diff --git a/docs6/src/file-formats.md b/docs6/src/file-formats.md index b9d5c9f0b..1bbbccd72 100644 --- a/docs6/src/file-formats.md +++ b/docs6/src/file-formats.md @@ -553,6 +553,7 @@ Essentials: mlr help file-formats Flags: mlr help flags + mlr help list-separator-aliases mlr help comments-in-data-flags mlr help compressed-data-flags mlr help csv-only-flags @@ -628,6 +629,7 @@ Essentials: mlr help file-formats Flags: mlr help flags + mlr help list-separator-aliases mlr help comments-in-data-flags mlr help compressed-data-flags mlr help csv-only-flags diff --git a/docs6/src/manpage.md b/docs6/src/manpage.md index e5b4e9de1..9f7740b47 100644 --- a/docs6/src/manpage.md +++ b/docs6/src/manpage.md @@ -131,6 +131,7 @@ HELP OPTIONS mlr help file-formats Flags: mlr help flags + mlr help list-separator-aliases mlr help comments-in-data-flags mlr help compressed-data-flags mlr help csv-only-flags @@ -626,6 +627,17 @@ SEPARATOR FLAGS - C-style escape sequences, e.g. `--rs '\r\n' --fs '\t'`. - To avoid backslashing, you can use any of the following names: + ascii_esc = "\x1b" + ascii_etx = "\x04" + ascii_fs = "\x1c" + ascii_gs = "\x1d" + ascii_null = "\x01" + ascii_rs = "\x1e" + ascii_soh = "\x02" + ascii_stx = "\x03" + ascii_us = "\x1f" + asv_fs = "\x1f" + asv_rs = "\x1e" colon = ":" comma = "," cr = "\r" @@ -640,7 +652,12 @@ SEPARATOR FLAGS semicolon = ";" slash = "/" space = " " + spaces = "( )+" tab = "\t" + tabs = "(\t)+" + usv_fs = "\xe2\x90\x9f" + usv_rs = "\xe2\x90\x9e" + whitespace = "([ \t])+" * Default separators by format: @@ -2741,5 +2758,5 @@ SEE ALSO - 2021-09-20 MILLER(1) + 2021-09-21 MILLER(1) diff --git a/docs6/src/manpage.txt b/docs6/src/manpage.txt index 0f36b976b..e448fe191 100644 --- a/docs6/src/manpage.txt +++ b/docs6/src/manpage.txt @@ -110,6 +110,7 @@ HELP OPTIONS mlr help file-formats Flags: mlr help flags + mlr help list-separator-aliases mlr help comments-in-data-flags mlr help compressed-data-flags mlr help csv-only-flags @@ -605,6 +606,17 @@ SEPARATOR FLAGS - C-style escape sequences, e.g. `--rs '\r\n' --fs '\t'`. - To avoid backslashing, you can use any of the following names: + ascii_esc = "\x1b" + ascii_etx = "\x04" + ascii_fs = "\x1c" + ascii_gs = "\x1d" + ascii_null = "\x01" + ascii_rs = "\x1e" + ascii_soh = "\x02" + ascii_stx = "\x03" + ascii_us = "\x1f" + asv_fs = "\x1f" + asv_rs = "\x1e" colon = ":" comma = "," cr = "\r" @@ -619,7 +631,12 @@ SEPARATOR FLAGS semicolon = ";" slash = "/" space = " " + spaces = "( )+" tab = "\t" + tabs = "(\t)+" + usv_fs = "\xe2\x90\x9f" + usv_rs = "\xe2\x90\x9e" + whitespace = "([ \t])+" * Default separators by format: @@ -2720,4 +2737,4 @@ SEE ALSO - 2021-09-20 MILLER(1) + 2021-09-21 MILLER(1) diff --git a/docs6/src/new-in-miller-6.md b/docs6/src/new-in-miller-6.md index 22fada1f8..59ac53188 100644 --- a/docs6/src/new-in-miller-6.md +++ b/docs6/src/new-in-miller-6.md @@ -137,6 +137,15 @@ For example (see [https://github.com/johnkerl/miller/issues/178](https://github. Miller now has a read-evaluate-print-loop ([REPL](repl.md)) where you can single-step through your data-file record, express arbitrary statements to converse with the data, etc. +## Regex support for IFS and IPS + +You can now split fields on whitespace when whitespace is a mix of tabs and +spaces. As well, you can use regular expressions for the input field-separator +and the input pair-separator. Please see the section on +[multi-character and regular-expression separators](reference-main-separators.md#multi-character-and-regular-expression-separators). + +In particular, for NIDX format, the default IFS now allows splitting on one or more of space or tab. + ## Case-folded sorting options The [sort](reference-verbs.md#sort) verb now accepts `-c` and `-cr` options for case-folded ascending/descending sort, respetively. diff --git a/docs6/src/new-in-miller-6.md.in b/docs6/src/new-in-miller-6.md.in index 0922fe815..0e479ffb7 100644 --- a/docs6/src/new-in-miller-6.md.in +++ b/docs6/src/new-in-miller-6.md.in @@ -97,6 +97,15 @@ GENMD_EOF Miller now has a read-evaluate-print-loop ([REPL](repl.md)) where you can single-step through your data-file record, express arbitrary statements to converse with the data, etc. +## Regex support for IFS and IPS + +You can now split fields on whitespace when whitespace is a mix of tabs and +spaces. As well, you can use regular expressions for the input field-separator +and the input pair-separator. Please see the section on +[multi-character and regular-expression separators](reference-main-separators.md#multi-character-and-regular-expression-separators). + +In particular, for NIDX format, the default IFS now allows splitting on one or more of space or tab. + ## Case-folded sorting options The [sort](reference-verbs.md#sort) verb now accepts `-c` and `-cr` options for case-folded ascending/descending sort, respetively. diff --git a/docs6/src/online-help.md b/docs6/src/online-help.md index ad660aecc..d6137bb19 100644 --- a/docs6/src/online-help.md +++ b/docs6/src/online-help.md @@ -49,6 +49,7 @@ Essentials: mlr help file-formats Flags: mlr help flags + mlr help list-separator-aliases mlr help comments-in-data-flags mlr help compressed-data-flags mlr help csv-only-flags @@ -102,6 +103,7 @@ Essentials: mlr help file-formats Flags: mlr help flags + mlr help list-separator-aliases mlr help comments-in-data-flags mlr help compressed-data-flags mlr help csv-only-flags diff --git a/docs6/src/proofreads.txt b/docs6/src/proofreads.txt index 0fd6da871..438e50d0d 100644 --- a/docs6/src/proofreads.txt +++ b/docs6/src/proofreads.txt @@ -4,8 +4,13 @@ ? twi-dm re all-contribs: all-contributors.org * nikos materials -> fold in -C! repifs !! https://pkg.go.dev/regexp#Regexp.Split 2-for-1 -- get regexp as well ? - - make table at seps.md.in, ffmt down vs XS across +c force CSV IFS single-char at CLIP? or CSV setup? IFS1? +C need multi-IRS reader for ASV & explicit CRLF (if supported); also need no-traiing-lf handling + +? look at: + regtest/cases-pending-go-port/dsl-output-redirects/0071/cmd + regtest/cases-pending-go-port/dsl-redirects/0004/cmd wtf no diff? + regtest/cases-pending-go-port/dsl-redirects/0010/cmd jvstack ? * r-strings branch! C stats1 --fr @@ -20,6 +25,8 @@ e fzf-ish w/ head -n 4, --from, up-arrow & append verb, then cat -- find & updat https://github.com/johnkerl/miller/issues/77#issuecomment-538553828 c! seps \001 etc ! + mlrc --iasv --oxtab cat regtest/input/example.asv + mlr --iasv --oxtab cat regtest/input/example.asv mlrc --iusv --oxtab cat regtest/input/example.usv mlr --iusv --oxtab cat regtest/input/example.usv @@ -27,6 +34,9 @@ o check for determinism regtest/cases/verb-join-prepipe/0003/cmd * UT for https://github.com/johnkerl/miller/issues/653 ---------------------------------------------------------------- +headerless CSV: separate page +e nidx, --implicit-csv-header, --headerless-csv-output; surver miller/issues ... +e make a --headerless-csv-input alias record-heterogeneity: l link-to's: diff --git a/docs6/src/record-heterogeneity.md b/docs6/src/record-heterogeneity.md index 5243782c8..752a70e46 100644 --- a/docs6/src/record-heterogeneity.md +++ b/docs6/src/record-heterogeneity.md @@ -138,8 +138,9 @@ keys from the header line together with the values from each data line, the second record has a missing value for key `c` (which ought to be fillable), while the third record has a value `10` with no key for it. -Using the `--allow-ragged-csv-input` option we can fill values in too-short -rows, and provide a key (column number starting with 1) for too-long rows: +Using the [`--allow-ragged-csv-input` flag](reference-main-flag-list.md#csv-only-flags) +we can fill values in too-short rows, and provide a key (column number starting +with 1) for too-long rows: 
 mlr --icsv --ojson --allow-ragged-csv-input cat data/het/ragged.csv
diff --git a/docs6/src/reference-main-flag-list.md b/docs6/src/reference-main-flag-list.md
index cbe109965..f0b76b650 100644
--- a/docs6/src/reference-main-flag-list.md
+++ b/docs6/src/reference-main-flag-list.md
@@ -489,6 +489,17 @@ Notes about all other separators:
   - C-style escape sequences, e.g. `--rs '\r\n' --fs '\t'`.
   - To avoid backslashing, you can use any of the following names:
 
+          ascii_esc  = "\x1b"
+          ascii_etx  = "\x04"
+          ascii_fs   = "\x1c"
+          ascii_gs   = "\x1d"
+          ascii_null = "\x01"
+          ascii_rs   = "\x1e"
+          ascii_soh  = "\x02"
+          ascii_stx  = "\x03"
+          ascii_us   = "\x1f"
+          asv_fs     = "\x1f"
+          asv_rs     = "\x1e"
           colon      = ":"
           comma      = ","
           cr         = "\r"
@@ -503,7 +514,12 @@ Notes about all other separators:
           semicolon  = ";"
           slash      = "/"
           space      = " "
+          spaces     = "( )+"
           tab        = "\t"
+          tabs       = "(\t)+"
+          usv_fs     = "\xe2\x90\x9f"
+          usv_rs     = "\xe2\x90\x9e"
+          whitespace = "([ \t])+"
 
 * Default separators by format:
 
diff --git a/docs6/src/reference-main-separators.md b/docs6/src/reference-main-separators.md
index b3c0a6e30..d46a8ba8f 100644
--- a/docs6/src/reference-main-separators.md
+++ b/docs6/src/reference-main-separators.md
@@ -50,8 +50,9 @@ part of the JSON specification.
 
