keyword-help alphabetize

This commit is contained in:
John Kerl 2016-10-01 12:56:16 -04:00
parent 4cbb0e1250
commit 4227b0f104
6 changed files with 583 additions and 551 deletions

View file

@ -4,124 +4,133 @@
#include "mlr_dsl_cst.h"
#include "context_flags.h"
static void mlr_dsl_filter_keyword_usage (FILE* ostream);
static void mlr_dsl_unset_keyword_usage (FILE* ostream);
static void mlr_dsl_tee_keyword_usage (FILE* ostream);
static void mlr_dsl_emit_keyword_usage (FILE* ostream);
static void mlr_dsl_emitp_keyword_usage (FILE* ostream);
static void mlr_dsl_emitf_keyword_usage (FILE* ostream);
static void mlr_dsl_dump_keyword_usage (FILE* ostream);
static void mlr_dsl_edump_keyword_usage (FILE* ostream);
static void mlr_dsl_print_keyword_usage (FILE* ostream);
static void mlr_dsl_printn_keyword_usage (FILE* ostream);
static void mlr_dsl_emit_keyword_usage (FILE* ostream);
static void mlr_dsl_emitf_keyword_usage (FILE* ostream);
static void mlr_dsl_emitp_keyword_usage (FILE* ostream);
static void mlr_dsl_eprint_keyword_usage (FILE* ostream);
static void mlr_dsl_eprintn_keyword_usage (FILE* ostream);
static void mlr_dsl_stdout_keyword_usage (FILE* ostream);
static void mlr_dsl_filter_keyword_usage (FILE* ostream);
static void mlr_dsl_print_keyword_usage (FILE* ostream);
static void mlr_dsl_printn_keyword_usage (FILE* ostream);
static void mlr_dsl_stderr_keyword_usage (FILE* ostream);
static void mlr_dsl_stdout_keyword_usage (FILE* ostream);
static void mlr_dsl_tee_keyword_usage (FILE* ostream);
static void mlr_dsl_unset_keyword_usage (FILE* ostream);
// xxx make table w/ func ptrs etc. reduce code/data dup.
// filter
// unset
// tee
// emit
// emitf
// emitp
// dump
// edump
// print
// printn
// eprint
// eprintn
// stderr
// stdout
// E
// ENV
// FILENAME
// FILENUM
// FNR
// NF
// NR
// PI
// all
// begin
// break
// call
// continue
// do
// elif
// else
// end
// for
// func
// if
// in
// local
// return
// subr
// while
// ================================================================
// Pass function_name == NULL to get usage for all keywords.
// Note keywords are defined in dsls/mlr_dsl_lexer.l.
void mlr_dsl_keyword_usage(FILE* ostream, char* keyword) {
if (keyword == NULL) {
mlr_dsl_filter_keyword_usage(ostream); fprintf(ostream, "\n");
mlr_dsl_unset_keyword_usage(ostream); fprintf(ostream, "\n");
mlr_dsl_tee_keyword_usage(ostream); fprintf(ostream, "\n");
mlr_dsl_emit_keyword_usage(ostream); fprintf(ostream, "\n");
mlr_dsl_emitp_keyword_usage(ostream); fprintf(ostream, "\n");
mlr_dsl_emitf_keyword_usage(ostream); fprintf(ostream, "\n");
mlr_dsl_dump_keyword_usage(ostream); fprintf(ostream, "\n");
mlr_dsl_edump_keyword_usage(ostream); fprintf(ostream, "\n");
mlr_dsl_print_keyword_usage(ostream); fprintf(ostream, "\n");
mlr_dsl_printn_keyword_usage(ostream); fprintf(ostream, "\n");
mlr_dsl_emit_keyword_usage(ostream); fprintf(ostream, "\n");
mlr_dsl_emitf_keyword_usage(ostream); fprintf(ostream, "\n");
mlr_dsl_emitp_keyword_usage(ostream); fprintf(ostream, "\n");
mlr_dsl_eprint_keyword_usage(ostream); fprintf(ostream, "\n");
mlr_dsl_eprintn_keyword_usage(ostream); fprintf(ostream, "\n");
mlr_dsl_stdout_keyword_usage(ostream); fprintf(ostream, "\n");
mlr_dsl_filter_keyword_usage(ostream); fprintf(ostream, "\n");
mlr_dsl_print_keyword_usage(ostream); fprintf(ostream, "\n");
mlr_dsl_printn_keyword_usage(ostream); fprintf(ostream, "\n");
mlr_dsl_stderr_keyword_usage(ostream);
mlr_dsl_stdout_keyword_usage(ostream); fprintf(ostream, "\n");
mlr_dsl_tee_keyword_usage(ostream); fprintf(ostream, "\n");
mlr_dsl_unset_keyword_usage(ostream); fprintf(ostream, "\n");
return;
}
if (streq(keyword, "filter")) {
mlr_dsl_filter_keyword_usage(ostream);
} else if (streq(keyword, "unset")) {
mlr_dsl_unset_keyword_usage(ostream);
} else if (streq(keyword, "tee")) {
mlr_dsl_tee_keyword_usage(ostream);
} else if (streq(keyword, "emit")) {
mlr_dsl_emit_keyword_usage(ostream);
} else if (streq(keyword, "emitp")) {
mlr_dsl_emitp_keyword_usage(ostream);
} else if (streq(keyword, "emitf")) {
mlr_dsl_emitf_keyword_usage(ostream);
} else if (streq(keyword, "dump")) {
mlr_dsl_dump_keyword_usage(ostream);
} else if (streq(keyword, "edump")) {
mlr_dsl_edump_keyword_usage(ostream);
} else if (streq(keyword, "print")) {
mlr_dsl_print_keyword_usage(ostream);
} else if (streq(keyword, "printn")) {
mlr_dsl_print_keyword_usage(ostream);
} else if (streq(keyword, "eprint")) {
mlr_dsl_eprint_keyword_usage(ostream);
} else if (streq(keyword, "eprintn")) {
mlr_dsl_eprint_keyword_usage(ostream);
} else if (streq(keyword, "stdout")) {
mlr_dsl_stdout_keyword_usage(ostream);
} else if (streq(keyword, "stderr")) {
mlr_dsl_stderr_keyword_usage(ostream);
if (streq(keyword, "dump")) { mlr_dsl_dump_keyword_usage(ostream);
} else if (streq(keyword, "edump")) { mlr_dsl_edump_keyword_usage(ostream);
} else if (streq(keyword, "emit")) { mlr_dsl_emit_keyword_usage(ostream);
} else if (streq(keyword, "emitf")) { mlr_dsl_emitf_keyword_usage(ostream);
} else if (streq(keyword, "emitp")) { mlr_dsl_emitp_keyword_usage(ostream);
} else if (streq(keyword, "eprint")) { mlr_dsl_eprint_keyword_usage(ostream);
} else if (streq(keyword, "eprintn")) { mlr_dsl_eprint_keyword_usage(ostream);
} else if (streq(keyword, "filter")) { mlr_dsl_filter_keyword_usage(ostream);
} else if (streq(keyword, "print")) { mlr_dsl_print_keyword_usage(ostream);
} else if (streq(keyword, "printn")) { mlr_dsl_print_keyword_usage(ostream);
} else if (streq(keyword, "stderr")) { mlr_dsl_stderr_keyword_usage(ostream);
} else if (streq(keyword, "stdout")) { mlr_dsl_stdout_keyword_usage(ostream);
} else if (streq(keyword, "tee")) { mlr_dsl_tee_keyword_usage(ostream);
} else if (streq(keyword, "unset")) { mlr_dsl_unset_keyword_usage(ostream);
} else {
fprintf(ostream, "%s: unrecognized keyword \"%s\".\n", MLR_GLOBALS.bargv0, keyword);
}
}
void mlr_dsl_list_all_keywords_raw(FILE* ostream) {
printf("filter\n");
printf("unset\n");
printf("tee\n");
printf("emit\n");
printf("emitp\n");
printf("emitf\n");
printf("dump\n");
printf("edump\n");
printf("print\n");
printf("printn\n");
printf("emit\n");
printf("emitf\n");
printf("emitp\n");
printf("eprint\n");
printf("eprintn\n");
printf("stdout\n");
printf("filter\n");
printf("print\n");
printf("printn\n");
printf("stderr\n");
printf("stdout\n");
printf("tee\n");
printf("unset\n");
}
// ----------------------------------------------------------------
static void mlr_dsl_filter_keyword_usage(FILE* ostream) {
static void mlr_dsl_dump_keyword_usage(FILE* ostream) {
fprintf(ostream,
"filter: includes/excludes the record in the output record stream.\n"
"dump: prints all currently defined out-of-stream variables immediately\n"
" to stdout as JSON.\n"
"\n"
" Example: mlr --from f.dat put 'filter (NR == 2 || $x > 5.4)'\n"
"\n"
" Instead of put with 'filter false' you can simply use put -q. The following\n"
" uses the input record to accumulate data but only prints the running sum\n"
" without printing the input record:\n"
"\n"
" Example: mlr --from f.dat put -q '@running_sum += $x * $y; emit @running_sum'\n");
}
static void mlr_dsl_unset_keyword_usage(FILE* ostream) {
fprintf(ostream,
"unset: clears field(s) from the current record, or an out-of-stream variable.\n"
"\n"
" Example: mlr --from f.dat put 'unset $x'\n"
" Example: mlr --from f.dat put 'unset $*'\n"
" Example: mlr --from f.dat put 'for (k, v in $*) { if (k =~ \"a.*\") { unset $[k] } }'\n"
