00:01:50 [[Talk:ESON]] N https://esolangs.org/w/index.php?oldid=67242 * IFcoltransG * (+185) Created page with "The hex regex looks ambiguous with the quaternary. Are you sure it isn't meant to be 'x'? ~~~~" 00:04:10 -!- LKoen has quit (Remote host closed the connection). 00:06:43 -!- LKoen has joined. 00:08:33 [[XS]] M https://esolangs.org/w/index.php?diff=67243&oldid=46834 * IFcoltransG * (+24) Added 'see also' to XSM 00:08:46 -!- FreeFull has quit. 00:48:26 -!- oerjan has joined. 00:53:14 -!- ArthurStrong has joined. 00:53:20 @messages-gold 00:53:20 fizzie said 14h 51m 15s ago: Updated things, maybe it's a newer version of Mercurial/hgweb. There's a notion of changeset "phases", from secret -> draft -> public. It's maybe showing those, and 00:53:20 counting everything as draft (the default for new changesets) as they're technically never been pushed to a remote repo (the browser shows the real thing). 00:53:48 mhm 00:58:15 `` ls -ld .hg 00:58:16 ls: cannot access '.hg': No such file or directory 00:58:19 hm 00:58:31 `` cat bin/hlnp 00:58:32 cat: bin/hlnp: No such file or directory 00:58:39 `` cat ../bin/hlnp 00:58:40 scowrevs="$(/usr/bin/paste -sd'|' /hackenv/share/scowrevs)"; hg log -r "tip:0 & ! ($scowrevs)" "$@" | sed 's/$\(^\| $[ curious. does hg recurse into parent directories to find .hg by default? 00:59:28 I'd assume most VCSes do 00:59:33 i suppose 00:59:41 as it's common to want to VCS from a subdirectory 00:59:46 git won't recurse across filesystems, though 01:00:00 well that explains why that didn't break 01:00:26 heh so git might have broken, since tmp is mounted separately 01:00:33 (or wait, is it) 01:00:44 i suppose it isn't 01:00:59 it was introduced with the .hgignore hack, after all 01:01:16 `` ls -ld .hg* 01:01:17 ls: cannot access '.hg*': No such file or directory 01:01:39 `` ls -ld ../.hg* 01:01:39 drwxr-xr-x 5 1000 1000 4096 Nov 19 01:01 ../.hg \ -rw-r--r-- 1 1000 1000 150 Jul 8 2017 ../.hg_archival.txt \ -rw-r--r-- 1 1000 1000 6 Jul 8 2017 ../.hgignore 01:02:26 hah, I didn't even realise that we created /tmp from inside HackEso, I assumed it was hardcoded 01:03:27 it wasn't, although now there's a hardcoded restore of .hgignore to ensure it doesn't break 01:03:54 hmm, is HackEso technically a codenomic? 01:04:17 I guess not, because of the hardcoded `rever 01:04:19 * `revert 01:04:38 meaning that nothing can ever become permanently disallowed 01:05:06 -!- mniip has quit (Ping timeout: 615 seconds). 01:05:07 that's not really possible anyway since you can run global commands. 01:05:31 except for that evil canary bug that someone once found, but that's been fixed 01:05:44 I'm sure there are permissions bugs left. 01:06:22 it was probably me, I liked doing weird things with the canary just to see what would happen 01:07:01 that said, if we're gradually moving more and more important things to /tmp, the canary probably won't help much 01:07:04 i think maybe it was actually chmod 000 . , but that broke everything because of side effects with the canary 01:07:06 as it won't stop a deletion from there 01:07:32 we're not supposed to move important things to tmp/ 01:07:33 /tmp is a bad name; it's either tmp or /hackenv/tmp. 01:07:55 everything there is in principle ephemeral 01:08:04 `touch /tmp/test 01:08:06 No output. 01:08:13 That's writable too, it's just not persistent. 01:08:13 `ls -l /tmp/test 01:08:14 ls: invalid option -- ' ' \ Try 'ls --help' for more information. 