 ## Input and output separators
 
-Miller lets you use the same separators for input and output, or, to change
-them between input and output, if you wish to transform your data in that way.
+Miller lets you use the same separators for input and output (e.g. CSV input,
+CSV output), or, to change them between input and output (e.g. CSV input, JSON
+output), if you wish to transform your data in that way.
 
 Miller uses the names `IRS` and `ORS` for the input and output record
 separators, `IFS` and `OFS` for the input and output field separators, and
@@ -59,6 +60,14 @@ separators, `IFS` and `OFS` for the input and output field separators, and
 
 For example:
 
+
+cat data/a.dkvp
+

+
+a=1,b=2,c=3
+a=4,b=5,c=6
+

+
 
 mlr --ifs , --ofs ';' --ips = --ops : cut -o -f c,a,b data/a.dkvp
 

@@ -71,6 +80,14 @@ If your data has non-default separators and you don't want to change those
 between input and output, you can use `--rs`, `--fs`, and `--ps`. Setting `--fs
 :` is the same as setting `--ifs : --ofs :`, but with fewer keystrokes.
 
+
+cat data/modsep.dkvp
+

+
+a:1;b:2;c:3
+a:4;b:5;c:6
+

+
 
 mlr --fs ';' --ps : cut -o -f c,a,b data/modsep.dkvp
 

@@ -79,7 +96,7 @@ c:3;a:1;b:2
 c:6;a:4;b:5
-## Multi-character separators +## Multi-character and regular-expression separators The separators default to single characters, but can be multiple characters if you like: @@ -91,16 +108,17 @@ c:=3;;;a:=1;;;b:=2 c:=6;;;a:=4;;;b:=5 -While the separators can be multiple characters, [regular -expressions](reference-main-regular-expressions.md) (which Miller supports in -many ways) are not (as of mid-2021) supported by Miller. So, in the above -example, you can say the field-separator is one semicolon, or three, but two or -four won't be recognized using `--ifs ';;;'`. +As of September 2021: -To fill this need, in the absence of full regular-expression support, Miller -has a `--repifs` option for input. This means, for example, using `--ifs -' ' --repifs` you can have the field separator be one _or more_ spaces. (Mixes -of spaces and tabs, however, won't be recognized as a separator.) +* `IFS` and `IPS` can be regular expressions. +* `IRS` must be a single character (nominally `\n`). +* `OFS`, `OPS`, and `ORS` can be multi-character. + +Since `IFS` and `IPS` can be regular expressions, if your data has field +separators which are one or more consecutive spaces, you can use `--ifs '( +)+'`. But that gets a little tedious, so Miller has the `--repifs` and +`--repips` flags you can use if you like. This wraps the `IFS` or `IPS`, say +`X`, as `(X)+`. The `--repifs` flag means that multiple successive occurrences of the field separator count as one. For example, in CSV data we often signify nulls by @@ -120,31 +138,19 @@ see by the dawn's early light what so -(TODO: FIXME) - 
 mlr --ifs ' ' --repifs --inidx --oxtab cat  data/extra-spaces.txt
 
 1 oh
-2 
-3 
-4 
-5 say
-6 
-7 
-8 can
-9 you
+2 say
+3 can
+4 you
 
 1 see
-2 
-3 
-4 by
-5 
-6 
-7 
-8 the
-9 dawn's
+2 by
+3 the
+4 dawn's
 
 1 early
 2 light
@@ -152,6 +158,51 @@ early light what so
 4 so
+## Aliases + +Many things we'd like to write as separators need to be escaped from the shell +-- e.g. `--ifs ';'` or `--ofs '|'`, and so on. You can use the following if you like: + +
+mlr help list-separator-aliases
+
+
+ascii_esc  = "\x1b"
+ascii_etx  = "\x04"
+ascii_fs   = "\x1c"
+ascii_gs   = "\x1d"
+ascii_null = "\x01"
+ascii_rs   = "\x1e"
+ascii_soh  = "\x02"
+ascii_stx  = "\x03"
+ascii_us   = "\x1f"
+asv_fs     = "\x1f"
+asv_rs     = "\x1e"
+colon      = ":"
+comma      = ","
+cr         = "\r"
+crcr       = "\r\r"
+crlf       = "\r\n"
+crlfcrlf   = "\r\n\r\n"
+equals     = "="
+lf         = "\n"
+lflf       = "\n\n"
+newline    = "\n"
+pipe       = "|"
+semicolon  = ";"
+slash      = "/"
+space      = " "
+spaces     = "( )+"
+tab        = "\t"
+tabs       = "(\t)+"
+usv_fs     = "\xe2\x90\x9f"
+usv_rs     = "\xe2\x90\x9e"
+whitespace = "([ \t])+"
+
+ +Note that `spaces`, `tabs`, and `whitespace` already are regexes so you +shouldn't use `--repifs` with them. + ## Command-line flags Given the above, we now have seen the following flags: @@ -162,15 +213,13 @@ Given the above, we now have seen the following flags: --ps --ips --ops -Also note that you can use names for certain characters: e.g. `--fs space` is -the same as `--fs ' '`. A full list is: `colon`, `comma`, `equals`, `newline`, -`pipe`, `semicolon`, `slash`, `space`, `tab`. +See also the [separator-flags section](reference-main-flag-list.md#separator-flags). ## DSL built-in variables Miller exposes for you read-only [built-in variables](reference-dsl-variables.md#built-in-variables) with names `IRS`, `ORS`, `IFS`, `OFS`, `IPS`, and `OPS`. Unlike in AWK, you can't set these in begin-blocks -- -their values indicate what you set at the command line -- so their use is limited. +their values indicate what you specified at the command line -- so their use is limited. 
 mlr --ifs , --ofs ';' --ips = --ops : --from data/a.dkvp put '$d = ">>>" . IFS . "|||" . OFS . "<<<"'
@@ -182,21 +231,22 @@ a:4;b:5;c:6;d:>>>,|||;<<<
 
 ## Which separators apply to which file formats
 
-TODO:
+Notes:
 
 * If CSV field separator is tab, we have TSV; see more examples (ASV, USV, etc.) at in the [CSV section](file-formats.md#csvtsvasvusvetc).
 * JSON: ignores all separator flags from the command line.
+* Headerless CSV overlaps quite a bit with NIDX format using comma for IFS. See also the page on [CSV with and without headers](csv-with-and-without-headers.md).
 
 |            | **RS**  | **FS**  | **PS**   |
 |------------|---------|---------|----------|
-| **CSV**    | Default `\n` *   | Default `,`    | None     |
-| **TSV**    | Default `\n` *  |  Default `\t`   | None     |
-| **JSON**   | N/A; records are between `{` and `}` | `,` but  not alterable    | `:` but not alterable |
-| **DKVP**   | Default `\n`    | Default `,`    | Default `=` |
-| **NIDX**   | Default `\n`    | Default space    | None     |
-| **XTAB**   | `\n\n` **    | `\n` *    | Space with repeats  |
-| **PPRINT** | Default `\n` *    | Space with repeats    | None     |
-| **Markdown** | `\n` * but not alterable    | One or more spaces then `|` then one or more spaces    | None     |
+| [**CSV and CSV-lite**](file-formats.md#csvtsvasvusvetc)    | Default `\n` *   | Default `,`    | None     |
+| [**TSV**](file-formats.md#csvtsvasvusvetc)    | Default `\n` *  |  Default `\t`   | None     |
+| [**JSON**](file-formats.md#json)   | N/A; records are between `{` and `}` | `,` but  not alterable    | `:` but not alterable |
+| [**DKVP**](file-formats.md#dkvp-key-value-pairs)   | Default `\n`    | Default `,`    | Default `=` |
+| [**NIDX**](file-formats.md#nidx-index-numbered-toolkit-style)   | Default `\n`    | Default space    | None     |
+| [**XTAB**](file-formats.md#xtab-vertical-tabular)   | `\n\n` **    | `\n` *    | Space with repeats  |
+| [**PPRINT**](file-formats.md#pprint-pretty-printed-tabular) | Default `\n` *    | Space with repeats    | None     |
+| [**Markdown**](file-formats.md#markdown-tabular) | `\n` * but not alterable    | One or more spaces then `|` then one or more spaces; not alterable | None     |
 
 \* or `\r\n` on Windows
 
diff --git a/docs6/src/reference-main-separators.md.in b/docs6/src/reference-main-separators.md.in
index e1e39a031..91cb6d398 100644
--- a/docs6/src/reference-main-separators.md.in
+++ b/docs6/src/reference-main-separators.md.in
@@ -30,8 +30,9 @@ part of the JSON specification.
 
 ## Input and output separators
 
-Miller lets you use the same separators for input and output, or, to change
-them between input and output, if you wish to transform your data in that way.
+Miller lets you use the same separators for input and output (e.g. CSV input,
+CSV output), or, to change them between input and output (e.g. CSV input, JSON
+output), if you wish to transform your data in that way.
 
 Miller uses the names `IRS` and `ORS` for the input and output record
 separators, `IFS` and `OFS` for the input and output field separators, and
@@ -39,6 +40,10 @@ separators, `IFS` and `OFS` for the input and output field separators, and
 
 For example:
 
+GENMD_RUN_COMMAND
+cat data/a.dkvp
+GENMD_EOF
+
 GENMD_RUN_COMMAND
 mlr --ifs , --ofs ';' --ips = --ops : cut -o -f c,a,b data/a.dkvp
 GENMD_EOF
@@ -47,11 +52,15 @@ If your data has non-default separators and you don't want to change those
 between input and output, you can use `--rs`, `--fs`, and `--ps`. Setting `--fs
 :` is the same as setting `--ifs : --ofs :`, but with fewer keystrokes.
 