" Example: mlr --from f.dat put '...; unset @sums'\n"
" Example: mlr --from f.dat put '...; unset @sums[\"green\"]'\n"
" Example: mlr --from f.dat put '...; unset @*'\n");
}
static void mlr_dsl_tee_keyword_usage(FILE* ostream) {
fprintf(ostream,
"tee: prints the current record to specified file.\n"
" This is an immediate print to the specified file (except for pprint format\n"
" which of course waits until the end of the input stream to format all output).\n"
" With >, >>, or |, the data do not become part of the output record stream but\n"
" are instead redirected.\n"
"\n"
" The > and >> are for write and append, as in the shell, but (as with awk) the\n"
" file-overwrite for > is on first write, not per record. The | is for piping to\n"
@ -130,17 +139,18 @@ static void mlr_dsl_tee_keyword_usage(FILE* ostream) {
" value of the piped-to command (for |). Output-formatting flags are taken from\n"
" the main command line.\n"
"\n"
" You can use any of the output-format command-line flags, e.g. --ocsv, --ofs,\n"
" etc., to control the format of the output. See also %s -h.\n"
" Example: mlr --from f.dat put -q '@v[NR]=$*; end { dump }'\n"
" Example: mlr --from f.dat put -q '@v[NR]=$*; end { dump > \"mytap.dat\"}'\n"
" Example: mlr --from f.dat put -q '@v[NR]=$*; end { dump >> \"mytap.dat\"}'\n"
" Example: mlr --from f.dat put -q '@v[NR]=$*; end { dump | \"jq .[]\"}'\n");
}
static void mlr_dsl_edump_keyword_usage(FILE* ostream) {
fprintf(ostream,
"edump: prints all currently defined out-of-stream variables immediately\n"
" to stderr as JSON.\n"
"\n"
" Example: mlr --from f.dat put 'tee > \"/tmp/data-\".$a, $*'\n"
" Example: mlr --from f.dat put 'tee >> \"/tmp/data-\".$a.$b, $*'\n"
" Example: mlr --from f.dat put 'tee > stderr, $*'\n"
" Example: mlr --from f.dat put -q 'tee | \"tr \[a-z\\] \[A-Z\\]\", $*'\n"
" Example: mlr --from f.dat put -q 'tee | \"tr \[a-z\\] \[A-Z\\] > /tmp/data-\".$a, $*'\n"
" Example: mlr --from f.dat put -q 'tee | \"gzip > /tmp/data-\".$a.\".gz\", $*'\n"
" Example: mlr --from f.dat put -q --ojson 'tee | \"gzip > /tmp/data-\".$a.\".gz\", $*'\n",
MLR_GLOBALS.bargv0);
" Example: mlr --from f.dat put -q '@v[NR]=$*; end { edump }'\n");
}
static void mlr_dsl_emit_keyword_usage(FILE* ostream) {
@ -175,6 +185,37 @@ static void mlr_dsl_emit_keyword_usage(FILE* ostream) {
MLR_GLOBALS.bargv0);
}
static void mlr_dsl_emitf_keyword_usage(FILE* ostream) {
fprintf(ostream,
"emitf: inserts non-indexed out-of-stream variable(s) side-by-side into the\n"
" output record stream.\n"
"\n"
" With >, >>, or |, the data do not become part of the output record stream but\n"
" are instead redirected.\n"
"\n"
" The > and >> are for write and append, as in the shell, but (as with awk) the\n"
" file-overwrite for > is on first write, not per record. The | is for piping to\n"
" a process which will process the data. There will be one open file for each\n"
" distinct file name (for > and >>) or one subordinate process for each distinct\n"
" value of the piped-to command (for |). Output-formatting flags are taken from\n"
" the main command line.\n"
"\n"
" You can use any of the output-format command-line flags, e.g. --ocsv, --ofs,\n"
" etc., to control the format of the output if the output is redirected. See also %s -h.\n"
"\n"
" Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf @a'\n"
" Example: mlr --from f.dat put --oxtab '@a=$i;@b+=$x;@c+=$y; emitf > \"tap-\".$i.\".dat\", @a'\n"
" Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf @a, @b, @c'\n"
" Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf > \"mytap.dat\", @a, @b, @c'\n"
" Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf >> \"mytap.dat\", @a, @b, @c'\n"
" Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf > stderr, @a, @b, @c'\n"
" Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf | \"grep somepattern\", @a, @b, @c'\n"
" Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf | \"grep somepattern > mytap.dat\", @a, @b, @c'\n"
"\n"
" Please see http://johnkerl.org/miller/doc for more information.\n",
MLR_GLOBALS.bargv0);
}
static void mlr_dsl_emitp_keyword_usage(FILE* ostream) {
fprintf(ostream,
"emitp: inserts an out-of-stream variable into the output record stream.\n"
@ -208,64 +249,32 @@ static void mlr_dsl_emitp_keyword_usage(FILE* ostream) {
MLR_GLOBALS.bargv0);
}
static void mlr_dsl_emitf_keyword_usage(FILE* ostream) {
static void mlr_dsl_eprint_keyword_usage(FILE* ostream) {
fprintf(ostream,
"emitf: inserts non-indexed out-of-stream variable(s) side-by-side into the\n"
" output record stream.\n"
"\n"
" With >, >>, or |, the data do not become part of the output record stream but\n"
" are instead redirected.\n"
"\n"
" The > and >> are for write and append, as in the shell, but (as with awk) the\n"
" file-overwrite for > is on first write, not per record. The | is for piping to\n"
" a process which will process the data. There will be one open file for each\n"
" distinct file name (for > and >>) or one subordinate process for each distinct\n"
" value of the piped-to command (for |). Output-formatting flags are taken from\n"
" the main command line.\n"
"\n"
" You can use any of the output-format command-line flags, e.g. --ocsv, --ofs,\n"
" etc., to control the format of the output if the output is redirected. See also %s -h.\n"
"\n"
" Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf @a'\n"
" Example: mlr --from f.dat put --oxtab '@a=$i;@b+=$x;@c+=$y; emitf > \"tap-\".$i.\".dat\", @a'\n"
" Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf @a, @b, @c'\n"
" Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf > \"mytap.dat\", @a, @b, @c'\n"
" Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf >> \"mytap.dat\", @a, @b, @c'\n"
" Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf > stderr, @a, @b, @c'\n"
" Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf | \"grep somepattern\", @a, @b, @c'\n"
" Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf | \"grep somepattern > mytap.dat\", @a, @b, @c'\n"
"\n"
" Please see http://johnkerl.org/miller/doc for more information.\n",
MLR_GLOBALS.bargv0);
"eprint: prints expression immediately to stderr.\n"
" Example: mlr --from f.dat put -q 'eprint \"The sum of x and y is \".($x+$y)'\n"
" Example: mlr --from f.dat put -q 'for (k, v in $*) { eprint k . \" => \" . v }'\n"
" Example: mlr --from f.dat put '(NR %% 1000 == 0) { eprint \"Checkpoint \".NR}'\n");
}
static void mlr_dsl_dump_keyword_usage(FILE* ostream) {
static void mlr_dsl_eprintn_keyword_usage(FILE* ostream) {
fprintf(ostream,
"dump: prints all currently defined out-of-stream variables immediately\n"
" to stdout as JSON.\n"
"\n"
" With >, >>, or |, the data do not become part of the output record stream but\n"
" are instead redirected.\n"
"\n"
" The > and >> are for write and append, as in the shell, but (as with awk) the\n"
" file-overwrite for > is on first write, not per record. The | is for piping to\n"
" a process which will process the data. There will be one open file for each\n"
" distinct file name (for > and >>) or one subordinate process for each distinct\n"
" value of the piped-to command (for |). Output-formatting flags are taken from\n"
" the main command line.\n"
"\n"
" Example: mlr --from f.dat put -q '@v[NR]=$*; end { dump }'\n"
" Example: mlr --from f.dat put -q '@v[NR]=$*; end { dump > \"mytap.dat\"}'\n"
" Example: mlr --from f.dat put -q '@v[NR]=$*; end { dump >> \"mytap.dat\"}'\n"
