more

.codespellignore

@@ -6,3 +6,4 @@ nd
 nin
 numer
 Wit
+te

.github/workflows/codespell.yml

@@ -32,12 +32,5 @@ jobs:
         with:
           check_filenames: true
           ignore_words_file: .codespellignore
-          # This simply does not work despite multiple attempts, despite
           # https://github.com/codespell-project/codespell
-          #
-          # skip: "*.csv","*.txt"
-          skip: "*.csv,*.txt,./test/cases"
-          #skip:
-          #  - docs/src/data/english-words.txt
-          #  - docs/src/ngrams/gsl-2000.txt
-          #  - "test/cases/**/*"
+          skip: "*.csv,*.dkvp,*.txt,./test/cases"

docs/src/reference-dsl-higher-order-functions.md

@@ -38,7 +38,7 @@ respectively.
 
 The [`select`](reference-dsl-builtin-functions.md#select) function takes a map
 or array as its first argument and a function as second argument.  It includes
-each input element in the ouptut if the function returns true.
+each input element in the output if the function returns true.
 
 For arrays, that function should take one argument, for array element; for
 maps, it should take two, for map-element key and value. In either case it
@@ -776,7 +776,7 @@ Sorted, then cubed, then summed:
 
 ### Remember return
 
-From other languages it's easy to accidentially write
+From other languages it's easy to accidentally write
 
 <pre class="pre-highlight-in-pair">
 <b>mlr -n put 'end { print select([1,2,3,4,5], func (e) { e >= 3 })}'</b>

docs/src/reference-dsl-higher-order-functions.md.in

@@ -22,7 +22,7 @@ respectively.
 
 The [`select`](reference-dsl-builtin-functions.md#select) function takes a map
 or array as its first argument and a function as second argument.  It includes
-each input element in the ouptut if the function returns true.
+each input element in the output if the function returns true.
 
 For arrays, that function should take one argument, for array element; for
 maps, it should take two, for map-element key and value. In either case it
@@ -426,7 +426,7 @@ GENMD-EOF
 
 ### Remember return
 
-From other languages it's easy to accidentially write
+From other languages it's easy to accidentally write
 
 GENMD-RUN-COMMAND-TOLERATING-ERROR
 mlr -n put 'end { print select([1,2,3,4,5], func (e) { e >= 3 })}'

docs/src/reference-dsl-time.md

@@ -19,7 +19,7 @@ Quick links:
 Dates/times are not a separate data type; Miller uses ints for
 [seconds since the epoch](https://en.wikipedia.org/wiki/Unix_time) and strings for formatted
 date/times. In this page we take a look at what some of the various options are
-for processing datetimes andd timezones in your data.
+for processing datetimes and timezones in your data.
 
 See also the [section on time-related
 functions](reference-dsl-builtin-functions.md#time-functions) for
@@ -43,7 +43,7 @@ they're independent of timezone or daylight-savings time.
 One minus is that, being just numbers, they're not particularly human-readable
 -- hence the to-string and from-string functions described below.  Another
 caveat (not really a minus) is that _epoch milliseconds_, rather than epoch
-seconds, are common in some contexts, particulary JavaScript. If you ever
+seconds, are common in some contexts, particularly JavaScript. If you ever
 (anywhere) see a timestamp for the year 49,000-something -- probably someone is
 treating epoch-milliseconds as epoch-seconds.
 

docs/src/reference-dsl-time.md.in

@@ -3,7 +3,7 @@
 Dates/times are not a separate data type; Miller uses ints for
 [seconds since the epoch](https://en.wikipedia.org/wiki/Unix_time) and strings for formatted
 date/times. In this page we take a look at what some of the various options are
-for processing datetimes andd timezones in your data.
+for processing datetimes and timezones in your data.
 
 See also the [section on time-related
 functions](reference-dsl-builtin-functions.md#time-functions) for
@@ -27,7 +27,7 @@ they're independent of timezone or daylight-savings time.
 One minus is that, being just numbers, they're not particularly human-readable
 -- hence the to-string and from-string functions described below.  Another
 caveat (not really a minus) is that _epoch milliseconds_, rather than epoch
-seconds, are common in some contexts, particulary JavaScript. If you ever
+seconds, are common in some contexts, particularly JavaScript. If you ever
 (anywhere) see a timestamp for the year 49,000-something -- probably someone is
 treating epoch-milliseconds as epoch-seconds.
 

internal/pkg/auxents/regtest/entry.go

@@ -1,5 +1,5 @@
 // ================================================================
-// TOOO
+// TODO
 // ================================================================
 
 package regtest

internal/pkg/auxents/repl/README.md

@@ -98,7 +98,7 @@ FILENAME="foo.dat",FILENUM=1,NR=1,FNR=1
 
 This is a small modification around the [CST](../../dsl/cst/) and the [`put` verb](../../transformers/put_or_filter.go).. Most of the keystroking here is for online help and command-line parsing.
 