+GENMD_RUN_COMMAND
+cat data/modsep.dkvp
+GENMD_EOF
+
 GENMD_RUN_COMMAND
 mlr --fs ';' --ps : cut -o -f c,a,b data/modsep.dkvp
 GENMD_EOF
 
-## Multi-character separators
+## Multi-character and regular-expression separators
 
 The separators default to single characters, but can be multiple characters if you like:
 
@@ -59,16 +68,17 @@ GENMD_RUN_COMMAND
 mlr --ifs ';' --ips : --ofs ';;;' --ops := cut -o -f c,a,b data/modsep.dkvp
 GENMD_EOF
 
-While the separators can be multiple characters, [regular
-expressions](reference-main-regular-expressions.md) (which Miller supports in
-many ways) are not (as of mid-2021) supported by Miller. So, in the above
-example, you can say the field-separator is one semicolon, or three, but two or
-four won't be recognized using `--ifs ';;;'`.
+As of September 2021:
 
-To fill this need, in the absence of full regular-expression support, Miller
-has a `--repifs` option for input. This means, for example, using `--ifs
-' ' --repifs` you can have the field separator be one _or more_ spaces. (Mixes
-of spaces and tabs, however, won't be recognized as a separator.)
+* `IFS` and `IPS` can be regular expressions.
+* `IRS` must be a single character (nominally `\n`).
+* `OFS`, `OPS`, and `ORS` can be multi-character.
+
+Since `IFS` and `IPS` can be regular expressions, if your data has field
+separators which are one or more consecutive spaces, you can use `--ifs '(
+)+'`. But that gets a little tedious, so Miller has the `--repifs` and
+`--repips` flags you can use if you like.  This wraps the `IFS` or `IPS`, say
+`X`, as `(X)+`.
 
 The `--repifs` flag means that multiple successive occurrences of the field
 separator count as one.  For example, in CSV data we often signify nulls by
@@ -83,12 +93,22 @@ GENMD_RUN_COMMAND
 cat data/extra-spaces.txt
 GENMD_EOF
 
-(TODO: FIXME)
-
 GENMD_RUN_COMMAND
 mlr --ifs ' ' --repifs --inidx --oxtab cat  data/extra-spaces.txt
 GENMD_EOF
 
+## Aliases
+
+Many things we'd like to write as separators need to be escaped from the shell
+-- e.g. `--ifs ';'` or `--ofs '|'`, and so on. You can use the following if you like:
+
+GENMD_RUN_COMMAND
+mlr help list-separator-aliases
+GENMD_EOF
+
+Note that `spaces`, `tabs`, and `whitespace` already are regexes so you
+shouldn't use `--repifs` with them.
+
 ## Command-line flags
 
 Given the above, we now have seen the following flags:
@@ -99,15 +119,13 @@ GENMD_CARDIFY
 --ps --ips --ops
 GENMD_EOF
 
-Also note that you can use names for certain characters: e.g. `--fs space` is
-the same as `--fs ' '`.  A full list is: `colon`, `comma`, `equals`, `newline`,
-`pipe`, `semicolon`, `slash`, `space`, `tab`.
+See also the [separator-flags section](reference-main-flag-list.md#separator-flags).
 
 ## DSL built-in variables
 
 Miller exposes for you read-only [built-in variables](reference-dsl-variables.md#built-in-variables) with
 names `IRS`, `ORS`, `IFS`, `OFS`, `IPS`, and `OPS`. Unlike in AWK, you can't set these in begin-blocks --
-their values indicate what you set at the command line -- so their use is limited.
+their values indicate what you specified at the command line -- so their use is limited.
 
 GENMD_RUN_COMMAND
 mlr --ifs , --ofs ';' --ips = --ops : --from data/a.dkvp put '$d = ">>>" . IFS . "|||" . OFS . "<<<"'
@@ -115,21 +133,22 @@ GENMD_EOF
 
 ## Which separators apply to which file formats
 
-TODO:
+Notes:
 
 * If CSV field separator is tab, we have TSV; see more examples (ASV, USV, etc.) at in the [CSV section](file-formats.md#csvtsvasvusvetc).
 * JSON: ignores all separator flags from the command line.
+* Headerless CSV overlaps quite a bit with NIDX format using comma for IFS. See also the page on [CSV with and without headers](csv-with-and-without-headers.md).
 
 |            | **RS**  | **FS**  | **PS**   |
 |------------|---------|---------|----------|
-| **CSV**    | Default `\n` *   | Default `,`    | None     |
-| **TSV**    | Default `\n` *  |  Default `\t`   | None     |
-| **JSON**   | N/A; records are between `{` and `}` | `,` but  not alterable    | `:` but not alterable |
-| **DKVP**   | Default `\n`    | Default `,`    | Default `=` |
-| **NIDX**   | Default `\n`    | Default space    | None     |
-| **XTAB**   | `\n\n` **    | `\n` *    | Space with repeats  |
-| **PPRINT** | Default `\n` *    | Space with repeats    | None     |
-| **Markdown** | `\n` * but not alterable    | One or more spaces then `|` then one or more spaces    | None     |
+| [**CSV and CSV-lite**](file-formats.md#csvtsvasvusvetc)    | Default `\n` *   | Default `,`    | None     |
+| [**TSV**](file-formats.md#csvtsvasvusvetc)    | Default `\n` *  |  Default `\t`   | None     |
+| [**JSON**](file-formats.md#json)   | N/A; records are between `{` and `}` | `,` but  not alterable    | `:` but not alterable |
+| [**DKVP**](file-formats.md#dkvp-key-value-pairs)   | Default `\n`    | Default `,`    | Default `=` |
+| [**NIDX**](file-formats.md#nidx-index-numbered-toolkit-style)   | Default `\n`    | Default space    | None     |
+| [**XTAB**](file-formats.md#xtab-vertical-tabular)   | `\n\n` **    | `\n` *    | Space with repeats  |
+| [**PPRINT**](file-formats.md#pprint-pretty-printed-tabular) | Default `\n` *    | Space with repeats    | None     |
+| [**Markdown**](file-formats.md#markdown-tabular) | `\n` * but not alterable    | One or more spaces then `|` then one or more spaces; not alterable | None     |
 