01:08:20 which creates some trouble for le/ which now can be broken 01:08:21 `` ls -l /tmp/test 01:08:21 ls: cannot access '/tmp/test': No such file or directory 01:08:31 ah, I see, it disappears every command 01:08:35 It's a tmpfs inside the per-command kernel, yes. 01:08:49 that means it's probably the best place for files that are genuinely temporary 01:08:55 like ibin/brachylog uses 01:09:29 I switched it to /tmp when fixing the $HACKENV thing. 01:10:16 oerjan: Incidentally, I didn't include misle in tmp yet. 01:10:42 (There's misle/rn and misle/rn_append, the counterparts of the same commands in le/ but for tmflry instead of wisdom.) 01:10:57 whoa 01:11:12 It's really only `foo/bar commands that, in the /hackenv/tmp cwd setup, unfortunately have to have some part inside tmp. 01:11:16 `` doag /hackenv/misle 01:11:17 6804:2016-02-10 undo c58a6174e051 \ 6800:2016-02-10 ` sed -i \'s/| lowercase//\' misle/* \ 6786:2016-02-10 ` sed -i \'s/Learned/Was lied to about/\' misle/* \ 6783:2016-02-10 ` mkdir misle; cp le/* misle; sed -i \'s/wisdom/tmflry/g\' misle/* 01:11:41 i've been misled 01:12:37 I've never really understood the concept of tmflry, TBH. 01:12:49 why doesn't `foo/bar look in /hackenv/bin/foo/bar? 01:13:13 Because it uses a shell to execute the command. 01:13:21 And "foo/bar" is not looked up in $PATH. 01:13:37 I mean, it doesn't need to do that, but that's the immediate reason. 01:13:42 fizzie: well, an actual learndb full of useful information is something many channels benefit from, probably this one would as well; however, nobody seemed inclined to make it and the naming was silly 01:13:49 `? INTERCAL 01:13:50 INTERCAL has excellent features for modular program for the enterprise market. 01:13:55 `? Brachylog 01:13:56 Brachylog? ¯\(°_o)/¯ 01:13:59 `? Jelly 01:14:00 Jelly? ¯\(°_o)/¯ 01:14:08 imagine if that give actual summaries of the esolangs 01:14:13 it'd be better for conversation 01:14:24 as it is, though, people just give esowiki links 01:14:28 https://esolangs.org/wiki/INTERCAL etc. 01:14:33 I think the problem is, not all the wisdom entries are foolishness either. 01:14:34 `? COME FROM 01:14:35 COME FROM? ¯\(°_o)/¯ 01:15:02 `? ¯\(°_o)/¯ 01:15:04 ¯\(°_o)/¯ is a misspelling of ¯\(°_o)/¯ 01:15:14 well that was interesting 01:15:38 I was vaguely considering I might have `!wiki INTERCAL` or some-such make esowiki print out the link plus the first paragraph. 01:16:41 (The convention of using `backtick quoting` for code text doesn't really work for talking about HackEso commands.) 01:16:54 do we at least have a command for linking to the wiki? 01:16:56 `wiki INTERCAL 01:16:57 https://esolangs.org/wiki/tmp/INTERCAL 01:17:08 Whoops, that looks like a bug. 01:17:10 beautiful :-D 01:17:19 `cat bin/wiki 01:17:20 cat: bin/wiki: No such file or directory 01:17:24 `cat /hackenv/bin/wiki 01:17:24 #!/usr/bin/env python \ import sys, os.path, urllib \ if len(sys.argv) <= 1: \ print "https://esolangs.org/" \ else: \ f = os.path.abspath(sys.argv[1]) \ if f.startswith('/hackenv/'): f = f[9:] \ print ("https://esolangs.org/wiki/" + \ urllib.quote(f)) 01:17:46 I'm not sure why exactly it treats the argument as a path. 01:18:09 nor am I 01:18:25 ^wiki INTERCAL 01:18:25 https://esolangs.org/wiki/INTERCAL 01:18:33 We also have the befunge equivalent. 