" Example: mlr --from f.dat put -q '@v[NR]=$*; end { dump | \"jq .[]\"}'\n");
"eprintn: prints expression immediately to stderr, without trailing newline.\n"
" Example: mlr --from f.dat put -q 'eprintn \"The sum of x and y is \".($x+$y); eprint \"\"'\n");
}
static void mlr_dsl_edump_keyword_usage(FILE* ostream) {
// ----------------------------------------------------------------
static void mlr_dsl_filter_keyword_usage(FILE* ostream) {
fprintf(ostream,
"edump: prints all currently defined out-of-stream variables immediately\n"
" to stderr as JSON.\n"
"filter: includes/excludes the record in the output record stream.\n"
"\n"
" Example: mlr --from f.dat put -q '@v[NR]=$*; end { edump }'\n");
" Example: mlr --from f.dat put 'filter (NR == 2 || $x > 5.4)'\n"
"\n"
" Instead of put with 'filter false' you can simply use put -q. The following\n"
" uses the input record to accumulate data but only prints the running sum\n"
" without printing the input record:\n"
"\n"
" Example: mlr --from f.dat put -q '@running_sum += $x * $y; emit @running_sum'\n");
}
static void mlr_dsl_print_keyword_usage(FILE* ostream) {
@ -282,18 +291,10 @@ static void mlr_dsl_printn_keyword_usage(FILE* ostream) {
" Example: mlr --from f.dat put -q 'printn \".\"; end { print \"\" }'\n");
}
static void mlr_dsl_eprint_keyword_usage(FILE* ostream) {
static void mlr_dsl_stderr_keyword_usage(FILE* ostream) {
fprintf(ostream,
"eprint: prints expression immediately to stderr.\n"
" Example: mlr --from f.dat put -q 'eprint \"The sum of x and y is \".($x+$y)'\n"
" Example: mlr --from f.dat put -q 'for (k, v in $*) { eprint k . \" => \" . v }'\n"
" Example: mlr --from f.dat put '(NR %% 1000 == 0) { eprint \"Checkpoint \".NR}'\n");
}
static void mlr_dsl_eprintn_keyword_usage(FILE* ostream) {
fprintf(ostream,
"eprintn: prints expression immediately to stderr, without trailing newline.\n"
" Example: mlr --from f.dat put -q 'eprintn \"The sum of x and y is \".($x+$y); eprint \"\"'\n");
"stderr: Used for tee, emit, emitf, emitp, print, and dump in place of filename\n"
" to print to standard error.\n");
}
static void mlr_dsl_stdout_keyword_usage(FILE* ostream) {
@ -302,8 +303,40 @@ static void mlr_dsl_stdout_keyword_usage(FILE* ostream) {
" to print to standard output.\n");
}
static void mlr_dsl_stderr_keyword_usage(FILE* ostream) {
static void mlr_dsl_tee_keyword_usage(FILE* ostream) {
fprintf(ostream,
"stderr: Used for tee, emit, emitf, emitp, print, and dump in place of filename\n"
" to print to standard error.\n");
"tee: prints the current record to specified file.\n"
" This is an immediate print to the specified file (except for pprint format\n"
" which of course waits until the end of the input stream to format all output).\n"
"\n"
" The > and >> are for write and append, as in the shell, but (as with awk) the\n"
" file-overwrite for > is on first write, not per record. The | is for piping to\n"
" a process which will process the data. There will be one open file for each\n"
" distinct file name (for > and >>) or one subordinate process for each distinct\n"
" value of the piped-to command (for |). Output-formatting flags are taken from\n"
" the main command line.\n"
"\n"
" You can use any of the output-format command-line flags, e.g. --ocsv, --ofs,\n"
" etc., to control the format of the output. See also %s -h.\n"
"\n"
" Example: mlr --from f.dat put 'tee > \"/tmp/data-\".$a, $*'\n"
" Example: mlr --from f.dat put 'tee >> \"/tmp/data-\".$a.$b, $*'\n"
" Example: mlr --from f.dat put 'tee > stderr, $*'\n"
" Example: mlr --from f.dat put -q 'tee | \"tr \[a-z\\] \[A-Z\\]\", $*'\n"
" Example: mlr --from f.dat put -q 'tee | \"tr \[a-z\\] \[A-Z\\] > /tmp/data-\".$a, $*'\n"
" Example: mlr --from f.dat put -q 'tee | \"gzip > /tmp/data-\".$a.\".gz\", $*'\n"
" Example: mlr --from f.dat put -q --ojson 'tee | \"gzip > /tmp/data-\".$a.\".gz\", $*'\n",
MLR_GLOBALS.bargv0);
}
static void mlr_dsl_unset_keyword_usage(FILE* ostream) {
fprintf(ostream,
"unset: clears field(s) from the current record, or an out-of-stream variable.\n"
"\n"
" Example: mlr --from f.dat put 'unset $x'\n"
" Example: mlr --from f.dat put 'unset $*'\n"
" Example: mlr --from f.dat put 'for (k, v in $*) { if (k =~ \"a.*\") { unset $[k] } }'\n"
" Example: mlr --from f.dat put '...; unset @sums'\n"
" Example: mlr --from f.dat put '...; unset @sums[\"green\"]'\n"
" Example: mlr --from f.dat put '...; unset @*'\n");
}

View file

@ -1595,32 +1595,13 @@ FUNCTIONS FOR FILTER/PUT
(class=time #args=0): Floating-point seconds since the epoch,
e.g. 1440768801.748936.
KEYWORDS FOR PUT
filter
filter: includes/excludes the record in the output record stream.
KEYWORDS FOR PUT AND FILTER
dump
dump: prints all currently defined out-of-stream variables immediately
to stdout as JSON.
Example: mlr --from f.dat put 'filter (NR == 2 || $x > 5.4)'
Instead of put with 'filter false' you can simply use put -q. The following
uses the input record to accumulate data but only prints the running sum
without printing the input record:
Example: mlr --from f.dat put -q '@running_sum += $x * $y; emit @running_sum'
unset
unset: clears field(s) from the current record, or an out-of-stream variable.
Example: mlr --from f.dat put 'unset $x'
Example: mlr --from f.dat put 'unset $*'
Example: mlr --from f.dat put 'for (k, v in $*) { if (k =~ "a.*") { unset $[k] } }'
Example: mlr --from f.dat put '...; unset @sums'
Example: mlr --from f.dat put '...; unset @sums["green"]'
Example: mlr --from f.dat put '...; unset @*'
tee
tee: prints the current record to specified file.
This is an immediate print to the specified file (except for pprint format
which of course waits until the end of the input stream to format all output).
With >, >>, or |, the data do not become part of the output record stream but
are instead redirected.
The > and >> are for write and append, as in the shell, but (as with awk) the
file-overwrite for > is on first write, not per record. The | is for piping to
@ -1629,16 +1610,16 @@ KEYWORDS FOR PUT
value of the piped-to command (for |). Output-formatting flags are taken from
the main command line.
You can use any of the output-format command-line flags, e.g. --ocsv, --ofs,
etc., to control the format of the output. See also mlr -h.
Example: mlr --from f.dat put -q '@v[NR]=$*; end { dump }'
Example: mlr --from f.dat put -q '@v[NR]=$*; end { dump > "mytap.dat"}'
Example: mlr --from f.dat put -q '@v[NR]=$*; end { dump >> "mytap.dat"}'
Example: mlr --from f.dat put -q '@v[NR]=$*; end { dump | "jq .[]"}'
Example: mlr --from f.dat put 'tee > "/tmp/data-".$a, $*'
Example: mlr --from f.dat put 'tee >> "/tmp/data-".$a.$b, $*'
Example: mlr --from f.dat put 'tee > stderr, $*'
Example: mlr --from f.dat put -q 'tee | "tr [a-z\] [A-Z\]", $*'
Example: mlr --from f.dat put -q 'tee | "tr [a-z\] [A-Z\] > /tmp/data-".$a, $*'
Example: mlr --from f.dat put -q 'tee | "gzip > /tmp/data-".$a.".gz", $*'
Example: mlr --from f.dat put -q --ojson 'tee | "gzip > /tmp/data-".$a.".gz", $*'
edump
edump: prints all currently defined out-of-stream variables immediately
to stderr as JSON.
Example: mlr --from f.dat put -q '@v[NR]=$*; end { edump }'
emit
emit: inserts an out-of-stream variable into the output record stream. Hashmap
@ -1669,6 +1650,34 @@ KEYWORDS FOR PUT
Please see http://johnkerl.org/miller/doc for more information.
emitf
emitf: inserts non-indexed out-of-stream variable(s) side-by-side into the
output record stream.
