Support PPRINT barred input (#1472)

* Support PPRINT barred input

* regression-test files

* output from `make dev`

* doc updates

docs/src/file-formats.md

@@ -366,7 +366,7 @@ Note that while Miller is a line-at-a-time processor and retains input lines in
 
 See [Record Heterogeneity](record-heterogeneity.md) for how Miller handles changes of field names within a single data stream.
 
-For output only (this isn't supported in the input-scanner as of 5.0.0) you can use `--barred` with pprint output format:
+Since Miller 5.0.0, you can use `--barred` or `--barred-output` with pprint output format:
 
 <pre class="pre-highlight-in-pair">
 <b>mlr --opprint --barred cat data/small</b>
@@ -383,6 +383,37 @@ For output only (this isn't supported in the input-scanner as of 5.0.0) you can
 +-----+-----+---+----------+----------+
 </pre>
 
+Since Miller 6.11.0, you can use `--barred-input` with pprint output format:
+
+<pre class="pre-highlight-in-pair">
+<b>mlr -o pprint --barred cat data/small | mlr -i pprint --barred-input -o json filter '$b == "pan"'</b>
+</pre>
+<pre class="pre-non-highlight-in-pair">
+[
+{
+  "a": "pan",
+  "b": "pan",
+  "i": 1,
+  "x": 0.346791,
+  "y": 0.726802
+},
+{
+  "a": "eks",
+  "b": "pan",
+  "i": 2,
+  "x": 0.758679,
+  "y": 0.522151
+},
+{
+  "a": "wye",
+  "b": "pan",
+  "i": 5,
+  "x": 0.573288,
+  "y": 0.863624
+}
+]
+</pre>
+
 ## Markdown tabular
 
 Markdown format looks like this:

docs/src/file-formats.md.in

@@ -153,12 +153,18 @@ Note that while Miller is a line-at-a-time processor and retains input lines in
 
 See [Record Heterogeneity](record-heterogeneity.md) for how Miller handles changes of field names within a single data stream.
 
-For output only (this isn't supported in the input-scanner as of 5.0.0) you can use `--barred` with pprint output format:
+Since Miller 5.0.0, you can use `--barred` or `--barred-output` with pprint output format:
 
 GENMD-RUN-COMMAND
 mlr --opprint --barred cat data/small
 GENMD-EOF
 
+Since Miller 6.11.0, you can use `--barred-input` with pprint output format:
+
+GENMD-RUN-COMMAND
+mlr -o pprint --barred cat data/small | mlr -i pprint --barred-input -o json filter '$b == "pan"'
+GENMD-EOF
+
 ## Markdown tabular
 
 Markdown format looks like this:

docs/src/manpage.md

@@ -19,9 +19,7 @@ Quick links:
 This is simply a copy of what you should see on running `man mlr` at a command prompt, once Miller is installed on your system.
 
 <pre class="pre-non-highlight-non-pair">
-MILLER(1)                                                            MILLER(1)
-
-
+4mMILLER24m(1)                                                            4mMILLER24m(1)
 
 1mNAME0m
        Miller -- like awk, sed, cut, join, and sort for name-indexed data such
@@ -697,8 +695,10 @@ MILLER(1)                                                            MILLER(1)
 1mPPRINT-ONLY FLAGS0m
        These are flags which are applicable to PPRINT format.
 
-       --barred                 Prints a border around PPRINT output (not available
-                                for input).
+       --barred or --barred-output
+                                Prints a border around PPRINT output.
+       --barred-input           When used in conjunction with --pprint, accepts
+                                barred input.
        --right                  Right-justifies all fields for PPRINT output.
 