01:18:58 Er, brainfuck equivalent. Kind of. 01:19:01 ^wiki /// 01:19:01 https://esolangs.org/wiki//// 01:19:13 ^wiki ;# 01:19:13 https://esolangs.org/wiki/;# 01:19:21 hmm, I don't think it's doing any sort of escaping 01:19:27 No, it's just a ,[.,] 01:20:06 (;# is an esolang, technically, but a really terrible one; it's basically a sub-TC minimalisation of BF to just the + and . commands) 01:20:25 (so in a way I'm glad we dont't have an article on it) 01:21:11 `dobg wiki 01:21:12 11334:2018-01-20 fetch bin/wiki https://hackego.esolangs.org/get/bin/wiki \ 10393:2017-03-11 ` chmod +x bin/wiki \ 10392:2017-03-11 fetch bin/wiki https://hackego.esolangs.org/get/bin/wiki \ 7080:2016-03-05 rm bin/wiki \ 7079:2016-03-05 ` echo "echo \\"http://esolangs.org/wiki/Main_Page\\"" > bin/wiki 01:21:33 `hurl ../bin/wiki 01:21:34 https://hack.esolangs.org/repo/log/tip/bin/wiki 01:22:22 `slbd wiki//6,7d;s/quote(f)/quote(sys.argv[1])/ 01:22:24 wiki//#!/usr/bin/env python \ import sys, os.path, urllib \ if len(sys.argv) <= 1: \ print "https://esolangs.org/" \ else: \ print ("https://esolangs.org/wiki/" + \ urllib.quote(sys.argv[1])) 01:22:26 there is something very weird about a 1 with an umlaut on it :-D 01:22:27 Let's give that a try. 01:22:35 `wiki INTERCAL 01:22:35 https://esolangs.org/wiki/INTERCAL 01:22:36 accented digits isn't something I'd even considered 01:22:54 `wiki ;# 01:22:55 https://esolangs.org/wiki/%3B%23 01:24:43 `hurl ../bin/url 01:24:44 https://hack.esolangs.org/repo/log/tip/bin/url 01:25:33 Right, maybe it was adapted from url and/or suchlike. 01:26:14 Wasn't clearing tmp/ supposed to be supported? 01:26:17 `unicode COMBINING CEDILLA 01:26:18 ̧ 01:26:30 5 01:26:51 fizzie: i must have done it by i don't remember 01:26:54 I meant 5̧ 01:27:04 Is the state in tmp/ now required for le/rn operation? 01:27:12 Yes. It is a shame. 01:27:27 hmm my client renders that 5-cedilla pretty well 01:27:36 s/hmm/hmm,/ 01:29:25 Wasn't clearing tmp/ supposed to be supported? <-- yes, but now we have a choice between that and keeping le/rn working. 01:30:57 or fizzie could add a hack to catch /-containing commands 01:32:20 I could make ` in general just do a custom lookup, it's already kind of a non-standard parsing. 01:32:45 In that it splits on first space to form the command and its full argument. 01:38:21 hmm, I assume you can't just hardcode it to run /hackenv/bin/command because you need to be able to run commands like ls too 01:38:23 -!- kspalaiologos has quit (Ping timeout: 250 seconds). 01:46:01 was HackEgo on CaC from the start? i vaguely think otherwise. 01:46:45 hm no it wasn't, there was at least one move that changed stuff 01:46:54 when it colocated with the wiki 01:47:23 The very first join is from codu.xen.prgmr.com. 01:47:54 [[HackEso]] https://esolangs.org/w/index.php?diff=67244&oldid=67233 * Oerjan * (+71) Fix a few errors and mention hurl 01:50:55 The hosts my logs have seen are HackEgo!~HackEgo@162.248.166.242 (CaC, 57k lines), HackEgo!codu@codu.org (who knows where, 12k lines), HackEgo!dlopen@libdl.so (ditto, 5.8k lines) and a few less common ones, including HackEgo!n=HackEgo@codu.xen.prgmr.com, HackEgo!dlopen@64.62.173.65. 01:51:13 Also, the way the command and arguments flow through all the levels is pretty awkward. 