With >, >>, or |, the data do not become part of the output record stream but
are instead redirected.
The > and >> are for write and append, as in the shell, but (as with awk) the
file-overwrite for > is on first write, not per record. The | is for piping to
a process which will process the data. There will be one open file for each
distinct file name (for > and >>) or one subordinate process for each distinct
value of the piped-to command (for |). Output-formatting flags are taken from
the main command line.
You can use any of the output-format command-line flags, e.g. --ocsv, --ofs,
etc., to control the format of the output if the output is redirected. See also mlr -h.
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf @a'
Example: mlr --from f.dat put --oxtab '@a=$i;@b+=$x;@c+=$y; emitf > "tap-".$i.".dat", @a'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf @a, @b, @c'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf > "mytap.dat", @a, @b, @c'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf >> "mytap.dat", @a, @b, @c'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf > stderr, @a, @b, @c'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf | "grep somepattern", @a, @b, @c'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf | "grep somepattern > mytap.dat", @a, @b, @c'
Please see http://johnkerl.org/miller/doc for more information.
emitp
emitp: inserts an out-of-stream variable into the output record stream.
Hashmap indices present in the data but not slotted by emitp arguments are
@ -1699,58 +1708,28 @@ KEYWORDS FOR PUT
Please see http://johnkerl.org/miller/doc for more information.
emitf
emitf: inserts non-indexed out-of-stream variable(s) side-by-side into the
output record stream.
eprint
eprint: prints expression immediately to stderr.
Example: mlr --from f.dat put -q 'eprint "The sum of x and y is ".($x+$y)'
Example: mlr --from f.dat put -q 'for (k, v in $*) { eprint k . " => " . v }'
Example: mlr --from f.dat put '(NR % 1000 == 0) { eprint "Checkpoint ".NR}'
With >, >>, or |, the data do not become part of the output record stream but
are instead redirected.
eprintn
eprint: prints expression immediately to stderr.
Example: mlr --from f.dat put -q 'eprint "The sum of x and y is ".($x+$y)'
Example: mlr --from f.dat put -q 'for (k, v in $*) { eprint k . " => " . v }'
Example: mlr --from f.dat put '(NR % 1000 == 0) { eprint "Checkpoint ".NR}'
The > and >> are for write and append, as in the shell, but (as with awk) the
file-overwrite for > is on first write, not per record. The | is for piping to
a process which will process the data. There will be one open file for each
distinct file name (for > and >>) or one subordinate process for each distinct
value of the piped-to command (for |). Output-formatting flags are taken from
the main command line.
filter
filter: includes/excludes the record in the output record stream.
You can use any of the output-format command-line flags, e.g. --ocsv, --ofs,
etc., to control the format of the output if the output is redirected. See also mlr -h.
Example: mlr --from f.dat put 'filter (NR == 2 || $x > 5.4)'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf @a'
Example: mlr --from f.dat put --oxtab '@a=$i;@b+=$x;@c+=$y; emitf > "tap-".$i.".dat", @a'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf @a, @b, @c'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf > "mytap.dat", @a, @b, @c'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf >> "mytap.dat", @a, @b, @c'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf > stderr, @a, @b, @c'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf | "grep somepattern", @a, @b, @c'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf | "grep somepattern > mytap.dat", @a, @b, @c'
Instead of put with 'filter false' you can simply use put -q. The following
uses the input record to accumulate data but only prints the running sum
without printing the input record:
Please see http://johnkerl.org/miller/doc for more information.
dump
dump: prints all currently defined out-of-stream variables immediately
to stdout as JSON.
With >, >>, or |, the data do not become part of the output record stream but
are instead redirected.
The > and >> are for write and append, as in the shell, but (as with awk) the
file-overwrite for > is on first write, not per record. The | is for piping to
a process which will process the data. There will be one open file for each
distinct file name (for > and >>) or one subordinate process for each distinct
value of the piped-to command (for |). Output-formatting flags are taken from
the main command line.
Example: mlr --from f.dat put -q '@v[NR]=$*; end { dump }'
Example: mlr --from f.dat put -q '@v[NR]=$*; end { dump > "mytap.dat"}'
Example: mlr --from f.dat put -q '@v[NR]=$*; end { dump >> "mytap.dat"}'
Example: mlr --from f.dat put -q '@v[NR]=$*; end { dump | "jq .[]"}'
edump
edump: prints all currently defined out-of-stream variables immediately
to stderr as JSON.
Example: mlr --from f.dat put -q '@v[NR]=$*; end { edump }'
Example: mlr --from f.dat put -q '@running_sum += $x * $y; emit @running_sum'
print
print: prints expression immediately to stdout.
@ -1764,25 +1743,46 @@ KEYWORDS FOR PUT
Example: mlr --from f.dat put -q 'for (k, v in $*) { print k . " => " . v }'
Example: mlr --from f.dat put '(NR % 1000 == 0) { print > stderr, "Checkpoint ".NR}'
eprint
eprint: prints expression immediately to stderr.
Example: mlr --from f.dat put -q 'eprint "The sum of x and y is ".($x+$y)'
Example: mlr --from f.dat put -q 'for (k, v in $*) { eprint k . " => " . v }'
Example: mlr --from f.dat put '(NR % 1000 == 0) { eprint "Checkpoint ".NR}'
eprintn
eprint: prints expression immediately to stderr.
Example: mlr --from f.dat put -q 'eprint "The sum of x and y is ".($x+$y)'
Example: mlr --from f.dat put -q 'for (k, v in $*) { eprint k . " => " . v }'
Example: mlr --from f.dat put '(NR % 1000 == 0) { eprint "Checkpoint ".NR}'
stderr
stderr: Used for tee, emit, emitf, emitp, print, and dump in place of filename
to print to standard error.
stdout
stdout: Used for tee, emit, emitf, emitp, print, and dump in place of filename
to print to standard output.
stderr
stderr: Used for tee, emit, emitf, emitp, print, and dump in place of filename
to print to standard error.
tee
tee: prints the current record to specified file.
This is an immediate print to the specified file (except for pprint format
which of course waits until the end of the input stream to format all output).
The > and >> are for write and append, as in the shell, but (as with awk) the
file-overwrite for > is on first write, not per record. The | is for piping to
a process which will process the data. There will be one open file for each
distinct file name (for > and >>) or one subordinate process for each distinct
value of the piped-to command (for |). Output-formatting flags are taken from
the main command line.
You can use any of the output-format command-line flags, e.g. --ocsv, --ofs,
etc., to control the format of the output. See also mlr -h.
Example: mlr --from f.dat put 'tee > "/tmp/data-".$a, $*'
Example: mlr --from f.dat put 'tee >> "/tmp/data-".$a.$b, $*'
Example: mlr --from f.dat put 'tee > stderr, $*'
Example: mlr --from f.dat put -q 'tee | "tr [a-z\] [A-Z\]", $*'
Example: mlr --from f.dat put -q 'tee | "tr [a-z\] [A-Z\] > /tmp/data-".$a, $*'
Example: mlr --from f.dat put -q 'tee | "gzip > /tmp/data-".$a.".gz", $*'
Example: mlr --from f.dat put -q --ojson 'tee | "gzip > /tmp/data-".$a.".gz", $*'
unset
unset: clears field(s) from the current record, or an out-of-stream variable.
Example: mlr --from f.dat put 'unset $x'
Example: mlr --from f.dat put 'unset $*'
Example: mlr --from f.dat put 'for (k, v in $*) { if (k =~ "a.*") { unset $[k] } }'
Example: mlr --from f.dat put '...; unset @sums'
Example: mlr --from f.dat put '...; unset @sums["green"]'
Example: mlr --from f.dat put '...; unset @*'
AUTHOR
Miller is written by John Kerl <kerl.john.r@gmail.com>.
@ -1797,7 +1797,7 @@ SEE ALSO
2016-09-30 MILLER(1)
2016-10-01 MILLER(1)
</pre>
</div>
<p/>

View file

@ -1448,32 +1448,13 @@ FUNCTIONS FOR FILTER/PUT
(class=time #args=0): Floating-point seconds since the epoch,
e.g. 1440768801.748936.
KEYWORDS FOR PUT
filter
filter: includes/excludes the record in the output record stream.
KEYWORDS FOR PUT AND FILTER
dump
dump: prints all currently defined out-of-stream variables immediately
to stdout as JSON.
Example: mlr --from f.dat put 'filter (NR == 2 || $x > 5.4)'
Instead of put with 'filter false' you can simply use put -q. The following
uses the input record to accumulate data but only prints the running sum
without printing the input record:
Example: mlr --from f.dat put -q '@running_sum += $x * $y; emit @running_sum'
unset
unset: clears field(s) from the current record, or an out-of-stream variable.