 1mPROFILING FLAGS0m
@@ -807,7 +807,7 @@ MILLER(1)                                                            MILLER(1)
                markdown " "    N/A    "\n"
                nidx     " "    N/A    "\n"
                pprint   " "    N/A    "\n"
-               tsv      "  "    N/A    "\n"
+               tsv      "     "    N/A    "\n"
                xtab     "\n"   " "    "\n\n"
 
        --fs {string}            Specify FS for input and output.
@@ -3687,7 +3687,5 @@ MILLER(1)                                                            MILLER(1)
        MIME Type for Comma-Separated Values (CSV) Files, the Miller docsite
        https://miller.readthedocs.io
 
-
-
-                                  2024-01-01                         MILLER(1)
+                                  2024-01-20                         4mMILLER24m(1)
 </pre>

docs/src/manpage.txt

@@ -1,6 +1,4 @@
-MILLER(1)                                                            MILLER(1)
-
-
+4mMILLER24m(1)                                                            4mMILLER24m(1)
 
 1mNAME0m
        Miller -- like awk, sed, cut, join, and sort for name-indexed data such
@@ -676,8 +674,10 @@ MILLER(1)                                                            MILLER(1)
 1mPPRINT-ONLY FLAGS0m
        These are flags which are applicable to PPRINT format.
 
-       --barred                 Prints a border around PPRINT output (not available
-                                for input).
+       --barred or --barred-output
+                                Prints a border around PPRINT output.
+       --barred-input           When used in conjunction with --pprint, accepts
+                                barred input.
        --right                  Right-justifies all fields for PPRINT output.
 
 1mPROFILING FLAGS0m
@@ -786,7 +786,7 @@ MILLER(1)                                                            MILLER(1)
                markdown " "    N/A    "\n"
                nidx     " "    N/A    "\n"
                pprint   " "    N/A    "\n"
-               tsv      "  "    N/A    "\n"
+               tsv      "     "    N/A    "\n"
                xtab     "\n"   " "    "\n\n"
 
        --fs {string}            Specify FS for input and output.
@@ -3666,6 +3666,4 @@ MILLER(1)                                                            MILLER(1)
        MIME Type for Comma-Separated Values (CSV) Files, the Miller docsite
        https://miller.readthedocs.io
 
-
-
-                                  2024-01-01                         MILLER(1)
+                                  2024-01-20                         4mMILLER24m(1)

docs/src/reference-main-flag-list.md

@@ -373,7 +373,8 @@ These are flags which are applicable to PPRINT format.
 
 **Flags:**
 
-* `--barred`: Prints a border around PPRINT output (not available for input).
+* `--barred or --barred-output`: Prints a border around PPRINT output.
+* `--barred-input`: When used in conjunction with --pprint, accepts barred input.
 * `--right`: Right-justifies all fields for PPRINT output.
 
 ## Profiling flags

man/manpage.txt

@@ -1,6 +1,4 @@
-MILLER(1)                                                            MILLER(1)
-
-
+4mMILLER24m(1)                                                            4mMILLER24m(1)
 
 1mNAME0m
        Miller -- like awk, sed, cut, join, and sort for name-indexed data such
@@ -676,8 +674,10 @@ MILLER(1)                                                            MILLER(1)
 1mPPRINT-ONLY FLAGS0m
        These are flags which are applicable to PPRINT format.
 
-       --barred                 Prints a border around PPRINT output (not available
-                                for input).
+       --barred or --barred-output
+                                Prints a border around PPRINT output.
+       --barred-input           When used in conjunction with --pprint, accepts
+                                barred input.
        --right                  Right-justifies all fields for PPRINT output.
 
 1mPROFILING FLAGS0m
@@ -786,7 +786,7 @@ MILLER(1)                                                            MILLER(1)
                markdown " "    N/A    "\n"
                nidx     " "    N/A    "\n"
                pprint   " "    N/A    "\n"
-               tsv      "  "    N/A    "\n"
+               tsv      "     "    N/A    "\n"
                xtab     "\n"   " "    "\n\n"
 
        --fs {string}            Specify FS for input and output.
@@ -3666,6 +3666,4 @@ MILLER(1)                                                            MILLER(1)
        MIME Type for Comma-Separated Values (CSV) Files, the Miller docsite
        https://miller.readthedocs.io
 