01:53:04 * oerjan remembers libdl.so 01:55:04 do you suppose this change is ok? <-- i don't see a rule that it is violating, which is sort of not in the spirit 01:59:05 First, in PRIVMSG/tr_60.cmd (called by multibot for trigger character `) it's split into the command and an optional argument on the first space. Then it calls lib/sandbox with Python subprocess.Popen. That next uses Python subprocess.call to form the umlbox command line: 'nice', '-n10', '/usr/bin/umlbox', ..., '.../limits', 'cmd', 'argument stuff'. Then umlbox shell-escapes all the arguments and 01:59:11 concatenates the results into a 'run' command in the umlbox config file. The umlbox init reads that, and invokes the result using system() -- so passing through a shell at that point. Finally, that triggers the lib/limits script, which sets a few ulimit values and uses bash exec to run the actual command. 02:00:16 `` cat /proc/$PPID/cmdline 02:00:19 sh.-c.'/srv/hackeso-code/multibot_cmds/lib/limits' '`' 'cat /proc/$PPID/cmdline' | cat. 02:00:40 Such a house of cards. 02:01:47 oerjan: Well, maybe subdirectories of tmp/ can be version-controlled. 02:02:05 Or maybe there can be some thing that detects when tmp/ is cleared and puts the things back. 02:05:50 -!- LKoen has quit (Remote host closed the connection). 02:10:33 * oerjan thinks today's schlock mercenary looks a bit inconsistent with the previous claim that most AIs aren't easily copyable 02:50:43 -!- imode has joined. 02:52:49 I think maybe I'm still missing something about non-chronological backjumping. 03:10:27 -!- ais523 has quit (Quit: quit). 03:13:56 `url ../bin/addquote 03:13:57 https://hack.esolangs.org/repo/file/tip/bin/addquote 03:14:29 `url ../bin/delquote 03:14:29 ../hello/oerjan 03:14:30 https://hack.esolangs.org/repo/file/tip/bin/delquote 03:14:53 hi/chaf 03:15:09 thought so 03:15:24 `` ls -l ../share/quotes 03:15:25 lrwxrwxrwx 1 1000 1000 9 Nov 18 10:40 ../share/quotes -> ../quotes 03:15:35 `` rm ../share/quotes 03:15:37 No output. 03:15:59 delquote works in a way that will break if it's a symbolic link 03:17:07 oerjan: ENOENT 03:17:18 did you mean /hackenv/hi/chaf 03:18:37 ENO 03:19:02 You know how it's megaconfusing when executing a file yields ENOENT even though it exists? 03:20:20 b_jonas: ^ 03:20:31 EYESENT 03:20:46 (not really) 03:21:24 `` ls -l program 03:21:25 -rwxr-xr-x 1 1000 1000 1576 Nov 19 03:20 program 03:21:28 `` ./program 03:21:28 /hackenv/bin/`: line 5: ./program: No such file or directory 03:21:50 `` strace ./program 03:21:51 execve("./program", ["./program"], 0x7fbf90dce0 /* 15 vars */) = -1 ENOENT (No such file or directory) \ strace: exec: No such file or directory \ +++ exited with 1 +++ 03:21:53 * oerjan instantly wanted to `doag that 03:21:57 then remembered 03:22:06 sorry 03:22:11 `` ../tmp/program # hth 03:22:12 /hackenv/bin/`: line 5: ../tmp/program: No such file or directory 03:23:40 kmc: puzzle hth 03:23:49 this is a conceptual problem: since files in tmp/ have no repo history, it can be hard to know why they were put there, and therefore whether they're worth saving 03:24:10 I guess it's not a very good puzzle because we've already talked about it. 03:24:22 oerjan: Wasn't the hg repository supposed to solve this problem in the first place? 03:24:26 and the change of pwd encourages people to put things there by accident 03:24:36 The idea was just that no one would care about hg history and it would describe everything. 03:24:36 shachaf: EFULLCIRCLE 03:24:48 So the solution is obvious: Add a second hg repository for tmp/. 03:25:05 EBRILLIANT 03:26:06 As an alternative, I propose something like automatic deletion of tmp/ every day. 03:26:09 Or every hour. 03:26:13 Or maybe just deleting old files automatically. 