 \* or `\r\n` on Windows
 
diff --git a/go/regtest/cases-pending-go-port/io-rfc-csv/0017/cmd b/go/regtest/cases-pending-go-port/io-rfc-csv/0017/cmd
new file mode 100644
index 000000000..23b7e071d
--- /dev/null
+++ b/go/regtest/cases-pending-go-port/io-rfc-csv/0017/cmd
@@ -0,0 +1 @@
+mlr --iasv --oxtab cat regtest/input/example.asv
diff --git a/go/regtest/cases-pending-go-port/mix-null-field-input/0018/experr b/go/regtest/cases-pending-go-port/io-rfc-csv/0017/experr
similarity index 100%
rename from go/regtest/cases-pending-go-port/mix-null-field-input/0018/experr
rename to go/regtest/cases-pending-go-port/io-rfc-csv/0017/experr
diff --git a/go/regtest/cases-pending-go-port/io-rfc-csv/0017/expout b/go/regtest/cases-pending-go-port/io-rfc-csv/0017/expout
new file mode 100644
index 000000000..eab299c2e
--- /dev/null
+++ b/go/regtest/cases-pending-go-port/io-rfc-csv/0017/expout
@@ -0,0 +1,7 @@
+a d
+b e
+c f
+
+a g
+b h
+c i
diff --git a/go/regtest/cases-pending-go-port/mix-null-field-input/0018/expout b/go/regtest/cases-pending-go-port/mix-null-field-input/0018/expout
deleted file mode 100644
index 923fbfaf4..000000000
--- a/go/regtest/cases-pending-go-port/mix-null-field-input/0018/expout
+++ /dev/null
@@ -1,2 +0,0 @@
-a       b
-x_y_cov 2.000000
diff --git a/go/regtest/cases/io-separator-aliases/0001/cmd b/go/regtest/cases/io-separator-aliases/0001/cmd
new file mode 100644
index 000000000..155640c60
--- /dev/null
+++ b/go/regtest/cases/io-separator-aliases/0001/cmd
@@ -0,0 +1 @@
+mlr --from ${CASEDIR}/input --n2j cat
diff --git a/go/regtest/cases/io-separator-aliases/0001/experr b/go/regtest/cases/io-separator-aliases/0001/experr
new file mode 100644
index 000000000..e69de29bb
diff --git a/go/regtest/cases/io-separator-aliases/0001/expout b/go/regtest/cases/io-separator-aliases/0001/expout
new file mode 100644
index 000000000..1b55d791d
--- /dev/null
+++ b/go/regtest/cases/io-separator-aliases/0001/expout
@@ -0,0 +1,20 @@
+{
+  "1": "a",
+  "2": "b",
+  "3": "c"
+}
+{
+  "1": "a",
+  "2": "b",
+  "3": "c"
+}
+{
+  "1": "a",
+  "2": "b",
+  "3": "c"
+}
+{
+  "1": "a",
+  "2": "b",
+  "3": "c"
+}
diff --git a/go/regtest/cases/io-separator-aliases/0001/input b/go/regtest/cases/io-separator-aliases/0001/input
new file mode 100644
index 000000000..aa98b4674
--- /dev/null
+++ b/go/regtest/cases/io-separator-aliases/0001/input
@@ -0,0 +1,4 @@
+a	b c
+a b	c
+a			b    c
+a		 	b  	  c
diff --git a/go/regtest/cases/io-separator-aliases/0002/cmd b/go/regtest/cases/io-separator-aliases/0002/cmd
new file mode 100644
index 000000000..2cac50b1b
--- /dev/null
+++ b/go/regtest/cases/io-separator-aliases/0002/cmd
@@ -0,0 +1 @@
+mlr --from ${CASEDIR}/input --n2j --ifs space cat
diff --git a/go/regtest/cases/io-separator-aliases/0002/experr b/go/regtest/cases/io-separator-aliases/0002/experr
new file mode 100644
index 000000000..e69de29bb
diff --git a/go/regtest/cases/io-separator-aliases/0002/expout b/go/regtest/cases/io-separator-aliases/0002/expout
new file mode 100644
index 000000000..58c249a18
--- /dev/null
+++ b/go/regtest/cases/io-separator-aliases/0002/expout
@@ -0,0 +1,23 @@
+{
+  "1": "a\tb",
+  "2": "c"
+}
+{
+  "1": "a",
+  "2": "b\tc"
+}
+{
+  "1": "a\t\t\tb",
+  "2": "",
+  "3": "",
+  "4": "",
+  "5": "c"
+}
+{
+  "1": "a\t\t",
+  "2": "\tb",
+  "3": "",
+  "4": "\t",
+  "5": "",
+  "6": "c"
+}
diff --git a/go/regtest/cases/io-separator-aliases/0002/input b/go/regtest/cases/io-separator-aliases/0002/input
new file mode 100644
index 000000000..aa98b4674
--- /dev/null
+++ b/go/regtest/cases/io-separator-aliases/0002/input
@@ -0,0 +1,4 @@
+a	b c
+a b	c
+a			b    c
+a		 	b  	  c
diff --git a/go/regtest/cases/io-separator-aliases/0003/cmd b/go/regtest/cases/io-separator-aliases/0003/cmd
new file mode 100644
index 000000000..32f9f822e
--- /dev/null
+++ b/go/regtest/cases/io-separator-aliases/0003/cmd
@@ -0,0 +1 @@
+mlr --from ${CASEDIR}/input --n2j --ifs spaces cat
diff --git a/go/regtest/cases/io-separator-aliases/0003/experr b/go/regtest/cases/io-separator-aliases/0003/experr
new file mode 100644
index 000000000..e69de29bb
diff --git a/go/regtest/cases/io-separator-aliases/0003/expout b/go/regtest/cases/io-separator-aliases/0003/expout
new file mode 100644
index 000000000..f8b2c1be5
--- /dev/null
+++ b/go/regtest/cases/io-separator-aliases/0003/expout
@@ -0,0 +1,18 @@
+{
+  "1": "a\tb",
+  "2": "c"
+}
+{
+  "1": "a",
+  "2": "b\tc"
+}
+{
+  "1": "a\t\t\tb",
+  "2": "c"
+}
+{
+  "1": "a\t\t",
+  "2": "\tb",
+  "3": "\t",
+  "4": "c"
+}
diff --git a/go/regtest/cases/io-separator-aliases/0003/input b/go/regtest/cases/io-separator-aliases/0003/input
new file mode 100644
index 000000000..aa98b4674
--- /dev/null
+++ b/go/regtest/cases/io-separator-aliases/0003/input
@@ -0,0 +1,4 @@
+a	b c
+a b	c
+a			b    c
+a		 	b  	  c
diff --git a/go/regtest/cases/io-separator-aliases/0004/cmd b/go/regtest/cases/io-separator-aliases/0004/cmd
new file mode 100644
index 000000000..1181c5456
--- /dev/null
+++ b/go/regtest/cases/io-separator-aliases/0004/cmd
@@ -0,0 +1 @@
+mlr --from ${CASEDIR}/input --n2j --ifs tab cat
diff --git a/go/regtest/cases/io-separator-aliases/0004/experr b/go/regtest/cases/io-separator-aliases/0004/experr
new file mode 100644
index 000000000..e69de29bb
diff --git a/go/regtest/cases/io-separator-aliases/0004/expout b/go/regtest/cases/io-separator-aliases/0004/expout
new file mode 100644
index 000000000..25703f986
--- /dev/null
+++ b/go/regtest/cases/io-separator-aliases/0004/expout
@@ -0,0 +1,21 @@
+{
+  "1": "a",
+  "2": "b c"
+}
+{
+  "1": "a b",
+  "2": "c"
+}
+{
+  "1": "a",
+  "2": "",
+  "3": "",
+  "4": "b    c"
+}
+{
+  "1": "a",
+  "2": "",
+  "3": " ",
+  "4": "b  ",
+  "5": "  c"
+}
diff --git a/go/regtest/cases/io-separator-aliases/0004/input b/go/regtest/cases/io-separator-aliases/0004/input
new file mode 100644
index 000000000..aa98b4674
--- /dev/null
+++ b/go/regtest/cases/io-separator-aliases/0004/input
@@ -0,0 +1,4 @@
+a	b c
+a b	c
+a			b    c
+a		 	b  	  c
diff --git a/go/regtest/cases/io-separator-aliases/0005/cmd b/go/regtest/cases/io-separator-aliases/0005/cmd
new file mode 100644
index 000000000..e8a1ca17d
--- /dev/null
+++ b/go/regtest/cases/io-separator-aliases/0005/cmd
@@ -0,0 +1 @@
+mlr --from ${CASEDIR}/input --n2j --ifs tabs cat
diff --git a/go/regtest/cases/io-separator-aliases/0005/experr b/go/regtest/cases/io-separator-aliases/0005/experr
new file mode 100644
index 000000000..e69de29bb
diff --git a/go/regtest/cases/io-separator-aliases/0005/expout b/go/regtest/cases/io-separator-aliases/0005/expout
new file mode 100644
index 000000000..dca9b8a13
--- /dev/null
+++ b/go/regtest/cases/io-separator-aliases/0005/expout
@@ -0,0 +1,18 @@
+{
+  "1": "a",
+  "2": "b c"
+}
+{
+  "1": "a b",
+  "2": "c"
+}
+{
+  "1": "a",
+  "2": "b    c"
+}
+{
+  "1": "a",
+  "2": " ",
+  "3": "b  ",
+  "4": "  c"
+}
diff --git a/go/regtest/cases/io-separator-aliases/0005/input b/go/regtest/cases/io-separator-aliases/0005/input
new file mode 100644
index 000000000..aa98b4674
--- /dev/null
+++ b/go/regtest/cases/io-separator-aliases/0005/input
@@ -0,0 +1,4 @@
+a	b c
+a b	c
+a			b    c
+a		 	b  	  c
diff --git a/go/regtest/cases/io-separator-aliases/0006/cmd b/go/regtest/cases/io-separator-aliases/0006/cmd
new file mode 100644
index 000000000..74823216a
--- /dev/null
+++ b/go/regtest/cases/io-separator-aliases/0006/cmd
@@ -0,0 +1 @@
+mlr --from ${CASEDIR}/input --n2j --ifs whitespace cat
diff --git a/go/regtest/cases/io-separator-aliases/0006/experr b/go/regtest/cases/io-separator-aliases/0006/experr
new file mode 100644
index 000000000..e69de29bb
diff --git a/go/regtest/cases/io-separator-aliases/0006/expout b/go/regtest/cases/io-separator-aliases/0006/expout
new file mode 100644
index 000000000..1b55d791d
--- /dev/null
+++ b/go/regtest/cases/io-separator-aliases/0006/expout
@@ -0,0 +1,20 @@
+{
+  "1": "a",
+  "2": "b",
+  "3": "c"
+}
+{
+  "1": "a",
+  "2": "b",
+  "3": "c"
+}
+{
+  "1": "a",
+  "2": "b",
+  "3": "c"
+}
+{
+  "1": "a",
+  "2": "b",
+  "3": "c"
+}
diff --git a/go/regtest/cases/io-separator-aliases/0006/input b/go/regtest/cases/io-separator-aliases/0006/input
new file mode 100644
index 000000000..aa98b4674
--- /dev/null
+++ b/go/regtest/cases/io-separator-aliases/0006/input
@@ -0,0 +1,4 @@
+a	b c
+a b	c
+a			b    c
+a		 	b  	  c
diff --git a/go/regtest/cases-pending-go-port/mix-null-field-input/0018/cmd b/go/regtest/cases/mix-null-field-input/0018/cmd
similarity index 100%
rename from go/regtest/cases-pending-go-port/mix-null-field-input/0018/cmd
rename to go/regtest/cases/mix-null-field-input/0018/cmd
diff --git a/go/regtest/cases/mix-null-field-input/0018/experr b/go/regtest/cases/mix-null-field-input/0018/experr
new file mode 100644
index 000000000..e69de29bb
diff --git a/go/regtest/cases/mix-null-field-input/0018/expout b/go/regtest/cases/mix-null-field-input/0018/expout
new file mode 100644
index 000000000..1b392ed31
--- /dev/null
+++ b/go/regtest/cases/mix-null-field-input/0018/expout
@@ -0,0 +1,2 @@
+a       b
+x_y_cov 2
diff --git a/go/regtest/input/example.asv b/go/regtest/input/example.asv
new file mode 100644
index 000000000..c0cc707fd
--- /dev/null
+++ b/go/regtest/input/example.asv
@@ -0,0 +1 @@
+abcdefghi
\ No newline at end of file
diff --git a/go/src/auxents/help/entry.go b/go/src/auxents/help/entry.go
index 19ac4ef30..300ee7add 100644
--- a/go/src/auxents/help/entry.go
+++ b/go/src/auxents/help/entry.go
@@ -71,6 +71,7 @@ func init() {
 				name: "Flags",
 				handlerInfos: []tHandlerInfo{
 					{name: "flags", zaryHandlerFunc: showFlagHelp},
+					{name: "list-separator-aliases", zaryHandlerFunc: listSeparatorAliases},
 					// Per-section entries will be computed and installed below
 				},
 			},
@@ -292,6 +293,10 @@ func showFlagHelp() {
 	cli.FLAG_TABLE.ShowHelp()
 }
 
+func listSeparatorAliases() {
+	cli.ListSeparatorAliasesForOnlineHelp()
+}
+
 // ----------------------------------------------------------------
 func helpAuxents() {
 	fmt.Print(`Miller has a few otherwise-standalone executables packaged within it.
diff --git a/go/src/auxents/repl/entry.go b/go/src/auxents/repl/entry.go
index 50d9a6e43..6ab0ad29c 100644
--- a/go/src/auxents/repl/entry.go
+++ b/go/src/auxents/repl/entry.go
@@ -144,8 +144,8 @@ func ReplMain(args []string) int {
 		}
 	}
 
-	cli.ApplyReaderOptionDefaults(&options.ReaderOptions)
-	cli.ApplyWriterOptionDefaults(&options.WriterOptions)
+	cli.FinalizeReaderOptions(&options.ReaderOptions)
+	cli.FinalizeWriterOptions(&options.WriterOptions)
 
 	// --auto-flatten is on by default. But if input and output formats are both JSON,
 	// then we don't need to actually do anything. See also mlrcli_parse.go.
diff --git a/go/src/cli/flag_types.go b/go/src/cli/flag_types.go
index d02a7b025..a4a9cdba2 100644
--- a/go/src/cli/flag_types.go
+++ b/go/src/cli/flag_types.go
@@ -50,14 +50,11 @@ import (
 // Data types used within the flags table.
 