-
-
-                                  2024-01-01                         MILLER(1)
+                                  2024-01-20                         4mMILLER24m(1)

man/mkman.rb

@@ -19,7 +19,7 @@ def main
   # Live code-generation needs to be using mlr from *this* tree, not from
   # somewhere else in the PATH.
   unless File.executable?('../mlr')
-    $stderr.puts "#{$0}: Need ../../mlr to exist: please check 'make build' in ../.."
+    $stderr.puts "#{$0}: Need ../mlr to exist: please check 'make build' in ../.."
     exit 1
   end
   `../mlr --version`

man/mlr.1

@@ -2,12 +2,12 @@
 .\"     Title: mlr
 .\"    Author: [see the "AUTHOR" section]
 .\" Generator: ./mkman.rb
-.\"      Date: 2024-01-01
+.\"      Date: 2024-01-20
 .\"    Manual: \ \&
 .\"    Source: \ \&
 .\"  Language: English
 .\"
-.TH "MILLER" "1" "2024-01-01" "\ \&" "\ \&"
+.TH "MILLER" "1" "2024-01-20" "\ \&" "\ \&"
 .\" -----------------------------------------------------------------
 .\" * Portability definitions
 .\" ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -811,8 +811,10 @@ those can be joined with a "-", like "red-bold", "bold-170", "bold-underline", e
 .nf
 These are flags which are applicable to PPRINT format.
 
---barred                 Prints a border around PPRINT output (not available
-                         for input).
+--barred or --barred-output
+                         Prints a border around PPRINT output.
+--barred-input           When used in conjunction with --pprint, accepts
+                         barred input.
 --right                  Right-justifies all fields for PPRINT output.
 .fi
 .if n \{\

pkg/cli/option_parse.go

@@ -494,13 +494,24 @@ var PPRINTOnlyFlagSection = FlagSection{
 		},
 
 		{
-			name: "--barred",
-			help: "Prints a border around PPRINT output (not available for input).",
+			name:     "--barred",
+			altNames: []string{"--barred-output"},
+			help:     "Prints a border around PPRINT output.",
 			parser: func(args []string, argc int, pargi *int, options *TOptions) {
 				options.WriterOptions.BarredPprintOutput = true
 				*pargi += 1
 			},
 		},
+
+		{
+			name: "--barred-input",
+			help: "When used in conjunction with --pprint, accepts barred input.",
+			parser: func(args []string, argc int, pargi *int, options *TOptions) {
+				options.ReaderOptions.BarredPprintInput = true
+				options.ReaderOptions.IFS = "|"
+				*pargi += 1
+			},
+		},
 	},
 }
 

pkg/cli/option_types.go

@@ -57,6 +57,7 @@ type TReaderOptions struct {
 	AllowRaggedCSVInput  bool
 	CSVLazyQuotes        bool
 	CSVTrimLeadingSpace  bool
+	BarredPprintInput    bool
 
 	CommentHandling TCommentHandling
 	CommentString   string

pkg/input/record_reader_csvlite.go

@@ -78,26 +78,6 @@ func NewRecordReaderCSVLite(
 	return reader, nil
 }
 
-func NewRecordReaderPPRINT(
-	readerOptions *cli.TReaderOptions,
-	recordsPerBatch int64,
-) (*RecordReaderCSVLite, error) {
-	reader := &RecordReaderCSVLite{
-		readerOptions:   readerOptions,
-		recordsPerBatch: recordsPerBatch,
-		fieldSplitter:   newFieldSplitter(readerOptions),
-
-		useVoidRep: true,
-		voidRep:    "-",
-	}
-	if reader.readerOptions.UseImplicitCSVHeader {
-		reader.recordBatchGetter = getRecordBatchImplicitCSVHeader
-	} else {
-		reader.recordBatchGetter = getRecordBatchExplicitCSVHeader
-	}
-	return reader, nil
-}
-
 func (reader *RecordReaderCSVLite) Read(
 	filenames []string,
 	context types.Context,