03:26:28 `` ls 03:26:29 a.c \ a.out \ as-encoding \ asmbf-1.1.1 \ banana.txt \ bfi \ compiled_brachylog.pl \ hexdump.hex \ input.brachylog \ jeval.whatis \ just \ karma \ le \ out \ OUT \ out.a \ out.a.hd \ out.a.xxd \ paste \ program \ single-word-character-names \ spline \ spout \ spout.raw \ temp.b \ test.sh \ tmp-interp \ tmp.txt \ uptime.out 03:28:45 maybe we should warn kspalaiologos before doing it. i think his asmbf workflow isn't quite compatible at the moment. 03:30:02 Also, you can apparently hg add things inside hgignored directories. 03:30:05 fizzie: ☝ 03:30:14 oh that's true 03:30:25 Though that requires superpowers which isn't in the spirit of le/rn 03:30:58 hm 03:31:35 I'm a little worried about the complexity of tmp handling to add version-controlled stuff inside it. I think I'll rather adjust `foo/bar to look for /hackenv/bin/foo/bar (in some shape or form, we'll see), which'll also mean you no longer need even the /hackenv/le, all the binaries can be in bin. 03:32:36 Or maybe we can just get rid of le/rn etc. which are silly commands anyway? 03:32:46 It could be called slashlearn, for instance. 03:32:58 Or lern or lrn or lesrn or le\rn 03:34:00 `` sort -t | tac 03:34:00 sort: option requires an argument -- 't' \ Try 'sort --help' for more information. 03:34:26 `` ls -t | tac 03:34:27 jeval.whatis \ tmp.txt \ out \ out.a \ OUT \ out.a.xxd \ out.a.hd \ a.c \ as-encoding \ single-word-character-names \ a.out \ hexdump.hex \ test.sh \ asmbf-1.1.1 \ just \ banana.txt \ le \ karma \ tmp-interp \ uptime.out \ spout.raw \ spout \ spline \ input.brachylog \ compiled_brachylog.pl \ paste \ temp.b \ bfi \ program 03:34:42 In related news, I would like a config option that can disable .hgignore. Then I could set up .hg/hgrc to point at a read-only ignore file. 03:35:20 Why shouldn't .hgignore belong to the people? 03:35:32 Because it's too hard to make things work sanely. 03:35:42 It doesn't belong to the people any more anyway. 03:35:43 `` ls -t | tac | head -n 12 | xargs rm -v 03:35:44 removed 'jeval.whatis' \ removed 'tmp.txt' \ removed 'out' \ removed 'out.a' \ removed 'OUT' \ removed 'out.a.xxd' \ removed 'out.a.hd' \ removed 'a.c' \ removed 'as-encoding' \ removed 'single-word-character-names' \ removed 'a.out' \ removed 'hexdump.hex' 03:35:46 Is that a goal? 03:35:59 I know it doesn't, but maybe it oughtta. 03:36:02 (compromise) 03:36:03 It's my goal, since I have to pretend to administer that thing. 03:36:17 Hey, you deleted out.a! 03:36:26 what was that for? 03:36:30 get.out.a.here 03:36:43 It was a variant of ./program 03:36:46 `` ./program 03:36:47 /hackenv/bin/`: line 5: ./program: No such file or directory 03:36:51 Oh no, ./program is gone too?! 03:36:52 shachaf: well it was OLD 03:37:30 (Incidentally, one way to "disable" .hgignore would be to only mount a subdirectory of the repository as /hackenv.) 03:37:34 (maybe not _that_ old, but i deleted the 12 oldest files) 03:37:48 (But moving every file into a subdirectory would be the mother of all scowrevs.) 03:37:52 (Anyway, sleep mode.) 03:38:20 (Well, I could always rewrite history so that it looked like it always had been like that.) 03:40:44 `` ls -t | tac 03:40:45 test.sh \ asmbf-1.1.1 \ just \ banana.txt \ le \ karma \ tmp-interp \ uptime.out \ spout.raw \ spout \ spline \ input.brachylog \ compiled_brachylog.pl \ paste \ temp.b \ bfi \ program 03:40:57 shachaf: program is still there 03:42:46 (wait that's the joke isn't it) 03:43:16 `cbt sport 03:43:17 cat "${2:-/dev/stdin}" >$HACKENV/tmp/spout.raw; distort $HACKENV/tmp/spout.raw | spore "${1-1}" 03:43:20 `cbt spore 03:43:21 cat "${2:-/dev/stdin}" > $HACKENV/tmp/spout; spam "${1-1}" 03:43:50 hm 03:43:59 -!