Example: mlr --from f.dat put 'unset $x'
Example: mlr --from f.dat put 'unset $*'
Example: mlr --from f.dat put 'for (k, v in $*) { if (k =~ "a.*") { unset $[k] } }'
Example: mlr --from f.dat put '...; unset @sums'
Example: mlr --from f.dat put '...; unset @sums["green"]'
Example: mlr --from f.dat put '...; unset @*'
tee
tee: prints the current record to specified file.
This is an immediate print to the specified file (except for pprint format
which of course waits until the end of the input stream to format all output).
With >, >>, or |, the data do not become part of the output record stream but
are instead redirected.
The > and >> are for write and append, as in the shell, but (as with awk) the
file-overwrite for > is on first write, not per record. The | is for piping to
@ -1482,16 +1463,16 @@ KEYWORDS FOR PUT
value of the piped-to command (for |). Output-formatting flags are taken from
the main command line.
You can use any of the output-format command-line flags, e.g. --ocsv, --ofs,
etc., to control the format of the output. See also mlr -h.
Example: mlr --from f.dat put -q '@v[NR]=$*; end { dump }'
Example: mlr --from f.dat put -q '@v[NR]=$*; end { dump > "mytap.dat"}'
Example: mlr --from f.dat put -q '@v[NR]=$*; end { dump >> "mytap.dat"}'
Example: mlr --from f.dat put -q '@v[NR]=$*; end { dump | "jq .[]"}'
Example: mlr --from f.dat put 'tee > "/tmp/data-".$a, $*'
Example: mlr --from f.dat put 'tee >> "/tmp/data-".$a.$b, $*'
Example: mlr --from f.dat put 'tee > stderr, $*'
Example: mlr --from f.dat put -q 'tee | "tr [a-z\] [A-Z\]", $*'
Example: mlr --from f.dat put -q 'tee | "tr [a-z\] [A-Z\] > /tmp/data-".$a, $*'
Example: mlr --from f.dat put -q 'tee | "gzip > /tmp/data-".$a.".gz", $*'
Example: mlr --from f.dat put -q --ojson 'tee | "gzip > /tmp/data-".$a.".gz", $*'
edump
edump: prints all currently defined out-of-stream variables immediately
to stderr as JSON.
Example: mlr --from f.dat put -q '@v[NR]=$*; end { edump }'
emit
emit: inserts an out-of-stream variable into the output record stream. Hashmap
@ -1522,6 +1503,34 @@ KEYWORDS FOR PUT
Please see http://johnkerl.org/miller/doc for more information.
emitf
emitf: inserts non-indexed out-of-stream variable(s) side-by-side into the
output record stream.
With >, >>, or |, the data do not become part of the output record stream but
are instead redirected.
The > and >> are for write and append, as in the shell, but (as with awk) the
file-overwrite for > is on first write, not per record. The | is for piping to
a process which will process the data. There will be one open file for each
distinct file name (for > and >>) or one subordinate process for each distinct
value of the piped-to command (for |). Output-formatting flags are taken from
the main command line.
You can use any of the output-format command-line flags, e.g. --ocsv, --ofs,
etc., to control the format of the output if the output is redirected. See also mlr -h.
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf @a'
Example: mlr --from f.dat put --oxtab '@a=$i;@b+=$x;@c+=$y; emitf > "tap-".$i.".dat", @a'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf @a, @b, @c'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf > "mytap.dat", @a, @b, @c'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf >> "mytap.dat", @a, @b, @c'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf > stderr, @a, @b, @c'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf | "grep somepattern", @a, @b, @c'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf | "grep somepattern > mytap.dat", @a, @b, @c'
Please see http://johnkerl.org/miller/doc for more information.
emitp
emitp: inserts an out-of-stream variable into the output record stream.
Hashmap indices present in the data but not slotted by emitp arguments are
@ -1552,58 +1561,28 @@ KEYWORDS FOR PUT
Please see http://johnkerl.org/miller/doc for more information.
emitf
emitf: inserts non-indexed out-of-stream variable(s) side-by-side into the
output record stream.
eprint
eprint: prints expression immediately to stderr.
Example: mlr --from f.dat put -q 'eprint "The sum of x and y is ".($x+$y)'
Example: mlr --from f.dat put -q 'for (k, v in $*) { eprint k . " => " . v }'
Example: mlr --from f.dat put '(NR % 1000 == 0) { eprint "Checkpoint ".NR}'
With >, >>, or |, the data do not become part of the output record stream but
are instead redirected.
eprintn
eprint: prints expression immediately to stderr.
Example: mlr --from f.dat put -q 'eprint "The sum of x and y is ".($x+$y)'
Example: mlr --from f.dat put -q 'for (k, v in $*) { eprint k . " => " . v }'
Example: mlr --from f.dat put '(NR % 1000 == 0) { eprint "Checkpoint ".NR}'
The > and >> are for write and append, as in the shell, but (as with awk) the
file-overwrite for > is on first write, not per record. The | is for piping to
a process which will process the data. There will be one open file for each
distinct file name (for > and >>) or one subordinate process for each distinct
value of the piped-to command (for |). Output-formatting flags are taken from
the main command line.
filter
filter: includes/excludes the record in the output record stream.
You can use any of the output-format command-line flags, e.g. --ocsv, --ofs,
etc., to control the format of the output if the output is redirected. See also mlr -h.
Example: mlr --from f.dat put 'filter (NR == 2 || $x > 5.4)'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf @a'
Example: mlr --from f.dat put --oxtab '@a=$i;@b+=$x;@c+=$y; emitf > "tap-".$i.".dat", @a'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf @a, @b, @c'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf > "mytap.dat", @a, @b, @c'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf >> "mytap.dat", @a, @b, @c'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf > stderr, @a, @b, @c'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf | "grep somepattern", @a, @b, @c'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf | "grep somepattern > mytap.dat", @a, @b, @c'
Instead of put with 'filter false' you can simply use put -q. The following
uses the input record to accumulate data but only prints the running sum
without printing the input record:
Please see http://johnkerl.org/miller/doc for more information.
dump
dump: prints all currently defined out-of-stream variables immediately
to stdout as JSON.
With >, >>, or |, the data do not become part of the output record stream but
are instead redirected.
The > and >> are for write and append, as in the shell, but (as with awk) the
file-overwrite for > is on first write, not per record. The | is for piping to
a process which will process the data. There will be one open file for each
distinct file name (for > and >>) or one subordinate process for each distinct
value of the piped-to command (for |). Output-formatting flags are taken from
the main command line.
Example: mlr --from f.dat put -q '@v[NR]=$*; end { dump }'
Example: mlr --from f.dat put -q '@v[NR]=$*; end { dump > "mytap.dat"}'
Example: mlr --from f.dat put -q '@v[NR]=$*; end { dump >> "mytap.dat"}'
Example: mlr --from f.dat put -q '@v[NR]=$*; end { dump | "jq .[]"}'
edump
edump: prints all currently defined out-of-stream variables immediately
to stderr as JSON.
Example: mlr --from f.dat put -q '@v[NR]=$*; end { edump }'
Example: mlr --from f.dat put -q '@running_sum += $x * $y; emit @running_sum'
print
print: prints expression immediately to stdout.
@ -1617,25 +1596,46 @@ KEYWORDS FOR PUT
Example: mlr --from f.dat put -q 'for (k, v in $*) { print k . " => " . v }'
Example: mlr --from f.dat put '(NR % 1000 == 0) { print > stderr, "Checkpoint ".NR}'
eprint
eprint: prints expression immediately to stderr.
Example: mlr --from f.dat put -q 'eprint "The sum of x and y is ".($x+$y)'
Example: mlr --from f.dat put -q 'for (k, v in $*) { eprint k . " => " . v }'
Example: mlr --from f.dat put '(NR % 1000 == 0) { eprint "Checkpoint ".NR}'
eprintn
eprint: prints expression immediately to stderr.
Example: mlr --from f.dat put -q 'eprint "The sum of x and y is ".($x+$y)'
Example: mlr --from f.dat put -q 'for (k, v in $*) { eprint k . " => " . v }'
Example: mlr --from f.dat put '(NR % 1000 == 0) { eprint "Checkpoint ".NR}'
stderr
stderr: Used for tee, emit, emitf, emitp, print, and dump in place of filename
to print to standard error.
stdout
stdout: Used for tee, emit, emitf, emitp, print, and dump in place of filename
to print to standard output.
stderr
stderr: Used for tee, emit, emitf, emitp, print, and dump in place of filename
to print to standard error.
tee
tee: prints the current record to specified file.