 // FlagParser is a function which takes a flag such as `--foo`.
-//
 // * It should assume that a flag.Owns method has already been invoked to be
 //   sure that this function is indeed the right one to call for `--foo`.
-//
 // * The FlagParser function is responsible for advancing *pargi by 1 (if
 //   `--foo`) or 2 (if `--foo bar`), checking to see if argc is long enough in
 //   the latter case, and mutating the options struct.
-//
 // * Successful handling of the flag is indicated by this function making a
 //   non-zero increment of *pargi.
 type FlagParser func(
@@ -68,6 +65,7 @@ type FlagParser func(
 )
 
 // ----------------------------------------------------------------
+
 // FlagTable holds all the flags for Miller, organized into sections.
 type FlagTable struct {
 	sections []*FlagSection
diff --git a/go/src/cli/mlrcli_util.go b/go/src/cli/mlrcli_util.go
index 7c38e796c..f0bc1063f 100644
--- a/go/src/cli/mlrcli_util.go
+++ b/go/src/cli/mlrcli_util.go
@@ -3,12 +3,10 @@ package cli
 import (
 	"fmt"
 	"os"
-
-	"mlr/src/lib"
 )
 
-// For flags with values, e.g. ["-n" "10"], while we're looking at the "-n"
-// this let us see if the "10" slot exists.
+// CheckArgCount is for flags with values, e.g. ["-n" "10"], while we're
+// looking at the "-n": this let us see if the "10" slot exists.
 func CheckArgCount(args []string, argi int, argc int, n int) {
 	if (argc - argi) < n {
 		fmt.Fprintf(os.Stderr, "%s: option \"%s\" missing argument(s).\n", "mlr", args[argi])
@@ -17,43 +15,13 @@ func CheckArgCount(args []string, argi int, argc int, n int) {
 	}
 }
 
-// ----------------------------------------------------------------
-// TODO: give symbolic name to all the RHSes
-
-var SEPARATOR_NAMES_TO_VALUES = map[string]string{
-	"colon":     ":",
-	"comma":     ",",
-	"cr":        "\\r",
-	"crcr":      "\\r\\r",
-	"crlf":      "\\r\\n",
-	"crlfcrlf":  "\\r\\n\\r\\n",
-	"equals":    "=",
-	"lf":        "\\n",
-	"lflf":      "\\n\\n",
-	"newline":   "\\n",
-	"pipe":      "|",
-	"semicolon": ";",
-	"slash":     "/",
-	"space":     " ",
-	"tab":       "\\t",
-
-	"ascii_null": "\\x01",
-	"ascii_soh":  "\\x02",
-	"ascii_stx":  "\\x03",
-	"ascii_etx":  "\\x04",
-
-	"ascii_esc":  "\\x1b",
-	"ascii_fs":   "\\x1c",
-	"ascii_gs":   "\\x1d",
-	"ascii_rs":   "\\x1e",
-	"ascii_us":   "\\x1f",
-}
-
+// SeparatorFromArg is for letting people do things like `--ifs pipe`
+// rather than `--ifs '|'`.
 func SeparatorFromArg(name string) string {
 	sep, ok := SEPARATOR_NAMES_TO_VALUES[name]
-	if !ok {
-		// "\001" -> control-A, etc.
-		return lib.UnbackslashStringLiteral(name)
+	if ok {
+		return sep
+	} else {
+		return name
 	}
-	return sep
 }
diff --git a/go/src/cli/option_parse.go b/go/src/cli/option_parse.go
index 71ede3aa1..f206d3251 100644
--- a/go/src/cli/option_parse.go
+++ b/go/src/cli/option_parse.go
@@ -15,79 +15,13 @@ import (
 	"mlr/src/lib"
 )
 
-const ASV_FS = "\x1f"
-const ASV_RS = "\x1e"
-const USV_FS = "\xe2\x90\x9f"
-const USV_RS = "\xe2\x90\x9e"
-
-const ASV_FS_FOR_HELP = "\\x1f"
-const ASV_RS_FOR_HELP = "\\x1e"
-const USV_FS_FOR_HELP = "U+241F (UTF-8 \\xe2\\x90\\x9f)"
-const USV_RS_FOR_HELP = "U+241E (UTF-8 \\xe2\\x90\\x9e)"
-const DEFAULT_JSON_FLATTEN_SEPARATOR = "."
-
-// ----------------------------------------------------------------
-// TODO: move these to their own file
-
-// E.g. if IFS isn't specified, it's space for NIDX and comma for DKVP, etc.
-
-var defaultFSes = map[string]string{
-	// "gen" : // TODO
-	"csv":      ",",
-	"csvlite":  ",",
-	"dkvp":     ",",
-	"json":     "N/A", // not honored; not parameterizable in JSON format
-	"nidx":     " ",
-	"markdown": " ",
-	"pprint":   " ",
-	"xtab":     "\n", // todo: windows-dependent ...
-}
-
-var defaultPSes = map[string]string{
-	"csv":      "N/A",
-	"csvlite":  "N/A",
-	"dkvp":     "=",
-	"json":     "N/A", // not honored; not parameterizable in JSON format
-	"markdown": "N/A",
-	"nidx":     "N/A",
-	"pprint":   "N/A",
-	"xtab":     " ", // todo: windows-dependent ...
-}
-
-var defaultRSes = map[string]string{
-	"csv":      "\n",
-	"csvlite":  "\n",
-	"dkvp":     "\n",
-	"json":     "N/A", // not honored; not parameterizable in JSON format
-	"markdown": "\n",
-	"nidx":     "\n",
-	"pprint":   "\n",
-	"xtab":     "\n\n", // todo: maybe jettison the idea of this being alterable
-}
-
-var defaultAllowRepeatIFSes = map[string]bool{
-	"csv":      false,
-	"csvlite":  false,
-	"dkvp":     false,
-	"json":     false,
-	"markdown": false,
-	"nidx":     false,
-	"pprint":   true,
-	"xtab":     false,
-}
-
-var defaultAllowRepeatIPSes = map[string]bool{
-	"csv":      false,
-	"csvlite":  false,
-	"dkvp":     false,
-	"json":     false,
-	"markdown": false,
-	"nidx":     false,
-	"pprint":   false,
-	"xtab":     true,
-}
-
-func ApplyReaderOptionDefaults(readerOptions *TReaderOptions) {
+// FinalizeReaderOptions does a few things. One is if a file format was
+// specified but one or more separators were not, a defaut specific to that
+// file format is applied. The second is computing regexes for IPS and IFS, and
+// unbackslashing IRS.  This is because the '\n' at the command line which is
+// Go "\\n" (a backslash and an n) needs to become the single newline
+// character, and likewise for "\t", etc.
+func FinalizeReaderOptions(readerOptions *TReaderOptions) {
 	if !readerOptions.IFSWasSpecified {
 		readerOptions.IFS = defaultFSes[readerOptions.InputFileFormat]
 	}
@@ -98,14 +32,37 @@ func ApplyReaderOptionDefaults(readerOptions *TReaderOptions) {
 		readerOptions.IRS = defaultRSes[readerOptions.InputFileFormat]
 	}
 	if !readerOptions.AllowRepeatIFSWasSpecified {
-		readerOptions.AllowRepeatIFS = defaultAllowRepeatIFSes[readerOptions.InputFileFormat]
+		// Special case for Miller 6 upgrade -- now that we have regexing for mixes of tabs
+		// and spaces, that should now be the default for NIDX. But *only* for NIDX format,
+		// and if IFS wasn't specified.
+		if readerOptions.InputFileFormat == "nidx" && !readerOptions.IFSWasSpecified {
+			readerOptions.IFS = WHITESPACE
+		} else {
+			readerOptions.AllowRepeatIFS = defaultAllowRepeatIFSes[readerOptions.InputFileFormat]
+		}
 	}
 	if !readerOptions.AllowRepeatIPSWasSpecified {
 		readerOptions.AllowRepeatIPS = defaultAllowRepeatIPSes[readerOptions.InputFileFormat]
 	}
+
+	if readerOptions.AllowRepeatIFS {
+		readerOptions.IFSRegex = lib.CompileMillerRegexOrDie("(" + readerOptions.IFS + ")+")
+	} else {
+		readerOptions.IFSRegex = lib.CompileMillerRegexOrDie(readerOptions.IFS)
+	}
+	if readerOptions.AllowRepeatIPS {
+		readerOptions.IPSRegex = lib.CompileMillerRegexOrDie("(" + readerOptions.IPS + ")+")
+	} else {
+		readerOptions.IPSRegex = lib.CompileMillerRegexOrDie(readerOptions.IPS)
+	}
+
+	readerOptions.IRS = lib.UnbackslashStringLiteral(readerOptions.IRS)
 }
 
-func ApplyWriterOptionDefaults(writerOptions *TWriterOptions) {
+// FinalizeWriterOptions unbackslashes OPS, OFS, and ORS.  This is because
+// because the '\n' at the command line which is Go "\\n" (a backslash and an
+// n) needs to become the single newline character., and likewise for "\t", etc.
+func FinalizeWriterOptions(writerOptions *TWriterOptions) {
 	if !writerOptions.OFSWasSpecified {
 		writerOptions.OFS = defaultFSes[writerOptions.OutputFileFormat]
 	}
@@ -115,6 +72,10 @@ func ApplyWriterOptionDefaults(writerOptions *TWriterOptions) {
 	if !writerOptions.ORSWasSpecified {
 		writerOptions.ORS = defaultRSes[writerOptions.OutputFileFormat]
 	}
+
+	writerOptions.OFS = lib.UnbackslashStringLiteral(writerOptions.OFS)
+	writerOptions.OPS = lib.UnbackslashStringLiteral(writerOptions.OPS)
+	writerOptions.ORS = lib.UnbackslashStringLiteral(writerOptions.ORS)
 }
 
 // ================================================================
@@ -211,11 +172,11 @@ Notes about all other separators:
 	fmt.Println()
 
 	// Go doesn't preserve insertion order in its arrays so here we are inlining a sort.
-	aliases := lib.GetArrayKeysSorted(SEPARATOR_NAMES_TO_VALUES_FOR_ONLINE_HELP)
+	aliases := lib.GetArrayKeysSorted(SEPARATOR_NAMES_TO_VALUES)
 	for _, alias := range aliases {
 		// Really absurd level of indent needed to get fixed-with font in mkdocs here,
 		// I don't know why. Usually it only takes 4, not 10.
-		fmt.Printf("          %-10s = \"%s\"\n", alias, SEPARATOR_NAMES_TO_VALUES_FOR_ONLINE_HELP[alias])
+		fmt.Printf("          %-10s = \"%s\"\n", alias, SEPARATOR_NAMES_TO_VALUES[alias])
 	}
 	fmt.Println()
 