pkg/input/record_reader_pprint.go

@@ -0,0 +1,462 @@
+package input
+
+// Multi-file cases:
+//
+// a,a        a,b        c          d
+// -- FILE1:  -- FILE1:  -- FILE1:  -- FILE1:
+// a,b,c      a,b,c      a,b,c      a,b,c
+// 1,2,3      1,2,3      1,2,3      1,2,3
+// 4,5,6      4,5,6      4,5,6      4,5,6
+// -- FILE2:  -- FILE2:
+// a,b,c      d,e,f,g    a,b,c      d,e,f
+// 7,8,9      3,4,5,6    7,8,9      3,4,5
+// --OUTPUT:  --OUTPUT:  --OUTPUT:  --OUTPUT:
+// a,b,c      a,b,c      a,b,c      a,b,c
+// 1,2,3      1,2,3      1,2,3      1,2,3
+// 4,5,6      4,5,6      4,5,6      4,5,6
+// 7,8,9                 7,8,9
+//            d,e,f,g               d,e,f
+//            3,4,5,6               3,4,5
+
+import (
+	"container/list"
+	"fmt"
+	"io"
+	"regexp"
+	"strconv"
+	"strings"
+
+	"github.com/johnkerl/miller/pkg/cli"
+	"github.com/johnkerl/miller/pkg/lib"
+	"github.com/johnkerl/miller/pkg/mlrval"
+	"github.com/johnkerl/miller/pkg/types"
+)
+
+func NewRecordReaderPPRINT(
+	readerOptions *cli.TReaderOptions,
+	recordsPerBatch int64,
+) (IRecordReader, error) {
+	if readerOptions.BarredPprintInput {
+		// Implemented in this file
+
+		// XXX TEMP
+		readerOptions.IFS = "|"
+		readerOptions.AllowRepeatIFS = false
+
+		reader := &RecordReaderPprintBarred{
+			readerOptions:    readerOptions,
+			recordsPerBatch:  recordsPerBatch,
+			separatorMatcher: regexp.MustCompile(`^\+[-+]*\+`),
+			fieldSplitter:    newFieldSplitter(readerOptions),
+		}
+		if reader.readerOptions.UseImplicitCSVHeader {
+			reader.recordBatchGetter = getRecordBatchImplicitPprintHeader
+		} else {
+			reader.recordBatchGetter = getRecordBatchExplicitPprintHeader
+		}
+		return reader, nil
+
+	} else {
+		// Use the CSVLite record-reader, which is implemented in another file,
+		// with multiple spaces instead of commas
+		reader := &RecordReaderCSVLite{
+			readerOptions:   readerOptions,
+			recordsPerBatch: recordsPerBatch,
+			fieldSplitter:   newFieldSplitter(readerOptions),
+
+			useVoidRep: true,
+			voidRep:    "-",
+		}
+		// XXX RENAME THERE
+		if reader.readerOptions.UseImplicitCSVHeader {
+			reader.recordBatchGetter = getRecordBatchImplicitCSVHeader
+		} else {
+			reader.recordBatchGetter = getRecordBatchExplicitCSVHeader
+		}
+		return reader, nil
+	}
+}
+
+type RecordReaderPprintBarred struct {
+	readerOptions   *cli.TReaderOptions
+	recordsPerBatch int64 // distinct from readerOptions.RecordsPerBatch for join/repl
+
+	separatorMatcher  *regexp.Regexp
+	fieldSplitter     iFieldSplitter
+	recordBatchGetter recordBatchGetterPprint
+
+	inputLineNumber int64
+	headerStrings   []string
+}
+
+// recordBatchGetterPprint points to either an explicit-PPRINT-header or
+// implicit-PPRINT-header record-batch getter.
+type recordBatchGetterPprint func(
+	reader *RecordReaderPprintBarred,
+	linesChannel <-chan *list.List,
+	filename string,
+	context *types.Context,
+	errorChannel chan error,
+) (
+	recordsAndContexts *list.List,
+	eof bool,
+)
+
+func (reader *RecordReaderPprintBarred) Read(
+	filenames []string,
+	context types.Context,
+	readerChannel chan<- *list.List, // list of *types.RecordAndContext
+	errorChannel chan error,
+	downstreamDoneChannel <-chan bool, // for mlr head
+) {
+	if filenames != nil { // nil for mlr -n
+		if len(filenames) == 0 { // read from stdin
+			handle, err := lib.OpenStdin(
+				reader.readerOptions.Prepipe,
+				reader.readerOptions.PrepipeIsRaw,
+				reader.readerOptions.FileInputEncoding,
+			)
+			if err != nil {
+				errorChannel <- err
+				return
+			}
+			reader.processHandle(
+				handle,
+				"(stdin)",
+				&context,
+				readerChannel,
+				errorChannel,
+				downstreamDoneChannel,
+			)
+		} else {
+			for _, filename := range filenames {
+				handle, err := lib.OpenFileForRead(
+					filename,
+					reader.readerOptions.Prepipe,
+					reader.readerOptions.PrepipeIsRaw,
+					reader.readerOptions.FileInputEncoding,
+				)
+				if err != nil {
+					errorChannel <- err
+					return
+				}
+				reader.processHandle(
+					handle,
+					filename,
+					&context,
+					readerChannel,
+					errorChannel,
+					downstreamDoneChannel,
+				)
+				handle.Close()
+			}
+		}
+	}
+	readerChannel <- types.NewEndOfStreamMarkerList(&context)
+}
+
+func (reader *RecordReaderPprintBarred) processHandle(
+	handle io.Reader,
+	filename string,
+	context *types.Context,
+	readerChannel chan<- *list.List, // list of *types.RecordAndContext