- hppavilion[1] has quit (Ping timeout: 246 seconds). 03:44:22 `slbd sport s,$HACKENV,,g 03:44:22 usage: sled file//script 03:44:30 `slbd sport//s,$HACKENV,,g 03:44:32 sport//cat "${2:-/dev/stdin}" >/tmp/spout.raw; distort /tmp/spout.raw | spore "${1-1}" 03:44:51 i don't think there's any reason to have that file persistent 03:45:13 `rm spout.raw 03:45:14 No output. 03:45:40 `` rm -v *brachylog* 03:45:40 removed 'compiled_brachylog.pl' \ removed 'input.brachylog' 03:45:55 and fizzie moved those to /tmp as well afaiu 03:46:37 `url ../bin/uptime 03:46:38 https://hack.esolangs.org/repo/file/tip/bin/uptime 03:47:33 `url uptime.out 03:47:34 https://hack.esolangs.org/tmp/uptime.out 03:48:17 seems like debugging output 03:52:17 -!- MDude has quit (Ping timeout: 240 seconds). 03:52:18 ^show 03:52:18 echo reverb rev rot13 rev2 fib wc ul cho choo pow2 source help hw srmlebac uenlsbcmra scramble unscramble asc ord prefixes tmp test celebrate wiki chr ha rainbow rainbow2 welcome me tell eval elikoski list ping def a thanks tmp2 8ball rreree rerere botsnack bf 03:52:39 ^show bf 03:52:39 (^bf -- evaluates brainfuck)S 03:53:27 ^show def 03:53:27 (hai)S 03:53:42 ^def 03:53:42 hai 03:54:45 ^str 04:20:06 oerjan: That was a sort of joke, yep. 04:26:16 OKAY 04:50:56 -!- imode has quit (Ping timeout: 240 seconds). 05:07:59 helo 05:08:02 what's puzzle 05:08:07 shachaf^ 05:08:32 I had some EtOH 05:08:39 I'm sauzzled 05:54:32 [[User:Zemeckis]] https://esolangs.org/w/index.php?diff=67245&oldid=50152 * Zemeckis * (-98) 05:59:19 `` ls -l program 05:59:20 -rwxr-xr-x 1 1000 1000 1576 Nov 19 03:20 program 05:59:23 `` ./program 05:59:24 /hackenv/bin/`: line 5: ./program: No such file or directory 05:59:27 `` strace ./program 05:59:28 execve("./program", ["./program"], 0x7fbfc5dce0 /* 15 vars */) = -1 ENOENT (No such file or directory) \ strace: exec: No such file or directory \ +++ exited with 1 +++ 05:59:58 kmc: that hth 06:17:13 [[Zemeckis]] N https://esolangs.org/w/index.php?oldid=67246 * Zemeckis * (+28) Redirected page to [[User:Zemeckis]] 06:25:10 [[JUSTIF]] https://esolangs.org/w/index.php?diff=67247&oldid=62061 * Voltage2007 * (+5) 06:46:43 [[Zemeckis]] https://esolangs.org/w/index.php?diff=67248&oldid=67246 * Zemeckis * (-28) Blanked the page 06:58:02 -!- arseniiv has joined. 07:00:53 -!- ineiros has quit (Remote host closed the connection). 07:03:27 [[4DChess]] N https://esolangs.org/w/index.php?oldid=67249 * Zemeckis * (+3027) Page created. 07:03:55 [[4DChess]] M https://esolangs.org/w/index.php?diff=67250&oldid=67249 * Zemeckis * (-1) 07:06:02 [[Talk:4DChess]] N https://esolangs.org/w/index.php?oldid=67251 * Zemeckis * (+140) Created page with "Feel free to improve anything in any way you see fit. ~~~~" 07:06:52 [[User:Zemeckis]] M https://esolangs.org/w/index.php?diff=67252&oldid=67245 * Zemeckis * (+14) /* Projects */ 07:07:48 [[BurgerFlipper]] https://esolangs.org/w/index.php?diff=67253&oldid=50159 * Zemeckis * (+23) 07:09:02 [[BurgerFlipper]] https://esolangs.org/w/index.php?diff=67254&oldid=67253 * Zemeckis * (-23) Undo revision 67253 by [[Special:Contributions/Zemeckis|Zemeckis]] ([[User talk:Zemeckis|talk]]) 07:18:08 [[4DChess]] M https://esolangs.org/w/index.php?diff=67255&oldid=67250 * Zemeckis * (+60) 07:22:45 It seems Schlock got himself a kind of shoulder angel. 