This is an immediate print to the specified file (except for pprint format
which of course waits until the end of the input stream to format all output).
The > and >> are for write and append, as in the shell, but (as with awk) the
file-overwrite for > is on first write, not per record. The | is for piping to
a process which will process the data. There will be one open file for each
distinct file name (for > and >>) or one subordinate process for each distinct
value of the piped-to command (for |). Output-formatting flags are taken from
the main command line.
You can use any of the output-format command-line flags, e.g. --ocsv, --ofs,
etc., to control the format of the output. See also mlr -h.
Example: mlr --from f.dat put 'tee > "/tmp/data-".$a, $*'
Example: mlr --from f.dat put 'tee >> "/tmp/data-".$a.$b, $*'
Example: mlr --from f.dat put 'tee > stderr, $*'
Example: mlr --from f.dat put -q 'tee | "tr [a-z\] [A-Z\]", $*'
Example: mlr --from f.dat put -q 'tee | "tr [a-z\] [A-Z\] > /tmp/data-".$a, $*'
Example: mlr --from f.dat put -q 'tee | "gzip > /tmp/data-".$a.".gz", $*'
Example: mlr --from f.dat put -q --ojson 'tee | "gzip > /tmp/data-".$a.".gz", $*'
unset
unset: clears field(s) from the current record, or an out-of-stream variable.
Example: mlr --from f.dat put 'unset $x'
Example: mlr --from f.dat put 'unset $*'
Example: mlr --from f.dat put 'for (k, v in $*) { if (k =~ "a.*") { unset $[k] } }'
Example: mlr --from f.dat put '...; unset @sums'
Example: mlr --from f.dat put '...; unset @sums["green"]'
Example: mlr --from f.dat put '...; unset @*'
AUTHOR
Miller is written by John Kerl <kerl.john.r@gmail.com>.
@ -1650,4 +1650,4 @@ SEE ALSO
2016-09-30 MILLER(1)
2016-10-01 MILLER(1)

View file

@ -108,7 +108,7 @@ output separator to the given value."""
end
keywords = `mlr --list-all-keywords-raw`
print make_section('KEYWORDS FOR PUT', [
print make_section('KEYWORDS FOR PUT AND FILTER', [
""
])
keywords = keywords.strip.split("\n").uniq

234
doc/mlr.1
View file

@ -2,12 +2,12 @@
.\" Title: mlr
.\" Author: [see the "AUTHOR" section]
.\" Generator: ./mkman.rb
.\" Date: 2016-09-30
.\" Date: 2016-10-01
.\" Manual: \ \&
.\" Source: \ \&
.\" Language: English
.\"
.TH "MILLER" "1" "2016-09-30" "\ \&" "\ \&"
.TH "MILLER" "1" "2016-10-01" "\ \&" "\ \&"
.\" -----------------------------------------------------------------
.\" * Portability definitions
.\" ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@ -2433,50 +2433,19 @@ e.g. 1440768801.748936.
.fi
.if n \{\
.RE
.SH "KEYWORDS FOR PUT"
.SH "KEYWORDS FOR PUT AND FILTER"
.sp
.SS "filter"
.SS "dump"
.if n \{\
.RS 0
.\}
.nf
filter: includes/excludes the record in the output record stream.
dump: prints all currently defined out-of-stream variables immediately
to stdout as JSON.
Example: mlr --from f.dat put 'filter (NR == 2 || $x > 5.4)'
Instead of put with 'filter false' you can simply use put -q. The following
uses the input record to accumulate data but only prints the running sum
without printing the input record:
Example: mlr --from f.dat put -q '@running_sum += $x * $y; emit @running_sum'
.fi
.if n \{\
.RE
.SS "unset"
.if n \{\
.RS 0
.\}
.nf
unset: clears field(s) from the current record, or an out-of-stream variable.
Example: mlr --from f.dat put 'unset $x'
Example: mlr --from f.dat put 'unset $*'
Example: mlr --from f.dat put 'for (k, v in $*) { if (k =~ "a.*") { unset $[k] } }'
Example: mlr --from f.dat put '...; unset @sums'
Example: mlr --from f.dat put '...; unset @sums["green"]'
Example: mlr --from f.dat put '...; unset @*'
.fi
.if n \{\
.RE
.SS "tee"
.if n \{\
.RS 0
.\}
.nf
tee: prints the current record to specified file.
This is an immediate print to the specified file (except for pprint format
which of course waits until the end of the input stream to format all output).
With >, >>, or |, the data do not become part of the output record stream but
are instead redirected.
The > and >> are for write and append, as in the shell, but (as with awk) the
file-overwrite for > is on first write, not per record. The | is for piping to
@ -2485,16 +2454,22 @@ tee: prints the current record to specified file.
value of the piped-to command (for |). Output-formatting flags are taken from
the main command line.
You can use any of the output-format command-line flags, e.g. --ocsv, --ofs,
etc., to control the format of the output. See also mlr -h.
Example: mlr --from f.dat put -q '@v[NR]=$*; end { dump }'
Example: mlr --from f.dat put -q '@v[NR]=$*; end { dump > "mytap.dat"}'
Example: mlr --from f.dat put -q '@v[NR]=$*; end { dump >> "mytap.dat"}'
Example: mlr --from f.dat put -q '@v[NR]=$*; end { dump | "jq .[]"}'
.fi
.if n \{\
.RE
.SS "edump"
.if n \{\
.RS 0
.\}
.nf
edump: prints all currently defined out-of-stream variables immediately
to stderr as JSON.
Example: mlr --from f.dat put 'tee > "/tmp/data-".$a, $*'
Example: mlr --from f.dat put 'tee >> "/tmp/data-".$a.$b, $*'
Example: mlr --from f.dat put 'tee > stderr, $*'
Example: mlr --from f.dat put -q 'tee | "tr [a-z\e] [A-Z\e]", $*'
Example: mlr --from f.dat put -q 'tee | "tr [a-z\e] [A-Z\e] > /tmp/data-".$a, $*'
Example: mlr --from f.dat put -q 'tee | "gzip > /tmp/data-".$a.".gz", $*'
Example: mlr --from f.dat put -q --ojson 'tee | "gzip > /tmp/data-".$a.".gz", $*'
Example: mlr --from f.dat put -q '@v[NR]=$*; end { edump }'
.fi
.if n \{\
.RE
@ -2533,6 +2508,40 @@ emit: inserts an out-of-stream variable into the output record stream. Hashmap
.fi
.if n \{\
.RE
.SS "emitf"
.if n \{\
.RS 0
.\}
.nf
emitf: inserts non-indexed out-of-stream variable(s) side-by-side into the
output record stream.
With >, >>, or |, the data do not become part of the output record stream but
are instead redirected.
The > and >> are for write and append, as in the shell, but (as with awk) the
file-overwrite for > is on first write, not per record. The | is for piping to
a process which will process the data. There will be one open file for each
distinct file name (for > and >>) or one subordinate process for each distinct
value of the piped-to command (for |). Output-formatting flags are taken from
the main command line.
You can use any of the output-format command-line flags, e.g. --ocsv, --ofs,
etc., to control the format of the output if the output is redirected. See also mlr -h.
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf @a'
Example: mlr --from f.dat put --oxtab '@a=$i;@b+=$x;@c+=$y; emitf > "tap-".$i.".dat", @a'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf @a, @b, @c'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf > "mytap.dat", @a, @b, @c'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf >> "mytap.dat", @a, @b, @c'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf > stderr, @a, @b, @c'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf | "grep somepattern", @a, @b, @c'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf | "grep somepattern > mytap.dat", @a, @b, @c'
Please see http://johnkerl.org/miller/doc for more information.
.fi
.if n \{\
.RE
.SS "emitp"
.if n \{\
.RS 0
@ -2569,74 +2578,44 @@ emitp: inserts an out-of-stream variable into the output record stream.
.fi
.if n \{\
.RE
.SS "emitf"
.SS "eprint"
.if n \{\
.RS 0
.\}
.nf
emitf: inserts non-indexed out-of-stream variable(s) side-by-side into the
output record stream.
With >, >>, or |, the data do not become part of the output record stream but
are instead redirected.
The > and >> are for write and append, as in the shell, but (as with awk) the
file-overwrite for > is on first write, not per record. The | is for piping to
a process which will process the data. There will be one open file for each
distinct file name (for > and >>) or one subordinate process for each distinct
value of the piped-to command (for |). Output-formatting flags are taken from
the main command line.
You can use any of the output-format command-line flags, e.g. --ocsv, --ofs,
etc., to control the format of the output if the output is redirected. See also mlr -h.
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf @a'
Example: mlr --from f.dat put --oxtab '@a=$i;@b+=$x;@c+=$y; emitf > "tap-".$i.".dat", @a'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf @a, @b, @c'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf > "mytap.dat", @a, @b, @c'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf >> "mytap.dat", @a, @b, @c'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf > stderr, @a, @b, @c'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf | "grep somepattern", @a, @b, @c'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf | "grep somepattern > mytap.dat", @a, @b, @c'
Please see http://johnkerl.org/miller/doc for more information.
eprint: prints expression immediately to stderr.
Example: mlr --from f.dat put -q 'eprint "The sum of x and y is ".($x+$y)'
Example: mlr --from f.dat put -q 'for (k, v in $*) { eprint k . " => " . v }'
Example: mlr --from f.dat put '(NR % 1000 == 0) { eprint "Checkpoint ".NR}'
.fi
.if n \{\
.RE
.SS "dump"
.SS "eprintn"
.if n \{\
.RS 0
.\}
.nf
dump: prints all currently defined out-of-stream variables immediately
to stdout as JSON.
With >, >>, or |, the data do not become part of the output record stream but
are instead redirected.
The > and >> are for write and append, as in the shell, but (as with awk) the
file-overwrite for > is on first write, not per record. The | is for piping to
a process which will process the data. There will be one open file for each
distinct file name (for > and >>) or one subordinate process for each distinct
value of the piped-to command (for |). Output-formatting flags are taken from
the main command line.
Example: mlr --from f.dat put -q '@v[NR]=$*; end { dump }'
Example: mlr --from f.dat put -q '@v[NR]=$*; end { dump > "mytap.dat"}'
Example: mlr --from f.dat put -q '@v[NR]=$*; end { dump >> "mytap.dat"}'
Example: mlr --from f.dat put -q '@v[NR]=$*; end { dump | "jq .[]"}'
eprint: prints expression immediately to stderr.
Example: mlr --from f.dat put -q 'eprint "The sum of x and y is ".($x+$y)'
Example: mlr --from f.dat put -q 'for (k, v in $*) { eprint k . " => " . v }'
Example: mlr --from f.dat put '(NR % 1000 == 0) { eprint "Checkpoint ".NR}'
.fi
.if n \{\
.RE
.SS "edump"
.SS "filter"
.if n \{\
.RS 0
.\}
.nf
edump: prints all currently defined out-of-stream variables immediately
to stderr as JSON.
filter: includes/excludes the record in the output record stream.
Example: mlr --from f.dat put -q '@v[NR]=$*; end { edump }'
Example: mlr --from f.dat put 'filter (NR == 2 || $x > 5.4)'
Instead of put with 'filter false' you can simply use put -q. The following
uses the input record to accumulate data but only prints the running sum
without printing the input record:
Example: mlr --from f.dat put -q '@running_sum += $x * $y; emit @running_sum'
.fi
.if n \{\
.RE
@ -2664,27 +2643,13 @@ print: prints expression immediately to stdout.
.fi
.if n \{\
.RE
.SS "eprint"
.SS "stderr"
.if n \{\
.RS 0
.\}
.nf
eprint: prints expression immediately to stderr.
Example: mlr --from f.dat put -q 'eprint "The sum of x and y is ".($x+$y)'
Example: mlr --from f.dat put -q 'for (k, v in $*) { eprint k . " => " . v }'
Example: mlr --from f.dat put '(NR % 1000 == 0) { eprint "Checkpoint ".NR}'
.fi
.if n \{\
.RE
.SS "eprintn"
.if n \{\
.RS 0
.\}
.nf
eprint: prints expression immediately to stderr.
Example: mlr --from f.dat put -q 'eprint "The sum of x and y is ".($x+$y)'
Example: mlr --from f.dat put -q 'for (k, v in $*) { eprint k . " => " . v }'
Example: mlr --from f.dat put '(NR % 1000 == 0) { eprint "Checkpoint ".NR}'
stderr: Used for tee, emit, emitf, emitp, print, and dump in place of filename
to print to standard error.
.fi
.if n \{\
.RE
@ -2698,13 +2663,48 @@ stdout: Used for tee, emit, emitf, emitp, print, and dump in place of filename
.fi
.if n \{\
.RE
.SS "stderr"
.SS "tee"
.if n \{\
.RS 0
.\}
.nf
stderr: Used for tee, emit, emitf, emitp, print, and dump in place of filename
to print to standard error.
tee: prints the current record to specified file.
This is an immediate print to the specified file (except for pprint format
which of course waits until the end of the input stream to format all output).
The > and >> are for write and append, as in the shell, but (as with awk) the
file-overwrite for > is on first write, not per record. The | is for piping to
a process which will process the data. There will be one open file for each
distinct file name (for > and >>) or one subordinate process for each distinct
value of the piped-to command (for |). Output-formatting flags are taken from
the main command line.
You can use any of the output-format command-line flags, e.g. --ocsv, --ofs,
etc., to control the format of the output. See also mlr -h.
Example: mlr --from f.dat put 'tee > "/tmp/data-".$a, $*'
Example: mlr --from f.dat put 'tee >> "/tmp/data-".$a.$b, $*'
Example: mlr --from f.dat put 'tee > stderr, $*'
Example: mlr --from f.dat put -q 'tee | "tr [a-z\e] [A-Z\e]", $*'
Example: mlr --from f.dat put -q 'tee | "tr [a-z\e] [A-Z\e] > /tmp/data-".$a, $*'
Example: mlr --from f.dat put -q 'tee | "gzip > /tmp/data-".$a.".gz", $*'
Example: mlr --from f.dat put -q --ojson 'tee | "gzip > /tmp/data-".$a.".gz", $*'
.fi
.if n \{\
.RE
.SS "unset"
.if n \{\
.RS 0
.\}
.nf
unset: clears field(s) from the current record, or an out-of-stream variable.
Example: mlr --from f.dat put 'unset $x'
Example: mlr --from f.dat put 'unset $*'
Example: mlr --from f.dat put 'for (k, v in $*) { if (k =~ "a.*") { unset $[k] } }'
Example: mlr --from f.dat put '...; unset @sums'
Example: mlr --from f.dat put '...; unset @sums["green"]'
Example: mlr --from f.dat put '...; unset @*'
.fi
.if n \{\
.RE

View file

@ -4579,28 +4579,11 @@ eks pan 2 0.7586799647899636 0.5221511083334797
<div class="pokipanel">
<pre>
$ mlr --help-all-keywords
filter: includes/excludes the record in the output record stream.
dump: prints all currently defined out-of-stream variables immediately
to stdout as JSON.
Example: mlr --from f.dat put 'filter (NR == 2 || $x &gt; 5.4)'
Instead of put with 'filter false' you can simply use put -q. The following
uses the input record to accumulate data but only prints the running sum
without printing the input record:
Example: mlr --from f.dat put -q '@running_sum += $x * $y; emit @running_sum'
unset: clears field(s) from the current record, or an out-of-stream variable.
Example: mlr --from f.dat put 'unset $x'
Example: mlr --from f.dat put 'unset $*'
Example: mlr --from f.dat put 'for (k, v in $*) { if (k =~ "a.*") { unset $[k] } }'
Example: mlr --from f.dat put '...; unset @sums'
Example: mlr --from f.dat put '...; unset @sums["green"]'
Example: mlr --from f.dat put '...; unset @*'
tee: prints the current record to specified file.
This is an immediate print to the specified file (except for pprint format
which of course waits until the end of the input stream to format all output).
With &gt;, &gt;&gt;, or |, the data do not become part of the output record stream but
are instead redirected.
The &gt; and &gt;&gt; are for write and append, as in the shell, but (as with awk) the
file-overwrite for &gt; is on first write, not per record. The | is for piping to
@ -4609,16 +4592,15 @@ tee: prints the current record to specified file.
value of the piped-to command (for |). Output-formatting flags are taken from
the main command line.
You can use any of the output-format command-line flags, e.g. --ocsv, --ofs,
etc., to control the format of the output. See also mlr -h.
Example: mlr --from f.dat put -q '@v[NR]=$*; end { dump }'
Example: mlr --from f.dat put -q '@v[NR]=$*; end { dump &gt; "mytap.dat"}'
Example: mlr --from f.dat put -q '@v[NR]=$*; end { dump &gt;&gt; "mytap.dat"}'
Example: mlr --from f.dat put -q '@v[NR]=$*; end { dump | "jq .[]"}'
Example: mlr --from f.dat put 'tee &gt; "/tmp/data-".$a, $*'
Example: mlr --from f.dat put 'tee &gt;&gt; "/tmp/data-".$a.$b, $*'
Example: mlr --from f.dat put 'tee &gt; stderr, $*'
Example: mlr --from f.dat put -q 'tee | "tr [a-z\] [A-Z\]", $*'
Example: mlr --from f.dat put -q 'tee | "tr [a-z\] [A-Z\] &gt; /tmp/data-".$a, $*'
Example: mlr --from f.dat put -q 'tee | "gzip &gt; /tmp/data-".$a.".gz", $*'
Example: mlr --from f.dat put -q --ojson 'tee | "gzip &gt; /tmp/data-".$a.".gz", $*'
edump: prints all currently defined out-of-stream variables immediately
to stderr as JSON.