+	errorChannel chan error,
+	downstreamDoneChannel <-chan bool, // for mlr head
+) {
+	context.UpdateForStartOfFile(filename)
+	reader.inputLineNumber = 0
+	reader.headerStrings = nil
+
+	recordsPerBatch := reader.recordsPerBatch
+	lineScanner := NewLineScanner(handle, reader.readerOptions.IRS)
+	linesChannel := make(chan *list.List, recordsPerBatch)
+	go channelizedLineScanner(lineScanner, linesChannel, downstreamDoneChannel, recordsPerBatch)
+
+	for {
+		recordsAndContexts, eof := reader.recordBatchGetter(reader, linesChannel, filename, context, errorChannel)
+		if recordsAndContexts.Len() > 0 {
+			readerChannel <- recordsAndContexts
+		}
+		if eof {
+			break
+		}
+	}
+}
+
+func getRecordBatchExplicitPprintHeader(
+	reader *RecordReaderPprintBarred,
+	linesChannel <-chan *list.List,
+	filename string,
+	context *types.Context,
+	errorChannel chan error,
+) (
+	recordsAndContexts *list.List,
+	eof bool,
+) {
+	recordsAndContexts = list.New()
+	dedupeFieldNames := reader.readerOptions.DedupeFieldNames
+
+	lines, more := <-linesChannel
+	if !more {
+		return recordsAndContexts, true
+	}
+
+	for e := lines.Front(); e != nil; e = e.Next() {
+		line := e.Value.(string)
+
+		reader.inputLineNumber++
+
+		// Check for comments-in-data feature
+		// TODO: function-pointer this away
+		if reader.readerOptions.CommentHandling != cli.CommentsAreData {
+			if strings.HasPrefix(line, reader.readerOptions.CommentString) {
+				if reader.readerOptions.CommentHandling == cli.PassComments {
+					recordsAndContexts.PushBack(types.NewOutputString(line+"\n", context))
+					continue
+				} else if reader.readerOptions.CommentHandling == cli.SkipComments {
+					continue
+				}
+				// else comments are data
+			}
+		}
+
+		if line == "" {
+			// Reset to new schema
+			reader.headerStrings = nil
+			continue
+		}
+
+		// Example input:
+		// +-----+-----+----+---------------------+---------------------+
+		// | a   | b   | i  | x                   | y                   |
+		// +-----+-----+----+---------------------+---------------------+
+		// | pan | pan | 1  | 0.3467901443380824  | 0.7268028627434533  |
+		// | eks | pan | 2  | 0.7586799647899636  | 0.5221511083334797  |
+		// +-----+-----+----+---------------------+---------------------+
+
+		// Skip lines like
+		// +-----+-----+----+---------------------+---------------------+
+		if reader.separatorMatcher.MatchString(line) {
+			continue
+		}
+
+		// Skip the leading and trailing pipes
+		paddedFields := reader.fieldSplitter.Split(line)
+		npad := len(paddedFields)
+		fields := make([]string, npad-2)
+		for i, _ := range paddedFields {
+			if i == 0 || i == npad-1 {
+				continue
+			}
+			fields[i-1] = strings.TrimSpace(paddedFields[i])
+		}
+
+		if reader.headerStrings == nil {
+			reader.headerStrings = fields
+			// Get data lines on subsequent loop iterations
+		} else {
+			if !reader.readerOptions.AllowRaggedCSVInput && len(reader.headerStrings) != len(fields) {
+				err := fmt.Errorf(
+					"mlr: PPRINT-barred header/data length mismatch %d != %d "+
+						"at filename %s line  %d.\n",
+					len(reader.headerStrings), len(fields), filename, reader.inputLineNumber,
+				)
+				errorChannel <- err
+				return
+			}
+
+			record := mlrval.NewMlrmapAsRecord()
+			if !reader.readerOptions.AllowRaggedCSVInput {
+				for i, field := range fields {
+					value := mlrval.FromDeferredType(field)
+					_, err := record.PutReferenceMaybeDedupe(reader.headerStrings[i], value, dedupeFieldNames)
+					if err != nil {
+						errorChannel <- err
+						return
+					}
+				}
+			} else {
+				nh := int64(len(reader.headerStrings))
+				nd := int64(len(fields))
+				n := lib.IntMin2(nh, nd)
+				var i int64
+				for i = 0; i < n; i++ {
+					field := fields[i]
+					value := mlrval.FromDeferredType(field)
+					_, err := record.PutReferenceMaybeDedupe(reader.headerStrings[i], value, dedupeFieldNames)
+					if err != nil {
+						errorChannel <- err
+						return
+					}
+				}
+				if nh < nd {
+					// if header shorter than data: use 1-up itoa keys
+					for i = nh; i < nd; i++ {
+						key := strconv.FormatInt(i+1, 10)
+						value := mlrval.FromDeferredType(fields[i])
+						_, err := record.PutReferenceMaybeDedupe(key, value, dedupeFieldNames)
+						if err != nil {
+							errorChannel <- err
+							return
+						}
+					}
+				}
+				if nh > nd {
+					// if header longer than data: use "" values
+					for i = nd; i < nh; i++ {
+						record.PutCopy(reader.headerStrings[i], mlrval.VOID)
+					}
+				}
+			}
+
+			context.UpdateForInputRecord()
+			recordsAndContexts.PushBack(types.NewRecordAndContext(record, context))
+
+		}
+	}
+
+	return recordsAndContexts, false
+}
+
+func getRecordBatchImplicitPprintHeader(
+	reader *RecordReaderPprintBarred,
+	linesChannel <-chan *list.List,
+	filename string,
+	context *types.Context,
+	errorChannel chan error,
+) (
+	recordsAndContexts *list.List,
+	eof bool,
+) {
+	recordsAndContexts = list.New()
+	dedupeFieldNames := reader.readerOptions.DedupeFieldNames
+
+	lines, more := <-linesChannel
+	if !more {
+		return recordsAndContexts, true
+	}
+
+	for e := lines.Front(); e != nil; e = e.Next() {
+		line := e.Value.(string)
+
+		reader.inputLineNumber++
+
+		// Check for comments-in-data feature
+		// TODO: function-pointer this away
+		if reader.readerOptions.CommentHandling != cli.CommentsAreData {
+			if strings.HasPrefix(line, reader.readerOptions.CommentString) {
+				if reader.readerOptions.CommentHandling == cli.PassComments {
+					recordsAndContexts.PushBack(types.NewOutputString(line+"\n", context))
+					continue
+				} else if reader.readerOptions.CommentHandling == cli.SkipComments {
+					continue
+				}
+				// else comments are data
+			}
+		}
+
+		if line == "" {
+			// Reset to new schema
+			reader.headerStrings = nil
+			continue
+		}
+
+		// Example input:
+		// +-----+-----+----+---------------------+---------------------+
+		// | a   | b   | i  | x                   | y                   |
+		// +-----+-----+----+---------------------+---------------------+
+		// | pan | pan | 1  | 0.3467901443380824  | 0.7268028627434533  |
+		// | eks | pan | 2  | 0.7586799647899636  | 0.5221511083334797  |
+		// +-----+-----+----+---------------------+---------------------+
+
+		// Skip lines like
+		// +-----+-----+----+---------------------+---------------------+
+		if reader.separatorMatcher.MatchString(line) {
+			continue
+		}
+
+		// Skip the leading and trailing pipes
+		paddedFields := reader.fieldSplitter.Split(line)
+		npad := len(paddedFields)
+		fields := make([]string, npad-2)
+		for i, _ := range paddedFields {
+			if i == 0 || i == npad-1 {
+				continue
+			}
+			fields[i-1] = strings.TrimSpace(paddedFields[i])
+		}
+
+		if reader.headerStrings == nil {
+			n := len(fields)
+			reader.headerStrings = make([]string, n)
+			for i := 0; i < n; i++ {
+				reader.headerStrings[i] = strconv.Itoa(i + 1)
+			}
+		} else {
+			if !reader.readerOptions.AllowRaggedCSVInput && len(reader.headerStrings) != len(fields) {
+				err := fmt.Errorf(
+					"mlr: CSV header/data length mismatch %d != %d "+
+						"at filename %s line  %d.\n",
+					len(reader.headerStrings), len(fields), filename, reader.inputLineNumber,
+				)
+				errorChannel <- err
+				return
+			}
+		}
+
+		record := mlrval.NewMlrmapAsRecord()
+		if !reader.readerOptions.AllowRaggedCSVInput {
+			for i, field := range fields {
+				value := mlrval.FromDeferredType(field)
+				_, err := record.PutReferenceMaybeDedupe(reader.headerStrings[i], value, dedupeFieldNames)
+				if err != nil {
+					errorChannel <- err
+					return
+				}
+			}
+		} else {
+			nh := int64(len(reader.headerStrings))
+			nd := int64(len(fields))
+			n := lib.IntMin2(nh, nd)
+			var i int64
+			for i = 0; i < n; i++ {
+				field := fields[i]
+				value := mlrval.FromDeferredType(field)
+				_, err := record.PutReferenceMaybeDedupe(reader.headerStrings[i], value, dedupeFieldNames)
+				if err != nil {
+					errorChannel <- err
+					return
+				}
+			}
+			if nh < nd {
+				// if header shorter than data: use 1-up itoa keys
+				key := strconv.FormatInt(i+1, 10)
+				value := mlrval.FromDeferredType(fields[i])
+				_, err := record.PutReferenceMaybeDedupe(key, value, dedupeFieldNames)
+				if err != nil {
+					errorChannel <- err
+					return
+				}
+			}
+			if nh > nd {
+				// if header longer than data: use "" values
+				for i = nd; i < nh; i++ {
+					_, err := record.PutReferenceMaybeDedupe(
+						reader.headerStrings[i],
+						mlrval.VOID.Copy(),
+						dedupeFieldNames,
+					)
+					if err != nil {
+						errorChannel <- err
+						return
+					}
+				}
+			}
+		}
+
+		context.UpdateForInputRecord()
+		recordsAndContexts.PushBack(types.NewRecordAndContext(record, context))
+	}
+
+	return recordsAndContexts, false
+}

test/cases/io-barred-pprint/barred-input-headerless/cmd

@@ -0,0 +1 @@
+mlr --hi --i pprint --barred-input -o json test/input/abixy.tbl

test/cases/io-barred-pprint/barred-input-headerless/experr

@@ -0,0 +1,2 @@
+mlr: option "--i" not recognized.
+Please run "mlr --help" for usage information.

test/cases/io-barred-pprint/barred-input/cmd

@@ -0,0 +1 @@
+mlr --i pprint --barred-input -o json test/input/abixy.tbl

test/cases/io-barred-pprint/barred-input/experr

@@ -0,0 +1,2 @@
+mlr: option "--i" not recognized.
+Please run "mlr --help" for usage information.

test/input/abixy.tbl

@@ -0,0 +1,14 @@
++-----+-----+----+---------------------+---------------------+
+| a   | b   | i  | x                   | y                   |
++-----+-----+----+---------------------+---------------------+
+| pan | pan | 1  | 0.3467901443380824  | 0.7268028627434533  |
+| eks | pan | 2  | 0.7586799647899636  | 0.5221511083334797  |
+| wye | wye | 3  | 0.20460330576630303 | 0.33831852551664776 |
+| eks | wye | 4  | 0.38139939387114097 | 0.13418874328430463 |
+| wye | pan | 5  | 0.5732889198020006  | 0.8636244699032729  |
+| zee | pan | 6  | 0.5271261600918548  | 0.49322128674835697 |
+| eks | zee | 7  | 0.6117840605678454  | 0.1878849191181694  |
+| zee | wye | 8  | 0.5985540091064224  | 0.976181385699006   |
+| hat | wye | 9  | 0.03144187646093577 | 0.7495507603507059  |
+| pan | wye | 10 | 0.5026260055412137  | 0.9526183602969864  |
++-----+-----+----+---------------------+---------------------+