-One subtlety is that non-assignment expressions like `NR < 10` are filter statements within `put` -- they can be used to control whether or not a given record is included in the outut stream. Here, in the REPL, these expressions are simply printed to the terminal. And for `:skip until ...` or `:process until ...`, they're used as the exit condition to break out of reading input records.
+One subtlety is that non-assignment expressions like `NR < 10` are filter statements within `put` -- they can be used to control whether or not a given record is included in the output stream. Here, in the REPL, these expressions are simply printed to the terminal. And for `:skip until ...` or `:process until ...`, they're used as the exit condition to break out of reading input records.
 
 # File structure
 

internal/pkg/auxents/repl/dsl.go

@@ -81,7 +81,7 @@ func (repl *Repl) handleDSLStringAux(
 		repl.runtimeState.Inrec = outrec
 
 		// The filter expression for the main Miller DSL is any non-assignment
-		// statment like 'true' or '$x > 0.5' etc. For the REPL, we re-use this for
+		// statement like 'true' or '$x > 0.5' etc. For the REPL, we re-use this for
 		// interactive expressions to be printed to the terminal. For the main DSL,
 		// the default is mlrval.FromTrue(); for the REPL, the default is
 		// mlrval.VOID.

internal/pkg/auxents/repl/session.go

@@ -1,7 +1,7 @@
 // ================================================================
 // Top-level handler for a REPL session, including setup/construction, and
 // ingesting command-lines. Command-line strings are triaged and send off to
-// the appropriate handlers: DSL parse/execute if the comand is a DSL statement
+// the appropriate handlers: DSL parse/execute if the command is a DSL statement
 // (like '$z = $x + $y'); REPL-command-line parse/execute otherwise (like
 // ':open foo.dat' or ':help').
 //
@@ -66,7 +66,7 @@ func NewRepl(
 	runtimeState := runtime.NewEmptyState(options)
 	runtimeState.Update(inrec, context)
 	// The filter expression for the main Miller DSL is any non-assignment
-	// statment like 'true' or '$x > 0.5' etc. For the REPL, we re-use this for
+	// statement like 'true' or '$x > 0.5' etc. For the REPL, we re-use this for
 	// interactive expressions to be printed to the terminal. For the main DSL,
 	// the default is mlrval.FromTrue(); for the REPL, the default is
 	// mlrval.VOID.

internal/pkg/auxents/repl/verbs.go

@@ -165,7 +165,7 @@ func handleLoad(repl *Repl, args []string) bool {
 // ----------------------------------------------------------------
 func usageOpen(repl *Repl) {
 	fmt.Printf(
-		":open {one or more data-file names in the format specifed by %s %s}.\n",
+		":open {one or more data-file names in the format specified by %s %s}.\n",
 		repl.exeName, repl.replName,
 	)
 	fmt.Print(
@@ -515,7 +515,7 @@ func handleSkipOrProcessUntil(repl *Repl, dslString string, processingNotSkippin
 				repl,
 				recordAndContext,
 				processingNotSkipping,
-				true, // testingByFilterExpression -- since we're continuing until the filter expresssion is true
+				true, // testingByFilterExpression -- since we're continuing until the filter expression is true
 			)
 			if shouldBreak {
 				break
@@ -597,7 +597,7 @@ func skipOrProcessRecord(
 // ----------------------------------------------------------------
 func usageWrite(repl *Repl) {
 	fmt.Println(":write with no arguments.")
-	fmt.Println("Sends the current record (maybe modifed by statements you enter)")
+	fmt.Println("Sends the current record (maybe modified by statements you enter)")
 	fmt.Printf("to standard output, with format as specified by %s %s.\n",
 		repl.exeName, repl.replName)
 }

internal/pkg/bifs/arithmetic.go

@@ -202,7 +202,7 @@ func BIF_minus_binary(input1, input2 *mlrval.Mlrval) *mlrval.Mlrval {
 // 2**63-1 (or is less than -2**63) using integer arithmetic (it may have
 // already overflowed) *or* using double-precision (granularity). Instead we
 // check if the absolute value of the product exceeds the largest representable
-// double less than 2**63. (An alterative would be to do all integer multiplies
+// double less than 2**63. (An alternative would be to do all integer multiplies
 // using handcrafted multi-word 128-bit arithmetic).
 
 func times_n_ii(input1, input2 *mlrval.Mlrval) *mlrval.Mlrval {

internal/pkg/bifs/collections.go

@@ -659,7 +659,7 @@ func BIF_append(input1, input2 *mlrval.Mlrval) *mlrval.Mlrval {
 }
 
 // ----------------------------------------------------------------
-// First argumemnt is prefix.
+// First argument is prefix.
 // Second argument is delimiter.
 // Third argument is map or array.
 // flatten("a", ".", {"b": { "c": 4 }}) is {"a.b.c" : 4}.

internal/pkg/input/record_reader_json.go

@@ -185,7 +185,7 @@ func (reader *RecordReaderJSON) processHandle(
 //
 // Miller lets users (on an opt-in basis) have comments in their data files,
 // for all formats including JSON. Comments are only honored at start of line.
-// Users can have them be printed to stdout straightaway, or simply discarded.
+// Users can have them be printed to stdout straight away, or simply discarded.
 //
 // For most file formats Miller is doing line-based I/O and can deal with
 // comment lines easily and simply. But for JSON, the Go library needs an

internal/pkg/lib/unbackslash.go

@@ -26,7 +26,7 @@ var unbackslashReplacements = map[byte]string{
 	'?':  "?",
 }
 
-// UnbackslashStringLiteral replaces "\t" with TAB, etc. for DSL expresions
+// UnbackslashStringLiteral replaces "\t" with TAB, etc. for DSL expressions
 // like '$foo = "a\tb"'.  See also
 // https://en.wikipedia.org/wiki/Escape_sequences_in_C
 // (predates the port of Miller from C to Go).

internal/pkg/mlrval/mlrval_json.go

@@ -209,7 +209,7 @@ func MlrvalDecodeFromJSON(decoder *json.Decoder) (
 				if !key.IsString() {
 					return nil, false, fmt.Errorf(
 						// TODO: print out what was gotten
-						"mlr JSON reader: obejct keys must be string-valued.",
+						"mlr JSON reader: object keys must be string-valued.",
 					)
 				}
 

internal/pkg/mlrval/mlrval_type.go

@@ -147,7 +147,7 @@ var TYPE_NAMES = [MT_DIM]string{
 	"int",
 	"float",
 	"bool",
-	"empty", // For backward compatiblity with the C impl: this is user-visible
+	"empty", // For backward compatibility with the C impl: this is user-visible
 	"string",
 	"array",
 	"map",

internal/pkg/output/file-output-handlers.go

@@ -49,7 +49,7 @@ type MultiOutputHandlerManager struct {
 	// For stdout or stderr
 	singleHandler *FileOutputHandler
 
-	// TOOD: make an enum
+	// TODO: make an enum
 	append              bool // True for ">>", false for ">" and "|"
 	pipe                bool // True for "|", false for ">" and ">>"
 	recordWriterOptions *cli.TWriterOptions

internal/pkg/parsing/mlr.bnf

@@ -338,7 +338,7 @@ Root
 ;
 
 // ----------------------------------------------------------------
-// A StatementBlock is a sequence of statemnts: either the stuff in between
+// A StatementBlock is a sequence of statements: either the stuff in between
 // (but not including) the curly braces in things like 'if (NR > 2) { $x = 1;
 // $y = 2 }', or, top-level Miller DSL statements like '$x = 1; $y = 2'.
 

internal/pkg/runtime/doc.go

@@ -1,3 +1,3 @@
 // Package runtime contains state for the concrete-syntax-tree executor which
-// runs user-specifed statements in the Miller domain-specific langauge.
+// runs user-specifed statements in the Miller domain-specific language.
 package runtime

internal/pkg/transformers/bootstrap.go

@@ -138,7 +138,7 @@ func (tr *TransformerBootstrap) Transform(
 	//
 	// However, in Go, there is concurrent processing.  It would be
 	// possible for us to emit a pointer to a particular record without
-	// copying, then when emitting that saem record a second time, copy it.
+	// copying, then when emitting that same record a second time, copy it.
 	// But due to concurrency, the pointed-to record could have already
 	// been mutated downstream. We wouldn't be copying our input as we
 	// received it -- we'd be copying something potentially modified.

internal/pkg/transformers/shuffle.go

@@ -129,7 +129,7 @@ func (tr *TransformerShuffle) Transform(
 			images[u] = images[i]
 			images[i] = temp
 			// Decrease the size of the pool by 1.  (Yes, unusedStart and k always have the same value.
-			// Using two variables wastes neglible memory and makes the code easier to understand.)
+			// Using two variables wastes negligible memory and makes the code easier to understand.)
 			unusedStart++
 			numUnused--
 		}

internal/pkg/transformers/utils/join-bucket-keeper.go

@@ -326,7 +326,7 @@ func (keeper *JoinBucketKeeper) FindJoinBucket(
 }
 
 // ----------------------------------------------------------------
-// This finds the first peek record which posseses all the necessary join-field
+// This finds the first peek record which possesses all the necessary join-field
 // keys.  Any other records found along the way, lacking the necessary
 // join-field keys, are moved to the left-unpaired list.