@@ -243,6 +204,16 @@ Notes about all other separators:
 	}
 }
 
+func ListSeparatorAliasesForOnlineHelp() {
+	// Go doesn't preserve insertion order in its arrays so here we are inlining a sort.
+	aliases := lib.GetArrayKeysSorted(SEPARATOR_NAMES_TO_VALUES)
+	for _, alias := range aliases {
+		// Really absurd level of indent needed to get fixed-with font in mkdocs here,
+		// I don't know why. Usually it only takes 4, not 10.
+		fmt.Printf("%-10s = \"%s\"\n", alias, SEPARATOR_NAMES_TO_VALUES[alias])
+	}
+}
+
 func init() { SeparatorFlagSection.Sort() }
 
 var SeparatorFlagSection = FlagSection{
diff --git a/go/src/cli/option_types.go b/go/src/cli/option_types.go
index ab39e19d9..5611c882e 100644
--- a/go/src/cli/option_types.go
+++ b/go/src/cli/option_types.go
@@ -7,6 +7,8 @@
 package cli
 
 import (
+	"regexp"
+
 	"mlr/src/lib"
 )
 
@@ -36,6 +38,8 @@ type TReaderOptions struct {
 	IRS             string
 	AllowRepeatIFS  bool
 	AllowRepeatIPS  bool
+	IFSRegex        *regexp.Regexp
+	IPSRegex        *regexp.Regexp
 
 	// If unspecified on the command line, these take input-format-dependent
 	// defaults.  E.g. default FS is comma for DKVP but space for NIDX;
diff --git a/go/src/cli/separators.go b/go/src/cli/separators.go
new file mode 100644
index 000000000..3d01eb218
--- /dev/null
+++ b/go/src/cli/separators.go
@@ -0,0 +1,134 @@
+package cli
+
+const COLON = ":"
+const COMMA = ","
+const CR = "\\r"
+const CRCR = "\\r\\r"
+const CRLF = "\\r\\n"
+const CRLFCRLF = "\\r\\n\\r\\n"
+const EQUALS = "="
+const LF = "\\n"
+const LFLF = "\\n\\n"
+const NEWLINE = "\\n"
+const PIPE = "|"
+const SEMICOLON = ";"
+const SLASH = "/"
+const SPACE = " "
+const SPACES = "( )+"
+const TAB = "\\t"
+const TABS = "(\\t)+"
+const WHITESPACE = "([ \\t])+"
+
+const ASCII_ESC = "\\x1b"
+const ASCII_ETX = "\\x04"
+const ASCII_FS = "\\x1c"
+const ASCII_GS = "\\x1d"
+const ASCII_NULL = "\\x01"
+const ASCII_RS = "\\x1e"
+const ASCII_SOH = "\\x02"
+const ASCII_STX = "\\x03"
+const ASCII_US = "\\x1f"
+
+const ASV_FS = "\\x1f"
+const ASV_RS = "\\x1e"
+const USV_FS = "\\xe2\\x90\\x9f"
+const USV_RS = "\\xe2\\x90\\x9e"
+
+const ASV_FS_FOR_HELP = "\\x1f"
+const ASV_RS_FOR_HELP = "\\x1e"
+const USV_FS_FOR_HELP = "U+241F (UTF-8 \\xe2\\x90\\x9f)"
+const USV_RS_FOR_HELP = "U+241E (UTF-8 \\xe2\\x90\\x9e)"
+
+const DEFAULT_JSON_FLATTEN_SEPARATOR = "."
+
+var SEPARATOR_NAMES_TO_VALUES = map[string]string{
+	"ascii_esc":  ASCII_ESC,
+	"ascii_etx":  ASCII_ETX,
+	"ascii_fs":   ASCII_FS,
+	"ascii_gs":   ASCII_GS,
+	"ascii_null": ASCII_NULL,
+	"ascii_rs":   ASCII_RS,
+	"ascii_soh":  ASCII_SOH,
+	"ascii_stx":  ASCII_STX,
+	"ascii_us":   ASCII_US,
+	"asv_fs":     ASV_FS,
+	"asv_rs":     ASV_RS,
+	"colon":      COLON,
+	"comma":      COMMA,
+	"cr":         CR,
+	"crcr":       CRCR,
+	"crlf":       CRLF,
+	"crlfcrlf":   CRLFCRLF,
+	"equals":     EQUALS,
+	"lf":         LF,
+	"lflf":       LFLF,
+	"newline":    NEWLINE,
+	"pipe":       PIPE,
+	"semicolon":  SEMICOLON,
+	"slash":      SLASH,
+	"space":      SPACE,
+	"spaces":     SPACES,
+	"tab":        TAB,
+	"tabs":       TABS,
+	"usv_fs":     USV_FS,
+	"usv_rs":     USV_RS,
+	"whitespace": WHITESPACE,
+}
+
+// E.g. if IFS isn't specified, it's space for NIDX and comma for DKVP, etc.
+
+var defaultFSes = map[string]string{
+	// "gen" : // TODO
+	"csv":      ",",
+	"csvlite":  ",",
+	"dkvp":     ",",
+	"json":     "N/A", // not alterable; not parameterizable in JSON format
+	"nidx":     " ",
+	"markdown": " ",
+	"pprint":   " ",
+	"xtab":     "\n", // todo: windows-dependent ...
+}
+
+var defaultPSes = map[string]string{
+	"csv":      "N/A",
+	"csvlite":  "N/A",
+	"dkvp":     "=",
+	"json":     "N/A", // not alterable; not parameterizable in JSON format
+	"markdown": "N/A",
+	"nidx":     "N/A",
+	"pprint":   "N/A",
+	"xtab":     " ", // todo: windows-dependent ...
+}
+
+var defaultRSes = map[string]string{
+	"csv":      "\n",
+	"csvlite":  "\n",
+	"dkvp":     "\n",
+	"json":     "N/A", // not alterable; not parameterizable in JSON format
+	"markdown": "\n",
+	"nidx":     "\n",
+	"pprint":   "\n",
+	"xtab":     "\n\n", // todo: maybe jettison the idea of this being alterable
+}
+
+var defaultAllowRepeatIFSes = map[string]bool{
+	"csv":      false,
+	"csvlite":  false,
+	"dkvp":     false,
+	"json":     false,
+	"markdown": false,
+	"nidx":     false,
+	"pprint":   true,
+	"xtab":     false,
+}
+
+var defaultAllowRepeatIPSes = map[string]bool{
+	"csv":      false,
+	"csvlite":  false,
+	"dkvp":     false,
+	"json":     false,
+	"markdown": false,
+	"nidx":     false,
+	"pprint":   false,
+	"xtab":     true,
+}
diff --git a/go/src/climain/mlrcli_mlrrc.go b/go/src/climain/mlrcli_mlrrc.go
index bb1be4ea6..01624e416 100644
--- a/go/src/climain/mlrcli_mlrrc.go
+++ b/go/src/climain/mlrcli_mlrrc.go
@@ -11,13 +11,10 @@ import (
 	"mlr/src/cli"
 )
 
-// ----------------------------------------------------------------
-// * If $MLRRC is set, use it and only it.
-// * Otherwise try first $HOME/.mlrrc and then ./.mlrrc but let them
-//   stack: e.g. $HOME/.mlrrc is lots of settings and maybe in one
-//   subdir you want to override just a setting or two.
-
-// TODO: move to separate file?
+// loadMlrrcOrDie rule: If $MLRRC is set, use it and only it.  Otherwise try
+// first $HOME/.mlrrc and then ./.mlrrc but let them stack: e.g. $HOME/.mlrrc
+// is lots of settings and maybe in one subdir you want to override just a
+// setting or two.
 func loadMlrrcOrDie(
 	options *cli.TOptions,
 ) {
@@ -41,6 +38,7 @@ func loadMlrrcOrDie(
 	tryLoadMlrrc(options, "./.mlrrc")
 }
 
+// tryLoadMlrrc is a helper function for loadMlrrcOrDie.
 func tryLoadMlrrc(
 	options *cli.TOptions,
 	path string,
@@ -85,6 +83,7 @@ func tryLoadMlrrc(
 	return true
 }
 
+// handleMlrrcLine is a helper function for loadMlrrcOrDie.
 func handleMlrrcLine(
 	options *cli.TOptions,
 	line string,
diff --git a/go/src/climain/mlrcli_parse.go b/go/src/climain/mlrcli_parse.go
index 621224d98..6e08c57a7 100644
--- a/go/src/climain/mlrcli_parse.go
+++ b/go/src/climain/mlrcli_parse.go
@@ -12,7 +12,8 @@ import (
 	"mlr/src/version"
 )
 
-// ----------------------------------------------------------------
+// ParseCommandLine is the entrypoint for handling the Miller command line:
+// flags, verbs and their flags, and input file name(s).
 func ParseCommandLine(args []string) (
 	options cli.TOptions,
 	recordTransformers []transformers.IRecordTransformer,
@@ -60,8 +61,8 @@ func ParseCommandLine(args []string) (
 		}
 	}
 
-	cli.ApplyReaderOptionDefaults(&options.ReaderOptions)
-	cli.ApplyWriterOptionDefaults(&options.WriterOptions)
+	cli.FinalizeReaderOptions(&options.ReaderOptions)
+	cli.FinalizeWriterOptions(&options.WriterOptions)
 
 	// Set an optional global formatter for floating-point values
 	if options.WriterOptions.FPOFMT != "" {
@@ -120,10 +121,9 @@ func ParseCommandLine(args []string) (
 	return options, recordTransformers, nil
 }
 
-// ----------------------------------------------------------------
-// Returns a list of transformers, from the starting point in args given by *pargi.
-// Bumps *pargi to point to remaining post-transformer-setup args, i.e. filenames.
-
+// parseTransformers returns a list of transformers, from the starting point in
+// args given by *pargi.  Bumps *pargi to point to remaining
+// post-transformer-setup args, i.e. filenames.
 func parseTransformers(
 	args []string,
 	pargi *int,
diff --git a/go/src/input/record_reader_csvlite.go b/go/src/input/record_reader_csvlite.go
index 9590d7674..c1a0d3096 100644
--- a/go/src/input/record_reader_csvlite.go
+++ b/go/src/input/record_reader_csvlite.go
@@ -33,23 +33,20 @@ import (
 
 // ----------------------------------------------------------------
 type RecordReaderCSVLite struct {
-	readerOptions     *cli.TReaderOptions
-	emptyStringMlrval types.Mlrval
+	readerOptions *cli.TReaderOptions
 }
 