Example: mlr --from f.dat put -q '@v[NR]=$*; end { edump }'
emit: inserts an out-of-stream variable into the output record stream. Hashmap
indices present in the data but not slotted by emit arguments are not output.
@ -4648,6 +4630,33 @@ emit: inserts an out-of-stream variable into the output record stream. Hashmap
Please see http://johnkerl.org/miller/doc for more information.
emitf: inserts non-indexed out-of-stream variable(s) side-by-side into the
output record stream.
With &gt;, &gt;&gt;, or |, the data do not become part of the output record stream but
are instead redirected.
The &gt; and &gt;&gt; are for write and append, as in the shell, but (as with awk) the
file-overwrite for &gt; is on first write, not per record. The | is for piping to
a process which will process the data. There will be one open file for each
distinct file name (for &gt; and &gt;&gt;) or one subordinate process for each distinct
value of the piped-to command (for |). Output-formatting flags are taken from
the main command line.
You can use any of the output-format command-line flags, e.g. --ocsv, --ofs,
etc., to control the format of the output if the output is redirected. See also mlr -h.
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf @a'
Example: mlr --from f.dat put --oxtab '@a=$i;@b+=$x;@c+=$y; emitf &gt; "tap-".$i.".dat", @a'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf @a, @b, @c'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf &gt; "mytap.dat", @a, @b, @c'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf &gt;&gt; "mytap.dat", @a, @b, @c'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf &gt; stderr, @a, @b, @c'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf | "grep somepattern", @a, @b, @c'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf | "grep somepattern &gt; mytap.dat", @a, @b, @c'
Please see http://johnkerl.org/miller/doc for more information.
emitp: inserts an out-of-stream variable into the output record stream.
Hashmap indices present in the data but not slotted by emitp arguments are
output concatenated with ":".
@ -4677,55 +4686,23 @@ emitp: inserts an out-of-stream variable into the output record stream.
Please see http://johnkerl.org/miller/doc for more information.
emitf: inserts non-indexed out-of-stream variable(s) side-by-side into the
output record stream.
eprint: prints expression immediately to stderr.
Example: mlr --from f.dat put -q 'eprint "The sum of x and y is ".($x+$y)'
Example: mlr --from f.dat put -q 'for (k, v in $*) { eprint k . " =&gt; " . v }'
Example: mlr --from f.dat put '(NR % 1000 == 0) { eprint "Checkpoint ".NR}'
With &gt;, &gt;&gt;, or |, the data do not become part of the output record stream but
are instead redirected.
eprintn: prints expression immediately to stderr, without trailing newline.
Example: mlr --from f.dat put -q 'eprintn "The sum of x and y is ".($x+$y); eprint ""'
The &gt; and &gt;&gt; are for write and append, as in the shell, but (as with awk) the
file-overwrite for &gt; is on first write, not per record. The | is for piping to
a process which will process the data. There will be one open file for each
distinct file name (for &gt; and &gt;&gt;) or one subordinate process for each distinct
value of the piped-to command (for |). Output-formatting flags are taken from
the main command line.
filter: includes/excludes the record in the output record stream.
You can use any of the output-format command-line flags, e.g. --ocsv, --ofs,
etc., to control the format of the output if the output is redirected. See also mlr -h.
Example: mlr --from f.dat put 'filter (NR == 2 || $x &gt; 5.4)'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf @a'
Example: mlr --from f.dat put --oxtab '@a=$i;@b+=$x;@c+=$y; emitf &gt; "tap-".$i.".dat", @a'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf @a, @b, @c'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf &gt; "mytap.dat", @a, @b, @c'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf &gt;&gt; "mytap.dat", @a, @b, @c'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf &gt; stderr, @a, @b, @c'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf | "grep somepattern", @a, @b, @c'
Example: mlr --from f.dat put '@a=$i;@b+=$x;@c+=$y; emitf | "grep somepattern &gt; mytap.dat", @a, @b, @c'
Instead of put with 'filter false' you can simply use put -q. The following
uses the input record to accumulate data but only prints the running sum
without printing the input record:
Please see http://johnkerl.org/miller/doc for more information.
dump: prints all currently defined out-of-stream variables immediately
to stdout as JSON.
With &gt;, &gt;&gt;, or |, the data do not become part of the output record stream but
are instead redirected.
The &gt; and &gt;&gt; are for write and append, as in the shell, but (as with awk) the
file-overwrite for &gt; is on first write, not per record. The | is for piping to
a process which will process the data. There will be one open file for each
distinct file name (for &gt; and &gt;&gt;) or one subordinate process for each distinct
value of the piped-to command (for |). Output-formatting flags are taken from
the main command line.
Example: mlr --from f.dat put -q '@v[NR]=$*; end { dump }'
Example: mlr --from f.dat put -q '@v[NR]=$*; end { dump &gt; "mytap.dat"}'
Example: mlr --from f.dat put -q '@v[NR]=$*; end { dump &gt;&gt; "mytap.dat"}'
Example: mlr --from f.dat put -q '@v[NR]=$*; end { dump | "jq .[]"}'
edump: prints all currently defined out-of-stream variables immediately
to stderr as JSON.
Example: mlr --from f.dat put -q '@v[NR]=$*; end { edump }'
Example: mlr --from f.dat put -q '@running_sum += $x * $y; emit @running_sum'
print: prints expression immediately to stdout.
Example: mlr --from f.dat put -q 'print "The sum of x and y is ".($x+$y)'
@ -4735,19 +4712,41 @@ print: prints expression immediately to stdout.
printn: prints expression immediately to stdout, without trailing newline.
Example: mlr --from f.dat put -q 'printn "."; end { print "" }'
eprint: prints expression immediately to stderr.
Example: mlr --from f.dat put -q 'eprint "The sum of x and y is ".($x+$y)'
Example: mlr --from f.dat put -q 'for (k, v in $*) { eprint k . " =&gt; " . v }'
Example: mlr --from f.dat put '(NR % 1000 == 0) { eprint "Checkpoint ".NR}'
eprintn: prints expression immediately to stderr, without trailing newline.
Example: mlr --from f.dat put -q 'eprintn "The sum of x and y is ".($x+$y); eprint ""'
stderr: Used for tee, emit, emitf, emitp, print, and dump in place of filename
to print to standard error.
stdout: Used for tee, emit, emitf, emitp, print, and dump in place of filename
to print to standard output.
stderr: Used for tee, emit, emitf, emitp, print, and dump in place of filename
to print to standard error.
tee: prints the current record to specified file.
This is an immediate print to the specified file (except for pprint format
which of course waits until the end of the input stream to format all output).
The &gt; and &gt;&gt; are for write and append, as in the shell, but (as with awk) the
file-overwrite for &gt; is on first write, not per record. The | is for piping to
a process which will process the data. There will be one open file for each
distinct file name (for &gt; and &gt;&gt;) or one subordinate process for each distinct
value of the piped-to command (for |). Output-formatting flags are taken from
the main command line.
You can use any of the output-format command-line flags, e.g. --ocsv, --ofs,
etc., to control the format of the output. See also mlr -h.
Example: mlr --from f.dat put 'tee &gt; "/tmp/data-".$a, $*'
Example: mlr --from f.dat put 'tee &gt;&gt; "/tmp/data-".$a.$b, $*'
Example: mlr --from f.dat put 'tee &gt; stderr, $*'
Example: mlr --from f.dat put -q 'tee | "tr [a-z\] [A-Z\]", $*'
Example: mlr --from f.dat put -q 'tee | "tr [a-z\] [A-Z\] &gt; /tmp/data-".$a, $*'
Example: mlr --from f.dat put -q 'tee | "gzip &gt; /tmp/data-".$a.".gz", $*'
Example: mlr --from f.dat put -q --ojson 'tee | "gzip &gt; /tmp/data-".$a.".gz", $*'
unset: clears field(s) from the current record, or an out-of-stream variable.
Example: mlr --from f.dat put 'unset $x'
Example: mlr --from f.dat put 'unset $*'
Example: mlr --from f.dat put 'for (k, v in $*) { if (k =~ "a.*") { unset $[k] } }'
Example: mlr --from f.dat put '...; unset @sums'
Example: mlr --from f.dat put '...; unset @sums["green"]'
Example: mlr --from f.dat put '...; unset @*'
</pre>
</div>
<p/>