) != -1) SystemsFile = FindSystemsFile(Sysfiles) if (SystemsFile == "") { if (debug) print \ "No Sysfiles file; systems file is /usr/lib/uucp/Systems." SystemsFile = "/usr/lib/uucp/Systems" } # Make WeCall[] indexes be the set of systems we call while ((result = (getline < PollFile)) == 1) if (($0 !~ "^#") && NF) { System = substr($1,1,7) WePoll[System] SysList[System] } close(PollFile) if (result < 0) printf "Warning: error reading poll file \"%s\".\n",PollFile while ((result = (getline < SystemsFile)) == 1) { if (($0 ~ "^#") || !NF) # ignore empty & comment lines continue System = substr($1,1,7) if ($2 ~ "[nN]ever") Never[System] else WeCall[System] SysList[System] Systems[System] } close(SystemsFile) if (result < 0) { printf "Error reading Systems file \"%s\".\n",SystemsFile return 0 } if (debug) { printf "Systems we poll: " for (Sys in WePoll) printf Sys " " printf "\nSystems we never call: " for (Sys in Never) printf Sys " " printf "\nSystems we call: " for (Sys in WeCall) printf Sys " " print "" for (Sys in SysList) if (Sys in WePoll) { if (Sys in Never) printf \ "Warning: System \"%s\" exists in Poll file %s,\n"\ " but is listed as being never called in systems file %s.\n", Sys,PollFile,SystemsFile else if (Sys in WeCall) printf \ "System \"%s\" exists in Poll file %s,\n"\ " and is listed as being called in systems file %s.\n", Sys,PollFile,SystemsFile else printf \ "Warning: System \"%s\" exists in Poll file %s,\n"\ " but has no entry in Systems file \"%s\".\n", Sys,PollFile,SystemsFile } else { if (Sys in Never) printf \ "System \"%s\" does not exist in Poll file %s,\n"\ " and is listed as being never called in systems file %s.\n", Sys,PollFile,SystemsFile else if (Sys in WeCall) printf \ "System \"%s\" does not exist in Poll file %s,\n"\ " but is listed as being called in systems file %s.\n", Sys,PollFile,SystemsFile } } for (System in WePoll) if (!(System in WeCall)) delete WePoll[System] return 1 } # read File into Arr (one record per element of Arr). # Records are lines which are continued onto the next # line if they end with \. function ReadRecFile(File,Arr,result,i,line) { i = -1 while ((result = (getline line < File)) == 1) { if (line ~ "^#") continue if (Arr[i] ~ /\\[ \t]*$/) { sub("\\\\[ \t]*$"," ",Arr[i]) Arr[i] = Arr[i] line } else Arr[++i] = line } close(File) return result } # Find uucico record in arr generated from Systems file, # and return the value of its systems field. function FindSystemsFile(Sysfiles,i,tok,file,elem,var,systemsfile) { for (i in Sysfiles) { split(Sysfiles[i],tok,"[ \t]+") var["service"] = "" var["systems"] = "Systems" for (file in tok) { split(tok[file],elem,"=") var[elem[1]] = elem[2] } if (var["service"] == "uucico") { systemsfile = var["systems"] if ( systemsfile !~ "^/" ) systemsfile = "/usr/lib/uucp/" systemsfile return systemsfile } } return "" } # Find last successful connection to sites # by searching their log files for successful-conversation lines. function FindLastConv(LogDir,Systems,LastConv, Cmd,LogFiles,Names,System,Line,count,Elem,i,Num) { Cmd = "cd " LogDir "; echo *" Cmd | getline LogFiles close(Cmd) Num = split(LogFiles,Elem," ") for (i = 1; i <= Num; i++) { System = Elem[i] if (System == "*" || System == "") continue if (debug) print "File found in log dir: " System > "/dev/stderr" Names[System] count++ } if (!count) { if (debug) printf "No log files found in %s.\n",LogDir return } # for each system that has a log file... if (debug) printf "Reading logfiles: " for (System in Systems) if (System in Names) { if (debug) printf "%s ",System LastConv[System] LogFile = LogDir "/" System while ((getline Line < LogFile) == 1) if (Line ~ /OK \(conversation/) LastConv[System] = Line close(LogFile) } if (debug) print "" } # Writes last successful conversation lines for systems to a last-conversation # file. If the last conversation line is empty, meaning that the system had a # logfile but no successful-conversation line was found, and does not already # have a last-conversation file, an initial last-sucessful-conversation file is # created for it anyway. function SaveLastConv(LCDir,LastConv, System,TrackFile,TrackFiles) { if (debug) print "Writing logfiles..." for (System in LastConv) { TrackFile = LogDir "/." System if (LastConv[System] != "") { if (debug) printf "Last conversation line for system \"%s\":\n%s\n", System, LastConv[System] print LastConv[System] > TrackFile TrackFiles = TrackFiles " " TrackFile } else if ((getline < TrackFile) != 1) { # if no last-successful-conversation file... if (debug) printf "No conversation line found for system \"%s\"\n",File print "uucp " System " NEVER" > TrackFile TrackFiles = TrackFiles " " TrackFile } close(TrackFile) } if (TrackFiles != "") system("chmod a+r" TrackFiles) } ### Start of ProcArgs library # @(#) ProcArgs 1.11 96/12/08 # 92/02/29 john h. dubois iii (john@armory.com) # 93/07/18 Added "#" arg type # 93/09/26 Do not count -h against MinArgs # 94/01/01 Stop scanning at first non-option arg. Added ">" option type. # Removed meaning of "+" or "-" by itself. # 94/03/08 Added & option and *()< option types. # 94/04/02 Added NoRCopt to Opts() # 94/06/11 Mark numeric variables as such. # 94/07/08 Opts(): Do not require any args if h option is given. # 95/01/22 Record options given more than once. Record option num in argv. # 95/06/08 Added ExclusiveOptions(). # 96/01/20 Let rcfiles be a colon-separated list of filenames. # Expand $VARNAME at the start of its filenames. # Let varname=0 and -option- turn off an option. # 96/05/05 Changed meaning of 7th arg to Opts; now can specify exactly how many # of the vars should be searched for in the environment. # Check for duplicate rcfiles. # 96/05/13 Return more specific error values. Note: ProcArgs() and InitOpts() # now return various negatives values on error, not just -1, and # Opts() may set Err to various positive values, not just 1. # Added AllowUnrecOpt. # 96/05/23 Check type given for & option # 96/06/15 Re-port to awk # 96/10/01 Moved file-reading code into ReadConfFile(), so that it can be # used by other functions. # 96/10/15 Added OptChars # 96/11/01 Added exOpts arg to Opts() # 96/11/16 Added ; type # 96/12/08 Added Opt2Set() & Opt2Sets() # 96/12/27 Added CmdLineOpt() # optlist is a string which contains all of the possible command line options. # A character followed by certain characters indicates that the option takes # an argument, with type as follows: # : String argument # ; Non-empty string argument # * Floating point argument # ( Non-negative floating point argument # ) Positive floating point argument # # Integer argument # < Non-negative integer argument # > Positive integer argument # The only difference the type of argument makes is in the runtime argument # error checking that is done. # The & option is a special case used to get numeric options without the # user having to give an option character. It is shorthand for [-+.0-9]. # If & is included in optlist and an option string that begins with one of # these characters is seen, the value given to "&" will include the first # char of the option. & must be followed by a type character other than ":" # or ";". # Note that if e.g. &> is given, an option of -.5 will produce an error. # Strings in argv[] which begin with "-" or "+" are taken to be # strings of options, except that a string which consists solely of "-" # or "+" is taken to be a non-option string; like other non-option strings, # it stops the scanning of argv and is left in argv[]. # An argument of "--" or "++" also stops the scanning of argv[] but is removed. # If an option takes an argument, the argument may either immediately # follow it or be given separately. # "-" and "+" options are treated the same. "+" is allowed because most awks # take any -options to be arguments to themselves. gawk 2.15 was enhanced to # stop scanning when it encounters an unrecognized option, though until 2.15.5 # this feature had a flaw that caused problems in some cases. See the OptChars # parameter to explicitly set the option-specifier characters. # If an option that does not take an argument is given, # an index with its name is created in Options and its value is set to the # number of times it occurs in argv[]. # If an option that does take an argument is given, an index with its name is # created in Options and its value is set to the value of the argument given # for it, and Options[option-name,"count"] is (initially) set to the 1. # If an option that takes an argument is given more than once, # Options[option-name,"count"] is incremented, and the value is assigned to # the index (option-name,instance) where instance is 2 for the second occurance # of the option, etc. # In other words, the first time an option with a value is encountered, the # value is assigned to an index consisting only of its name; for any further # occurances of the option, the value index has an extra (count) dimension. # The sequence number for each option found in argv[] is stored in # Options[option-name,"num",instance], where instance is 1 for the first # occurance of the option, etc. The sequence number starts at 1 and is # incremented for each option, both those that have a value and those that # do not. Options set from a config file have a value of 0 assigned to this. # Options and their arguments are deleted from argv. # Note that this means that there may be gaps left in the indices of argv[]. # If compress is nonzero, argv[] is packed by moving its elements so that # they have contiguous integer indices starting with 0. # Option processing will stop with the first unrecognized option, just as # though -- was given except that unlike -- the unrecognized option will not be # removed from ARGV[]. Normally, an error value is returned in this case. # If AllowUnrecOpt is true, it is not an error for an unrecognized option to # be found, so the number of remaining arguments is returned instead. # If OptChars is not a null string, it is the set of characters that indicate # that an argument is an option string if the string begins with one of the # characters. A string consisting solely of two of the same option-indicator # characters stops the scanning of argv[]. The default is "-+". # argv[0] is not examined. # The number of arguments left in argc is returned. # If an error occurs, the global string OptErr is set to an error message # and a negative value is returned. # Current error values: # -1: option that required an argument did not get it. # -2: argument of incorrect type supplied for an option. # -3: unrecognized (invalid) option. function ProcArgs(argc,argv,OptList,Options,compress,AllowUnrecOpt,OptChars, ArgNum,ArgsLeft,Arg,ArgLen,ArgInd,Option,Pos,NumOpt,Value,HadValue,specGiven, NeedNextOpt,GotValue,OptionNum,Escape,dest,src,count,c,OptTerm,OptCharSet) { # ArgNum is the index of the argument being processed. # ArgsLeft is the number of arguments left in argv. # Arg is the argument being processed. # ArgLen is the length of the argument being processed. # ArgInd is the position of the character in Arg being processed. # Option is the character in Arg being processed. # Pos is the position in OptList of the option being processed. # NumOpt is true if a numeric option may be given. ArgsLeft = argc NumOpt = index(OptList,"&") OptionNum = 0 if (OptChars == "") OptChars = "-+" while (OptChars != "") { c = substr(OptChars,1,1) OptChars = substr(OptChars,2) OptCharSet[c] OptTerm[c c] } for (ArgNum = 1; ArgNum < argc; ArgNum++) { Arg = argv[ArgNum] if (length(Arg) < 2 || !((specGiven = substr(Arg,1,1)) in OptCharSet)) break # Not an option; quit if (Arg in OptTerm) { delete argv[ArgNum] ArgsLeft-- break } ArgLen = length(Arg) for (ArgInd = 2; ArgInd <= ArgLen; ArgInd++) { Option = substr(Arg,ArgInd,1) if (NumOpt && Option ~ /[-+.0-9]/) { # If this option is a numeric option, make its flag be & and # its option string flag position be the position of & in # the option string. Option = "&" Pos = NumOpt # Prefix Arg with a char so that ArgInd will point to the # first char of the numeric option. Arg = "&" Arg ArgLen++ } # Find position of flag in option string, to get its type (if any). # Disallow & as literal flag. else if (!(Pos = index(OptList,Option)) || Option == "&") { if (AllowUnrecOpt) { Escape = 1 break } else { OptErr = "Invalid option: " specGiven Option return -3 } } # Find what the value of the option will be if it takes one. # NeedNextOpt is true if the option specifier is the last char of # this arg, which means that if the option requires a value it is # the next arg. if (NeedNextOpt = (ArgInd >= ArgLen)) { # Value is the next arg if (GotValue = ArgNum + 1 < argc) Value = argv[ArgNum+1] } else { # Value is included with option Value = substr(Arg,ArgInd + 1) GotValue = 1 } if (HadValue = AssignVal(Option,Value,Options, substr(OptList,Pos + 1,1),GotValue,"",++OptionNum,!NeedNextOpt, specGiven)) { if (HadValue < 0) # error occured return HadValue if (HadValue == 2) ArgInd++ # Account for the single-char value we used. else { if (NeedNextOpt) { # option took next arg as value delete argv[++ArgNum] ArgsLeft-- } break # This option has been used up } } } if (Escape) break # Do not delete arg until after processing of it, so that if it is not # recognized it can be left in ARGV[]. delete argv[ArgNum] ArgsLeft-- } if (compress != 0) { dest = 1 src = argc - ArgsLeft + 1 for (count = ArgsLeft - 1; count; count--) { ARGV[dest] = ARGV[src] dest++ src++ } } return ArgsLeft } # Assignment to values in Options[] occurs only in this function. # Option: Option specifier character. # Value: Value to be assigned to option, if it takes a value. # Options[]: Options array to return values in. # ArgType: Argument type specifier character. # GotValue: Whether any value is available to be assigned to this option. # Name: Name of option being processed. # OptionNum: Number of this option (starting with 1) if set in argv[], # or 0 if it was given in a config file or in the environment. # SingleOpt: true if the value (if any) that is available for this option was # given as part of the same command line arg as the option. Used only for # options from the command line. # specGiven is the option specifier character use, if any (e.g. - or +), # for use in error messages. # Global variables: OptErr # Return value: negative value on error, 0 if option did not require an # argument, 1 if it did & used the whole arg, 2 if it required just one char of # the arg. # Current error values: # -1: Option that required an argument did not get it. # -2: Value of incorrect type supplied for option. # -3: Bad type given for option & function AssignVal(Option,Value,Options,ArgType,GotValue,Name,OptionNum, SingleOpt,specGiven, UsedValue,Err,NumTypes) { # If option takes a value... [ NumTypes = "*()#<>]" if (Option == "&" && ArgType !~ "[" NumTypes) { # ] OptErr = "Bad type given for & option" return -3 } if (UsedValue = (ArgType ~ "[:;" NumTypes)) { # ] if (!GotValue) { if (Name != "") OptErr = "Variable requires a value -- " Name else OptErr = "option requires an argument -- " Option return -1 } if ((Err = CheckType(ArgType,Value,Option,Name,specGiven)) != "") { OptErr = Err return -2 } # Mark this as a numeric variable; will be propogated to Options[] val. if (ArgType != ":" && ArgType != ";") Value += 0 if ((Instance = ++Options[Option,"count"]) > 1) Options[Option,Instance] = Value else Options[Option] = Value } # If this is an environ or rcfile assignment & it was given a value... else if (!OptionNum && Value != "") { UsedValue = 1 # If the value is "0" or "-" and this is the first instance of it, # do not set Options[Option]; this allows an assignment in an rcfile to # turn off an option (for the simple "Option in Options" test) in such # a way that it cannot be turned on in a later file. if (!(Option in Options) && (Value == "0" || Value == "-")) Instance = 1 else Instance = ++Options[Option] # Save the value even though this is a flag Options[Option,Instance] = Value } # If this is a command line flag and has a - following it in the same arg, # it is being turned off. else if (OptionNum && SingleOpt && substr(Value,1,1) == "-") { UsedValue = 2 if (Option in Options) Instance = ++Options[Option] else Instance = 1 Options[Option,Instance] } # If this is a flag assignment without a value, increment the count for the # flag unless it was turned off. The indicator for a flag being turned off # is that the flag index has not been set in Options[] but it has an # instance count. else if (Option in Options || !((Option,1) in Options)) # Increment number of times this flag seen; will inc null value to 1 Instance = ++Options[Option] Options[Option,"num",Instance] = OptionNum return UsedValue } # Option is the option letter # Value is the value being assigned # Name is the var name of the option, if any # ArgType is one of: # : String argument # ; Non-null string argument # * Floating point argument # ( Non-negative floating point argument # ) Positive floating point argument # # Integer argument # < Non-negative integer argument # > Positive integer argument # specGiven is the option specifier character use, if any (e.g. - or +), # for use in error messages. # Returns null on success, err string on error function CheckType(ArgType,Value,Option,Name,specGiven, Err,ErrStr) { if (ArgType == ":") return "" if (ArgType == ";") { if (Value == "") Err = "must be a non-empty string" } # A number begins with optional + or -, and is followed by a string of # digits or a decimal with digits before it, after it, or both else if (Value !~ /^[-+]?([0-9]+|[0-9]*\.[0-9]+|[0-9]+\.)$/) Err = "must be a number" else if (ArgType ~ "[#<>]" && Value ~ /\./) Err = "may not include a fraction" else if (ArgType ~ "[()<>]" && Value < 0) Err = "may not be negative" # ( else if (ArgType ~ "[)>]" && Value == 0) Err = "must be a positive number" if (Err != "") { ErrStr = "Bad value \"" Value "\". Value assigned to " if (Name != "") return ErrStr "variable " substr(Name,1,1) " " Err else { if (Option == "&") Option = Value return ErrStr "option " specGiven substr(Option,1,1) " " Err } } else return "" } # Note: only the above functions are needed by ProcArgs. # The rest of these functions call ProcArgs() and also do other # option-processing stuff. # Opts: Process command line arguments. # Opts processes command line arguments using ProcArgs() # and checks for errors. If an error occurs, a message is printed # and the program is exited. # # Input variables: # Name is the name of the program, for error messages. # Usage is a usage message, for error messages. # OptList the option description string, as used by ProcArgs(). # MinArgs is the minimum number of non-option arguments that this # program should have, non including ARGV[0] and +h. # If the program does not require any non-option arguments, # MinArgs should be omitted or given as 0. # rcFiles, if given, is a colon-seprated list of filenames to read for # variable initialization. If a filename begins with ~/, the ~ is replaced # by the value of the environment variable HOME. If a filename begins with # $, the part from the character after the $ up until (but not including) # the first character not in [a-zA-Z0-9_] will be searched for in the # environment; if found its value will be substituted, if not the filename will # be discarded. # rcfiles are read in the order given. # Values given in them will not override values given on the command line, # and values given in later files will not override those set in earlier # files, because AssignVal() will store each with a different instance index. # The first instance of each variable, either on the command line or in an # rcfile, will be stored with no instance index, and this is the value # normally used by programs that call this function. # VarNames is a comma-separated list of variable names to map to options, # in the same order as the options are given in OptList. # If EnvSearch is given and nonzero, the first EnvSearch variables will also be # searched for in the environment. If set to -1, all values will be searched # for in the environment. Values given in the environment will override # those given in the rcfiles but not those given on the command line. # NoRCopt, if given, is an additional letter option that if given on the # command line prevents the rcfiles from being read. # See ProcArgs() for a description of AllowUnRecOpt and optChars, and # ExclusiveOptions() for a description of exOpts. # Special options: # If x is made an option and is given, some debugging info is output. # h is assumed to be the help option. # Global variables: # The command line arguments are taken from ARGV[]. # The arguments that are option specifiers and values are removed from # ARGV[], leaving only ARGV[0] and the non-option arguments. # The number of elements in ARGV[] should be in ARGC. # After processing, ARGC is set to the number of elements left in ARGV[]. # The option values are put in Options[]. # On error, Err is set to a positive integer value so it can be checked for in # an END block. # Return value: The number of elements left in ARGV is returned. # Must keep OptErr global since it may be set by InitOpts(). function Opts(Name,Usage,OptList,MinArgs,rcFiles,VarNames,EnvSearch,NoRCopt, AllowUnrecOpt,optChars,exOpts, ArgsLeft,e) { if (MinArgs == "") MinArgs = 0 ArgsLeft = ProcArgs(ARGC,ARGV,OptList NoRCopt,Options,1,AllowUnrecOpt, optChars) if (ArgsLeft < (MinArgs+1) && !("h" in Options)) { if (ArgsLeft >= 0) { OptErr = "Not enough arguments" Err = 4 } else Err = -ArgsLeft printf "%s: %s.\nUse -h for help.\n%s\n", Name,OptErr,Usage > "/dev/stderr" exit 1 } if (rcFiles != "" && (NoRCopt == "" || !(NoRCopt in Options)) && (e = InitOpts(rcFiles,Options,OptList,VarNames,EnvSearch)) < 0) { print Name ": " OptErr ".\nUse -h for help." > "/dev/stderr" Err = -e exit 1 } if ((exOpts != "") && ((OptErr = ExclusiveOptions(exOpts,Options)) != "")) { printf "%s: Error: %s\n",Name,OptErr > "/dev/stderr" Err = 1 exit 1 } return ArgsLeft } # ReadConfFile(): Read a file containing var/value assignments, in the form # . # Whitespace (spaces and tabs) around a variable (leading whitespace on the # line and whitespace between the variable name and the assignment character) # is stripped. Lines that do not contain an assignment operator or which # contain a null variable name are ignored, other than possibly being noted in # the return value. If more than one assignment is made to a variable, the # first assignment is used. # Input variables: # File is the file to read. # Comment is the line-comment character. If it is found as the first non- # whitespace character on a line, the line is ignored. # Assign is the assignment string. The first instance of Assign on a line # separates the variable name from its value. # If StripWhite is true, whitespace around the value (whitespace between the # assignment char and trailing whitespace on the line) is stripped. # VarPat is a pattern that variable names must match. # Example: "^[a-zA-Z][a-zA-Z0-9]+$" # If FlagsOK is true, variables are allowed to be "set" by being put alone on # a line; no assignment operator is needed. These variables are set in # the output array with a null value. Lines containing nothing but # whitespace are still ignored. # Output variables: # Values[] contains the assignments, with the indexes being the variable names # and the values being the assigned values. # Lines[] contains the line number that each variable occured on. A flag set # is record by giving it an index in Lines[] but not in Values[]. # Return value: # If any errors occur, a string consisting of descriptions of the errors # separated by newlines is returned. In no case will the string start with a # numeric value. If no errors occur, the number of lines read is returned. function ReadConfigFile(Values,Lines,File,Comment,Assign,StripWhite,VarPat, FlagsOK, Line,Status,Errs,AssignLen,LineNum,Var,Val) { if (Comment != "") Comment = "^" Comment AssignLen = length(Assign) if (VarPat == "") VarPat = "." # null varname not allowed while ((Status = (getline Line < File)) == 1) { LineNum++ sub("^[ \t]+","",Line) if (Line == "") # blank line continue if (Comment != "" && Line ~ Comment) continue if (Pos = index(Line,Assign)) { Var = substr(Line,1,Pos-1) Val = substr(Line,Pos+AssignLen) if (StripWhite) { sub("^[ \t]+","",Val) sub("[ \t]+$","",Val) } } else { Var = Line # If no value, var is entire line Val = "" } if (!FlagsOK && Val == "") { Errs = Errs \ sprintf("\nBad assignment on line %d of file %s: %s", LineNum,File,Line) continue } sub("[ \t]+$","",Var) if (Var !~ VarPat) { Errs = Errs sprintf("\nBad variable name on line %d of file %s: %s", LineNum,File,Var) continue } if (!(Var in Lines)) { Lines[Var] = LineNum if (Pos) Values[Var] = Val } } if (Status) Errs = Errs "\nCould not read file " File close(File) return Errs == "" ? LineNum : substr(Errs,2) # Skip first newline } # Variables: # Data is stored in Options[]. # rcFiles, OptList, VarNames, and EnvSearch are as as described for Opts(). # Global vars: # Sets OptErr. Uses ENVIRON[]. # If anything is read from any of the rcfiles, sets READ_RCFILE to 1. function InitOpts(rcFiles,Options,OptList,VarNames,EnvSearch, Line,Var,Pos,Vars,Map,CharOpt,NumVars,TypesInd,Types,Type,Ret,i,rcFile, fNames,numrcFiles,filesRead,Err,Values,retStr) { split("",filesRead,"") # make awk know this is an array NumVars = split(VarNames,Vars,",") TypesInd = Ret = 0 if (EnvSearch == -1) EnvSearch = NumVars for (i = 1; i <= NumVars; i++) { Var = Vars[i] CharOpt = substr(OptList,++TypesInd,1) if (CharOpt ~ "^[:;*()#<>&]$") CharOpt = substr(OptList,++TypesInd,1) Map[Var] = CharOpt Types[Var] = Type = substr(OptList,TypesInd+1,1) # Do not overwrite entries from environment if (i <= EnvSearch && Var in ENVIRON && (Err = AssignVal(CharOpt,ENVIRON[Var],Options,Type,1,Var,0)) < 0) return Err } numrcFiles = split(rcFiles,fNames,":") for (i = 1; i <= numrcFiles; i++) { rcFile = fNames[i] if (rcFile ~ "^~/") rcFile = ENVIRON["HOME"] substr(rcFile,2) else if (rcFile ~ /^\$/) { rcFile = substr(rcFile,2) match(rcFile,"^[a-zA-Z0-9_]*") envvar = substr(rcFile,1,RLENGTH) if (envvar in ENVIRON) rcFile = ENVIRON[envvar] substr(rcFile,RLENGTH+1) else continue } if (rcFile in filesRead) continue # rcfiles are liable to be given more than once, e.g. UHOME and HOME # may be the same filesRead[rcFile] if ("x" in Options) printf "Reading configuration file %s\n",rcFile > "/dev/stderr" retStr = ReadConfigFile(Values,Lines,rcFile,"#","=",0,"",1) if (retStr > 0) READ_RCFILE = 1 else if (ret != "") { OptErr = retStr Ret = -1 } for (Var in Lines) if (Var in Map) { if ((Err = AssignVal(Map[Var], Var in Values ? Values[Var] : "",Options,Types[Var], Var in Values,Var,0)) < 0) return Err } else { OptErr = sprintf(\ "Unknown var \"%s\" assigned to on line %d\nof file %s",Var, Lines[Var],rcFile) Ret = -1 } } if ("x" in Options) for (Var in Map) if (Map[Var] in Options) printf "(%s) %s=%s\n",Map[Var],Var,Options[Map[Var]] > \ "/dev/stderr" else printf "(%s) %s not set\n",Map[Var],Var > "/dev/stderr" return Ret } # OptSets is a semicolon-separated list of sets of option sets. # Within a list of option sets, the option sets are separated by commas. For # each set of sets, if any option in one of the sets is in Options[] AND any # option in one of the other sets is in Options[], an error string is returned. # If no conflicts are found, nothing is returned. # Example: if OptSets = "ab,def,g;i,j", an error will be returned due to # the exclusions presented by the first set of sets (ab,def,g) if: # (a or b is in Options[]) AND (d, e, or f is in Options[]) OR # (a or b is in Options[]) AND (g is in Options) OR # (d, e, or f is in Options[]) AND (g is in Options) # An error will be returned due to the exclusions presented by the second set # of sets (i,j) if: (i is in Options[]) AND (j is in Options[]). # todo: make options given on command line unset options given in config file # todo: that they conflict with. function ExclusiveOptions(OptSets,Options, Sets,SetSet,NumSets,Pos1,Pos2,Len,s1,s2,c1,c2,ErrStr,L1,L2,SetSets,NumSetSets, SetNum,OSetNum) { NumSetSets = split(OptSets,SetSets,";") # For each set of sets... for (SetSet = 1; SetSet <= NumSetSets; SetSet++) { # NumSets is the number of sets in this set of sets. NumSets = split(SetSets[SetSet],Sets,",") # For each set in a set of sets except the last... for (SetNum = 1; SetNum < NumSets; SetNum++) { s1 = Sets[SetNum] L1 = length(s1) for (Pos1 = 1; Pos1 <= L1; Pos1++) # If any of the options in this set was given, check whether # any of the options in the other sets was given. Only check # later sets since earlier sets will have already been checked # against this set. if ((c1 = substr(s1,Pos1,1)) in Options) for (OSetNum = SetNum+1; OSetNum <= NumSets; OSetNum++) { s2 = Sets[OSetNum] L2 = length(s2) for (Pos2 = 1; Pos2 <= L2; Pos2++) if ((c2 = substr(s2,Pos2,1)) in Options) ErrStr = ErrStr "\n"\ sprintf("Cannot give both %s and %s options.", c1,c2) } } } if (ErrStr != "") return substr(ErrStr,2) return "" } # The value of each instance of option Opt that occurs in Options[] is made an # index of Set[]. # The return value is the number of instances of Opt in Options. function Opt2Set(Options,Opt,Set, count) { if (!(Opt in Options)) return 0 Set[Options[Opt]] count = Options[Opt,"count"] for (; count > 1; count--) Set[Options[Opt,count]] return count } # The value of each instance of option Opt that occurs in Options[] that # begins with "!" is made an index of nSet[] (with the ! stripped from it). # Other values are made indexes of Set[]. # The return value is the number of instances of Opt in Options. function Opt2Sets(Options,Opt,Set,nSet, count,aSet,ret) { ret = Opt2Set(Options,Opt,aSet) for (value in aSet) if (substr(value,1,1) == "!") nSet[substr(value,2)] else Set[value] return ret } # Returns true if option Opt was given on the command line. function CmdLineOpt(Options,Opt, i) { for (i = 1; (Opt,"num",i) in Options; i++) if (Options[Opt,"num",i] != 0) return 1 return 0 } ### End of ProcArgs library ### Begin array routines # InitArr: Initialize an array with values. # Ind and Vals are separated into lists on Sep. # For each item in Ind, an index with that name is created in Arr[], # and the value with the same position in Vals is stored in it. # Global variables: none. function InitArr(Arr,Ind,Vals,sep, numind,indnames,values) { split(Ind,indnames,sep) split(Vals,values,sep) for (numind in indnames) Arr[indnames[numind]] = values[numind] } function ClearArr(Arr, Elem) { for (Elem in Arr) delete Arr[Elem] } function CopyArr(From,To, Elem) { for (Elem in From) To[Elem] = From[Elem] } # Subtract the values in Subtrahend from those in Minuend function SubtractArr(Minuend,Subtrahend, Elem) { for (Elem in Subtrahend) Minuend[Elem] -= Subtrahend[Elem] } # For each element of the array In, an element is created in Out having # an index equal to the value of the element in In and a value equal to # the index of the element in In. function Invert(In,Out, Index) { for (Index in In) Out[In[Index]] = Index } # Assign: make an array from a list of assignments. # An index with the name of each variable in the list is created in the array. # Its value is set to the value given for it. # Input variables: # Elements is a string containing the list of variable-value pairs. # Sep is the string that separates the pairs in the list. # AssignOp is the string that separates variables from values. # Output variables: # Arr is the array. # Return value: the number of elements added to the set. # Example: # Assign(Arr,"foo=blot bar=blat baz=blit"," ","=") function Assign(Arr,Elements,Sep,AssignOp, Num,Names,Elem,Assignments,Assignment,i) { Num = split(Elements,Assignments,Sep) for (i = 1; i <= Num; i++) { Assignment = Assignments[i] Ind = index(Assignment,AssignOp) Arr[substr(Assignment,1,Ind - 1)] = substr(Assignment,Ind + 1) } return Num } # Packs Arr[], which should have integer indices starting at or above n, to # contiguous integer indices starting with n. # If n is not given it defaults to 0. # Num should be the number of elements in Arr. function PackArr(Arr,Num,n, NewInd,OldInd) { NewInd = OldInd = n+0 for (; Num; Num--) { while (!(OldInd in Arr)) OldInd++ if (NewInd != OldInd) { Arr[NewInd] = Arr[OldInd] delete Arr[OldInd] } OldInd++ NewInd++ } } ### End array routines ### Begin set library # 96/05/23 added return values jhdiii # 96/05/25 added set2list() # Return value: the number of new elements added to Inter function Intersection(A,B,Inter, Elem,Count) { for (Elem in A) if (Elem in B && !(Elem in Inter)) { Inter[Elem] Count++ } return Count } # Return value: the number of new elements added to Both function Union(A,B,Both) { return CopySet(A,Both) + CopySet(B,Both) } # Deletes any elements that are in both Minuend and Subtrahend from Minuend. # Return value: the number of elements deleted. function SubtractSet(Minuend,Subtrahend, Elem,nDel) { for (Elem in Subtrahend) if (Elem in Minuend) { delete Minuend[Elem] nDel++ } return nDel } # Return value: the number of new elements added to To function CopySet(From,To, Elem,n) { for (Elem in From) if (!(Elem in To)) { To[Elem] n++ } return n } # Returns 1 if Set is empty, 0 if not. function IsEmpty(Set, i) { for (i in Set) return 0 return 1 } # MakeSet: make a set from a list. # An index with the name of each element of the list is created in the given # array. # Input variables: # Elements is a string containing the list of elements. # Sep is the character that separates the elements of the list. # Output variables: # Set is the array. # Return value: the number of new elements added to the set. function MakeSet(Set,Elements,Sep, i,Num,Names,nFound,ind) { nFound = 0 Num = split(Elements,Names,Sep) for (i = 1; i <= Num; i++) { ind = Names[i] if (!(ind in Set)) { Set[ind] nFound++ } } return nFound } # Returns the number of elements in set Set function NumElem(Set, elem,Num) { for (elem in Set) Num++ return Num } # Remove all elements from Set function DeleteAll(Set, i) { split("",Set,",") } # Returns a list of all of the elements in Set[], with each pair of elements # separated by Sep. function set2list(Set,Sep, list,elem) { for (elem in Set) list = list Sep elem return substr(list,2) # skip 1st separator } ### End set library ### Begin timedate routines. # These functions operate on absolute dates & times. # convert month/day or year/month/day date to yymmdd date # uses global "year" var if year not given function makedate(InDate,Elements,d,date) { Elements = split(InDate,d,"/") date = d[1] * 100 + d[2] if (Elements == 2) date += year else if (Elements == 3) date = date * 100 + d[3] else return -1 return date } # convert yymmdd date to yy/mm/dd date function unmakedate(Date) { return substr(Date,1,2) "/" substr(Date,3,2) "/" substr(Date,5,2) } function MkMonth2Num( Month) { split("Jan,Feb,Mar,Apr,May,Jun,Jul,Aug,Sep,Oct,Nov,Dec",Months,",") for (Month in Months) Month2Num[Months[Month]] = sprintf("%02d",Month) } # Takes a date and stores its components in the following elements of Date[]: # year yy # month mm # day dd # hour hh # min mm # The following are set in Date[] if given: # tz TTT|offset # lyear yyyy # weekday Www # sec ss # On success, the date in touch/date/etc. format (MMddhhmmyy) is returned. # On failure, a negative value is returned. # InDate form: # [Weekday[,] (Month [d]d)|([d]d Month) TZ|time|year TZ|time|year [TZ|time|year] # where Www is a weekday name that starts with a recognized 3-char prefix, # Month is a month name that starts with a recognized 3-char prefix, # [d]d is a day of the month, # TZ is a timezone name (three upper case alpha chars) or offset from GMT # as [-+]NNNN, time is of the form [h]h:mm[:ss], # and year is of the form [cc]nn where cc is >= 19. # Common patterns for a particular date: # [Tue[,]] Jun 12 11:02:46 [BST|-0800] [19]90 # [Tue[,]] 12 Jun [19]90 11:02:46 [BST|-0800] function ParseDate(InDate,Date, El,MonthName,TimeEl,i,Months,Ind,Num) { if (!("Jan" in Month2Num)) { MkMonth2Num() split("month,day,hour,min,year",TouchParts,",") } # Clear Date[] split("",Date," ") Num = split(InDate,El," +") if (!(4 <= Num && Num <= 6)) return -1 Ind = 1 if (El[Ind] ~ "^(Mon|Tue|Wed|Thu|Fri|Sat|Sun)[a-z]*,?") { Date["weekday"] = substr(El[Ind],1,3) Ind++ } if ((El[Ind] + 0) > 0) { Date["day"] = sprintf("%02d",El[Ind++]) MonthName = substr(El[Ind++],1,3) } else { MonthName = substr(El[Ind++],1,3) Date["day"] = sprintf("%02d",El[Ind++]) } if ((Date["day"] + 0 > 31) || (Date["day"] + 0 < 1)) return -5 if (!(MonthName in Month2Num)) return -3 Date["month"] = Month2Num[MonthName] for (; Ind <= Num; Ind++) { if ((El[Ind] ~ "^[0-2]?[0-9]:[0-5][0-9](:[0-5][0-9])?$") && \ !("hour" in Date)) { split(El[Ind],TimeEl,":") Date["hour"] = sprintf("%02d",TimeEl[1]) Date["min"] = TimeEl[2] if (3 in TimeEl) Date["sec"] = TimeEl[3] } else if ((El[Ind] ~ "^[1-9][0-9][0-9][0-9]$") && !("year" in Date)) { Date["year"] = substr(El[Ind],3) Date["lyear"] = El[Ind] } else if ((El[Ind] ~ "^[0-9][0-9]$") && !("year" in Date)) Date["year"] = El[Ind] else if ((El[Ind] ~ "^([A-Z][A-Z][A-Z])|([-+][0-2][0-9][0-5][0-9])$") \ && !("tz" in Date)) Date["tz"] = El[Ind] else return -2 } for (i in TouchParts) if (!(TouchParts[i] in Date)) return -i - 5 touchdate = Date["month"] Date["day"] Date["hour"] Date["min"] Date["year"] return touchdate } # Convert a file timestamp as printed by 'l' to an epoch time. # noTZ should be 1 if the date output was produced with a 0 TZ; in this case # no attempt is made to undo the TZ adjustment. function lDate2unixtime(Mon,Day,Year,noTZ, Month) { if (!(1 in Month2Num)) { MkMonth2Num() CurYear = strftime("%y") CurMonth = strftime("%m") } Month = Month2Num[Mon] # Deal with varying dates printed by l # Use year if given # Subtract 1 from year if month given is from last year if (Year ~ ":") # If year is actually time... Year = (CurYear - (Month > CurMonth)) % 100 return date2unixtime(Year,Month,Day,noTZ) } # Returns the number of seconds that passed from 1970 Jan 1 00:00:00 # to the given date. # Timezone should be given as a numeric offset from GMT in seconds. # Use 0 for Timezone if the date being converted was not generated with a # timezone adjustment. function unixtime(Year,Month,Day,Hour,Minute,Second,Timezone) { return ((YMD2day(Year,Month,Day) * 24 + Hour) * 60 + Minute) * 60 + \ Second + Timezone } # date2unixtime returns the number of seconds that passed from # 1970 Jan 1 00:00:00 GMT to the given date, which is assumed to be in the # local timezone. Note that if the given date occured in daylight savings # time and the current time (which is used to calculate TZOffset) is not, # or vice versa, this will be off by the DST shift. # If noTZ is set, the date is taken to be in GMT and TZ modifications are not # done. # Globals: Sets/uses TZOffset and MDays[]. function date2unixtime(Year,Month,Day,noTZ, LeapDays) { if (!noTZ && TZOffset == "") MakeTZOffset() if (Year > 100) Year -= 1900 LeapDays = int((Year - 68) / 4) if (Month <= 2 && Year % 4 == 0) LeapDays -= 1 if (!MDays[2]) split("0 31 59 90 120 151 181 212 243 273 304 334 365",MDays," ") return ((Year - 70) * 365 + MDays[Month + 0] + Day - 1 + LeapDays) \ * 24 * 3600 - (noTZ ? 0 : TZOffset) } # Sets global TZOffset to the number of seconds that need to be substracted # from the local date (without time of day) to give an epoch time. # TZOffset can also be added to systime() before doing %86400 to get the # current day number in the local timezone. # Note that TZOffset is only correct if the given date is in the same DST # phase as the current date. # 95/03/26 Calculate TZOffset more accurately. function MakeTZOffset( t) { t = systime() TZOffset = strftime("%H",t)*3600+strftime("%M",t)*60+strftime("%S",t) - \ t%86400 if (strftime("%j",0) != "001") # If TZ offset > 0 TZOffset -= 24*3600 } # Convert a numeric timezone to a number of seconds. # Example: converts -0830 to -30600 function TZ2sec(NTimezone) { if (NTimezone < 0) { NTimezone = substr(NTimezone,2) Mult = -1 } else Mult = 1 return (substr(NTimezone,1,2)*3600+substr(NTimezone,3,2)*60)*Mult } # Only works for current time... does *not* take a systime argument! function my_strftime(Format, Time) { "date \"+" Format "\"" | getline Time return Time } ### End timedate routines ### Begin epochdays routines. # These functions operate on epoch days and epoch months, which have the same 0 # time as UNIX epoch seconds. These functions are mainly used to avoid having # to deal with timezone issues. # @(#) epochdays 1.1 95/08/26 # YMD2day(year,month,day-of-month) returns the number of days that passed from # 1970 Jan 1 to the given date. # All parameters should be given in numeric form. # If year < 70, it is assumed to be part of the 2000 century # If year in (70..99), it is assumed to be part of the 1900 century. # Globals: sets and uses MDays[] function YMD2day(Year,Month,Day, LeapDays) { Year+=0 Month+=0 if (Year < 70) Year += 100 else if (Year >= 100) Year -= 1900 # Year is now the number of years since 1900. LeapDays = int((Year - 68) / 4) if (Month <= 2 && Year % 4 == 0) LeapDays -= 1 if (!(0 in MDays)) split("0 31 59 90 120 151 181 212 243 273 304 334 365",MDays," ") return (Year - 70) * 365 + MDays[Month] + Day - 1 + LeapDays } # date2day("yy/mm/dd") returns the number of days that passed from # 1970 Jan 1 to the given date. -1 is returned on error. # The fields are returned in Fields: year in Fields[1], month in Fields[2], # and day (if given) in Fields[3]. function date2day(Date,Fields, Num,Year,Month) { Num = split(Date,Fields,"/") if (Num != 2 && Num != 3) return -1 if (!(Year = Fields[1] + 0) || !(Month = Fields[2] + 0)) return -1 if (Num == 3) Day = Fields[3] return YMD2day(Year,Month,Day) } # diffdays(year1,month1,day-of-month1,year2,month2,day-of-month2) # returns the number of complete days that passed from date 1 to date 2 function diffdays(year1,month1,day1,year2,month2,day2) { return YMD2day(year2,month2,day2) - YMD2day(year1,month1,day1) } # Given an epoch month, return the first day of that month function month2day(Month) { return YMD2day(int(Month/12) + 1970,Month % 12 + 1,1) } # Given an epoch day, returns epoch month function day2month(Day, Date) { day2YMD(Day,Date) return (Date["y"]-1970)*12 + Date["m"]-1 } # Given an epoch month, returns the number of days in that month. function monthdays(month, year) { if (!(0 in MDur)) split("31 28 31 30 31 30 31 31 30 31 30 31",MDur) year = int(month/12) month = month%12+1 return (!((year+2)%4) && month == 2) ? 29 : MDur[month] } # Given an epoch day (day since 1970 Jan 1; day 0 = 1970 Jan 1, etc.), # returns the date elements in Date: # Date["y"] = year (4 digits), Date["m"] = month (jan = 1, etc.), # Date["d"] = day of month. # Globals: Sets/uses MDays[]. function day2YMD(Day,Date, QYears,Year,NonLeapYears,Month) { if (!(0 in LDays)) { split("0 31 59 90 120 151 181 212 243 273 304 334 365",MDays," ") split("0 31 60 91 121 152 182 213 244 274 305 335 366",LDays," ") } Day += 365 # Day is now # of days since Jan 1 1969. 1968 was a leap year. QYears = int(Day / (365*4+1)) Year = 1969 + QYears * 4 Day -= QYears * (365*4+1) # Day now contains no complete leap years. Year += NonLeapYears = int(Day/365) Leap = !(Year % 4) Day -= NonLeapYears * 365 # Day now contains the day of year. # Find the month. Divide day by 32 to get either the correct month or # the month prior to it. Month = int(Day++ / 32) + 1 if (Day > (Leap ? LDays[Month+1] : MDays[Month+1])) Month++ Day -= Leap ? LDays[Month] : MDays[Month] Date["d"] = Day Date["m"] = Month Date["y"] = Year } # Given a month number, return a date in the form yy/mm function month2date(MonthNum) { return sprintf("%02d/%02d",(MonthNum / 12 + 70) % 100, MonthNum % 12 + 1) } # Given a day number, return a date in the form yy/mm/dd function day2date(day) { day2YMD(day,Date) return sprintf("%02d/%02d/%02d",Date["y"]%100,Date["m"],Date["d"]) } ### End epochdays routines ### Begin qsort routines # Arr[] is an array of values with arbitrary indices. # k[] is returned with numeric indices 1..n. # The values in k[] are the indices of Arr[], # ordered so that if Arr[] is stepped through # in the order Arr[k[1]] .. Arr[k[n]], it will be stepped # through in order of the values of its elements. # The return value is the number of elements in the arrays (n). function qsortArbIndByValue(Arr,k, ArrInd,ElNum) { ElNum = 0 for (ArrInd in Arr) k[++ElNum] = ArrInd qsortSegment(Arr,k,1,ElNum) return ElNum } # Sort a segment of an array. # Arr[] contains data with arbitrary indices. # k[] has indices 1..nelem, with the indices of arr[] as values. # This function sorts the elements of arr that are pointed to by # k[start..end], swapping the values of elements of k[] so that # when this function returns arr[k[start..end]] will be in order. function qsortSegment(Arr,k,start,end, left,right,sepval,tmp,tmpe,tmps) { # handle two-element case explicitly for a tiny speedup if ((end - start) == 1) { if (Arr[tmps = k[start]] > Arr[tmpe = k[end]]) { k[start] = tmpe k[end] = tmps } return } # Make sure comparisons act on these as numbers left = start+0 right = end+0 sepval = Arr[k[int((left + right) / 2)]] # Make every element <= sepval be to the left of every element > sepval while (left < right) { while (Arr[k[left]] < sepval) left++ while (Arr[k[right]] > sepval) right-- if (left < right) { tmp = k[left] k[left++] = k[right] k[right--] = tmp } } if (left == right) if (Arr[k[left]] < sepval) left++ else right-- if (start < right) qsortSegment(Arr,k,start,right) if (left < end) qsortSegment(Arr,k,left,end) } # Arr[] is an array of values with arbitrary indices. # k[] is returned with numeric indices 1..n. # The values in k are the indices of Arr[], # ordered so that if Arr[] is stepped through # in the order Arr[k[1]] .. Arr[k[n]], it will be stepped # through in order of the values of its indices. # The return value is the number of elements in the arrays (n). # If the indexes are numeric, Numeric should be true, so that they can be # compared as such rather than as strings. Numeric indexes do not have to be # contiguous. function qsortByArbIndex(Arr,k,Numeric, ArrInd,ElNum) { ElNum = 0 if (Numeric) # Indexes do not preserve numeric type, so must be forced for (ArrInd in Arr) k[++ElNum] = ArrInd+0 else for (ArrInd in Arr) k[++ElNum] = ArrInd qsortNumIndByValue(k,1,ElNum) return ElNum } # Arr is an array of elements with contiguous numeric indexes to be sorted # by value. # start and end are the starting and ending indexes of the range to be sorted. function qsortNumIndByValue(Arr,start,end, left,right,sepval,tmp,tmpe,tmps) { # handle two-element case explicitly for a tiny speedup if ((start - end) == 1) { if ((tmps = Arr[start]) > (tmpe = Arr[end])) { Arr[start] = tmpe Arr[end] = tmps } return } left = start+0 right = end+0 sepval = Arr[int((left + right) / 2)] while (left < right) { while (Arr[left] < sepval) left++ while (Arr[right] > sepval) right-- if (left <= right) { tmp = Arr[left] Arr[left++] = Arr[right] Arr[right--] = tmp } } if (start < right) qsortNumIndByValue(Arr,start,right) if (left < end) qsortNumIndByValue(Arr,left,end) } ### End qsort routines