 // ----------------------------------------------------------------
 func NewRecordReaderCSVLite(readerOptions *cli.TReaderOptions) *RecordReaderCSVLite {
 	return &RecordReaderCSVLite{
-		readerOptions:     readerOptions,
-		emptyStringMlrval: types.MlrvalFromString(""),
+		readerOptions: readerOptions,
 	}
 }
 
 // ----------------------------------------------------------------
 func NewRecordReaderPPRINT(readerOptions *cli.TReaderOptions) *RecordReaderCSVLite {
 	return &RecordReaderCSVLite{
-		readerOptions:     readerOptions,
-		emptyStringMlrval: types.MlrvalFromString(""),
+		readerOptions: readerOptions,
 	}
 }
 
@@ -170,7 +167,7 @@ func (reader *RecordReaderCSVLite) processHandleExplicitCSVHeader(
 				continue
 			}
 
-			fields := lib.SplitString(line, reader.readerOptions.IFS)
+			fields := lib.RegexSplitString(reader.readerOptions.IFSRegex, line, -1)
 			if reader.readerOptions.AllowRepeatIFS {
 				fields = reader.stripEmpties(fields)
 			}
@@ -216,7 +213,7 @@ func (reader *RecordReaderCSVLite) processHandleExplicitCSVHeader(
 					if nh > nd {
 						// if header longer than data: use "" values
 						for i = nd; i < nh; i++ {
-							record.PutCopy(headerStrings[i], &reader.emptyStringMlrval)
+							record.PutCopy(headerStrings[i], types.MLRVAL_VOID)
 						}
 					}
 				}
@@ -279,7 +276,7 @@ func (reader *RecordReaderCSVLite) processHandleImplicitCSVHeader(
 				continue
 			}
 
-			fields := lib.SplitString(line, reader.readerOptions.IFS)
+			fields := lib.RegexSplitString(reader.readerOptions.IFSRegex, line, -1)
 			if reader.readerOptions.AllowRepeatIFS {
 				fields = reader.stripEmpties(fields)
 			}
@@ -327,7 +324,7 @@ func (reader *RecordReaderCSVLite) processHandleImplicitCSVHeader(
 				if nh > nd {
 					// if header longer than data: use "" values
 					for i = nd; i < nh; i++ {
-						record.PutCopy(headerStrings[i], &reader.emptyStringMlrval)
+						record.PutCopy(headerStrings[i], types.MLRVAL_VOID)
 					}
 				}
 			}
diff --git a/go/src/input/record_reader_dkvp.go b/go/src/input/record_reader_dkvp.go
index 4404d561d..74ee4d8c5 100644
--- a/go/src/input/record_reader_dkvp.go
+++ b/go/src/input/record_reader_dkvp.go
@@ -13,7 +13,6 @@ import (
 
 type RecordReaderDKVP struct {
 	readerOptions *cli.TReaderOptions
-	// TODO: parameterize IRS
 }
 
 func NewRecordReaderDKVP(readerOptions *cli.TReaderOptions) *RecordReaderDKVP {
@@ -99,7 +98,7 @@ func (reader *RecordReaderDKVP) processHandle(
 		// xxx temp pending autodetect, and pending more windows-port work
 		line = strings.TrimRight(line, "\r")
 
-		record := reader.recordFromDKVPLine(&line)
+		record := reader.recordFromDKVPLine(line)
 		context.UpdateForInputRecord()
 		inputChannel <- types.NewRecordAndContext(
 			record,
@@ -110,12 +109,13 @@ func (reader *RecordReaderDKVP) processHandle(
 
 // ----------------------------------------------------------------
 func (reader *RecordReaderDKVP) recordFromDKVPLine(
-	line *string,
+	line string,
 ) *types.Mlrmap {
 	record := types.NewMlrmap()
-	pairs := lib.SplitString(*line, reader.readerOptions.IFS)
+	pairs := lib.RegexSplitString(reader.readerOptions.IFSRegex, line, -1)
+
 	for i, pair := range pairs {
-		kv := strings.SplitN(pair, reader.readerOptions.IPS, 2)
+		kv := lib.RegexSplitString(reader.readerOptions.IPSRegex, pair, 2)
 		// TODO check length 0. also, check input is empty since "".split() -> [""] not []
 		if len(kv) == 1 {
 			// E.g the pair has no equals sign: "a" rather than "a=1" or
diff --git a/go/src/input/record_reader_nidx.go b/go/src/input/record_reader_nidx.go
index 6f09018d2..f4a201764 100644
--- a/go/src/input/record_reader_nidx.go
+++ b/go/src/input/record_reader_nidx.go
@@ -12,7 +12,6 @@ import (
 )
 
 type RecordReaderNIDX struct {
-	// TODO: use the parameterization for readerOptions.IFS/readerOptions.IPS
 	readerOptions *cli.TReaderOptions
 }
 
@@ -100,7 +99,7 @@ func (reader *RecordReaderNIDX) processHandle(
 		line = strings.TrimRight(line, "\n")
 		line = strings.TrimRight(line, "\r")
 
-		record := recordFromNIDXLine(line, reader.readerOptions.IFS)
+		record := reader.recordFromNIDXLine(line)
 
 		context.UpdateForInputRecord()
 		inputChannel <- types.NewRecordAndContext(
@@ -111,12 +110,11 @@ func (reader *RecordReaderNIDX) processHandle(
 }
 
 // ----------------------------------------------------------------
-func recordFromNIDXLine(
+func (reader *RecordReaderNIDX) recordFromNIDXLine(
 	line string,
-	ifs string,
 ) *types.Mlrmap {
 	record := types.NewMlrmap()
-	values := lib.SplitString(line, ifs) // TODO: repifs ...
+	values := lib.RegexSplitString(reader.readerOptions.IFSRegex, line, -1)
 	var i int = 0
 	for _, value := range values {
 		i++
diff --git a/go/src/input/record_reader_xtab.go b/go/src/input/record_reader_xtab.go
index b8268893d..10b4c0834 100644
--- a/go/src/input/record_reader_xtab.go
+++ b/go/src/input/record_reader_xtab.go
@@ -5,7 +5,6 @@ import (
 	"container/list"
 	"errors"
 	"io"
-	"regexp"
 	"strings"
 
 	"mlr/src/cli"
@@ -15,21 +14,13 @@ import (
 
 type RecordReaderXTAB struct {
 	readerOptions *cli.TReaderOptions
-	ifsRegex      *regexp.Regexp
 	// TODO: parameterize IRS
-
-	// TODO: port from C
-	// 	int    allow_repeat_ips;
-	// 	int    do_auto_line_term;
-	// 	int    at_eof;
 }
 
 // ----------------------------------------------------------------
 func NewRecordReaderXTAB(readerOptions *cli.TReaderOptions) *RecordReaderXTAB {
 	return &RecordReaderXTAB{
 		readerOptions: readerOptions,
-		// TODO: incorporate IFS
-		ifsRegex: regexp.MustCompile("\\s+"),
 	}
 }
 
@@ -154,8 +145,7 @@ func (reader *RecordReaderXTAB) recordFromXTABLines(
 	for entry := lines.Front(); entry != nil; entry = entry.Next() {
 		line := entry.Value.(string)
 
-		// TODO -- incorporate IFS
-		kv := reader.ifsRegex.Split(line, 2)
+		kv := lib.RegexSplitString(reader.readerOptions.IPSRegex, line, 2)
 		if len(kv) < 1 {
 			return nil, errors.New("mlr: internal coding error in XTAB reader")
 		}
diff --git a/go/src/lib/regex.go b/go/src/lib/regex.go
index acf1c3076..916213df8 100644
--- a/go/src/lib/regex.go
+++ b/go/src/lib/regex.go
@@ -94,6 +94,17 @@ func CompileMillerRegexOrDie(regexString string) *regexp.Regexp {
 	return regex
 }
 
+// In Go as in all languages I'm aware of with a string-split, "a,b,c" splits
+// on "," to ["a", "b", "c" and "a" splits to ["a"], both of which are fine --
+// but "" splits to [""] when I wish it were []. This function does the latter.
+func RegexSplitString(regex *regexp.Regexp, input string, n int) []string {
+	if input == "" {
+		return make([]string, 0)
+	} else {
+		return regex.Split(input, n)
+	}
+}
+
 // MakeEmptyRegexCaptures is for initial CST state at the start of executing
 // the DSL expression for the current record.  Even if '$x =~ "(..)_(...)" set
 // "\1" and "\2" on the previous record, at start of processing for the current
diff --git a/go/src/output/record_writer_markdown.go b/go/src/output/record_writer_markdown.go
index d17a63224..795687883 100644
--- a/go/src/output/record_writer_markdown.go
+++ b/go/src/output/record_writer_markdown.go
@@ -12,6 +12,7 @@ import (
 
 type RecordWriterMarkdown struct {
 	writerOptions *cli.TWriterOptions
+	ors           string
 
 	numHeaderLinesOutput int
 	lastJoinedHeader     string
diff --git a/go/src/output/record_writer_nidx.go b/go/src/output/record_writer_nidx.go
index 8d3edcc57..56c65924c 100644
--- a/go/src/output/record_writer_nidx.go
+++ b/go/src/output/record_writer_nidx.go
@@ -10,6 +10,8 @@ import (
 
 type RecordWriterNIDX struct {
 	writerOptions *cli.TWriterOptions
+	ofs           string
+	ors           string
 }
 
 func NewRecordWriterNIDX(writerOptions *cli.TWriterOptions) *RecordWriterNIDX {
diff --git a/go/src/output/record_writer_pprint.go b/go/src/output/record_writer_pprint.go
index 421297332..dc35cda5d 100644
--- a/go/src/output/record_writer_pprint.go
+++ b/go/src/output/record_writer_pprint.go
@@ -67,7 +67,7 @@ func (writer *RecordWriterPPRINT) Write(
 				)
 				if nonEmpty {
 					// Print a newline
-					ostream.Write([]byte("\n"))
+					ostream.Write([]byte(writer.writerOptions.ORS))
 				}
 				// Start a new batch
 				writer.batch = list.New()
@@ -166,13 +166,13 @@ func (writer *RecordWriterPPRINT) writeHeterogenousListNonBarred(
 						buffer.WriteString(colorizer.MaybeColorizeKey(formatted, outputIsStdout))
 					} else {
 						buffer.WriteString(colorizer.MaybeColorizeKey(pe.Key, outputIsStdout))
-						buffer.WriteString("\n") // TODO: ORS
+						buffer.WriteString(writer.writerOptions.ORS)
 					}
 				} else {
 					formatted := fmt.Sprintf("%*s ", maxWidths[pe.Key], pe.Key)
 					buffer.WriteString(colorizer.MaybeColorizeKey(formatted, outputIsStdout))
 					if pe.Next == nil {
-						buffer.WriteString("\n") // TODO: ORS
+						buffer.WriteString(writer.writerOptions.ORS)
 					}
 				}
 