07:22:47 EtOH 07:25:27 [[Special:Log/delete]] delete * Oerjan * deleted "[[Zemeckis]]": Author request: content before blanking was: "#REDIRECT [[User: Zemeckis]]" 07:27:08 [[BurgerFlipper]] M https://esolangs.org/w/index.php?diff=67256&oldid=67254 * Zemeckis * (+0) 07:27:09 int-e: just watch out for the shoulder devil 07:27:27 [[BurgerFlipper]] https://esolangs.org/w/index.php?diff=67257&oldid=67256 * Zemeckis * (+0) Undo revision 67256 by [[Special:Contributions/Zemeckis|Zemeckis]] ([[User talk:Zemeckis|talk]]) 07:27:42 [[BurgerFlipper]] https://esolangs.org/w/index.php?diff=67258&oldid=67257 * Zemeckis * (+0) 07:29:15 oerjan: I'm sure she has the capacity to be both./ 07:31:51 given the neighborhood, i was imagining something more tentacly 07:32:51 we'll see 07:33:18 [[4DChess]] M https://esolangs.org/w/index.php?diff=67259&oldid=67255 * Zemeckis * (+6) 07:35:01 -!- mniip has joined. 07:39:58 9 07:43:50 -!- kspalaiologos has joined. 07:44:03 Greetings 07:44:21 `asmbfx out n.A 07:44:21 No output. 07:44:29 `asmbfx out .A 07:44:30 A 07:44:37 Yeah it works 07:46:22 . o O ( Что EtOH? ) 07:46:59 (Not a real question; I duckduckwent.) 07:48:00 ?? 07:51:37 `asmbfx lbl 1/out .A/jmp 1 07:51:52 I'm curious what happens 07:51:58 It seems like it hanged 07:52:07 Yeah 07:52:13 It's dead 07:52:27 `asmbf 07:52:35 ``` ls 07:52:36 asmbf-1.1.1 \ banana.txt \ bfi \ just \ karma \ le \ paste \ program \ spline \ spout \ temp.b \ test.sh \ tmp-interp \ uptime.out 07:52:57 No output. 07:54:07 `` du -s paste 07:54:09 816paste 08:04:42 kspalaiologos: i cleaned up the tmp directory a bit (mostly older stuff) 08:05:19 `stat le 08:05:20 File: le -> /hackenv/le \ Size: 11 Blocks: 0 IO Block: 1024 symbolic link \ Device: 12h/18dInode: 1206924 Links: 1 \ Access: (0777/lrwxrwxrwx) Uid: ( 1000/ UNKNOWN) Gid: ( 1000/ UNKNOWN) \ Access: 2019-11-16 21:29:43.000000000 +0000 \ Modify: 2019-11-16 21:29:43.000000000 +0000 \ Change: 2019-11-16 21:29:43.000000000 +0000 \ Birth: - 08:05:42 (hmm, perhaps the most spammy way to figure out that's a symlink) 08:06:26 tried to stop before your recent additions, though 08:06:55 (although everything in tmp _is_ in principle temporary) 08:07:50 `1 stat le 08:07:51 1/1: File: le -> /hackenv/le \ Size: 11 Blocks: 0 IO Block: 1024 symbolic link \ Device: 12h/18dInode: 1206924 Links: 1 \ Access: (0777/lrwxrwxrwx) Uid: ( 1000/ UNKNOWN) Gid: ( 1000/ UNKNOWN) \ Access: 2019-11-16 21:29:43.000000000 +0000 \ Modify: 2019-11-16 21:29:43.000000000 +0000 \ Change: 2019-11-16 21:29:43.000000000 +0000 \ Birth: - 08:08:10 hm it wasn't cut off, so you _could_ get longer 08:08:35 yeah, it wasn't really meant as a challenge 08:08:42 (come to think of it, i should have used `2) 08:09:06 anyway 08:09:15 -!- oerjan has quit (Quit: Nite). 08:40:21 " hah, I didn't even realise that we created /tmp from inside HackEso, I assumed it was hardcoded" => it is also hardcoded, since you can access tmp through the web interface directly like https://hack.esolangs.org/tmp/banana.txt 08:43:33 ``` asmbf mov r1, 3 08:43:34 +>+[<[>>+>+<<<-]>>[<<+>>-]>[[-]>>[-]+++<<]<<<[>>+>+<<<-]>>[<<+>>-]>[[-]<<<[-]>[-]>>]<<] 08:43:37 ? 08:43:50 `asmbf mov r1,2 08:43:51 +>+[<[>>+>+<<<-]>>[<<+>>-]>[[-]>>[-]++<<]<<<[>>+>+<<<-]>>[<<+>>-]>[[-]<<<[-]>[-]>>]<<] 08:44:13 `asmbfx lbl 1/out 48/jmp 1 08:44:14 000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000 08:44:18 Works 08:47:32 ``` ./labels.pl <<<"@x1y1/%x1y1" 08:47:33 bash: ./labels.pl: No such file or directory 08:47:50 ``` labels.pl <<<"@x1y1/%x1y1 08:47:51 bash: -c: line 0: unexpected EOF while looking for matching `"' \ bash: -c: line 1: syntax error: unexpected end of file 08:48:01 -!- kspalaiologos has quit (Remote host closed the connection). 08:48:09 -!- kspalaiologos has joined. 08:48:16 My client crashed 08:48:42 ``` labels.pl <<<"@x1y1/%x1y1" 08:48:43 lbl 1 08:48:51 It's bricked 08:49:00 For some bizzare reason 08:49:20 ``` labels.pl <<<"@x1y1/%x1y1" > tmp.s 08:49:21 No output. 08:49:29 ``` cat tmp.b 08:49:30 cat: tmp.b: No such file or directory 08:49:41 ``` cat tmp.s 08:49:42 lbl 1 08:49:53 ``` rm tmp.s 08:49:54 No output. 08:52:54 oerjan: re share/quotes , yeah, I even mentioned that a symlink to the writable file is a bit tricky because something could overwrite it with a regular file. I should have realized that that implies the whole symlink thing is a bad idea and shouldn't exist, because you can't safely change commands over without desyncing it. 08:53:08 so we're better with no symlink, and changing over in an incompatible way if we want 08:53:41 (or change over in a more complex way, but still without a symlink) 08:56:10 oerjan: re tmp history, I just suggested that we could solve that for paste only going forward, by making paste log the filename and the IRC_* environment variables somewhere under tmp 08:58:31 that would let people like me search and clean up their own pastes 09:07:36 -!- b_jonas has quit (Quit: leaving). 09:10:25 -!- tromp_ has joined. 09:12:17 -!- tromp has quit (Ping timeout: 246 seconds). 09:50:01 -!- sprocklem has quit (Ping timeout: 265 seconds). 09:55:32 -!- sprocklem has joined. 10:01:08 -!- wib_jonas has joined. 10:05:58 -!- sprocklem has quit (Ping timeout: 265 seconds). 10:21:33 -!- sprocklem has joined. 10:23:40 -!- Sgeo__ has quit (Read error: Connection reset by peer). 10:24:07 -!- Sgeo__ has joined. 10:27:08 -!- ArthurStrong has quit (Quit: leaving). 10:36:19 ``` echo $$ 10:36:21 55 10:36:22 ``` echo $$ 10:36:23 55 10:36:24 ``` echo $$ 10:36:25 55 10:38:13 I recall when people saved a few bytes in some golf programs on anagol by repeatedly submtiting until the pid became just what they want 10:38:27 that doesn't work easily in HackEso because you always get the same pid 10:39:59 apparently the first process of the command always gets the pid 53, but the triple backtick spawns a few more 10:44:47 the anagol server even has a tool for that 11:03:01 Realized I could make /hackenv/tmp more easily un-mess-uppable and stop playing around with .hgignore by just moving it outside the repository completely, and mounting it separately into the umlbox. Not sure if hg would cross a filesystem boundary when looking up the .hg directory. (Git has that special GIT_DISCOVERY_ACROSS_FILESYSTEM option.) 11:04:19 fizzie: you could make it a symlink to a directory outside /hackenv, then hg surely won't follow it 11:07:00 I meant more that it would be desirable for 'hg' commands inside umlbox to ascend from /hackenv/tmp to /hackenv to find /hackenv/.hg, so that the read-only version control commands work without changing the working directory. 11:07:36 (When executing the actions outside the sandbox, there would be no tmp, so nothing to follow.) 11:09:29 ah 11:09:35 yes, that would make sense 11:10:33 ``` cat /hackenv/bin/lastfiles 11:10:34 hg log --removed -l 1 --template "$HACKENV/{join(files,'\n$HACKENV/')}\n" -- "$@" 11:10:39