@@ -194,13 +194,13 @@ func (writer *RecordWriterPPRINT) writeHeterogenousListNonBarred(
 					buffer.WriteString(colorizer.MaybeColorizeValue(formatted, outputIsStdout))
 				} else {
 					buffer.WriteString(colorizer.MaybeColorizeValue(s, outputIsStdout))
-					buffer.WriteString("\n") // TODO: ORS
+					buffer.WriteString(writer.writerOptions.ORS)
 				}
 			} else {
 				formatted := fmt.Sprintf("%*s ", maxWidths[pe.Key], s)
 				buffer.WriteString(colorizer.MaybeColorizeValue(formatted, outputIsStdout))
 				if pe.Next == nil {
-					buffer.WriteString("\n") // TODO: ORS
+					buffer.WriteString(writer.writerOptions.ORS)
 				}
 			}
 		}
@@ -257,7 +257,7 @@ func (writer *RecordWriterPPRINT) writeHeterogenousListBarred(
 					buffer.WriteString(horizontalMiddle)
 				} else {
 					buffer.WriteString(horizontalEnd)
-					buffer.WriteString("\n") // TOOD: ORS
+					buffer.WriteString(writer.writerOptions.ORS)
 				}
 			}
 
@@ -274,7 +274,7 @@ func (writer *RecordWriterPPRINT) writeHeterogenousListBarred(
 					buffer.WriteString(verticalMiddle)
 				} else {
 					buffer.WriteString(verticalEnd)
-					buffer.WriteString("\n") // TOOD: ORS
+					buffer.WriteString(writer.writerOptions.ORS)
 				}
 			}
 
@@ -285,7 +285,7 @@ func (writer *RecordWriterPPRINT) writeHeterogenousListBarred(
 					buffer.WriteString(horizontalMiddle)
 				} else {
 					buffer.WriteString(horizontalEnd)
-					buffer.WriteString("\n") // TOOD: ORS
+					buffer.WriteString(writer.writerOptions.ORS)
 				}
 			}
 
@@ -309,7 +309,7 @@ func (writer *RecordWriterPPRINT) writeHeterogenousListBarred(
 				buffer.WriteString(fmt.Sprint(verticalMiddle))
 			} else {
 				buffer.WriteString(verticalEnd)
-				buffer.WriteString("\n") // TOOD: ORS
+				buffer.WriteString(writer.writerOptions.ORS)
 			}
 		}
 
@@ -321,7 +321,7 @@ func (writer *RecordWriterPPRINT) writeHeterogenousListBarred(
 					buffer.WriteString(horizontalMiddle)
 				} else {
 					buffer.WriteString(horizontalEnd)
-					buffer.WriteString("\n") // TOOD: ORS
+					buffer.WriteString(writer.writerOptions.ORS)
 				}
 			}
 		}
diff --git a/go/src/output/record_writer_xtab.go b/go/src/output/record_writer_xtab.go
index b67b91934..7deb57257 100644
--- a/go/src/output/record_writer_xtab.go
+++ b/go/src/output/record_writer_xtab.go
@@ -46,7 +46,7 @@ func (writer *RecordWriterXTAB) Write(
 	if writer.onFirst {
 		writer.onFirst = false
 	} else {
-		buffer.WriteString("\n")
+		buffer.WriteString("\n") // TODO: ORS
 	}
 
 	for pe := outrec.Head; pe != nil; pe = pe.Next {
@@ -56,10 +56,10 @@ func (writer *RecordWriterXTAB) Write(
 		buffer.WriteString(colorizer.MaybeColorizeKey(pe.Key, outputIsStdout))
 		buffer.WriteString(" ")
 		for i := 0; i < padLength; i++ {
-			buffer.WriteString(" ")
+			buffer.WriteString(writer.writerOptions.OPS)
 		}
 		buffer.WriteString(colorizer.MaybeColorizeValue(pe.Value.String(), outputIsStdout))
-		buffer.WriteString("\n")
+		buffer.WriteString("\n") // TODO: ORS
 	}
 	ostream.Write(buffer.Bytes())
 }
diff --git a/go/src/transformers/join.go b/go/src/transformers/join.go
index 2f25038fa..4f3a6fd40 100644
--- a/go/src/transformers/join.go
+++ b/go/src/transformers/join.go
@@ -219,7 +219,7 @@ func transformerJoinParseCLI(
 		}
 	}
 
-	cli.ApplyReaderOptionDefaults(&opts.joinFlagOptions.ReaderOptions)
+	cli.FinalizeReaderOptions(&opts.joinFlagOptions.ReaderOptions)
 
 	if opts.leftFileName == "" {
 		fmt.Fprintf(os.Stderr, "%s %s: need left file name\n", "mlr", verb)
diff --git a/go/src/transformers/put-or-filter.go b/go/src/transformers/put-or-filter.go
index 1494a10f3..014164abc 100644
--- a/go/src/transformers/put-or-filter.go
+++ b/go/src/transformers/put-or-filter.go
@@ -249,7 +249,7 @@ func transformerPutOrFilterParseCLI(
 		}
 	}
 
-	cli.ApplyWriterOptionDefaults(&options.WriterOptions)
+	cli.FinalizeWriterOptions(&options.WriterOptions)
 
 	// If they've used either of 'mlr put -f {filename}' or 'mlr put -e
 	// {expression}' then that specifies their DSL expression. But if they've
diff --git a/go/src/transformers/tee.go b/go/src/transformers/tee.go
index 41359c67f..08283e4e2 100644
--- a/go/src/transformers/tee.go
+++ b/go/src/transformers/tee.go
@@ -98,7 +98,7 @@ func transformerTeeParseCLI(
 		}
 	}
 
-	cli.ApplyWriterOptionDefaults(&localOptions.WriterOptions)
+	cli.FinalizeWriterOptions(&localOptions.WriterOptions)
 
 	// Get the filename/command from the command line, after the flags
 	if argi >= argc {
diff --git a/man6/manpage.txt b/man6/manpage.txt
index 0f36b976b..e448fe191 100644
--- a/man6/manpage.txt
+++ b/man6/manpage.txt
@@ -110,6 +110,7 @@ HELP OPTIONS
          mlr help file-formats
        Flags:
          mlr help flags
+         mlr help list-separator-aliases
          mlr help comments-in-data-flags
          mlr help compressed-data-flags
          mlr help csv-only-flags
@@ -605,6 +606,17 @@ SEPARATOR FLAGS
          - C-style escape sequences, e.g. `--rs '\r\n' --fs '\t'`.
          - To avoid backslashing, you can use any of the following names:
 
+                 ascii_esc  = "\x1b"
+                 ascii_etx  = "\x04"
+                 ascii_fs   = "\x1c"
+                 ascii_gs   = "\x1d"
+                 ascii_null = "\x01"
+                 ascii_rs   = "\x1e"
+                 ascii_soh  = "\x02"
+                 ascii_stx  = "\x03"
+                 ascii_us   = "\x1f"
+                 asv_fs     = "\x1f"
+                 asv_rs     = "\x1e"
                  colon      = ":"
                  comma      = ","
                  cr         = "\r"
@@ -619,7 +631,12 @@ SEPARATOR FLAGS
                  semicolon  = ";"
                  slash      = "/"
                  space      = " "
+                 spaces     = "( )+"
                  tab        = "\t"
+                 tabs       = "(\t)+"
+                 usv_fs     = "\xe2\x90\x9f"
+                 usv_rs     = "\xe2\x90\x9e"
+                 whitespace = "([ \t])+"
 
        * Default separators by format:
 
@@ -2720,4 +2737,4 @@ SEE ALSO
 
 
 
-                                  2021-09-20                         MILLER(1)
+                                  2021-09-21                         MILLER(1)
diff --git a/man6/mlr6.1 b/man6/mlr6.1
index bea053408..298d069e8 100644
--- a/man6/mlr6.1
+++ b/man6/mlr6.1
@@ -2,12 +2,12 @@
 .\"     Title: mlr
 .\"    Author: [see the "AUTHOR" section]
 .\" Generator: ./mkman.rb
-.\"      Date: 2021-09-20
+.\"      Date: 2021-09-21
 .\"    Manual: \ \&
 .\"    Source: \ \&
 .\"  Language: English
 .\"
-.TH "MILLER" "1" "2021-09-20" "\ \&" "\ \&"
+.TH "MILLER" "1" "2021-09-21" "\ \&" "\ \&"
 .\" -----------------------------------------------------------------
 .\" * Portability definitions
 .\" ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -145,6 +145,7 @@ Essentials:
   mlr help file-formats
 Flags:
   mlr help flags
+  mlr help list-separator-aliases
   mlr help comments-in-data-flags
   mlr help compressed-data-flags
   mlr help csv-only-flags
@@ -748,6 +749,17 @@ Notes about all other separators:
   - C-style escape sequences, e.g. `--rs '\er\en' --fs '\et'`.
   - To avoid backslashing, you can use any of the following names:
 
+          ascii_esc  = "\ex1b"
+          ascii_etx  = "\ex04"
+          ascii_fs   = "\ex1c"
+          ascii_gs   = "\ex1d"
+          ascii_null = "\ex01"
+          ascii_rs   = "\ex1e"
+          ascii_soh  = "\ex02"
+          ascii_stx  = "\ex03"
+          ascii_us   = "\ex1f"
+          asv_fs     = "\ex1f"
+          asv_rs     = "\ex1e"
           colon      = ":"
           comma      = ","
           cr         = "\er"
@@ -762,7 +774,12 @@ Notes about all other separators:
           semicolon  = ";"
           slash      = "/"
           space      = " "
+          spaces     = "( )+"
           tab        = "\et"
+          tabs       = "(\et)+"
+          usv_fs     = "\exe2\ex90\ex9f"
+          usv_rs     = "\exe2\ex90\ex9e"
+          whitespace = "([ \et])+"
 
 * Default separators by format: